Merge branch 'perf/core' of...

Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-6

Conflicts:
	include/trace/ftrace.h
	kernel/trace/trace_kprobe.c
Acked-by: NMasami Hiramatsu <mhiramat@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Documentation/DocBook/libata.tmpl

@@ -107,10 +107,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
 	issue of SET FEATURES - XFER MODE, and prior to operation.
 	</para>
 	<para>
-	Called by ata_device_add() after ata_dev_identify() determines
-	a device is present.
-	</para>
-	<para>
 	This entry may be specified as NULL in ata_port_operations.
 	</para>
 
@@ -154,8 +150,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in
 
 	<sect2><title>Taskfile read/write</title>
 	<programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
@@ -164,36 +160,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	hardware registers / DMA buffers, to obtain the current set of
 	taskfile register values.
 	Most drivers for taskfile-based hardware (PIO or MMIO) use
-	ata_tf_load() and ata_tf_read() for these hooks.
+	ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
 	</para>
 
 	</sect2>
 
 	<sect2><title>PIO data read/write</title>
 	<programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
 	</programlisting>
 
 	<para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
-ata_mmio_data_xfer().
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
 	</para>
 
 	</sect2>
 
 	<sect2><title>ATA command execute</title>
 	<programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
 	causes an ATA command, previously loaded with
 	->tf_load(), to be initiated in hardware.
-	Most drivers for taskfile-based hardware use ata_exec_command()
+	Most drivers for taskfile-based hardware use ata_sff_exec_command()
 	for this hook.
 	</para>
 
@@ -218,8 +213,8 @@ command.
 
 	<sect2><title>Read specific ATA shadow registers</title>
 	<programlisting>
-u8   (*check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
 	</programlisting>
 
 	<para>
@@ -227,20 +222,14 @@ u8   (*check_altstatus)(struct ata_port *ap);
 	hardware.  On some hardware, reading the Status register has
 	the side effect of clearing the interrupt condition.
 	Most drivers for taskfile-based hardware use
-	ata_check_status() for this hook.
-	</para>
-	<para>
-	Note that because this is called from ata_device_add(), at
-	least a dummy function that clears device interrupts must be
-	provided for all drivers, even if the controller doesn't
-	actually have a taskfile status register.
+	ata_sff_check_status() for this hook.
 	</para>
 
 	</sect2>
 
 	<sect2><title>Select ATA device on bus</title>
 	<programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
 	</programlisting>
 
 	<para>
@@ -251,9 +240,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
 	</para>
 	<para>
 	Most drivers for taskfile-based hardware use
-	ata_std_dev_select() for this hook.  Controllers which do not
-	support second drives on a port (such as SATA contollers) will
-	use ata_noop_dev_select().
+	ata_sff_dev_select() for this hook.
 	</para>
 
 	</sect2>
@@ -441,13 +428,13 @@ void (*irq_clear) (struct ata_port *);
 	to struct ata_host_set.
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_interrupt() for the
+	Most legacy IDE drivers use ata_sff_interrupt() for the
 	irq_handler hook, which scans all ports in the host_set,
 	determines which queued command was active (if any), and calls
-	ata_host_intr(ap,qc).
+	ata_sff_host_intr(ap,qc).
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+	Most legacy IDE drivers use ata_sff_irq_clear() for the
 	irq_clear() hook, which simply clears the interrupt and error
 	flags in the DMA status register.
 	</para>
@@ -496,10 +483,6 @@ void (*host_stop) (struct ata_host_set *host_set);
 	data from port at this time.
 	</para>
 	<para>
-	Many drivers use ata_port_stop() as this hook, which frees the
-	PRD table.
-	</para>
-	<para>
 	->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.

Documentation/i2c/writing-clients

@@ -74,6 +74,11 @@ structure at all.  You should use this to keep device-specific data.
 	/* retrieve the value */
 	void *i2c_get_clientdata(const struct i2c_client *client);
 
+Note that starting with kernel 2.6.34, you don't have to set the `data' field
+to NULL in remove() or if probe() failed anymore. The i2c-core does this
+automatically on these occasions. Those are also the only times the core will
+touch this field.
+
 
 Accessing the client
 ====================

Documentation/input/elantech.txt

@@ -333,14 +333,14 @@ byte 0:
 byte 1:
 
    bit   7   6   5   4   3   2   1   0
-        x15 x14 x13 x12 x11 x10 x9  x8
+         .   .   .   .   .  x10 x9  x8
 
 byte 2:
 
    bit   7   6   5   4   3   2   1   0
         x7  x6  x5  x4  x4  x2  x1  x0
 
-         x15..x0 = absolute x value (horizontal)
+         x10..x0 = absolute x value (horizontal)
 
 byte 3:
 
@@ -350,14 +350,14 @@ byte 3:
 byte 4:
 
    bit   7   6   5   4   3   2   1   0
-        y15 y14 y13 y12 y11 y10 y8  y8
+         .   .   .   .   .   .  y9  y8
 
 byte 5:
 
    bit   7   6   5   4   3   2   1   0
         y7  y6  y5  y4  y3  y2  y1  y0
 
-         y15..y0 = absolute y value (vertical)
+         y9..y0 = absolute y value (vertical)
 
 
 4.2.2 Two finger touch

Documentation/kprobes.txt

@@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped.
 
 1.4 How Does Jump Optimization Work?
 
-If you configured your kernel with CONFIG_OPTPROBES=y (currently
-this option is supported on x86/x86-64, non-preemptive kernel) and
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
 the "debug.kprobes_optimization" kernel parameter is set to 1 (see
 sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
 instruction instead of a breakpoint instruction at each probepoint.
@@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 - Specify an empty function for the kprobe's post_handler or break_handler.
  or
-- Config CONFIG_OPTPROBES=n.
- or
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
 2. Architectures Supported
@@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
-If you want to reduce probing overhead, set "Kprobes jump optimization
-support" (CONFIG_OPTPROBES) to "y". You can find this option under the
-"Kprobes" line.
-
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"

Documentation/spi/spidev_test.c

@@ -58,7 +58,7 @@ static void transfer(int fd)
 	};
 
 	ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-	if (ret == 1)
+	if (ret < 1)
 		pabort("can't send spi message");
 
 	for (ret = 0; ret < ARRAY_SIZE(tx); ret++) {

Documentation/trace/kprobetrace.txt

@@ -40,7 +40,9 @@ Synopsis of kprobe_events
   $stack	: Fetch stack address.
   $retval	: Fetch return value.(*)
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
-  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
+  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
+		  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.

MAINTAINERS

@@ -4353,13 +4353,13 @@ M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
 M:	Arnaldo Carvalho de Melo <acme@redhat.com>
 S:	Supported
-F:	kernel/perf_event.c
+F:	kernel/perf_event*.c
 F:	include/linux/perf_event.h
-F:	arch/*/kernel/perf_event.c
-F:	arch/*/kernel/*/perf_event.c
-F:	arch/*/kernel/*/*/perf_event.c
+F:	arch/*/kernel/perf_event*.c
+F:	arch/*/kernel/*/perf_event*.c
+F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
-F:	arch/*/lib/perf_event.c
+F:	arch/*/lib/perf_event*.c
 F:	arch/*/kernel/perf_callchain.c
 F:	tools/perf/
 

arch/Kconfig

@@ -42,15 +42,10 @@ config KPROBES
 	  If in doubt, say "N".
 
 config OPTPROBES
-	bool "Kprobes jump optimization support (EXPERIMENTAL)"
-	default y
-	depends on KPROBES
+	def_bool y
+	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	depends on HAVE_OPTPROBES
 	select KALLSYMS_ALL
-	help
-	  This option will allow kprobes to optimize breakpoint to
-	  a jump for reducing its overhead.
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
@@ -142,6 +137,17 @@ config HAVE_HW_BREAKPOINT
 	bool
 	depends on PERF_EVENTS
 
+config HAVE_MIXED_BREAKPOINTS_REGS
+	bool
+	depends on HAVE_HW_BREAKPOINT
+	help
+	  Depending on the arch implementation of hardware breakpoints,
+	  some of them have separate registers for data and instruction
+	  breakpoints addresses, others have mixed registers to store
+	  them but define the access type in a control register.
+	  Select this option if your arch implements breakpoints under the
+	  latter fashion.
+
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 

arch/arm/plat-omap/include/plat/usb.h

@@ -46,7 +46,7 @@ struct ehci_hcd_omap_platform_data {
 struct omap_musb_board_data {
 	u8	interface_type;
 	u8	mode;
-	u8	power;
+	u16	power;
 };
 
 enum musb_interface    {MUSB_INTERFACE_ULPI, MUSB_INTERFACE_UTMI};

arch/mips/Kconfig

@@ -49,7 +49,7 @@ config AR7
 	  family: TNETD7100, 7200 and 7300.
 
