Merge "Merge android-4.4.169 (dfca92b) into msm-4.4"

176 files changed, 2316 insertions, 1786 deletions

diff --git a/Documentation/Makefile b/Documentation/Makefile
index fc759598c4c9..59d516b7afcb 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,4 +1,3 @@
 subdir-y := accounting auxdisplay blackfin connector \
 	filesystems filesystems ia64 laptops misc-devices \
-	networking pcmcia prctl ptp spi timers vDSO video4linux \
-	watchdog
+	pcmcia prctl ptp spi timers vDSO video4linux watchdog
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
deleted file mode 100644
index 4c5d7c485439..000000000000
--- a/Documentation/networking/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := timestamping
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
deleted file mode 100644
index 8c20dfaa4d6e..000000000000
--- a/Documentation/networking/timestamping/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# To compile, from the source root
-#
-#    make headers_install
-#    make M=documentation
-
-# List of programs to build
-hostprogs-y := hwtstamp_config timestamping txtimestamp
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
-HOSTCFLAGS_txtimestamp.o += -I$(objtree)/usr/include
-HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include
diff --git a/Makefile b/Makefile
index 4c581af6508c..142b5348920c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 167
+SUBLEVEL = 169
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index cb69299a492e..f120d823e8c2 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/page.h>
+#include <asm/unaligned.h>
 
 #ifdef CONFIG_ISA_ARCV2
 #include <asm/barrier.h>
@@ -85,6 +86,42 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 	return w;
 }
 
+/*
+ * {read,write}s{b,w,l}() repeatedly access the same IO address in
+ * native endianness in 8-, 16-, 32-bit chunks {into,from} memory,
+ * @count times
+ */
+#define __raw_readsx(t,f) \
+static inline void __raw_reads##f(const volatile void __iomem *addr,	\
+				  void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			*buf++ = x;					\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			put_unaligned(x, buf++);			\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_readsb __raw_readsb
+__raw_readsx(8, b)
+#define __raw_readsw __raw_readsw
+__raw_readsx(16, w)
+#define __raw_readsl __raw_readsl
+__raw_readsx(32, l)
+
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
 {
@@ -117,6 +154,35 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
+#define __raw_writesx(t,f)						\
+static inline void __raw_writes##f(volatile void __iomem *addr, 	\
+				   const void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	const u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			__raw_write##f(*buf++, addr);			\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			__raw_write##f(get_unaligned(buf++), addr);	\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_writesb __raw_writesb
+__raw_writesx(8, b)
+#define __raw_writesw __raw_writesw
+__raw_writesx(16, w)
+#define __raw_writesl __raw_writesl
+__raw_writesx(32, l)
+
 /*
  * MMIO can also get buffered/optimized in micro-arch, so barriers needed
  * Based on ARM model for the typical use case
@@ -132,10 +198,16 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
 #define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+#define readsb(p,d,l)		({ __raw_readsb(p,d,l); __iormb(); })
+#define readsw(p,d,l)		({ __raw_readsw(p,d,l); __iormb(); })
+#define readsl(p,d,l)		({ __raw_readsl(p,d,l); __iormb(); })
 
 #define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+#define writesb(p,d,l)		({ __iowmb(); __raw_writesb(p,d,l); })
+#define writesw(p,d,l)		({ __iowmb(); __raw_writesw(p,d,l); })
+#define writesl(p,d,l)		({ __iowmb(); __raw_writesl(p,d,l); })
 
 /*
  * Relaxed API for drivers which can handle barrier ordering themselves
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index a95499ea8706..fa1d41edce68 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -511,6 +511,9 @@ static void modem_pm(struct uart_port *port, unsigned int state, unsigned old)
 {
 	struct modem_private_data *priv = port->private_data;
 
+	if (!priv)
+		return;
+
 	if (IS_ERR(priv->regulator))
 		return;
 
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 30768003f854..8c505284bc0c 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -344,7 +344,7 @@ static void omap44xx_prm_reconfigure_io_chain(void)
  * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and
  * omap44xx_prm_reconfigure_io_chain() must be called.  No return value.
  */
-static void __init omap44xx_prm_enable_io_wakeup(void)
+static void omap44xx_prm_enable_io_wakeup(void)
 {
 	s32 inst = omap4_prmst_get_prm_dev_inst();
 
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 2ddf36403d1c..08975bddefc1 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -359,14 +359,16 @@ ENTRY(v7_dma_inv_range)
 	ALT_UP(W(nop))
 #endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
+	addne	r0, r0, r2
 
 	tst	r1, r3
 	bic	r1, r1, r3
 	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D / U line
-1:
-	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
-	add	r0, r0, r2
 	cmp	r0, r1
+1:
+	mcrlo	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
+	addlo	r0, r0, r2
+	cmplo	r0, r1
 	blo	1b
 	dsb	st
 	ret	lr
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index 877da1908234..98e2a5dbcfda 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2724,7 +2724,6 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 			     (unsigned long int)(oper.indata + prev_ix),
 			     noinpages,
 			     0,  /* read access only for in data */
-			     0, /* no force */
 			     inpages,
 			     NULL);
 
@@ -2740,8 +2739,7 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 				     current->mm,
 				     (unsigned long int)oper.cipher_outdata,
 				     nooutpages,
-				     1, /* write access for out data */
-				     0, /* no force */
+				     FOLL_WRITE, /* write access for out data */
 				     outpages,
 				     NULL);
 		up_read(&current->mm->mmap_sem);
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 0c161ed6d18e..8205b456de7a 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -143,7 +143,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	int ret;
 
         ret = get_user_pages(current, current->mm, virt_addr,
-                        1, VM_READ, 0, NULL, NULL);
+			     1, FOLL_WRITE, NULL, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index 349995d19c7f..e596e0a1cecc 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -303,7 +303,7 @@ slow_irqon:
 
 	ret = get_user_pages_unlocked(current, mm, start,
 				      (end - start) >> PAGE_SHIFT,
-				      write, 0, pages);
+				      pages, write ? FOLL_WRITE : 0);
 
 	/* Have to be a bit careful with return values */
 	if (nr > 0) {
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 99e4487248ff..57003d1bd243 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -70,7 +70,8 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o): \
 libfdt       := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
 libfdtheader := fdt.h libfdt.h libfdt_internal.h
 
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o \
+	treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
 src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index dab616a33b8d..f2197654be07 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -34,5 +34,10 @@ void arch_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
 
-	phb->controller_ops.teardown_msi_irqs(dev);
+	/*
+	 * We can be called even when arch_setup_msi_irqs() returns -ENOSYS,
+	 * so check the pointer again.
+	 */
+	if (phb->controller_ops.teardown_msi_irqs)
+		phb->controller_ops.teardown_msi_irqs(dev);
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 929c147e07b4..1b69bfdf59f9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -344,6 +344,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 		break;
 
 	case PERF_TYPE_HARDWARE:
+		if (is_sampling_event(event))	/* No sampling support */
+			return -ENOENT;
 		ev = attr->config;
 		/* Count user space (problem-state) only */
 		if (!attr->exclude_user && attr->exclude_kernel) {
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 12bbf0e8478f..7ad41be8b373 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -242,7 +242,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	start += nr << PAGE_SHIFT;
 	pages += nr;
 	ret = get_user_pages_unlocked(current, mm, start,
-			     nr_pages - nr, write, 0, pages);
+			     nr_pages - nr, pages, write ? FOLL_WRITE : 0);
 	/* Have to be a bit careful with return values */
 	if (nr > 0)
 		ret = (ret < 0) ? nr : ret + nr;
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
index e7af6a65baab..8c51a0e94854 100644
--- a/arch/sh/mm/gup.c
+++ b/arch/sh/mm/gup.c
@@ -258,7 +258,8 @@ slow_irqon:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(current, mm, start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 2e5c4fc2daa9..150f48303fb0 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -250,7 +250,8 @@ slow:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(current, mm, start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3a37cdbdfbaa..c048d0d70cc4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -765,7 +765,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*cpu_has_high_real_mode_segbase)(void);
+	bool (*has_emulated_msr)(int index);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8857f6f4daa9..4018d80a4394 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -151,6 +151,11 @@ extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
 #define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -436,7 +441,7 @@ do {									\
 ({									\
 	int __gu_err;							\
 	unsigned long __gu_val;						\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -478,6 +483,10 @@ struct __large_struct { unsigned long buf[100]; };
 	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current_thread_info()->uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
 	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\
@@ -542,7 +551,7 @@ struct __large_struct { unsigned long buf[100]; };
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -577,7 +586,7 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 7d3bdd1ed697..d6d245088dd5 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -102,17 +102,17 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
@@ -130,17 +130,17 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index ec9d2bcc8c24..411b6156bfeb 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -58,31 +58,31 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
@@ -92,7 +92,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 		__uaccess_end();
 		return ret;
 	case 16:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))
@@ -192,7 +192,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	switch (size) {
 	case 1: {
 		u8 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u8 __user *)src,
 			       ret, "b", "b", "=q", 1);
 		if (likely(!ret))
@@ -203,7 +203,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 	case 2: {
 		u16 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u16 __user *)src,
 			       ret, "w", "w", "=r", 2);
 		if (likely(!ret))
@@ -215,7 +215,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 
 	case 4: {
 		u32 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u32 __user *)src,
 			       ret, "l", "k", "=r", 4);
 		if (likely(!ret))
@@ -226,7 +226,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 	case 8: {
 		u64 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u64 __user *)src,
 			       ret, "q", "", "=r", 8);
 		if (likely(!ret))
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b12c0287d6cf..e8b46f575306 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -693,7 +693,8 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
 
-	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD))
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+	    cpu_has(c, X86_FEATURE_VIRT_SSBD))
 		set_cpu_cap(c, X86_FEATURE_SSBD);
 
 	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 338d13d4fd2f..b857bb9f6f23 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -341,6 +341,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
+	/* cpuid 0x80000008.ebx */
+	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
+		F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
+
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_supported_word5_x86_features =
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
@@ -358,6 +362,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word10_x86_features =
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -435,11 +443,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			cpuid_mask(&entry->ebx, 9);
 			// TSC_ADJUST is emulated
 			entry->ebx |= F(TSC_ADJUST);
-		} else
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			cpuid_mask(&entry->edx, CPUID_7_EDX);
+		} else {
 			entry->ebx = 0;
+			entry->edx = 0;
+		}
 		entry->eax = 0;
 		entry->ecx = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
@@ -583,7 +594,21 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		if (!g_phys_as)
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
-		entry->ebx = entry->edx = 0;
+		entry->edx = 0;
+		/*
+		 * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+		 * hardware cpuid
+		 */
+		if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			entry->ebx |= F(AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+			entry->ebx |= F(AMD_IBRS);
+		if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
+		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
+		cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+		if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+			entry->ebx |= F(VIRT_SSBD);
 		break;
 	}
 	case 0x80000019:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d1534feefcfe..72f159f4d456 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -159,6 +159,46 @@ static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
 	return best && (best->edx & bit(X86_FEATURE_RDTSCP));
 }
 
+static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && (best->ebx & bit(X86_FEATURE_AMD_IBPB)))
+		return true;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL));
+}
+
+static inline bool guest_cpuid_has_spec_ctrl(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && (best->ebx & bit(X86_FEATURE_AMD_IBRS)))
+		return true;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & (bit(X86_FEATURE_SPEC_CTRL) | bit(X86_FEATURE_SPEC_CTRL_SSBD)));
+}
+
+static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES));
+}
+
+static inline bool guest_cpuid_has_virt_ssbd(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	return best && (best->ebx & bit(X86_FEATURE_VIRT_SSBD));
+}
+
+
+
 /*
  * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
  */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a1afd80a68aa..3c70f6c76d3a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -56,7 +56,7 @@
 #define APIC_BUS_CYCLE_NS 1
 
 /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
-#define apic_debug(fmt, arg...)
+#define apic_debug(fmt, arg...) do {} while (0)
 
 #define APIC_LVT_NUM			6
 /* 14 is the version for Xeon and Pentium 8.4.8*/
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index df7827a981dd..ecdf724da371 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,6 +37,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
+#include <asm/microcode.h>
 #include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
@@ -147,6 +148,14 @@ struct vcpu_svm {
 		u64 gs_base;
 	} host;
 
+	u64 spec_ctrl;
+	/*
+	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+	 * translated into the appropriate L2_CFG bits on the host to
+	 * perform speculative control.
+	 */
+	u64 virt_spec_ctrl;
+
 	u32 *msrpm;
 
 	ulong nmi_iret_rip;
@@ -182,6 +191,8 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_CSTAR,				.always = true  },
 	{ .index = MSR_SYSCALL_MASK,			.always = true  },
 #endif
+	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
+	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -411,6 +422,7 @@ struct svm_cpu_data {
 	struct kvm_ldttss_desc *tss_desc;
 
 	struct page *save_area;
+	struct vmcb *current_vmcb;
 };
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
@@ -762,6 +774,25 @@ static bool valid_msr_intercept(u32 index)
 	return false;
 }
 
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
+{
+	u8 bit_write;
+	unsigned long tmp;
+	u32 offset;
+	u32 *msrpm;
+
+	msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
+				      to_svm(vcpu)->msrpm;
+
+	offset    = svm_msrpm_offset(msr);
+	bit_write = 2 * (msr & 0x0f) + 1;
+	tmp       = msrpm[offset];
+
+	BUG_ON(offset == MSR_INVALID);
+
+	return !!test_bit(bit_write,  &tmp);
+}
+
 static void set_msr_interception(u32 *msrpm, unsigned msr,
 				 int read, int write)
 {
@@ -1120,6 +1151,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
+	svm->spec_ctrl = 0;
+	svm->virt_spec_ctrl = 0;
+
 	if (!init_event) {
 		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
 					   MSR_IA32_APICBASE_ENABLE;
@@ -1210,11 +1244,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So do a full IBPB now.
+	 */
+	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
@@ -1239,6 +1279,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
 		}
 	}
+	if (sd->current_vmcb != svm->vmcb) {
+		sd->current_vmcb = svm->vmcb;
+		indirect_branch_prediction_barrier();
+	}
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3051,6 +3095,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_VM_CR:
 		msr_info->data = svm->nested.vm_cr_msr;
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		msr_info->data = svm->spec_ctrl;
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		msr_info->data = svm->virt_spec_ctrl;
+		break;
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = 0x01000065;
 		break;
@@ -3125,6 +3183,59 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+			return 1;
+
+		svm->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_svm_vmrun_msrpm.
+		 * We update the L1 MSR bit as well since it will end up
+		 * touching the MSR anyway now.
+		 */
+		set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+		if (is_guest_mode(vcpu))
+			break;
+		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		if (data & ~SPEC_CTRL_SSBD)
+			return 1;
+
+		svm->virt_spec_ctrl = data;
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
@@ -3811,6 +3922,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	local_irq_enable();
 
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
 		"mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
@@ -3915,6 +4034,26 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 #endif
 
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 */
+	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	reload_tss(vcpu);
 
 	local_irq_disable();
@@ -4015,7 +4154,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
 {
 	return true;
 }
@@ -4299,7 +4438,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
-	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5a4b1978cbf..e4b5fd72ca24 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -48,6 +48,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/spec-ctrl.h>
 
 #include "trace.h"
@@ -109,6 +110,14 @@ static u64 __read_mostly host_xss;
 static bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
+#define MSR_TYPE_R	1
+#define MSR_TYPE_W	2
+#define MSR_TYPE_RW	3
+
+#define MSR_BITMAP_MODE_X2APIC		1
+#define MSR_BITMAP_MODE_X2APIC_APICV	2
+#define MSR_BITMAP_MODE_LM		4
+
 #define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
 
 #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
@@ -172,7 +181,6 @@ module_param(ple_window_max, int, S_IRUGO);
 extern const ulong vmx_return;
 
 #define NR_AUTOLOAD_MSRS 8
-#define VMCS02_POOL_SIZE 1
 
 struct vmcs {
 	u32 revision_id;
@@ -189,6 +197,7 @@ struct loaded_vmcs {
 	struct vmcs *vmcs;
 	int cpu;
 	int launched;
+	unsigned long *msr_bitmap;
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -205,7 +214,7 @@ struct shared_msr_entry {
  * stored in guest memory specified by VMPTRLD, but is opaque to the guest,
  * which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
  * More than one of these structures may exist, if L1 runs multiple L2 guests.
- * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
+ * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
  * underlying hardware which will be used to run L2.
  * This structure is packed to ensure that its layout is identical across
  * machines (necessary for live migration).
@@ -384,13 +393,6 @@ struct __packed vmcs12 {
  */
 #define VMCS12_SIZE 0x1000
 
-/* Used to remember the last vmcs02 used for some recently used vmcs12s */
-struct vmcs02_list {
-	struct list_head list;
-	gpa_t vmptr;
-	struct loaded_vmcs vmcs02;
-};
-
 /*
  * The nested_vmx structure is part of vcpu_vmx, and holds information we need
  * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -412,16 +414,16 @@ struct nested_vmx {
 	 */
 	bool sync_shadow_vmcs;
 
-	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
-	struct list_head vmcs02_pool;
-	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
 	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
+
+	struct loaded_vmcs vmcs02;
+
 	/*
-	 * Guest pages referred to in vmcs02 with host-physical pointers, so
-	 * we must keep them pinned while L2 runs.
+	 * Guest pages referred to in the vmcs02 with host-physical
+	 * pointers, so we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
 	struct page *virtual_apic_page;
@@ -531,6 +533,7 @@ struct vcpu_vmx {
 	unsigned long         host_rsp;
 	u8                    fail;
 	bool                  nmi_known_unmasked;
+	u8		      msr_bitmap_mode;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
@@ -542,6 +545,10 @@ struct vcpu_vmx {
 	u64 		      msr_host_kernel_gs_base;
 	u64 		      msr_guest_kernel_gs_base;
 #endif
+
+	u64 		      arch_capabilities;
+	u64 		      spec_ctrl;
+
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
 	/*
@@ -889,6 +896,9 @@ static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -908,11 +918,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
 
 static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
-static unsigned long *vmx_msr_bitmap_legacy;
-static unsigned long *vmx_msr_bitmap_longmode;
-static unsigned long *vmx_msr_bitmap_legacy_x2apic;
-static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
 static unsigned long *vmx_vmread_bitmap;
 static unsigned long *vmx_vmwrite_bitmap;
 
@@ -1689,6 +1694,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+/*
+ * Check if MSR is intercepted for currently loaded MSR bitmap.
+ */
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 		unsigned long entry, unsigned long exit)
 {
@@ -2074,6 +2125,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
+		indirect_branch_prediction_barrier();
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
@@ -2353,27 +2405,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 	vmx->guest_msrs[from] = tmp;
 }
 
-static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
-{
-	unsigned long *msr_bitmap;
-
-	if (is_guest_mode(vcpu))
-		msr_bitmap = vmx_msr_bitmap_nested;
-	else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
-		if (is_long_mode(vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
-	} else {
-		if (is_long_mode(vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy;
-	}
-
-	vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-}
-
 /*
  * Set up the vmcs to automatically save and restore system
  * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
@@ -2414,7 +2445,7 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	vmx->save_nmsrs = save_nmsrs;
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmx_set_msr_bitmap(&vmx->vcpu);
+		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
 /*
@@ -2828,6 +2859,19 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		msr_info->data = guest_read_tsc(vcpu);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		msr_info->data = to_vmx(vcpu)->spec_ctrl;
+		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_arch_capabilities(vcpu))
+			return 1;
+		msr_info->data = to_vmx(vcpu)->arch_capabilities;
+		break;
 	case MSR_IA32_SYSENTER_CS:
 		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
@@ -2927,6 +2971,68 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+			return 1;
+
+		vmx->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging. We update the vmcs01 here for L1 as well
+		 * since it will end up touching the MSR anyway now.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+					      MSR_IA32_SPEC_CTRL,
+					      MSR_TYPE_RW);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * vmcs02.msr_bitmap here since it gets completely overwritten
+		 * in the merging.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
+					      MSR_TYPE_W);
+		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vmx->arch_capabilities = data;
+		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -3352,11 +3458,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 	return vmcs;
 }
 
-static struct vmcs *alloc_vmcs(void)
-{
-	return alloc_vmcs_cpu(raw_smp_processor_id());
-}
-
 static void free_vmcs(struct vmcs *vmcs)
 {
 	free_pages((unsigned long)vmcs, vmcs_config.order);
@@ -3372,6 +3473,34 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	loaded_vmcs_clear(loaded_vmcs);
 	free_vmcs(loaded_vmcs->vmcs);
 	loaded_vmcs->vmcs = NULL;
+	if (loaded_vmcs->msr_bitmap)
+		free_page((unsigned long)loaded_vmcs->msr_bitmap);
+}
+
+static struct vmcs *alloc_vmcs(void)
+{
+	return alloc_vmcs_cpu(raw_smp_processor_id());
+}
+
+static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+	loaded_vmcs->vmcs = alloc_vmcs();
+	if (!loaded_vmcs->vmcs)
+		return -ENOMEM;
+
+	loaded_vmcs_init(loaded_vmcs);
+
+	if (cpu_has_vmx_msr_bitmap()) {
+		loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+		if (!loaded_vmcs->msr_bitmap)
+			goto out_vmcs;
+		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+	}
+	return 0;
+
+out_vmcs:
+	free_loaded_vmcs(loaded_vmcs);
+	return -ENOMEM;
 }
 
 static void free_kvm_area(void)
@@ -4370,10 +4499,8 @@ static void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-#define MSR_TYPE_R	1
-#define MSR_TYPE_W	2
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
-						u32 msr, int type)
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -4407,8 +4534,8 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 	}
 }
 
-static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
-						u32 msr, int type)
+static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+							 u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -4488,37 +4615,76 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
 	}
 }
 
-static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+			     			      u32 msr, int type, bool value)
 {
-	if (!longmode_only)
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
-						msr, MSR_TYPE_R | MSR_TYPE_W);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
-						msr, MSR_TYPE_R | MSR_TYPE_W);
+	if (value)
+		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+	else
+		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
 }
 
-static void vmx_enable_intercept_msr_read_x2apic(u32 msr)
+static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 {
-	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_R);
-	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_R);
+	u8 mode = 0;
+
+	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+		mode |= MSR_BITMAP_MODE_X2APIC;
+		if (enable_apicv)
+			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
+	}
+
+	if (is_long_mode(vcpu))
+		mode |= MSR_BITMAP_MODE_LM;
+
+	return mode;
 }
 
-static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
+static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
+					 u8 mode)
 {
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_R);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_R);
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+
+	if (mode & MSR_BITMAP_MODE_X2APIC) {
+		/*
+		 * TPR reads and writes can be virtualized even if virtual interrupt
+		 * delivery is not in use.
+		 */
+		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
+			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_ID), MSR_TYPE_R);
+			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+		}
+	}
 }
 
-static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 {
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
-			msr, MSR_TYPE_W);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
-			msr, MSR_TYPE_W);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	u8 mode = vmx_msr_bitmap_mode(vcpu);
+	u8 changed = mode ^ vmx->msr_bitmap_mode;
+
+	if (!changed)
+		return;
+
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
+				  !(mode & MSR_BITMAP_MODE_LM));
+
+	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
+		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+
+	vmx->msr_bitmap_mode = mode;
 }
 
 static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
@@ -4526,6 +4692,28 @@ static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 	return enable_apicv && lapic_in_kernel(vcpu);
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4533,18 +4721,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	void *vapic_page;
 	u16 status;
 
-	if (vmx->nested.pi_desc &&
-	    vmx->nested.pi_pending) {
-		vmx->nested.pi_pending = false;
-		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return;
-
-		max_irr = find_last_bit(
-			(unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
 
-		if (max_irr == 256)
-			return;
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
 
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
@@ -4556,6 +4741,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -4818,7 +5005,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
 	}
 	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
+		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
 
 	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
 
@@ -4890,6 +5077,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
@@ -4918,6 +5107,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u64 cr0;
 
 	vmx->rmode.vm86_active = 0;
+	vmx->spec_ctrl = 0;
 
 	vmx->soft_vnmi_blocked = 0;
 
@@ -6159,7 +6349,7 @@ static void wakeup_handler(void)
 
 static __init int hardware_setup(void)
 {
-	int r = -ENOMEM, i, msr;
+	int r = -ENOMEM, i;
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
 
@@ -6174,38 +6364,13 @@ static __init int hardware_setup(void)
 	if (!vmx_io_bitmap_b)
 		goto out;
 
-	vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy)
-		goto out1;
-
-	vmx_msr_bitmap_legacy_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_legacy_x2apic)
-		goto out2;
-
-	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode)
-		goto out3;
-
-	vmx_msr_bitmap_longmode_x2apic =
-				(unsigned long *)__get_free_page(GFP_KERNEL);
-	if (!vmx_msr_bitmap_longmode_x2apic)
-		goto out4;
-
-	if (nested) {
-		vmx_msr_bitmap_nested =
-			(unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!vmx_msr_bitmap_nested)
-			goto out5;
-	}
-
 	vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmread_bitmap)
-		goto out6;
+		goto out1;
 
 	vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmwrite_bitmap)
-		goto out7;
+		goto out2;
 
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
@@ -6214,14 +6379,9 @@ static __init int hardware_setup(void)
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
-	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
-	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-	if (nested)
-		memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
-
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
-		goto out8;
+		goto out3;
 	}
 
 	if (boot_cpu_has(X86_FEATURE_NX))
@@ -6287,38 +6447,8 @@ static __init int hardware_setup(void)
 		kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
 	}
 
-	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-
-	memcpy(vmx_msr_bitmap_legacy_x2apic,
-			vmx_msr_bitmap_legacy, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_longmode_x2apic,
-			vmx_msr_bitmap_longmode, PAGE_SIZE);
-
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
-	if (enable_apicv) {
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			vmx_disable_intercept_msr_read_x2apic(msr);
-
-		/* According SDM, in x2apic mode, the whole id reg is used.
-		 * But in KVM, it only use the highest eight bits. Need to
-		 * intercept it */
-		vmx_enable_intercept_msr_read_x2apic(0x802);
-		/* TMCCT */
-		vmx_enable_intercept_msr_read_x2apic(0x839);
-		/* TPR */
-		vmx_disable_intercept_msr_write_x2apic(0x808);
-		/* EOI */
-		vmx_disable_intercept_msr_write_x2apic(0x80b);
-		/* SELF-IPI */
-		vmx_disable_intercept_msr_write_x2apic(0x83f);
-	}
-
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,
 			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
@@ -6349,21 +6479,10 @@ static __init int hardware_setup(void)
 
 	return alloc_kvm_area();
 
-out8:
-	free_page((unsigned long)vmx_vmwrite_bitmap);
-out7:
-	free_page((unsigned long)vmx_vmread_bitmap);
-out6:
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-out4:
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
 out3:
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+	free_page((unsigned long)vmx_vmwrite_bitmap);
 out2:
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
+	free_page((unsigned long)vmx_vmread_bitmap);
 out1:
 	free_page((unsigned long)vmx_io_bitmap_b);
 out:
@@ -6374,16 +6493,10 @@ out:
 
 static __exit void hardware_unsetup(void)
 {
-	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-	free_page((unsigned long)vmx_msr_bitmap_legacy);
-	free_page((unsigned long)vmx_msr_bitmap_longmode);
 	free_page((unsigned long)vmx_io_bitmap_b);
 	free_page((unsigned long)vmx_io_bitmap_a);
 	free_page((unsigned long)vmx_vmwrite_bitmap);
 	free_page((unsigned long)vmx_vmread_bitmap);
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
 
 	free_kvm_area();
 }
@@ -6427,93 +6540,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu)
 }
 
