Merge tag 'kvmarm-fixes-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for Linux 5.9, take #1

- Multiple stolen time fixes, with a new capability to match x86
- Fix for hugetlbfs mappings when PUD and PMD are the same level
- Fix for hugetlbfs mappings when PTE mappings are enforced
  (dirty logging, for example)
- Fix tracing output of 64bit values

329 files changed, 1498 insertions, 3201 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index a1124481d910..af14a567b493 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -481,9 +481,6 @@ config HAVE_STACKPROTECTOR
 	  An arch should select this symbol if:
 	  - it has implemented a stack canary (e.g. __stack_chk_guard)
 
-config CC_HAS_STACKPROTECTOR_NONE
-	def_bool $(cc-option,-fno-stack-protector)
-
 config STACKPROTECTOR
 	bool "Stack Protector buffer overflow detection"
 	depends on HAVE_STACKPROTECTOR
@@ -975,6 +972,9 @@ config HAVE_SPARSE_SYSCALL_NR
 	  entries at 4000, 5000 and 6000 locations. This option turns on syscall
 	  related optimizations for a given architecture.
 
+config ARCH_HAS_VDSO_DATA
+	bool
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/include/asm/core_apecs.h b/arch/alpha/include/asm/core_apecs.h
index 0a07055bc0fe..2d9726fc02ef 100644
--- a/arch/alpha/include/asm/core_apecs.h
+++ b/arch/alpha/include/asm/core_apecs.h
@@ -384,7 +384,7 @@ struct el_apecs_procdata
 		}						\
 	} while (0)
 
-__EXTERN_INLINE unsigned int apecs_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -420,7 +420,7 @@ __EXTERN_INLINE void apecs_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -456,7 +456,7 @@ __EXTERN_INLINE void apecs_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int apecs_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int apecs_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < APECS_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_cia.h b/arch/alpha/include/asm/core_cia.h
index c706a7f2b061..cb22991f6761 100644
--- a/arch/alpha/include/asm/core_cia.h
+++ b/arch/alpha/include/asm/core_cia.h
@@ -342,7 +342,7 @@ struct el_CIA_sysdata_mcheck {
 #define vuip	volatile unsigned int __force *
 #define vulp	volatile unsigned long __force *
 
-__EXTERN_INLINE unsigned int cia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -374,7 +374,7 @@ __EXTERN_INLINE void cia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -404,7 +404,7 @@ __EXTERN_INLINE void cia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int cia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int cia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < CIA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h
index 84d5e5b84f4f..ec86314418cb 100644
--- a/arch/alpha/include/asm/core_lca.h
+++ b/arch/alpha/include/asm/core_lca.h
@@ -230,7 +230,7 @@ union el_lca {
 	} while (0)
 
 
-__EXTERN_INLINE unsigned int lca_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -266,7 +266,7 @@ __EXTERN_INLINE void lca_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	unsigned long result, base_and_type;
@@ -302,7 +302,7 @@ __EXTERN_INLINE void lca_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + base_and_type) = w;
 }
 
-__EXTERN_INLINE unsigned int lca_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int lca_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (addr < LCA_DENSE_MEM)
diff --git a/arch/alpha/include/asm/core_marvel.h b/arch/alpha/include/asm/core_marvel.h
index cc6fd92d5fa9..b266e02e284b 100644
--- a/arch/alpha/include/asm/core_marvel.h
+++ b/arch/alpha/include/asm/core_marvel.h
@@ -332,10 +332,10 @@ struct io7 {
 #define vucp	volatile unsigned char __force *
 #define vusp	volatile unsigned short __force *
 
-extern unsigned int marvel_ioread8(void __iomem *);
+extern unsigned int marvel_ioread8(const void __iomem *);
 extern void marvel_iowrite8(u8 b, void __iomem *);
 
-__EXTERN_INLINE unsigned int marvel_ioread16(void __iomem *addr)
+__EXTERN_INLINE unsigned int marvel_ioread16(const void __iomem *addr)
 {
 	return __kernel_ldwu(*(vusp)addr);
 }
diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h
index b30dc128210d..cb24d1bd6141 100644
--- a/arch/alpha/include/asm/core_mcpcia.h
+++ b/arch/alpha/include/asm/core_mcpcia.h
@@ -267,7 +267,7 @@ extern inline int __mcpcia_is_mmio(unsigned long addr)
 	return (addr & 0x80000000UL) == 0;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread8(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -291,7 +291,7 @@ __EXTERN_INLINE void mcpcia_iowrite8(u8 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x00) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread16(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread16(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK;
 	unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK;
@@ -315,7 +315,7 @@ __EXTERN_INLINE void mcpcia_iowrite16(u16 b, void __iomem *xaddr)
 	*(vuip) ((addr << 5) + hose + 0x08) = w;
 }
 
-__EXTERN_INLINE unsigned int mcpcia_ioread32(void __iomem *xaddr)
+__EXTERN_INLINE unsigned int mcpcia_ioread32(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long)xaddr;
 
diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h
index e0b33d09e93a..12bb7addc789 100644
--- a/arch/alpha/include/asm/core_t2.h
+++ b/arch/alpha/include/asm/core_t2.h
@@ -572,7 +572,7 @@ __EXTERN_INLINE int t2_is_mmio(const volatile void __iomem *addr)
    it doesn't make sense to merge the pio and mmio routines.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int t2_ioread##NS(void __iomem *xaddr)		\
+__EXTERN_INLINE unsigned int t2_ioread##NS(const void __iomem *xaddr)		\
 {									\
 	if (t2_is_mmio(xaddr))						\
 		return t2_read##OS(xaddr);				\
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index a4d0c19f1e79..1f6a909d1fa5 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -150,9 +150,9 @@ static inline void generic_##NAME(TYPE b, QUAL void __iomem *addr)	\
 	alpha_mv.mv_##NAME(b, addr);					\
 }
 
-REMAP1(unsigned int, ioread8, /**/)
-REMAP1(unsigned int, ioread16, /**/)
-REMAP1(unsigned int, ioread32, /**/)
+REMAP1(unsigned int, ioread8, const)
+REMAP1(unsigned int, ioread16, const)
+REMAP1(unsigned int, ioread32, const)
 REMAP1(u8, readb, const volatile)
 REMAP1(u16, readw, const volatile)
 REMAP1(u32, readl, const volatile)
@@ -307,7 +307,7 @@ static inline int __is_mmio(const volatile void __iomem *addr)
  */
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
-extern inline unsigned int ioread8(void __iomem *addr)
+extern inline unsigned int ioread8(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -316,7 +316,7 @@ extern inline unsigned int ioread8(void __iomem *addr)
 	return ret;
 }
 
-extern inline unsigned int ioread16(void __iomem *addr)
+extern inline unsigned int ioread16(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -359,7 +359,7 @@ extern inline void outw(u16 b, unsigned long port)
 #endif
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
-extern inline unsigned int ioread32(void __iomem *addr)
+extern inline unsigned int ioread32(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -489,10 +489,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 }
 #endif
 
-#define ioread16be(p) be16_to_cpu(ioread16(p))
-#define ioread32be(p) be32_to_cpu(ioread32(p))
-#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p))
-#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p))
+#define ioread16be(p) swab16(ioread16(p))
+#define ioread32be(p) swab32(ioread32(p))
+#define iowrite16be(v,p) iowrite16(swab16(v), (p))
+#define iowrite32be(v,p) iowrite32(swab32(v), (p))
 
 #define inb_p		inb
 #define inw_p		inw
diff --git a/arch/alpha/include/asm/io_trivial.h b/arch/alpha/include/asm/io_trivial.h
index ba3d8f0cfe0c..a1a29cbe02fa 100644
--- a/arch/alpha/include/asm/io_trivial.h
+++ b/arch/alpha/include/asm/io_trivial.h
@@ -7,15 +7,15 @@
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread8)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread8)(const void __iomem *a)
 {
-	return __kernel_ldbu(*(volatile u8 __force *)a);
+	return __kernel_ldbu(*(const volatile u8 __force *)a);
 }
 
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread16)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread16)(const void __iomem *a)
 {
-	return __kernel_ldwu(*(volatile u16 __force *)a);
+	return __kernel_ldwu(*(const volatile u16 __force *)a);
 }
 
 __EXTERN_INLINE void
@@ -33,9 +33,9 @@ IO_CONCAT(__IO_PREFIX,iowrite16)(u16 b, void __iomem *a)
 
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
 __EXTERN_INLINE unsigned int
-IO_CONCAT(__IO_PREFIX,ioread32)(void __iomem *a)
+IO_CONCAT(__IO_PREFIX,ioread32)(const void __iomem *a)
 {
-	return *(volatile u32 __force *)a;
+	return *(const volatile u32 __force *)a;
 }
 
 __EXTERN_INLINE void
@@ -73,14 +73,14 @@ IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a)
 __EXTERN_INLINE u8
 IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 }
 
 __EXTERN_INLINE u16
 IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a)
 {
-	void __iomem *addr = (void __iomem *)a;
+	const void __iomem *addr = (const void __iomem *)a;
 	return IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 }
 
diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h
index 436dc905b6ad..916895155a88 100644
--- a/arch/alpha/include/asm/jensen.h
+++ b/arch/alpha/include/asm/jensen.h
@@ -305,7 +305,7 @@ __EXTERN_INLINE int jensen_is_mmio(const volatile void __iomem *addr)
    that it doesn't make sense to merge them.  */
 
 #define IOPORT(OS, NS)							\
-__EXTERN_INLINE unsigned int jensen_ioread##NS(void __iomem *xaddr)	\
+__EXTERN_INLINE unsigned int jensen_ioread##NS(const void __iomem *xaddr)	\
 {									\
 	if (jensen_is_mmio(xaddr))					\
 		return jensen_read##OS(xaddr - 0x100000000ul);		\
diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h
index a6b73c6d10ee..a4e96e2bec74 100644
--- a/arch/alpha/include/asm/machvec.h
+++ b/arch/alpha/include/asm/machvec.h
@@ -46,9 +46,9 @@ struct alpha_machine_vector
 	void (*mv_pci_tbi)(struct pci_controller *hose,
 			   dma_addr_t start, dma_addr_t end);
 
-	unsigned int (*mv_ioread8)(void __iomem *);
-	unsigned int (*mv_ioread16)(void __iomem *);
-	unsigned int (*mv_ioread32)(void __iomem *);
+	unsigned int (*mv_ioread8)(const void __iomem *);
+	unsigned int (*mv_ioread16)(const void __iomem *);
+	unsigned int (*mv_ioread32)(const void __iomem *);
 
 	void (*mv_iowrite8)(u8, void __iomem *);
 	void (*mv_iowrite16)(u16, void __iomem *);
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 1fe2b56cb861..1b6f25efa247 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -20,7 +20,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * Is a address valid? This does a straightforward calculation rather
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index 4c80d992a659..4485b77f8658 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -806,7 +806,7 @@ void __iomem *marvel_ioportmap (unsigned long addr)
 }
 
 unsigned int
-marvel_ioread8(void __iomem *xaddr)
+marvel_ioread8(const void __iomem *xaddr)
 {
 	unsigned long addr = (unsigned long) xaddr;
 	if (__marvel_is_port_kbd(addr))
diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c
index 938de13adfbf..838586abb1e0 100644
--- a/arch/alpha/kernel/io.c
+++ b/arch/alpha/kernel/io.c
@@ -14,7 +14,7 @@
    "generic", which bumps through the machine vector.  */
 
 unsigned int
-ioread8(void __iomem *addr)
+ioread8(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -23,7 +23,7 @@ ioread8(void __iomem *addr)
 	return ret;
 }
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -32,7 +32,7 @@ unsigned int ioread16(void __iomem *addr)
 	return ret;
 }
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	unsigned int ret;
 	mb();
@@ -257,7 +257,7 @@ EXPORT_SYMBOL(readq_relaxed);
 /*
  * Read COUNT 8-bit bytes from port PORT into memory starting at SRC.
  */
-void ioread8_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	while ((unsigned long)dst & 0x3) {
 		if (!count)
@@ -300,7 +300,7 @@ EXPORT_SYMBOL(insb);
  * the interfaces seems to be slow: just using the inlined version
  * of the inw() breaks things.
  */
-void ioread16_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	if (unlikely((unsigned long)dst & 0x3)) {
 		if (!count)
@@ -340,7 +340,7 @@ EXPORT_SYMBOL(insw);
  * but the interfaces seems to be slow: just using the inlined version
  * of the inl() breaks things.
  */
-void ioread32_rep(void __iomem *port, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *port, void *dst, unsigned long count)
 {
 	if (unlikely((unsigned long)dst & 0x3)) {
 		while (count--) {
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index a28fb211881d..ec8bed9e7b75 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -249,7 +249,7 @@
 316	common	mlockall			sys_mlockall
 317	common	munlockall			sys_munlockall
 318	common	sysinfo				sys_sysinfo
-319	common	_sysctl				sys_sysctl
+319	common	_sysctl				sys_ni_syscall
 # 320 was sys_idle
 321	common	oldumount			sys_oldumount
 322	common	swapon				sys_swapon
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index c2303a8c2b9f..09172f017efc 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
@@ -116,6 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 #endif
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -148,7 +150,7 @@ retry:
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -164,10 +166,6 @@ retry:
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/arc/include/asm/segment.h b/arch/arc/include/asm/segment.h
index 6a2a5be5026d..871f8ab11bfd 100644
--- a/arch/arc/include/asm/segment.h
+++ b/arch/arc/include/asm/segment.h
@@ -14,8 +14,7 @@ typedef unsigned long mm_segment_t;
 
 #define KERNEL_DS		MAKE_MM_SEG(0)
 #define USER_DS			MAKE_MM_SEG(TASK_SIZE)
-
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASMARC_SEGMENT_H */
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 105420c23c8b..efeba1fe7252 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -91,7 +91,7 @@ fault:
 		 goto fail;
 
 	mmap_read_lock(current->mm);
-	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+	ret = fixup_user_fault(current->mm, (unsigned long) uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(current->mm);
 
@@ -296,11 +296,6 @@ void flush_thread(void)
 {
 }
 
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
-{
-	return 0;
-}
-
 int elf_check_arch(const struct elf32_hdr *x)
 {
 	unsigned int eflags;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 7287c793d1c9..f5657cb68e4f 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -105,6 +105,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	if (write)
 		flags |= FAULT_FLAG_WRITE;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -130,7 +131,7 @@ retry:
 		goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -155,22 +156,9 @@ bad_area:
 	 * Major/minor page fault accounting
 	 * (in case of retry we only land here once)
 	 */
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
-	if (likely(!(fault & VM_FAULT_ERROR))) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
-
+	if (likely(!(fault & VM_FAULT_ERROR)))
 		/* Normal return path: fault Handled Gracefully */
 		return;
-	}
 
 	if (!user_mode(regs))
 		goto no_context;
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 00602a6fba04..b1147b7f2c8d 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -84,9 +84,8 @@ endif
 
 # -fstack-protector-strong triggers protection checks in this code,
 # but it is being used too early to link to meaningful stack_chk logic.
-nossp-flags-$(CONFIG_CC_HAS_STACKPROTECTOR_NONE) := -fno-stack-protector
 $(foreach o, $(libfdt_objs) atags_to_fdt.o, \
-	$(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt $(nossp-flags-y)))
+	$(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt -fno-stack-protector))
 
 # These were previously generated C files. When you are building the kernel
 # with O=, make sure to remove the stale files in the output tree. Otherwise,
@@ -103,13 +102,9 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
 
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 
-ifeq ($(CONFIG_FUNCTION_TRACER),y)
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
-endif
-
 ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
 	     -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += -pg
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 45de2ff6a777..b88d0caa4b2d 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -290,7 +290,7 @@
 				am33xx_pinmux: pinmux@800 {
 					compatible = "pinctrl-single";
 					reg = <0x800 0x238>;
-					#pinctrl-cells = <1>;
+					#pinctrl-cells = <2>;
 					pinctrl-single,register-width = <32>;
 					pinctrl-single,function-mask = <0x7f>;
 				};
diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig
index f56ac394caf1..4e49d6cb2f62 100644
--- a/arch/arm/configs/am200epdkit_defconfig
+++ b/arch/arm/configs/am200epdkit_defconfig
@@ -3,7 +3,6 @@ CONFIG_LOCALVERSION="gum"
 CONFIG_SYSVIPC=y
 CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_EXPERT=y
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index c675bc0d5aa8..be666f58bf7a 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -9,9 +9,6 @@ struct dev_archdata {
 #ifdef CONFIG_DMABOUNCE
 	struct dmabounce_device_info *dmabounce;
 #endif
-#ifdef CONFIG_IOMMU_API
-	void *iommu; /* private IOMMU data */
-#endif
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index b5fdd30252f8..a13d90206472 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -76,7 +76,7 @@ static inline void set_fs(mm_segment_t fs)
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * We use 33-bit arithmetic here.  Success returns zero, failure returns
@@ -267,7 +267,7 @@ extern int __put_user_8(void *, unsigned long long);
  */
 #define USER_DS			KERNEL_DS
 
-#define segment_eq(a, b)		(1)
+#define uaccess_kernel()	(true)
 #define __addr_ok(addr)		((void)(addr), 1)
 #define __range_ok(addr, size)	((void)(addr), 0)
 #define get_fs()		(KERNEL_DS)
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 1b207cf07697..2134cbd5469f 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -113,7 +113,8 @@ static inline bool arm_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable arm_vdso_hres_capable
 
-static __always_inline u64 __arch_get_hw_counter(int clock_mode)
+static __always_inline u64 __arch_get_hw_counter(int clock_mode,
+						 const struct vdso_data *vd)
 {
 #ifdef CONFIG_ARM_ARCH_TIMER
 	u64 cycle_now;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 3395be186c7d..8e6ace03e960 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -281,21 +281,6 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
 	return 1;
 }
 
-/*
- * fill in the fpe structure for a core dump...
- */
-int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
-{
-	struct thread_info *thread = current_thread_info();
-	int used_math = thread->used_cp[1] | thread->used_cp[2];
-
-	if (used_math)
-		memcpy(fp, &thread->fpstate.soft, sizeof (*fp));
-
-	return used_math != 0;
-}
-EXPORT_SYMBOL(dump_fpu);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab2568996ddb..c9dc912b83f0 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -713,7 +713,9 @@ struct page *get_signal_page(void)
 /* Defer to generic check */
 asmlinkage void addr_limit_check_failed(void)
 {
+#ifdef CONFIG_MMU
 	addr_limit_user_check();
+#endif
 }
 
 #ifdef CONFIG_DEBUG_RSEQ
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c6550eddfce1..efa402025031 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -202,7 +202,8 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 
 static vm_fault_t __kprobes
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		unsigned int flags, struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk,
+		struct pt_regs *regs)
 {
 	struct vm_area_struct *vma;
 	vm_fault_t fault;
@@ -224,7 +225,7 @@ good_area:
 		goto out;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */
@@ -266,6 +267,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -290,7 +293,7 @@ retry:
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+	fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs);
 
 	/* If we need to retry but a fatal signal is pending, handle the
 	 * signal first. We do not need to release the mmap_lock because
@@ -302,23 +305,7 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
-
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-					regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-					regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 			goto retry;
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 7e8ee4adf269..171077cbf419 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -162,7 +162,7 @@
 146	common	writev			sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
-149	common	_sysctl			sys_sysctl
+149	common	_sysctl			sys_ni_syscall
 150	common	mlock			sys_mlock
 151	common	munlock			sys_munlock
 152	common	mlockall		sys_mlockall
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 12b778d55342..996498751318 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -6,9 +6,6 @@
 #define __ASM_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_IOMMU_API
-	void *iommu;			/* private IOMMU data */
-#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e52c927aade5..905c2b87e05a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -368,7 +368,6 @@ struct kvm_vcpu_arch {
 
 	/* Guest PV state */
 	struct {
-		u64 steal;
 		u64 last_steal;
 		gpa_t base;
 	} steal;
@@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8d7c466f809b..991dd5f031e4 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -50,7 +50,7 @@ static inline void set_fs(mm_segment_t fs)
 				CONFIG_ARM64_UAO));
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /*
  * Test whether a block of memory is a valid user space address.
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 17e81bd9a2d3..734860ac7cf9 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -308,8 +308,8 @@ __SYSCALL(__NR_writev, compat_sys_writev)
 __SYSCALL(__NR_getsid, sys_getsid)
 #define __NR_fdatasync 148
 __SYSCALL(__NR_fdatasync, sys_fdatasync)
-#define __NR__sysctl 149
-__SYSCALL(__NR__sysctl, compat_sys_sysctl)
+			/* 149 was sys_sysctl */
+__SYSCALL(149, sys_ni_syscall)
 #define __NR_mlock 150
 __SYSCALL(__NR_mlock, sys_mlock)
 #define __NR_munlock 151
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index 75cbae60455b..7508b0ac1d21 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -103,7 +103,8 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 	return ret;
 }
 
-static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
 {
 	u64 res;
 
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 9c29ad3049f8..631ab1281633 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -64,7 +64,8 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 	return ret;
 }
 
-static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
 {
 	u64 res;
 
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index dab88260b137..7689f2031c0c 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -180,7 +180,7 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
 
 	/*
 	 * We didn't take an exception to get here, set PAN. UAO will be cleared
-	 * by sdei_event_handler()s set_fs(USER_DS) call.
+	 * by sdei_event_handler()s force_uaccess_begin() call.
 	 */
 	__uaccess_enable_hw_pan();
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 691d21e4c717..57876b0b870b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ba00bcc0c884..9a636b8064f1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1877,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1970,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce1557e..920ac43077ad 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053c5ee4..ff0444352bba 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate,
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e0f5bd..8d78acc4fba7 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64,
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64,
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg,
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 8afb238ff335..f07333e86c2f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -404,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADACCESS	0x020000
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
-			   unsigned int mm_flags, unsigned long vm_flags)
+				  unsigned int mm_flags, unsigned long vm_flags,
+				  struct pt_regs *regs)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 
@@ -428,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -450,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	const struct fault_info *inf;
 	struct mm_struct *mm = current->mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned long vm_flags = VM_ACCESS_FLAGS;
 	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
 
@@ -516,8 +517,7 @@ retry:
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, mm_flags, vm_flags);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -538,25 +538,8 @@ retry:
 	 * Handle the "normal" (no error) case first.
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS)))) {
-		/*
-		 * Major/minor page fault accounting is only done
-		 * once. If we go through a retry, it is extremely
-		 * likely that the page will be found in page cache at
-		 * that point.
-		 */
-		if (major) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-				      addr);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-				      addr);
-		}
-
+			      VM_FAULT_BADACCESS))))
 		return 0;
-	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index aafcee3e3f7e..73f8b49d485c 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -461,13 +461,3 @@ void __init arm64_numa_init(void)
 
 	numa_init(dummy_numa_init);
 }
-
-/*
- * We hope that we will be hotplugging memory on nodes we already know about,
- * such that acpi_get_node() succeeds and we never fall back to this...
- */
-int memory_add_physaddr_to_nid(u64 addr)
-{
-	pr_warn("Unknown node for memory at 0x%llx, assuming node 0\n", addr);
-	return 0;
-}
diff --git a/arch/csky/include/asm/segment.h b/arch/csky/include/asm/segment.h
index db2640d5f575..79ede9b1a646 100644
--- a/arch/csky/include/asm/segment.h
+++ b/arch/csky/include/asm/segment.h
@@ -13,6 +13,6 @@ typedef struct {
 #define USER_DS			((mm_segment_t) { 0x80000000UL })
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(x)		(current_thread_info()->addr_limit = (x))
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASM_CSKY_SEGMENT_H */
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index b1dce9f2f04d..081b178b41b1 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -150,7 +150,8 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0,
+				regs);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -160,16 +161,6 @@ good_area:
 			goto bad_area;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-			      address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-			      address);
-	}
-
 	mmap_read_unlock(mm);
 	return;
 
diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h
index a407978f9f9f..37950725d9b9 100644
--- a/arch/h8300/include/asm/segment.h
+++ b/arch/h8300/include/asm/segment.h
@@ -33,7 +33,7 @@ static inline mm_segment_t get_fs(void)
 	return USER_DS;
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index d294e71d11d8..dfd322c5ce83 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -154,15 +154,6 @@ unsigned long get_wchan(struct task_struct *p)
 }
 
 /*
- * Required placeholder.
- */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
-{
-	return 0;
-}
-
-
-/*
  * Called on the exit path of event entry; see vm_entry.S
  *
  * Interrupts will already be disabled.
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index cd3808f96b93..ef32c5a84ff3 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -18,6 +18,7 @@
 #include <linux/signal.h>
 #include <linux/extable.h>
 #include <linux/hardirq.h>
+#include <linux/perf_event.h>
 
 /*
  * Decode of hardware exception sends us to one of several
@@ -53,6 +54,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -88,7 +91,7 @@ good_area:
 		break;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -96,10 +99,6 @@ good_area:
 	/* The most common case -- we are done. */
 	if (likely(!(fault & VM_FAULT_ERROR))) {
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			if (fault & VM_FAULT_MAJOR)
-				current->maj_flt++;
-			else
-				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags |= FAULT_FLAG_TRIED;
 				goto retry;
diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h
index 3eb397415381..918b198cd5bb 100644
--- a/arch/ia64/include/asm/device.h
+++ b/arch/ia64/include/asm/device.h
@@ -6,9 +6,6 @@
 #define _ASM_IA64_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_IOMMU_API
-	void *iommu; /* hook for IOMMU specific extension */
-#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 7847ae40a181..aa92234c0142 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -18,7 +18,6 @@
 #include <linux/bitops.h>
 #include <linux/irqreturn.h>
 
-#include <asm/io.h>
 #include <asm/param.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
@@ -44,11 +43,6 @@ ia64_get_lid (void)
 
 #ifdef CONFIG_SMP
 
-#define XTP_OFFSET		0x1e0008
-
-#define SMP_IRQ_REDIRECTION	(1 << 0)
-#define SMP_IPI_REDIRECTION	(1 << 1)
-
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
 extern struct smp_boot_data {
@@ -62,7 +56,6 @@ extern cpumask_t cpu_core_map[NR_CPUS];
 DECLARE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map);
 extern int smp_num_siblings;
 extern void __iomem *ipi_base_addr;
-extern unsigned char smp_int_redirect;
 
 extern volatile int ia64_cpu_to_sapicid[];
 #define cpu_physical_id(i)	ia64_cpu_to_sapicid[i]
@@ -84,34 +77,6 @@ cpu_logical_id (int cpuid)
 	return i;
 }
 
-/*
- * XTP control functions:
- *	min_xtp   : route all interrupts to this CPU
- *	normal_xtp: nominal XTP value
- *	max_xtp   : never deliver interrupts to this CPU.
- */
-
-static inline void
-min_xtp (void)
-{
-	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
-		writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */
-}
-
-static inline void
-normal_xtp (void)
-{
-	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
-		writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */
-}
-
-static inline void
-max_xtp (void)
-{
-	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
-		writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */
-}
-
 /* Upping and downing of CPUs */
 extern int __cpu_disable (void);
 extern void __cpu_die (unsigned int cpu);
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 8aa473a4b0f4..179243c3dfc7 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -50,7 +50,7 @@
 #define get_fs()  (current_thread_info()->addr_limit)
 #define set_fs(x) (current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * When accessing user memory, we need to make sure the entire area really is in
diff --git a/arch/ia64/include/asm/xtp.h b/arch/ia64/include/asm/xtp.h
new file mode 100644
index 000000000000..5bf1d70ad860
--- /dev/null
+++ b/arch/ia64/include/asm/xtp.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_IA64_XTP_H
+#define _ASM_IA64_XTP_H
+
+#include <asm/io.h>
+
+#ifdef CONFIG_SMP
+
+#define XTP_OFFSET		0x1e0008
+
+#define SMP_IRQ_REDIRECTION	(1 << 0)
+#define SMP_IPI_REDIRECTION	(1 << 1)
+
+extern unsigned char smp_int_redirect;
+
+/*
+ * XTP control functions:
+ *	min_xtp   : route all interrupts to this CPU
+ *	normal_xtp: nominal XTP value
+ *	max_xtp   : never deliver interrupts to this CPU.
+ */
+
+static inline void
+min_xtp (void)
+{
+	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+		writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */
+}
+
+static inline void
+normal_xtp (void)
+{
+	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+		writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */
+}
+
+static inline void
+max_xtp (void)
+{
+	if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+		writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */
+}
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_IA64_XTP_Hy */
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index fad4db20ce65..35adcf89035a 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -95,6 +95,7 @@
 #include <asm/iosapic.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
+#include <asm/xtp.h>
 
 #undef DEBUG_INTERRUPT_ROUTING
 
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 0a8e5e585edc..ecef17c7c35b 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -25,6 +25,7 @@
 #include <linux/kernel_stat.h>
 
 #include <asm/mca.h>
+#include <asm/xtp.h>
 
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index ec0b40f6e9c6..f19cb97c0098 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -47,6 +47,7 @@
 #include <linux/uaccess.h>
 #include <asm/unwind.h>
 #include <asm/user.h>
+#include <asm/xtp.h>
 
 #include "entry.h"
 
@@ -531,51 +532,17 @@ do_copy_task_regs (struct task_struct *task, struct unw_frame_info *info, void *
 }
 
 void
-do_dump_task_fpu (struct task_struct *task, struct unw_frame_info *info, void *arg)
-{
-	elf_fpreg_t *dst = arg;
-	int i;
-
-	memset(dst, 0, sizeof(elf_fpregset_t));	/* don't leak any "random" bits */
-
-	if (unw_unwind_to_user(info) < 0)
-		return;
-
-	/* f0 is 0.0, f1 is 1.0 */
-
-	for (i = 2; i < 32; ++i)
-		unw_get_fr(info, i, dst + i);
-
-	ia64_flush_fph(task);
-	if ((task->thread.flags & IA64_THREAD_FPH_VALID) != 0)
-		memcpy(dst + 32, task->thread.fph, 96*16);
-}
-
-void
 do_copy_regs (struct unw_frame_info *info, void *arg)
 {
 	do_copy_task_regs(current, info, arg);
 }
 
 void
-do_dump_fpu (struct unw_frame_info *info, void *arg)
-{
-	do_dump_task_fpu(current, info, arg);
-}
-
-void
 ia64_elf_core_copy_regs (struct pt_regs *pt, elf_gregset_t dst)
 {
 	unw_init_running(do_copy_regs, dst);
 }
 
-int
-dump_fpu (struct pt_regs *pt, elf_fpregset_t dst)
-{
-	unw_init_running(do_dump_fpu, dst);
-	return 1;	/* f0-f31 are always valid so we always return 1 */
-}
-
 /*
  * Flush thread state.  This is called when a thread does an execve().
  */
diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c
index c455ece977ad..e4f0705c0282 100644
--- a/arch/ia64/kernel/sal.c
+++ b/arch/ia64/kernel/sal.c
@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/sal.h>
 #include <asm/pal.h>
+#include <asm/xtp.h>
 
  __cacheline_aligned DEFINE_SPINLOCK(sal_lock);
 unsigned long sal_platform_features;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index d2d440fe855b..dd595fbd8006 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -65,6 +65,7 @@
 #include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/uv/uv.h>
+#include <asm/xtp.h>
 
 #if defined(CONFIG_SMP) && (IA64_CPU_SIZE > PAGE_SIZE)
 # error "struct cpuinfo_ia64 too big!"
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 0e2742003121..7b7b64eb3129 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -45,6 +45,7 @@
 #include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
+#include <asm/xtp.h>
 
 /*
  * Note: alignment of 4 entries/cacheline was empirically determined
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ced9c83e47c9..f52a41f4c340 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -135,7 +135,7 @@
 123	common	writev				sys_writev
 124	common	pread64				sys_pread64
 125	common	pwrite64			sys_pwrite64
-126	common	_sysctl				sys_sysctl
+126	common	_sysctl				sys_ni_syscall
 127	common	mmap				sys_mmap
 128	common	munmap				sys_munmap
 129	common	mlock				sys_mlock
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 3a4dec334cc5..cd9766d2b6e0 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/kdebug.h>
 #include <linux/prefetch.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/processor.h>
 #include <asm/exception.h>
@@ -105,6 +106,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 		flags |= FAULT_FLAG_USER;
 	if (mask & VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -143,7 +146,7 @@ retry:
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -166,10 +169,6 @@ retry:
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index 5e1015eb6d0d..f34964271101 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -106,7 +106,5 @@ int memory_add_physaddr_to_nid(u64 addr)
 		return 0;
 	return nid;
 }
-
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 #endif
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 6663f1741798..6f2f38d05772 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -16,6 +16,7 @@ config M68K
 	select HAVE_DEBUG_BUGVERBOSE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_ATOMIC64
+	select NO_DMA if !MMU && !COLDFIRE
 	select HAVE_UID16
 	select VIRT_TO_BUS
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
@@ -59,9 +60,6 @@ config TIME_LOW_RES
 config NO_IOPORT_MAP
 	def_bool y
 
-config NO_DMA
-	def_bool (MMU && SUN3) || (!MMU && !COLDFIRE)
-
 config ZONE_DMA
 	bool
 	default y
diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine
index a82651d58af4..17e8c3a292d7 100644
--- a/arch/m68k/Kconfig.machine
+++ b/arch/m68k/Kconfig.machine
@@ -126,6 +126,7 @@ config SUN3
 	depends on MMU
 	depends on !MMU_MOTOROLA
 	select MMU_SUN3 if MMU
+	select NO_DMA
 	select M68020
 	help
 	  This option enables support for the Sun 3 series of workstations
diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h
index c6686559e9b7..2b5e68a71ef7 100644
--- a/arch/m68k/include/asm/segment.h
+++ b/arch/m68k/include/asm/segment.h
@@ -52,7 +52,7 @@ static inline void set_fs(mm_segment_t val)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h
index 191e75a6bb24..5337bc2c262f 100644
--- a/arch/m68k/include/asm/tlbflush.h
+++ b/arch/m68k/include/asm/tlbflush.h
@@ -85,10 +85,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (vma->vm_mm == current->active_mm) {
-		mm_segment_t old_fs = get_fs();
-		set_fs(USER_DS);
+		mm_segment_t old_fs = force_uaccess_begin();
+
 		__flush_tlb_one(addr);
-		set_fs(old_fs);
+		force_uaccess_end(old_fs);
 	}
 }
 
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 1a4822de7292..81fc799d8392 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 508abb63da67..795f483b1050 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -12,6 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
@@ -84,6 +85,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 
@@ -134,7 +137,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
 	if (fault_signal_pending(fault, regs))
@@ -150,16 +153,7 @@ good_area:
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 6723c56ec378..304b04ffea2f 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -41,7 +41,7 @@
 # define get_fs()	(current_thread_info()->addr_limit)
 # define set_fs(val)	(current_thread_info()->addr_limit = (val))
 
-# define segment_eq(a, b)	((a).seg == (b).seg)
+# define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 #ifndef CONFIG_MMU
 
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index a3f4be8e7238..b4e263916f41 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index a2bfe587b491..b3fed2cecf84 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -28,6 +28,7 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/perf_event.h>
 
