Add bpf trampoline support for arm64. Most of the logic is the same as x86.
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
v2: - Add Song's ACK - Change the multi-line comment in is_valid_bpf_tramp_flags() into net style (patch 3) - Fix a deadloop issue in ftrace selftest (patch 2) - Replace pt_regs->x0 with pt_regs->orig_x0 in patch 1 commit message - Replace "bpf trampoline" with "custom trampoline" in patch 1, as ftrace direct call is not only used by bpf trampoline.
v1: https://lore.kernel.org/bpf/20220413054959.1053668-1-xukuohai@huawei.com/
Xu Kuohai (6): arm64: ftrace: Add ftrace direct call support ftrace: Fix deadloop caused by direct call in ftrace selftest bpf: Move is_valid_bpf_tramp_flags() to the public trampoline code bpf, arm64: Impelment bpf_arch_text_poke() for arm64 bpf, arm64: bpf trampoline for arm64 selftests/bpf: Fix trivial typo in fentry_fexit.c
arch/arm64/Kconfig | 2 + arch/arm64/include/asm/ftrace.h | 10 + arch/arm64/kernel/asm-offsets.c | 1 + arch/arm64/kernel/entry-ftrace.S | 28 +- arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 390 +++++++++++++++++- arch/x86/net/bpf_jit_comp.c | 20 - include/linux/bpf.h | 5 + kernel/bpf/bpf_struct_ops.c | 4 +- kernel/bpf/trampoline.c | 35 +- kernel/trace/trace_selftest.c | 4 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 4 +- 12 files changed, 482 insertions(+), 35 deletions(-)
Add ftrace direct support for arm64.
1. When there is custom trampoline only, replace the fentry nop to a jump instruction that jumps directly to the custom trampoline.
2. When ftrace trampoline and custom trampoline coexist, jump from fentry to ftrace trampoline first, then jump to custom trampoline when ftrace trampoline exits. The current unused register pt_regs->orig_x0 is used as an intermediary for jumping from ftrace trampoline to custom trampoline.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com --- arch/arm64/Kconfig | 2 ++ arch/arm64/include/asm/ftrace.h | 10 ++++++++++ arch/arm64/kernel/asm-offsets.c | 1 + arch/arm64/kernel/entry-ftrace.S | 18 +++++++++++++++--- 4 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57c4c995965f..81cc330daafc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -177,6 +177,8 @@ config ARM64 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS \ if $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \ + if DYNAMIC_FTRACE_WITH_REGS select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 1494cfa8639b..3a363d6a3bd0 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -78,6 +78,16 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; }
+static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, + unsigned long addr) +{ + /* + * Place custom trampoline address in regs->orig_x0 to let ftrace + * trampoline jump to it. + */ + regs->orig_x0 = addr; +} + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS struct dyn_ftrace; int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 1197e7679882..b1ed0bf01c59 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -80,6 +80,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); + DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index e535480a4069..dfe62c55e3a2 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -60,6 +60,9 @@ str x29, [sp, #S_FP] .endif
+ /* Set orig_x0 to zero */ + str xzr, [sp, #S_ORIG_X0] + /* Save the callsite's SP and LR */ add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] @@ -119,12 +122,21 @@ ftrace_common_return: /* Restore the callsite's FP, LR, PC */ ldr x29, [sp, #S_FP] ldr x30, [sp, #S_LR] - ldr x9, [sp, #S_PC] - + ldr x10, [sp, #S_PC] + + ldr x11, [sp, #S_ORIG_X0] + cbz x11, 1f + /* Set x9 to parent ip before jump to custom trampoline */ + mov x9, x30 + /* Set lr to self ip */ + ldr x30, [sp, #S_PC] + /* Set x10 (used for return address) to custom trampoline */ + mov x10, x11 +1: /* Restore the callsite's SP */ add sp, sp, #PT_REGS_SIZE + 16
- ret x9 + ret x10 SYM_CODE_END(ftrace_common)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
After direct call is enabled for arm64, ftrace selftest enters a dead loop:
<trace_selftest_dynamic_test_func>: 00 bti c 01 mov x9, x30 <trace_direct_tramp>: 02 bl <trace_direct_tramp> ----------> ret | lr/x30 is 03, return to 03 | 03 mov w0, #0x0 <-----------------------------| | | | dead loop! | | | 04 ret ---- lr/x30 is still 03, go back to 03 ----|
The reason is that when the direct caller trace_direct_tramp() returns to the patched function trace_selftest_dynamic_test_func(), lr is still the address after the instrumented instruction in the patched function, so when the patched function exits, it returns to itself!
To fix this issue, we need to restore lr before trace_direct_tramp() exits, so make trace_direct_tramp() a weak symbol and rewrite it for arm64.
To detect this issue directly, call DYN_FTRACE_TEST_NAME() before register_ftrace_graph().
Reported-by: Li Huafei lihuafei1@huawei.com Signed-off-by: Xu Kuohai xukuohai@huawei.com --- arch/arm64/kernel/entry-ftrace.S | 10 ++++++++++ kernel/trace/trace_selftest.c | 4 +++- 2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index dfe62c55e3a2..e58eb06ec9b2 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -357,3 +357,13 @@ SYM_CODE_START(return_to_handler) ret SYM_CODE_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SELFTEST +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_FUNC_START(trace_direct_tramp) + mov x10, x30 + mov x30, x9 + ret x10 +SYM_FUNC_END(trace_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif /* CONFIG_FTRACE_SELFTEST */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index abcadbe933bb..38b0d5c9a1e0 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -785,7 +785,7 @@ static struct fgraph_ops fgraph_ops __initdata = { };
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -noinline __noclone static void trace_direct_tramp(void) { } +void __weak trace_direct_tramp(void) { } #endif
/* @@ -868,6 +868,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out;
+ DYN_FTRACE_TEST_NAME(); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret);
On Thu, 14 Apr 2022 12:22:16 -0400 Xu Kuohai xukuohai@huawei.com wrote:
After direct call is enabled for arm64, ftrace selftest enters a dead loop:
<trace_selftest_dynamic_test_func>: 00 bti c 01 mov x9, x30 <trace_direct_tramp>: 02 bl <trace_direct_tramp> ----------> ret | lr/x30 is 03, return to 03 | 03 mov w0, #0x0 <-----------------------------| | | | dead loop! | | | 04 ret ---- lr/x30 is still 03, go back to 03 ----|
The reason is that when the direct caller trace_direct_tramp() returns to the patched function trace_selftest_dynamic_test_func(), lr is still the address after the instrumented instruction in the patched function, so when the patched function exits, it returns to itself!
