linux-user/ppc: Fix ppc64 rt_sigframe stack offset
PATCH 1/1 linux-user/ppc: Fix ppc64 rt_sigframe stack offset
The kernel's 64-bit signal delivery (signal_64.c) uses:
newsp = frame - __SIGNAL_FRAMESIZE
while the 32-bit path (signal_32.c) uses:
newsp = frame - (__SIGNAL_FRAMESIZE + 16)
The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in signal_32.c). The 64-bit rt_sigframe starts with ucontext directly and does not need this adjustment.
QEMU's setup_rt_frame() unconditionally used (SIGNAL_FRAMESIZE + 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked because do_rt_sigreturn had the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.
Guard the +16 with #if !defined(TARGET_PPC64) in both setup_rt_frame and do_rt_sigreturn to match the kernel.
This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.
--- linux-user/ppc/signal.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
linux-user/ppc/signal.c +12 -0
@@ -525,7 +525,15 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, env->fpscr =0 ;/* Create a stack frame for the caller of the handler. */ +#if defined(TARGET_PPC64 ) + newsp = rt_sf_addr -SIGNAL_FRAMESIZE ; +#else +/* +* The +16 is to get the siginfo and ucontext in the same positions +* as in older kernels. See Linux's arch/powerpc/kernel/signal_32.c. +*/ newsp = rt_sf_addr - (SIGNAL_FRAMESIZE +16 ); +#endif err |=put_user (env->gpr[1 ], newsp, target_ulong);if (err)
@@ -641,7 +649,11 @@ long do_rt_sigreturn(CPUPPCState *env)struct target_rt_sigframe *rt_sf =NULL ;target_ulong rt_sf_addr; +#if defined(TARGET_PPC64 ) + rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE ; +#else rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE +16 ; +#endif if (!lock_user_struct (VERIFY_READ , rt_sf, rt_sf_addr,1 )) goto sigsegv;
Signature · 1 line
2.52.0
Quoted 58 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Guard the +16 with #if !defined(TARGET_PPC64) in both
setup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)linux-user/ppc/signal.c +8
-0@@ -525,7 +525,15 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, env->fpscr =0 ;/* Create a stack frame for the caller of the handler. */ +#if defined(TARGET_PPC64 ) + newsp = rt_sf_addr -SIGNAL_FRAMESIZE ; +#else +/* +* The +16 is to get the siginfo and ucontext in the same positions +* as in older kernels. See Linux's arch/powerpc/kernel/signal_32.c. +*/ newsp = rt_sf_addr - (SIGNAL_FRAMESIZE +16 ); +#endif err |=put_user (env->gpr[1 ], newsp, target_ulong);if (err)
linux-user/ppc/signal.c long do_rt_sigreturn(CPUPPCState *env) · line 658
Quoted 10 lines
linux-user/ppc/signal.c +4
-0@@ -641,7 +649,11 @@ long do_rt_sigreturn(CPUPPCState *env)struct target_rt_sigframe *rt_sf =NULL ;target_ulong rt_sf_addr; +#if defined(TARGET_PPC64 ) + rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE ; +#else rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE +16 ; +#endif if (!lock_user_struct (VERIFY_READ , rt_sf, rt_sf_addr,1 )) goto sigsegv;
Thanks for this patch; comparing against the kernel code QEMU is definitely wrong here.
I think I would prefer it if we avoided the in-code ifdefs and instead had something like this defined at the top of the file, e.g. below the target_rt_sigframe definition:
#ifdef TARGET_PPC64
#define RT_SIGFRAME_ADJUST 0
#else
/*
* For 32-bit rt sigframes we have an extra 16 bytes of gap
* on top of __SIGNAL_FRAMESIZE; this is to get the siginfo
* and ucontext in the same positions as in older kernels.
* See Linux's arch/powerpc/kernel/signal_32.c.
*/
#define RT_SIGFRAME_ADJUST 16
#endif
Then we can have the code unconditionally do
newsp = rt_sf_addr - (SIGNAL_FRAMESIZE + RT_SIGFRAME_ADJUST);
etc.
