Linux 3.2.98

Make sure dmesg reports when KPTI is enabled.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

Documentation/cgroups/cpusets.txt

@@ -345,14 +345,14 @@ the named feature on.
 The implementation is simple.
 
 Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
-PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
+PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
-is modified to perform an inline check for this PF_SPREAD_PAGE task
+is modified to perform an inline check for this PFA_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
 Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
-PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
+PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
 The cpuset_mem_spread_node() routine is also simple.  It uses the

Documentation/kernel-parameters.txt

@@ -1799,8 +1799,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nointroute	[IA-64]
 
+	noinvpcid	[X86] Disable the INVPCID cpu feature.
+
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
+	nopti		[X86-64] Disable KAISER isolation of kernel from user.
+
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
 
 	no-kvmapf	[X86,KVM] Disable paravirtualized asynchronous page
@@ -1827,6 +1831,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	nopat		[X86] Disable PAT (page attribute table extension of
 			pagetables) support.
 
+	nopcid		[X86-64] Disable the PCID cpu feature.
+
 	norandmaps	Don't use address space randomization.  Equivalent to
 			echo 0 > /proc/sys/kernel/randomize_va_space
 
@@ -2239,6 +2245,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
+	pti=		[X86_64]
+			Control KAISER user/kernel address space isolation:
+			on - enable
+			off - disable
+			auto - default setting
+
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
@@ -2457,6 +2469,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	spia_pedr=
 	spia_peddr=
 
+	stack_guard_gap=	[MM]
+			override the default stack gap protection. The value
+			is in page units and it defines how many pages prior
+			to (for stacks growing down) resp. after (for stacks
+			growing up) the main stack are reserved for no other
+			mapping. Default value is 256 pages.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.
 

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 2
-SUBLEVEL = 84
+SUBLEVEL = 98
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/alpha/include/asm/types.h

@@ -9,10 +9,18 @@
  * need to be careful to avoid a name clashes.
  */
 
-#ifdef __KERNEL__
-#include <asm-generic/int-ll64.h>
-#else
+/*
+ * This is here because we used to use l64 for alpha
+ * and we don't want to impact user mode with our change to ll64
+ * in the kernel.
+ *
+ * However, some user programs are fine with this.  They can
+ * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here.
+ */
+#if !defined(__SANE_USERSPACE_TYPES__) && !defined(__KERNEL__)
 #include <asm-generic/int-l64.h>
+#else
+#include <asm-generic/int-ll64.h>
 #endif
 
 #ifndef __ASSEMBLY__

arch/alpha/kernel/osf_sys.c

@@ -1026,8 +1026,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 	if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
 		return -EFAULT;
 
-	err = 0;
-	err |= put_user(status, ustatus);
+	err = put_user(status, ustatus);
+	if (ret < 0)
+		return err ? err : ret;
+
 	err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
 	err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
 	err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
@@ -1147,7 +1149,7 @@ arch_get_unmapped_area_1(unsigned long addr, unsigned long len,
 		/* At this point:  (!vma || addr < vma->vm_end). */
 		if (limit - len < addr)
 			return -ENOMEM;
-		if (!vma || addr + len <= vma->vm_start)
+		if (!vma || addr + len <= vm_start_gap(vma))
 			return addr;
 		addr = vma->vm_end;
 		vma = vma->vm_next;

arch/arm/include/asm/cputype.h

@@ -25,6 +25,9 @@
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
 
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION		0x510002d0
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15

arch/arm/kernel/hw_breakpoint.c

@@ -1001,6 +1001,22 @@ static int __init arch_hw_breakpoint_init(void)
 		return 0;
 	}
 
+	/*
+	 * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+	 * whenever a WFI is issued, even if the core is not powered down, in
+	 * violation of the architecture.  When DBGPRSR.SPD is set, accesses to
+	 * breakpoint and watchpoint registers are treated as undefined, so
+	 * this results in boot time and runtime failures when these are
+	 * accessed and we unexpectedly take a trap.
+	 *
+	 * It's not clear if/how this can be worked around, so we blacklist
+	 * Scorpion CPUs to avoid these issues.
+	*/
+	if ((read_cpuid_id() & 0xff00fff0) == ARM_CPU_PART_SCORPION) {
+		pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+		return 0;
+	}
+
 	/* Determine how many BRPs/WRPs are available. */
 	core_num_brps = get_num_brps();
 	core_num_wrps = get_num_wrps();

arch/arm/kernel/ptrace.c

@@ -593,7 +593,7 @@ static int gpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs newregs;
+	struct pt_regs newregs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &newregs,

arch/arm/kernel/return_address.c

@@ -58,10 +58,6 @@ void *return_address(unsigned int level)
 
 #else /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
 
-#if defined(CONFIG_ARM_UNWIND)
-#warning "TODO: return_address should use unwind tables"
-#endif
-
 void *return_address(unsigned int level)
 {
 	return NULL;

arch/arm/kernel/traps.c

@@ -130,30 +130,26 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 	set_fs(fs);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
 	const int thumb = thumb_mode(regs);
 	const int width = thumb ? 4 : 8;
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
 	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * Note that we now dump the code first, just in case the backtrace
+	 * kills us.
 	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 
 	for (i = -4; i < 1 + !!thumb; i++) {
 		unsigned int val, bad;
 
 		if (thumb)
-			bad = __get_user(val, &((u16 *)addr)[i]);
+			bad = get_user(val, &((u16 *)addr)[i]);
 		else
-			bad = __get_user(val, &((u32 *)addr)[i]);
+			bad = get_user(val, &((u32 *)addr)[i]);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ",
@@ -164,8 +160,20 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	mm_segment_t fs;
+
+	if (!user_mode(regs)) {
+		fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 #ifdef CONFIG_ARM_UNWIND

arch/arm/mach-pxa/Kconfig

@@ -563,6 +563,7 @@ config ARCH_PXA_ESERIES
 	bool "PXA based Toshiba e-series PDAs"
 	select PXA25x
 	select FB_W100
+	select FB
 
 config MACH_E330
 	bool "Toshiba e330"

arch/arm/mm/dma-mapping.c

@@ -374,7 +374,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_dmacoherent(pgprot_kernel));
+			   pgprot_dmacoherent(PAGE_KERNEL));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
@@ -386,7 +386,7 @@ void *
 dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_writecombine(pgprot_kernel));
+			   pgprot_writecombine(PAGE_KERNEL));
 }
 EXPORT_SYMBOL(dma_alloc_writecombine);
 

arch/arm/mm/mmap.c

@@ -30,7 +30,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 	int do_align = 0;
 	int aliasing = cache_is_vipt_aliasing();
 
@@ -62,7 +62,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (len > mm->cached_hole_size) {
@@ -96,15 +96,17 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (!vma || addr + len <= vma->vm_start) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (!vma || addr + len <= vm_start) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 		addr = vma->vm_end;
 		if (do_align)
 			addr = COLOUR_ALIGN(addr, pgoff);

arch/cris/boot/rescue/Makefile

@@ -10,6 +10,9 @@
 
 asflags-y += $(LINUXINCLUDE)
 ccflags-y += -O2 $(LINUXINCLUDE)
+
+ifdef CONFIG_ETRAX_AXISFLASHMAP
+
 arch-$(CONFIG_ETRAX_ARCH_V10) = v10
 arch-$(CONFIG_ETRAX_ARCH_V32) = v32
 
@@ -28,6 +31,11 @@ $(obj)/rescue.bin: $(obj)/rescue.o FORCE
 	$(call if_changed,objcopy)
 	cp -p $(obj)/rescue.bin $(objtree)
 
+else
+$(obj)/rescue.bin:
+
+endif
+
 $(obj)/testrescue.bin: $(obj)/testrescue.o
 	$(OBJCOPY) $(OBJCOPYFLAGS) $(obj)/testrescue.o tr.bin
 # Pad it to 784 bytes

arch/frv/mm/elf-fdpic.c

@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(current->mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			goto success;
 	}
 
@@ -89,7 +89,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 			for (; vma; vma = vma->vm_next) {
 				if (addr > limit)
 					break;
-				if (addr + len <= vma->vm_start)
+				if (addr + len <= vm_start_gap(vma))
 					goto success;
 				addr = vma->vm_end;
 			}
@@ -104,7 +104,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		for (; vma; vma = vma->vm_next) {
 			if (addr > limit)
 				break;
-			if (addr + len <= vma->vm_start)
+			if (addr + len <= vm_start_gap(vma))
 				goto success;
 			addr = vma->vm_end;
 		}

arch/ia64/kernel/sys_ia64.c

@@ -27,7 +27,8 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len
 	long map_shared = (flags & MAP_SHARED);
 	unsigned long start_addr, align_mask = PAGE_SIZE - 1;
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
+	unsigned long prev_end;
 
 	if (len > RGN_MAP_LIMIT)
 		return -ENOMEM;
@@ -58,7 +59,17 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len
   full_search:
 	start_addr = addr = (addr + align_mask) & ~align_mask;
 
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+	for (vma = find_vma_prev(mm, addr, &prev); ; prev = vma,
+						vma = vma->vm_next) {
+		if (prev) {
+			prev_end = vm_end_gap(prev);
+			if (addr < prev_end) {
+				addr = (prev_end + align_mask) & ~align_mask;
+				/* If vma already violates gap, forget it */
+				if (vma && addr > vma->vm_start)
+					addr = vma->vm_start;
+			}
+		}
 		/* At this point:  (!vma || addr < vma->vm_end). */
 		if (TASK_SIZE - len < addr || RGN_MAP_LIMIT - len < REGION_OFFSET(addr)) {
 			if (start_addr != TASK_UNMAPPED_BASE) {
@@ -68,12 +79,11 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len
 			}
 			return -ENOMEM;
 		}
-		if (!vma || addr + len <= vma->vm_start) {
+		if (!vma || addr + len <= vm_start_gap(vma)) {
 			/* Remember the address where we stopped this search:  */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		addr = (vma->vm_end + align_mask) & ~align_mask;
 	}
 }
 

arch/ia64/mm/hugetlbpage.c

@@ -171,9 +171,9 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, u
 		/* At this point:  (!vmm || addr < vmm->vm_end). */
 		if (REGION_OFFSET(addr) + len > RGN_MAP_LIMIT)
 			return -ENOMEM;
-		if (!vmm || (addr + len) <= vmm->vm_start)
+		if (!vmm || (addr + len) <= vm_start_gap(vmm))
 			return addr;
-		addr = ALIGN(vmm->vm_end, HPAGE_SIZE);
+		addr = ALIGN(vm_end_gap(vmm), HPAGE_SIZE);
 	}
 }
 

arch/m32r/include/asm/io.h

@@ -67,6 +67,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 
 extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(off,size) ioremap(off,size)
+#define ioremap_wc ioremap_nocache
 
 /*
  * IO bus memory addresses are also 1:1 with the physical address
@@ -162,13 +163,21 @@ static inline void _writel(unsigned long l, unsigned long addr)
 #define __raw_writew writew
 #define __raw_writel writel
 
-#define ioread8 read
+#define ioread8 readb
 #define ioread16 readw
 #define ioread32 readl
 #define iowrite8 writeb
 #define iowrite16 writew
 #define iowrite32 writel
 
+#define ioread8_rep(p, dst, count) insb((unsigned long)(p), (dst), (count))
+#define ioread16_rep(p, dst, count) insw((unsigned long)(p), (dst), (count))
+#define ioread32_rep(p, dst, count) insl((unsigned long)(p), (dst), (count))
+
+#define iowrite8_rep(p, src, count) outsb((unsigned long)(p), (src), (count))
+#define iowrite16_rep(p, src, count) outsw((unsigned long)(p), (src), (count))
+#define iowrite32_rep(p, src, count) outsl((unsigned long)(p), (src), (count))
+
 #define mmiowb()
 
