On Fri, Mar 3, 2023 at 12:37 AM Puranjay Mohan <puranjay12@xxxxxxxxx> wrote: > > Parsing of USDT arguments is architecture-specific; on arm it is > relatively easy since registers used are r[0-10], fp, ip, sp, lr, > pc. Format is slightly different compared to aarch64; forms are > > - "size @ [ reg, #offset ]" for dereferences, for example > "-8 @ [ sp, #76 ]" ; " -4 @ [ sp ]" > - "size @ reg" for register values; for example > "-4@r0" > - "size @ #value" for raw values; for example > "-8@#1" > > Add support for parsing USDT arguments for ARM architecture. > > Signed-off-by: Puranjay Mohan <puranjay12@xxxxxxxxx> > --- You don't mention that in the commit message, but how did you test these changes? > Changes in V1[1] to V2 > - Resending as V1 shows up as Superseded in patchwork. > > [1] https://patchwork.kernel.org/project/netdevbpf/patch/20230220212741.13515-1-puranjay12@xxxxxxxxx/ > --- > tools/lib/bpf/usdt.c | 82 ++++++++++++++++++++++++++++++++++++++++++++ > 1 file changed, 82 insertions(+) > > diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c > index 75b411fc2c77..ef097b882a4d 100644 > --- a/tools/lib/bpf/usdt.c > +++ b/tools/lib/bpf/usdt.c > @@ -1505,6 +1505,88 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec > return len; > } > > +#elif defined(__arm__) > + > +static int calc_pt_regs_off(const char *reg_name) > +{ > + int reg_num; > + > + if (sscanf(reg_name, "r%d", ®_num) == 1) { > + if (reg_num >= 0 && reg_num <= 10) > + return offsetof(struct pt_regs, uregs[reg_num]); > + } else if (strcmp(reg_name, "fp") == 0) { > + return offsetof(struct pt_regs, ARM_fp); > + } else if (strcmp(reg_name, "ip") == 0) { > + return offsetof(struct pt_regs, ARM_ip); > + } else if (strcmp(reg_name, "sp") == 0) { > + return offsetof(struct pt_regs, ARM_sp); > + } else if (strcmp(reg_name, "lr") == 0) { > + return offsetof(struct pt_regs, ARM_lr); > + } else if (strcmp(reg_name, "pc") == 0) { > + return offsetof(struct pt_regs, ARM_pc); > + } > + pr_warn("usdt: unrecognized register '%s'\n", reg_name); > + return -ENOENT; > +} > + let's use a more tabular approach, just like, say, riscv does? > +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) > +{ > + char reg_name[16]; > + int arg_sz, len, reg_off; > + long off; > + > + if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], #%ld ] %n", &arg_sz, reg_name, > + &off, &len) == 3) { if long function call is wrapped, argument on new line should be aligned with the first argument on previous line. I'd suggest wrapping right after format string, and start with &arg_sz aligned with arg_str > + /* Memory dereference case, e.g., -4@[fp, #96] */ > + arg->arg_type = USDT_ARG_REG_DEREF; > + arg->val_off = off; > + reg_off = calc_pt_regs_off(reg_name); > + if (reg_off < 0) > + return reg_off; > + arg->reg_off = reg_off; > + } else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) { > + /* Memory dereference case, e.g., -4@[sp] */ > + arg->arg_type = USDT_ARG_REG_DEREF; > + arg->val_off = 0; > + reg_off = calc_pt_regs_off(reg_name); > + if (reg_off < 0) > + return reg_off; > + arg->reg_off = reg_off; > + } else if (sscanf(arg_str, " %d @ #%ld %n", &arg_sz, &off, &len) == 2) { is the '#<num>' value always in decimal or it could be hex sometimes? > + /* Constant value case, e.g., 4@#5 */ > + arg->arg_type = USDT_ARG_CONST; > + arg->val_off = off; > + arg->reg_off = 0; > + } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) { > + /* Register read case, e.g., -8@r4 */ > + arg->arg_type = USDT_ARG_REG; > + arg->val_off = 0; > + reg_off = calc_pt_regs_off(reg_name); > + if (reg_off < 0) > + return reg_off; > + arg->reg_off = reg_off; > + } else { > + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); > + return -EINVAL; > + } > + > + arg->arg_signed = arg_sz < 0; > + if (arg_sz < 0) > + arg_sz = -arg_sz; > + > + switch (arg_sz) { > + case 1: case 2: case 4: case 8: > + arg->arg_bitshift = 64 - arg_sz * 8; > + break; > + default: > + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", > + arg_num, arg_str, arg_sz); > + return -EINVAL; > + } This part is repeated verbatim for each architecture, perhaps it's better to do this post-processing and checking in parse_usdt_spec(). Would you mind adding another patch to your series that refactors parse_usdt_arg() implementation to fill out struct usdt_arg_spec and return arg_sz as out parameter. And then parse_usdt_spec() will check arg_sz, set arg_signed and arg_bitshift parts? > + > + return len; > +} > + > #else > > static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) > -- > 2.39.1 >
