Linux 4.2

Commit cf736ea6f9 ("thermal: power_allocator: do not use devm*
interfaces") forgot to change a devm_kcalloc() to just kcalloc(), but
it's corresponding devm_kfree() was changed to kfree().  Allocate with
kcalloc() to match the kfree().

Fixes: cf736ea6f9 ("thermal: power_allocator: do not use devm* interfaces")
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Eduardo Valentin <edubezval@gmail.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

.get_maintainer.ignore

@@ -0,0 +1 @@
+Christoph Hellwig <hch@lst.de>

.mailmap

@@ -17,6 +17,7 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
 Andreas Herrmann <aherrman@de.ibm.com>
+Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>

Documentation/devicetree/bindings/arm/cpus.txt

@@ -199,6 +199,7 @@ nodes to be present and contain the properties described below.
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
 			    "rockchip,rk3066-smp"
+			    "ste,dbx500-smp"
 
 	- cpu-release-addr
 		Usage: required for systems that have an "enable-method"

Documentation/devicetree/bindings/phy/ti-phy.txt

@@ -82,6 +82,9 @@ Optional properties:
  - id: If there are multiple instance of the same type, in order to
    differentiate between each instance "id" can be used (e.g., multi-lane PCIe
    PHY). If "id" is not provided, it is set to default value of '1'.
+ - syscon-pllreset: Handle to system control region that contains the
+   CTRL_CORE_SMA_SW_0 register and register offset to the CTRL_CORE_SMA_SW_0
+   register that contains the SATA_PLL_SOFT_RESET bit. Only valid for sata_phy.
 
 This is usually a subnode of ocp2scp to which it is connected.
 
@@ -100,3 +103,16 @@ usb3phy@4a084400 {
 			"sysclk",
 			"refclk";
 };
+
+sata_phy: phy@4A096000 {
+	compatible = "ti,phy-pipe3-sata";
+	reg = <0x4A096000 0x80>, /* phy_rx */
+	      <0x4A096400 0x64>, /* phy_tx */
+	      <0x4A096800 0x40>; /* pll_ctrl */
+	reg-names = "phy_rx", "phy_tx", "pll_ctrl";
+	ctrl-module = <&omap_control_sata>;
+	clocks = <&sys_clkin1>, <&sata_ref_clk>;
+	clock-names = "sysclk", "refclk";
+	syscon-pllreset = <&scm_conf 0x3fc>;
+	#phy-cells = <0>;
+};

Documentation/input/alps.txt

@@ -119,8 +119,10 @@ ALPS Absolute Mode - Protocol Version 2
  byte 5:  0   z6   z5   z4   z3   z2   z1   z0
 
 Protocol Version 2 DualPoint devices send standard PS/2 mouse packets for
-the DualPoint Stick. For non interleaved dualpoint devices the pointingstick
-buttons get reported separately in the PSM, PSR and PSL bits.
+the DualPoint Stick. The M, R and L bits signal the combined status of both
+the pointingstick and touchpad buttons, except for Dell dualpoint devices
+where the pointingstick buttons get reported separately in the PSM, PSR
+and PSL bits.
 
 Dualpoint device -- interleaved packet format
 ---------------------------------------------

MAINTAINERS

@@ -3587,6 +3587,15 @@ S:	Maintained
 F:	drivers/gpu/drm/rockchip/
 F:	Documentation/devicetree/bindings/video/rockchip*
 
+DRM DRIVERS FOR STI
+M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
+M:	Vincent Abriou <vincent.abriou@st.com>
+L:	dri-devel@lists.freedesktop.org
+T:	git http://git.linaro.org/people/benjamin.gaignard/kernel.git
+S:	Maintained
+F:	drivers/gpu/drm/sti
+F:	Documentation/devicetree/bindings/gpu/st,stih4xx.txt
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -5840,6 +5849,7 @@ S:	Odd Fixes
 
 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
 M:	"J. Bruce Fields" <bfields@fieldses.org>
+M:	Jeff Layton <jlayton@poochiereds.net>
 L:	linux-nfs@vger.kernel.org
 W:	http://nfs.sourceforge.net/
 S:	Supported

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION =
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -597,6 +597,11 @@ endif # $(dot-config)
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
+# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
+# values of the respective KBUILD_* variables
+ARCH_CPPFLAGS :=
+ARCH_AFLAGS :=
+ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
@@ -848,10 +853,10 @@ export mod_strip_cmd
 mod_compress_cmd = true
 ifdef CONFIG_MODULE_COMPRESS
   ifdef CONFIG_MODULE_COMPRESS_GZIP
-    mod_compress_cmd = gzip -n
+    mod_compress_cmd = gzip -n -f
   endif # CONFIG_MODULE_COMPRESS_GZIP
   ifdef CONFIG_MODULE_COMPRESS_XZ
-    mod_compress_cmd = xz
+    mod_compress_cmd = xz -f
   endif # CONFIG_MODULE_COMPRESS_XZ
 endif # CONFIG_MODULE_COMPRESS
 export mod_compress_cmd

arch/arc/Kconfig

@@ -313,11 +313,11 @@ config ARC_PAGE_SIZE_8K
 
 config ARC_PAGE_SIZE_16K
 	bool "16KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
 
@@ -365,6 +365,11 @@ config ARC_HAS_LLSC
 	default y
 	depends on !ARC_CANT_LLSC
 
+config ARC_STAR_9000923308
+	bool "Workaround for llock/scond livelock"
+	default y
+	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
+
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
@@ -379,6 +384,10 @@ config ARC_HAS_LL64
 	  dest operands with 2 possible source operands.
 	default y
 
+config ARC_HAS_DIV_REM
+	bool "Insn: div, divu, rem, remu"
+	default y
+
 config ARC_HAS_RTC
 	bool "Local 64-bit r/o cycle counter"
 	default n

arch/arc/Makefile

@@ -36,8 +36,16 @@ cflags-$(atleast_gcc44)			+= -fsection-anchors
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 
+ifdef CONFIG_ISA_ARCV2
+
 ifndef CONFIG_ARC_HAS_LL64
-cflags-$(CONFIG_ISA_ARCV2)		+= -mno-ll64
+cflags-y				+= -mno-ll64
+endif
+
+ifndef CONFIG_ARC_HAS_DIV_REM
+cflags-y				+= -mno-div-rem
+endif
+
 endif
 
