diff mbox series

[2/3] libbpf: Remove powerpc prefix from syscall function names

Message ID 20241104050007.13812-3-skb99@linux.ibm.com
State New
Headers show
Series Fix test_bpf_syscall_macro selftest on powerpc | expand

Commit Message

Saket Kumar Bhaskar Nov. 4, 2024, 5 a.m. UTC
Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
syscall entry points") drops _powerpc prefix to syscall entry points,
even though powerpc now supports syscall wrapper, so /proc/kallsyms
have symbols for syscall entry without powerpc prefix(sys_*).

For this reason, arch specific prefix for syscall functions in powerpc
is dropped.

Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
---
 tools/lib/bpf/libbpf.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

Comments

Andrii Nakryiko Nov. 8, 2024, 6:43 p.m. UTC | #1
On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
>
> Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> syscall entry points") drops _powerpc prefix to syscall entry points,
> even though powerpc now supports syscall wrapper, so /proc/kallsyms
> have symbols for syscall entry without powerpc prefix(sys_*).
>
> For this reason, arch specific prefix for syscall functions in powerpc
> is dropped.
>
> Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> ---
>  tools/lib/bpf/libbpf.c | 12 +++++++++---
>  1 file changed, 9 insertions(+), 3 deletions(-)
>
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 219facd0e66e..3a370fa37d8a 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
>  #elif defined(__riscv)
>         return "riscv";
>  #elif defined(__powerpc__)
> -       return "powerpc";
> -#elif defined(__powerpc64__)
> -       return "powerpc64";
> +       return "";
>  #else
>         return NULL;
>  #endif
> @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
>         if (!ksys_pfx)
>                 return 0;
>
> +#if defined(__powerpc__)
> +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> +#else
>         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> +#endif

The problem is that on older versions of kernel it will have this
prefix, while on newer ones it won't. So to not break anything on old
kernels, we'd need to do feature detection and pick whether to use
prefix or not, right?

So it seems like this change needs a bit more work.

pw-bot: cr

>
>         if (determine_kprobe_perf_type() >= 0) {
>                 int pfd;
> @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
>                  * compiler does not know that we have an explicit conditional
>                  * as well.
>                  */
> +#if defined(__powerpc__)
> +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> +#else
>                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
>                          arch_specific_syscall_pfx() ? : "", syscall_name);
> +#endif
>         } else {
>                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
>         }
> --
> 2.43.5
>
Saket Kumar Bhaskar Nov. 20, 2024, 2:52 p.m. UTC | #2
On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> >
> > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > syscall entry points") drops _powerpc prefix to syscall entry points,
> > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > have symbols for syscall entry without powerpc prefix(sys_*).
> >
> > For this reason, arch specific prefix for syscall functions in powerpc
> > is dropped.
> >
> > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > ---
> >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> >  1 file changed, 9 insertions(+), 3 deletions(-)
> >
> > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > index 219facd0e66e..3a370fa37d8a 100644
> > --- a/tools/lib/bpf/libbpf.c
> > +++ b/tools/lib/bpf/libbpf.c
> > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> >  #elif defined(__riscv)
> >         return "riscv";
> >  #elif defined(__powerpc__)
> > -       return "powerpc";
> > -#elif defined(__powerpc64__)
> > -       return "powerpc64";
> > +       return "";
> >  #else
> >         return NULL;
> >  #endif
> > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> >         if (!ksys_pfx)
> >                 return 0;
> >
> > +#if defined(__powerpc__)
> > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > +#else
> >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > +#endif
> 
> The problem is that on older versions of kernel it will have this
> prefix, while on newer ones it won't. So to not break anything on old
> kernels, we'd need to do feature detection and pick whether to use
> prefix or not, right?
> 
> So it seems like this change needs a bit more work.
> 
> pw-bot: cr
> 
Hi Andrii,

IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper) 
and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points) 
went into the same kernel version v6.1-rc1, there won't me much kernel
versions that has only one of these patches.

Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
and it the test passed in this case too.

Thanks,
Saket
> >
> >         if (determine_kprobe_perf_type() >= 0) {
> >                 int pfd;
> > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> >                  * compiler does not know that we have an explicit conditional
> >                  * as well.
> >                  */
> > +#if defined(__powerpc__)
> > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > +#else
> >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > +#endif
> >         } else {
> >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> >         }
> > --
> > 2.43.5
> >
Andrii Nakryiko Nov. 22, 2024, midnight UTC | #3
On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
>
> On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > >
> > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > have symbols for syscall entry without powerpc prefix(sys_*).
> > >
> > > For this reason, arch specific prefix for syscall functions in powerpc
> > > is dropped.
> > >
> > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > ---
> > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > >
> > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > index 219facd0e66e..3a370fa37d8a 100644
> > > --- a/tools/lib/bpf/libbpf.c
> > > +++ b/tools/lib/bpf/libbpf.c
> > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > >  #elif defined(__riscv)
> > >         return "riscv";
> > >  #elif defined(__powerpc__)
> > > -       return "powerpc";
> > > -#elif defined(__powerpc64__)
> > > -       return "powerpc64";
> > > +       return "";
> > >  #else
> > >         return NULL;
> > >  #endif
> > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > >         if (!ksys_pfx)
> > >                 return 0;
> > >
> > > +#if defined(__powerpc__)
> > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > +#else
> > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > +#endif
> >
> > The problem is that on older versions of kernel it will have this
> > prefix, while on newer ones it won't. So to not break anything on old
> > kernels, we'd need to do feature detection and pick whether to use
> > prefix or not, right?
> >
> > So it seems like this change needs a bit more work.
> >
> > pw-bot: cr
> >
> Hi Andrii,
>
> IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> went into the same kernel version v6.1-rc1, there won't me much kernel
> versions that has only one of these patches.
>
> Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> and it the test passed in this case too.
>

Keep in mind that libbpf is supposed to work across many kernel
versions. So as long as there are powerpc (old) kernels that do use
arch-specific prefix, we need to detect them and supply prefix when
attaching ksyscall programs.

