diff options
| author | Flavio Cruz <flaviocruz@gmail.com> | 2024-02-19 23:58:00 -0500 |
|---|---|---|
| committer | Samuel Thibault <samuel.thibault@ens-lyon.org> | 2024-03-11 23:48:10 +0100 |
| commit | 661835c91d14a41755c5f340ba0257c6ca8db1a1 (patch) | |
| tree | fe1a18724d73eede6bc5c7c72858b74a8efe4bdd /i386 | |
| parent | afec41f9d80cb1f923d0d4f76af832b036dc2f4f (diff) | |
| download | gnumach-661835c91d14a41755c5f340ba0257c6ca8db1a1.tar.gz gnumach-661835c91d14a41755c5f340ba0257c6ca8db1a1.tar.bz2 gnumach-661835c91d14a41755c5f340ba0257c6ca8db1a1.zip | |
x86_64: avoid iterating over the message twice in copyoutmsg/copyinmsg for faster RPCs.
This is a follow up to
https://git.savannah.gnu.org/cgit/hurd/gnumach.git/commit/?id=69620634858b2992e1a362e33c95d9a8ee57bce7
where we made inlined ports 8 bytes long to avoid resizing.
The last thing that copy{in,out}msg were doing was just updating
msgt_size field since that's required for kernel stub code and implicitly
assumed by IPC code. This was moved into ipc_kmsg_copy{in,out}_body.
For a 32 bit userland, the code also stops updating
msgt_size for out of line ports, same as the 64 bit userland.
Message-ID: <ZdQxWNSieTHcpM1b@jupiter.tail36e24.ts.net>
Diffstat (limited to 'i386')
| -rw-r--r-- | i386/i386/locore.h | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/i386/i386/locore.h b/i386/i386/locore.h index 374c8cf9..217e6dec 100644 --- a/i386/i386/locore.h +++ b/i386/i386/locore.h @@ -50,7 +50,13 @@ extern int discover_x86_cpu_type (void); extern int copyin (const void *userbuf, void *kernelbuf, size_t cn); extern int copyinmsg (const void *userbuf, void *kernelbuf, size_t cn, size_t kn); extern int copyout (const void *kernelbuf, void *userbuf, size_t cn); +#ifdef USER32 extern int copyoutmsg (const void *kernelbuf, void *userbuf, size_t cn); +#else +static inline int copyoutmsg (const void *kernelbuf, void *userbuf, size_t cn) { + return copyout (kernelbuf, userbuf, cn); +} +#endif extern int inst_fetch (int eip, int cs); |