 /*
- * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
- * We could reuse a single VMCS for all the L2 guests, but we also want the
- * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
- * allows keeping them loaded on the processor, and in the future will allow
- * optimizations where prepare_vmcs02 doesn't need to set all the fields on
- * every entry if they never change.
- * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
- * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
- *
- * The following functions allocate and free a vmcs02 in this pool.
- */
-
-/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
-static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
-{
-	struct vmcs02_list *item;
-	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
-		if (item->vmptr == vmx->nested.current_vmptr) {
-			list_move(&item->list, &vmx->nested.vmcs02_pool);
-			return &item->vmcs02;
-		}
-
-	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
-		/* Recycle the least recently used VMCS. */
-		item = list_entry(vmx->nested.vmcs02_pool.prev,
-			struct vmcs02_list, list);
-		item->vmptr = vmx->nested.current_vmptr;
-		list_move(&item->list, &vmx->nested.vmcs02_pool);
-		return &item->vmcs02;
-	}
-
-	/* Create a new VMCS */
-	item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
-	if (!item)
-		return NULL;
-	item->vmcs02.vmcs = alloc_vmcs();
-	if (!item->vmcs02.vmcs) {
-		kfree(item);
-		return NULL;
-	}
-	loaded_vmcs_init(&item->vmcs02);
-	item->vmptr = vmx->nested.current_vmptr;
-	list_add(&(item->list), &(vmx->nested.vmcs02_pool));
-	vmx->nested.vmcs02_num++;
-	return &item->vmcs02;
-}
-
-/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
-static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
-{
-	struct vmcs02_list *item;
-	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
-		if (item->vmptr == vmptr) {
-			free_loaded_vmcs(&item->vmcs02);
-			list_del(&item->list);
-			kfree(item);
-			vmx->nested.vmcs02_num--;
-			return;
-		}
-}
-
-/*
- * Free all VMCSs saved for this vcpu, except the one pointed by
- * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
- * must be &vmx->vmcs01.
- */
-static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
-{
-	struct vmcs02_list *item, *n;
-
-	WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
-	list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
-		/*
-		 * Something will leak if the above WARN triggers.  Better than
-		 * a use-after-free.
-		 */
-		if (vmx->loaded_vmcs == &item->vmcs02)
-			continue;
-
-		free_loaded_vmcs(&item->vmcs02);
-		list_del(&item->list);
-		kfree(item);
-		vmx->nested.vmcs02_num--;
-	}
-}
-
-/*
  * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
  * set the success or error code of an emulated VMX instruction, as specified
  * by Vol 2B, VMX Instruction Reference, "Conventions".
@@ -6786,6 +6812,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	struct vmcs *shadow_vmcs;
 	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
 		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	int r;
 
 	/* The Intel VMX Instruction Reference lists a bunch of bits that
 	 * are prerequisite to running VMXON, most notably cr4.VMXE must be
@@ -6825,10 +6852,14 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	r = alloc_loaded_vmcs(&vmx->nested.vmcs02);
+	if (r < 0)
+		goto out_vmcs02;
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
 		if (!shadow_vmcs)
-			return -ENOMEM;
+			goto out_shadow_vmcs;
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -6836,9 +6867,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		vmx->nested.current_shadow_vmcs = shadow_vmcs;
 	}
 
-	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
-	vmx->nested.vmcs02_num = 0;
-
 	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_REL);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
@@ -6850,6 +6878,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
+
+out_shadow_vmcs:
+	free_loaded_vmcs(&vmx->nested.vmcs02);
+
+out_vmcs02:
+	return -ENOMEM;
 }
 
 /*
@@ -6921,7 +6955,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
-	/* Unpin physical memory we referred to in current vmcs02 */
+	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
@@ -6937,7 +6971,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 		vmx->nested.pi_desc = NULL;
 	}
 
-	nested_free_all_saved_vmcss(vmx);
+	free_loaded_vmcs(&vmx->nested.vmcs02);
 }
 
 /* Emulate the VMXOFF instruction */
@@ -6971,8 +7005,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 			vmptr + offsetof(struct vmcs12, launch_state),
 			&zero, sizeof(zero));
 
-	nested_free_vmcs02(vmx, vmptr);
-
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
@@ -7757,6 +7789,19 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+	 * Page). The CPU may write to these pages via their host
+	 * physical address while L2 is running, bypassing any
+	 * address-translation-based dirty tracking (e.g. EPT write
+	 * protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
 	if (vmx->nested.nested_run_pending)
 		return false;
 
@@ -8244,7 +8289,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
-	vmx_set_msr_bitmap(vcpu);
+	vmx_update_msr_bitmap(vcpu);
 }
 
 static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
@@ -8413,9 +8458,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 		local_irq_enable();
 }
 
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
 {
-	return enable_unrestricted_guest || emulate_invalid_guest_state;
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
 }
 
 static bool vmx_mpx_supported(void)
@@ -8607,7 +8664,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+
 	vmx->__launched = vmx->loaded_vmcs->launched;
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
@@ -8725,6 +8791,26 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 */
+	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
+
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
 
@@ -8824,6 +8910,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 {
 	int err;
 	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	unsigned long *msr_bitmap;
 	int cpu;
 
 	if (!vmx)
@@ -8856,16 +8943,24 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx->guest_msrs)
 		goto free_pml;
 
-	vmx->loaded_vmcs = &vmx->vmcs01;
-	vmx->loaded_vmcs->vmcs = alloc_vmcs();
-	if (!vmx->loaded_vmcs->vmcs)
-		goto free_msrs;
 	if (!vmm_exclusive)
 		kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id())));
-	loaded_vmcs_init(vmx->loaded_vmcs);
+	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (!vmm_exclusive)
 		kvm_cpu_vmxoff();
+	if (err < 0)
+		goto free_msrs;
+
+	msr_bitmap = vmx->vmcs01.msr_bitmap;
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	vmx->msr_bitmap_mode = 0;
 
+	vmx->loaded_vmcs = &vmx->vmcs01;
 	cpu = get_cpu();
 	vmx_vcpu_load(&vmx->vcpu, cpu);
 	vmx->vcpu.cpu = cpu;
@@ -9248,9 +9343,26 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 {
 	int msr;
 	struct page *page;
-	unsigned long *msr_bitmap;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+	/*
+	 * pred_cmd & spec_ctrl are trying to verify two things:
+	 *
+	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+	 *    ensures that we do not accidentally generate an L02 MSR bitmap
+	 *    from the L12 MSR bitmap that is too permissive.
+	 * 2. That L1 or L2s have actually used the MSR. This avoids
+	 *    unnecessarily merging of the bitmap if the MSR is unused. This
+	 *    works properly because we only update the L01 MSR bitmap lazily.
+	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+	 *    updated to reflect this when L1 (or its L2s) actually write to
+	 *    the MSR.
+	 */
+	bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+	bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
 
-	if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
+	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    !pred_cmd && !spec_ctrl)
 		return false;
 
 	page = nested_get_page(vcpu, vmcs12->msr_bitmap);
@@ -9258,59 +9370,46 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 		return false;
 	}
-	msr_bitmap = (unsigned long *)kmap(page);
+	msr_bitmap_l1 = (unsigned long *)kmap(page);
+
+	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
 
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
 			for (msr = 0x800; msr <= 0x8ff; msr++)
 				nested_vmx_disable_intercept_for_msr(
-					msr_bitmap,
-					vmx_msr_bitmap_nested,
+					msr_bitmap_l1, msr_bitmap_l0,
 					msr, MSR_TYPE_R);
-		/* TPR is allowed */
-		nested_vmx_disable_intercept_for_msr(msr_bitmap,
-				vmx_msr_bitmap_nested,
+
+		nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
 				MSR_TYPE_R | MSR_TYPE_W);
+
 		if (nested_cpu_has_vid(vmcs12)) {
-			/* EOI and self-IPI are allowed */
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_EOI >> 4),
 				MSR_TYPE_W);
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
 				MSR_TYPE_W);
 		}
-	} else {
-		/*
-		 * Enable reading intercept of all the x2apic
-		 * MSRs. We should not rely on vmcs12 to do any
-		 * optimizations here, it may have been modified
-		 * by L1.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				msr,
-				MSR_TYPE_R);
-
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_EOI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
-				MSR_TYPE_W);
 	}
+
+	if (spec_ctrl)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_SPEC_CTRL,
+					MSR_TYPE_R | MSR_TYPE_W);
+
+	if (pred_cmd)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_PRED_CMD,
+					MSR_TYPE_W);
+
 	kunmap(page);
 	nested_release_page_clean(page);
 
@@ -9729,10 +9828,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
-		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
-		/* MSR_BITMAP will be set by following vmx_set_efer. */
-	} else
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+		; /* MSR_BITMAP will be set by following vmx_set_efer. */
+	else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
 	/*
@@ -9784,6 +9883,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	else
 		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
+	if (cpu_has_vmx_msr_bitmap())
+		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
 	if (enable_vpid) {
 		/*
 		 * There is no direct mapping between vpid02 and vpid12, the
@@ -9876,7 +9978,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int cpu;
-	struct loaded_vmcs *vmcs02;
 	bool ia32e;
 	u32 msr_entry_idx;
 
@@ -10016,10 +10117,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 
-	vmcs02 = nested_get_current_vmcs02(vmx);
-	if (!vmcs02)
-		return -ENOMEM;
-
 	enter_guest_mode(vcpu);
 
 	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
@@ -10028,7 +10125,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 
 	cpu = get_cpu();
-	vmx->loaded_vmcs = vmcs02;
+	vmx->loaded_vmcs = &vmx->nested.vmcs02;
 	vmx_vcpu_put(vcpu);
 	vmx_vcpu_load(vcpu, cpu);
 	vcpu->cpu = cpu;
@@ -10489,7 +10586,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmx_set_msr_bitmap(vcpu);
+		vmx_update_msr_bitmap(vcpu);
 
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
@@ -10540,10 +10637,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS));
 	vmx_segment_cache_clear(vmx);
 
-	/* if no vmcs02 cache requested, remove the one we used */
-	if (VMCS02_POOL_SIZE == 0)
-		nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
-
 	load_vmcs12_host_state(vcpu, vmcs12);
 
 	/* Update TSC_OFFSET if TSC was changed while L2 ran */
@@ -10871,7 +10964,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vcpu_create = vmx_create_vcpu,
 	.vcpu_free = vmx_free_vcpu,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e6ab034f0bc7..aa1a0277a678 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -961,6 +961,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
 };
 
 static unsigned num_msrs_to_save;
@@ -984,6 +985,7 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
 	MSR_IA32_SMBASE,
+	MSR_AMD64_VIRT_SPEC_CTRL,
 };
 
 static unsigned num_emulated_msrs;
@@ -2583,7 +2585,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
@@ -4072,14 +4074,8 @@ static void kvm_init_msr_list(void)
 	num_msrs_to_save = j;
 
 	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
-		switch (emulated_msrs[i]) {
-		case MSR_IA32_SMBASE:
-			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
-				continue;
-			break;
-		default:
-			break;
-		}
+		if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+			continue;
 
 		if (j < i)
 			emulated_msrs[j] = emulated_msrs[i];
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 91d93b95bd86..0a6fcae404f8 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,12 +570,12 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
@@ -583,12 +583,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
 		n = __copy_user_zeroing_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
@@ -596,13 +596,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel((void __user *)to,
 				      (const void *)from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero);
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -619,7 +619,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 #else
 	__copy_user_zeroing(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache);
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);
@@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 #else
 	__copy_user(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index ae9a37bf1371..7d2542ad346a 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -388,7 +388,7 @@ slow_irqon:
 
 		ret = get_user_pages_unlocked(current, mm, start,
 					      (end - start) >> PAGE_SHIFT,
-					      write, 0, pages);
+					      pages, write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7ed47b1e6f42..7e94fc6f608a 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -536,10 +536,9 @@ static int mpx_resolve_fault(long __user *addr, int write)
 {
 	long gup_ret;
 	int nr_pages = 1;
-	int force = 0;
 
 	gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
-				 nr_pages, write, force, NULL, NULL);
+				 nr_pages, write ? FOLL_WRITE : 0, NULL, NULL);
 	/*
 	 * get_user_pages() returns number of pages gotten.
 	 * 0 means we failed to fault in and get anything,
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 524142117296..82324fc25d5e 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -179,7 +179,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 			num--;
 		}
 
-		if (efi_x >= si->lfb_width) {
+		if (efi_x + font->width > si->lfb_width) {
 			efi_x = 0;
 			efi_y += font->height;
 		}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ba514fa733de..d543172b20b3 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4297,6 +4297,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "SSD*INTEL*",			NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Samsung*SSD*",		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "SAMSUNG*SSD*",		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "SAMSUNG*MZ7KM*",		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "ST[1248][0248]0[FH]*",	NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
 
 	/*
diff --git a/drivers/clk/mmp/clk.c b/drivers/clk/mmp/clk.c
index 61893fe73251..18b6c9b55b95 100644
--- a/drivers/clk/mmp/clk.c
+++ b/drivers/clk/mmp/clk.c
@@ -182,7 +182,7 @@ void mmp_clk_add(struct mmp_clk_unit *unit, unsigned int id,
 		pr_err("CLK %d has invalid pointer %p\n", id, clk);
 		return;
 	}
-	if (id > unit->nr_clks) {
+	if (id >= unit->nr_clks) {
 		pr_err("CLK %d is invalid\n", id);
 		return;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e40a6d8b0b92..062c23125b2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -496,9 +496,13 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 	int r;
 
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
+	unsigned int flags = 0;
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 
+	if (write)
+		flags |= FOLL_WRITE;
+
 	if (current->mm != gtt->usermm)
 		return -EPERM;
 
@@ -519,7 +523,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 		struct page **pages = ttm->pages + pinned;
 
 		r = get_user_pages(current, current->mm, userptr, num_pages,
-				   write, 0, pages, NULL);
+				   flags, pages, NULL);
 		if (r < 0)
 			goto release_pages;
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 21085f669e21..b19ba1792607 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -968,9 +968,21 @@ static int get_clock(void *i2c_priv)
 {
 	struct ast_i2c_chan *i2c = i2c_priv;
 	struct ast_private *ast = i2c->dev->dev_private;
-	uint32_t val;
+	uint32_t val, val2, count, pass;
+
+	count = 0;
+	pass = 0;
+	val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01;
+	do {
+		val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01;
+		if (val == val2) {
+			pass++;
+		} else {
+			pass = 0;
+			val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01;
+		}
+	} while ((pass < 5) && (count++ < 0x10000));
 
-	val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4;
 	return val & 1 ? 1 : 0;
 }
 
@@ -978,9 +990,21 @@ static int get_data(void *i2c_priv)
 {
 	struct ast_i2c_chan *i2c = i2c_priv;
 	struct ast_private *ast = i2c->dev->dev_private;
-	uint32_t val;
+	uint32_t val, val2, count, pass;
+
+	count = 0;
+	pass = 0;
+	val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01;
+	do {
+		val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01;
+		if (val == val2) {
+			pass++;
+		} else {
+			pass = 0;
+			val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01;
+		}
+	} while ((pass < 5) && (count++ < 0x10000));
 
-	val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5;
 	return val & 1 ? 1 : 0;
 }
 
@@ -993,7 +1017,7 @@ static void set_clock(void *i2c_priv, int clock)
 
 	for (i = 0; i < 0x10000; i++) {
 		ujcrb7 = ((clock & 0x01) ? 0 : 1);
-		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfe, ujcrb7);
+		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf4, ujcrb7);
 		jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x01);
 		if (ujcrb7 == jtemp)
 			break;
@@ -1009,7 +1033,7 @@ static void set_data(void *i2c_priv, int data)
 
 	for (i = 0; i < 0x10000; i++) {
 		ujcrb7 = ((data & 0x01) ? 0 : 1) << 2;
-		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfb, ujcrb7);
+		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf1, ujcrb7);
 		jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x04);
 		if (ujcrb7 == jtemp)
 			break;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index c17efdb238a6..639ea28808e2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -471,7 +471,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 		goto err_free;
 	}
 
-	ret = get_vaddr_frames(start, npages, true, true, g2d_userptr->vec);
+	ret = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
+		g2d_userptr->vec);
 	if (ret != npages) {
 		DRM_ERROR("failed to get user pages from userptr.\n");
 		if (ret < 0)
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 359fe2b8bb8a..b02113b57d51 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -581,13 +581,17 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 		pvec = drm_malloc_ab(npages, sizeof(struct page *));
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
+		unsigned int flags = 0;
+
+		if (!obj->userptr.read_only)
+			flags |= FOLL_WRITE;
 
 		down_read(&mm->mmap_sem);
 		while (pinned < npages) {
 			ret = get_user_pages(work->task, mm,
 					     obj->userptr.ptr + pinned * PAGE_SIZE,
 					     npages - pinned,
-					     !obj->userptr.read_only, 0,
+					     flags,
 					     pvec + pinned, NULL);
 			if (ret < 0)
 				break;
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 7d40f38092d4..99f89841a74a 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -95,8 +95,13 @@ static void msm_atomic_wait_for_commit_done(
 		if (old_state->legacy_cursor_update)
 			continue;
 
+		if (drm_crtc_vblank_get(crtc))
+			continue;
+
 		if (kms->funcs->wait_for_crtc_commit_done)
 			kms->funcs->wait_for_crtc_commit_done(kms, crtc);
+
+		drm_crtc_vblank_put(crtc);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index d684e2b79d2b..0c380fe77382 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -557,7 +557,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 		struct page **pages = ttm->pages + pinned;
 
 		r = get_user_pages(current, current->mm, userptr, num_pages,
-				   write, 0, pages, NULL);
+				   write ? FOLL_WRITE : 0, pages, NULL);
 		if (r < 0)
 			goto release_pages;
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index d1f3be78c649..f22e1e1ee64a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -547,11 +547,6 @@ static int rockchip_drm_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static void rockchip_drm_platform_shutdown(struct platform_device *pdev)
-{
-	rockchip_drm_platform_remove(pdev);
-}
-
 static const struct of_device_id rockchip_drm_dt_ids[] = {
 	{ .compatible = "rockchip,display-subsystem", },
 	{ /* sentinel */ },
@@ -561,7 +556,6 @@ MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids);
 static struct platform_driver rockchip_drm_platform_driver = {
 	.probe = rockchip_drm_platform_probe,
 	.remove = rockchip_drm_platform_remove,
-	.shutdown = rockchip_drm_platform_shutdown,
 	.driver = {
 		.name = "rockchip-drm",
 		.of_match_table = rockchip_drm_dt_ids,
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index d0cbd5ecd7f0..4459cb32d1fe 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -242,8 +242,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	ret = get_user_pages(current, current->mm,
 			     (unsigned long)xfer->mem_addr,
 			     vsg->num_pages,
-			     (vsg->direction == DMA_FROM_DEVICE),
-			     0, vsg->pages, NULL);
+			     (vsg->direction == DMA_FROM_DEVICE) ? FOLL_WRITE : 0,
+			     vsg->pages, NULL);
 
 	up_read(&current->mm->mmap_sem);
 	if (ret != vsg->num_pages) {
diff --git a/drivers/gpu/msm/kgsl.c b/drivers/gpu/msm/kgsl.c
index 55ebc0a8e26c..b8519a16df92 100644
--- a/drivers/gpu/msm/kgsl.c
+++ b/drivers/gpu/msm/kgsl.c
@@ -2149,7 +2149,8 @@ static int memdesc_sg_virt(struct kgsl_memdesc *memdesc, struct file *vmfile)
 
 	if (ret == 0) {
 		npages = get_user_pages(current, current->mm, memdesc->useraddr,
-					sglen, write, 0, pages, NULL);
+					sglen, write ? FOLL_WRITE : 0,
+					pages, NULL);
 		ret = (npages < 0) ? (int)npages : 0;
 	}
 	up_read(&current->mm->mmap_sem);
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 9ac6e1673375..1f291b344178 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -273,7 +273,7 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg,
 		break;
 	case INA2XX_CURRENT:
 		/* signed register, result in mA */
-		val = regval * data->current_lsb_uA;
+		val = (s16)regval * data->current_lsb_uA;
 		val = DIV_ROUND_CLOSEST(val, 1000);
 		break;
 	case INA2XX_CALIBRATION:
diff --git a/drivers/hwmon/w83795.c b/drivers/hwmon/w83795.c
index 49276bbdac3d..1bb80f992aa8 100644
--- a/drivers/hwmon/w83795.c
+++ b/drivers/hwmon/w83795.c
@@ -1691,7 +1691,7 @@ store_sf_setup(struct device *dev, struct device_attribute *attr,
  * somewhere else in the code
  */
 #define SENSOR_ATTR_TEMP(index) {					\
-	SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 4 ? S_IWUSR : 0), \
+	SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 5 ? S_IWUSR : 0), \
 		show_temp_mode, store_temp_mode, NOT_USED, index - 1),	\
 	SENSOR_ATTR_2(temp##index##_input, S_IRUGO, show_temp,		\
 		NULL, TEMP_READ, index - 1),				\
diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c
index c335cc7852f9..9c9fd2e87a4b 100644
--- a/drivers/i2c/busses/i2c-axxia.c
+++ b/drivers/i2c/busses/i2c-axxia.c
@@ -74,8 +74,7 @@
 				 MST_STATUS_ND)
 #define   MST_STATUS_ERR	(MST_STATUS_NAK | \
 				 MST_STATUS_AL  | \
-				 MST_STATUS_IP  | \
-				 MST_STATUS_TSS)
+				 MST_STATUS_IP)
 #define MST_TX_BYTES_XFRD	0x50
 #define MST_RX_BYTES_XFRD	0x54
 #define SCL_HIGH_PERIOD		0x80
@@ -241,7 +240,7 @@ static int axxia_i2c_empty_rx_fifo(struct axxia_i2c_dev *idev)
 			 */
 			if (c <= 0 || c > I2C_SMBUS_BLOCK_MAX) {
 				idev->msg_err = -EPROTO;
-				i2c_int_disable(idev, ~0);
+				i2c_int_disable(idev, ~MST_STATUS_TSS);
 				complete(&idev->msg_complete);
 				break;
 			}
@@ -299,14 +298,19 @@ static irqreturn_t axxia_i2c_isr(int irq, void *_dev)
 
 	if (status & MST_STATUS_SCC) {
 		/* Stop completed */
-		i2c_int_disable(idev, ~0);
+		i2c_int_disable(idev, ~MST_STATUS_TSS);
 		complete(&idev->msg_complete);
 	} else if (status & MST_STATUS_SNS) {
 		/* Transfer done */
-		i2c_int_disable(idev, ~0);
+		i2c_int_disable(idev, ~MST_STATUS_TSS);
 		if (i2c_m_rd(idev->msg) && idev->msg_xfrd < idev->msg->len)
 			axxia_i2c_empty_rx_fifo(idev);
 		complete(&idev->msg_complete);
+	} else if (status & MST_STATUS_TSS) {
+		/* Transfer timeout */
+		idev->msg_err = -ETIMEDOUT;
+		i2c_int_disable(idev, ~MST_STATUS_TSS);
+		complete(&idev->msg_complete);
 	} else if (unlikely(status & MST_STATUS_ERR)) {
 		/* Transfer error */
 		i2c_int_disable(idev, ~0);
@@ -339,10 +343,10 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg)
 	u32 rx_xfer, tx_xfer;
 	u32 addr_1, addr_2;
 	unsigned long time_left;
+	unsigned int wt_value;
 
 	idev->msg = msg;
 	idev->msg_xfrd = 0;
-	idev->msg_err = 0;
 	reinit_completion(&idev->msg_complete);
 
 	if (i2c_m_ten(msg)) {
@@ -382,9 +386,18 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg)
 	else if (axxia_i2c_fill_tx_fifo(idev) != 0)
 		int_mask |= MST_STATUS_TFL;
 
+	wt_value = WT_VALUE(readl(idev->base + WAIT_TIMER_CONTROL));
+	/* Disable wait timer temporarly */
+	writel(wt_value, idev->base + WAIT_TIMER_CONTROL);
+	/* Check if timeout error happened */
+	if (idev->msg_err)
+		goto out;
+
 	/* Start manual mode */
 	writel(CMD_MANUAL, idev->base + MST_COMMAND);
 
+	writel(WT_EN | wt_value, idev->base + WAIT_TIMER_CONTROL);
+
 	i2c_int_enable(idev, int_mask);
 
 	time_left = wait_for_completion_timeout(&idev->msg_complete,
@@ -395,13 +408,15 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg)
 	if (readl(idev->base + MST_COMMAND) & CMD_BUSY)
 		dev_warn(idev->dev, "busy after xfer\n");
 
-	if (time_left == 0)
+	if (time_left == 0) {
 		idev->msg_err = -ETIMEDOUT;
-
-	if (idev->msg_err == -ETIMEDOUT)
 		i2c_recover_bus(&idev->adapter);
+		axxia_i2c_init(idev);
+	}
 
-	if (unlikely(idev->msg_err) && idev->msg_err != -ENXIO)
+out:
+	if (unlikely(idev->msg_err) && idev->msg_err != -ENXIO &&
+			idev->msg_err != -ETIMEDOUT)
 		axxia_i2c_init(idev);
 
 	return idev->msg_err;
@@ -409,7 +424,7 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg)
 
 static int axxia_i2c_stop(struct axxia_i2c_dev *idev)
 {
-	u32 int_mask = MST_STATUS_ERR | MST_STATUS_SCC;
+	u32 int_mask = MST_STATUS_ERR | MST_STATUS_SCC | MST_STATUS_TSS;
 	unsigned long time_left;
 
 	reinit_completion(&idev->msg_complete);
@@ -436,6 +451,9 @@ axxia_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 	int i;
 	int ret = 0;
 
+	idev->msg_err = 0;
+	i2c_int_enable(idev, MST_STATUS_TSS);
+
 	for (i = 0; ret == 0 && i < num; ++i)
 		ret = axxia_i2c_xfer_msg(idev, &msgs[i]);
 
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c
index efefcfa24a4c..d2178f701b41 100644
--- a/drivers/i2c/busses/i2c-scmi.c
+++ b/drivers/i2c/busses/i2c-scmi.c
@@ -364,6 +364,7 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 {
 	struct acpi_smbus_cmi *smbus_cmi;
 	const struct acpi_device_id *id;
+	int ret;
 
 	smbus_cmi = kzalloc(sizeof(struct acpi_smbus_cmi), GFP_KERNEL);
 	if (!smbus_cmi)
@@ -385,8 +386,10 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 	acpi_walk_namespace(ACPI_TYPE_METHOD, smbus_cmi->handle, 1,
 			    acpi_smbus_cmi_query_methods, NULL, smbus_cmi, NULL);
 
-	if (smbus_cmi->cap_info == 0)
+	if (smbus_cmi->cap_info == 0) {
+		ret = -ENODEV;
 		goto err;
+	}
 
 	snprintf(smbus_cmi->adapter.name, sizeof(smbus_cmi->adapter.name),
 		"SMBus CMI adapter %s",
@@ -397,7 +400,8 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 	smbus_cmi->adapter.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
 	smbus_cmi->adapter.dev.parent = &device->dev;
 
-	if (i2c_add_adapter(&smbus_cmi->adapter)) {
+	ret = i2c_add_adapter(&smbus_cmi->adapter);
+	if (ret) {
 		dev_err(&device->dev, "Couldn't register adapter!\n");
 		goto err;
 	}
@@ -407,7 +411,7 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 err:
 	kfree(smbus_cmi);
 	device->driver_data = NULL;
-	return -EIO;
+	return ret;
 }
 
 static int acpi_smbus_cmi_remove(struct acpi_device *device)
diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c
index 96a345248224..0add5bb3cee8 100644
--- a/drivers/ide/pmac.c
+++ b/drivers/ide/pmac.c
@@ -920,6 +920,7 @@ static u8 pmac_ide_cable_detect(ide_hwif_t *hwif)
 	struct device_node *root = of_find_node_by_path("/");
 	const char *model = of_get_property(root, "model", NULL);
 