> Thanks,
> Saket
> > >
> > >         if (determine_kprobe_perf_type() >= 0) {
> > >                 int pfd;
> > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > >                  * compiler does not know that we have an explicit conditional
> > >                  * as well.
> > >                  */
> > > +#if defined(__powerpc__)
> > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > +#else
> > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > +#endif
> > >         } else {
> > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > >         }
> > > --
> > > 2.43.5
> > >
Saket Kumar Bhaskar Jan. 10, 2025, 10:49 a.m. UTC | #4
On Thu, Nov 21, 2024 at 04:00:13PM -0800, Andrii Nakryiko wrote:
> On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> >
> > On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > >
> > > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > > have symbols for syscall entry without powerpc prefix(sys_*).
> > > >
> > > > For this reason, arch specific prefix for syscall functions in powerpc
> > > > is dropped.
> > > >
> > > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > > ---
> > > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > > >
> > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > index 219facd0e66e..3a370fa37d8a 100644
> > > > --- a/tools/lib/bpf/libbpf.c
> > > > +++ b/tools/lib/bpf/libbpf.c
> > > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > > >  #elif defined(__riscv)
> > > >         return "riscv";
> > > >  #elif defined(__powerpc__)
> > > > -       return "powerpc";
> > > > -#elif defined(__powerpc64__)
> > > > -       return "powerpc64";
> > > > +       return "";
> > > >  #else
> > > >         return NULL;
> > > >  #endif
> > > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > >         if (!ksys_pfx)
> > > >                 return 0;
> > > >
> > > > +#if defined(__powerpc__)
> > > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > > +#else
> > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > +#endif
> > >
> > > The problem is that on older versions of kernel it will have this
> > > prefix, while on newer ones it won't. So to not break anything on old
> > > kernels, we'd need to do feature detection and pick whether to use
> > > prefix or not, right?
> > >
> > > So it seems like this change needs a bit more work.
> > >
> > > pw-bot: cr
> > >
> > Hi Andrii,
> >
> > IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> > and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> > went into the same kernel version v6.1-rc1, there won't me much kernel
> > versions that has only one of these patches.
> >
> > Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> > and it the test passed in this case too.
> >
> 
> Keep in mind that libbpf is supposed to work across many kernel
> versions. So as long as there are powerpc (old) kernels that do use
> arch-specific prefix, we need to detect them and supply prefix when
> attaching ksyscall programs.
> 
Hi Andrii,

Sorry about the delayed response, I have started looking at this after
a vacation.

There are unlikely to be any old kernels that use arch-specific prefix
as syscall wrapper support was added to powerpc in v6.1 and 
commit 94746890202cf that dropped the prefix also went into the same 
kernel release (v6.1-rc1). So, is it worth it support both sys_bpf and
__powerpc_sys_bpf cases?

But yes, there can be a kernel without syscall wrapper but having the 
sys_bpf symbol. So, how about identifying syscall wrapper enablement
with __se_sys_bpf instead:


diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 66173ddb5a2d..ff69a30cfe9b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11163,11 +11163,15 @@ int probe_kern_syscall_wrapper(int token_fd)
 	char syscall_name[64];
 	const char *ksys_pfx;
 
+#if defined(__powerpc__)
+	snprintf(syscall_name, sizeof(syscall_name), "__se_sys_bpf", ksys_pfx);
+#else
 	ksys_pfx = arch_specific_syscall_pfx();
 	if (!ksys_pfx)
 		return 0;
 
 	snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
+#endif
 
 	if (determine_kprobe_perf_type() >= 0) {
 		int pfd;
@@ -11176,16 +11180,28 @@ int probe_kern_syscall_wrapper(int token_fd)
 		if (pfd >= 0)
 			close(pfd);
 
+#if defined(__powerpc__)
 		return pfd >= 0 ? 1 : 0;
+#else
+		return pfd >= 0 ? 1 : 0;
+#endif
 	} else { /* legacy mode */
 		char probe_name[128];
 
 		gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0);
 		if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0)
+#if defined(__powerpc__)
+			return 1;
+#else
 			return 0;
+#endif
 
 		(void)remove_kprobe_event_legacy(probe_name, false);
+#if defined(__powerpc__)
+		return 0;
+#else
 		return 1;
+#endif
 	}
 }

Actually, all architectures could use this '__se_' prefix instead of
arch specific prefix  to identify if syscall wrapper is enabled.
Separate way to handle powerpc case may not be needed. Will
wait for your inputs to send v2.

