Merge tag 'v4.9.169' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into odroidn2-4.9.y

This is the 4.9.169 stable release

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 168
+SUBLEVEL = 169
 EXTRAVERSION =
 NAME = Roaring Lionus
 
@@ -511,7 +511,7 @@ endif
 ifeq ($(cc-name),clang)
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	:= --target=$(notdir $(CROSS_COMPILE:%-=%))
-GCC_TOOLCHAIN_DIR := $(dir $(shell which $(LD)))
+GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
 CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif

arch/arm/boot/dts/sama5d2-pinfunc.h

@@ -517,7 +517,7 @@
 #define PIN_PC9__GPIO			PINMUX_PIN(PIN_PC9, 0, 0)
 #define PIN_PC9__FIQ			PINMUX_PIN(PIN_PC9, 1, 3)
 #define PIN_PC9__GTSUCOMP		PINMUX_PIN(PIN_PC9, 2, 1)
-#define PIN_PC9__ISC_D0			PINMUX_PIN(PIN_PC9, 2, 1)
+#define PIN_PC9__ISC_D0			PINMUX_PIN(PIN_PC9, 3, 1)
 #define PIN_PC9__TIOA4			PINMUX_PIN(PIN_PC9, 4, 2)
 #define PIN_PC10			74
 #define PIN_PC10__GPIO			PINMUX_PIN(PIN_PC10, 0, 0)

arch/arm64/include/asm/futex.h

@@ -30,8 +30,8 @@ do {									\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
-"2:	stlxr	%w3, %w0, %2\n"						\
-"	cbnz	%w3, 1b\n"						\
+"2:	stlxr	%w0, %w3, %2\n"						\
+"	cbnz	%w0, 1b\n"						\
 "	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
@@ -50,29 +50,29 @@ do {									\
 static inline int
 arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int oldval = 0, ret, tmp;
+	int oldval, ret, tmp;
 
 	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w0, %w4",
+		__futex_atomic_op("mov	%w3, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w0, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w0, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w0, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w0, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:

arch/arm64/mm/init.c

@@ -271,7 +271,7 @@ void __init arm64_memblock_init(void)
 		 * memory spans, randomize the linear region as well.
 		 */
 		if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
-			range = range / ARM64_MEMSTART_ALIGN + 1;
+			range /= ARM64_MEMSTART_ALIGN;
 			memstart_addr -= ARM64_MEMSTART_ALIGN *
 					 ((range * memstart_offset_seed) >> 16);
 		}

arch/parisc/include/asm/processor.h

@@ -323,6 +323,8 @@ extern int _parisc_requires_coherency;
 #define parisc_requires_coherency()	(0)
 #endif
 
+extern int running_on_qemu;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_PARISC_PROCESSOR_H */

arch/parisc/kernel/process.c

@@ -206,12 +206,6 @@ void __cpuidle arch_cpu_idle(void)
 
 static int __init parisc_idle_init(void)
 {
-	const char *marker;
-
-	/* check QEMU/SeaBIOS marker in PAGE0 */
-	marker = (char *) &PAGE0->pad0;
-	running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
-
 	if (!running_on_qemu)
 		cpu_idle_poll_ctrl(1);
 

arch/parisc/kernel/setup.c

@@ -403,6 +403,9 @@ void start_parisc(void)
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
 
+	/* check QEMU/SeaBIOS marker in PAGE0 */
+	running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
+
 	cpunum = smp_processor_id();
 
 	set_firmware_width_unlocked();

arch/parisc/kernel/time.c

@@ -299,7 +299,7 @@ static int __init init_cr16_clocksource(void)
 	 * The cr16 interval timers are not syncronized across CPUs, so mark
 	 * them unstable and lower rating on SMP systems.
 	 */
-	if (num_online_cpus() > 1) {
+	if (num_online_cpus() > 1 && !running_on_qemu) {
 		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
 		clocksource_cr16.rating = 0;
 	}

arch/powerpc/Kconfig

@@ -128,7 +128,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
-	select GENERIC_CPU_VULNERABILITIES	if PPC_BOOK3S_64
+	select GENERIC_CPU_VULNERABILITIES	if PPC_BARRIER_NOSPEC
 	select GENERIC_TIME_VSYSCALL_OLD
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
@@ -164,6 +164,11 @@ config PPC
 	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_KERNEL_GZIP
 
+config PPC_BARRIER_NOSPEC
+    bool
+    default y
+    depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E
+
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
 

arch/powerpc/include/asm/asm-prototypes.h

@@ -121,4 +121,10 @@ extern s64 __ashrdi3(s64, int);
 extern int __cmpdi2(s64, s64);
 extern int __ucmpdi2(u64, u64);
 
+/* Patch sites */
+extern s32 patch__call_flush_count_cache;
+extern s32 patch__flush_count_cache_return;
+
+extern long flush_count_cache;
+
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/include/asm/barrier.h

@@ -77,6 +77,27 @@ do {									\
 
 #define smp_mb__before_spinlock()   smp_mb()
 
+#ifdef CONFIG_PPC_BOOK3S_64
+#define NOSPEC_BARRIER_SLOT   nop
+#elif defined(CONFIG_PPC_FSL_BOOK3E)
+#define NOSPEC_BARRIER_SLOT   nop; nop
+#endif
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+/*
+ * Prevent execution of subsequent instructions until preceding branches have
+ * been fully resolved and are no longer executing speculatively.
+ */
+#define barrier_nospec_asm NOSPEC_BARRIER_FIXUP_SECTION; NOSPEC_BARRIER_SLOT
+
+// This also acts as a compiler barrier due to the memory clobber.
+#define barrier_nospec() asm (stringify_in_c(barrier_nospec_asm) ::: "memory")
+
+#else /* !CONFIG_PPC_BARRIER_NOSPEC */
+#define barrier_nospec_asm
+#define barrier_nospec()
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
 #include <asm-generic/barrier.h>
 
 #endif /* _ASM_POWERPC_BARRIER_H */

arch/powerpc/include/asm/code-patching-asm.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+#ifndef _ASM_POWERPC_CODE_PATCHING_ASM_H
+#define _ASM_POWERPC_CODE_PATCHING_ASM_H
+
+/* Define a "site" that can be patched */
+.macro patch_site label name
+	.pushsection ".rodata"
+	.balign 4
+	.global \name
+\name:
+	.4byte	\label - .
+	.popsection
+.endm
+
+#endif /* _ASM_POWERPC_CODE_PATCHING_ASM_H */

arch/powerpc/include/asm/code-patching.h

@@ -28,6 +28,8 @@ unsigned int create_cond_branch(const unsigned int *addr,
 				unsigned long target, int flags);
 int patch_branch(unsigned int *addr, unsigned long target, int flags);
 int patch_instruction(unsigned int *addr, unsigned int instr);
+int patch_instruction_site(s32 *addr, unsigned int instr);
+int patch_branch_site(s32 *site, unsigned long target, int flags);
 
 int instr_is_relative_branch(unsigned int instr);
 int instr_is_relative_link_branch(unsigned int instr);

arch/powerpc/include/asm/feature-fixups.h

@@ -213,6 +213,25 @@ void setup_feature_keys(void);
 	FTR_ENTRY_OFFSET 951b-952b;			\
 	.popsection;
 
+#define NOSPEC_BARRIER_FIXUP_SECTION			\
+953:							\
+	.pushsection __barrier_nospec_fixup,"a";	\
+	.align 2;					\
+954:							\
+	FTR_ENTRY_OFFSET 953b-954b;			\
+	.popsection;
+
+#define START_BTB_FLUSH_SECTION			\
+955:							\
+
+#define END_BTB_FLUSH_SECTION			\
+956:							\
+	.pushsection __btb_flush_fixup,"a";	\
+	.align 2;							\
+957:						\
+	FTR_ENTRY_OFFSET 955b-957b;			\
+	FTR_ENTRY_OFFSET 956b-957b;			\
+	.popsection;
 
 #ifndef __ASSEMBLY__
 
@@ -220,6 +239,8 @@ extern long stf_barrier_fallback;
 extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
 extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
 extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
+extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
 
 #endif
 

arch/powerpc/include/asm/hvcall.h

@@ -316,10 +316,12 @@
 #define H_CPU_CHAR_BRANCH_HINTS_HONORED	(1ull << 58) // IBM bit 5
 #define H_CPU_CHAR_THREAD_RECONFIG_CTRL	(1ull << 57) // IBM bit 6
 #define H_CPU_CHAR_COUNT_CACHE_DISABLED	(1ull << 56) // IBM bit 7
+#define H_CPU_CHAR_BCCTR_FLUSH_ASSIST	(1ull << 54) // IBM bit 9
 
 #define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
 #define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1
 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ull << 61) // IBM bit 2
+#define H_CPU_BEHAV_FLUSH_COUNT_CACHE	(1ull << 58) // IBM bit 5
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>

arch/powerpc/include/asm/ppc_asm.h

@@ -437,7 +437,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 .machine push ;					\
 .machine "power4" ;				\
        lis     scratch,0x60000000@h;		\
-       dcbt    r0,scratch,0b01010;		\
+       dcbt    0,scratch,0b01010;		\
 .machine pop
 