 config BCM47XX
-	bool "BCM47XX based boards"
+	bool "Broadcom BCM47XX based boards"
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
@@ -509,6 +509,7 @@ config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
 	select DMA_COHERENT
+	select HAVE_PATA_PLATFORM
 	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -523,6 +524,7 @@ config SIBYTE_LITTLESUR
 	depends on EXPERIMENTAL
 	select BOOT_ELF32
 	select DMA_COHERENT
+	select HAVE_PATA_PLATFORM
 	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -1305,6 +1307,33 @@ config CPU_CAVIUM_OCTEON
 
 endchoice
 
+if CPU_LOONGSON2F
+config CPU_NOP_WORKAROUNDS
+	bool
+
+config CPU_JUMP_WORKAROUNDS
+	bool
+
+config CPU_LOONGSON2F_WORKAROUNDS
+	bool "Loongson 2F Workarounds"
+	default y
+	select CPU_NOP_WORKAROUNDS
+	select CPU_JUMP_WORKAROUNDS
+	help
+	  Loongson 2F01 / 2F02 processors have the NOP & JUMP issues which
+	  require workarounds.  Without workarounds the system may hang
+	  unexpectedly.  For more information please refer to the gas
+	  -mfix-loongson2f-nop and -mfix-loongson2f-jump options.
+
+	  Loongson 2F03 and later have fixed these issues and no workarounds
+	  are needed.  The workarounds have no significant side effect on them
+	  but may decrease the performance of the system so this option should
+	  be disabled unless the kernel is intended to be run on 2F01 or 2F02
+	  systems.
+
+	  If unsure, please say Y.
+endif # CPU_LOONGSON2F
+
 config SYS_SUPPORTS_ZBOOT
 	bool
 	select HAVE_KERNEL_GZIP

arch/mips/Makefile

@@ -136,6 +136,19 @@ cflags-$(CONFIG_CPU_LOONGSON2E) += \
 	$(call cc-option,-march=loongson2e,-march=r4600)
 cflags-$(CONFIG_CPU_LOONGSON2F) += \
 	$(call cc-option,-march=loongson2f,-march=r4600)
+# enable the workarounds for loongson2f
+ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop)
+  else
+    cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop
+  endif
+  ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),)
+    $(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump)
+  else
+    cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump
+  endif
+endif
 
 cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
 			-Wa,-mips32 -Wa,--trap

arch/mips/alchemy/devboards/db1200/setup.c

@@ -66,12 +66,16 @@ static int __init db1200_arch_init(void)
 	set_irq_type(AU1200_GPIO7_INT, IRQF_TRIGGER_LOW);
 	bcsr_init_irq(DB1200_INT_BEGIN, DB1200_INT_END, AU1200_GPIO7_INT);
 
-	/* do not autoenable these: CPLD has broken edge int handling,
-	 * and the CD handler setup requires manual enabling to work
-	 * around that.
+	/* insert/eject pairs: one of both is always screaming.  To avoid
+	 * issues they must not be automatically enabled when initially
+	 * requested.
 	 */
 	irq_to_desc(DB1200_SD0_INSERT_INT)->status |= IRQ_NOAUTOEN;
 	irq_to_desc(DB1200_SD0_EJECT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC0_INSERT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC0_EJECT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC1_INSERT_INT)->status |= IRQ_NOAUTOEN;
+	irq_to_desc(DB1200_PC1_EJECT_INT)->status |= IRQ_NOAUTOEN;
 
 	return 0;
 }

arch/mips/include/asm/cmpxchg.h

@@ -16,7 +16,7 @@
 ({									\
 	__typeof(*(m)) __ret;						\
 									\
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\

arch/mips/include/asm/mach-loongson/loongson.h

@@ -307,7 +307,7 @@ extern unsigned long _loongson_addrwincfg_base;
  */
 #define LOONGSON_ADDRWIN_CFG(s, d, w, src, dst, size) do {\
 	s##_WIN##w##_BASE = (src); \
-	s##_WIN##w##_MMAP = (src) | ADDRWIN_MAP_DST_##d; \
+	s##_WIN##w##_MMAP = (dst) | ADDRWIN_MAP_DST_##d; \
 	s##_WIN##w##_MASK = ~(size-1); \
 } while (0)
 

arch/mips/include/asm/pgtable-64.h

@@ -120,9 +120,14 @@
 #endif
 #define FIRST_USER_ADDRESS	0UL
 
-#define VMALLOC_START		MAP_BASE
+/*
+ * TLB refill handlers also map the vmalloc area into xuseg.  Avoid
+ * the first couple of pages so NULL pointer dereferences will still
+ * reliably trap.
+ */
+#define VMALLOC_START		(MAP_BASE + (2 * PAGE_SIZE))
 #define VMALLOC_END	\
-	(VMALLOC_START + \
+	(MAP_BASE + \
 	 min(PTRS_PER_PGD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, \
 	     (1UL << cpu_vmbits)) - (1UL << 32))
 

arch/mips/include/asm/ptrace.h

@@ -142,9 +142,9 @@ extern int ptrace_set_watch_regs(struct task_struct *child,
 
 extern asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit);
 
-extern NORET_TYPE void die(const char *, const struct pt_regs *) ATTRIB_NORET;
+extern NORET_TYPE void die(const char *, struct pt_regs *) ATTRIB_NORET;
 
-static inline void die_if_kernel(const char *str, const struct pt_regs *regs)
+static inline void die_if_kernel(const char *str, struct pt_regs *regs)
 {
 	if (unlikely(!user_mode(regs)))
 		die(str, regs);

arch/mips/include/asm/stackframe.h

@@ -121,7 +121,7 @@
 		.endm
 #else
 		.macro	get_saved_sp	/* Uniprocessor variation */
-#ifdef CONFIG_CPU_LOONGSON2F
+#ifdef CONFIG_CPU_JUMP_WORKAROUNDS
 		/*
 		 * Clear BTB (branch target buffer), forbid RAS (return address
 		 * stack) to workaround the Out-of-order Issue in Loongson2F

arch/mips/include/asm/uasm.h

@@ -167,6 +167,24 @@ static inline void __cpuinit uasm_l##lb(struct uasm_label **lab, u32 *addr) \
 #define uasm_i_ssnop(buf) uasm_i_sll(buf, 0, 0, 1)
 #define uasm_i_ehb(buf) uasm_i_sll(buf, 0, 0, 3)
 
+static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1,
+				    unsigned int a2, unsigned int a3)
+{
+	if (a3 < 32)
+		uasm_i_dsrl(p, a1, a2, a3);
+	else
+		uasm_i_dsrl32(p, a1, a2, a3 - 32);
+}
+
+static inline void uasm_i_dsll_safe(u32 **p, unsigned int a1,
+				    unsigned int a2, unsigned int a3)
+{
+	if (a3 < 32)
+		uasm_i_dsll(p, a1, a2, a3);
+	else
+		uasm_i_dsll32(p, a1, a2, a3 - 32);
+}
+
 /* Handle relocations. */
 struct uasm_reloc {
 	u32 *addr;

arch/mips/jazz/setup.c

@@ -76,15 +76,9 @@ void __init plat_mem_setup(void)
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {
-		0, 0,		/* orig-x, orig-y */
-		0,		/* unused */
-		0,		/* orig_video_page */
-		0,		/* orig_video_mode */
-		160,		/* orig_video_cols */
-		0, 0, 0,	/* unused, ega_bx, unused */
-		64,		/* orig_video_lines */
-		0,		/* orig_video_isVGA */
-		16		/* orig_video_points */
+		.orig_video_cols	= 160,
+		.orig_video_lines	= 64,
+		.orig_video_points	= 16,
 	};
 #endif
 

arch/mips/kernel/traps.c

@@ -352,9 +352,10 @@ void show_registers(const struct pt_regs *regs)
 
 static DEFINE_SPINLOCK(die_lock);
 
-void __noreturn die(const char * str, const struct pt_regs * regs)
+void __noreturn die(const char * str, struct pt_regs * regs)
 {
 	static int die_counter;
+	int sig = SIGSEGV;
 #ifdef CONFIG_MIPS_MT_SMTC
 	unsigned long dvpret = dvpe();
 #endif /* CONFIG_MIPS_MT_SMTC */
@@ -365,6 +366,10 @@ void __noreturn die(const char * str, const struct pt_regs * regs)
 #ifdef CONFIG_MIPS_MT_SMTC
 	mips_mt_regdump(dvpret);
 #endif /* CONFIG_MIPS_MT_SMTC */
+
+	if (notify_die(DIE_OOPS, str, regs, 0, current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+		sig = 0;
+
 	printk("%s[#%d]:\n", str, ++die_counter);
 	show_registers(regs);
 	add_taint(TAINT_DIE);
@@ -379,7 +384,7 @@ void __noreturn die(const char * str, const struct pt_regs * regs)
 		panic("Fatal exception");
 	}
 