thanks
-- PMM
Quoted 91 lines · Peter Maydell
Quoted 58 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Guard the +16 with #if !defined(TARGET_PPC64) in both
setup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)linux-user/ppc/signal.c +8
-0@@ -525,7 +525,15 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, env->fpscr =0 ;/* Create a stack frame for the caller of the handler. */ +#if defined(TARGET_PPC64 ) + newsp = rt_sf_addr -SIGNAL_FRAMESIZE ; +#else +/* +* The +16 is to get the siginfo and ucontext in the same positions +* as in older kernels. See Linux's arch/powerpc/kernel/signal_32.c. +*/ newsp = rt_sf_addr - (SIGNAL_FRAMESIZE +16 ); +#endif err |=put_user (env->gpr[1 ], newsp, target_ulong);if (err)linux-user/ppc/signal.c long do_rt_sigreturn(CPUPPCState *env) · line 658
Quoted 10 lines
linux-user/ppc/signal.c +4
-0@@ -641,7 +649,11 @@ long do_rt_sigreturn(CPUPPCState *env)struct target_rt_sigframe *rt_sf =NULL ;target_ulong rt_sf_addr; +#if defined(TARGET_PPC64 ) + rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE ; +#else rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE +16 ; +#endif if (!lock_user_struct (VERIFY_READ , rt_sf, rt_sf_addr,1 )) goto sigsegv;Thanks for this patch; comparing against the kernel code QEMU is definitely wrong here.
I think I would prefer it if we avoided the in-code ifdefs and instead had something like this defined at the top of the file, e.g. below the
target_rt_sigframedefinition:#ifdef
TARGET_PPC64
#defineRT_SIGFRAME_ADJUST0
#else
/*
* For 32-bit rt sigframes we have an extra 16 bytes of gap
* on top of__SIGNAL_FRAMESIZE; this is to get the siginfo
* and ucontext in the same positions as in older kernels.
* See Linux'sarch/powerpc/kernel/signal_32.c.
*/
#defineRT_SIGFRAME_ADJUST16
#endif
Quoted 6 lines
Then we can have the code unconditionally do
newsp =rt_sf_addr- (SIGNAL_FRAMESIZE+RT_SIGFRAME_ADJUST);
etc.thanks
-- PMM
Thanks Peter! That is definitely a lot cleaner. I've sent a revised patch.
PATCH 1/1 linux-user/ppc: Fix ppc64 rt_sigframe stack offset
In reply to Matt TurnerThe kernel's 64-bit signal delivery (signal_64.c) uses:
newsp = frame - __SIGNAL_FRAMESIZE
while the 32-bit path (signal_32.c) uses:
newsp = frame - (__SIGNAL_FRAMESIZE + 16)
The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in signal_32.c). The 64-bit rt_sigframe starts with ucontext directly and does not need this adjustment.
QEMU's setup_rt_frame() unconditionally used (SIGNAL_FRAMESIZE + 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked because do_rt_sigreturn had the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.
Define RT_SIGFRAME_ADJUST (0 on ppc64, 16 on ppc32) and use it in both setup_rt_frame and do_rt_sigreturn to match the kernel.
This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.
--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
linux-user/ppc/signal.c +14 -2
@@ -210,6 +210,18 @@ QEMU_BUILD_BUG_ON(offsetof(struct target_rt_sigframe, uc.tuc_mcontext)#endif +#ifdef TARGET_PPC64 +#define RT_SIGFRAME_ADJUST 0 +#else +/* +* For 32-bit rt sigframes we have an extra 16 bytes of gap +* on top of __SIGNAL_FRAMESIZE; this is to get the siginfo +* and ucontext in the same positions as in older kernels. +* See Linux's arch/powerpc/kernel/signal_32.c. +*/ +#define RT_SIGFRAME_ADJUST 16 +#endif +#if defined(TARGET_PPC64 ) struct target_func_ptr {
@@ -525,7 +537,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, env->fpscr =0 ;/* Create a stack frame for the caller of the handler. */ - newsp = rt_sf_addr - (SIGNAL_FRAMESIZE +16 ); + newsp = rt_sf_addr - (SIGNAL_FRAMESIZE +RT_SIGFRAME_ADJUST ); err |=put_user (env->gpr[1 ], newsp, target_ulong);if (err)
@@ -641,7 +653,7 @@ long do_rt_sigreturn(CPUPPCState *env)struct target_rt_sigframe *rt_sf =NULL ;target_ulong rt_sf_addr; - rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE +16 ; + rt_sf_addr = env->gpr[1 ] +SIGNAL_FRAMESIZE +RT_SIGFRAME_ADJUST ;if (!lock_user_struct (VERIFY_READ , rt_sf, rt_sf_addr,1 )) goto sigsegv;
Signature · 1 line
2.52.0
Quoted 32 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Define
RT_SIGFRAME_ADJUST(0 on ppc64, 16 on ppc32) and use it in bothsetup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.
Quoted 5 lines
Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
thanks
-- PMM
Quoted 34 lines · Peter Maydell
Quoted 32 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Define
RT_SIGFRAME_ADJUST(0 on ppc64, 16 on ppc32) and use it in bothsetup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.