 /*
@@ -780,4 +780,25 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 	.long 0x2400004c  /* rfid				*/
 #endif /* !CONFIG_PPC_BOOK3E */
 #endif /*  __ASSEMBLY__ */
+
+/*
+ * Helper macro for exception table entries
+ */
+#define EX_TABLE(_fault, _target)		\
+	stringify_in_c(.section __ex_table,"a";)\
+	stringify_in_c(.balign 4;)		\
+	stringify_in_c(.long (_fault) - . ;)	\
+	stringify_in_c(.long (_target) - . ;)	\
+	stringify_in_c(.previous)
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define BTB_FLUSH(reg)			\
+	lis reg,BUCSR_INIT@h;		\
+	ori reg,reg,BUCSR_INIT@l;	\
+	mtspr SPRN_BUCSR,reg;		\
+	isync;
+#else
+#define BTB_FLUSH(reg)
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
 #endif /* _ASM_POWERPC_PPC_ASM_H */

arch/powerpc/include/asm/security_features.h

@@ -22,6 +22,7 @@ enum stf_barrier_type {
 
 void setup_stf_barrier(void);
 void do_stf_barrier_fixups(enum stf_barrier_type types);
+void setup_count_cache_flush(void);
 
 static inline void security_ftr_set(unsigned long feature)
 {
@@ -59,6 +60,9 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Indirect branch prediction cache disabled
 #define SEC_FTR_COUNT_CACHE_DISABLED	0x0000000000000020ull
 
+// bcctr 2,0,0 triggers a hardware assisted count cache flush
+#define SEC_FTR_BCCTR_FLUSH_ASSIST	0x0000000000000800ull
+
 
 // Features indicating need for Spectre/Meltdown mitigations
 
@@ -74,6 +78,9 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Firmware configuration indicates user favours security over performance
 #define SEC_FTR_FAVOUR_SECURITY		0x0000000000000200ull
 
+// Software required to flush count cache on context switch
+#define SEC_FTR_FLUSH_COUNT_CACHE	0x0000000000000400ull
+
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \

arch/powerpc/include/asm/setup.h

@@ -8,6 +8,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex);
 
 extern unsigned int rtas_data;
 extern unsigned long long memory_limit;
+extern bool init_mem_is_free;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
@@ -50,6 +51,26 @@ enum l1d_flush_type {
 
 void setup_rfi_flush(enum l1d_flush_type, bool enable);
 void do_rfi_flush_fixups(enum l1d_flush_type types);
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+void setup_barrier_nospec(void);
+#else
+static inline void setup_barrier_nospec(void) { };
+#endif
+void do_barrier_nospec_fixups(bool enable);
+extern bool barrier_nospec_enabled;
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+void do_barrier_nospec_fixups_range(bool enable, void *start, void *end);
+#else
+static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { };
+#endif
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+void setup_spectre_v2(void);
+#else
+static inline void setup_spectre_v2(void) {};
+#endif
+void do_btb_flush_fixups(void);
 
 #endif /* !__ASSEMBLY__ */
 

arch/powerpc/include/asm/uaccess.h

@@ -269,6 +269,7 @@ do {								\
 	__chk_user_ptr(ptr);					\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
+	barrier_nospec();					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
@@ -280,8 +281,10 @@ do {								\
 	unsigned long  __gu_val = 0;					\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
 	might_fault();							\
-	if (access_ok(VERIFY_READ, __gu_addr, (size)))			\
+	if (access_ok(VERIFY_READ, __gu_addr, (size))) {		\
+		barrier_nospec();					\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
 	__gu_err;							\
 })
@@ -292,6 +295,7 @@ do {								\
 	unsigned long __gu_val;					\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
+	barrier_nospec();					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
@@ -348,15 +352,19 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
 
 		switch (n) {
 		case 1:
+			barrier_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret);
 			break;
 		case 2:
+			barrier_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret);
 			break;
 		case 4:
+			barrier_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret);
 			break;
 		case 8:
+			barrier_nospec();
 			__get_user_size(*(u64 *)to, from, 8, ret);
 			break;
 		}
@@ -366,6 +374,7 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
 
 	check_object_size(to, n, false);
 
+	barrier_nospec();
 	return __copy_tofrom_user((__force void __user *)to, from, n);
 }
 

arch/powerpc/kernel/Makefile

@@ -44,9 +44,10 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o security.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
+obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o

arch/powerpc/kernel/entry_32.S

@@ -34,6 +34,7 @@
 #include <asm/ftrace.h>
 #include <asm/ptrace.h>
 #include <asm/export.h>
+#include <asm/barrier.h>
 
 /*
  * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
@@ -347,6 +348,15 @@ syscall_dotrace_cont:
 	ori	r10,r10,sys_call_table@l
 	slwi	r0,r0,2
 	bge-	66f
+
+	barrier_nospec_asm
+	/*
+	 * Prevent the load of the handler below (based on the user-passed
+	 * system call number) being speculatively executed until the test
+	 * against NR_syscalls and branch to .66f above has
+	 * committed.
+	 */
+
 	lwzx	r10,r10,r0	/* Fetch system call handler [ptr] */
 	mtlr	r10
 	addi	r9,r1,STACK_FRAME_OVERHEAD

arch/powerpc/kernel/entry_64.S

@@ -26,6 +26,7 @@
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/thread_info.h>
+#include <asm/code-patching-asm.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/cputable.h>
@@ -38,6 +39,7 @@
 #include <asm/context_tracking.h>
 #include <asm/tm.h>
 #include <asm/ppc-opcode.h>
+#include <asm/barrier.h>
 #include <asm/export.h>
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/exception-64s.h>
@@ -78,6 +80,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
 	beq	2f			/* if from kernel mode */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+START_BTB_FLUSH_SECTION
+	BTB_FLUSH(r10)
+END_BTB_FLUSH_SECTION
+#endif
 	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
 2:	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
@@ -180,6 +187,15 @@ system_call:			/* label this so stack traces look sane */
 	clrldi	r8,r8,32
 15:
 	slwi	r0,r0,4
+
+	barrier_nospec_asm
+	/*
+	 * Prevent the load of the handler below (based on the user-passed
+	 * system call number) being speculatively executed until the test
+	 * against NR_syscalls and branch to .Lsyscall_enosys above has
+	 * committed.
+	 */
+
 	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
 	mtctr   r12
 	bctrl			/* Call handler */
@@ -473,6 +489,57 @@ _GLOBAL(ret_from_kernel_thread)
 	li	r3,0
 	b	.Lsyscall_exit
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
+#define FLUSH_COUNT_CACHE	\
+1:	nop;			\
+	patch_site 1b, patch__call_flush_count_cache
+
+
+#define BCCTR_FLUSH	.long 0x4c400420
+
+.macro nops number
+	.rept \number
+	nop
+	.endr
+.endm
+
+.balign 32
+.global flush_count_cache
+flush_count_cache:
+	/* Save LR into r9 */
+	mflr	r9
+
+	.rept 64
+	bl	.+4
+	.endr
+	b	1f
+	nops	6
+
+	.balign 32
+	/* Restore LR */
+1:	mtlr	r9
+	li	r9,0x7fff
+	mtctr	r9
+
+	BCCTR_FLUSH
+
+2:	nop
+	patch_site 2b patch__flush_count_cache_return
+
+	nops	3
+
+	.rept 278
+	.balign 32
+	BCCTR_FLUSH
+	nops	7
+	.endr
+
+	blr
+#else
+#define FLUSH_COUNT_CACHE
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -504,6 +571,8 @@ _GLOBAL(_switch)
 	std	r23,_CCR(r1)
 	std	r1,KSP(r3)	/* Set old stack pointer */
 
+	FLUSH_COUNT_CACHE
+
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all

arch/powerpc/kernel/exceptions-64e.S

@@ -295,7 +295,8 @@ ret_from_mc_except:
 	andi.	r10,r11,MSR_PR;		/* save stack pointer */	    \
 	beq	1f;			/* branch around if supervisor */   \
 	ld	r1,PACAKSAVE(r13);	/* get kernel stack coming from usr */\
-1:	cmpdi	cr1,r1,0;		/* check if SP makes sense */	    \
+1:	type##_BTB_FLUSH		\
+	cmpdi	cr1,r1,0;		/* check if SP makes sense */	    \
 	bge-	cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \
 	mfspr	r10,SPRN_##type##_SRR0;	/* read SRR0 before touching stack */
 
@@ -327,6 +328,30 @@ ret_from_mc_except:
 #define SPRN_MC_SRR0	SPRN_MCSRR0
 #define SPRN_MC_SRR1	SPRN_MCSRR1
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define GEN_BTB_FLUSH			\
+	START_BTB_FLUSH_SECTION		\
+		beq 1f;			\
+		BTB_FLUSH(r10)			\
+		1:		\
+	END_BTB_FLUSH_SECTION
+
+#define CRIT_BTB_FLUSH			\
+	START_BTB_FLUSH_SECTION		\
+		BTB_FLUSH(r10)		\
+	END_BTB_FLUSH_SECTION
+
+#define DBG_BTB_FLUSH CRIT_BTB_FLUSH
+#define MC_BTB_FLUSH CRIT_BTB_FLUSH
+#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH
+#else
+#define GEN_BTB_FLUSH
+#define CRIT_BTB_FLUSH
+#define DBG_BTB_FLUSH
+#define MC_BTB_FLUSH
+#define GDBELL_BTB_FLUSH
+#endif
+
 #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition)			    \
 	EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n))
 