-	do_exit(SIGSEGV);
+	do_exit(sig);
 }
 
 extern struct exception_table_entry __start___dbe_table[];
@@ -1557,12 +1562,7 @@ static char panic_null_cerr[] __cpuinitdata =
 void __cpuinit set_uncached_handler(unsigned long offset, void *addr,
 	unsigned long size)
 {
-#ifdef CONFIG_32BIT
-	unsigned long uncached_ebase = KSEG1ADDR(ebase);
-#endif
-#ifdef CONFIG_64BIT
-	unsigned long uncached_ebase = TO_UNCAC(ebase);
-#endif
+	unsigned long uncached_ebase = CKSEG1ADDR(ebase);
 
 	if (!addr)
 		panic(panic_null_cerr);

arch/mips/loongson/common/machtype.c

@@ -24,7 +24,7 @@ static const char *system_types[] = {
 	[MACH_LEMOTE_FL2F]              "lemote-fuloong-2f-box",
 	[MACH_LEMOTE_ML2F7]             "lemote-mengloong-2f-7inches",
 	[MACH_LEMOTE_YL2F89]            "lemote-yeeloong-2f-8.9inches",
-	[MACH_DEXXON_GDIUM2F10]         "dexxon-gidum-2f-10inches",
+	[MACH_DEXXON_GDIUM2F10]         "dexxon-gdium-2f",
 	[MACH_LEMOTE_NAS]		"lemote-nas-2f",
 	[MACH_LEMOTE_LL2F]              "lemote-lynloong-2f",
 	[MACH_LOONGSON_END]             NULL,

arch/mips/loongson/common/mem.c

@@ -75,7 +75,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 	unsigned long end = offset + size;
 
 	if (__uncached_access(file, offset)) {
-		if (((uca_start && offset) >= uca_start) &&
+		if (uca_start && (offset >= uca_start) &&
 		    (end <= uca_end))
 			return __pgprot((pgprot_val(vma_prot) &
 					 ~_CACHE_MASK) |
@@ -96,7 +96,7 @@ static int __init find_vga_mem_init(void)
 		return 0;
 
 	for_each_pci_dev(dev) {
-		if ((dev->class >> 8) == PCI_CLASS_DISPLAY_VGA) {
+		if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
 			for (idx = 0; idx < PCI_NUM_RESOURCES; idx++) {
 				r = &dev->resource[idx];
 				if (!r->start && r->end)

arch/mips/loongson/common/reset.c

@@ -16,13 +16,31 @@
 
 #include <loongson.h>
 
+static inline void loongson_reboot(void)
+{
+#ifndef CONFIG_CPU_JUMP_WORKAROUNDS
+	((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) ();
+#else
+	void (*func)(void);
+
+	func = (void *)ioremap_nocache(LOONGSON_BOOT_BASE, 4);
+
+	__asm__ __volatile__(
+	"       .set    noat                                            \n"
+	"       jr      %[func]                                         \n"
+	"       .set    at                                              \n"
+	: /* No outputs */
+	: [func] "r" (func));
+#endif
+}
+
 static void loongson_restart(char *command)
 {
 	/* do preparation for reboot */
 	mach_prepare_reboot();
 
 	/* reboot via jumping to boot base address */
-	((void (*)(void))ioremap_nocache(LOONGSON_BOOT_BASE, 4)) ();
+	loongson_reboot();
 }
 
 static void loongson_poweroff(void)

arch/mips/loongson/common/setup.c

@@ -41,15 +41,12 @@ void __init plat_mem_setup(void)
 	conswitchp = &vga_con;
 
 	screen_info = (struct screen_info) {
-		0, 25,		/* orig-x, orig-y */
-		    0,		/* unused */
-		    0,		/* orig-video-page */
-		    0,		/* orig-video-mode */
-		    80,		/* orig-video-cols */
-		    0, 0, 0,	/* ega_ax, ega_bx, ega_cx */
-		    25,		/* orig-video-lines */
-		    VIDEO_TYPE_VGAC,	/* orig-video-isVGA */
-		    16		/* orig-video-points */
+		.orig_x			= 0,
+		.orig_y			= 25,
+		.orig_video_cols	= 80,
+		.orig_video_lines	= 25,
+		.orig_video_isVGA	= VIDEO_TYPE_VGAC,
+		.orig_video_points	= 16,
 	};
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;

arch/mips/loongson/lemote-2f/irq.c

@@ -79,7 +79,7 @@ void mach_irq_dispatch(unsigned int pending)
 	if (pending & CAUSEF_IP7)
 		do_IRQ(LOONGSON_TIMER_IRQ);
 	else if (pending & CAUSEF_IP6) {	/* North Bridge, Perf counter */
-#ifdef CONFIG_OPROFILE
+#if defined(CONFIG_OPROFILE) || defined(CONFIG_OPROFILE_MODULE)
 		do_IRQ(LOONGSON2_PERFCNT_IRQ);
 #endif
 		bonito_irqdispatch();

arch/mips/mm/tlbex.c

@@ -31,6 +31,16 @@
 #include <asm/war.h>
 #include <asm/uasm.h>
 
+/*
+ * TLB load/store/modify handlers.
+ *
+ * Only the fastpath gets synthesized at runtime, the slowpath for
+ * do_page_fault remains normal asm.
+ */
+extern void tlb_do_page_fault_0(void);
+extern void tlb_do_page_fault_1(void);
+
+
 static inline int r45k_bvahwbug(void)
 {
 	/* XXX: We should probe for the presence of this bug, but we don't. */
@@ -83,6 +93,7 @@ enum label_id {
 	label_nopage_tlbm,
 	label_smp_pgtable_change,
 	label_r3000_write_probe_fail,
+	label_large_segbits_fault,
 #ifdef CONFIG_HUGETLB_PAGE
 	label_tlb_huge_update,
 #endif
@@ -101,6 +112,7 @@ UASM_L_LA(_nopage_tlbs)
 UASM_L_LA(_nopage_tlbm)
 UASM_L_LA(_smp_pgtable_change)
 UASM_L_LA(_r3000_write_probe_fail)
+UASM_L_LA(_large_segbits_fault)
 #ifdef CONFIG_HUGETLB_PAGE
 UASM_L_LA(_tlb_huge_update)
 #endif
@@ -157,6 +169,10 @@ static u32 tlb_handler[128] __cpuinitdata;
 static struct uasm_label labels[128] __cpuinitdata;
 static struct uasm_reloc relocs[128] __cpuinitdata;
 
+#ifdef CONFIG_64BIT
+static int check_for_high_segbits __cpuinitdata;
+#endif
+
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 /*
  * CONFIG_MIPS_PGD_C0_CONTEXT implies 64 bit and lack of pgd_current,
@@ -408,7 +424,7 @@ static __cpuinit __maybe_unused void build_convert_pte_to_entrylo(u32 **p,
 		UASM_i_ROTR(p, reg, reg, ilog2(_PAGE_GLOBAL) - ilog2(_PAGE_NO_EXEC));
 	} else {
 #ifdef CONFIG_64BIT_PHYS_ADDR
-		uasm_i_dsrl(p, reg, reg, ilog2(_PAGE_GLOBAL));
+		uasm_i_dsrl_safe(p, reg, reg, ilog2(_PAGE_GLOBAL));
 #else
 		UASM_i_SRL(p, reg, reg, ilog2(_PAGE_GLOBAL));
 #endif
@@ -532,7 +548,24 @@ build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 	 * The vmalloc handling is not in the hotpath.
 	 */
 	uasm_i_dmfc0(p, tmp, C0_BADVADDR);
-	uasm_il_bltz(p, r, tmp, label_vmalloc);
+
+	if (check_for_high_segbits) {
+		/*
+		 * The kernel currently implicitely assumes that the
+		 * MIPS SEGBITS parameter for the processor is
+		 * (PGDIR_SHIFT+PGDIR_BITS) or less, and will never
+		 * allocate virtual addresses outside the maximum
+		 * range for SEGBITS = (PGDIR_SHIFT+PGDIR_BITS). But
+		 * that doesn't prevent user code from accessing the
+		 * higher xuseg addresses.  Here, we make sure that
+		 * everything but the lower xuseg addresses goes down
+		 * the module_alloc/vmalloc path.
+		 */
+		uasm_i_dsrl_safe(p, ptr, tmp, PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3);
+		uasm_il_bnez(p, r, ptr, label_vmalloc);
+	} else {
+		uasm_il_bltz(p, r, tmp, label_vmalloc);
+	}
 	/* No uasm_i_nop needed here, since the next insn doesn't touch TMP. */
 