Quoted 7 lines
Quoted 5 lines
Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)Reviewed-by Peter Maydell <[email protected]>
Thanks!
I sent this to Laurent Vivier <[email protected]> since that's what get_maintainer.pl said, but I see that he hasn't committed this year. Should I wait on him, or can you see that this gets in?
Also, I think this is probably worth including in the stable branch(es), so I've cc'd [email protected].
Matt
Quoted 46 lines · Matt Turner
Quoted 34 lines · Peter Maydell
Quoted 32 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Define
RT_SIGFRAME_ADJUST(0 on ppc64, 16 on ppc32) and use it in bothsetup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.Quoted 7 lines
Quoted 5 lines
Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)Reviewed-by Peter Maydell <[email protected]>Thanks!
Quoted 8 lines
I sent this to Laurent Vivier <[email protected]> since that's what
get_maintainer.plsaid, but I see that he hasn't committed this year. Should I wait on him, or can you see that this gets in?Also, I think this is probably worth including in the stable branch(es), so I've cc'd [email protected].
Matt
Sorry to ping. Just trying to get clarity on what I need to do.
Hi Matt,
Quoted 51 lines · Matt Turner
Quoted 50 lines · Matt Turner
Quoted 34 lines · Peter Maydell
Quoted 32 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Define
RT_SIGFRAME_ADJUST(0 on ppc64, 16 on ppc32) and use it in bothsetup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.Quoted 7 lines
Quoted 5 lines
Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)Reviewed-by Peter Maydell <[email protected]>Thanks!
I sent this to Laurent Vivier <[email protected]> since that's what
get_maintainer.plsaid, but I see that he hasn't committed this year. Should I wait on him, or can you see that this gets in?
Quoted 6 lines
Quoted 4 lines
Also, I think this is probably worth including in the stable branch(es), so I've cc'd [email protected].
Matt
Sorry to ping. Just trying to get clarity on what I need to do.
I've picked it up into my linux-user-next git tree and will push then soon:
https://gitlab.com/hdeller/qemu/-/commits/linux-user-next?ref_type=heads
Helge
Quoted 60 lines · Helge Deller
Hi Matt,
Quoted 56 lines · Matt Turner
Quoted 54 lines · Matt Turner
Quoted 34 lines · Peter Maydell
Quoted 32 lines · Matt Turner
The kernel's 64-bit signal delivery (
signal_64.c) uses:newsp = frame -
__SIGNAL_FRAMESIZEwhile the 32-bit path (
signal_32.c) uses:newsp = frame - (
__SIGNAL_FRAMESIZE+ 16)The extra 16 bytes in the 32-bit case is to place siginfo and ucontext at the same offsets as older kernels (see the comment in
signal_32.c). The 64-bitrt_sigframestarts with ucontext directly and does not need this adjustment.QEMU's
setup_rt_frame()unconditionally used (SIGNAL_FRAMESIZE+ 16) for both 32-bit and 64-bit, placing the handler's SP 16 bytes too low on ppc64. Signal delivery and return still worked becausedo_rt_sigreturnhad the matching wrong offset, but the vDSO DWARF unwind info encodes the correct kernel offset. This caused any DWARF unwinder (libunwind, libgcc, etc.) to compute a CFA that is 16 bytes off, reading garbage register values from the signal frame.Define
RT_SIGFRAME_ADJUST(0 on ppc64, 16 on ppc32) and use it in bothsetup_rt_frameanddo_rt_sigreturnto match the kernel.This was verified by A/B testing with libunwind's test suite:
ppc64le: Gtest-bt, Ltest-bt, Gtest-concurrent, Ltest-concurrent,
and Ltest-sig-context all change from FAIL to PASS.
ppc64be: Gtest-bt, Ltest-bt, and Ltest-sig-context all change
from FAIL to PASS.Quoted 7 lines
Quoted 5 lines
Signed-off-by Matt Turner <[email protected]>--- linux-user/ppc/signal.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)Reviewed-by Peter Maydell <[email protected]>Thanks!
I sent this to Laurent Vivier <[email protected]> since that's what
get_maintainer.plsaid, but I see that he hasn't committed this year. Should I wait on him, or can you see that this gets in?Also, I think this is probably worth including in the stable branch(es), so I've cc'd [email protected].
Matt
Quoted 8 lines
Quoted 1 line
Sorry to ping. Just trying to get clarity on what I need to do.
I've picked it up into my linux-user-next git tree and will push then soon:
https://gitlab.com/hdeller/qemu/-/commits/linux-user-next?ref_type=heads
Helge
Awesome, thanks Helge!