arch/powerpc/kernel/head_booke.h

@@ -31,6 +31,16 @@
  */
 #define THREAD_NORMSAVE(offset)	(THREAD_NORMSAVES + (offset * 4))
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define BOOKE_CLEAR_BTB(reg)									\
+START_BTB_FLUSH_SECTION								\
+	BTB_FLUSH(reg)									\
+END_BTB_FLUSH_SECTION
+#else
+#define BOOKE_CLEAR_BTB(reg)
+#endif
+
+
 #define NORMAL_EXCEPTION_PROLOG(intno)						     \
 	mtspr	SPRN_SPRG_WSCRATCH0, r10;	/* save one register */	     \
 	mfspr	r10, SPRN_SPRG_THREAD;					     \
@@ -42,6 +52,7 @@
 	andi.	r11, r11, MSR_PR;	/* check whether user or kernel    */\
 	mr	r11, r1;						     \
 	beq	1f;							     \
+	BOOKE_CLEAR_BTB(r11)						\
 	/* if from user, start at top of this thread's kernel stack */       \
 	lwz	r11, THREAD_INFO-THREAD(r10);				     \
 	ALLOC_STACK_FRAME(r11, THREAD_SIZE);				     \
@@ -127,6 +138,7 @@
 	stw	r9,_CCR(r8);		/* save CR on stack		   */\
 	mfspr	r11,exc_level_srr1;	/* check whether user or kernel    */\
 	DO_KVM	BOOKE_INTERRUPT_##intno exc_level_srr1;		             \
+	BOOKE_CLEAR_BTB(r10)						\
 	andi.	r11,r11,MSR_PR;						     \
 	mfspr	r11,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
 	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\

arch/powerpc/kernel/head_fsl_booke.S

@@ -452,6 +452,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
 	DO_KVM	BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
 	mfspr	r10, SPRN_DEAR		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -546,6 +553,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
 	DO_KVM	BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
+
 	mfspr	r10, SPRN_SRR0		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the

arch/powerpc/kernel/module.c

@@ -72,7 +72,15 @@ int module_finalize(const Elf_Ehdr *hdr,
 		do_feature_fixups(powerpc_firmware_features,
 				  (void *)sect->sh_addr,
 				  (void *)sect->sh_addr + sect->sh_size);
-#endif
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+	sect = find_section(hdr, sechdrs, "__spec_barrier_fixup");
+	if (sect != NULL)
+		do_barrier_nospec_fixups_range(barrier_nospec_enabled,
+				  (void *)sect->sh_addr,
+				  (void *)sect->sh_addr + sect->sh_size);
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
 
 	sect = find_section(hdr, sechdrs, "__lwsync_fixup");
 	if (sect != NULL)

arch/powerpc/kernel/security.c

@@ -9,11 +9,121 @@
 #include <linux/device.h>
 #include <linux/seq_buf.h>
 
+#include <asm/asm-prototypes.h>
+#include <asm/code-patching.h>
+#include <asm/debug.h>
 #include <asm/security_features.h>
+#include <asm/setup.h>
 
 
 unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
 
+enum count_cache_flush_type {
+	COUNT_CACHE_FLUSH_NONE	= 0x1,
+	COUNT_CACHE_FLUSH_SW	= 0x2,
+	COUNT_CACHE_FLUSH_HW	= 0x4,
+};
+static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+
+bool barrier_nospec_enabled;
+static bool no_nospec;
+static bool btb_flush_enabled;
+#ifdef CONFIG_PPC_FSL_BOOK3E
+static bool no_spectrev2;
+#endif
+
+static void enable_barrier_nospec(bool enable)
+{
+	barrier_nospec_enabled = enable;
+	do_barrier_nospec_fixups(enable);
+}
+
+void setup_barrier_nospec(void)
+{
+	bool enable;
+
+	/*
+	 * It would make sense to check SEC_FTR_SPEC_BAR_ORI31 below as well.
+	 * But there's a good reason not to. The two flags we check below are
+	 * both are enabled by default in the kernel, so if the hcall is not
+	 * functional they will be enabled.
+	 * On a system where the host firmware has been updated (so the ori
+	 * functions as a barrier), but on which the hypervisor (KVM/Qemu) has
+	 * not been updated, we would like to enable the barrier. Dropping the
+	 * check for SEC_FTR_SPEC_BAR_ORI31 achieves that. The only downside is
+	 * we potentially enable the barrier on systems where the host firmware
+	 * is not updated, but that's harmless as it's a no-op.
+	 */
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
+
+	if (!no_nospec)
+		enable_barrier_nospec(enable);
+}
+
+static int __init handle_nospectre_v1(char *p)
+{
+	no_nospec = true;
+
+	return 0;
+}
+early_param("nospectre_v1", handle_nospectre_v1);
+
+#ifdef CONFIG_DEBUG_FS
+static int barrier_nospec_set(void *data, u64 val)
+{
+	switch (val) {
+	case 0:
+	case 1:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (!!val == !!barrier_nospec_enabled)
+		return 0;
+
+	enable_barrier_nospec(!!val);
+
+	return 0;
+}
+
+static int barrier_nospec_get(void *data, u64 *val)
+{
+	*val = barrier_nospec_enabled ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_barrier_nospec,
+			barrier_nospec_get, barrier_nospec_set, "%llu\n");
+
+static __init int barrier_nospec_debugfs_init(void)
+{
+	debugfs_create_file("barrier_nospec", 0600, powerpc_debugfs_root, NULL,
+			    &fops_barrier_nospec);
+	return 0;
+}
+device_initcall(barrier_nospec_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+static int __init handle_nospectre_v2(char *p)
+{
+	no_spectrev2 = true;
+
+	return 0;
+}
+early_param("nospectre_v2", handle_nospectre_v2);
+void setup_spectre_v2(void)
+{
+	if (no_spectrev2)
+		do_btb_flush_fixups();
+	else
+		btb_flush_enabled = true;
+}
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
+#ifdef CONFIG_PPC_BOOK3S_64
 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	bool thread_priv;
@@ -46,25 +156,39 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha
 
 	return sprintf(buf, "Vulnerable\n");
 }
+#endif
 
 ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR))
-		return sprintf(buf, "Not affected\n");
+	struct seq_buf s;
 
-	return sprintf(buf, "Vulnerable\n");
+	seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+	if (security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) {
+		if (barrier_nospec_enabled)
+			seq_buf_printf(&s, "Mitigation: __user pointer sanitization");
+		else
+			seq_buf_printf(&s, "Vulnerable");
+
+		if (security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31))
+			seq_buf_printf(&s, ", ori31 speculation barrier enabled");
+
+		seq_buf_printf(&s, "\n");
+	} else
+		seq_buf_printf(&s, "Not affected\n");
+
+	return s.len;
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	bool bcs, ccd, ori;
 	struct seq_buf s;
+	bool bcs, ccd;
 
 	seq_buf_init(&s, buf, PAGE_SIZE - 1);
 
 	bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED);
 	ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);
-	ori = security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31);
 
 	if (bcs || ccd) {
 		seq_buf_printf(&s, "Mitigation: ");
@@ -77,17 +201,23 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 
 		if (ccd)
 			seq_buf_printf(&s, "Indirect branch cache disabled");
-	} else
-		seq_buf_printf(&s, "Vulnerable");
+	} else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+		seq_buf_printf(&s, "Mitigation: Software count cache flush");
 
-	if (ori)
-		seq_buf_printf(&s, ", ori31 speculation barrier enabled");
+		if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
+			seq_buf_printf(&s, " (hardware accelerated)");
+	} else if (btb_flush_enabled) {
+		seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
+	} else {
+		seq_buf_printf(&s, "Vulnerable");
+	}
 
 	seq_buf_printf(&s, "\n");
 
 	return s.len;
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
 /*
  * Store-forwarding barrier support.
  */
@@ -235,3 +365,71 @@ static __init int stf_barrier_debugfs_init(void)
 }
 device_initcall(stf_barrier_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
+
+static void toggle_count_cache_flush(bool enable)
+{
+	if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+		patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP);
+		count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+		pr_info("count-cache-flush: software flush disabled.\n");
+		return;
+	}
+
+	patch_branch_site(&patch__call_flush_count_cache,
+			  (u64)&flush_count_cache, BRANCH_SET_LINK);
+
+	if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
+		count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
+		pr_info("count-cache-flush: full software flush sequence enabled.\n");
+		return;
+	}
+
+	patch_instruction_site(&patch__flush_count_cache_return, PPC_INST_BLR);
+	count_cache_flush_type = COUNT_CACHE_FLUSH_HW;
+	pr_info("count-cache-flush: hardware assisted flush sequence enabled\n");
+}
+
+void setup_count_cache_flush(void)
+{
+	toggle_count_cache_flush(true);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int count_cache_flush_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	toggle_count_cache_flush(enable);
+
+	return 0;
+}
+
+static int count_cache_flush_get(void *data, u64 *val)
+{
+	if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE)
+		*val = 0;
+	else
+		*val = 1;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
+			count_cache_flush_set, "%llu\n");
+
+static __init int count_cache_flush_debugfs_init(void)
+{
+	debugfs_create_file("count_cache_flush", 0600, powerpc_debugfs_root,
+			    NULL, &fops_count_cache_flush);
+	return 0;
+}
+device_initcall(count_cache_flush_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+#endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/kernel/setup-common.c

@@ -918,6 +918,9 @@ void __init setup_arch(char **cmdline_p)
 	if (ppc_md.setup_arch)
 		ppc_md.setup_arch();
 
+	setup_barrier_nospec();
+	setup_spectre_v2();
+
 	paging_init();
 