 #ifdef CONFIG_MIPS_PGD_C0_CONTEXT
@@ -549,14 +582,14 @@ build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 	 * SMTC uses TCBind value as "CPU" index
 	 */
 	uasm_i_mfc0(p, ptr, C0_TCBIND);
-	uasm_i_dsrl(p, ptr, ptr, 19);
+	uasm_i_dsrl_safe(p, ptr, ptr, 19);
 # else
 	/*
 	 * 64 bit SMP running in XKPHYS has smp_processor_id() << 3
 	 * stored in CONTEXT.
 	 */
 	uasm_i_dmfc0(p, ptr, C0_CONTEXT);
-	uasm_i_dsrl(p, ptr, ptr, 23);
+	uasm_i_dsrl_safe(p, ptr, ptr, 23);
 # endif
 	UASM_i_LA_mostly(p, tmp, pgdc);
 	uasm_i_daddu(p, ptr, ptr, tmp);
@@ -569,44 +602,78 @@ build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 
 	uasm_l_vmalloc_done(l, *p);
 
-	if (PGDIR_SHIFT - 3 < 32)		/* get pgd offset in bytes */
-		uasm_i_dsrl(p, tmp, tmp, PGDIR_SHIFT-3);
-	else
-		uasm_i_dsrl32(p, tmp, tmp, PGDIR_SHIFT - 3 - 32);
+	/* get pgd offset in bytes */
+	uasm_i_dsrl_safe(p, tmp, tmp, PGDIR_SHIFT - 3);
 
 	uasm_i_andi(p, tmp, tmp, (PTRS_PER_PGD - 1)<<3);
 	uasm_i_daddu(p, ptr, ptr, tmp); /* add in pgd offset */
 #ifndef __PAGETABLE_PMD_FOLDED
 	uasm_i_dmfc0(p, tmp, C0_BADVADDR); /* get faulting address */
 	uasm_i_ld(p, ptr, 0, ptr); /* get pmd pointer */
-	uasm_i_dsrl(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */
+	uasm_i_dsrl_safe(p, tmp, tmp, PMD_SHIFT-3); /* get pmd offset in bytes */
 	uasm_i_andi(p, tmp, tmp, (PTRS_PER_PMD - 1)<<3);
 	uasm_i_daddu(p, ptr, ptr, tmp); /* add in pmd offset */
 #endif
 }
 
+enum vmalloc64_mode {not_refill, refill};
 /*
  * BVADDR is the faulting address, PTR is scratch.
  * PTR will hold the pgd for vmalloc.
  */
 static void __cpuinit
 build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
-			unsigned int bvaddr, unsigned int ptr)
+			unsigned int bvaddr, unsigned int ptr,
+			enum vmalloc64_mode mode)
 {
 	long swpd = (long)swapper_pg_dir;
+	int single_insn_swpd;
+	int did_vmalloc_branch = 0;
+
+	single_insn_swpd = uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd);
 
 	uasm_l_vmalloc(l, *p);
 
-	if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) {
-		uasm_il_b(p, r, label_vmalloc_done);
-		uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
-	} else {
-		UASM_i_LA_mostly(p, ptr, swpd);
-		uasm_il_b(p, r, label_vmalloc_done);
-		if (uasm_in_compat_space_p(swpd))
-			uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(swpd));
-		else
-			uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(swpd));
+	if (mode == refill && check_for_high_segbits) {
+		if (single_insn_swpd) {
+			uasm_il_bltz(p, r, bvaddr, label_vmalloc_done);
+			uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
+			did_vmalloc_branch = 1;
+			/* fall through */
+		} else {
+			uasm_il_bgez(p, r, bvaddr, label_large_segbits_fault);
+		}
+	}
+	if (!did_vmalloc_branch) {
+		if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) {
+			uasm_il_b(p, r, label_vmalloc_done);
+			uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
+		} else {
+			UASM_i_LA_mostly(p, ptr, swpd);
+			uasm_il_b(p, r, label_vmalloc_done);
+			if (uasm_in_compat_space_p(swpd))
+				uasm_i_addiu(p, ptr, ptr, uasm_rel_lo(swpd));
+			else
+				uasm_i_daddiu(p, ptr, ptr, uasm_rel_lo(swpd));
+		}
+	}
+	if (mode == refill && check_for_high_segbits) {
+		uasm_l_large_segbits_fault(l, *p);
+		/*
+		 * We get here if we are an xsseg address, or if we are
+		 * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary.
+		 *
+		 * Ignoring xsseg (assume disabled so would generate
+		 * (address errors?), the only remaining possibility
+		 * is the upper xuseg addresses.  On processors with
+		 * TLB_SEGBITS <= PGDIR_SHIFT+PGDIR_BITS, these
+		 * addresses would have taken an address error. We try
+		 * to mimic that here by taking a load/istream page
+		 * fault.
+		 */
+		UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0);
+		uasm_i_jr(p, ptr);
+		uasm_i_nop(p);
 	}
 }
 
@@ -720,9 +787,9 @@ static void __cpuinit build_update_entries(u32 **p, unsigned int tmp,
 			UASM_i_MTC0(p, tmp, C0_ENTRYLO0); /* load it */
 			UASM_i_ROTR(p, ptep, ptep, ilog2(_PAGE_GLOBAL) - ilog2(_PAGE_NO_EXEC));
 		} else {
-			uasm_i_dsrl(p, tmp, tmp, ilog2(_PAGE_GLOBAL)); /* convert to entrylo0 */
+			uasm_i_dsrl_safe(p, tmp, tmp, ilog2(_PAGE_GLOBAL)); /* convert to entrylo0 */
 			UASM_i_MTC0(p, tmp, C0_ENTRYLO0); /* load it */
-			uasm_i_dsrl(p, ptep, ptep, ilog2(_PAGE_GLOBAL)); /* convert to entrylo1 */
+			uasm_i_dsrl_safe(p, ptep, ptep, ilog2(_PAGE_GLOBAL)); /* convert to entrylo1 */
 		}
 		UASM_i_MTC0(p, ptep, C0_ENTRYLO1); /* load it */
 	} else {
@@ -793,9 +860,9 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
 		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
-		uasm_i_dsrl(&p, K0, K0, 12 + 1);
-		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_dsrl_safe(&p, K1, K0, 62);
+		uasm_i_dsrl_safe(&p, K0, K0, 12 + 1);
+		uasm_i_dsll_safe(&p, K0, K0, 64 + 12 + 1 - segbits);
 		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
@@ -825,7 +892,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 #endif
 
 #ifdef CONFIG_64BIT
-	build_get_pgd_vmalloc64(&p, &l, &r, K0, K1);
+	build_get_pgd_vmalloc64(&p, &l, &r, K0, K1, refill);
 #endif
 
 	/*
@@ -934,15 +1001,6 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	dump_handler((u32 *)ebase, 64);
 }
 
-/*
- * TLB load/store/modify handlers.
- *
- * Only the fastpath gets synthesized at runtime, the slowpath for
- * do_page_fault remains normal asm.
- */
-extern void tlb_do_page_fault_0(void);
-extern void tlb_do_page_fault_1(void);
-
 /*
  * 128 instructions for the fastpath handler is generous and should
  * never be exceeded.
@@ -1302,7 +1360,7 @@ build_r4000_tlbchange_handler_tail(u32 **p, struct uasm_label **l,
 	uasm_i_eret(p); /* return from trap */
 
 #ifdef CONFIG_64BIT
-	build_get_pgd_vmalloc64(p, l, r, tmp, ptr);
+	build_get_pgd_vmalloc64(p, l, r, tmp, ptr, not_refill);
 #endif
 }
 
@@ -1322,9 +1380,9 @@ static void __cpuinit build_r4000_tlb_load_handler(void)
 		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
 		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
-		uasm_i_dsrl(&p, K0, K0, 12 + 1);
-		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_dsrl_safe(&p, K1, K0, 62);
+		uasm_i_dsrl_safe(&p, K0, K0, 12 + 1);
+		uasm_i_dsll_safe(&p, K0, K0, 64 + 12 + 1 - segbits);
 		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
@@ -1526,6 +1584,10 @@ void __cpuinit build_tlb_refill_handler(void)
 	 */
 	static int run_once = 0;
 
