Linux 3.5.4

commit 43ca6cb28c upstream.

The old interface is bugged and reads the wrong sensor when retrieving
the reading for the chassis fan (it reads the CPU sensor); the new
interface works fine.

Reported-by: Göran Uddeborg <goeran@uddeborg.se>
Tested-by: Göran Uddeborg <goeran@uddeborg.se>
Signed-off-by: Luca Tettamanti <kronos.it@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/i2c/busses/i2c-i801

@@ -21,6 +21,7 @@ Supported adapters:
   * Intel DH89xxCC (PCH)
   * Intel Panther Point (PCH)
   * Intel Lynx Point (PCH)
+  * Intel Lynx Point-LP (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller

Documentation/security/Yama.txt

@@ -46,14 +46,13 @@ restrictions, it can call prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, ...)
 so that any otherwise allowed process (even those in external pid namespaces)
 may attach.
 
-These restrictions do not change how ptrace via PTRACE_TRACEME operates.
-
-The sysctl settings are:
+The sysctl settings (writable only with CAP_SYS_PTRACE) are:
 
 0 - classic ptrace permissions: a process can PTRACE_ATTACH to any other
     process running under the same uid, as long as it is dumpable (i.e.
     did not transition uids, start privileged, or have called
-    prctl(PR_SET_DUMPABLE...) already).
+    prctl(PR_SET_DUMPABLE...) already). Similarly, PTRACE_TRACEME is
+    unchanged.
 
 1 - restricted ptrace: a process must have a predefined relationship
     with the inferior it wants to call PTRACE_ATTACH on. By default,
@@ -61,12 +60,13 @@ The sysctl settings are:
     classic criteria is also met. To change the relationship, an
     inferior can call prctl(PR_SET_PTRACER, debugger, ...) to declare
     an allowed debugger PID to call PTRACE_ATTACH on the inferior.
+    Using PTRACE_TRACEME is unchanged.
 
 2 - admin-only attach: only processes with CAP_SYS_PTRACE may use ptrace
-    with PTRACE_ATTACH.
+    with PTRACE_ATTACH, or through children calling PTRACE_TRACEME.
 
-3 - no attach: no processes may use ptrace with PTRACE_ATTACH. Once set,
-    this sysctl cannot be changed to a lower value.
+3 - no attach: no processes may use ptrace with PTRACE_ATTACH nor via
+    PTRACE_TRACEME. Once set, this sysctl value cannot be changed.
 
 The original children-only logic was based on the restrictions in grsecurity.
 

Documentation/sound/alsa/HD-Audio-Models.txt

@@ -21,10 +21,11 @@ ALC267/268
 ==========
   N/A
 
-ALC269
+ALC269/270/275/276/280/282
 ======
   laptop-amic	Laptops with analog-mic input
   laptop-dmic	Laptops with digital-mic input
+  lenovo-dock   Enables docking station I/O for some Lenovos
 
 ALC662/663/272
 ==============

Documentation/stable_kernel_rules.txt

@@ -1,4 +1,4 @@
-Everything you ever wanted to know about Linux 2.6 -stable releases.
+Everything you ever wanted to know about Linux -stable releases.
 
 Rules on what kind of patches are accepted, and which ones are not, into the
 "-stable" tree:
@@ -42,10 +42,10 @@ Procedure for submitting patches to the -stable tree:
    cherry-picked than this can be specified in the following format in
    the sign-off area:
 
-     Cc: <stable@vger.kernel.org> # .32.x: a1f84a3: sched: Check for idle
-     Cc: <stable@vger.kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
-     Cc: <stable@vger.kernel.org> # .32.x: fd21073: sched: Fix affinity logic
-     Cc: <stable@vger.kernel.org> # .32.x
+     Cc: <stable@vger.kernel.org> # 3.3.x: a1f84a3: sched: Check for idle
+     Cc: <stable@vger.kernel.org> # 3.3.x: 1b9508f: sched: Rate-limit newidle
+     Cc: <stable@vger.kernel.org> # 3.3.x: fd21073: sched: Fix affinity logic
+     Cc: <stable@vger.kernel.org> # 3.3.x
     Signed-off-by: Ingo Molnar <mingo@elte.hu>
 
    The tag sequence has the meaning of:
@@ -79,6 +79,15 @@ Review cycle:
    security kernel team, and not go through the normal review cycle.
    Contact the kernel security team for more details on this procedure.
 
+Trees:
+
+ - The queues of patches, for both completed versions and in progress
+   versions can be found at:
+	http://git.kernel.org/?p=linux/kernel/git/stable/stable-queue.git
+ - The finalized and tagged releases of all stable kernels can be found
+   in separate branches per version at:
+	http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git
+
 
 Review committee:
 

MAINTAINERS

@@ -5635,7 +5635,7 @@ F:	Documentation/blockdev/ramdisk.txt
 F:	drivers/block/brd.c
 
 RANDOM NUMBER DRIVER
-M:	Matt Mackall <mpm@selenic.com>
+M:	Theodore Ts'o" <tytso@mit.edu>
 S:	Maintained
 F:	drivers/char/random.c
 

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 5
-SUBLEVEL = 0
+SUBLEVEL = 4
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/alpha/include/asm/fpu.h

@@ -1,7 +1,9 @@
 #ifndef __ASM_ALPHA_FPU_H
 #define __ASM_ALPHA_FPU_H
 
+#ifdef __KERNEL__
 #include <asm/special_insns.h>
+#endif
 
 /*
  * Alpha floating-point control register defines:

arch/alpha/include/asm/socket.h

@@ -76,9 +76,11 @@
 /* Instruct lower device to use last 4-bytes of skb data as FCS */
 #define SO_NOFCS		43
 
+#ifdef __KERNEL__
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
 #define SOCK_NONBLOCK	0x40000000
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_SOCKET_H */

arch/arm/Kconfig

@@ -2083,6 +2083,7 @@ source "drivers/cpufreq/Kconfig"
 config CPU_FREQ_IMX
 	tristate "CPUfreq driver for i.MX CPUs"
 	depends on ARCH_MXC && CPU_FREQ
+	select CPU_FREQ_TABLE
 	help
 	  This enables the CPUfreq driver for i.MX CPUs.
 

arch/arm/boot/dts/imx53-ard.dts

@@ -66,10 +66,30 @@
 			interrupt-parent = <&gpio2>;
 			interrupts = <31>;
 			reg-io-width = <4>;
+			/*
+			 * VDD33A and VDDVARIO of LAN9220 are supplied by
+			 * SW4_3V3 of LTC3589.  Before the regulator driver
+			 * for this PMIC is available, we use a fixed dummy
+			 * 3V3 regulator to get LAN9220 driver probing work.
+			 */
+			vdd33a-supply = <&reg_3p3v>;
+			vddvario-supply = <&reg_3p3v>;
 			smsc,irq-push-pull;
 		};
 	};
 
+	regulators {
+		compatible = "simple-bus";
+
+		reg_3p3v: 3p3v {
+			compatible = "regulator-fixed";
+			regulator-name = "3P3V";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 

arch/arm/boot/dts/tegra-trimslice.dts

@@ -276,9 +276,11 @@
 
 	usb@c5000000 {
 		status = "okay";
+		nvidia,vbus-gpio = <&gpio 170 0>; /* gpio PV2 */
 	};
 
 	usb@c5004000 {
+		status = "okay";
 		nvidia,phy-reset-gpio = <&gpio 168 0>; /* gpio PV0 */
 	};
 

arch/arm/configs/mxs_defconfig

@@ -33,7 +33,6 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_AEABI=y
-CONFIG_DEFAULT_MMAP_MIN_ADDR=65536
 CONFIG_AUTO_ZRELADDR=y
 CONFIG_FPE_NWFPE=y
 CONFIG_NET=y

arch/arm/include/asm/cacheflush.h

@@ -215,7 +215,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm)
 static inline void
 vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 					vma->vm_flags);
 }
@@ -223,7 +225,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 static inline void
 vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 		unsigned long addr = user_addr & PAGE_MASK;
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}

arch/arm/include/asm/pgtable.h

@@ -195,25 +195,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
-#if __LINUX_ARM_ARCH__ < 6
-static inline void __sync_icache_dcache(pte_t pteval)
-{
-}
-#else
-extern void __sync_icache_dcache(pte_t pteval);
-#endif
-
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pteval)
-{
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
-		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
-	}
-}
-
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
 #define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
@@ -226,6 +207,27 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
 	 (L_PTE_PRESENT | L_PTE_USER))
 