 #define flush_write_buffers() do { } while (0)  /* M32R_FIXME */

arch/mips/Makefile

@@ -285,11 +285,11 @@ CLEAN_FILES += vmlinux.32 vmlinux.64
 
 archprepare:
 ifdef CONFIG_MIPS32_N32
-	@echo '  Checking missing-syscalls for N32'
+	@$(kecho) '  Checking missing-syscalls for N32'
 	$(Q)$(MAKE) $(build)=. missing-syscalls missing_syscalls_flags="-mabi=n32"
 endif
 ifdef CONFIG_MIPS32_O32
-	@echo '  Checking missing-syscalls for O32'
+	@$(kecho) '  Checking missing-syscalls for O32'
 	$(Q)$(MAKE) $(build)=. missing-syscalls missing_syscalls_flags="-mabi=32"
 endif
 

arch/mips/ar7/clock.c

@@ -430,6 +430,9 @@ EXPORT_SYMBOL(clk_disable);
 
 unsigned long clk_get_rate(struct clk *clk)
 {
+	if (!clk)
+		return 0;
+
 	return clk->rate;
 }
 EXPORT_SYMBOL(clk_get_rate);

arch/mips/ar7/platform.c

@@ -541,6 +541,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
+	uart_port.flags		= UPF_FIXED_TYPE;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;

arch/mips/bcm63xx/clk.c

@@ -193,6 +193,9 @@ EXPORT_SYMBOL(clk_disable);
 
 unsigned long clk_get_rate(struct clk *clk)
 {
+	if (!clk)
+		return 0;
+
 	return clk->rate;
 }
 

arch/mips/cavium-octeon/octeon-memcpy.S

@@ -223,18 +223,18 @@ EXC(	STORE	t2, UNIT(6)(dst),	s_exc_p10u)
 	ADD	src, src, 16*NBYTES
 EXC(	STORE	t3, UNIT(7)(dst),	s_exc_p9u)
 	ADD	dst, dst, 16*NBYTES
-EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-8)(dst),	s_exc_p8u)
 EXC(	STORE	t1, UNIT(-7)(dst),	s_exc_p7u)
 EXC(	STORE	t2, UNIT(-6)(dst),	s_exc_p6u)
 EXC(	STORE	t3, UNIT(-5)(dst),	s_exc_p5u)
-EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-4)(dst),	s_exc_p4u)
 EXC(	STORE	t1, UNIT(-3)(dst),	s_exc_p3u)
 EXC(	STORE	t2, UNIT(-2)(dst),	s_exc_p2u)
@@ -400,6 +400,10 @@ done:
 	 nop
 	END(memcpy)
 
+l_exc_copy_rewind16:
+	/* Rewind src and dst by 16*NBYTES for l_exc_copy */
+	SUB	src, src, 16*NBYTES
+	SUB	dst, dst, 16*NBYTES
 l_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a

arch/mips/configs/ip27_defconfig

@@ -206,7 +206,6 @@ CONFIG_MLX4_EN=m
 # CONFIG_MLX4_DEBUG is not set
 CONFIG_TEHUTI=m
 CONFIG_BNX2X=m
-CONFIG_QLGE=m
 CONFIG_SFC=m
 CONFIG_BE2NET=m
 CONFIG_LIBERTAS_THINFIRM=m

arch/mips/include/asm/checksum.h

@@ -155,7 +155,9 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr,
 	"	daddu	%0, %4		\n"
 	"	dsll32	$1, %0, 0	\n"
 	"	daddu	%0, $1		\n"
+	"	sltu	$1, %0, $1	\n"
 	"	dsra32	%0, %0, 0	\n"
+	"	addu	%0, $1		\n"
 #endif
 	"	.set	pop"
 	: "=r" (sum)

arch/mips/include/asm/kprobes.h

@@ -40,7 +40,8 @@ typedef union mips_instruction kprobe_opcode_t;
 
 #define flush_insn_slot(p)						\
 do {									\
-	flush_icache_range((unsigned long)p->addr,			\
+	if (p->addr)							\
+		flush_icache_range((unsigned long)p->addr,		\
 			   (unsigned long)p->addr +			\
 			   (MAX_INSN_SIZE * sizeof(kprobe_opcode_t)));	\
 } while (0)

arch/mips/kernel/branch.c

@@ -247,7 +247,8 @@ unaligned:
 	return -EFAULT;
 
 sigill:
-	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
-	force_sig(SIGBUS, current);
+	pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n",
+		current->comm);
+	force_sig(SIGILL, current);
 	return -EFAULT;
 }

arch/mips/kernel/entry.S

@@ -10,6 +10,7 @@
 
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -145,6 +146,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and
@@ -172,6 +174,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace

arch/mips/kernel/kgdb.c

@@ -236,9 +236,6 @@ static int compute_signal(int tt)
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
 	int reg;
-	struct thread_info *ti = task_thread_info(p);
-	unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32;
-	struct pt_regs *regs = (struct pt_regs *)ksp - 1;
 #if (KGDB_GDB_REG_SIZE == 32)
 	u32 *ptr = (u32 *)gdb_regs;
 #else
@@ -246,25 +243,46 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 #endif
 
 	for (reg = 0; reg < 16; reg++)
-		*(ptr++) = regs->regs[reg];
+		*(ptr++) = 0;
 
 	/* S0 - S7 */
-	for (reg = 16; reg < 24; reg++)
-		*(ptr++) = regs->regs[reg];
+	*(ptr++) = p->thread.reg16;
+	*(ptr++) = p->thread.reg17;
+	*(ptr++) = p->thread.reg18;
+	*(ptr++) = p->thread.reg19;
+	*(ptr++) = p->thread.reg20;
+	*(ptr++) = p->thread.reg21;
+	*(ptr++) = p->thread.reg22;
+	*(ptr++) = p->thread.reg23;
 
 	for (reg = 24; reg < 28; reg++)
 		*(ptr++) = 0;
 
 	/* GP, SP, FP, RA */
-	for (reg = 28; reg < 32; reg++)
-		*(ptr++) = regs->regs[reg];
+	*(ptr++) = (long)p;
+	*(ptr++) = p->thread.reg29;
+	*(ptr++) = p->thread.reg30;
+	*(ptr++) = p->thread.reg31;
 
-	*(ptr++) = regs->cp0_status;
-	*(ptr++) = regs->lo;
-	*(ptr++) = regs->hi;
-	*(ptr++) = regs->cp0_badvaddr;
-	*(ptr++) = regs->cp0_cause;
-	*(ptr++) = regs->cp0_epc;
+	*(ptr++) = p->thread.cp0_status;
+
+	/* lo, hi */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * BadVAddr, Cause
+	 * Ideally these would come from the last exception frame up the stack
+	 * but that requires unwinding, otherwise we can't know much for sure.
+	 */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * PC
+	 * use return address (RA), i.e. the moment after return from resume()
+	 */
+	*(ptr++) = p->thread.reg31;
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)

arch/mips/kernel/mips_ksyms.c

@@ -5,7 +5,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05 by Ralf Baechle
+ * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05, 12 by Ralf Baechle
  * Copyright (C) 1999, 2000, 01 Silicon Graphics, Inc.
  */
 #include <linux/interrupt.h>
@@ -34,6 +34,12 @@ EXPORT_SYMBOL(memmove);
 
 EXPORT_SYMBOL(kernel_thread);
 
+/*
+ * Functions that operate on entire pages.  Mostly used by memory management.
+ */
+EXPORT_SYMBOL(clear_page);
+EXPORT_SYMBOL(copy_page);
+
 /*
  * Userspace access stuff.
  */

arch/mips/kernel/syscall.c

@@ -203,7 +203,7 @@ static inline int mips_atomic_set(struct pt_regs *regs,
 		"1:	ll	%[old], (%[addr])			\n"
 		"	move	%[tmp], %[new]				\n"
 		"2:	sc	%[tmp], (%[addr])			\n"
-		"	bnez	%[tmp], 4f				\n"
+		"	beqz	%[tmp], 4f				\n"
 		"3:							\n"
 		"	.subsection 2					\n"
 		"4:	b	1b					\n"

arch/mips/mm/Makefile

@@ -3,8 +3,8 @@
 #
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
-				   init.o mmap.o tlbex.o tlbex-fault.o uasm.o \
-				   page.o
+				   init.o mmap.o page.o page-funcs.o \
+				   tlbex.o tlbex-fault.o uasm.o
 
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o

arch/mips/mm/mmap.c

@@ -70,6 +70,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long addr = addr0;
+	unsigned long vm_start;
 	int do_color_align;
 
 	if (unlikely(len > TASK_SIZE))
@@ -103,7 +104,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -118,7 +119,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 			/* At this point:  (!vma || addr < vma->vm_end). */
 			if (TASK_SIZE - len < addr)
 				return -ENOMEM;
-			if (!vma || addr + len <= vma->vm_start)
+			if (!vma || addr + len <= vm_start_gap(vma))
 				return addr;
 			addr = vma->vm_end;
 			if (do_color_align)
@@ -145,7 +146,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 		/* make sure it can fit in the remaining address space */
 		if (likely(addr > len)) {
 			vma = find_vma(mm, addr - len);
-			if (!vma || addr <= vma->vm_start) {
+			if (!vma || addr <= vm_start_gap(vma)) {
 				/* cache the address as a hint for next time */
 				return mm->free_area_cache = addr - len;
 			}
@@ -165,20 +166,22 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 			 * return with success:
 			 */
 			vma = find_vma(mm, addr);
-			if (likely(!vma || addr + len <= vma->vm_start)) {
+			if (vma)
+				vm_start = vm_start_gap(vma);
+			if (likely(!vma || addr + len <= vm_start)) {
 				/* cache the address as a hint for next time */
 				return mm->free_area_cache = addr;
 			}
 
 			/* remember the largest hole we saw so far */
-			if (addr + mm->cached_hole_size < vma->vm_start)
-				mm->cached_hole_size = vma->vm_start - addr;
+			if (addr + mm->cached_hole_size < vm_start)
+				mm->cached_hole_size = vm_start - addr;
 
 			/* try just below the current vma->vm_start */
-			addr = vma->vm_start - len;
+			addr = vm_start - len;
 			if (do_color_align)
 				addr = COLOUR_ALIGN_DOWN(addr, pgoff);
-		} while (likely(len < vma->vm_start));
+		} while (likely(len < vm_start));
 
 bottomup:
 		/*

arch/mips/mm/page-funcs.S

@@ -0,0 +1,50 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Micro-assembler generated clear_page/copy_page functions.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.
+ * Copyright (C) 2012  Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <asm/asm.h>
+#include <asm/regdef.h>
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+#define cpu_clear_page_function_name	clear_page_cpu
+#define cpu_copy_page_function_name	copy_page_cpu
+#else
+#define cpu_clear_page_function_name	clear_page
+#define cpu_copy_page_function_name	copy_page
+#endif
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x058 bytes
+ * R4600 v1.7:				0x05c bytes
+ * R4600 v2.0:				0x060 bytes
+ * With prefetching, 16 word strides	0x120 bytes
+ */
+EXPORT(__clear_page_start)
+LEAF(cpu_clear_page_function_name)
+1:	j	1b		/* Dummy, will be replaced. */
+	.space 288
+END(cpu_clear_page_function_name)
+EXPORT(__clear_page_end)
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x11c bytes
+ * R4600 v1.7:				0x080 bytes
+ * R4600 v2.0:				0x07c bytes
+ * With prefetching, 16 word strides	0x540 bytes
+ */
+EXPORT(__copy_page_start)
+LEAF(cpu_copy_page_function_name)
+1:	j	1b		/* Dummy, will be replaced. */
+	.space 1344
+END(cpu_copy_page_function_name)
+EXPORT(__copy_page_end)

arch/mips/mm/page.c

@@ -6,6 +6,7 @@
  * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 2007  Maciej W. Rozycki
  * Copyright (C) 2008  Thiemo Seufer
+ * Copyright (C) 2012  MIPS Technologies, Inc.
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -72,45 +73,6 @@ static struct uasm_reloc __cpuinitdata relocs[5];
 #define cpu_is_r4600_v1_x()	((read_c0_prid() & 0xfffffff0) == 0x00002010)
 #define cpu_is_r4600_v2_x()	((read_c0_prid() & 0xfffffff0) == 0x00002020)
 
