| Message ID | 1649458366-25288-3-git-send-email-alan.maguire@oracle.com (mailing list archive) |
|---|---|
| State | Changes Requested |
| Delegated to: | BPF |
| Headers | show |
| Series | libbpf: usdt aarch64 support | expand |
On Fri, Apr 8, 2022 at 3:53 PM Alan Maguire <alan.maguire@oracle.com> wrote: > > Parsing of USDT arguments is architecture-specific; on aarch64 it is > relatively easy since registers used are x[0-31], sp. Format is > slightly different compared to x86_64; forms are > > - "size @ [ reg[,offset] ]" for dereferences, for example > "-8 @ [ sp, 76 ]" ; " -4 @ [ sp ]" > - "size @ reg" for register values; for example > "-4@x0" > - "size @ value" for raw values; for example > "-8@1" > > Signed-off-by: Alan Maguire <alan.maguire@oracle.com> > --- > tools/lib/bpf/usdt.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- > 1 file changed, 49 insertions(+), 1 deletion(-) > > diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c > index 0677bbd..6165d40 100644 > --- a/tools/lib/bpf/usdt.c > +++ b/tools/lib/bpf/usdt.c > @@ -1170,7 +1170,7 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, > > /* Architecture-specific logic for parsing USDT argument location specs */ > > -#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) > +#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) || defined(__aarch64__) > > static int init_usdt_arg_spec(struct usdt_arg_spec *arg, enum usdt_arg_type arg_type, int arg_sz, > __u64 val_off, int reg_off) > @@ -1316,6 +1316,54 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec > return len; > } > > +#elif defined(__aarch64__) > + > +static int calc_pt_regs_off(const char *reg_name) > +{ > + int reg_num; > + > + if (sscanf(reg_name, "x%d", ®_num) == 1) { > + if (reg_num >= 0 && reg_num < 31) > + return offsetof(struct user_pt_regs, regs[reg_num]); > + } else if (strcmp(reg_name, "sp") == 0) { > + return offsetof(struct user_pt_regs, sp); > + } > + pr_warn("usdt: unrecognized register '%s'\n", reg_name); > + return -ENOENT; > +} > + > +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) > +{ > + char *reg_name = NULL; > + int arg_sz, len, ret; > + long off = 0; > + > + if (sscanf(arg_str, " %d @ \[ %m[^,], %ld ] %n", &arg_sz, ®_name, &off, &len) == 3 || > + sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, ®_name, &len) == 2) { I'm not sure about the behavior here w.r.t. reg_name and memory allocation. What if first sscanf() matches reg_name but fails at %ld, will reg_name be allocated and then second sscanf() will reallocate (and thus we'll have a memory leak). We might have similar problems in other implementations, actually... Either way, came here to ask to split two sscanfs into two separate branches, so that we have a clear linear pattern. One sscanf, handle it if successful, otherwise move on to next case. Also a question about [a-z0-9] for register in one case and [^,] in another. Should the first one be [a-z0-9] as well? > + /* Memory dereference case, e.g., -4@[sp, 96], -4@[sp] */ > + ret = init_usdt_arg_spec(arg, USDT_ARG_REG_DEREF, arg_sz, off, > + calc_pt_regs_off(reg_name)); > + free(reg_name); > + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { > + /* Constant value case, e.g., 4@5 */ > + ret = init_usdt_arg_spec(arg, USDT_ARG_CONST, arg_sz, off, 0); > + } else if (sscanf(arg_str, " %d @ %ms %n", &arg_sz, ®_name, &len) == 2) { > + /* Register read case, e.g., -8@x4 */ > + ret = init_usdt_arg_spec(arg, USDT_ARG_REG, arg_sz, 0, calc_pt_regs_off(reg_name)); > + free(reg_name); > + } else { > + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); > + return -EINVAL; > + } > + > + if (ret < 0) { > + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", > + arg_num, arg_str, arg_sz); > + return ret; > + } > + return len; > +} > + > #else > > static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) > -- > 1.8.3.1 >
On Mon, 11 Apr 2022, Andrii Nakryiko wrote: > On Fri, Apr 8, 2022 at 3:53 PM Alan Maguire <alan.maguire@oracle.com> wrote: > > > > Parsing of USDT arguments is architecture-specific; on aarch64 it is > > relatively easy since registers used are x[0-31], sp. Format is > > slightly different compared to x86_64; forms are > > > > - "size @ [ reg[,offset] ]" for dereferences, for example > > "-8 @ [ sp, 76 ]" ; " -4 @ [ sp ]" > > - "size @ reg" for register values; for example > > "-4@x0" > > - "size @ value" for raw values; for example > > "-8@1" > > > > Signed-off-by: Alan Maguire <alan.maguire@oracle.com> > > --- > > tools/lib/bpf/usdt.