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
+		__sync_icache_dcache(pteval);
+		ext |= PTE_EXT_NG;
+	}
+
+	set_pte_ext(ptep, pteval, ext);
+}
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
@@ -251,13 +253,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------------> <- type --> 0 0 0
+ *   <--------------- offset ----------------------> < type -> 0 0 0
  *
- * This gives us up to 63 swap files and 32GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	3
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
 

arch/arm/kernel/entry-armv.S

@@ -244,6 +244,19 @@ svc_preempt:
 	b	1b
 #endif
 
+__und_fault:
+	@ Correct the PC such that it is pointing at the instruction
+	@ which caused the fault.  If the faulting instruction was ARM
+	@ the PC will be pointing at the next instruction, and have to
+	@ subtract 4.  Otherwise, it is Thumb, and the PC will be
+	@ pointing at the second half of the Thumb instruction.  We
+	@ have to subtract 2.
+	ldr	r2, [r0, #S_PC]
+	sub	r2, r2, r1
+	str	r2, [r0, #S_PC]
+	b	do_undefinstr
+ENDPROC(__und_fault)
+
 	.align	5
 __und_svc:
 #ifdef CONFIG_KPROBES
@@ -261,25 +274,32 @@ __und_svc:
 	@
 	@  r0 - instruction
 	@
-#ifndef	CONFIG_THUMB2_KERNEL
+#ifndef CONFIG_THUMB2_KERNEL
 	ldr	r0, [r4, #-4]
 #else
+	mov	r1, #2
 	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
 	cmp	r0, #0xe800			@ 32-bit instruction if xx >= 0
-	ldrhhs	r9, [r4]			@ bottom 16 bits
-	orrhs	r0, r9, r0, lsl #16
+	blo	__und_svc_fault
+	ldrh	r9, [r4]			@ bottom 16 bits
+	add	r4, r4, #2
+	str	r4, [sp, #S_PC]
+	orr	r0, r9, r0, lsl #16
 #endif
-	adr	r9, BSYM(1f)
+	adr	r9, BSYM(__und_svc_finish)
 	mov	r2, r4
 	bl	call_fpe
 
+	mov	r1, #4				@ PC correction to apply
+__und_svc_fault:
 	mov	r0, sp				@ struct pt_regs *regs
-	bl	do_undefinstr
+	bl	__und_fault
 
 	@
 	@ IRQs off again before pulling preserved data off the stack
 	@
-1:	disable_irq_notrace
+__und_svc_finish:
+	disable_irq_notrace
 
 	@
 	@ restore SPSR and restart the instruction
@@ -423,25 +443,33 @@ __und_usr:
 	mov	r2, r4
 	mov	r3, r5
 
+	@ r2 = regs->ARM_pc, which is either 2 or 4 bytes ahead of the
+	@      faulting instruction depending on Thumb mode.
+	@ r3 = regs->ARM_cpsr
 	@
-	@ fall through to the emulation code, which returns using r9 if
-	@ it has emulated the instruction, or the more conventional lr
-	@ if we are to treat this as a real undefined instruction
-	@
-	@  r0 - instruction
+	@ The emulation code returns using r9 if it has emulated the
+	@ instruction, or the more conventional lr if we are to treat
+	@ this as a real undefined instruction
 	@
 	adr	r9, BSYM(ret_from_exception)
-	adr	lr, BSYM(__und_usr_unknown)
+
 	tst	r3, #PSR_T_BIT			@ Thumb mode?
-	itet	eq				@ explicit IT needed for the 1f label
-	subeq	r4, r2, #4			@ ARM instr at LR - 4
-	subne	r4, r2, #2			@ Thumb instr at LR - 2
-1:	ldreqt	r0, [r4]
+	bne	__und_usr_thumb
+	sub	r4, r2, #4			@ ARM instr at LR - 4
+1:	ldrt	r0, [r4]
 #ifdef CONFIG_CPU_ENDIAN_BE8
-	reveq	r0, r0				@ little endian instruction
+	rev	r0, r0				@ little endian instruction
 #endif
-	beq	call_fpe
+	@ r0 = 32-bit ARM instruction which caused the exception
+	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
+	@ r4 = PC value for the faulting instruction
+	@ lr = 32-bit undefined instruction function
+	adr	lr, BSYM(__und_usr_fault_32)
+	b	call_fpe
+
+__und_usr_thumb:
 	@ Thumb instruction
+	sub	r4, r2, #2			@ First half of thumb instr at LR - 2
 #if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
 /*
  * Thumb-2 instruction handling.  Note that because pre-v6 and >= v6 platforms
@@ -455,7 +483,7 @@ __und_usr:
 	ldr	r5, .LCcpu_architecture
 	ldr	r5, [r5]
 	cmp	r5, #CPU_ARCH_ARMv7
-	blo	__und_usr_unknown
+	blo	__und_usr_fault_16		@ 16bit undefined instruction
 /*
  * The following code won't get run unless the running CPU really is v7, so
  * coding round the lack of ldrht on older arches is pointless.  Temporarily
@@ -463,15 +491,18 @@ __und_usr:
  */
 	.arch	armv6t2
 #endif
-2:
- ARM(	ldrht	r5, [r4], #2	)
- THUMB(	ldrht	r5, [r4]	)
- THUMB(	add	r4, r4, #2	)
+2:	ldrht	r5, [r4]
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_unknown
-3:	ldrht	r0, [r4]
+	blo	__und_usr_fault_16		@ 16bit undefined instruction
+3:	ldrht	r0, [r2]
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
+	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
+	adr	lr, BSYM(__und_usr_fault_32)
+	@ r0 = the two 16-bit Thumb instructions which caused the exception
+	@ r2 = PC value for the following Thumb instruction (:= regs->ARM_pc)
+	@ r4 = PC value for the first 16-bit Thumb instruction
+	@ lr = 32bit undefined instruction function
 
 #if __LINUX_ARM_ARCH__ < 7
 /* If the target arch was overridden, change it back: */
@@ -482,17 +513,13 @@ __und_usr:
 #endif
 #endif /* __LINUX_ARM_ARCH__ < 7 */
 #else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */
-	b	__und_usr_unknown
+	b	__und_usr_fault_16
 #endif
- UNWIND(.fnend		)
+ UNWIND(.fnend)
 ENDPROC(__und_usr)
 
-	@
-	@ fallthrough to call_fpe
-	@
-
 /*
- * The out of line fixup for the ldrt above.
+ * The out of line fixup for the ldrt instructions above.
  */
 	.pushsection .fixup, "ax"
 	.align	2
@@ -524,11 +551,12 @@ ENDPROC(__und_usr)
  * NEON handler code.
  *
  * Emulators may wish to make use of the following registers:
- *  r0  = instruction opcode.
- *  r2  = PC+4
+ *  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+ *  r2  = PC value to resume execution after successful emulation
  *  r9  = normal "successful" return address
- *  r10 = this threads thread_info structure.
+ *  r10 = this threads thread_info structure
  *  lr  = unrecognised instruction return address
+ * IRQs disabled, FIQs enabled.
  */
 	@
 	@ Fall-through from Thumb-2 __und_usr
@@ -659,12 +687,17 @@ ENTRY(no_fp)
 	mov	pc, lr
 ENDPROC(no_fp)
 
-__und_usr_unknown:
-	enable_irq
+__und_usr_fault_32:
+	mov	r1, #4
+	b	1f
+__und_usr_fault_16:
+	mov	r1, #2
+1:	enable_irq
 	mov	r0, sp
 	adr	lr, BSYM(ret_from_exception)
-	b	do_undefinstr
-ENDPROC(__und_usr_unknown)
+	b	__und_fault
+ENDPROC(__und_usr_fault_32)
+ENDPROC(__und_usr_fault_16)
 
 	.align	5
 __pabt_usr:

arch/arm/kernel/process.c

@@ -247,6 +247,7 @@ void machine_shutdown(void)
 void machine_halt(void)
 {
 	machine_shutdown();
+	local_irq_disable();
 	while (1);
 }
 
@@ -268,6 +269,7 @@ void machine_restart(char *cmd)
 
 	/* Whoops - the platform was unable to reboot. Tell the user! */
 	printk("Reboot failed -- System halted\n");
+	local_irq_disable();
 	while (1);
 }
 

arch/arm/kernel/smp.c

@@ -563,7 +563,8 @@ void smp_send_stop(void)
 
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
-	smp_cross_call(&mask, IPI_CPU_STOP);
+	if (!cpumask_empty(&mask))
+		smp_cross_call(&mask, IPI_CPU_STOP);
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;

arch/arm/kernel/traps.c

@@ -370,18 +370,10 @@ static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
 
 asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 {
-	unsigned int correction = thumb_mode(regs) ? 2 : 4;
 	unsigned int instr;
 	siginfo_t info;
 	void __user *pc;
 
-	/*
-	 * According to the ARM ARM, PC is 2 or 4 bytes ahead,
-	 * depending whether we're in Thumb mode or not.
-	 * Correct this offset.
-	 */
-	regs->ARM_pc -= correction;
-
 	pc = (void __user *)instruction_pointer(regs);
 
 	if (processor_mode(regs) == SVC_MODE) {

arch/arm/mach-imx/Makefile

@@ -9,7 +9,8 @@ obj-$(CONFIG_SOC_IMX27) += clk-imx27.o mm-imx27.o ehci-imx27.o
 obj-$(CONFIG_SOC_IMX31) += mm-imx3.o cpu-imx31.o clk-imx31.o iomux-imx31.o ehci-imx31.o pm-imx3.o
 obj-$(CONFIG_SOC_IMX35) += mm-imx3.o cpu-imx35.o clk-imx35.o ehci-imx35.o pm-imx3.o
 
-obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o pm-imx5.o cpu_op-mx51.o
+imx5-pm-$(CONFIG_PM) += pm-imx5.o
+obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o $(imx5-pm-y) cpu_op-mx51.o
 
 obj-$(CONFIG_COMMON_CLK) += clk-pllv1.o clk-pllv2.o clk-pllv3.o clk-gate2.o \
 			    clk-pfd.o clk-busy.o
@@ -69,14 +70,13 @@ obj-$(CONFIG_DEBUG_LL) += lluart.o
 obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o
 obj-$(CONFIG_HAVE_IMX_MMDC) += mmdc.o
 obj-$(CONFIG_HAVE_IMX_SRC) += src.o
-obj-$(CONFIG_CPU_V7) += head-v7.o
-AFLAGS_head-v7.o :=-Wa,-march=armv7-a
-obj-$(CONFIG_SMP) += platsmp.o
+AFLAGS_headsmp.o :=-Wa,-march=armv7-a
+obj-$(CONFIG_SMP) += headsmp.o platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
 obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o
 
 ifeq ($(CONFIG_PM),y)
-obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o
+obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o
 endif
 
 # i.MX5 based machines

arch/arm/mach-imx/clk-imx31.c

@@ -129,7 +129,7 @@ int __init mx31_clocks_init(unsigned long fref)
 	clk_register_clkdev(clk[nfc], NULL, "mxc_nand.0");
 	clk_register_clkdev(clk[ipu_gate], NULL, "ipu-core");
 	clk_register_clkdev(clk[ipu_gate], NULL, "mx3_sdc_fb");
-	clk_register_clkdev(clk[kpp_gate], "kpp", NULL);
+	clk_register_clkdev(clk[kpp_gate], NULL, "imx-keypad");
 	clk_register_clkdev(clk[usb_div_post], "per", "mxc-ehci.0");
 	clk_register_clkdev(clk[usb_gate], "ahb", "mxc-ehci.0");
 	clk_register_clkdev(clk[ipg], "ipg", "mxc-ehci.0");

arch/arm/mach-imx/clk-imx51-imx53.c

@@ -293,6 +293,7 @@ static void __init mx5_clocks_common_init(unsigned long rate_ckil,
 	clk_prepare_enable(clk[aips_tz2]); /* fec */
 	clk_prepare_enable(clk[spba]);
 	clk_prepare_enable(clk[emi_fast_gate]); /* fec */
+	clk_prepare_enable(clk[emi_slow_gate]); /* eim */
 	clk_prepare_enable(clk[tmax1]);
 	clk_prepare_enable(clk[tmax2]); /* esdhc2, fec */
 	clk_prepare_enable(clk[tmax3]); /* esdhc1, esdhc4 */

arch/arm/mach-imx/hotplug.c

@@ -42,22 +42,6 @@ static inline void cpu_enter_lowpower(void)
 	  : "cc");
 }
 
-static inline void cpu_leave_lowpower(void)
-{
-	unsigned int v;
-
-	asm volatile(
-		"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, %1\n"
-	"	mcr	p15, 0, %0, c1, c0, 0\n"
-	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	orr	%0, %0, %2\n"
-	"	mcr	p15, 0, %0, c1, c0, 1\n"
-	  : "=&r" (v)
-	  : "Ir" (CR_C), "Ir" (0x40)
-	  : "cc");
-}
-
 /*
  * platform-specific code to shutdown a CPU
  *
@@ -67,11 +51,10 @@ void platform_cpu_die(unsigned int cpu)
 {
 	cpu_enter_lowpower();
 	imx_enable_cpu(cpu, false);
-	cpu_do_idle();
-	cpu_leave_lowpower();
 
-	/* We should never return from idle */
-	panic("cpu %d unexpectedly exit from shutdown\n", cpu);
+	/* spin here until hardware takes it down */
+	while (1)
+		;
 }
 
 int platform_cpu_disable(unsigned int cpu)

arch/arm/mach-omap2/opp.c

@@ -53,7 +53,7 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 	omap_table_init = 1;
 
 	/* Lets now register with OPP library */
-	for (i = 0; i < opp_def_size; i++) {
+	for (i = 0; i < opp_def_size; i++, opp_def++) {
 		struct omap_hwmod *oh;
 		struct device *dev;
 
@@ -86,7 +86,6 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 					__func__, opp_def->freq,
 					opp_def->hwmod_name, i, r);
 		}
-		opp_def++;
 	}
 
 	return 0;

arch/arm/mach-pxa/raumfeld.c

@@ -953,12 +953,12 @@ static struct i2c_board_info raumfeld_connector_i2c_board_info __initdata = {
 
 static struct eeti_ts_platform_data eeti_ts_pdata = {
 	.irq_active_high = 1,
+	.irq_gpio = GPIO_TOUCH_IRQ,
 };
 
 static struct i2c_board_info raumfeld_controller_i2c_board_info __initdata = {
 	.type	= "eeti_ts",
 	.addr	= 0x0a,
-	.irq	= PXA_GPIO_TO_IRQ(GPIO_TOUCH_IRQ),
 	.platform_data = &eeti_ts_pdata,
 };
 

arch/arm/mach-s3c24xx/include/mach/dma.h

@@ -24,7 +24,8 @@
 */
 
 enum dma_ch {
-	DMACH_XD0,
+	DMACH_DT_PROP = -1,	/* not yet supported, do not use */
+	DMACH_XD0 = 0,
 	DMACH_XD1,
 	DMACH_SDI,
 	DMACH_SPI0,

arch/arm/mm/flush.c

@@ -231,8 +231,6 @@ void __sync_icache_dcache(pte_t pteval)
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;

arch/arm/mm/tlb-v7.S

@@ -39,10 +39,18 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	asid	r3, r3				@ mask ASID
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(W(mov)	r3, #0	)
+	ALT_UP(W(nop)		)
+#endif
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 3)	@ TLB invalidate U MVA all ASID (shareable)
+#else
 	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+#endif
 	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 
 	add	r0, r0, #PAGE_SZ
@@ -67,7 +75,11 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	mov	r0, r0, lsl #PAGE_SHIFT
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 3)	@ TLB invalidate U MVA all ASID (shareable)
+#else
 	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+#endif
 	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1

arch/arm/plat-omap/dmtimer.c

@@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(omap_dm_timer_enable);
 
 void omap_dm_timer_disable(struct omap_dm_timer *timer)
 {
-	pm_runtime_put(&timer->pdev->dev);
+	pm_runtime_put_sync(&timer->pdev->dev);
 }
 EXPORT_SYMBOL_GPL(omap_dm_timer_disable);
 

arch/arm/plat-s3c24xx/dma.c

@@ -430,7 +430,7 @@ s3c2410_dma_canload(struct s3c2410_dma_chan *chan)
  * when necessary.
 */
 
-int s3c2410_dma_enqueue(unsigned int channel, void *id,
+int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
 			dma_addr_t data, int size)
 {
 	struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);

arch/arm/vfp/entry.S

@@ -7,18 +7,20 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * Basic entry code, called from the kernel's undefined instruction trap.
- *  r0  = faulted instruction
- *  r5  = faulted PC+4
- *  r9  = successful return
- *  r10 = thread_info structure
- *  lr  = failure return
  */
 #include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
 #include "../kernel/entry-header.S"
 
+@ VFP entry point.
+@
+@  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+@  r2  = PC value to resume execution after successful emulation
+@  r9  = normal "successful" return address
+@  r10 = this threads thread_info structure
+@  lr  = unrecognised instruction return address
+@  IRQs disabled.
+@
 ENTRY(do_vfp)
 #ifdef CONFIG_PREEMPT
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count

arch/arm/vfp/vfphw.S

@@ -61,13 +61,13 @@
 
 @ VFP hardware support entry point.
 @
-@  r0  = faulted instruction
-@  r2  = faulted PC+4
-@  r9  = successful return
+@  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+@  r2  = PC value to resume execution after successful emulation
+@  r9  = normal "successful" return address
 @  r10 = vfp_state union
 @  r11 = CPU number
-@  lr  = failure return
-
+@  lr  = unrecognised instruction return address
+@  IRQs enabled.
 ENTRY(vfp_support_entry)
 	DBGSTR3	"instr %08x pc %08x state %p", r0, r2, r10
 
@@ -161,9 +161,12 @@ vfp_hw_state_valid:
 					@ exception before retrying branch
 					@ out before setting an FPEXC that
 					@ stops us reading stuff
-	VFPFMXR	FPEXC, r1		@ restore FPEXC last
-	sub	r2, r2, #4
-	str	r2, [sp, #S_PC]		@ retry the instruction
+	VFPFMXR	FPEXC, r1		@ Restore FPEXC last
+	sub	r2, r2, #4		@ Retry current instruction - if Thumb
+	str	r2, [sp, #S_PC]		@ mode it's two 16-bit instructions,
+					@ else it's one 32-bit instruction, so
+					@ always subtract 4 from the following
+					@ instruction address.
 #ifdef CONFIG_PREEMPT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count

arch/arm/vfp/vfpmodule.c

@@ -457,10 +457,16 @@ static int vfp_pm_suspend(void)
 