+	of_node_put(root);
 	/* Get cable type from device-tree. */
 	if (cable && !strncmp(cable, "80-", 3)) {
 		/* Some drives fail to detect 80c cable in PowerBook */
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 98fd9a594841..8762eac47570 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -95,6 +95,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	DEFINE_DMA_ATTRS(attrs);
 	struct scatterlist *sg, *sg_list_start;
 	int need_release = 0;
+	unsigned int gup_flags = FOLL_WRITE;
 
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
@@ -177,6 +178,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (ret)
 		goto out;
 
+	if (!umem->writable)
+		gup_flags |= FOLL_FORCE;
+
 	need_release = 1;
 	sg_list_start = umem->sg_head.sgl;
 
@@ -184,7 +188,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		ret = get_user_pages(current, current->mm, cur_base,
 				     min_t(unsigned long, npages,
 					   PAGE_SIZE / sizeof (struct page *)),
-				     1, !umem->writable, page_list, vma_list);
+				     gup_flags, page_list, vma_list);
 
 		if (ret < 0)
 			goto out;
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 40becdb3196e..738ccfee7cae 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -527,6 +527,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 	u64 off;
 	int j, k, ret = 0, start_idx, npages = 0;
 	u64 base_virt_addr;
+	unsigned int flags = 0;
 
 	if (access_mask == 0)
 		return -EINVAL;
@@ -556,6 +557,9 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 		goto out_put_task;
 	}
 
+	if (access_mask & ODP_WRITE_ALLOWED_BIT)
+		flags |= FOLL_WRITE;
+
 	start_idx = (user_virt - ib_umem_start(umem)) >> PAGE_SHIFT;
 	k = start_idx;
 
@@ -574,8 +578,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 		 */
 		npages = get_user_pages(owning_process, owning_mm, user_virt,
 					gup_num_pages,
-					access_mask & ODP_WRITE_ALLOWED_BIT, 0,
-					local_page_list, NULL);
+					flags, local_page_list, NULL);
 		up_read(&owning_mm->mmap_sem);
 
 		if (npages < 0)
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index 7d2e42dd6926..8676685dbf3d 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -472,8 +472,8 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 		goto out;
 	}
 
-	ret = get_user_pages(current, current->mm, uaddr & PAGE_MASK, 1, 1, 0,
-			     pages, NULL);
+	ret = get_user_pages(current, current->mm, uaddr & PAGE_MASK, 1,
+			     FOLL_WRITE, pages, NULL);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index ab1588ae1c85..75c3f0dffe63 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -68,7 +68,8 @@ static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
 	for (got = 0; got < num_pages; got += ret) {
 		ret = get_user_pages(current, current->mm,
 				     start_page + got * PAGE_SIZE,
-				     num_pages - got, 1, 1,
+				     num_pages - got,
+				     FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);
 		if (ret < 0)
 			goto bail_release;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 645a5f6e6c88..7f0d75e29441 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -113,6 +113,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	int flags;
 	dma_addr_t pa;
 	DEFINE_DMA_ATTRS(attrs);
+	unsigned int gup_flags;
 
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
@@ -140,6 +141,8 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 
 	flags = IOMMU_READ | IOMMU_CACHE;
 	flags |= (writable) ? IOMMU_WRITE : 0;
+	gup_flags = FOLL_WRITE;
+	gup_flags |= (writable) ? 0 : FOLL_FORCE;
 	cur_base = addr & PAGE_MASK;
 	ret = 0;
 
@@ -147,7 +150,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 		ret = get_user_pages(current, current->mm, cur_base,
 					min_t(unsigned long, npages,
 					PAGE_SIZE / sizeof(struct page *)),
-					1, !writable, page_list, NULL);
+					gup_flags, page_list, NULL);
 
 		if (ret < 0)
 			goto out;
diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index 6639b2b8528a..f78c464899db 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -60,8 +60,18 @@
 
 /* OMAP4 values */
 #define OMAP4_VAL_IRQDISABLE		0x0
-#define OMAP4_VAL_DEBOUNCINGTIME	0x7
-#define OMAP4_VAL_PVT			0x7
+
+/*
+ * Errata i689: If a key is released for a time shorter than debounce time,
+ * the keyboard will idle and never detect the key release. The workaround
+ * is to use at least a 12ms debounce time. See omap5432 TRM chapter
+ * "26.4.6.2 Keyboard Controller Timer" for more information.
+ */
+#define OMAP4_KEYPAD_PTV_DIV_128        0x6
+#define OMAP4_KEYPAD_DEBOUNCINGTIME_MS(dbms, ptv)     \
+	((((dbms) * 1000) / ((1 << ((ptv) + 1)) * (1000000 / 32768))) - 1)
+#define OMAP4_VAL_DEBOUNCINGTIME_16MS					\
+	OMAP4_KEYPAD_DEBOUNCINGTIME_MS(16, OMAP4_KEYPAD_PTV_DIV_128)
 
 enum {
 	KBD_REVISION_OMAP4 = 0,
@@ -181,9 +191,9 @@ static int omap4_keypad_open(struct input_dev *input)
 
 	kbd_writel(keypad_data, OMAP4_KBD_CTRL,
 			OMAP4_DEF_CTRL_NOSOFTMODE |
-			(OMAP4_VAL_PVT << OMAP4_DEF_CTRL_PTV_SHIFT));
+			(OMAP4_KEYPAD_PTV_DIV_128 << OMAP4_DEF_CTRL_PTV_SHIFT));
 	kbd_writel(keypad_data, OMAP4_KBD_DEBOUNCINGTIME,
-			OMAP4_VAL_DEBOUNCINGTIME);
+			OMAP4_VAL_DEBOUNCINGTIME_16MS);
 	/* clear pending interrupts */
 	kbd_write_irqreg(keypad_data, OMAP4_KBD_IRQSTATUS,
 			 kbd_read_irqreg(keypad_data, OMAP4_KBD_IRQSTATUS));
diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c
index f770f6a2c987..3ea9edc8cdbe 100644
--- a/drivers/media/dvb-frontends/ascot2e.c
+++ b/drivers/media/dvb-frontends/ascot2e.c
@@ -155,7 +155,9 @@ static int ascot2e_write_regs(struct ascot2e_priv *priv,
 
 static int ascot2e_write_reg(struct ascot2e_priv *priv, u8 reg, u8 val)
 {
-	return ascot2e_write_regs(priv, reg, &val, 1);
+	u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return ascot2e_write_regs(priv, reg, &tmp, 1);
 }
 
 static int ascot2e_read_regs(struct ascot2e_priv *priv,
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index 107853b0fddd..bde77671a37c 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -241,7 +241,9 @@ static int cxd2841er_write_regs(struct cxd2841er_priv *priv,
 static int cxd2841er_write_reg(struct cxd2841er_priv *priv,
 			       u8 addr, u8 reg, u8 val)
 {
-	return cxd2841er_write_regs(priv, addr, reg, &val, 1);
+	u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return cxd2841er_write_regs(priv, addr, reg, &tmp, 1);
 }
 
 static int cxd2841er_read_regs(struct cxd2841er_priv *priv,
diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c
index 000606af70f7..f770ab72a8e3 100644
--- a/drivers/media/dvb-frontends/horus3a.c
+++ b/drivers/media/dvb-frontends/horus3a.c
@@ -89,7 +89,9 @@ static int horus3a_write_regs(struct horus3a_priv *priv,
 
 static int horus3a_write_reg(struct horus3a_priv *priv, u8 reg, u8 val)
 {
-	return horus3a_write_regs(priv, reg, &val, 1);
+	u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return horus3a_write_regs(priv, reg, &tmp, 1);
 }
 
 static int horus3a_enter_power_save(struct horus3a_priv *priv)
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index cadcae4cff89..ac9d2591bb6f 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -99,8 +99,9 @@ static int itd1000_read_reg(struct itd1000_state *state, u8 reg)
 
 static inline int itd1000_write_reg(struct itd1000_state *state, u8 r, u8 v)
 {
-	int ret = itd1000_write_regs(state, r, &v, 1);
-	state->shadow[r] = v;
+	u8 tmp = v; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+	int ret = itd1000_write_regs(state, r, &tmp, 1);
+	state->shadow[r] = tmp;
 	return ret;
 }
 
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index c36e6764eead..c44188271028 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -142,7 +142,10 @@ static inline int mt312_readreg(struct mt312_state *state,
 static inline int mt312_writereg(struct mt312_state *state,
 				 const enum mt312_reg_addr reg, const u8 val)
 {
-	return mt312_write(state, reg, &val, 1);
+	u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+
+	return mt312_write(state, reg, &tmp, 1);
 }
 
 static inline u32 mt312_div(u32 a, u32 b)
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index 756650f154ab..ad9b7d4f8d95 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -552,7 +552,8 @@ int stb0899_write_regs(struct stb0899_state *state, unsigned int reg, u8 *data,
 
 int stb0899_write_reg(struct stb0899_state *state, unsigned int reg, u8 data)
 {
-	return stb0899_write_regs(state, reg, &data, 1);
+	u8 tmp = data;
+	return stb0899_write_regs(state, reg, &tmp, 1);
 }
 
 /*
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 4ef8a5c7003e..44fac2570034 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -226,12 +226,14 @@ static int stb6100_write_reg_range(struct stb6100_state *state, u8 buf[], int st
 
 static int stb6100_write_reg(struct stb6100_state *state, u8 reg, u8 data)
 {
+	u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
 	if (unlikely(reg >= STB6100_NUMREGS)) {
 		dprintk(verbose, FE_ERROR, 1, "Invalid register offset 0x%x", reg);
 		return -EREMOTEIO;
 	}
-	data = (data & stb6100_template[reg].mask) | stb6100_template[reg].set;
-	return stb6100_write_reg_range(state, &data, reg, 1);
+	tmp = (tmp & stb6100_template[reg].mask) | stb6100_template[reg].set;
+	return stb6100_write_reg_range(state, &tmp, reg, 1);
 }
 
 
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 44cb73f68af6..ddd0d778ad6e 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -804,7 +804,9 @@ int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len)
 
 static int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data)
 {
-	return stv0367_writeregs(state, reg, &data, 1);
+	u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return stv0367_writeregs(state, reg, &tmp, 1);
 }
 
 static u8 stv0367_readreg(struct stv0367_state *state, u16 reg)
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index 25bdf6e0f963..f0377e2b341b 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -761,7 +761,9 @@ static int stv090x_write_regs(struct stv090x_state *state, unsigned int reg, u8
 
 static int stv090x_write_reg(struct stv090x_state *state, unsigned int reg, u8 data)
 {
-	return stv090x_write_regs(state, reg, &data, 1);
+	u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return stv090x_write_regs(state, reg, &tmp, 1);
 }
 
 static int stv090x_i2c_gate_ctrl(struct stv090x_state *state, int enable)
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index e66154e5c1d7..45d14869e7b8 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -97,7 +97,9 @@ static int stv6110x_write_regs(struct stv6110x_state *stv6110x, int start, u8 da
 
 static int stv6110x_write_reg(struct stv6110x_state *stv6110x, u8 reg, u8 data)
 {
-	return stv6110x_write_regs(stv6110x, reg, &data, 1);
+	u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return stv6110x_write_regs(stv6110x, reg, &tmp, 1);
 }
 
 static int stv6110x_init(struct dvb_frontend *fe)
diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c
index ee09ec26c553..b273e4fd8024 100644
--- a/drivers/media/dvb-frontends/zl10039.c
+++ b/drivers/media/dvb-frontends/zl10039.c
@@ -138,7 +138,9 @@ static inline int zl10039_writereg(struct zl10039_state *state,
 				const enum zl10039_reg_addr reg,
 				const u8 val)
 {
-	return zl10039_write(state, reg, &val, 1);
+	const u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */
+
+	return zl10039_write(state, reg, &tmp, 1);
 }
 
 static int zl10039_init(struct dvb_frontend *fe)
diff --git a/drivers/media/pci/ivtv/ivtv-udma.c b/drivers/media/pci/ivtv/ivtv-udma.c
index 24152accc66c..8729fdebef8f 100644
--- a/drivers/media/pci/ivtv/ivtv-udma.c
+++ b/drivers/media/pci/ivtv/ivtv-udma.c
@@ -125,7 +125,8 @@ int ivtv_udma_setup(struct ivtv *itv, unsigned long ivtv_dest_addr,
 
 	/* Get user pages for DMA Xfer */
 	err = get_user_pages_unlocked(current, current->mm,
-			user_dma.uaddr, user_dma.page_count, 0, 1, dma->map);
+			user_dma.uaddr, user_dma.page_count, dma->map,
+			FOLL_FORCE);
 
 	if (user_dma.page_count != err) {
 		IVTV_DEBUG_WARN("failed to map user pages, returned %d instead of %d\n",
diff --git a/drivers/media/pci/ivtv/ivtv-yuv.c b/drivers/media/pci/ivtv/ivtv-yuv.c
index 2b8e7b2f2b86..9cd995f418e0 100644
--- a/drivers/media/pci/ivtv/ivtv-yuv.c
+++ b/drivers/media/pci/ivtv/ivtv-yuv.c
@@ -76,13 +76,13 @@ static int ivtv_yuv_prep_user_dma(struct ivtv *itv, struct ivtv_user_dma *dma,
 
 	/* Get user pages for DMA Xfer */
 	y_pages = get_user_pages_unlocked(current, current->mm,
-				y_dma.uaddr, y_dma.page_count, 0, 1,
-				&dma->map[0]);
+				y_dma.uaddr, y_dma.page_count,
+				&dma->map[0], FOLL_FORCE);
 	uv_pages = 0; /* silence gcc. value is set and consumed only if: */
 	if (y_pages == y_dma.page_count) {
 		uv_pages = get_user_pages_unlocked(current, current->mm,
-					uv_dma.uaddr, uv_dma.page_count, 0, 1,
-					&dma->map[y_pages]);
+					uv_dma.uaddr, uv_dma.page_count,
+					&dma->map[y_pages], FOLL_FORCE);
 	}
 
 	if (y_pages != y_dma.page_count || uv_pages != uv_dma.page_count) {
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 70c28d19ea04..596359576109 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -214,7 +214,7 @@ static int omap_vout_get_userptr(struct videobuf_buffer *vb, u32 virtp,
 	if (!vec)
 		return -ENOMEM;
 
-	ret = get_vaddr_frames(virtp, 1, true, false, vec);
+	ret = get_vaddr_frames(virtp, 1, FOLL_WRITE, vec);
 	if (ret != 1) {
 		frame_vector_destroy(vec);
 		return -EINVAL;
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index f669cedca8bd..f74a74d91b9e 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -156,6 +156,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 {
 	unsigned long first, last;
 	int err, rw = 0;
+	unsigned int flags = FOLL_FORCE;
 
 	dma->direction = direction;
 	switch (dma->direction) {
@@ -178,13 +179,15 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	if (NULL == dma->pages)
 		return -ENOMEM;
 
+	if (rw == READ)
+		flags |= FOLL_WRITE;
+
 	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
 		data, size, dma->nr_pages);
 
 	err = get_user_pages(current, current->mm,
 			     data & PAGE_MASK, dma->nr_pages,
-			     rw == READ, 1, /* force */
-			     dma->pages, NULL);
+			     flags, dma->pages, NULL);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c
index 3c3b517f1d1c..1cd322e939c7 100644
--- a/drivers/media/v4l2-core/videobuf2-memops.c
+++ b/drivers/media/v4l2-core/videobuf2-memops.c
@@ -42,6 +42,10 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
 	unsigned long first, last;
 	unsigned long nr;
 	struct frame_vector *vec;
+	unsigned int flags = FOLL_FORCE;
+
+	if (write)
+		flags |= FOLL_WRITE;
 
 	first = start >> PAGE_SHIFT;
 	last = (start + length - 1) >> PAGE_SHIFT;
@@ -49,7 +53,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
 	vec = frame_vector_create(nr);
 	if (!vec)
 		return ERR_PTR(-ENOMEM);
-	ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec);
+	ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec);
 	if (ret < 0)
 		goto out_destroy;
 	/* We accept only complete set of PFNs */
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index 8bd63128d536..71c69e1c4ac0 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -1398,8 +1398,7 @@ retry:
 				mm,
 				(u64)addr,
 				nr_pages,
-				!!(prot & SCIF_PROT_WRITE),
-				0,
+				(prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
 				pinned_pages->pages,
 				NULL);
 		up_write(&mm->mmap_sem);
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index f74fc0ca2ef9..e6b723c6a2af 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -199,7 +199,7 @@ static int non_atomic_pte_lookup(struct vm_area_struct *vma,
 	*pageshift = PAGE_SHIFT;
 #endif
 	if (get_user_pages
-	    (current, current->mm, vaddr, 1, write, 0, &page, NULL) <= 0)
+	    (current, current->mm, vaddr, 1, write ? FOLL_WRITE : 0, &page, NULL) <= 0)
 		return -EFAULT;
 	*paddr = page_to_phys(page);
 	put_page(page);
diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c
index c52c8ccc90b7..a5cbf0fa3cfa 100644
--- a/drivers/misc/uid_sys_stats.c
+++ b/drivers/misc/uid_sys_stats.c
@@ -129,7 +129,7 @@ static void get_full_task_comm(struct task_entry *task_entry,
 	struct mm_struct *mm = task->mm;
 
 	/* fill the first TASK_COMM_LEN bytes with thread name */
-	get_task_comm(task_entry->comm, task);
+	__get_task_comm(task_entry->comm, TASK_COMM_LEN, task);
 	i = strlen(task_entry->comm);
 	while (i < TASK_COMM_LEN)
 		task_entry->comm[i++] = ' ';
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index b9958a123594..5bcf4f45f8b4 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -105,6 +105,7 @@ struct mmc_omap_slot {
 	unsigned int		vdd;
 	u16			saved_con;
 	u16			bus_mode;
+	u16			power_mode;
 	unsigned int		fclk_freq;
 
 	struct tasklet_struct	cover_tasklet;
@@ -1156,7 +1157,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct mmc_omap_slot *slot = mmc_priv(mmc);
 	struct mmc_omap_host *host = slot->host;
 	int i, dsor;
-	int clk_enabled;
+	int clk_enabled, init_stream;
 
 	mmc_omap_select_slot(slot, 0);
 
@@ -1166,6 +1167,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		slot->vdd = ios->vdd;
 
 	clk_enabled = 0;
+	init_stream = 0;
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
 		mmc_omap_set_power(slot, 0, ios->vdd);
@@ -1173,13 +1175,17 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	case MMC_POWER_UP:
 		/* Cannot touch dsor yet, just power up MMC */
 		mmc_omap_set_power(slot, 1, ios->vdd);
+		slot->power_mode = ios->power_mode;
 		goto exit;
 	case MMC_POWER_ON:
 		mmc_omap_fclk_enable(host, 1);
 		clk_enabled = 1;
 		dsor |= 1 << 11;
+		if (slot->power_mode != MMC_POWER_ON)
+			init_stream = 1;
 		break;
 	}
+	slot->power_mode = ios->power_mode;
 
 	if (slot->bus_mode != ios->bus_mode) {
 		if (slot->pdata->set_bus_mode != NULL)
@@ -1195,7 +1201,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	for (i = 0; i < 2; i++)
 		OMAP_MMC_WRITE(host, CON, dsor);
 	slot->saved_con = dsor;
-	if (ios->power_mode == MMC_POWER_ON) {
+	if (init_stream) {
 		/* worst case at 400kHz, 80 cycles makes 200 microsecs */
 		int usecs = 250;
 
@@ -1233,6 +1239,7 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id)
 	slot->host = host;
 	slot->mmc = mmc;
 	slot->id = id;
+	slot->power_mode = MMC_POWER_UNDEFINED;
 	slot->pdata = &host->pdata->slots[id];
 
 	host->slots[id] = slot;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 940e2ebbdea8..399c627b15cc 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2011,6 +2011,9 @@ void bond_3ad_unbind_slave(struct slave *slave)
 		   aggregator->aggregator_identifier);
 
 	/* Tell the partner that this port is not suitable for aggregation */
+	port->actor_oper_port_state &= ~AD_STATE_SYNCHRONIZATION;
+	port->actor_oper_port_state &= ~AD_STATE_COLLECTING;
+	port->actor_oper_port_state &= ~AD_STATE_DISTRIBUTING;
 	port->actor_oper_port_state &= ~AD_STATE_AGGREGATION;
 	__update_lacpdu_from_port(port);
 	ad_lacpdu_send(port);
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index 0527f485c3dc..973fcd442aea 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -98,8 +98,7 @@ static int mv88e6060_switch_reset(struct dsa_switch *ds)
 	/* Reset the switch. */
 	REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL,
 		  GLOBAL_ATU_CONTROL_SWRESET |
-		  GLOBAL_ATU_CONTROL_ATUSIZE_1024 |
-		  GLOBAL_ATU_CONTROL_ATE_AGE_5MIN);
+		  GLOBAL_ATU_CONTROL_LEARNDIS);
 
 	/* Wait up to one second for reset to complete. */
 	timeout = jiffies + 1 * HZ;
@@ -124,13 +123,10 @@ static int mv88e6060_setup_global(struct dsa_switch *ds)
 	 */
 	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL, GLOBAL_CONTROL_MAX_FRAME_1536);
 
-	/* Enable automatic address learning, set the address
-	 * database size to 1024 entries, and set the default aging
-	 * time to 5 minutes.
+	/* Disable automatic address learning.
 	 */
 	REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL,
-		  GLOBAL_ATU_CONTROL_ATUSIZE_1024 |
-		  GLOBAL_ATU_CONTROL_ATE_AGE_5MIN);
+		  GLOBAL_ATU_CONTROL_LEARNDIS);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 16baaafed26c..cbdeb54eab51 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1090,6 +1090,9 @@ static void nic_remove(struct pci_dev *pdev)
 {
 	struct nicpf *nic = pci_get_drvdata(pdev);
 
+	if (!nic)
+		return;
+
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 253f8ed0537a..60c727b0b7ab 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -919,10 +919,8 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	}
 
 	ret = register_netdev(ndev);
-	if (ret) {
-		free_netdev(ndev);
+	if (ret)
 		goto alloc_fail;
-	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index ffd2e74e5638..dcd718ce13d5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -1429,7 +1429,9 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 		*autoneg = false;
 
 		if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
-		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) {
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) {
 			*speed = IXGBE_LINK_SPEED_1GB_FULL;
 			return 0;
 		}
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index deae10d7426d..9b588251f2a7 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -578,6 +578,7 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 	struct cp_private *cp;
 	int handled = 0;
 	u16 status;
+	u16 mask;
 
 	if (unlikely(dev == NULL))
 		return IRQ_NONE;
@@ -585,6 +586,10 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 
 	spin_lock(&cp->lock);
 
+	mask = cpr16(IntrMask);
+	if (!mask)
+		goto out_unlock;
+
 	status = cpr16(IntrStatus);
 	if (!status || (status == 0xFFFF))
 		goto out_unlock;
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 3920c3eb6006..df6063faad2e 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -821,37 +821,49 @@ static int rocker_tlv_put(struct rocker_desc_info *desc_info,
 static int rocker_tlv_put_u8(struct rocker_desc_info *desc_info,
 			     int attrtype, u8 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value);
+	u8 tmp = value; /* work around GCC PR81715 */
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &tmp);
 }
 
 static int rocker_tlv_put_u16(struct rocker_desc_info *desc_info,
 			      int attrtype, u16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value);
+	u16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &tmp);
 }
 
 static int rocker_tlv_put_be16(struct rocker_desc_info *desc_info,
 			       int attrtype, __be16 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &value);
+	__be16 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &tmp);
 }
 
 static int rocker_tlv_put_u32(struct rocker_desc_info *desc_info,
 			      int attrtype, u32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value);
+	u32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &tmp);
 }
 
 static int rocker_tlv_put_be32(struct rocker_desc_info *desc_info,
 			       int attrtype, __be32 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &value);
+	__be32 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &tmp);
 }
 
 static int rocker_tlv_put_u64(struct rocker_desc_info *desc_info,
 			      int attrtype, u64 value)
 {
-	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value);
+	u64 tmp = value;
+
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &tmp);
 }
 
 static struct rocker_tlv *
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 1f2f25a71d18..70f26b30729c 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1265,20 +1265,17 @@ static int gen10g_resume(struct phy_device *phydev)
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
-			       PHY_10BT_FEATURES);
-
 	switch (max_speed) {
-	default:
-		return -ENOTSUPP;
-	case SPEED_1000:
-		phydev->supported |= PHY_1000BT_FEATURES;
+	case SPEED_10:
+		phydev->supported &= ~PHY_100BT_FEATURES;
 		/* fall through */
 	case SPEED_100:
-		phydev->supported |= PHY_100BT_FEATURES;
-		/* fall through */
-	case SPEED_10:
-		phydev->supported |= PHY_10BT_FEATURES;
+		phydev->supported &= ~PHY_1000BT_FEATURES;
+		break;
+	case SPEED_1000:
+		break;
+	default:
+		return -ENOTSUPP;
 	}
 
 	return 0;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2da9822a910c..d235d186df5e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1476,9 +1476,9 @@ static void tun_setup(struct net_device *dev)
  */
 static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
 {
-	if (!data)
-		return 0;
-	return -EINVAL;
+	/* NL_SET_ERR_MSG(extack,
+		       "tun/tap creation via rtnetlink is not supported."); */
+	return -EOPNOTSUPP;
 }
 
 static struct rtnl_link_ops tun_link_ops __read_mostly = {
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index ab480ea6d95a..0d1abcfec003 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3195,16 +3195,16 @@ static int __init init_mac80211_hwsim(void)
 	if (err)
 		return err;
 
+	err = hwsim_init_netlink();
+	if (err)
+		goto out_unregister_driver;
+
 	hwsim_class = class_create(THIS_MODULE, "mac80211_hwsim");
 	if (IS_ERR(hwsim_class)) {
 		err = PTR_ERR(hwsim_class);
-		goto out_unregister_driver;
+		goto out_exit_netlink;
 	}
 
-	err = hwsim_init_netlink();
-	if (err < 0)
-		goto out_unregister_driver;
-
 	for (i = 0; i < radios; i++) {
 		struct hwsim_new_radio_params param = { 0 };
 
@@ -3310,6 +3310,8 @@ out_free_mon:
 	free_netdev(hwsim_mon);
 out_free_radios:
 	mac80211_hwsim_free();
+out_exit_netlink:
+	hwsim_exit_netlink();
 out_unregister_driver:
 	platform_driver_unregister(&mac80211_hwsim_driver);
 	return err;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
index a7c81e988656..383977ea3a3c 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
@@ -568,7 +568,7 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = {
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 11),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 1)),	/* PH_EINT11 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 11)),	/* PH_EINT11 */
 };
 
 static const struct sunxi_pinctrl_desc sun8i_a83t_pinctrl_data = {
diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c
index a161fbf6f172..63ad5b543f14 100644
--- a/drivers/rtc/rtc-snvs.c
+++ b/drivers/rtc/rtc-snvs.c
@@ -47,49 +47,83 @@ struct snvs_rtc_data {
 	struct clk *clk;
 };
 
+/* Read 64 bit timer register, which could be in inconsistent state */
+static u64 rtc_read_lpsrt(struct snvs_rtc_data *data)
+{
+	u32 msb, lsb;
+
+	regmap_read(data->regmap, data->offset + SNVS_LPSRTCMR, &msb);
+	regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &lsb);
+	return (u64)msb << 32 | lsb;
+}
+
+/* Read the secure real time counter, taking care to deal with the cases of the
+ * counter updating while being read.
+ */
 static u32 rtc_read_lp_counter(struct snvs_rtc_data *data)
 {
 	u64 read1, read2;
-	u32 val;
+	unsigned int timeout = 100;
 