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -121,6 +122,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -214,7 +217,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -230,10 +233,6 @@ good_area:
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (unlikely(fault & VM_FAULT_MAJOR))
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig
index 6b471cdb16cf..e924c817f73d 100644
--- a/arch/mips/configs/cu1000-neo_defconfig
+++ b/arch/mips/configs/cu1000-neo_defconfig
@@ -17,7 +17,6 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 62b298c50905..61fc01f177a6 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -72,7 +72,7 @@ extern u64 __ua_limit;
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel()	(get_fs().seg == KERNEL_DS.seg)
 
 /*
  * eva_kernel_access() - determine whether kernel memory access on an EVA system
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index c63ddcaea54c..2203e2d0ae2a 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -167,7 +167,8 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data)
 
 #endif
 
-static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
 {
 #ifdef CONFIG_CSRC_R4K
 	if (clock_mode == VDSO_CLOCKMODE_R4K)
@@ -175,7 +176,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
 #endif
 #ifdef CONFIG_CLKSRC_MIPS_GIC
 	if (clock_mode == VDSO_CLOCKMODE_GIC)
-		return read_gic_count(get_vdso_data());
+		return read_gic_count(vd);
 #endif
 	/*
 	 * Core checks mode already. So this raced against a concurrent
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 6b4ee92e3aed..f9df9edb67a4 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -159,7 +159,7 @@
 149	n32	munlockall			sys_munlockall
 150	n32	vhangup				sys_vhangup
 151	n32	pivot_root			sys_pivot_root
-152	n32	_sysctl				compat_sys_sysctl
+152	n32	_sysctl				sys_ni_syscall
 153	n32	prctl				sys_prctl
 154	n32	adjtimex			sys_adjtimex_time32
 155	n32	setrlimit			compat_sys_setrlimit
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 391acbf425a0..557f9954a2b9 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -159,7 +159,7 @@
 149	n64	munlockall			sys_munlockall
 150	n64	vhangup				sys_vhangup
 151	n64	pivot_root			sys_pivot_root
-152	n64	_sysctl				sys_sysctl
+152	n64	_sysctl				sys_ni_syscall
 153	n64	prctl				sys_prctl
 154	n64	adjtimex			sys_adjtimex
 155	n64	setrlimit			sys_setrlimit
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 5727c5187508..195b43cf27c8 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -164,7 +164,7 @@
 150	o32	unused150			sys_ni_syscall
 151	o32	getsid				sys_getsid
 152	o32	fdatasync			sys_fdatasync
-153	o32	_sysctl				sys_sysctl			compat_sys_sysctl
+153	o32	_sysctl				sys_ni_syscall
 154	o32	mlock				sys_mlock
 155	o32	munlock				sys_munlock
 156	o32	mlockall			sys_mlockall
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 0adce604fa44..126a5f3f4e4c 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -191,17 +191,16 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			 * memory, so we need to "switch" the address limit to
 			 * user space, so that address check can work properly.
 			 */
-			seg = get_fs();
-			set_fs(USER_DS);
+			seg = force_uaccess_begin();
 			switch (insn.spec3_format.func) {
 			case lhe_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -209,12 +208,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lwe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -222,12 +221,12 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case lhue_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				LoadHWUE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				compute_return_epc(regs);
@@ -235,35 +234,35 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 				break;
 			case she_op:
 				if (!access_ok(addr, 2)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreHWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			case swe_op:
 				if (!access_ok(addr, 4)) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto sigbus;
 				}
 				compute_return_epc(regs);
 				value = regs->regs[insn.spec3_format.rt];
 				StoreWE(addr, value, res);
 				if (res) {
-					set_fs(seg);
+					force_uaccess_end(seg);
 					goto fault;
 				}
 				break;
 			default:
-				set_fs(seg);
+				force_uaccess_end(seg);
 				goto sigill;
 			}
-			set_fs(seg);
+			force_uaccess_end(seg);
 		}
 #endif
 		break;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 01b168a90434..7c871b14e74a 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -96,6 +96,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -152,12 +154,11 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -168,15 +169,6 @@ good_area:
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-						  regs, address);
-			tsk->maj_flt++;
-		} else {
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-						  regs, address);
-			tsk->min_flt++;
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 2e64c7600eea..57fe83235281 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -35,8 +35,7 @@ cflags-vdso := $(ccflags-vdso) \
 	-O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
 	-mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
 	-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
-	$(call cc-option, -fno-asynchronous-unwind-tables) \
-	$(call cc-option, -fno-stack-protector)
+	$(call cc-option, -fno-asynchronous-unwind-tables)
 aflags-vdso := $(ccflags-vdso) \
 	-D__ASSEMBLY__ -Wa,-gdwarf-2
 
diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h
index 3a9219f53ee0..010ba5f1d7dd 100644
--- a/arch/nds32/include/asm/uaccess.h
+++ b/arch/nds32/include/asm/uaccess.h
@@ -44,7 +44,7 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size))
 
diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index e85bbbadc0e7..e01ad5d17224 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -121,7 +121,7 @@ void show_regs(struct pt_regs *regs)
 		regs->uregs[3], regs->uregs[2], regs->uregs[1], regs->uregs[0]);
 	pr_info("  IRQs o%s  Segment %s\n",
 		interrupts_enabled(regs) ? "n" : "ff",
-		segment_eq(get_fs(), KERNEL_DS)? "kernel" : "user");
+		uaccess_kernel() ? "kernel" : "user");
 }
 
 EXPORT_SYMBOL(show_regs);
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index c8b9061a2ee3..1eb7ded6992b 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -512,7 +512,7 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 {
 	unsigned long inst;
 	int ret = -EFAULT;
-	mm_segment_t seg = get_fs();
+	mm_segment_t seg;
 
 	inst = get_inst(regs->ipc);
 
@@ -520,13 +520,12 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs)
 	      "Faulting addr: 0x%08lx, pc: 0x%08lx [inst: 0x%08lx ]\n", addr,
 	      regs->ipc, inst);
 
-	set_fs(USER_DS);
-
+	seg = force_uaccess_begin();
 	if (inst & NDS32_16BIT_INSTRUCTION)
 		ret = do_16((inst >> 16) & 0xffff, regs);
 	else
 		ret = do_32(inst, regs);
-	set_fs(seg);
+	force_uaccess_end(seg);
 
 	return ret;
 }
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 8fb73f6401a0..f02524eb6d56 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -121,6 +121,8 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	if (unlikely(faulthandler_disabled() || !mm))
 		goto no_context;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -206,7 +208,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, regs);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
@@ -228,22 +230,7 @@ good_area:
 			goto bad_area;
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the initial
-	 * attempt. If we go through a retry, it is extremely likely that the
-	 * page will be found in page cache at that point.
-	 */
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index e83f831a76f9..a741abbed6fb 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -30,7 +30,7 @@
 #define get_fs()		(current_thread_info()->addr_limit)
 #define set_fs(seg)		(current_thread_info()->addr_limit = (seg))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __access_ok(addr, len)			\
 	(((signed long)(((long)get_fs().seg) &	\
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 0a42ab8e4c32..88a4ec03edab 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -252,14 +252,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	regs->sp = sp;
 }
 
-#include <linux/elfcore.h>
-
-/* Fill in the FPU structure for a core dump. */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *r)
-{
-	return 0; /* Nios2 has no FPU and thus no FPU registers */
-}
-
 asmlinkage int nios2_clone(unsigned long clone_flags, unsigned long newsp,
 			   int __user *parent_tidptr, int __user *child_tidptr,
 			   unsigned long tls)
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 4112ef0e247e..9476feecf512 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
 
 #include <asm/mmu_context.h>
 #include <asm/traps.h>
@@ -83,6 +84,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	if (!mmap_read_trylock(mm)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->ea))
 			goto bad_area_nosemaphore;
@@ -131,7 +134,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -146,16 +149,7 @@ good_area:
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h
index db02fb2077d9..7d6b4a77b379 100644
--- a/arch/openrisc/include/asm/io.h
+++ b/arch/openrisc/include/asm/io.h
@@ -14,6 +14,8 @@
 #ifndef __ASM_OPENRISC_IO_H
 #define __ASM_OPENRISC_IO_H
 
+#include <linux/types.h>
+
 /*
  * PCI: can we really do 0 here if we have no port IO?
  */
@@ -25,9 +27,12 @@
 #define PIO_OFFSET		0
 #define PIO_MASK		0
 
-#include <asm-generic/io.h>
-
+#define ioremap ioremap
 void __iomem *ioremap(phys_addr_t offset, unsigned long size);
+
+#define iounmap iounmap
 extern void iounmap(void *addr);
 
+#include <asm-generic/io.h>
+
 #endif
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 17c24f14615f..f0390211236b 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -43,21 +43,22 @@
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
 
-#define segment_eq(a, b)	((a) == (b))
+#define uaccess_kernel()	(get_fs() == KERNEL_DS)
 
 /* Ensure that the range from addr to addr+size is all within the process'
  * address space
  */
-#define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs()-size))
+static inline int __range_ok(unsigned long addr, unsigned long size)
+{
+	const mm_segment_t fs = get_fs();
 
-/* Ensure that addr is below task's addr_limit */
-#define __addr_ok(addr) ((unsigned long) addr < get_fs())
+	return size <= fs && addr <= (fs - size);
+}
 
 #define access_ok(addr, size)						\
 ({ 									\
-	unsigned long __ao_addr = (unsigned long)(addr);		\
-	unsigned long __ao_size = (unsigned long)(size);		\
-	__range_ok(__ao_addr, __ao_size);				\
+	__chk_user_ptr(addr);						\
+	__range_ok((unsigned long)(addr), (size));			\
 })
 
 /*
@@ -100,7 +101,7 @@ extern long __put_user_bad(void);
 #define __put_user_check(x, ptr, size)					\
 ({									\
 	long __pu_err = -EFAULT;					\
-	__typeof__(*(ptr)) *__pu_addr = (ptr);				\
+	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
 	if (access_ok(__pu_addr, size))			\
 		__put_user_size((x), __pu_addr, (size), __pu_err);	\
 	__pu_err;							\
@@ -173,7 +174,7 @@ struct __large_struct {
 #define __get_user_check(x, ptr, size)					\
 ({									\
 	long __gu_err = -EFAULT, __gu_val = 0;				\
-	const __typeof__(*(ptr)) * __gu_addr = (ptr);			\
+	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
 	if (access_ok(__gu_addr, size))			\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -241,17 +242,17 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long size)
 	return __copy_tofrom_user(to, (__force const void *)from, size);
 }
 static inline unsigned long
-raw_copy_to_user(void *to, const void __user *from, unsigned long size)
+raw_copy_to_user(void __user *to, const void *from, unsigned long size)
 {
 	return __copy_tofrom_user((__force void *)to, from, size);
 }
 #define INLINE_COPY_FROM_USER
 #define INLINE_COPY_TO_USER
 
-extern unsigned long __clear_user(void *addr, unsigned long size);
+extern unsigned long __clear_user(void __user *addr, unsigned long size);
 
 static inline __must_check unsigned long
-clear_user(void *addr, unsigned long size)
+clear_user(void __user *addr, unsigned long size)
 {
 	if (likely(access_ok(addr, size)))
 		size = __clear_user(addr, size);
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 848f74c2c47a..0ff391f00334 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -214,13 +214,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	regs->sp = sp;
 }
 
-/* Fill in the fpu structure for a core dump.  */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu)
-{
-	/* TODO */
-	return 0;
-}
-
 extern struct thread_info *_switch(struct thread_info *old_ti,
 				   struct thread_info *new_ti);
 extern int lwa_flag;
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index 8aa438e1f51f..b18e775f8be3 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -292,13 +292,15 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.brk = (unsigned long)_end;
 
 #ifdef CONFIG_BLK_DEV_INITRD
-	initrd_start = (unsigned long)&__initrd_start;
-	initrd_end = (unsigned long)&__initrd_end;
 	if (initrd_start == initrd_end) {
+		printk(KERN_INFO "Initial ramdisk not found\n");
 		initrd_start = 0;
 		initrd_end = 0;
+	} else {
+		printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n",
+		       (void *)(initrd_start), initrd_end - initrd_start);
+		initrd_below_start_ok = 1;
 	}
-	initrd_below_start_ok = 1;
 #endif
 
 	/* setup memblock allocator */
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 4f0754874d78..97804f21a40c 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -68,7 +68,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 
 asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
 {
-	struct rt_sigframe *frame = (struct rt_sigframe __user *)regs->sp;
+	struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->sp;
 	sigset_t set;
 
 	/*
@@ -76,7 +76,7 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
 	 * then frame should be dword aligned here.  If it's
 	 * not, then the user is trying to mess with us.
 	 */
-	if (((long)frame) & 3)
+	if (((unsigned long)frame) & 3)
 		goto badframe;
 
 	if (!access_ok(frame, sizeof(*frame)))
@@ -151,7 +151,7 @@ static inline void __user *get_sigframe(struct ksignal *ksig,
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
-	struct rt_sigframe *frame;
+	struct rt_sigframe __user *frame;
 	unsigned long return_ip;
 	int err = 0;
 
@@ -181,10 +181,10 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 		l.ori r11,r0,__NR_sigreturn
 		l.sys 1
 	 */
-	err |= __put_user(0xa960,             (short *)(frame->retcode + 0));
-	err |= __put_user(__NR_rt_sigreturn,  (short *)(frame->retcode + 2));
-	err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4));
-	err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8));
+	err |= __put_user(0xa960,             (short __user *)(frame->retcode + 0));
+	err |= __put_user(__NR_rt_sigreturn,  (short __user *)(frame->retcode + 2));
+	err |= __put_user(0x20000001, (unsigned long __user *)(frame->retcode + 4));
+	err |= __put_user(0x15000000, (unsigned long __user *)(frame->retcode + 8));
 
 	if (err)
 		return -EFAULT;
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index bd1e660bbc89..29c82ef2e207 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -219,30 +219,99 @@ static inline void ipi_flush_tlb_all(void *ignored)
 	local_flush_tlb_all();
 }
 
+static inline void ipi_flush_tlb_mm(void *info)
+{
+	struct mm_struct *mm = (struct mm_struct *)info;
+
+	local_flush_tlb_mm(mm);
+}
+
+static void smp_flush_tlb_mm(struct cpumask *cmask, struct mm_struct *mm)
+{
+	unsigned int cpuid;
+
+	if (cpumask_empty(cmask))
+		return;
+
+	cpuid = get_cpu();
+
+	if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) {
+		/* local cpu is the only cpu present in cpumask */
+		local_flush_tlb_mm(mm);
+	} else {
+		on_each_cpu_mask(cmask, ipi_flush_tlb_mm, mm, 1);
+	}
+	put_cpu();
+}
+
+struct flush_tlb_data {
+	unsigned long addr1;
+	unsigned long addr2;
+};
+
+static inline void ipi_flush_tlb_page(void *info)
+{
+	struct flush_tlb_data *fd = (struct flush_tlb_data *)info;
+
+	local_flush_tlb_page(NULL, fd->addr1);
+}
+
+static inline void ipi_flush_tlb_range(void *info)
+{
+	struct flush_tlb_data *fd = (struct flush_tlb_data *)info;
+
+	local_flush_tlb_range(NULL, fd->addr1, fd->addr2);
+}
+
+static void smp_flush_tlb_range(struct cpumask *cmask, unsigned long start,
+				unsigned long end)
+{
+	unsigned int cpuid;
+
+	if (cpumask_empty(cmask))
+		return;
+
+	cpuid = get_cpu();
+
+	if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) {
+		/* local cpu is the only cpu present in cpumask */
+		if ((end - start) <= PAGE_SIZE)
+			local_flush_tlb_page(NULL, start);
+		else
+			local_flush_tlb_range(NULL, start, end);
+	} else {
+		struct flush_tlb_data fd;
+
+		fd.addr1 = start;
+		fd.addr2 = end;
+
+		if ((end - start) <= PAGE_SIZE)
+			on_each_cpu_mask(cmask, ipi_flush_tlb_page, &fd, 1);
+		else
+			on_each_cpu_mask(cmask, ipi_flush_tlb_range, &fd, 1);
+	}
+	put_cpu();
+}
+
 void flush_tlb_all(void)
 {
 	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 }
 
-/*
- * FIXME: implement proper functionality instead of flush_tlb_all.
- * *But*, as things currently stands, the local_tlb_flush_* functions will
- * all boil down to local_tlb_flush_all anyway.
- */
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	smp_flush_tlb_mm(mm_cpumask(mm), mm);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
-	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	smp_flush_tlb_range(mm_cpumask(vma->vm_mm), uaddr, uaddr + PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
 		     unsigned long start, unsigned long end)
 {
-	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	smp_flush_tlb_range(mm_cpumask(vma->vm_mm), start, end);
 }
 
 /* Instruction cache invalidate - performed on each cpu */
diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c
index 43f140a28bc7..54d38809e22c 100644
--- a/arch/openrisc/kernel/stacktrace.c
+++ b/arch/openrisc/kernel/stacktrace.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 
 #include <asm/processor.h>
@@ -68,12 +69,25 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	unsigned long *sp = NULL;
 
+	if (!try_get_task_stack(tsk))
+		return;
+
 	if (tsk == current)
 		sp = (unsigned long *) &sp;
-	else
-		sp = (unsigned long *) KSTK_ESP(tsk);
+	else {
+		unsigned long ksp;
+
+		/* Locate stack from kernel context */
+		ksp = task_thread_info(tsk)->ksp;
+		ksp += STACK_FRAME_OVERHEAD;	/* redzone */
+		ksp += sizeof(struct pt_regs);
+
+		sp = (unsigned long *) ksp;
+	}
 
 	unwind_stack(trace, sp, save_stack_address_nosched);
+
+	put_task_stack(tsk);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 60449fd7f16f..22fbc5fb24b3 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -96,18 +96,6 @@ SECTIONS
 
         __init_end = .;
 
-	. = ALIGN(PAGE_SIZE);
-	.initrd			: AT(ADDR(.initrd) - LOAD_OFFSET)
-	{
-		__initrd_start = .;
-		*(.initrd)
-		__initrd_end = .;
-		FILL (0);
-                . = ALIGN (PAGE_SIZE);
-	}
-
-        __vmlinux_end = .;            /* last address of the physical file */
-
 	BSS_SECTION(0, 0, 0x20)
 
         _end = .;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index d2224ccca294..ca97d9baab51 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/sched/signal.h>
+#include <linux/perf_event.h>
 
 #include <linux/uaccess.h>
 #include <asm/siginfo.h>
@@ -103,6 +104,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_interrupt() || !mm)
 		goto no_context;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -159,7 +162,7 @@ good_area:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -176,10 +179,6 @@ good_area:
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
 		/*RGD modeled on Cris */
-		if (fault & VM_FAULT_MAJOR)
-			tsk->maj_flt++;
-		else
-			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c
index 4b680aed8f5f..2b6feabf6381 100644
--- a/arch/openrisc/mm/tlb.c
+++ b/arch/openrisc/mm/tlb.c
@@ -137,21 +137,28 @@ void local_flush_tlb_mm(struct mm_struct *mm)
 void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	       struct task_struct *next_tsk)
 {
+	unsigned int cpu;
+
+	if (unlikely(prev == next))
+		return;
+
+	cpu = smp_processor_id();
+
+	cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+
 	/* remember the pgd for the fault handlers
 	 * this is similar to the pgd register in some other CPU's.
 	 * we need our own copy of it because current and active_mm
 	 * might be invalid at points where we still need to derefer
 	 * the pgd.
 	 */
-	current_pgd[smp_processor_id()] = next->pgd;
+	current_pgd[cpu] = next->pgd;
 
 	/* We don't have context support implemented, so flush all
 	 * entries belonging to previous map
 	 */
-
-	if (prev != next)
-		local_flush_tlb_mm(prev);
-
+	local_flush_tlb_mm(prev);
 }
 
 /*
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 03862320f779..21b375c67e53 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -34,13 +34,13 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
 /* Can't use raw_spin_lock_irq because of #include problems, so
  * this is the substitute */
 #define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
+	arch_spinlock_t *s = ATOMIC_HASH(l);	\
 	local_irq_save(f);			\
 	arch_spin_lock(s);			\
 } while(0)
 
 #define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);			\
+	arch_spinlock_t *s = ATOMIC_HASH(l);		\
 	arch_spin_unlock(s);				\
 	local_irq_restore(f);				\
 } while(0)
@@ -85,7 +85,7 @@ static __inline__ void atomic_##op(int i, atomic_t *v)			\
 	_atomic_spin_lock_irqsave(v, flags);				\
 	v->counter c_op i;						\
 	_atomic_spin_unlock_irqrestore(v, flags);			\
-}									\
+}
 
 #define ATOMIC_OP_RETURN(op, c_op)					\
 static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
@@ -148,7 +148,7 @@ static __inline__ void atomic64_##op(s64 i, atomic64_t *v)		\
 	_atomic_spin_lock_irqsave(v, flags);				\
 	v->counter c_op i;						\
 	_atomic_spin_unlock_irqrestore(v, flags);			\
-}									\
+}
 
 #define ATOMIC64_OP_RETURN(op, c_op)					\
 static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
index dbaaca84f27f..640d46edf32e 100644
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -26,6 +26,67 @@
 #define __smp_rmb()	mb()
 #define __smp_wmb()	mb()
 
+#define __smp_store_release(p, v)					\
+do {									\
+	typeof(p) __p = (p);						\
+        union { typeof(*p) __val; char __c[1]; } __u =			\
+                { .__val = (__force typeof(*p)) (v) };			\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("stb,ma %0,0(%1)"				\
+				: : "r"(*(__u8 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("sth,ma %0,0(%1)"				\
+				: : "r"(*(__u16 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("stw,ma %0,0(%1)"				\
+				: : "r"(*(__u32 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("std,ma %0,0(%1)"			\
+				: : "r"(*(__u64 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("ldb,ma 0(%1),%0"				\
+				: "=r"(*(__u8 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("ldh,ma 0(%1),%0"				\
+				: "=r"(*(__u16 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("ldw,ma 0(%1),%0"				\
+				: "=r"(*(__u32 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("ldd,ma 0(%1),%0"			\
+				: "=r"(*(__u64 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+	__u.__val;							\
+})
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 301af07a04d4..3bd465a27791 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -305,9 +305,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 struct task_struct;
 
-extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
-#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
-
 struct pt_regs;	/* forward declaration... */
 
 
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 116effe26143..45e20d38dc59 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -303,8 +303,8 @@ extern void outsl (unsigned long port, const void *src, unsigned long count);
 #define ioread64be ioread64be
 #define iowrite64 iowrite64
 #define iowrite64be iowrite64be
-extern u64 ioread64(void __iomem *addr);
-extern u64 ioread64be(void __iomem *addr);
+extern u64 ioread64(const void __iomem *addr);
+extern u64 ioread64be(const void __iomem *addr);
 extern void iowrite64(u64 val, void __iomem *addr);
 extern void iowrite64be(u64 val, void __iomem *addr);
 
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index cc7ecc2ef55d..a6482b2ce0ea 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -10,6 +10,7 @@
 
 #include <asm/cache.h>
 
+#define __HAVE_ARCH_PMD_ALLOC_ONE
 #define __HAVE_ARCH_PMD_FREE
 #define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
@@ -67,6 +68,11 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 			(__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT)));
 }
 
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	return (pmd_t *)__get_free_pages(GFP_PGTABLE_KERNEL, PMD_ORDER);
+}
+
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h
index 45537cd4d1d3..06b510f8172e 100644
--- a/arch/parisc/include/asm/timex.h
+++ b/arch/parisc/include/asm/timex.h
@@ -7,6 +7,7 @@
 #ifndef _ASMPARISC_TIMEX_H
 #define _ASMPARISC_TIMEX_H
 
+#include <asm/special_insns.h>
 
 #define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
 
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index ebbb9ffe038c..ed2cd4fb479b 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -14,7 +14,7 @@
 #define KERNEL_DS	((mm_segment_t){0})
 #define USER_DS 	((mm_segment_t){1})
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 1df0f67ed667..4bab21c71055 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -64,7 +64,8 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent,
 				function_trace_op, regs);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	if (ftrace_graph_return != (trace_func_graph_ret_t) ftrace_stub ||
+	if (dereference_function_descriptor(ftrace_graph_return) !=
+	    dereference_function_descriptor(ftrace_stub) ||
 	    ftrace_graph_entry != ftrace_graph_entry_stub) {
 		unsigned long *parent_rp;
 
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 86ec30cc0e77..f196d96e2f9f 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -152,25 +152,6 @@ void release_thread(struct task_struct *dead_task)
 }
 
 /*
- * Fill in the FPU structure for a core dump.
- */
-
-int dump_fpu (struct pt_regs * regs, elf_fpregset_t *r)
-{
-	if (regs == NULL)
-		return 0;
-
-	memcpy(r, regs->fr, sizeof *r);
-	return 1;
-}
-
-int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
-{
-	memcpy(r, tsk->thread.regs.fr, sizeof(*r));
-	return 1;
-}
-
-/*
  * Idle thread support
  *
  * Detect when running on QEMU with SeaBIOS PDC Firmware and let
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 292baabefade..def64d221cd4 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -163,7 +163,7 @@
 146	common	writev			sys_writev			compat_sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
-149	common	_sysctl			sys_sysctl			compat_sys_sysctl
+149	common	_sysctl			sys_ni_syscall
 150	common	mlock			sys_mlock
 151	common	munlock			sys_munlock
 152	common	mlockall		sys_mlockall
diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c
index 0195aec657e2..ce400417d54e 100644
--- a/arch/parisc/lib/iomap.c
+++ b/arch/parisc/lib/iomap.c
@@ -43,13 +43,13 @@
 #endif
 
 struct iomap_ops {
-	unsigned int (*read8)(void __iomem *);
-	unsigned int (*read16)(void __iomem *);
-	unsigned int (*read16be)(void __iomem *);
-	unsigned int (*read32)(void __iomem *);
-	unsigned int (*read32be)(void __iomem *);
-	u64 (*read64)(void __iomem *);
-	u64 (*read64be)(void __iomem *);
+	unsigned int (*read8)(const void __iomem *);
+	unsigned int (*read16)(const void __iomem *);
+	unsigned int (*read16be)(const void __iomem *);
+	unsigned int (*read32)(const void __iomem *);
+	unsigned int (*read32be)(const void __iomem *);
+	u64 (*read64)(const void __iomem *);
+	u64 (*read64be)(const void __iomem *);
 	void (*write8)(u8, void __iomem *);
 	void (*write16)(u16, void __iomem *);
 	void (*write16be)(u16, void __iomem *);
@@ -57,9 +57,9 @@ struct iomap_ops {
 	void (*write32be)(u32, void __iomem *);
 	void (*write64)(u64, void __iomem *);
 	void (*write64be)(u64, void __iomem *);
-	void (*read8r)(void __iomem *, void *, unsigned long);
-	void (*read16r)(void __iomem *, void *, unsigned long);
-	void (*read32r)(void __iomem *, void *, unsigned long);
+	void (*read8r)(const void __iomem *, void *, unsigned long);
+	void (*read16r)(const void __iomem *, void *, unsigned long);
+	void (*read32r)(const void __iomem *, void *, unsigned long);
 	void (*write8r)(void __iomem *, const void *, unsigned long);
 	void (*write16r)(void __iomem *, const void *, unsigned long);
 	void (*write32r)(void __iomem *, const void *, unsigned long);
@@ -69,17 +69,17 @@ struct iomap_ops {
 
 #define ADDR2PORT(addr) ((unsigned long __force)(addr) & 0xffffff)
 
-static unsigned int ioport_read8(void __iomem *addr)
+static unsigned int ioport_read8(const void __iomem *addr)
 {
 	return inb(ADDR2PORT(addr));
 }
 
-static unsigned int ioport_read16(void __iomem *addr)
+static unsigned int ioport_read16(const void __iomem *addr)
 {
 	return inw(ADDR2PORT(addr));
 }
 
-static unsigned int ioport_read32(void __iomem *addr)
+static unsigned int ioport_read32(const void __iomem *addr)
 {
 	return inl(ADDR2PORT(addr));
 }
@@ -99,17 +99,17 @@ static void ioport_write32(u32 datum, void __iomem *addr)
 	outl(datum, ADDR2PORT(addr));
 }
 
-static void ioport_read8r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read8r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insb(ADDR2PORT(addr), dst, count);
 }
 
-static void ioport_read16r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read16r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insw(ADDR2PORT(addr), dst, count);
 }
 
-static void ioport_read32r(void __iomem *addr, void *dst, unsigned long count)
+static void ioport_read32r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	insl(ADDR2PORT(addr), dst, count);
 }
@@ -150,37 +150,37 @@ static const struct iomap_ops ioport_ops = {
 
 /* Legacy I/O memory ops */
 
-static unsigned int iomem_read8(void __iomem *addr)
+static unsigned int iomem_read8(const void __iomem *addr)
 {
 	return readb(addr);
 }
 
-static unsigned int iomem_read16(void __iomem *addr)
+static unsigned int iomem_read16(const void __iomem *addr)
 {
 	return readw(addr);
 }
 
-static unsigned int iomem_read16be(void __iomem *addr)
+static unsigned int iomem_read16be(const void __iomem *addr)
 {
 	return __raw_readw(addr);
 }
 
-static unsigned int iomem_read32(void __iomem *addr)
+static unsigned int iomem_read32(const void __iomem *addr)
 {
 	return readl(addr);
 }
 
-static unsigned int iomem_read32be(void __iomem *addr)
+static unsigned int iomem_read32be(const void __iomem *addr)
 {
 	return __raw_readl(addr);
 }
 
-static u64 iomem_read64(void __iomem *addr)
+static u64 iomem_read64(const void __iomem *addr)
 {
 	return readq(addr);
 }
 
-static u64 iomem_read64be(void __iomem *addr)
+static u64 iomem_read64be(const void __iomem *addr)
 {
 	return __raw_readq(addr);
 }
@@ -220,7 +220,7 @@ static void iomem_write64be(u64 datum, void __iomem *addr)
 	__raw_writel(datum, addr);
 }
 
-static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read8r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u8 *)dst = __raw_readb(addr);
@@ -228,7 +228,7 @@ static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read16r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u16 *)dst = __raw_readw(addr);
@@ -236,7 +236,7 @@ static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-static void iomem_read32r(void __iomem *addr, void *dst, unsigned long count)
+static void iomem_read32r(const void __iomem *addr, void *dst, unsigned long count)
 {
 	while (count--) {
 		*(u32 *)dst = __raw_readl(addr);
@@ -297,49 +297,49 @@ static const struct iomap_ops *iomap_ops[8] = {
 };
 
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read8(addr);
 	return *((u8 *)addr);
 }
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read16(addr);
 	return le16_to_cpup((u16 *)addr);
 }
 
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read16be(addr);
 	return *((u16 *)addr);
 }
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read32(addr);
 	return le32_to_cpup((u32 *)addr);
 }
 
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read32be(addr);
 	return *((u32 *)addr);
 }
 
-u64 ioread64(void __iomem *addr)
+u64 ioread64(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read64(addr);
 	return le64_to_cpup((u64 *)addr);
 }
 
-u64 ioread64be(void __iomem *addr)
+u64 ioread64be(const void __iomem *addr)
 {
 	if (unlikely(INDIRECT_ADDR(addr)))
 		return iomap_ops[ADDR_TO_REGION(addr)]->read64be(addr);
@@ -411,7 +411,7 @@ void iowrite64be(u64 datum, void __iomem *addr)
 
 /* Repeating interfaces */
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read8r(addr, dst, count);
@@ -423,7 +423,7 @@ void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read16r(addr, dst, count);
@@ -435,7 +435,7 @@ void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
 	}
 }
 
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	if (unlikely(INDIRECT_ADDR(addr))) {
 		iomap_ops[ADDR_TO_REGION(addr)]->read32r(addr, dst, count);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 66ac0719bd49..4bfe2da9fbe3 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -18,6 +18,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
+#include <linux/perf_event.h>
 
 #include <asm/traps.h>
 
@@ -281,6 +282,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	acc_type = parisc_acctyp(code, regs->iir);
 	if (acc_type & VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma_prev(mm, address, &prev_vma);
@@ -302,7 +304,7 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -323,10 +325,6 @@ good_area:
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			/*
 			 * No need to mmap_read_unlock(mm) as we would
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 44af71543380..b88fd27a45f0 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -366,6 +366,8 @@ initrd-y := $(patsubst zImage%, zImage.initrd%, \
 		$(patsubst treeImage%, treeImage.initrd%, $(image-y)))))
 initrd-y := $(filter-out $(image-y), $(initrd-y))
 targets	+= $(image-y) $(initrd-y)
+targets += $(foreach x, dtbImage uImage cuImage simpleImage treeImage, \
+		$(patsubst $(x).%, dts/%.dtb, $(filter $(x).%, $(image-y))))
 
 $(addprefix $(obj)/, $(initrd-y)): $(obj)/ramdisk.image.gz
 
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index d8a0729cf754..219559d65864 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -29,9 +29,6 @@ struct dev_archdata {
 	struct iommu_table	*iommu_table_base;
 #endif
 
-#ifdef CONFIG_IOMMU_API
-	void			*iommu_domain;
-#endif
 #ifdef CONFIG_PPC64
 	struct pci_dn		*pci_data;
 #endif
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 64c04ab09112..00699903f1ef 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -38,8 +38,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
 #ifdef __powerpc64__
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index d4d5946224f8..cbf41fb4ee89 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -16,7 +16,7 @@ CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 
-CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
+CFLAGS_prom_init.o += -fno-stack-protector
 CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
 CFLAGS_prom_init.o += -ffreestanding
 
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 5ac84efc6ede..9fe4fb3b08aa 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -15,23 +15,23 @@
  * Here comes the ppc64 implementation of the IOMAP 
  * interfaces.
  */
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	return readb(addr);
 }
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	return readw(addr);
 }
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	return readw_be(addr);
 }
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	return readl(addr);
 }
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	return readl_be(addr);
 }
@@ -41,27 +41,27 @@ EXPORT_SYMBOL(ioread16be);
 EXPORT_SYMBOL(ioread32);
 EXPORT_SYMBOL(ioread32be);
 #ifdef __powerpc64__
-u64 ioread64(void __iomem *addr)
+u64 ioread64(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	return readq(addr);
 }
-u64 ioread64be(void __iomem *addr)
+u64 ioread64be(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
@@ -139,15 +139,15 @@ EXPORT_SYMBOL(iowrite64be_hi_lo);
  * FIXME! We could make these do EEH handling if we really
  * wanted. Not clear if we do.
  */
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsb(addr, dst, count);
 }
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsw(addr, dst, count);
 }
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	readsl(addr, dst, count);
 }
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index be9f74546068..c2d737ff2e7b 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -197,7 +197,7 @@
 146	common	writev				sys_writev			compat_sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+149	nospu	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 1478fceeb683..1da9dbba9217 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1115,9 +1115,8 @@ void hash__early_init_mmu_secondary(void)
 			&& cpu_has_feature(CPU_FTR_HVMODE))
 		tlbiel_all();
 
-#ifdef CONFIG_PPC_MEM_KEYS
-	mtspr(SPRN_UAMOR, default_uamor);
-#endif
+	if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY))
+		mtspr(SPRN_UAMOR, default_uamor);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 69a6b87f2bb4..b1d091a97611 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -73,12 +73,6 @@ static int scan_pkey_feature(void)
 	if (early_radix_enabled())
 		return 0;
 