 		/* disable, just in case */
 		fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+	} else if (vfp_current_hw_state[ti->cpu]) {
+#ifndef CONFIG_SMP
+		fmxr(FPEXC, fpexc | FPEXC_EN);
+		vfp_save_state(vfp_current_hw_state[ti->cpu], fpexc);
+		fmxr(FPEXC, fpexc);
+#endif
 	}
 
 	/* clear any information we had about last context state */
-	memset(vfp_current_hw_state, 0, sizeof(vfp_current_hw_state));
+	vfp_current_hw_state[ti->cpu] = NULL;
 
 	return 0;
 }
@@ -713,8 +719,10 @@ static int __init vfp_init(void)
 			if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100)
 				elf_hwcap |= HWCAP_NEON;
 #endif
+#ifdef CONFIG_VFPv3
 			if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000)
 				elf_hwcap |= HWCAP_VFPv4;
+#endif
 		}
 	}
 	return 0;

arch/ia64/include/asm/atomic.h

@@ -17,8 +17,8 @@
 #include <asm/intrinsics.h>
 
 
-#define ATOMIC_INIT(i)		((atomic_t) { (i) })
-#define ATOMIC64_INIT(i)	((atomic64_t) { (i) })
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)

arch/ia64/kernel/irq_ia64.c

@@ -23,7 +23,6 @@
 #include <linux/ioport.h>
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>	/* for rand_initialize_irq() */
 #include <linux/signal.h>
 #include <linux/smp.h>
 #include <linux/threads.h>

arch/m68k/kernel/sys_m68k.c

@@ -479,9 +479,13 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
 			goto bad_access;
 		}
 
-		mem_value = *mem;
+		/*
+		 * No need to check for EFAULT; we know that the page is
+		 * present and writable.
+		 */
+		__get_user(mem_value, mem);
 		if (mem_value == oldval)
-			*mem = newval;
+			__put_user(newval, mem);
 
 		pte_unmap_unlock(pte, ptl);
 		up_read(&mm->mmap_sem);

arch/mips/kernel/kspd.c

@@ -323,7 +323,7 @@ static void sp_cleanup(void)
 	fdt = files_fdtable(files);
 	for (;;) {
 		unsigned long set;
-		i = j * __NFDBITS;
+		i = j * BITS_PER_LONG;
 		if (i >= fdt->max_fds)
 			break;
 		set = fdt->open_fds[j++];

arch/mips/pci/pci-ar724x.c

@@ -23,9 +23,12 @@
 #define AR724X_PCI_MEM_BASE	0x10000000
 #define AR724X_PCI_MEM_SIZE	0x08000000
 
+#define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
 #define AR724X_PCI_REG_INT_MASK		0x50
 
+#define AR724X_PCI_RESET_LINK_UP	BIT(0)
+
 #define AR724X_PCI_INT_DEV0		BIT(14)
 
 #define AR724X_PCI_IRQ_COUNT		1
@@ -38,6 +41,15 @@ static void __iomem *ar724x_pci_ctrl_base;
 
 static u32 ar724x_pci_bar0_value;
 static bool ar724x_pci_bar0_is_cached;
+static bool ar724x_pci_link_up;
+
+static inline bool ar724x_pci_check_link(void)
+{
+	u32 reset;
+
+	reset = __raw_readl(ar724x_pci_ctrl_base + AR724X_PCI_REG_RESET);
+	return reset & AR724X_PCI_RESET_LINK_UP;
+}
 
 static int ar724x_pci_read(struct pci_bus *bus, unsigned int devfn, int where,
 			    int size, uint32_t *value)
@@ -46,6 +58,9 @@ static int ar724x_pci_read(struct pci_bus *bus, unsigned int devfn, int where,
 	void __iomem *base;
 	u32 data;
 
+	if (!ar724x_pci_link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (devfn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
@@ -96,6 +111,9 @@ static int ar724x_pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 	u32 data;
 	int s;
 
+	if (!ar724x_pci_link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (devfn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
@@ -280,6 +298,10 @@ int __init ar724x_pcibios_init(int irq)
 	if (ar724x_pci_ctrl_base == NULL)
 		goto err_unmap_devcfg;
 
+	ar724x_pci_link_up = ar724x_pci_check_link();
+	if (!ar724x_pci_link_up)
+		pr_warn("ar724x: PCIe link is down\n");
+
 	ar724x_pci_irq_init(irq);
 	register_pci_controller(&ar724x_pci_controller);
 

arch/parisc/include/asm/atomic.h

@@ -141,7 +141,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
 
-#define ATOMIC_INIT(i)	((atomic_t) { (i) })
+#define ATOMIC_INIT(i)	{ (i) }
 
 #define smp_mb__before_atomic_dec()	smp_mb()
 #define smp_mb__after_atomic_dec()	smp_mb()
@@ -150,7 +150,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #ifdef CONFIG_64BIT
 
-#define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
+#define ATOMIC64_INIT(i) { (i) }
 
 static __inline__ s64
 __atomic64_add_return(s64 i, atomic64_t *v)

arch/powerpc/boot/dts/p1022ds.dtsi

@@ -33,22 +33,6 @@
  */
 
 &board_lbc {
-	/*
-	 * This node is used to access the pixis via "indirect" mode,
-	 * which is done by writing the pixis register index to chip
-	 * select 0 and the value to/from chip select 1.  Indirect
-	 * mode is the only way to access the pixis when DIU video
-	 * is enabled.  Note that this assumes that the first column
-	 * of the 'ranges' property above is the chip select number.
-	 */
-	board-control@0,0 {
-		compatible = "fsl,p1022ds-indirect-pixis";
-		reg = <0x0 0x0 1	/* CS0 */
-		       0x1 0x0 1>;	/* CS1 */
-		interrupt-parent = <&mpic>;
-		interrupts = <8 0 0 0>;
-	};
-
 	nor@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;

arch/powerpc/include/asm/reg.h

@@ -1024,7 +1024,8 @@
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
 #define mfmsr()		({unsigned long rval; \
-			asm volatile("mfmsr %0" : "=r" (rval)); rval;})
+			asm volatile("mfmsr %0" : "=r" (rval) : \
+						: "memory"); rval;})
 #ifdef CONFIG_PPC_BOOK3S_64
 #define __mtmsrd(v, l)	asm volatile("mtmsrd %0," __stringify(l) \
 				     : : "r" (v) : "memory")

arch/powerpc/kernel/asm-offsets.c

@@ -76,6 +76,7 @@ int main(void)
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
 	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */

arch/powerpc/kernel/dbell.c

@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	mb();
 	ppc_msgsnd(PPC_DBELL, 0, data);
 }
 

arch/powerpc/kernel/entry_64.S

@@ -369,6 +369,12 @@ _GLOBAL(ret_from_fork)
 	li	r3,0
 	b	syscall_exit
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -508,9 +514,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-	ld	r6,_CCR(r1)
-	mtcrf	0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	ld	r0,THREAD_VRSAVE(r4)
@@ -519,14 +522,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+	lwz	r6,THREAD_DSCR_INHERIT(r4)
+	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
-	cmpd	r0,r25
-	beq	1f
+	cmpwi	r6,0
+	bne	1f
+	ld	r0,0(r7)
+1:	cmpd	r0,r25
+	beq	2f
 	mtspr	SPRN_DSCR,r0
-1:	
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+	ld	r6,_CCR(r1)
+	mtcrf	0xFF,r6
+
 	/* r3-r13 are destroyed -- Cort */
 	REST_8GPRS(14, r1)
 	REST_10GPRS(22, r1)

arch/powerpc/kernel/ftrace.c

@@ -245,9 +245,9 @@ __ftrace_make_nop(struct module *mod,
 
 	/*
 	 * On PPC32 the trampoline looks like:
-	 *  0x3d, 0x60, 0x00, 0x00  lis r11,sym@ha
-	 *  0x39, 0x6b, 0x00, 0x00  addi r11,r11,sym@l
-	 *  0x7d, 0x69, 0x03, 0xa6  mtctr r11
+	 *  0x3d, 0x80, 0x00, 0x00  lis r12,sym@ha
+	 *  0x39, 0x8c, 0x00, 0x00  addi r12,r12,sym@l
+	 *  0x7d, 0x89, 0x03, 0xa6  mtctr r12
 	 *  0x4e, 0x80, 0x04, 0x20  bctr
 	 */
 
@@ -262,9 +262,9 @@ __ftrace_make_nop(struct module *mod,
 	pr_devel(" %08x %08x ", jmp[0], jmp[1]);
 
