6.17-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiawei Zhao phoenix500526@163.com
[ Upstream commit 758acb9ccfdbf854b55abaceaf1f3f229cde3d19 ]
On x86-64, USDT arguments can be specified using Scale-Index-Base (SIB) addressing, e.g. "1@-96(%rbp,%rax,8)". The current USDT implementation in libbpf cannot parse this format, causing `bpf_program__attach_usdt()` to fail with -ENOENT (unrecognized register).
This patch fixes this by implementing the necessary changes: - add correct handling for SIB-addressed arguments in `bpf_usdt_arg`. - add adaptive support to `__bpf_usdt_arg_type` and `__bpf_usdt_arg_spec` to represent SIB addressing parameters.
Signed-off-by: Jiawei Zhao phoenix500526@163.com Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20250827053128.1301287-2-phoenix500526@163.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/usdt.bpf.h | 44 ++++++++++++++++++++++++++-- tools/lib/bpf/usdt.c | 62 ++++++++++++++++++++++++++++++++++++---- 2 files changed, 99 insertions(+), 7 deletions(-)
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index 2a7865c8e3fe3..43deb05a51970 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -34,13 +34,32 @@ enum __bpf_usdt_arg_type { BPF_USDT_ARG_CONST, BPF_USDT_ARG_REG, BPF_USDT_ARG_REG_DEREF, + BPF_USDT_ARG_SIB, };
+/* + * This struct layout is designed specifically to be backwards/forward + * compatible between libbpf versions for ARG_CONST, ARG_REG, and + * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+. + */ struct __bpf_usdt_arg_spec { /* u64 scalar interpreted depending on arg_type, see below */ __u64 val_off; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ /* arg location case, see bpf_usdt_arg() for details */ - enum __bpf_usdt_arg_type arg_type; + enum __bpf_usdt_arg_type arg_type: 8; + /* index register offset within struct pt_regs */ + __u16 idx_reg_off: 12; + /* scale factor for index register (1, 2, 4, or 8) */ + __u16 scale_bitshift: 4; + /* reserved for future use, keeps reg_off offset stable */ + __u8 __reserved: 8; +#else + __u8 __reserved: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum __bpf_usdt_arg_type arg_type: 8; +#endif /* offset of referenced register within struct pt_regs */ short reg_off; /* whether arg should be interpreted as signed value */ @@ -149,7 +168,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) { struct __bpf_usdt_spec *spec; struct __bpf_usdt_arg_spec *arg_spec; - unsigned long val; + unsigned long val, idx; int err, spec_id;
*res = 0; @@ -202,6 +221,27 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) return err; #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ val >>= arg_spec->arg_bitshift; +#endif + break; + case BPF_USDT_ARG_SIB: + /* Arg is in memory addressed by SIB (Scale-Index-Base) mode + * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). We first + * fetch the base register contents and the index register + * contents from pt_regs. Then we calculate the final address + * as base + (index * scale) + offset, and do a user-space + * probe read to fetch the argument value. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off); + if (err) + return err; + err = bpf_probe_read_user(&val, sizeof(val), (void *)(val + (idx << arg_spec->scale_bitshift) + arg_spec->val_off)); + if (err) + return err; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + val >>= arg_spec->arg_bitshift; #endif break; default: diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 3373b9d45ac44..867bff6b06990 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -200,12 +200,23 @@ enum usdt_arg_type { USDT_ARG_CONST, USDT_ARG_REG, USDT_ARG_REG_DEREF, + USDT_ARG_SIB, };
/* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */ struct usdt_arg_spec { __u64 val_off; - enum usdt_arg_type arg_type; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + enum usdt_arg_type arg_type: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + __u8 __reserved: 8; /* keep reg_off offset stable */ +#else + __u8 __reserved: 8; /* keep reg_off offset stable */ + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum usdt_arg_type arg_type: 8; +#endif short reg_off; bool arg_signed; char arg_bitshift; @@ -1283,11 +1294,51 @@ static int calc_pt_regs_off(const char *reg_name)
static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { - char reg_name[16]; - int len, reg_off; - long off; + char reg_name[16] = {0}, idx_reg_name[16] = {0}; + int len, reg_off, idx_reg_off, scale = 1; + long off = 0; + + if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 || + sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, &off, reg_name, idx_reg_name, &len) == 4 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, reg_name, idx_reg_name, &len) == 3 + ) { + /* + * Scale Index Base case: + * 1@-96(%rbp,%rax,8) + * 1@(%rbp,%rax,8) + * 1@-96(%rbp,%rax) + * 1@(%rbp,%rax) + */ + arg->arg_type = USDT_ARG_SIB; + arg->val_off = off;
- if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) { + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + + idx_reg_off = calc_pt_regs_off(idx_reg_name); + if (idx_reg_off < 0) + return idx_reg_off; + arg->idx_reg_off = idx_reg_off; + + /* validate scale factor and set fields directly */ + switch (scale) { + case 1: arg->scale_bitshift = 0; break; + case 2: arg->scale_bitshift = 1; break; + case 4: arg->scale_bitshift = 2; break; + case 8: arg->scale_bitshift = 3; break; + default: + pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale); + return -EINVAL; + } + } else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", + arg_sz, &off, reg_name, &len) == 3) { /* Memory dereference case, e.g., -4@-20(%rbp) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1306,6 +1357,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec } else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) { /* Register read case, e.g., -4@%eax */ arg->arg_type = USDT_ARG_REG; + /* register read has no memory offset */ arg->val_off = 0;
reg_off = calc_pt_regs_off(reg_name);