Thanks,
Saket
> > Thanks,
> > Saket
> > > >
> > > >         if (determine_kprobe_perf_type() >= 0) {
> > > >                 int pfd;
> > > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > > >                  * compiler does not know that we have an explicit conditional
> > > >                  * as well.
> > > >                  */
> > > > +#if defined(__powerpc__)
> > > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > > +#else
> > > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > > +#endif
> > > >         } else {
> > > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > > >         }
> > > > --
> > > > 2.43.5
> > > >
Andrii Nakryiko Jan. 10, 2025, 10:29 p.m. UTC | #5
On Fri, Jan 10, 2025 at 2:49 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
>
> On Thu, Nov 21, 2024 at 04:00:13PM -0800, Andrii Nakryiko wrote:
> > On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > >
> > > On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > > > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > >
> > > > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > > > have symbols for syscall entry without powerpc prefix(sys_*).
> > > > >
> > > > > For this reason, arch specific prefix for syscall functions in powerpc
> > > > > is dropped.
> > > > >
> > > > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > > > ---
> > > > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > > > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > > > >
> > > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > > index 219facd0e66e..3a370fa37d8a 100644
> > > > > --- a/tools/lib/bpf/libbpf.c
> > > > > +++ b/tools/lib/bpf/libbpf.c
> > > > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > > > >  #elif defined(__riscv)
> > > > >         return "riscv";
> > > > >  #elif defined(__powerpc__)
> > > > > -       return "powerpc";
> > > > > -#elif defined(__powerpc64__)
> > > > > -       return "powerpc64";
> > > > > +       return "";
> > > > >  #else
> > > > >         return NULL;
> > > > >  #endif
> > > > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > >         if (!ksys_pfx)
> > > > >                 return 0;
> > > > >
> > > > > +#if defined(__powerpc__)
> > > > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > > > +#else
> > > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > > +#endif
> > > >
> > > > The problem is that on older versions of kernel it will have this
> > > > prefix, while on newer ones it won't. So to not break anything on old
> > > > kernels, we'd need to do feature detection and pick whether to use
> > > > prefix or not, right?
> > > >
> > > > So it seems like this change needs a bit more work.
> > > >
> > > > pw-bot: cr
> > > >
> > > Hi Andrii,
> > >
> > > IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> > > and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> > > went into the same kernel version v6.1-rc1, there won't me much kernel
> > > versions that has only one of these patches.
> > >
> > > Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> > > and it the test passed in this case too.
> > >
> >
> > Keep in mind that libbpf is supposed to work across many kernel
> > versions. So as long as there are powerpc (old) kernels that do use
> > arch-specific prefix, we need to detect them and supply prefix when
> > attaching ksyscall programs.
> >
> Hi Andrii,
>
> Sorry about the delayed response, I have started looking at this after
> a vacation.
>
> There are unlikely to be any old kernels that use arch-specific prefix
> as syscall wrapper support was added to powerpc in v6.1 and
> commit 94746890202cf that dropped the prefix also went into the same
> kernel release (v6.1-rc1). So, is it worth it support both sys_bpf and
> __powerpc_sys_bpf cases?
>
> But yes, there can be a kernel without syscall wrapper but having the
> sys_bpf symbol. So, how about identifying syscall wrapper enablement
> with __se_sys_bpf instead:
>
>
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 66173ddb5a2d..ff69a30cfe9b 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -11163,11 +11163,15 @@ int probe_kern_syscall_wrapper(int token_fd)
>         char syscall_name[64];
>         const char *ksys_pfx;
>
> +#if defined(__powerpc__)
> +       snprintf(syscall_name, sizeof(syscall_name), "__se_sys_bpf", ksys_pfx);
> +#else
>         ksys_pfx = arch_specific_syscall_pfx();
>         if (!ksys_pfx)
>                 return 0;
>
>         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> +#endif
>
>         if (determine_kprobe_perf_type() >= 0) {
>                 int pfd;
> @@ -11176,16 +11180,28 @@ int probe_kern_syscall_wrapper(int token_fd)
>                 if (pfd >= 0)
>                         close(pfd);
>
> +#if defined(__powerpc__)
>                 return pfd >= 0 ? 1 : 0;
> +#else
> +               return pfd >= 0 ? 1 : 0;
> +#endif
>         } else { /* legacy mode */
>                 char probe_name[128];
>
>                 gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0);
>                 if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0)
> +#if defined(__powerpc__)
> +                       return 1;
> +#else
>                         return 0;
> +#endif
>
>                 (void)remove_kprobe_event_legacy(probe_name, false);
> +#if defined(__powerpc__)
> +               return 0;
> +#else
>                 return 1;
> +#endif
>         }
>  }
>
> Actually, all architectures could use this '__se_' prefix instead of
> arch specific prefix  to identify if syscall wrapper is enabled.
> Separate way to handle powerpc case may not be needed. Will
> wait for your inputs to send v2.

the problem is that __se_sys_bpf is not traceable (it's a static
function), so it seems like this won't work


it's been a while, let me try to clarify my understanding of the
issue. The problem is that powerpc is special in that when syscall
wrapper is used, then, unlike all other architectures, they opted to
not have arch-specific prefix for syscall wrappers, is that right? and
that's why all the dancing you are trying to add. Am I right?

