When we reserve space for an FPU state in a signal frame, we need to use
the size of the current fpu state. The kernel cpuid can report a smaller size.
On restore, we need to read the size of an fpu state from a signal frame.
After S/R, it can't be different from the current fpu size.
PiperOrigin-RevId: 546972243
We don't care about corrupting the current state, because sigreturn
syscalls never report errors and they queue SIGSEGV in case of any
problems.
Here are results fro the signal_benchmark on the kvm platform:
Before:
BM_FaultSignalFixup/real_time 6127 ns 6087 ns 111708
After:
BM_FaultSignalFixup/real_time 3661 ns 3654 ns 199755
PiperOrigin-RevId: 462021118
Since `arch.Context64` is the only concrete implementation of
`arch.Context`, this does not functionally change anything.
While `arch.Context64` *can* mean multiple things in the codebase, since
the `arch` module uses conditional compilation to create different builds
for AMD64 vs ARM64, the `Context64` type is still singular within each
possible version this can compile to.
This avoids the overhead involved in calling interface
functions in Go:
https://github.com/teh-cmc/go-internals/blob/master/chapter2_interfaces/README.md#dynamic-dispatch
This overhead is particularly painful for functions like `SyscallSaveOrig`
which is a no-op on AMD64.
On KVM, this reduces syscall latency by 4~5%:
```
name old wall_ns/op new wall_ns/op delta
Getpid 602 ± 4% 579 ± 3% -3.94% (p=0.000 n=66+195)
GetpidOpt 604 ± 3% 573 ± 3% -5.10% (p=0.000 n=71+194)
name old cpu_ns/op new cpu_ns/op delta
Getpid 604 ± 5% 581 ± 0% -3.81% (p=0.000 n=75+130)
GetpidOpt 604 ± 2% 574 ± 3% -4.95% (p=0.000 n=71+196)
```
PiperOrigin-RevId: 461742893
reflect.ValueOf takes an interface{}, so when passed a slice the compiler emits
a call to runtime.convTslice to heap-allocate a copy of the slice header.
PiperOrigin-RevId: 394310052
Remove three syserror entries duplicated in linuxerr. Because of the
linuxerr.Equals method, this is a mere change of return values from
syserror to linuxerr definitions.
Done with only these three errnos as CLs removing all grow to a significantly
large size.
PiperOrigin-RevId: 382173835
Split usermem package to help remove syserror dependency in go_marshal.
New hostarch package contains code not dependent on syserror.
PiperOrigin-RevId: 365651233
The syscall package has been deprecated in favor of golang.org/x/sys.
Note that syscall is still used in the following places:
- pkg/sentry/socket/hostinet/stack.go: some netlink related functionalities
are not yet available in golang.org/x/sys.
- syscall.Stat_t is still used in some places because os.FileInfo.Sys() still
returns it and not unix.Stat_t.
Updates #214
PiperOrigin-RevId: 360701387
See https://github.com/golang/go/issues/19367 for rationale. Note that the
upstream decision arrived at in that thread, while useful for some of our use
cases, doesn't account for all of our SliceHeader use cases (we often use
SliceHeader to extract pointers from slices in a way that avoids bounds
checking and/or handles nil slices correctly) and also doesn't exist yet.
PiperOrigin-RevId: 358071574
In order to improve the performance and stability, I reorg 2 modules slightly.
arch: no red zone on Arm64.
ring0: use stp instead of movd, and set RSV_REG_APP=R19.
Signed-off-by: Robin Luk <[email protected]>
These options allow overriding the signal that gets sent to the process when
I/O operations are available on the file descriptor, rather than the default
`SIGIO` signal. Doing so also populates `siginfo` to contain extra information
about which file descriptor caused the event (`si_fd`) and what events happened
on it (`si_band`). The logic around which FD is populated within `si_fd`
matches Linux's, which means it has some weird edge cases where that value may
not actually refer to a file descriptor that is still valid.
This CL also ports extra S/R logic regarding async handler in VFS2.
Without this, async I/O handlers aren't properly re-registered after S/R.
PiperOrigin-RevId: 345436598
- Rewrite arch.Stack.{Push,Pop}. For the most part, stack now
implements marshal.CopyContext and can be used as the target of
marshal operations. Stack.Push had some extra logic for
automatically null-terminating slices. This was only used for two
specific types of slices, and is now handled explicitly.
- Delete usermem.CopyObject{In,Out}.
- Replace most remaining uses of the encoding/binary package with
go-marshal. Most of these were using the binary package to compute
the size of a struct, which go-marshal can directly replace. ~3 uses
of the binary package remain. These aren't reasonably replaceable by
go-marshal: for example one use is to construct the syscall
trampoline for systrap.
- Fill out remaining convenience wrappers in the primitive package.
PiperOrigin-RevId: 334502375
This patch adds minor changes for Arm64 platform:
1, add SetRobustList/GetRobustList support for arm64 syscall module.
2, add newfstatat support for arm64 vfs2 syscall module.
3, add tls value in ProtoBuf.
Signed-off-by: Bin Lu <[email protected]>
This patch load/save TLS for the container application.
Related issue: full context-switch supporting for Arm64 #1238
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gvisor/pull/2761 from lubinszARM:pr_tls_2 cb5dbca1c9c3f378002406da7a58887f9b5032b3
PiperOrigin-RevId: 322887044
* Aggregate architecture Overview in "What is gVisor?" as it makes more sense
in one place.
* Drop "user-space kernel" and use "application kernel". The term "user-space
kernel" is confusing when some platform implementation do not run in
user-space (instead running in guest ring zero).
* Clear up the relationship between the Platform page in the user guide and the
Platform page in the architecture guide, and ensure they are cross-linked.
* Restore the call-to-action quick start link in the main page, and drop the
GitHub link (which also appears in the top-right).
* Improve image formatting by centering all doc and blog images, and move the
image captions to the alt text.
PiperOrigin-RevId: 311845158
The comments in the ticket indicate that this behavior
is fine and that the ticket should be closed, so we shouldn't
need pointers to the ticket.
PiperOrigin-RevId: 306266071
SA_RESTORER is always used on Intel platform.
But this flag is optional on other platforms.
The vdso is enabled, so we can use the sigreturn trampolines
the vdso provides instead on Arm platform.
Signed-off-by: Bin Lu <[email protected]>
This issue was caused by 'restart_syscall'.
The value of Register R0 should be stored after finishing sysemu.
So that we can restore the value and restart syscall.
Signed-off-by: Bin Lu <[email protected]>