 	/* Initialize the MMU context management stuff. */

arch/powerpc/kernel/signal_64.c

@@ -746,12 +746,25 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 		if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
 					   &uc_transact->uc_mcontext))
 			goto badframe;
-	}
-	else
-	/* Fall through, for non-TM restore */
+	} else
 #endif
-	if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext))
-		goto badframe;
+	{
+		/*
+		 * Fall through, for non-TM restore
+		 *
+		 * Unset MSR[TS] on the thread regs since MSR from user
+		 * context does not have MSR active, and recheckpoint was
+		 * not called since restore_tm_sigcontexts() was not called
+		 * also.
+		 *
+		 * If not unsetting it, the code can RFID to userspace with
+		 * MSR[TS] set, but without CPU in the proper state,
+		 * causing a TM bad thing.
+		 */
+		current->thread.regs->msr &= ~MSR_TS_MASK;
+		if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext))
+			goto badframe;
+	}
 
 	if (restore_altstack(&uc->uc_stack))
 		goto badframe;

arch/powerpc/kernel/swsusp_asm64.S

@@ -179,7 +179,7 @@ nothing_to_copy:
 	sld	r3, r3, r0
 	li	r0, 0
 1:
-	dcbf	r0,r3
+	dcbf	0,r3
 	addi	r3,r3,0x20
 	bdnz	1b
 

arch/powerpc/kernel/vmlinux.lds.S

@@ -153,8 +153,25 @@ SECTIONS
 		*(__rfi_flush_fixup)
 		__stop___rfi_flush_fixup = .;
 	}
-#endif
+#endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+	. = ALIGN(8);
+	__spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) {
+		__start___barrier_nospec_fixup = .;
+		*(__barrier_nospec_fixup)
+		__stop___barrier_nospec_fixup = .;
+	}
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	. = ALIGN(8);
+	__spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) {
+		__start__btb_flush_fixup = .;
+		*(__btb_flush_fixup)
+		__stop__btb_flush_fixup = .;
+	}
+#endif
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes

arch/powerpc/kvm/bookehv_interrupts.S

@@ -75,6 +75,10 @@
 	PPC_LL	r1, VCPU_HOST_STACK(r4)
 	PPC_LL	r2, HOST_R2(r1)
 
+START_BTB_FLUSH_SECTION
+	BTB_FLUSH(r10)
+END_BTB_FLUSH_SECTION
+
 	mfspr	r10, SPRN_PID
 	lwz	r8, VCPU_HOST_PID(r4)
 	PPC_LL	r11, VCPU_SHARED(r4)

arch/powerpc/kvm/e500_emulate.c

@@ -277,6 +277,13 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va
 		vcpu->arch.pwrmgtcr0 = spr_val;
 		break;
 
+	case SPRN_BUCSR:
+		/*
+		 * If we are here, it means that we have already flushed the
+		 * branch predictor, so just return to guest.
+		 */
+		break;
+
 	/* extra exceptions */
 #ifdef CONFIG_SPE_POSSIBLE
 	case SPRN_IVOR32:

arch/powerpc/lib/code-patching.c

@@ -14,12 +14,20 @@
 #include <asm/page.h>
 #include <asm/code-patching.h>
 #include <asm/uaccess.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
 
 
 int patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", addr);
+		return 0;
+	}
+
 	__put_user_size(instr, addr, 4, err);
 	if (err)
 		return err;
@@ -32,6 +40,22 @@ int patch_branch(unsigned int *addr, unsigned long target, int flags)
 	return patch_instruction(addr, create_branch(addr, target, flags));
 }
 
+int patch_branch_site(s32 *site, unsigned long target, int flags)
+{
+	unsigned int *addr;
+
+	addr = (unsigned int *)((unsigned long)site + *site);
+	return patch_instruction(addr, create_branch(addr, target, flags));
+}
+
+int patch_instruction_site(s32 *site, unsigned int instr)
+{
+	unsigned int *addr;
+
+	addr = (unsigned int *)((unsigned long)site + *site);
+	return patch_instruction(addr, instr);
+}
+
 unsigned int create_branch(const unsigned int *addr,
 			   unsigned long target, int flags)
 {

arch/powerpc/lib/copypage_power7.S

@@ -45,13 +45,13 @@ _GLOBAL(copypage_power7)
 .machine push
 .machine "power4"
 	/* setup read stream 0  */
-	dcbt	r0,r4,0b01000  	/* addr from */
-	dcbt	r0,r7,0b01010   /* length and depth from */
+	dcbt	0,r4,0b01000  	/* addr from */
+	dcbt	0,r7,0b01010   /* length and depth from */
 	/* setup write stream 1 */
-	dcbtst	r0,r9,0b01000   /* addr to */
-	dcbtst	r0,r10,0b01010  /* length and depth to */
+	dcbtst	0,r9,0b01000   /* addr to */
+	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* all streams GO */
+	dcbt	0,r8,0b01010	/* all streams GO */
 .machine pop
 
 #ifdef CONFIG_ALTIVEC
@@ -83,7 +83,7 @@ _GLOBAL(copypage_power7)
 	li	r12,112
 
 	.align	5
-1:	lvx	v7,r0,r4
+1:	lvx	v7,0,r4
 	lvx	v6,r4,r6
 	lvx	v5,r4,r7
 	lvx	v4,r4,r8
@@ -92,7 +92,7 @@ _GLOBAL(copypage_power7)
 	lvx	v1,r4,r11
 	lvx	v0,r4,r12
 	addi	r4,r4,128
-	stvx	v7,r0,r3
+	stvx	v7,0,r3
 	stvx	v6,r3,r6
 	stvx	v5,r3,r7
 	stvx	v4,r3,r8

arch/powerpc/lib/copyuser_power7.S

@@ -327,13 +327,13 @@ err1;	stb	r0,0(r3)
 .machine push
 .machine "power4"
 	/* setup read stream 0 */
-	dcbt	r0,r6,0b01000   /* addr from */
-	dcbt	r0,r7,0b01010   /* length and depth from */
+	dcbt	0,r6,0b01000   /* addr from */
+	dcbt	0,r7,0b01010   /* length and depth from */
 	/* setup write stream 1 */
-	dcbtst	r0,r9,0b01000   /* addr to */
-	dcbtst	r0,r10,0b01010  /* length and depth to */
+	dcbtst	0,r9,0b01000   /* addr to */
+	dcbtst	0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* all streams GO */
+	dcbt	0,r8,0b01010	/* all streams GO */
 .machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
@@ -388,26 +388,26 @@ err3;	std	r0,0(r3)
 	li	r11,48
 
 	bf	cr7*4+3,5f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	addi	r4,r4,16
-err3;	stvx	v1,r0,r3
+err3;	stvx	v1,0,r3
 	addi	r3,r3,16
 
 5:	bf	cr7*4+2,6f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 err3;	lvx	v0,r4,r9
 	addi	r4,r4,32
-err3;	stvx	v1,r0,r3
+err3;	stvx	v1,0,r3
 err3;	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-err3;	lvx	v3,r0,r4
+err3;	lvx	v3,0,r4
 err3;	lvx	v2,r4,r9
 err3;	lvx	v1,r4,r10
 err3;	lvx	v0,r4,r11
 	addi	r4,r4,64
-err3;	stvx	v3,r0,r3
+err3;	stvx	v3,0,r3
 err3;	stvx	v2,r3,r9
 err3;	stvx	v1,r3,r10
 err3;	stvx	v0,r3,r11
@@ -433,7 +433,7 @@ err3;	stvx	v0,r3,r11
 	 */
 	.align	5
 8:
-err4;	lvx	v7,r0,r4
+err4;	lvx	v7,0,r4
 err4;	lvx	v6,r4,r9
 err4;	lvx	v5,r4,r10
 err4;	lvx	v4,r4,r11
@@ -442,7 +442,7 @@ err4;	lvx	v2,r4,r14
 err4;	lvx	v1,r4,r15
 err4;	lvx	v0,r4,r16
 	addi	r4,r4,128
-err4;	stvx	v7,r0,r3
+err4;	stvx	v7,0,r3
 err4;	stvx	v6,r3,r9
 err4;	stvx	v5,r3,r10
 err4;	stvx	v4,r3,r11
@@ -463,29 +463,29 @@ err4;	stvx	v0,r3,r16
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-err3;	lvx	v3,r0,r4
+err3;	lvx	v3,0,r4
 err3;	lvx	v2,r4,r9
 err3;	lvx	v1,r4,r10
 err3;	lvx	v0,r4,r11
 	addi	r4,r4,64
-err3;	stvx	v3,r0,r3
+err3;	stvx	v3,0,r3
 err3;	stvx	v2,r3,r9
 err3;	stvx	v1,r3,r10
 err3;	stvx	v0,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 err3;	lvx	v0,r4,r9
 	addi	r4,r4,32
-err3;	stvx	v1,r0,r3
+err3;	stvx	v1,0,r3
 err3;	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	addi	r4,r4,16
-err3;	stvx	v1,r0,r3
+err3;	stvx	v1,0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */
@@ -565,25 +565,25 @@ err3;	lvx	v0,0,r4
 	addi	r4,r4,16
 
 	bf	cr7*4+3,5f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 	addi	r3,r3,16
 	vor	v0,v1,v1
 