 	/* verify that this is what we expect it to be */
-	if (((jmp[0] & 0xffff0000) != 0x3d600000) ||
-	    ((jmp[1] & 0xffff0000) != 0x396b0000) ||
-	    (jmp[2] != 0x7d6903a6) ||
+	if (((jmp[0] & 0xffff0000) != 0x3d800000) ||
+	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
+	    (jmp[2] != 0x7d8903a6) ||
 	    (jmp[3] != 0x4e800420)) {
 		printk(KERN_ERR "Not a trampoline\n");
 		return -EINVAL;

arch/powerpc/kernel/process.c

@@ -802,16 +802,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		if (current->thread.dscr_inherit) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = current->thread.dscr;
-		} else if (0 != dscr_default) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = dscr_default;
-		} else {
-			p->thread.dscr_inherit = 0;
-			p->thread.dscr = 0;
-		}
+		p->thread.dscr_inherit = current->thread.dscr_inherit;
+		p->thread.dscr = current->thread.dscr;
 	}
 #endif
 

arch/powerpc/kernel/smp.c

@@ -197,8 +197,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
 	char *message = (char *)&info->messages;
 
+	/*
+	 * Order previous accesses before accesses in the IPI handler.
+	 */
+	smp_mb();
 	message[msg] = 1;
-	mb();
+	/*
+	 * cause_ipi functions are required to include a full barrier
+	 * before doing whatever causes the IPI.
+	 */
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -210,7 +217,7 @@ irqreturn_t smp_ipi_demux(void)
 	mb();	/* order any irq clear */
 
 	do {
-		all = xchg_local(&info->messages, 0);
+		all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))

arch/powerpc/kernel/sysfs.c

@@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev,
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = dscr_default;
+		mtspr(SPRN_DSCR, dscr_default);
+	}
+}
+
 static ssize_t __used store_dscr_default(struct device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
@@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev,
 		return -EINVAL;
 	dscr_default = val;
 
+	on_each_cpu(update_dscr, NULL, 1);
+
 	return count;
 }
 

arch/powerpc/kernel/traps.c

@@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs)
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mtdscr, regs);
 		rd = (instword >> 21) & 0x1f;
-		mtspr(SPRN_DSCR, regs->gpr[rd]);
+		current->thread.dscr = regs->gpr[rd];
 		current->thread.dscr_inherit = 1;
+		mtspr(SPRN_DSCR, current->thread.dscr);
 		return 0;
 	}
 #endif

arch/powerpc/platforms/85xx/p1022_ds.c

@@ -27,6 +27,7 @@
 #include <sysdev/fsl_pci.h>
 #include <asm/udbg.h>
 #include <asm/fsl_guts.h>
+#include <asm/fsl_lbc.h>
 #include "smp.h"
 
 #include "mpc85xx.h"
@@ -142,17 +143,73 @@ static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port,
 {
 }
 
+struct fsl_law {
+	u32	lawbar;
+	u32	reserved1;
+	u32	lawar;
+	u32	reserved[5];
+};
+
+#define LAWBAR_MASK	0x00F00000
+#define LAWBAR_SHIFT	12
+
+#define LAWAR_EN	0x80000000
+#define LAWAR_TGT_MASK	0x01F00000
+#define LAW_TRGT_IF_LBC	(0x04 << 20)
+
+#define LAWAR_MASK	(LAWAR_EN | LAWAR_TGT_MASK)
+#define LAWAR_MATCH	(LAWAR_EN | LAW_TRGT_IF_LBC)
+
+#define BR_BA		0xFFFF8000
+
+/*
+ * Map a BRx value to a physical address
+ *
+ * The localbus BRx registers only store the lower 32 bits of the address.  To
+ * obtain the upper four bits, we need to scan the LAW table.  The entry which
+ * maps to the localbus will contain the upper four bits.
+ */
+static phys_addr_t lbc_br_to_phys(const void *ecm, unsigned int count, u32 br)
+{
+#ifndef CONFIG_PHYS_64BIT
+	/*
+	 * If we only have 32-bit addressing, then the BRx address *is* the
+	 * physical address.
+	 */
+	return br & BR_BA;
+#else
+	const struct fsl_law *law = ecm + 0xc08;
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		u64 lawbar = in_be32(&law[i].lawbar);
+		u32 lawar = in_be32(&law[i].lawar);
+
+		if ((lawar & LAWAR_MASK) == LAWAR_MATCH)
+			/* Extract the upper four bits */
+			return (br & BR_BA) | ((lawbar & LAWBAR_MASK) << 12);
+	}
+
+	return 0;
+#endif
+}
+
 /**
  * p1022ds_set_monitor_port: switch the output to a different monitor port
- *
  */
 static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
 	struct device_node *guts_node;
-	struct device_node *indirect_node = NULL;
+	struct device_node *lbc_node = NULL;
+	struct device_node *law_node = NULL;
 	struct ccsr_guts __iomem *guts;
+	struct fsl_lbc_regs *lbc = NULL;
+	void *ecm = NULL;
 	u8 __iomem *lbc_lcs0_ba = NULL;
 	u8 __iomem *lbc_lcs1_ba = NULL;
+	phys_addr_t cs0_addr, cs1_addr;
+	const __be32 *iprop;
+	unsigned int num_laws;
 	u8 b;
 
 	/* Map the global utilities registers. */
@@ -168,25 +225,43 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 		goto exit;
 	}
 
-	indirect_node = of_find_compatible_node(NULL, NULL,
-					     "fsl,p1022ds-indirect-pixis");
-	if (!indirect_node) {
-		pr_err("p1022ds: missing pixis indirect mode node\n");
+	lbc_node = of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc");
+	if (!lbc_node) {
+		pr_err("p1022ds: missing localbus node\n");
 		goto exit;
 	}
 
-	lbc_lcs0_ba = of_iomap(indirect_node, 0);
-	if (!lbc_lcs0_ba) {
-		pr_err("p1022ds: could not map localbus chip select 0\n");
+	lbc = of_iomap(lbc_node, 0);
+	if (!lbc) {
+		pr_err("p1022ds: could not map localbus node\n");
 		goto exit;
 	}
 
-	lbc_lcs1_ba = of_iomap(indirect_node, 1);
-	if (!lbc_lcs1_ba) {
-		pr_err("p1022ds: could not map localbus chip select 1\n");
+	law_node = of_find_compatible_node(NULL, NULL, "fsl,ecm-law");
+	if (!law_node) {
+		pr_err("p1022ds: missing local access window node\n");
 		goto exit;
 	}
 
+	ecm = of_iomap(law_node, 0);
+	if (!ecm) {
+		pr_err("p1022ds: could not map local access window node\n");
+		goto exit;
+	}
+
+	iprop = of_get_property(law_node, "fsl,num-laws", 0);
+	if (!iprop) {
+		pr_err("p1022ds: LAW node is missing fsl,num-laws property\n");
+		goto exit;
+	}
+	num_laws = be32_to_cpup(iprop);
+
+	cs0_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[0].br));
+	cs1_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[1].br));
+
+	lbc_lcs0_ba = ioremap(cs0_addr, 1);
+	lbc_lcs1_ba = ioremap(cs1_addr, 1);
+
 	/* Make sure we're in indirect mode first. */
 	if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) !=
 	    PMUXCR_ELBCDIU_DIU) {
@@ -254,10 +329,15 @@ exit:
 		iounmap(lbc_lcs1_ba);
 	if (lbc_lcs0_ba)
 		iounmap(lbc_lcs0_ba);
+	if (lbc)
+		iounmap(lbc);
+	if (ecm)
+		iounmap(ecm);
 	if (guts)
 		iounmap(guts);
 
-	of_node_put(indirect_node);
+	of_node_put(law_node);
+	of_node_put(lbc_node);
 	of_node_put(guts_node);
 }
 

arch/powerpc/platforms/pseries/eeh_event.c

@@ -85,8 +85,10 @@ static int eeh_event_handler(void * dummy)
 	set_current_state(TASK_INTERRUPTIBLE);	/* Don't add to load average */
 	edev = handle_eeh_events(event);
 
-	eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
-	pci_dev_put(edev->pdev);
+	if (edev) {
+		eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
+		pci_dev_put(edev->pdev);
+	}
 
 	kfree(event);
 	mutex_unlock(&eeh_event_mutex);

arch/powerpc/sysdev/xics/icp-hv.c

@@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value)
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
 	int hw_cpu = get_hard_smp_processor_id(n_cpu);
-	long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+	long rc;
+
+	/* Make sure all previous accesses are ordered before IPI sending */
+	mb();
+	rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
 	if (rc != H_SUCCESS) {
 		pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
 			"returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);

arch/s390/include/asm/mmu_context.h

@@ -13,7 +13,6 @@
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/ctl_reg.h>
-#include <asm-generic/mm_hooks.h>
 
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
@@ -93,4 +92,17 @@ static inline void activate_mm(struct mm_struct *prev,
         switch_mm(prev, next, current);
 }
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+#ifdef CONFIG_64BIT
+	if (oldmm->context.asce_limit < mm->context.asce_limit)
+		crst_table_downgrade(mm, oldmm->context.asce_limit);
+#endif
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
 #endif /* __S390_MMU_CONTEXT_H */

arch/s390/include/asm/processor.h

@@ -122,7 +122,9 @@ struct stack_frame {
 	regs->psw.mask	= psw_user_bits | PSW_MASK_BA;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
 	regs->gprs[15]	= new_stackp;					\
+	__tlb_flush_mm(current->mm);					\
 	crst_table_downgrade(current->mm, 1UL << 31);			\
+	update_mm(current->mm, current);				\
 } while (0)
 