+#ifdef CONFIG_64BIT
+	check_for_high_segbits = current_cpu_data.vmbits > (PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3);
+#endif
+
 	switch (current_cpu_type()) {
 	case CPU_R2000:
 	case CPU_R3000:

arch/mips/nxp/pnx8550/common/reset.c

@@ -20,6 +20,8 @@
  * Reset the PNX8550 board.
  *
  */
+#include <linux/kernel.h>
+
 #include <asm/reboot.h>
 #include <glb.h>
 

arch/mips/pci/pci-sb1250.c

@@ -37,6 +37,7 @@
 #include <linux/mm.h>
 #include <linux/console.h>
 #include <linux/tty.h>
+#include <linux/vt.h>
 
 #include <asm/io.h>
 
@@ -254,7 +255,7 @@ static int __init sb1250_pcibios_init(void)
 	 * XXX ehs: Should this happen in PCI Device mode?
 	 */
 	io_map_base = ioremap(A_PHYS_LDTPCI_IO_MATCH_BYTES, 1024 * 1024);
-	sb1250_controller.io_map_base = io_map_base;
+	sb1250_controller.io_map_base = (unsigned long)io_map_base;
 	set_io_port_base((unsigned long)io_map_base);
 
 #ifdef CONFIG_SIBYTE_HAS_LDT

arch/mips/sgi-ip22/ip22-berr.c

@@ -89,7 +89,7 @@ static void print_buserr(void)
 void ip22_be_interrupt(int irq)
 {
 	const int field = 2 * sizeof(unsigned long);
-	const struct pt_regs *regs = get_irq_regs();
+	struct pt_regs *regs = get_irq_regs();
 
 	save_and_clear_buserr();
 	print_buserr();

arch/mips/sgi-ip22/ip28-berr.c

@@ -453,7 +453,7 @@ static int ip28_be_interrupt(const struct pt_regs *regs)
 
 void ip22_be_interrupt(int irq)
 {
-	const struct pt_regs *regs = get_irq_regs();
+	struct pt_regs *regs = get_irq_regs();
 
 	count_be_interrupt++;
 

arch/mips/sibyte/swarm/setup.c

@@ -145,15 +145,14 @@ void __init plat_mem_setup(void)
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {
-		0, 0,           /* orig-x, orig-y */
-		0,              /* unused */
-		52,             /* orig_video_page */
-		3,              /* orig_video_mode */
-		80,             /* orig_video_cols */
-		4626, 3, 9,     /* unused, ega_bx, unused */
-		25,             /* orig_video_lines */
-		0x22,           /* orig_video_isVGA */
-		16              /* orig_video_points */
+		.orig_video_page	= 52,
+		.orig_video_mode	= 3,
+		.orig_video_cols	= 80,
+		.flags			= 12,
+		.orig_video_ega_bx	= 3,
+		.orig_video_lines	= 25,
+		.orig_video_isVGA	= 0x22,
+		.orig_video_points	= 16,
        };
        /* XXXKW for CFE, get lines/cols from environment */
 #endif

arch/powerpc/kernel/perf_event.c

@@ -35,6 +35,9 @@ struct cpu_hw_events {
 	u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
 	unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
+
+	unsigned int group_flag;
+	int n_txn_start;
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
@@ -718,66 +721,6 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static void event_sched_in(struct perf_event *event)
-{
-	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = smp_processor_id();
-	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
-	if (is_software_event(event))
-		event->pmu->enable(event);
-}
-
-/*
- * Called to enable a whole group of events.
- * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
- * Assumes the caller has disabled interrupts and has
- * frozen the PMU with hw_perf_save_disable.
- */
-int hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx)
-{
-	struct cpu_hw_events *cpuhw;
-	long i, n, n0;
-	struct perf_event *sub;
-
-	if (!ppmu)
-		return 0;
-	cpuhw = &__get_cpu_var(cpu_hw_events);
-	n0 = cpuhw->n_events;
-	n = collect_events(group_leader, ppmu->n_counter - n0,
-			   &cpuhw->event[n0], &cpuhw->events[n0],
-			   &cpuhw->flags[n0]);
-	if (n < 0)
-		return -EAGAIN;
-	if (check_excludes(cpuhw->event, cpuhw->flags, n0, n))
-		return -EAGAIN;
-	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n + n0);
-	if (i < 0)
-		return -EAGAIN;
-	cpuhw->n_events = n0 + n;
-	cpuhw->n_added += n;
-
-	/*
-	 * OK, this group can go on; update event states etc.,
-	 * and enable any software events
-	 */
-	for (i = n0; i < n0 + n; ++i)
-		cpuhw->event[i]->hw.config = cpuhw->events[i];
-	cpuctx->active_oncpu += n;
-	n = 1;
-	event_sched_in(group_leader);
-	list_for_each_entry(sub, &group_leader->sibling_list, group_entry) {
-		if (sub->state != PERF_EVENT_STATE_OFF) {
-			event_sched_in(sub);
-			++n;
-		}
-	}
-	ctx->nr_active += n;
-
-	return 1;
-}
-
 /*
  * Add a event to the PMU.
  * If all events are not already frozen, then we disable and
@@ -805,12 +748,22 @@ static int power_pmu_enable(struct perf_event *event)
 	cpuhw->event[n0] = event;
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
+
+	/*
+	 * If group events scheduling transaction was started,
+	 * skip the schedulability test here, it will be peformed
+	 * at commit time(->commit_txn) as a whole
+	 */
+	if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED)
+		goto nocheck;
+
 	if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
 		goto out;
 	if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1))
 		goto out;
-
 	event->hw.config = cpuhw->events[n0];
+
+nocheck:
 	++cpuhw->n_events;
 	++cpuhw->n_added;
 
@@ -896,11 +849,65 @@ static void power_pmu_unthrottle(struct perf_event *event)
 	local_irq_restore(flags);
 }
 
+/*
+ * Start group events scheduling transaction
+ * Set the flag to make pmu::enable() not perform the
+ * schedulability test, it will be performed at commit time
+ */
+void power_pmu_start_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+	cpuhw->n_txn_start = cpuhw->n_events;
+}
+
+/*
+ * Stop group events scheduling transaction
+ * Clear the flag and pmu::enable() will perform the
+ * schedulability test.
+ */
+void power_pmu_cancel_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+}
+
+/*
+ * Commit group events scheduling transaction
+ * Perform the group schedulability test as a whole
+ * Return 0 if success
+ */
+int power_pmu_commit_txn(const struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw;
+	long i, n;
+
+	if (!ppmu)
+		return -EAGAIN;
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+	n = cpuhw->n_events;
+	if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
+		return -EAGAIN;
+	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n);
+	if (i < 0)
+		return -EAGAIN;
+
+	for (i = cpuhw->n_txn_start; i < n; ++i)
+		cpuhw->event[i]->hw.config = cpuhw->events[i];
+
+	return 0;
+}
+
 struct pmu power_pmu = {
 	.enable		= power_pmu_enable,
 	.disable	= power_pmu_disable,
 	.read		= power_pmu_read,
 	.unthrottle	= power_pmu_unthrottle,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
 };
 
 /*

arch/sh/Kconfig

@@ -44,6 +44,7 @@ config SUPERH32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_ARCH_KGDB
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS if HAVE_HW_BREAKPOINT
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 

arch/sh/include/asm/hw_breakpoint.h

@@ -46,10 +46,14 @@ struct pmu;
 /* Maximum number of UBC channels */
 #define HBP_NUM		2
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_va_in_userspace(unsigned long va, u16 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
-					 struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/sh/kernel/hw_breakpoint.c

@@ -119,26 +119,17 @@ static int get_hbp_len(u16 hbp_len)
 	return len_in_bytes;
 }
 
-/*
- * Check for virtual address in user space.
- */
-int arch_check_va_in_userspace(unsigned long va, u16 hbp_len)
-{
-	unsigned int len;
-
-	len = get_hbp_len(hbp_len);
-
-	return (va <= TASK_SIZE - len);
-}
-
 /*
  * Check for virtual address in kernel space.
  */
-static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -226,8 +217,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -270,15 +260,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 	if (info->address & align)
 		return -EINVAL;
 
-	/* Check that the virtual address is in the proper range */
-	if (tsk) {
-		if (!arch_check_va_in_userspace(info->address, info->len))
-			return -EFAULT;
-	} else {
-		if (!arch_check_va_in_kernelspace(info->address, info->len))
-			return -EFAULT;
-	}
-
 	return 0;
 }
 
@@ -363,8 +344,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (arch_check_va_in_userspace(bp->attr.bp_addr,
-					       bp->attr.bp_len)) {
+		if (!arch_check_bp_in_kernelspace(bp)) {
 			siginfo_t info;
 
 			info.si_signo = args->signr;

arch/sh/kernel/ptrace_32.c

@@ -85,7 +85,7 @@ static int set_single_step(struct task_struct *tsk, unsigned long addr)
 
 	bp = thread->ptrace_bps[0];
 	if (!bp) {
-		hw_breakpoint_init(&attr);
+		ptrace_breakpoint_init(&attr);
 
 		attr.bp_addr = addr;
 		attr.bp_len = HW_BREAKPOINT_LEN_2;

arch/x86/Kconfig

@@ -53,11 +53,15 @@ config X86
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
 
+config INSTRUCTION_DECODER
+	def_bool (KPROBES || PERF_EVENTS)
+
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32

arch/x86/Kconfig.cpu

@@ -502,23 +502,3 @@ config CPU_SUP_UMC_32
 	  CPU might render the kernel unbootable.
 
