* [PATCH bpf-next v2 1/3] bpf: make bpf_prog_pack allocator portable
2023-06-07 9:18 [PATCH bpf-next v2 0/3] bpf, arm64: use BPF prog pack allocator in BPF JIT Puranjay Mohan
@ 2023-06-07 9:18 ` Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 2/3] arm64: patching: Add aarch64_insn_copy() Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 3/3] bpf, arm64: use bpf_jit_binary_pack_alloc Puranjay Mohan
2 siblings, 0 replies; 7+ messages in thread
From: Puranjay Mohan @ 2023-06-07 9:18 UTC (permalink / raw)
To: ast, daniel, andrii, martin.lau, song, catalin.marinas,
mark.rutland, bpf, kpsingh, linux-arm-kernel, linux-kernel
Cc: puranjay12
The bpf_prog_pack allocator currently uses module_alloc() and
module_memfree() to allocate and free memory. This is not portable
because different architectures use different methods for allocating
memory for BPF programs. Like ARM64 uses vmalloc()/vfree().
Use bpf_jit_alloc_exec() and bpf_jit_free_exec() for memory management
in bpf_prog_pack allocator. Other architectures can override these with
their implementation and will be able to use bpf_prog_pack directly.
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Song Liu <song@kernel.org>
---
Changes in v1 => v2:
- No code changes.
- Added Acked-by: Song Liu <song@kernel.org>
kernel/bpf/core.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7421487422d4..2bc9092bf9be 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -860,7 +860,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
GFP_KERNEL);
if (!pack)
return NULL;
- pack->ptr = module_alloc(BPF_PROG_PACK_SIZE);
+ pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE);
if (!pack->ptr) {
kfree(pack);
return NULL;
@@ -884,7 +884,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
mutex_lock(&pack_mutex);
if (size > BPF_PROG_PACK_SIZE) {
size = round_up(size, PAGE_SIZE);
- ptr = module_alloc(size);
+ ptr = bpf_jit_alloc_exec(size);
if (ptr) {
bpf_fill_ill_insns(ptr, size);
set_vm_flush_reset_perms(ptr);
@@ -922,7 +922,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
mutex_lock(&pack_mutex);
if (hdr->size > BPF_PROG_PACK_SIZE) {
- module_memfree(hdr);
+ bpf_jit_free_exec(hdr);
goto out;
}
@@ -946,7 +946,7 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
BPF_PROG_CHUNK_COUNT, 0) == 0) {
list_del(&pack->list);
- module_memfree(pack->ptr);
+ bpf_jit_free_exec(pack->ptr);
kfree(pack);
}
out:
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH bpf-next v2 2/3] arm64: patching: Add aarch64_insn_copy()
2023-06-07 9:18 [PATCH bpf-next v2 0/3] bpf, arm64: use BPF prog pack allocator in BPF JIT Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 1/3] bpf: make bpf_prog_pack allocator portable Puranjay Mohan
@ 2023-06-07 9:18 ` Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 3/3] bpf, arm64: use bpf_jit_binary_pack_alloc Puranjay Mohan
2 siblings, 0 replies; 7+ messages in thread
From: Puranjay Mohan @ 2023-06-07 9:18 UTC (permalink / raw)
To: ast, daniel, andrii, martin.lau, song, catalin.marinas,
mark.rutland, bpf, kpsingh, linux-arm-kernel, linux-kernel
Cc: puranjay12
This will be used by BPF JIT compiler to dump JITed binary to a RX huge
page, and thus allow multiple BPF programs sharing the a huge (2MB)
page.
The bpf_prog_pack allocator that implements the above feature allocates
a RX/RW buffer pair. The JITed code is written to the RW buffer and then
this function will be used to copy the code from RW to RX buffer.
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Song Liu <song@kernel.org>
---
Changes in v1 => v2:
- Renamed addr/opcode to dst/src.
