Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip Pull locking and misc x86 updates from Ingo Molnar: "Lots of changes in this cycle - in part because locking/core attracted a number of related x86 low level work which was easier to handle in a single tree: - Linux Kernel Memory Consistency Model updates (Alan Stern, Paul E. McKenney, Andrea Parri) - lockdep scalability improvements and micro-optimizations (Waiman Long) - rwsem improvements (Waiman Long) - spinlock micro-optimization (Matthew Wilcox) - qspinlocks: Provide a liveness guarantee (more fairness) on x86. (Peter Zijlstra) - Add support for relative references in jump tables on arm64, x86 and s390 to optimize jump labels (Ard Biesheuvel, Heiko Carstens) - Be a lot less permissive on weird (kernel address) uaccess faults on x86: BUG() when uaccess helpers fault on kernel addresses (Jann Horn) - macrofy x86 asm statements to un-confuse the GCC inliner. (Nadav Amit) - ... and a handful of other smaller changes as well" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits) locking/lockdep: Make global debug_locks* variables read-mostly locking/lockdep: Fix debug_locks off performance problem locking/pvqspinlock: Extend node size when pvqspinlock is configured locking/qspinlock_stat: Count instances of nested lock slowpaths locking/qspinlock, x86: Provide liveness guarantee x86/asm: 'Simplify' GEN_*_RMWcc() macros locking/qspinlock: Rework some comments locking/qspinlock: Re-order code locking/lockdep: Remove duplicated 'lock_class_ops' percpu array x86/defconfig: Enable CONFIG_USB_XHCI_HCD=y futex: Replace spin_is_locked() with lockdep locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs x86/cpufeature: Macrofy inline assembly code to work around GCC inlining bugs x86/extable: Macrofy inline assembly code to work around GCC inlining bugs x86/paravirt: Work around GCC inlining bugs when compiling paravirt ops x86/bug: Macrofy the BUG table section handling, to work around GCC inlining bugs x86/alternatives: Macrofy lock prefixes to work around GCC inlining bugs x86/refcount: Work around GCC inlining bug x86/objtool: Use asm macros to work around GCC inlining bugs ...
mrcsosa · Oct 23, 2018 · 0200fbd · 0200fbd
2 parents de3fbb2 + 01a14bd
commit 0200fbd
Show file tree

Hide file tree

Showing 95 changed files with 1,522 additions and 934 deletions.
diff --git a/Documentation/locking/lockstat.txt b/Documentation/locking/lockstat.txt
@@ -91,7 +91,7 @@ Look at the current lock statistics:
 07                         &mm->mmap_sem-R:            37            100           1.31      299502.61      325629.52        3256.30         212344       34316685           0.10        7744.91    95016910.20           2.77
 08                         ---------------
 09                           &mm->mmap_sem              1          [<ffffffff811502a7>] khugepaged_scan_mm_slot+0x57/0x280
-19                           &mm->mmap_sem             96          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
+10                           &mm->mmap_sem             96          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
 11                           &mm->mmap_sem             34          [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0
 12                           &mm->mmap_sem             17          [<ffffffff81127e71>] vm_munmap+0x41/0x80
 13                         ---------------

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
@@ -471,8 +471,7 @@ And a couple of implicit varieties:
      operations after the ACQUIRE operation will appear to happen after the
      ACQUIRE operation with respect to the other components of the system.
      ACQUIRE operations include LOCK operations and both smp_load_acquire()
-     and smp_cond_acquire() operations. The later builds the necessary ACQUIRE
-     semantics from relying on a control dependency and smp_rmb().
+     and smp_cond_load_acquire() operations.
 
      Memory operations that occur before an ACQUIRE operation may appear to
      happen after it completes.

diff --git a/Makefile b/Makefile
@@ -1073,7 +1073,7 @@ scripts: scripts_basic asm-generic gcc-plugins $(autoksyms_h)
 # version.h and scripts_basic is processed / created.
 