 	  If unsure, say N.
-
-config X86_DS
-	def_bool X86_PTRACE_BTS
-	depends on X86_DEBUGCTLMSR
-	select HAVE_HW_BRANCH_TRACER
-
-config X86_PTRACE_BTS
-	bool "Branch Trace Store"
-	default y
-	depends on X86_DEBUGCTLMSR
-	depends on BROKEN
-	---help---
-	  This adds a ptrace interface to the hardware's branch trace store.
-
-	  Debuggers may use it to collect an execution trace of the debugged
-	  application in order to answer the question 'how did I get here?'.
-	  Debuggers may trace user mode as well as kernel mode.
-
-	  Say Y unless there is no application development on this machine
-	  and you want to save a small amount of code size.

arch/x86/Kconfig.debug

@@ -174,15 +174,6 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config X86_DS_SELFTEST
-    bool "DS selftest"
-    default y
-    depends on DEBUG_KERNEL
-    depends on X86_DS
-	---help---
-	  Perform Debug Store selftests at boot time.
-	  If in doubt, say "N".
-
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 

arch/x86/include/asm/apic.h

@@ -373,6 +373,7 @@ extern atomic_t init_deasserted;
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static inline u32 apic_read(u32 reg)
 {
 	return apic->read(reg);
@@ -403,10 +404,19 @@ static inline u32 safe_apic_wait_icr_idle(void)
 	return apic->safe_wait_icr_idle();
 }
 
+#else /* CONFIG_X86_LOCAL_APIC */
+
+static inline u32 apic_read(u32 reg) { return 0; }
+static inline void apic_write(u32 reg, u32 val) { }
+static inline u64 apic_icr_read(void) { return 0; }
+static inline void apic_icr_write(u32 low, u32 high) { }
+static inline void apic_wait_icr_idle(void) { }
+static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 static inline void ack_APIC_irq(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
@@ -414,7 +424,6 @@ static inline void ack_APIC_irq(void)
 
 	/* Docs say use 0 for future compatibility */
 	apic_write(APIC_EOI, 0);
-#endif
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)

arch/x86/include/asm/ds.h

-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
-
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/err.h>
-
-
-#ifdef CONFIG_X86_DS
-
-struct task_struct;
-struct ds_context;
-struct ds_tracer;
-struct bts_tracer;
-struct pebs_tracer;
-
-typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
-typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
-
-
-/*
- * A list of features plus corresponding macros to talk about them in
- * the ds_request function's flags parameter.
- *
- * We use the enum to index an array of corresponding control bits;
- * we use the macro to index a flags bit-vector.
- */
-enum ds_feature {
-	dsf_bts = 0,
-	dsf_bts_kernel,
-#define BTS_KERNEL (1 << dsf_bts_kernel)
-	/* trace kernel-mode branches */
-
-	dsf_bts_user,
-#define BTS_USER (1 << dsf_bts_user)
-	/* trace user-mode branches */
-
-	dsf_bts_overflow,
-	dsf_bts_max,
-	dsf_pebs = dsf_bts_max,
-
-	dsf_pebs_max,
-	dsf_ctl_max = dsf_pebs_max,
-	dsf_bts_timestamps = dsf_ctl_max,
-#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
-	/* add timestamps into BTS trace */
-
-#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
-};
-
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns a pointer to a tracer structure on success, or
- * ERR_PTR(errcode) on failure.
- *
- * The interrupt threshold is independent from the overflow callback
- * to allow users to use their own overflow interrupt handling mechanism.
- *
- * The function might sleep.
- *
- * task: the task to request recording for
- * cpu:  the cpu to request recording for
- * base: the base pointer for the (non-pageable) buffer;
- * size: the size of the provided buffer in bytes
- * ovfl: pointer to a function to be called on buffer overflow;
- *       NULL if cyclic buffer requested
- * th: the interrupt threshold in records from the end of the buffer;
- *     -1 if no interrupt threshold is requested.
- * flags: a bit-mask of the above flags
- */
-extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
-					      void *base, size_t size,
-					      bts_ovfl_callback_t ovfl,
-					      size_t th, unsigned int flags);
-extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
-					     bts_ovfl_callback_t ovfl,
-					     size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
-						void *base, size_t size,
-						pebs_ovfl_callback_t ovfl,
-						size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
-					       void *base, size_t size,
-					       pebs_ovfl_callback_t ovfl,
-					       size_t th, unsigned int flags);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Must be called with irq's enabled.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern void ds_release_bts(struct bts_tracer *tracer);
-extern void ds_suspend_bts(struct bts_tracer *tracer);
-extern void ds_resume_bts(struct bts_tracer *tracer);
-extern void ds_release_pebs(struct pebs_tracer *tracer);
-extern void ds_suspend_pebs(struct pebs_tracer *tracer);
-extern void ds_resume_pebs(struct pebs_tracer *tracer);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Cpu tracers must call this on the traced cpu.
- * Task tracers must call ds_release_~_noirq() for themselves.
- *
- * May be called with irq's disabled.
- *
- * Returns 0 if successful;
- * -EPERM if the cpu tracer does not trace the current cpu.
- * -EPERM if the task tracer does not trace itself.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_release_bts_noirq(struct bts_tracer *tracer);
-extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
-extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
-extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
-
-
-/*
- * The raw DS buffer state as it is used for BTS and PEBS recording.
- *
- * This is the low-level, arch-dependent interface for working
- * directly on the raw trace data.
- */
-struct ds_trace {
-	/* the number of bts/pebs records */
-	size_t n;
-	/* the size of a bts/pebs record in bytes */
-	size_t size;
-	/* pointers into the raw buffer:
-	   - to the first entry */
-	void *begin;
-	/* - one beyond the last entry */
-	void *end;
-	/* - one beyond the newest entry */
-	void *top;
-	/* - the interrupt threshold */
-	void *ith;
-	/* flags given on ds_request() */
-	unsigned int flags;
-};
-
-/*
- * An arch-independent view on branch trace data.
- */
-enum bts_qualifier {
-	bts_invalid,
-#define BTS_INVALID bts_invalid
-
-	bts_branch,
-#define BTS_BRANCH bts_branch
-
-	bts_task_arrives,
-#define BTS_TASK_ARRIVES bts_task_arrives
-
-	bts_task_departs,
-#define BTS_TASK_DEPARTS bts_task_departs
-
-	bts_qual_bit_size = 4,
-	bts_qual_max = (1 << bts_qual_bit_size),
-};
-
-struct bts_struct {
-	__u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			__u64 from;
-			__u64 to;
-		} lbr;
-		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
-		struct {
-			__u64 clock;
-			pid_t pid;
-		} event;
-	} variant;
-};
-
-
-/*
- * The BTS state.
- *
- * This gives access to the raw DS state and adds functions to provide
- * an arch-independent view of the BTS data.
- */
-struct bts_trace {
-	struct ds_trace ds;
-
-	int (*read)(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out);
-	int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
-};
-
-
-/*
- * The PEBS state.
- *
- * This gives access to the raw DS state and the PEBS-specific counter
- * reset value.
- */
-struct pebs_trace {
-	struct ds_trace ds;
-
-	/* the number of valid counters in the below array */
-	unsigned int counters;
-
-#define MAX_PEBS_COUNTERS 4
-	/* the counter reset value */
-	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
-};
-
-
-/*
- * Read the BTS or PEBS trace.
- *
- * Returns a view on the trace collected for the parameter tracer.
- *
- * The view remains valid as long as the traced task is not running or
- * the tracer is suspended.
- * Writes into the trace buffer are not reflected.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
-extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
-
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_reset_bts(struct bts_tracer *tracer);
-extern int ds_reset_pebs(struct pebs_tracer *tracer);
-
-/*
- * Set the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_pebs()
- * counter: the index of the counter
- * value: the new counter reset value
- */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
-			     unsigned int counter, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-/*
- * Context switch work
- */
-extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-
-#else /* CONFIG_X86_DS */
-
-struct cpuinfo_x86;
-static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
-static inline void ds_switch_to(struct task_struct *prev,
-				struct task_struct *next) {}
-
-#endif /* CONFIG_X86_DS */
-#endif /* _ASM_X86_DS_H */

arch/x86/include/asm/hw_breakpoint.h

@@ -41,12 +41,16 @@ struct arch_hw_breakpoint {
 /* Total number of available HW breakpoint registers */
 #define HBP_NUM 4
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 struct perf_event;
 struct pmu;
 
-extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
-					 struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/x86/include/asm/insn.h

@@ -68,6 +68,8 @@ struct insn {
 	const insn_byte_t *next_byte;
 };
 
+#define MAX_INSN_SIZE	16
+
 #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
 #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
 #define X86_MODRM_RM(modrm) ((modrm) & 0x07)

arch/x86/include/asm/io.h

@@ -347,6 +347,7 @@ extern void __iomem *early_ioremap(resource_size_t phys_addr,
 extern void __iomem *early_memremap(resource_size_t phys_addr,
 				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
 
 #define IO_SPACE_LIMIT 0xffff
 

arch/x86/include/asm/kprobes.h

@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -36,7 +37,6 @@ typedef u8 kprobe_opcode_t;
 #define RELATIVEJUMP_SIZE 5
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
-#define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
 	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \

arch/x86/include/asm/msr-index.h

@@ -71,11 +71,14 @@
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
-#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
-
-#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
-#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
 #define MSR_IA32_MC0_CTL		0x00000400
 #define MSR_IA32_MC0_STATUS		0x00000401
@@ -359,6 +362,8 @@
 #define MSR_P4_U2L_ESCR0		0x000003b0
 #define MSR_P4_U2L_ESCR1		0x000003b1
 
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
 /* Intel Core-based CPU performance counters */
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a

arch/x86/include/asm/perf_event.h

@@ -5,7 +5,7 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_GENERIC				       32
 #define X86_PMC_MAX_FIXED					3
 
 #define X86_PMC_IDX_GENERIC				        0
@@ -18,39 +18,31 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL_ENABLE			  (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
-#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
-
-/*
- * Includes eventsel and unit mask as well:
- */
-
-
-#define INTEL_ARCH_EVTSEL_MASK		0x000000FFULL
-#define INTEL_ARCH_UNIT_MASK		0x0000FF00ULL
-#define INTEL_ARCH_EDGE_MASK		0x00040000ULL
-#define INTEL_ARCH_INV_MASK		0x00800000ULL
-#define INTEL_ARCH_CNT_MASK		0xFF000000ULL
-#define INTEL_ARCH_EVENT_MASK	(INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
-
-/*
- * filter mask to validate fixed counter events.
- * the following filters disqualify for fixed counters:
- *  - inv
- *  - edge
- *  - cnt-mask
- *  The other filters are supported by fixed counters.
- *  The any-thread option is supported starting with v3.
- */
-#define INTEL_ARCH_FIXED_MASK \
-	(INTEL_ARCH_CNT_MASK| \
-	 INTEL_ARCH_INV_MASK| \
-	 INTEL_ARCH_EDGE_MASK|\
-	 INTEL_ARCH_UNIT_MASK|\
-	 INTEL_ARCH_EVENT_MASK)
+#define ARCH_PERFMON_EVENTSEL_EVENT			0x000000FFULL
+#define ARCH_PERFMON_EVENTSEL_UMASK			0x0000FF00ULL
+#define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
+#define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
+#define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
+#define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
+#define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
+#define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
+
+#define AMD64_EVENTSEL_EVENT	\
+	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
+#define INTEL_ARCH_EVENT_MASK	\
+	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+
+#define X86_RAW_EVENT_MASK		\
+	(ARCH_PERFMON_EVENTSEL_EVENT |	\
+	 ARCH_PERFMON_EVENTSEL_UMASK |	\
+	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
+	 ARCH_PERFMON_EVENTSEL_INV   |	\
+	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define AMD64_RAW_EVENT_MASK		\
+	(X86_RAW_EVENT_MASK          |  \
+	 AMD64_EVENTSEL_EVENT)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -67,7 +59,7 @@
 union cpuid10_eax {
 	struct {
 		unsigned int version_id:8;
-		unsigned int num_events:8;
+		unsigned int num_counters:8;
 		unsigned int bit_width:8;
 		unsigned int mask_length:8;
 	} split;
@@ -76,7 +68,7 @@ union cpuid10_eax {
 
 union cpuid10_edx {
 	struct {
-		unsigned int num_events_fixed:4;
+		unsigned int num_counters_fixed:4;
 		unsigned int reserved:28;
 	} split;
 	unsigned int full;
@@ -136,6 +128,18 @@ extern void perf_events_lapic_init(void);
 
 #define PERF_EVENT_INDEX_OFFSET			0
 
+/*
+ * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
+ * This flag is otherwise unused and ABI specified to be 0, so nobody should
+ * care what we do with it.
+ */
+#define PERF_EFLAGS_EXACT	(1UL << 3)
+
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }

arch/x86/include/asm/processor.h

@@ -21,7 +21,6 @@ struct mm_struct;
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
-#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +28,7 @@ struct mm_struct;
 #include <linux/threads.h>
 #include <linux/math64.h>
 #include <linux/init.h>
+#include <linux/err.h>
 
 #define HBP_NUM 4
 /*
@@ -473,10 +473,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
-	unsigned long	debugctlmsr;
-	/* Debug Store context; see asm/ds.h */
-	struct ds_context	*ds_ctx;
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -803,7 +799,7 @@ extern void cpu_init(void);
 
 static inline unsigned long get_debugctlmsr(void)
 {
-    unsigned long debugctlmsr = 0;
+	unsigned long debugctlmsr = 0;
 
 #ifndef CONFIG_X86_DEBUGCTLMSR
 	if (boot_cpu_data.x86 < 6)
@@ -811,21 +807,6 @@ static inline unsigned long get_debugctlmsr(void)
 #endif
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
-    return debugctlmsr;
-}
-
-static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
-{
-	u64 debugctlmsr = 0;
-	u32 val1, val2;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return 0;
-#endif
-	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
-	debugctlmsr = val1 | ((u64)val2 << 32);
-
 	return debugctlmsr;
 }
 
@@ -838,18 +819,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
-static inline void update_debugctlmsr_on_cpu(int cpu,
-					     unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
-		     (u32)((u64)debugctlmsr),
-		     (u32)((u64)debugctlmsr >> 32));
-}
-
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:

arch/x86/include/asm/ptrace-abi.h

@@ -82,61 +82,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-
-/* configuration/status structure used in PTRACE_BTS_CONFIG and
-   PTRACE_BTS_STATUS commands.
-*/
-struct ptrace_bts_config {
-	/* requested or actual size of BTS buffer in bytes */
-	__u32 size;
-	/* bitmask of below flags */
-	__u32 flags;
-	/* buffer overflow signal */
-	__u32 signal;
-	/* actual size of bts_struct in bytes */
-	__u32 bts_size;
-};
-#endif /* __ASSEMBLY__ */
-
-#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
-#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
-#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
-				       instead of wrapping around */
-#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
-
-#define PTRACE_BTS_CONFIG	40
-/* Configure branch trace recording.
-   ADDR points to a struct ptrace_bts_config.
-   DATA gives the size of that buffer.
-   A new buffer is allocated, if requested in the flags.
-   An overflow signal may only be requested for new buffers.
-   Returns the number of bytes read.
-*/
-#define PTRACE_BTS_STATUS	41
-/* Return the current configuration in a struct ptrace_bts_config
-   pointed to by ADDR; DATA gives the size of that buffer.
-   Returns the number of bytes written.
-*/
-#define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records for draining.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_GET		43
-/* Get a single BTS record.
-   DATA defines the index into the BTS array, where 0 is the newest
-   entry, and higher indices refer to older entries.
-   ADDR is pointing to struct bts_struct (see asm/ds.h).
-*/
-#define PTRACE_BTS_CLEAR	44
-/* Clear the BTS buffer.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_DRAIN	45
-/* Read all available BTS records and clear the buffer.
-   ADDR points to an array of struct bts_struct.
-   DATA gives the size of that buffer.
-   BTS records are read from oldest to newest.
-   Returns number of BTS records drained.
-*/
+#endif
 
