summaryrefslogtreecommitdiff
path: root/arch/x86/net
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/net')
-rw-r--r--arch/x86/net/Makefile2
-rw-r--r--arch/x86/net/bpf_jit_comp.c341
-rw-r--r--arch/x86/net/bpf_timed_may_goto.S55
3 files changed, 365 insertions, 33 deletions
diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile
index 383c87300b0d..dddbefc0f439 100644
--- a/arch/x86/net/Makefile
+++ b/arch/x86/net/Makefile
@@ -6,5 +6,5 @@
ifeq ($(CONFIG_X86_32),y)
obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
else
- obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+ obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
endif
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 06b080b61aa5..15672cb926fc 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT5(b1, b2, b3, b4, b5) \
+ do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0)
#define EMIT1_off32(b1, off) \
do { EMIT1(b1); EMIT(off, 4); } while (0)
@@ -325,6 +327,22 @@ struct jit_context {
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE)
+static void push_r9(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x51); /* push r9 */
+ *pprog = prog;
+}
+
+static void pop_r9(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x59); /* pop r9 */
+ *pprog = prog;
+}
+
static void push_r12(u8 **pprog)
{
u8 *prog = *pprog;
@@ -394,16 +412,20 @@ static void emit_nops(u8 **pprog, int len)
* Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
* in arch/x86/kernel/alternative.c
*/
+static int emit_call(u8 **prog, void *func, void *ip);
-static void emit_fineibt(u8 **pprog, u32 hash)
+static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
{
u8 *prog = *pprog;
EMIT_ENDBR();
EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */
- EMIT2(0x74, 0x07); /* jz.d8 +7 */
- EMIT2(0x0f, 0x0b); /* ud2 */
- EMIT1(0x90); /* nop */
+ if (cfi_bhi) {
+ emit_call(&prog, __bhi_args[arity], ip + 11);
+ } else {
+ EMIT2(0x75, 0xf9); /* jne.d8 .-7 */
+ EMIT3(0x0f, 0x1f, 0x00); /* nop3 */
+ }
EMIT_ENDBR_POISON();
*pprog = prog;
@@ -432,13 +454,13 @@ static void emit_kcfi(u8 **pprog, u32 hash)
*pprog = prog;
}
-static void emit_cfi(u8 **pprog, u32 hash)
+static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity)
{
u8 *prog = *pprog;
switch (cfi_mode) {
case CFI_FINEIBT:
- emit_fineibt(&prog, hash);
+ emit_fineibt(&prog, ip, hash, arity);
break;
case CFI_KCFI:
@@ -489,13 +511,17 @@ static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
* bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
* while jumping to another program
*/
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf,
bool tail_call_reachable, bool is_subprog,
bool is_exception_cb)
{
u8 *prog = *pprog;
- emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
+ if (is_subprog) {
+ emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5);
+ } else {
+ emit_cfi(&prog, ip, cfi_bpf_hash, 1);
+ }
/* BPF trampoline can be made to work without these nops,
* but let's waste 5 bytes for now and optimize later
*/
@@ -605,7 +631,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
- text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
+ smp_text_poke_single(ip, new_insn, X86_PATCH_SIZE, NULL);
ret = 0;
}
out:
@@ -625,7 +651,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
* See emit_prologue(), for IBT builds the trampoline hook is preceded
* with an ENDBR instruction.