- Added Acked-by: Song Liu <song@kernel.org>
arch/arm64/include/asm/patching.h | 1 +
arch/arm64/kernel/patching.c | 39 +++++++++++++++++++++++++++++++
2 files changed, 40 insertions(+)
diff --git a/arch/arm64/include/asm/patching.h b/arch/arm64/include/asm/patching.h
index 68908b82b168..f78a0409cbdb 100644
--- a/arch/arm64/include/asm/patching.h
+++ b/arch/arm64/include/asm/patching.h
@@ -8,6 +8,7 @@ int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
int aarch64_insn_write_literal_u64(void *addr, u64 val);
+void *aarch64_insn_copy(void *dst, const void *src, size_t len);
int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index b4835f6d594b..419a9428402e 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -105,6 +105,45 @@ noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val)
return ret;
}
+/**
+ * aarch64_insn_copy - Copy instructions into (an unused part of) RX memory
+ * @dst: address to modify
+ * @src: source of the copy
+ * @len: length to copy
+ *
+ * Useful for JITs to dump new code blocks into unused regions of RX memory.
+ */
+noinstr void *aarch64_insn_copy(void *dst, const void *src, size_t len)
+{
+ unsigned long flags;
+ size_t patched = 0;
+ size_t size;
+ void *waddr;
+ void *ptr;
+ int ret;
+
+ raw_spin_lock_irqsave(&patch_lock, flags);
+
+ while (patched < len) {
+ ptr = dst + patched;
+ size = min_t(size_t, PAGE_SIZE - offset_in_page(ptr),
+ len - patched);
+
+ waddr = patch_map(ptr, FIX_TEXT_POKE0);
+ ret = copy_to_kernel_nofault(waddr, src + patched, size);
+ patch_unmap(FIX_TEXT_POKE0);
+
+ if (ret < 0) {
+ raw_spin_unlock_irqrestore(&patch_lock, flags);
+ return NULL;
+ }
+ patched += size;
+ }
+ raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+ return dst;
+}
+
int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
{
u32 *tp = addr;
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH bpf-next v2 3/3] bpf, arm64: use bpf_jit_binary_pack_alloc
2023-06-07 9:18 [PATCH bpf-next v2 0/3] bpf, arm64: use BPF prog pack allocator in BPF JIT Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 1/3] bpf: make bpf_prog_pack allocator portable Puranjay Mohan
2023-06-07 9:18 ` [PATCH bpf-next v2 2/3] arm64: patching: Add aarch64_insn_copy() Puranjay Mohan
@ 2023-06-07 9:18 ` Puranjay Mohan
2023-06-08 16:28 ` Song Liu
2 siblings, 1 reply; 7+ messages in thread
From: Puranjay Mohan @ 2023-06-07 9:18 UTC (permalink / raw)
To: ast, daniel, andrii, martin.lau, song, catalin.marinas,
mark.rutland, bpf, kpsingh, linux-arm-kernel, linux-kernel
Cc: puranjay12
Use bpf_jit_binary_pack_alloc for memory management of JIT binaries in
ARM64 BPF JIT. The bpf_jit_binary_pack_alloc creates a pair of RW and RX
buffers. The JIT writes the program into the RW buffer. When the JIT is
done, the program is copied to the final RX buffer
with bpf_jit_binary_pack_finalize.
Implement bpf_arch_text_copy() and bpf_arch_text_invalidate() for ARM64
JIT as these functions are required by bpf_jit_binary_pack allocator.
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
Changes in v1 => v2:
- Made the naming of ro_ prefix consistent.
