Linked scalar registers are recorded in the jump history packed into a u64 as five 11-bit entries, each naming a frame and a register or stack slot. The 6-bit slot field covers exactly the 64 slots of a 512-byte frame, so a spilled scalar in a deeper slot could not be linked and larger frames were ruled out by construction. Store the linked registers as an array of five u16 entries plus a count instead, each entry holding the frame number, a register-or-slot bit and an 11-bit register or slot index, which covers frames of up to 16 KiB. Callers that record no linked registers pass NULL. The history entry grows from 16 to 20 bytes, and the history is the one verifier structure whose size follows the number of instructions a loop iterates over rather than the state count. Measured over the 5075 selftest programs, peak verifier memory is unchanged for all but the loop-heavy ones, which grow by 8 to 16%: loop1/nested_loops from 17.6 to 19.2 MiB, verifier_loops1/jumps_out_rather_than_in from 4.4 to 5.1 MiB, strobemeta by 0.3% and pyperf600_nounroll by 0.8%. Verdicts, processed instructions and state counts stay the same everywhere. No functional change. Signed-off-by: Kumar Kartikeya Dwivedi --- include/linux/bpf_verifier.h | 16 +++++-- kernel/bpf/backtrack.c | 18 +++++--- kernel/bpf/states.c | 2 +- kernel/bpf/verifier.c | 86 ++++++++++++++++-------------------- 4 files changed, 62 insertions(+), 60 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5a1d21455831..1d80f7a4f26d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -428,6 +428,9 @@ enum { INSN_F_STACK_ARG_ACCESS = BIT(3), }; +/* Registers linked to one jump condition that a history entry can record */ +#define BPF_LINKED_REGS_MAX 5 + struct bpf_jmp_history_entry { /* insn idx can't be bigger than 1 million */ u32 idx : 20; @@ -438,10 +441,14 @@ struct bpf_jmp_history_entry { u32 prev_idx : 20; u32 spi : 12; /* stack slot index */ /* - * additional registers that need precision tracking when this - * jump is backtracked, vector of five 11-bit records + * Scalar registers and spilled scalars linked to the condition of + * this jump, which need precision tracking together when the jump is + * backtracked. Each is packed as 4 bits of frame number, one bit + * telling a register from a stack slot and 11 bits of register or + * slot index, see linked_regs_pack(). */ - u64 linked_regs; + u16 linked_regs[BPF_LINKED_REGS_MAX]; + u8 linked_regs_cnt; }; static_assert(MAX_CALL_FRAMES <= (1 << 4)); @@ -1288,7 +1295,8 @@ struct list_head *bpf_explored_state(struct bpf_verifier_env *env, int idx); void bpf_free_verifier_state(struct bpf_verifier_state *state, bool free_self); void bpf_free_backedges(struct bpf_scc_visit *visit); int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, - int insn_flags, int spi, int frame, u64 linked_regs); + int insn_flags, int spi, int frame, const u16 *linked_regs, + u8 linked_regs_cnt); void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist); void bpf_mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c index 9cc712f1619b..06630acd0d1f 100644 --- a/kernel/bpf/backtrack.c +++ b/kernel/bpf/backtrack.c @@ -9,7 +9,8 @@ /* for any branch, call, exit record the history of jmps in the given state */ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, - int insn_flags, int spi, int frame, u64 linked_regs) + int insn_flags, int spi, int frame, const u16 *linked_regs, + u8 linked_regs_cnt) { u32 cnt = cur->jmp_history_cnt; struct bpf_jmp_history_entry *p; @@ -27,10 +28,13 @@ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state