To fix this issue, we need to restore lr before trace_direct_tramp() exits, so make trace_direct_tramp() a weak symbol and rewrite it for arm64.
To detect this issue directly, call DYN_FTRACE_TEST_NAME() before register_ftrace_graph().
Reported-by: Li Huafei lihuafei1@huawei.com Signed-off-by: Xu Kuohai xukuohai@huawei.com
arch/arm64/kernel/entry-ftrace.S | 10 ++++++++++ kernel/trace/trace_selftest.c | 4 +++- 2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index dfe62c55e3a2..e58eb06ec9b2 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -357,3 +357,13 @@ SYM_CODE_START(return_to_handler) ret SYM_CODE_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#ifdef CONFIG_FTRACE_SELFTEST +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_FUNC_START(trace_direct_tramp)
- mov x10, x30
- mov x30, x9
- ret x10
+SYM_FUNC_END(trace_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif /* CONFIG_FTRACE_SELFTEST */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index abcadbe933bb..38b0d5c9a1e0 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -785,7 +785,7 @@ static struct fgraph_ops fgraph_ops __initdata = { }; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -noinline __noclone static void trace_direct_tramp(void) { } +void __weak trace_direct_tramp(void) { } #endif /*
@@ -868,6 +868,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out;
- DYN_FTRACE_TEST_NAME();
This doesn't look like it belongs in this patch.
-- Steve
- ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret);
On 4/21/2022 7:24 AM, Steven Rostedt wrote:
On Thu, 14 Apr 2022 12:22:16 -0400 Xu Kuohai xukuohai@huawei.com wrote:
After direct call is enabled for arm64, ftrace selftest enters a dead loop:
<trace_selftest_dynamic_test_func>: 00 bti c 01 mov x9, x30 <trace_direct_tramp>: 02 bl <trace_direct_tramp> ----------> ret | lr/x30 is 03, return to 03 | 03 mov w0, #0x0 <-----------------------------| | | | dead loop! | | | 04 ret ---- lr/x30 is still 03, go back to 03 ----|
The reason is that when the direct caller trace_direct_tramp() returns to the patched function trace_selftest_dynamic_test_func(), lr is still the address after the instrumented instruction in the patched function, so when the patched function exits, it returns to itself!
To fix this issue, we need to restore lr before trace_direct_tramp() exits, so make trace_direct_tramp() a weak symbol and rewrite it for arm64.
To detect this issue directly, call DYN_FTRACE_TEST_NAME() before register_ftrace_graph().
Reported-by: Li Huafei lihuafei1@huawei.com Signed-off-by: Xu Kuohai xukuohai@huawei.com
arch/arm64/kernel/entry-ftrace.S | 10 ++++++++++ kernel/trace/trace_selftest.c | 4 +++- 2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index dfe62c55e3a2..e58eb06ec9b2 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -357,3 +357,13 @@ SYM_CODE_START(return_to_handler) ret SYM_CODE_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#ifdef CONFIG_FTRACE_SELFTEST +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_FUNC_START(trace_direct_tramp)
- mov x10, x30
- mov x30, x9
- ret x10
+SYM_FUNC_END(trace_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif /* CONFIG_FTRACE_SELFTEST */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index abcadbe933bb..38b0d5c9a1e0 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -785,7 +785,7 @@ static struct fgraph_ops fgraph_ops __initdata = { }; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -noinline __noclone static void trace_direct_tramp(void) { } +void __weak trace_direct_tramp(void) { } #endif /*
@@ -868,6 +868,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out;
- DYN_FTRACE_TEST_NAME();
This doesn't look like it belongs in this patch.
-- Steve
This was added to run trace_direct_tramp() separately before registering function graph, so the dead loop can be caught accurately. However, the dead loop can also be caught when running function graph test, so this is somewhat unnecessary and will be removed in v3.
- ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret);
.
is_valid_bpf_tramp_flags() is not relevant to architecture, so move it to the public trampoline code.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com --- arch/x86/net/bpf_jit_comp.c | 20 -------------------- include/linux/bpf.h | 5 +++++ kernel/bpf/bpf_struct_ops.c | 4 ++-- kernel/bpf/trampoline.c | 35 ++++++++++++++++++++++++++++++++--- 4 files changed, 39 insertions(+), 25 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..774f05f92737 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1900,23 +1900,6 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; }
-static bool is_valid_bpf_tramp_flags(unsigned int flags) -{ - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) - return false; - - /* - * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, - * and it must be used alone. - */ - if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && - (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) - return false; - - return true; -} - /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1995,9 +1978,6 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (nr_args > 6) return -ENOTSUPP;
- if (!is_valid_bpf_tramp_flags(flags)) - return -EINVAL; - /* Generated trampoline stack layout: * * RBP + 8 [ return address ] diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..c650b7fe87ee 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -706,6 +706,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); +int bpf_prepare_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_progs *tprogs, + void *orig_call); + /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 21069dbe9138..5f9bdd530df2 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -325,8 +325,8 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; - return arch_prepare_bpf_trampoline(NULL, image, image_end, - model, flags, tprogs, NULL); + return bpf_prepare_trampoline(NULL, image, image_end, model, flags, + tprogs, NULL); }
static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index ada97751ae1b..3844504df9e5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -360,9 +360,9 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (ip_arg) flags |= BPF_TRAMP_F_IP_ARG;
- err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, - &tr->func.model, flags, tprogs, - tr->func.addr); + err = bpf_prepare_trampoline(im, im->image, im->image + PAGE_SIZE, + &tr->func.model, flags, tprogs, + tr->func.addr); if (err < 0) goto out;
@@ -641,6 +641,35 @@ arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image return -ENOTSUPP; }