Now image/header/image_ptr are read/write and
ro_image/ro_header/ro_image_ptr are read-only.
arch/arm64/net/bpf_jit_comp.c | 126 +++++++++++++++++++++++++++-------
1 file changed, 103 insertions(+), 23 deletions(-)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 145b540ec34f..0e38fa63b551 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -76,6 +76,7 @@ struct jit_ctx {
int *offset;
int exentry_idx;
__le32 *image;
+ __le32 *ro_image;
u32 stack_size;
int fpb_offset;
};
@@ -205,6 +206,20 @@ static void jit_fill_hole(void *area, unsigned int size)
*ptr++ = cpu_to_le32(AARCH64_BREAK_FAULT);
}
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+ __le32 *ptr;
+ int ret;
+
+ for (ptr = dst; len >= sizeof(u32); len -= sizeof(u32)) {
+ ret = aarch64_insn_patch_text_nosync(ptr++, AARCH64_BREAK_FAULT);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static inline int epilogue_offset(const struct jit_ctx *ctx)
{
int to = ctx->epilogue_offset;
@@ -701,7 +716,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
struct jit_ctx *ctx,
int dst_reg)
{
- off_t offset;
+ off_t ins_offset;
+ off_t fixup_offset;
unsigned long pc;
struct exception_table_entry *ex;
@@ -717,12 +733,11 @@ static int add_exception_handler(const struct bpf_insn *insn,
return -EINVAL;
ex = &ctx->prog->aux->extable[ctx->exentry_idx];
- pc = (unsigned long)&ctx->image[ctx->idx - 1];
+ pc = (unsigned long)&ctx->ro_image[ctx->idx - 1];
- offset = pc - (long)&ex->insn;
- if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+ ins_offset = pc - (long)&ex->insn;
+ if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
return -ERANGE;
- ex->insn = offset;
/*
* Since the extable follows the program, the fixup offset is always
@@ -732,11 +747,20 @@ static int add_exception_handler(const struct bpf_insn *insn,
* modifying the upper bits because the table is already sorted, and
* isn't part of the main exception table.
*/
- offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
- if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+ fixup_offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
+ if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
return -ERANGE;
- ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+ /*
+ * The offsets above have been calculated using the RO buffer but we
+ * need to use the R/W buffer for writes.
+ * switch ex to rw buffer for writing.
+ */
+ ex = (void *)ctx->image + ((void *)ex - (void *)ctx->ro_image);
+
+ ex->insn = ins_offset;
+
+ ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
ex->type = EX_TYPE_BPF;
@@ -1446,7 +1470,8 @@ static inline void bpf_flush_icache(void *start, void *end)
struct arm64_jit_data {
struct bpf_binary_header *header;
- u8 *image;
+ u8 *ro_image;
+ struct bpf_binary_header *ro_header;
struct jit_ctx ctx;
};
@@ -1455,12 +1480,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
int image_size, prog_size, extable_size, extable_align, extable_offset;
struct bpf_prog *tmp, *orig_prog = prog;
struct bpf_binary_header *header;
+ struct bpf_binary_header *ro_header;
struct arm64_jit_data *jit_data;
bool was_classic = bpf_prog_was_classic(prog);
bool tmp_blinded = false;
bool extra_pass = false;
struct jit_ctx ctx;
u8 *image_ptr;
+ u8 *ro_image_ptr;
if (!prog->jit_requested)
return orig_prog;
@@ -1487,8 +1514,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
}
if (jit_data->ctx.offset) {
ctx = jit_data->ctx;
- image_ptr = jit_data->image;
+ ro_image_ptr = jit_data->ro_image;
+ ro_header = jit_data->ro_header;
header = jit_data->header;
+ image_ptr = (void *)header + ((void *)ro_image_ptr
+ - (void *)ro_header);
extra_pass = true;
prog_size = sizeof(u32) * ctx.idx;
goto skip_init_ctx;
@@ -1533,18 +1563,27 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
/* also allocate space for plt target */
extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
image_size = extable_offset + extable_size;
- header = bpf_jit_binary_alloc(image_size, &image_ptr,
- sizeof(u32), jit_fill_hole);
- if (header == NULL) {
+ ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
+ sizeof(u32), &header, &image_ptr,
+ jit_fill_hole);
+ if (!ro_header) {
prog = orig_prog;
goto out_off;
}
/* 2. Now, the actual pass. */
+ /*
+ * Use the image(RW) for writing the JITed instructions. But also save
+ * the ro_image(RX) for calculating the offsets in the image. The RW
+ * image will be later copied to the RX image from where the program
+ * will run. The bpf_jit_binary_pack_finalize() will do this copy in the
+ * final step.
