Commit bb78c145 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'x86_core_for_v6.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull x86 cpu updates from Borislav Petkov:

 - Add helpers for WB{NO,}INVD with the purpose of using them in KVM and
   thus diminish the number of invalidations needed. With preceding
   cleanups, as always

* tag 'x86_core_for_v6.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/lib: Add WBINVD and WBNOINVD helpers to target multiple CPUs
  x86/lib: Add WBNOINVD helper functions
  x86/lib: Drop the unused return value from wbinvd_on_all_cpus()
  drm/gpu: Remove dead checks on wbinvd_on_all_cpus()'s return value
parents 04d29e36 4fdc3431

arch/x86/include/asm/smp.h

+20 −3
Original line number Diff line number Diff line
@@ -112,7 +112,10 @@ void __noreturn hlt_play_dead(void); 
void native_play_dead(void);

void play_dead_common(void);

void wbinvd_on_cpu(int cpu);

int wbinvd_on_all_cpus(void);

void wbinvd_on_all_cpus(void);

void wbinvd_on_cpus_mask(struct cpumask *cpus);

void wbnoinvd_on_all_cpus(void);

void wbnoinvd_on_cpus_mask(struct cpumask *cpus);



void smp_kick_mwait_play_dead(void);

void __noreturn mwait_play_dead(unsigned int eax_hint);
@@ -148,10 +151,24 @@ static inline struct cpumask *cpu_l2c_shared_mask(int cpu) 


#else /* !CONFIG_SMP */

#define wbinvd_on_cpu(cpu)     wbinvd()

static inline int wbinvd_on_all_cpus(void)

static inline void wbinvd_on_all_cpus(void)

{

	wbinvd();

	return 0;

}



static inline void wbinvd_on_cpus_mask(struct cpumask *cpus)

{

	wbinvd();

}



static inline void wbnoinvd_on_all_cpus(void)

{

	wbnoinvd();

}



static inline void wbnoinvd_on_cpus_mask(struct cpumask *cpus)

{

	wbnoinvd();

}



static inline struct cpumask *cpu_llc_shared_mask(int cpu)

arch/x86/include/asm/special_insns.h

+28 −1
Original line number Diff line number Diff line
@@ -104,11 +104,38 @@ static inline void wrpkru(u32 pkru) 
}

#endif



/*

 * Write back all modified lines in all levels of cache associated with this

 * logical processor to main memory, and then invalidate all caches.  Depending

 * on the micro-architecture, WBINVD (and WBNOINVD below) may or may not affect

 * lower level caches associated with another logical processor that shares any

 * level of this processor's cache hierarchy.

 */

static __always_inline void wbinvd(void)

{

	asm volatile("wbinvd" : : : "memory");

}



/* Instruction encoding provided for binutils backwards compatibility. */

#define ASM_WBNOINVD _ASM_BYTES(0xf3,0x0f,0x09)



/*

 * Write back all modified lines in all levels of cache associated with this

 * logical processor to main memory, but do NOT explicitly invalidate caches,

 * i.e. leave all/most cache lines in the hierarchy in non-modified state.

 */

static __always_inline void wbnoinvd(void)

{

	/*

	 * Explicitly encode WBINVD if X86_FEATURE_WBNOINVD is unavailable even

	 * though WBNOINVD is backwards compatible (it's simply WBINVD with an

	 * ignored REP prefix), to guarantee that WBNOINVD isn't used if it

	 * needs to be avoided for any reason.  For all supported usage in the

	 * kernel, WBINVD is functionally a superset of WBNOINVD.

	 */

	alternative("wbinvd", ASM_WBNOINVD, X86_FEATURE_WBNOINVD);

}



static inline unsigned long __read_cr4(void)

{

	return native_read_cr4();

arch/x86/kvm/x86.c

+1 −2
Original line number Diff line number Diff line
@@ -8295,8 +8295,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) 
		int cpu = get_cpu();



		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);

		on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,

				wbinvd_ipi, NULL, 1);

		wbinvd_on_cpus_mask(vcpu->arch.wbinvd_dirty_mask);

		put_cpu();

		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);

	} else

arch/x86/lib/cache-smp.c

+24 −2
Original line number Diff line number Diff line
@@ -14,9 +14,31 @@ void wbinvd_on_cpu(int cpu) 
}

EXPORT_SYMBOL(wbinvd_on_cpu);



int wbinvd_on_all_cpus(void)

void wbinvd_on_all_cpus(void)

{

	on_each_cpu(__wbinvd, NULL, 1);

	return 0;

}

EXPORT_SYMBOL(wbinvd_on_all_cpus);



void wbinvd_on_cpus_mask(struct cpumask *cpus)

{

	on_each_cpu_mask(cpus, __wbinvd, NULL, 1);

}

EXPORT_SYMBOL_GPL(wbinvd_on_cpus_mask);



static void __wbnoinvd(void *dummy)

{

	wbnoinvd();

}



void wbnoinvd_on_all_cpus(void)

{

	on_each_cpu(__wbnoinvd, NULL, 1);

}

EXPORT_SYMBOL_GPL(wbnoinvd_on_all_cpus);



void wbnoinvd_on_cpus_mask(struct cpumask *cpus)

{

	on_each_cpu_mask(cpus, __wbnoinvd, NULL, 1);

}

EXPORT_SYMBOL_GPL(wbnoinvd_on_cpus_mask);

drivers/gpu/drm/drm_cache.c

+3 −6
Original line number Diff line number Diff line
@@ -93,8 +93,7 @@ drm_clflush_pages(struct page *pages[], unsigned long num_pages) 
		return;

	}



	if (wbinvd_on_all_cpus())

		pr_err("Timed out waiting for cache flush\n");

	wbinvd_on_all_cpus();



#elif defined(__powerpc__)

	unsigned long i;
@@ -139,8 +138,7 @@ drm_clflush_sg(struct sg_table *st) 
		return;

	}



	if (wbinvd_on_all_cpus())

		pr_err("Timed out waiting for cache flush\n");

	wbinvd_on_all_cpus();

#else

	WARN_ONCE(1, "Architecture has no drm_cache.c support\n");

#endif
@@ -172,8 +170,7 @@ drm_clflush_virt_range(void *addr, unsigned long length) 
		return;

	}



	if (wbinvd_on_all_cpus())

		pr_err("Timed out waiting for cache flush\n");

	wbinvd_on_all_cpus();

#else

	WARN_ONCE(1, "Architecture has no drm_cache.c support\n");

#endif