-	/*
-	 * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1
-	 */
-	if (!early_cpu_has_feature(CPU_FTR_ARCH_206))
-		return 0;
-
 	ret = of_scan_flat_dt(dt_scan_storage_keys, &pkeys_total);
 	if (ret == 0) {
 		/*
@@ -124,6 +118,12 @@ void __init pkey_early_init_devtree(void)
 		     __builtin_popcountl(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)
 				!= (sizeof(u64) * BITS_PER_BYTE));
 
+	/*
+	 * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1
+	 */
+	if (!early_cpu_has_feature(CPU_FTR_ARCH_206))
+		return;
+
 	/* scan the device tree for pkey feature */
 	pkeys_total = scan_pkey_feature();
 	if (!pkeys_total)
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index b83abbead4a2..8acd00178956 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	}
 
 	ret = 0;
-	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL);
 	if (unlikely(*flt & VM_FAULT_ERROR)) {
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
@@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		BUG();
 	}
 
-	if (*flt & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
-
 out_unlock:
 	mmap_read_unlock(mm);
 	return ret;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 925a7231abb3..0add963a849b 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -511,7 +511,7 @@ retry:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	major |= fault & VM_FAULT_MAJOR;
 
@@ -537,14 +537,9 @@ retry:
 	/*
 	 * Major/minor page fault accounting.
 	 */
-	if (major) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	if (major)
 		cmo_account_page_fault();
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
+
 	return 0;
 }
 NOKPROBE_SYMBOL(__do_page_fault);
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index f4247ade71ca..cf85f0662d0d 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS_bootx_init.o  		+= -fPIC
-CFLAGS_bootx_init.o  		+= $(call cc-option, -fno-stack-protector)
+CFLAGS_bootx_init.o		+= -fno-stack-protector
 
 KASAN_SANITIZE_bootx_init.o := n
 
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 89c76ca35640..eb25d7554ffd 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -7,8 +7,7 @@ UBSAN_SANITIZE := n
 KASAN_SANITIZE := n
 
 # Disable ftrace for the entire directory
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
 
 ifdef CONFIG_CC_IS_CLANG
 # clang stores addresses on the stack causing the frame size to blow
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 8ce9d607b53d..f56c66b3f5fe 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -8,6 +8,8 @@
 #ifndef _ASM_RISCV_UACCESS_H
 #define _ASM_RISCV_UACCESS_H
 
+#include <asm/pgtable.h>		/* for TASK_SIZE */
+
 /*
  * User space memory access functions
  */
@@ -62,11 +64,9 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max()	(get_fs().seg)
 
-
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index 3099362d9f26..f839f16e0d2a 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -60,7 +60,8 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 	return ret;
 }
 
-static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
 {
 	/*
 	 * The purpose of csr_read(CSR_TIME) is to trap the system into
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index d0c5c316e9bb..0a4e81b8dc79 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -77,16 +77,10 @@ relocate:
 	csrw CSR_SATP, a0
 .align 2
 1:
-	/* Set trap vector to exception handler */
-	la a0, handle_exception
+	/* Set trap vector to spin forever to help debug */
+	la a0, .Lsecondary_park
 	csrw CSR_TVEC, a0
 
-	/*
-	 * Set sup0 scratch register to 0, indicating to exception vector that
-	 * we are presently executing in kernel.
-	 */
-	csrw CSR_SCRATCH, zero
-
 	/* Reload the global pointer */
 .option push
 .option norelax
@@ -144,9 +138,23 @@ secondary_start_common:
 	la a0, swapper_pg_dir
 	call relocate
 #endif
+	call setup_trap_vector
 	tail smp_callin
 #endif /* CONFIG_SMP */
 
+.align 2
+setup_trap_vector:
+	/* Set trap vector to exception handler */
+	la a0, handle_exception
+	csrw CSR_TVEC, a0
+
+	/*
+	 * Set sup0 scratch register to 0, indicating to exception vector that
+	 * we are presently executing in kernel.
+	 */
+	csrw CSR_SCRATCH, zero
+	ret
+
 .Lsecondary_park:
 	/* We lack SMP support or have too many harts, so park this hart */
 	wfi
@@ -240,6 +248,7 @@ clear_bss_done:
 	call relocate
 #endif /* CONFIG_MMU */
 
+	call setup_trap_vector
 	/* Restore C environment */
 	la tp, init_task
 	sw zero, TASK_TI_CPU(tp)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 5873835a3e6b..716d64e36f83 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -109,7 +109,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, regs);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
@@ -127,21 +127,7 @@ good_area:
 		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index e63940bb57cd..8b98c501142d 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -7,5 +7,4 @@ obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
 obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-y				+= net/
 obj-$(CONFIG_PCI)		+= pci/
-obj-$(CONFIG_NUMA)		+= numa/
 obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8c0b52940165..3d86e12e8e3c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -126,7 +126,6 @@ config S390
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_VMALLOC
-	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY
@@ -766,6 +765,7 @@ config VFIO_AP
 	def_tristate n
 	prompt "VFIO support for AP devices"
 	depends on S390_AP_IOMMU && VFIO_MDEV_DEVICE && KVM
+	depends on ZCRYPT
 	help
 		This driver grants access to Adjunct Processor (AP) devices
 		via the VFIO mediated device interface.
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 8dfa2cf1f05c..ba94b03c8b2f 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
-KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += -ffreestanding
 KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index cae473a7b6f7..11c5952e1afa 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -45,7 +45,11 @@ static inline int atomic_fetch_add(int i, atomic_t *v)
 static inline void atomic_add(int i, atomic_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
+	/*
+	 * Order of conditions is important to circumvent gcc 10 bug:
+	 * https://gcc.gnu.org/pipermail/gcc-patches/2020-July/549318.html
+	 */
+	if ((i > -129) && (i < 128) && __builtin_constant_p(i)) {
 		__atomic_add_const(i, &v->counter);
 		return;
 	}
@@ -112,7 +116,11 @@ static inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
 static inline void atomic64_add(s64 i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
+	/*
+	 * Order of conditions is important to circumvent gcc 10 bug:
+	 * https://gcc.gnu.org/pipermail/gcc-patches/2020-July/549318.html
+	 */
+	if ((i > -129) && (i < 128) && __builtin_constant_p(i)) {
 		__atomic64_add_const(i, (long *)&v->counter);
 		return;
 	}
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 17a26261f288..c1b82bcc017c 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -2,7 +2,7 @@
 /*
  *   S/390 debug facility
  *
- *    Copyright IBM Corp. 1999, 2000
+ *    Copyright IBM Corp. 1999, 2020
  */
 #ifndef DEBUG_H
 #define DEBUG_H
@@ -26,19 +26,14 @@
 #define DEBUG_DATA(entry) (char *)(entry + 1) /* data is stored behind */
 					      /* the entry information */
 
-#define __DEBUG_FEATURE_VERSION	   2  /* version of debug feature */
+#define __DEBUG_FEATURE_VERSION	   3  /* version of debug feature */
 
 struct __debug_entry {
-	union {
-		struct {
-			unsigned long clock	: 52;
-			unsigned long exception	:  1;
-			unsigned long level	:  3;
-			unsigned long cpuid	:  8;
-		} fields;
-		unsigned long stck;
-	} id;
+	unsigned long clock	: 60;
+	unsigned long exception	:  1;
+	unsigned long level	:  3;
 	void *caller;
+	unsigned short cpu;
 } __packed;
 
 typedef struct __debug_entry debug_entry_t;
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index fbb507504a3b..3a0ac0c7a9a3 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -86,12 +86,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 
-#define node_distance(a, b) __node_distance(a, b)
-static inline int __node_distance(int a, int b)
-{
-	return 0;
-}
-
 #else /* !CONFIG_NUMA */
 
 #define numa_node_id numa_node_id
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 324438889fe1..f09444d6aeab 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define USER_DS_SACF	(3)
 
 #define get_fs()        (current->thread.mm_segment)
-#define segment_eq(a,b) (((a) & 2) == ((b) & 2))
+#define uaccess_kernel() ((get_fs() & 2) == KERNEL_DS)
 
 void set_fs(mm_segment_t fs);
 
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index a8f136943deb..efca70970761 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -49,6 +49,7 @@ CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
 
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_SCHED_TOPOLOGY)	+= topology.o
+obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
 obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index beb4b44a11d1..b6619ae9a3e0 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -2,7 +2,7 @@
 /*
  *   S/390 debug facility
  *
- *    Copyright IBM Corp. 1999, 2012
+ *    Copyright IBM Corp. 1999, 2020
  *
  *    Author(s): Michael Holzheu (holzheu@de.ibm.com),
  *		 Holger Smolinski (Holger.Smolinski@de.ibm.com)
@@ -433,7 +433,7 @@ static int debug_format_entry(file_private_info_t *p_info)
 	act_entry = (debug_entry_t *) ((char *)id_snap->areas[p_info->act_area]
 				       [p_info->act_page] + p_info->act_entry);
 
-	if (act_entry->id.stck == 0LL)
+	if (act_entry->clock == 0LL)
 		goto out; /* empty entry */
 	if (view->header_proc)
 		len += view->header_proc(id_snap, view, p_info->act_area,
@@ -829,12 +829,17 @@ static inline debug_entry_t *get_active_entry(debug_info_t *id)
 static inline void debug_finish_entry(debug_info_t *id, debug_entry_t *active,
 				      int level, int exception)
 {
-	active->id.stck = get_tod_clock_fast() -
-		*(unsigned long long *) &tod_clock_base[1];
-	active->id.fields.cpuid = smp_processor_id();
+	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	unsigned long timestamp;
+
+	get_tod_clock_ext(clk);
+	timestamp = *(unsigned long *) &clk[0] >> 4;
+	timestamp -= TOD_UNIX_EPOCH >> 12;
+	active->clock = timestamp;
+	active->cpu = smp_processor_id();
 	active->caller = __builtin_return_address(0);
-	active->id.fields.exception = exception;
-	active->id.fields.level = level;
+	active->exception = exception;
+	active->level = level;
 	proceed_active_entry(id);
 	if (exception)
 		proceed_active_area(id);
@@ -1398,25 +1403,24 @@ static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
 int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
 			 int area, debug_entry_t *entry, char *out_buf)
 {
-	unsigned long base, sec, usec;
+	unsigned long sec, usec;
 	unsigned long caller;
 	unsigned int level;
 	char *except_str;
 	int rc = 0;
 
-	level = entry->id.fields.level;
-	base = (*(unsigned long *) &tod_clock_base[0]) >> 4;
-	sec = (entry->id.stck >> 12) + base - (TOD_UNIX_EPOCH >> 12);
+	level = entry->level;
+	sec = entry->clock;
 	usec = do_div(sec, USEC_PER_SEC);
 
-	if (entry->id.fields.exception)
+	if (entry->exception)
 		except_str = "*";
 	else
 		except_str = "-";
 	caller = (unsigned long) entry->caller;
-	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK  ",
+	rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %04u %pK  ",
 		      area, sec, usec, level, except_str,
-		      entry->id.fields.cpuid, (void *)caller);
+		      entry->cpu, (void *)caller);
 	return rc;
 }
 EXPORT_SYMBOL(debug_dflt_header_fn);
diff --git a/arch/s390/numa/numa.c b/arch/s390/kernel/numa.c
index 51c5a9f6e525..51c5a9f6e525 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/kernel/numa.c
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b06dec1267d0..ec801d3bbb37 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -160,24 +160,6 @@ asmlinkage void execve_tail(void)
 	asm volatile("sfpc %0" : : "d" (0));
 }
 
-/*
- * fill in the FPU structure for a core dump.
- */
-int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
-{
-	save_fpu_regs();
-	fpregs->fpc = current->thread.fpu.fpc;
-	fpregs->pad = 0;
-	if (MACHINE_HAS_VX)
-		convert_vx_to_fp((freg_t *)&fpregs->fprs,
-				 current->thread.fpu.vxrs);
-	else
-		memcpy(&fpregs->fprs, current->thread.fpu.fprs,
-		       sizeof(fpregs->fprs));
-	return 1;
-}
-EXPORT_SYMBOL(dump_fpu);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct unwind_state state;
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index f1fda4375526..10456bc936fb 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -138,7 +138,7 @@
 146  common	writev			sys_writev			compat_sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
-149  common	_sysctl			sys_sysctl			compat_sys_sysctl
+149  common	_sysctl			-				-
 150  common	mlock			sys_mlock			sys_mlock
 151  common	munlock			sys_munlock			sys_munlock
 152  common	mlockall		sys_mlockall			sys_mlockall
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1608fd99bbee..2f177298c663 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2768,7 +2768,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
 	struct page *page = NULL;
 
 	mmap_read_lock(kvm->mm);
-	get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE,
+	get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE,
 			      &page, NULL, NULL);
 	mmap_read_unlock(kvm->mm);
 	return page;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 66da278a67fb..6b74b92c1a58 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1892,7 +1892,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
 		if (r) {
-			r = fixup_user_fault(current, current->mm, hva,
+			r = fixup_user_fault(current->mm, hva,
 					     FAULT_FLAG_WRITE, &unlocked);
 			if (r)
 				break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 2f721a923b54..cd74989ce0b0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -273,7 +273,7 @@ retry:
 	rc = get_guest_storage_key(current->mm, vmaddr, &key);
 
 	if (rc) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -319,7 +319,7 @@ retry:
 	mmap_read_lock(current->mm);
 	rc = reset_guest_reference_bit(current->mm, vmaddr);
 	if (rc < 0) {
-		rc = fixup_user_fault(current, current->mm, vmaddr,
+		rc = fixup_user_fault(current->mm, vmaddr,
 				      FAULT_FLAG_WRITE, &unlocked);
 		if (!rc) {
 			mmap_read_unlock(current->mm);
@@ -390,7 +390,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 						m3 & SSKE_MC);
 
 		if (rc < 0) {
-			rc = fixup_user_fault(current, current->mm, vmaddr,
+			rc = fixup_user_fault(current->mm, vmaddr,
 					      FAULT_FLAG_WRITE, &unlocked);
 			rc = !rc ? -EAGAIN : rc;
 		}
@@ -1094,7 +1094,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
 			if (rc < 0) {
-				rc = fixup_user_fault(current, current->mm, vmaddr,
+				rc = fixup_user_fault(current->mm, vmaddr,
 						      FAULT_FLAG_WRITE, &unlocked);
 				rc = !rc ? -EAGAIN : rc;
 			}
diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c
index eb382ceaa116..7c988994931f 100644
--- a/arch/s390/lib/test_unwind.c
+++ b/arch/s390/lib/test_unwind.c
@@ -64,6 +64,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs,
 			break;
 		if (state.reliable && !addr) {
 			pr_err("unwind state reliable but addr is 0\n");
+			kfree(bt);
 			return -EINVAL;
 		}
 		sprint_symbol(sym, addr);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index aebf9183bedd..4c8c063bce5b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -476,7 +476,7 @@ retry:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 	if (fault_signal_pending(fault, regs)) {
 		fault = VM_FAULT_SIGNAL;
 		if (flags & FAULT_FLAG_RETRY_NOWAIT)
@@ -486,21 +486,7 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR))
 		goto out_up;
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			if (IS_ENABLED(CONFIG_PGSTE) && gmap &&
 			    (flags & FAULT_FLAG_RETRY_NOWAIT)) {
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 190357ff86b3..373542ca1113 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -649,7 +649,7 @@ retry:
 		rc = vmaddr;
 		goto out_up;
 	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
+	if (fixup_user_fault(gmap->mm, vmaddr, fault_flags,
 			     &unlocked)) {
 		rc = -EFAULT;
 		goto out_up;
@@ -879,7 +879,7 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
 
 	BUG_ON(gmap_is_shadow(gmap));
 	fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
-	if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked))
+	if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked))
 		return -EFAULT;
 	if (unlocked)
 		/* lost mmap_lock, caller has to retry __gmap_translate */
@@ -2485,23 +2485,36 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
 }
 EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
+				    unsigned long end, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+
+	split_huge_pmd(vma, pmd, addr);
+	return 0;
+}
+
+static const struct mm_walk_ops thp_split_walk_ops = {
+	.pmd_entry	= thp_split_walk_pmd_entry,
+};
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	struct vm_area_struct *vma;
-	unsigned long addr;
 
 	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
-		for (addr = vma->vm_start;
-		     addr < vma->vm_end;
-		     addr += PAGE_SIZE)
-			follow_page(vma, addr, FOLL_SPLIT);
 		vma->vm_flags &= ~VM_HUGEPAGE;
 		vma->vm_flags |= VM_NOHUGEPAGE;
+		walk_page_vma(vma, &thp_split_walk_ops, NULL);
 	}
 	mm->def_flags |= VM_NOHUGEPAGE;
-#endif
 }
+#else
+static inline void thp_split_mm(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
  * Remove all empty zero pages from the mapping for lazy refaulting
diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile
deleted file mode 100644
index c89d26f4f77d..000000000000
--- a/arch/s390/numa/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-y			+= numa.o
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 9fc2b010e938..d20927128fce 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -1,75 +1,77 @@
 # SPDX-License-Identifier: GPL-2.0
 config SUPERH
 	def_bool y
+	select ARCH_32BIT_OFF_T
+	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
 	select ARCH_HAS_BINFMT_FLAT if !MMU
+	select ARCH_HAS_GIGANTIC_PAGE
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HIBERNATION_POSSIBLE if MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
-	select HAVE_PATA_PLATFORM
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select CLKDEV_LOOKUP
+	select CPU_NO_EFFICIENT_FFS
 	select DMA_DECLARE_COHERENT
-	select HAVE_IDE if HAS_IOPORT_MAP
-	select HAVE_OPROFILE
+	select GENERIC_ATOMIC64
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
+	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_SHOW
+	select GENERIC_PCI_IOMAP if PCI
+	select GENERIC_SCHED_CLOCK
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_SMP_IDLE_THREAD
+	select GUP_GET_PTE_LOW_HIGH if X2TLB
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_PERF_EVENTS
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
-	select HAVE_FAST_GUP if MMU
-	select ARCH_HAVE_CUSTOM_GPIO_H
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
-	select ARCH_HAS_GCOV_PROFILE_ALL
-	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_KERNEL_GZIP
-	select CPU_NO_EFFICIENT_FFS
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FAST_GUP if MMU
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUTEX_CMPXCHG if FUTEX
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_HW_BREAKPOINT
+	select HAVE_IDE if HAS_IOPORT_MAP
+	select HAVE_IOREMAP_PROT if MMU && !X2TLB
 	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
-	select HAVE_KERNEL_XZ
 	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_XZ
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_MIXED_BREAKPOINTS_REGS
+	select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER
+	select HAVE_NMI
+	select HAVE_OPROFILE
+	select HAVE_PATA_PLATFORM
+	select HAVE_PERF_EVENTS
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_UID16
-	select ARCH_WANT_IPC_PARSE_VERSION
+	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_REGS_AND_STACK_ACCESS_API
-	select MAY_HAVE_SPARSE_IRQ
 	select IRQ_FORCED_THREADING
-	select RTC_LIB
-	select GENERIC_ATOMIC64
-	select GENERIC_IRQ_SHOW
-	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_IDLE_POLL_SETUP
-	select GENERIC_CLOCKEVENTS
-	select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
-	select GENERIC_PCI_IOMAP if PCI
-	select GENERIC_SCHED_CLOCK
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER
+	select MAY_HAVE_SPARSE_IRQ
 	select MODULES_USE_ELF_RELA
+	select NEED_SG_DMA_LENGTH
+	select NO_DMA if !MMU && !DMA_COHERENT
 	select NO_GENERIC_PCI_IOPORT_MAP if PCI
-	select OLD_SIGSUSPEND
 	select OLD_SIGACTION
+	select OLD_SIGSUSPEND
 	select PCI_DOMAINS if PCI
-	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_NMI
-	select NEED_SG_DMA_LENGTH
-	select ARCH_HAS_GIGANTIC_PAGE
-	select ARCH_32BIT_OFF_T
-	select GUP_GET_PTE_LOW_HIGH if X2TLB
-	select HAVE_KPROBES
-	select HAVE_KRETPROBES
-	select HAVE_IOREMAP_PROT if MMU && !X2TLB
-	select HAVE_FUNCTION_TRACER
-	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_DYNAMIC_FTRACE
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_ARCH_KGDB
-	select HAVE_HW_BREAKPOINT
-	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
-	select ARCH_HIBERNATION_POSSIBLE if MMU
+	select PERF_USE_VMALLOC
+	select RTC_LIB
 	select SPARSE_IRQ
-	select HAVE_STACKPROTECTOR
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
@@ -123,8 +125,8 @@ config ARCH_HAS_ILOG2_U64
 
 config NO_IOPORT_MAP
 	def_bool !PCI
-	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \
-		   !SH_HP6XX && !SH_SOLUTION_ENGINE
+	depends on !SH_SH4202_MICRODEV && !SH_SHMIN && !SH_HP6XX && \
+		   !SH_SOLUTION_ENGINE
 
 config IO_TRAPPED
 	bool
@@ -136,8 +138,10 @@ config DMA_COHERENT
 	bool
 
 config DMA_NONCOHERENT
-	def_bool !DMA_COHERENT
+	def_bool !NO_DMA && !DMA_COHERENT
+	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_DIRECT_REMAP
 
 config PGTABLE_LEVELS
 	default 3 if X2TLB
@@ -630,7 +634,7 @@ config SMP
 	  Y to "Enhanced Real Time Clock Support", below.
 
 	  See also <file:Documentation/admin-guide/lockup-watchdogs.rst> and the SMP-HOWTO
-	  available at <http://www.tldp.org/docs.html#howto>.
+	  available at <https://www.tldp.org/docs.html#howto>.
 
 	  If you don't know what to do here, say N.
 
@@ -726,7 +730,6 @@ config ZERO_PAGE_OFFSET
 config BOOT_LINK_OFFSET
 	hex
 	default "0x00210000" if SH_SHMIN
-	default "0x00400000" if SH_CAYMAN
 	default "0x00810000" if SH_7780_SOLUTION_ENGINE
 	default "0x009e0000" if SH_TITAN
 	default "0x01800000" if SH_SDK7780
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index da9cf952f33c..2faebfd72eca 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -15,11 +15,7 @@ ifneq ($(SUBARCH),$(ARCH))
   endif
 endif
 
-ifeq ($(ARCH),sh)
 KBUILD_DEFCONFIG	:= shx3_defconfig
-else
-KBUILD_DEFCONFIG	:= cayman_defconfig
-endif
 
 isa-y					:= any
 isa-$(CONFIG_SH_DSP)			:= sh
@@ -143,7 +139,6 @@ machdir-$(CONFIG_SH_SH7763RDP)			+= mach-sh7763rdp
 machdir-$(CONFIG_SH_SH4202_MICRODEV)		+= mach-microdev
 machdir-$(CONFIG_SH_LANDISK)			+= mach-landisk
 machdir-$(CONFIG_SH_LBOX_RE2)			+= mach-lboxre2
-machdir-$(CONFIG_SH_CAYMAN)			+= mach-cayman
 machdir-$(CONFIG_SH_RSK)			+= mach-rsk
 
 ifneq ($(machdir-y),)
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index fb0ca0c1efe1..83bcb6d2daca 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -340,12 +340,6 @@ config SH_MAGIC_PANEL_R2
 	help
 	  Select Magic Panel R2 if configuring for Magic Panel R2.
 
-config SH_CAYMAN
-	bool "Hitachi Cayman"
-	depends on CPU_SUBTYPE_SH5_101 || CPU_SUBTYPE_SH5_103
-	select HAVE_PCI
-	select ARCH_MIGHT_HAVE_PC_SERIO
-
 config SH_POLARIS
 	bool "SMSC Polaris"
 	select CPU_HAS_IPR_IRQ
diff --git a/arch/sh/boards/board-sh2007.c b/arch/sh/boards/board-sh2007.c
index ef9c87deeb08..6ea85e480851 100644
--- a/arch/sh/boards/board-sh2007.c
+++ b/arch/sh/boards/board-sh2007.c
@@ -126,14 +126,14 @@ static void __init sh2007_init_irq(void)
  */
 static void __init sh2007_setup(char **cmdline_p)
 {
-	printk(KERN_INFO "SH-2007 Setup...");
+	pr_info("SH-2007 Setup...");
 
 	/* setup wait control registers for area 5 */
 	__raw_writel(CS5BCR_D, CS5BCR);
 	__raw_writel(CS5WCR_D, CS5WCR);
 	__raw_writel(CS5PCR_D, CS5PCR);
 
-	printk(KERN_INFO " done.\n");
+	pr_cont(" done.\n");
 }
 
 /*
diff --git a/arch/sh/boards/mach-cayman/Makefile b/arch/sh/boards/mach-cayman/Makefile
deleted file mode 100644
index 775a4be57434..000000000000
--- a/arch/sh/boards/mach-cayman/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the Hitachi Cayman specific parts of the kernel
-#
-obj-y := setup.o irq.o panic.o
diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c
deleted file mode 100644
index 0305d0b51730..000000000000
--- a/arch/sh/boards/mach-cayman/irq.c
+++ /dev/null
@@ -1,148 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/sh/mach-cayman/irq.c - SH-5 Cayman Interrupt Support
- *
- * This file handles the board specific parts of the Cayman interrupt system
- *
- * Copyright (C) 2002 Stuart Menefy
- */
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/signal.h>
-#include <cpu/irq.h>
-#include <asm/page.h>
-
-/* Setup for the SMSC FDC37C935 / LAN91C100FD */
-#define SMSC_IRQ         IRQ_IRL1
-
-/* Setup for PCI Bus 2, which transmits interrupts via the EPLD */
-#define PCI2_IRQ         IRQ_IRL3
-
-unsigned long epld_virt;
-
-#define EPLD_BASE        0x04002000
-#define EPLD_STATUS_BASE (epld_virt + 0x10)
-#define EPLD_MASK_BASE   (epld_virt + 0x20)
-
-/* Note the SMSC SuperIO chip and SMSC LAN chip interrupts are all muxed onto
-   the same SH-5 interrupt */
-
-static irqreturn_t cayman_interrupt_smsc(int irq, void *dev_id)
-{
-        printk(KERN_INFO "CAYMAN: spurious SMSC interrupt\n");
-	return IRQ_NONE;
-}
-
-static irqreturn_t cayman_interrupt_pci2(int irq, void *dev_id)
-{
-        printk(KERN_INFO "CAYMAN: spurious PCI interrupt, IRQ %d\n", irq);
-	return IRQ_NONE;
-}
-
-static void enable_cayman_irq(struct irq_data *data)
-{
-	unsigned int irq = data->irq;
-	unsigned long flags;
-	unsigned long mask;
-	unsigned int reg;
-	unsigned char bit;
-
-	irq -= START_EXT_IRQS;
-	reg = EPLD_MASK_BASE + ((irq / 8) << 2);
-	bit = 1<<(irq % 8);
-	local_irq_save(flags);
-	mask = __raw_readl(reg);
-	mask |= bit;
-	__raw_writel(mask, reg);
-	local_irq_restore(flags);
-}
-
-static void disable_cayman_irq(struct irq_data *data)
-{
-	unsigned int irq = data->irq;
-	unsigned long flags;
-	unsigned long mask;
-	unsigned int reg;
-	unsigned char bit;
-
-	irq -= START_EXT_IRQS;
-	reg = EPLD_MASK_BASE + ((irq / 8) << 2);
-	bit = 1<<(irq % 8);
-	local_irq_save(flags);
-	mask = __raw_readl(reg);
-	mask &= ~bit;
-	__raw_writel(mask, reg);
-	local_irq_restore(flags);
-}
-
-struct irq_chip cayman_irq_type = {
-	.name		= "Cayman-IRQ",
-	.irq_unmask	= enable_cayman_irq,
-	.irq_mask	= disable_cayman_irq,
-};
-
-int cayman_irq_demux(int evt)
-{
-	int irq = intc_evt_to_irq[evt];
-
-	if (irq == SMSC_IRQ) {
-		unsigned long status;
-		int i;
-
-		status = __raw_readl(EPLD_STATUS_BASE) &
-			 __raw_readl(EPLD_MASK_BASE) & 0xff;
-		if (status == 0) {
-			irq = -1;
-		} else {
-			for (i=0; i<8; i++) {
-				if (status & (1<<i))
-					break;
-			}
-			irq = START_EXT_IRQS + i;
-		}
-	}
-
-	if (irq == PCI2_IRQ) {
-		unsigned long status;
-		int i;
-
-		status = __raw_readl(EPLD_STATUS_BASE + 3 * sizeof(u32)) &
-			 __raw_readl(EPLD_MASK_BASE + 3 * sizeof(u32)) & 0xff;
-		if (status == 0) {
-			irq = -1;
-		} else {
-			for (i=0; i<8; i++) {
-				if (status & (1<<i))
-					break;
-			}
-			irq = START_EXT_IRQS + (3 * 8) + i;
-		}
-	}
-
-	return irq;
-}
-
-void init_cayman_irq(void)
-{
-	int i;
-
-	epld_virt = (unsigned long)ioremap(EPLD_BASE, 1024);
-	if (!epld_virt) {
-		printk(KERN_ERR "Cayman IRQ: Unable to remap EPLD\n");
-		return;
-	}
-
-	for (i = 0; i < NR_EXT_IRQS; i++) {
-		irq_set_chip_and_handler(START_EXT_IRQS + i,
-					 &cayman_irq_type, handle_level_irq);
-	}
-
-	/* Setup the SMSC interrupt */
-	if (request_irq(SMSC_IRQ, cayman_interrupt_smsc, 0, "Cayman SMSC Mux",
-			NULL))
-		pr_err("Failed to register Cayman SMSC Mux interrupt\n");
-	if (request_irq(PCI2_IRQ, cayman_interrupt_pci2, 0, "Cayman PCI2 Mux",
-			NULL))
-		pr_err("Failed to register Cayman PCI2 Mux interrupt\n");
-}
diff --git a/arch/sh/boards/mach-cayman/panic.c b/arch/sh/boards/mach-cayman/panic.c
deleted file mode 100644
index cfc46314e7d9..000000000000
--- a/arch/sh/boards/mach-cayman/panic.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2003  Richard Curnow, SuperH UK Limited
- */
-
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <cpu/registers.h>
-
-/* THIS IS A PHYSICAL ADDRESS */
-#define HDSP2534_ADDR (0x04002100)
-
-static void poor_mans_delay(void)
-{
-	int i;
-
-	for (i = 0; i < 2500000; i++)
-		cpu_relax();
-}
-
-static void show_value(unsigned long x)
-{
-	int i;
-	unsigned nibble;
-	for (i = 0; i < 8; i++) {
-		nibble = ((x >> (i * 4)) & 0xf);
-
-		__raw_writeb(nibble + ((nibble > 9) ? 55 : 48),
-			  HDSP2534_ADDR + 0xe0 + ((7 - i) << 2));
-	}
-}
-
-void
-panic_handler(unsigned long panicPC, unsigned long panicSSR,
-	      unsigned long panicEXPEVT)
-{
-	while (1) {
-		/* This piece of code displays the PC on the LED display */
-		show_value(panicPC);
-		poor_mans_delay();
-		show_value(panicSSR);
-		poor_mans_delay();
-		show_value(panicEXPEVT);
-		poor_mans_delay();
-	}
-}
diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c
deleted file mode 100644
index 8ef76e288da0..000000000000
--- a/arch/sh/boards/mach-cayman/setup.c
+++ /dev/null
@@ -1,181 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/sh/mach-cayman/setup.c
- *
- * SH5 Cayman support
- *
- * Copyright (C) 2002  David J. Mckay & Benedict Gaster
- * Copyright (C) 2003 - 2007  Paul Mundt
- */
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <cpu/irq.h>
-
-/*
- * Platform Dependent Interrupt Priorities.
- */
-
-/* Using defaults defined in irq.h */
-#define	RES NO_PRIORITY		/* Disabled */
-#define IR0 IRL0_PRIORITY	/* IRLs */
-#define IR1 IRL1_PRIORITY
-#define IR2 IRL2_PRIORITY
-#define IR3 IRL3_PRIORITY
-#define PCA INTA_PRIORITY	/* PCI Ints */
-#define PCB INTB_PRIORITY
-#define PCC INTC_PRIORITY
-#define PCD INTD_PRIORITY
-#define SER TOP_PRIORITY
-#define ERR TOP_PRIORITY
-#define PW0 TOP_PRIORITY
-#define PW1 TOP_PRIORITY
-#define PW2 TOP_PRIORITY
-#define PW3 TOP_PRIORITY
-#define DM0 NO_PRIORITY		/* DMA Ints */
-#define DM1 NO_PRIORITY
-#define DM2 NO_PRIORITY
-#define DM3 NO_PRIORITY
-#define DAE NO_PRIORITY
-#define TU0 TIMER_PRIORITY	/* TMU Ints */
-#define TU1 NO_PRIORITY
-#define TU2 NO_PRIORITY
-#define TI2 NO_PRIORITY
-#define ATI NO_PRIORITY		/* RTC Ints */
-#define PRI NO_PRIORITY
-#define CUI RTC_PRIORITY
-#define ERI SCIF_PRIORITY	/* SCIF Ints */
-#define RXI SCIF_PRIORITY
-#define BRI SCIF_PRIORITY
-#define TXI SCIF_PRIORITY
-#define ITI TOP_PRIORITY	/* WDT Ints */
-
-/* Setup for the SMSC FDC37C935 */
-#define SMSC_SUPERIO_BASE	0x04000000
-#define SMSC_CONFIG_PORT_ADDR	0x3f0
-#define SMSC_INDEX_PORT_ADDR	SMSC_CONFIG_PORT_ADDR
-#define SMSC_DATA_PORT_ADDR	0x3f1
-
-#define SMSC_ENTER_CONFIG_KEY	0x55
-#define SMSC_EXIT_CONFIG_KEY	0xaa
-
-#define SMCS_LOGICAL_DEV_INDEX	0x07
-#define SMSC_DEVICE_ID_INDEX	0x20
-#define SMSC_DEVICE_REV_INDEX	0x21
-#define SMSC_ACTIVATE_INDEX	0x30
-#define SMSC_PRIMARY_BASE_INDEX  0x60
-#define SMSC_SECONDARY_BASE_INDEX 0x62
-#define SMSC_PRIMARY_INT_INDEX	0x70
-#define SMSC_SECONDARY_INT_INDEX 0x72
-
-#define SMSC_IDE1_DEVICE	1
-#define SMSC_KEYBOARD_DEVICE	7
-#define SMSC_CONFIG_REGISTERS	8
-
-#define SMSC_SUPERIO_READ_INDEXED(index) ({ \
-	outb((index), SMSC_INDEX_PORT_ADDR); \
-	inb(SMSC_DATA_PORT_ADDR); })
-#define SMSC_SUPERIO_WRITE_INDEXED(val, index) ({ \
-	outb((index), SMSC_INDEX_PORT_ADDR); \
-	outb((val),   SMSC_DATA_PORT_ADDR); })
-
-#define IDE1_PRIMARY_BASE	0x01f0
-#define IDE1_SECONDARY_BASE	0x03f6
-
-unsigned long smsc_superio_virt;
-
-int platform_int_priority[NR_INTC_IRQS] = {
-	IR0, IR1, IR2, IR3, PCA, PCB, PCC, PCD,	/* IRQ  0- 7 */
-	RES, RES, RES, RES, SER, ERR, PW3, PW2,	/* IRQ  8-15 */
-	PW1, PW0, DM0, DM1, DM2, DM3, DAE, RES,	/* IRQ 16-23 */
-	RES, RES, RES, RES, RES, RES, RES, RES,	/* IRQ 24-31 */
-	TU0, TU1, TU2, TI2, ATI, PRI, CUI, ERI,	/* IRQ 32-39 */
-	RXI, BRI, TXI, RES, RES, RES, RES, RES,	/* IRQ 40-47 */
-	RES, RES, RES, RES, RES, RES, RES, RES,	/* IRQ 48-55 */
-	RES, RES, RES, RES, RES, RES, RES, ITI,	/* IRQ 56-63 */
-};
-
-static int __init smsc_superio_setup(void)
-{
-	unsigned char devid, devrev;
-
-	smsc_superio_virt = (unsigned long)ioremap(SMSC_SUPERIO_BASE, 1024);
-	if (!smsc_superio_virt) {
-		panic("Unable to remap SMSC SuperIO\n");
-	}
-
-	/* Initially the chip is in run state */
-	/* Put it into configuration state */
-	outb(SMSC_ENTER_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
-	outb(SMSC_ENTER_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
-
-	/* Read device ID info */
-	devid = SMSC_SUPERIO_READ_INDEXED(SMSC_DEVICE_ID_INDEX);
-	devrev = SMSC_SUPERIO_READ_INDEXED(SMSC_DEVICE_REV_INDEX);
-	printk("SMSC SuperIO devid %02x rev %02x\n", devid, devrev);
-
-	/* Select the keyboard device */
-	SMSC_SUPERIO_WRITE_INDEXED(SMSC_KEYBOARD_DEVICE, SMCS_LOGICAL_DEV_INDEX);
-
-	/* enable it */
-	SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_ACTIVATE_INDEX);
-
-	/* Select the interrupts */
-	/* On a PC keyboard is IRQ1, mouse is IRQ12 */
-	SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX);
-	SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX);
-
-	/*
-	 * Only IDE1 exists on the Cayman
-	 */
-
-	/* Power it on */
-	SMSC_SUPERIO_WRITE_INDEXED(1 << SMSC_IDE1_DEVICE, 0x22);
-
-	SMSC_SUPERIO_WRITE_INDEXED(SMSC_IDE1_DEVICE, SMCS_LOGICAL_DEV_INDEX);
-	SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_ACTIVATE_INDEX);
-
-	SMSC_SUPERIO_WRITE_INDEXED(IDE1_PRIMARY_BASE >> 8,
-				   SMSC_PRIMARY_BASE_INDEX + 0);
-	SMSC_SUPERIO_WRITE_INDEXED(IDE1_PRIMARY_BASE & 0xff,
-				   SMSC_PRIMARY_BASE_INDEX + 1);
-
-	SMSC_SUPERIO_WRITE_INDEXED(IDE1_SECONDARY_BASE >> 8,
-				   SMSC_SECONDARY_BASE_INDEX + 0);
-	SMSC_SUPERIO_WRITE_INDEXED(IDE1_SECONDARY_BASE & 0xff,
-				   SMSC_SECONDARY_BASE_INDEX + 1);
-
-	SMSC_SUPERIO_WRITE_INDEXED(14, SMSC_PRIMARY_INT_INDEX);
-
-	SMSC_SUPERIO_WRITE_INDEXED(SMSC_CONFIG_REGISTERS,
-				   SMCS_LOGICAL_DEV_INDEX);
-
-	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc2); /* GP42 = nIDE1_OE */
-	SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */
-	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */
-	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */
-
-	/* Exit the configuration state */
-	outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
-
-	return 0;
-}
-device_initcall(smsc_superio_setup);
-
-static void __iomem *cayman_ioport_map(unsigned long port, unsigned int len)
-{
-	if (port < 0x400) {
-		extern unsigned long smsc_superio_virt;
-		return (void __iomem *)((port << 2) | smsc_superio_virt);
-	}
-
-	return (void __iomem *)port;
-}
-
-extern void init_cayman_irq(void);
-
-static struct sh_machine_vector mv_cayman __initmv = {
-	.mv_name		= "Hitachi Cayman",
-	.mv_ioport_map		= cayman_ioport_map,
-	.mv_init_irq		= init_cayman_irq,
-};
diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c
index 16b4d8b0bb85..2c44b94f82fb 100644
--- a/arch/sh/boards/mach-landisk/setup.c
+++ b/arch/sh/boards/mach-landisk/setup.c
@@ -82,6 +82,9 @@ device_initcall(landisk_devices_setup);
 
 static void __init landisk_setup(char **cmdline_p)
 {
+	/* I/O port identity mapping */
+	__set_io_port_base(0);
+
 	/* LED ON */
 	__raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED);
 
