diff options
| -rw-r--r-- | arch/riscv/include/asm/patch.h | 1 | ||||
| -rw-r--r-- | arch/riscv/kernel/patch.c | 114 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit.h | 3 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit_comp64.c | 60 | ||||
| -rw-r--r-- | arch/riscv/net/bpf_jit_core.c | 106 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 8 |
6 files changed, 255 insertions, 37 deletions
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h index 63c98833d510..e88b52d39eac 100644 --- a/arch/riscv/include/asm/patch.h +++ b/arch/riscv/include/asm/patch.h @@ -7,6 +7,7 @@ #define _ASM_RISCV_PATCH_H int patch_text_nosync(void *addr, const void *insns, size_t len); +int patch_text_set_nosync(void *addr, u8 c, size_t len); int patch_text(void *addr, u32 *insns, int ninsns); extern int riscv_patch_in_stop_machine; diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 575e71d6c8ae..13ee7bf589a1 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -6,6 +6,7 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memory.h> +#include <linux/string.h> #include <linux/uaccess.h> #include <linux/stop_machine.h> #include <asm/kprobes.h> @@ -53,13 +54,52 @@ static void patch_unmap(int fixmap) } NOKPROBE_SYMBOL(patch_unmap); -static int patch_insn_write(void *addr, const void *insn, size_t len) +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + void *waddr = addr; + bool across_pages = (((uintptr_t)addr & ~PAGE_MASK) + len) > PAGE_SIZE; + + /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + /* + * Before reaching here, it was expected to lock the text_mutex + * already, so we don't need to give another lock here and could + * ensure that it was safe between each cores. + */ + lockdep_assert_held(&text_mutex); + + if (across_pages) + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + memset(waddr, c, len); + + patch_unmap(FIX_TEXT_POKE0); + + if (across_pages) + patch_unmap(FIX_TEXT_POKE1); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) { void *waddr = addr; bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE; int ret; /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + + /* * Before reaching here, it was expected to lock the text_mutex * already, so we don't need to give another lock here and could * ensure that it was safe between each cores. @@ -74,7 +114,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) lockdep_assert_held(&text_mutex); if (across_pages) - patch_map(addr + len, FIX_TEXT_POKE1); + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); waddr = patch_map(addr, FIX_TEXT_POKE0); @@ -87,15 +127,79 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) return ret; } -NOKPROBE_SYMBOL(patch_insn_write); +NOKPROBE_SYMBOL(__patch_insn_write); #else -static int patch_insn_write(void *addr, const void *insn, size_t len) +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + memset(addr, c, len); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) { return copy_to_kernel_nofault(addr, insn, len); } -NOKPROBE_SYMBOL(patch_insn_write); +NOKPROBE_SYMBOL(__patch_insn_write); #endif /* CONFIG_MMU */ +static int patch_insn_set(void *addr, u8 c, size_t len) +{ + size_t patched = 0; + size_t size; + int ret = 0; + + /* + * __patch_insn_set() can only work on 2 pages at a time so call it in a + * loop with len <= 2 * PAGE_SIZE. + */ + while (patched < len && !ret) { + size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched); + ret = __patch_insn_set(addr + patched, c, size); + + patched += size; + } + + return ret; +} +NOKPROBE_SYMBOL(patch_insn_set); + +int patch_text_set_nosync(void *addr, u8 c, size_t len) +{ + u32 *tp = addr; + int ret; + + ret = patch_insn_set(tp, c, len); + + if (!ret) + flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len); + + return ret; +} +NOKPROBE_SYMBOL(patch_text_set_nosync); + +static int patch_insn_write(void *addr, const void *insn, size_t len) +{ + size_t patched = 0; + size_t size; + int ret = 0; + + /* + * Copy the instructions to the destination address, two pages at a time + * because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE. + */ + while (patched < len && !ret) { + size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched); + ret = __patch_insn_write(addr + patched, insn + patched, size); + + patched += size; + } + + return ret; +} +NOKPROBE_SYMBOL(patch_insn_write); + int patch_text_nosync(void *addr, const void *insns, size_t len) { u32 *tp = addr; diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index d21c6c92a683..a5ce1ab76ece 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -68,6 +68,7 @@ static inline bool is_creg(u8 reg) struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ + u16 *ro_insns; int ninsns; int prologue_len; int epilogue_offset; @@ -85,7 +86,9 @@ static inline int ninsns_rvoff(int ninsns) struct rv_jit_data { struct bpf_binary_header *header; + struct bpf_binary_header *ro_header; u8 *image; + u8 *ro_image; struct rv_jit_context ctx; }; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 8423f4ddf8f5..ecd3ae6f4116 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -144,7 +144,11 @@ static bool in_auipc_jalr_range(s64 val) /* Emit fixed-length instructions for address */ static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx) { - u64 ip = (u64)(ctx->insns + ctx->ninsns); + /* + * Use the ro_insns(RX) to calculate the offset as the BPF program will + * finally run from this memory region. + */ + u64 ip = (u64)(ctx->ro_insns + ctx->ninsns); s64 off = addr - ip; s64 upper = (off + (1 << 11)) >> 12; s64 lower = off & 0xfff; @@ -464,8 +468,12 @@ static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx) s64 off = 0; u64 ip; - if (addr && ctx->insns) { - ip = (u64)(long)(ctx->insns + ctx->ninsns); + if (addr && ctx->insns && ctx->ro_insns) { + /* + * Use the ro_insns(RX) to calculate the offset as the BPF + * program will finally run from this memory region. + */ + ip = (u64)(long)(ctx->ro_insns + ctx->ninsns); off = addr - ip; } @@ -578,9 +586,10 @@ static int add_exception_handler(const struct bpf_insn *insn, { struct exception_table_entry *ex; unsigned long pc; - off_t offset; + off_t ins_offset; + off_t fixup_offset; - if (!ctx->insns || !ctx->prog->aux->extable || + if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable || (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX)) return 0; @@ -594,12 +603,17 @@ static int add_exception_handler(const struct bpf_insn *insn, return -EINVAL; ex = &ctx->prog->aux->extable[ctx->nexentries]; - pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len]; + pc = (unsigned long)&ctx->ro_insns[ctx->ninsns - insn_len]; - offset = pc - (long)&ex->insn; - if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN)) + /* + * This is the relative offset of the instruction that may fault from + * the exception table itself. This will be written to the exception + * table and if this instruction faults, the destination register will + * be set to '0' and the execution will jump to the next instruction. + */ + 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 @@ -608,12 +622,25 @@ static int add_exception_handler(const struct bpf_insn *insn, * bits. We don't need to worry about buildtime or runtime sort * modifying the upper bits because the table is already sorted, and * isn't part of the main exception table. + * + * The fixup_offset is set to the next instruction from the instruction + * that may fault. The execution will jump to this after handling the + * fault. */ - offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16)); - if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset)) + fixup_offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16)); + 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->insns + ((void *)ex - (void *)ctx->ro_insns); + + 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; @@ -1007,6 +1034,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, ctx.ninsns = 0; ctx.insns = NULL; + ctx.ro_insns = NULL; ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); if (ret < 0) return ret; @@ -1015,7 +1043,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, return -EFBIG; ctx.ninsns = 0; + /* + * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the + * JITed instructions and later copies it to a RX region (ctx.ro_insns). + * It also uses ctx.ro_insns to calculate offsets for jumps etc. As the + * trampoline image uses the same memory area for writing and execution, + * both ctx.insns and ctx.ro_insns can be set to image. + */ ctx.insns = image; + ctx.ro_insns = image; ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); if (ret < 0) return ret; diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 7a26a3e1c73c..7b70ccb7fec3 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -8,6 +8,8 @@ #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/memory.h> +#include <asm/patch.h> #include "bpf_jit.h" /* Number of iterations to try until offsets converge. */ @@ -117,16 +119,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) sizeof(struct exception_table_entry); prog_size = sizeof(*ctx->insns) * ctx->ninsns; - jit_data->header = - bpf_jit_binary_alloc(prog_size + extable_size, - &jit_data->image, - sizeof(u32), - bpf_fill_ill_insns); - if (!jit_data->header) { + jit_data->ro_header = + bpf_jit_binary_pack_alloc(prog_size + extable_size, + &jit_data->ro_image, sizeof(u32), + &jit_data->header, &jit_data->image, + bpf_fill_ill_insns); + if (!jit_data->ro_header) { prog = orig_prog; goto out_offset; } + /* + * 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->ro_insns = (u16 *)jit_data->ro_image; ctx->insns = (u16 *)jit_data->image; /* * Now, when the image is allocated, the image can @@ -138,14 +148,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (i == NR_JIT_ITERATIONS) { pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - if (jit_data->header) - bpf_jit_binary_free(jit_data->header); prog = orig_prog; - goto out_offset; + goto out_free_hdr; } if (extable_size) - prog->aux->extable = (void *)ctx->insns + prog_size; + prog->aux->extable = (void *)ctx->ro_insns + prog_size; skip_init_ctx: pass++; @@ -154,23 +162,33 @@ skip_init_ctx: bpf_jit_build_prologue(ctx); if (build_body(ctx, extra_pass, NULL)) { - bpf_jit_binary_free(jit_data->header); prog = orig_prog; - goto out_offset; + goto out_free_hdr; } bpf_jit_build_epilogue(ctx); if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, prog_size, pass, ctx->insns); - prog->bpf_func = (void *)ctx->insns; + prog->bpf_func = (void *)ctx->ro_insns; prog->jited = 1; prog->jited_len = prog_size; - bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); - if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(jit_data->header); + if (WARN_ON(bpf_jit_binary_pack_finalize(prog, jit_data->ro_header, + jit_data->header))) { + /* ro_header has been freed */ + jit_data->ro_header = NULL; + prog = orig_prog; + goto out_offset; + } + /* + * The instructions have now been copied to the ROX region from + * where they will execute. + * Write any modified data cache blocks out to memory and + * invalidate the corresponding blocks in the instruction cache. + */ + bpf_flush_icache(jit_data->ro_header, ctx->ro_insns + ctx->ninsns); for (i = 0; i < prog->len; i++) ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); @@ -185,6 +203,14 @@ out: bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free_hdr: + if (jit_data->header) { + bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size, + sizeof(jit_data->header->size)); + bpf_jit_binary_pack_free(jit_data->ro_header, jit_data->header); + } + goto out_offset; } u64 bpf_jit_alloc_exec_limit(void) @@ -204,3 +230,51 @@ void bpf_jit_free_exec(void *addr) { return vfree(addr); } + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_nosync(dst, src, len); + mutex_unlock(&text_mutex); + + if (ret) + return ERR_PTR(-EINVAL); + + return dst; +} + +int bpf_arch_text_invalidate(void *dst, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_set_nosync(dst, 0, len); + mutex_unlock(&text_mutex); + + return ret; +} + +void bpf_jit_free(struct bpf_prog *prog) +{ + if (prog->jited) { + struct rv_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); +} diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 0f8f036d8bd1..4e3ce0542e31 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -870,7 +870,7 @@ 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; @@ -894,7 +894,7 @@ 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); @@ -932,7 +932,7 @@ 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; } @@ -956,7 +956,7 @@ 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: |