+	/* As expected, the registers might update between the read of the LSB
+	 * reg and the MSB reg.  It's also possible that one register might be
+	 * in partially modified state as well.
+	 */
+	read1 = rtc_read_lpsrt(data);
 	do {
-		regmap_read(data->regmap, data->offset + SNVS_LPSRTCMR, &val);
-		read1 = val;
-		read1 <<= 32;
-		regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &val);
-		read1 |= val;
-
-		regmap_read(data->regmap, data->offset + SNVS_LPSRTCMR, &val);
-		read2 = val;
-		read2 <<= 32;
-		regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &val);
-		read2 |= val;
-	} while (read1 != read2);
+		read2 = read1;
+		read1 = rtc_read_lpsrt(data);
+	} while (read1 != read2 && --timeout);
+	if (!timeout)
+		dev_err(&data->rtc->dev, "Timeout trying to get valid LPSRT Counter read\n");
 
 	/* Convert 47-bit counter to 32-bit raw second count */
 	return (u32) (read1 >> CNTR_TO_SECS_SH);
 }
 
-static void rtc_write_sync_lp(struct snvs_rtc_data *data)
+/* Just read the lsb from the counter, dealing with inconsistent state */
+static int rtc_read_lp_counter_lsb(struct snvs_rtc_data *data, u32 *lsb)
 {
-	u32 count1, count2, count3;
-	int i;
-
-	/* Wait for 3 CKIL cycles */
-	for (i = 0; i < 3; i++) {
-		do {
-			regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count1);
-			regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count2);
-		} while (count1 != count2);
-
-		/* Now wait until counter value changes */
-		do {
-			do {
-				regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count2);
-				regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count3);
-			} while (count2 != count3);
-		} while (count3 == count1);
+	u32 count1, count2;
+	unsigned int timeout = 100;
+
+	regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count1);
+	do {
+		count2 = count1;
+		regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count1);
+	} while (count1 != count2 && --timeout);
+	if (!timeout) {
+		dev_err(&data->rtc->dev, "Timeout trying to get valid LPSRT Counter read\n");
+		return -ETIMEDOUT;
 	}
+
+	*lsb = count1;
+	return 0;
+}
+
+static int rtc_write_sync_lp(struct snvs_rtc_data *data)
+{
+	u32 count1, count2;
+	u32 elapsed;
+	unsigned int timeout = 1000;
+	int ret;
+
+	ret = rtc_read_lp_counter_lsb(data, &count1);
+	if (ret)
+		return ret;
+
+	/* Wait for 3 CKIL cycles, about 61.0-91.5 µs */
+	do {
+		ret = rtc_read_lp_counter_lsb(data, &count2);
+		if (ret)
+			return ret;
+		elapsed = count2 - count1; /* wrap around _is_ handled! */
+	} while (elapsed < 3 && --timeout);
+	if (!timeout) {
+		dev_err(&data->rtc->dev, "Timeout waiting for LPSRT Counter to change\n");
+		return -ETIMEDOUT;
+	}
+	return 0;
 }
 
 static int snvs_rtc_enable(struct snvs_rtc_data *data, bool enable)
@@ -173,9 +207,7 @@ static int snvs_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 			   (SNVS_LPCR_LPTA_EN | SNVS_LPCR_LPWUI_EN),
 			   enable ? (SNVS_LPCR_LPTA_EN | SNVS_LPCR_LPWUI_EN) : 0);
 
-	rtc_write_sync_lp(data);
-
-	return 0;
+	return rtc_write_sync_lp(data);
 }
 
 static int snvs_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
@@ -183,10 +215,14 @@ static int snvs_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	struct snvs_rtc_data *data = dev_get_drvdata(dev);
 	struct rtc_time *alrm_tm = &alrm->time;
 	unsigned long time;
+	int ret;
 
 	rtc_tm_to_time(alrm_tm, &time);
 
 	regmap_update_bits(data->regmap, data->offset + SNVS_LPCR, SNVS_LPCR_LPTA_EN, 0);
+	ret = rtc_write_sync_lp(data);
+	if (ret)
+		return ret;
 	regmap_write(data->regmap, data->offset + SNVS_LPTAR, time);
 
 	/* Clear alarm interrupt status bit */
diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c
index 33fbe8249fd5..044cffbc45e8 100644
--- a/drivers/sbus/char/display7seg.c
+++ b/drivers/sbus/char/display7seg.c
@@ -221,6 +221,7 @@ static int d7s_probe(struct platform_device *op)
 	dev_set_drvdata(&op->dev, p);
 	d7s_device = p;
 	err = 0;
+	of_node_put(opts);
 
 out:
 	return err;
diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c
index 5609b602c54d..baa9b322520b 100644
--- a/drivers/sbus/char/envctrl.c
+++ b/drivers/sbus/char/envctrl.c
@@ -910,8 +910,10 @@ static void envctrl_init_i2c_child(struct device_node *dp,
 			for (len = 0; len < PCF8584_MAX_CHANNELS; ++len) {
 				pchild->mon_type[len] = ENVCTRL_NOMON;
 			}
+			of_node_put(root_node);
 			return;
 		}
+		of_node_put(root_node);
 	}
 
 	/* Get the monitor channels. */
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index a74f8fbefd33..009a2ef829d6 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2416,8 +2416,8 @@ int iscsi_eh_session_reset(struct scsi_cmnd *sc)
 failed:
 		ISCSI_DBG_EH(session,
 			     "failing session reset: Could not log back into "
-			     "%s, %s [age %d]\n", session->targetname,
-			     conn->persistent_address, session->age);
+			     "%s [age %d]\n", session->targetname,
+			     session->age);
 		spin_unlock_bh(&session->frwd_lock);
 		mutex_unlock(&session->eh_mutex);
 		return FAILED;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 03054c0e7689..3c3e8115f73d 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -187,30 +187,25 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	struct scsi_device *SDev;
 	struct scsi_sense_hdr sshdr;
 	int result, err = 0, retries = 0;
-	struct request_sense *sense = cgc->sense;
+	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE];
 
 	SDev = cd->device;
 
-	if (!sense) {
-		sense = kmalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-		if (!sense) {
-			err = -ENOMEM;
-			goto out;
-		}
-	}
-
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
 		err = -ENODEV;
 		goto out;
 	}
 
-	memset(sense, 0, sizeof(*sense));
+	memset(sense_buffer, 0, sizeof(sense_buffer));
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, (char *)sense,
+			      cgc->buffer, cgc->buflen, sense_buffer,
 			      cgc->timeout, IOCTL_RETRIES, 0, NULL);
 
-	scsi_normalize_sense((char *)sense, sizeof(*sense), &sshdr);
+	scsi_normalize_sense(sense_buffer, sizeof(sense_buffer), &sshdr);
+
+	if (cgc->sense)
+		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
 
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
@@ -261,8 +256,6 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 
 	/* Wake up a process waiting for device */
       out:
-	if (!cgc->sense)
-		kfree(sense);
 	cgc->stat = err;
 	return err;
 }
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 2e522951b619..088a68ab4246 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4821,9 +4821,8 @@ static int sgl_map_user_pages(struct st_buffer *STbp,
 		current->mm,
 		uaddr,
 		nr_pages,
-		rw == READ,
-		0, /* don't force */
-		pages);
+		pages,
+		rw == READ ? FOLL_WRITE : 0); /* don't force */
 
 	/* Errors and no page mapped should return here */
 	if (res < nr_pages)
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 0de2f9069e23..23081ed8f1e3 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -1199,8 +1199,6 @@ static void pvscsi_shutdown_intr(struct pvscsi_adapter *adapter)
 
 static void pvscsi_release_resources(struct pvscsi_adapter *adapter)
 {
-	pvscsi_shutdown_intr(adapter);
-
 	if (adapter->workqueue)
 		destroy_workqueue(adapter->workqueue);
 
@@ -1529,6 +1527,7 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 out_reset_adapter:
 	ll_adapter_reset(adapter);
 out_release_resources:
+	pvscsi_shutdown_intr(adapter);
 	pvscsi_release_resources(adapter);
 	scsi_host_put(host);
 out_disable_device:
@@ -1537,6 +1536,7 @@ out_disable_device:
 	return error;
 
 out_release_resources_and_disable:
+	pvscsi_shutdown_intr(adapter);
 	pvscsi_release_resources(adapter);
 	goto out_disable_device;
 }
diff --git a/drivers/staging/rdma/hfi1/user_pages.c b/drivers/staging/rdma/hfi1/user_pages.c
index 9071afbd7bf4..b776b74d3d14 100644
--- a/drivers/staging/rdma/hfi1/user_pages.c
+++ b/drivers/staging/rdma/hfi1/user_pages.c
@@ -85,7 +85,7 @@ static int __hfi1_get_user_pages(unsigned long start_page, size_t num_pages,
 	for (got = 0; got < num_pages; got += ret) {
 		ret = get_user_pages(current, current->mm,
 				     start_page + got * PAGE_SIZE,
-				     num_pages - got, 1, 1,
+				     num_pages - got, FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);
 		if (ret < 0)
 			goto bail_release;
diff --git a/drivers/staging/rdma/ipath/ipath_user_pages.c b/drivers/staging/rdma/ipath/ipath_user_pages.c
index d29b4daf61f8..f69ec728e0de 100644
--- a/drivers/staging/rdma/ipath/ipath_user_pages.c
+++ b/drivers/staging/rdma/ipath/ipath_user_pages.c
@@ -72,7 +72,7 @@ static int __ipath_get_user_pages(unsigned long start_page, size_t num_pages,
 	for (got = 0; got < num_pages; got += ret) {
 		ret = get_user_pages(current, current->mm,
 				     start_page + got * PAGE_SIZE,
-				     num_pages - got, 1, 1,
+				     num_pages - got, FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);
 		if (ret < 0)
 			goto bail_release;
diff --git a/drivers/staging/speakup/kobjects.c b/drivers/staging/speakup/kobjects.c
index 06ef26872462..52aed7cfeb24 100644
--- a/drivers/staging/speakup/kobjects.c
+++ b/drivers/staging/speakup/kobjects.c
@@ -387,7 +387,7 @@ static ssize_t synth_store(struct kobject *kobj, struct kobj_attribute *attr,
 	len = strlen(buf);
 	if (len < 2 || len > 9)
 		return -EINVAL;
-	strncpy(new_synth_name, buf, len);
+	memcpy(new_synth_name, buf, len);
 	if (new_synth_name[len - 1] == '\n')
 		len--;
 	new_synth_name[len] = '\0';
@@ -514,7 +514,7 @@ static ssize_t punc_store(struct kobject *kobj, struct kobj_attribute *attr,
 		return -EINVAL;
 	}
 
-	strncpy(punc_buf, buf, x);
+	memcpy(punc_buf, buf, x);
 
 	while (x && punc_buf[x - 1] == '\n')
 		x--;
diff --git a/drivers/tty/serial/suncore.c b/drivers/tty/serial/suncore.c
index 127472bd6a7c..209f314745ab 100644
--- a/drivers/tty/serial/suncore.c
+++ b/drivers/tty/serial/suncore.c
@@ -111,6 +111,7 @@ void sunserial_console_termios(struct console *con, struct device_node *uart_dp)
 		mode = of_get_property(dp, mode_prop, NULL);
 		if (!mode)
 			mode = "9600,8,n,1,-";
+		of_node_put(dp);
 	}
 
 	cflag = CREAD | HUPCL | CLOCAL;
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index 9b7d39484ed3..d1ed92acafa3 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -2037,6 +2037,7 @@ static inline int machine_without_vbus_sense(void)
 {
 	return machine_is_omap_innovator()
 		|| machine_is_omap_osk()
+		|| machine_is_omap_palmte()
 		|| machine_is_sx1()
 		/* No known omap7xx boards with vbus sense */
 		|| cpu_is_omap7xx();
@@ -2045,7 +2046,7 @@ static inline int machine_without_vbus_sense(void)
 static int omap_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver)
 {
-	int		status = -ENODEV;
+	int		status;
 	struct omap_ep	*ep;
 	unsigned long	flags;
 
@@ -2083,6 +2084,7 @@ static int omap_udc_start(struct usb_gadget *g,
 			goto done;
 		}
 	} else {
+		status = 0;
 		if (can_pullup(udc))
 			pullup_enable(udc);
 		else
@@ -2612,9 +2614,22 @@ omap_ep_setup(char *name, u8 addr, u8 type,
 
 static void omap_udc_release(struct device *dev)
 {
-	complete(udc->done);
+	pullup_disable(udc);
+	if (!IS_ERR_OR_NULL(udc->transceiver)) {
+		usb_put_phy(udc->transceiver);
+		udc->transceiver = NULL;
+	}
+	omap_writew(0, UDC_SYSCON1);
+	remove_proc_file();
+	if (udc->dc_clk) {
+		if (udc->clk_requested)
+			omap_udc_enable_clock(0);
+		clk_put(udc->hhc_clk);
+		clk_put(udc->dc_clk);
+	}
+	if (udc->done)
+		complete(udc->done);
 	kfree(udc);
-	udc = NULL;
 }
 
 static int
@@ -2886,8 +2901,8 @@ bad_on_1710:
 		udc->clr_halt = UDC_RESET_EP;
 
 	/* USB general purpose IRQ:  ep0, state changes, dma, etc */
-	status = request_irq(pdev->resource[1].start, omap_udc_irq,
-			0, driver_name, udc);
+	status = devm_request_irq(&pdev->dev, pdev->resource[1].start,
+				  omap_udc_irq, 0, driver_name, udc);
 	if (status != 0) {
 		ERR("can't get irq %d, err %d\n",
 			(int) pdev->resource[1].start, status);
@@ -2895,20 +2910,20 @@ bad_on_1710:
 	}
 
 	/* USB "non-iso" IRQ (PIO for all but ep0) */
-	status = request_irq(pdev->resource[2].start, omap_udc_pio_irq,
-			0, "omap_udc pio", udc);
+	status = devm_request_irq(&pdev->dev, pdev->resource[2].start,
+				  omap_udc_pio_irq, 0, "omap_udc pio", udc);
 	if (status != 0) {
 		ERR("can't get irq %d, err %d\n",
 			(int) pdev->resource[2].start, status);
-		goto cleanup2;
+		goto cleanup1;
 	}
 #ifdef	USE_ISO
-	status = request_irq(pdev->resource[3].start, omap_udc_iso_irq,
-			0, "omap_udc iso", udc);
+	status = devm_request_irq(&pdev->dev, pdev->resource[3].start,
+				  omap_udc_iso_irq, 0, "omap_udc iso", udc);
 	if (status != 0) {
 		ERR("can't get irq %d, err %d\n",
 			(int) pdev->resource[3].start, status);
-		goto cleanup3;
+		goto cleanup1;
 	}
 #endif
 	if (cpu_is_omap16xx() || cpu_is_omap7xx()) {
@@ -2919,23 +2934,8 @@ bad_on_1710:
 	}
 
 	create_proc_file();
-	status = usb_add_gadget_udc_release(&pdev->dev, &udc->gadget,
-			omap_udc_release);
-	if (status)
-		goto cleanup4;
-
-	return 0;
-
-cleanup4:
-	remove_proc_file();
-
-#ifdef	USE_ISO
-cleanup3:
-	free_irq(pdev->resource[2].start, udc);
-#endif
-
-cleanup2:
-	free_irq(pdev->resource[1].start, udc);
+	return usb_add_gadget_udc_release(&pdev->dev, &udc->gadget,
+					  omap_udc_release);
 
 cleanup1:
 	kfree(udc);
@@ -2962,42 +2962,15 @@ static int omap_udc_remove(struct platform_device *pdev)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	if (!udc)
-		return -ENODEV;
-
-	usb_del_gadget_udc(&udc->gadget);
-	if (udc->driver)
-		return -EBUSY;
-
 	udc->done = &done;
 
-	pullup_disable(udc);
-	if (!IS_ERR_OR_NULL(udc->transceiver)) {
-		usb_put_phy(udc->transceiver);
-		udc->transceiver = NULL;
-	}
-	omap_writew(0, UDC_SYSCON1);
-
-	remove_proc_file();
-
-#ifdef	USE_ISO
-	free_irq(pdev->resource[3].start, udc);
-#endif
-	free_irq(pdev->resource[2].start, udc);
-	free_irq(pdev->resource[1].start, udc);
+	usb_del_gadget_udc(&udc->gadget);
 
-	if (udc->dc_clk) {
-		if (udc->clk_requested)
-			omap_udc_enable_clock(0);
-		clk_put(udc->hhc_clk);
-		clk_put(udc->dc_clk);
-	}
+	wait_for_completion(&done);
 
 	release_mem_region(pdev->resource[0].start,
 			pdev->resource[0].end - pdev->resource[0].start + 1);
 
-	wait_for_completion(&done);
-
 	return 0;
 }
 
diff --git a/drivers/video/fbdev/matrox/matroxfb_Ti3026.c b/drivers/video/fbdev/matrox/matroxfb_Ti3026.c
index 195ad7cac1ba..68fa037d8cbc 100644
--- a/drivers/video/fbdev/matrox/matroxfb_Ti3026.c
+++ b/drivers/video/fbdev/matrox/matroxfb_Ti3026.c
@@ -372,7 +372,7 @@ static int Ti3026_init(struct matrox_fb_info *minfo, struct my_timming *m)
 
 	DBG(__func__)
 
-	memcpy(hw->DACreg, MGADACbpp32, sizeof(hw->DACreg));
+	memcpy(hw->DACreg, MGADACbpp32, sizeof(MGADACbpp32));
 	switch (minfo->fbcon.var.bits_per_pixel) {
 		case 4:	hw->DACreg[POS3026_XLATCHCTRL] = TVP3026_XLATCHCTRL_16_1;	/* or _8_1, they are same */
 			hw->DACreg[POS3026_XTRUECOLORCTRL] = TVP3026_XTRUECOLORCTRL_PSEUDOCOLOR;
diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
index 0e24eb9c219c..750a384bf191 100644
--- a/drivers/video/fbdev/pvr2fb.c
+++ b/drivers/video/fbdev/pvr2fb.c
@@ -687,7 +687,7 @@ static ssize_t pvr2fb_write(struct fb_info *info, const char *buf,
 		return -ENOMEM;
 
 	ret = get_user_pages_unlocked(current, current->mm, (unsigned long)buf,
-				      nr_pages, WRITE, 0, pages);
+				      nr_pages, pages, FOLL_WRITE);
 
 	if (ret < nr_pages) {
 		nr_pages = ret;
diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c
index 32c8fc5f7a5c..590a0f51a249 100644
--- a/drivers/virt/fsl_hypervisor.c
+++ b/drivers/virt/fsl_hypervisor.c
@@ -246,8 +246,8 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
 	down_read(&current->mm->mmap_sem);
 	num_pinned = get_user_pages(current, current->mm,
 		param.local_vaddr - lb_offset, num_pages,
-		(param.source == -1) ? READ : WRITE,
-		0, pages, NULL);
+		(param.source == -1) ? 0 : FOLL_WRITE,
+		pages, NULL);
 	up_read(&current->mm->mmap_sem);
 
 	if (num_pinned != num_pages) {
diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
index 5063c5e796b7..84a1fab0dd6b 100644
--- a/drivers/xen/xlate_mmu.c
+++ b/drivers/xen/xlate_mmu.c
@@ -34,6 +34,7 @@
 #include <asm/xen/hypervisor.h>
 
 #include <xen/xen.h>
+#include <xen/xen-ops.h>
 #include <xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/memory.h>
diff --git a/fs/aio.c b/fs/aio.c
index 3fe07571f942..e8810a263bf3 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -40,6 +40,7 @@
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/mount.h>
+#include <linux/nospec.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -1064,6 +1065,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	if (!table || id >= table->nr)
 		goto out;
 
+	id = array_index_nospec(id, table->nr);
 	ctx = rcu_dereference(table->table[id]);
 	if (ctx && ctx->user_id == ctx_id) {
 		if (percpu_ref_tryget_live(&ctx->users))
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 83c73738165e..40d1ab957fb6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3232,7 +3232,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m)
 	kfree(m);
 }
 
-static void tail_append_pending_moves(struct pending_dir_move *moves,
+static void tail_append_pending_moves(struct send_ctx *sctx,
+				      struct pending_dir_move *moves,
 				      struct list_head *stack)
 {
 	if (list_empty(&moves->list)) {
@@ -3243,6 +3244,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves,
 		list_add_tail(&moves->list, stack);
 		list_splice_tail(&list, stack);
 	}
+	if (!RB_EMPTY_NODE(&moves->node)) {
+		rb_erase(&moves->node, &sctx->pending_dir_moves);
+		RB_CLEAR_NODE(&moves->node);
+	}
 }
 
 static int apply_children_dir_moves(struct send_ctx *sctx)
@@ -3257,7 +3262,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
 		return 0;
 
 	INIT_LIST_HEAD(&stack);
-	tail_append_pending_moves(pm, &stack);
+	tail_append_pending_moves(sctx, pm, &stack);
 
 	while (!list_empty(&stack)) {
 		pm = list_first_entry(&stack, struct pending_dir_move, list);
@@ -3268,7 +3273,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
 			goto out;
 		pm = get_pending_dir_moves(sctx, parent_ino);
 		if (pm)
-			tail_append_pending_moves(pm, &stack);
+			tail_append_pending_moves(sctx, pm, &stack);
 	}
 	return 0;
 
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 5b68cf526887..c05ab2ec0fef 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -963,11 +963,8 @@ error:
 void cachefiles_uncache_page(struct fscache_object *_object, struct page *page)
 {
 	struct cachefiles_object *object;
-	struct cachefiles_cache *cache;
 
 	object = container_of(_object, struct cachefiles_object, fscache);
-	cache = container_of(object->fscache.cache,
-			     struct cachefiles_cache, cache);
 
 	_enter("%p,{%lu}", object, page->index);
 
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index e7b478b49985..8bef27b8f85d 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -111,7 +111,7 @@ config CIFS_XATTR
 
 config CIFS_POSIX
         bool "CIFS POSIX Extensions"
-        depends on CIFS_XATTR
+        depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY && CIFS_XATTR
         help
           Enabling this option will cause the cifs client to attempt to
 	  negotiate a newer dialect with servers, such as Samba 3.0.5
diff --git a/fs/exec.c b/fs/exec.c
index 6bbea71c6d92..ab6e34e1de21 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -191,6 +191,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 {
 	struct page *page;
 	int ret;
+	unsigned int gup_flags = FOLL_FORCE;
 
 #ifdef CONFIG_STACK_GROWSUP
 	if (write) {
@@ -199,8 +200,12 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return NULL;
 	}
 #endif
-	ret = get_user_pages(current, bprm->mm, pos,
-			1, write, 1, &page, NULL);
+
+	if (write)
+		gup_flags |= FOLL_WRITE;
+
+	ret = get_user_pages(current, bprm->mm, pos, 1, gup_flags,
+			&page, NULL);
 	if (ret <= 0)
 		return NULL;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 714cd37a6ba3..6599c6124552 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -76,7 +76,7 @@ static bool dentry_connected(struct dentry *dentry)
 		struct dentry *parent = dget_parent(dentry);
 
 		dput(dentry);
-		if (IS_ROOT(dentry)) {
+		if (dentry == parent) {
 			dput(parent);
 			return false;
 		}
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 7a182c87f378..ab1d7f35f6c2 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -715,6 +715,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob
 
 	if (awaken)
 		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+
 
 	/* Prevent a race with our last child, which has to signal EV_CLEARED
 	 * before dropping our spinlock.
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 1ab19e660e69..1ff5774a5382 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -328,13 +328,14 @@ void hfs_bmap_free(struct hfs_bnode *node)
 
 		nidx -= len * 8;
 		i = node->next;
-		hfs_bnode_put(node);
 		if (!i) {
 			/* panic */;
 			pr_crit("unable to free bnode %u. bmap not found!\n",
 				node->this);
+			hfs_bnode_put(node);
 			return;
 		}
+		hfs_bnode_put(node);
 		node = hfs_bnode_find(tree, i);
 		if (IS_ERR(node))
 			return;
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 3345c7553edc..7adc8a327e03 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -453,14 +453,15 @@ void hfs_bmap_free(struct hfs_bnode *node)
 
 		nidx -= len * 8;
 		i = node->next;
-		hfs_bnode_put(node);
 		if (!i) {
 			/* panic */;
 			pr_crit("unable to free bnode %u. "
 					"bmap not found!\n",
 				node->this);
+			hfs_bnode_put(node);
 			return;
 		}
+		hfs_bnode_put(node);
 		node = hfs_bnode_find(tree, i);
 		if (IS_ERR(node))
 			return;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a17da8b57fc6..ab34f613fa85 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -118,6 +118,16 @@ static void huge_pagevec_release(struct pagevec *pvec)
 	pagevec_reinit(pvec);
 }
 
+/*
+ * Mask used when checking the page offset value passed in via system
+ * calls.  This value will be converted to a loff_t which is signed.
+ * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the
+ * value.  The extra bit (- 1 in the shift value) is to take the sign
+ * bit into account.
+ */
+#define PGOFF_LOFFT_MAX \
+	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
@@ -136,17 +146,31 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
+	/*
+	 * page based offset in vm_pgoff could be sufficiently large to
+	 * overflow a loff_t when converted to byte offset.  This can
+	 * only happen on architectures where sizeof(loff_t) ==
+	 * sizeof(unsigned long).  So, only check in those instances.
+	 */
+	if (sizeof(unsigned long) == sizeof(loff_t)) {
+		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+			return -EINVAL;
+	}
+
+	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	/* check for overflow */
+	if (len < vma_len)
+		return -EINVAL;
 
 	mutex_lock(&inode->i_mutex);
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
 	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
@@ -155,7 +179,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = 0;
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
-		inode->i_size = len;
+		i_size_write(inode, len);
 out:
 	mutex_unlock(&inode->i_mutex);
 
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 827fc9809bc2..3494e220b510 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -125,10 +125,10 @@ check_err:
 
 check_gen:
 	if (handle->ih_generation != inode->i_generation) {
-		iput(inode);
 		trace_ocfs2_get_dentry_generation((unsigned long long)blkno,
 						  handle->ih_generation,
 						  inode->i_generation);
+		iput(inode);
 		result = ERR_PTR(-ESTALE);
 		goto bail;
 	}
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 124471d26a73..c1a83c58456e 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -156,18 +156,14 @@ out:
 }
 
 /*
- * lock allocators, and reserving appropriate number of bits for
- * meta blocks and data clusters.
- *
- * in some cases, we don't need to reserve clusters, just let data_ac
- * be NULL.
+ * lock allocator, and reserve appropriate number of bits for
+ * meta blocks.
  */
-static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
 					struct ocfs2_extent_tree *et,
 					u32 clusters_to_move,
 					u32 extents_to_split,
 					struct ocfs2_alloc_context **meta_ac,
-					struct ocfs2_alloc_context **data_ac,
 					int extra_blocks,
 					int *credits)
 {
@@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode,
 		goto out;
 	}
 
-	if (data_ac) {
-		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
 
 	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
 
@@ -260,10 +249,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
-						 &context->meta_ac,
-						 &context->data_ac,
-						 extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						*len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -286,6 +275,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
+	/*
+	 * Make sure ocfs2_reserve_cluster is called after
+	 * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
+	 *
+	 * If ocfs2_reserve_cluster is called
+	 * before __ocfs2_flush_truncate_log, dead lock on global bitmap
+	 * may happen.
+	 *
+	 */
+	ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_mutex;
+	}
+
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
@@ -606,9 +610,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
-						 &context->meta_ac,
-						 NULL, extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ee9b7f0ea938..86cc5554198f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -255,7 +255,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 	 * Inherently racy -- command line shares address space
 	 * with code and data.
 	 */
-	rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+	rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
 	if (rv <= 0)
 		goto out_free_page;
 