+ */
ctx.image = (__le32 *)image_ptr;
+ ctx.ro_image = (__le32 *)ro_image_ptr;
if (extable_size)
- prog->aux->extable = (void *)image_ptr + extable_offset;
+ prog->aux->extable = (void *)ro_image_ptr + extable_offset;
skip_init_ctx:
ctx.idx = 0;
ctx.exentry_idx = 0;
@@ -1552,9 +1591,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
build_prologue(&ctx, was_classic);
if (build_body(&ctx, extra_pass)) {
- bpf_jit_binary_free(header);
prog = orig_prog;
- goto out_off;
+ goto out_free_hdr;
}
build_epilogue(&ctx);
@@ -1562,34 +1600,37 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
/* 3. Extra pass to validate JITed code. */
if (validate_ctx(&ctx)) {
- bpf_jit_binary_free(header);
prog = orig_prog;
- goto out_off;
+ goto out_free_hdr;
}
/* And we're done. */
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, prog_size, 2, ctx.image);
- bpf_flush_icache(header, ctx.image + ctx.idx);
+ bpf_flush_icache(ro_header, ctx.ro_image + ctx.idx);
if (!prog->is_func || extra_pass) {
if (extra_pass && ctx.idx != jit_data->ctx.idx) {
pr_err_once("multi-func JIT bug %d != %d\n",
ctx.idx, jit_data->ctx.idx);
- bpf_jit_binary_free(header);
prog->bpf_func = NULL;
prog->jited = 0;
prog->jited_len = 0;
+ goto out_free_hdr;
+ }
+ if (WARN_ON(bpf_jit_binary_pack_finalize(prog, ro_header,
+ header))) {
+ ro_header = NULL;
goto out_off;
}
- bpf_jit_binary_lock_ro(header);
} else {
jit_data->ctx = ctx;
- jit_data->image = image_ptr;
+ jit_data->ro_image = ro_image_ptr;
jit_data->header = header;
+ jit_data->ro_header = ro_header;
}
- prog->bpf_func = (void *)ctx.image;
+ prog->bpf_func = (void *)ctx.ro_image;
prog->jited = 1;
prog->jited_len = prog_size;
@@ -1610,6 +1651,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bpf_jit_prog_release_other(prog, prog == orig_prog ?
tmp : orig_prog);
return prog;
+
+out_free_hdr:
+ if (header) {
+ bpf_arch_text_copy(&ro_header->size, &header->size,
+ sizeof(header->size));
+ bpf_jit_binary_pack_free(ro_header, header);
+ }
+ goto out_off;
}
bool bpf_jit_supports_kfunc_call(void)
@@ -1617,6 +1666,13 @@ bool bpf_jit_supports_kfunc_call(void)
return true;
}
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+ if (!aarch64_insn_copy(dst, src, len))
+ return ERR_PTR(-EINVAL);
+ return dst;
+}
+
u64 bpf_jit_alloc_exec_limit(void)
{
return VMALLOC_END - VMALLOC_START;
@@ -2221,3 +2277,27 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
return ret;
}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+ if (prog->jited) {
+ struct arm64_jit_data *jit_data = prog->aux->jit_data;
+ struct bpf_binary_header *hdr;
+
+ /*
+ * If we fail the final pass of JIT (from jit_subprogs),
+ * the program may not be finalized yet. Call finalize here
+ * before freeing it.
+ */
+ if (jit_data) {
+ bpf_jit_binary_pack_finalize(prog, jit_data->ro_header,
+ jit_data->header);
+ kfree(jit_data);
+ }
+ hdr = bpf_jit_binary_pack_hdr(prog);
+ bpf_jit_binary_pack_free(hdr, NULL);
+ WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
+ }
+
+ bpf_prog_unlock_free(prog);
+}
--
2.39.2
^ permalink raw reply related [flat|nested] 7+ messages in thread