+static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + +int +bpf_prepare_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_progs *tprogs, + void *orig_call) +{ + if (!is_valid_bpf_tramp_flags(flags)) + return -EINVAL; + + return arch_prepare_bpf_trampoline(tr, image, image_end, m, flags, + tprogs, orig_call); +} + static int __init init_trampolines(void) { int i;
Impelment bpf_arch_text_poke() for arm64, so bpf trampoline code can use it to replace nop with jump, or replace jump with nop.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com --- arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea27..1a1c3ea75ee2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -9,6 +9,7 @@
#include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/memory.h> #include <linux/filter.h> #include <linux/printk.h> #include <linux/slab.h> @@ -18,6 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> +#include <asm/patching.h> #include <asm/set_memory.h>
#include "bpf_jit.h" @@ -1529,3 +1531,53 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); } + +static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip, + void *addr, u32 *insn) +{ + if (!addr) + *insn = aarch64_insn_gen_nop(); + else + *insn = aarch64_insn_gen_branch_imm((unsigned long)ip, + (unsigned long)addr, + type); + + return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT; +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, + void *old_addr, void *new_addr) +{ + int ret; + u32 old_insn; + u32 new_insn; + u32 replaced; + enum aarch64_insn_branch_type branch_type; + + if (poke_type == BPF_MOD_CALL) + branch_type = AARCH64_INSN_BRANCH_LINK; + else + branch_type = AARCH64_INSN_BRANCH_NOLINK; + + if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0) + return -EFAULT; + + if (gen_branch_or_nop(branch_type, ip, new_addr, &new_insn) < 0) + return -EFAULT; + + mutex_lock(&text_mutex); + if (aarch64_insn_read(ip, &replaced)) { + ret = -EFAULT; + goto out; + } + + if (replaced != old_insn) { + ret = -EFAULT; + goto out; + } + + ret = aarch64_insn_patch_text_nosync((void *)ip, new_insn); +out: + mutex_unlock(&text_mutex); + return ret; +}
Hi,
On 4/15/2022 12:22 AM, Xu Kuohai wrote:
Impelment bpf_arch_text_poke() for arm64, so bpf trampoline code can use it to replace nop with jump, or replace jump with nop.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea27..1a1c3ea75ee2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -9,6 +9,7 @@ #include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/memory.h> #include <linux/filter.h> #include <linux/printk.h> #include <linux/slab.h> @@ -18,6 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> +#include <asm/patching.h> #include <asm/set_memory.h> #include "bpf_jit.h" @@ -1529,3 +1531,53 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); }
+static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
void *addr, u32 *insn)+{
- if (!addr)
*insn = aarch64_insn_gen_nop();- else
*insn = aarch64_insn_gen_branch_imm((unsigned long)ip,(unsigned long)addr,type);- return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT;
+}
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
void *old_addr, void *new_addr)+{
- int ret;
- u32 old_insn;
- u32 new_insn;
- u32 replaced;
- enum aarch64_insn_branch_type branch_type;
In bpf_arch_text_poke() of x86, it disables the poking of kernel module, can you explain why it is OK to do so in arm64 ? Because there is no test cases for fentry on linux kernel module, could you please add some tests for it ?
- if (poke_type == BPF_MOD_CALL)
branch_type = AARCH64_INSN_BRANCH_LINK;- else
branch_type = AARCH64_INSN_BRANCH_NOLINK;- if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0)
return -EFAULT;- if (gen_branch_or_nop(branch_type, ip, new_addr, &new_insn) < 0)
return -EFAULT;- mutex_lock(&text_mutex);
- if (aarch64_insn_read(ip, &replaced)) {
ret = -EFAULT;goto out;- }
- if (replaced != old_insn) {
ret = -EFAULT;goto out;- }
- ret = aarch64_insn_patch_text_nosync((void *)ip, new_insn);
+out:
- mutex_unlock(&text_mutex);
- return ret;
+}
On 4/15/2022 10:34 AM, Hou Tao wrote:
Hi,
On 4/15/2022 12:22 AM, Xu Kuohai wrote:
Impelment bpf_arch_text_poke() for arm64, so bpf trampoline code can use it to replace nop with jump, or replace jump with nop.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea27..1a1c3ea75ee2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -9,6 +9,7 @@ #include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/memory.h> #include <linux/filter.h> #include <linux/printk.h> #include <linux/slab.h> @@ -18,6 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> +#include <asm/patching.h> #include <asm/set_memory.h> #include "bpf_jit.h" @@ -1529,3 +1531,53 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); }
+static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
void *addr, u32 *insn)+{
- if (!addr)
*insn = aarch64_insn_gen_nop();- else
*insn = aarch64_insn_gen_branch_imm((unsigned long)ip,(unsigned long)addr,type);- return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT;
+}
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
void *old_addr, void *new_addr)+{
- int ret;
- u32 old_insn;
- u32 new_insn;
- u32 replaced;
- enum aarch64_insn_branch_type branch_type;
In bpf_arch_text_poke() of x86, it disables the poking of kernel module, can you explain why it is OK to do so in arm64 ? Because there is no test cases for fentry on linux kernel module, could you please add some tests for it ?
Oops, I forget to check this condition. It's not safe to patch a ko without ko unloading disabled.
For arm64, the fentry is only patched by ftrace since the nop instruciton to be instrumented is not the first instruction, so bpf_text_poke() fails when comparing the old instruction (pointed to by the "old_addr") with the nop. Since the nop in fentry is reserved by ftrace, I dont think it's reasonable to patch the nop by another interface not provided by ftrace.
Besides, for long jumps outside the range of 128MB, a single branch instruction is not sufficient, perhaps we could use ftrace trampoline or some other method to support long jumps.
- if (poke_type == BPF_MOD_CALL)
branch_type = AARCH64_INSN_BRANCH_LINK;- else
branch_type = AARCH64_INSN_BRANCH_NOLINK;- if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0)
return -EFAULT;- if (gen_branch_or_nop(branch_type, ip, new_addr, &new_insn) < 0)
return -EFAULT;- mutex_lock(&text_mutex);
- if (aarch64_insn_read(ip, &replaced)) {
ret = -EFAULT;goto out;- }
- if (replaced != old_insn) {
ret = -EFAULT;goto out;- }
- ret = aarch64_insn_patch_text_nosync((void *)ip, new_insn);
+out:
- mutex_unlock(&text_mutex);
- return ret;
+}
.