@@ -273,7 +273,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			int nr_read;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -308,7 +308,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -357,7 +357,7 @@ skip_argv:
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -869,6 +869,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	unsigned long addr = *ppos;
 	ssize_t copied;
 	char *page;
+	unsigned int flags;
 
 	if (!mm)
 		return 0;
@@ -881,6 +882,11 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	if (!atomic_inc_not_zero(&mm->mm_users))
 		goto free;
 
+	/* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+	flags = FOLL_FORCE;
+	if (write)
+		flags |= FOLL_WRITE;
+
 	while (count > 0) {
 		int this_len = min_t(int, count, PAGE_SIZE);
 
@@ -889,7 +895,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 			break;
 		}
 
-		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		this_len = access_remote_vm(mm, addr, page, this_len, flags);
 		if (!this_len) {
 			if (!copied)
 				copied = -EIO;
@@ -1001,8 +1007,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		max_len = min_t(size_t, PAGE_SIZE, count);
 		this_len = min(max_len, this_len);
 
-		retval = access_remote_vm(mm, (env_start + src),
-			page, this_len, 0);
+		retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
 
 		if (retval <= 0) {
 			ret = retval;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 99c4ffaa43a8..2df3b2358b0a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -143,7 +143,7 @@ static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
 		struct page *page;
 
 		pages_pinned = get_user_pages(current, mm, page_start_vaddr,
-				1, 0, 0, &page, NULL);
+				1, 0, &page, NULL);
 		if (pages_pinned < 1) {
 			seq_puts(m, "<fault>]");
 			return;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 40a0fe0a4e05..6fbfa8189451 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -392,8 +392,8 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 		} else {
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
-		memcpy(psinfo->buf, s, c);
-		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, 0, c, psinfo);
+		psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0,
+				  s, 0, c, psinfo);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index 6dd158a216f4..ffb093e72b6c 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -26,6 +26,34 @@ config SQUASHFS
 	  If unsure, say N.
 
 choice
+	prompt "File decompression options"
+	depends on SQUASHFS
+	help
+	  Squashfs now supports two options for decompressing file
+	  data.  Traditionally Squashfs has decompressed into an
+	  intermediate buffer and then memcopied it into the page cache.
+	  Squashfs now supports the ability to decompress directly into
+	  the page cache.
+
+	  If unsure, select "Decompress file data into an intermediate buffer"
+
+config SQUASHFS_FILE_CACHE
+	bool "Decompress file data into an intermediate buffer"
+	help
+	  Decompress file data into an intermediate buffer and then
+	  memcopy it into the page cache.
+
+config SQUASHFS_FILE_DIRECT
+	bool "Decompress files directly into the page cache"
+	help
+	  Directly decompress file data into the page cache.
+	  Doing so can significantly improve performance because
+	  it eliminates a memcpy and it also removes the lock contention
+	  on the single buffer.
+
+endchoice
+
+choice
 	prompt "Decompressor parallelisation options"
 	depends on SQUASHFS
 	help
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index fe51f1507ed1..246a6f329d89 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -5,7 +5,8 @@
 obj-$(CONFIG_SQUASHFS) += squashfs.o
 squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
 squashfs-y += namei.o super.o symlink.o decompressor.o
-squashfs-y += file_direct.o page_actor.o
+squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
+squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index b3b95e2ae2ff..82bc942fc437 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -28,12 +28,9 @@
 
 #include <linux/fs.h>
 #include <linux/vfs.h>
-#include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/pagemap.h>
 #include <linux/buffer_head.h>
-#include <linux/workqueue.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -41,381 +38,45 @@
 #include "decompressor.h"
 #include "page_actor.h"
 
-static struct workqueue_struct *squashfs_read_wq;
-
-struct squashfs_read_request {
-	struct super_block *sb;
-	u64 index;
-	int length;
-	int compressed;
-	int offset;
-	u64 read_end;
-	struct squashfs_page_actor *output;
-	enum {
-		SQUASHFS_COPY,
-		SQUASHFS_DECOMPRESS,
-		SQUASHFS_METADATA,
-	} data_processing;
-	bool synchronous;
-
-	/*
-	 * If the read is synchronous, it is possible to retrieve information
-	 * about the request by setting these pointers.
-	 */
-	int *res;
-	int *bytes_read;
-	int *bytes_uncompressed;
-
-	int nr_buffers;
-	struct buffer_head **bh;
-	struct work_struct offload;
-};
-
-struct squashfs_bio_request {
-	struct buffer_head **bh;
-	int nr_buffers;
-};
-
-static int squashfs_bio_submit(struct squashfs_read_request *req);
-
-int squashfs_init_read_wq(void)
-{
-	squashfs_read_wq = create_workqueue("SquashFS read wq");
-	return !!squashfs_read_wq;
-}
-
-void squashfs_destroy_read_wq(void)
-{
-	flush_workqueue(squashfs_read_wq);
-	destroy_workqueue(squashfs_read_wq);
-}
-
-static void free_read_request(struct squashfs_read_request *req, int error)
-{
-	if (!req->synchronous)
-		squashfs_page_actor_free(req->output, error);
-	if (req->res)
-		*(req->res) = error;
-	kfree(req->bh);
-	kfree(req);
-}
-
-static void squashfs_process_blocks(struct squashfs_read_request *req)
-{
-	int error = 0;
-	int bytes, i, length;
-	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
-	struct squashfs_page_actor *actor = req->output;
-	struct buffer_head **bh = req->bh;
-	int nr_buffers = req->nr_buffers;
-
-	for (i = 0; i < nr_buffers; ++i) {
-		if (!bh[i])
-			continue;
-		wait_on_buffer(bh[i]);
-		if (!buffer_uptodate(bh[i]))
-			error = -EIO;
-	}
-	if (error)
-		goto cleanup;
-
-	if (req->data_processing == SQUASHFS_METADATA) {
-		/* Extract the length of the metadata block */
-		if (req->offset != msblk->devblksize - 1) {
-			length = le16_to_cpup((__le16 *)
-					(bh[0]->b_data + req->offset));
-		} else {
-			length = (unsigned char)bh[0]->b_data[req->offset];
-			length |= (unsigned char)bh[1]->b_data[0] << 8;
-		}
-		req->compressed = SQUASHFS_COMPRESSED(length);
-		req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
-						       : SQUASHFS_COPY;
-		length = SQUASHFS_COMPRESSED_SIZE(length);
-		if (req->index + length + 2 > req->read_end) {
-			for (i = 0; i < nr_buffers; ++i)
-				put_bh(bh[i]);
-			kfree(bh);
-			req->length = length;
-			req->index += 2;
-			squashfs_bio_submit(req);
-			return;
-		}
-		req->length = length;
-		req->offset = (req->offset + 2) % PAGE_SIZE;
-		if (req->offset < 2) {
-			put_bh(bh[0]);
-			++bh;
-			--nr_buffers;
-		}
-	}
-	if (req->bytes_read)
-		*(req->bytes_read) = req->length;
-
-	if (req->data_processing == SQUASHFS_COPY) {
-		squashfs_bh_to_actor(bh, nr_buffers, req->output, req->offset,
-			req->length, msblk->devblksize);
-	} else if (req->data_processing == SQUASHFS_DECOMPRESS) {
-		req->length = squashfs_decompress(msblk, bh, nr_buffers,
-			req->offset, req->length, actor);
-		if (req->length < 0) {
-			error = -EIO;
-			goto cleanup;
-		}
-	}
-
-	/* Last page may have trailing bytes not filled */
-	bytes = req->length % PAGE_SIZE;
-	if (bytes && actor->page[actor->pages - 1])
-		zero_user_segment(actor->page[actor->pages - 1], bytes,
-				  PAGE_SIZE);
-
-cleanup:
-	if (req->bytes_uncompressed)
-		*(req->bytes_uncompressed) = req->length;
-	if (error) {
-		for (i = 0; i < nr_buffers; ++i)
-			if (bh[i])
-				put_bh(bh[i]);
-	}
-	free_read_request(req, error);
-}
-
-static void read_wq_handler(struct work_struct *work)
-{
-	squashfs_process_blocks(container_of(work,
-		    struct squashfs_read_request, offload));
-}
-
-static void squashfs_bio_end_io(struct bio *bio)
-{
-	int i;
-	int error = bio->bi_error;
-	struct squashfs_bio_request *bio_req = bio->bi_private;
-
-	bio_put(bio);
-
-	for (i = 0; i < bio_req->nr_buffers; ++i) {
-		if (!bio_req->bh[i])
-			continue;
-		if (!error)
-			set_buffer_uptodate(bio_req->bh[i]);
-		else
-			clear_buffer_uptodate(bio_req->bh[i]);
-		unlock_buffer(bio_req->bh[i]);
-	}
-	kfree(bio_req);
-}
-
-static int bh_is_optional(struct squashfs_read_request *req, int idx)
-{
-	int start_idx, end_idx;
-	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
-
-	start_idx = (idx * msblk->devblksize - req->offset) >> PAGE_SHIFT;
-	end_idx = ((idx + 1) * msblk->devblksize - req->offset + 1) >> PAGE_SHIFT;
-	if (start_idx >= req->output->pages)
-		return 1;
-	if (start_idx < 0)
-		start_idx = end_idx;
-	if (end_idx >= req->output->pages)
-		end_idx = start_idx;
-	return !req->output->page[start_idx] && !req->output->page[end_idx];
-}
-
-static int actor_getblks(struct squashfs_read_request *req, u64 block)
-{
-	int i;
-
-	req->bh = kmalloc_array(req->nr_buffers, sizeof(*(req->bh)), GFP_NOIO);
-	if (!req->bh)
-		return -ENOMEM;
-
-	for (i = 0; i < req->nr_buffers; ++i) {
-		/*
-		 * When dealing with an uncompressed block, the actor may
-		 * contains NULL pages. There's no need to read the buffers
-		 * associated with these pages.
-		 */
-		if (!req->compressed && bh_is_optional(req, i)) {
-			req->bh[i] = NULL;
-			continue;
-		}
-		req->bh[i] = sb_getblk(req->sb, block + i);
-		if (!req->bh[i]) {
-			while (--i) {
-				if (req->bh[i])
-					put_bh(req->bh[i]);
-			}
-			return -1;
-		}
-	}
-	return 0;
-}
-
-static int squashfs_bio_submit(struct squashfs_read_request *req)
+/*
+ * Read the metadata block length, this is stored in the first two
+ * bytes of the metadata block.
+ */
+static struct buffer_head *get_block_length(struct super_block *sb,
+			u64 *cur_index, int *offset, int *length)
 {
-	struct bio *bio = NULL;
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	struct buffer_head *bh;
-	struct squashfs_bio_request *bio_req = NULL;
-	int b = 0, prev_block = 0;
-	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
-
-	u64 read_start = round_down(req->index, msblk->devblksize);
-	u64 read_end = round_up(req->index + req->length, msblk->devblksize);
-	sector_t block = read_start >> msblk->devblksize_log2;
-	sector_t block_end = read_end >> msblk->devblksize_log2;
-	int offset = read_start - round_down(req->index, PAGE_SIZE);
-	int nr_buffers = block_end - block;
-	int blksz = msblk->devblksize;
-	int bio_max_pages = nr_buffers > BIO_MAX_PAGES ? BIO_MAX_PAGES
-						       : nr_buffers;
 
-	/* Setup the request */
-	req->read_end = read_end;
-	req->offset = req->index - read_start;
-	req->nr_buffers = nr_buffers;
-	if (actor_getblks(req, block) < 0)
-		goto getblk_failed;
-
-	/* Create and submit the BIOs */
-	for (b = 0; b < nr_buffers; ++b, offset += blksz) {
-		bh = req->bh[b];
-		if (!bh || !trylock_buffer(bh))
-			continue;
-		if (buffer_uptodate(bh)) {
-			unlock_buffer(bh);
-			continue;
+	bh = sb_bread(sb, *cur_index);
+	if (bh == NULL)
+		return NULL;
+
+	if (msblk->devblksize - *offset == 1) {
+		*length = (unsigned char) bh->b_data[*offset];
+		put_bh(bh);
+		bh = sb_bread(sb, ++(*cur_index));
+		if (bh == NULL)
+			return NULL;
+		*length |= (unsigned char) bh->b_data[0] << 8;
+		*offset = 1;
+	} else {
+		*length = (unsigned char) bh->b_data[*offset] |
+			(unsigned char) bh->b_data[*offset + 1] << 8;
+		*offset += 2;
+
+		if (*offset == msblk->devblksize) {
+			put_bh(bh);
+			bh = sb_bread(sb, ++(*cur_index));
+			if (bh == NULL)
+				return NULL;
+			*offset = 0;
 		}
-		offset %= PAGE_SIZE;
-
-		/* Append the buffer to the current BIO if it is contiguous */
-		if (bio && bio_req && prev_block + 1 == b) {
-			if (bio_add_page(bio, bh->b_page, blksz, offset)) {
-				bio_req->nr_buffers += 1;
-				prev_block = b;
-				continue;
-			}
-		}
-
-		/* Otherwise, submit the current BIO and create a new one */
-		if (bio)
-			submit_bio(READ, bio);
-		bio_req = kcalloc(1, sizeof(struct squashfs_bio_request),
-				  GFP_NOIO);
-		if (!bio_req)
-			goto req_alloc_failed;
-		bio_req->bh = &req->bh[b];
-		bio = bio_alloc(GFP_NOIO, bio_max_pages);
-		if (!bio)
-			goto bio_alloc_failed;
-		bio->bi_bdev = req->sb->s_bdev;
-		bio->bi_iter.bi_sector = (block + b)
-				       << (msblk->devblksize_log2 - 9);
-		bio->bi_private = bio_req;
-		bio->bi_end_io = squashfs_bio_end_io;
-
-		bio_add_page(bio, bh->b_page, blksz, offset);
-		bio_req->nr_buffers += 1;
-		prev_block = b;
 	}
-	if (bio)
-		submit_bio(READ, bio);
 
-	if (req->synchronous)
-		squashfs_process_blocks(req);
-	else {
-		INIT_WORK(&req->offload, read_wq_handler);
-		schedule_work(&req->offload);
-	}
-	return 0;
-
-bio_alloc_failed:
-	kfree(bio_req);
-req_alloc_failed:
-	unlock_buffer(bh);
-	while (--nr_buffers >= b)
-		if (req->bh[nr_buffers])
-			put_bh(req->bh[nr_buffers]);
-	while (--b >= 0)
-		if (req->bh[b])
-			wait_on_buffer(req->bh[b]);
-getblk_failed:
-	free_read_request(req, -ENOMEM);
-	return -ENOMEM;
+	return bh;
 }
 
-static int read_metadata_block(struct squashfs_read_request *req,
-			       u64 *next_index)
-{
-	int ret, error, bytes_read = 0, bytes_uncompressed = 0;
-	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
-
-	if (req->index + 2 > msblk->bytes_used) {
-		free_read_request(req, -EINVAL);
-		return -EINVAL;
-	}
-	req->length = 2;
-
-	/* Do not read beyond the end of the device */
-	if (req->index + req->length > msblk->bytes_used)
-		req->length = msblk->bytes_used - req->index;
-	req->data_processing = SQUASHFS_METADATA;
-
-	/*
-	 * Reading metadata is always synchronous because we don't know the
-	 * length in advance and the function is expected to update
-	 * 'next_index' and return the length.
-	 */
-	req->synchronous = true;
-	req->res = &error;
-	req->bytes_read = &bytes_read;
-	req->bytes_uncompressed = &bytes_uncompressed;
-
-	TRACE("Metadata block @ 0x%llx, %scompressed size %d, src size %d\n",
-	      req->index, req->compressed ? "" : "un", bytes_read,
-	      req->output->length);
-
-	ret = squashfs_bio_submit(req);
-	if (ret)
-		return ret;
-	if (error)
-		return error;
-	if (next_index)
-		*next_index += 2 + bytes_read;
-	return bytes_uncompressed;
-}
-
-static int read_data_block(struct squashfs_read_request *req, int length,
-			   u64 *next_index, bool synchronous)
-{
-	int ret, error = 0, bytes_uncompressed = 0, bytes_read = 0;
-
-	req->compressed = SQUASHFS_COMPRESSED_BLOCK(length);
-	req->length = length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
-	req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
-					       : SQUASHFS_COPY;
-
-	req->synchronous = synchronous;
-	if (synchronous) {
-		req->res = &error;
-		req->bytes_read = &bytes_read;
-		req->bytes_uncompressed = &bytes_uncompressed;
-	}
-
-	TRACE("Data block @ 0x%llx, %scompressed size %d, src size %d\n",
-	      req->index, req->compressed ? "" : "un", req->length,
-	      req->output->length);
-
-	ret = squashfs_bio_submit(req);
-	if (ret)
-		return ret;
-	if (synchronous)
-		ret = error ? error : bytes_uncompressed;
-	if (next_index)
-		*next_index += length;
-	return ret;
-}
 
 /*
  * Read and decompress a metadata block or datablock.  Length is non-zero
@@ -426,50 +87,130 @@ static int read_data_block(struct squashfs_read_request *req, int length,
  * generated a larger block - this does occasionally happen with compression
  * algorithms).
  */
-static int __squashfs_read_data(struct super_block *sb, u64 index, int length,
-	u64 *next_index, struct squashfs_page_actor *output, bool sync)
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+		u64 *next_index, struct squashfs_page_actor *output)
 {
-	struct squashfs_read_request *req;
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	struct buffer_head **bh;
+	int offset = index & ((1 << msblk->devblksize_log2) - 1);
+	u64 cur_index = index >> msblk->devblksize_log2;
+	int bytes, compressed, b = 0, k = 0, avail, i;
 
-	req = kcalloc(1, sizeof(struct squashfs_read_request), GFP_KERNEL);
-	if (!req) {
-		if (!sync)
-			squashfs_page_actor_free(output, -ENOMEM);
+	bh = kcalloc(((output->length + msblk->devblksize - 1)
+		>> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
+	if (bh == NULL)
 		return -ENOMEM;
-	}
 
-	req->sb = sb;
-	req->index = index;
-	req->output = output;
+	if (length) {
+		/*
+		 * Datablock.
+		 */
+		bytes = -offset;
+		compressed = SQUASHFS_COMPRESSED_BLOCK(length);
+		length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
+		if (next_index)
+			*next_index = index + length;
+
+		TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
+			index, compressed ? "" : "un", length, output->length);
+
+		if (length < 0 || length > output->length ||
+				(index + length) > msblk->bytes_used)
+			goto read_failure;
+
+		for (b = 0; bytes < length; b++, cur_index++) {
+			bh[b] = sb_getblk(sb, cur_index);
+			if (bh[b] == NULL)
+				goto block_release;
+			bytes += msblk->devblksize;
+		}
+		ll_rw_block(READ, b, bh);
+	} else {
+		/*
+		 * Metadata block.
+		 */
+		if ((index + 2) > msblk->bytes_used)
+			goto read_failure;
+
+		bh[0] = get_block_length(sb, &cur_index, &offset, &length);
+		if (bh[0] == NULL)
+			goto read_failure;
+		b = 1;
+
+		bytes = msblk->devblksize - offset;
+		compressed = SQUASHFS_COMPRESSED(length);
+		length = SQUASHFS_COMPRESSED_SIZE(length);
+		if (next_index)
+			*next_index = index + length + 2;
 
-	if (next_index)
-		*next_index = index;
+		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
+				compressed ? "" : "un", length);
 
-	if (length)
-		length = read_data_block(req, length, next_index, sync);
-	else
-		length = read_metadata_block(req, next_index);
+		if (length < 0 || length > output->length ||
+					(index + length) > msblk->bytes_used)
+			goto block_release;
 
-	if (length < 0) {
-		ERROR("squashfs_read_data failed to read block 0x%llx\n",
-		      (unsigned long long)index);
-		return -EIO;
+		for (; bytes < length; b++) {
+			bh[b] = sb_getblk(sb, ++cur_index);
+			if (bh[b] == NULL)
+				goto block_release;
+			bytes += msblk->devblksize;
+		}
+		ll_rw_block(READ, b - 1, bh + 1);
 	}
 
-	return length;
-}
+	for (i = 0; i < b; i++) {
+		wait_on_buffer(bh[i]);
+		if (!buffer_uptodate(bh[i]))
+			goto block_release;
+	}
 
-int squashfs_read_data(struct super_block *sb, u64 index, int length,
-	u64 *next_index, struct squashfs_page_actor *output)
-{
-	return __squashfs_read_data(sb, index, length, next_index, output,
-				    true);
-}
+	if (compressed) {
+		if (!msblk->stream)
+			goto read_failure;
+		length = squashfs_decompress(msblk, bh, b, offset, length,
+			output);
+		if (length < 0)
+			goto read_failure;
+	} else {
+		/*
+		 * Block is uncompressed.
+		 */
+		int in, pg_offset = 0;
+		void *data = squashfs_first_page(output);
+
+		for (bytes = length; k < b; k++) {
+			in = min(bytes, msblk->devblksize - offset);
+			bytes -= in;
+			while (in) {
+				if (pg_offset == PAGE_CACHE_SIZE) {
+					data = squashfs_next_page(output);
+					pg_offset = 0;
+				}
+				avail = min_t(int, in, PAGE_CACHE_SIZE -
+						pg_offset);
+				memcpy(data + pg_offset, bh[k]->b_data + offset,
+						avail);
+				in -= avail;
+				pg_offset += avail;
+				offset += avail;
+			}
+			offset = 0;
+			put_bh(bh[k]);
+		}
+		squashfs_finish_page(output);
+	}
 
-int squashfs_read_data_async(struct super_block *sb, u64 index, int length,
-	u64 *next_index, struct squashfs_page_actor *output)
-{
+	kfree(bh);
+	return length;
+
+block_release:
+	for (; k < b; k++)
+		put_bh(bh[k]);
 
-	return __squashfs_read_data(sb, index, length, next_index, output,
-				    false);
+read_failure:
+	ERROR("squashfs_read_data failed to read block 0x%llx\n",
+					(unsigned long long) index);
+	kfree(bh);
+	return -EIO;
 }
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 7d78c3d28bbd..91ce49c05b7c 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -209,14 +209,17 @@ void squashfs_cache_put(struct squashfs_cache_entry *entry)
  */
 void squashfs_cache_delete(struct squashfs_cache *cache)
 {
-	int i;
+	int i, j;
 
 	if (cache == NULL)
 		return;
 
 	for (i = 0; i < cache->entries; i++) {
-		if (cache->entry[i].page)
-			free_page_array(cache->entry[i].page, cache->pages);
+		if (cache->entry[i].data) {
+			for (j = 0; j < cache->pages; j++)
+				kfree(cache->entry[i].data[j]);
+			kfree(cache->entry[i].data);
+		}
 		kfree(cache->entry[i].actor);
 	}
 
@@ -233,7 +236,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
 struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 	int block_size)
 {
-	int i;
+	int i, j;
 	struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 
 	if (cache == NULL) {
@@ -265,13 +268,22 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 		init_waitqueue_head(&cache->entry[i].wait_queue);
 		entry->cache = cache;
 		entry->block = SQUASHFS_INVALID_BLK;
-		entry->page = alloc_page_array(cache->pages, GFP_KERNEL);
-		if (!entry->page) {
+		entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL);
+		if (entry->data == NULL) {
 			ERROR("Failed to allocate %s cache entry\n", name);
 			goto cleanup;
 		}
-		entry->actor = squashfs_page_actor_init(entry->page,
-			cache->pages, 0, NULL);
+
+		for (j = 0; j < cache->pages; j++) {
+			entry->data[j] = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+			if (entry->data[j] == NULL) {
+				ERROR("Failed to allocate %s buffer\n", name);
+				goto cleanup;
+			}
+		}
+
+		entry->actor = squashfs_page_actor_init(entry->data,
+						cache->pages, 0);
 		if (entry->actor == NULL) {
 			ERROR("Failed to allocate %s cache entry\n", name);
 			goto cleanup;
@@ -302,20 +314,18 @@ int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry,
 		return min(length, entry->length - offset);
 
 	while (offset < entry->length) {
-		void *buff = kmap_atomic(entry->page[offset / PAGE_CACHE_SIZE])
-			     + (offset % PAGE_CACHE_SIZE);
+		void *buff = entry->data[offset / PAGE_CACHE_SIZE]
+				+ (offset % PAGE_CACHE_SIZE);
 		int bytes = min_t(int, entry->length - offset,
 				PAGE_CACHE_SIZE - (offset % PAGE_CACHE_SIZE));
 
 		if (bytes >= remaining) {
 			memcpy(buffer, buff, remaining);
-			kunmap_atomic(buff);
 			remaining = 0;
 			break;
 		}
 
 		memcpy(buffer, buff, bytes);
-		kunmap_atomic(buff);
 		buffer += bytes;
 		remaining -= bytes;
 		offset += bytes;
@@ -409,38 +419,43 @@ struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb,
 void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 {
 	int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	struct page **page;
-	void *buff;
-	int res;
+	int i, res;
+	void *table, *buffer, **data;
 	struct squashfs_page_actor *actor;
 
-	page = alloc_page_array(pages, GFP_KERNEL);
-	if (!page)
+	table = buffer = kmalloc(length, GFP_KERNEL);
+	if (table == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	actor = squashfs_page_actor_init(page, pages, length, NULL);
-	if (actor == NULL) {
+	data = kcalloc(pages, sizeof(void *), GFP_KERNEL);
+	if (data == NULL) {
 		res = -ENOMEM;
 		goto failed;
 	}
 
+	actor = squashfs_page_actor_init(data, pages, length);
+	if (actor == NULL) {
+		res = -ENOMEM;
+		goto failed2;
+	}
+
+	for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
+		data[i] = buffer;
+
 	res = squashfs_read_data(sb, block, length |
 		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor);
 
+	kfree(data);
+	kfree(actor);
+
 	if (res < 0)
-		goto failed2;
+		goto failed;
 
-	buff = kmalloc(length, GFP_KERNEL);
-	if (!buff)
-		goto failed2;
-	squashfs_actor_to_buf(actor, buff, length);
-	squashfs_page_actor_free(actor, 0);
-	free_page_array(page, pages);
-	return buff;
+	return table;
 
 failed2:
-	squashfs_page_actor_free(actor, 0);
+	kfree(data);
 failed:
-	free_page_array(page, pages);
+	kfree(table);
 	return ERR_PTR(res);
 }
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index 7de35bf297aa..e9034bf6e5ae 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -24,8 +24,7 @@
 #include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/highmem.h>
-#include <linux/fs.h>
+#include <linux/buffer_head.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -95,44 +94,40 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
 static void *get_comp_opts(struct super_block *sb, unsigned short flags)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	void *comp_opts, *buffer = NULL;
-	struct page *page;
+	void *buffer = NULL, *comp_opts;
 	struct squashfs_page_actor *actor = NULL;
 	int length = 0;
 
-	if (!SQUASHFS_COMP_OPTS(flags))
-		return squashfs_comp_opts(msblk, buffer, length);
-
 	/*
 	 * Read decompressor specific options from file system if present
 	 */
-
-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
-
-	actor = squashfs_page_actor_init(&page, 1, 0, NULL);
-	if (actor == NULL) {
-		comp_opts = ERR_PTR(-ENOMEM);
-		goto actor_error;
-	}
-
-	length = squashfs_read_data(sb,
-		sizeof(struct squashfs_super_block), 0, NULL, actor);
-
-	if (length < 0) {
-		comp_opts = ERR_PTR(length);
-		goto read_error;
+	if (SQUASHFS_COMP_OPTS(flags)) {
+		buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+		if (buffer == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		actor = squashfs_page_actor_init(&buffer, 1, 0);
+		if (actor == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		length = squashfs_read_data(sb,
+			sizeof(struct squashfs_super_block), 0, NULL, actor);
+
+		if (length < 0) {
+			comp_opts = ERR_PTR(length);
+			goto out;
+		}
 	}
 