 #endif /* _ASM_X86_PTRACE_ABI_H */

arch/x86/include/asm/ptrace.h

@@ -289,12 +289,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void ptrace_bts_untrace(struct task_struct *tsk);
-
-#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */

arch/x86/include/asm/thread_info.h

@@ -92,8 +92,7 @@ struct thread_info {
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
 #define TIF_FREEZE		23	/* is freezing for suspend */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 
@@ -115,8 +114,7 @@ struct thread_info {
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 
@@ -147,7 +145,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
+	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)

arch/x86/kernel/Makefile

@@ -47,8 +47,6 @@ obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
-obj-$(CONFIG_X86_DS)		+= ds.o
-obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o

arch/x86/kernel/apic/io_apic.c

@@ -2545,6 +2545,9 @@ void irq_force_complete_move(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg = desc->chip_data;
 
+	if (!cfg)
+		return;
+
 	__irq_complete_move(&desc, cfg->vector);
 }
 #else

arch/x86/kernel/cpu/cpufreq/powernow-k8.c

@@ -929,7 +929,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else

arch/x86/kernel/cpu/intel.c

@@ -12,7 +12,6 @@
 #include <asm/processor.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
-#include <asm/ds.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
 
@@ -388,7 +387,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
 			set_cpu_cap(c, X86_FEATURE_PEBS);
-		ds_init_intel(c);
 	}
 
 	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)

arch/x86/kernel/cpu/perf_event_amd.c

@@ -2,7 +2,7 @@
 
 static DEFINE_RAW_SPINLOCK(amd_nb_lock);
 
-static __initconst u64 amd_hw_cache_event_ids
+static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -111,22 +111,19 @@ static u64 amd_pmu_event_map(int hw_event)
 	return amd_perfmon_event_map[hw_event];
 }
 
-static u64 amd_pmu_raw_event(u64 hw_event)
+static int amd_pmu_hw_config(struct perf_event *event)
 {
-#define K7_EVNTSEL_EVENT_MASK	0xF000000FFULL
-#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
-#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
-#define K7_EVNTSEL_INV_MASK	0x000800000ULL
-#define K7_EVNTSEL_REG_MASK	0x0FF000000ULL
-
-#define K7_EVNTSEL_MASK			\
-	(K7_EVNTSEL_EVENT_MASK |	\
-	 K7_EVNTSEL_UNIT_MASK  |	\
-	 K7_EVNTSEL_EDGE_MASK  |	\
-	 K7_EVNTSEL_INV_MASK   |	\
-	 K7_EVNTSEL_REG_MASK)
-
-	return hw_event & K7_EVNTSEL_MASK;
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return 0;
+
+	event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+
+	return 0;
 }
 
 /*
@@ -165,7 +162,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (nb->owners[i] == event) {
 			cmpxchg(nb->owners+i, event, NULL);
 			break;
@@ -215,7 +212,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
 	struct perf_event *old = NULL;
-	int max = x86_pmu.num_events;
+	int max = x86_pmu.num_counters;
 	int i, j, k = -1;
 
 	/*
@@ -293,7 +290,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_events; i++) {
+	for (i = 0; i < x86_pmu.num_counters; i++) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -371,21 +368,22 @@ static void amd_pmu_cpu_dead(int cpu)
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static __initconst struct x86_pmu amd_pmu = {
+static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
+	.hw_config		= amd_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
 	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
+	.num_counters		= 4,
+	.cntval_bits		= 48,
+	.cntval_mask		= (1ULL << 48) - 1,
 	.apic			= 1,
 	/* use highest bit to detect overflow */
 	.max_period		= (1ULL << 47) - 1,

arch/x86/kernel/cpu/perf_event_p6.c

@@ -27,24 +27,6 @@ static u64 p6_pmu_event_map(int hw_event)
  */
 #define P6_NOP_EVENT			0x0000002EULL
 
-static u64 p6_pmu_raw_event(u64 hw_event)
-{
-#define P6_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define P6_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define P6_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define P6_EVNTSEL_INV_MASK		0x00800000ULL
-#define P6_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define P6_EVNTSEL_MASK			\
-	(P6_EVNTSEL_EVENT_MASK |	\
-	 P6_EVNTSEL_UNIT_MASK  |	\
-	 P6_EVNTSEL_EDGE_MASK  |	\
-	 P6_EVNTSEL_INV_MASK   |	\
-	 P6_EVNTSEL_REG_MASK)
-
-	return hw_event & P6_EVNTSEL_MASK;
-}
-
 static struct event_constraint p6_event_constraints[] =
 {
 	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
@@ -66,7 +48,7 @@ static void p6_pmu_disable_all(void)
 	wrmsrl(MSR_P6_EVNTSEL0, val);
 }
 
-static void p6_pmu_enable_all(void)
+static void p6_pmu_enable_all(int added)
 {
 	unsigned long val;
 
@@ -102,22 +84,23 @@ static void p6_pmu_enable_event(struct perf_event *event)
 	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static __initconst struct x86_pmu p6_pmu = {
+static __initconst const struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= p6_pmu_disable_all,
 	.enable_all		= p6_pmu_enable_all,
 	.enable			= p6_pmu_enable_event,
 	.disable		= p6_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_P6_EVNTSEL0,
 	.perfctr		= MSR_P6_PERFCTR0,
 	.event_map		= p6_pmu_event_map,
-	.raw_event		= p6_pmu_raw_event,
 	.max_events		= ARRAY_SIZE(p6_perfmon_event_map),
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_events		= 2,
+	.num_counters		= 2,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the
@@ -125,8 +108,8 @@ static __initconst struct x86_pmu p6_pmu = {
 	 *
 	 * See IA-32 Intel Architecture Software developer manual Vol 3B
 	 */
-	.event_bits		= 32,
-	.event_mask		= (1ULL << 32) - 1,
+	.cntval_bits		= 32,
+	.cntval_mask		= (1ULL << 32) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
 	.event_constraints	= p6_event_constraints,
 };

arch/x86/kernel/ds_selftest.h

-/*
- * Debug Store support - selftest
- *
- *
- * Copyright (C) 2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2009
- */
-
-#ifdef CONFIG_X86_DS_SELFTEST
-extern int ds_selftest_bts(void);
-extern int ds_selftest_pebs(void);
-#else
-static inline int ds_selftest_bts(void) { return 0; }
-static inline int ds_selftest_pebs(void) { return 0; }
-#endif

arch/x86/kernel/dumpstack.c

@@ -224,11 +224,6 @@ unsigned __kprobes long oops_begin(void)
 	int cpu;
 	unsigned long flags;
 
-	/* notify the hw-branch tracer so it may disable tracing and
-	   add the last trace to the trace buffer -
-	   the earlier this happens, the more useful the trace. */
-	trace_hw_branch_oops();
-
 	oops_enter();
 
 	/* racy, but better than risking deadlock. */

arch/x86/kernel/hw_breakpoint.c

@@ -188,26 +188,17 @@ static int get_hbp_len(u8 hbp_len)
 	return len_in_bytes;
 }
 
-/*
- * Check for virtual address in user space.
- */
-int arch_check_va_in_userspace(unsigned long va, u8 hbp_len)
-{
-	unsigned int len;
-
-	len = get_hbp_len(hbp_len);
-
-	return (va <= TASK_SIZE - len);
-}
-
 /*
  * Check for virtual address in kernel space.
  */
-static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -300,8 +291,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -314,16 +304,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 
 	ret = -EINVAL;
 
-	if (info->type == X86_BREAKPOINT_EXECUTE)
-		/*
-		 * Ptrace-refactoring code
-		 * For now, we'll allow instruction breakpoint only for user-space
-		 * addresses
-		 */
-		if ((!arch_check_va_in_userspace(info->address, info->len)) &&
-			info->len != X86_BREAKPOINT_EXECUTE)
-			return ret;
-
 	switch (info->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
@@ -350,15 +330,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 	if (info->address & align)
 		return -EINVAL;
 
-	/* Check that the virtual address is in the proper range */
-	if (tsk) {
-		if (!arch_check_va_in_userspace(info->address, info->len))
-			return -EFAULT;
-	} else {
-		if (!arch_check_va_in_kernelspace(info->address, info->len))
-			return -EFAULT;
-	}
-
 	return 0;
 }
 

arch/x86/kernel/process_32.c

@@ -55,7 +55,6 @@
 #include <asm/cpu.h>
 #include <asm/idle.h>
 #include <asm/syscalls.h>
-#include <asm/ds.h>
 #include <asm/debugreg.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -238,13 +237,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		kfree(p->thread.io_bitmap_ptr);
 		p->thread.io_bitmap_max = 0;
 	}
-
-	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
-	p->thread.ds_ctx = NULL;
-
-	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
-	p->thread.debugctlmsr = 0;
-
 	return err;
 }