>
> Thanks,
> Saket
> > > Thanks,
> > > Saket
> > > > >
> > > > >         if (determine_kprobe_perf_type() >= 0) {
> > > > >                 int pfd;
> > > > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > > > >                  * compiler does not know that we have an explicit conditional
> > > > >                  * as well.
> > > > >                  */
> > > > > +#if defined(__powerpc__)
> > > > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > > > +#else
> > > > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > > > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > > > +#endif
> > > > >         } else {
> > > > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > > > >         }
> > > > > --
> > > > > 2.43.5
> > > > >
Saket Kumar Bhaskar Jan. 11, 2025, 7:53 p.m. UTC | #6
CCing Maddy and MPE
On Fri, Jan 10, 2025 at 02:29:42PM -0800, Andrii Nakryiko wrote:
> On Fri, Jan 10, 2025 at 2:49 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> >
> > On Thu, Nov 21, 2024 at 04:00:13PM -0800, Andrii Nakryiko wrote:
> > > On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > >
> > > > On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > > > > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > > >
> > > > > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > > > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > > > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > > > > have symbols for syscall entry without powerpc prefix(sys_*).
> > > > > >
> > > > > > For this reason, arch specific prefix for syscall functions in powerpc
> > > > > > is dropped.
> > > > > >
> > > > > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > > > > ---
> > > > > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > > > > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > > > > >
> > > > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > > > index 219facd0e66e..3a370fa37d8a 100644
> > > > > > --- a/tools/lib/bpf/libbpf.c
> > > > > > +++ b/tools/lib/bpf/libbpf.c
> > > > > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > > > > >  #elif defined(__riscv)
> > > > > >         return "riscv";
> > > > > >  #elif defined(__powerpc__)
> > > > > > -       return "powerpc";
> > > > > > -#elif defined(__powerpc64__)
> > > > > > -       return "powerpc64";
> > > > > > +       return "";
> > > > > >  #else
> > > > > >         return NULL;
> > > > > >  #endif
> > > > > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > > >         if (!ksys_pfx)
> > > > > >                 return 0;
> > > > > >
> > > > > > +#if defined(__powerpc__)
> > > > > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > > > > +#else
> > > > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > > > +#endif
> > > > >
> > > > > The problem is that on older versions of kernel it will have this
> > > > > prefix, while on newer ones it won't. So to not break anything on old
> > > > > kernels, we'd need to do feature detection and pick whether to use
> > > > > prefix or not, right?
> > > > >
> > > > > So it seems like this change needs a bit more work.
> > > > >
> > > > > pw-bot: cr
> > > > >
> > > > Hi Andrii,
> > > >
> > > > IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> > > > and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> > > > went into the same kernel version v6.1-rc1, there won't me much kernel
> > > > versions that has only one of these patches.
> > > >
> > > > Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> > > > and it the test passed in this case too.
> > > >
> > >
> > > Keep in mind that libbpf is supposed to work across many kernel
> > > versions. So as long as there are powerpc (old) kernels that do use
> > > arch-specific prefix, we need to detect them and supply prefix when
> > > attaching ksyscall programs.
> > >
> > Hi Andrii,
> >
> > Sorry about the delayed response, I have started looking at this after
> > a vacation.
> >
> > There are unlikely to be any old kernels that use arch-specific prefix
> > as syscall wrapper support was added to powerpc in v6.1 and
> > commit 94746890202cf that dropped the prefix also went into the same
> > kernel release (v6.1-rc1). So, is it worth it support both sys_bpf and
> > __powerpc_sys_bpf cases?
> >
> > But yes, there can be a kernel without syscall wrapper but having the
> > sys_bpf symbol. So, how about identifying syscall wrapper enablement
> > with __se_sys_bpf instead:
> >
> >
> > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > index 66173ddb5a2d..ff69a30cfe9b 100644
> > --- a/tools/lib/bpf/libbpf.c
> > +++ b/tools/lib/bpf/libbpf.c
> > @@ -11163,11 +11163,15 @@ int probe_kern_syscall_wrapper(int token_fd)
> >         char syscall_name[64];
> >         const char *ksys_pfx;
> >
> > +#if defined(__powerpc__)
> > +       snprintf(syscall_name, sizeof(syscall_name), "__se_sys_bpf", ksys_pfx);
> > +#else
> >         ksys_pfx = arch_specific_syscall_pfx();
> >         if (!ksys_pfx)
> >                 return 0;
> >
> >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > +#endif
> >
> >         if (determine_kprobe_perf_type() >= 0) {
> >                 int pfd;
> > @@ -11176,16 +11180,28 @@ int probe_kern_syscall_wrapper(int token_fd)
> >                 if (pfd >= 0)
> >                         close(pfd);
> >
> > +#if defined(__powerpc__)
> >                 return pfd >= 0 ? 1 : 0;
> > +#else
> > +               return pfd >= 0 ? 1 : 0;
> > +#endif
> >         } else { /* legacy mode */
> >                 char probe_name[128];
> >
> >                 gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0);
> >                 if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0)
> > +#if defined(__powerpc__)
> > +                       return 1;
> > +#else
> >                         return 0;
> > +#endif
> >
> >                 (void)remove_kprobe_event_legacy(probe_name, false);
> > +#if defined(__powerpc__)
> > +               return 0;
> > +#else
> >                 return 1;
> > +#endif
> >         }
> >  }
> >
> > Actually, all architectures could use this '__se_' prefix instead of
> > arch specific prefix  to identify if syscall wrapper is enabled.
> > Separate way to handle powerpc case may not be needed. Will
> > wait for your inputs to send v2.
> 
> the problem is that __se_sys_bpf is not traceable (it's a static
> function), so it seems like this won't work
> 
> 
> it's been a while, let me try to clarify my understanding of the
> issue. The problem is that powerpc is special in that when syscall
> wrapper is used, then, unlike all other architectures, they opted to
> not have arch-specific prefix for syscall wrappers, is that right? and
> that's why all the dancing you are trying to add. Am I right?
> 
Yes, you got it right. For more details, you can refer to the 
reasoning behind the change here:
https://github.com/torvalds/linux/commit/94746890202cf

