Merge branch 'x86/mm' into x86/core, to resolve conflicts

 Conflicts:
	arch/x86/mm/numa.c
	arch/x86/mm/pgtable.c

Signed-off-by: Ingo Molnar <[email protected]>

Author: Ingo Molnar

arch/x86/Kconfig.assembler

@@ -15,10 +15,6 @@ config AS_SHA256_NI
 	def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
 	help
 	  Supported by binutils >= 2.24 and LLVM integrated assembler
-config AS_TPAUSE
-	def_bool $(as-instr,tpause %ecx)
-	help
-	  Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7
 
 config AS_GFNI
 	def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2)

arch/x86/include/asm/mwait.h

@@ -25,29 +25,31 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-static __always_inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
+static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx));
 }
 
-static __always_inline void __monitorx(const void *eax, unsigned long ecx,
-			      unsigned long edx)
+static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitorx %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfa;"
+	/* "monitorx %eax, %ecx, %edx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfa"
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
 
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -76,13 +78,12 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
  * EAX                     (logical) address to monitor
  * ECX                     #GP if not zero
  */
-static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
-				     unsigned long ecx)
+static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
 	/* No MDS buffer clear as this is AMD/HYGON only */
 
-	/* "mwaitx %eax, %ebx, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb;"
+	/* "mwaitx %eax, %ebx, %ecx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfb"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
@@ -95,12 +96,11 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
  * executing mwait, it would otherwise go unnoticed and the next tick
  * would not be reprogrammed accordingly before mwait ever wakes up.
  */
-static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+
+	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -113,16 +113,13 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  * New with Core Duo processors, MWAIT can take some hints based on CPU
  * capability.
  */
-static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
-		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
-			mb();
-			clflush((void *)&current_thread_info()->flags);
-			mb();
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 
 		if (!need_resched()) {
 			if (ecx & 1) {
@@ -144,16 +141,9 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
  */
 static inline void __tpause(u32 ecx, u32 edx, u32 eax)
 {
-	/* "tpause %ecx, %edx, %eax;" */
-	#ifdef CONFIG_AS_TPAUSE
-	asm volatile("tpause %%ecx\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#else
-	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#endif
+	/* "tpause %ecx" */
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+		     :: "c" (ecx), "d" (edx), "a" (eax));
 }
 
 #endif /* _ASM_X86_MWAIT_H */

arch/x86/include/asm/page_32_types.h

@@ -73,7 +73,6 @@ extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
 extern void find_low_pfn_range(void);
-extern void setup_bootmem_allocator(void);
 
 #endif	/* !__ASSEMBLER__ */
 

arch/x86/include/asm/pgtable-2level_types.h

@@ -18,8 +18,6 @@ typedef union {
 } pte_t;
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	0
-
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*

arch/x86/include/asm/pgtable-3level_types.h

@@ -27,9 +27,7 @@ typedef union {
 } pmd_t;
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
-
-#define ARCH_PAGE_TABLE_SYNC_MASK	(SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
+#define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map

arch/x86/include/asm/pgtable.h

@@ -292,13 +292,6 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
 	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
-#define p4d_leaf p4d_leaf
-static inline bool p4d_leaf(p4d_t p4d)
-{
-	/* No 512 GiB pages yet */
-	return 0;
-}
-
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 #define pmd_leaf pmd_leaf
@@ -1472,9 +1465,6 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
 }
 
-#define pgd_leaf	pgd_leaf
-static inline bool pgd_leaf(pgd_t pgd) { return false; }
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages

arch/x86/include/asm/pgtable_64_types.h

@@ -46,8 +46,6 @@ extern unsigned int ptrs_per_p4d;
 
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	0
-
 #ifdef CONFIG_X86_5LEVEL
 
 /*

arch/x86/kernel/process.c

@@ -901,13 +901,10 @@ static __init bool prefer_mwait_c1_over_halt(void)
 static __cpuidle void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
-		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
-			mb(); /* quirk */
-			clflush((void *)&current_thread_info()->flags);
-			mb(); /* quirk */
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 		if (!need_resched()) {
 			__sti_mwait(0, 0);
 			raw_local_irq_disable();

arch/x86/mm/Makefile

@@ -47,7 +47,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 

arch/x86/mm/fault.c

@@ -13,7 +13,6 @@
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
-#include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
@@ -1496,8 +1495,6 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 
 	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
-	prefetchw(&current->mm->mmap_lock);
-
 	/*
 	 * KVM uses #PF vector to deliver 'page not present' events to guests
 	 * (asynchronous page fault mechanism). The event happens when a