*/
- if (is_endbr(*(u32 *)ip))
+ if (is_endbr(ip))
ip += ENDBR_INSN_SIZE;
return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
@@ -637,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+ if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
+ OPTIMIZER_HIDE_VAR(reg);
+ emit_jump(&prog, its_static_thunk(reg), ip);
+ } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -659,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (cpu_wants_rethunk()) {
emit_jump(&prog, x86_return_thunk, ip);
} else {
EMIT1(0xC3); /* ret */
@@ -1226,8 +1255,8 @@ static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm)
emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm);
}
-static int emit_atomic(u8 **pprog, u8 atomic_op,
- u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
+static int emit_atomic_rmw(u8 **pprog, u32 atomic_op,
+ u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
{
u8 *prog = *pprog;
@@ -1267,8 +1296,9 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
return 0;
}
-static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
- u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+static int emit_atomic_rmw_index(u8 **pprog, u32 atomic_op, u32 size,
+ u32 dst_reg, u32 src_reg, u32 index_reg,
+ int off)
{
u8 *prog = *pprog;
@@ -1281,7 +1311,7 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg));
break;
default:
- pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n");
+ pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
return -EFAULT;
}
@@ -1315,6 +1345,49 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
return 0;
}
+static int emit_atomic_ld_st(u8 **pprog, u32 atomic_op, u32 dst_reg,
+ u32 src_reg, s16 off, u8 bpf_size)
+{
+ switch (atomic_op) {
+ case BPF_LOAD_ACQ:
+ /* dst_reg = smp_load_acquire(src_reg + off16) */
+ emit_ldx(pprog, bpf_size, dst_reg, src_reg, off);
+ break;
+ case BPF_STORE_REL:
+ /* smp_store_release(dst_reg + off16, src_reg) */
+ emit_stx(pprog, bpf_size, dst_reg, src_reg, off);
+ break;
+ default:
+ pr_err("bpf_jit: unknown atomic load/store opcode %02x\n",
+ atomic_op);
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static int emit_atomic_ld_st_index(u8 **pprog, u32 atomic_op, u32 size,
+ u32 dst_reg, u32 src_reg, u32 index_reg,
+ int off)
+{
+ switch (atomic_op) {
+ case BPF_LOAD_ACQ:
+ /* dst_reg = smp_load_acquire(src_reg + idx_reg + off16) */
+ emit_ldx_index(pprog, size, dst_reg, src_reg, index_reg, off);
+ break;
+ case BPF_STORE_REL:
+ /* smp_store_release(dst_reg + idx_reg + off16, src_reg) */
+ emit_stx_index(pprog, size, dst_reg, src_reg, index_reg, off);
+ break;
+ default:
+ pr_err("bpf_jit: unknown atomic load/store opcode %02x\n",
+ atomic_op);
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
#define DONT_CLEAR 1
bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
@@ -1404,6 +1477,24 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
*pprog = prog;
}
+static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
+{
+ u8 *prog = *pprog;
+
+ /* movabs r9, priv_frame_ptr */
+ emit_mov_imm64(&prog, X86_REG_R9, (__force long) priv_frame_ptr >> 32,
+ (u32) (__force long) priv_frame_ptr);
+
+#ifdef CONFIG_SMP
+ /* add <r9>, gs:[<off>] */
+ EMIT2(0x65, 0x4c);
+ EMIT3(0x03, 0x0c, 0x25);
+ EMIT((u32)(unsigned long)&this_cpu_off, 4);
+#endif
+
+ *pprog = prog;
+}
+
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
#define __LOAD_TCC_PTR(off) \
@@ -1412,6 +1503,52 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
#define LOAD_TAIL_CALL_CNT_PTR(stack) \
__LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack))
+/* Memory size/value to protect private stack overflow/underflow */
+#define PRIV_STACK_GUARD_SZ 8
+#define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL
+
+static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
+ struct bpf_prog *bpf_prog)
+{
+ u8 *prog = *pprog;
+ u8 *func;
+
+ if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) {
+ /* The clearing sequence clobbers eax and ecx. */
+ EMIT1(0x50); /* push rax */
+ EMIT1(0x51); /* push rcx */
+ ip += 2;
+
+ func = (u8 *)clear_bhb_loop;
+ ip += x86_call_depth_emit_accounting(&prog, func, ip);
+
+ if (emit_call(&prog, func, ip))
+ return -EINVAL;
+ EMIT1(0x59); /* pop rcx */
+ EMIT1(0x58); /* pop rax */
+ }
+ /* Insert IBHF instruction */
+ if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) &&
+ cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) ||
+ cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) {
+ /*
+ * Add an Indirect Branch History Fence (IBHF). IBHF acts as a
+ * fence preventing branch history from before the fence from
+ * affecting indirect branches after the fence. This is
+ * specifically used in cBPF jitted code to prevent Intra-mode
+ * BHI attacks. The IBHF instruction is designed to be a NOP on
+ * hardware that doesn't need or support it. The REP and REX.W
+ * prefixes are required by the microcode, and they also ensure
+ * that the NOP is unlikely to be used in existing code.