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables

arch/arc/include/asm/arcregs.h

@@ -89,11 +89,10 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-
+#define AUX_NON_VOL		0x5e
 
 /*
  * Floating Pt Registers
@@ -240,9 +239,9 @@ struct bcr_extn_xymem {
 
 struct bcr_perip {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, pad:8;
+	unsigned int start:8, pad2:8, sz:8, ver:8;
 #else
-	unsigned int pad:8, sz:8, pad2:8, start:8;
+	unsigned int ver:8, sz:8, pad2:8, start:8;
 #endif
 };
 

arch/arc/include/asm/atomic.h

@@ -23,33 +23,60 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-#ifdef CONFIG_ISA_ARCV2
-#define PREFETCHW	"	prefetchw   [%1]	\n"
-#else
-#define PREFETCHW
+#ifdef CONFIG_ARC_STAR_9000923308
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay = 1, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bz	4f			\n"				\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"4: ; --- success ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
+
+#else	/* !CONFIG_ARC_STAR_9000923308 */
+
+#define SCOND_FAIL_RETRY_VAR_DEF
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bnz     1b			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS
+
 #endif
 
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -58,19 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	smp_mb();							\
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)							\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val)						\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 									\
 	smp_mb();							\
 									\
-	return temp;							\
+	return val;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -150,6 +179,9 @@ ATOMIC_OP(and, &=, and)
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
 
 /**
  * __atomic_add_unless - add unless the number is a given value

arch/arc/include/asm/ptrace.h

@@ -20,20 +20,20 @@
 struct pt_regs {
 
 	/* Real registers */
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long lp_start, lp_end, lp_count;
+	unsigned long lp_start, lp_end, lp_count;
 
-	long status32;	/* status32_l1, status32_l2, erstatus */
-	long ret;	/* ilink1, ilink2 or eret */
-	long blink;
-	long fp;
-	long r26;	/* gp */
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
 
-	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
 
-	long sp;	/* user/kernel sp depending on where we came from  */
-	long orig_r0;
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
 
 	/*
 	 * To distinguish bet excp, syscall, irq
@@ -55,13 +55,13 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long user_r25;
+	unsigned long user_r25;
 };
 #else
 
 struct pt_regs {
 
-	long orig_r0;
+	unsigned long orig_r0;
 
 	union {
 		struct {
@@ -76,26 +76,26 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long user_r25;
+	unsigned long user_r25;
 
-	long r26;	/* gp */
-	long fp;
-	long sp;	/* user/kernel sp depending on where we came from  */
+	unsigned long r26;	/* gp */
+	unsigned long fp;
+	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	long r12;
+	unsigned long r12;
 
 	/*------- Below list auto saved by h/w -----------*/
-	long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
 
-	long blink;
-	long lp_end, lp_start, lp_count;
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
 
-	long ei, ldi, jli;
+	unsigned long ei, ldi, jli;
 
-	long ret;
-	long status32;
+	unsigned long ret;
+	unsigned long status32;
 };
 
 #endif
@@ -103,10 +103,10 @@ struct pt_regs {
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
+#define instruction_pointer(regs)	((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */
@@ -142,7 +142,7 @@ struct callee_regs {
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	return regs->r0;
+	return (long)regs->r0;
 }
 
 #endif /* !__ASSEMBLY__ */

arch/arc/include/asm/spinlock.h

@@ -18,9 +18,518 @@
 #define arch_spin_unlock_wait(x) \
 	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
+/*
+ * A normal LLOCK/SCOND based system, w/o need for livelock workaround
+ */
+#ifndef CONFIG_ARC_STAR_9000923308
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+#else	/* CONFIG_ARC_STAR_9000923308 */
+
+/*
+ * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
+ * coherency transactions in the SCU. The exclusive line state keeps rotating
+ * among contenting cores leading to a never ending cycle. So break the cycle
+ * by deferring the retry of failed exclusive access (SCOND). The actual delay
+ * needed is function of number of contending cores as well as the unrelated
+ * coherency traffic from other cores. To keep the code simple, start off with
+ * small delay of 1 which would suffice most cases and in case of contention
+ * double the delay. Eventually the delay is sufficient such that the coherency
+ * pipeline is drained, thus a subsequent exclusive access would succeed.
+ */
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"					\n"				\
+	"4: ; --- done ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	scond	%[UNLOCKED], [%[rwlock]]\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
+
+#endif	/* CONFIG_ARC_STAR_9000923308 */
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
 	 * This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
-	: "+&r" (tmp)
+	: "+&r" (val)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
 
@@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	smp_mb();
 }
 
+/* 1 - lock taken successfully */
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
 	smp_mb();
 
-	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
 
 	/*
 	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
@@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 /*
  * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
  *
  * The spinlock itself is contained in @counter and access to it is
  * serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
  */
 
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x)	((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
 /* 1 - lock taken successfully */
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
@@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	arch_spin_unlock(&(rw->lock_mutex));
 }
 
+#endif
+
+#define arch_read_can_lock(x)	((x)->counter > 0)
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
 #define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
 

arch/arc/include/asm/spinlock_types.h

@@ -26,7 +26,9 @@ typedef struct {
  */
 typedef struct {
 	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
 	arch_spinlock_t		lock_mutex;
+#endif
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED__	0x01000000

arch/arc/include/uapi/asm/ptrace.h

@@ -32,20 +32,20 @@
 */
 struct user_regs_struct {
 
-	long pad;
+	unsigned long pad;
 	struct {
-		long bta, lp_start, lp_end, lp_count;
-		long status32, ret, blink, fp, gp;
-		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
-		long sp;
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
 	} scratch;
-	long pad2;
+	unsigned long pad2;
 	struct {
-		long r25, r24, r23, r22, r21, r20;
-		long r19, r18, r17, r16, r15, r14, r13;
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
 	} callee;
-	long efa;	/* break pt addr, for break points in delay slots */
-	long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
 };
 #endif /* !__ASSEMBLY__ */
 

arch/arc/kernel/setup.c

@@ -47,6 +47,7 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_perip uncached_space;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	unsigned long perip_space;
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
@@ -56,7 +57,12 @@ static void read_arc_build_cfg_regs(void)
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-	BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE);
+        if (uncached_space.ver < 3)
+		perip_space = uncached_space.start << 24;
+	else
+		perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
+
+	BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE);
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
@@ -330,6 +336,10 @@ static void arc_chk_core_config(void)
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+
+	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
+		panic("llock/scond livelock workaround missing\n");
 }
 