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index ad0e2403e56f..589d2d8a573d 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -28,10 +28,7 @@ IMAGE_OFFSET	:= $(shell /bin/bash -c 'printf "0x%08x" \
 			$(CONFIG_BOOT_LINK_OFFSET)]')
 endif
 
-ifeq ($(CONFIG_MCOUNT),y)
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
-endif
+ccflags-remove-$(CONFIG_MCOUNT) += -pg
 
 LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
 		   -T $(obj)/../../kernel/vmlinux.lds
diff --git a/arch/sh/configs/cayman_defconfig b/arch/sh/configs/cayman_defconfig
deleted file mode 100644
index 911437c163c7..000000000000
--- a/arch/sh/configs/cayman_defconfig
+++ /dev/null
@@ -1,66 +0,0 @@
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_FORCE_MAX_ZONEORDER=11
-CONFIG_MEMORY_START=0x80000000
-CONFIG_MEMORY_SIZE=0x00400000
-CONFIG_FLATMEM_MANUAL=y
-CONFIG_CACHE_OFF=y
-CONFIG_SH_PCLK_FREQ=50000000
-CONFIG_HEARTBEAT=y
-CONFIG_PREEMPT=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-# CONFIG_IPV6 is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_SCSI_SPI_ATTRS=y
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_HW_RANDOM=y
-CONFIG_I2C=m
-CONFIG_WATCHDOG=y
-CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_SH_MOBILE_LCDC=m
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x16=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-# CONFIG_LOGO_SUPERH_MONO is not set
-# CONFIG_LOGO_SUPERH_VGA16 is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_MINIX_FS=y
-CONFIG_ROMFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_SCHEDSTATS=y
-CONFIG_FRAME_POINTER=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/sh/configs/dreamcast_defconfig b/arch/sh/configs/dreamcast_defconfig
index ae067e0b15e3..6a82c7b8ff32 100644
--- a/arch/sh/configs/dreamcast_defconfig
+++ b/arch/sh/configs/dreamcast_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index a5b865a75d22..9a988c347e9d 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
 CONFIG_IPC_NS=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index a92db6694ce2..70e6605d7f7e 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -3,7 +3,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH7709=y
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index 567af752b1bb..ba6ec042606f 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 10f6d371ce2c..05e4ac6fed5f 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig
index ed84d1303acf..c65667d00313 100644
--- a/arch/sh/configs/microdev_defconfig
+++ b/arch/sh/configs/microdev_defconfig
@@ -2,7 +2,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH4_202=y
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index 37e9521a99e5..a24cf8cd2cea 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -4,7 +4,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index c97ec60cff27..e922659fdadb 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 CONFIG_SLAB=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index 55fce65eb454..5978866358ec 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -7,7 +7,6 @@ CONFIG_RCU_TRACE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index 6a3cfe08295f..fc9c22152b08 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index 2b3d7d280672..ff3fd6787fd6 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 21a43f14ffac..ff5bb4489922 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -18,7 +18,6 @@ CONFIG_USER_NS=y
 CONFIG_PID_NS=y
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_ELF_CORE is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index 4e794e719a28..5d6c19338ebf 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -2,7 +2,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
diff --git a/arch/sh/configs/se7619_defconfig b/arch/sh/configs/se7619_defconfig
index 3264415a5931..71a672c30716 100644
--- a/arch/sh/configs/se7619_defconfig
+++ b/arch/sh/configs/se7619_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 # CONFIG_ELF_CORE is not set
diff --git a/arch/sh/configs/se7705_defconfig b/arch/sh/configs/se7705_defconfig
index 4496b94b7d88..ed00a6eeadf5 100644
--- a/arch/sh/configs/se7705_defconfig
+++ b/arch/sh/configs/se7705_defconfig
@@ -2,7 +2,6 @@
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig
index b23f67542728..3f1c13799d79 100644
--- a/arch/sh/configs/se7750_defconfig
+++ b/arch/sh/configs/se7750_defconfig
@@ -5,7 +5,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig
index 162343683937..4a024065bb75 100644
--- a/arch/sh/configs/se7751_defconfig
+++ b/arch/sh/configs/se7751_defconfig
@@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/secureedge5410_defconfig b/arch/sh/configs/secureedge5410_defconfig
index 360592d63a2f..8422599cfb04 100644
--- a/arch/sh/configs/secureedge5410_defconfig
+++ b/arch/sh/configs/secureedge5410_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 87db9a84b5ec..f0073ed39947 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -3,7 +3,6 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=m
diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig
index 08426913c0e3..0d814770b07f 100644
--- a/arch/sh/configs/sh7710voipgw_defconfig
+++ b/arch/sh/configs/sh7710voipgw_defconfig
@@ -2,7 +2,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SHMEM is not set
diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig
index d0933a9b9799..a2700ab165af 100644
--- a/arch/sh/configs/sh7757lcr_defconfig
+++ b/arch/sh/configs/sh7757lcr_defconfig
@@ -8,7 +8,6 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS_ALL=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index d0a0aa74cecf..26c5fd02c87a 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
 CONFIG_IPC_NS=y
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig
index a27b129b93c5..c0b6f40d01cc 100644
--- a/arch/sh/configs/shmin_defconfig
+++ b/arch/sh/configs/shmin_defconfig
@@ -1,7 +1,6 @@
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_HOTPLUG is not set
 # CONFIG_BUG is not set
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 4ec961ace688..ba887f1351be 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -6,7 +6,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/arch/sh/drivers/pci/Makefile b/arch/sh/drivers/pci/Makefile
index a5c1e9066f83..d313fd3ce709 100644
--- a/arch/sh/drivers/pci/Makefile
+++ b/arch/sh/drivers/pci/Makefile
@@ -25,4 +25,3 @@ obj-$(CONFIG_SH_7780_SOLUTION_ENGINE)	+= fixups-sdk7780.o
 obj-$(CONFIG_SH_TITAN)			+= fixups-titan.o
 obj-$(CONFIG_SH_LANDISK)		+= fixups-landisk.o
 obj-$(CONFIG_SH_LBOX_RE2)		+= fixups-rts7751r2d.o
-obj-$(CONFIG_SH_CAYMAN)			+= fixups-cayman.o
diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c
index fe163ecd0719..2fd2b77e12ce 100644
--- a/arch/sh/drivers/pci/common.c
+++ b/arch/sh/drivers/pci/common.c
@@ -54,7 +54,7 @@ int __init pci_is_66mhz_capable(struct pci_channel *hose,
 	int cap66 = -1;
 	u16 stat;
 
-	printk(KERN_INFO "PCI: Checking 66MHz capabilities...\n");
+	pr_info("PCI: Checking 66MHz capabilities...\n");
 
 	for (pci_devfn = 0; pci_devfn < 0xff; pci_devfn++) {
 		if (PCI_FUNC(pci_devfn))
@@ -134,7 +134,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr,
 		pcibios_report_status(PCI_STATUS_REC_TARGET_ABORT |
 				      PCI_STATUS_SIG_TARGET_ABORT |
 				      PCI_STATUS_REC_MASTER_ABORT, 1);
-		printk("\n");
+		pr_cont("\n");
 
 		cmd |= PCI_STATUS_REC_TARGET_ABORT;
 	}
@@ -143,7 +143,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr,
 		printk(KERN_DEBUG "PCI: parity error detected: ");
 		pcibios_report_status(PCI_STATUS_PARITY |
 				      PCI_STATUS_DETECTED_PARITY, 1);
-		printk("\n");
+		pr_cont("\n");
 
 		cmd |= PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY;
 
diff --git a/arch/sh/drivers/pci/fixups-cayman.c b/arch/sh/drivers/pci/fixups-cayman.c
deleted file mode 100644
index c797bfbe2e98..000000000000
--- a/arch/sh/drivers/pci/fixups-cayman.c
+++ /dev/null
@@ -1,78 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/types.h>
-#include <cpu/irq.h>
-#include "pci-sh5.h"
-
-int pcibios_map_platform_irq(const struct pci_dev *dev, u8 slot, u8 pin)
-{
-	int result = -1;
-
-	/* The complication here is that the PCI IRQ lines from the Cayman's 2
-	   5V slots get into the CPU via a different path from the IRQ lines
-	   from the 3 3.3V slots.  Thus, we have to detect whether the card's
-	   interrupts go via the 5V or 3.3V path, i.e. the 'bridge swizzling'
-	   at the point where we cross from 5V to 3.3V is not the normal case.
-
-	   The added complication is that we don't know that the 5V slots are
-	   always bus 2, because a card containing a PCI-PCI bridge may be
-	   plugged into a 3.3V slot, and this changes the bus numbering.
-
-	   Also, the Cayman has an intermediate PCI bus that goes a custom
-	   expansion board header (and to the secondary bridge).  This bus has
-	   never been used in practice.
-
-	   The 1ary onboard PCI-PCI bridge is device 3 on bus 0
-	   The 2ary onboard PCI-PCI bridge is device 0 on the 2ary bus of
-	   the 1ary bridge.
-	   */
-
-	struct slot_pin {
-		int slot;
-		int pin;
-	} path[4];
-	int i=0;
-
-	while (dev->bus->number > 0) {
-
-		slot = path[i].slot = PCI_SLOT(dev->devfn);
-		pin = path[i].pin = pci_swizzle_interrupt_pin(dev, pin);
-		dev = dev->bus->self;
-		i++;
-		if (i > 3) panic("PCI path to root bus too long!\n");
-	}
-
-	slot = PCI_SLOT(dev->devfn);
-	/* This is the slot on bus 0 through which the device is eventually
-	   reachable. */
-
-	/* Now work back up. */
-	if ((slot < 3) || (i == 0)) {
-		/* Bus 0 (incl. PCI-PCI bridge itself) : perform the final
-		   swizzle now. */
-		result = IRQ_INTA + pci_swizzle_interrupt_pin(dev, pin) - 1;
-	} else {
-		i--;
-		slot = path[i].slot;
-		pin  = path[i].pin;
-		if (slot > 0) {
-			panic("PCI expansion bus device found - not handled!\n");
-		} else {
-			if (i > 0) {
-				/* 5V slots */
-				i--;
-				slot = path[i].slot;
-				pin  = path[i].pin;
-				/* 'pin' was swizzled earlier wrt slot, don't do it again. */
-				result = IRQ_P2INTA + (pin - 1);
-			} else {
-				/* IRQ for 2ary PCI-PCI bridge : unused */
-				result = -1;
-			}
-		}
-	}
-
-	return result;
-}
diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c
index 287b3a68570c..9a624a6ee354 100644
--- a/arch/sh/drivers/pci/pci-sh7780.c
+++ b/arch/sh/drivers/pci/pci-sh7780.c
@@ -148,7 +148,7 @@ static irqreturn_t sh7780_pci_serr_irq(int irq, void *dev_id)
 
 	printk(KERN_DEBUG "PCI: system error received: ");
 	pcibios_report_status(PCI_STATUS_SIG_SYSTEM_ERROR, 1);
-	printk("\n");
+	pr_cont("\n");
 
 	/* Deassert SERR */
 	__raw_writel(SH4_PCIINTM_SDIM, hose->reg_base + SH4_PCIINTM);
@@ -179,7 +179,7 @@ static int __init sh7780_pci_setup_irqs(struct pci_channel *hose)
 	ret = request_irq(hose->serr_irq, sh7780_pci_serr_irq, 0,
 			  "PCI SERR interrupt", hose);
 	if (unlikely(ret)) {
-		printk(KERN_ERR "PCI: Failed hooking SERR IRQ\n");
+		pr_err("PCI: Failed hooking SERR IRQ\n");
 		return ret;
 	}
 
@@ -250,7 +250,7 @@ static int __init sh7780_pci_init(void)
 	const char *type;
 	int ret, i;
 
-	printk(KERN_NOTICE "PCI: Starting initialization.\n");
+	pr_notice("PCI: Starting initialization.\n");
 
 	chan->reg_base = 0xfe040000;
 
@@ -270,7 +270,7 @@ static int __init sh7780_pci_init(void)
 
 	id = __raw_readw(chan->reg_base + PCI_VENDOR_ID);
 	if (id != PCI_VENDOR_ID_RENESAS) {
-		printk(KERN_ERR "PCI: Unknown vendor ID 0x%04x.\n", id);
+		pr_err("PCI: Unknown vendor ID 0x%04x.\n", id);
 		return -ENODEV;
 	}
 
@@ -281,14 +281,13 @@ static int __init sh7780_pci_init(void)
 	       (id == PCI_DEVICE_ID_RENESAS_SH7785) ? "SH7785" :
 					  NULL;
 	if (unlikely(!type)) {
-		printk(KERN_ERR "PCI: Found an unsupported Renesas host "
-		       "controller, device id 0x%04x.\n", id);
+		pr_err("PCI: Found an unsupported Renesas host controller, device id 0x%04x.\n",
+		       id);
 		return -EINVAL;
 	}
 
-	printk(KERN_NOTICE "PCI: Found a Renesas %s host "
-	       "controller, revision %d.\n", type,
-	       __raw_readb(chan->reg_base + PCI_REVISION_ID));
+	pr_notice("PCI: Found a Renesas %s host controller, revision %d.\n",
+		  type, __raw_readb(chan->reg_base + PCI_REVISION_ID));
 
 	/*
 	 * Now throw it in to register initialization mode and
@@ -395,9 +394,9 @@ static int __init sh7780_pci_init(void)
 
 	sh7780_pci66_init(chan);
 
-	printk(KERN_NOTICE "PCI: Running at %dMHz.\n",
-	       (__raw_readw(chan->reg_base + PCI_STATUS) & PCI_STATUS_66MHZ) ?
-	       66 : 33);
+	pr_notice("PCI: Running at %dMHz.\n",
+		  (__raw_readw(chan->reg_base + PCI_STATUS) & PCI_STATUS_66MHZ)
+		  ? 66 : 33);
 
 	return 0;
 
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index c7784e156964..6ab0b7377f66 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -120,8 +120,7 @@ int register_pci_controller(struct pci_channel *hose)
 	 * Do not panic here but later - this might happen before console init.
 	 */
 	if (!hose->io_map_base) {
-		printk(KERN_WARNING
-		       "registering PCI controller with io_map_base unset\n");
+		pr_warn("registering PCI controller with io_map_base unset\n");
 	}
 
 	/*
@@ -145,7 +144,7 @@ out:
 	for (--i; i >= 0; i--)
 		release_resource(&hose->resources[i]);
 
-	printk(KERN_WARNING "Skipping PCI bus scan due to resource conflict\n");
+	pr_warn("Skipping PCI bus scan due to resource conflict\n");
 	return -1;
 }
 
@@ -213,8 +212,8 @@ pcibios_bus_report_status_early(struct pci_channel *hose,
 					pci_devfn, PCI_STATUS,
 					status & status_mask);
 		if (warn)
-			printk("(%02x:%02x: %04X) ", current_bus,
-			       pci_devfn, status);
+			pr_cont("(%02x:%02x: %04X) ", current_bus, pci_devfn,
+				status);
 	}
 }
 
@@ -249,7 +248,7 @@ pcibios_bus_report_status(struct pci_bus *bus, unsigned int status_mask,
 		pci_write_config_word(dev, PCI_STATUS, status & status_mask);
 
 		if (warn)
-			printk("(%s: %04X) ", pci_name(dev), status);
+			pr_cont("(%s: %04X) ", pci_name(dev), status);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list)
diff --git a/arch/sh/include/asm/adc.h b/arch/sh/include/asm/adc.h
index 99ec66849559..feccfe639e38 100644
--- a/arch/sh/include/asm/adc.h
+++ b/arch/sh/include/asm/adc.h
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_ADC_H
 #define __ASM_ADC_H
-#ifdef __KERNEL__
 /*
  * Copyright (C) 2004  Andriy Skulysh
  */
@@ -10,5 +9,4 @@
 
 int adc_single(unsigned int channel);
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_ADC_H */
diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
index 34bfbcddcce0..468fba333e89 100644
--- a/arch/sh/include/asm/addrspace.h
+++ b/arch/sh/include/asm/addrspace.h
@@ -7,8 +7,6 @@
 #ifndef __ASM_SH_ADDRSPACE_H
 #define __ASM_SH_ADDRSPACE_H
 
-#ifdef __KERNEL__
-
 #include <cpu/addrspace.h>
 
 /* If this CPU supports segmentation, hook up the helpers */
@@ -62,5 +60,4 @@
 #define P3_ADDR_MAX		P4SEG
 #endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_ADDRSPACE_H */
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index 445dd14c448a..450b5854d7c6 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_BITOPS_H
 #define __ASM_SH_BITOPS_H
 
-#ifdef __KERNEL__
-
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
@@ -71,6 +69,4 @@ static inline unsigned long __ffs(unsigned long word)
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_SH_BITOPS_H */
diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h
index 2408ac4873aa..a293343456af 100644
--- a/arch/sh/include/asm/cache.h
+++ b/arch/sh/include/asm/cache.h
@@ -8,7 +8,6 @@
  */
 #ifndef __ASM_SH_CACHE_H
 #define __ASM_SH_CACHE_H
-#ifdef __KERNEL__
 
 #include <linux/init.h>
 #include <cpu/cache.h>
@@ -44,5 +43,4 @@ struct cache_info {
 	unsigned long flags;
 };
 #endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHE_H */
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index fe7400079b97..4486a865ff62 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_CACHEFLUSH_H
 #define __ASM_SH_CACHEFLUSH_H
 
-#ifdef __KERNEL__
-
 #include <linux/mm.h>
 
 /*
@@ -109,5 +107,4 @@ static inline void *sh_cacheop_vaddr(void *vaddr)
 	return vaddr;
 }
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/include/asm/dma.h b/arch/sh/include/asm/dma.h
index 4d5a21a891c0..17d23ae98c77 100644
--- a/arch/sh/include/asm/dma.h
+++ b/arch/sh/include/asm/dma.h
@@ -6,7 +6,6 @@
  */
 #ifndef __ASM_SH_DMA_H
 #define __ASM_SH_DMA_H
-#ifdef __KERNEL__
 
 #include <linux/spinlock.h>
 #include <linux/wait.h>
@@ -144,5 +143,4 @@ extern int isa_dma_bridge_buggy;
 #define isa_dma_bridge_buggy	(0)
 #endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_DMA_H */
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index 7661fb5d548a..2862d6d1cb64 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -90,7 +90,6 @@ typedef struct user_fpu_struct elf_fpregset_t;
 #endif
 #define ELF_ARCH	EM_SH
 
-#ifdef __KERNEL__
 /*
  * This is used to ensure we don't load something for the wrong architecture.
  */
@@ -209,5 +208,4 @@ do {								\
 	NEW_AUX_ENT(AT_L2_CACHESHAPE, l2_cache_shape);		\
 } while (0)
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_ELF_H */
diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h
index 43cfaf929aa7..04584be8986c 100644
--- a/arch/sh/include/asm/fpu.h
+++ b/arch/sh/include/asm/fpu.h
@@ -37,11 +37,6 @@ struct user_regset;
 extern int do_fpu_inst(unsigned short, struct pt_regs *);
 extern int init_fpu(struct task_struct *);
 
-extern int fpregs_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf);
-
 static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
 {
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
diff --git a/arch/sh/include/asm/freq.h b/arch/sh/include/asm/freq.h
index 18133bf83738..87c23621b7ae 100644
--- a/arch/sh/include/asm/freq.h
+++ b/arch/sh/include/asm/freq.h
@@ -6,9 +6,7 @@
  */
 #ifndef __ASM_SH_FREQ_H
 #define __ASM_SH_FREQ_H
-#ifdef __KERNEL__
 
 #include <cpu/freq.h>
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_FREQ_H */
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index b39cda09fb95..b70f3fce6ed7 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_FUTEX_H
 #define __ASM_SH_FUTEX_H
 
-#ifdef __KERNEL__
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
@@ -71,5 +69,4 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval,
 	return ret;
 }
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_FUTEX_H */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 26f0f9b4658b..6d5c6463bc07 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -17,13 +17,12 @@
 #include <asm/cache.h>
 #include <asm/addrspace.h>
 #include <asm/machvec.h>
+#include <asm/page.h>
 #include <linux/pgtable.h>
 #include <asm-generic/iomap.h>
 
-#ifdef __KERNEL__
 #define __IO_PREFIX     generic
 #include <asm/io_generic.h>
-#include <asm/io_trapped.h>
 #include <asm-generic/pci_iomap.h>
 #include <mach/mangle-port.h>
 
@@ -243,125 +242,38 @@ unsigned long long poke_real_address_q(unsigned long long addr,
 #define phys_to_virt(address)	(__va(address))
 #endif
 
-/*
- * On 32-bit SH, we traditionally have the whole physical address space
- * mapped at all times (as MIPS does), so "ioremap()" and "iounmap()" do
- * not need to do anything but place the address in the proper segment.
- * This is true for P1 and P2 addresses, as well as some P3 ones.
- * However, most of the P3 addresses and newer cores using extended
- * addressing need to map through page tables, so the ioremap()
- * implementation becomes a bit more complicated.
- *
- * See arch/sh/mm/ioremap.c for additional notes on this.
- *
- * We cheat a bit and always return uncachable areas until we've fixed
- * the drivers to handle caching properly.
- *
- * On the SH-5 the concept of segmentation in the 1:1 PXSEG sense simply
- * doesn't exist, so everything must go through page tables.
- */
 #ifdef CONFIG_MMU
+void iounmap(void __iomem *addr);
 void __iomem *__ioremap_caller(phys_addr_t offset, unsigned long size,
 			       pgprot_t prot, void *caller);
-void iounmap(void __iomem *addr);
-
-static inline void __iomem *
-__ioremap(phys_addr_t offset, unsigned long size, pgprot_t prot)
-{
-	return __ioremap_caller(offset, size, prot, __builtin_return_address(0));
-}
-
-static inline void __iomem *
-__ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
-{
-#ifdef CONFIG_29BIT
-	phys_addr_t last_addr = offset + size - 1;
-
-	/*
-	 * For P1 and P2 space this is trivial, as everything is already
-	 * mapped. Uncached access for P1 addresses are done through P2.
-	 * In the P3 case or for addresses outside of the 29-bit space,
-	 * mapping must be done by the PMB or by using page tables.
-	 */
-	if (likely(PXSEG(offset) < P3SEG && PXSEG(last_addr) < P3SEG)) {
-		u64 flags = pgprot_val(prot);
-
-		/*
-		 * Anything using the legacy PTEA space attributes needs
-		 * to be kicked down to page table mappings.
-		 */
-		if (unlikely(flags & _PAGE_PCC_MASK))
-			return NULL;
-		if (unlikely(flags & _PAGE_CACHABLE))
-			return (void __iomem *)P1SEGADDR(offset);
-
-		return (void __iomem *)P2SEGADDR(offset);
-	}
-
-	/* P4 above the store queues are always mapped. */
-	if (unlikely(offset >= P3_ADDR_MAX))
-		return (void __iomem *)P4SEGADDR(offset);
-#endif
-
-	return NULL;
-}
-
-static inline void __iomem *
-__ioremap_mode(phys_addr_t offset, unsigned long size, pgprot_t prot)
-{
-	void __iomem *ret;
-
-	ret = __ioremap_trapped(offset, size);
-	if (ret)
-		return ret;
-
-	ret = __ioremap_29bit(offset, size, prot);
-	if (ret)
-		return ret;
-
-	return __ioremap(offset, size, prot);
-}
-#else
-#define __ioremap(offset, size, prot)		((void __iomem *)(offset))
-#define __ioremap_mode(offset, size, prot)	((void __iomem *)(offset))
-static inline void iounmap(void __iomem *addr) {}
-#endif /* CONFIG_MMU */
 
 static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size)
 {
-	return __ioremap_mode(offset, size, PAGE_KERNEL_NOCACHE);
+	return __ioremap_caller(offset, size, PAGE_KERNEL_NOCACHE,
+			__builtin_return_address(0));
 }
 
 static inline void __iomem *
 ioremap_cache(phys_addr_t offset, unsigned long size)
 {
-	return __ioremap_mode(offset, size, PAGE_KERNEL);
+	return __ioremap_caller(offset, size, PAGE_KERNEL,
+			__builtin_return_address(0));
 }
 #define ioremap_cache ioremap_cache
 
 #ifdef CONFIG_HAVE_IOREMAP_PROT
-static inline void __iomem *
-ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags)
+static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
+		unsigned long flags)
 {
-	return __ioremap_mode(offset, size, __pgprot(flags));
+	return __ioremap_caller(offset, size, __pgprot(flags),
+			__builtin_return_address(0));
 }
-#endif
+#endif /* CONFIG_HAVE_IOREMAP_PROT */
 
-#ifdef CONFIG_IOREMAP_FIXED
-extern void __iomem *ioremap_fixed(phys_addr_t, unsigned long, pgprot_t);
-extern int iounmap_fixed(void __iomem *);
-extern void ioremap_fixed_init(void);
-#else
-static inline void __iomem *
-ioremap_fixed(phys_addr_t phys_addr, unsigned long size, pgprot_t prot)
-{
-	BUG();
-	return NULL;
-}
-
-static inline void ioremap_fixed_init(void) { }
-static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
-#endif
+#else /* CONFIG_MMU */
+#define iounmap(addr)		do { } while (0)
+#define ioremap(offset, size)	((void __iomem *)(unsigned long)(offset))
+#endif /* CONFIG_MMU */
 
 #define ioremap_uc	ioremap
 
@@ -380,6 +292,4 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
 int valid_phys_addr_range(phys_addr_t addr, size_t size);
 int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
 
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_SH_IO_H */
diff --git a/arch/sh/include/asm/kdebug.h b/arch/sh/include/asm/kdebug.h
index 960545306afa..de8693fabb1d 100644
--- a/arch/sh/include/asm/kdebug.h
+++ b/arch/sh/include/asm/kdebug.h
@@ -12,8 +12,7 @@ enum die_val {
 };
 
 /* arch/sh/kernel/dumpstack.c */
-extern void printk_address(unsigned long address, int reliable,
-			   const char *loglvl);
+extern void printk_address(unsigned long address, int reliable);
 extern void dump_mem(const char *str, const char *loglvl,
 		     unsigned long bottom, unsigned long top);
 
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index 48e67d544d53..f664e51e8a15 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -8,7 +8,6 @@
 #ifndef __ASM_SH_MMU_CONTEXT_H
 #define __ASM_SH_MMU_CONTEXT_H
 
-#ifdef __KERNEL__
 #include <cpu/mmu_context.h>
 #include <asm/tlbflush.h>
 #include <linux/uaccess.h>
@@ -177,5 +176,4 @@ static inline void disable_mmu(void)
 #define disable_mmu()	do { } while (0)
 #endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_MMU_CONTEXT_H */
diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h
index cbaee1d1b673..6552a088dc97 100644
--- a/arch/sh/include/asm/mmzone.h
+++ b/arch/sh/include/asm/mmzone.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_MMZONE_H
 #define __ASM_SH_MMZONE_H
 
-#ifdef __KERNEL__
-
 #ifdef CONFIG_NEED_MULTIPLE_NODES
 #include <linux/numa.h>
 
@@ -44,5 +42,4 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 /* arch/sh/mm/init.c */
 void __init allocate_pgdat(unsigned int nid);
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_MMZONE_H */
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 10a36b1cf2ea..ad22e88c6657 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_PCI_H
 #define __ASM_SH_PCI_H
 
-#ifdef __KERNEL__
-
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
@@ -96,6 +94,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? 15 : 14;
 }
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_PCI_H */
-
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index d44409413418..aa92cc933889 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -8,7 +8,6 @@
 
 #ifndef __ASM_SH_PROCESSOR_32_H
 #define __ASM_SH_PROCESSOR_32_H
-#ifdef __KERNEL__
 
 #include <linux/compiler.h>
 #include <linux/linkage.h>
@@ -203,5 +202,4 @@ static inline void prefetchw(const void *x)
 }
 #endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_PROCESSOR_32_H */
diff --git a/arch/sh/include/asm/segment.h b/arch/sh/include/asm/segment.h
index 33d1d28057cb..02e54a3335d6 100644
--- a/arch/sh/include/asm/segment.h
+++ b/arch/sh/include/asm/segment.h
@@ -24,8 +24,7 @@ typedef struct {
 #define USER_DS		KERNEL_DS
 #endif
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define get_fs()	(current_thread_info()->addr_limit)
 #define set_fs(x)	(current_thread_info()->addr_limit = (x))
diff --git a/arch/sh/include/asm/smc37c93x.h b/arch/sh/include/asm/smc37c93x.h
index f054c30a171a..891f2f8f2fd0 100644
--- a/arch/sh/include/asm/smc37c93x.h
+++ b/arch/sh/include/asm/smc37c93x.h
@@ -112,8 +112,8 @@ typedef struct uart_reg {
 #define FCR_RFRES	0x0200	/* Receiver FIFO reset */
 #define FCR_TFRES	0x0400	/* Transmitter FIFO reset */
 #define FCR_DMA		0x0800	/* DMA mode select */
-#define FCR_RTL		0x4000	/* Receiver triger (LSB) */
-#define FCR_RTM		0x8000	/* Receiver triger (MSB) */
+#define FCR_RTL		0x4000	/* Receiver trigger (LSB) */
+#define FCR_RTM		0x8000	/* Receiver trigger (MSB) */
 
 /* Line Control Register */
 
diff --git a/arch/sh/include/asm/sparsemem.h b/arch/sh/include/asm/sparsemem.h
index 4eb899751e45..4703cbe23844 100644
--- a/arch/sh/include/asm/sparsemem.h
+++ b/arch/sh/include/asm/sparsemem.h
@@ -2,16 +2,11 @@
 #ifndef __ASM_SH_SPARSEMEM_H
 #define __ASM_SH_SPARSEMEM_H
 
-#ifdef __KERNEL__
 /*
  * SECTION_SIZE_BITS		2^N: how big each section will be
- * MAX_PHYSADDR_BITS		2^N: how much physical address space we have
- * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
+ * MAX_PHYSMEM_BITS		2^N: how much physical address space we have
  */
 #define SECTION_SIZE_BITS	26
-#define MAX_PHYSADDR_BITS	32
 #define MAX_PHYSMEM_BITS	32
 