+ *
+ * IBHF is not a valid instruction in 32-bit mode.
+ */
+ EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */
+ }
+ *pprog = prog;
+ return 0;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
@@ -1421,18 +1558,28 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
int insn_cnt = bpf_prog->len;
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+ void __percpu *priv_frame_ptr = NULL;
u64 arena_vm_start, user_vm_start;
+ void __percpu *priv_stack_ptr;
int i, excnt = 0;
int ilen, proglen = 0;
u8 *prog = temp;
+ u32 stack_depth;
int err;
+ stack_depth = bpf_prog->aux->stack_depth;
+ priv_stack_ptr = bpf_prog->aux->priv_stack_ptr;
+ if (priv_stack_ptr) {
+ priv_frame_ptr = priv_stack_ptr + PRIV_STACK_GUARD_SZ + round_up(stack_depth, 8);
+ stack_depth = 0;
+ }
+
arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
detect_reg_usage(insn, insn_cnt, callee_regs_used);
- emit_prologue(&prog, bpf_prog->aux->stack_depth,
+ emit_prologue(&prog, image, stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
/* Exception callback will clobber callee regs for its own use, and
@@ -1454,6 +1601,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
emit_mov_imm64(&prog, X86_REG_R12,
arena_vm_start >> 32, (u32) arena_vm_start);
+ if (priv_frame_ptr)
+ emit_priv_frame_ptr(&prog, priv_frame_ptr);
+
ilen = prog - temp;
if (rw_image)
memcpy(rw_image + proglen, temp, ilen);
@@ -1473,6 +1623,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
u8 *func;
int nops;
+ if (priv_frame_ptr) {
+ if (src_reg == BPF_REG_FP)
+ src_reg = X86_REG_R9;
+
+ if (dst_reg == BPF_REG_FP)
+ dst_reg = X86_REG_R9;
+ }
+
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
@@ -2054,6 +2212,13 @@ populate_extable:
}
break;
+ case BPF_STX | BPF_ATOMIC | BPF_B:
+ case BPF_STX | BPF_ATOMIC | BPF_H:
+ if (!bpf_atomic_is_load_store(insn)) {
+ pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
+ return -EFAULT;
+ }
+ fallthrough;
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
if (insn->imm == (BPF_AND | BPF_FETCH) ||
@@ -2089,10 +2254,10 @@ populate_extable:
EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
add_2reg(0xC0, AUX_REG, real_src_reg));
/* Attempt to swap in new value */
- err = emit_atomic(&prog, BPF_CMPXCHG,
- real_dst_reg, AUX_REG,
- insn->off,
- BPF_SIZE(insn->code));
+ err = emit_atomic_rmw(&prog, BPF_CMPXCHG,
+ real_dst_reg, AUX_REG,
+ insn->off,
+ BPF_SIZE(insn->code));
if (WARN_ON(err))
return err;
/*
@@ -2107,17 +2272,35 @@ populate_extable:
break;
}
- err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
- insn->off, BPF_SIZE(insn->code));
+ if (bpf_atomic_is_load_store(insn))
+ err = emit_atomic_ld_st(&prog, insn->imm, dst_reg, src_reg,
+ insn->off, BPF_SIZE(insn->code));
+ else
+ err = emit_atomic_rmw(&prog, insn->imm, dst_reg, src_reg,
+ insn->off, BPF_SIZE(insn->code));
if (err)
return err;
break;
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
+ if (!bpf_atomic_is_load_store(insn)) {
+ pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
+ return -EFAULT;
+ }
+ fallthrough;
case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
start_of_ldx = prog;
- err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code),
- dst_reg, src_reg, X86_REG_R12, insn->off);
+
+ if (bpf_atomic_is_load_store(insn))
+ err = emit_atomic_ld_st_index(&prog, insn->imm,
+ BPF_SIZE(insn->code), dst_reg,
+ src_reg, X86_REG_R12, insn->off);
+ else
+ err = emit_atomic_rmw_index(&prog, insn->imm, BPF_SIZE(insn->code),
+ dst_reg, src_reg, X86_REG_R12,
+ insn->off);
if (err)
return err;
goto populate_extable;
@@ -2127,15 +2310,21 @@ populate_extable:
u8 *ip = image + addrs[i - 1];