 /*

arch/arc/kernel/time.c

@@ -203,34 +203,24 @@ static int arc_clkevent_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void arc_clkevent_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *dev)
+static int arc_clkevent_set_periodic(struct clock_event_device *dev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-                /*
-                 * At X Hz, 1 sec = 1000ms -> X cycles;
-                 *                    10ms -> X / 100 cycles
-                 */
-		arc_timer_event_setup(arc_get_core_freq() / HZ);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	default:
-		break;
-	}
-
-	return;
+	/*
+	 * At X Hz, 1 sec = 1000ms -> X cycles;
+	 *		      10ms -> X / 100 cycles
+	 */
+	arc_timer_event_setup(arc_get_core_freq() / HZ);
+	return 0;
 }
 
 static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
-	.name		= "ARC Timer0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.mode		= CLOCK_EVT_MODE_UNUSED,
-	.rating		= 300,
-	.irq		= TIMER0_IRQ,	/* hardwired, no need for resources */
-	.set_next_event = arc_clkevent_set_next_event,
-	.set_mode	= arc_clkevent_set_mode,
+	.name			= "ARC Timer0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.irq			= TIMER0_IRQ,	/* hardwired, no need for resources */
+	.set_next_event		= arc_clkevent_set_next_event,
+	.set_state_periodic	= arc_clkevent_set_periodic,
 };
 
 static irqreturn_t timer_irq_handler(int irq, void *dev_id)
@@ -240,7 +230,7 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id)
 	 * irq_set_chip_and_handler() asked for handle_percpu_devid_irq()
 	 */
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
-	int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC;
+	int irq_reenable = clockevent_state_periodic(evt);
 
 	/*
 	 * Any write to CTRL reg ACks the interrupt, we rewrite the

arch/arc/lib/memcpy-archs.S

@@ -206,7 +206,7 @@ unalignedOffby3:
 	ld.ab	r6, [r1, 4]
 	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetch [r3, 32]	;Prefetch the next write location
+	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5

arch/arc/lib/memset-archs.S

@@ -10,12 +10,6 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-#ifdef PREALLOC_NOT_AVAIL
-#define PREWRITE(A,B)	prefetchw [(A),(B)]
-#else
-#define PREWRITE(A,B)	prealloc [(A),(B)]
-#endif
-
 ENTRY(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -51,9 +45,15 @@ ENTRY(memset)
 
 ;;; Convert len to Dwords, unfold x8
 	lsr.f	lp_count, lp_count, 6
+
 	lpnz	@.Lset64bytes
 	;; LOOP START
-	PREWRITE(r3, 64)	;Prefetch the next write location
+#ifdef PREALLOC_NOT_AVAIL
+	prefetchw [r3, 64]	;Prefetch the next write location
+#else
+	prealloc  [r3, 64]
+#endif
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -62,16 +62,45 @@ ENTRY(memset)
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset64bytes:
 
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
 	prefetchw   [r3, 32]	;Prefetch the next write location
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset32bytes:
 
 	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes

arch/arc/plat-axs10x/axs10x.c

@@ -389,6 +389,21 @@ axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od)
 
 static void __init axs103_early_init(void)
 {
+	/*
+	 * AXS103 configurations for SMP/QUAD configurations share device tree
+	 * which defaults to 90 MHz. However recent failures of Quad config
+	 * revealed P&R timing violations so clamp it down to safe 50 MHz
+	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
+	 *
+	 * This hack is really hacky as of now. Fix it properly by getting the
+	 * number of cores as return value of platform's early SMP callback
+	 */
+#ifdef CONFIG_ARC_MCIP
+	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
+	if (num_cores > 2)
+		arc_set_core_freq(50 * 1000000);
+#endif
+
 	switch (arc_get_core_freq()/1000000) {
 	case 33:
 		axs103_set_freq(1, 1, 1);

arch/arm/Makefile

@@ -312,6 +312,9 @@ INSTALL_TARGETS	= zinstall uinstall install
 
 PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 
+bootpImage uImage: zImage
+zImage: Image
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 

arch/arm/boot/dts/dra7.dtsi

@@ -116,7 +116,7 @@
 				ranges = <0 0x2000 0x2000>;
 
 				scm_conf: scm_conf@0 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x0 0x1400>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -1140,6 +1140,7 @@
 				ctrl-module = <&omap_control_sata>;
 				clocks = <&sys_clkin1>, <&sata_ref_clk>;
 				clock-names = "sysclk", "refclk";
+				syscon-pllreset = <&scm_conf 0x3fc>;
 				#phy-cells = <0>;
 			};
 

arch/arm/boot/dts/imx6qdl.dtsi

@@ -181,10 +181,10 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clks IMX6QDL_CLK_PCIE_AXI>,
 				 <&clks IMX6QDL_CLK_LVDS1_GATE>,
 				 <&clks IMX6QDL_CLK_PCIE_REF_125M>;

arch/arm/boot/dts/k2e.dtsi

@@ -131,10 +131,17 @@
 					<GIC_SPI 376 IRQ_TYPE_EDGE_RISING>;
 			};
 		};
+
+		mdio: mdio@24200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x24200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2e-netcp.dtsi"
 	};
 };
-
-&mdio {
-	reg = <0x24200f00 0x100>;
-};

