diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-01 08:40:25 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-01 08:40:25 -0700 |
| commit | 5778077d03cb25aac9b6a428e18970642fc019e3 (patch) | |
| tree | 2e3f3da1fb99c3646da5ed9a09644696ca5f2309 /arch/x86/lib/delay.c | |
| parent | 65a99597f044c083983f4274ab049c9ec3b9d764 (diff) | |
| parent | 7e01ebffffedec22cea86ebe94802f909e4579ca (diff) | |
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 asm changes from Ingo Molnar:
"The biggest changes in this cycle were:
- Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC)
primitives. (Andy Lutomirski)
- Add new, comprehensible entry and exit handlers written in C.
(Andy Lutomirski)
- vm86 mode cleanups and fixes. (Brian Gerst)
- 32-bit compat code cleanups. (Brian Gerst)
The amount of simplification in low level assembly code is already
palpable:
arch/x86/entry/entry_32.S | 130 +----
arch/x86/entry/entry_64.S | 197 ++-----
but more simplifications are planned.
There's also the usual laudry mix of low level changes - see the
changelog for details"
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits)
x86/asm: Drop repeated macro of X86_EFLAGS_AC definition
x86/asm/msr: Make wrmsrl() a function
x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer
x86/asm: Add MONITORX/MWAITX instruction support
x86/traps: Weaken context tracking entry assertions
x86/asm/tsc: Add rdtscll() merge helper
selftests/x86: Add syscall_nt selftest
selftests/x86: Disable sigreturn_64
x86/vdso: Emit a GNU hash
x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks
x86/entry/32: Migrate to C exit path
x86/entry/32: Remove 32-bit syscall audit optimizations
x86/vm86: Rename vm86->v86flags and v86mask
x86/vm86: Rename vm86->vm86_info to user_vm86
x86/vm86: Clean up vm86.h includes
x86/vm86: Move the vm86 IRQ definitions to vm86.h
x86/vm86: Use the normal pt_regs area for vm86
x86/vm86: Eliminate 'struct kernel_vm86_struct'
x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86'
x86/vm86: Move vm86 fields out of 'thread_struct'
...
Diffstat (limited to 'arch/x86/lib/delay.c')
| -rw-r--r-- | arch/x86/lib/delay.c | 60 |
1 files changed, 51 insertions, 9 deletions
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 39d6a3db0b96..e912b2f6d36e 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -20,6 +20,7 @@ #include <asm/processor.h> #include <asm/delay.h> #include <asm/timer.h> +#include <asm/mwait.h> #ifdef CONFIG_SMP # include <asm/smp.h> @@ -49,16 +50,14 @@ static void delay_loop(unsigned long loops) /* TSC based delay: */ static void delay_tsc(unsigned long __loops) { - u32 bclock, now, loops = __loops; + u64 bclock, now, loops = __loops; int cpu; preempt_disable(); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); for (;;) { - rdtsc_barrier(); - rdtscl(now); + now = rdtsc_ordered(); if ((now - bclock) >= loops) break; @@ -79,14 +78,51 @@ static void delay_tsc(unsigned long __loops) if (unlikely(cpu != smp_processor_id())) { loops -= (now - bclock); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); } } preempt_enable(); } /* + * 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. + */ +static void delay_mwaitx(unsigned long __loops) +{ + u64 start, end, delay, loops = __loops; + + start = rdtsc_ordered(); + + for (;;) { + delay = min_t(u64, MWAITX_MAX_LOOPS, loops); + + /* + * Use cpu_tss as a cacheline-aligned, seldomly + * accessed per-cpu variable as the monitor target. + */ + __monitorx(this_cpu_ptr(&cpu_tss), 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); + + end = rdtsc_ordered(); + + if (loops <= end - start) + break; + + loops -= end - start; + + start = end; + } +} + +/* * Since we calibrate only once at boot, this * function should be set once at boot and not changed */ @@ -94,13 +130,19 @@ static void (*delay_fn)(unsigned long) = delay_loop; void use_tsc_delay(void) { - delay_fn = delay_tsc; + if (delay_fn == delay_loop) + delay_fn = delay_tsc; +} + +void use_mwaitx_delay(void) +{ + delay_fn = delay_mwaitx; } int read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscll(*timer_val); + *timer_val = rdtsc(); return 0; } return -1; |