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x058 bytes
- * R4600 v1.7:				0x05c bytes
- * R4600 v2.0:				0x060 bytes
- * With prefetching, 16 word strides	0x120 bytes
- */
-
-static u32 clear_page_array[0x120 / 4];
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-void clear_page_cpu(void *page) __attribute__((alias("clear_page_array")));
-#else
-void clear_page(void *page) __attribute__((alias("clear_page_array")));
-#endif
-
-EXPORT_SYMBOL(clear_page);
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x11c bytes
- * R4600 v1.7:				0x080 bytes
- * R4600 v2.0:				0x07c bytes
- * With prefetching, 16 word strides	0x540 bytes
- */
-static u32 copy_page_array[0x540 / 4];
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-void
-copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array")));
-#else
-void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
-#endif
-
-EXPORT_SYMBOL(copy_page);
-
-
 static int pref_bias_clear_store __cpuinitdata;
 static int pref_bias_copy_load __cpuinitdata;
 static int pref_bias_copy_store __cpuinitdata;
@@ -283,10 +245,15 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off)
 		}
 }
 
+extern u32 __clear_page_start;
+extern u32 __clear_page_end;
+extern u32 __copy_page_start;
+extern u32 __copy_page_end;
+
 void __cpuinit build_clear_page(void)
 {
 	int off;
-	u32 *buf = (u32 *)&clear_page_array;
+	u32 *buf = &__clear_page_start;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
@@ -357,17 +324,17 @@ void __cpuinit build_clear_page(void)
 	uasm_i_jr(&buf, RA);
 	uasm_i_nop(&buf);
 
-	BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array));
+	BUG_ON(buf > &__clear_page_end);
 
 	uasm_resolve_relocs(relocs, labels);
 
 	pr_debug("Synthesized clear page handler (%u instructions).\n",
-		 (u32)(buf - clear_page_array));
+		 (u32)(buf - &__clear_page_start));
 
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (buf - clear_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
+	for (i = 0; i < (buf - &__clear_page_start); i++)
+		pr_debug("\t.word 0x%08x\n", (&__clear_page_start)[i]);
 	pr_debug("\t.set pop\n");
 }
 
@@ -428,7 +395,7 @@ static inline void build_copy_store_pref(u32 **buf, int off)
 void __cpuinit build_copy_page(void)
 {
 	int off;
-	u32 *buf = (u32 *)&copy_page_array;
+	u32 *buf = &__copy_page_start;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
@@ -596,21 +563,23 @@ void __cpuinit build_copy_page(void)
 	uasm_i_jr(&buf, RA);
 	uasm_i_nop(&buf);
 
-	BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array));
+	BUG_ON(buf > &__copy_page_end);
 
 	uasm_resolve_relocs(relocs, labels);
 
 	pr_debug("Synthesized copy page handler (%u instructions).\n",
-		 (u32)(buf - copy_page_array));
+		 (u32)(buf - &__copy_page_start));
 
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (buf - copy_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
+	for (i = 0; i < (buf - &__copy_page_start); i++)
+		pr_debug("\t.word 0x%08x\n", (&__copy_page_start)[i]);
 	pr_debug("\t.set pop\n");
 }
 
 #ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+extern void clear_page_cpu(void *page);
+extern void copy_page_cpu(void *to, void *from);
 
 /*
  * Pad descriptors to cacheline, since each is exclusively owned by a

arch/parisc/include/asm/bitops.h

@@ -6,7 +6,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
 #include <asm/byteorder.h>
 #include <linux/atomic.h>
 
@@ -16,6 +16,12 @@
  * to include/asm-i386/bitops.h or kerneldoc
  */
 
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 

arch/parisc/include/asm/bitsperlong.h

@@ -9,10 +9,8 @@
  */
 #if (defined(__KERNEL__) && defined(CONFIG_64BIT)) || defined (__LP64__)
 #define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
 #else
 #define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
 #endif
 
 #include <asm-generic/bitsperlong.h>

arch/parisc/include/asm/swab.h

@@ -1,6 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
+#include <asm/bitsperlong.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 }
 #define __arch_swab32 __arch_swab32
 
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
 /*
 ** From "PA-RISC 2.0 Architecture", HP Professional Books.
 ** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 	return x;
 }
 #define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
 
 #endif /* _PARISC_SWAB_H */

arch/parisc/kernel/sys_parisc.c

@@ -35,17 +35,27 @@
 
 static unsigned long get_unshared_area(unsigned long addr, unsigned long len)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
+	unsigned long prev_end;
 
 	addr = PAGE_ALIGN(addr);
 
-	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
+	for (vma = find_vma_prev(current->mm, addr, &prev); ; prev = vma,
+							vma = vma->vm_next) {
+		if (prev) {
+			prev_end = vm_end_gap(prev);
+			if (addr < prev_end) {
+				addr = prev_end;
+				/* If vma already violates gap, forget it */
+				if (vma && addr > vma->vm_start)
+					addr = vma->vm_start;
+			}
+		}
 		/* At this point:  (!vma || addr < vma->vm_end). */
 		if (TASK_SIZE - len < addr)
 			return -ENOMEM;
-		if (!vma || addr + len <= vma->vm_start)
+		if (!vma || addr + len <= vm_start_gap(vma))
 			return addr;
-		addr = vma->vm_end;
 	}
 }
 
@@ -70,22 +80,32 @@ static int get_offset(struct address_space *mapping)
 static unsigned long get_shared_area(struct address_space *mapping,
 		unsigned long addr, unsigned long len, unsigned long pgoff)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
+	unsigned long prev_end;
 	int offset = mapping ? get_offset(mapping) : 0;
 
 	offset = (offset + (pgoff << PAGE_SHIFT)) & 0x3FF000;
 
 	addr = DCACHE_ALIGN(addr - offset) + offset;
 
-	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
+	for (vma = find_vma_prev(current->mm, addr, &prev); ; prev = vma,
+							vma = vma->vm_next) {
+		if (prev) {
+			prev_end = vm_end_gap(prev);
+			if (addr < prev_end) {
+				addr = DCACHE_ALIGN(prev_end - offset) + offset;
+				if (addr < prev_end)	/* handle wraparound */
+					return -ENOMEM;
+				/* If vma already violates gap, forget it */
+				if (vma && addr > vma->vm_start)
+					addr = vma->vm_start;
+			}
+		}
 		/* At this point:  (!vma || addr < vma->vm_end). */
 		if (TASK_SIZE - len < addr)
 			return -ENOMEM;
-		if (!vma || addr + len <= vma->vm_start)
+		if (!vma || addr + len <= vm_start_gap(vma))
 			return addr;
-		addr = DCACHE_ALIGN(vma->vm_end - offset) + offset;
-		if (addr < vma->vm_end) /* handle wraparound */
-			return -ENOMEM;
 	}
 }
 

arch/parisc/kernel/syscall.S

@@ -82,8 +82,6 @@ linux_gateway_entry:
 	mtsp	%r0,%sr4			/* get kernel space into sr4 */
 	mtsp	%r0,%sr5			/* get kernel space into sr5 */
 	mtsp	%r0,%sr6			/* get kernel space into sr6 */
-	mfsp    %sr7,%r1                        /* save user sr7 */
-	mtsp    %r1,%sr3                        /* and store it in sr3 */
 
 #ifdef CONFIG_64BIT
 	/* for now we can *always* set the W bit on entry to the syscall
@@ -109,6 +107,14 @@ linux_gateway_entry:
 	depdi	0, 31, 32, %r21
 1:	
 #endif
+
+	/* We use a rsm/ssm pair to prevent sr3 from being clobbered
+	 * by external interrupts.
+	 */
+	mfsp    %sr7,%r1                        /* save user sr7 */
+	rsm	PSW_SM_I, %r0			/* disable interrupts */
+	mtsp    %r1,%sr3                        /* and store it in sr3 */
+
 	mfctl   %cr30,%r1
 	xor     %r1,%r30,%r30                   /* ye olde xor trick */
 	xor     %r1,%r30,%r1
@@ -123,6 +129,7 @@ linux_gateway_entry:
 	 */
 
 	mtsp	%r0,%sr7			/* get kernel space into sr7 */
+	ssm	PSW_SM_I, %r0			/* enable interrupts */
 	STREGM	%r1,FRAME_SIZE(%r30)		/* save r1 (usp) here for now */
 	mfctl	%cr30,%r1			/* get task ptr in %r1 */
 	LDREG	TI_TASK(%r1),%r1

arch/parisc/kernel/syscall_table.S

@@ -364,7 +364,7 @@
 	ENTRY_SAME(ni_syscall)	/* 263: reserved for vserver */
 	ENTRY_SAME(add_key)
 	ENTRY_SAME(request_key)		/* 265 */
-	ENTRY_SAME(keyctl)
+	ENTRY_COMP(keyctl)
 	ENTRY_SAME(ioprio_set)
 	ENTRY_SAME(ioprio_get)
 	ENTRY_SAME(inotify_init)

arch/powerpc/boot/4xx.c

@@ -564,7 +564,7 @@ void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk)
 		fbdv = 16;
 	cbdv = ((pllmr & 0x00060000) >> 17) + 1; /* CPU:PLB */
 	opdv = ((pllmr & 0x00018000) >> 15) + 1; /* PLB:OPB */
-	ppdv = ((pllmr & 0x00001800) >> 13) + 1; /* PLB:PCI */
+	ppdv = ((pllmr & 0x00006000) >> 13) + 1; /* PLB:PCI */
 	epdv = ((pllmr & 0x00001800) >> 11) + 2; /* PLB:EBC */
 	udiv = ((cpc0_cr0 & 0x3e) >> 1) + 1;
 

arch/powerpc/boot/ps3-head.S

@@ -57,11 +57,6 @@ __system_reset_overlay:
 	bctr
 
 1:
-	/* Save the value at addr zero for a null pointer write check later. */
-
-	li	r4, 0
-	lwz	r3, 0(r4)
-
 	/* Primary delays then goes to _zimage_start in wrapper. */
 
 	or	31, 31, 31 /* db16cyc */

arch/powerpc/boot/ps3.c

@@ -119,13 +119,12 @@ void ps3_copy_vectors(void)
 	flush_cache((void *)0x100, 512);
 }
 
-void platform_init(unsigned long null_check)
+void platform_init(void)
 {
 	const u32 heapsize = 0x1000000 - (u32)_end; /* 16MiB */
 	void *chosen;
 	unsigned long ft_addr;
 	u64 rm_size;
-	unsigned long val;
 
 	console_ops.write = ps3_console_write;
 	platform_ops.exit = ps3_exit;
@@ -153,11 +152,6 @@ void platform_init(unsigned long null_check)
 
 	printf(" flat tree at 0x%lx\n\r", ft_addr);
 