arch/arm/boot/dts/k2hk.dtsi

@@ -98,6 +98,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x25c>;
 		};
+
+		mdio: mdio@02090300 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x02090300 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2hk-netcp.dtsi"
 	};
 };

arch/arm/boot/dts/k2l.dtsi

@@ -29,7 +29,6 @@
 	};
 
 	soc {
-
 		/include/ "k2l-clocks.dtsi"
 
 		uart2: serial@02348400 {
@@ -79,6 +78,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x24c>;
 		};
+
+		mdio: mdio@26200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x26200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2l-netcp.dtsi"
 	};
 };
@@ -96,7 +106,3 @@
        /* Pin muxed. Enabled and configured by Bootloader */
        status = "disabled";
 };
-
-&mdio {
-	reg = <0x26200f00 0x100>;
-};

arch/arm/boot/dts/keystone.dtsi

@@ -267,17 +267,6 @@
 				  1 0 0x21000A00 0x00000100>;
 		};
 
-		mdio: mdio@02090300 {
-			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg		= <0x02090300 0x100>;
-			status = "disabled";
-			clocks = <&clkpa>;
-			clock-names = "fck";
-			bus_freq	= <2500000>;
-		};
-
 		kirq0: keystone_irq@26202a0 {
 			compatible = "ti,keystone-irq";
 			interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;

arch/arm/boot/dts/omap2430.dtsi

@@ -51,7 +51,8 @@
 				};
 
 				scm_conf: scm_conf@270 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x270 0x240>;
 					#address-cells = <1>;
 					#size-cells = <1>;

arch/arm/boot/dts/omap4.dtsi

@@ -191,7 +191,8 @@
 				};
 
 				omap4_padconf_global: omap4_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0x170>;
 					#address-cells = <1>;
 					#size-cells = <1>;

arch/arm/boot/dts/omap5.dtsi

@@ -180,7 +180,8 @@
 				};
 
 				omap5_padconf_global: omap5_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0xec>;
 					#address-cells = <1>;
 					#size-cells = <1>;

arch/arm/boot/dts/ste-dbx5x0.dtsi

@@ -15,6 +15,33 @@
 #include "skeleton.dtsi"
 
 / {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "ste,dbx500-smp";
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+			};
+		};
+		CPU0: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x300>;
+		};
+		CPU1: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x301>;
+		};
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -22,32 +49,6 @@
 		interrupt-parent = <&intc>;
 		ranges;
 
-		cpus {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			cpu-map {
-				cluster0 {
-					core0 {
-						cpu = <&CPU0>;
-					};
-					core1 {
-						cpu = <&CPU1>;
-					};
-				};
-			};
-			CPU0: cpu@0 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <0>;
-			};
-			CPU1: cpu@1 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <1>;
-			};
-		};
-
 		ptm@801ae000 {
 			compatible = "arm,coresight-etm3x", "arm,primecell";
 			reg = <0x801ae000 0x1000>;

arch/arm/kernel/entry-common.S

@@ -61,6 +61,7 @@ work_pending:
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
 	b	local_restart			@ ... and off we go
+ENDPROC(ret_fast_syscall)
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.

arch/arm/kernel/head.S

@@ -399,6 +399,9 @@ ENTRY(secondary_startup)
 	sub	lr, r4, r5			@ mmu has been enabled
 	add	r3, r7, lr
 	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
+ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
+ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
 	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	badr	lr, __enable_mmu		@ return address
 	mov	r13, r12			@ __secondary_switched address

arch/arm/kernel/vdso.c

@@ -296,7 +296,6 @@ static bool tk_is_cntvct(const struct timekeeper *tk)
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	struct timespec64 *wtm = &tk->wall_to_monotonic;
 
 	if (!cntvct_ok) {
@@ -308,10 +307,10 @@ void update_vsyscall(struct timekeeper *tk)
 
 	vdso_write_begin(vdso_data);
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= (u32)(tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift);
 	vdso_data->wtm_clock_sec		= wtm->tv_sec;
 	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
 

arch/arm/lib/uaccess_with_memcpy.c

@@ -96,7 +96,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 	}
 
 	/* the mmap semaphore is taken only if not in an atomic context */
-	atomic = in_atomic();
+	atomic = faulthandler_disabled();
 
 	if (!atomic)
 		down_read(&current->mm->mmap_sem);

arch/arm/mach-exynos/pm_domains.c

@@ -146,9 +146,8 @@ static __init int exynos4_pm_init_power_domain(void)
 		pd->base = of_iomap(np, 0);
 		if (!pd->base) {
 			pr_warn("%s: failed to map memory\n", __func__);
-			kfree(pd->pd.name);
+			kfree_const(pd->pd.name);
 			kfree(pd);
-			of_node_put(np);
 			continue;
 		}
 

arch/arm/mach-omap2/omap-wakeupgen.c

@@ -392,6 +392,7 @@ static struct irq_chip wakeupgen_chip = {
 	.irq_mask		= wakeupgen_mask,
 	.irq_unmask		= wakeupgen_unmask,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= irq_chip_set_type_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,

arch/arm/vdso/Makefile

@@ -14,7 +14,7 @@ VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 VDSO_LDFLAGS += -nostdlib -shared
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id)
-VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd)
+VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd)
 
 obj-$(CONFIG_VDSO) += vdso.o
 extra-$(CONFIG_VDSO) += vdso.lds

arch/arm64/kernel/signal32.c

@@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -201,8 +202,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))

arch/arm64/kernel/vdso.c

@@ -199,16 +199,15 @@ up_fail:
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift;
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 

arch/arm64/kvm/inject_fault.c

@@ -168,8 +168,8 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_abt32(vcpu, false, addr);
-
-	inject_abt64(vcpu, false, addr);
+	else
+		inject_abt64(vcpu, false, addr);
 }
 
 /**
@@ -184,8 +184,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_abt32(vcpu, true, addr);
-
-	inject_abt64(vcpu, true, addr);
+	else
+		inject_abt64(vcpu, true, addr);
 }
 