Thanks,
Saket
> >
> > Thanks,
> > Saket
> > > > Thanks,
> > > > Saket
> > > > > >
> > > > > >         if (determine_kprobe_perf_type() >= 0) {
> > > > > >                 int pfd;
> > > > > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > > > > >                  * compiler does not know that we have an explicit conditional
> > > > > >                  * as well.
> > > > > >                  */
> > > > > > +#if defined(__powerpc__)
> > > > > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > > > > +#else
> > > > > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > > > > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > > > > +#endif
> > > > > >         } else {
> > > > > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > > > > >         }
> > > > > > --
> > > > > > 2.43.5
> > > > > >
Andrii Nakryiko Jan. 14, 2025, 10:40 p.m. UTC | #7
On Sat, Jan 11, 2025 at 11:53 AM Saket Kumar Bhaskar
<skb99@linux.ibm.com> wrote:
>
> CCing Maddy and MPE
> On Fri, Jan 10, 2025 at 02:29:42PM -0800, Andrii Nakryiko wrote:
> > On Fri, Jan 10, 2025 at 2:49 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > >
> > > On Thu, Nov 21, 2024 at 04:00:13PM -0800, Andrii Nakryiko wrote:
> > > > On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > >
> > > > > On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > > > > > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > > > >
> > > > > > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > > > > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > > > > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > > > > > have symbols for syscall entry without powerpc prefix(sys_*).
> > > > > > >
> > > > > > > For this reason, arch specific prefix for syscall functions in powerpc
> > > > > > > is dropped.
> > > > > > >
> > > > > > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > > > > > ---
> > > > > > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > > > > > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > > > > > >
> > > > > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > > > > index 219facd0e66e..3a370fa37d8a 100644
> > > > > > > --- a/tools/lib/bpf/libbpf.c
> > > > > > > +++ b/tools/lib/bpf/libbpf.c
> > > > > > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > > > > > >  #elif defined(__riscv)
> > > > > > >         return "riscv";
> > > > > > >  #elif defined(__powerpc__)
> > > > > > > -       return "powerpc";
> > > > > > > -#elif defined(__powerpc64__)
> > > > > > > -       return "powerpc64";
> > > > > > > +       return "";
> > > > > > >  #else
> > > > > > >         return NULL;
> > > > > > >  #endif
> > > > > > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > > > >         if (!ksys_pfx)
> > > > > > >                 return 0;
> > > > > > >
> > > > > > > +#if defined(__powerpc__)
> > > > > > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > > > > > +#else
> > > > > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > > > > +#endif
> > > > > >
> > > > > > The problem is that on older versions of kernel it will have this
> > > > > > prefix, while on newer ones it won't. So to not break anything on old
> > > > > > kernels, we'd need to do feature detection and pick whether to use
> > > > > > prefix or not, right?
> > > > > >
> > > > > > So it seems like this change needs a bit more work.
> > > > > >
> > > > > > pw-bot: cr
> > > > > >
> > > > > Hi Andrii,
> > > > >
> > > > > IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> > > > > and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> > > > > went into the same kernel version v6.1-rc1, there won't me much kernel
> > > > > versions that has only one of these patches.
> > > > >
> > > > > Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> > > > > and it the test passed in this case too.
> > > > >
> > > >
> > > > Keep in mind that libbpf is supposed to work across many kernel
> > > > versions. So as long as there are powerpc (old) kernels that do use
> > > > arch-specific prefix, we need to detect them and supply prefix when
> > > > attaching ksyscall programs.
> > > >
> > > Hi Andrii,
> > >
> > > Sorry about the delayed response, I have started looking at this after
> > > a vacation.
> > >
> > > There are unlikely to be any old kernels that use arch-specific prefix
> > > as syscall wrapper support was added to powerpc in v6.1 and
> > > commit 94746890202cf that dropped the prefix also went into the same
> > > kernel release (v6.1-rc1). So, is it worth it support both sys_bpf and
> > > __powerpc_sys_bpf cases?
> > >
> > > But yes, there can be a kernel without syscall wrapper but having the
> > > sys_bpf symbol. So, how about identifying syscall wrapper enablement
> > > with __se_sys_bpf instead:
> > >
> > >
> > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > index 66173ddb5a2d..ff69a30cfe9b 100644
> > > --- a/tools/lib/bpf/libbpf.c
> > > +++ b/tools/lib/bpf/libbpf.c
> > > @@ -11163,11 +11163,15 @@ int probe_kern_syscall_wrapper(int token_fd)
> > >         char syscall_name[64];
> > >         const char *ksys_pfx;
> > >
> > > +#if defined(__powerpc__)
> > > +       snprintf(syscall_name, sizeof(syscall_name), "__se_sys_bpf", ksys_pfx);
> > > +#else
> > >         ksys_pfx = arch_specific_syscall_pfx();
> > >         if (!ksys_pfx)
> > >                 return 0;
> > >
> > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > +#endif
> > >
> > >         if (determine_kprobe_perf_type() >= 0) {
> > >                 int pfd;
> > > @@ -11176,16 +11180,28 @@ int probe_kern_syscall_wrapper(int token_fd)
> > >                 if (pfd >= 0)
> > >                         close(pfd);
> > >
> > > +#if defined(__powerpc__)
> > >                 return pfd >= 0 ? 1 : 0;
> > > +#else
> > > +               return pfd >= 0 ? 1 : 0;
> > > +#endif
> > >         } else { /* legacy mode */
> > >                 char probe_name[128];
> > >
> > >                 gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0);
> > >                 if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0)
> > > +#if defined(__powerpc__)
> > > +                       return 1;
> > > +#else
> > >                         return 0;
> > > +#endif
> > >
> > >                 (void)remove_kprobe_event_legacy(probe_name, false);
> > > +#if defined(__powerpc__)
> > > +               return 0;
> > > +#else
> > >                 return 1;
> > > +#endif
> > >         }
> > >  }
> > >
> > > Actually, all architectures could use this '__se_' prefix instead of
> > > arch specific prefix  to identify if syscall wrapper is enabled.
> > > Separate way to handle powerpc case may not be needed. Will
> > > wait for your inputs to send v2.
> >
> > the problem is that __se_sys_bpf is not traceable (it's a static
> > function), so it seems like this won't work
> >
> >
> > it's been a while, let me try to clarify my understanding of the
> > issue. The problem is that powerpc is special in that when syscall
> > wrapper is used, then, unlike all other architectures, they opted to
> > not have arch-specific prefix for syscall wrappers, is that right? and
> > that's why all the dancing you are trying to add. Am I right?
> >
> Yes, you got it right. For more details, you can refer to the
> reasoning behind the change here:
> https://github.com/torvalds/linux/commit/94746890202cf