-#endif
-
 #endif /* __ASM_SH_SPARSEMEM_H */
diff --git a/arch/sh/include/asm/stacktrace.h b/arch/sh/include/asm/stacktrace.h
index 50c173c0b9f5..4f98cdc64ec5 100644
--- a/arch/sh/include/asm/stacktrace.h
+++ b/arch/sh/include/asm/stacktrace.h
@@ -12,8 +12,6 @@
 
 struct stacktrace_ops {
 	void (*address)(void *data, unsigned long address, int reliable);
-	/* On negative return stop dumping */
-	int (*stack)(void *data, char *name);
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
diff --git a/arch/sh/include/asm/string_32.h b/arch/sh/include/asm/string_32.h
index 3558b1d7123e..a276b193d3b4 100644
--- a/arch/sh/include/asm/string_32.h
+++ b/arch/sh/include/asm/string_32.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_STRING_H
 #define __ASM_SH_STRING_H
 
-#ifdef __KERNEL__
-
 /*
  * Copyright (C) 1999 Niibe Yutaka
  * But consider these trivial functions to be public domain.
@@ -28,32 +26,6 @@ static inline char *strcpy(char *__dest, const char *__src)
 	return __xdest;
 }
 
-#define __HAVE_ARCH_STRNCPY
-static inline char *strncpy(char *__dest, const char *__src, size_t __n)
-{
-	register char *__xdest = __dest;
-	unsigned long __dummy;
-
-	if (__n == 0)
-		return __xdest;
-
-	__asm__ __volatile__(
-		"1:\n"
-		"mov.b	@%1+, %2\n\t"
-		"mov.b	%2, @%0\n\t"
-		"cmp/eq	#0, %2\n\t"
-		"bt/s	2f\n\t"
-		" cmp/eq	%5,%1\n\t"
-		"bf/s	1b\n\t"
-		" add	#1, %0\n"
-		"2:"
-		: "=r" (__dest), "=r" (__src), "=&z" (__dummy)
-		: "0" (__dest), "1" (__src), "r" (__src+__n)
-		: "memory", "t");
-
-	return __xdest;
-}
-
 #define __HAVE_ARCH_STRCMP
 static inline int strcmp(const char *__cs, const char *__ct)
 {
@@ -127,6 +99,4 @@ extern void *memchr(const void *__s, int __c, size_t __n);
 #define __HAVE_ARCH_STRLEN
 extern size_t strlen(const char *);
 
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_SH_STRING_H */
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 0b5b8e75edac..cb51a7528384 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -40,10 +40,7 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	if (error)
-		regs->regs[0] = -error;
-	else
-		regs->regs[0] = val;
+	regs->regs[0] = (long) error ?: val;
 }
 
 static inline void syscall_get_arguments(struct task_struct *task,
diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h
index 9f9faf63b48c..5c555b864fe0 100644
--- a/arch/sh/include/asm/syscalls_32.h
+++ b/arch/sh/include/asm/syscalls_32.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_SH_SYSCALLS_32_H
 #define __ASM_SH_SYSCALLS_32_H
 
-#ifdef __KERNEL__
-
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -26,5 +24,4 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
 asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0,
 				 unsigned long thread_info_flags);
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_SYSCALLS_32_H */
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index 6404be69d5fa..243ea5150aa0 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -10,8 +10,6 @@
  *  Copyright (C) 2002  David Howells (dhowells@redhat.com)
  *  - Incorporating suggestions made by Linus Torvalds and Dave Miller
  */
-#ifdef __KERNEL__
-
 #include <asm/page.h>
 
 /*
@@ -170,7 +168,4 @@ static inline unsigned int get_thread_fault_code(void)
 }
 
 #endif	/* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
 #endif /* __ASM_SH_THREAD_INFO_H */
diff --git a/arch/sh/include/asm/uaccess_32.h b/arch/sh/include/asm/uaccess_32.h
index 624cf55acc27..5d7ddc092afd 100644
--- a/arch/sh/include/asm/uaccess_32.h
+++ b/arch/sh/include/asm/uaccess_32.h
@@ -26,6 +26,9 @@ do {								\
 	case 4:							\
 		__get_user_asm(x, ptr, retval, "l");		\
 		break;						\
+	case 8:							\
+		__get_user_u64(x, ptr, retval);			\
+		break;						\
 	default:						\
 		__get_user_unknown();				\
 		break;						\
@@ -66,6 +69,56 @@ do {							\
 
 extern void __get_user_unknown(void);
 
+#if defined(CONFIG_CPU_LITTLE_ENDIAN)
+#define __get_user_u64(x, addr, err) \
+({ \
+__asm__ __volatile__( \
+	"1:\n\t" \
+	"mov.l	%2,%R1\n\t" \
+	"mov.l	%T2,%S1\n\t" \
+	"2:\n" \
+	".section	.fixup,\"ax\"\n" \
+	"3:\n\t" \
+	"mov  #0,%R1\n\t"   \
+	"mov  #0,%S1\n\t"   \
+	"mov.l	4f, %0\n\t" \
+	"jmp	@%0\n\t" \
+	" mov	%3, %0\n\t" \
+	".balign	4\n" \
+	"4:	.long	2b\n\t" \
+	".previous\n" \
+	".section	__ex_table,\"a\"\n\t" \
+	".long	1b, 3b\n\t" \
+	".long	1b + 2, 3b\n\t" \
+	".previous" \
+	:"=&r" (err), "=&r" (x) \
+	:"m" (__m(addr)), "i" (-EFAULT), "0" (err)); })
+#else
+#define __get_user_u64(x, addr, err) \
+({ \
+__asm__ __volatile__( \
+	"1:\n\t" \
+	"mov.l	%2,%S1\n\t" \
+	"mov.l	%T2,%R1\n\t" \
+	"2:\n" \
+	".section	.fixup,\"ax\"\n" \
+	"3:\n\t" \
+	"mov  #0,%S1\n\t"   \
+	"mov  #0,%R1\n\t"   \
+	"mov.l	4f, %0\n\t" \
+	"jmp	@%0\n\t" \
+	" mov	%3, %0\n\t" \
+	".balign	4\n" \
+	"4:	.long	2b\n\t" \
+	".previous\n" \
+	".section	__ex_table,\"a\"\n\t" \
+	".long	1b, 3b\n\t" \
+	".long	1b + 2, 3b\n\t" \
+	".previous" \
+	:"=&r" (err), "=&r" (x) \
+	:"m" (__m(addr)), "i" (-EFAULT), "0" (err)); })
+#endif
+
 #define __put_user_size(x,ptr,size,retval)		\
 do {							\
 	retval = 0;					\
diff --git a/arch/sh/include/asm/watchdog.h b/arch/sh/include/asm/watchdog.h
index cecd0fc507f9..b9ca4c99f046 100644
--- a/arch/sh/include/asm/watchdog.h
+++ b/arch/sh/include/asm/watchdog.h
@@ -8,7 +8,6 @@
  */
 #ifndef __ASM_SH_WATCHDOG_H
 #define __ASM_SH_WATCHDOG_H
-#ifdef __KERNEL__
 
 #include <linux/types.h>
 #include <linux/io.h>
@@ -157,5 +156,4 @@ static inline void sh_wdt_write_csr(__u8 val)
 	__raw_writew((WTCSR_HIGH << 8) | (__u16)val, WTCSR);
 }
 #endif /* CONFIG_CPU_SUBTYPE_SH7785 || CONFIG_CPU_SUBTYPE_SH7780 */
-#endif /* __KERNEL__ */
 #endif /* __ASM_SH_WATCHDOG_H */
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index b0f5574b6228..aa0fbc9202b1 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -47,5 +47,3 @@ obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
 obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-coherent.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
-
-ccflags-y := -Werror
diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c
index 845543780cc5..08e1af63edd9 100644
--- a/arch/sh/kernel/disassemble.c
+++ b/arch/sh/kernel/disassemble.c
@@ -376,148 +376,148 @@ static void print_sh_insn(u32 memaddr, u16 insn)
 		}
 
 	ok:
-		printk("%-8s  ", op->name);
+		pr_cont("%-8s  ", op->name);
 		lastsp = (op->arg[0] == A_END);
 		disp_pc = 0;
 		for (n = 0; n < 6 && op->arg[n] != A_END; n++) {
 			if (n && op->arg[1] != A_END)
-				printk(", ");
+				pr_cont(", ");
 			switch (op->arg[n]) {
 			case A_IMM:
-				printk("#%d", (char)(imm));
+				pr_cont("#%d", (char)(imm));
 				break;
 			case A_R0:
-				printk("r0");
+				pr_cont("r0");
 				break;
 			case A_REG_N:
-				printk("r%d", rn);
+				pr_cont("r%d", rn);
 				break;
 			case A_INC_N:
-				printk("@r%d+", rn);
+				pr_cont("@r%d+", rn);
 				break;
 			case A_DEC_N:
-				printk("@-r%d", rn);
+				pr_cont("@-r%d", rn);
 				break;
 			case A_IND_N:
-				printk("@r%d", rn);
+				pr_cont("@r%d", rn);
 				break;
 			case A_DISP_REG_N:
-				printk("@(%d,r%d)", imm, rn);
+				pr_cont("@(%d,r%d)", imm, rn);
 				break;
 			case A_REG_M:
-				printk("r%d", rm);
+				pr_cont("r%d", rm);
 				break;
 			case A_INC_M:
-				printk("@r%d+", rm);
+				pr_cont("@r%d+", rm);
 				break;
 			case A_DEC_M:
-				printk("@-r%d", rm);
+				pr_cont("@-r%d", rm);
 				break;
 			case A_IND_M:
-				printk("@r%d", rm);
+				pr_cont("@r%d", rm);
 				break;
 			case A_DISP_REG_M:
-				printk("@(%d,r%d)", imm, rm);
+				pr_cont("@(%d,r%d)", imm, rm);
 				break;
 			case A_REG_B:
-				printk("r%d_bank", rb);
+				pr_cont("r%d_bank", rb);
 				break;
 			case A_DISP_PC:
 				disp_pc = 1;
 				disp_pc_addr = imm + 4 + (memaddr & relmask);
-				printk("%08x <%pS>", disp_pc_addr,
-				       (void *)disp_pc_addr);
+				pr_cont("%08x <%pS>", disp_pc_addr,
+					(void *)disp_pc_addr);
 				break;
 			case A_IND_R0_REG_N:
-				printk("@(r0,r%d)", rn);
+				pr_cont("@(r0,r%d)", rn);
 				break;
 			case A_IND_R0_REG_M:
-				printk("@(r0,r%d)", rm);
+				pr_cont("@(r0,r%d)", rm);
 				break;
 			case A_DISP_GBR:
-				printk("@(%d,gbr)",imm);
+				pr_cont("@(%d,gbr)", imm);
 				break;
 			case A_R0_GBR:
-				printk("@(r0,gbr)");
+				pr_cont("@(r0,gbr)");
 				break;
 			case A_BDISP12:
 			case A_BDISP8:
-				printk("%08x", imm + memaddr);
+				pr_cont("%08x", imm + memaddr);
 				break;
 			case A_SR:
-				printk("sr");
+				pr_cont("sr");
 				break;
 			case A_GBR:
-				printk("gbr");
+				pr_cont("gbr");
 				break;
 			case A_VBR:
-				printk("vbr");
+				pr_cont("vbr");
 				break;
 			case A_SSR:
-				printk("ssr");
+				pr_cont("ssr");
 				break;
 			case A_SPC:
-				printk("spc");
+				pr_cont("spc");
 				break;
 			case A_MACH:
-				printk("mach");
+				pr_cont("mach");
 				break;
 			case A_MACL:
-				printk("macl");
+				pr_cont("macl");
 				break;
 			case A_PR:
-				printk("pr");
+				pr_cont("pr");
 				break;
 			case A_SGR:
-				printk("sgr");
+				pr_cont("sgr");
 				break;
 			case A_DBR:
-				printk("dbr");
+				pr_cont("dbr");
 				break;
 			case FD_REG_N:
 			case F_REG_N:
-				printk("fr%d", rn);
+				pr_cont("fr%d", rn);
 				break;
 			case F_REG_M:
-				printk("fr%d", rm);
+				pr_cont("fr%d", rm);
 				break;
 			case DX_REG_N:
 				if (rn & 1) {
-					printk("xd%d", rn & ~1);
+					pr_cont("xd%d", rn & ~1);
 					break;
 				}
 				/* else, fall through */
 			case D_REG_N:
-				printk("dr%d", rn);
+				pr_cont("dr%d", rn);
 				break;
 			case DX_REG_M:
 				if (rm & 1) {
-					printk("xd%d", rm & ~1);
+					pr_cont("xd%d", rm & ~1);
 					break;
 				}
 				/* else, fall through */
 			case D_REG_M:
-				printk("dr%d", rm);
+				pr_cont("dr%d", rm);
 				break;
 			case FPSCR_M:
 			case FPSCR_N:
-				printk("fpscr");
+				pr_cont("fpscr");
 				break;
 			case FPUL_M:
 			case FPUL_N:
-				printk("fpul");
+				pr_cont("fpul");
 				break;
 			case F_FR0:
-				printk("fr0");
+				pr_cont("fr0");
 				break;
 			case V_REG_N:
-				printk("fv%d", rn*4);
+				pr_cont("fv%d", rn*4);
 				break;
 			case V_REG_M:
-				printk("fv%d", rm*4);
+				pr_cont("fv%d", rm*4);
 				break;
 			case XMTRX_M4:
-				printk("xmtrx");
+				pr_cont("xmtrx");
 				break;
 			default:
 				return;
@@ -532,7 +532,7 @@ static void print_sh_insn(u32 memaddr, u16 insn)
 			else
 				__get_user(val, (u32 *)disp_pc_addr);
 
-			printk("  ! %08x <%pS>", val, (void *)val);
+			pr_cont("  ! %08x <%pS>", val, (void *)val);
 		}
 
 		return;
@@ -541,7 +541,7 @@ static void print_sh_insn(u32 memaddr, u16 insn)
 
 	}
 
-	printk(".word 0x%x%x%x%x", nibs[0], nibs[1], nibs[2], nibs[3]);
+	pr_info(".word 0x%x%x%x%x", nibs[0], nibs[1], nibs[2], nibs[3]);
 }
 
 void show_code(struct pt_regs *regs)
@@ -552,20 +552,21 @@ void show_code(struct pt_regs *regs)
 	if (regs->pc & 0x1)
 		return;
 
-	printk("Code:\n");
+	pr_info("Code:\n");
 
 	for (i = -3 ; i < 6 ; i++) {
 		unsigned short insn;
 
 		if (__get_user(insn, pc + i)) {
-			printk(" (Bad address in pc)\n");
+			pr_err(" (Bad address in pc)\n");
 			break;
 		}
 
-		printk("%s%08lx:  ", (i ? "  ": "->"), (unsigned long)(pc + i));
+		pr_info("%s%08lx:  ", (i ? "  " : "->"),
+			(unsigned long)(pc + i));
 		print_sh_insn((unsigned long)(pc + i), insn);
-		printk("\n");
+		pr_cont("\n");
 	}
 
-	printk("\n");
+	pr_info("\n");
 }
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index d4811691b93c..cd46a9825e3c 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -3,60 +3,13 @@
  * Copyright (C) 2004 - 2007  Paul Mundt
  */
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/module.h>
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs)
+void arch_dma_prep_coherent(struct page *page, size_t size)
 {
-	void *ret, *ret_nocache;
-	int order = get_order(size);
-
-	gfp |= __GFP_ZERO;
-
-	ret = (void *)__get_free_pages(gfp, order);
-	if (!ret)
-		return NULL;
-
-	/*
-	 * Pages from the page allocator may have data present in
-	 * cache. So flush the cache before using uncached memory.
-	 */
-	arch_sync_dma_for_device(virt_to_phys(ret), size,
-			DMA_BIDIRECTIONAL);
-
-	ret_nocache = (void __force *)ioremap(virt_to_phys(ret), size);
-	if (!ret_nocache) {
-		free_pages((unsigned long)ret, order);
-		return NULL;
-	}
-
-	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
-
-	*dma_handle = virt_to_phys(ret);
-	if (!WARN_ON(!dev))
-		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
-
-	return ret_nocache;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	int order = get_order(size);
-	unsigned long pfn = (dma_handle >> PAGE_SHIFT);
-	int k;
-
-	if (!WARN_ON(!dev))
-		pfn += dev->dma_pfn_offset;
-
-	for (k = 0; k < (1 << order); k++)
-		__free_pages(pfn_to_page(pfn + k), 0);
-
-	iounmap(vaddr);
+	__flush_purge_region(page_address(page), size);
 }
 
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index a13c045804ed..758a6c89e911 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -16,8 +16,8 @@
 #include <asm/unwinder.h>
 #include <asm/stacktrace.h>
 
-void dump_mem(const char *str, const char *loglvl,
-	      unsigned long bottom, unsigned long top)
+void dump_mem(const char *str, const char *loglvl, unsigned long bottom,
+	      unsigned long top)
 {
 	unsigned long p;
 	int i;
@@ -31,23 +31,23 @@ void dump_mem(const char *str, const char *loglvl,
 			unsigned int val;
 
 			if (p < bottom || p >= top)
-				printk("%s         ", loglvl);
+				pr_cont("         ");
 			else {
 				if (__get_user(val, (unsigned int __user *)p)) {
-					printk("%s\n", loglvl);
+					pr_cont("\n");
 					return;
 				}
-				printk("%s%08x ", loglvl, val);
+				pr_cont("%08x ", val);
 			}
 		}
-		printk("%s\n", loglvl);
+		pr_cont("\n");
 	}
 }
 
-void printk_address(unsigned long address, int reliable, const char *loglvl)
+void printk_address(unsigned long address, int reliable)
 {
-	printk("%s [<%p>] %s%pS\n", loglvl, (void *) address,
-			reliable ? "" : "? ", (void *) address);
+	pr_cont(" [<%px>] %s%pS\n", (void *) address,
+		reliable ? "" : "? ", (void *) address);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -107,22 +107,16 @@ stack_reader_dump(struct task_struct *task, struct pt_regs *regs,
 	}
 }
 
-static int print_trace_stack(void *data, char *name)
-{
-	printk("%s <%s> ", (char *)data, name);
-	return 0;
-}
-
 /*
  * Print one address/symbol entries per line.
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk_address(addr, reliable, (char *)data);
+	printk("%s", (char *)data);
+	printk_address(addr, reliable);
 }
 
 static const struct stacktrace_ops print_trace_ops = {
-	.stack = print_trace_stack,
 	.address = print_trace_address,
 };
 
@@ -136,7 +130,7 @@ void show_trace(struct task_struct *tsk, unsigned long *sp,
 
 	unwind_stack(tsk, regs, sp, &print_trace_ops, (void *)loglvl);
 
-	printk("%s\n", loglvl);
+	pr_cont("\n");
 
 	if (!tsk)
 		tsk = current;
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 9bac5bbb67f3..ad963104d22d 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -178,34 +178,6 @@ syscall_exit_work:
 	bra	resume_userspace
 	 nop
 
-	.align	2
-syscall_trace_entry:
-	!                     	Yes it is traced.
-	mov     r15, r4
-	mov.l	7f, r11		! Call do_syscall_trace_enter which notifies
-	jsr	@r11	    	! superior (will chomp R[0-7])
-	 nop
-	mov.l	r0, @(OFF_R0,r15)	! Save return value
-	!			Reload R0-R4 from kernel stack, where the
-	!   	    	    	parent may have modified them using
-	!   	    	    	ptrace(POKEUSR).  (Note that R0-R2 are
-	!   	    	    	reloaded from the kernel stack by syscall_call
-	!   	    	    	below, so don't need to be reloaded here.)
-	!   	    	    	This allows the parent to rewrite system calls
-	!   	    	    	and args on the fly.
-	mov.l	@(OFF_R4,r15), r4   ! arg0
-	mov.l	@(OFF_R5,r15), r5
-	mov.l	@(OFF_R6,r15), r6
-	mov.l	@(OFF_R7,r15), r7   ! arg3
-	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
-	!
-	mov.l	6f, r10			! Number of syscalls
-	cmp/hs	r10, r3
-	bf	syscall_call
-	mov	#-ENOSYS, r0
-	bra	syscall_exit
-	 mov.l	r0, @(OFF_R0,r15)	! Return value
-
 __restore_all:
 	mov	#OFF_SR, r0
 	mov.l	@(r0,r15), r0	! get status register
@@ -388,6 +360,37 @@ syscall_exit:
 	bf	syscall_exit_work
 	bra	__restore_all
 	 nop
+
+	.align	2
+syscall_trace_entry:
+	!                     	Yes it is traced.
+	mov     r15, r4
+	mov.l	7f, r11		! Call do_syscall_trace_enter which notifies
+	jsr	@r11	    	! superior (will chomp R[0-7])
+	 nop
+	cmp/eq	#-1, r0
+	bt	syscall_exit
+	mov.l	r0, @(OFF_R0,r15)	! Save return value
+	!			Reload R0-R4 from kernel stack, where the
+	!   	    	    	parent may have modified them using
+	!   	    	    	ptrace(POKEUSR).  (Note that R0-R2 are
+	!   	    	    	reloaded from the kernel stack by syscall_call
+	!   	    	    	below, so don't need to be reloaded here.)
+	!   	    	    	This allows the parent to rewrite system calls
+	!   	    	    	and args on the fly.
+	mov.l	@(OFF_R4,r15), r4   ! arg0
+	mov.l	@(OFF_R5,r15), r5
+	mov.l	@(OFF_R6,r15), r6
+	mov.l	@(OFF_R7,r15), r7   ! arg3
+	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
+	!
+	mov.l	6f, r10			! Number of syscalls
+	cmp/hs	r10, r3
+	bf	syscall_call
+	mov	#-ENOSYS, r0
+	bra	syscall_exit
+	 mov.l	r0, @(OFF_R0,r15)	! Return value
+
 	.align	2
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index 037aab2708b7..004ad0130b10 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -102,7 +102,6 @@ int register_trapped_io(struct trapped_io *tiop)
 	pr_warn("unable to install trapped io filter\n");
 	return -1;
 }
-EXPORT_SYMBOL_GPL(register_trapped_io);
 
 void __iomem *match_trapped_io_handler(struct list_head *list,
 				       unsigned long offset,
@@ -131,7 +130,6 @@ void __iomem *match_trapped_io_handler(struct list_head *list,
 	spin_unlock_irqrestore(&trapped_lock, flags);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(match_trapped_io_handler);
 
 static struct trapped_io *lookup_tiop(unsigned long address)
 {
diff --git a/arch/sh/kernel/iomap.c b/arch/sh/kernel/iomap.c
index ef9e2c97cbb7..0a0dff4e66de 100644
--- a/arch/sh/kernel/iomap.c
+++ b/arch/sh/kernel/iomap.c
@@ -8,31 +8,31 @@
 #include <linux/module.h>
 #include <linux/io.h>
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	return readb(addr);
 }
 EXPORT_SYMBOL(ioread8);
 
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	return readw(addr);
 }
 EXPORT_SYMBOL(ioread16);
 
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	return be16_to_cpu(__raw_readw(addr));
 }
 EXPORT_SYMBOL(ioread16be);
 
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	return readl(addr);
 }
 EXPORT_SYMBOL(ioread32);
 
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	return be32_to_cpu(__raw_readl(addr));
 }
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(iowrite32be);
  * convert to CPU byte order. We write in "IO byte
  * order" (we also don't have IO barriers).
  */
-static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
 		u8 data = __raw_readb(addr);
@@ -83,7 +83,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 	}
 }
 
-static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
 {
 	while (--count >= 0) {
 		u16 data = __raw_readw(addr);
@@ -92,7 +92,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
 	}
 }
 
-static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
 {
 	while (--count >= 0) {
 		u32 data = __raw_readl(addr);
@@ -125,19 +125,19 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 	}
 }
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insb(addr, dst, count);
 }
 EXPORT_SYMBOL(ioread8_rep);
 
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insw(addr, dst, count);
 }
 EXPORT_SYMBOL(ioread16_rep);
 
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	mmio_insl(addr, dst, count);
 }
diff --git a/arch/sh/kernel/ioport.c b/arch/sh/kernel/ioport.c
index 34f8cdbbcf0b..f39446a658bd 100644
--- a/arch/sh/kernel/ioport.c
+++ b/arch/sh/kernel/ioport.c
@@ -7,6 +7,7 @@
  */
 #include <linux/module.h>
 #include <linux/io.h>
+#include <asm/io_trapped.h>
 
 unsigned long sh_io_port_base __read_mostly = -1;
 EXPORT_SYMBOL(sh_io_port_base);
diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c
index beadbbdb4486..d606679a211e 100644
--- a/arch/sh/kernel/machvec.c
+++ b/arch/sh/kernel/machvec.c
@@ -15,6 +15,7 @@
 #include <asm/setup.h>
 #include <asm/io.h>
 #include <asm/irq.h>
+#include <asm/processor.h>
 
 #define MV_NAME_SIZE 32
 
@@ -64,10 +65,10 @@ static int __init early_parse_mv(char *from)
 
 	mvp = get_mv_byname(mv_name);
 	if (unlikely(!mvp)) {
-		printk("Available vectors:\n\n\t'%s', ", sh_mv.mv_name);
+		pr_info("Available vectors:\n\n\t'%s', ", sh_mv.mv_name);
 		for_each_mv(mvp)
-			printk("'%s', ", mvp->mv_name);
-		printk("\n\n");
+			pr_cont("'%s', ", mvp->mv_name);
+		pr_cont("\n\n");
 		panic("Failed to select machvec '%s' -- halting.\n",
 		      mv_name);
 	} else
@@ -104,7 +105,7 @@ void __init sh_mv_setup(void)
 			sh_mv = *(struct sh_machine_vector *)&__machvec_start;
 	}
 
-	printk(KERN_NOTICE "Booting machvec: %s\n", get_system_type());
+	pr_notice("Booting machvec: %s\n", get_system_type());
 
 	/*
 	 * Manually walk the vec, fill in anything that the board hasn't yet
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index 6281f2fdf9ca..c9d3aa18732d 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -11,11 +11,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static int callchain_stack(void *data, char *name)
-{
-	return 0;
-}
-
 static void callchain_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry_ctx *entry = data;
@@ -25,7 +20,6 @@ static void callchain_address(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops callchain_ops = {
-	.stack		= callchain_stack,
 	.address	= callchain_address,
 };
 
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index cde0a66116d2..80a5d1c66a51 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -30,34 +30,30 @@
 
 void show_regs(struct pt_regs * regs)
 {
-	printk("\n");
+	pr_info("\n");
 	show_regs_print_info(KERN_DEFAULT);
 
-	printk("PC is at %pS\n", (void *)instruction_pointer(regs));
-	printk("PR is at %pS\n", (void *)regs->pr);
+	pr_info("PC is at %pS\n", (void *)instruction_pointer(regs));
+	pr_info("PR is at %pS\n", (void *)regs->pr);
 
-	printk("PC  : %08lx SP  : %08lx SR  : %08lx ",
-	       regs->pc, regs->regs[15], regs->sr);
+	pr_info("PC  : %08lx SP  : %08lx SR  : %08lx ", regs->pc,
+		regs->regs[15], regs->sr);
 #ifdef CONFIG_MMU
-	printk("TEA : %08x\n", __raw_readl(MMU_TEA));
+	pr_cont("TEA : %08x\n", __raw_readl(MMU_TEA));
 #else
-	printk("\n");
+	pr_cont("\n");
 #endif
 
-	printk("R0  : %08lx R1  : %08lx R2  : %08lx R3  : %08lx\n",
-	       regs->regs[0],regs->regs[1],
-	       regs->regs[2],regs->regs[3]);
-	printk("R4  : %08lx R5  : %08lx R6  : %08lx R7  : %08lx\n",
-	       regs->regs[4],regs->regs[5],
-	       regs->regs[6],regs->regs[7]);
-	printk("R8  : %08lx R9  : %08lx R10 : %08lx R11 : %08lx\n",
-	       regs->regs[8],regs->regs[9],
-	       regs->regs[10],regs->regs[11]);
-	printk("R12 : %08lx R13 : %08lx R14 : %08lx\n",
-	       regs->regs[12],regs->regs[13],
-	       regs->regs[14]);
-	printk("MACH: %08lx MACL: %08lx GBR : %08lx PR  : %08lx\n",
-	       regs->mach, regs->macl, regs->gbr, regs->pr);
+	pr_info("R0  : %08lx R1  : %08lx R2  : %08lx R3  : %08lx\n",
+		regs->regs[0], regs->regs[1], regs->regs[2], regs->regs[3]);
+	pr_info("R4  : %08lx R5  : %08lx R6  : %08lx R7  : %08lx\n",
+		regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]);
+	pr_info("R8  : %08lx R9  : %08lx R10 : %08lx R11 : %08lx\n",
+		regs->regs[8], regs->regs[9], regs->regs[10], regs->regs[11]);
+	pr_info("R12 : %08lx R13 : %08lx R14 : %08lx\n",
+		regs->regs[12], regs->regs[13], regs->regs[14]);
+	pr_info("MACH: %08lx MACL: %08lx GBR : %08lx PR  : %08lx\n",
+		regs->mach, regs->macl, regs->gbr, regs->pr);
 
 	show_trace(NULL, (unsigned long *)regs->regs[15], regs, KERN_DEFAULT);
 	show_code(regs);
@@ -93,24 +89,6 @@ void release_thread(struct task_struct *dead_task)
 	/* do nothing */
 }
 
-/* Fill in the fpu structure for a core dump.. */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
-{
-	int fpvalid = 0;
-
-#if defined(CONFIG_SH_FPU)
-	struct task_struct *tsk = current;
-
-	fpvalid = !!tsk_used_math(tsk);
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      (struct membuf){fpu, sizeof(*fpu)});
-#endif
-
-	return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 5c93bdb6c41a..b05bf92f9c32 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -165,7 +165,7 @@ static int genregs_set(struct task_struct *target,
 }
 
 #ifdef CONFIG_SH_FPU
-int fpregs_get(struct task_struct *target,
+static int fpregs_get(struct task_struct *target,
 	       const struct user_regset *regset,
 	       struct membuf to)
 {
@@ -457,8 +457,6 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
-	secure_computing_strict(regs->regs[0]);
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(regs))
 		/*
@@ -468,6 +466,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
+	if (secure_computing() == -1)
+		return -1;
+
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[0]);
 
diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c
index 2950b19ad077..daf0b53ee066 100644
--- a/arch/sh/kernel/stacktrace.c
+++ b/arch/sh/kernel/stacktrace.c
@@ -15,11 +15,6 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
-static int save_stack_stack(void *data, char *name)
-{
-	return 0;
-}
-
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
  */
@@ -40,7 +35,6 @@ static void save_stack_address(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops save_stack_ops = {
-	.stack = save_stack_stack,
 	.address = save_stack_address,
 };
 
@@ -73,7 +67,6 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 }
 
 static const struct stacktrace_ops save_stack_ops_nosched = {
-	.stack = save_stack_stack,
 	.address = save_stack_address_nosched,
 };
 
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 96848db9659e..ae0a00beea5f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -156,7 +156,7 @@
 146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
-149	common	_sysctl				sys_sysctl
+149	common	_sysctl				sys_ni_syscall
 150	common	mlock				sys_mlock
 151	common	munlock				sys_munlock
 152	common	mlockall			sys_mlockall
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 058c6181bb30..b62ad0ba2395 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -482,8 +482,6 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 	error_code = lookup_exception_vector();
 #endif
 
-	oldfs = get_fs();
-
 	if (user_mode(regs)) {
 		int si_code = BUS_ADRERR;
 		unsigned int user_action;
@@ -491,13 +489,13 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 		local_irq_enable();
 		inc_unaligned_user_access();
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1),
 				   sizeof(instruction))) {
-			set_fs(oldfs);
+			force_uaccess_end(oldfs);
 			goto uspace_segv;
 		}
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		/* shout about userspace fixups */
 		unaligned_fixups_notify(current, instruction, regs);
@@ -520,11 +518,11 @@ fixup:
 			goto uspace_segv;
 		}
 
-		set_fs(USER_DS);
+		oldfs = force_uaccess_begin();
 		tmp = handle_unaligned_access(instruction, regs,
 					      &user_mem_access, 0,
 					      address);
-		set_fs(oldfs);
+		force_uaccess_end(oldfs);
 
 		if (tmp == 0)
 			return; /* sorted */
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index d0abbe5e38b0..eb473d373ca4 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -30,5 +30,3 @@ memset-$(CONFIG_CPU_SH4)	:= memset-sh4.o
 lib-$(CONFIG_MMU)		+= copy_page.o __clear_user.o
 lib-$(CONFIG_MCOUNT)		+= mcount.o
 lib-y				+= $(memcpy-y) $(memset-y) $(udivsi3-y)
-
-ccflags-y := -Werror
diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c
index 540e670dbafc..dad8e6a54906 100644
--- a/arch/sh/lib/delay.c
+++ b/arch/sh/lib/delay.c
@@ -29,7 +29,6 @@ void __delay(unsigned long loops)
 		: "0" (loops)
 		: "t");
 }
-EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile
index 487da0ff03b3..f69ddc70b146 100644
--- a/arch/sh/mm/Makefile
+++ b/arch/sh/mm/Makefile
@@ -43,5 +43,3 @@ obj-$(CONFIG_UNCACHED_MAPPING)	+= uncached.o
 obj-$(CONFIG_HAVE_SRAM_POOL)	+= sram.o
 
 GCOV_PROFILE_pmb.o := n
-
-ccflags-y := -Werror
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 3169a343a5ab..0de206c1acfe 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -57,8 +57,6 @@ int __init platform_resource_setup_memory(struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
-	memset(buf, 0, memsize);
-
 	r->flags = IORESOURCE_MEM;
 	r->start = dma_handle;
 	r->end = r->start + memsize - 1;
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index fbe1f2fe9a8c..88a1f453d73e 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -208,13 +208,12 @@ show_fault_oops(struct pt_regs *regs, unsigned long address)
 	if (!oops_may_print())
 		return;
 
-	printk(KERN_ALERT "PC:");
 	pr_alert("BUG: unable to handle kernel %s at %08lx\n",
 		 address < PAGE_SIZE ? "NULL pointer dereference"
 				     : "paging request",
 		 address);
 	pr_alert("PC:");
-	printk_address(regs->pc, 1, KERN_ALERT);
+	printk_address(regs->pc, 1);
 
 	show_pte(NULL, address);
 }
@@ -482,22 +481,13 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))
 			return;
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 613de8096335..4735176ab811 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -29,6 +29,7 @@
 #include <asm/cache.h>
 #include <asm/pgalloc.h>
 #include <linux/sizes.h>
+#include "ioremap.h"
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
@@ -425,15 +426,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return ret;
 }
 