 /**
@@ -198,6 +198,6 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
 	if (!(vcpu->arch.hcr_el2 & HCR_RW))
 		inject_undef32(vcpu);
-
-	inject_undef64(vcpu);
+	else
+		inject_undef64(vcpu);
 }

arch/mips/Kconfig

@@ -151,7 +151,6 @@ config BMIPS_GENERIC
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
-	select RAW_IRQ_ACCESSORS
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN

arch/mips/ath79/setup.c

@@ -190,6 +190,7 @@ int get_c0_perfcount_int(void)
 {
 	return ATH79_MISC_IRQ(5);
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {

arch/mips/cavium-octeon/smp.c

@@ -42,7 +42,7 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action);
 
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 

arch/mips/include/asm/mach-bcm63xx/dma-coherence.h

@@ -1,10 +0,0 @@
-#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#include <asm/mach-generic/dma-coherence.h>
-
-#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */

arch/mips/include/asm/pgtable.h

@@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+			"	.set	push\n"
+			"	.set	noreorder\n"
+			"1:	" LL_INSN "	%[tmp], %[buddy]\n"
+			"	bnez	%[tmp], 2f\n"
+			"	 or	%[tmp], %[tmp], %[global]\n"
+			"	" SC_INSN "	%[tmp], %[buddy]\n"
+			"	beqz	%[tmp], 1b\n"
+			"	 nop\n"
+			"2:\n"
+			"	.set pop"
+			: [buddy] "+m" (buddy->pte),
+			  [tmp] "=&r" (tmp)
+			: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 #endif
 }

arch/mips/include/asm/smp.h

@@ -83,8 +83,6 @@ static inline void __cpu_die(unsigned int cpu)
 extern void play_dead(void);
 #endif
 
-extern asmlinkage void smp_call_function_interrupt(void);
-
 static inline void arch_send_call_function_single_ipi(int cpu)
 {
 	extern struct plat_smp_ops *mp_ops;	/* private */

arch/mips/include/asm/stackframe.h

@@ -152,6 +152,31 @@
 		.set	noreorder
 		bltz	k0, 8f
 		 move	k1, sp
+#ifdef CONFIG_EVA
+		/*
+		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
+		 * EntryHi. Toggling Config7.RPS is slower and less portable.
+		 *
+		 * The RPS isn't automatically flushed when exceptions are
+		 * taken, which can result in kernel mode speculative accesses
+		 * to user addresses if the RPS mispredicts. That's harmless
+		 * when user and kernel share the same address space, but with
+		 * EVA the same user segments may be unmapped to kernel mode,
+		 * even containing sensitive MMIO regions or invalid memory.
+		 *
+		 * This can happen when the kernel sets the return address to
+		 * ret_from_* and jr's to the exception handler, which looks
+		 * more like a tail call than a function call. If nested calls
+		 * don't evict the last user address in the RPS, it will
+		 * mispredict the return and fetch from a user controlled
+		 * address into the icache.
+		 *
+		 * More recent EVA-capable cores with MAAR to restrict
+		 * speculative accesses aren't affected.
+		 */
+		MFC0	k0, CP0_ENTRYHI
+		MTC0	k0, CP0_ENTRYHI
+#endif
 		.set	reorder
 		/* Called from user mode, new stack. */
 		get_saved_sp

arch/mips/kernel/genex.S

@@ -407,7 +407,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	noat
 	SAVE_ALL
 	FEXPORT(handle_\exception\ext)
-	__BUILD_clear_\clear
+	__build_clear_\clear
 	.set	at
 	__BUILD_\verbose \exception
 	move	a0, sp

arch/mips/kernel/mips-mt-fpaff.c

@@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
 	unsigned int real_len;
-	cpumask_t mask;
+	cpumask_t allowed, mask;
 	int retval;
 	struct task_struct *p;
 
@@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 	if (retval)
 		goto out_unlock;
 
-	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);

arch/mips/kernel/prom.c

@@ -38,7 +38,7 @@ char *mips_get_machine_name(void)
 	return mips_machine_name;
 }
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	return add_memory_region(base, size, BOOT_MEM_RAM);

arch/mips/kernel/relocate_kernel.S

@@ -24,7 +24,7 @@ LEAF(relocate_new_kernel)
 
 process_entry:
 	PTR_L		s2, (s0)
-	PTR_ADD		s0, s0, SZREG
+	PTR_ADDIU	s0, s0, SZREG
 
 	/*
 	 * In case of a kdump/crash kernel, the indirection page is not
@@ -61,9 +61,9 @@ copy_word:
 	/* copy page word by word */
 	REG_L		s5, (s2)
 	REG_S		s5, (s4)
-	PTR_ADD		s4, s4, SZREG
-	PTR_ADD		s2, s2, SZREG
-	LONG_SUB	s6, s6, 1
+	PTR_ADDIU	s4, s4, SZREG
+	PTR_ADDIU	s2, s2, SZREG
+	LONG_ADDIU	s6, s6, -1
 	beq		s6, zero, process_entry
 	b		copy_word
 	b		process_entry

arch/mips/kernel/scall64-64.S

@@ -80,7 +80,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_64_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall

arch/mips/kernel/scall64-n32.S

@@ -72,7 +72,7 @@ n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_N32_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall

arch/mips/kernel/signal32.c

@@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))

arch/mips/kernel/smp-bmips.c

@@ -284,7 +284,7 @@ static irqreturn_t bmips5000_ipi_interrupt(int irq, void *dev_id)
 	if (action == 0)
 		scheduler_ipi();
 	else
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
@@ -336,7 +336,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }

arch/mips/kernel/smp.c

@@ -192,16 +192,6 @@ asmlinkage void start_secondary(void)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-/*
- * Call into both interrupt handlers, as we share the IPI for them
- */
-void __irq_entry smp_call_function_interrupt(void)
-{
-	irq_enter();
-	generic_smp_call_function_interrupt();
-	irq_exit();
-}
-
 static void stop_this_cpu(void *dummy)
 {
 	/*

arch/mips/kernel/traps.c

@@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task,
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
+	mm_segment_t old_fs = get_fs();
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
@@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 			prepare_frametrace(&regs);
 		}
 	}
+	/*
+	 * show_stack() deals exclusively with kernel mode, so be sure to access
+	 * the stack in the kernel (not user) address space.
+	 */
+	set_fs(KERNEL_DS);
 	show_stacktrace(task, &regs);
+	set_fs(old_fs);
 }
 
 static void show_code(unsigned int __user *pc)
@@ -1519,6 +1526,7 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
 	const int field = 2 * sizeof(unsigned long);
 	int multi_match = regs->cp0_status & ST0_TS;
 	enum ctx_state prev_state;
+	mm_segment_t old_fs = get_fs();
 
 	prev_state = exception_enter();
 	show_regs(regs);
@@ -1540,8 +1548,13 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
 		dump_tlb_all();
 	}
 