 /* Forward declaration, a strange C thing */

arch/s390/kernel/compat_linux.c

@@ -622,7 +622,6 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
 		return -EFAULT;
 	if (a.offset & ~PAGE_MASK)
 		return -EINVAL;
-	a.addr = (unsigned long) compat_ptr(a.addr);
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
 			      a.offset >> PAGE_SHIFT);
 }
@@ -633,7 +632,6 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
 
 	if (copy_from_user(&a, arg, sizeof(a)))
 		return -EFAULT;
-	a.addr = (unsigned long) compat_ptr(a.addr);
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
 }
 

arch/s390/kernel/compat_wrapper.S

@@ -1636,7 +1636,7 @@ ENTRY(compat_sys_process_vm_readv_wrapper)
 	llgfr	%r6,%r6			# unsigned long
 	llgf	%r0,164(%r15)		# unsigned long
 	stg	%r0,160(%r15)
-	jg	sys_process_vm_readv
+	jg	compat_sys_process_vm_readv
 
 ENTRY(compat_sys_process_vm_writev_wrapper)
 	lgfr	%r2,%r2			# compat_pid_t
@@ -1646,4 +1646,4 @@ ENTRY(compat_sys_process_vm_writev_wrapper)
 	llgfr	%r6,%r6			# unsigned long
 	llgf	%r0,164(%r15)		# unsigned long
 	stg	%r0,160(%r15)
-	jg	sys_process_vm_writev
+	jg	compat_sys_process_vm_writev

arch/s390/kernel/processor.c

@@ -26,12 +26,14 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id);
 void __cpuinit cpu_init(void)
 {
 	struct cpuid *id = &per_cpu(cpu_id, smp_processor_id());
+	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
 
 	get_cpu_id(id);
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
+	memset(idle, 0, sizeof(*idle));
 }
 
 /*

arch/s390/kernel/smp.c

@@ -984,14 +984,11 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 	unsigned int cpu = (unsigned int)(long)hcpu;
 	struct cpu *c = &pcpu_devices[cpu].cpu;
 	struct device *s = &c->dev;
-	struct s390_idle_data *idle;
 	int err = 0;
 
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		idle = &per_cpu(s390_idle, cpu);
-		memset(idle, 0, sizeof(struct s390_idle_data));
 		err = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
 		break;
 	case CPU_DEAD:

arch/s390/mm/fault.c

@@ -443,6 +443,7 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 	struct pt_regs regs;
 	int access, fault;
 
+	/* Emulate a uaccess fault from kernel mode. */
 	regs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK;
 	if (!irqs_disabled())
 		regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT;
@@ -452,12 +453,12 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 	regs.int_parm_long = (uaddr & PAGE_MASK) | 2;
 	access = write ? VM_WRITE : VM_READ;
 	fault = do_exception(&regs, access);
-	if (unlikely(fault)) {
-		if (fault & VM_FAULT_OOM)
-			return -EFAULT;
-		else if (fault & VM_FAULT_SIGBUS)
-			do_sigbus(&regs);
-	}
+	/*
+	 * Since the fault happened in kernel mode while performing a uaccess
+	 * all we need to do now is emulating a fixup in case "fault" is not
+	 * zero.
+	 * For the calling uaccess functions this results always in -EFAULT.
+	 */
 	return fault ? -EFAULT : 0;
 }
 

arch/s390/mm/mmap.c

@@ -105,9 +105,15 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 int s390_mmap_check(unsigned long addr, unsigned long len)
 {
+	int rc;
+
 	if (!is_compat_task() &&
-	    len >= TASK_SIZE && TASK_SIZE < (1UL << 53))
-		return crst_table_upgrade(current->mm, 1UL << 53);
+	    len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) {
+		rc = crst_table_upgrade(current->mm, 1UL << 53);
+		if (rc)
+			return rc;
+		update_mm(current->mm, current);
+	}
 	return 0;
 }
 
@@ -127,6 +133,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 		rc = crst_table_upgrade(mm, 1UL << 53);
 		if (rc)
 			return (unsigned long) rc;
+		update_mm(mm, current);
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
 	}
 	return area;
@@ -149,6 +156,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 		rc = crst_table_upgrade(mm, 1UL << 53);
 		if (rc)
 			return (unsigned long) rc;
+		update_mm(mm, current);
 		area = arch_get_unmapped_area_topdown(filp, addr, len,
 						      pgoff, flags);
 	}

arch/s390/mm/pgtable.c

@@ -85,7 +85,6 @@ repeat:
 		crst_table_free(mm, table);
 	if (mm->context.asce_limit < limit)
 		goto repeat;
-	update_mm(mm, current);
 	return 0;
 }
 
@@ -93,9 +92,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 {
 	pgd_t *pgd;
 
-	if (mm->context.asce_limit <= limit)
-		return;
-	__tlb_flush_mm(mm);
 	while (mm->context.asce_limit > limit) {
 		pgd = mm->pgd;
 		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
@@ -118,7 +114,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 		mm->task_size = mm->context.asce_limit;
 		crst_table_free(mm, (unsigned long *) pgd);
 	}
-	update_mm(mm, current);
 }
 #endif
 

arch/sh/mm/fault.c

@@ -58,11 +58,15 @@ static void show_pte(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 
-	if (mm)
+	if (mm) {
 		pgd = mm->pgd;
-	else
+	} else {
 		pgd = get_TTB();
 
+		if (unlikely(!pgd))
+			pgd = swapper_pg_dir;
+	}
+
 	printk(KERN_ALERT "pgd = %p\n", pgd);
 	pgd += pgd_index(addr);
 	printk(KERN_ALERT "[%08lx] *pgd=%0*Lx", addr,

arch/x86/kernel/alternative.c

@@ -219,7 +219,7 @@ void __init arch_init_ideal_nops(void)
 			ideal_nops = intel_nops;
 #endif
 		}
-
+		break;
 	default:
 #ifdef CONFIG_X86_64
 		ideal_nops = k8_nops;

arch/x86/kernel/cpu/mcheck/mce.c

@@ -1186,6 +1186,7 @@ void mce_notify_process(void)
 {
 	unsigned long pfn;
 	struct mce_info *mi = mce_find_info();
+	int flags = MF_ACTION_REQUIRED;
 
 	if (!mi)
 		mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL);
@@ -1200,8 +1201,9 @@ void mce_notify_process(void)
 	 * doomed. We still need to mark the page as poisoned and alert any
 	 * other users of the page.
 	 */
-	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
-			   mi->restartable == 0) {
+	if (!mi->restartable)
+		flags |= MF_MUST_KILL;
+	if (memory_failure(pfn, MCE_VECTOR, flags) < 0) {
 		pr_err("Memory error not recovered");
 		force_sig(SIGBUS, current);
 	}

arch/x86/kernel/microcode_amd.c

@@ -143,11 +143,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 				  unsigned int *current_size)
 {
 	struct microcode_header_amd *mc_hdr;
-	unsigned int actual_size;
+	unsigned int actual_size, patch_size;
 	u16 equiv_cpu_id;
 
 	/* size of the current patch we're staring at */
-	*current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+	patch_size = *(u32 *)(ucode_ptr + 4);
+	*current_size = patch_size + SECTION_HDR_SIZE;
 
 	equiv_cpu_id = find_equiv_id();
 	if (!equiv_cpu_id)
@@ -174,7 +175,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 	/*
 	 * now that the header looks sane, verify its size
 	 */
-	actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+	actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
 	if (!actual_size)
 		return 0;
 

arch/x86/kernel/microcode_core.c

@@ -298,19 +298,31 @@ static ssize_t reload_store(struct device *dev,
 			    const char *buf, size_t size)
 {
 	unsigned long val;
-	int cpu = dev->id;
-	ssize_t ret = 0;
+	int cpu;
+	ssize_t ret = 0, tmp_ret;
+
+	/* allow reload only from the BSP */
+	if (boot_cpu_data.cpu_index != dev->id)
+		return -EINVAL;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
 		return ret;
 