func = (u8 *) __bpf_call_base + imm32;
- if (tail_call_reachable) {
- LOAD_TAIL_CALL_CNT_PTR(bpf_prog->aux->stack_depth);
+ if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
+ LOAD_TAIL_CALL_CNT_PTR(stack_depth);
ip += 7;
}
if (!imm32)
return -EINVAL;
+ if (priv_frame_ptr) {
+ push_r9(&prog);
+ ip += 2;
+ }
ip += x86_call_depth_emit_accounting(&prog, func, ip);
if (emit_call(&prog, func, ip))
return -EINVAL;
+ if (priv_frame_ptr)
+ pop_r9(&prog);
break;
}
@@ -2145,13 +2334,13 @@ populate_extable:
&bpf_prog->aux->poke_tab[imm32 - 1],
&prog, image + addrs[i - 1],
callee_regs_used,
- bpf_prog->aux->stack_depth,
+ stack_depth,
ctx);
else
emit_bpf_tail_call_indirect(bpf_prog,
&prog,
callee_regs_used,
- bpf_prog->aux->stack_depth,
+ stack_depth,
image + addrs[i - 1],
ctx);
break;
@@ -2402,6 +2591,13 @@ emit_jmp:
seen_exit = true;
/* Update cleanup_addr */
ctx->cleanup_addr = proglen;
+ if (bpf_prog_was_classic(bpf_prog) &&
+ !capable(CAP_SYS_ADMIN)) {
+ u8 *ip = image + addrs[i - 1];
+
+ if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
+ return -EINVAL;
+ }
if (bpf_prog->aux->exception_boundary) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
@@ -2971,7 +3167,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/* skip patched call instruction and point orig_call to actual
* body of the kernel function.
*/
- if (is_endbr(*(u32 *)orig_call))
+ if (is_endbr(orig_call))
orig_call += ENDBR_INSN_SIZE;
orig_call += X86_PATCH_SIZE;
}
@@ -2982,7 +3178,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/*
* Indirect call for bpf_struct_ops
*/
- emit_cfi(&prog, cfi_get_func_hash(func_addr));
+ emit_cfi(&prog, image,
+ cfi_get_func_hash(func_addr),
+ cfi_get_func_arity(func_addr));
} else {
/*
* Direct-call fentry stub, as such it needs accounting for the
@@ -3303,6 +3501,42 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
}
+static const char *bpf_get_prog_name(struct bpf_prog *prog)
+{
+ if (prog->aux->ksym.prog)
+ return prog->aux->ksym.name;
+ return prog->aux->name;
+}
+
+static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
+{
+ int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+ u64 *stack_ptr;
+
+ for_each_possible_cpu(cpu) {
+ stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+ stack_ptr[0] = PRIV_STACK_GUARD_VAL;
+ stack_ptr[underflow_idx] = PRIV_STACK_GUARD_VAL;
+ }
+}
+
+static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size,
+ struct bpf_prog *prog)
+{
+ int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+ u64 *stack_ptr;
+
+ for_each_possible_cpu(cpu) {
+ stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+ if (stack_ptr[0] != PRIV_STACK_GUARD_VAL ||
+ stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) {
+ pr_err("BPF private stack overflow/underflow detected for prog %sx\n",
+ bpf_get_prog_name(prog));
+ break;
+ }
+ }
+}
+
struct x64_jit_data {
struct bpf_binary_header *rw_header;
struct bpf_binary_header *header;
@@ -3320,7 +3554,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
struct bpf_binary_header *rw_header = NULL;
struct bpf_binary_header *header = NULL;
struct bpf_prog *tmp, *orig_prog = prog;
+ void __percpu *priv_stack_ptr = NULL;
struct x64_jit_data *jit_data;
+ int priv_stack_alloc_sz;
int proglen, oldproglen = 0;
struct jit_context ctx = {};
bool tmp_blinded = false;
@@ -3356,6 +3592,23 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
}
prog->aux->jit_data = jit_data;
}
+ priv_stack_ptr = prog->aux->priv_stack_ptr;
+ if (!priv_stack_ptr && prog->aux->jits_use_priv_stack) {
+ /* Allocate actual private stack size with verifier-calculated
+ * stack size plus two memory guards to protect overflow and
+ * underflow.