+	if (!user_mode(regs))
+		set_fs(KERNEL_DS);
+
 	show_code((unsigned int __user *) regs->cp0_epc);
 
+	set_fs(old_fs);
+
 	/*
 	 * Some chips may have other causes of machine check (e.g. SB1
 	 * graduation timer)

arch/mips/kernel/unaligned.c

@@ -438,7 +438,7 @@ do {                                                        \
 		: "memory");                                \
 } while(0)
 
-#define     StoreDW(addr, value, res) \
+#define     _StoreDW(addr, value, res) \
 do {                                                        \
 		__asm__ __volatile__ (                      \
 			".set\tpush\n\t"		    \

arch/mips/lantiq/irq.c

@@ -293,7 +293,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
@@ -466,6 +466,7 @@ int get_c0_perfcount_int(void)
 {
 	return ltq_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {

arch/mips/loongson64/loongson-3/smp.c

@@ -266,8 +266,11 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);

arch/mips/mm/cache.c

@@ -160,18 +160,18 @@ static inline void setup_protection_map(void)
 		protection_map[1]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[2]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[3]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
-		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[5]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[7]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 
 		protection_map[8]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[9]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
 		protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE  | _PAGE_NO_READ);
+		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 		protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 
 	} else {

arch/mips/mm/fault.c

@@ -133,7 +133,8 @@ good_area:
 #endif
 				goto bad_area;
 			}
-			if (!(vma->vm_flags & VM_READ)) {
+			if (!(vma->vm_flags & VM_READ) &&
+			    exception_epc(regs) != address) {
 #if 0
 				pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
 					  raw_smp_processor_id(),

arch/mips/mti-malta/malta-int.c

@@ -222,7 +222,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }

arch/mips/mti-malta/malta-time.c

@@ -154,6 +154,7 @@ int get_c0_perfcount_int(void)
 
 	return mips_cpu_perf_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
@@ -171,14 +172,17 @@ unsigned int get_c0_compare_int(void)
 
 static void __init init_rtc(void)
 {
-	/* stop the clock whilst setting it up */
-	CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL);
+	unsigned char freq, ctrl;
 
-	/* 32KHz time base */
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
+	/* Set 32KHz time base if not already set */
+	freq = CMOS_READ(RTC_FREQ_SELECT);
+	if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ)
+		CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
 
-	/* start the clock */
-	CMOS_WRITE(RTC_24H, RTC_CONTROL);
+	/* Ensure SET bit is clear so RTC can run */
+	ctrl = CMOS_READ(RTC_CONTROL);
+	if (ctrl & RTC_SET)
+		CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
 }
 
 void __init plat_time_init(void)

arch/mips/mti-sead3/sead3-time.c

@@ -77,6 +77,7 @@ int get_c0_perfcount_int(void)
 		return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
 	return -1;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {

arch/mips/netlogic/common/smp.c

@@ -86,7 +86,7 @@ void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc)
 {
 	clear_c0_eimr(irq);
 	ack_c0_eirr(irq);
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	set_c0_eimr(irq);
 }
 

arch/mips/paravirt/paravirt-smp.c

@@ -114,7 +114,7 @@ static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 

arch/mips/pistachio/time.c

@@ -26,6 +26,7 @@ int get_c0_perfcount_int(void)
 {
 	return gic_get_c0_perfcount_int();
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 int get_c0_fdc_int(void)
 {

arch/mips/pmcs-msp71xx/msp_smp.c

@@ -44,7 +44,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }

arch/mips/ralink/irq.c

@@ -89,6 +89,7 @@ int get_c0_perfcount_int(void)
 {
 	return rt_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {

arch/mips/sgi-ip27/ip27-irq.c

@@ -107,10 +107,14 @@ static void ip27_do_irq_mask0(void)
 		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else if (pend0 & (1UL << CPU_CALL_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_B_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else
 #endif
 	{

arch/mips/sibyte/bcm1480/smp.c

@@ -29,8 +29,6 @@
 #include <asm/sibyte/bcm1480_regs.h>
 #include <asm/sibyte/bcm1480_int.h>
 
-extern void smp_call_function_interrupt(void);
-
 /*
  * These are routines for dealing with the bcm1480 smp capabilities
  * independent of board/firmware
@@ -184,6 +182,9 @@ void bcm1480_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }

arch/mips/sibyte/sb1250/smp.c

@@ -172,6 +172,9 @@ void sb1250_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }

arch/powerpc/kernel/pci_of_scan.c

@@ -191,6 +191,9 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	pci_device_add(dev, bus);
 
+	/* Setup MSI caps & disable MSI/MSI-X interrupts */
+	pci_msi_setup_pci_dev(dev);
+
 	return dev;
 }
 EXPORT_SYMBOL(of_create_pci_dev);

arch/powerpc/kernel/signal_32.c

@@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))

arch/s390/kvm/kvm-s390.c

@@ -1742,10 +1742,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->requests)
-		return 0;
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
+	if (!vcpu->requests)
+		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.

