aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/lib')
-rw-r--r--arch/x86/lib/checksum_32.S4
-rw-r--r--arch/x86/lib/csum-wrappers_64.c35
-rw-r--r--arch/x86/lib/delay.c114
-rw-r--r--arch/x86/lib/retpoline.S63
4 files changed, 137 insertions, 79 deletions
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4742e8fa7ee7..d1d768912368 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -153,7 +153,7 @@ SYM_FUNC_START(csum_partial)
negl %ebx
lea 45f(%ebx,%ebx,2), %ebx
testl %esi, %esi
- JMP_NOSPEC %ebx
+ JMP_NOSPEC ebx
# Handle 2-byte-aligned regions
20: addw (%esi), %ax
@@ -436,7 +436,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
andl $-32,%edx
lea 3f(%ebx,%ebx), %ebx
testl %esi, %esi
- JMP_NOSPEC %ebx
+ JMP_NOSPEC ebx
1: addl $64,%esi
addl $64,%edi
SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index c66c8b00f236..ee63d7576fd2 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -10,7 +10,7 @@
#include <asm/smap.h>
/**
- * csum_partial_copy_from_user - Copy and checksum from user space.
+ * csum_and_copy_from_user - Copy and checksum from user space.
* @src: source address (user space)
* @dst: destination address
* @len: number of bytes to be copied.
@@ -21,13 +21,13 @@
* src and dst are best aligned to 64bits.
*/
__wsum
-csum_partial_copy_from_user(const void __user *src, void *dst,
+csum_and_copy_from_user(const void __user *src, void *dst,
int len, __wsum isum, int *errp)
{
might_sleep();
*errp = 0;
- if (!likely(access_ok(src, len)))
+ if (!user_access_begin(src, len))
goto out_err;
/*
@@ -42,8 +42,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
while (((unsigned long)src & 6) && len >= 2) {
__u16 val16;
- if (__get_user(val16, (const __u16 __user *)src))
- goto out_err;
+ unsafe_get_user(val16, (const __u16 __user *)src, out);
*(__u16 *)dst = val16;
isum = (__force __wsum)add32_with_carry(
@@ -53,25 +52,26 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
len -= 2;
}
}
- stac();
isum = csum_partial_copy_generic((__force const void *)src,
dst, len, isum, errp, NULL);
- clac();
+ user_access_end();
if (unlikely(*errp))
goto out_err;
return isum;
+out:
+ user_access_end();
out_err:
*errp = -EFAULT;
memset(dst, 0, len);
return isum;
}
-EXPORT_SYMBOL(csum_partial_copy_from_user);
+EXPORT_SYMBOL(csum_and_copy_from_user);
/**
- * csum_partial_copy_to_user - Copy and checksum to user space.
+ * csum_and_copy_to_user - Copy and checksum to user space.
* @src: source address
* @dst: destination address (user space)
* @len: number of bytes to be copied.
@@ -82,14 +82,14 @@ EXPORT_SYMBOL(csum_partial_copy_from_user);
* src and dst are best aligned to 64bits.
*/
__wsum
-csum_partial_copy_to_user(const void *src, void __user *dst,
+csum_and_copy_to_user(const void *src, void __user *dst,
int len, __wsum isum, int *errp)
{
__wsum ret;
might_sleep();
- if (unlikely(!access_ok(dst, len))) {
+ if (!user_access_begin(dst, len)) {
*errp = -EFAULT;
return 0;
}
@@ -100,9 +100,7 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
isum = (__force __wsum)add32_with_carry(
(__force unsigned)isum, val16);
- *errp = __put_user(val16, (__u16 __user *)dst);
- if (*errp)
- return isum;
+ unsafe_put_user(val16, (__u16 __user *)dst, out);
src += 2;
dst += 2;
len -= 2;
@@ -110,13 +108,16 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
}
*errp = 0;
- stac();
ret = csum_partial_copy_generic(src, (void __force *)dst,
len, isum, NULL, errp);
- clac();
+ user_access_end();
return ret;
+out:
+ user_access_end();
+ *errp = -EFAULT;
+ return isum;
}
-EXPORT_SYMBOL(csum_partial_copy_to_user);
+EXPORT_SYMBOL(csum_and_copy_to_user);
/**
* csum_partial_copy_nocheck - Copy and checksum.