-#ifdef CONFIG_NUMA
-int memory_add_physaddr_to_nid(u64 addr)
-{
-	/* Node 0 for now.. */
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c
index f6d02246d665..21342581144d 100644
--- a/arch/sh/mm/ioremap.c
+++ b/arch/sh/mm/ioremap.c
@@ -18,12 +18,59 @@
 #include <linux/mm.h>
 #include <linux/pci.h>
 #include <linux/io.h>
+#include <asm/io_trapped.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/addrspace.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
+#include "ioremap.h"
+
+/*
+ * On 32-bit SH, we traditionally have the whole physical address space mapped
+ * at all times (as MIPS does), so "ioremap()" and "iounmap()" do not need to do
+ * anything but place the address in the proper segment.  This is true for P1
+ * and P2 addresses, as well as some P3 ones.  However, most of the P3 addresses
+ * and newer cores using extended addressing need to map through page tables, so
+ * the ioremap() implementation becomes a bit more complicated.
+ */
+#ifdef CONFIG_29BIT
+static void __iomem *
+__ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
+{
+	phys_addr_t last_addr = offset + size - 1;
+
+	/*
+	 * For P1 and P2 space this is trivial, as everything is already
+	 * mapped. Uncached access for P1 addresses are done through P2.
+	 * In the P3 case or for addresses outside of the 29-bit space,
+	 * mapping must be done by the PMB or by using page tables.
+	 */
+	if (likely(PXSEG(offset) < P3SEG && PXSEG(last_addr) < P3SEG)) {
+		u64 flags = pgprot_val(prot);
+
+		/*
+		 * Anything using the legacy PTEA space attributes needs
+		 * to be kicked down to page table mappings.
+		 */
+		if (unlikely(flags & _PAGE_PCC_MASK))
+			return NULL;
+		if (unlikely(flags & _PAGE_CACHABLE))
+			return (void __iomem *)P1SEGADDR(offset);
+
+		return (void __iomem *)P2SEGADDR(offset);
+	}
+
+	/* P4 above the store queues are always mapped. */
+	if (unlikely(offset >= P3_ADDR_MAX))
+		return (void __iomem *)P4SEGADDR(offset);
+
+	return NULL;
+}
+#else
+#define __ioremap_29bit(offset, size, prot)		NULL
+#endif /* CONFIG_29BIT */
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
@@ -42,6 +89,14 @@ __ioremap_caller(phys_addr_t phys_addr, unsigned long size,
 	unsigned long offset, last_addr, addr, orig_addr;
 	void __iomem *mapped;
 
+	mapped = __ioremap_trapped(phys_addr, size);
+	if (mapped)
+		return mapped;
+
+	mapped = __ioremap_29bit(phys_addr, size, pgprot);
+	if (mapped)
+		return mapped;
+
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
 	if (!size || last_addr < phys_addr)
diff --git a/arch/sh/mm/ioremap.h b/arch/sh/mm/ioremap.h
new file mode 100644
index 000000000000..f2544e721a35
--- /dev/null
+++ b/arch/sh/mm/ioremap.h
@@ -0,0 +1,23 @@
+#ifndef _SH_MM_IORMEMAP_H
+#define _SH_MM_IORMEMAP_H 1
+
+#ifdef CONFIG_IOREMAP_FIXED
+void __iomem *ioremap_fixed(phys_addr_t, unsigned long, pgprot_t);
+int iounmap_fixed(void __iomem *);
+void ioremap_fixed_init(void);
+#else
+static inline void __iomem *
+ioremap_fixed(phys_addr_t phys_addr, unsigned long size, pgprot_t prot)
+{
+	BUG();
+	return NULL;
+}
+static inline void ioremap_fixed_init(void)
+{
+}
+static inline int iounmap_fixed(void __iomem *addr)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IOREMAP_FIXED */
+#endif /* _SH_MM_IORMEMAP_H */
diff --git a/arch/sh/mm/ioremap_fixed.c b/arch/sh/mm/ioremap_fixed.c
index aab3f82856bb..136113bcac25 100644
--- a/arch/sh/mm/ioremap_fixed.c
+++ b/arch/sh/mm/ioremap_fixed.c
@@ -23,6 +23,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
+#include "ioremap.h"
 
 struct ioremap_map {
 	void __iomem *addr;
diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c
index 5c8f9247c3c2..cf7ce4b57359 100644
--- a/arch/sh/mm/pgtable.c
+++ b/arch/sh/mm/pgtable.c
@@ -2,8 +2,6 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO
-
 static struct kmem_cache *pgd_cachep;
 #if PAGETABLE_LEVELS > 2
 static struct kmem_cache *pmd_cachep;
@@ -13,6 +11,7 @@ void pgd_ctor(void *x)
 {
 	pgd_t *pgd = x;
 
+	memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
 	memcpy(pgd + USER_PTRS_PER_PGD,
 	       swapper_pg_dir + USER_PTRS_PER_PGD,
 	       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
@@ -32,7 +31,7 @@ void pgtable_cache_init(void)
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(pgd_cachep, PGALLOC_GFP);
+	return kmem_cache_alloc(pgd_cachep, GFP_KERNEL);
 }
 
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -48,7 +47,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	return kmem_cache_alloc(pmd_cachep, PGALLOC_GFP);
+	return kmem_cache_alloc(pmd_cachep, GFP_KERNEL | __GFP_ZERO);
 }
 
 void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sh/oprofile/backtrace.c b/arch/sh/oprofile/backtrace.c
index f1205f92631d..cc16cf86cd92 100644
--- a/arch/sh/oprofile/backtrace.c
+++ b/arch/sh/oprofile/backtrace.c
@@ -19,12 +19,6 @@
 #include <asm/sections.h>
 #include <asm/stacktrace.h>
 
-static int backtrace_stack(void *data, char *name)
-{
-	/* Yes, we want all stacks */
-	return 0;
-}
-
 static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	unsigned int *depth = data;
@@ -34,7 +28,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 }
 
 static struct stacktrace_ops backtrace_ops = {
-	.stack = backtrace_stack,
 	.address = backtrace_address,
 };
 
diff --git a/arch/sh/tools/mach-types b/arch/sh/tools/mach-types
index 569977e52c91..29e648855d50 100644
--- a/arch/sh/tools/mach-types
+++ b/arch/sh/tools/mach-types
@@ -46,7 +46,6 @@ X3PROTO			SH_X3PROTO
 MAGICPANELR2		SH_MAGIC_PANEL_R2
 R2D_PLUS		RTS7751R2D_PLUS
 R2D_1			RTS7751R2D_1
-CAYMAN			SH_CAYMAN
 SDK7780			SH_SDK7780
 MIGOR			SH_MIGOR
 RSK7201			SH_RSK7201
diff --git a/arch/sparc/include/asm/sparsemem.h b/arch/sparc/include/asm/sparsemem.h
index 1dd1b61432db..aa9a676bc341 100644
--- a/arch/sparc/include/asm/sparsemem.h
+++ b/arch/sparc/include/asm/sparsemem.h
@@ -7,7 +7,6 @@
 #include <asm/page.h>
 
 #define SECTION_SIZE_BITS       30
-#define MAX_PHYSADDR_BITS       MAX_PHYS_ADDRESS_BITS
 #define MAX_PHYSMEM_BITS        MAX_PHYS_ADDRESS_BITS
 
 #endif /* !(__KERNEL__) */
diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h
index c7e4fb601a57..dcfad4613e18 100644
--- a/arch/sparc/include/asm/timer_64.h
+++ b/arch/sparc/include/asm/timer_64.h
@@ -7,6 +7,7 @@
 #ifndef _SPARC64_TIMER_H
 #define _SPARC64_TIMER_H
 
+#include <uapi/asm/asi.h>
 #include <linux/types.h>
 #include <linux/init.h>
 
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index d6d8413eca83..0a2d3ebc4bb8 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -28,7 +28,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	((current->thread.current_ds) = (val))
 
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 /* We have there a nice not-mapped page at PAGE_OFFSET - PAGE_SIZE, so that this test
  * can be fairly lightweight.
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index bf9d330073b2..698cf69f74e9 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -32,7 +32,7 @@
 
 #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)})
 
-#define segment_eq(a, b)  ((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define set_fs(val)								\
 do {										\
diff --git a/arch/sparc/include/asm/vvar.h b/arch/sparc/include/asm/vvar.h
index 0289503d1cb0..6eaf5cfcaae1 100644
--- a/arch/sparc/include/asm/vvar.h
+++ b/arch/sparc/include/asm/vvar.h
@@ -6,7 +6,8 @@
 #define _ASM_SPARC_VVAR_DATA_H
 
 #include <asm/clocksource.h>
-#include <linux/seqlock.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
 #include <linux/time.h>
 #include <linux/types.h>
 
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 3f519e1047b6..adfcaeab3ddc 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -380,55 +380,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	return 0;
 }
 
-/*
- * fill in the fpu structure for a core dump.
- */
-int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs)
-{
-	if (used_math()) {
-		memset(fpregs, 0, sizeof(*fpregs));
-		fpregs->pr_q_entrysize = 8;
-		return 1;
-	}
-#ifdef CONFIG_SMP
-	if (test_thread_flag(TIF_USEDFPU)) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		if (regs != NULL) {
-			regs->psr &= ~(PSR_EF);
-			clear_thread_flag(TIF_USEDFPU);
-		}
-	}
-#else
-	if (current == last_task_used_math) {
-		put_psr(get_psr() | PSR_EF);
-		fpsave(&current->thread.float_regs[0], &current->thread.fsr,
-		       &current->thread.fpqueue[0], &current->thread.fpqdepth);
-		if (regs != NULL) {
-			regs->psr &= ~(PSR_EF);
-			last_task_used_math = NULL;
-		}
-	}
-#endif
-	memcpy(&fpregs->pr_fr.pr_regs[0],
-	       &current->thread.float_regs[0],
-	       (sizeof(unsigned long) * 32));
-	fpregs->pr_fsr = current->thread.fsr;
-	fpregs->pr_qcnt = current->thread.fpqdepth;
-	fpregs->pr_q_entrysize = 8;
-	fpregs->pr_en = 1;
-	if(fpregs->pr_qcnt != 0) {
-		memcpy(&fpregs->pr_q[0],
-		       &current->thread.fpqueue[0],
-		       sizeof(struct fpq) * fpregs->pr_qcnt);
-	}
-	/* Zero out the rest. */
-	memset(&fpregs->pr_q[fpregs->pr_qcnt], 0,
-	       sizeof(struct fpq) * (32 - fpregs->pr_qcnt));
-	return 1;
-}
-
 unsigned long get_wchan(struct task_struct *task)
 {
 	unsigned long pc, fp, bias = 0;
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 04ef19b88632..a75093b993f9 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -666,72 +666,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-typedef struct {
-	union {
-		unsigned int	pr_regs[32];
-		unsigned long	pr_dregs[16];
-	} pr_fr;
-	unsigned int __unused;
-	unsigned int	pr_fsr;
-	unsigned char	pr_qcnt;
-	unsigned char	pr_q_entrysize;
-	unsigned char	pr_en;
-	unsigned int	pr_q[64];
-} elf_fpregset_t32;
-
-/*
- * fill in the fpu structure for a core dump.
- */
-int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs)
-{
-	unsigned long *kfpregs = current_thread_info()->fpregs;
-	unsigned long fprs = current_thread_info()->fpsaved[0];
-
-	if (test_thread_flag(TIF_32BIT)) {
-		elf_fpregset_t32 *fpregs32 = (elf_fpregset_t32 *)fpregs;
-
-		if (fprs & FPRS_DL)
-			memcpy(&fpregs32->pr_fr.pr_regs[0], kfpregs,
-			       sizeof(unsigned int) * 32);
-		else
-			memset(&fpregs32->pr_fr.pr_regs[0], 0,
-			       sizeof(unsigned int) * 32);
-		fpregs32->pr_qcnt = 0;
-		fpregs32->pr_q_entrysize = 8;
-		memset(&fpregs32->pr_q[0], 0,
-		       (sizeof(unsigned int) * 64));
-		if (fprs & FPRS_FEF) {
-			fpregs32->pr_fsr = (unsigned int) current_thread_info()->xfsr[0];
-			fpregs32->pr_en = 1;
-		} else {
-			fpregs32->pr_fsr = 0;
-			fpregs32->pr_en = 0;
-		}
-	} else {
-		if(fprs & FPRS_DL)
-			memcpy(&fpregs->pr_regs[0], kfpregs,
-			       sizeof(unsigned int) * 32);
-		else
-			memset(&fpregs->pr_regs[0], 0,
-			       sizeof(unsigned int) * 32);
-		if(fprs & FPRS_DU)
-			memcpy(&fpregs->pr_regs[16], kfpregs+16,
-			       sizeof(unsigned int) * 32);
-		else
-			memset(&fpregs->pr_regs[16], 0,
-			       sizeof(unsigned int) * 32);
-		if(fprs & FPRS_FEF) {
-			fpregs->pr_fsr = current_thread_info()->xfsr[0];
-			fpregs->pr_gsr = current_thread_info()->gsr[0];
-		} else {
-			fpregs->pr_fsr = fpregs->pr_gsr = 0;
-		}
-		fpregs->pr_fprs = fprs;
-	}
-	return 1;
-}
-EXPORT_SYMBOL(dump_fpu);
-
 unsigned long get_wchan(struct task_struct *task)
 {
 	unsigned long pc, fp, bias = 0;
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 46024e80ee86..4af114e84f20 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -300,7 +300,7 @@
 249	64	nanosleep		sys_nanosleep
 250	32	mremap			sys_mremap
 250	64	mremap			sys_64_mremap
-251	common	_sysctl			sys_sysctl			compat_sys_sysctl
+251	common	_sysctl			sys_ni_syscall
 252	common	getsid			sys_getsid
 253	common	fdatasync		sys_fdatasync
 254	32	nfsservctl		sys_ni_syscall			sys_nis_syscall
diff --git a/arch/sparc/kernel/vdso.c b/arch/sparc/kernel/vdso.c
index 58880662b271..0e27437eb97b 100644
--- a/arch/sparc/kernel/vdso.c
+++ b/arch/sparc/kernel/vdso.c
@@ -7,7 +7,6 @@
  *  a different vsyscall implementation for Linux/IA32 and for the name.
  */
 
-#include <linux/seqlock.h>
 #include <linux/time.h>
 #include <linux/timekeeper_internal.h>
 
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index cfef656eda0f..8071bfd72349 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -234,7 +234,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -250,15 +250,6 @@ good_area:
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, address);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
@@ -410,7 +401,7 @@ good_area:
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(vma, address, flags)) {
+	switch (handle_mm_fault(vma, address, flags, NULL)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index a3806614e4dc..0a6bcc85fba7 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -422,7 +422,7 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		goto exit_exception;
@@ -438,15 +438,6 @@ good_area:
 	}
 
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
-				      1, regs, address);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, address);
-		}
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index 708cb6304c2d..f44355e46f31 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -54,7 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 # optimize sibling calls.
 #
 CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
-       $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
+       $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
        -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
@@ -93,7 +93,7 @@ KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -fpic
-KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
+KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index ef69be17ff70..eb51fec75948 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -14,6 +14,7 @@ config UML
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_BUGVERBOSE
+	select NO_DMA
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
@@ -167,9 +168,6 @@ config MMAPPER
 	  This driver allows a host file to be used as emulated IO memory inside
 	  UML.
 
-config NO_DMA
-	def_bool y
-
 config PGTABLE_LEVELS
 	int
 	default 3 if 3_LEVEL_PGTABLES
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 3f27aa3ec0a6..1cea46ff9bb7 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -121,8 +121,7 @@ LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
 LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie)
 
 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
-	$(call cc-option, -fno-stack-protector,) \
-	$(call cc-option, -fno-stack-protector-all,)
+	-fno-stack-protector $(call cc-option, -fno-stack-protector-all)
 
 # Options used by linker script
 export LDS_START      := $(START)
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 351aee52aca6..a6c4bb6c2c01 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data)
 		}
 		break;
 	case VHOST_USER_SLAVE_IOTLB_MSG:
-		/* not supported - VIRTIO_F_IOMMU_PLATFORM */
+		/* not supported - VIRTIO_F_ACCESS_PLATFORM */
 	case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
 		/* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */
 	default:
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 2b3afa354a90..ad12f78bda7e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -71,7 +71,7 @@ good_area:
 	do {
 		vm_fault_t fault;
 
-		fault = handle_mm_fault(vma, address, flags);
+		fault = handle_mm_fault(vma, address, flags, NULL);
 
 		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 			goto out_nosemaphore;
@@ -88,10 +88,6 @@ good_area:
 			BUG();
 		}
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			if (fault & VM_FAULT_MAJOR)
-				current->maj_flt++;
-			else
-				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9a2849527dd7..7101ac64bb20 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -209,6 +209,7 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select MMU_GATHER_RCU_TABLE_FREE		if PARAVIRT
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1e634d7ee6eb..4346ffb2e39f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -36,8 +36,8 @@ REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   -mno-mmx -mno-sse
 
-REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
-REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
+REALMODE_CFLAGS += -ffreestanding
+REALMODE_CFLAGS += -fno-stack-protector
 REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member)
 REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
 export REALMODE_CFLAGS
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index c08714ae76ec..3962f592633d 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -35,8 +35,8 @@ cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
-KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
+KBUILD_CFLAGS += -ffreestanding
+KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
 KBUILD_CFLAGS += -Wno-pointer-sign
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 29b7d52143e9..df8c017e6161 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -449,8 +449,6 @@
 
 .macro SWITCH_TO_KERNEL_STACK
 
-	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
-
 	BUG_IF_WRONG_CR3
 
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
@@ -599,8 +597,6 @@
  */
 .macro SWITCH_TO_ENTRY_STACK
 
-	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
-
 	/* Bytes to copy */
 	movl	$PTREGS_SIZE, %ecx
 
@@ -872,17 +868,6 @@ SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
  * will ignore all of the single-step traps generated in this range.
  */
 
-#ifdef CONFIG_XEN_PV
-/*
- * Xen doesn't set %esp to be precisely what the normal SYSENTER
- * entry point expects, so fix it up before using the normal path.
- */
-SYM_CODE_START(xen_sysenter_target)
-	addl	$5*4, %esp			/* remove xen-provided frame */
-	jmp	.Lsysenter_past_esp
-SYM_CODE_END(xen_sysenter_target)
-#endif
-
 /*
  * 32-bit SYSENTER entry.
  *
@@ -965,9 +950,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	movl	%esp, %eax
 	call	do_SYSENTER_32
-	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
-		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
 
 	STACKLEAK_ERASE
 
@@ -1165,95 +1149,6 @@ SYM_FUNC_END(entry_INT80_32)
 #endif
 .endm
 
-#ifdef CONFIG_PARAVIRT
-SYM_CODE_START(native_iret)
-	iret
-	_ASM_EXTABLE(native_iret, asm_iret_error)
-SYM_CODE_END(native_iret)
-#endif
-
-#ifdef CONFIG_XEN_PV
-/*
- * See comment in entry_64.S for further explanation
- *
- * Note: This is not an actual IDT entry point. It's a XEN specific entry
- * point and therefore named to match the 64-bit trampoline counterpart.
- */
-SYM_FUNC_START(xen_asm_exc_xen_hypervisor_callback)
-	/*
-	 * Check to see if we got the event in the critical
-	 * region in xen_iret_direct, after we've reenabled
-	 * events and checked for pending events.  This simulates
-	 * iret instruction's behaviour where it delivers a
-	 * pending interrupt when enabling interrupts:
-	 */
-	cmpl	$xen_iret_start_crit, (%esp)
-	jb	1f
-	cmpl	$xen_iret_end_crit, (%esp)
-	jae	1f
-	call	xen_iret_crit_fixup
-1:
-	pushl	$-1				/* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-
-	mov	%esp, %eax
-	call	xen_pv_evtchn_do_upcall
-	jmp	handle_exception_return
-SYM_FUNC_END(xen_asm_exc_xen_hypervisor_callback)
-
-/*
- * Hypervisor uses this for application faults while it executes.
- * We get here for two reasons:
- *  1. Fault while reloading DS, ES, FS or GS
- *  2. Fault while executing IRET
- * Category 1 we fix up by reattempting the load, and zeroing the segment
- * register if the load fails.
- * Category 2 we fix up by jumping to do_iret_error. We cannot use the
- * normal Linux return path in this case because if we use the IRET hypercall
- * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
- * We distinguish between categories by maintaining a status value in EAX.
- */
-SYM_FUNC_START(xen_failsafe_callback)
-	pushl	%eax
-	movl	$1, %eax
-1:	mov	4(%esp), %ds
-2:	mov	8(%esp), %es
-3:	mov	12(%esp), %fs
-4:	mov	16(%esp), %gs
-	/* EAX == 0 => Category 1 (Bad segment)
-	   EAX != 0 => Category 2 (Bad IRET) */
-	testl	%eax, %eax
-	popl	%eax
-	lea	16(%esp), %esp
-	jz	5f
-	jmp	asm_iret_error
-5:	pushl	$-1				/* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	jmp	handle_exception_return
-
-.section .fixup, "ax"
-6:	xorl	%eax, %eax
-	movl	%eax, 4(%esp)
-	jmp	1b
-7:	xorl	%eax, %eax
-	movl	%eax, 8(%esp)
-	jmp	2b
-8:	xorl	%eax, %eax
-	movl	%eax, 12(%esp)
-	jmp	3b
-9:	xorl	%eax, %eax
-	movl	%eax, 16(%esp)
-	jmp	4b
-.previous
-	_ASM_EXTABLE(1b, 6b)
-	_ASM_EXTABLE(2b, 7b)
-	_ASM_EXTABLE(3b, 8b)
-	_ASM_EXTABLE(4b, 9b)
-SYM_FUNC_END(xen_failsafe_callback)
-#endif /* CONFIG_XEN_PV */
-
 SYM_CODE_START_LOCAL_NOALIGN(handle_exception)
 	/* the function address is in %gs's slot on the stack */
 	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index e31a75262c9c..9d1102873666 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -160,7 +160,7 @@
 146	i386	writev			sys_writev			compat_sys_writev
 147	i386	getsid			sys_getsid
 148	i386	fdatasync		sys_fdatasync
-149	i386	_sysctl			sys_sysctl			compat_sys_sysctl
+149	i386	_sysctl			sys_ni_syscall
 150	i386	mlock			sys_mlock
 151	i386	munlock			sys_munlock
 152	i386	mlockall		sys_mlockall
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9d82078c949a..f30d6ae9a688 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -164,7 +164,7 @@
 153	common	vhangup			sys_vhangup
 154	common	modify_ldt		sys_modify_ldt
 155	common	pivot_root		sys_pivot_root
-156	64	_sysctl			sys_sysctl
+156	64	_sysctl			sys_ni_syscall
 157	common	prctl			sys_prctl
 158	common	arch_prctl		sys_arch_prctl
 159	common	adjtimex		sys_adjtimex
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 04e65f0698f6..215376d975a2 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -82,7 +82,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 # optimize sibling calls.
 #
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
-       $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
+       $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
        -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
@@ -151,7 +151,7 @@ KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
-KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
+KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
index e78047d119f6..2cbd39939dc6 100644
--- a/arch/x86/entry/vdso/vdso32/note.S
+++ b/arch/x86/entry/vdso/vdso32/note.S
@@ -16,33 +16,3 @@ ELFNOTE_START(Linux, 0, "a")
 ELFNOTE_END
 
 BUILD_SALT
-
-#ifdef CONFIG_XEN
-/*
- * Add a special note telling glibc's dynamic linker a fake hardware
- * flavor that it will use to choose the search path for libraries in the
- * same way it uses real hardware capabilities like "mmx".
- * We supply "nosegneg" as the fake capability, to indicate that we
- * do not like negative offsets in instructions using segment overrides,
- * since we implement those inefficiently.  This makes it possible to
- * install libraries optimized to avoid those access patterns in someplace
- * like /lib/i686/tls/nosegneg.  Note that an /etc/ld.so.conf.d/file
- * corresponding to the bits here is needed to make ldconfig work right.
- * It should contain:
- *	hwcap 1 nosegneg
- * to match the mapping of bit to name that we give here.
- *
- * At runtime, the fake hardware feature will be considered to be present
- * if its bit is set in the mask word.  So, we start with the mask 0, and
- * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
- */
-
-#include "../../xen/vdso.h"	/* Defines VDSO_NOTE_NONEGSEG_BIT.  */
-
-ELFNOTE_START(GNU, 2, "a")
-	.long 1			/* ncaps */
-VDSO32_NOTE_MASK:		/* Symbol used by arch/x86/xen/setup.c */
-	.long 0			/* mask */
-	.byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg"	/* bit, name */
-ELFNOTE_END
-#endif
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 68b38820b10e..67b411f7e8c4 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -130,11 +130,17 @@ struct rapl_pmus {
 	struct rapl_pmu		*pmus[];
 };
 
+enum rapl_unit_quirk {
+	RAPL_UNIT_QUIRK_NONE,
+	RAPL_UNIT_QUIRK_INTEL_HSW,
+	RAPL_UNIT_QUIRK_INTEL_SPR,
+};
+
 struct rapl_model {
 	struct perf_msr *rapl_msrs;
 	unsigned long	events;
 	unsigned int	msr_power_unit;
-	bool		apply_quirk;
+	enum rapl_unit_quirk	unit_quirk;
 };
 
  /* 1/2^hw_unit Joule */
@@ -612,14 +618,28 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
+	switch (rm->unit_quirk) {
 	/*
 	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
 	 * different than the unit from power unit MSR. See
 	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
-	if (rm->apply_quirk)
+	case RAPL_UNIT_QUIRK_INTEL_HSW:
+		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		break;
+	/*
+	 * SPR shares the same DRAM domain energy unit as HSW, plus it
+	 * also has a fixed energy unit for Psys domain.
+	 */
+	case RAPL_UNIT_QUIRK_INTEL_SPR:
 		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		rapl_hw_unit[PERF_RAPL_PSYS] = 0;
+		break;
+	default:
+		break;
+	}
+
 
 	/*
 	 * Calculate the timer rate:
@@ -665,7 +685,7 @@ static const struct attribute_group *rapl_attr_update[] = {
 	&rapl_events_pkg_group,
 	&rapl_events_ram_group,
 	&rapl_events_gpu_group,
-	&rapl_events_gpu_group,
+	&rapl_events_psys_group,
 	NULL,
 };
 
@@ -698,7 +718,6 @@ static struct rapl_model model_snb = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -707,7 +726,6 @@ static struct rapl_model model_snbep = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -717,7 +735,6 @@ static struct rapl_model model_hsw = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -726,7 +743,7 @@ static struct rapl_model model_hsx = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -734,7 +751,7 @@ static struct rapl_model model_hsx = {
 static struct rapl_model model_knl = {
 	.events		= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -745,14 +762,22 @@ static struct rapl_model model_skl = {
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
-	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
+};
+
+static struct rapl_model model_spr = {
+	.events		= BIT(PERF_RAPL_PP0) |
+			  BIT(PERF_RAPL_PKG) |
+			  BIT(PERF_RAPL_RAM) |
+			  BIT(PERF_RAPL_PSYS),
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_SPR,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_amd_fam17h = {
 	.events		= BIT(PERF_RAPL_PKG),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
 	.rapl_msrs      = amd_rapl_msrs,
 };
@@ -787,6 +812,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
 	X86_MATCH_VENDOR_FAM(AMD,	0x17,		&model_amd_fam17h),
 	X86_MATCH_VENDOR_FAM(HYGON,	0x18,		&model_amd_fam17h),
 	{},
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 49bd6cf3eec9..7c0a52ca2f4d 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -3,9 +3,6 @@
 #define _ASM_X86_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_IOMMU_API
-	void *iommu; /* hook for IOMMU specific extension */
-#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b9527a54db99..0f0dd645b594 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -26,9 +26,9 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
-#include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
+#include <asm/pgtable_types.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 60b944dd2df1..4f77b8f22e54 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -8,6 +8,7 @@
 #include <asm/io.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
+#include <asm/paravirt.h>
 
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
@@ -54,6 +55,17 @@ typedef int (*hyperv_fill_flush_list_func)(
 	vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
 #define hv_get_raw_timer() rdtsc_ordered()
 
+/*
+ * Reference to pv_ops must be inline so objtool
+ * detection of noinstr violations can work correctly.
+ */
+static __always_inline void hv_setup_sched_clock(void *sched_clock)
+{
+#ifdef CONFIG_PARAVIRT
+	pv_ops.time.sched_clock = sched_clock;
+#endif
+}
+
 void hyperv_vector_handler(struct pt_regs *regs);
 
 static inline void hv_enable_stimer0_percpu_irq(int irq) {}
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 6e81788a30c1..28996fe19301 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -25,7 +25,7 @@ void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
 void entry_INT80_compat(void);
-#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+#ifdef CONFIG_XEN_PV
 void xen_entry_INT80_compat(void);
 #endif
 #endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 6669164abadc..9646c300f128 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -301,7 +301,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+#ifdef CONFIG_XEN_PV
 extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
 #endif
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index e15f364efbcc..c0538f82c9a2 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -5,16 +5,6 @@
 #include <linux/cpumask.h>
 #include <asm/percpu.h>
 
-/*
- * We need the APIC definitions automatically as part of 'smp.h'
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-# include <asm/mpspec.h>
-# include <asm/apic.h>
-# ifdef CONFIG_X86_IO_APIC
-#  include <asm/io_apic.h>
-# endif
-#endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
 
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index b7b2624fba86..01a300a9700b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -6,6 +6,7 @@
 #define _ASM_X86_TSC_H
 
 #include <asm/processor.h>
+#include <asm/cpufeature.h>
 
 /*
  * Standard way to access the cycle counter.
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2f3e8f2a958f..ecefaffd15d4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,7 +33,7 @@ static inline void set_fs(mm_segment_t fs)
 	set_thread_flag(TIF_FSCHECK);
 }
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #define user_addr_max() (current->thread.addr_limit.seg)
 
 /*
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index fb81fea99093..df01d7349d79 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -241,7 +241,8 @@ static u64 vread_hvclock(void)
 }
 #endif
 
-static inline u64 __arch_get_hw_counter(s32 clock_mode)
+static inline u64 __arch_get_hw_counter(s32 clock_mode,
+					const struct vdso_data *vd)
 {
 	if (likely(clock_mode == VDSO_CLOCKMODE_TSC))
 		return (u64)rdtsc_ordered();
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index d1175533d125..c3daf0aaa0ee 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -875,8 +875,6 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
 
-	local_irq_save(flags);
-
 	/*
 	 * Map the page without the global bit, as TLB flushing is done with
 	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
@@ -893,6 +891,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	VM_BUG_ON(!ptep);
 
+	local_irq_save(flags);
+
 	pte = mk_pte(pages[0], pgprot);
 	set_pte_at(poking_mm, poking_addr, ptep, pte);
 
@@ -942,8 +942,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	BUG_ON(memcmp(addr, opcode, len));
 
-	pte_unmap_unlock(ptep, ptl);
 	local_irq_restore(flags);
+	pte_unmap_unlock(ptep, ptl);
 	return addr;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ccf726cc87b7..5f943b938167 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -46,6 +46,7 @@
 #include <asm/proto.h>
 #include <asm/traps.h>
 #include <asm/apic.h>
+#include <asm/acpi.h>
 #include <asm/io_apic.h>
 #include <asm/desc.h>
 #include <asm/hpet.h>
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 98c9bb75d185..780c702969b7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -10,6 +10,7 @@
  * like self-ipi, etc...
  */
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 
 #include <asm/apic.h>
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 38b5b51d42f6..98d015a4405a 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -9,6 +9,7 @@
 #include <linux/smp.h>
 
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 
 #include "local.h"
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d1fc62a67320..34a992e275ef 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *  Bits copied from original nmi.c file
  *
  */
+#include <linux/thread_info.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
 
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 6ca0f91372fd..387154e39e08 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -2,6 +2,7 @@
 
 #include <linux/cpumask.h>
 #include <linux/smp.h>
+#include <asm/io_apic.h>
 
 #include "local.h"
 
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 04797f05ce94..a997d849509a 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -10,6 +10,7 @@
 
 #include <linux/jump_label.h>
 
+#include <asm/irq_vectors.h>
 #include <asm/apic.h>
 
 /* APIC flat 64 */
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 67b33d67002f..7bda71def557 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
+#include <asm/io_apic.h>
 #include <asm/apic.h>
 #include <asm/acpi.h>
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 29f0e0984557..bd3835d6b535 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -8,6 +8,7 @@
  * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
  * James Cleverdon.
  */
+#include <linux/thread_info.h>
 #include <asm/apic.h>
 
 #include "local.h"
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index dba6a83bc349..93792b457b81 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,8 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n
 KCSAN_SANITIZE_common.o := n
 
 # Make sure load_percpu_segment has no stackprotector
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_common.o		:= $(nostackp)
+CFLAGS_common.o		:= -fno-stack-protector
 
 obj-y			:= cacheinfo.o scattered.o topology.o
 obj-y			+= common.o
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 1da9b1c9a2db..0b2c03943ac6 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -11,14 +11,15 @@
 
 #include <linux/interrupt.h>
 #include <asm/apic.h>
+#include <asm/cpufeatures.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
 #include <asm/idtentry.h>
 #include <asm/irq_regs.h>
 
-static uint32_t __init acrn_detect(void)
+static u32 __init acrn_detect(void)
 {
-	return hypervisor_cpuid_base("ACRNACRNACRN\0\0", 0);
+	return hypervisor_cpuid_base("ACRNACRNACRN", 0);
 }
 
 static void __init acrn_init_platform(void)
@@ -29,12 +30,7 @@ static void __init acrn_init_platform(void)
 
 static bool acrn_x2apic_available(void)
 {
-	/*
-	 * x2apic is not supported for now. Future enablement will have to check
-	 * X86_FEATURE_X2APIC to determine whether x2apic is supported in the
-	 * guest.
-	 */
-	return false;
+	return boot_cpu_has(X86_FEATURE_X2APIC);
 }
 
 static void (*acrn_intr_handler)(void);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d4806eac9325..dcc3d943c68f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -15,6 +15,7 @@
 #include <asm/cpu.h>
 #include <asm/spec-ctrl.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index f0b743a2fe9c..d3f0db463f96 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -31,6 +31,7 @@
 #include <asm/intel-family.h>
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
+#include <asm/tlbflush.h>
 
 #include "cpu.h"
 
@@ -1549,7 +1550,12 @@ static ssize_t l1tf_show_state(char *buf)
 
 static ssize_t itlb_multihit_show_state(char *buf)
 {
-	if (itlb_multihit_kvm_mitigation)
+	if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
+	    !boot_cpu_has(X86_FEATURE_VMX))
+		return sprintf(buf, "KVM: Mitigation: VMX unsupported\n");
+	else if (!(cr4_read_shadow() & X86_CR4_VMXE))
+		return sprintf(buf, "KVM: Mitigation: VMX disabled\n");
+	else if (itlb_multihit_kvm_mitigation)
 		return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
 	else
 		return sprintf(buf, "KVM: Vulnerable\n");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 965474d78cef..c5d6f17d9b9d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -45,6 +45,7 @@
 #include <asm/mtrr.h>
 #include <asm/hwcap2.h>
 #include <linux/numa.h>
+#include <asm/numa.h>
 #include <asm/asm.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 4e28c1fc8749..ac6c30e5801d 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -10,6 +10,7 @@
 
 #include <asm/cpu.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 #include <asm/cacheinfo.h>
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b6b7b38dff5f..59a1e3ce3f14 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -23,6 +23,7 @@
 #include <asm/cmdline.h>
 #include <asm/traps.h>
 #include <asm/resctrl.h>
+#include <asm/numa.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index af94f05a5c66..31125448b174 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -361,13 +361,6 @@ static void __init ms_hyperv_init_platform(void)
 #endif
 }
 