Hi Xu,
Thanks for working on this.
We are also looking forward to using fentry hooks on arm64. In particular, attaching to entry/exit into/from XDP progs.
On Thu, Apr 14, 2022 at 12:22 PM -04, Xu Kuohai wrote:
Impelment bpf_arch_text_poke() for arm64, so bpf trampoline code can use it to replace nop with jump, or replace jump with nop.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea27..1a1c3ea75ee2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -9,6 +9,7 @@ #include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/memory.h> #include <linux/filter.h> #include <linux/printk.h> #include <linux/slab.h> @@ -18,6 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> +#include <asm/patching.h> #include <asm/set_memory.h> #include "bpf_jit.h" @@ -1529,3 +1531,53 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); }
+static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
void *addr, u32 *insn)+{
- if (!addr)
*insn = aarch64_insn_gen_nop();- else
*insn = aarch64_insn_gen_branch_imm((unsigned long)ip,(unsigned long)addr,type);- return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT;
+}
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
void *old_addr, void *new_addr)+{
- int ret;
- u32 old_insn;
- u32 new_insn;
- u32 replaced;
- enum aarch64_insn_branch_type branch_type;
- if (poke_type == BPF_MOD_CALL)
branch_type = AARCH64_INSN_BRANCH_LINK;
This path, bpf_arch_text_poke(<ip>, BPF_MOD_CALL, ...), is what we hit when attaching a BPF program entry. It is exercised by selftest #232 xdp_bpf2bpf.
However, with this patchset alone it will not work because we don't emit, yet, the ftrace patch (MOV X9, LR; NOP) as a part of BPF prog prologue, like ftrace_init_nop() does. So patching attempt will fail.
I think that is what you mentioned to in your reply to Hou [1]
So my question is - is support for attaching to BPF progs in scope for this patchset?
If no, then perhaps it would be better for now to fail early with something like -EOPNOTSUPP when poke_type is BPF_MOD_CALL, rather then attempt to patch the code.
If you plan to enable it as a part of this patchset, then I've given it a quick try, and it seems that not a lot is needed get fentry to BPF attachment to work.
I'm including the diff for my quick and dirty attempt below. With that patch on top, the xdp_bpf2bpf tests pass:
#232 xdp_bpf2bpf:OK
[1] https://lore.kernel.org/bpf/d8c4f1fb-a020-9457-44e2-dc63982a9213@huawei.com/
- else
branch_type = AARCH64_INSN_BRANCH_NOLINK;- if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0)
return -EFAULT;- if (gen_branch_or_nop(branch_type, ip, new_addr, &new_insn) < 0)
return -EFAULT;- mutex_lock(&text_mutex);
- if (aarch64_insn_read(ip, &replaced)) {
ret = -EFAULT;goto out;- }
- if (replaced != old_insn) {
ret = -EFAULT;goto out;- }
- ret = aarch64_insn_patch_text_nosync((void *)ip, new_insn);
+out:
- mutex_unlock(&text_mutex);
The body of this critical section is identical as ftrace_modify_code(). Perhaps we could export it and reuse?
- return ret;
+}
--- diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 5f6bd755050f..94d8251500ab 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -240,9 +240,9 @@ static bool is_lsi_offset(int offset, int scale) /* Tail call offset to jump into */ #if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) || \ IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) -#define PROLOGUE_OFFSET 9 +#define PROLOGUE_OFFSET 11 #else -#define PROLOGUE_OFFSET 8 +#define PROLOGUE_OFFSET 10 #endif
static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) @@ -281,6 +281,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) * */
+ /* Set up ftrace patch (initially in disabled state) */ + emit(A64_MOV(1, A64_R(9), A64_LR), ctx); + emit(A64_NOP, ctx); + /* Sign lr */ if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) emit(A64_PACIASP, ctx); @@ -1888,10 +1892,16 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, u32 replaced; enum aarch64_insn_branch_type branch_type;
- if (poke_type == BPF_MOD_CALL) + if (poke_type == BPF_MOD_CALL) { branch_type = AARCH64_INSN_BRANCH_LINK; - else + /* + * Adjust addr to point at the BL in the callsite. + * See ftrace_init_nop() for the callsite sequence. + */ + ip = (void *)((unsigned long)ip + AARCH64_INSN_SIZE); + } else { branch_type = AARCH64_INSN_BRANCH_NOLINK; + }
if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0) return -EFAULT;
On 4/22/2022 6:54 PM, Jakub Sitnicki wrote:
Hi Xu,
Thanks for working on this.
We are also looking forward to using fentry hooks on arm64. In particular, attaching to entry/exit into/from XDP progs.
On Thu, Apr 14, 2022 at 12:22 PM -04, Xu Kuohai wrote:
Impelment bpf_arch_text_poke() for arm64, so bpf trampoline code can use it to replace nop with jump, or replace jump with nop.
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea27..1a1c3ea75ee2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -9,6 +9,7 @@ #include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/memory.h> #include <linux/filter.h> #include <linux/printk.h> #include <linux/slab.h> @@ -18,6 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> +#include <asm/patching.h> #include <asm/set_memory.h> #include "bpf_jit.h" @@ -1529,3 +1531,53 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); }
+static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
void *addr, u32 *insn)+{
- if (!addr)
*insn = aarch64_insn_gen_nop();- else
*insn = aarch64_insn_gen_branch_imm((unsigned long)ip,(unsigned long)addr,type);- return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT;
+}
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
void *old_addr, void *new_addr)+{
- int ret;
- u32 old_insn;
- u32 new_insn;
- u32 replaced;
- enum aarch64_insn_branch_type branch_type;
- if (poke_type == BPF_MOD_CALL)
branch_type = AARCH64_INSN_BRANCH_LINK;This path, bpf_arch_text_poke(<ip>, BPF_MOD_CALL, ...), is what we hit when attaching a BPF program entry. It is exercised by selftest #232 xdp_bpf2bpf.
However, with this patchset alone it will not work because we don't emit, yet, the ftrace patch (MOV X9, LR; NOP) as a part of BPF prog prologue, like ftrace_init_nop() does. So patching attempt will fail.