env->cur_hist_ent->flags |= insn_flags; env->cur_hist_ent->spi = spi; env->cur_hist_ent->frame = frame; - verifier_bug_if(env->cur_hist_ent->linked_regs != 0, env, - "insn history: insn_idx %d linked_regs: %#llx", - env->insn_idx, env->cur_hist_ent->linked_regs); - env->cur_hist_ent->linked_regs = linked_regs; + verifier_bug_if(env->cur_hist_ent->linked_regs_cnt != 0, env, + "insn history: insn_idx %d has %u linked regs", + env->insn_idx, env->cur_hist_ent->linked_regs_cnt); + if (linked_regs_cnt) + memcpy(env->cur_hist_ent->linked_regs, linked_regs, + linked_regs_cnt * sizeof(*linked_regs)); + env->cur_hist_ent->linked_regs_cnt = linked_regs_cnt; return 0; } @@ -47,7 +51,9 @@ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state p->flags = insn_flags; p->spi = spi; p->frame = frame; - p->linked_regs = linked_regs; + if (linked_regs_cnt) + memcpy(p->linked_regs, linked_regs, linked_regs_cnt * sizeof(*linked_regs)); + p->linked_regs_cnt = linked_regs_cnt; cur->jmp_history_cnt = cnt; env->cur_hist_ent = p; diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c index 9930d3fa5f99..a7c87a1d8cc8 100644 --- a/kernel/bpf/states.c +++ b/kernel/bpf/states.c @@ -1416,7 +1416,7 @@ int bpf_is_state_visited(struct bpf_verifier_env *env, int insn_idx) */ err = 0; if (bpf_is_jmp_point(env, env->insn_idx)) - err = bpf_push_jmp_history(env, cur, 0, 0, 0, 0); + err = bpf_push_jmp_history(env, cur, 0, 0, 0, NULL, 0); err = err ? : propagate_precision(env, &sl->state, cur, NULL); if (err) return err; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 33504528ddda..4ce187002333 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3374,26 +3374,25 @@ static void mark_non_stack_access(struct bpf_verifier_env *env, int idx) env->insn_aux_data[idx].non_stack_access = true; } +/* Layout of one packed linked register in the jump history, see linked_regs_pack() */ #define LR_FRAMENO_BITS 4 -#define LR_SPI_BITS 6 -#define LR_ENTRY_BITS (LR_SPI_BITS + LR_FRAMENO_BITS + 1) -#define LR_SIZE_BITS 4 -#define LR_FRAMENO_MASK ((1ull << LR_FRAMENO_BITS) - 1) -#define LR_SPI_MASK ((1ull << LR_SPI_BITS) - 1) -#define LR_SIZE_MASK ((1ull << LR_SIZE_BITS) - 1) -#define LR_SPI_OFF LR_FRAMENO_BITS -#define LR_IS_REG_OFF (LR_SPI_BITS + LR_FRAMENO_BITS) -#define LINKED_REGS_MAX 5 +#define LR_INDEX_BITS 11 +#define LR_FRAMENO_MASK ((1u << LR_FRAMENO_BITS) - 1) +#define LR_IS_REG BIT(LR_FRAMENO_BITS) +#define LR_INDEX_OFF (LR_FRAMENO_BITS + 1) +#define LR_INDEX_MASK ((1u << LR_INDEX_BITS) - 1) +#define LINKED_REGS_MAX BPF_LINKED_REGS_MAX static_assert(MAX_CALL_FRAMES <= (1 << LR_FRAMENO_BITS)); -static_assert(LINKED_REGS_MAX < (1 << LR_SIZE_BITS)); -static_assert(LINKED_REGS_MAX * LR_ENTRY_BITS + LR_SIZE_BITS <= 64); +static_assert(MAX_BPF_REG <= (1 << LR_INDEX_BITS)); +static_assert(MAX_BPF_STACK_SLOTS <= (1 << LR_INDEX_BITS)); +static_assert(LR_INDEX_OFF + LR_INDEX_BITS <= 16); struct linked_reg { u8 frameno; union { - u8 spi; - u8 regno; + u16 spi; + u16 regno; }; bool is_reg; }; @@ -3412,48 +3411,34 @@ static struct linked_reg *linked_regs_push(struct linked_regs *s) } /* - * Use u64 as a vector of 5 11-bit values, use first 4-bits to track - * number of elements currently in stack. - * Pack one history entry for linked registers as 11 bits in the following format: - * - 4-bits frameno - * - 6-bits spi_or_reg - * - 1-bit is_reg + * Pack linked registers for a jump history entry, one u16 each: + * - 4 bits frameno + * - 1 bit is_reg + * - 11 bits register or stack slot index */ -static u64 linked_regs_pack(struct linked_regs *s) +static void linked_regs_pack(const struct linked_regs *s, u16 *packed) { - u64 val = 0; int i; for (i = 0; i < s->cnt; ++i) { - struct linked_reg *e = &s->entries[i]; - u64 tmp = 0; - - tmp |= e->frameno; - tmp |= e->spi << LR_SPI_OFF; - tmp |= (e->is_reg ? 