-	if (val == 1) {
-		get_online_cpus();
-		if (cpu_online(cpu))
-			ret = reload_for_cpu(cpu);
-		put_online_cpus();
+	if (val != 1)
+		return size;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		tmp_ret = reload_for_cpu(cpu);
+		if (tmp_ret != 0)
+			pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
+		/* save retval of the first encountered reload error */
+		if (!ret)
+			ret = tmp_ret;
 	}
+	put_online_cpus();
 
 	if (!ret)
 		ret = size;

arch/x86/kvm/emulate.c

@@ -4426,12 +4426,12 @@ twobyte_insn:
 		break;
 	case 0xb6 ... 0xb7:	/* movzx */
 		ctxt->dst.bytes = ctxt->op_bytes;
-		ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val
+		ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val
 						       : (u16) ctxt->src.val;
 		break;
 	case 0xbe ... 0xbf:	/* movsx */
 		ctxt->dst.bytes = ctxt->op_bytes;
-		ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val :
+		ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val :
 							(s16) ctxt->src.val;
 		break;
 	case 0xc0 ... 0xc1:	/* xadd */

arch/x86/kvm/i8259.c

@@ -305,6 +305,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 	addr &= 1;
 	if (addr == 0) {
 		if (val & 0x10) {
+			u8 edge_irr = s->irr & ~s->elcr;
+			int i;
+			bool found;
+			struct kvm_vcpu *vcpu;
+
 			s->init4 = val & 1;
 			s->last_irr = 0;
 			s->irr &= s->elcr;
@@ -322,6 +327,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 			if (val & 0x08)
 				pr_pic_unimpl(
 					"level sensitive irq not supported");
+
+			kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
+				if (kvm_apic_accept_pic_intr(vcpu)) {
+					found = true;
+					break;
+				}
+
+
+			if (found)
+				for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
+					if (edge_irr & (1 << irq))
+						pic_clear_isr(s, irq);
 		} else if (val & 0x08) {
 			if (val & 0x04)
 				s->poll = 1;

arch/x86/kvm/vmx.c

@@ -615,6 +615,10 @@ static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
 static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
+static void vmx_set_segment(struct kvm_vcpu *vcpu,
+			    struct kvm_segment *var, int seg);
+static void vmx_get_segment(struct kvm_vcpu *vcpu,
+			    struct kvm_segment *var, int seg);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -1470,13 +1474,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 		loadsegment(ds, vmx->host_state.ds_sel);
 		loadsegment(es, vmx->host_state.es_sel);
 	}
-#else
-	/*
-	 * The sysexit path does not restore ds/es, so we must set them to
-	 * a reasonable value ourselves.
-	 */
-	loadsegment(ds, __USER_DS);
-	loadsegment(es, __USER_DS);
 #endif
 	reload_tss();
 #ifdef CONFIG_X86_64
@@ -2770,6 +2767,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_segment var;
 
 	if (enable_unrestricted_guest)
 		return;
@@ -2813,20 +2811,23 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	if (emulate_invalid_guest_state)
 		goto continue_rmode;
 
-	vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4);
-	vmcs_write32(GUEST_SS_LIMIT, 0xffff);
-	vmcs_write32(GUEST_SS_AR_BYTES, 0xf3);
+	vmx_get_segment(vcpu, &var, VCPU_SREG_SS);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_SS);
 
-	vmcs_write32(GUEST_CS_AR_BYTES, 0xf3);
-	vmcs_write32(GUEST_CS_LIMIT, 0xffff);
-	if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000)
-		vmcs_writel(GUEST_CS_BASE, 0xf0000);
-	vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);
+	vmx_get_segment(vcpu, &var, VCPU_SREG_CS);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_CS);
 
-	fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
-	fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
-	fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
-	fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
+	vmx_get_segment(vcpu, &var, VCPU_SREG_ES);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_ES);
+
+	vmx_get_segment(vcpu, &var, VCPU_SREG_DS);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_DS);
+
+	vmx_get_segment(vcpu, &var, VCPU_SREG_GS);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_GS);
+
+	vmx_get_segment(vcpu, &var, VCPU_SREG_FS);
+	vmx_set_segment(vcpu, &var, VCPU_SREG_FS);
 
 continue_rmode:
 	kvm_mmu_reset_context(vcpu);
@@ -3229,6 +3230,44 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 
 	vmcs_write32(sf->ar_bytes, ar);
 	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+
+	/*
+	 * Fix segments for real mode guest in hosts that don't have
+	 * "unrestricted_mode" or it was disabled.
+	 * This is done to allow migration of the guests from hosts with
+	 * unrestricted guest like Westmere to older host that don't have
+	 * unrestricted guest like Nehelem.
+	 */
+	if (!enable_unrestricted_guest && vmx->rmode.vm86_active) {
+		switch (seg) {
+		case VCPU_SREG_CS:
+			vmcs_write32(GUEST_CS_AR_BYTES, 0xf3);
+			vmcs_write32(GUEST_CS_LIMIT, 0xffff);
+			if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000)
+				vmcs_writel(GUEST_CS_BASE, 0xf0000);
+			vmcs_write16(GUEST_CS_SELECTOR,
+				     vmcs_readl(GUEST_CS_BASE) >> 4);
+			break;
+		case VCPU_SREG_ES:
+			fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
+			break;
+		case VCPU_SREG_DS:
+			fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
+			break;
+		case VCPU_SREG_GS:
+			fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
+			break;
+		case VCPU_SREG_FS:
+			fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
+			break;
+		case VCPU_SREG_SS:
+			vmcs_write16(GUEST_SS_SELECTOR,
+				     vmcs_readl(GUEST_SS_BASE) >> 4);
+			vmcs_write32(GUEST_SS_LIMIT, 0xffff);
+			vmcs_write32(GUEST_SS_AR_BYTES, 0xf3);
+			break;
+		}
+	}
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -6273,6 +6312,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+#ifndef CONFIG_X86_64
+	/*
+	 * The sysexit path does not restore ds/es, so we must set them to
+	 * a reasonable value ourselves.
+	 *
+	 * We can't defer this to vmx_load_host_state() since that function
+	 * may be executed in interrupt context, which saves and restore segments
+	 * around it, nullifying its effect.
+	 */
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+#endif
+
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
 				  | (1 << VCPU_EXREG_RFLAGS)
 				  | (1 << VCPU_EXREG_CPL)

arch/x86/kvm/x86.c

@@ -907,6 +907,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	 */
 	getboottime(&boot);
 
+	if (kvm->arch.kvmclock_offset) {
+		struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
+		boot = timespec_sub(boot, ts);
+	}
 	wc.sec = boot.tv_sec;
 	wc.nsec = boot.tv_nsec;
 	wc.version = version;

arch/x86/mm/hugetlbpage.c

@@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	struct vm_area_struct *svma;
 	unsigned long saddr;
 	pte_t *spte = NULL;
+	pte_t *pte;
 
 	if (!vma_shareable(vma, addr))
-		return;
+		return (pte_t *)pmd_alloc(mm, pud, addr);
 
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
 }
 
 /*
@@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (pud_none(*pud))
-				huge_pmd_share(mm, addr, pud);
-			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));

arch/x86/syscalls/syscall_64.tbl

@@ -60,8 +60,8 @@
 51	common	getsockname		sys_getsockname
 52	common	getpeername		sys_getpeername
 53	common	socketpair		sys_socketpair
-54	common	setsockopt		sys_setsockopt
-55	common	getsockopt		sys_getsockopt
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
 56	common	clone			stub_clone
 57	common	fork			stub_fork
 58	common	vfork			stub_vfork
@@ -318,7 +318,7 @@
 309	common	getcpu			sys_getcpu
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
-312	64	kcmp			sys_kcmp
+312	common	kcmp			sys_kcmp
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -353,3 +353,5 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt

arch/x86/xen/p2m.c

@@ -194,6 +194,13 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID
  * boundary violation will require three middle nodes. */
 RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
 
+/* When we populate back during bootup, the amount of pages can vary. The
+ * max we have is seen is 395979, but that does not mean it can't be more.
+ * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
+ * it can re-use Xen provided mfn_list array, so we only need to allocate at
+ * most three P2M top nodes. */
+RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -570,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn)
 	}
 	return true;
 }
+
+/*
+ * Skim over the P2M tree looking at pages that are either filled with
+ * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
+ * replace the P2M leaf with a p2m_missing or p2m_identity.
+ * Stick the old page in the new P2M tree location.
+ */
+bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
+{
+	unsigned topidx;
+	unsigned mididx;
+	unsigned ident_pfns;
+	unsigned inv_pfns;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
+	unsigned idx;
+	unsigned long pfn;
+
+	/* We only look when this entails a P2M middle layer */
+	if (p2m_index(set_pfn))
+		return false;
+
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+		topidx = p2m_top_index(pfn);
+
+		if (!p2m_top[topidx])
+			continue;
+
+		if (p2m_top[topidx] == p2m_mid_missing)
+			continue;
+
+		mididx = p2m_mid_index(pfn);
+		p2m = p2m_top[topidx][mididx];
+		if (!p2m)
+			continue;
+
+		if ((p2m == p2m_missing) || (p2m == p2m_identity))
+			continue;
+
+		if ((unsigned long)p2m == INVALID_P2M_ENTRY)
+			continue;
+
+		ident_pfns = 0;
+		inv_pfns = 0;
+		for (idx = 0; idx < P2M_PER_PAGE; idx++) {
+			/* IDENTITY_PFNs are 1:1 */
+			if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
+				ident_pfns++;
+			else if (p2m[idx] == INVALID_P2M_ENTRY)
+				inv_pfns++;
+			else
+				break;
+		}
+		if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
+			goto found;
+	}
+	return false;
+found:
+	/* Found one, replace old with p2m_identity or p2m_missing */
+	p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
+	/* And the other for save/restore.. */
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	/* NOTE: Even if it is a p2m_identity it should still be point to
+	 * a page filled with INVALID_P2M_ENTRY entries. */
+	mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);
+
+	/* Reset where we want to stick the old page in. */
+	topidx = p2m_top_index(set_pfn);
+	mididx = p2m_mid_index(set_pfn);
+
+	/* This shouldn't happen */
+	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
+		early_alloc_p2m(set_pfn);
+
+	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
+		return false;
+
+	p2m_init(p2m);
+	p2m_top[topidx][mididx] = p2m;
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
 bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
 		if (!early_alloc_p2m(pfn))
 			return false;
 