-	val = *(unsigned long *)0;
-
-	if (val != null_check)
-		printf("null check failed: %lx != %lx\n\r", val, null_check);
-
 	((kernel_entry_t)0)(ft_addr, 0, NULL);
 
 	ps3_exit();

arch/powerpc/include/asm/page.h

@@ -118,7 +118,19 @@ extern phys_addr_t kernstart_addr;
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * On hash the vmalloc and other regions alias to the kernel region when passed
+ * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
+ * return true for some vmalloc addresses, which is incorrect. So explicitly
+ * check that the address is in the kernel region.
+ */
+#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+				pfn_valid(__pa(kaddr) >> PAGE_SHIFT))
+#else
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#endif
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't

arch/powerpc/include/asm/ppc-opcode.h

@@ -31,7 +31,7 @@
 #define PPC_INST_MCRXR			0x7c000400
 #define PPC_INST_MCRXR_MASK		0xfc0007fe
 #define PPC_INST_MFSPR_PVR		0x7c1f42a6
-#define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
+#define PPC_INST_MFSPR_PVR_MASK		0xfc1ffffe
 #define PPC_INST_MSGSND			0x7c00019c
 #define PPC_INST_NOP			0x60000000
 #define PPC_INST_POPCNTB		0x7c0000f4
@@ -42,9 +42,9 @@
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
 #define PPC_INST_MFSPR_DSCR		0x7c1102a6
-#define PPC_INST_MFSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR		0x7c1103a6
-#define PPC_INST_MTSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_MASK	0xfc1ffffe
 
 #define PPC_INST_STRING			0x7c00042a
 #define PPC_INST_STRING_MASK		0xfc0007fe
@@ -58,7 +58,7 @@
 #define PPC_INST_WAIT			0x7c00007c
 #define PPC_INST_TLBIVAX		0x7c000624
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
-#define PPC_INST_XXLOR			0xf0000510
+#define PPC_INST_XXLOR			0xf0000490
 
 #define PPC_INST_NAP			0x4c000364
 #define PPC_INST_SLEEP			0x4c0003a4

arch/powerpc/include/asm/qe.h

@@ -193,6 +193,7 @@ static inline int qe_alive_during_sleep(void)
 #define qe_muram_free cpm_muram_free
 #define qe_muram_addr cpm_muram_addr
 #define qe_muram_offset cpm_muram_offset
+#define qe_muram_dma cpm_muram_dma
 
 /* Structure that defines QE firmware binary files.
  *

arch/powerpc/include/asm/reg.h

@@ -1054,7 +1054,9 @@
 				"	.llong 0\n"			\
 				"	.llong 0\n"			\
 				".previous"				\
-			: "=r" (rval) : "i" (CPU_FTR_CELL_TB_BUG)); rval;})
+			: "=r" (rval) \
+			: "i" (CPU_FTR_CELL_TB_BUG) : "cr0"); \
+			rval;})
 #else
 #define mftb()		({unsigned long rval;	\
 			asm volatile("mftb %0" : "=r" (rval)); rval;})

arch/powerpc/kernel/align.c

@@ -764,14 +764,25 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
-	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
-	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
-		nb = 8;
-		flags = LD+SW;
-	} else if (IS_XFORM(instruction) &&
-		   ((instruction >> 1) & 0x3ff) == 660) {
-		nb = 8;
-		flags = ST+SW;
+	/*
+	 * Handle some cases which give overlaps in the DSISR values.
+	 */
+	if (IS_XFORM(instruction)) {
+		switch ((instruction >> 1) & 0x3ff) {
+		case 532:	/* ldbrx */
+			nb = 8;
+			flags = LD+SW;
+			break;
+		case 660:	/* stdbrx */
+			nb = 8;
+			flags = ST+SW;
+			break;
+		case 20:	/* lwarx */
+		case 84:	/* ldarx */
+		case 116:	/* lharx */
+		case 276:	/* lqarx */
+			return 0;	/* not emulated ever */
+		}
 	}
 
 	/* Byteswap little endian loads and stores */

arch/powerpc/kernel/hw_breakpoint.c

@@ -226,8 +226,10 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	rcu_read_lock();
 
 	bp = __get_cpu_var(bp_per_reg);
-	if (!bp)
+	if (!bp) {
+		rc = NOTIFY_DONE;
 		goto out;
+	}
 	info = counter_arch_bp(bp);
 
 	/*

arch/powerpc/kernel/ibmebus.c

@@ -179,6 +179,7 @@ static int ibmebus_create_device(struct device_node *dn)
 static int ibmebus_create_devices(const struct of_device_id *matches)
 {
 	struct device_node *root, *child;
+	struct device *dev;
 	int ret = 0;
 
 	root = of_find_node_by_path("/");
@@ -187,9 +188,12 @@ static int ibmebus_create_devices(const struct of_device_id *matches)
 		if (!of_match_node(matches, child))
 			continue;
 
-		if (bus_find_device(&ibmebus_bus_type, NULL, child,
-				    ibmebus_match_node))
+		dev = bus_find_device(&ibmebus_bus_type, NULL, child,
+				      ibmebus_match_node);
+		if (dev) {
+			put_device(dev);
 			continue;
+		}
 
 		ret = ibmebus_create_device(child);
 		if (ret) {
@@ -261,6 +265,7 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device_node *dn = NULL;
+	struct device *dev;
 	char *path;
 	ssize_t rc = 0;
 
@@ -268,8 +273,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 	if (!path)
 		return -ENOMEM;
 
-	if (bus_find_device(&ibmebus_bus_type, NULL, path,
-			    ibmebus_match_path)) {
+	dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+			      ibmebus_match_path);
+	if (dev) {
+		put_device(dev);
 		printk(KERN_WARNING "%s: %s has already been probed\n",
 		       __func__, path);
 		rc = -EEXIST;
@@ -305,6 +312,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 	if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
 				   ibmebus_match_path))) {
 		of_device_unregister(to_platform_device(dev));
+		put_device(dev);
 
 		kfree(path);
 		return count;

arch/powerpc/kernel/idle_power7.S

@@ -67,7 +67,7 @@ _GLOBAL(power7_idle)
 	std	r0,0(r1)
 	ptesync
 	ld	r0,0(r1)
-1:	cmp	cr0,r0,r0
+1:	cmpd	cr0,r0,r0
 	bne	1b
 	PPC_NAP
 	b	.

arch/powerpc/kernel/kprobes.c

@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
+#include <linux/ftrace.h>
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
 #include <asm/uaccess.h>
@@ -530,6 +531,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 
@@ -552,6 +562,8 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }

arch/powerpc/kernel/nvram_64.c

@@ -280,7 +280,7 @@ int __init nvram_remove_partition(const char *name, int sig,
 
 		/* Make partition a free partition */
 		part->header.signature = NVRAM_SIG_FREE;
-		strncpy(part->header.name, "wwwwwwwwwwww", 12);
+		memset(part->header.name, 'w', 12);
 		part->header.checksum = nvram_checksum(&part->header);
 		rc = nvram_write_header(part);
 		if (rc <= 0) {
@@ -298,8 +298,8 @@ int __init nvram_remove_partition(const char *name, int sig,
 		}
 		if (prev) {
 			prev->header.length += part->header.length;
-			prev->header.checksum = nvram_checksum(&part->header);
-			rc = nvram_write_header(part);
+			prev->header.checksum = nvram_checksum(&prev->header);
+			rc = nvram_write_header(prev);
 			if (rc <= 0) {
 				printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
 				return rc;

arch/powerpc/kernel/ptrace.c

@@ -359,6 +359,10 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 	flush_fp_to_thread(target);
 
 #ifdef CONFIG_VSX
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_FPR(i);
+	memcpy(&buf[32], &target->thread.fpscr, sizeof(double));
+
 	/* copy to local buffer then write that out */
 	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 	if (i)
@@ -501,6 +505,9 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset,
 
 	flush_vsx_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.fpr[i][TS_VSRLOWOFFSET];
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	for (i = 0; i < 32 ; i++)

arch/powerpc/kernel/setup_64.c

@@ -508,6 +508,23 @@ static void __init exc_lvl_early_init(void)
 #define exc_lvl_early_init()
 #endif
 
+/*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+	ti->task = NULL;
+	ti->cpu = cpu;
+	ti->preempt_count = 0;
+	ti->local_flags = 0;
+	ti->flags = 0;
+}
+
 /*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled.
@@ -525,12 +542,20 @@ static void __init emergency_stack_init(void)
 	 * Since we use these as temporary stacks during secondary CPU
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
+	 *
+	 * The IRQ stacks allocated elsewhere in this file are zeroed and
+	 * initialized in kernel/irq.c. These are initialized here in order
+	 * to have emergency stacks available as early as possible.
 	 */
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
+		struct thread_info *ti;
 		sp  = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
+		ti = __va(sp);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		sp += THREAD_SIZE;
 		paca[i].emergency_sp = __va(sp);
 	}

arch/powerpc/kernel/vdso64/datapage.S

@@ -57,7 +57,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	bl	V_LOCAL_FUNC(__get_datapage)
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP64
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	li	r0,__NR_syscalls

arch/powerpc/kernel/vdso64/gettimeofday.S

@@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	bne	cr0,99f
 
 	li	r3,0
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	lis	r5,CLOCK_REALTIME_RES@h

arch/powerpc/lib/copyuser_64.S

@@ -330,6 +330,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	addi	r3,r3,8
 171:
 177:
+179:
 	addi	r3,r3,8
 370:
 372:
@@ -344,7 +345,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 173:
 174:
 175:
-179:
 181:
 184:
 186:

arch/powerpc/lib/sstep.c

@@ -863,6 +863,19 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			goto instr_done;
 #endif
 		case 19:	/* mfcr */
+			if ((instr >> 20) & 1) {
+				imm = 0xf0000000UL;
+				for (sh = 0; sh < 8; ++sh) {
+					if (instr & (0x80000 >> sh)) {
+						regs->gpr[rd] = regs->ccr & imm;
+						break;
+					}
+					imm >>= 4;
+				}
+
+				goto instr_done;
+			}
+
 			regs->gpr[rd] = regs->ccr;
 			regs->gpr[rd] &= 0xffffffffUL;
 			goto instr_done;

arch/powerpc/mm/hash_utils_64.c

@@ -383,7 +383,7 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 	printk(KERN_INFO "Huge page(16GB) memory: "
 			"addr = 0x%lX size = 0x%lX pages = %d\n",
 			phys_addr, block_size, expected_pages);
-	if (phys_addr + (16 * GB) <= memblock_end_of_DRAM()) {
+	if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) {
 		memblock_reserve(phys_addr, block_size * expected_pages);
 		add_gpage(phys_addr, block_size, expected_pages);
 	}

arch/powerpc/mm/slice.c

@@ -98,7 +98,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
 	if ((mm->task_size - len) < addr)
 		return 0;
 	vma = find_vma(mm, addr);
-	return (!vma || (addr + len) <= vma->vm_start);
+	return (!vma || (addr + len) <= vm_start_gap(vma));
 }
 
 static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
@@ -227,7 +227,7 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 					      int psize, int use_cache)
 {
 	struct vm_area_struct *vma;
-	unsigned long start_addr, addr;
+	unsigned long start_addr, addr, vm_start;
 	struct slice_mask mask;
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 
@@ -256,7 +256,9 @@ full_search:
 				addr = _ALIGN_UP(addr + 1,  1ul << SLICE_HIGH_SHIFT);
 			continue;
 		}
-		if (!vma || addr + len <= vma->vm_start) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (!vma || addr + len <= vm_start) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
@@ -264,8 +266,8 @@ full_search:
 				mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (use_cache && (addr + mm->cached_hole_size) < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 		addr = vma->vm_end;
 	}
 
@@ -284,7 +286,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 					     int psize, int use_cache)
 {
 	struct vm_area_struct *vma;
-	unsigned long addr;
+	unsigned long addr, vm_start;
 	struct slice_mask mask;
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 
@@ -336,7 +338,9 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 		 * return with success:
 		 */
 		vma = find_vma(mm, addr);
-		if (!vma || (addr + len) <= vma->vm_start) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (!vma || (addr + len) <= vm_start) {
 			/* remember the address as a hint for next time */
 			if (use_cache)
 				mm->free_area_cache = addr;
@@ -344,11 +348,11 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 		}
 