-	buffer = kmap_atomic(page);
 	comp_opts = squashfs_comp_opts(msblk, buffer, length);
-	kunmap_atomic(buffer);
 
-read_error:
-	squashfs_page_actor_free(actor, 0);
-actor_error:
-	__free_page(page);
+out:
+	kfree(actor);
+	kfree(buffer);
 	return comp_opts;
 }
 
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 43d946617d2d..1ec7bae2751d 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -47,16 +47,12 @@
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/mutex.h>
-#include <linux/mm_inline.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
 #include "squashfs_fs_i.h"
 #include "squashfs.h"
 
-// Backported from 4.5
-#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
-
 /*
  * Locate cache slot in range [offset, index] for specified inode.  If
  * there's more than one return the slot closest to index.
@@ -446,21 +442,6 @@ static int squashfs_readpage_fragment(struct page *page)
 	return res;
 }
 
-static int squashfs_readpages_fragment(struct page *page,
-	struct list_head *readahead_pages, struct address_space *mapping)
-{
-	if (!page) {
-		page = lru_to_page(readahead_pages);
-		list_del(&page->lru);
-		if (add_to_page_cache_lru(page, mapping, page->index,
-			mapping_gfp_constraint(mapping, GFP_KERNEL))) {
-			put_page(page);
-			return 0;
-		}
-	}
-	return squashfs_readpage_fragment(page);
-}
-
 static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
 {
 	struct inode *inode = page->mapping->host;
@@ -473,105 +454,54 @@ static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
 	return 0;
 }
 
-static int squashfs_readpages_sparse(struct page *page,
-	struct list_head *readahead_pages, int index, int file_end,
-	struct address_space *mapping)
-{
-	if (!page) {
-		page = lru_to_page(readahead_pages);
-		list_del(&page->lru);
-		if (add_to_page_cache_lru(page, mapping, page->index,
-			mapping_gfp_constraint(mapping, GFP_KERNEL))) {
-			put_page(page);
-			return 0;
-		}
-	}
-	return squashfs_readpage_sparse(page, index, file_end);
-}
-
-static int __squashfs_readpages(struct file *file, struct page *page,
-	struct list_head *readahead_pages, unsigned int nr_pages,
-	struct address_space *mapping)
+static int squashfs_readpage(struct file *file, struct page *page)
 {
-	struct inode *inode = mapping->host;
+	struct inode *inode = page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
 	int file_end = i_size_read(inode) >> msblk->block_log;
 	int res;
-
-	do {
-		struct page *cur_page = page ? page
-					     : lru_to_page(readahead_pages);
-		int page_index = cur_page->index;
-		int index = page_index >> (msblk->block_log - PAGE_CACHE_SHIFT);
-
-		if (page_index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-						PAGE_CACHE_SHIFT))
-			return 1;
-
-		if (index < file_end || squashfs_i(inode)->fragment_block ==
-						SQUASHFS_INVALID_BLK) {
-			u64 block = 0;
-			int bsize = read_blocklist(inode, index, &block);
-
-			if (bsize < 0)
-				return -1;
-
-			if (bsize == 0) {
-				res = squashfs_readpages_sparse(page,
-					readahead_pages, index, file_end,
-					mapping);
-			} else {
-				res = squashfs_readpages_block(page,
-					readahead_pages, &nr_pages, mapping,
-					page_index, block, bsize);
-			}
-		} else {
-			res = squashfs_readpages_fragment(page,
-				readahead_pages, mapping);
-		}
-		if (res)
-			return 0;
-		page = NULL;
-	} while (readahead_pages && !list_empty(readahead_pages));
-
-	return 0;
-}
-
-static int squashfs_readpage(struct file *file, struct page *page)
-{
-	int ret;
+	void *pageaddr;
 
 	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
-	      page->index, squashfs_i(page->mapping->host)->start);
+				page->index, squashfs_i(inode)->start);
 
-	get_page(page);
+	if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+					PAGE_CACHE_SHIFT))
+		goto out;
 
-	ret = __squashfs_readpages(file, page, NULL, 1, page->mapping);
-	if (ret) {
-		flush_dcache_page(page);
-		if (ret < 0)
-			SetPageError(page);
-		else
-			SetPageUptodate(page);
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
-		unlock_page(page);
-		put_page(page);
-	}
+	if (index < file_end || squashfs_i(inode)->fragment_block ==
+					SQUASHFS_INVALID_BLK) {
+		u64 block = 0;
+		int bsize = read_blocklist(inode, index, &block);
+		if (bsize < 0)
+			goto error_out;
 
-	return 0;
-}
+		if (bsize == 0)
+			res = squashfs_readpage_sparse(page, index, file_end);
+		else
+			res = squashfs_readpage_block(page, block, bsize);
+	} else
+		res = squashfs_readpage_fragment(page);
+
+	if (!res)
+		return 0;
+
+error_out:
+	SetPageError(page);
+out:
+	pageaddr = kmap_atomic(page);
+	memset(pageaddr, 0, PAGE_CACHE_SIZE);
+	kunmap_atomic(pageaddr);
+	flush_dcache_page(page);
+	if (!PageError(page))
+		SetPageUptodate(page);
+	unlock_page(page);
 
-static int squashfs_readpages(struct file *file, struct address_space *mapping,
-			      struct list_head *pages, unsigned int nr_pages)
-{
-	TRACE("Entered squashfs_readpages, %u pages, first page index %lx\n",
-		nr_pages, lru_to_page(pages)->index);
-	__squashfs_readpages(file, NULL, pages, nr_pages, mapping);
 	return 0;
 }
 
 
 const struct address_space_operations squashfs_aops = {
-	.readpage = squashfs_readpage,
-	.readpages = squashfs_readpages,
+	.readpage = squashfs_readpage
 };
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
new file mode 100644
index 000000000000..f2310d2a2019
--- /dev/null
+++ b/fs/squashfs/file_cache.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/* Read separately compressed datablock and memcopy into page cache */
+int squashfs_readpage_block(struct page *page, u64 block, int bsize)
+{
+	struct inode *i = page->mapping->host;
+	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+		block, bsize);
+	int res = buffer->error;
+
+	if (res)
+		ERROR("Unable to read page, block %llx, size %x\n", block,
+			bsize);
+	else
+		squashfs_copy_cache(page, buffer, buffer->length, 0);
+
+	squashfs_cache_put(buffer);
+	return res;
+}
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index c97af4c6ccd0..43e7a7eddac0 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -13,7 +13,6 @@
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/mutex.h>
-#include <linux/mm_inline.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -21,139 +20,157 @@
 #include "squashfs.h"
 #include "page_actor.h"
 
-// Backported from 4.5
-#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+	int pages, struct page **page);
 
-static void release_actor_pages(struct page **page, int pages, int error)
-{
-	int i;
-
-	for (i = 0; i < pages; i++) {
-		if (!page[i])
-			continue;
-		flush_dcache_page(page[i]);
-		if (!error)
-			SetPageUptodate(page[i]);
-		else {
-			SetPageError(page[i]);
-			zero_user_segment(page[i], 0, PAGE_CACHE_SIZE);
-		}
-		unlock_page(page[i]);
-		put_page(page[i]);
-	}
-	kfree(page);
-}
+/* Read separately compressed datablock directly into page cache */
+int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 
-/*
- * Create a "page actor" which will kmap and kunmap the
- * page cache pages appropriately within the decompressor
- */
-static struct squashfs_page_actor *actor_from_page_cache(
-	unsigned int actor_pages, struct page *target_page,
-	struct list_head *rpages, unsigned int *nr_pages, int start_index,
-	struct address_space *mapping)
 {
+	struct inode *inode = target_page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+
+	int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int start_index = target_page->index & ~mask;
+	int end_index = start_index | mask;
+	int i, n, pages, missing_pages, bytes, res = -ENOMEM;
 	struct page **page;
 	struct squashfs_page_actor *actor;
-	int i, n;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
-
-	page = kmalloc_array(actor_pages, sizeof(void *), GFP_KERNEL);
-	if (!page)
-		return NULL;
-
-	for (i = 0, n = start_index; i < actor_pages; i++, n++) {
-		if (target_page == NULL && rpages && !list_empty(rpages)) {
-			struct page *cur_page = lru_to_page(rpages);
-
-			if (cur_page->index < start_index + actor_pages) {
-				list_del(&cur_page->lru);
-				--(*nr_pages);
-				if (add_to_page_cache_lru(cur_page, mapping,
-							  cur_page->index, gfp))
-					put_page(cur_page);
-				else
-					target_page = cur_page;
-			} else
-				rpages = NULL;
-		}
+	void *pageaddr;
+
+	if (end_index > file_end)
+		end_index = file_end;
+
+	pages = end_index - start_index + 1;
 
-		if (target_page && target_page->index == n) {
-			page[i] = target_page;
-			target_page = NULL;
-		} else {
-			page[i] = grab_cache_page_nowait(mapping, n);
-			if (page[i] == NULL)
-				continue;
+	page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL);
+	if (page == NULL)
+		return res;
+
+	/*
+	 * Create a "page actor" which will kmap and kunmap the
+	 * page cache pages appropriately within the decompressor
+	 */
+	actor = squashfs_page_actor_init_special(page, pages, 0);
+	if (actor == NULL)
+		goto out;
+
+	/* Try to grab all the pages covered by the Squashfs block */
+	for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) {
+		page[i] = (n == target_page->index) ? target_page :
+			grab_cache_page_nowait(target_page->mapping, n);
+
+		if (page[i] == NULL) {
+			missing_pages++;
+			continue;
 		}
 
 		if (PageUptodate(page[i])) {
 			unlock_page(page[i]);
-			put_page(page[i]);
+			page_cache_release(page[i]);
 			page[i] = NULL;
+			missing_pages++;
 		}
 	}
 
-	actor = squashfs_page_actor_init(page, actor_pages, 0,
-			release_actor_pages);
-	if (!actor) {
-		release_actor_pages(page, actor_pages, -ENOMEM);
-		kfree(page);
-		return NULL;
+	if (missing_pages) {
+		/*
+		 * Couldn't get one or more pages, this page has either
+		 * been VM reclaimed, but others are still in the page cache
+		 * and uptodate, or we're racing with another thread in
+		 * squashfs_readpage also trying to grab them.  Fall back to
+		 * using an intermediate buffer.
+		 */
+		res = squashfs_read_cache(target_page, block, bsize, pages,
+								page);
+		if (res < 0)
+			goto mark_errored;
+
+		goto out;
 	}
-	return actor;
-}
 
-int squashfs_readpages_block(struct page *target_page,
-			     struct list_head *readahead_pages,
-			     unsigned int *nr_pages,
-			     struct address_space *mapping,
-			     int page_index, u64 block, int bsize)
+	/* Decompress directly into the page cache buffers */
+	res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
+	if (res < 0)
+		goto mark_errored;
+
+	/* Last page may have trailing bytes not filled */
+	bytes = res % PAGE_CACHE_SIZE;
+	if (bytes) {
+		pageaddr = kmap_atomic(page[pages - 1]);
+		memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
+		kunmap_atomic(pageaddr);
+	}
 
-{
-	struct squashfs_page_actor *actor;
-	struct inode *inode = mapping->host;
-	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	int start_index, end_index, file_end, actor_pages, res;
-	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	/* Mark pages as uptodate, unlock and release */
+	for (i = 0; i < pages; i++) {
+		flush_dcache_page(page[i]);
+		SetPageUptodate(page[i]);
+		unlock_page(page[i]);
+		if (page[i] != target_page)
+			page_cache_release(page[i]);
+	}
 
-	/*
-	 * If readpage() is called on an uncompressed datablock, we can just
-	 * read the pages instead of fetching the whole block.
-	 * This greatly improves the performance when a process keep doing
-	 * random reads because we only fetch the necessary data.
-	 * The readahead algorithm will take care of doing speculative reads
-	 * if necessary.
-	 * We can't read more than 1 block even if readahead provides use more
-	 * pages because we don't know yet if the next block is compressed or
-	 * not.
+	kfree(actor);
+	kfree(page);
+
+	return 0;
+
+mark_errored:
+	/* Decompression failed, mark pages as errored.  Target_page is
+	 * dealt with by the caller
 	 */
-	if (bsize && !SQUASHFS_COMPRESSED_BLOCK(bsize)) {
-		u64 block_end = block + msblk->block_size;
-
-		block += (page_index & mask) * PAGE_CACHE_SIZE;
-		actor_pages = (block_end - block) / PAGE_CACHE_SIZE;
-		if (*nr_pages < actor_pages)
-			actor_pages = *nr_pages;
-		start_index = page_index;
-		bsize = min_t(int, bsize, (PAGE_CACHE_SIZE * actor_pages)
-					  | SQUASHFS_COMPRESSED_BIT_BLOCK);
-	} else {
-		file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
-		start_index = page_index & ~mask;
-		end_index = start_index | mask;
-		if (end_index > file_end)
-			end_index = file_end;
-		actor_pages = end_index - start_index + 1;
+	for (i = 0; i < pages; i++) {
+		if (page[i] == NULL || page[i] == target_page)
+			continue;
+		flush_dcache_page(page[i]);
+		SetPageError(page[i]);
+		unlock_page(page[i]);
+		page_cache_release(page[i]);
 	}
 
-	actor = actor_from_page_cache(actor_pages, target_page,
-				      readahead_pages, nr_pages, start_index,
-				      mapping);
-	if (!actor)
-		return -ENOMEM;
+out:
+	kfree(actor);
+	kfree(page);
+	return res;
+}
+
+
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+	int pages, struct page **page)
+{
+	struct inode *i = target_page->mapping->host;
+	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+						 block, bsize);
+	int bytes = buffer->length, res = buffer->error, n, offset = 0;
+	void *pageaddr;
+
+	if (res) {
+		ERROR("Unable to read page, block %llx, size %x\n", block,
+			bsize);
+		goto out;
+	}
+
+	for (n = 0; n < pages && bytes > 0; n++,
+			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
+		int avail = min_t(int, bytes, PAGE_CACHE_SIZE);
+
+		if (page[n] == NULL)
+			continue;
+
+		pageaddr = kmap_atomic(page[n]);
+		squashfs_copy_data(pageaddr, buffer, offset, avail);
+		memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+		kunmap_atomic(pageaddr);
+		flush_dcache_page(page[n]);
+		SetPageUptodate(page[n]);
+		unlock_page(page[n]);
+		if (page[n] != target_page)
+			page_cache_release(page[n]);
+	}
 
-	res = squashfs_read_data_async(inode->i_sb, block, bsize, NULL,
-				       actor);
-	return res < 0 ? res : 0;
+out:
+	squashfs_cache_put(buffer);
+	return res;
 }
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index df4fa3c7ddd0..c31e2bc9c081 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -94,17 +94,39 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct buffer_head **bh, int b, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	int res;
-	size_t dest_len = output->length;
 	struct squashfs_lz4 *stream = strm;
+	void *buff = stream->input, *data;
+	int avail, i, bytes = length, res;
+	size_t dest_len = output->length;
+
+	for (i = 0; i < b; i++) {
+		avail = min(bytes, msblk->devblksize - offset);
+		memcpy(buff, bh[i]->b_data + offset, avail);
+		buff += avail;
+		bytes -= avail;
+		offset = 0;
+		put_bh(bh[i]);
+	}
 
-	squashfs_bh_to_buf(bh, b, stream->input, offset, length,
-		msblk->devblksize);
 	res = lz4_decompress_unknownoutputsize(stream->input, length,
 					stream->output, &dest_len);
 	if (res)
 		return -EIO;
-	squashfs_buf_to_actor(stream->output, output, dest_len);
+
+	bytes = dest_len;
+	data = squashfs_first_page(output);
+	buff = stream->output;
+	while (data) {
+		if (bytes <= PAGE_CACHE_SIZE) {
+			memcpy(data, buff, bytes);
+			break;
+		}
+		memcpy(data, buff, PAGE_CACHE_SIZE);
+		buff += PAGE_CACHE_SIZE;
+		bytes -= PAGE_CACHE_SIZE;
+		data = squashfs_next_page(output);
+	}
+	squashfs_finish_page(output);
 
 	return dest_len;
 }
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 2c844d53a59e..244b9fbfff7b 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -79,19 +79,45 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct buffer_head **bh, int b, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	int res;
-	size_t out_len = output->length;
 	struct squashfs_lzo *stream = strm;
+	void *buff = stream->input, *data;
+	int avail, i, bytes = length, res;
+	size_t out_len = output->length;
+
+	for (i = 0; i < b; i++) {
+		avail = min(bytes, msblk->devblksize - offset);
+		memcpy(buff, bh[i]->b_data + offset, avail);
+		buff += avail;
+		bytes -= avail;
+		offset = 0;
+		put_bh(bh[i]);
+	}
 
-	squashfs_bh_to_buf(bh, b, stream->input, offset, length,
-		msblk->devblksize);
 	res = lzo1x_decompress_safe(stream->input, (size_t)length,
 					stream->output, &out_len);
 	if (res != LZO_E_OK)
-		return -EIO;
-	squashfs_buf_to_actor(stream->output, output, out_len);
+		goto failed;
 
-	return out_len;
+	res = bytes = (int)out_len;
+	data = squashfs_first_page(output);
+	buff = stream->output;
+	while (data) {
+		if (bytes <= PAGE_CACHE_SIZE) {
+			memcpy(data, buff, bytes);
+			break;
+		} else {
+			memcpy(data, buff, PAGE_CACHE_SIZE);
+			buff += PAGE_CACHE_SIZE;
+			bytes -= PAGE_CACHE_SIZE;
+			data = squashfs_next_page(output);
+		}
+	}
+	squashfs_finish_page(output);
+
+	return res;
+
+failed:
+	return -EIO;
 }
 
 const struct squashfs_decompressor squashfs_lzo_comp_ops = {
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 53863508e400..5a1c11f56441 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -9,145 +9,92 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/buffer_head.h>
 #include "page_actor.h"
 
-struct squashfs_page_actor *squashfs_page_actor_init(struct page **page,
-	int pages, int length, void (*release_pages)(struct page **, int, int))
-{
-	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
-
-	if (actor == NULL)
-		return NULL;
+/*
+ * This file contains implementations of page_actor for decompressing into
+ * an intermediate buffer, and for decompressing directly into the
+ * page cache.
+ *
+ * Calling code should avoid sleeping between calls to squashfs_first_page()
+ * and squashfs_finish_page().
+ */
 
-	actor->length = length ? : pages * PAGE_CACHE_SIZE;
-	actor->page = page;
-	actor->pages = pages;
-	actor->next_page = 0;
-	actor->pageaddr = NULL;
-	actor->release_pages = release_pages;
-	return actor;
+/* Implementation of page_actor for decompressing into intermediate buffer */
+static void *cache_first_page(struct squashfs_page_actor *actor)
+{
+	actor->next_page = 1;
+	return actor->buffer[0];
 }
 
-void squashfs_page_actor_free(struct squashfs_page_actor *actor, int error)
+static void *cache_next_page(struct squashfs_page_actor *actor)
 {
-	if (!actor)
-		return;
+	if (actor->next_page == actor->pages)
+		return NULL;
 
-	if (actor->release_pages)
-		actor->release_pages(actor->page, actor->pages, error);
-	kfree(actor);
+	return actor->buffer[actor->next_page++];
 }
 
-void squashfs_actor_to_buf(struct squashfs_page_actor *actor, void *buf,
-	int length)
+static void cache_finish_page(struct squashfs_page_actor *actor)
 {
-	void *pageaddr;
-	int pos = 0, avail, i;
-
-	for (i = 0; i < actor->pages && pos < length; ++i) {
-		avail = min_t(int, length - pos, PAGE_CACHE_SIZE);
-		if (actor->page[i]) {
-			pageaddr = kmap_atomic(actor->page[i]);
-			memcpy(buf + pos, pageaddr, avail);
-			kunmap_atomic(pageaddr);
-		}
-		pos += avail;
-	}
+	/* empty */
 }
 
-void squashfs_buf_to_actor(void *buf, struct squashfs_page_actor *actor,
-	int length)
+struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
+	int pages, int length)
 {
-	void *pageaddr;
-	int pos = 0, avail, i;
-
-	for (i = 0; i < actor->pages && pos < length; ++i) {
-		avail = min_t(int, length - pos, PAGE_CACHE_SIZE);
-		if (actor->page[i]) {
-			pageaddr = kmap_atomic(actor->page[i]);
-			memcpy(pageaddr, buf + pos, avail);
-			kunmap_atomic(pageaddr);
-		}
-		pos += avail;
-	}
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+	if (actor == NULL)
+		return NULL;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->buffer = buffer;
+	actor->pages = pages;
+	actor->next_page = 0;
+	actor->squashfs_first_page = cache_first_page;
+	actor->squashfs_next_page = cache_next_page;
+	actor->squashfs_finish_page = cache_finish_page;
+	return actor;
 }
 
-void squashfs_bh_to_actor(struct buffer_head **bh, int nr_buffers,
-	struct squashfs_page_actor *actor, int offset, int length, int blksz)
+/* Implementation of page_actor for decompressing directly into page cache. */
+static void *direct_first_page(struct squashfs_page_actor *actor)
 {
-	void *kaddr = NULL;
-	int bytes = 0, pgoff = 0, b = 0, p = 0, avail, i;
-
-	while (bytes < length) {
-		if (actor->page[p]) {
-			kaddr = kmap_atomic(actor->page[p]);
-			while (pgoff < PAGE_CACHE_SIZE && bytes < length) {
-				avail = min_t(int, blksz - offset,
-						PAGE_CACHE_SIZE - pgoff);
-				memcpy(kaddr + pgoff, bh[b]->b_data + offset,
-				       avail);
-				pgoff += avail;
-				bytes += avail;
-				offset = (offset + avail) % blksz;
-				if (!offset) {
-					put_bh(bh[b]);
-					++b;
-				}
-			}
-			kunmap_atomic(kaddr);
-			pgoff = 0;
-		} else {
-			for (i = 0; i < PAGE_CACHE_SIZE / blksz; ++i) {
-				if (bh[b])
-					put_bh(bh[b]);
-				++b;
-			}
-			bytes += PAGE_CACHE_SIZE;
-		}
-		++p;
-	}
+	actor->next_page = 1;
+	return actor->pageaddr = kmap_atomic(actor->page[0]);
 }
 
-void squashfs_bh_to_buf(struct buffer_head **bh, int nr_buffers, void *buf,
-	int offset, int length, int blksz)
+static void *direct_next_page(struct squashfs_page_actor *actor)
 {
-	int i, avail, bytes = 0;
-
-	for (i = 0; i < nr_buffers && bytes < length; ++i) {
-		avail = min_t(int, length - bytes, blksz - offset);
-		if (bh[i]) {
-			memcpy(buf + bytes, bh[i]->b_data + offset, avail);
-			put_bh(bh[i]);
-		}
-		bytes += avail;
-		offset = 0;
-	}
+	if (actor->pageaddr)
+		kunmap_atomic(actor->pageaddr);
+
+	return actor->pageaddr = actor->next_page == actor->pages ? NULL :
+		kmap_atomic(actor->page[actor->next_page++]);
 }
 
-void free_page_array(struct page **page, int nr_pages)
+static void direct_finish_page(struct squashfs_page_actor *actor)
 {
-	int i;
-
-	for (i = 0; i < nr_pages; ++i)
-		__free_page(page[i]);
-	kfree(page);
+	if (actor->pageaddr)
+		kunmap_atomic(actor->pageaddr);
 }
 
-struct page **alloc_page_array(int nr_pages, int gfp_mask)
+struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
+	int pages, int length)
 {
-	int i;
-	struct page **page;
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
 
-	page = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
-	if (!page)
+	if (actor == NULL)
 		return NULL;
-	for (i = 0; i < nr_pages; ++i) {
-		page[i] = alloc_page(gfp_mask);
-		if (!page[i]) {
-			free_page_array(page, i);
-			return NULL;
-		}
-	}
-	return page;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->page = page;
+	actor->pages = pages;
+	actor->next_page = 0;
+	actor->pageaddr = NULL;
+	actor->squashfs_first_page = direct_first_page;
+	actor->squashfs_next_page = direct_next_page;
+	actor->squashfs_finish_page = direct_finish_page;
+	return actor;
 }
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index aa1ed790b5a3..26dd82008b82 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -5,61 +5,77 @@
  * Phillip Lougher <phillip@squashfs.org.uk>
  *
  * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level squashfsory.
+ * the COPYING file in the top-level directory.
  */
 
+#ifndef CONFIG_SQUASHFS_FILE_DIRECT
 struct squashfs_page_actor {
-	struct page	**page;
-	void	*pageaddr;
+	void	**page;
 	int	pages;
 	int	length;
 	int	next_page;
-	void	(*release_pages)(struct page **, int, int);
 };
 
-extern struct squashfs_page_actor *squashfs_page_actor_init(struct page **,
-	int, int, void (*)(struct page **, int, int));
-extern void squashfs_page_actor_free(struct squashfs_page_actor *, int);
+static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
+	int pages, int length)
+{
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
 
-extern void squashfs_actor_to_buf(struct squashfs_page_actor *, void *, int);
-extern void squashfs_buf_to_actor(void *, struct squashfs_page_actor *, int);
-extern void squashfs_bh_to_actor(struct buffer_head **, int,
-	struct squashfs_page_actor *, int, int, int);
-extern void squashfs_bh_to_buf(struct buffer_head **, int, void *, int, int,
-	int);
+	if (actor == NULL)
+		return NULL;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->page = page;
+	actor->pages = pages;
+	actor->next_page = 0;
+	return actor;
+}
 
-/*
- * Calling code should avoid sleeping between calls to squashfs_first_page()
- * and squashfs_finish_page().
- */
 static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
 {
 	actor->next_page = 1;
-	return actor->pageaddr = actor->page[0] ? kmap_atomic(actor->page[0])
-						: NULL;
+	return actor->page[0];
 }
 
 static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
 {
-	if (!IS_ERR_OR_NULL(actor->pageaddr))
-		kunmap_atomic(actor->pageaddr);
-
-	if (actor->next_page == actor->pages)
-		return actor->pageaddr = ERR_PTR(-ENODATA);
-
-	actor->pageaddr = actor->page[actor->next_page] ?
-	    kmap_atomic(actor->page[actor->next_page]) : NULL;
-	++actor->next_page;
-	return actor->pageaddr;
+	return actor->next_page == actor->pages ? NULL :
+		actor->page[actor->next_page++];
 }
 
 static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
 {
-	if (!IS_ERR_OR_NULL(actor->pageaddr))
-		kunmap_atomic(actor->pageaddr);
+	/* empty */
 }
+#else
+struct squashfs_page_actor {
+	union {
+		void		**buffer;
+		struct page	**page;
+	};
+	void	*pageaddr;
+	void    *(*squashfs_first_page)(struct squashfs_page_actor *);
+	void    *(*squashfs_next_page)(struct squashfs_page_actor *);
+	void    (*squashfs_finish_page)(struct squashfs_page_actor *);
+	int	pages;
+	int	length;
+	int	next_page;
+};
 
-extern struct page **alloc_page_array(int, int);
-extern void free_page_array(struct page **, int);
-
+extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int);
+extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page
+							 **, int, int);
+static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
+{
+	return actor->squashfs_first_page(actor);
+}
+static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
+{
+	return actor->squashfs_next_page(actor);
+}
+static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
+{
+	actor->squashfs_finish_page(actor);
+}
+#endif
 #endif
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 6093579c6c5d..887d6d270080 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -28,14 +28,8 @@
 #define WARNING(s, args...)	pr_warn("SQUASHFS: "s, ## args)
 