 5:	bf	cr7*4+2,6f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 err3;	lvx	v0,r4,r9
 	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 err3;	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-err3;	lvx	v3,r0,r4
+err3;	lvx	v3,0,r4
 	VPERM(v8,v0,v3,v16)
 err3;	lvx	v2,r4,r9
 	VPERM(v9,v3,v2,v16)
@@ -592,7 +592,7 @@ err3;	lvx	v1,r4,r10
 err3;	lvx	v0,r4,r11
 	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 err3;	stvx	v9,r3,r9
 err3;	stvx	v10,r3,r10
 err3;	stvx	v11,r3,r11
@@ -618,7 +618,7 @@ err3;	stvx	v11,r3,r11
 	 */
 	.align	5
 8:
-err4;	lvx	v7,r0,r4
+err4;	lvx	v7,0,r4
 	VPERM(v8,v0,v7,v16)
 err4;	lvx	v6,r4,r9
 	VPERM(v9,v7,v6,v16)
@@ -635,7 +635,7 @@ err4;	lvx	v1,r4,r15
 err4;	lvx	v0,r4,r16
 	VPERM(v15,v1,v0,v16)
 	addi	r4,r4,128
-err4;	stvx	v8,r0,r3
+err4;	stvx	v8,0,r3
 err4;	stvx	v9,r3,r9
 err4;	stvx	v10,r3,r10
 err4;	stvx	v11,r3,r11
@@ -656,7 +656,7 @@ err4;	stvx	v15,r3,r16
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-err3;	lvx	v3,r0,r4
+err3;	lvx	v3,0,r4
 	VPERM(v8,v0,v3,v16)
 err3;	lvx	v2,r4,r9
 	VPERM(v9,v3,v2,v16)
@@ -665,27 +665,27 @@ err3;	lvx	v1,r4,r10
 err3;	lvx	v0,r4,r11
 	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 err3;	stvx	v9,r3,r9
 err3;	stvx	v10,r3,r10
 err3;	stvx	v11,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 err3;	lvx	v0,r4,r9
 	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 err3;	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-err3;	lvx	v1,r0,r4
+err3;	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-err3;	stvx	v8,r0,r3
+err3;	stvx	v8,0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */

arch/powerpc/lib/feature-fixups.c

@@ -277,8 +277,101 @@ void do_rfi_flush_fixups(enum l1d_flush_type types)
 		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
 						: "unknown");
 }
+
+void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end)
+{
+	unsigned int instr, *dest;
+	long *start, *end;
+	int i;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	instr = 0x60000000; /* nop */
+
+	if (enable) {
+		pr_info("barrier-nospec: using ORI speculation barrier\n");
+		instr = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+		patch_instruction(dest, instr);
+	}
+
+	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
+}
+
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+void do_barrier_nospec_fixups(bool enable)
+{
+	void *start, *end;
+
+	start = PTRRELOC(&__start___barrier_nospec_fixup),
+	end = PTRRELOC(&__stop___barrier_nospec_fixup);
+
+	do_barrier_nospec_fixups_range(enable, start, end);
+}
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end)
+{
+	unsigned int instr[2], *dest;
+	long *start, *end;
+	int i;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	instr[0] = PPC_INST_NOP;
+	instr[1] = PPC_INST_NOP;
+
+	if (enable) {
+		pr_info("barrier-nospec: using isync; sync as speculation barrier\n");
+		instr[0] = PPC_INST_ISYNC;
+		instr[1] = PPC_INST_SYNC;
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+		patch_instruction(dest, instr[0]);
+		patch_instruction(dest + 1, instr[1]);
+	}
+
+	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
+}
+
+static void patch_btb_flush_section(long *curr)
+{
+	unsigned int *start, *end;
+
+	start = (void *)curr + *curr;
+	end = (void *)curr + *(curr + 1);
+	for (; start < end; start++) {
+		pr_devel("patching dest %lx\n", (unsigned long)start);
+		patch_instruction(start, PPC_INST_NOP);
+	}
+}
+
+void do_btb_flush_fixups(void)
+{
+	long *start, *end;
+
+	start = PTRRELOC(&__start__btb_flush_fixup);
+	end = PTRRELOC(&__stop__btb_flush_fixup);
+
+	for (; start < end; start += 2)
+		patch_btb_flush_section(start);
+}
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 {
 	long *start, *end;

arch/powerpc/lib/memcpy_power7.S

@@ -261,12 +261,12 @@ _GLOBAL(memcpy_power7)
 
 .machine push
 .machine "power4"
-	dcbt	r0,r6,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
+	dcbt	0,r6,0b01000
+	dcbt	0,r7,0b01010
+	dcbtst	0,r9,0b01000
+	dcbtst	0,r10,0b01010
 	eieio
-	dcbt	r0,r8,0b01010	/* GO */
+	dcbt	0,r8,0b01010	/* GO */
 .machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
@@ -321,26 +321,26 @@ _GLOBAL(memcpy_power7)
 	li	r11,48
 
 	bf	cr7*4+3,5f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	addi	r4,r4,16
-	stvx	v1,r0,r3
+	stvx	v1,0,r3
 	addi	r3,r3,16
 
 5:	bf	cr7*4+2,6f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	lvx	v0,r4,r9
 	addi	r4,r4,32
-	stvx	v1,r0,r3
+	stvx	v1,0,r3
 	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-	lvx	v3,r0,r4
+	lvx	v3,0,r4
 	lvx	v2,r4,r9
 	lvx	v1,r4,r10
 	lvx	v0,r4,r11
 	addi	r4,r4,64
-	stvx	v3,r0,r3
+	stvx	v3,0,r3
 	stvx	v2,r3,r9
 	stvx	v1,r3,r10
 	stvx	v0,r3,r11
@@ -366,7 +366,7 @@ _GLOBAL(memcpy_power7)
 	 */
 	.align	5
 8:
-	lvx	v7,r0,r4
+	lvx	v7,0,r4
 	lvx	v6,r4,r9
 	lvx	v5,r4,r10
 	lvx	v4,r4,r11
@@ -375,7 +375,7 @@ _GLOBAL(memcpy_power7)
 	lvx	v1,r4,r15
 	lvx	v0,r4,r16
 	addi	r4,r4,128
-	stvx	v7,r0,r3
+	stvx	v7,0,r3
 	stvx	v6,r3,r9
 	stvx	v5,r3,r10
 	stvx	v4,r3,r11
@@ -396,29 +396,29 @@ _GLOBAL(memcpy_power7)
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-	lvx	v3,r0,r4
+	lvx	v3,0,r4
 	lvx	v2,r4,r9
 	lvx	v1,r4,r10
 	lvx	v0,r4,r11
 	addi	r4,r4,64
-	stvx	v3,r0,r3
+	stvx	v3,0,r3
 	stvx	v2,r3,r9
 	stvx	v1,r3,r10
 	stvx	v0,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	lvx	v0,r4,r9
 	addi	r4,r4,32
-	stvx	v1,r0,r3
+	stvx	v1,0,r3
 	stvx	v0,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	addi	r4,r4,16
-	stvx	v1,r0,r3
+	stvx	v1,0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */
@@ -499,25 +499,25 @@ _GLOBAL(memcpy_power7)
 	addi	r4,r4,16
 
 	bf	cr7*4+3,5f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	addi	r3,r3,16
 	vor	v0,v1,v1
 
 5:	bf	cr7*4+2,6f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	lvx	v0,r4,r9
 	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 6:	bf	cr7*4+1,7f
-	lvx	v3,r0,r4
+	lvx	v3,0,r4
 	VPERM(v8,v0,v3,v16)
 	lvx	v2,r4,r9
 	VPERM(v9,v3,v2,v16)
@@ -526,7 +526,7 @@ _GLOBAL(memcpy_power7)
 	lvx	v0,r4,r11
 	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	stvx	v9,r3,r9
 	stvx	v10,r3,r10
 	stvx	v11,r3,r11
@@ -552,7 +552,7 @@ _GLOBAL(memcpy_power7)
 	 */
 	.align	5
 8:
-	lvx	v7,r0,r4
+	lvx	v7,0,r4
 	VPERM(v8,v0,v7,v16)
 	lvx	v6,r4,r9
 	VPERM(v9,v7,v6,v16)
@@ -569,7 +569,7 @@ _GLOBAL(memcpy_power7)
 	lvx	v0,r4,r16
 	VPERM(v15,v1,v0,v16)
 	addi	r4,r4,128
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	stvx	v9,r3,r9
 	stvx	v10,r3,r10
 	stvx	v11,r3,r11
@@ -590,7 +590,7 @@ _GLOBAL(memcpy_power7)
 	mtocrf	0x01,r6
 
 	bf	cr7*4+1,9f
-	lvx	v3,r0,r4
+	lvx	v3,0,r4
 	VPERM(v8,v0,v3,v16)
 	lvx	v2,r4,r9
 	VPERM(v9,v3,v2,v16)
@@ -599,27 +599,27 @@ _GLOBAL(memcpy_power7)
 	lvx	v0,r4,r11
 	VPERM(v11,v1,v0,v16)
 	addi	r4,r4,64
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	stvx	v9,r3,r9
 	stvx	v10,r3,r10
 	stvx	v11,r3,r11
 	addi	r3,r3,64
 
 9:	bf	cr7*4+2,10f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	lvx	v0,r4,r9
 	VPERM(v9,v1,v0,v16)
 	addi	r4,r4,32
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	stvx	v9,r3,r9
 	addi	r3,r3,32
 
 10:	bf	cr7*4+3,11f
-	lvx	v1,r0,r4
+	lvx	v1,0,r4
 	VPERM(v8,v0,v1,v16)
 	addi	r4,r4,16
-	stvx	v8,r0,r3
+	stvx	v8,0,r3
 	addi	r3,r3,16
 
 	/* Up to 15B to go */

arch/powerpc/lib/string_64.S

@@ -192,7 +192,7 @@ err1;	std	r0,8(r3)
 	mtctr	r6
 	mr	r8,r3
 14:
-err1;	dcbz	r0,r3
+err1;	dcbz	0,r3
 	add	r3,r3,r9
 	bdnz	14b
 

arch/powerpc/mm/mem.c

@@ -62,6 +62,7 @@
 #endif
 
 unsigned long long memory_limit;
+bool init_mem_is_free;
 
 #ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
@@ -396,6 +397,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 	ppc_md.progress = ppc_printk_progress;
+	init_mem_is_free = true;
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 

arch/powerpc/mm/tlb_low_64e.S

@@ -69,6 +69,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	std	r15,EX_TLB_R15(r12)
 	std	r10,EX_TLB_CR(r12)
 #ifdef CONFIG_PPC_FSL_BOOK3E
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
 	std	r7,EX_TLB_R7(r12)
 #endif
 	TLB_MISS_PROLOG_STATS

arch/powerpc/platforms/powernv/setup.c

@@ -77,6 +77,12 @@ static void init_fw_feat_flags(struct device_node *np)
 	if (fw_feature_is("enabled", "fw-count-cache-disabled", np))
 		security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED);
 