That was an unfortunate decision to deviate :(

Alright, so where are we? We can't do __se_<syscall> approach, but we
need to have some reliable way to determine whether powerpc uses
syscall wrapper. Can you please summarize available options for
powerpc? Sorry, it's been a while, so we need to re-page in all the
context.

>
> Thanks,
> Saket
> > >
> > > Thanks,
> > > Saket
> > > > > Thanks,
> > > > > Saket
> > > > > > >
> > > > > > >         if (determine_kprobe_perf_type() >= 0) {
> > > > > > >                 int pfd;
> > > > > > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > > > > > >                  * compiler does not know that we have an explicit conditional
> > > > > > >                  * as well.
> > > > > > >                  */
> > > > > > > +#if defined(__powerpc__)
> > > > > > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > > > > > +#else
> > > > > > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > > > > > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > > > > > +#endif
> > > > > > >         } else {
> > > > > > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > > > > > >         }
> > > > > > > --
> > > > > > > 2.43.5
> > > > > > >
Andrii Nakryiko Jan. 16, 2025, 11:19 p.m. UTC | #8
On Wed, Jan 15, 2025 at 6:16 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
>
> On Tue, Jan 14, 2025 at 02:40:20PM -0800, Andrii Nakryiko wrote:
> > On Sat, Jan 11, 2025 at 11:53 AM Saket Kumar Bhaskar
> > <skb99@linux.ibm.com> wrote:
> > >
> > > CCing Maddy and MPE
> > > On Fri, Jan 10, 2025 at 02:29:42PM -0800, Andrii Nakryiko wrote:
> > > > On Fri, Jan 10, 2025 at 2:49 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > >
> > > > > On Thu, Nov 21, 2024 at 04:00:13PM -0800, Andrii Nakryiko wrote:
> > > > > > On Wed, Nov 20, 2024 at 6:52 AM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > > > >
> > > > > > > On Fri, Nov 08, 2024 at 10:43:54AM -0800, Andrii Nakryiko wrote:
> > > > > > > > On Sun, Nov 3, 2024 at 9:00 PM Saket Kumar Bhaskar <skb99@linux.ibm.com> wrote:
> > > > > > > > >
> > > > > > > > > Since commit 94746890202cf ("powerpc: Don't add __powerpc_ prefix to
> > > > > > > > > syscall entry points") drops _powerpc prefix to syscall entry points,
> > > > > > > > > even though powerpc now supports syscall wrapper, so /proc/kallsyms
> > > > > > > > > have symbols for syscall entry without powerpc prefix(sys_*).
> > > > > > > > >
> > > > > > > > > For this reason, arch specific prefix for syscall functions in powerpc
> > > > > > > > > is dropped.
> > > > > > > > >
> > > > > > > > > Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> > > > > > > > > ---
> > > > > > > > >  tools/lib/bpf/libbpf.c | 12 +++++++++---
> > > > > > > > >  1 file changed, 9 insertions(+), 3 deletions(-)
> > > > > > > > >
> > > > > > > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > > > > > > index 219facd0e66e..3a370fa37d8a 100644
> > > > > > > > > --- a/tools/lib/bpf/libbpf.c
> > > > > > > > > +++ b/tools/lib/bpf/libbpf.c
> > > > > > > > > @@ -11110,9 +11110,7 @@ static const char *arch_specific_syscall_pfx(void)
> > > > > > > > >  #elif defined(__riscv)
> > > > > > > > >         return "riscv";
> > > > > > > > >  #elif defined(__powerpc__)
> > > > > > > > > -       return "powerpc";
> > > > > > > > > -#elif defined(__powerpc64__)
> > > > > > > > > -       return "powerpc64";
> > > > > > > > > +       return "";
> > > > > > > > >  #else
> > > > > > > > >         return NULL;
> > > > > > > > >  #endif
> > > > > > > > > @@ -11127,7 +11125,11 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > > > > > >         if (!ksys_pfx)
> > > > > > > > >                 return 0;
> > > > > > > > >
> > > > > > > > > +#if defined(__powerpc__)
> > > > > > > > > +       snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
> > > > > > > > > +#else
> > > > > > > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > > > > > > +#endif
> > > > > > > >
> > > > > > > > The problem is that on older versions of kernel it will have this
> > > > > > > > prefix, while on newer ones it won't. So to not break anything on old
> > > > > > > > kernels, we'd need to do feature detection and pick whether to use
> > > > > > > > prefix or not, right?
> > > > > > > >
> > > > > > > > So it seems like this change needs a bit more work.
> > > > > > > >
> > > > > > > > pw-bot: cr
> > > > > > > >
> > > > > > > Hi Andrii,
> > > > > > >
> > > > > > > IMO since both the patches 7e92e01b7245(powerpc: Provide syscall wrapper)
> > > > > > > and 94746890202cf(powerpc: Don't add __powerpc_ prefix to syscall entry points)
> > > > > > > went into the same kernel version v6.1-rc1, there won't me much kernel