 /* block.c */
-extern int squashfs_init_read_wq(void);
-extern void squashfs_destroy_read_wq(void);
 extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
 				struct squashfs_page_actor *);
-extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
-	struct squashfs_page_actor *);
-extern int squashfs_read_data_async(struct super_block *, u64, int, u64 *,
-	struct squashfs_page_actor *);
 
 /* cache.c */
 extern struct squashfs_cache *squashfs_cache_init(char *, int, int);
@@ -76,9 +70,8 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
 void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
 				int);
 
-/* file_direct.c */
-extern int squashfs_readpages_block(struct page *, struct list_head *,
-	unsigned int *, struct address_space *, int, u64, int);
+/* file_xxx.c */
+extern int squashfs_readpage_block(struct page *, u64, int);
 
 /* id.c */
 extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h
index 3b767ce1e46d..ef69c31947bf 100644
--- a/fs/squashfs/squashfs_fs_sb.h
+++ b/fs/squashfs/squashfs_fs_sb.h
@@ -49,7 +49,7 @@ struct squashfs_cache_entry {
 	int			num_waiters;
 	wait_queue_head_t	wait_queue;
 	struct squashfs_cache	*cache;
-	struct page		**page;
+	void			**data;
 	struct squashfs_page_actor	*actor;
 };
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 4ffbddb688aa..93aa3e23c845 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -445,15 +445,9 @@ static int __init init_squashfs_fs(void)
 	if (err)
 		return err;
 
-	if (!squashfs_init_read_wq()) {
-		destroy_inodecache();
-		return -ENOMEM;
-        }
-
 	err = register_filesystem(&squashfs_fs_type);
 	if (err) {
 		destroy_inodecache();
-		squashfs_destroy_read_wq();
 		return err;
 	}
 
@@ -467,7 +461,6 @@ static void __exit exit_squashfs_fs(void)
 {
 	unregister_filesystem(&squashfs_fs_type);
 	destroy_inodecache();
-	squashfs_destroy_read_wq();
 }
 
 
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 14cd373e1897..c609624e4b8a 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -55,7 +55,7 @@ static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk,
 	struct comp_opts *opts;
 	int err = 0, n;
 
-	opts = kmalloc(sizeof(*opts), GFP_ATOMIC);
+	opts = kmalloc(sizeof(*opts), GFP_KERNEL);
 	if (opts == NULL) {
 		err = -ENOMEM;
 		goto out2;
@@ -136,7 +136,6 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	enum xz_ret xz_err;
 	int avail, total = 0, k = 0;
 	struct squashfs_xz *stream = strm;
-	void *buf = NULL;
 
 	xz_dec_reset(stream->state);
 	stream->buf.in_pos = 0;
@@ -157,20 +156,12 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 
 		if (stream->buf.out_pos == stream->buf.out_size) {
 			stream->buf.out = squashfs_next_page(output);
-			if (!IS_ERR(stream->buf.out)) {
+			if (stream->buf.out != NULL) {
 				stream->buf.out_pos = 0;
 				total += PAGE_CACHE_SIZE;
 			}
 		}
 
-		if (!stream->buf.out) {
-			if (!buf) {
-				buf = kmalloc(PAGE_CACHE_SIZE, GFP_ATOMIC);
-				if (!buf)
-					goto out;
-			}
-			stream->buf.out = buf;
-		}
 		xz_err = xz_dec_run(stream->state, &stream->buf);
 
 		if (stream->buf.in_pos == stream->buf.in_size && k < b)
@@ -182,13 +173,11 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	if (xz_err != XZ_STREAM_END || k < b)
 		goto out;
 
-	kfree(buf);
 	return total + stream->buf.out_pos;
 
 out:
 	for (; k < b; k++)
 		put_bh(bh[k]);
-	kfree(buf);
 
 	return -EIO;
 }
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 09c892b5308e..8727caba6882 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -66,7 +66,6 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct buffer_head **bh, int b, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	void *buf = NULL;
 	int zlib_err, zlib_init = 0, k = 0;
 	z_stream *stream = strm;
 
@@ -85,19 +84,10 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 
 		if (stream->avail_out == 0) {
 			stream->next_out = squashfs_next_page(output);
-			if (!IS_ERR(stream->next_out))
+			if (stream->next_out != NULL)
 				stream->avail_out = PAGE_CACHE_SIZE;
 		}
 
-		if (!stream->next_out) {
-			if (!buf) {
-				buf = kmalloc(PAGE_CACHE_SIZE, GFP_ATOMIC);
-				if (!buf)
-					goto out;
-			}
-			stream->next_out = buf;
-		}
-
 		if (!zlib_init) {
 			zlib_err = zlib_inflateInit(stream);
 			if (zlib_err != Z_OK) {
@@ -125,13 +115,11 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	if (k < b)
 		goto out;
 
-	kfree(buf);
 	return stream->total_out;
 
 out:
 	for (; k < b; k++)
 		put_bh(bh[k]);
-	kfree(buf);
 
 	return -EIO;
 }
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 02fa1dcc5969..29f5b2e589a1 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait)
                 }
         }
 	brelse(bh);
-	return 0;
+	return err;
 }
 
 int sysv_write_inode(struct inode *inode, struct writeback_control *wbc)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a8e09a66bb2d..47c7bb494c74 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1208,7 +1208,7 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-		void *buf, int len, int write);
+		void *buf, int len, unsigned int gup_flags);
 
 long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		      unsigned long start, unsigned long nr_pages,
@@ -1216,19 +1216,17 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		      struct vm_area_struct **vmas, int *nonblocking);
 long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages,
+		    unsigned int gup_flags, struct page **pages,
 		    struct vm_area_struct **vmas);
 long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages,
-		    int *locked);
+		    unsigned int gup_flags, struct page **pages, int *locked);
 long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			       unsigned long start, unsigned long nr_pages,
-			       int write, int force, struct page **pages,
-			       unsigned int gup_flags);
+			       struct page **pages, unsigned int gup_flags);
 long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages);
+		    struct page **pages, unsigned int gup_flags);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 
@@ -1246,7 +1244,7 @@ struct frame_vector {
 struct frame_vector *frame_vector_create(unsigned int nr_frames);
 void frame_vector_destroy(struct frame_vector *vec);
 int get_vaddr_frames(unsigned long start, unsigned int nr_pfns,
-		     bool write, bool force, struct frame_vector *vec);
+		     unsigned int gup_flags, struct frame_vector *vec);
 void put_vaddr_frames(struct frame_vector *vec);
 int frame_vector_to_pages(struct frame_vector *vec);
 void frame_vector_to_pfns(struct frame_vector *vec);
@@ -2142,6 +2140,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_MLOCK	0x1000	/* lock present pages */
 #define FOLL_COW	0x4000	/* internal GUP flag */
+#define FOLL_ANON	0x8000	/* don't do file mappings */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 907f3fd191ac..3e28a1a8d823 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -65,8 +65,8 @@ struct k_itimer {
 	spinlock_t it_lock;
 	clockid_t it_clock;		/* which timer type */
 	timer_t it_id;			/* timer id */
-	int it_overrun;			/* overrun on pending signal  */
-	int it_overrun_last;		/* overrun on last delivered signal */
+	s64 it_overrun;			/* overrun on pending signal  */
+	s64 it_overrun_last;		/* overrun on last delivered signal */
 	int it_requeue_pending;		/* waiting to requeue this timer */
 #define REQUEUE_PENDING 1
 	int it_sigev_notify;		/* notify word of sigevent struct */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 8b683841e574..f6017ddc4ded 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -448,6 +448,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 
 static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
+	unsigned int hh_alen = 0;
 	unsigned int seq;
 	int hh_len;
 
@@ -455,16 +456,33 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 		seq = read_seqbegin(&hh->hh_lock);
 		hh_len = hh->hh_len;
 		if (likely(hh_len <= HH_DATA_MOD)) {
-			/* this is inlined by gcc */
-			memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+			hh_alen = HH_DATA_MOD;
+
+			/* skb_push() would proceed silently if we have room for
+			 * the unaligned size but not for the aligned size:
+			 * check headroom explicitly.
+			 */
+			if (likely(skb_headroom(skb) >= HH_DATA_MOD)) {
+				/* this is inlined by gcc */
+				memcpy(skb->data - HH_DATA_MOD, hh->hh_data,
+				       HH_DATA_MOD);
+			}
 		} else {
-			int hh_alen = HH_DATA_ALIGN(hh_len);
+			hh_alen = HH_DATA_ALIGN(hh_len);
 
-			memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+			if (likely(skb_headroom(skb) >= hh_alen)) {
+				memcpy(skb->data - hh_alen, hh->hh_data,
+				       hh_alen);
+			}
 		}
 	} while (read_seqretry(&hh->hh_lock, seq));
 
-	skb_push(skb, hh_len);
+	if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	__skb_push(skb, hh_len);
 	return dev_queue_xmit(skb);
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 35dfa9e9d69e..c43ca9857479 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -191,6 +191,7 @@ struct bpf_insn_aux_data {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
 		struct bpf_map *map_ptr;	/* pointer for call insn into lookup_elem */
 	};
+	int sanitize_stack_off; /* stack slot to be cleared */
 	bool seen; /* this insn was processed by the verifier */
 };
 
@@ -569,10 +570,11 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 /* check_stack_read/write functions track spill/fill of registers,
  * stack boundary and alignment are checked in check_mem_access()
  */
-static int check_stack_write(struct verifier_state *state, int off, int size,
-			     int value_regno)
+static int check_stack_write(struct verifier_env *env,
+			     struct verifier_state *state, int off,
+			     int size, int value_regno, int insn_idx)
 {
-	int i;
+	int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
 	 * so it's aligned access and [off, off + size) are within stack limits
 	 */
@@ -587,15 +589,37 @@ static int check_stack_write(struct verifier_state *state, int off, int size,
 		}
 
 		/* save register state */
-		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
-			state->regs[value_regno];
-
-		for (i = 0; i < BPF_REG_SIZE; i++)
+		state->spilled_regs[spi] = state->regs[value_regno];
+
+		for (i = 0; i < BPF_REG_SIZE; i++) {
+			if (state->stack_slot_type[MAX_BPF_STACK + off + i] == STACK_MISC &&
+			    !env->allow_ptr_leaks) {
+				int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+				int soff = (-spi - 1) * BPF_REG_SIZE;
+
+				/* detected reuse of integer stack slot with a pointer
+				 * which means either llvm is reusing stack slot or
+				 * an attacker is trying to exploit CVE-2018-3639
+				 * (speculative store bypass)
+				 * Have to sanitize that slot with preemptive
+				 * store of zero.
+				 */
+				if (*poff && *poff != soff) {
+					/* disallow programs where single insn stores
+					 * into two different stack slots, since verifier
+					 * cannot sanitize them
+					 */
+					verbose("insn %d cannot access two stack slots fp%d and fp%d",
+						insn_idx, *poff, soff);
+					return -EINVAL;
+				}
+				*poff = soff;
+			}
 			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
+		}
 	} else {
 		/* regular write of data into stack */
-		state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
-			(struct reg_state) {};
+		state->spilled_regs[spi] = (struct reg_state) {};
 
 		for (i = 0; i < size; i++)
 			state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
@@ -696,7 +720,7 @@ static bool is_ctx_reg(struct verifier_env *env, int regno)
  * if t==write && value_regno==-1, some unknown value is stored into memory
  * if t==read && value_regno==-1, don't care what we read from memory
  */
-static int check_mem_access(struct verifier_env *env, u32 regno, int off,
+static int check_mem_access(struct verifier_env *env, int insn_idx, u32 regno, int off,
 			    int bpf_size, enum bpf_access_type t,
 			    int value_regno)
 {
@@ -748,7 +772,8 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 				verbose("attempt to corrupt spilled pointer on stack\n");
 				return -EACCES;
 			}
-			err = check_stack_write(state, off, size, value_regno);
+			err = check_stack_write(env, state, off, size,
+						value_regno, insn_idx);
 		} else {
 			err = check_stack_read(state, off, size, value_regno);
 		}
@@ -760,7 +785,7 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 	return err;
 }
 
-static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
+static int check_xadd(struct verifier_env *env, int insn_idx, struct bpf_insn *insn)
 {
 	struct reg_state *regs = env->cur_state.regs;
 	int err;
@@ -793,13 +818,13 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	/* check whether atomic_add can read the memory */
-	err = check_mem_access(env, insn->dst_reg, insn->off,
+	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_READ, -1);
 	if (err)
 		return err;
 
 	/* check whether atomic_add can write into the same memory */
-	return check_mem_access(env, insn->dst_reg, insn->off,
+	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 				BPF_SIZE(insn->code), BPF_WRITE, -1);
 }
 
@@ -1838,13 +1863,14 @@ static int do_check(struct verifier_env *env)
 			/* check that memory (src_reg + off) is readable,
 			 * the state of dst_reg will be updated by this func
 			 */
-			err = check_mem_access(env, insn->src_reg, insn->off,
+			err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_READ,
 					       insn->dst_reg);
 			if (err)
 				return err;
 
-			if (BPF_SIZE(insn->code) != BPF_W) {
+			if (BPF_SIZE(insn->code) != BPF_W &&
+			    BPF_SIZE(insn->code) != BPF_DW) {
 				insn_idx++;
 				continue;
 			}
@@ -1876,7 +1902,7 @@ static int do_check(struct verifier_env *env)
 			enum bpf_reg_type *prev_dst_type, dst_reg_type;
 
 			if (BPF_MODE(insn->code) == BPF_XADD) {
-				err = check_xadd(env, insn);
+				err = check_xadd(env, insn_idx, insn);
 				if (err)
 					return err;
 				insn_idx++;
@@ -1895,7 +1921,7 @@ static int do_check(struct verifier_env *env)
 			dst_reg_type = regs[insn->dst_reg].type;
 
 			/* check that memory (dst_reg + off) is writeable */
-			err = check_mem_access(env, insn->dst_reg, insn->off,
+			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
 					       insn->src_reg);
 			if (err)
@@ -1930,7 +1956,7 @@ static int do_check(struct verifier_env *env)
 			}
 
 			/* check that memory (dst_reg + off) is writeable */
-			err = check_mem_access(env, insn->dst_reg, insn->off,
+			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
 					       -1);
 			if (err)
@@ -2220,13 +2246,43 @@ static int convert_ctx_accesses(struct verifier_env *env)
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		u32 cnt;
 
-		if (insn->code == (BPF_LDX | BPF_MEM | BPF_W))
+		if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
+		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
 			type = BPF_READ;
-		else if (insn->code == (BPF_STX | BPF_MEM | BPF_W))
+		else if (insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+			 insn->code == (BPF_STX | BPF_MEM | BPF_DW))
 			type = BPF_WRITE;
 		else
 			continue;
 
+		if (type == BPF_WRITE &&
+		    env->insn_aux_data[i + delta].sanitize_stack_off) {
+			struct bpf_insn patch[] = {
+				/* Sanitize suspicious stack slot with zero.
+				 * There are no memory dependencies for this store,
+				 * since it's only using frame pointer and immediate
+				 * constant of zero
+				 */
+				BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+					   env->insn_aux_data[i + delta].sanitize_stack_off,
+					   0),
+				/* the original STX instruction will immediately
+				 * overwrite the same stack slot with appropriate value
+				 */
+				*insn,
+			};
+
+			cnt = ARRAY_SIZE(patch);
+			new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
 			continue;
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d8fc54eef51c..26a4cba37128 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -299,7 +299,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
 
 retry:
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
+	ret = get_user_pages(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page, &vma);
 	if (ret <= 0)
 		return ret;
 
@@ -1699,7 +1699,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	if (likely(result == 0))
 		goto out;
 
-	result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+	result = get_user_pages(NULL, mm, vaddr, 1, FOLL_FORCE, &page, NULL);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 051544aec37c..d176c127f744 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -103,7 +103,7 @@ static void bump_cpu_timer(struct k_itimer *timer,
 			continue;
 
 		timer->it.cpu.expires += incr;
-		timer->it_overrun += 1 << i;
+		timer->it_overrun += 1LL << i;
 		delta -= incr;
 	}
 }
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index fc7c37ad90a0..0e6ed2e7d066 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -355,6 +355,17 @@ static __init int init_posix_timers(void)
 
 __initcall(init_posix_timers);
 
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+	s64 sum = timr->it_overrun_last + (s64)baseval;
+
+	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
 static void schedule_next_timer(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
@@ -362,12 +373,11 @@ static void schedule_next_timer(struct k_itimer *timr)
 	if (timr->it.real.interval.tv64 == 0)
 		return;
 
-	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
-						timer->base->get_time(),
-						timr->it.real.interval);
+	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+					    timr->it.real.interval);
 
 	timr->it_overrun_last = timr->it_overrun;
-	timr->it_overrun = -1;
+	timr->it_overrun = -1LL;
 	++timr->it_requeue_pending;
 	hrtimer_restart(timer);
 }
@@ -396,7 +406,7 @@ void do_schedule_next_timer(struct siginfo *info)
 		else
 			schedule_next_timer(timr);
 
-		info->si_overrun += timr->it_overrun_last;
+		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
 	}
 
 	if (timr)
@@ -491,8 +501,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 					now = ktime_add(now, kj);
 			}
 #endif
-			timr->it_overrun += (unsigned int)
-				hrtimer_forward(timer, now,
+			timr->it_overrun += hrtimer_forward(timer, now,
 						timr->it.real.interval);
 			ret = HRTIMER_RESTART;
 			++timr->it_requeue_pending;
@@ -633,7 +642,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 	it_id_set = IT_ID_SET;
 	new_timer->it_id = (timer_t) new_timer_id;
 	new_timer->it_clock = which_clock;
-	new_timer->it_overrun = -1;
+	new_timer->it_overrun = -1LL;
 
 	if (timer_event_spec) {
 		if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
@@ -762,7 +771,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 	 */
 	if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
 			timr->it_sigev_notify == SIGEV_NONE))
-		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+		timr->it_overrun += hrtimer_forward(timer, now, iv);
 
 	remaining = __hrtimer_expires_remaining_adjusted(timer, now);
 	/* Return 0 only, when the timer is expired and not pending */
@@ -824,7 +833,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	if (!timr)
 		return -EINVAL;
 
-	overrun = timr->it_overrun_last;
+	overrun = timer_overrun_to_int(timr, 0);
 	unlock_timer(timr, flags);
 
 	return overrun;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 998d730401b3..d38f8dde3c75 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -389,7 +389,7 @@ static int __init init_timer_list_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = proc_create("timer_list", 0444, NULL, &timer_list_fops);
+	pe = proc_create("timer_list", 0400, NULL, &timer_list_fops);
 	if (!pe)
 		return -ENOMEM;
 	return 0;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4228fd3682c3..3dd40c736067 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -119,11 +119,13 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
 			i++;
 		} else if (fmt[i] == 'p' || fmt[i] == 's') {
 			mod[fmt_cnt]++;
-			i++;
-			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+			/* disallow any further format extensions */
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
 			fmt_cnt++;
-			if (fmt[i - 1] == 's') {
+			if (fmt[i] == 's') {
 				if (str_seen)
 					/* allow only one '%s' per fmt string */
 					return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ac758a53fcea..d90b42b39908 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4767,6 +4767,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
 	if (ops->flags & FTRACE_OPS_FL_ENABLED)
 		ftrace_shutdown(ops, 0);
 	ops->flags |= FTRACE_OPS_FL_DELETED;
+	ftrace_free_filter(ops);
 	mutex_unlock(&ftrace_lock);
 }
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b8a894adab2c..8be66a2b0cac 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -727,8 +727,10 @@ static int set_trigger_filter(char *filter_str,
 
 	/* The filter is for the 'trigger' event, not the triggered event */
 	ret = create_event_filter(file->event_call, filter_str, false, &filter);
-	if (ret)
-		goto out;
+	/*
+	 * If create_event_filter() fails, filter still needs to be freed.
+	 * Which the calling code will do with data->filter.
+	 */
  assign:
 	tmp = rcu_access_pointer(data->filter);
 
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 04e3bb84560e..7caa6ce8e2e2 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -1090,7 +1090,8 @@ void __init debug_objects_mem_init(void)
 
 	obj_cache = kmem_cache_create("debug_objects_cache",
 				      sizeof (struct debug_obj), 0,
-				      SLAB_DEBUG_OBJECTS, NULL);
+				      SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE,
+				      NULL);
 
 	if (!obj_cache || debug_objects_replace_static_objects()) {
 		debug_objects_enabled = 0;
diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c
index 245900b98c8e..222c8010bda0 100644
--- a/lib/interval_tree_test.c
+++ b/lib/interval_tree_test.c
@@ -1,27 +1,38 @@
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/interval_tree.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <asm/timex.h>
 
-#define NODES        100
-#define PERF_LOOPS   100000
-#define SEARCHES     100
-#define SEARCH_LOOPS 10000
+#define __param(type, name, init, msg)		\
+	static type name = init;		\
+	module_param(name, type, 0444);		\
+	MODULE_PARM_DESC(name, msg);
+
+__param(int, nnodes, 100, "Number of nodes in the interval tree");
+__param(int, perf_loops, 1000, "Number of iterations modifying the tree");
+
+__param(int, nsearches, 100, "Number of searches to the interval tree");
+__param(int, search_loops, 1000, "Number of iterations searching the tree");
+__param(bool, search_all, false, "Searches will iterate all nodes in the tree");
+
+__param(uint, max_endpoint, ~0, "Largest value for the interval's endpoint");
 
 static struct rb_root root = RB_ROOT;
-static struct interval_tree_node nodes[NODES];
-static u32 queries[SEARCHES];
+static struct interval_tree_node *nodes = NULL;
+static u32 *queries = NULL;
 
 static struct rnd_state rnd;
 
 static inline unsigned long
-search(unsigned long query, struct rb_root *root)
+search(struct rb_root *root, unsigned long start, unsigned long last)
 {
 	struct interval_tree_node *node;
 	unsigned long results = 0;
 
-	for (node = interval_tree_iter_first(root, query, query); node;
-	     node = interval_tree_iter_next(node, query, query))
+	for (node = interval_tree_iter_first(root, start, last); node;
+	     node = interval_tree_iter_next(node, start, last))
 		results++;
 	return results;
 }
@@ -29,19 +40,22 @@ search(unsigned long query, struct rb_root *root)
 static void init(void)
 {
 	int i;
-	for (i = 0; i < NODES; i++) {
-		u32 a = prandom_u32_state(&rnd);
-		u32 b = prandom_u32_state(&rnd);
-		if (a <= b) {
-			nodes[i].start = a;
-			nodes[i].last = b;
-		} else {
-			nodes[i].start = b;
-			nodes[i].last = a;
-		}
+
+	for (i = 0; i < nnodes; i++) {
+		u32 b = (prandom_u32_state(&rnd) >> 4) % max_endpoint;
+		u32 a = (prandom_u32_state(&rnd) >> 4) % b;
+
+		nodes[i].start = a;
+		nodes[i].last = b;
 	}
-	for (i = 0; i < SEARCHES; i++)
-		queries[i] = prandom_u32_state(&rnd);
+
+	/*
+	 * Limit the search scope to what the user defined.
+	 * Otherwise we are merely measuring empty walks,
+	 * which is pointless.
+	 */
+	for (i = 0; i < nsearches; i++)
+		queries[i] = (prandom_u32_state(&rnd) >> 4) % max_endpoint;
 }
 
 static int interval_tree_test_init(void)
@@ -50,6 +64,16 @@ static int interval_tree_test_init(void)
 	unsigned long results;
 	cycles_t time1, time2, time;
 
+	nodes = kmalloc(nnodes * sizeof(struct interval_tree_node), GFP_KERNEL);
+	if (!nodes)
+		return -ENOMEM;
+
+	queries = kmalloc(nsearches * sizeof(int), GFP_KERNEL);
+	if (!queries) {
+		kfree(nodes);
+		return -ENOMEM;
+	}
+
 	printk(KERN_ALERT "interval tree insert/remove");
 
 	prandom_seed_state(&rnd, 3141592653589793238ULL);
@@ -57,39 +81,46 @@ static int interval_tree_test_init(void)
 
 	time1 = get_cycles();
 
-	for (i = 0; i < PERF_LOOPS; i++) {
-		for (j = 0; j < NODES; j++)
+	for (i = 0; i < perf_loops; i++) {
+		for (j = 0; j < nnodes; j++)
 			interval_tree_insert(nodes + j, &root);
-		for (j = 0; j < NODES; j++)
+		for (j = 0; j < nnodes; j++)
 			interval_tree_remove(nodes + j, &root);
 	}
 
 	time2 = get_cycles();
 	time = time2 - time1;
 
-	time = div_u64(time, PERF_LOOPS);
+	time = div_u64(time, perf_loops);
 	printk(" -> %llu cycles\n", (unsigned long long)time);
 
 	printk(KERN_ALERT "interval tree search");
 
-	for (j = 0; j < NODES; j++)
+	for (j = 0; j < nnodes; j++)
 		interval_tree_insert(nodes + j, &root);
 
 	time1 = get_cycles();
 
 	results = 0;
-	for (i = 0; i < SEARCH_LOOPS; i++)
-		for (j = 0; j < SEARCHES; j++)
-			results += search(queries[j], &root);
+	for (i = 0; i < search_loops; i++)
+		for (j = 0; j < nsearches; j++) {
+			unsigned long start = search_all ? 0 : queries[j];
+			unsigned long last = search_all ? max_endpoint : queries[j];
+
+			results += search(&root, start, last);
+		}
 
 	time2 = get_cycles();
 	time = time2 - time1;
 
-	time = div_u64(time, SEARCH_LOOPS);
-	results = div_u64(results, SEARCH_LOOPS);
+	time = div_u64(time, search_loops);
+	results = div_u64(results, search_loops);
 	printk(" -> %llu cycles (%lu results)\n",
 	       (unsigned long long)time, results);
 
+	kfree(queries);
+	kfree(nodes);
+
 	return -EAGAIN; /* Fail will directly unload the module */
 }
 
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
index 8b3c9dc88262..afedd3770562 100644
--- a/lib/rbtree_test.c
+++ b/lib/rbtree_test.c
@@ -1,11 +1,18 @@
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/rbtree_augmented.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <asm/timex.h>
 
-#define NODES       100
-#define PERF_LOOPS  100000
-#define CHECK_LOOPS 100
+#define __param(type, name, init, msg)		\
+	static type name = init;		\
+	module_param(name, type, 0444);		\
+	MODULE_PARM_DESC(name, msg);
+
+__param(int, nnodes, 100, "Number of nodes in the rb-tree");
+__param(int, perf_loops, 1000, "Number of iterations modifying the rb-tree");
+__param(int, check_loops, 100, "Number of iterations modifying and verifying the rb-tree");
 
 struct test_node {
 	u32 key;
@@ -17,7 +24,7 @@ struct test_node {
 };
 
 static struct rb_root root = RB_ROOT;
-static struct test_node nodes[NODES];
+static struct test_node *nodes = NULL;
 
 static struct rnd_state rnd;
 
@@ -95,7 +102,7 @@ static void erase_augmented(struct test_node *node, struct rb_root *root)
 static void init(void)
 {
 	int i;
-	for (i = 0; i < NODES; i++) {
+	for (i = 0; i < nnodes; i++) {
 		nodes[i].key = prandom_u32_state(&rnd);
 		nodes[i].val = prandom_u32_state(&rnd);
 	}
@@ -177,6 +184,10 @@ static int __init rbtree_test_init(void)
 	int i, j;
 	cycles_t time1, time2, time;
 