 # Listed in dependency order
-PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3
+PHONY += prepare archprepare macroprepare prepare0 prepare1 prepare2 prepare3
 
 # prepare3 is used to check if we are building in a separate output directory,
 # and if so do:
@@ -1096,7 +1096,9 @@ prepare2: prepare3 outputmakefile asm-generic
 prepare1: prepare2 $(version_h) $(autoksyms_h) include/generated/utsrelease.h
 	$(cmd_crmodverdir)
 
-archprepare: archheaders archscripts prepare1 scripts_basic
+macroprepare: prepare1 archmacros
+
+archprepare: archheaders archscripts macroprepare scripts_basic
 
 prepare0: archprepare gcc-plugins
 	$(Q)$(MAKE) $(build)=.
@@ -1164,6 +1166,9 @@ archheaders:
 PHONY += archscripts
 archscripts:
 
+PHONY += archmacros
+archmacros:
+
 PHONY += __headers
 __headers: $(version_h) scripts_basic uapi-asm-generic archheaders archscripts
 	$(Q)$(MAKE) $(build)=scripts build_unifdef

diff --git a/arch/Kconfig b/arch/Kconfig
@@ -359,6 +359,9 @@ config HAVE_PERF_USER_STACK_DUMP
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
+config HAVE_ARCH_JUMP_LABEL_RELATIVE
+	bool
+
 config HAVE_RCU_TABLE_FREE
 	bool
 

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
@@ -105,6 +105,7 @@ config ARM64
 	select HAVE_ARCH_BITREVERSE
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS

diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
@@ -26,41 +26,39 @@
 
 #define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
 
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key *key,
+					       bool branch)
 {
-	asm_volatile_goto("1: nop\n\t"
-		 ".pushsection __jump_table,  \"aw\"\n\t"
-		 ".align 3\n\t"
-		 ".quad 1b, %l[l_yes], %c0\n\t"
-		 ".popsection\n\t"
+	asm_volatile_goto(
+		"1:	nop					\n\t"
+		 "	.pushsection	__jump_table, \"aw\"	\n\t"
+		 "	.align		3			\n\t"
+		 "	.long		1b - ., %l[l_yes] - .	\n\t"
+		 "	.quad		%c0 - .			\n\t"
+		 "	.popsection				\n\t"
 		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes:
 	return true;
 }
 
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+						    bool branch)
 {
-	asm_volatile_goto("1: b %l[l_yes]\n\t"
-		 ".pushsection __jump_table,  \"aw\"\n\t"
-		 ".align 3\n\t"
-		 ".quad 1b, %l[l_yes], %c0\n\t"
-		 ".popsection\n\t"
+	asm_volatile_goto(
+		"1:	b		%l[l_yes]		\n\t"
+		 "	.pushsection	__jump_table, \"aw\"	\n\t"
+		 "	.align		3			\n\t"
+		 "	.long		1b - ., %l[l_yes] - .	\n\t"
+		 "	.quad		%c0 - .			\n\t"
+		 "	.popsection				\n\t"
 		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes:
 	return true;
 }
 
-typedef u64 jump_label_t;
-
-struct jump_entry {
-	jump_label_t code;
-	jump_label_t target;
-	jump_label_t key;
-};
-
 #endif  /* __ASSEMBLY__ */
 #endif	/* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
@@ -25,12 +25,12 @@
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	void *addr = (void *)entry->code;
+	void *addr = (void *)jump_entry_code(entry);
 	u32 insn;
 
 	if (type == JUMP_LABEL_JMP) {
-		insn = aarch64_insn_gen_branch_imm(entry->code,
-						   entry->target,
+		insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry),
+						   jump_entry_target(entry),
 						   AARCH64_INSN_BRANCH_NOLINK);
 	} else {
 		insn = aarch64_insn_gen_nop();

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
@@ -126,6 +126,7 @@ config S390
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER

diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
@@ -14,41 +14,33 @@
  * We use a brcl 0,2 instruction for jump labels at compile time so it
  * can be easily distinguished from a hotpatch generated instruction.
  */
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
-		".pushsection __jump_table, \"aw\"\n"
-		".balign 8\n"
-		".quad 0b, %l[label], %0\n"
-		".popsection\n"
-		: : "X" (&((char *)key)[branch]) : : label);
-
+	asm_volatile_goto("0:	brcl	0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
+			  ".pushsection __jump_table,\"aw\"\n"
+			  ".balign	8\n"
+			  ".long	0b-.,%l[label]-.\n"
+			  ".quad	%0-.\n"
+			  ".popsection\n"
+			  : : "X" (&((char *)key)[branch]) : : label);
 	return false;
 label:
 	return true;
 }
 
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 15, %l[label]\n"
-		".pushsection __jump_table, \"aw\"\n"
-		".balign 8\n"
-		".quad 0b, %l[label], %0\n"
-		".popsection\n"
-		: : "X" (&((char *)key)[branch]) : : label);
-
+	asm_volatile_goto("0:	brcl 15,%l[label]\n"
+			  ".pushsection __jump_table,\"aw\"\n"
+			  ".balign	8\n"
+			  ".long	0b-.,%l[label]-.\n"
+			  ".quad	%0-.\n"
+			  ".popsection\n"
+			  : : "X" (&((char *)key)[branch]) : : label);
 	return false;
 label:
 	return true;
 }
 
