x86: Use rd/wr fs/gs base in arch_prctl
Convert arch_prctl to use the new instructions to
change fs/gs if available, instead of using MSRs.
This is merely a small performance optimization,
no new functionality.
With the new instructions the syscall is really obsolete,
as everything can be set directly in ring 3. But the syscall
is widely used by existing software, so we still support it.
The syscall still enforces that the addresses are not
in kernel space, even though that is not needed more.
This is mainly so that the programs written for new CPUs
do not suddenly fail on old CPUs.
With the new instructions available it prefers to use
them in the context switch, instead of using the old
"use GDT segment rewrite" trick.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9bad75a..7669b3b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -486,15 +486,23 @@
int ret = 0;
int doit = task == current;
int cpu;
+ int fast_seg = boot_cpu_has(X86_FEATURE_FSGSBASE);
switch (code) {
case ARCH_SET_GS:
+ /*
+ * With fast_seg we don't need that check anymore,
+ * but keep it so that programs do not suddenly
+ * start failing when run on older CPUs.
+ * If you really want to set a address in kernel space
+ * use WRGSBASE directly.
+ */
if (addr >= TASK_SIZE_OF(task))
return -EPERM;
cpu = get_cpu();
/* handle small bases via the GDT because that's faster to
switch. */
- if (addr <= 0xffffffff) {
+ if (addr <= 0xffffffff && !fast_seg) {
set_32bit_tls(task, GS_TLS, addr);
if (doit) {
load_TLS(&task->thread, cpu);
@@ -506,8 +514,17 @@
task->thread.gsindex = 0;
task->thread.gs = addr;
if (doit) {
- load_gs_index(0);
- ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
+ if (fast_seg) {
+ local_irq_disable();
+ swapgs();
+ loadsegment(gs, 0);
+ wrgsbase(addr);
+ swapgs();
+ local_irq_enable();
+ } else {
+ load_gs_index(0);
+ ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
+ }
}
}
put_cpu();
@@ -520,7 +537,7 @@
cpu = get_cpu();
/* handle small bases via the GDT because that's faster to
switch. */
- if (addr <= 0xffffffff) {
+ if (addr <= 0xffffffff && !fast_seg) {
set_32bit_tls(task, FS_TLS, addr);
if (doit) {
load_TLS(&task->thread, cpu);
@@ -535,7 +552,10 @@
/* set the selector to 0 to not confuse
__switch_to */
loadsegment(fs, 0);
- ret = wrmsrl_safe(MSR_FS_BASE, addr);
+ if (fast_seg)
+ wrfsbase(addr);
+ else
+ ret = wrmsrl_safe(MSR_FS_BASE, addr);
}
}
put_cpu();
@@ -544,6 +564,8 @@
unsigned long base;
if (task->thread.fsindex == FS_TLS_SEL)
base = read_32bit_tls(task, FS_TLS);
+ else if (doit && fast_seg)
+ base = rdfsbase();
else if (doit)
rdmsrl(MSR_FS_BASE, base);
else
@@ -558,9 +580,16 @@
base = read_32bit_tls(task, GS_TLS);
else if (doit) {
savesegment(gs, gsindex);
- if (gsindex)
- rdmsrl(MSR_KERNEL_GS_BASE, base);
- else
+ if (gsindex) {
+ if (fast_seg) {
+ local_irq_disable();
+ swapgs();
+ base = rdgsbase();
+ swapgs();
+ local_irq_enable();
+ } else
+ rdmsrl(MSR_KERNEL_GS_BASE, base);
+ } else
base = task->thread.gs;
} else
base = task->thread.gs;