+	nodes = kmalloc(nnodes * sizeof(*nodes), GFP_KERNEL);
+	if (!nodes)
+		return -ENOMEM;
+
 	printk(KERN_ALERT "rbtree testing");
 
 	prandom_seed_state(&rnd, 3141592653589793238ULL);
@@ -184,27 +195,27 @@ static int __init rbtree_test_init(void)
 
 	time1 = get_cycles();
 
-	for (i = 0; i < PERF_LOOPS; i++) {
-		for (j = 0; j < NODES; j++)
+	for (i = 0; i < perf_loops; i++) {
+		for (j = 0; j < nnodes; j++)
 			insert(nodes + j, &root);
-		for (j = 0; j < NODES; j++)
+		for (j = 0; j < nnodes; j++)
 			erase(nodes + j, &root);
 	}
 
 	time2 = get_cycles();
 	time = time2 - time1;
 
-	time = div_u64(time, PERF_LOOPS);
+	time = div_u64(time, perf_loops);
 	printk(" -> %llu cycles\n", (unsigned long long)time);
 
-	for (i = 0; i < CHECK_LOOPS; i++) {
+	for (i = 0; i < check_loops; i++) {
 		init();
-		for (j = 0; j < NODES; j++) {
+		for (j = 0; j < nnodes; j++) {
 			check(j);
 			insert(nodes + j, &root);
 		}
-		for (j = 0; j < NODES; j++) {
-			check(NODES - j);
+		for (j = 0; j < nnodes; j++) {
+			check(nnodes - j);
 			erase(nodes + j, &root);
 		}
 		check(0);
@@ -216,32 +227,34 @@ static int __init rbtree_test_init(void)
 
 	time1 = get_cycles();
 
-	for (i = 0; i < PERF_LOOPS; i++) {
-		for (j = 0; j < NODES; j++)
+	for (i = 0; i < perf_loops; i++) {
+		for (j = 0; j < nnodes; j++)
 			insert_augmented(nodes + j, &root);
-		for (j = 0; j < NODES; j++)
+		for (j = 0; j < nnodes; j++)
 			erase_augmented(nodes + j, &root);
 	}
 
 	time2 = get_cycles();
 	time = time2 - time1;
 
-	time = div_u64(time, PERF_LOOPS);
+	time = div_u64(time, perf_loops);
 	printk(" -> %llu cycles\n", (unsigned long long)time);
 
-	for (i = 0; i < CHECK_LOOPS; i++) {
+	for (i = 0; i < check_loops; i++) {
 		init();
-		for (j = 0; j < NODES; j++) {
+		for (j = 0; j < nnodes; j++) {
 			check_augmented(j);
 			insert_augmented(nodes + j, &root);
 		}
-		for (j = 0; j < NODES; j++) {
-			check_augmented(NODES - j);
+		for (j = 0; j < nnodes; j++) {
+			check_augmented(nnodes - j);
 			erase_augmented(nodes + j, &root);
 		}
 		check_augmented(0);
 	}
 
+	kfree(nodes);
+
 	return -EAGAIN; /* Fail will directly unload the module */
 }
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 771234d050c7..6bc452b33b76 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -17,6 +17,8 @@
  * 08/12/11 beckyb	Add highmem support
  */
 
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
 #include <linux/cache.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
@@ -143,20 +145,16 @@ static bool no_iotlb_memory;
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-	unsigned char *vstart, *vend;
 
 	if (no_iotlb_memory) {
-		pr_warn("software IO TLB: No low mem\n");
+		pr_warn("No low mem\n");
 		return;
 	}
 
-	vstart = phys_to_virt(io_tlb_start);
-	vend = phys_to_virt(io_tlb_end);
-
-	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
 	       (unsigned long long)io_tlb_start,
 	       (unsigned long long)io_tlb_end,
-	       bytes >> 20, vstart, vend - 1);
+	       bytes >> 20);
 }
 
 int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
@@ -230,7 +228,7 @@ swiotlb_init(int verbose)
 	if (io_tlb_start)
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	pr_warn("Cannot allocate SWIOTLB buffer");
+	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
 
@@ -272,8 +270,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 		return -ENOMEM;
 	}
 	if (order != get_order(bytes)) {
-		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
-		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+		pr_warn("only able to allocate %ld MB\n",
+			(PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
 	}
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
@@ -680,7 +678,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	return ret;
 
 err_warn:
-	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+	pr_warn("coherent allocation failed for device %s size=%zu\n",
 		dev_name(hwdev), size);
 	dump_stack();
 
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index 7cf2b7163222..c1e7926a41c4 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -11,10 +11,7 @@
  * get_vaddr_frames() - map virtual addresses to pfns
  * @start:	starting user address
  * @nr_frames:	number of pages / pfns from start to map
- * @write:	whether pages will be written to by the caller
- * @force:	whether to force write access even if user mapping is
- *		readonly. See description of the same argument of
-		get_user_pages().
+ * @gup_flags:	flags modifying lookup behaviour
  * @vec:	structure which receives pages / pfns of the addresses mapped.
  *		It should have space for at least nr_frames entries.
  *
@@ -34,7 +31,7 @@
  * This function takes care of grabbing mmap_sem as necessary.
  */
 int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
-		     bool write, bool force, struct frame_vector *vec)
+		     unsigned int gup_flags, struct frame_vector *vec)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
@@ -59,7 +56,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 		vec->got_ref = true;
 		vec->is_pfns = false;
 		ret = get_user_pages_locked(current, mm, start, nr_frames,
-			write, force, (struct page **)(vec->ptrs), &locked);
+			gup_flags, (struct page **)(vec->ptrs), &locked);
 		goto out;
 	}
 
diff --git a/mm/gup.c b/mm/gup.c
index 018144c4b9ec..2cd3b31e3666 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -368,6 +368,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (vm_flags & (VM_IO | VM_PFNMAP))
 		return -EFAULT;
 
+	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+		return -EFAULT;
+
 	if (gup_flags & FOLL_WRITE) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
@@ -627,7 +630,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						struct mm_struct *mm,
 						unsigned long start,
 						unsigned long nr_pages,
-						int write, int force,
 						struct page **pages,
 						struct vm_area_struct **vmas,
 						int *locked, bool notify_drop,
@@ -645,10 +647,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 
 	if (pages)
 		flags |= FOLL_GET;
-	if (write)
-		flags |= FOLL_WRITE;
-	if (force)
-		flags |= FOLL_FORCE;
 
 	pages_done = 0;
 	lock_dropped = false;
@@ -742,11 +740,12 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
  */
 long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
-			   int write, int force, struct page **pages,
+			   unsigned int gup_flags, struct page **pages,
 			   int *locked)
 {
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, NULL, locked, true, FOLL_TOUCH);
+	return __get_user_pages_locked(tsk, mm, start, nr_pages,
+				       pages, NULL, locked, true,
+				       gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
@@ -762,14 +761,14 @@ EXPORT_SYMBOL(get_user_pages_locked);
  */
 __always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 					       unsigned long start, unsigned long nr_pages,
-					       int write, int force, struct page **pages,
-					       unsigned int gup_flags)
+					       struct page **pages, unsigned int gup_flags)
 {
 	long ret;
 	int locked = 1;
+
 	down_read(&mm->mmap_sem);
-	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				      pages, NULL, &locked, false, gup_flags);
+	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, NULL,
+				      &locked, false, gup_flags);
 	if (locked)
 		up_read(&mm->mmap_sem);
 	return ret;
@@ -795,10 +794,10 @@ EXPORT_SYMBOL(__get_user_pages_unlocked);
  */
 long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			     unsigned long start, unsigned long nr_pages,
-			     int write, int force, struct page **pages)
+			     struct page **pages, unsigned int gup_flags)
 {
-	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
-					 force, pages, FOLL_TOUCH);
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages,
+					 pages, gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -858,11 +857,13 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
  */
 long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages, int write,
-		int force, struct page **pages, struct vm_area_struct **vmas)
+		unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas)
 {
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, vmas, NULL, false, FOLL_TOUCH);
+	return __get_user_pages_locked(tsk, mm, start, nr_pages,
+				       pages, vmas, NULL, false,
+				       gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -1411,7 +1412,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		pages += nr;
 
 		ret = get_user_pages_unlocked(current, mm, start,
-					      nr_pages - nr, write, 0, pages);
+					      nr_pages - nr, pages,
+					      write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6f99a0f906bb..f1a45f5077fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4053,6 +4053,14 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct resv_map *resv_map;
 	long gbl_reserve;
 
+	/* This should never happen */
+	if (from > to) {
+#ifdef CONFIG_DEBUG_VM
+		WARN(1, "%s called with a negative range\n", __func__);
+#endif
+		return -EINVAL;
+	}
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
@@ -4142,7 +4150,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	return 0;
 out_err:
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_abort(resv_map, from, to);
+		/* Don't call region_abort if region_chg failed */
+		if (chg >= 0)
+			region_abort(resv_map, from, to);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
diff --git a/mm/memory.c b/mm/memory.c
index fb55c14556e6..5dfc9fac8b74 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3712,10 +3712,11 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
  * given task for page fault accounting.
  */
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long addr, void *buf, int len, int write)
+		unsigned long addr, void *buf, int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;
 	void *old_buf = buf;
+	int write = gup_flags & FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
 	/* ignore errors, just check how much was successfully transferred */
@@ -3725,7 +3726,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		struct page *page = NULL;
 
 		ret = get_user_pages(tsk, mm, addr, 1,
-				write, 1, &page, &vma);
+				gup_flags, &page, &vma);
 		if (ret <= 0) {
 #ifndef CONFIG_HAVE_IOREMAP_PROT
 			break;
@@ -3777,14 +3778,14 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
  * @addr:	start address to access
  * @buf:	source or destination buffer
  * @len:	number of bytes to transfer
- * @write:	whether the access is a write
+ * @gup_flags:	flags modifying lookup behaviour
  *
  * The caller must hold a reference on @mm.
  */
 int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-		void *buf, int len, int write)
+		void *buf, int len, unsigned int gup_flags)
 {
-	return __access_remote_vm(NULL, mm, addr, buf, len, write);
+	return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
 }
 
 /*
@@ -3797,12 +3798,17 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
 {
 	struct mm_struct *mm;
 	int ret;
+	unsigned int flags = FOLL_FORCE;
 
 	mm = get_task_mm(tsk);
 	if (!mm)
 		return 0;
 
-	ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
+	if (write)
+		flags |= FOLL_WRITE;
+
+	ret = __access_remote_vm(tsk, mm, addr, buf, len, flags);
+
 	mmput(mm);
 
 	return ret;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e48fa18e1828..63c19c24dfe1 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -819,7 +819,7 @@ static int lookup_node(struct mm_struct *mm, unsigned long addr)
 	struct page *p;
 	int err;
 
-	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
+	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, &p, NULL);
 	if (err >= 0) {
 		err = page_to_nid(p);
 		put_page(p);
diff --git a/mm/nommu.c b/mm/nommu.c
index 8d75e425c21c..ca1884c40190 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -184,40 +184,32 @@ finish_or_fault:
  */
 long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages,
+		    unsigned int gup_flags, struct page **pages,
 		    struct vm_area_struct **vmas)
 {
-	int flags = 0;
-
-	if (write)
-		flags |= FOLL_WRITE;
-	if (force)
-		flags |= FOLL_FORCE;
-
-	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
-				NULL);
+	return __get_user_pages(tsk, mm, start, nr_pages,
+				gup_flags, pages, vmas, NULL);
 }
 EXPORT_SYMBOL(get_user_pages);
 
 long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
-			   int write, int force, struct page **pages,
+			   unsigned int gup_flags, struct page **pages,
 			   int *locked)
 {
-	return get_user_pages(tsk, mm, start, nr_pages, write, force,
+	return get_user_pages(tsk, mm, start, nr_pages, gup_flags,
 			      pages, NULL);
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
 long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			       unsigned long start, unsigned long nr_pages,
-			       int write, int force, struct page **pages,
-			       unsigned int gup_flags)
+			       struct page **pages, unsigned int gup_flags)
 {
 	long ret;
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages(tsk, mm, start, nr_pages, write, force,
-			     pages, NULL);
+	ret = __get_user_pages(tsk, mm, start, nr_pages, gup_flags, pages,
+			       NULL, NULL);
 	up_read(&mm->mmap_sem);
 	return ret;
 }
@@ -225,10 +217,10 @@ EXPORT_SYMBOL(__get_user_pages_unlocked);
 
 long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			     unsigned long start, unsigned long nr_pages,
-			     int write, int force, struct page **pages)
+			     struct page **pages, unsigned int gup_flags)
 {
-	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
-					 force, pages, 0);
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages,
+					 pages, gup_flags);
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -1944,9 +1936,10 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
 EXPORT_SYMBOL(filemap_map_pages);
 
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long addr, void *buf, int len, int write)
+		unsigned long addr, void *buf, int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;
+	int write = gup_flags & FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
 
@@ -1981,14 +1974,14 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
  * @addr:	start address to access
  * @buf:	source or destination buffer
  * @len:	number of bytes to transfer
- * @write:	whether the access is a write
+ * @gup_flags:	flags modifying lookup behaviour
  *
  * The caller must hold a reference on @mm.
  */
 int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-		void *buf, int len, int write)
+		void *buf, int len, unsigned int gup_flags)
 {
-	return __access_remote_vm(NULL, mm, addr, buf, len, write);
+	return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
 }
 
 /*
@@ -2006,7 +1999,8 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 	if (!mm)
 		return 0;
 
-	len = __access_remote_vm(tsk, mm, addr, buf, len, write);
+	len = __access_remote_vm(tsk, mm, addr, buf, len,
+			write ? FOLL_WRITE : 0);
 
 	mmput(mm);
 	return len;
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 5d453e58ddbf..1b5a6104c5fc 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -88,19 +88,23 @@ static int process_vm_rw_single_vec(unsigned long addr,
 	ssize_t rc = 0;
 	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
 		/ sizeof(struct pages *);
+	unsigned int flags = 0;
 
 	/* Work out address and page range required */
 	if (len == 0)
 		return 0;
 	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
 
+	if (vm_write)
+		flags |= FOLL_WRITE;
+
 	while (!rc && nr_pages && iov_iter_count(iter)) {
 		int pages = min(nr_pages, max_pages_per_loop);
 		size_t bytes;
 
 		/* Get the pages we're interested in */
 		pages = get_user_pages_unlocked(task, mm, pa, pages,
-						vm_write, 0, process_pages);
+						process_pages, flags);
 		if (pages <= 0)
 			return -EFAULT;
 
diff --git a/mm/util.c b/mm/util.c
index f5480eb305c7..4b3890dc40e3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -278,7 +278,7 @@ int __weak get_user_pages_fast(unsigned long start,
 {
 	struct mm_struct *mm = current->mm;
 	return get_user_pages_unlocked(current, mm, start, nr_pages,
-				       write, 0, pages);
+				       pages, write ? FOLL_WRITE : 0);
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index d4f5f220a8e5..28453d698d86 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -26,7 +26,7 @@ struct page **ceph_get_direct_page_vector(const void __user *data,
 	while (got < num_pages) {
 		rc = get_user_pages_unlocked(current, current->mm,
 		    (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
-		    num_pages - got, write_page, 0, pages + got);
+		    num_pages - got, pages + got, write_page ? FOLL_WRITE : 0);
 		if (rc < 0)
 			break;
 		BUG_ON(rc == 0);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d2a46ffe6382..d52b633164c9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2931,6 +2931,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
 {
 	int err;
 
+	if (dev->type != ARPHRD_ETHER)
+		return -EINVAL;
+
 	netif_addr_lock_bh(dev);
 	err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc);
 	if (err)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f3952c75c47a..9ada5e4a28e5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2263,14 +2263,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		skb = tcp_write_queue_tail(sk);
 	}
 
+	if (unlikely(!skb)) {
+		WARN_ONCE(tp->packets_out,
+			  "invalid inflight: %u state %u cwnd %u mss %d\n",
+			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+		inet_csk(sk)->icsk_pending = 0;
+		return;
+	}
+
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
 		goto rearm_timer;
 
-	/* Retransmit last segment. */
-	if (WARN_ON(!skb))
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 530b62fd6b64..f8cca81d66f2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -169,37 +169,37 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
+	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
 	u32 mtu;
 
-	if (opt) {
-		unsigned int head_room;
+	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+	if (opt)
+		head_room += opt->opt_nflen + opt->opt_flen;
 
-		/* First: exthdrs may take lots of space (~8K for now)
-		   MAX_HEADER is not enough.
-		 */
-		head_room = opt->opt_nflen + opt->opt_flen;
-		seg_len += head_room;
-		head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
-
-		if (skb_headroom(skb) < head_room) {
-			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
-			if (!skb2) {
-				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-					      IPSTATS_MIB_OUTDISCARDS);
-				kfree_skb(skb);
-				return -ENOBUFS;
-			}
-			if (skb->sk)
-				skb_set_owner_w(skb2, skb->sk);
-			consume_skb(skb);
-			skb = skb2;
+	if (unlikely(skb_headroom(skb) < head_room)) {
+		struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
+		if (!skb2) {
+			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+				      IPSTATS_MIB_OUTDISCARDS);
+			kfree_skb(skb);
+			return -ENOBUFS;
 		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	if (opt) {
+		seg_len += opt->opt_nflen + opt->opt_flen;
+
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
+
 		if (opt->opt_nflen)
 			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
 	}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 000dd7e6c310..9066003b21b1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1886,7 +1886,8 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		params[ac].acm = acm;
 		params[ac].uapsd = uapsd;
 
-		if (params[ac].cw_min > params[ac].cw_max) {
+		if (params[ac].cw_min == 0 ||
+		    params[ac].cw_min > params[ac].cw_max) {
 			sdata_info(sdata,
 				   "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
 				   params[ac].cw_min, params[ac].cw_max, aci);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 743ff23885da..7acf1f2b8dfc 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -432,6 +432,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	int count = 1;
 	int rc = NET_XMIT_SUCCESS;
 
+	/* Do not fool qdisc_drop_all() */
+	skb->prev = NULL;
+
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
 		++count;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2e98f4a243e5..112c191b8336 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -758,8 +758,15 @@ void xprt_connect(struct rpc_task *task)
 			return;
 		if (xprt_test_and_set_connecting(xprt))
 			return;
-		xprt->stat.connect_start = jiffies;
-		xprt->ops->connect(xprt, task);
+		/* Race breaker */
+		if (!xprt_connected(xprt)) {
+			xprt->stat.connect_start = jiffies;
+			xprt->ops->connect(xprt, task);
+		} else {
+			xprt_clear_connecting(xprt);
+			task->tk_status = 0;
+			rpc_wake_up_queued_task(&xprt->pending, task);
+		}
 	}
 	xprt_release_write(xprt, task);
 }
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 38651454ed08..6f388e77999c 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -874,7 +874,8 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
 	}
 	/* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */
 #ifdef CONFIG_MMU
-	if (get_user_pages(current, bprm->mm, pos, 1, 0, 1, &page, NULL) <= 0)
+	if (get_user_pages(current, bprm->mm, pos, 1,
+			   FOLL_FORCE, &page, NULL) <= 0)
 		return false;
 #else
 	page = bprm->page[pos / PAGE_SIZE];
diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c
index 69f76ff5693d..718d5e3b7806 100644
--- a/sound/isa/wavefront/wavefront_synth.c
+++ b/sound/isa/wavefront/wavefront_synth.c
@@ -785,6 +785,9 @@ wavefront_send_patch (snd_wavefront_t *dev, wavefront_patch_info *header)
 	DPRINT (WF_DEBUG_LOAD_PATCH, "downloading patch %d\n",
 				      header->number);
 
+	if (header->number >= ARRAY_SIZE(dev->patch_status))
+		return -EINVAL;
+
 	dev->patch_status[header->number] |= WF_SLOT_FILLED;
 
 	bptr = buf;
@@ -809,6 +812,9 @@ wavefront_send_program (snd_wavefront_t *dev, wavefront_patch_info *header)
 	DPRINT (WF_DEBUG_LOAD_PATCH, "downloading program %d\n",
 		header->number);
 
+	if (header->number >= ARRAY_SIZE(dev->prog_status))
+		return -EINVAL;
+
 	dev->prog_status[header->number] = WF_SLOT_USED;
 
 	/* XXX need to zero existing SLOT_USED bit for program_status[i]
@@ -898,6 +904,9 @@ wavefront_send_sample (snd_wavefront_t *dev,
 		header->number = x;
 	}
 
+	if (header->number >= WF_MAX_SAMPLE)
+		return -EINVAL;
+
 	if (header->size) {
 
 		/* XXX it's a debatable point whether or not RDONLY semantics
diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c
index 09db2aec12a3..776e809a8aab 100644
--- a/sound/soc/omap/omap-dmic.c
+++ b/sound/soc/omap/omap-dmic.c
@@ -48,6 +48,8 @@ struct omap_dmic {
 	struct device *dev;
 	void __iomem *io_base;
 	struct clk *fclk;
+	struct pm_qos_request pm_qos_req;
+	int latency;
 	int fclk_freq;
 	int out_freq;
 	int clk_div;
@@ -124,6 +126,8 @@ static void omap_dmic_dai_shutdown(struct snd_pcm_substream *substream,
 
 	mutex_lock(&dmic->mutex);
 
+	pm_qos_remove_request(&dmic->pm_qos_req);
+
 	if (!dai->active)
 		dmic->active = 0;
 
@@ -226,6 +230,8 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream,
 	/* packet size is threshold * channels */
 	dma_data = snd_soc_dai_get_dma_data(dai, substream);
 	dma_data->maxburst = dmic->threshold * channels;
+	dmic->latency = (OMAP_DMIC_THRES_MAX - dmic->threshold) * USEC_PER_SEC /
+			params_rate(params);
 
 	return 0;
 }
@@ -236,6 +242,9 @@ static int omap_dmic_dai_prepare(struct snd_pcm_substream *substream,
 	struct omap_dmic *dmic = snd_soc_dai_get_drvdata(dai);
 	u32 ctrl;
 
+	if (pm_qos_request_active(&dmic->pm_qos_req))
+		pm_qos_update_request(&dmic->pm_qos_req, dmic->latency);
+
 	/* Configure uplink threshold */
 	omap_dmic_write(dmic, OMAP_DMIC_FIFO_CTRL_REG, dmic->threshold);
 
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index 8d0d45d330e7..8eb2d12b6a34 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -54,6 +54,8 @@ struct omap_mcpdm {
 	unsigned long phys_base;
 	void __iomem *io_base;
 	int irq;
+	struct pm_qos_request pm_qos_req;
+	int latency[2];
 
 	struct mutex mutex;
 
@@ -273,6 +275,9 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
 	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+	int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE;
+	int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 
 	mutex_lock(&mcpdm->mutex);
 
@@ -285,6 +290,14 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream,
 		}
 	}
 
+	if (mcpdm->latency[stream2])
+		pm_qos_update_request(&mcpdm->pm_qos_req,
+				      mcpdm->latency[stream2]);
+	else if (mcpdm->latency[stream1])
+		pm_qos_remove_request(&mcpdm->pm_qos_req);
+
+	mcpdm->latency[stream1] = 0;
+
 	mutex_unlock(&mcpdm->mutex);
 }
 
@@ -296,7 +309,7 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,
 	int stream = substream->stream;
 	struct snd_dmaengine_dai_dma_data *dma_data;
 	u32 threshold;
-	int channels;
+	int channels, latency;
 	int link_mask = 0;
 
 	channels = params_channels(params);
@@ -336,14 +349,25 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,
 
 		dma_data->maxburst =
 				(MCPDM_DN_THRES_MAX - threshold) * channels;
+		latency = threshold;
 	} else {
 		/* If playback is not running assume a stereo stream to come */
 		if (!mcpdm->config[!stream].link_mask)
 			mcpdm->config[!stream].link_mask = (0x3 << 3);
 
 		dma_data->maxburst = threshold * channels;
+		latency = (MCPDM_DN_THRES_MAX - threshold);
 	}
 
+	/*
+	 * The DMA must act to a DMA request within latency time (usec) to avoid
+	 * under/overflow
+	 */
+	mcpdm->latency[stream] = latency * USEC_PER_SEC / params_rate(params);
+
+	if (!mcpdm->latency[stream])
+		mcpdm->latency[stream] = 10;
+
 	/* Check if we need to restart McPDM with this stream */
 	if (mcpdm->config[stream].link_mask &&
 	    mcpdm->config[stream].link_mask != link_mask)
@@ -358,6 +382,20 @@ static int omap_mcpdm_prepare(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
 	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+	struct pm_qos_request *pm_qos_req = &mcpdm->pm_qos_req;
+	int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE;
+	int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
+	int latency = mcpdm->latency[stream2];
+
+	/* Prevent omap hardware from hitting off between FIFO fills */
+	if (!latency || mcpdm->latency[stream1] < latency)
+		latency = mcpdm->latency[stream1];
+
+	if (pm_qos_request_active(pm_qos_req))
+		pm_qos_update_request(pm_qos_req, latency);
+	else if (latency)
+		pm_qos_add_request(pm_qos_req, PM_QOS_CPU_DMA_LATENCY, latency);
 
 	if (!omap_mcpdm_active(mcpdm)) {
 		omap_mcpdm_start(mcpdm);
@@ -419,6 +457,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai)
 	free_irq(mcpdm->irq, (void *)mcpdm);
 	pm_runtime_disable(mcpdm->dev);
 
+	if (pm_qos_request_active(&mcpdm->pm_qos_req))
+		pm_qos_remove_request(&mcpdm->pm_qos_req);
+
 	return 0;
 }
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index fae57d18bbd7..275df1d7a138 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1728,6 +1728,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	}
 
 	card->instantiated = 1;
+	dapm_mark_endpoints_dirty(card);
 	snd_soc_dapm_sync(&card->dapm);
 	mutex_unlock(&card->mutex);
 	mutex_unlock(&client_mutex);
diff --git a/Documentation/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore
index 9e69e982fb38..9e69e982fb38 100644
--- a/Documentation/networking/timestamping/.gitignore
+++ b/tools/testing/selftests/networking/timestamping/.gitignore
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
new file mode 100644
index 000000000000..ccbb9edbbbb9
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := hwtstamp_config timestamping txtimestamp
+
+all: $(TEST_PROGS)
+
+include ../../lib.mk
+
+clean:
+	rm -fr $(TEST_PROGS)
diff --git a/Documentation/networking/timestamping/hwtstamp_config.c b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
index e8b685a7f15f..e8b685a7f15f 100644
--- a/Documentation/networking/timestamping/hwtstamp_config.c
+++ b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
diff --git a/Documentation/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c
index 5cdfd743447b..5cdfd743447b 100644
--- a/Documentation/networking/timestamping/timestamping.c
+++ b/tools/testing/selftests/networking/timestamping/timestamping.c
diff --git a/Documentation/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
index 5df07047ca86..5df07047ca86 100644
--- a/Documentation/networking/timestamping/txtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 4f70d12e392d..eddce59986ee 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,7 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	might_sleep();
 
-	get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL);
+	get_user_pages_unlocked(NULL, mm, addr, 1, NULL, FOLL_WRITE);
 	kvm_async_page_present_sync(vcpu, apf);
 
 	spin_lock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b814ae6822b6..e4be695eb789 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1352,10 +1352,15 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 		npages = get_user_page_nowait(current, current->mm,
 					      addr, write_fault, page);
 		up_read(&current->mm->mmap_sem);
-	} else
+	} else {
+		unsigned int flags = FOLL_TOUCH | FOLL_HWPOISON;
+
+		if (write_fault)
+			flags |= FOLL_WRITE;
+
 		npages = __get_user_pages_unlocked(current, current->mm, addr, 1,
-						   write_fault, 0, page,
-						   FOLL_TOUCH|FOLL_HWPOISON);
+						   page, flags);
+	}
 	if (npages != 1)
 		return npages;