I think that is what you mentioned to in your reply to Hou [1]
So my question is - is support for attaching to BPF progs in scope for this patchset?
If no, then perhaps it would be better for now to fail early with something like -EOPNOTSUPP when poke_type is BPF_MOD_CALL, rather then attempt to patch the code.
If you plan to enable it as a part of this patchset, then I've given it a quick try, and it seems that not a lot is needed get fentry to BPF attachment to work.
I'm including the diff for my quick and dirty attempt below. With that patch on top, the xdp_bpf2bpf tests pass:
#232 xdp_bpf2bpf:OK
[1] https://lore.kernel.org/bpf/d8c4f1fb-a020-9457-44e2-dc63982a9213@huawei.com/
Hi Jakub,
Thanks for your testing and suggestion! I added bpf2bpf poking to this series and rebased it to [2] a few days ago, so there are some conflicts with the bpf-next branch. I'll rebase it to bpf-next and send v3.
[2] https://lore.kernel.org/bpf/20220416042940.656344-1-kuifeng@fb.com/
- else
branch_type = AARCH64_INSN_BRANCH_NOLINK;- if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0)
return -EFAULT;- if (gen_branch_or_nop(branch_type, ip, new_addr, &new_insn) < 0)
return -EFAULT;- mutex_lock(&text_mutex);
- if (aarch64_insn_read(ip, &replaced)) {
ret = -EFAULT;goto out;- }
- if (replaced != old_insn) {
ret = -EFAULT;goto out;- }
- ret = aarch64_insn_patch_text_nosync((void *)ip, new_insn);
+out:
- mutex_unlock(&text_mutex);
The body of this critical section is identical as ftrace_modify_code(). Perhaps we could export it and reuse?
ftrace_modify_code() is defined in the arch code, and the prototypes are not consistent across archs, so it doesn't seem appropriate to export ftrace_modify_code() as a public interface.
- return ret;
+}
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 5f6bd755050f..94d8251500ab 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -240,9 +240,9 @@ static bool is_lsi_offset(int offset, int scale) /* Tail call offset to jump into */ #if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) || \ IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) -#define PROLOGUE_OFFSET 9 +#define PROLOGUE_OFFSET 11 #else -#define PROLOGUE_OFFSET 8 +#define PROLOGUE_OFFSET 10 #endif static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) @@ -281,6 +281,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) * */
- /* Set up ftrace patch (initially in disabled state) */
- emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
- emit(A64_NOP, ctx);
/* Sign lr */
if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) emit(A64_PACIASP, ctx); @@ -1888,10 +1892,16 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, u32 replaced; enum aarch64_insn_branch_type branch_type;
- if (poke_type == BPF_MOD_CALL)
- if (poke_type == BPF_MOD_CALL) { branch_type = AARCH64_INSN_BRANCH_LINK;
- else
/** Adjust addr to point at the BL in the callsite.* See ftrace_init_nop() for the callsite sequence.*/ip = (void *)((unsigned long)ip + AARCH64_INSN_SIZE);- } else { branch_type = AARCH64_INSN_BRANCH_NOLINK;
- }
if (gen_branch_or_nop(branch_type, ip, old_addr, &old_insn) < 0) return -EFAULT; .
On Sun, Apr 24, 2022 at 01:05 PM +08, Xu Kuohai wrote:
Thanks for your testing and suggestion! I added bpf2bpf poking to this series and rebased it to [2] a few days ago, so there are some conflicts with the bpf-next branch. I'll rebase it to bpf-next and send v3.
[2] https://lore.kernel.org/bpf/20220416042940.656344-1-kuifeng@fb.com/
Looking forward to it.
I think it would be okay to post v3 saying that it depends on the "Attach a cookie to a tracing program" series and won't apply cleanly to bpf-next with out.
It would give us more time to review.
On 4/25/2022 10:26 PM, Jakub Sitnicki wrote:
On Sun, Apr 24, 2022 at 01:05 PM +08, Xu Kuohai wrote:
Thanks for your testing and suggestion! I added bpf2bpf poking to this series and rebased it to [2] a few days ago, so there are some conflicts with the bpf-next branch. I'll rebase it to bpf-next and send v3.
[2] https://lore.kernel.org/bpf/20220416042940.656344-1-kuifeng@fb.com/
Looking forward to it.
I think it would be okay to post v3 saying that it depends on the "Attach a cookie to a tracing program" series and won't apply cleanly to bpf-next with out.
It would give us more time to review. .
Ah, already sent v3 based on bpf-next :(, will send an update after [2] is merged.
