Merge tag 'for-linus' of git://github.com/openrisc/linux

Pull OpenRISC updates from Stafford Horne:
 "A few patches all over the place during this cycle, mostly bug and
  sparse warning fixes for OpenRISC, but a few enhancements too. Note,
  there are 2 non OpenRISC specific fixups.

  Non OpenRISC fixes:

   - In init we need to align the init_task correctly to fix an issue
     with MUTEX_FLAGS, reviewed by Peter Z. No one picked this up so I
     kept it on my tree.

   - In asm-generic/io.h I fixed up some sparse warnings, OK'd by Arnd.
     Arnd asked to merge it via my tree.

  OpenRISC fixes:

   - Many fixes for OpenRISC sprase warnings.

   - Add support OpenRISC SMP tlb flushing rather than always flushing
     the entire TLB on every CPU.

   - Fix bug when dumping stack via /proc/xxx/stack of user threads"

* tag 'for-linus' of git://github.com/openrisc/linux:
  openrisc: uaccess: Add user address space check to access_ok
  openrisc: signal: Fix sparse address space warnings
  openrisc: uaccess: Remove unused macro __addr_ok
  openrisc: uaccess: Use static inline function in access_ok
  openrisc: uaccess: Fix sparse address space warnings
  openrisc: io: Fixup defines and move include to the end
  asm-generic/io.h: Fix sparse warnings on big-endian architectures
  openrisc: Implement proper SMP tlb flushing
  openrisc: Fix oops caused when dumping stack
  openrisc: Add support for external initrd images
  init: Align init_task to avoid conflict with MUTEX_FLAGS
  openrisc: fix __user in raw_copy_to_user()'s prototype
diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h
index db02fb2..7d6b4a7 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 48b6915..f039021 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -48,16 +48,17 @@
 /* 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/setup.c b/arch/openrisc/kernel/setup.c
index 8aa438e..b18e775 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 4f07548..97804f2 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 bd1e660..29c82ef 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 43f140a..54d3880 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 60449fd..22fbc5f 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -96,18 +96,6 @@
 
         __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/tlb.c b/arch/openrisc/mm/tlb.c
index 4b680ae..2b6feab 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/include/asm-generic/io.h b/include/asm-generic/io.h
index 30a3aab..dabf8cb 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -163,7 +163,7 @@ static inline u16 readw(const volatile void __iomem *addr)
 	u16 val;
 
 	__io_br();
-	val = __le16_to_cpu(__raw_readw(addr));
+	val = __le16_to_cpu((__le16 __force)__raw_readw(addr));
 	__io_ar(val);
 	return val;
 }
@@ -176,7 +176,7 @@ static inline u32 readl(const volatile void __iomem *addr)
 	u32 val;
 
 	__io_br();
-	val = __le32_to_cpu(__raw_readl(addr));
+	val = __le32_to_cpu((__le32 __force)__raw_readl(addr));
 	__io_ar(val);
 	return val;
 }
@@ -212,7 +212,7 @@ static inline void writeb(u8 value, volatile void __iomem *addr)
 static inline void writew(u16 value, volatile void __iomem *addr)
 {
 	__io_bw();
-	__raw_writew(cpu_to_le16(value), addr);
+	__raw_writew((u16 __force)cpu_to_le16(value), addr);
 	__io_aw();
 }
 #endif
@@ -222,7 +222,7 @@ static inline void writew(u16 value, volatile void __iomem *addr)
 static inline void writel(u32 value, volatile void __iomem *addr)
 {
 	__io_bw();
-	__raw_writel(__cpu_to_le32(value), addr);
+	__raw_writel((u32 __force)__cpu_to_le32(value), addr);
 	__io_aw();
 }
 #endif
@@ -474,7 +474,7 @@ static inline u16 _inw(unsigned long addr)
 	u16 val;
 
 	__io_pbr();
-	val = __le16_to_cpu(__raw_readw(PCI_IOBASE + addr));
+	val = __le16_to_cpu((__le16 __force)__raw_readw(PCI_IOBASE + addr));
 	__io_par(val);
 	return val;
 }
@@ -487,7 +487,7 @@ static inline u32 _inl(unsigned long addr)
 	u32 val;
 
 	__io_pbr();
-	val = __le32_to_cpu(__raw_readl(PCI_IOBASE + addr));
+	val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr));
 	__io_par(val);
 	return val;
 }
@@ -508,7 +508,7 @@ static inline void _outb(u8 value, unsigned long addr)
 static inline void _outw(u16 value, unsigned long addr)
 {
 	__io_pbw();
-	__raw_writew(cpu_to_le16(value), PCI_IOBASE + addr);
+	__raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr);
 	__io_paw();
 }
 #endif
@@ -518,7 +518,7 @@ static inline void _outw(u16 value, unsigned long addr)
 static inline void _outl(u32 value, unsigned long addr)
 {
 	__io_pbw();
-	__raw_writel(cpu_to_le32(value), PCI_IOBASE + addr);
+	__raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr);
 	__io_paw();
 }
 #endif
diff --git a/init/init_task.c b/init/init_task.c
index 89024e8..f6889fc 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -65,6 +65,7 @@ struct task_struct init_task
 #ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
 	__init_task_data
 #endif
+	__aligned(L1_CACHE_BYTES)
 = {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	.thread_info	= INIT_THREAD_INFO(init_task),