arch/sparc/include/asm/visasm.h

@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__

arch/sparc/lib/NG4memcpy.S

@@ -240,8 +240,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned

arch/sparc/lib/VISsave.S

@@ -44,9 +44,8 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs

arch/sparc/lib/ksyms.c

@@ -135,10 +135,6 @@ EXPORT_SYMBOL(copy_user_page);
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);

arch/tile/kernel/compat_signal.c

@@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
-	memset(to, 0, sizeof(*to));
-
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);

arch/x86/entry/entry_64_compat.S

@@ -140,6 +140,7 @@ sysexit_from_sys_call:
 	 */
 	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
 	movl	RIP(%rsp), %ecx		/* User %eip */
+	movq    RAX(%rsp), %rax
 	RESTORE_RSI_RDI
 	xorl	%edx, %edx		/* Do not leak kernel information */
 	xorq	%r8, %r8
@@ -219,7 +220,6 @@ sysexit_from_sys_call:
 1:	setbe	%al			/* 1 if error, 0 if not */
 	movzbl	%al, %edi		/* zero-extend that into %edi */
 	call	__audit_syscall_exit
-	movq	RAX(%rsp), %rax		/* reload syscall return value */
 	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -368,6 +368,7 @@ sysretl_from_sys_call:
 	RESTORE_RSI_RDI_RDX
 	movl	RIP(%rsp), %ecx
 	movl	EFLAGS(%rsp), %r11d
+	movq    RAX(%rsp), %rax
 	xorq	%r10, %r10
 	xorq	%r9, %r9
 	xorq	%r8, %r8

arch/x86/include/asm/sigcontext.h

@@ -57,9 +57,9 @@ struct sigcontext {
 	unsigned long ip;
 	unsigned long flags;
 	unsigned short cs;
-	unsigned short __pad2;	/* Was called gs, but was always zero. */
-	unsigned short __pad1;	/* Was called fs, but was always zero. */
-	unsigned short ss;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
 	unsigned long err;
 	unsigned long trapno;
 	unsigned long oldmask;

arch/x86/include/asm/switch_to.h

@@ -79,12 +79,12 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
 
 #define __EXTRA_CLOBBER  \
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15", "flags"
+	  "r12", "r13", "r14", "r15"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #define __switch_canary							  \
@@ -100,11 +100,7 @@ do {									\
 #define __switch_canary_iparam
 #endif	/* CC_STACKPROTECTOR */
 
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
- * has no effect.
- */
+/* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
 	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \

arch/x86/include/uapi/asm/sigcontext.h

@@ -177,24 +177,9 @@ struct sigcontext {
 	__u64 rip;
 	__u64 eflags;		/* RFLAGS */
 	__u16 cs;
-
-	/*
-	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
-	 * Linux saved and restored fs and gs in these slots.  This
-	 * was counterproductive, as fsbase and gsbase were never
-	 * saved, so arch_prctl was presumably unreliable.
-	 *
-	 * If these slots are ever needed for any other purpose, there
-	 * is some risk that very old 64-bit binaries could get
-	 * confused.  I doubt that many such binaries still work,
-	 * though, since the same patch in 2.5.64 also removed the
-	 * 64-bit set_thread_area syscall, so it appears that there is
-	 * no TLS API that works in both pre- and post-2.5.64 kernels.
-	 */
-	__u16 __pad2;		/* Was gs. */
-	__u16 __pad1;		/* Was fs. */
-
-	__u16 ss;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
 	__u64 err;
 	__u64 trapno;
 	__u64 oldmask;

arch/x86/kernel/apic/apic.c

@@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void)
 {
 	u64 msr;
 
-	if (cpu_has_apic)
+	if (!cpu_has_apic)
 		return;
 
 	rdmsrl(MSR_IA32_APICBASE, msr);
@@ -1483,10 +1483,13 @@ void x2apic_setup(void)
 
 static __init void x2apic_disable(void)
 {
-	u32 x2apic_id;
+	u32 x2apic_id, state = x2apic_state;
 
-	if (x2apic_state != X2APIC_ON)
-		goto out;
+	x2apic_mode = 0;
+	x2apic_state = X2APIC_DISABLED;
+
+	if (state != X2APIC_ON)
+		return;
 
 	x2apic_id = read_apic_id();
 	if (x2apic_id >= 255)
@@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void)
 
 	__x2apic_disable();
 	register_lapic_address(mp_lapic_addr);
-out:
-	x2apic_state = X2APIC_DISABLED;
-	x2apic_mode = 0;
 }
 
 static __init void x2apic_enable(void)

arch/x86/kernel/apic/vector.c

@@ -322,7 +322,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector_policy(virq, irq_data->node, data,
+		err = assign_irq_vector_policy(virq + i, irq_data->node, data,
 					       info);
 		if (err)
 			goto error;

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
-			return NOTIFY_BAD;
+			goto err;
 	}
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu)
 
 		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
 		if (!cpuc->constraint_list)
-			return NOTIFY_BAD;
+			goto err_shared_regs;
 
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
-		if (!cpuc->excl_cntrs) {
-			kfree(cpuc->constraint_list);
-			kfree(cpuc->shared_regs);
-			return NOTIFY_BAD;
-		}
+		if (!cpuc->excl_cntrs)
+			goto err_constraint_list;
+
 		cpuc->excl_thread_id = 0;
 	}
 
 	return NOTIFY_OK;
+
+err_constraint_list:
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
+
+err_shared_regs:
+	kfree(cpuc->shared_regs);
+	cpuc->shared_regs = NULL;
+
+err:
+	return NOTIFY_BAD;
 }
 
 static void intel_pmu_cpu_starting(int cpu)

arch/x86/kernel/cpu/perf_event_intel_cqm.c

@@ -1255,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu)
 	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1296,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb,
 	unsigned int cpu  = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		intel_cqm_cpu_prepare(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		intel_cqm_cpu_exit(cpu);
 		break;
 	case CPU_STARTING:
+		intel_cqm_cpu_starting(cpu);
 		cqm_pick_event_reader(cpu);
 		break;
 	}
@@ -1373,7 +1371,7 @@ static int __init intel_cqm_init(void)
 		goto out;
 
 	for_each_online_cpu(i) {
-		intel_cqm_cpu_prepare(i);
+		intel_cqm_cpu_starting(i);
 		cqm_pick_event_reader(i);
 	}
 

arch/x86/kernel/fpu/core.c

@@ -270,7 +270,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (src_fpu->fpstate_active)
+	if (src_fpu->fpstate_active && cpu_has_fpu)
 		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;

arch/x86/kernel/fpu/init.c

@@ -40,7 +40,12 @@ static void fpu__init_cpu_generic(void)
 	write_cr0(cr0);
 