1 : 0) << LR_IS_REG_OFF; + const struct linked_reg *e = &s->entries[i]; - val <<= LR_ENTRY_BITS; - val |= tmp; + packed[i] = e->frameno | (e->is_reg ? LR_IS_REG : 0) | (e->spi << LR_INDEX_OFF); } - val <<= LR_SIZE_BITS; - val |= s->cnt; - return val; } -static void linked_regs_unpack(u64 val, struct linked_regs *s) +static void linked_regs_unpack(const struct bpf_jmp_history_entry *hist, struct linked_regs *s) { int i; - s->cnt = val & LR_SIZE_MASK; - val >>= LR_SIZE_BITS; - + s->cnt = hist->linked_regs_cnt; for (i = 0; i < s->cnt; ++i) { struct linked_reg *e = &s->entries[i]; + u16 packed = hist->linked_regs[i]; - e->frameno = val & LR_FRAMENO_MASK; - e->spi = (val >> LR_SPI_OFF) & LR_SPI_MASK; - e->is_reg = (val >> LR_IS_REG_OFF) & 0x1; - val >>= LR_ENTRY_BITS; + e->frameno = packed & LR_FRAMENO_MASK; + e->is_reg = packed & LR_IS_REG; + e->spi = (packed >> LR_INDEX_OFF) & LR_INDEX_MASK; } } @@ -3495,10 +3480,10 @@ void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_ bool some_precise = false; int i; - if (!hist || hist->linked_regs == 0) + if (!hist || !hist->linked_regs_cnt) return; - linked_regs_unpack(hist->linked_regs, &linked_regs); + linked_regs_unpack(hist, &linked_regs); for (i = 0; i < linked_regs.cnt; ++i) { struct linked_reg *e = &linked_regs.entries[i]; @@ -3784,7 +3769,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (insn_flags) return bpf_push_jmp_history(env, env->cur_state, insn_flags, - hist_spi, hist_frame, 0); + hist_spi, hist_frame, NULL, 0); return 0; } @@ -4162,7 +4147,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, } if (insn_flags) return bpf_push_jmp_history(env, env->cur_state, insn_flags, - hist_spi, hist_frame, 0); + hist_spi, hist_frame, NULL, 0); return 0; } @@ -4352,7 +4337,7 @@ static int check_stack_arg_write(struct bpf_verifier_env *env, struct bpf_func_s bpf_diag_mod_end(env); state->no_stack_arg_load = true; return bpf_push_jmp_history(env, env->cur_state, - INSN_F_STACK_ARG_ACCESS, spi, 0, 0); + INSN_F_STACK_ARG_ACCESS, spi, 0, NULL, 0); } /* @@ -4386,7 +4371,7 @@ static int check_stack_arg_read(struct bpf_verifier_env *env, struct bpf_func_st cur->regs[dst_regno] = *arg; bpf_diag_mod_end(env); return bpf_push_jmp_history(env, env->cur_state, - INSN_F_STACK_ARG_ACCESS, spi, 0, 0); + INSN_F_STACK_ARG_ACCESS, spi, 0, NULL, 0); } static int mark_stack_arg_precision(struct bpf_verifier_env *env, int arg_idx) @@ -17934,7 +17919,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } if (insn_flags) { - err = bpf_push_jmp_history(env, this_branch, insn_flags, 0, 0, 0); + err = bpf_push_jmp_history(env, this_branch, insn_flags, 0, 0, NULL, 0); if (err) return err; } @@ -18004,7 +17989,10 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * if parent state is created. */ if (linked_regs.cnt > 1) { - err = bpf_push_jmp_history(env, this_branch, 0, 0, 0, linked_regs_pack(&linked_regs)); + u16 packed[LINKED_REGS_MAX]; + + linked_regs_pack(&linked_regs, packed); + err = bpf_push_jmp_history(env, this_branch, 0, 0, 0, packed, linked_regs.cnt); if (err) return err; } @@ -19402,7 +19390,7 @@ static int do_check(struct bpf_verifier_env *env) } if (bpf_is_jmp_point(env, env->insn_idx)) { - err = bpf_push_jmp_history(env, state, 0, 0, 0, 0); + err = bpf_push_jmp_history(env, state, 0, 0, 0, NULL, 0); if (err) return err; } -- 2.53.0