+	if (fw_feature_is("enabled", "fw-count-cache-flush-bcctr2,0,0", np))
+		security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST);
+
+	if (fw_feature_is("enabled", "needs-count-cache-flush-on-context-switch", np))
+		security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE);
+
 	/*
 	 * The features below are enabled by default, so we instead look to see
 	 * if firmware has *disabled* them, and clear them if so.
@@ -123,6 +129,7 @@ static void pnv_setup_rfi_flush(void)
 		  security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
 
 	setup_rfi_flush(type, enable);
+	setup_count_cache_flush();
 }
 
 static void __init pnv_setup_arch(void)

arch/powerpc/platforms/pseries/setup.c

@@ -475,6 +475,12 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
 	if (result->character & H_CPU_CHAR_COUNT_CACHE_DISABLED)
 		security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED);
 
+	if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST)
+		security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST);
+
+	if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE)
+		security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE);
+
 	/*
 	 * The features below are enabled by default, so we instead look to see
 	 * if firmware has *disabled* them, and clear them if so.
@@ -525,6 +531,7 @@ void pseries_setup_rfi_flush(void)
 		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR);
 
 	setup_rfi_flush(types, enable);
+	setup_count_cache_flush();
 }
 
 static void __init pSeries_setup_arch(void)

arch/x86/entry/vdso/Makefile

@@ -47,10 +47,8 @@ targets += $(vdso_img_sodbg)
 
 export CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-			-Wl,--no-undefined \
-			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
-			$(DISABLE_LTO)
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+			-z max-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
@@ -96,10 +94,8 @@ CFLAGS_REMOVE_vvar.o = -pg
 #
 
 CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
-			   -Wl,-soname=linux-vdso.so.1 \
-			   -Wl,-z,max-page-size=4096 \
-			   -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+			   -z max-page-size=4096
 
 # 64-bit objects to re-brand as x32
 vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
@@ -127,7 +123,7 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
 
 # This makes sure the $(obj) subdirectory exists even though vdso32/
 # is not a kbuild sub-make subdirectory.
@@ -165,9 +161,9 @@ $(obj)/vdso32.so.dbg: FORCE \
 # The DSO images are built using a special linker script.
 #
 quiet_cmd_vdso = VDSO    $@
-      cmd_vdso = $(CC) -nostdlib -o $@ \
+      cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
 VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \

arch/x86/include/asm/suspend_32.h

@@ -11,7 +11,13 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	u16 es, fs, gs, ss;
+	/*
+	 * On x86_32, all segment registers, with the possible exception of
+	 * gs, are saved at kernel entry in pt_regs.
+	 */
+#ifdef CONFIG_X86_32_LAZY_GS
+	u16 gs;
+#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;

arch/x86/include/asm/suspend_64.h

@@ -19,8 +19,20 @@
  */
 struct saved_context {
 	struct pt_regs regs;
-	u16 ds, es, fs, gs, ss;
-	unsigned long gs_base, gs_kernel_base, fs_base;
+
+	/*
+	 * User CS and SS are saved in current_pt_regs().  The rest of the
+	 * segment selectors need to be saved and restored here.
+	 */
+	u16 ds, es, fs, gs;
+
+	/*
+	 * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+	 * so we save them separately.  We save the kernelmode GSBASE to
+	 * restore percpu access after resume.
+	 */
+	unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
@@ -29,8 +41,7 @@ struct saved_context {
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
 	u16 idt_pad;
-	u16 idt_limit;
-	unsigned long idt_base;
+	struct desc_ptr idt;
 	u16 ldt;
 	u16 tss;
 	unsigned long tr;

arch/x86/include/asm/xen/hypercall.h

@@ -215,6 +215,9 @@ privcmd_call(unsigned call,
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
+	if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
+		return -EINVAL;
+
 	stac();
 	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM

arch/x86/power/cpu.c

@@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * descriptor tables
 	 */
-#ifdef CONFIG_X86_32
 	store_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
-	store_idt((struct desc_ptr *)&ctxt->idt_limit);
-#endif
+
 	/*
 	 * We save it here, but restore it only in the hibernate case.
 	 * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit
@@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * segment registers
 	 */
-#ifdef CONFIG_X86_32
-	savesegment(es, ctxt->es);
-	savesegment(fs, ctxt->fs);
+#ifdef CONFIG_X86_32_LAZY_GS
 	savesegment(gs, ctxt->gs);
-	savesegment(ss, ctxt->ss);
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
-	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
-	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
-	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
-	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+#endif
+#ifdef CONFIG_X86_64
+	savesegment(gs, ctxt->gs);
+	savesegment(fs, ctxt->fs);
+	savesegment(ds, ctxt->ds);
+	savesegment(es, ctxt->es);
 
 	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
-	rdmsrl(MSR_GS_BASE, ctxt->gs_base);
-	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
 	mtrr_save_fixed_ranges(NULL);
 
 	rdmsrl(MSR_EFER, ctxt->efer);
@@ -178,6 +170,9 @@ static void fix_processor_context(void)
 	write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
 	syscall_init();				/* This sets MSR_*STAR and related */
+#else
+	if (boot_cpu_has(X86_FEATURE_SEP))
+		enable_sep_cpu();
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_mm_ldt(current->active_mm);	/* This does lldt */
@@ -186,9 +181,12 @@ static void fix_processor_context(void)
 }
 
 /**
- *	__restore_processor_state - restore the contents of CPU registers saved
- *		by __save_processor_state()
- *	@ctxt - structure to load the registers contents from
+ * __restore_processor_state - restore the contents of CPU registers saved
+ *                             by __save_processor_state()
+ * @ctxt - structure to load the registers contents from
+ *
+ * The asm code that gets us here will have restored a usable GDT, although
+ * it will be pointing to the wrong alias.
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
@@ -211,46 +209,52 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	write_cr2(ctxt->cr2);
 	write_cr0(ctxt->cr0);
 
-	/*
-	 * now restore the descriptor tables to their proper values
-	 * ltr is done i fix_processor_context().
-	 */
-#ifdef CONFIG_X86_32
+	/* Restore the IDT. */
 	load_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
-	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
-#endif
 
 	/*
-	 * segment registers
+	 * Just in case the asm code got us here with the SS, DS, or ES
+	 * out of sync with the GDT, update them.
 	 */
-#ifdef CONFIG_X86_32
+	loadsegment(ss, __KERNEL_DS);
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+
+	/*
+	 * Restore percpu access.  Percpu access can happen in exception
+	 * handlers or in complicated helpers like load_gs_index().
+	 */
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+#else
+	loadsegment(fs, __KERNEL_PERCPU);
+	loadsegment(gs, __KERNEL_STACK_CANARY);
+#endif
+
+	/* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
+	fix_processor_context();
+
+	/*
+	 * Now that we have descriptor tables fully restored and working
+	 * exception handling, restore the usermode segments.
+	 */
+#ifdef CONFIG_X86_64
+	loadsegment(ds, ctxt->es);
 	loadsegment(es, ctxt->es);
 	loadsegment(fs, ctxt->fs);
-	loadsegment(gs, ctxt->gs);
-	loadsegment(ss, ctxt->ss);
+	load_gs_index(ctxt->gs);
 
 	/*
-	 * sysenter MSRs
+	 * Restore FSBASE and GSBASE after restoring the selectors, since
+	 * restoring the selectors clobbers the bases.  Keep in mind
+	 * that MSR_KERNEL_GS_BASE is horribly misnamed.
 	 */
-	if (boot_cpu_has(X86_FEATURE_SEP))
-		enable_sep_cpu();
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
-	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
-	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
-	load_gs_index(ctxt->gs);
-	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
-
 	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
-	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+#elif defined(CONFIG_X86_32_LAZY_GS)
+	loadsegment(gs, ctxt->gs);
 #endif
 
-	fix_processor_context();
-
 	do_fpu_end();
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();

arch/xtensa/kernel/stacktrace.c

@@ -272,10 +272,14 @@ static int return_address_cb(struct stackframe *frame, void *data)
 	return 1;
 }
 
+/*
+ * level == 0 is for the return address from the caller of this function,
+ * not from this function itself.
+ */
 unsigned long return_address(unsigned level)
 {
 	struct return_addr_data r = {
-		.skip = level + 1,
+		.skip = level,
 	};
 	walk_stackframe(stack_pointer(NULL), return_address_cb, &r);
 	return r.addr;

block/bio.c

@@ -1214,8 +1214,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+			if (!map_data)
+				__free_page(page);
 			break;
+		}
 
 		len -= bytes;
 		offset = 0;

drivers/char/Kconfig

@@ -377,7 +377,7 @@ config XILINX_HWICAP
 
 config R3964
 	tristate "Siemens R3964 line discipline"
-	depends on TTY
+	depends on TTY && BROKEN
 	---help---
 	  This driver allows synchronous communication with devices using the
 	  Siemens R3964 packet protocol. Unless you are dealing with special

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -959,6 +959,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1377,14 +1379,16 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, bnapi, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
 	prefetch(data);
 
 	agg_bufs = (le32_to_cpu(rxcmp->rx_cmp_misc_v1) & RX_CMP_AGG_BUFS) >>
@@ -1400,11 +1404,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(bnapi, cp_cons, agg_bufs);
 
 		rc = -EIO;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
 		goto next_rx;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en_common.c

@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -151,6 +156,7 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
 		if (err)
@@ -159,6 +165,7 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev)
 
 out:
 	kvfree(in);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }

drivers/net/usb/qmi_wwan.c

@@ -890,6 +890,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */

drivers/pci/quirks.c

@@ -3883,6 +3883,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9128,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130,
 			 quirk_dma_func1_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9170,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c47 + c57 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172,
 			 quirk_dma_func1_alias);

drivers/tty/Kconfig

@@ -455,4 +455,27 @@ config MIPS_EJTAG_FDC_KGDB_CHAN
 	help
 	  FDC channel number to use for KGDB.
 