 		/* remember the largest hole we saw so far */
-		if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (use_cache && (addr + mm->cached_hole_size) < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = vma->vm_start;
+		addr = vm_start;
 	}
 
 	/*

arch/s390/boot/compressed/misc.c

@@ -135,31 +135,34 @@ static void check_ipl_parmblock(void *start, unsigned long size)
 
 unsigned long decompress_kernel(void)
 {
-	unsigned long output_addr;
-	unsigned char *output;
+	void *output, *kernel_end;
 
-	output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
-	check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
-	memset(&_bss, 0, &_ebss - &_bss);
-	free_mem_ptr = (unsigned long)&_end;
-	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
-	output = (unsigned char *) output_addr;
+	output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE);
+	kernel_end = output + SZ__bss_start;
+	check_ipl_parmblock((void *) 0, (unsigned long) kernel_end);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/*
 	 * Move the initrd right behind the end of the decompressed
-	 * kernel image.
+	 * kernel image. This also prevents initrd corruption caused by
+	 * bss clearing since kernel_end will always be located behind the
+	 * current bss section..
 	 */
-	if (INITRD_START && INITRD_SIZE &&
-	    INITRD_START < (unsigned long) output + SZ__bss_start) {
-		check_ipl_parmblock(output + SZ__bss_start,
-				    INITRD_START + INITRD_SIZE);
-		memmove(output + SZ__bss_start,
-			(void *) INITRD_START, INITRD_SIZE);
-		INITRD_START = (unsigned long) output + SZ__bss_start;
+	if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
+		check_ipl_parmblock(kernel_end, INITRD_SIZE);
+		memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
+		INITRD_START = (unsigned long) kernel_end;
 	}
 #endif
 
+	/*
+	 * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
+	 * initialized afterwards since they reside in bss.
+	 */
+	memset(&_bss, 0, &_ebss - &_bss);
+	free_mem_ptr = (unsigned long) &_end;
+	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
 	puts("Uncompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	puts("Ok, booting the kernel.\n");

arch/s390/include/asm/syscall.h

@@ -62,6 +62,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
 {
 	unsigned long mask = -1UL;
 
+	/*
+	 * No arguments for this syscall, there's nothing to do.
+	 */
+	if (!n)
+		return;
+
 	BUG_ON(i + n > 6);
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_31BIT))

arch/s390/mm/gup.c

@@ -51,13 +51,12 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	unsigned long mask, result;
 	struct page *head, *page, *tail;
+	unsigned long mask;
 	int refs;
 
-	result = write ? 0 : _SEGMENT_ENTRY_RO;
-	mask = result | _SEGMENT_ENTRY_INV;
-	if ((pmd_val(pmd) & mask) != result)
+	mask = (write ? _SEGMENT_ENTRY_RO : 0) | _SEGMENT_ENTRY_INV;
+	if ((pmd_val(pmd) & mask) != 0)
 		return 0;
 	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
 

arch/sh/include/cpu-sh4/cpu/sh7722.h

@@ -67,7 +67,7 @@ enum {
 	GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0,
 
 	/* PTQ */
-	GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4,
+	GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4,
 	GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0,
 
 	/* PTR */

arch/sh/include/cpu-sh4/cpu/sh7757.h

@@ -40,7 +40,7 @@ enum {
 
 	/* PTJ */
 	GPIO_PTJ0, GPIO_PTJ1, GPIO_PTJ2, GPIO_PTJ3,
-	GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, GPIO_PTJ7_RESV,
+	GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6,
 
 	/* PTK */
 	GPIO_PTK0, GPIO_PTK1, GPIO_PTK2, GPIO_PTK3,
@@ -48,7 +48,7 @@ enum {
 
 	/* PTL */
 	GPIO_PTL0, GPIO_PTL1, GPIO_PTL2, GPIO_PTL3,
-	GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, GPIO_PTL7_RESV,
+	GPIO_PTL4, GPIO_PTL5, GPIO_PTL6,
 
 	/* PTM */
 	GPIO_PTM0, GPIO_PTM1, GPIO_PTM2, GPIO_PTM3,
@@ -56,7 +56,7 @@ enum {
 
 	/* PTN */
 	GPIO_PTN0, GPIO_PTN1, GPIO_PTN2, GPIO_PTN3,
-	GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, GPIO_PTN7_RESV,
+	GPIO_PTN4, GPIO_PTN5, GPIO_PTN6,
 
 	/* PTO */
 	GPIO_PTO0, GPIO_PTO1, GPIO_PTO2, GPIO_PTO3,
@@ -68,7 +68,7 @@ enum {
 
 	/* PTQ */
 	GPIO_PTQ0, GPIO_PTQ1, GPIO_PTQ2, GPIO_PTQ3,
-	GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, GPIO_PTQ7_RESV,
+	GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6,
 
 	/* PTR */
 	GPIO_PTR0, GPIO_PTR1, GPIO_PTR2, GPIO_PTR3,

arch/sh/mm/mmap.c

@@ -47,7 +47,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 	int do_colour_align;
 
 	if (flags & MAP_FIXED) {
@@ -75,7 +75,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -106,15 +106,17 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (likely(!vma || addr + len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		addr = vma->vm_end;
 		if (do_colour_align)
@@ -130,6 +132,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
+	unsigned long vm_start;
 	int do_colour_align;
 
 	if (flags & MAP_FIXED) {
@@ -158,7 +161,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -179,7 +182,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* make sure it can fit in the remaining address space */
 	if (likely(addr > len)) {
 		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start) {
+		if (!vma || addr <= vm_start_gap(vma)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr-len);
 		}
@@ -199,20 +202,22 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		 * return with success:
 		 */
 		vma = find_vma(mm, addr);
-		if (likely(!vma || addr+len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr);
 		}
 
 		/* remember the largest hole we saw so far */
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = vma->vm_start-len;
+		addr = vm_start-len;
 		if (do_colour_align)
 			addr = COLOUR_ALIGN_DOWN(addr, pgoff);
-	} while (likely(len < vma->vm_start));
+	} while (likely(len < vm_start));
 
 bottomup:
 	/*

arch/sparc/kernel/leon_kernel.c

@@ -288,37 +288,37 @@ void __init leon_init_timers(irq_handler_t counter_fn)
 
 	/* Find GPTIMER Timer Registers base address otherwise bail out. */
 	nnp = rootnp;
-	do {
-		np = of_find_node_by_name(nnp, "GAISLER_GPTIMER");
-		if (!np) {
-			np = of_find_node_by_name(nnp, "01_011");
-			if (!np)
-				goto bad;
+
+retry:
+	np = of_find_node_by_name(nnp, "GAISLER_GPTIMER");
+	if (!np) {
+		np = of_find_node_by_name(nnp, "01_011");
+		if (!np)
+			goto bad;
+	}
+
+	ampopts = 0;
+	pp = of_find_property(np, "ampopts", &len);
+	if (pp) {
+		ampopts = *(int *)pp->value;
+		if (ampopts == 0) {
+			/* Skip this instance, resource already
+			 * allocated by other OS */
+			nnp = np;
+			goto retry;
 		}
+	}
 
-		ampopts = 0;
-		pp = of_find_property(np, "ampopts", &len);
-		if (pp) {
-			ampopts = *(int *)pp->value;
-			if (ampopts == 0) {
-				/* Skip this instance, resource already
-				 * allocated by other OS */
-				nnp = np;
-				continue;
-			}
-		}
+	/* Select Timer-Instance on Timer Core. Default is zero */
+	leon3_gptimer_idx = ampopts & 0x7;
 
-		/* Select Timer-Instance on Timer Core. Default is zero */
-		leon3_gptimer_idx = ampopts & 0x7;
-
-		pp = of_find_property(np, "reg", &len);
-		if (pp)
-			leon3_gptimer_regs = *(struct leon3_gptimer_regs_map **)
-						pp->value;
-		pp = of_find_property(np, "interrupts", &len);
-		if (pp)
-			leon3_gptimer_irq = *(unsigned int *)pp->value;
-	} while (0);
+	pp = of_find_property(np, "reg", &len);
+	if (pp)
+		leon3_gptimer_regs = *(struct leon3_gptimer_regs_map **)
+					pp->value;
+	pp = of_find_property(np, "interrupts", &len);
+	if (pp)
+		leon3_gptimer_irq = *(unsigned int *)pp->value;
 
 	if (!(leon3_gptimer_regs && leon3_irqctrl_regs && leon3_gptimer_irq))
 		goto bad;

arch/sparc/kernel/sys_sparc_32.c

@@ -71,7 +71,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		}
 		if (TASK_SIZE - PAGE_SIZE - len < addr)
 			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
+		if (!vmm || addr + len <= vm_start_gap(vmm))
 			return addr;
 		addr = vmm->vm_end;
 		if (flags & MAP_SHARED)

arch/sparc/kernel/sys_sparc_64.c

@@ -117,7 +117,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct * vma;
 	unsigned long task_size = TASK_SIZE;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 	int do_color_align;
 
 	if (flags & MAP_FIXED) {
@@ -147,7 +147,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -181,15 +181,17 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (likely(!vma || addr + len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		addr = vma->vm_end;
 		if (do_color_align)
@@ -205,7 +207,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	unsigned long task_size = STACK_TOP32;
-	unsigned long addr = addr0;
+	unsigned long addr = addr0, vm_start;
 	int do_color_align;
 
 	/* This should only ever run for 32-bit processes.  */
@@ -237,7 +239,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -258,7 +260,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* make sure it can fit in the remaining address space */
 	if (likely(addr > len)) {
 		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start) {
+		if (!vma || addr <= vm_start_gap(vma)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr-len);
 		}
@@ -278,20 +280,22 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		 * return with success:
 		 */
 		vma = find_vma(mm, addr);
-		if (likely(!vma || addr+len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr);
 		}
 
  		/* remember the largest hole we saw so far */
- 		if (addr + mm->cached_hole_size < vma->vm_start)
- 		        mm->cached_hole_size = vma->vm_start - addr;
+ 		if (addr + mm->cached_hole_size < vm_start)
+ 		        mm->cached_hole_size = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = vma->vm_start-len;
+		addr = vm_start - len;
 		if (do_color_align)
 			addr = COLOUR_ALIGN_DOWN(addr, pgoff);
-	} while (likely(len < vma->vm_start));
+	} while (likely(len < vm_start));
 
 bottomup:
 	/*

arch/sparc/mm/hugetlbpage.c

@@ -33,7 +33,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct * vma;
 	unsigned long task_size = TASK_SIZE;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 
 	if (test_thread_flag(TIF_32BIT))
 		task_size = STACK_TOP32;
@@ -67,15 +67,17 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (likely(!vma || addr + len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
 	}
@@ -90,6 +92,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
+	unsigned long vm_start;
 
 	/* This should only ever run for 32-bit processes.  */
 	BUG_ON(!test_thread_flag(TIF_32BIT));
@@ -106,7 +109,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* make sure it can fit in the remaining address space */
 	if (likely(addr > len)) {
 		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start) {
+		if (!vma || addr <= vm_start_gap(vma)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr-len);
 		}
@@ -124,18 +127,20 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		 * return with success:
 		 */
 		vma = find_vma(mm, addr);
-		if (likely(!vma || addr+len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr);
 		}
 