-void hv_setup_sched_clock(void *sched_clock)
-{
-#ifdef CONFIG_PARAVIRT
-	pv_ops.time.sched_clock = sched_clock;
-#endif
-}
-
 const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
 	.name			= "Microsoft Hyper-V",
 	.detect			= ms_hyperv_platform,
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index fd87b59452a3..a8f3af257e26 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -230,7 +230,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
 	int ret = 0;
 
 	/* Exclude the low 1M because it is always reserved */
-	ret = crash_exclude_mem_range(cmem, 0, 1<<20);
+	ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1);
 	if (ret)
 		return ret;
 
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 8d85e00bb40a..a0e8fc7d85f1 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -20,6 +20,7 @@
 #include <asm/irqdomain.h>
 #include <asm/hpet.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/pci_x86.h>
 #include <asm/setup.h>
 #include <asm/i8259.h>
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 7a2bf884fede..038e19c0019e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -611,6 +611,10 @@ static void check_xstate_against_struct(int nr)
  * This essentially double-checks what the cpu told us about
  * how large the XSAVE buffer needs to be.  We are recalculating
  * it to be safe.
+ *
+ * Dynamic XSAVE features allocate their own buffers and are not
+ * covered by these checks. Only the size of the buffer for task->fpu
+ * is checked here.
  */
 static void do_extra_xstate_size_checks(void)
 {
@@ -673,6 +677,33 @@ static unsigned int __init get_xsaves_size(void)
 	return ebx;
 }
 
+/*
+ * Get the total size of the enabled xstates without the dynamic supervisor
+ * features.
+ */
+static unsigned int __init get_xsaves_size_no_dynamic(void)
+{
+	u64 mask = xfeatures_mask_dynamic();
+	unsigned int size;
+
+	if (!mask)
+		return get_xsaves_size();
+
+	/* Disable dynamic features. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+
+	/*
+	 * Ask the hardware what size is required of the buffer.
+	 * This is the size required for the task->fpu buffer.
+	 */
+	size = get_xsaves_size();
+
+	/* Re-enable dynamic features so XSAVES will work on them again. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+
+	return size;
+}
+
 static unsigned int __init get_xsave_size(void)
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -710,7 +741,7 @@ static int __init init_xstate_size(void)
 	xsave_size = get_xsave_size();
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		possible_xstate_size = get_xsaves_size();
+		possible_xstate_size = get_xsaves_size_no_dynamic();
 	else
 		possible_xstate_size = xsave_size;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index f66a6b90f954..7ed84c282233 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -134,38 +134,7 @@ SYM_CODE_START(startup_32)
 	movl %eax,pa(initial_page_table+0xffc)
 #endif
 
-#ifdef CONFIG_PARAVIRT
-	/* This is can only trip for a broken bootloader... */
-	cmpw $0x207, pa(boot_params + BP_version)
-	jb .Ldefault_entry
-
-	/* Paravirt-compatible boot parameters.  Look to see what architecture
-		we're booting under. */
-	movl pa(boot_params + BP_hardware_subarch), %eax
-	cmpl $num_subarch_entries, %eax
-	jae .Lbad_subarch
-
-	movl pa(subarch_entries)(,%eax,4), %eax
-	subl $__PAGE_OFFSET, %eax
-	jmp *%eax
-
-.Lbad_subarch:
-SYM_INNER_LABEL_ALIGN(xen_entry, SYM_L_WEAK)
-	/* Unknown implementation; there's really
-	   nothing we can do at this point. */
-	ud2a
-
-	__INITDATA
-
-subarch_entries:
-	.long .Ldefault_entry		/* normal x86/PC */
-	.long xen_entry			/* Xen hypervisor */
-	.long .Ldefault_entry		/* Moorestown MID */
-num_subarch_entries = (. - subarch_entries) / 4
-.previous
-#else
 	jmp .Ldefault_entry
-#endif /* CONFIG_PARAVIRT */
 SYM_CODE_END(startup_32)
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index dd73135d7cee..beb1bada1b0a 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -22,6 +22,8 @@
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
 #include <asm/desc.h>
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
 #include <asm/apic.h>
 #include <asm/setup.h>
 #include <asm/i8259.h>
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 6eb8b50ea07e..4eb8f2d19a87 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -13,6 +13,8 @@
 #include <linux/reboot.h>
 #include <linux/serial_8250.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
 #include <asm/cpu.h>
 #include <asm/hypervisor.h>
 #include <asm/i8259.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index c27b82b62c8b..411af4aa7b51 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,6 +19,8 @@
 #include <linux/smp.h>
 #include <linux/pci.h>
 
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
 #include <asm/irqdomain.h>
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index d6f946707270..9afefe325acb 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -390,7 +390,7 @@ unsigned long x86_fsgsbase_read_task(struct task_struct *task,
 		 */
 		mutex_lock(&task->mm->context.lock);
 		ldt = task->mm->context.ldt;
-		if (unlikely(idx >= ldt->nr_entries))
+		if (unlikely(!ldt || idx >= ldt->nr_entries))
 			base = 0;
 		else
 			base = get_desc_base(ldt->entries + idx);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b9a68d8e06d8..3511736fbc74 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -25,6 +25,7 @@
 #include <xen/xen.h>
 
 #include <asm/apic.h>
+#include <asm/numa.h>
 #include <asm/bios_ebda.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index b8810ebbc8ae..0a2ec801b63f 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -31,6 +31,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
+#include <asm/io_apic.h>
 #include <asm/cpu.h>
 
 static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 4fec6f3a1858..6555a857a1e6 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/thread_info.h>
 
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
@@ -133,10 +134,15 @@ static const struct freq_desc freq_desc_ann = {
 	.mask = 0x0f,
 };
 
-/* 24 MHz crystal? : 24 * 13 / 4 = 78 MHz */
+/*
+ * 24 MHz crystal? : 24 * 13 / 4 = 78 MHz
+ * Frequency step for Lightning Mountain SoC is fixed to 78 MHz,
+ * so all the frequency entries are 78000.
+ */
 static const struct freq_desc freq_desc_lgm = {
 	.use_msr_plat = true,
-	.freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 },
+	.freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000,
+		   78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 },
 	.mask = 0x0f,
 };
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 539ea1cd6020..432ef34b9ea9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3581,6 +3581,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = sched_info_on();
+		break;
 	default:
 		break;
 	}
@@ -10667,11 +10670,17 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	int ret;
 
 	irqfd->producer = prod;
+	kvm_arch_start_assignment(irqfd->kvm);
+	ret = kvm_x86_ops.update_pi_irte(irqfd->kvm,
+					 prod->irq, irqfd->gsi, 1);
+
+	if (ret)
+		kvm_arch_end_assignment(irqfd->kvm);
 
-	return kvm_x86_ops.update_pi_irte(irqfd->kvm,
-					   prod->irq, irqfd->gsi, 1);
+	return ret;
 }
 
 void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
@@ -10694,6 +10703,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
+
+	kvm_arch_end_assignment(irqfd->kvm);
 }
 
 int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 6110bce7237b..d46fff11f06f 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_cmdline.o = -pg
 endif
 
-CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+CFLAGS_cmdline.o := -fno-stack-protector
 endif
 
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index f7fd0e868c9c..5864219221ca 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -22,10 +22,9 @@ obj-y				:=  init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
 obj-y				+= pat/
 
 # Make sure __phys_addr has no stackprotector
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_physaddr.o		:= $(nostackp)
-CFLAGS_setup_nx.o		:= $(nostackp)
-CFLAGS_mem_encrypt_identity.o	:= $(nostackp)
+CFLAGS_physaddr.o		:= -fno-stack-protector
+CFLAGS_setup_nx.o		:= -fno-stack-protector
+CFLAGS_mem_encrypt_identity.o	:= -fno-stack-protector
 
 CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 0c7643d9f7cb..35f1498e9832 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1139,7 +1139,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
 	struct mm_struct *mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_DEFAULT;
 
 	tsk = current;
@@ -1291,8 +1291,7 @@ good_area:
 	 * userland). The return to userland is identified whenever
 	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -1319,18 +1318,6 @@ good_area:
 		return;
 	}
 
-	/*
-	 * Major/minor page fault accounting. If any of the events
-	 * returned VM_FAULT_MAJOR, we account it as a major fault.
-	 */
-	if (major) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
-
 	check_v8086_mode(regs, address, tsk);
 }
 NOKPROBE_SYMBOL(do_user_addr_fault);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4cb958419fb0..7c055259de3a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -52,6 +52,7 @@
 #include <asm/cpu_entry_area.h>
 #include <asm/init.h>
 #include <asm/pgtable_areas.h>
+#include <asm/numa.h>
 
 #include "mm_internal.h"
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3b246ae40c8f..a4ac13cc3fdc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1452,6 +1452,15 @@ static unsigned long probe_memory_block_size(void)
 		goto done;
 	}
 
+	/*
+	 * Use max block size to minimize overhead on bare metal, where
+	 * alignment for memory hotplug isn't a concern.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
+
 	/* Find the largest allowed block size that aligns to memory end */
 	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
 		if (IS_ALIGNED(boot_mem_end, bz))
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index b05f45e5e8e2..aa76ec2d359b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -929,5 +929,4 @@ int memory_add_physaddr_to_nid(u64 start)
 		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index 37923d715741..6907b523e856 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -3,8 +3,7 @@ OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y
 
 # __restore_processor_state() restores %gs after S3 resume and so should not
 # itself be stack-protected
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_cpu.o	:= $(nostackp)
+CFLAGS_cpu.o	:= -fno-stack-protector
 
 obj-$(CONFIG_PM_SLEEP)		+= cpu.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 088bd764e0b7..95ea17a9d20c 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -32,9 +32,9 @@ KCOV_INSTRUMENT := n
 # make up the standalone purgatory.ro
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
-PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
-PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector)
+PURGATORY_CFLAGS += -fno-stack-protector
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
@@ -64,6 +64,9 @@ CFLAGS_sha256.o			+= $(PURGATORY_CFLAGS)
 CFLAGS_REMOVE_string.o		+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_string.o			+= $(PURGATORY_CFLAGS)
 
+AFLAGS_REMOVE_setup-x86_$(BITS).o	+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_entry64.o			+= -Wa,-gdwarf-2
+
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 0caddd6acb22..5943387e3f35 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -42,7 +42,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 # optimize sibling calls.
 #
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
-       $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
+       $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
        -fno-omit-frame-pointer -foptimize-sibling-calls
 
 $(vobjs): KBUILD_CFLAGS += $(CFL)
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 1aded63a95cb..218acbd5c7a0 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -19,6 +19,7 @@ config XEN_PV
 	bool "Xen PV guest support"
 	default y
 	depends on XEN
+	depends on X86_64
 	select PARAVIRT_XXL
 	select XEN_HAVE_PVMMU
 	select XEN_HAVE_VPMU
@@ -50,7 +51,7 @@ config XEN_PVHVM_SMP
 
 config XEN_512GB
 	bool "Limit Xen pv-domain memory to 512GB"
-	depends on XEN_PV && X86_64
+	depends on XEN_PV
 	default y
 	help
 	  Limit paravirtualized user domains to 512GB of RAM.
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 084de77a109e..fc5c5ba4aacb 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y
+OBJECT_FILES_NON_STANDARD_xen-asm.o := y
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
@@ -9,9 +9,8 @@ CFLAGS_REMOVE_irq.o = -pg
 endif
 
 # Make sure early boot has no stackprotector
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_enlighten_pv.o		:= $(nostackp)
-CFLAGS_mmu_pv.o			:= $(nostackp)
+CFLAGS_enlighten_pv.o		:= -fno-stack-protector
+CFLAGS_mmu_pv.o			:= -fno-stack-protector
 
 obj-y				+= enlighten.o
 obj-y				+= mmu.o
@@ -34,7 +33,6 @@ obj-$(CONFIG_XEN_PV)		+= mmu_pv.o
 obj-$(CONFIG_XEN_PV)		+= irq.o
 obj-$(CONFIG_XEN_PV)		+= multicalls.o
 obj-$(CONFIG_XEN_PV)		+= xen-asm.o
-obj-$(CONFIG_XEN_PV)		+= xen-asm_$(BITS).o
 
 obj-$(CONFIG_XEN_PVH)		+= enlighten_pvh.o
 
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 5e53bfbe5823..e82fd1910dae 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
+#include <linux/thread_info.h>
 
 #include <asm/x86_init.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/xen/hypercall.h>
 
 #include <xen/xen.h>
@@ -58,10 +60,6 @@ static u32 xen_apic_read(u32 reg)
 
 	if (reg == APIC_LVR)
 		return 0x14;
-#ifdef CONFIG_X86_32
-	if (reg == APIC_LDR)
-		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-#endif
 	if (reg != APIC_ID)
 		return 0;
 
@@ -127,14 +125,6 @@ static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
 	return initial_apic_id >> index_msb;
 }
 
-#ifdef CONFIG_X86_32
-static int xen_x86_32_early_logical_apicid(int cpu)
-{
-	/* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */
-	return 1 << cpu;
-}
-#endif
-
 static void xen_noop(void)
 {
 }
@@ -197,11 +187,6 @@ static struct apic xen_pv_apic = {
 	.icr_write 			= xen_apic_icr_write,
 	.wait_icr_idle 			= xen_noop,
 	.safe_wait_icr_idle 		= xen_safe_apic_wait_icr_idle,
-
-#ifdef CONFIG_X86_32
-	/* generic_processor_info and setup_local_APIC. */
-	.x86_32_early_logical_apicid	= xen_x86_32_early_logical_apicid,
-#endif
 };
 
 static void __init xen_apic_check(void)
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 3e89b0067ff0..9e87ab010c82 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -11,6 +11,7 @@
 
 #include <asm/cpu.h>
 #include <asm/smp.h>
+#include <asm/io_apic.h>
 #include <asm/reboot.h>
 #include <asm/setup.h>
 #include <asm/idtentry.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 2aab43a13a8c..22e741e0b10c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -119,14 +119,6 @@ static void __init xen_banner(void)
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
-
-#ifdef CONFIG_X86_32
-	pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"
-		"Support for running as 32-bit PV-guest under Xen will soon be removed\n"
-		"from the Linux kernel!\n"
-		"Please use either a 64-bit kernel or switch to HVM or PVH mode!\n"
-		"WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n");
-#endif
 }
 
 static void __init xen_pv_init_platform(void)
@@ -353,15 +345,13 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	pte_t *ptep;
 	pte_t pte;
 	unsigned long pfn;
-	struct page *page;
 	unsigned char dummy;
+	void *va;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
 
 	pfn = pte_pfn(*ptep);
-	page = pfn_to_page(pfn);
-
 	pte = pfn_pte(pfn, prot);
 
 	/*
@@ -391,14 +381,10 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
-	if (!PageHighMem(page)) {
-		void *av = __va(PFN_PHYS(pfn));
+	va = __va(PFN_PHYS(pfn));
 
-		if (av != v)
-			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
-				BUG();
-	} else
-		kmap_flush_unused();
+	if (va != v && HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+		BUG();
 
 	preempt_enable();
 }
@@ -538,30 +524,12 @@ static void load_TLS_descriptor(struct thread_struct *t,
 static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 {
 	/*
-	 * XXX sleazy hack: If we're being called in a lazy-cpu zone
-	 * and lazy gs handling is enabled, it means we're in a
-	 * context switch, and %gs has just been saved.  This means we
-	 * can zero it out to prevent faults on exit from the
-	 * hypervisor if the next process has no %gs.  Either way, it
-	 * has been saved, and the new value will get loaded properly.
-	 * This will go away as soon as Xen has been modified to not
-	 * save/restore %gs for normal hypercalls.
-	 *
-	 * On x86_64, this hack is not used for %gs, because gs points
-	 * to KERNEL_GS_BASE (and uses it for PDA references), so we
-	 * must not zero %gs on x86_64
-	 *
-	 * For x86_64, we need to zero %fs, otherwise we may get an
+	 * In lazy mode we need to zero %fs, otherwise we may get an
 	 * exception between the new %fs descriptor being loaded and
 	 * %fs being effectively cleared at __switch_to().
 	 */
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-#ifdef CONFIG_X86_32
-		lazy_load_gs(0);
-#else
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
 		loadsegment(fs, 0);
-#endif
-	}
 
 	xen_mc_batch();
 
@@ -572,13 +540,11 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 
-#ifdef CONFIG_X86_64
 static void xen_load_gs_index(unsigned int idx)
 {
 	if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
 		BUG();
 }
-#endif
 
 static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 				const void *ptr)
@@ -597,7 +563,6 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 	preempt_enable();
 }
 
-#ifdef CONFIG_X86_64
 void noist_exc_debug(struct pt_regs *regs);
 
 DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
@@ -697,7 +662,6 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist)
 
 	return true;
 }
-#endif
 
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
 			    struct trap_info *info)
@@ -710,10 +674,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 	info->vector = vector;
 
 	addr = gate_offset(val);
-#ifdef CONFIG_X86_64
 	if (!get_trap_addr((void **)&addr, val->bits.ist))
 		return 0;
-#endif	/* CONFIG_X86_64 */
 	info->address = addr;
 
 	info->cs = gate_segment(val);
@@ -958,15 +920,12 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
-#ifdef CONFIG_X86_64
 	unsigned int which;
 	u64 base;
-#endif
 
 	ret = 0;
 
 	switch (msr) {
-#ifdef CONFIG_X86_64
 	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
 	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
 	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
@@ -976,7 +935,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		if (HYPERVISOR_set_segment_base(which, base) != 0)
 			ret = -EIO;
 		break;
-#endif
 
 	case MSR_STAR:
 	case MSR_CSTAR:
@@ -1058,9 +1016,7 @@ void __init xen_setup_vcpu_info_placement(void)
 static const struct pv_info xen_info __initconst = {
 	.shared_kernel_pmd = 0,
 
-#ifdef CONFIG_X86_64
 	.extra_user_64bit_cs = FLAT_USER_CS64,
-#endif
 	.name = "Xen",
 };
 
@@ -1086,18 +1042,14 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
-#ifdef CONFIG_X86_64
 	.usergs_sysret64 = xen_sysret64,
-#endif
 
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
 	.load_gdt = xen_load_gdt,
 	.load_idt = xen_load_idt,
 	.load_tls = xen_load_tls,
-#ifdef CONFIG_X86_64
 	.load_gs_index = xen_load_gs_index,
-#endif
 
 	.alloc_ldt = xen_alloc_ldt,
 	.free_ldt = xen_free_ldt,
@@ -1364,15 +1316,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* keep using Xen gdt for now; no urgent need to change it */
 
-#ifdef CONFIG_X86_32
-	pv_info.kernel_rpl = 1;
-	if (xen_feature(XENFEAT_supervisor_mode_kernel))
-		pv_info.kernel_rpl = 0;
-#else
 	pv_info.kernel_rpl = 0;
-#endif
-	/* set the limit of our address space */
-	xen_reserve_top();
 
 	/*
 	 * We used to do this in xen_arch_setup, but that is too late
@@ -1384,12 +1328,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	if (rc != 0)
 		xen_raw_printk("physdev_op failed %d\n", rc);
 
-#ifdef CONFIG_X86_32
-	/* set up basic CPUID stuff */
-	cpu_detect(&new_cpu_data);
-	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
-	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
-#endif
 
 	if (xen_start_info->mod_start) {
 	    if (xen_start_info->flags & SIF_MOD_START_PFN)
@@ -1458,12 +1396,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_efi_init(&boot_params);
 
 	/* Start the world */
-#ifdef CONFIG_X86_32
-	i386_start_kernel();
-#else
 	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
-#endif
 }
 
 static int xen_cpu_up_prepare_pv(unsigned int cpu)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index a58d9c69807a..3273c985d3dd 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -86,19 +86,8 @@
 #include "mmu.h"
 #include "debugfs.h"
 
-#ifdef CONFIG_X86_32
-/*
- * Identity map, in addition to plain kernel map.  This needs to be
- * large enough to allocate page table pages to allocate the rest.
- * Each page can map 2MB.
- */
-#define LEVEL1_IDENT_ENTRIES	(PTRS_PER_PTE * 4)
-static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-#endif
-#ifdef CONFIG_X86_64
 /* l3 pud for userspace vsyscall mapping */
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
-#endif /* CONFIG_X86_64 */
 
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
@@ -280,10 +269,7 @@ static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
 	if (!xen_batched_set_pte(ptep, pteval)) {
 		/*
 		 * Could call native_set_pte() here and trap and
-		 * emulate the PTE write but with 32-bit guests this
-		 * needs two traps (one for each of the two 32-bit
-		 * words in the PTE) so do one hypercall directly
-		 * instead.
+		 * emulate the PTE write, but a hypercall is much cheaper.
 		 */
 		struct mmu_update u;
 
@@ -439,26 +425,6 @@ static void xen_set_pud(pud_t *ptr, pud_t val)
 	xen_set_pud_hyper(ptr, val);
 }
 
-#ifdef CONFIG_X86_PAE
-static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	trace_xen_mmu_set_pte_atomic(ptep, pte);
-	__xen_set_pte(ptep, pte);
-}
-
-static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	trace_xen_mmu_pte_clear(mm, addr, ptep);
-	__xen_set_pte(ptep, native_make_pte(0));
-}
-
-static void xen_pmd_clear(pmd_t *pmdp)
-{
-	trace_xen_mmu_pmd_clear(pmdp);
-	set_pmd(pmdp, __pmd(0));
-}
-#endif	/* CONFIG_X86_PAE */
-
 __visible pmd_t xen_make_pmd(pmdval_t pmd)
 {
 	pmd = pte_pfn_to_mfn(pmd);
@@ -466,7 +432,6 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
 
-#ifdef CONFIG_X86_64
 __visible pudval_t xen_pud_val(pud_t pud)
 {
 	return pte_mfn_to_pfn(pud.pud);
@@ -571,27 +536,27 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
 #endif  /* CONFIG_PGTABLE_LEVELS >= 5 */
-#endif	/* CONFIG_X86_64 */
 
-static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
+static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
+			 void (*func)(struct mm_struct *mm, struct page *,
+				      enum pt_level),
+			 bool last, unsigned long limit)
 {
-	int i, nr, flush = 0;
+	int i, nr;
 
 	nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD;
 	for (i = 0; i < nr; i++) {
 		if (!pmd_none(pmd[i]))
-			flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE);
+			(*func)(mm, pmd_page(pmd[i]), PT_PTE);
 	}
-	return flush;
 }
 
-static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
+static void xen_pud_walk(struct mm_struct *mm, pud_t *pud,
+			 void (*func)(struct mm_struct *mm, struct page *,
+				      enum pt_level),
+			 bool last, unsigned long limit)
 {
-	int i, nr, flush = 0;
+	int i, nr;
 
 	nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD;
 	for (i = 0; i < nr; i++) {
@@ -602,29 +567,26 @@ static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
 
 		pmd = pmd_offset(&pud[i], 0);
 		if (PTRS_PER_PMD > 1)
-			flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
-		flush |= xen_pmd_walk(mm, pmd, func,
-				last && i == nr - 1, limit);
+			(*func)(mm, virt_to_page(pmd), PT_PMD);
+		xen_pmd_walk(mm, pmd, func, last && i == nr - 1, limit);
 	}
-	return flush;
 }
 
-static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
-		int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
-		bool last, unsigned long limit)
+static void xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
+			 void (*func)(struct mm_struct *mm, struct page *,
+				      enum pt_level),
+			 bool last, unsigned long limit)
 {
-	int flush = 0;
 	pud_t *pud;
 
 
 	if (p4d_none(*p4d))
-		return flush;
+		return;
 
 	pud = pud_offset(p4d, 0);
 	if (PTRS_PER_PUD > 1)
-		flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
-	flush |= xen_pud_walk(mm, pud, func, last, limit);
-	return flush;
+		(*func)(mm, virt_to_page(pud), PT_PUD);
+	xen_pud_walk(mm, pud, func, last, limit);
 }
 
 /*
@@ -636,32 +598,27 @@ static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
  * will be STACK_TOP_MAX, but at boot we need to pin up to
  * FIXADDR_TOP.
  *
- * For 32-bit the important bit is that we don't pin beyond there,
- * because then we start getting into Xen's ptes.
- *
- * For 64-bit, we must skip the Xen hole in the middle of the address
- * space, just after the big x86-64 virtual hole.
+ * We must skip the Xen hole in the middle of the address space, just after
+ * the big x86-64 virtual hole.
  */
-static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
-			  int (*func)(struct mm_struct *mm, struct page *,
-				      enum pt_level),
-			  unsigned long limit)
+static void __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
+			   void (*func)(struct mm_struct *mm, struct page *,
+					enum pt_level),
+			   unsigned long limit)
 {
-	int i, nr, flush = 0;
+	int i, nr;
 	unsigned hole_low = 0, hole_high = 0;
 
 	/* The limit is the last byte to be touched */
 	limit--;
 	BUG_ON(limit >= FIXADDR_TOP);
 
-#ifdef CONFIG_X86_64
 	/*
 	 * 64-bit has a great big hole in the middle of the address
 	 * space, which contains the Xen mappings.
 	 */
 	hole_low = pgd_index(GUARD_HOLE_BASE_ADDR);
 	hole_high = pgd_index(GUARD_HOLE_END_ADDR);
-#endif
 
 	nr = pgd_index(limit) + 1;
 	for (i = 0; i < nr; i++) {
@@ -674,22 +631,20 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 			continue;
 
 		p4d = p4d_offset(&pgd[i], 0);
-		flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
+		xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
 	}
 
 	/* Do the top level last, so that the callbacks can use it as
 	   a cue to do final things like tlb flushes. */
-	flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
-
-	return flush;
+	(*func)(mm, virt_to_page(pgd), PT_PGD);
 }
 
-static int xen_pgd_walk(struct mm_struct *mm,
-			int (*func)(struct mm_struct *mm, struct page *,
-				    enum pt_level),
-			unsigned long limit)
+static void xen_pgd_walk(struct mm_struct *mm,
+			 void (*func)(struct mm_struct *mm, struct page *,
+				      enum pt_level),
+			 unsigned long limit)
 {
-	return __xen_pgd_walk(mm, mm->pgd, func, limit);
+	__xen_pgd_walk(mm, mm->pgd, func, limit);
 }
 
 /* If we're using split pte locks, then take the page's lock and
@@ -722,26 +677,17 @@ static void xen_do_pin(unsigned level, unsigned long pfn)
 	xen_extend_mmuext_op(&op);
 }
 
-static int xen_pin_page(struct mm_struct *mm, struct page *page,
-			enum pt_level level)
+static void xen_pin_page(struct mm_struct *mm, struct page *page,
+			 enum pt_level level)
 {
 	unsigned pgfl = TestSetPagePinned(page);
-	int flush;
-
-	if (pgfl)
-		flush = 0;		/* already pinned */
-	else if (PageHighMem(page))
-		/* kmaps need flushing if we found an unpinned
-		   highpage */
-		flush = 1;
-	else {
+
+	if (!pgfl) {
 		void *pt = lowmem_page_address(page);
 		unsigned long pfn = page_to_pfn(page);
 		struct multicall_space mcs = __xen_mc_entry(0);
 		spinlock_t *ptl;
 
-		flush = 0;
-
 		/*
 		 * We need to hold the pagetable lock between the time
 		 * we make the pagetable RO and when we actually pin
@@ -778,8 +724,6 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
 			xen_mc_callback(xen_pte_unlock, ptl);
 		}
 	}
-
-	return flush;
 }
 
 /* This is called just after a mm has been created, but it has not
@@ -787,39 +731,22 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
+	pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
 	trace_xen_mmu_pgd_pin(mm, pgd);
 
 	xen_mc_batch();
 
-	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
-		/* re-enable interrupts for flushing */
-		xen_mc_issue(0);
+	__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT);
 
-		kmap_flush_unused();
+	xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
 
-		xen_mc_batch();
+	if (user_pgd) {
+		xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
+		xen_do_pin(MMUEXT_PIN_L4_TABLE,
+			   PFN_DOWN(__pa(user_pgd)));
 	}
 
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
-		xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
-
-		if (user_pgd) {
-			xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
-			xen_do_pin(MMUEXT_PIN_L4_TABLE,
-				   PFN_DOWN(__pa(user_pgd)));
-		}
-	}
-#else /* CONFIG_X86_32 */
-#ifdef CONFIG_X86_PAE
-	/* Need to make sure unshared kernel PMD is pinnable */
-	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
-		     PT_PMD);
-#endif
-	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
-#endif /* CONFIG_X86_64 */
 	xen_mc_issue(0);
 }
 
@@ -854,11 +781,10 @@ void xen_mm_pin_all(void)
 	spin_unlock(&pgd_lock);
 }
 
-static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
-				  enum pt_level level)
+static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
+				   enum pt_level level)
 {
 	SetPagePinned(page);
-	return 0;
 }
 
 /*
@@ -870,18 +796,16 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 static void __init xen_after_bootmem(void)
 {
 	static_branch_enable(&xen_struct_pages_ready);
-#ifdef CONFIG_X86_64
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
-#endif
 	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
 }
 
-static int xen_unpin_page(struct mm_struct *mm, struct page *page,
-			  enum pt_level level)
+static void xen_unpin_page(struct mm_struct *mm, struct page *page,
+			   enum pt_level level)
 {
 	unsigned pgfl = TestClearPagePinned(page);
 
-	if (pgfl && !PageHighMem(page)) {
+	if (pgfl) {
 		void *pt = lowmem_page_address(page);
 		unsigned long pfn = page_to_pfn(page);
 		spinlock_t *ptl = NULL;
@@ -912,36 +836,24 @@ static int xen_unpin_page(struct mm_struct *mm, struct page *page,
 			xen_mc_callback(xen_pte_unlock, ptl);
 		}
 	}
-
-	return 0;		/* never need to flush on unpin */
 }
 
 /* Release a pagetables pages back as normal RW */
 static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 {
+	pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
 	trace_xen_mmu_pgd_unpin(mm, pgd);
 
 	xen_mc_batch();
 
 	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
-		if (user_pgd) {
-			xen_do_pin(MMUEXT_UNPIN_TABLE,
-				   PFN_DOWN(__pa(user_pgd)));
-			xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
-		}
+	if (user_pgd) {
+		xen_do_pin(MMUEXT_UNPIN_TABLE,
+			   PFN_DOWN(__pa(user_pgd)));
+		xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
 	}
-#endif
-
-#ifdef CONFIG_X86_PAE
-	/* Need to make sure unshared kernel PMD is unpinned */
-	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
-		       PT_PMD);
-#endif
 
 	__xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
 
@@ -1089,7 +1001,6 @@ static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 		BUG();
 }
 
-#ifdef CONFIG_X86_64
 static void __init xen_cleanhighmap(unsigned long vaddr,
 				    unsigned long vaddr_end)
 {
@@ -1273,17 +1184,15 @@ static void __init xen_pagetable_cleanhighmap(void)
 	xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
 	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
 }
-#endif
 
 static void __init xen_pagetable_p2m_setup(void)
 {
 	xen_vmalloc_p2m_tree();
 
-#ifdef CONFIG_X86_64
 	xen_pagetable_p2m_free();
 
 	xen_pagetable_cleanhighmap();
-#endif
+
 	/* And revector! Bye bye old array */
 	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
 }
@@ -1420,6 +1329,8 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3)
 }
 static void xen_write_cr3(unsigned long cr3)
 {
+	pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+
 	BUG_ON(preemptible());
 
 	xen_mc_batch();  /* disables interrupts */
@@ -1430,20 +1341,14 @@ static void xen_write_cr3(unsigned long cr3)
 
 	__xen_write_cr3(true, cr3);
 
-#ifdef CONFIG_X86_64
-	{
-		pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
-		if (user_pgd)
-			__xen_write_cr3(false, __pa(user_pgd));
-		else
-			__xen_write_cr3(false, 0);
-	}
-#endif
+	if (user_pgd)
+		__xen_write_cr3(false, __pa(user_pgd));
+	else
+		__xen_write_cr3(false, 0);
 
 	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
 
-#ifdef CONFIG_X86_64
 /*
  * At the start of the day - when Xen launches a guest, it has already
  * built pagetables for the guest. We diligently look over them
@@ -1478,49 +1383,39 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 
 	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
-#endif
 
 static int xen_pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd = mm->pgd;
-	int ret = 0;
+	struct page *page = virt_to_page(pgd);
+	pgd_t *user_pgd;
+	int ret = -ENOMEM;
 
 	BUG_ON(PagePinned(virt_to_page(pgd)));
+	BUG_ON(page->private != 0);
 
-#ifdef CONFIG_X86_64
-	{
-		struct page *page = virt_to_page(pgd);
-		pgd_t *user_pgd;
+	user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	page->private = (unsigned long)user_pgd;
 
-		BUG_ON(page->private != 0);
-
-		ret = -ENOMEM;
-
-		user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		page->private = (unsigned long)user_pgd;
-
-		if (user_pgd != NULL) {
+	if (user_pgd != NULL) {
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
-			user_pgd[pgd_index(VSYSCALL_ADDR)] =
-				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+		user_pgd[pgd_index(VSYSCALL_ADDR)] =
+			__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
 #endif
-			ret = 0;
-		}
-
-		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+		ret = 0;
 	}
-#endif
+
+	BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+
 	return ret;
 }
 
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-#ifdef CONFIG_X86_64
 	pgd_t *user_pgd = xen_get_user_pgd(pgd);
 
 	if (user_pgd)
 		free_page((unsigned long)user_pgd);
-#endif
 }
 
 /*
@@ -1539,7 +1434,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
  */
 __visible pte_t xen_make_pte_init(pteval_t pte)
 {
-#ifdef CONFIG_X86_64
 	unsigned long pfn;
 
 	/*
@@ -1553,7 +1447,7 @@ __visible pte_t xen_make_pte_init(pteval_t pte)
 	    pfn >= xen_start_info->first_p2m_pfn &&
 	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
 		pte &= ~_PAGE_RW;
-#endif
+
 	pte = pte_pfn_to_mfn(pte);
 	return native_make_pte(pte);
 }
@@ -1561,13 +1455,6 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
 
 static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
-#ifdef CONFIG_X86_32
-	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
-	if (pte_mfn(pte) != INVALID_P2M_ENTRY
-	    && pte_val_ma(*ptep) & _PAGE_PRESENT)
-		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
-			       pte_val_ma(pte));
-#endif
 	__xen_set_pte(ptep, pte);
 }
 
@@ -1642,20 +1529,14 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 		if (static_branch_likely(&xen_struct_pages_ready))
 			SetPagePinned(page);
 
-		if (!PageHighMem(page)) {
-			xen_mc_batch();
+		xen_mc_batch();
 
-			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
+		__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
-				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-		} else {
-			/* make sure there are no stray mappings of
-			   this page */
-			kmap_flush_unused();
-		}
+		xen_mc_issue(PARAVIRT_LAZY_MMU);
 	}
 }
 
@@ -1678,16 +1559,15 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 	trace_xen_mmu_release_ptpage(pfn, level, pinned);
 
 	if (pinned) {
-		if (!PageHighMem(page)) {
-			xen_mc_batch();
+		xen_mc_batch();
 
-			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
-				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+			__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 
-			__set_pfn_prot(pfn, PAGE_KERNEL);
+		__set_pfn_prot(pfn, PAGE_KERNEL);
+
+		xen_mc_issue(PARAVIRT_LAZY_MMU);
 