> > > > > > > versions that has only one of these patches.
> > > > > > >
> > > > > > > Also, to test more I tried this patch with ARCH_HAS_SYSCALL_WRAPPER disabled,
> > > > > > > and it the test passed in this case too.
> > > > > > >
> > > > > >
> > > > > > Keep in mind that libbpf is supposed to work across many kernel
> > > > > > versions. So as long as there are powerpc (old) kernels that do use
> > > > > > arch-specific prefix, we need to detect them and supply prefix when
> > > > > > attaching ksyscall programs.
> > > > > >
> > > > > Hi Andrii,
> > > > >
> > > > > Sorry about the delayed response, I have started looking at this after
> > > > > a vacation.
> > > > >
> > > > > There are unlikely to be any old kernels that use arch-specific prefix
> > > > > as syscall wrapper support was added to powerpc in v6.1 and
> > > > > commit 94746890202cf that dropped the prefix also went into the same
> > > > > kernel release (v6.1-rc1). So, is it worth it support both sys_bpf and
> > > > > __powerpc_sys_bpf cases?
> > > > >
> > > > > But yes, there can be a kernel without syscall wrapper but having the
> > > > > sys_bpf symbol. So, how about identifying syscall wrapper enablement
> > > > > with __se_sys_bpf instead:
> > > > >
> > > > >
> > > > > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > > > > index 66173ddb5a2d..ff69a30cfe9b 100644
> > > > > --- a/tools/lib/bpf/libbpf.c
> > > > > +++ b/tools/lib/bpf/libbpf.c
> > > > > @@ -11163,11 +11163,15 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > >         char syscall_name[64];
> > > > >         const char *ksys_pfx;
> > > > >
> > > > > +#if defined(__powerpc__)
> > > > > +       snprintf(syscall_name, sizeof(syscall_name), "__se_sys_bpf", ksys_pfx);
> > > > > +#else
> > > > >         ksys_pfx = arch_specific_syscall_pfx();
> > > > >         if (!ksys_pfx)
> > > > >                 return 0;
> > > > >
> > > > >         snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
> > > > > +#endif
> > > > >
> > > > >         if (determine_kprobe_perf_type() >= 0) {
> > > > >                 int pfd;
> > > > > @@ -11176,16 +11180,28 @@ int probe_kern_syscall_wrapper(int token_fd)
> > > > >                 if (pfd >= 0)
> > > > >                         close(pfd);
> > > > >
> > > > > +#if defined(__powerpc__)
> > > > >                 return pfd >= 0 ? 1 : 0;
> > > > > +#else
> > > > > +               return pfd >= 0 ? 1 : 0;
> > > > > +#endif
> > > > >         } else { /* legacy mode */
> > > > >                 char probe_name[128];
> > > > >
> > > > >                 gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0);
> > > > >                 if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0)
> > > > > +#if defined(__powerpc__)
> > > > > +                       return 1;
> > > > > +#else
> > > > >                         return 0;
> > > > > +#endif
> > > > >
> > > > >                 (void)remove_kprobe_event_legacy(probe_name, false);
> > > > > +#if defined(__powerpc__)
> > > > > +               return 0;
> > > > > +#else
> > > > >                 return 1;
> > > > > +#endif
> > > > >         }
> > > > >  }
> > > > >
> > > > > Actually, all architectures could use this '__se_' prefix instead of
> > > > > arch specific prefix  to identify if syscall wrapper is enabled.
> > > > > Separate way to handle powerpc case may not be needed. Will
> > > > > wait for your inputs to send v2.
> > > >
> > > > the problem is that __se_sys_bpf is not traceable (it's a static
> > > > function), so it seems like this won't work
> > > >
> > > >
> > > > it's been a while, let me try to clarify my understanding of the
> > > > issue. The problem is that powerpc is special in that when syscall
> > > > wrapper is used, then, unlike all other architectures, they opted to
> > > > not have arch-specific prefix for syscall wrappers, is that right? and
> > > > that's why all the dancing you are trying to add. Am I right?
> > > >
> > > Yes, you got it right. For more details, you can refer to the
> > > reasoning behind the change here:
> > > https://github.com/torvalds/linux/commit/94746890202cf
> >
> > That was an unfortunate decision to deviate :(
> >
> > Alright, so where are we? We can't do __se_<syscall> approach, but we
> > need to have some reliable way to determine whether powerpc uses
> > syscall wrapper. Can you please summarize available options for
> > powerpc? Sorry, it's been a while, so we need to re-page in all the
> > context.
> >
> Hi Andrii,
>
> 1. On powerpc we are able to set kprobe on __se_sys_bpf, we are thinking to
>    use this to check if syscall wrapper is enabled.

