| Message ID | 20180904204553.6971-2-adhemerval.zanella@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | General fixes and refactor for BZ#12683 | expand |
Adhemerval Zanella <adhemerval.zanella@linaro.org> writes: > This patch the required CFI information on powerpc indirect syscall > so backtrace works correctly on signal handler. > > Checked on powerpc-linux-gnu and powerpc64le-linux-gnu. > > * sysdeps/unix/sysv/linux/powerpc/syscall.S (syscall): Add CFI > information. > --- > ChangeLog | 5 +++++ > sysdeps/unix/sysv/linux/powerpc/syscall.S | 1 + > 2 files changed, 6 insertions(+) > > diff --git a/sysdeps/unix/sysv/linux/powerpc/syscall.S b/sysdeps/unix/sysv/linux/powerpc/syscall.S > index 2da91721be..e30f461a17 100644 > --- a/sysdeps/unix/sysv/linux/powerpc/syscall.S > +++ b/sysdeps/unix/sysv/linux/powerpc/syscall.S > @@ -19,6 +19,7 @@ > > ENTRY (syscall) > ABORT_TRANSACTION > + cfi_def_cfa_offset (0) Why is this necessary in a function that is defined via ENTRY (or ENTRY_TOCLESS) that already has cfi_startproc? Does the error you found mean that parameter simple from cfi_startproc is being set by mistake? -- Tulio Magno
On 06/09/2018 12:18, Tulio Magno Quites Machado Filho wrote: > Adhemerval Zanella <adhemerval.zanella@linaro.org> writes: > >> This patch the required CFI information on powerpc indirect syscall >> so backtrace works correctly on signal handler. >> >> Checked on powerpc-linux-gnu and powerpc64le-linux-gnu. >> >> * sysdeps/unix/sysv/linux/powerpc/syscall.S (syscall): Add CFI >> information. >> --- >> ChangeLog | 5 +++++ >> sysdeps/unix/sysv/linux/powerpc/syscall.S | 1 + >> 2 files changed, 6 insertions(+) >> >> diff --git a/sysdeps/unix/sysv/linux/powerpc/syscall.S b/sysdeps/unix/sysv/linux/powerpc/syscall.S >> index 2da91721be..e30f461a17 100644 >> --- a/sysdeps/unix/sysv/linux/powerpc/syscall.S >> +++ b/sysdeps/unix/sysv/linux/powerpc/syscall.S >> @@ -19,6 +19,7 @@ >> >> ENTRY (syscall) >> ABORT_TRANSACTION >> + cfi_def_cfa_offset (0) > > Why is this necessary in a function that is defined via ENTRY (or > ENTRY_TOCLESS) that already has cfi_startproc? > > Does the error you found mean that parameter simple from cfi_startproc is being > set by mistake? > Re-testing it on powerpc64le it seems that current cfi directives provided by ENTRY indeed are suffice. The cfi_def_cfa_offset came in fact from a previous iteration, which I initially added a frame set/restore. So I withdraw this patch.
diff --git a/sysdeps/unix/sysv/linux/powerpc/syscall.S b/sysdeps/unix/sysv/linux/powerpc/syscall.S index 2da91721be..e30f461a17 100644 --- a/sysdeps/unix/sysv/linux/powerpc/syscall.S +++ b/sysdeps/unix/sysv/linux/powerpc/syscall.S @@ -19,6 +19,7 @@ ENTRY (syscall) ABORT_TRANSACTION + cfi_def_cfa_offset (0) mr r0,r3 mr r3,r4 mr r4,r5