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-		}
 		ClearPagePinned(page);
 	}
 }
@@ -1702,7 +1582,6 @@ static void xen_release_pmd(unsigned long pfn)
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#ifdef CONFIG_X86_64
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -1712,20 +1591,6 @@ static void xen_release_pud(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PUD);
 }
-#endif
-
-void __init xen_reserve_top(void)
-{
-#ifdef CONFIG_X86_32
-	unsigned long top = HYPERVISOR_VIRT_START;
-	struct xen_platform_parameters pp;
-
-	if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
-		top = pp.virt_start;
-
-	reserve_top_address(-top);
-#endif	/* CONFIG_X86_32 */
-}
 
 /*
  * Like __va(), but returns address in the kernel mapping (which is
@@ -1733,11 +1598,7 @@ void __init xen_reserve_top(void)
  */
 static void * __init __ka(phys_addr_t paddr)
 {
-#ifdef CONFIG_X86_64
 	return (void *)(paddr + __START_KERNEL_map);
-#else
-	return __va(paddr);
-#endif
 }
 
 /* Convert a machine address to physical address */
@@ -1771,56 +1632,7 @@ static void __init set_page_prot(void *addr, pgprot_t prot)
 {
 	return set_page_prot_flags(addr, prot, UVMF_NONE);
 }
-#ifdef CONFIG_X86_32
-static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
-{
-	unsigned pmdidx, pteidx;
-	unsigned ident_pte;
-	unsigned long pfn;
-
-	level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES,
-				      PAGE_SIZE);
-
-	ident_pte = 0;
-	pfn = 0;
-	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
-		pte_t *pte_page;
-
-		/* Reuse or allocate a page of ptes */
-		if (pmd_present(pmd[pmdidx]))
-			pte_page = m2v(pmd[pmdidx].pmd);
-		else {
-			/* Check for free pte pages */
-			if (ident_pte == LEVEL1_IDENT_ENTRIES)
-				break;
-
-			pte_page = &level1_ident_pgt[ident_pte];
-			ident_pte += PTRS_PER_PTE;
-
-			pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
-		}
-
-		/* Install mappings */
-		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
-			pte_t pte;
 
-			if (pfn > max_pfn_mapped)
-				max_pfn_mapped = pfn;
-
-			if (!pte_none(pte_page[pteidx]))
-				continue;
-
-			pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
-			pte_page[pteidx] = pte;
-		}
-	}
-
-	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
-		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
-
-	set_page_prot(pmd, PAGE_KERNEL_RO);
-}
-#endif
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
@@ -1831,13 +1643,8 @@ void __init xen_setup_machphys_mapping(void)
 	} else {
 		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
 	}
-#ifdef CONFIG_X86_32
-	WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
-		< machine_to_phys_mapping);
-#endif
 }
 
-#ifdef CONFIG_X86_64
 static void __init convert_pfn_mfn(void *v)
 {
 	pte_t *pte = v;
@@ -2168,105 +1975,6 @@ void __init xen_relocate_p2m(void)
 	xen_start_info->nr_p2m_frames = n_frames;
 }
 
-#else	/* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
-static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
-RESERVE_BRK(fixup_kernel_pmd, PAGE_SIZE);
-RESERVE_BRK(fixup_kernel_pte, PAGE_SIZE);
-
-static void __init xen_write_cr3_init(unsigned long cr3)
-{
-	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
-
-	BUG_ON(read_cr3_pa() != __pa(initial_page_table));
-	BUG_ON(cr3 != __pa(swapper_pg_dir));
-
-	/*
-	 * We are switching to swapper_pg_dir for the first time (from
-	 * initial_page_table) and therefore need to mark that page
-	 * read-only and then pin it.
-	 *
-	 * Xen disallows sharing of kernel PMDs for PAE
-	 * guests. Therefore we must copy the kernel PMD from
-	 * initial_page_table into a new kernel PMD to be used in
-	 * swapper_pg_dir.
-	 */
-	swapper_kernel_pmd =
-		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-	copy_page(swapper_kernel_pmd, initial_kernel_pmd);
-	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
-		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
-	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
-
-	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
-	xen_write_cr3(cr3);
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
-
-	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
-			  PFN_DOWN(__pa(initial_page_table)));
-	set_page_prot(initial_page_table, PAGE_KERNEL);
-	set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
-
-	pv_ops.mmu.write_cr3 = &xen_write_cr3;
-}
-
-/*
- * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
- * not the first page table in the page table pool.
- * Iterate through the initial page tables to find the real page table base.
- */
-static phys_addr_t __init xen_find_pt_base(pmd_t *pmd)
-{
-	phys_addr_t pt_base, paddr;
-	unsigned pmdidx;
-
-	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
-
-	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
-		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
-			paddr = m2p(pmd[pmdidx].pmd);
-			pt_base = min(pt_base, paddr);
-		}
-
-	return pt_base;
-}
-
-void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
-{
-	pmd_t *kernel_pmd;
-
-	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-
-	xen_pt_base = xen_find_pt_base(kernel_pmd);
-	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
-
-	initial_kernel_pmd =
-		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-
-	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
-
-	copy_page(initial_kernel_pmd, kernel_pmd);
-
-	xen_map_identity_early(initial_kernel_pmd, max_pfn);
-
-	copy_page(initial_page_table, pgd);
-	initial_page_table[KERNEL_PGD_BOUNDARY] =
-		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
-
-	set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
-	set_page_prot(initial_page_table, PAGE_KERNEL_RO);
-	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
-
-	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
-			  PFN_DOWN(__pa(initial_page_table)));
-	xen_write_cr3(__pa(initial_page_table));
-
-	memblock_reserve(xen_pt_base, xen_pt_size);
-}
-#endif	/* CONFIG_X86_64 */
-
 void __init xen_reserve_special_pages(void)
 {
 	phys_addr_t paddr;
@@ -2300,12 +2008,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	switch (idx) {
 	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-#ifdef CONFIG_X86_32
-	case FIX_WP_TEST:
-# ifdef CONFIG_HIGHMEM
-	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
-# endif
-#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	case VSYSCALL_PAGE:
 #endif
 		/* All local page mappings */
@@ -2357,9 +2060,7 @@ static void __init xen_post_allocator_init(void)
 	pv_ops.mmu.set_pte = xen_set_pte;
 	pv_ops.mmu.set_pmd = xen_set_pmd;
 	pv_ops.mmu.set_pud = xen_set_pud;
-#ifdef CONFIG_X86_64
 	pv_ops.mmu.set_p4d = xen_set_p4d;
-#endif
 
 	/* This will work as long as patching hasn't happened yet
 	   (which it hasn't) */
@@ -2367,15 +2068,11 @@ static void __init xen_post_allocator_init(void)
 	pv_ops.mmu.alloc_pmd = xen_alloc_pmd;
 	pv_ops.mmu.release_pte = xen_release_pte;
 	pv_ops.mmu.release_pmd = xen_release_pmd;
-#ifdef CONFIG_X86_64
 	pv_ops.mmu.alloc_pud = xen_alloc_pud;
 	pv_ops.mmu.release_pud = xen_release_pud;
-#endif
 	pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte);
 
-#ifdef CONFIG_X86_64
 	pv_ops.mmu.write_cr3 = &xen_write_cr3;
-#endif
 }
 
 static void xen_leave_lazy_mmu(void)
@@ -2420,17 +2117,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
 	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 
-#ifdef CONFIG_X86_PAE
-	.set_pte_atomic = xen_set_pte_atomic,
-	.pte_clear = xen_pte_clear,
-	.pmd_clear = xen_pmd_clear,
-#endif	/* CONFIG_X86_PAE */
 	.set_pud = xen_set_pud_hyper,
 
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#ifdef CONFIG_X86_64
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
 	.set_p4d = xen_set_p4d_hyper,
@@ -2442,7 +2133,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
 	.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
 #endif
-#endif	/* CONFIG_X86_64 */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 0acba2c712ab..be4151f42611 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -379,12 +379,8 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m)
 
 		if (type == P2M_TYPE_PFN || i < chunk) {
 			/* Use initial p2m page contents. */
-#ifdef CONFIG_X86_64
 			mfns = alloc_p2m_page();
 			copy_page(mfns, xen_p2m_addr + pfn);
-#else
-			mfns = xen_p2m_addr + pfn;
-#endif
 			ptep = populate_extra_pte((unsigned long)(p2m + pfn));
 			set_pte(ptep,
 				pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL));
@@ -467,7 +463,7 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine);
  * Allocate new pmd(s). It is checked whether the old pmd is still in place.
  * If not, nothing is changed. This is okay as the only reason for allocating
  * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
- * pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
+ * pmd.
  */
 static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
 {
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 3566e37241d7..7eab14d56369 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -32,7 +32,6 @@
 #include <xen/features.h>
 #include <xen/hvc-console.h>
 #include "xen-ops.h"
-#include "vdso.h"
 #include "mmu.h"
 
 #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
@@ -545,13 +544,10 @@ static unsigned long __init xen_get_pages_limit(void)
 {
 	unsigned long limit;
 
-#ifdef CONFIG_X86_32
-	limit = GB(64) / PAGE_SIZE;
-#else
 	limit = MAXMEM / PAGE_SIZE;
 	if (!xen_initial_domain() && xen_512gb_limit)
 		limit = GB(512) / PAGE_SIZE;
-#endif
+
 	return limit;
 }
 
@@ -722,17 +718,8 @@ static void __init xen_reserve_xen_mfnlist(void)
 	if (!xen_is_e820_reserved(start, size))
 		return;
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Relocating the p2m on 32 bit system to an arbitrary virtual address
-	 * is not supported, so just give up.
-	 */
-	xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n");
-	BUG();
-#else
 	xen_relocate_p2m();
 	memblock_free(start, size);
-#endif
 }
 
 /**
@@ -921,20 +908,6 @@ char * __init xen_memory_setup(void)
 	return "Xen";
 }
 
-/*
- * Set the bit indicating "nosegneg" library variants should be used.
- * We only need to bother in pure 32-bit mode; compat 32-bit processes
- * can have un-truncated segments, so wrapping around is allowed.
- */
-static void __init fiddle_vdso(void)
-{
-#ifdef CONFIG_X86_32
-	u32 *mask = vdso_image_32.data +
-		vdso_image_32.sym_VDSO32_NOTE_MASK;
-	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
-#endif
-}
-
 static int register_callback(unsigned type, const void *func)
 {
 	struct callback_register callback = {
@@ -951,11 +924,7 @@ void xen_enable_sysenter(void)
 	int ret;
 	unsigned sysenter_feature;
 
-#ifdef CONFIG_X86_32
-	sysenter_feature = X86_FEATURE_SEP;
-#else
 	sysenter_feature = X86_FEATURE_SYSENTER32;
-#endif
 
 	if (!boot_cpu_has(sysenter_feature))
 		return;
@@ -967,7 +936,6 @@ void xen_enable_sysenter(void)
 
 void xen_enable_syscall(void)
 {
-#ifdef CONFIG_X86_64
 	int ret;
 
 	ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
@@ -983,7 +951,6 @@ void xen_enable_syscall(void)
 		if (ret != 0)
 			setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
 	}
-#endif /* CONFIG_X86_64 */
 }
 
 static void __init xen_pvmmu_arch_setup(void)
@@ -1024,7 +991,6 @@ void __init xen_arch_setup(void)
 	disable_cpuidle();
 	disable_cpufreq();
 	WARN_ON(xen_set_default_idle());
-	fiddle_vdso();
 #ifdef CONFIG_NUMA
 	numa_off = 1;
 #endif
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f8d39440b292..f5e7db4f82ab 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/thread_info.h>
 #include <asm/smp.h>
 
 #include <xen/events.h>
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 9ea598dcc132..c2ac319f11a4 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -29,6 +29,7 @@
 #include <asm/idtentry.h>
 #include <asm/desc.h>
 #include <asm/cpu.h>
+#include <asm/io_apic.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/vcpu.h>
@@ -210,15 +211,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void)
 		 * sure the old memory can be recycled. */
 		make_lowmem_page_readwrite(xen_initial_gdt);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
-	 * expects __USER_DS
-	 */
-	loadsegment(ds, __USER_DS);
-	loadsegment(es, __USER_DS);
-#endif
-
 	xen_filter_cpu_maps();
 	xen_setup_vcpu_info_placement();
 
@@ -299,10 +291,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 
 	gdt = get_cpu_gdt_rw(cpu);
 
-#ifdef CONFIG_X86_32
-	ctxt->user_regs.fs = __KERNEL_PERCPU;
-	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
-#endif
 	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
 	/*
@@ -340,12 +328,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	ctxt->kernel_ss = __KERNEL_DS;
 	ctxt->kernel_sp = task_top_of_stack(idle);
 
-#ifdef CONFIG_X86_32
-	ctxt->event_callback_cs     = __KERNEL_CS;
-	ctxt->failsafe_callback_cs  = __KERNEL_CS;
-#else
 	ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
 	ctxt->event_callback_eip    =
 		(unsigned long)xen_asm_exc_xen_hypervisor_callback;
 	ctxt->failsafe_callback_eip =
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index 8303b58c79a9..cae9660f4c67 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 
-#include <asm/fixmap.h>
-
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 
+#include <asm/fixmap.h>
+
 #include "xen-ops.h"
 
 void xen_pv_pre_suspend(void)
diff --git a/arch/x86/xen/vdso.h b/arch/x86/xen/vdso.h
deleted file mode 100644
index 873c54c488fe..000000000000
--- a/arch/x86/xen/vdso.h
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/* Bit used for the pseudo-hwcap for non-negative segments.  We use
-   bit 1 to avoid bugs in some versions of glibc when bit 0 is
-   used; the choice is otherwise arbitrary. */
-#define VDSO_NOTE_NONEGSEG_BIT	1
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 508fe204520b..1cb0e84b9161 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -6,12 +6,18 @@
  * operations here; the indirect forms are better handled in C.
  */
 
+#include <asm/errno.h>
 #include <asm/asm-offsets.h>
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
-#include <asm/frame.h>
+#include <asm/segment.h>
+#include <asm/thread_info.h>
 #include <asm/asm.h>
+#include <asm/frame.h>
 
+#include <xen/interface/xen.h>
+
+#include <linux/init.h>
 #include <linux/linkage.h>
 
 /*
@@ -76,11 +82,7 @@ SYM_FUNC_END(xen_save_fl_direct)
  */
 SYM_FUNC_START(xen_restore_fl_direct)
 	FRAME_BEGIN
-#ifdef CONFIG_X86_64
 	testw $X86_EFLAGS_IF, %di
-#else
-	testb $X86_EFLAGS_IF>>8, %ah
-#endif
 	setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	/*
 	 * Preempt here doesn't matter because that will deal with any
@@ -104,15 +106,6 @@ SYM_FUNC_END(xen_restore_fl_direct)
  */
 SYM_FUNC_START(check_events)
 	FRAME_BEGIN
-#ifdef CONFIG_X86_32
-	push %eax
-	push %ecx
-	push %edx
-	call xen_force_evtchn_callback
-	pop %edx
-	pop %ecx
-	pop %eax
-#else
 	push %rax
 	push %rcx
 	push %rdx
@@ -132,7 +125,6 @@ SYM_FUNC_START(check_events)
 	pop %rdx
 	pop %rcx
 	pop %rax
-#endif
 	FRAME_END
 	ret
 SYM_FUNC_END(check_events)
@@ -151,3 +143,175 @@ SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_END
 	ret
 SYM_FUNC_END(xen_read_cr2_direct);
+
+.macro xen_pv_trap name
+SYM_CODE_START(xen_\name)
+	pop %rcx
+	pop %r11
+	jmp  \name
+SYM_CODE_END(xen_\name)
+_ASM_NOKPROBE(xen_\name)
+.endm
+
+xen_pv_trap asm_exc_divide_error
+xen_pv_trap asm_xenpv_exc_debug
+xen_pv_trap asm_exc_int3
+xen_pv_trap asm_xenpv_exc_nmi
+xen_pv_trap asm_exc_overflow
+xen_pv_trap asm_exc_bounds
+xen_pv_trap asm_exc_invalid_op
+xen_pv_trap asm_exc_device_not_available
+xen_pv_trap asm_exc_double_fault
+xen_pv_trap asm_exc_coproc_segment_overrun
+xen_pv_trap asm_exc_invalid_tss
+xen_pv_trap asm_exc_segment_not_present
+xen_pv_trap asm_exc_stack_segment
+xen_pv_trap asm_exc_general_protection
+xen_pv_trap asm_exc_page_fault
+xen_pv_trap asm_exc_spurious_interrupt_bug
+xen_pv_trap asm_exc_coprocessor_error
+xen_pv_trap asm_exc_alignment_check
+#ifdef CONFIG_X86_MCE
+xen_pv_trap asm_exc_machine_check
+#endif /* CONFIG_X86_MCE */
+xen_pv_trap asm_exc_simd_coprocessor_error
+#ifdef CONFIG_IA32_EMULATION
+xen_pv_trap entry_INT80_compat
+#endif
+xen_pv_trap asm_exc_xen_hypervisor_callback
+
+	__INIT
+SYM_CODE_START(xen_early_idt_handler_array)
+	i = 0
+	.rept NUM_EXCEPTION_VECTORS
+	pop %rcx
+	pop %r11
+	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
+	i = i + 1
+	.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
+	.endr
+SYM_CODE_END(xen_early_idt_handler_array)
+	__FINIT
+
+hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
+/*
+ * Xen64 iret frame:
+ *
+ *	ss
+ *	rsp
+ *	rflags
+ *	cs
+ *	rip		<-- standard iret frame
+ *
+ *	flags
+ *
+ *	rcx		}
+ *	r11		}<-- pushed by hypercall page
+ * rsp->rax		}
+ */
+SYM_CODE_START(xen_iret)
+	pushq $0
+	jmp hypercall_iret
+SYM_CODE_END(xen_iret)
+
+SYM_CODE_START(xen_sysret64)
+	/*
+	 * We're already on the usermode stack at this point, but
+	 * still with the kernel gs, so we can easily switch back.
+	 *
+	 * tss.sp2 is scratch space.
+	 */
+	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
+	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+	pushq $__USER_DS
+	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
+	pushq %r11
+	pushq $__USER_CS
+	pushq %rcx
+
+	pushq $VGCF_in_syscall
+	jmp hypercall_iret
+SYM_CODE_END(xen_sysret64)
+
+/*
+ * Xen handles syscall callbacks much like ordinary exceptions, which
+ * means we have:
+ * - kernel gs
+ * - kernel rsp
+ * - an iret-like stack frame on the stack (including rcx and r11):
+ *	ss
+ *	rsp
+ *	rflags
+ *	cs
+ *	rip
+ *	r11
+ * rsp->rcx
+ */
+
+/* Normal 64-bit system call target */
+SYM_FUNC_START(xen_syscall_target)
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER_DS and __USER_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER_DS, 4*8(%rsp)
+	movq $__USER_CS, 1*8(%rsp)
+
+	jmp entry_SYSCALL_64_after_hwframe
+SYM_FUNC_END(xen_syscall_target)
+
+#ifdef CONFIG_IA32_EMULATION
+
+/* 32-bit compat syscall target */
+SYM_FUNC_START(xen_syscall32_target)
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER32_DS, 4*8(%rsp)
+	movq $__USER32_CS, 1*8(%rsp)
+
+	jmp entry_SYSCALL_compat_after_hwframe
+SYM_FUNC_END(xen_syscall32_target)
+
+/* 32-bit compat sysenter target */
+SYM_FUNC_START(xen_sysenter_target)
+	/*
+	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
+	 * that we don't need to guard against single step exceptions here.
+	 */
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER32_DS, 4*8(%rsp)
+	movq $__USER32_CS, 1*8(%rsp)
+
+	jmp entry_SYSENTER_compat_after_hwframe
+SYM_FUNC_END(xen_sysenter_target)
+
+#else /* !CONFIG_IA32_EMULATION */
+
+SYM_FUNC_START_ALIAS(xen_syscall32_target)
+SYM_FUNC_START(xen_sysenter_target)
+	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
+	mov $-ENOSYS, %rax
+	pushq $0
+	jmp hypercall_iret
+SYM_FUNC_END(xen_sysenter_target)
+SYM_FUNC_END_ALIAS(xen_syscall32_target)
+
+#endif	/* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
deleted file mode 100644
index 4757cec33abe..000000000000
--- a/arch/x86/xen/xen-asm_32.S
+++ /dev/null
@@ -1,185 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Asm versions of Xen pv-ops, suitable for direct use.
- *
- * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C.
- */
-
-#include <asm/thread_info.h>
-#include <asm/processor-flags.h>
-#include <asm/segment.h>
-#include <asm/asm.h>
-
-#include <xen/interface/xen.h>
-
-#include <linux/linkage.h>
-
-/* Pseudo-flag used for virtual NMI, which we don't implement yet */
-#define XEN_EFLAGS_NMI  0x80000000
-
-/*
- * This is run where a normal iret would be run, with the same stack setup:
- *	8: eflags
- *	4: cs
- *	esp-> 0: eip
- *
- * This attempts to make sure that any pending events are dealt with
- * on return to usermode, but there is a small window in which an
- * event can happen just before entering usermode.  If the nested
- * interrupt ends up setting one of the TIF_WORK_MASK pending work
- * flags, they will not be tested again before returning to
- * usermode. This means that a process can end up with pending work,
- * which will be unprocessed until the process enters and leaves the
- * kernel again, which could be an unbounded amount of time.  This
- * means that a pending signal or reschedule event could be
- * indefinitely delayed.
- *
- * The fix is to notice a nested interrupt in the critical window, and
- * if one occurs, then fold the nested interrupt into the current
- * interrupt stack frame, and re-process it iteratively rather than
- * recursively.  This means that it will exit via the normal path, and
- * all pending work will be dealt with appropriately.
- *
- * Because the nested interrupt handler needs to deal with the current
- * stack state in whatever form its in, we keep things simple by only
- * using a single register which is pushed/popped on the stack.
- */
-
-.macro POP_FS
-1:
-	popw %fs
-.pushsection .fixup, "ax"
-2:	movw $0, (%esp)
-	jmp 1b
-.popsection
-	_ASM_EXTABLE(1b,2b)
-.endm
-
-SYM_CODE_START(xen_iret)
-	/* test eflags for special cases */
-	testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
-	jnz hyper_iret
-
-	push %eax
-	ESP_OFFSET=4	# bytes pushed onto stack
-
-	/* Store vcpu_info pointer for easy access */
-#ifdef CONFIG_SMP
-	pushw %fs
-	movl $(__KERNEL_PERCPU), %eax
-	movl %eax, %fs
-	movl %fs:xen_vcpu, %eax
-	POP_FS
-#else
-	movl %ss:xen_vcpu, %eax
-#endif
-
-	/* check IF state we're restoring */
-	testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp)
-
-	/*
-	 * Maybe enable events.  Once this happens we could get a
-	 * recursive event, so the critical region starts immediately
-	 * afterwards.  However, if that happens we don't end up
-	 * resuming the code, so we don't have to be worried about
-	 * being preempted to another CPU.
-	 */
-	setz %ss:XEN_vcpu_info_mask(%eax)
-xen_iret_start_crit:
-
-	/* check for unmasked and pending */
-	cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
-
-	/*
-	 * If there's something pending, mask events again so we can
-	 * jump back into exc_xen_hypervisor_callback. Otherwise do not
-	 * touch XEN_vcpu_info_mask.
-	 */
-	jne 1f
-	movb $1, %ss:XEN_vcpu_info_mask(%eax)
-
-1:	popl %eax
-
-	/*
-	 * From this point on the registers are restored and the stack
-	 * updated, so we don't need to worry about it if we're
-	 * preempted
-	 */
-iret_restore_end:
-
-	/*
-	 * Jump to hypervisor_callback after fixing up the stack.
-	 * Events are masked, so jumping out of the critical region is
-	 * OK.
-	 */
-	je xen_asm_exc_xen_hypervisor_callback
-
-1:	iret
-xen_iret_end_crit:
-	_ASM_EXTABLE(1b, asm_iret_error)
-
-hyper_iret:
-	/* put this out of line since its very rarely used */
-	jmp hypercall_page + __HYPERVISOR_iret * 32
-SYM_CODE_END(xen_iret)
-
-	.globl xen_iret_start_crit, xen_iret_end_crit
-
-/*
- * This is called by xen_asm_exc_xen_hypervisor_callback in entry_32.S when it sees
- * that the EIP at the time of interrupt was between
- * xen_iret_start_crit and xen_iret_end_crit.
- *
- * The stack format at this point is:
- *	----------------
- *	 ss		: (ss/esp may be present if we came from usermode)
- *	 esp		:
- *	 eflags		}  outer exception info
- *	 cs		}
- *	 eip		}
- *	----------------
- *	 eax		:  outer eax if it hasn't been restored
- *	----------------
- *	 eflags		}
- *	 cs		}  nested exception info
- *	 eip		}
- *	 return address	: (into xen_asm_exc_xen_hypervisor_callback)
- *
- * In order to deliver the nested exception properly, we need to discard the
- * nested exception frame such that when we handle the exception, we do it
- * in the context of the outer exception rather than starting a new one.
- *
- * The only caveat is that if the outer eax hasn't been restored yet (i.e.
- * it's still on stack), we need to restore its value here.
-*/
-.pushsection .noinstr.text, "ax"
-SYM_CODE_START(xen_iret_crit_fixup)
-	/*
-	 * Paranoia: Make sure we're really coming from kernel space.
-	 * One could imagine a case where userspace jumps into the
-	 * critical range address, but just before the CPU delivers a
-	 * PF, it decides to deliver an interrupt instead.  Unlikely?
-	 * Definitely.  Easy to avoid?  Yes.
-	 */
-	testb $2, 2*4(%esp)		/* nested CS */
-	jnz 2f
-
-	/*
-	 * If eip is before iret_restore_end then stack
-	 * hasn't been restored yet.
-	 */
-	cmpl $iret_restore_end, 1*4(%esp)
-	jae 1f
-
-	movl 4*4(%esp), %eax		/* load outer EAX */
-	ret $4*4			/* discard nested EIP, CS, and EFLAGS as
-					 * well as the just restored EAX */
-
-1:
-	ret $3*4			/* discard nested EIP, CS, and EFLAGS */
-
-2:
-	ret
-SYM_CODE_END(xen_iret_crit_fixup)
-.popsection
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
deleted file mode 100644
index aab1d99b2b48..000000000000
--- a/arch/x86/xen/xen-asm_64.S
+++ /dev/null
@@ -1,192 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Asm versions of Xen pv-ops, suitable for direct use.
- *
- * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C.
- */
-
-#include <asm/errno.h>
-#include <asm/percpu.h>
-#include <asm/processor-flags.h>
-#include <asm/segment.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
-#include <xen/interface/xen.h>
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-
-.macro xen_pv_trap name
-SYM_CODE_START(xen_\name)
-	pop %rcx
-	pop %r11
-	jmp  \name
-SYM_CODE_END(xen_\name)
-_ASM_NOKPROBE(xen_\name)
-.endm
-
-xen_pv_trap asm_exc_divide_error
-xen_pv_trap asm_xenpv_exc_debug
-xen_pv_trap asm_exc_int3
-xen_pv_trap asm_xenpv_exc_nmi
-xen_pv_trap asm_exc_overflow
-xen_pv_trap asm_exc_bounds
-xen_pv_trap asm_exc_invalid_op
-xen_pv_trap asm_exc_device_not_available
-xen_pv_trap asm_exc_double_fault
-xen_pv_trap asm_exc_coproc_segment_overrun
-xen_pv_trap asm_exc_invalid_tss
-xen_pv_trap asm_exc_segment_not_present
-xen_pv_trap asm_exc_stack_segment
-xen_pv_trap asm_exc_general_protection
-xen_pv_trap asm_exc_page_fault
-xen_pv_trap asm_exc_spurious_interrupt_bug
-xen_pv_trap asm_exc_coprocessor_error
-xen_pv_trap asm_exc_alignment_check
-#ifdef CONFIG_X86_MCE
-xen_pv_trap asm_exc_machine_check
-#endif /* CONFIG_X86_MCE */
-xen_pv_trap asm_exc_simd_coprocessor_error
-#ifdef CONFIG_IA32_EMULATION
-xen_pv_trap entry_INT80_compat
-#endif
-xen_pv_trap asm_exc_xen_hypervisor_callback
-
-	__INIT
-SYM_CODE_START(xen_early_idt_handler_array)
-	i = 0
-	.rept NUM_EXCEPTION_VECTORS
-	pop %rcx
-	pop %r11
-	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
-	i = i + 1
-	.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
-	.endr
-SYM_CODE_END(xen_early_idt_handler_array)
-	__FINIT
-
-hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
-/*
- * Xen64 iret frame:
- *
- *	ss
- *	rsp
- *	rflags
- *	cs
- *	rip		<-- standard iret frame
- *
- *	flags
- *
- *	rcx		}
- *	r11		}<-- pushed by hypercall page
- * rsp->rax		}
- */
-SYM_CODE_START(xen_iret)
-	pushq $0
-	jmp hypercall_iret
-SYM_CODE_END(xen_iret)
-
-SYM_CODE_START(xen_sysret64)
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back.
-	 *
-	 * tss.sp2 is scratch space.
-	 */
-	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER_DS
-	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	pushq %r11
-	pushq $__USER_CS
-	pushq %rcx
-
-	pushq $VGCF_in_syscall
-	jmp hypercall_iret
-SYM_CODE_END(xen_sysret64)
-
-/*
- * Xen handles syscall callbacks much like ordinary exceptions, which
- * means we have:
- * - kernel gs
- * - kernel rsp
- * - an iret-like stack frame on the stack (including rcx and r11):
- *	ss
- *	rsp
- *	rflags
- *	cs
- *	rip
- *	r11
- * rsp->rcx
- */
-
-/* Normal 64-bit system call target */
-SYM_FUNC_START(xen_syscall_target)
-	popq %rcx
-	popq %r11
-
-	/*
-	 * Neither Xen nor the kernel really knows what the old SS and
-	 * CS were.  The kernel expects __USER_DS and __USER_CS, so
-	 * report those values even though Xen will guess its own values.
-	 */
-	movq $__USER_DS, 4*8(%rsp)
-	movq $__USER_CS, 1*8(%rsp)
-
-	jmp entry_SYSCALL_64_after_hwframe
-SYM_FUNC_END(xen_syscall_target)
-
-#ifdef CONFIG_IA32_EMULATION
-
-/* 32-bit compat syscall target */
-SYM_FUNC_START(xen_syscall32_target)
-	popq %rcx
-	popq %r11
-
-	/*
-	 * Neither Xen nor the kernel really knows what the old SS and
-	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
-	 * report those values even though Xen will guess its own values.
-	 */
-	movq $__USER32_DS, 4*8(%rsp)
-	movq $__USER32_CS, 1*8(%rsp)
-
-	jmp entry_SYSCALL_compat_after_hwframe
-SYM_FUNC_END(xen_syscall32_target)
-
-/* 32-bit compat sysenter target */
-SYM_FUNC_START(xen_sysenter_target)
-	/*
-	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
-	 * that we don't need to guard against single step exceptions here.
-	 */
-	popq %rcx
-	popq %r11
-
-	/*
-	 * Neither Xen nor the kernel really knows what the old SS and
-	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
-	 * report those values even though Xen will guess its own values.
-	 */
-	movq $__USER32_DS, 4*8(%rsp)
-	movq $__USER32_CS, 1*8(%rsp)
-
-	jmp entry_SYSENTER_compat_after_hwframe
-SYM_FUNC_END(xen_sysenter_target)
-
-#else /* !CONFIG_IA32_EMULATION */
-
-SYM_FUNC_START_ALIAS(xen_syscall32_target)
-SYM_FUNC_START(xen_sysenter_target)
-	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
-	mov $-ENOSYS, %rax
-	pushq $0
-	jmp hypercall_iret
-SYM_FUNC_END(xen_sysenter_target)
-SYM_FUNC_END_ALIAS(xen_syscall32_target)
-
-#endif	/* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 1ba601df3a37..2d7c8f34f56c 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -35,13 +35,8 @@ SYM_CODE_START(startup_xen)
 	rep __ASM_SIZE(stos)
 
 	mov %_ASM_SI, xen_start_info
-#ifdef CONFIG_X86_64
 	mov initial_stack(%rip), %rsp
-#else
-	mov initial_stack, %esp
-#endif
 
-#ifdef CONFIG_X86_64
 	/* Set up %gs.
 	 *
 	 * The base of %gs always points to fixed_percpu_data.  If the
@@ -53,7 +48,6 @@ SYM_CODE_START(startup_xen)
 	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
 	cdq
 	wrmsr
-#endif
 
 	call xen_start_kernel
 SYM_CODE_END(startup_xen)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 53b224fd6177..45d556f71858 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -33,7 +33,6 @@ void xen_setup_mfn_list_list(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
-void xen_reserve_top(void);
 void __init xen_reserve_special_pages(void);
 void __init xen_pt_check_e820(void);
 
diff --git a/arch/xtensa/boot/boot-elf/Makefile b/arch/xtensa/boot/boot-elf/Makefile
index 0ebc9827f7e5..f7c775d53012 100644
--- a/arch/xtensa/boot/boot-elf/Makefile
+++ b/arch/xtensa/boot/boot-elf/Makefile
@@ -26,7 +26,7 @@ $(obj)/Image.o: $(obj)/../vmlinux.bin $(OBJS)
 		$(OBJS) $@
 
 $(obj)/../Image.elf: $(obj)/Image.o $(obj)/boot.lds
-	$(Q)$(LD) $(KBUILD_LDFLAGS) $(LDFLAGS_vmlinux) \
+	$(Q)$(LD) $(KBUILD_LDFLAGS) \
 		-T $(obj)/boot.lds \
 		--build-id=none \
 		-o $@ $(obj)/Image.o
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index e57f0d0a88d8..b9758119feca 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -35,7 +35,7 @@
 #define get_fs()	(current->thread.current_ds)
 #define set_fs(val)	(current->thread.current_ds = (val))
 
-#define segment_eq(a, b)	((a).seg == (b).seg)
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 
 #define __kernel_ok (uaccess_kernel())
 #define __user_ok(addr, size) \
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index d216ccba42f7..6276e3c2d3fc 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -222,7 +222,7 @@
 204	common	quotactl			sys_quotactl
 # 205 was old nfsservctl
 205	common	nfsservctl			sys_ni_syscall
-206	common	_sysctl				sys_sysctl
+206	common	_sysctl				sys_ni_syscall
 207	common	bdflush				sys_bdflush
 208	common	uname				sys_newuname
 209	common	sysinfo				sys_sysinfo
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index c128dcc7c85b..7666408ce12a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,9 @@ void do_page_fault(struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
@@ -107,7 +110,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (fault_signal_pending(fault, regs))
 		return;
@@ -122,10 +125,6 @@ good_area:
 		BUG();
 	}
 	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
@@ -139,12 +138,6 @@ good_area:
 	}
 
 	mmap_read_unlock(mm);
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-	if (flags & VM_FAULT_MAJOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	else
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-
 	return;
 
 	/* Something tried to access memory that isn't in our memory map..