  		/* remember the largest hole we saw so far */
- 		if (addr + mm->cached_hole_size < vma->vm_start)
- 		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start-len) & HPAGE_MASK;
-	} while (likely(len < vma->vm_start));
+		addr = (vm_start - len) & HPAGE_MASK;
+	} while (likely(len < vm_start));
 
 bottomup:
 	/*
@@ -182,7 +187,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, HPAGE_SIZE);
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (mm->get_unmapped_area == arch_get_unmapped_area)

arch/tile/kernel/setup.c

@@ -119,7 +119,8 @@ early_param("maxmem", setup_maxmem);
 static int __init setup_maxnodemem(char *str)
 {
 	char *endp;
-	long maxnodemem_mb, node;
+	long maxnodemem_mb;
+	unsigned long node;
 
 	node = str ? simple_strtoul(str, &endp, 0) : INT_MAX;
 	if (node >= MAX_NUMNODES || *endp != ':' ||

arch/tile/mm/hugetlbpage.c

@@ -159,7 +159,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 
 	if (len > mm->cached_hole_size) {
 		start_addr = mm->free_area_cache;
@@ -185,12 +185,14 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (!vma || addr + len <= vma->vm_start) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (!vma || addr + len <= vm_start) {
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-			mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 		addr = ALIGN(vma->vm_end, huge_page_size(h));
 	}
 }
@@ -204,6 +206,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 	struct vm_area_struct *vma, *prev_vma;
 	unsigned long base = mm->mmap_base, addr = addr0;
 	unsigned long largest_hole = mm->cached_hole_size;
+	unsigned long vm_start;
 	int first_time = 1;
 
 	/* don't allow allocations above current base */
@@ -234,9 +237,10 @@ try_again:
 
 		/*
 		 * new region fits between prev_vma->vm_end and
-		 * vma->vm_start, use it:
+		 * vm_start, use it:
 		 */
-		if (addr + len <= vma->vm_start &&
+		vm_start = vm_start_gap(vma);
+		if (addr + len <= vm_start &&
 			    (!prev_vma || (addr >= prev_vma->vm_end))) {
 			/* remember the address as a hint for next time */
 			mm->cached_hole_size = largest_hole;
@@ -251,13 +255,13 @@ try_again:
 		}
 
 		/* remember the largest hole we saw so far */
-		if (addr + largest_hole < vma->vm_start)
-			largest_hole = vma->vm_start - addr;
+		if (addr + largest_hole < vm_start)
+			largest_hole = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start - len) & huge_page_mask(h);
+		addr = (vm_start - len) & huge_page_mask(h);
 
-	} while (len <= vma->vm_start);
+	} while (len <= vm_start);
 
 fail:
 	/*
@@ -312,7 +316,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (current->mm->get_unmapped_area == arch_get_unmapped_area)

arch/x86/boot/boot.h

@@ -16,7 +16,7 @@
 #ifndef BOOT_BOOT_H
 #define BOOT_BOOT_H
 
-#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+#define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
 #ifndef __ASSEMBLY__
 

arch/x86/boot/compressed/misc.h

@@ -7,6 +7,7 @@
  * we just keep it from happening
  */
 #undef CONFIG_PARAVIRT
+#undef CONFIG_PAGE_TABLE_ISOLATION
 #ifdef CONFIG_X86_32
 #define _ASM_X86_DESC_H 1
 #endif

arch/x86/crypto/salsa20_glue.c

@@ -64,13 +64,6 @@ static int encrypt(struct blkcipher_desc *desc,
 
 	salsa20_ivsetup(ctx, walk.iv);
 
-	if (likely(walk.nbytes == nbytes))
-	{
-		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
-				      walk.dst.virt.addr, nbytes);
-		return blkcipher_walk_done(desc, &walk, 0);
-	}
-
 	while (walk.nbytes >= 64) {
 		salsa20_encrypt_bytes(ctx, walk.src.virt.addr,
 				      walk.dst.virt.addr,

arch/x86/ia32/ia32entry.S

@@ -12,6 +12,10 @@
 #include <asm/ia32_unistd.h>	
 #include <asm/thread_info.h>	
 #include <asm/segment.h>
+#include <asm/pgtable_types.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeature.h>
+#include <asm/kaiser.h>
 #include <asm/irqflags.h>
 #include <linux/linkage.h>
 
@@ -120,6 +124,7 @@ ENTRY(ia32_sysenter_target)
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rsp,rbp
 	SWAPGS_UNSAFE_STACK
+	SWITCH_KERNEL_CR3_NO_STACK
 	movq	PER_CPU_VAR(kernel_stack), %rsp
 	addq	$(KERNEL_STACK_OFFSET),%rsp
 	/*
@@ -183,6 +188,7 @@ sysexit_from_sys_call:
 	popq_cfi %rcx				/* User %esp */
 	CFI_REGISTER rsp,rcx
 	TRACE_IRQS_ON
+	SWITCH_USER_CR3
 	ENABLE_INTERRUPTS_SYSEXIT32
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -281,6 +287,7 @@ ENTRY(ia32_cstar_target)
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	SWAPGS_UNSAFE_STACK
+	SWITCH_KERNEL_CR3_NO_STACK
 	movl	%esp,%r8d
 	CFI_REGISTER	rsp,r8
 	movq	PER_CPU_VAR(kernel_stack),%rsp
@@ -337,6 +344,7 @@ sysretl_from_sys_call:
 	xorq	%r9,%r9
 	xorq	%r8,%r8
 	TRACE_IRQS_ON
+	SWITCH_USER_CR3
 	movl RSP-ARGOFFSET(%rsp),%esp
 	CFI_RESTORE rsp
 	USERGS_SYSRET32
@@ -409,6 +417,7 @@ ENTRY(ia32_syscall)
 	CFI_REL_OFFSET	rip,RIP-RIP
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	SWAPGS
+	SWITCH_KERNEL_CR3_NO_STACK
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:

arch/x86/include/asm/alternative-asm.h

@@ -15,12 +15,53 @@
 	.endm
 #endif
 
-.macro altinstruction_entry orig alt feature orig_len alt_len
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
 	.long \orig - .
 	.long \alt - .
 	.word \feature
 	.byte \orig_len
 	.byte \alt_len
+	.byte \pad_len
+.endm
+
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr
+144:
+	.popsection
+.endm
+
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+	.skip -(((145f-144f)-(144f-143f)-(141b-140b)) > 0) * ((145f-144f)-(144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	.popsection
 .endm
 
 #endif  /*  __ASSEMBLY__  */

arch/x86/include/asm/alternative.h

@@ -47,8 +47,9 @@ struct alt_instr {
 	s32 repl_offset;	/* offset to replacement instruction */
 	u16 cpuid;		/* cpuid bit set for replacement */
 	u8  instrlen;		/* length of original instruction */
-	u8  replacementlen;	/* length of new instruction, <= instrlen */
-};
+	u8  replacementlen;	/* length of new instruction */
+	u8  padlen;		/* length of build-time padding */
+} __packed;
 
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
@@ -75,23 +76,65 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
+#define b_replacement(num)	"664"#num
+#define e_replacement(num)	"665"#num
+
+#define alt_end_marker		"663"
+#define alt_slen		"662b-661b"
+#define alt_pad_len		alt_end_marker"b-662b"
+#define alt_total_slen		alt_end_marker"b-661b"
+#define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
+
+#define __OLDINSTR(oldinstr, num)					\
+	"661:\n\t" oldinstr "\n662:\n"					\
+	".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * "		\
+		"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"
+
+#define OLDINSTR(oldinstr, num)						\
+	__OLDINSTR(oldinstr, num)					\
+	alt_end_marker ":\n"
+
+/*
+ * Pad the second replacement alternative with additional NOPs if it is
+ * additionally longer than the first replacement alternative.
+ */
+#define OLDINSTR_2(oldinstr, num1, num2)					\
+	__OLDINSTR(oldinstr, num1)						\
+	".skip -(((" alt_rlen(num2) ")-(" alt_rlen(num1) ")-(662b-661b)) > 0) * " \
+		"((" alt_rlen(num2) ")-(" alt_rlen(num1) ")-(662b-661b)),0x90\n"  \
+	alt_end_marker ":\n"
+
+#define ALTINSTR_ENTRY(feature, num)					      \
+	" .long 661b - .\n"				/* label           */ \
+	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
+	" .word " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte " alt_total_slen "\n"			/* source len      */ \
+	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
+	" .byte " alt_pad_len "\n"			/* pad len */
+
+#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */     \
+	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
+
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
-									\
-      "661:\n\t" oldinstr "\n662:\n"					\
-      ".section .altinstructions,\"a\"\n"				\
-      "	 .long 661b - .\n"			/* label           */	\
-      "	 .long 663f - .\n"			/* new instruction */	\
-      "	 .word " __stringify(feature) "\n"	/* feature bit     */	\
-      "	 .byte 662b-661b\n"			/* sourcelen       */	\
-      "	 .byte 664f-663f\n"			/* replacementlen  */	\
-      ".previous\n"							\
-      ".section .discard,\"aw\",@progbits\n"				\
-      "	 .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */	\
-      ".previous\n"							\
-      ".section .altinstr_replacement, \"ax\"\n"			\
-      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
-      ".previous"
+	OLDINSTR(oldinstr, 1)						\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature, 1)					\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
+	".popsection"
+
+#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
+	OLDINSTR_2(oldinstr, 1, 2)					\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature1, 1)					\
+	ALTINSTR_ENTRY(feature2, 2)					\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
+	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
+	".popsection"
 
 /*
  * This must be included *after* the definition of ALTERNATIVE due to
@@ -114,6 +157,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alternative(oldinstr, newinstr, feature)			\
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
 
+#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
+	asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *

arch/x86/include/asm/cmdline.h

@@ -0,0 +1,8 @@
+#ifndef _ASM_X86_CMDLINE_H
+#define _ASM_X86_CMDLINE_H
+
+int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
+int cmdline_find_option(const char *cmdline_ptr, const char *option,
+			char *buffer, int bufsize);
+
+#endif /* _ASM_X86_CMDLINE_H */

arch/x86/include/asm/cpufeature.h

@@ -176,6 +176,10 @@
 #define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
 #define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
 #define X86_FEATURE_DTHERM	(7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_INVPCID_SINGLE (7*32+ 8) /* Effectively INVPCID && CR4.PCIDE=1 */
+
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER	( 7*32+31) /* "" CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
@@ -198,8 +202,11 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_HLE		(9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
 #define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -334,7 +341,7 @@ extern const char * const x86_power_flags[32];
  */
 static __always_inline __pure bool __static_cpu_has(u16 bit)
 {
-#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+#ifdef CC_HAVE_ASM_GOTO
 		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
@@ -343,6 +350,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			 " .word %P0\n"		/* feature bit */
 			 " .byte 2b - 1b\n"	/* source len */
 			 " .byte 0\n"		/* replacement len */
+			 " .byte 0\n"		/* pad len */
 			 ".previous\n"
 			 /* skipping size check since replacement size = 0 */
 			 : : "i" (bit) : : t_no);
@@ -360,6 +368,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			     " .word %P1\n"		/* feature bit */
 			     " .byte 2b - 1b\n"		/* source len */
 			     " .byte 4f - 3f\n"		/* replacement len */
+			     " .byte 0\n"		/* pad len */
 			     ".previous\n"
 			     ".section .discard,\"aw\",@progbits\n"
 			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */

arch/x86/include/asm/desc.h

@@ -40,7 +40,7 @@ struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
 
-DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {

arch/x86/include/asm/elf.h

@@ -192,6 +192,7 @@ void set_personality_ia32(void);
 
 #define ELF_CORE_COPY_REGS(pr_reg, regs)			\
 do {								\
+	unsigned long base;					\
 	unsigned v;						\
 	(pr_reg)[0] = (regs)->r15;				\
 	(pr_reg)[1] = (regs)->r14;				\
@@ -214,8 +215,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fs;			\
-	(pr_reg)[22] = current->thread.gs;			\
+	rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base;		\
+	rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base;	\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\
@@ -298,7 +299,7 @@ do {									\
 