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
fentry before bpf trampoline hooked: mov x9, x30 nop
fentry after bpf trampoline hooked: mov x9, x30 bl <bpf_trampoline>
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com --- arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 338 +++++++++++++++++++++++++++++++++- 2 files changed, 348 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 194c95ccc1cf..e29761dc8004 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -86,9 +86,18 @@ AARCH64_INSN_VARIANT_64BIT, \ AARCH64_INSN_LDST_##ls##_PAIR_##type) /* Rn -= 16; Rn[0] = Rt; Rn[8] = Rt2; */ -#define A64_PUSH(Rt, Rt2, Rn) A64_LS_PAIR(Rt, Rt2, Rn, -16, STORE, PRE_INDEX) +#define A64_PUSH(Rt, Rt2, Rn) \ + A64_LS_PAIR(Rt, Rt2, Rn, -16, STORE, PRE_INDEX) /* Rt = Rn[0]; Rt2 = Rn[8]; Rn += 16; */ -#define A64_POP(Rt, Rt2, Rn) A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX) +#define A64_POP(Rt, Rt2, Rn) \ + A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX) + +/* Rn[imm] = Xt1; Rn[imm + 8] = Xt2 */ +#define A64_STP(Xt1, Xt2, Xn, imm) \ + A64_LS_PAIR(Xt1, Xt2, Xn, imm, STORE, SIGNED_OFFSET) +/* Xt1 = Rn[imm]; Xt2 = Rn[imm + 8] */ +#define A64_LDP(Xt1, Xt2, Xn, imm) \ + A64_LS_PAIR(Xt1, Xt2, Xn, imm, LOAD, SIGNED_OFFSET)
/* Load/store exclusive */ #define A64_SIZE(sf) \ @@ -270,6 +279,7 @@ #define A64_BTI_C A64_HINT(AARCH64_INSN_HINT_BTIC) #define A64_BTI_J A64_HINT(AARCH64_INSN_HINT_BTIJ) #define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC) +#define A64_NOP A64_HINT(AARCH64_INSN_HINT_NOP)
/* DMB */ #define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 1a1c3ea75ee2..5f6bd755050f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1333,10 +1333,16 @@ static int validate_code(struct jit_ctx *ctx)
for (i = 0; i < ctx->idx; i++) { u32 a64_insn = le32_to_cpu(ctx->image[i]); - if (a64_insn == AARCH64_BREAK_FAULT) return -1; } + return 0; +} + +static int validate_ctx(struct jit_ctx *ctx) +{ + if (validate_code(ctx)) + return -1;
if (WARN_ON_ONCE(ctx->exentry_idx != ctx->prog->aux->num_exentries)) return -1; @@ -1461,7 +1467,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) build_epilogue(&ctx);
/* 3. Extra pass to validate JITed code. */ - if (validate_code(&ctx)) { + if (validate_ctx(&ctx)) { bpf_jit_binary_free(header); prog = orig_prog; goto out_off; @@ -1532,6 +1538,334 @@ void bpf_jit_free_exec(void *addr) return vfree(addr); }
+static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_prog *p, + int args_off, int retval_off, bool save_ret) +{ + u32 *branch; + u64 enter_prog; + u64 exit_prog; + u8 tmp = bpf2a64[TMP_REG_1]; + u8 r0 = bpf2a64[BPF_REG_0]; + + if (p->aux->sleepable) { + enter_prog = (u64)__bpf_prog_enter_sleepable; + exit_prog = (u64)__bpf_prog_exit_sleepable; + } else { + enter_prog = (u64)__bpf_prog_enter; + exit_prog = (u64)__bpf_prog_exit; + } + + /* bl __bpf_prog_enter */ + emit_addr_mov_i64(A64_R(0), (const u64)p, ctx); + emit_addr_mov_i64(tmp, enter_prog, ctx); + emit(A64_BLR(tmp), ctx); + + /* + * if (__bpf_prog_enter(prog) == 0) + * goto skip_exec_of_prog; + */ + branch = ctx->image + ctx->idx; + emit(A64_NOP, ctx); + + /* move return value to x19 */ + emit(A64_MOV(1, A64_R(19), r0), ctx); + + /* bl bpf_prog */ + emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); + if (!p->jited) + emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); + emit_addr_mov_i64(tmp, (const u64)p->bpf_func, ctx); + emit(A64_BLR(tmp), ctx); + + /* store return value */ + if (save_ret) + emit(A64_STR64I(r0, A64_SP, retval_off), ctx); + + if (ctx->image) { + int offset = &ctx->image[ctx->idx] - branch; + *branch = A64_CBZ(1, A64_R(0), offset); + } + + /* bl __bpf_prog_exit */ + emit_addr_mov_i64(A64_R(0), (const u64)p, ctx); + emit(A64_MOV(1, A64_R(1), A64_R(19)), ctx); + emit_addr_mov_i64(tmp, exit_prog, ctx); + emit(A64_BLR(tmp), ctx); +} + +static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_progs *tp, + int args_off, int retval_off, u32 **branches) +{ + int i; + + /* The first fmod_ret program will receive a garbage return value. + * Set this to 0 to avoid confusing the program. + */ + emit(A64_STR64I(A64_ZR, A64_SP, retval_off), ctx); + for (i = 0; i < tp->nr_progs; i++) { + invoke_bpf_prog(ctx, tp->progs[i], args_off, retval_off, true); + /* + * if (*(u64 *)(sp + retval_off) != 0) + * goto do_fexit; + */ + emit(A64_LDR64I(A64_R(10), A64_SP, retval_off), ctx); + /* Save the location of branch, and generate a nop. + * This nop will be replaced with a cbnz later. + */ + branches[i] = ctx->image + ctx->idx; + emit(A64_NOP, ctx); + } +} + +static void save_args(struct jit_ctx *ctx, int args_off, int nargs) +{ + int i; + + for (i = 0; i < nargs; i++) { + emit(A64_STR64I(i, A64_SP, args_off), ctx); + args_off += 8; + } +} + +static void restore_args(struct jit_ctx *ctx, int args_off, int nargs) +{ + int i; + + for (i = 0; i < nargs; i++) { + emit(A64_LDR64I(i, A64_SP, args_off), ctx); + args_off += 8; + } +} + +/* + * Based on the x86's implementation of arch_prepare_bpf_trampoline(). + * + * We dpend on DYNAMIC_FTRACE_WITH_REGS to set return address and nop. + * + * fentry before bpf trampoline hooked: + * mov x9, x30 + * nop + * + * fentry after bpf trampoline hooked: + * mov x9, x30 + * bl <bpf_trampoline> + * + */ +static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, + struct bpf_tramp_progs *tprogs, void *orig_call, + int nargs, u32 flags) +{ + int i; + int stack_size; + int retaddr_off; + int regs_off; + int retval_off; + int args_off; + int nargs_off; + struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; + struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; + struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; + bool save_ret; + u32 **branches = NULL; + + /* + * trampoline stack layout: + * [ parent ip ] + * [ FP ] + * SP + retaddr_off [ self ip ] + * FP [ FP ] + * + * sp + regs_off [ x19 ] callee-saved regs, currently + * only x19 is used + * + * SP + retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or + * BPF_TRAMP_F_RET_FENTRY_RET flags + * + * [ argN ] + * [ ... ] + * sp + args_off [ arg1 ] + * + * SP + nargs_off [ args count ] + * + * SP + 0 [ traced function ] BPF_TRAMP_F_IP_ARG flag + */ + + stack_size = 0; + /* room for IP address argument */ + if (flags & BPF_TRAMP_F_IP_ARG) + stack_size += 8; + + nargs_off = stack_size; + /* room for args count */ + stack_size += 8; + + args_off = stack_size; + /* room for args */ + stack_size += nargs * 8; + + /* room for return value */ + retval_off = stack_size; + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; + + /* room for callee-saved registers, currently only x19 is used */ + regs_off = stack_size; + stack_size += 8; + + retaddr_off = stack_size + 8; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) + emit(A64_BTI_C, ctx); + + /* frame for parent function */ + emit(A64_PUSH(A64_FP, A64_R(9), A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); + + /* frame for patched function */ + emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); + + /* allocate stack space */ + emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + + if (flags & BPF_TRAMP_F_IP_ARG) { + /* save ip address of the traced function */ + emit_addr_mov_i64(A64_R(10), (const u64)orig_call, ctx); + emit(A64_STR64I(A64_R(10), A64_SP, 0), ctx); + } + + /* save args count*/ + emit(A64_MOVZ(1, A64_R(10), nargs, 0), ctx); + emit(A64_STR64I(A64_R(10), A64_SP, nargs_off), ctx); + + /* save args */ + save_args(ctx, args_off, nargs); + + /* save callee saved registers */ + emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx); + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + emit_addr_mov_i64(A64_R(0), (const u64)im, ctx); + emit_addr_mov_i64(A64_R(10), (const u64)__bpf_tramp_enter, ctx); + emit(A64_BLR(A64_R(10)), ctx); + } + + for (i = 0; i < fentry->nr_progs; i++) + invoke_bpf_prog(ctx, fentry->progs[i], args_off, retval_off, + flags & BPF_TRAMP_F_RET_FENTRY_RET); + + if (fmod_ret->nr_progs) { + branches = kcalloc(fmod_ret->nr_progs, sizeof(u32 *), + GFP_KERNEL); + if (!branches) + return -ENOMEM; + + invoke_bpf_mod_ret(ctx, fmod_ret, args_off, retval_off, + branches); + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + restore_args(ctx, args_off, nargs); + emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); + emit(A64_BLR(A64_R(10)), ctx); + emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx); + im->ip_after_call = ctx->image + ctx->idx; + emit(A64_NOP, ctx); + } + + /* update the branches saved in invoke_bpf_mod_ret with cbnz */ + for (i = 0; i < fmod_ret->nr_progs && ctx->image != NULL; i++) { + int offset = &ctx->image[ctx->idx] - branches[i]; + *branches[i] = A64_CBNZ(1, A64_R(10), offset); + } + + for (i = 0; i < fexit->nr_progs; i++) + invoke_bpf_prog(ctx, fexit->progs[i], args_off, retval_off, + false); + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_args(ctx, args_off, nargs); + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = ctx->image + ctx->idx; + emit_addr_mov_i64(A64_R(0), (const u64)im, ctx); + emit_addr_mov_i64(A64_R(10), (const u64)__bpf_tramp_exit, ctx); + emit(A64_BLR(A64_R(10)), ctx); + } + + /* restore x19 */ + emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx); + + if (save_ret) + emit(A64_LDR64I(A64_R(0), A64_SP, retval_off), ctx); + + /* reset SP */ + emit(A64_MOV(1, A64_SP, A64_FP), ctx); + + /* pop frames */ + emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_POP(A64_FP, A64_R(9), A64_SP), ctx); + + if (flags & BPF_TRAMP_F_SKIP_FRAME) { + /* skip patched function, return to parent */ + emit(A64_MOV(1, A64_LR, A64_R(9)), ctx); + emit(A64_RET(A64_R(9)), ctx); + } else { + /* return to patched function */ + emit(A64_MOV(1, A64_R(10), A64_LR), ctx); + emit(A64_MOV(1, A64_LR, A64_R(9)), ctx); + emit(A64_RET(A64_R(10)), ctx); + } + + if (ctx->image) + bpf_flush_icache(ctx->image, ctx->image + ctx->idx); + + kfree(branches); + + return ctx->idx; +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_progs *tprogs, + void *orig_call) +{ + int ret; + int nargs = m->nr_args; + int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE; + struct jit_ctx ctx = { + .image = NULL, + .idx = 0 + }; + + /* we depends on ftrace to set return address and place nop */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return -ENOTSUPP; + + /* the first 8 arguments are passed by registers */ + if (nargs > 8) + return -ENOTSUPP; + + ret = prepare_trampoline(&ctx, im, tprogs, orig_call, nargs, flags); + if (ret < 0) + return ret; + + if (ret > max_insns) + return -EFBIG; + + ctx.image = image; + ctx.idx = 0; + + jit_fill_hole(image, (unsigned int)(image_end - image)); + ret = prepare_trampoline(&ctx, im, tprogs, orig_call, nargs, flags); + + if (ret > 0 && validate_code(&ctx) < 0) + ret = -EINVAL; + + return ret; +} + static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip, void *addr, u32 *insn) {
On Thu, Apr 14, 2022 at 9:10 AM Xu Kuohai xukuohai@huawei.com wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
fentry before bpf trampoline hooked: mov x9, x30 nop
fentry after bpf trampoline hooked: mov x9, x30 bl <bpf_trampoline>
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
Can you please also take a look at [0], which is an ongoing work to add support for BPF cookie to BPF trampoline-based BPF programs. It's very close to being done, so it would be good if you can implement that at the same time.
[0] https://patchwork.kernel.org/project/netdevbpf/patch/20220412165555.4146407-...
arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 338 +++++++++++++++++++++++++++++++++- 2 files changed, 348 insertions(+), 4 deletions(-)
[...]
On 4/16/2022 1:12 AM, Andrii Nakryiko wrote:
On Thu, Apr 14, 2022 at 9:10 AM Xu Kuohai xukuohai@huawei.com wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
fentry before bpf trampoline hooked: mov x9, x30 nop
fentry after bpf trampoline hooked: mov x9, x30 bl <bpf_trampoline>
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
Can you please also take a look at [0], which is an ongoing work to add support for BPF cookie to BPF trampoline-based BPF programs. It's very close to being done, so it would be good if you can implement that at the same time.
OK, I'll take a look and try to implemnt it.