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index c126571e5e2e..65d15df6212d 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -27,9 +27,20 @@
# include <asm/smp.h>
#endif
+static void delay_loop(u64 __loops);
+
+/*
+ * Calibration and selection of the delay mechanism happens only once
+ * during boot.
+ */
+static void (*delay_fn)(u64) __ro_after_init = delay_loop;
+static void (*delay_halt_fn)(u64 start, u64 cycles) __ro_after_init;
+
/* simple loop based delay: */
-static void delay_loop(unsigned long loops)
+static void delay_loop(u64 __loops)
{
+ unsigned long loops = (unsigned long)__loops;
+
asm volatile(
" test %0,%0 \n"
" jz 3f \n"
@@ -49,9 +60,9 @@ static void delay_loop(unsigned long loops)
}
/* TSC based delay: */
-static void delay_tsc(unsigned long __loops)
+static void delay_tsc(u64 cycles)
{
- u64 bclock, now, loops = __loops;
+ u64 bclock, now;
int cpu;
preempt_disable();
@@ -59,7 +70,7 @@ static void delay_tsc(unsigned long __loops)
bclock = rdtsc_ordered();
for (;;) {
now = rdtsc_ordered();
- if ((now - bclock) >= loops)
+ if ((now - bclock) >= cycles)
break;
/* Allow RT tasks to run */
@@ -77,7 +88,7 @@ static void delay_tsc(unsigned long __loops)
* counter for this CPU.
*/
if (unlikely(cpu != smp_processor_id())) {
- loops -= (now - bclock);
+ cycles -= (now - bclock);
cpu = smp_processor_id();
bclock = rdtsc_ordered();
}
@@ -86,65 +97,96 @@ static void delay_tsc(unsigned long __loops)
}
/*
+ * On Intel the TPAUSE instruction waits until any of:
+ * 1) the TSC counter exceeds the value provided in EDX:EAX
+ * 2) global timeout in IA32_UMWAIT_CONTROL is exceeded
+ * 3) an external interrupt occurs
+ */
+static void delay_halt_tpause(u64 start, u64 cycles)
+{
+ u64 until = start + cycles;
+ u32 eax, edx;
+
+ eax = lower_32_bits(until);
+ edx = upper_32_bits(until);
+
+ /*
+ * Hard code the deeper (C0.2) sleep state because exit latency is
+ * small compared to the "microseconds" that usleep() will delay.
+ */
+ __tpause(TPAUSE_C02_STATE, edx, eax);
+}
+
+/*
* On some AMD platforms, MWAITX has a configurable 32-bit timer, that
- * counts with TSC frequency. The input value is the loop of the
- * counter, it will exit when the timer expires.
+ * counts with TSC frequency. The input value is the number of TSC cycles
+ * to wait. MWAITX will also exit when the timer expires.
*/
-static void delay_mwaitx(unsigned long __loops)
+static void delay_halt_mwaitx(u64 unused, u64 cycles)
{
- u64 start, end, delay, loops = __loops;
+ u64 delay;
+
+ delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles);
+ /*
+ * Use cpu_tss_rw as a cacheline-aligned, seldomly accessed per-cpu
+ * variable as the monitor target.
+ */
+ __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
+
+ /*
+ * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not
+ * enter any deep C-state and we use it here in delay() to minimize
+ * wakeup latency.
+ */
+ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
+}
+
+/*
+ * Call a vendor specific function to delay for a given amount of time. Because
+ * these functions may return earlier than requested, check for actual elapsed
+ * time and call again until done.
+ */
+static void delay_halt(u64 __cycles)
+{
+ u64 start, end, cycles = __cycles;
/*
* Timer value of 0 causes MWAITX to wait indefinitely, unless there
* is a store on the memory monitored by MONITORX.