 #define AT_SYSINFO		32
 
-#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(VDSO_CURRENT_BASE)
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 

arch/x86/include/asm/hardirq.h

@@ -18,8 +18,8 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	unsigned int irq_tlb_count;
 #endif
+	unsigned int irq_tlb_count;
 #ifdef CONFIG_X86_THERMAL_VECTOR
 	unsigned int irq_thermal_count;
 #endif

arch/x86/include/asm/hw_irq.h

@@ -164,7 +164,7 @@ extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
 extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
+DECLARE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq);
 extern void setup_vector_irq(int cpu);
 
 #ifdef CONFIG_X86_IO_APIC

arch/x86/include/asm/kaiser.h

@@ -0,0 +1,141 @@
+#ifndef _ASM_X86_KAISER_H
+#define _ASM_X86_KAISER_H
+
+#include <asm/processor-flags.h> /* For PCID constants */
+
+/*
+ * This file includes the definitions for the KAISER feature.
+ * KAISER is a counter measure against x86_64 side channel attacks on
+ * the kernel virtual memory.  It has a shadow pgd for every process: the
+ * shadow pgd has a minimalistic kernel-set mapped, but includes the whole
+ * user memory. Within a kernel context switch, or when an interrupt is handled,
+ * the pgd is switched to the normal one. When the system switches to user mode,
+ * the shadow pgd is enabled. By this, the virtual memory caches are freed,
+ * and the user may not attack the whole kernel memory.
+ *
+ * A minimalistic kernel mapping holds the parts needed to be mapped in user
+ * mode, such as the entry/exit functions of the user space, or the stacks.
+ */
+
+#define KAISER_SHADOW_PGD_OFFSET 0x1000
+
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+.macro _SWITCH_TO_KERNEL_CR3 reg
+movq %cr3, \reg
+andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
+/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID
+movq \reg, %cr3
+.endm
+
+.macro _SWITCH_TO_USER_CR3 reg regb
+/*
+ * regb must be the low byte portion of reg: because we have arranged
+ * for the low byte of the user PCID to serve as the high byte of NOFLUSH
+ * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are
+ * not enabled): so that the one register can update both memory and cr3.
+ */
+movq %cr3, \reg
+orq  PER_CPU_VAR(x86_cr3_pcid_user), \reg
+js   9f
+/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */
+movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
+9:
+movq \reg, %cr3
+.endm
+
+.macro SWITCH_KERNEL_CR3
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
+_SWITCH_TO_KERNEL_CR3 %rax
+popq %rax
+8:
+.endm
+
+.macro SWITCH_USER_CR3
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
+_SWITCH_TO_USER_CR3 %rax %al
+popq %rax
+8:
+.endm
+
+.macro SWITCH_KERNEL_CR3_NO_STACK
+ALTERNATIVE "jmp 8f", \
+	__stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \
+	X86_FEATURE_KAISER
+_SWITCH_TO_KERNEL_CR3 %rax
+movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
+8:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION */
+
+.macro SWITCH_KERNEL_CR3
+.endm
+.macro SWITCH_USER_CR3
+.endm
+.macro SWITCH_KERNEL_CR3_NO_STACK
+.endm
+
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Upon kernel/user mode switch, it may happen that the address
+ * space has to be switched before the registers have been
+ * stored.  To change the address space, another register is
+ * needed.  A register therefore has to be stored/restored.
+*/
+DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+
+DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
+
+extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+
+extern int kaiser_enabled;
+extern void __init kaiser_check_boottime_disable(void);
+#else
+#define kaiser_enabled	0
+static inline void __init kaiser_check_boottime_disable(void) {}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Kaiser function prototypes are needed even when CONFIG_PAGE_TABLE_ISOLATION is not set,
+ * so as to build with tests on kaiser_enabled instead of #ifdefs.
+ */
+
+/**
+ *  kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
+ *  @addr: the start address of the range
+ *  @size: the size of the range
+ *  @flags: The mapping flags of the pages
+ *
+ *  The mapping is done on a global scope, so no bigger
+ *  synchronization has to be done.  the pages have to be
+ *  manually unmapped again when they are not needed any longer.
+ */
+extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
+
+/**
+ *  kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping
+ *  @addr: the start address of the range
+ *  @size: the size of the range
+ */
+extern void kaiser_remove_mapping(unsigned long start, unsigned long size);
+
+/**
+ *  kaiser_init - Initialize the shadow mapping
+ *
+ *  Most parts of the shadow mapping can be mapped upon boot
+ *  time.  Only per-process things like the thread stacks
+ *  or a new LDT have to be mapped at runtime.  These boot-
+ *  time mappings are permanent and never unmapped.
+ */
+extern void kaiser_init(void);
+
+#endif /* __ASSEMBLY */
+
+#endif /* _ASM_X86_KAISER_H */

arch/x86/include/asm/kvm_para.h

@@ -195,13 +195,13 @@ static inline unsigned int kvm_arch_para_features(void)
 
 #ifdef CONFIG_KVM_GUEST
 void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
 #else
 #define kvm_guest_init() do { } while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 static inline u32 kvm_read_and_reset_pf_reason(void)
 {

arch/x86/include/asm/mmu.h

@@ -20,12 +20,6 @@ typedef struct {
 	void *vdso;
 } mm_context_t;
 
-#ifdef CONFIG_SMP
 void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
 
 #endif /* _ASM_X86_MMU_H */

arch/x86/include/asm/mmu_context.h

@@ -69,82 +69,16 @@ void destroy_context(struct mm_struct *mm);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
-#ifdef CONFIG_SMP
 	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
+extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+		      struct task_struct *tsk);
 
-	if (likely(prev != next)) {
-#ifdef CONFIG_SMP
-		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		percpu_write(cpu_tlbstate.active_mm, next);
-#endif
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-
-		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
-		 */
-		load_cr3(next->pgd);
-
-		/* stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
-
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-	}
-#ifdef CONFIG_SMP
-	else {
-		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			load_mm_ldt(next);
-		}
-	}
-#endif
-}
+extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			       struct task_struct *tsk);
+#define switch_mm_irqs_off switch_mm_irqs_off
 
 #define activate_mm(prev, next)			\
 do {						\

arch/x86/include/asm/pgtable.h

@@ -17,6 +17,11 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/x86_init.h>
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -570,7 +575,17 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	pgdval_t ignore_flags = _PAGE_USER;
+	/*
+	 * We set NX on KAISER pgds that map userspace memory so
+	 * that userspace can not meaningfully use the kernel
+	 * page table by accident; it will fault on the first
+	 * instruction it tries to run.  See native_set_pgd().
+	 */
+	if (kaiser_enabled)
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -770,7 +785,15 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (kaiser_enabled) {
+		/* Clone the shadow pgd part as well */
+		memcpy(native_get_shadow_pgd(dst),
+			native_get_shadow_pgd(src),
+			count * sizeof(pgd_t));
+	}
+#endif
 }
 
 

arch/x86/include/asm/pgtable_64.h

@@ -105,9 +105,31 @@ static inline void native_pud_clear(pud_t *pud)
 	native_set_pud(pud, native_make_pud(0));
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
+{
+#ifdef CONFIG_DEBUG_VM
+	/* linux/mmdebug.h may not have been included at this point */
+	BUG_ON(!kaiser_enabled);
+#endif
+	return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
+}
+#else
+static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
+{
+	return NULL;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pgd;
+	*pgdp = kaiser_set_shadow_pgd(pgdp, pgd);
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)

arch/x86/include/asm/pgtable_types.h

@@ -62,7 +62,7 @@
 #endif
 
 #define _PAGE_FILE	(_AT(pteval_t, 1) << _PAGE_BIT_FILE)
-#define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
+#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
 			 _PAGE_ACCESSED | _PAGE_DIRTY)
@@ -74,6 +74,33 @@
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
+/* The ASID is the lower 12 bits of CR3 */
+#define X86_CR3_PCID_ASID_MASK  (_AC((1<<12)-1,UL))
+
+/* Mask for all the PCID-related bits in CR3: */
+#define X86_CR3_PCID_MASK       (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK)
+#define X86_CR3_PCID_ASID_KERN  (_AC(0x0,UL))
+
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && defined(CONFIG_X86_64)
+/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */
+#define X86_CR3_PCID_ASID_USER	(_AC(0x80,UL))
+
+#define X86_CR3_PCID_KERN_FLUSH		(X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_FLUSH		(X86_CR3_PCID_ASID_USER)
+#define X86_CR3_PCID_KERN_NOFLUSH	(X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_NOFLUSH	(X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER)
+#else
+#define X86_CR3_PCID_ASID_USER  (_AC(0x0,UL))
+/*
+ * PCIDs are unsupported on 32-bit and none of these bits can be
+ * set in CR3:
+ */
+#define X86_CR3_PCID_KERN_FLUSH		(0)
+#define X86_CR3_PCID_USER_FLUSH		(0)
+#define X86_CR3_PCID_KERN_NOFLUSH	(0)
+#define X86_CR3_PCID_USER_NOFLUSH	(0)
+#endif
+
 #define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
 #define _PAGE_CACHE_WB		(0)
 #define _PAGE_CACHE_WC		(_PAGE_PWT)

arch/x86/include/asm/processor-flags.h

@@ -43,6 +43,8 @@
  */
 #define X86_CR3_PWT	0x00000008 /* Page Write Through */
 #define X86_CR3_PCD	0x00000010 /* Page Cache Disable */
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH (_AC(1,ULL) << X86_CR3_PCID_NOFLUSH_BIT)
 
 /*
  * Intel CPU features in CR4
@@ -60,6 +62,7 @@
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
 #define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */
+#define X86_CR4_PCIDE	0x00020000 /* enable PCID support */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 #define X86_CR4_SMEP	0x00100000 /* enable SMEP support */
 

arch/x86/include/asm/processor.h

@@ -266,7 +266,7 @@ struct tss_struct {
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, init_tss);
 
 /*
  * Save the original ist values for checking stack pointers during debugging

arch/x86/include/asm/tlbflush.h

@@ -6,6 +6,55 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/smp.h>
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
@@ -15,6 +64,24 @@
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
+/*
+ * Declare a couple of kaiser interfaces here for convenience,
+ * to avoid the need for asm/kaiser.h in unexpected places.
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern int kaiser_enabled;
+extern void kaiser_setup_pcid(void);
+extern void kaiser_flush_tlb_on_return_to_user(void);
+#else
+#define kaiser_enabled 0
+static inline void kaiser_setup_pcid(void)
+{
+}
+static inline void kaiser_flush_tlb_on_return_to_user(void)
+{
+}
+#endif
+
 static inline void __native_flush_tlb(void)
 {
 	/*
@@ -23,6 +90,8 @@ static inline void __native_flush_tlb(void)
 	 * back:
 	 */
 	preempt_disable();
+	if (kaiser_enabled)
+		kaiser_flush_tlb_on_return_to_user();
 	native_write_cr3(native_read_cr3());
 	preempt_enable();
 }
@@ -32,6 +101,17 @@ static inline void __native_flush_tlb_global(void)
 	unsigned long flags;
 	unsigned long cr4;
 