On 4/16/2022 9:57 AM, Xu Kuohai wrote:
On 4/16/2022 1:12 AM, Andrii Nakryiko wrote:
On Thu, Apr 14, 2022 at 9:10 AM Xu Kuohai xukuohai@huawei.com wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
fentry before bpf trampoline hooked: mov x9, x30 nop
fentry after bpf trampoline hooked: mov x9, x30 bl <bpf_trampoline>
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
Can you please also take a look at [0], which is an ongoing work to add support for BPF cookie to BPF trampoline-based BPF programs. It's very close to being done, so it would be good if you can implement that at the same time.
OK, I'll take a look and try to implemnt it.
already implemented, but there are some conflicts between these two series, will send v3 after trampoline cookie are merged.
On Wed, Apr 20, 2022 at 9:44 AM Xu Kuohai xukuohai@huawei.com wrote:
On 4/16/2022 9:57 AM, Xu Kuohai wrote:
On 4/16/2022 1:12 AM, Andrii Nakryiko wrote:
On Thu, Apr 14, 2022 at 9:10 AM Xu Kuohai xukuohai@huawei.com wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
fentry before bpf trampoline hooked: mov x9, x30 nop
fentry after bpf trampoline hooked: mov x9, x30 bl <bpf_trampoline>
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com
Can you please also take a look at [0], which is an ongoing work to add support for BPF cookie to BPF trampoline-based BPF programs. It's very close to being done, so it would be good if you can implement that at the same time.
OK, I'll take a look and try to implemnt it.
already implemented, but there are some conflicts between these two series, will send v3 after trampoline cookie are merged.
Awesome work, Thanks for doing this!
The "ipv6" word in assertion message should be "fentry_fexit".
Signed-off-by: Xu Kuohai xukuohai@huawei.com Acked-by: Song Liu songliubraving@fb.com --- tools/testing/selftests/bpf/prog_tests/fentry_fexit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 130f5b82d2e6..e3c139bde46e 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -28,8 +28,8 @@ void test_fentry_fexit(void)
prog_fd = fexit_skel->progs.test1.prog_fd; err = bpf_prog_test_run_opts(prog_fd, &topts); - ASSERT_OK(err, "ipv6 test_run"); - ASSERT_OK(topts.retval, "ipv6 test retval"); + ASSERT_OK(err, "fentry_fexit test_run"); + ASSERT_OK(topts.retval, "fentry_fexit test retval");
fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss;
Hi,
On 4/15/2022 12:22 AM, Xu Kuohai wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
bpf_struct_ops also depends on bpf trampoline, could you please also add the test results for bpf_struct_ops related tests case ?
v2:
- Add Song's ACK
- Change the multi-line comment in is_valid_bpf_tramp_flags() into net style (patch 3)
- Fix a deadloop issue in ftrace selftest (patch 2)
- Replace pt_regs->x0 with pt_regs->orig_x0 in patch 1 commit message
- Replace "bpf trampoline" with "custom trampoline" in patch 1, as ftrace direct call is not only used by bpf trampoline.
v1: https://lore.kernel.org/bpf/20220413054959.1053668-1-xukuohai@huawei.com/
Xu Kuohai (6): arm64: ftrace: Add ftrace direct call support ftrace: Fix deadloop caused by direct call in ftrace selftest bpf: Move is_valid_bpf_tramp_flags() to the public trampoline code bpf, arm64: Impelment bpf_arch_text_poke() for arm64 bpf, arm64: bpf trampoline for arm64 selftests/bpf: Fix trivial typo in fentry_fexit.c
arch/arm64/Kconfig | 2 + arch/arm64/include/asm/ftrace.h | 10 + arch/arm64/kernel/asm-offsets.c | 1 + arch/arm64/kernel/entry-ftrace.S | 28 +- arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 390 +++++++++++++++++- arch/x86/net/bpf_jit_comp.c | 20 - include/linux/bpf.h | 5 + kernel/bpf/bpf_struct_ops.c | 4 +- kernel/bpf/trampoline.c | 35 +- kernel/trace/trace_selftest.c | 4 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 4 +- 12 files changed, 482 insertions(+), 35 deletions(-)
On 4/15/2022 10:37 AM, Hou Tao wrote:
Hi,
On 4/15/2022 12:22 AM, Xu Kuohai wrote:
Add bpf trampoline support for arm64. Most of the logic is the same as x86.
Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK
bpf_struct_ops also depends on bpf trampoline, could you please also add the test results for bpf_struct_ops related tests case ?
Yes, more tests is needed. I'm curently testing with bpftrace's kfunc and bpf selftest, more testing results will be posted.
v2:
- Add Song's ACK
- Change the multi-line comment in is_valid_bpf_tramp_flags() into net style (patch 3)
- Fix a deadloop issue in ftrace selftest (patch 2)
- Replace pt_regs->x0 with pt_regs->orig_x0 in patch 1 commit message
- Replace "bpf trampoline" with "custom trampoline" in patch 1, as ftrace direct call is not only used by bpf trampoline.
v1: https://lore.kernel.org/bpf/20220413054959.1053668-1-xukuohai@huawei.com/
Xu Kuohai (6): arm64: ftrace: Add ftrace direct call support ftrace: Fix deadloop caused by direct call in ftrace selftest bpf: Move is_valid_bpf_tramp_flags() to the public trampoline code bpf, arm64: Impelment bpf_arch_text_poke() for arm64 bpf, arm64: bpf trampoline for arm64 selftests/bpf: Fix trivial typo in fentry_fexit.c
arch/arm64/Kconfig | 2 + arch/arm64/include/asm/ftrace.h | 10 + arch/arm64/kernel/asm-offsets.c | 1 + arch/arm64/kernel/entry-ftrace.S | 28 +- arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 390 +++++++++++++++++- arch/x86/net/bpf_jit_comp.c | 20 - include/linux/bpf.h | 5 + kernel/bpf/bpf_struct_ops.c | 4 +- kernel/bpf/trampoline.c | 35 +- kernel/trace/trace_selftest.c | 4 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 4 +- 12 files changed, 482 insertions(+), 35 deletions(-)
.
linux-kselftest-mirror@lists.linaro.org
-
Andrii Nakryiko -
Hou Tao -
Jakub Sitnicki -
KP Singh -
Steven Rostedt -
Xu Kuohai