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- > > 1 file changed, 49 insertions(+), 1 deletion(-) > > > > diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c > > index 0677bbd..6165d40 100644 > > --- a/tools/lib/bpf/usdt.c > > +++ b/tools/lib/bpf/usdt.c > > @@ -1170,7 +1170,7 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, > > > > /* Architecture-specific logic for parsing USDT argument location specs */ > > > > -#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) > > +#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) || defined(__aarch64__) > > > > static int init_usdt_arg_spec(struct usdt_arg_spec *arg, enum usdt_arg_type arg_type, int arg_sz, > > __u64 val_off, int reg_off) > > @@ -1316,6 +1316,54 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec > > return len; > > } > > > > +#elif defined(__aarch64__) > > + > > +static int calc_pt_regs_off(const char *reg_name) > > +{ > > + int reg_num; > > + > > + if (sscanf(reg_name, "x%d", ®_num) == 1) { > > + if (reg_num >= 0 && reg_num < 31) > > + return offsetof(struct user_pt_regs, regs[reg_num]); > > + } else if (strcmp(reg_name, "sp") == 0) { > > + return offsetof(struct user_pt_regs, sp); > > + } > > + pr_warn("usdt: unrecognized register '%s'\n", reg_name); > > + return -ENOENT; > > +} > > + > > +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) > > +{ > > + char *reg_name = NULL; > > + int arg_sz, len, ret; > > + long off = 0; > > + > > + if (sscanf(arg_str, " %d @ \[ %m[^,], %ld ] %n", &arg_sz, ®_name, &off, &len) == 3 || > > + sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, ®_name, &len) == 2) { > > I'm not sure about the behavior here w.r.t. reg_name and memory > allocation. What if first sscanf() matches reg_name but fails at %ld, > will reg_name be allocated and then second sscanf() will reallocate > (and thus we'll have a memory leak). > > We might have similar problems in other implementations, actually... > > Either way, came here to ask to split two sscanfs into two separate > branches, so that we have a clear linear pattern. One sscanf, handle > it if successful, otherwise move on to next case. > good point; I'll separate the sscanfs into branches for v2. > Also a question about [a-z0-9] for register in one case and [^,] in > another. Should the first one be [a-z0-9] as well? > probably no harm, yep. I'll drop the refactoring patch too; I was a bit worried I'd break Ilya's s390 code anyhow. Thanks! Alan
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 0677bbd..6165d40 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -1170,7 +1170,7 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, /* Architecture-specific logic for parsing USDT argument location specs */ -#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) +#if defined(__x86_64__) || defined(__i386__) || defined(__s390x__) || defined(__aarch64__) static int init_usdt_arg_spec(struct usdt_arg_spec *arg, enum usdt_arg_type arg_type, int arg_sz, __u64 val_off, int reg_off) @@ -1316,6 +1316,54 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return len; } +#elif defined(__aarch64__) + +static int calc_pt_regs_off(const char *reg_name) +{ + int reg_num; + + if (sscanf(reg_name, "x%d", ®_num) == 1) { + if (reg_num >= 0 && reg_num < 31) + return offsetof(struct user_pt_regs, regs[reg_num]); + } else if (strcmp(reg_name, "sp") == 0) { + return offsetof(struct user_pt_regs, sp); + } + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, ret; + long off = 0; + + if (sscanf(arg_str, " %d @ \[ %m[^,], %ld ] %n", &arg_sz, ®_name, &off, &len) == 3 || + sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, ®_name, &len) == 2) { + /* Memory dereference case, e.g., -4@[sp, 96], -4@[sp] */ + ret = init_usdt_arg_spec(arg, USDT_ARG_REG_DEREF, arg_sz, off, + calc_pt_regs_off(reg_name)); + free(reg_name); + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@5 */ + ret = init_usdt_arg_spec(arg, USDT_ARG_CONST, arg_sz, off, 0); + } else if (sscanf(arg_str, " %d @ %ms %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -8@x4 */ + ret = init_usdt_arg_spec(arg, USDT_ARG_REG, arg_sz, 0, calc_pt_regs_off(reg_name)); + free(reg_name); + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + if (ret < 0) { + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return ret; + } + return len; +} + #else static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
Parsing of USDT arguments is architecture-specific; on aarch64 it is relatively easy since registers used are x[0-31], sp. Format is slightly different compared to x86_64; forms are - "size @ [ reg[,offset] ]" for dereferences, for example "-8 @ [ sp, 76 ]" ; " -4 @ [ sp ]" - "size @ reg" for register values; for example "-4@x0" - "size @ value" for raw values; for example "-8@1" Signed-off-by: Alan Maguire <alan.maguire@oracle.com> --- tools/lib/bpf/usdt.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-)