d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Complete r323772 on amd64.

Browse Source 
Compilers are allowed to combine plain reads into group operations,
e.g. 64bit element copies of one array into another can be
legitimately optimized back to a memcpy() call, which r323772 tried to
prevent.

Qualify accesses to LDT descriptors with volatile dereference to
ensure that each write indeed occurs.  After that, our usual claim of
native-size aligned writes being atomic applies.

This is equivalent to atomic_store(memory_order_relaxed) C11 accesses,
but our machine/atomic.h does not provide corresponding primitive.

Noted and reviewed by:	bde
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
This commit is contained in:
kib 2017-10-05 12:16:45 +00:00
parent 3684a76fa7
commit 00ef4a21e2
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
sys/amd64/amd64/sys_machdep.c
View File

@ -616,7 +616,7 @@ amd64_set_ldt(struct thread *td, struct i386_ldt_args *uap,
return (EINVAL);
mtx_lock(&dt_lock);
for (i = uap->start; i < largest_ld; i++)
((uint64_t *)(pldt->ldt_base))[i] = 0;
((volatile uint64_t *)(pldt->ldt_base))[i] = 0;
mtx_unlock(&dt_lock);
return (0);
}
@ -734,15 +734,15 @@ amd64_set_ldt_data(struct thread *td, int start, int num,
{
struct mdproc *mdp;
struct proc_ldt *pldt;
uint64_t *dst, *src;
volatile uint64_t *dst, *src;
int i;
mtx_assert(&dt_lock, MA_OWNED);
mdp = &td->td_proc->p_md;
pldt = mdp->md_ldt;
dst = (uint64_t *)(pldt->ldt_base);
src = (uint64_t *)descs;
dst = (volatile uint64_t *)(pldt->ldt_base);
src = (volatile uint64_t *)descs;
for (i = 0; i < num; i++)
dst[start + i] = src[i];
return (0);