+config LDISC_AUTOLOAD
+	bool "Automatically load TTY Line Disciplines"
+	default y
+	help
+	  Historically the kernel has always automatically loaded any
+	  line discipline that is in a kernel module when a user asks
+	  for it to be loaded with the TIOCSETD ioctl, or through other
+	  means.  This is not always the best thing to do on systems
+	  where you know you will not be using some of the more
+	  "ancient" line disciplines, so prevent the kernel from doing
+	  this unless the request is coming from a process with the
+	  CAP_SYS_MODULE permissions.
+
+	  Say 'Y' here if you trust your userspace users to do the right
+	  thing, or if you have only provided the line disciplines that
+	  you know you will be using, or if you wish to continue to use
+	  the traditional method of on-demand loading of these modules
+	  by any user.
+
+	  This functionality can be changed at runtime with the
+	  dev.tty.ldisc_autoload sysctl, this configuration option will
+	  only set the default value of this functionality.
+
 endif # TTY

drivers/tty/tty_io.c

@@ -520,6 +520,8 @@ void proc_clear_tty(struct task_struct *p)
 	tty_kref_put(tty);
 }
 
+extern void tty_sysctl_init(void);
+
 /**
  * proc_set_tty -  set the controlling terminal
  *
@@ -3705,6 +3707,7 @@ void console_sysfs_notify(void)
  */
 int __init tty_init(void)
 {
+	tty_sysctl_init();
 	cdev_init(&tty_cdev, &tty_fops);
 	if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) ||
 	    register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0)

drivers/tty/tty_ldisc.c

@@ -155,6 +155,13 @@ static void put_ldops(struct tty_ldisc_ops *ldops)
  *		takes tty_ldiscs_lock to guard against ldisc races
  */
 
+#if defined(CONFIG_LDISC_AUTOLOAD)
+	#define INITIAL_AUTOLOAD_STATE	1
+#else
+	#define INITIAL_AUTOLOAD_STATE	0
+#endif
+static int tty_ldisc_autoload = INITIAL_AUTOLOAD_STATE;
+
 static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc)
 {
 	struct tty_ldisc *ld;
@@ -169,6 +176,8 @@ static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc)
 	 */
 	ldops = get_ldops(disc);
 	if (IS_ERR(ldops)) {
+		if (!capable(CAP_SYS_MODULE) && !tty_ldisc_autoload)
+			return ERR_PTR(-EPERM);
 		request_module("tty-ldisc-%d", disc);
 		ldops = get_ldops(disc);
 		if (IS_ERR(ldops))
@@ -774,3 +783,41 @@ void tty_ldisc_deinit(struct tty_struct *tty)
 		tty_ldisc_put(tty->ldisc);
 	tty->ldisc = NULL;
 }
+
+static int zero;
+static int one = 1;
+static struct ctl_table tty_table[] = {
+	{
+		.procname	= "ldisc_autoload",
+		.data		= &tty_ldisc_autoload,
+		.maxlen		= sizeof(tty_ldisc_autoload),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static struct ctl_table tty_dir_table[] = {
+	{
+		.procname	= "tty",
+		.mode		= 0555,
+		.child		= tty_table,
+	},
+	{ }
+};
+
+static struct ctl_table tty_root_table[] = {
+	{
+		.procname	= "dev",
+		.mode		= 0555,
+		.child		= tty_dir_table,
+	},
+	{ }
+};
+
+void tty_sysctl_init(void)
+{
+	register_sysctl_table(tty_root_table);
+}

drivers/virtio/virtio_ring.c

@@ -1040,6 +1040,8 @@ struct virtqueue *vring_create_virtqueue(
 					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
 		if (queue)
 			break;
+		if (!may_reduce_num)
+			return NULL;
 	}
 
 	if (!num)

fs/btrfs/ioctl.c

@@ -385,6 +385,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/*
+	 * If the fs is mounted with nologreplay, which requires it to be
+	 * mounted in RO mode as well, we can not allow discard on free space
+	 * inside block groups, because log trees refer to extents that are not
+	 * pinned in a block group's free space cache (pinning the extents is
+	 * precisely the first phase of replaying a log tree).
+	 */
+	if (btrfs_test_opt(fs_info, NOLOGREPLAY))
+		return -EROFS;
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
 				dev_list) {

include/linux/bitrev.h

@@ -31,32 +31,32 @@ static inline u32 __bitrev32(u32 x)
 
 #define __constant_bitrev32(x)	\
 ({					\
-	u32 __x = x;			\
-	__x = (__x >> 16) | (__x << 16);	\
-	__x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8);	\
-	__x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4);	\
-	__x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2);	\
-	__x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1);	\
-	__x;								\
+	u32 ___x = x;			\
+	___x = (___x >> 16) | (___x << 16);	\
+	___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8);	\
+	___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4);	\
+	___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2);	\
+	___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1);	\
+	___x;								\
 })
 
 #define __constant_bitrev16(x)	\
 ({					\
-	u16 __x = x;			\
-	__x = (__x >> 8) | (__x << 8);	\
-	__x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4);	\
-	__x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2);	\
-	__x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1);	\
-	__x;								\
+	u16 ___x = x;			\
+	___x = (___x >> 8) | (___x << 8);	\
+	___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4);	\
+	___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2);	\
+	___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1);	\
+	___x;								\
 })
 
 #define __constant_bitrev8(x)	\
 ({					\
-	u8 __x = x;			\
-	__x = (__x >> 4) | (__x << 4);	\
-	__x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2);	\
-	__x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1);	\
-	__x;								\
+	u8 ___x = x;			\
+	___x = (___x >> 4) | (___x << 4);	\
+	___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2);	\
+	___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1);	\
+	___x;								\
 })
 
 #define bitrev32(x) \

include/linux/mlx5/driver.h

@@ -578,6 +578,8 @@ enum mlx5_pci_status {
 };
 
 struct mlx5_td {
+	/* protects tirs list changes while tirs refresh */
+	struct mutex     list_lock;
 	struct list_head tirs_list;
 	u32              tdn;
 };

include/linux/string.h

@@ -111,6 +111,9 @@ extern void * memscan(void *,int,__kernel_size_t);
 #ifndef __HAVE_ARCH_MEMCMP
 extern int memcmp(const void *,const void *,__kernel_size_t);
 #endif
+#ifndef __HAVE_ARCH_BCMP
+extern int bcmp(const void *,const void *,__kernel_size_t);
+#endif
 #ifndef __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif

include/linux/virtio_ring.h

@@ -62,7 +62,7 @@ struct virtqueue;
 /*
  * Creates a virtqueue and allocates the descriptor ring.  If
  * may_reduce_num is set, then this may allocate a smaller ring than
- * expected.  The caller should query virtqueue_get_ring_size to learn
+ * expected.  The caller should query virtqueue_get_vring_size to learn
  * the actual size of the ring.
  */
 struct virtqueue *vring_create_virtqueue(unsigned int index,

include/net/ip.h

@@ -581,7 +581,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 			     unsigned char __user *data, int optlen);
 void ip_options_undo(struct ip_options *opt);
 void ip_forward_options(struct sk_buff *skb);
-int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
 
 /*
  *	Functions provided by ip_sockglue.c

include/net/net_namespace.h

@@ -53,6 +53,7 @@ struct net {
 						 */
 	spinlock_t		rules_mod_lock;
 
+	u32			hash_mix;
 	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */

include/net/netns/hash.h

@@ -1,21 +1,10 @@
 #ifndef __NET_NS_HASH_H__
 #define __NET_NS_HASH_H__
 
-#include <asm/cache.h>
-
-struct net;
+#include <net/net_namespace.h>
 
 static inline u32 net_hash_mix(const struct net *net)
 {
-#ifdef CONFIG_NET_NS
-	/*
-	 * shift this right to eliminate bits, that are
-	 * always zeroed
-	 */
-
-	return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT);
-#else
-	return 0;
-#endif
+	return net->hash_mix;
 }
 #endif

kernel/irq/chip.c

@@ -1152,6 +1152,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
 int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
 {
 	data = data->parent_data;
+
+	if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+		return 0;
+
 	if (data->chip->irq_set_wake)
 		return data->chip->irq_set_wake(data, on);
 

kernel/sched/fair.c

@@ -8241,10 +8241,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last_h_load_update == now)
 		return;
 
-	cfs_rq->h_load_next = NULL;
+	WRITE_ONCE(cfs_rq->h_load_next, NULL);
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_load_next = se;
+		WRITE_ONCE(cfs_rq->h_load_next, se);
 		if (cfs_rq->last_h_load_update == now)
 			break;
 	}
@@ -8254,7 +8254,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 		cfs_rq->last_h_load_update = now;
 	}
 
-	while ((se = cfs_rq->h_load_next) != NULL) {
+	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
 		load = cfs_rq->h_load;
 		load = div64_ul(load * se->avg.load_avg,
 			cfs_rq_load_avg(cfs_rq) + 1);

lib/string.c

@@ -772,6 +772,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count)
 EXPORT_SYMBOL(memcmp);
 #endif
 
+#ifndef __HAVE_ARCH_BCMP
+/**
+ * bcmp - returns 0 if and only if the buffers have identical contents.
+ * @a: pointer to first buffer.
+ * @b: pointer to second buffer.
+ * @len: size of buffers.
+ *
+ * The sign or magnitude of a non-zero return value has no particular
+ * meaning, and architectures may implement their own more efficient bcmp(). So
+ * while this particular implementation is a simple (tail) call to memcmp, do
+ * not rely on anything but whether the return value is zero or non-zero.
+ */
+#undef bcmp
+int bcmp(const void *a, const void *b, size_t len)
+{
+	return memcmp(a, b, len);
+}
+EXPORT_SYMBOL(bcmp);
+#endif
+
 #ifndef __HAVE_ARCH_MEMSCAN
 /**
  * memscan - Find a character in an area of memory.