+	if (this_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+	 	 * Note, this works with CR4.PCIDE=0 or 1.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can
@@ -40,25 +120,61 @@ static inline void __native_flush_tlb_global(void)
 	raw_local_irq_save(flags);
 
 	cr4 = native_read_cr4();
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	if (cr4 & X86_CR4_PGE) {
+		/* clear PGE and flush TLB of all entries */
+		native_write_cr4(cr4 & ~X86_CR4_PGE);
+		/* restore PGE as it was before */
+		native_write_cr4(cr4);
+	} else {
+		/* do it with cr3, letting kaiser flush user PCID */
+		__native_flush_tlb();
+	}
 
 	raw_local_irq_restore(flags);
 }
 
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
-	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+	/*
+	 * SIMICS #GP's if you run INVPCID with type 2/3
+	 * and X86_CR4_PCIDE clear.  Shame!
+	 *
+	 * The ASIDs used below are hard-coded.  But, we must not
+	 * call invpcid(type=1/2) before CR4.PCIDE=1.  Just call
+	 * invlpg in the case we are called early.
+	 */
+
+	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
+		if (kaiser_enabled)
+			kaiser_flush_tlb_on_return_to_user();
+		asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+		return;
+	}
+	/* Flush the address out of both PCIDs. */
+	/*
+	 * An optimization here might be to determine addresses
+	 * that are only kernel-mapped and only flush the kernel
+	 * ASID.  But, userspace flushes are probably much more
+	 * important performance-wise.
+	 *
+	 * Make sure to do only a single invpcid when KAISER is
+	 * disabled and we have only a single ASID.
+	 */
+	if (kaiser_enabled)
+		invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+	invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
 }
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_pge)
-		__flush_tlb_global();
-	else
-		__flush_tlb();
+	__flush_tlb_global();
+	/*
+	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
+	 * we'd end up flushing kernel translations for the current ASID but
+	 * we might fail to flush kernel translations for other cached ASIDs.
+	 *
+	 * To avoid this issue, we force PCID off if PGE is off.
+	 */
 }
 
 static inline void __flush_tlb_one(unsigned long addr)
@@ -88,52 +204,8 @@ static inline void __flush_tlb_one(unsigned long addr)
  *
  * ..but the i386 has somewhat limited tlb flushing capabilities,
  * and page-granular flushes are available only on i486 and up.
- *
- * x86-64 can only flush individual pages or full VMs. For a range flush
- * we always do the full VM. Might be worth trying if for a small
- * range a few INVLPGs in a row are a win.
  */
 
-#ifndef CONFIG_SMP
-
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long addr)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
-					   struct mm_struct *mm,
-					   unsigned long va)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-#else  /* SMP */
-
-#include <asm/smp.h>
-
 #define local_flush_tlb() __flush_tlb()
 
 extern void flush_tlb_all(void);
@@ -167,8 +239,6 @@ static inline void reset_lazy_tlbstate(void)
 	percpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
 
-#endif	/* SMP */
-
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(mask, mm, va)
 #endif

arch/x86/include/asm/uaccess.h

@@ -32,9 +32,9 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
+#define __addr_ok(addr) 	\
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.
@@ -46,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 
@@ -76,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses: the first is the
@@ -347,7 +348,7 @@ do {									\
 #define __get_user_asm_u64(x, ptr, retval, errret) \
 	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
 #define __get_user_asm_ex_u64(x, ptr) \
-	 __get_user_asm_ex(x, ptr, "q", "", "=r")
+	 __get_user_asm_ex(x, ptr, "q", "", "=&r")
 #endif
 
 #define __get_user_size(x, ptr, size, retval, errret)			\
@@ -389,13 +390,13 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm_ex(x, ptr, "b", "b", "=q");		\
+		__get_user_asm_ex(x, ptr, "b", "b", "=&q");		\
 		break;							\
 	case 2:								\
-		__get_user_asm_ex(x, ptr, "w", "w", "=r");		\
+		__get_user_asm_ex(x, ptr, "w", "w", "=&r");		\
 		break;							\
 	case 4:								\
-		__get_user_asm_ex(x, ptr, "l", "k", "=r");		\
+		__get_user_asm_ex(x, ptr, "l", "k", "=&r");		\
 		break;							\
 	case 8:								\
 		__get_user_asm_ex_u64(x, ptr);				\
@@ -409,7 +410,7 @@ do {									\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
 		     _ASM_EXTABLE(1b, 2b - 1b)				\
-		     : ltype(x) : "m" (__m(addr)))
+		     : ltype(x) : "m" (__m(addr)), "0" (0))
 
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\

arch/x86/include/asm/vsyscall.h

@@ -22,6 +22,7 @@ enum vsyscall_num {
 /* kernel space (writeable) */
 extern int vgetcpu_mode;
 extern struct timezone sys_tz;
+extern unsigned long vsyscall_pgprot;
 
 #include <asm/vvar.h>
 

arch/x86/kernel/acpi/boot.c

@@ -951,6 +951,14 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
 	int pin;
 	struct mpc_intsrc mp_irq;
 
+	/*
+	 * Check bus_irq boundary.
+	 */
+	if (bus_irq >= NR_IRQS_LEGACY) {
+		pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq);
+		return;
+	}
+
 	/*
 	 * Convert 'gsi' to 'ioapic.pin'.
 	 */

arch/x86/kernel/alternative.c

@@ -63,8 +63,26 @@ static int __init setup_noreplace_paravirt(char *str)
 __setup("noreplace-paravirt", setup_noreplace_paravirt);
 #endif
 
-#define DPRINTK(fmt, args...) if (debug_alternative) \
-	printk(KERN_DEBUG fmt, args)
+#define DPRINTK(fmt, args...)						\
+do {									\
+	if (debug_alternative)						\
+		printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args);	\
+} while (0)
+
+#define DUMP_BYTES(buf, len, fmt, args...)				\
+do {									\
+	if (unlikely(debug_alternative)) {				\
+		int j;							\
+									\
+		if (!(len))						\
+			break;						\
+									\
+		printk(KERN_DEBUG fmt, ##args);				\
+		for (j = 0; j < (len) - 1; j++)				\
+			printk(KERN_CONT "%02hhx ", buf[j]);		\
+		printk(KERN_CONT "%02hhx\n", buf[j]);			\
+	}								\
+} while (0)
 
 /*
  * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
@@ -251,12 +269,86 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void *text_poke_early(void *addr, const void *opcode, size_t len);
 
-/* Replace instructions with better alternatives for this CPU type.
-   This runs before SMP is initialized to avoid SMP problems with
-   self modifying code. This implies that asymmetric systems where
-   APs have less capabilities than the boot processor are not handled.
-   Tough. Make sure you disable such features by hand. */
+/*
+ * Are we looking at a near JMP with a 1 or 4-byte displacement.
+ */
+static inline bool is_jmp(const u8 opcode)
+{
+	return opcode == 0xeb || opcode == 0xe9;
+}
 
+static void __init_or_module
+recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
+{
+	u8 *next_rip, *tgt_rip;
+	s32 n_dspl, o_dspl;
+	int repl_len;
+
+	if (a->replacementlen != 5)
+		return;
+
+	o_dspl = *(s32 *)(insnbuf + 1);
+
+	/* next_rip of the replacement JMP */
+	next_rip = repl_insn + a->replacementlen;
+	/* target rip of the replacement JMP */
+	tgt_rip  = next_rip + o_dspl;
+	n_dspl = tgt_rip - orig_insn;
+
+	DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+
+	if (tgt_rip - orig_insn >= 0) {
+		if (n_dspl - 2 <= 127)
+			goto two_byte_jmp;
+		else
+			goto five_byte_jmp;
+	/* negative offset */
+	} else {
+		if (((n_dspl - 2) & 0xff) == (n_dspl - 2))
+			goto two_byte_jmp;
+		else
+			goto five_byte_jmp;
+	}
+
+two_byte_jmp:
+	n_dspl -= 2;
+
+	insnbuf[0] = 0xeb;
+	insnbuf[1] = (s8)n_dspl;
+	add_nops(insnbuf + 2, 3);
+
+	repl_len = 2;
+	goto done;
+
+five_byte_jmp:
+	n_dspl -= 5;
+
+	insnbuf[0] = 0xe9;
+	*(s32 *)&insnbuf[1] = n_dspl;
+
+	repl_len = 5;
+
+done:
+
+	DPRINTK("final displ: 0x%08x, JMP 0x%lx",
+		n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
+}
+
+static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
+{
+	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+
+	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+		   instr, a->instrlen - a->padlen, a->padlen);
+}
+
+/*
+ * Replace instructions with better alternatives for this CPU type. This runs
+ * before SMP is initialized to avoid SMP problems with self modifying code.
+ * This implies that asymmetric systems where APs have less capabilities than
+ * the boot processor are not handled. Tough. Make sure you disable such
+ * features by hand.
+ */
 void __init_or_module apply_alternatives(struct alt_instr *start,
 					 struct alt_instr *end)
 {
@@ -264,10 +356,10 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	u8 *instr, *replacement;
 	u8 insnbuf[MAX_PATCH_LEN];
 
-	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+	DPRINTK("alt table %p -> %p", start, end);
 	/*
 	 * The scan order should be from start to end. A later scanned
-	 * alternative code can overwrite a previous scanned alternative code.
+	 * alternative code can overwrite previously scanned alternative code.
 	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
 	 * patch code.
 	 *
@@ -275,29 +367,54 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	 * order.
 	 */
 	for (a = start; a < end; a++) {
+		int insnbuf_sz = 0;
+
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		BUG_ON(a->replacementlen > a->instrlen);
 		BUG_ON(a->instrlen > sizeof(insnbuf));
 		BUG_ON(a->cpuid >= NCAPINTS*32);
-		if (!boot_cpu_has(a->cpuid))
+		if (!boot_cpu_has(a->cpuid)) {
+			if (a->padlen > 1)
+				optimize_nops(a, instr);
+
 			continue;
+		}
+
+		DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d)",
+			a->cpuid >> 5,
+			a->cpuid & 0x1f,
+			instr, a->instrlen,
+			replacement, a->replacementlen);
+
+		DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
+		DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
 
 		memcpy(insnbuf, replacement, a->replacementlen);
+		insnbuf_sz = a->replacementlen;
 
 		/* 0xe8 is a relative jump; fix the offset. */
-		if (*insnbuf == 0xe8 && a->replacementlen == 5)
-		    *(s32 *)(insnbuf + 1) += replacement - instr;
+		if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+			*(s32 *)(insnbuf + 1) += replacement - instr;
+			DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
+				*(s32 *)(insnbuf + 1),
+				(unsigned long)instr + *(s32 *)(insnbuf + 1) + 5);
+		}
 
-		add_nops(insnbuf + a->replacementlen,
-			 a->instrlen - a->replacementlen);
+		if (a->replacementlen && is_jmp(replacement[0]))
+			recompute_jump(a, instr, replacement, insnbuf);
 
-		text_poke_early(instr, insnbuf, a->instrlen);
+		if (a->instrlen > a->replacementlen) {
+			add_nops(insnbuf + a->replacementlen,
+				 a->instrlen - a->replacementlen);
+			insnbuf_sz += a->instrlen - a->replacementlen;
+		}
+		DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
+
+		text_poke_early(instr, insnbuf, insnbuf_sz);
 	}
 }
 
 #ifdef CONFIG_SMP
-
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
 {
@@ -383,8 +500,8 @@ void __init_or_module alternatives_smp_module_add(struct module *mod,
 	smp->locks_end	= locks_end;
 	smp->text	= text;
 	smp->text_end	= text_end;
-	DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
-		__func__, smp->locks, smp->locks_end,
+	DPRINTK("locks %p -> %p, text %p -> %p, name %s\n",
+		smp->locks, smp->locks_end,
 		smp->text, smp->text_end, smp->name);
 
 	mutex_lock(&smp_alt);
@@ -408,7 +525,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
 			continue;
 		list_del(&item->next);
 		mutex_unlock(&smp_alt);
-		DPRINTK("%s: %s\n", __func__, item->name);
+		DPRINTK("%s\n", item->name);
 		kfree(item);
 		return;
 	}
@@ -483,7 +600,7 @@ int alternatives_text_reserved(void *start, void *end)
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PARAVIRT
 void __init_or_module apply_paravirt(struct paravirt_patch_site *start,