+ */
+ priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) +
+ 2 * PRIV_STACK_GUARD_SZ;
+ priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 8, GFP_KERNEL);
+ if (!priv_stack_ptr) {
+ prog = orig_prog;
+ goto out_priv_stack;
+ }
+
+ priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz);
+ prog->aux->priv_stack_ptr = priv_stack_ptr;
+ }
addrs = jit_data->addrs;
if (addrs) {
ctx = jit_data->ctx;
@@ -3491,6 +3744,11 @@ out_image:
bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
kvfree(addrs);
+ if (!image && priv_stack_ptr) {
+ free_percpu(priv_stack_ptr);
+ prog->aux->priv_stack_ptr = NULL;
+ }
+out_priv_stack:
kfree(jit_data);
prog->aux->jit_data = NULL;
}
@@ -3529,6 +3787,8 @@ void bpf_jit_free(struct bpf_prog *prog)
if (prog->jited) {
struct x64_jit_data *jit_data = prog->aux->jit_data;
struct bpf_binary_header *hdr;
+ void __percpu *priv_stack_ptr;
+ int priv_stack_alloc_sz;
/*
* If we fail the final pass of JIT (from jit_subprogs),
@@ -3544,6 +3804,13 @@ void bpf_jit_free(struct bpf_prog *prog)
prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset();
hdr = bpf_jit_binary_pack_hdr(prog);
bpf_jit_binary_pack_free(hdr, NULL);
+ priv_stack_ptr = prog->aux->priv_stack_ptr;
+ if (priv_stack_ptr) {
+ priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) +
+ 2 * PRIV_STACK_GUARD_SZ;
+ priv_stack_check_guard(priv_stack_ptr, priv_stack_alloc_sz, prog);
+ free_percpu(prog->aux->priv_stack_ptr);
+ }
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
}
@@ -3559,6 +3826,11 @@ bool bpf_jit_supports_exceptions(void)
return IS_ENABLED(CONFIG_UNWINDER_ORC);
}
+bool bpf_jit_supports_private_stack(void)
+{
+ return true;
+}
+
void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
{
#if defined(CONFIG_UNWINDER_ORC)
@@ -3652,3 +3924,8 @@ u64 bpf_arch_uaddress_limit(void)
{
return 0;
}
+
+bool bpf_jit_supports_timed_may_goto(void)
+{
+ return true;
+}
diff --git a/arch/x86/net/bpf_timed_may_goto.S b/arch/x86/net/bpf_timed_may_goto.S
new file mode 100644
index 000000000000..54c690cae190
--- /dev/null
+++ b/arch/x86/net/bpf_timed_may_goto.S
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+
+ .code64
+ .section .text, "ax"
+
+SYM_FUNC_START(arch_bpf_timed_may_goto)
+ ANNOTATE_NOENDBR
+
+ /*
+ * r10 passes us stack depth, load the pointer to count and timestamp
+ * into r10 by adding it to BPF frame pointer.
+ */
+ leaq (%rbp, %r10, 1), %r10
+
+ /* Setup frame. */
+ pushq %rbp
+ movq %rsp, %rbp
+
+ /* Save r0-r5. */
+ pushq %rax
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %r8
+
+ /*
+ * r10 has the pointer to count and timestamp, pass it as first
+ * argument.
+ */
+ movq %r10, %rdi
+
+ /* Emit call depth accounting for call below. */
+ CALL_DEPTH_ACCOUNT
+ call bpf_check_timed_may_goto
+
+ /* BPF_REG_AX=r10 will be stored into count, so move return value to it. */
+ movq %rax, %r10
+
+ /* Restore r5-r0. */
+ popq %r8
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
+ popq %rax
+
+ leave
+ RET
+SYM_FUNC_END(arch_bpf_timed_may_goto)
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-27 02:08:54 +0300