net/core/ethtool.c

@@ -1801,17 +1801,22 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
-	if (!data)
-		return -ENOMEM;
+	if (gstrings.len) {
+		data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
+		if (!data)
+			return -ENOMEM;
 
-	__ethtool_get_strings(dev, gstrings.string_set, data);
+		__ethtool_get_strings(dev, gstrings.string_set, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
 		goto out;
 	useraddr += sizeof(gstrings);
-	if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
+	if (gstrings.len &&
+	    copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
 		goto out;
 	ret = 0;
 
@@ -1899,17 +1904,21 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = kmalloc(n_stats * sizeof(u64), GFP_USER);
-	if (!data)
-		return -ENOMEM;
+	if (n_stats) {
+		data = kmalloc(n_stats * sizeof(u64), GFP_USER);
+		if (!data)
+			return -ENOMEM;
 
-	ops->get_ethtool_stats(dev, &stats, data);
+		ops->get_ethtool_stats(dev, &stats, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
 		goto out;
 	useraddr += sizeof(stats);
-	if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64)))
+	if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64)))
 		goto out;
 	ret = 0;
 
@@ -1938,19 +1947,23 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = kmalloc_array(n_stats, sizeof(u64), GFP_USER);
-	if (!data)
-		return -ENOMEM;
+	if (n_stats) {
+		data = kmalloc_array(n_stats, sizeof(u64), GFP_USER);
+		if (!data)
+			return -ENOMEM;
 
-	mutex_lock(&phydev->lock);
-	phydev->drv->get_stats(phydev, &stats, data);
-	mutex_unlock(&phydev->lock);
+		mutex_lock(&phydev->lock);
+		phydev->drv->get_stats(phydev, &stats, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
 		goto out;
 	useraddr += sizeof(stats);
-	if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64)))
+	if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64)))
 		goto out;
 	ret = 0;
 

net/core/net_namespace.c

@@ -282,6 +282,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 
 	atomic_set(&net->count, 1);
 	atomic_set(&net->passive, 1);
+	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);

net/ipv4/ip_input.c

@@ -259,11 +259,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -299,7 +298,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -361,7 +360,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);

net/ipv4/ip_options.c

@@ -614,7 +614,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -649,7 +649,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);

net/ipv4/tcp_dctcp.c

@@ -66,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -211,21 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
+static void dctcp_react_to_loss(struct sock *sk)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
 static void dctcp_state(struct sock *sk, u8 new_state)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
-
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -237,6 +234,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;

net/ipv6/ip6_output.c

@@ -601,7 +601,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
-	unsigned int mtu, hlen, left, len;
+	unsigned int mtu, hlen, left, len, nexthdr_offset;
 	int hroom, troom;
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
@@ -612,6 +612,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		goto fail;
 	hlen = err;
 	nexthdr = *prevhdr;
+	nexthdr_offset = prevhdr - skb_network_header(skb);
 
 	mtu = ip6_skb_dst_mtu(skb);
 
@@ -646,6 +647,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	    (err = skb_checksum_help(skb)))
 		goto fail;
 
+	prevhdr = skb_network_header(skb) + nexthdr_offset;
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		int first_len = skb_pagelen(skb);

net/ipv6/ip6_tunnel.c

@@ -634,7 +634,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 					   IPPROTO_IPIP,
 					   RT_TOS(eiph->tos), 0);
 		if (IS_ERR(rt) ||
-		    rt->dst.dev->type != ARPHRD_TUNNEL) {
+		    rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
 			goto out;
@@ -644,7 +644,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		ip_rt_put(rt);
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
 				   skb2->dev) ||
-		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
 			goto out;
 	}
 

net/ipv6/sit.c

@@ -661,6 +661,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
 			goto out;
 
+		/* skb can be uncloned in iptunnel_pull_header, so
+		 * old iph is no longer valid
+		 */
+		iph = (const struct iphdr *)skb_mac_header(skb);
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
 			if (log_ecn_error)

net/kcm/kcmsock.c

@@ -2058,14 +2058,14 @@ static int __init kcm_init(void)
 	if (err)
 		goto fail;
 
-	err = sock_register(&kcm_family_ops);
-	if (err)
-		goto sock_register_fail;
-
 	err = register_pernet_device(&kcm_net_ops);
 	if (err)
 		goto net_ops_fail;
 
+	err = sock_register(&kcm_family_ops);
+	if (err)
+		goto sock_register_fail;
+
 	err = kcm_proc_init();
 	if (err)
 		goto proc_init_fail;
@@ -2073,12 +2073,12 @@ static int __init kcm_init(void)
 	return 0;
 
 proc_init_fail:
-	unregister_pernet_device(&kcm_net_ops);
-
-net_ops_fail:
 	sock_unregister(PF_KCM);
 
 sock_register_fail:
+	unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
 	proto_unregister(&kcm_proto);
 
 fail:
@@ -2094,8 +2094,8 @@ fail:
 static void __exit kcm_exit(void)
 {
 	kcm_proc_exit();
-	unregister_pernet_device(&kcm_net_ops);
 	sock_unregister(PF_KCM);
+	unregister_pernet_device(&kcm_net_ops);
 	proto_unregister(&kcm_proto);
 	destroy_workqueue(kcm_wq);
 

net/openvswitch/flow_netlink.c

@@ -1853,14 +1853,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	struct sw_flow_actions *acts;
 	int new_acts_size;
-	int req_size = NLA_ALIGN(attr_len);
+	size_t req_size = NLA_ALIGN(attr_len);
 	int next_offset = offsetof(struct sw_flow_actions, actions) +
 					(*sfa)->actions_len;
 
 	if (req_size <= (ksize(*sfa) - next_offset))
 		goto out;
 
-	new_acts_size = ksize(*sfa) * 2;
+	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
 		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {

net/rds/tcp.c

@@ -527,7 +527,7 @@ static void rds_tcp_kill_sock(struct net *net)
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
 		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
-		if (net != c_net || !tc->t_sock)
+		if (net != c_net)
 			continue;
 		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
 			list_move_tail(&tc->t_tcp_node, &tmp_list);

net/sctp/protocol.c

@@ -600,6 +600,7 @@ out:
 static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 {
 	/* No address mapping for V4 sockets */
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 	return sizeof(struct sockaddr_in);
 }
 

sound/core/seq/seq_clientmgr.c

@@ -1249,7 +1249,7 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client,
 
 	/* fill the info fields */
 	if (client_info->name[0])
-		strlcpy(client->name, client_info->name, sizeof(client->name));
+		strscpy(client->name, client_info->name, sizeof(client->name));
 
 	client->filter = client_info->filter;
 	client->event_lost = client_info->event_lost;
@@ -1527,7 +1527,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg)
 	/* set queue name */
 	if (!info->name[0])
 		snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue);
-	strlcpy(q->name, info->name, sizeof(q->name));
+	strscpy(q->name, info->name, sizeof(q->name));
 	snd_use_lock_free(&q->use_lock);
 
 	return 0;
@@ -1589,7 +1589,7 @@ static int snd_seq_ioctl_set_queue_info(struct snd_seq_client *client,
 		queuefree(q);
 		return -EPERM;
 	}
-	strlcpy(q->name, info->name, sizeof(q->name));
+	strscpy(q->name, info->name, sizeof(q->name));
 	queuefree(q);
 
 	return 0;

sound/soc/fsl/fsl_esai.c

@@ -59,6 +59,8 @@ struct fsl_esai {
 	u32 fifo_depth;
 	u32 slot_width;
 	u32 slots;
+	u32 tx_mask;
+	u32 rx_mask;
 	u32 hck_rate[2];
 	u32 sck_rate[2];
 	bool hck_dir[2];
@@ -359,21 +361,13 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask,
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR,
 			   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
 
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask));
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB,
-			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask));
-
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
 			   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
 
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask));
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB,
-			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
-
 	esai_priv->slot_width = slot_width;
 	esai_priv->slots = slots;
+	esai_priv->tx_mask = tx_mask;
+	esai_priv->rx_mask = rx_mask;
 
 	return 0;
 }
@@ -594,6 +588,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u8 i, channels = substream->runtime->channels;
 	u32 pins = DIV_ROUND_UP(channels, esai_priv->slots);
+	u32 mask;
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -606,15 +601,38 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 		for (i = 0; tx && i < channels; i++)
 			regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);
 
+		/*
+		 * When set the TE/RE in the end of enablement flow, there
+		 * will be channel swap issue for multi data line case.
+		 * In order to workaround this issue, we switch the bit
+		 * enablement sequence to below sequence
+		 * 1) clear the xSMB & xSMA: which is done in probe and
+		 *                           stop state.
+		 * 2) set TE/RE
+		 * 3) set xSMB
+		 * 4) set xSMA:  xSMA is the last one in this flow, which
+		 *               will trigger esai to start.
+		 */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
 				   tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK,
 				   tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins));
+		mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask;
+
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+				   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask));
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+				   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask));
+
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
 				   tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0);
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+				   ESAI_xSMA_xS_MASK, 0);
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+				   ESAI_xSMB_xS_MASK, 0);
 
 		/* Disable and reset FIFO */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx),
@@ -904,6 +922,15 @@ static int fsl_esai_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	esai_priv->tx_mask = 0xFFFFFFFF;
+	esai_priv->rx_mask = 0xFFFFFFFF;
+
+	/* Clear the TSMA, TSMB, RSMA, RSMB */
+	regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0);
+
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component,
 					      &fsl_esai_dai, 1);
 	if (ret) {