-typedef unsigned long jump_label_t;
-
-struct jump_entry {
-	jump_label_t code;
-	jump_label_t target;
-	jump_label_t key;
-};
-
 #endif  /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
@@ -33,13 +33,13 @@ static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn)
 {
 	/* brcl 15,offset */
 	insn->opcode = 0xc0f4;
-	insn->offset = (entry->target - entry->code) >> 1;
+	insn->offset = (jump_entry_target(entry) - jump_entry_code(entry)) >> 1;
 }
 
 static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
 			   struct insn *new)
 {
-	unsigned char *ipc = (unsigned char *)entry->code;
+	unsigned char *ipc = (unsigned char *)jump_entry_code(entry);
 	unsigned char *ipe = (unsigned char *)expected;
 	unsigned char *ipn = (unsigned char *)new;
 
@@ -59,6 +59,7 @@ static void __jump_label_transform(struct jump_entry *entry,
 				   enum jump_label_type type,
 				   int init)
 {
+	void *code = (void *)jump_entry_code(entry);
 	struct insn old, new;
 
 	if (type == JUMP_LABEL_JMP) {
@@ -69,13 +70,13 @@ static void __jump_label_transform(struct jump_entry *entry,
 		jump_label_make_nop(entry, &new);
 	}
 	if (init) {
-		if (memcmp((void *)entry->code, &orignop, sizeof(orignop)))
+		if (memcmp(code, &orignop, sizeof(orignop)))
 			jump_label_bug(entry, &orignop, &new);
 	} else {
-		if (memcmp((void *)entry->code, &old, sizeof(old)))
+		if (memcmp(code, &old, sizeof(old)))
 			jump_label_bug(entry, &old, &new);
 	}
-	s390_kernel_write((void *)entry->code, &new, sizeof(new));
+	s390_kernel_write(code, &new, sizeof(new));
 }
 
 static int __sm_arch_jump_label_transform(void *data)

diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
@@ -65,6 +65,7 @@ SECTIONS
 	__start_ro_after_init = .;
 	.data..ro_after_init : {
 		 *(.data..ro_after_init)
+		JUMP_TABLE_DATA
 	}
 	EXCEPTION_TABLE(16)
 	. = ALIGN(PAGE_SIZE);

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN			if X86_64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
@@ -193,7 +193,6 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
 asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
-asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
@@ -237,6 +236,13 @@ archscripts: scripts_basic
 archheaders:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
+archmacros:
+	$(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
+
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+export ASM_MACRO_FLAGS
+KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
+
 ###
 # Kernel objects
 

diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
@@ -247,6 +247,7 @@ CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
 CONFIG_USB_OHCI_HCD=y

diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
@@ -243,6 +243,7 @@ CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
 CONFIG_USB_OHCI_HCD=y

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
@@ -338,7 +338,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro CALL_enter_from_user_mode
 #ifdef CONFIG_CONTEXT_TRACKING
 #ifdef HAVE_JUMP_LABEL
-	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+	STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
 #endif
 	call enter_from_user_mode
 .Lafter_call_\@:

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
@@ -7,16 +7,24 @@
 #include <asm/asm.h>
 
 #ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-672:	lock
+.macro LOCK_PREFIX_HERE
 	.pushsection .smp_locks,"a"
 	.balign 4
-	.long 672b - .
+	.long 671f - .		# offset
 	.popsection
-	.endm
+671:
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+	LOCK_PREFIX_HERE
+	lock \insn
+.endm
 #else
-	.macro LOCK_PREFIX
-	.endm
+.macro LOCK_PREFIX_HERE
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+.endm
 #endif
 
 /*

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
@@ -31,15 +31,8 @@
  */
 
 #ifdef CONFIG_SMP
-#define LOCK_PREFIX_HERE \
-		".pushsection .smp_locks,\"a\"\n"	\
-		".balign 4\n"				\
-		".long 671f - .\n" /* offset */		\
-		".popsection\n"				\
-		"671:"
-
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
-
+#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t"
+#define LOCK_PREFIX "LOCK_PREFIX "
 #else /* ! CONFIG_SMP */
 #define LOCK_PREFIX_HERE ""
 #define LOCK_PREFIX ""