I'm not trying to be difficult, but what does guarantee that this is
always the case. I'm looking at this:

static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))

in arch/powerpc/include/asm/syscall_wrapper.h

It's static, so it's up to the compiler to decide whether to inline
this function or not. Once inlined, it's effectively not there.

>
> Snippet from kernel where syscall wrapper wasn't there for powerpc:
>
> # uname -r
> 6.0.0
>
> # cat kprobe_events
> p:kprobes/p_kprobe2_user_events_osquery netlink_ack
> r64:kprobes/r_kprobe_user_events_osquery audit_receive
> p:kprobes/p_kprobe_user_events_osquery audit_receive
> p:kprobes/my_probe __se_sys_bpf
>
> # cat trace
> # tracer: nop
> #
> # entries-in-buffer/entries-written: 20/20   #P:64
> #
> #                                _-----=> irqs-off/BH-disabled
> #                               / _----=> need-resched
> #                              | / _---=> hardirq/softirq
> #                              || / _--=> preempt-depth
> #                              ||| / _-=> migrate-disable
> #                              |||| /     delay
> #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
> #              | |         |   |||||     |         |
>       test_progs-1971    [034] .....   532.732614: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.732843: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733120: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733485: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733499: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733507: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733512: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733552: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733577: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733581: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733586: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733592: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733596: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733601: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733606: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733612: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733622: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733658: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.733740: my_probe: (sys_bpf+0xc/0x40)
>       test_progs-1971    [034] .....   532.736043: my_probe: (sys_bpf+0xc/0x40)
>
> 2. The other is sys_bpf, but this symbol exists in both cases(kernel where syscall
>    wrapper is enabled and where it is disabled).
>
> Kernel with syscall wrapper not introduced in powerpc:
>
> # uname -r
> 6.0.0
>
> # cat /proc/kallsyms | grep sys_bpf
> c000000000383630 t __sys_bpf
> c0000000003844a0 T bpf_sys_bpf
> c000000000384510 T kern_sys_bpf
> c000000000384840 T sys_bpf
> c000000000384840 T __se_sys_bpf
> c000000001030c80 d bpf_sys_bpf_proto
> c0000000014a8bf8 d __ksymtab_kern_sys_bpf
> c0000000014eac1f r __kstrtab_kern_sys_bpf
> c0000000014fa53b r __kstrtabns_kern_sys_bpf
> c000000002151e90 d _eil_addr_sys_bpf
>
> Kernel with syscall wrapper introduced in powerpc:
>
> # uname -r
> 6.13.0-rc6+
>
> # cat /proc/kallsyms | grep sys_bpf
> c0000000003d7750 t __sys_bpf
> c0000000003d83ac T bpf_sys_bpf
> c0000000003d8418 T kern_sys_bpf
> c0000000003d8734 T sys_bpf
> c000000001243328 d bpf_sys_bpf_proto
> c0000000017776b0 r __ksymtab_kern_sys_bpf
> c0000000021b7520 d _eil_addr_sys_bpf
>
> Thanks,
> Saket
> > >
> > > Thanks,
> > > Saket
> > > > >
> > > > > Thanks,
> > > > > Saket
> > > > > > > Thanks,
> > > > > > > Saket
> > > > > > > > >
> > > > > > > > >         if (determine_kprobe_perf_type() >= 0) {
> > > > > > > > >                 int pfd;
> > > > > > > > > @@ -11272,8 +11274,12 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
> > > > > > > > >                  * compiler does not know that we have an explicit conditional
> > > > > > > > >                  * as well.
> > > > > > > > >                  */
> > > > > > > > > +#if defined(__powerpc__)
> > > > > > > > > +               snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
> > > > > > > > > +#else
> > > > > > > > >                 snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
> > > > > > > > >                          arch_specific_syscall_pfx() ? : "", syscall_name);
> > > > > > > > > +#endif
> > > > > > > > >         } else {
> > > > > > > > >                 snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
> > > > > > > > >         }
> > > > > > > > > --
> > > > > > > > > 2.43.5
> > > > > > > > >
diff mbox series

Patch

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 219facd0e66e..3a370fa37d8a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -11110,9 +11110,7 @@  static const char *arch_specific_syscall_pfx(void)
 #elif defined(__riscv)
 	return "riscv";
 #elif defined(__powerpc__)
-	return "powerpc";
-#elif defined(__powerpc64__)
-	return "powerpc64";
+	return "";
 #else
 	return NULL;
 #endif
@@ -11127,7 +11125,11 @@  int probe_kern_syscall_wrapper(int token_fd)
 	if (!ksys_pfx)
 		return 0;
 
+#if defined(__powerpc__)
+	snprintf(syscall_name, sizeof(syscall_name), "sys_bpf");
+#else
 	snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx);
+#endif
 
 	if (determine_kprobe_perf_type() >= 0) {
 		int pfd;
@@ -11272,8 +11274,12 @@  struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog,
 		 * compiler does not know that we have an explicit conditional
 		 * as well.
 		 */
+#if defined(__powerpc__)
+		snprintf(func_name, sizeof(func_name), "sys_%s", syscall_name);
+#else
 		snprintf(func_name, sizeof(func_name), "__%s_sys_%s",
 			 arch_specific_syscall_pfx() ? : "", syscall_name);
+#endif
 	} else {
 		snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name);
 	}