*/
- if (loops == 0)
+ if (!cycles)
return;
start = rdtsc_ordered();
for (;;) {
- delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
-
- /*
- * Use cpu_tss_rw as a cacheline-aligned, seldomly
- * accessed per-cpu variable as the monitor target.
- */
- __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
-
- /*
- * AMD, like Intel's MWAIT version, supports the EAX hint and
- * EAX=0xf0 means, do not enter any deep C-state and we use it
- * here in delay() to minimize wakeup latency.
- */
- __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
-
+ delay_halt_fn(start, cycles);
end = rdtsc_ordered();
- if (loops <= end - start)
+ if (cycles <= end - start)
break;
- loops -= end - start;
-
+ cycles -= end - start;
start = end;
}
}
-/*
- * Since we calibrate only once at boot, this
- * function should be set once at boot and not changed
- */
-static void (*delay_fn)(unsigned long) = delay_loop;
-
-void use_tsc_delay(void)
+void __init use_tsc_delay(void)
{
if (delay_fn == delay_loop)
delay_fn = delay_tsc;
}
+void __init use_tpause_delay(void)
+{
+ delay_halt_fn = delay_halt_tpause;
+ delay_fn = delay_halt;
+}
+
void use_mwaitx_delay(void)
{
- delay_fn = delay_mwaitx;
+ delay_halt_fn = delay_halt_mwaitx;
+ delay_fn = delay_halt;
}
int read_current_timer(unsigned long *timer_val)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 363ec132df7e..b4c43a9b1483 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,15 +7,31 @@
#include <asm/alternative-asm.h>
#include <asm/export.h>
#include <asm/nospec-branch.h>
+#include <asm/unwind_hints.h>
+#include <asm/frame.h>
.macro THUNK reg
.section .text.__x86.indirect_thunk
+ .align 32
SYM_FUNC_START(__x86_indirect_thunk_\reg)
- CFI_STARTPROC
- JMP_NOSPEC %\reg
- CFI_ENDPROC
+ JMP_NOSPEC \reg
SYM_FUNC_END(__x86_indirect_thunk_\reg)
+
+SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call .Ldo_rop_\@
+.Lspec_trap_\@:
+ UNWIND_HINT_EMPTY
+ pause
+ lfence
+ jmp .Lspec_trap_\@
+.Ldo_rop_\@:
+ mov %\reg, (%_ASM_SP)
+ UNWIND_HINT_RET_OFFSET
+ ret
+SYM_FUNC_END(__x86_retpoline_\reg)
+
.endm
/*
@@ -24,25 +40,24 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg)
* only see one instance of "__x86_indirect_thunk_\reg" rather
* than one per register with the correct names. So we do it
* the simple and nasty way...
+ *
+ * Worse, you can only have a single EXPORT_SYMBOL per line,
+ * and CPP can't insert newlines, so we have to repeat everything
+ * at least twice.
*/
-#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
-#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
-#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
-
-GENERATE_THUNK(_ASM_AX)
-GENERATE_THUNK(_ASM_BX)
-GENERATE_THUNK(_ASM_CX)
-GENERATE_THUNK(_ASM_DX)
-GENERATE_THUNK(_ASM_SI)
-GENERATE_THUNK(_ASM_DI)
-GENERATE_THUNK(_ASM_BP)
-#ifdef CONFIG_64BIT
-GENERATE_THUNK(r8)
-GENERATE_THUNK(r9)
-GENERATE_THUNK(r10)
-GENERATE_THUNK(r11)
-GENERATE_THUNK(r12)
-GENERATE_THUNK(r13)
-GENERATE_THUNK(r14)
-GENERATE_THUNK(r15)
-#endif
+
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define EXPORT_RETPOLINE(reg) __EXPORT_THUNK(__x86_retpoline_ ## reg)
+
+#undef GEN
+#define GEN(reg) THUNK reg
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) EXPORT_THUNK(reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) EXPORT_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
Powered by cgit, Gruvboxed by Blaster4385.