 	/* Flush out any pending x87 state: */
-	asm volatile ("fninit");
+#ifdef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu)
+		fpstate_init_soft(&current->thread.fpu.state.soft);
+	else
+#endif
+		asm volatile ("fninit");
 }
 
 /*

arch/x86/kernel/process.c

@@ -408,6 +408,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 static void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
 			smp_mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
@@ -419,6 +420,7 @@ static void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 	}

arch/x86/kernel/signal.c

@@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+		/* Kernel saves and restores only the CS segment register on signals,
+		 * which is the bare minimum needed to allow mixed 32/64-bit code.
+		 * App's signal handler can save/restore other segments if needed. */
+		COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 #else /* !CONFIG_X86_32 */
 		put_user_ex(regs->flags, &sc->flags);
 		put_user_ex(regs->cs, &sc->cs);
-		put_user_ex(0, &sc->__pad2);
-		put_user_ex(0, &sc->__pad1);
-		put_user_ex(regs->ss, &sc->ss);
+		put_user_ex(0, &sc->gs);
+		put_user_ex(0, &sc->fs);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	regs->sp = (unsigned long)frame;
 
-	/*
-	 * Set up the CS and SS registers to run signal handlers in
-	 * 64-bit mode, even if the handler happens to be interrupting
-	 * 32-bit or 16-bit code.
-	 *
-	 * SS is subtle.  In 64-bit mode, we don't need any particular
-	 * SS descriptor, but we do need SS to be valid.  It's possible
-	 * that the old SS is entirely bogus -- this can happen if the
-	 * signal we're trying to deliver is #GP or #SS caused by a bad
-	 * SS value.
-	 */
+	/* Set up the CS register to run signal handlers in 64-bit mode,
+	   even if the handler happens to be interrupting 32-bit code. */
 	regs->cs = __USER_CS;
-	regs->ss = __USER_DS;
 
 	return 0;
 }

arch/x86/kernel/step.c

@@ -28,11 +28,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		struct desc_struct *desc;
 		unsigned long base;
 
-		seg &= ~7UL;
+		seg >>= 3;
 
 		mutex_lock(&child->mm->context.lock);
 		if (unlikely(!child->mm->context.ldt ||
-			     (seg >> 3) >= child->mm->context.ldt->size))
+			     seg >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
 			desc = &child->mm->context.ldt->entries[seg];

arch/x86/kvm/mtrr.c

@@ -672,16 +672,16 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 	if (iter.mtrr_disabled)
 		return mtrr_disabled_type();
 
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
 	/*
 	 * We just check one page, partially covered by MTRRs is
 	 * impossible.
 	 */
 	WARN_ON(iter.partial_map);
 
-	/* not contained in any MTRRs. */
-	if (type == -1)
-		return mtrr_default_type(mtrr_state);
-
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);

arch/x86/kvm/x86.c

@@ -2105,7 +2105,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (guest_cpuid_has_tsc_adjust(vcpu)) {
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
-				kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true);
+				adjust_tsc_offset_guest(vcpu, adj);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -6327,6 +6327,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 static void process_smi(struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment cs, ds;
+	struct desc_ptr dt;
 	char buf[512];
 	u32 cr0;
 
@@ -6359,6 +6360,10 @@ static void process_smi(struct kvm_vcpu *vcpu)
 
 	kvm_x86_ops->set_cr4(vcpu, 0);
 
+	/* Undocumented: IDT limit is set to zero on entry to SMM.  */
+	dt.address = dt.size = 0;
+	kvm_x86_ops->set_idt(vcpu, &dt);
+
 	__kvm_set_dr(vcpu, 7, DR7_FIXED_1);
 
 	cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;

arch/x86/math-emu/fpu_entry.c

@@ -29,7 +29,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
-#include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/fpu/internal.h>
 
@@ -181,7 +180,7 @@ void math_emulate(struct math_emu_info *info)
 			math_abort(FPU_info, SIGILL);
 		}
 
-		code_descriptor = LDT_DESCRIPTOR(FPU_CS);
+		code_descriptor = FPU_get_ldt_descriptor(FPU_CS);
 		if (SEG_D_SIZE(code_descriptor)) {
 			/* The above test may be wrong, the book is not clear */
 			/* Segmented 32 bit protected mode */

arch/x86/math-emu/fpu_system.h

@@ -16,9 +16,24 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 
-/* s is always from a cpu register, and the cpu does bounds checking
- * during register load --> no further bounds checks needed */
-#define LDT_DESCRIPTOR(s)	(((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
+{
+	static struct desc_struct zero_desc;
+	struct desc_struct ret = zero_desc;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	seg >>= 3;
+	mutex_lock(&current->mm->context.lock);
+	if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+		ret = current->mm->context.ldt->entries[seg];
+	mutex_unlock(&current->mm->context.lock);
+#endif
+	return ret;
+}
+
 #define SEG_D_SIZE(x)		((x).b & (3 << 21))
 #define SEG_G_BIT(x)		((x).b & (1 << 23))
 #define SEG_GRANULARITY(x)	(((x).b & (1 << 23)) ? 4096 : 1)

arch/x86/math-emu/get_address.c

@@ -20,7 +20,6 @@
 #include <linux/stddef.h>
 
 #include <asm/uaccess.h>
-#include <asm/desc.h>
 
 #include "fpu_system.h"
 #include "exception.h"
@@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 		addr->selector = PM_REG_(segment);
 	}
 
-	descriptor = LDT_DESCRIPTOR(PM_REG_(segment));
+	descriptor = FPU_get_ldt_descriptor(addr->selector);
 	base_address = SEG_BASE_ADDR(descriptor);
 	address = base_address + offset;
 	limit = base_address