+		if (early_can_reuse_p2m_middle(pfn, mfn))
+			return __set_phys_to_machine(pfn, mfn);
+
 		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
 			return false;
 

arch/x86/xen/setup.c

@@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	memblock_reserve(start, size);
 
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
+	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
+
+		if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+			continue;
+		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			pfn, mfn);
 
-	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
 }
 
 static unsigned long __init xen_do_chunk(unsigned long start,

block/blk-ioc.c

@@ -244,6 +244,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 
 	/* initialize */
 	atomic_long_set(&ioc->refcount, 1);
+	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
 	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);

drivers/acpi/ac.c

@@ -292,7 +292,9 @@ static int acpi_ac_add(struct acpi_device *device)
 	ac->charger.properties = ac_props;
 	ac->charger.num_properties = ARRAY_SIZE(ac_props);
 	ac->charger.get_property = get_ac_property;
-	power_supply_register(&ac->device->dev, &ac->charger);
+	result = power_supply_register(&ac->device->dev, &ac->charger);
+	if (result)
+		goto end;
 
 	printk(KERN_INFO PREFIX "%s [%s] (%s)\n",
 	       acpi_device_name(device), acpi_device_bid(device),

drivers/acpi/acpica/tbxface.c

@@ -436,6 +436,7 @@ acpi_get_table_with_size(char *signature,
 
 	return (AE_NOT_FOUND);
 }
+ACPI_EXPORT_SYMBOL(acpi_get_table_with_size)
 
 acpi_status
 acpi_get_table(char *signature,

drivers/acpi/apei/apei-base.c

@@ -586,6 +586,11 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
 	}
 	*access_bit_width = 1UL << (access_size_code + 2);
 
+	/* Fixup common BIOS bug */
+	if (bit_width == 32 && bit_offset == 0 && (*paddr & 0x03) == 0 &&
+	    *access_bit_width < 32)
+		*access_bit_width = 32;
+
 	if ((bit_width + bit_offset) > *access_bit_width) {
 		pr_warning(FW_BUG APEI_PFX
 			   "Invalid bit width + offset in GAR [0x%llx/%u/%u/%u/%u]\n",

drivers/acpi/processor_driver.c

@@ -442,7 +442,7 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb,
 		/* Normal CPU soft online event */
 		} else {
 			acpi_processor_ppc_has_changed(pr, 0);
-			acpi_processor_cst_has_changed(pr);
+			acpi_processor_hotplug(pr);
 			acpi_processor_reevaluate_tstate(pr, action);
 			acpi_processor_tstate_has_changed(pr);
 		}

drivers/base/core.c

@@ -1848,6 +1848,7 @@ int __dev_printk(const char *level, const struct device *dev,
 		 struct va_format *vaf)
 {
 	char dict[128];
+	const char *level_extra = "";
 	size_t dictlen = 0;
 	const char *subsys;
 
@@ -1894,10 +1895,14 @@ int __dev_printk(const char *level, const struct device *dev,
 				    "DEVICE=+%s:%s", subsys, dev_name(dev));
 	}
 skip:
+	if (level[3])
+		level_extra = &level[3]; /* skip past "<L>" */
+
 	return printk_emit(0, level[1] - '0',
 			   dictlen ? dict : NULL, dictlen,
-			   "%s %s: %pV",
-			   dev_driver_string(dev), dev_name(dev), vaf);
+			   "%s %s: %s%pV",
+			   dev_driver_string(dev), dev_name(dev),
+			   level_extra, vaf);
 }
 EXPORT_SYMBOL(__dev_printk);
 

drivers/base/power/main.c

@@ -989,8 +989,16 @@ static int dpm_suspend_late(pm_message_t state)
 int dpm_suspend_end(pm_message_t state)
 {
 	int error = dpm_suspend_late(state);
+	if (error)
+		return error;
 
-	return error ? : dpm_suspend_noirq(state);
+	error = dpm_suspend_noirq(state);
+	if (error) {
+		dpm_resume_early(state);
+		return error;
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(dpm_suspend_end);
 

drivers/block/cciss_scsi.c

@@ -763,16 +763,7 @@ static void complete_scsi_command(CommandList_struct *c, int timeout,
 		{
 			case CMD_TARGET_STATUS:
 				/* Pass it up to the upper layers... */
-				if( ei->ScsiStatus)
-                		{
-#if 0
-                    			printk(KERN_WARNING "cciss: cmd %p "
-						"has SCSI Status = %x\n",
-						c, ei->ScsiStatus);
-#endif
-					cmd->result |= (ei->ScsiStatus << 1);
-                		}
-				else {  /* scsi status is zero??? How??? */
+				if (!ei->ScsiStatus) {
 					
 	/* Ordinarily, this case should never happen, but there is a bug
 	   in some released firmware revisions that allows it to happen

drivers/block/virtio_blk.c

@@ -21,8 +21,6 @@ struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
-	spinlock_t lock;
-
 	struct virtio_device *vdev;
 	struct virtqueue *vq;
 
@@ -65,7 +63,7 @@ static void blk_done(struct virtqueue *vq)
 	unsigned int len;
 	unsigned long flags;
 
-	spin_lock_irqsave(&vblk->lock, flags);
+	spin_lock_irqsave(vblk->disk->queue->queue_lock, flags);
 	while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
 		int error;
 
@@ -99,7 +97,7 @@ static void blk_done(struct virtqueue *vq)
 	}
 	/* In case queue is stopped waiting for more buffers. */
 	blk_start_queue(vblk->disk->queue);
-	spin_unlock_irqrestore(&vblk->lock, flags);
+	spin_unlock_irqrestore(vblk->disk->queue->queue_lock, flags);
 }
 
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
@@ -431,7 +429,6 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		goto out_free_index;
 	}
 
-	spin_lock_init(&vblk->lock);
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 	sg_init_table(vblk->sg, vblk->sg_elems);
@@ -456,7 +453,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		goto out_mempool;
 	}
 
-	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, NULL);
 	if (!q) {
 		err = -ENOMEM;
 		goto out_put_disk;
@@ -576,30 +573,20 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 	int index = vblk->index;
-	struct virtblk_req *vbr;
-	unsigned long flags;
 
 	/* Prevent config work handler from accessing the device. */
 	mutex_lock(&vblk->config_lock);
 	vblk->config_enable = false;
 	mutex_unlock(&vblk->config_lock);
 
+	del_gendisk(vblk->disk);
+	blk_cleanup_queue(vblk->disk->queue);
+
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
 	flush_work(&vblk->config_work);
 
-	del_gendisk(vblk->disk);
-
-	/* Abort requests dispatched to driver. */
-	spin_lock_irqsave(&vblk->lock, flags);
-	while ((vbr = virtqueue_detach_unused_buf(vblk->vq))) {
-		__blk_end_request_all(vbr->req, -EIO);
-		mempool_free(vbr, vblk->pool);
-	}
-	spin_unlock_irqrestore(&vblk->lock, flags);
-
-	blk_cleanup_queue(vblk->disk->queue);
 	put_disk(vblk->disk);
 	mempool_destroy(vblk->pool);
 	vdev->config->del_vqs(vdev);

drivers/char/mspec.c

@@ -283,7 +283,7 @@ mspec_mmap(struct file *file, struct vm_area_struct *vma,
 	vdata->flags = flags;
 	vdata->type = type;
 	spin_lock_init(&vdata->lock);
-	vdata->refcnt = ATOMIC_INIT(1);
+	atomic_set(&vdata->refcnt, 1);
 	vma->vm_private_data = vdata;
 
 	vma->vm_flags |= (VM_IO | VM_RESERVED | VM_PFNMAP | VM_DONTEXPAND);

drivers/char/random.c

@@ -125,21 +125,26 @@
  * The current exported interfaces for gathering environmental noise
  * from the devices are:
  *
+ *	void add_device_randomness(const void *buf, unsigned int size);
  * 	void add_input_randomness(unsigned int type, unsigned int code,
  *                                unsigned int value);
- * 	void add_interrupt_randomness(int irq);
+ *	void add_interrupt_randomness(int irq, int irq_flags);
  * 	void add_disk_randomness(struct gendisk *disk);
  *
+ * add_device_randomness() is for adding data to the random pool that
+ * is likely to differ between two devices (or possibly even per boot).
+ * This would be things like MAC addresses or serial numbers, or the
+ * read-out of the RTC. This does *not* add any actual entropy to the
+ * pool, but it initializes the pool to different values for devices
+ * that might otherwise be identical and have very little entropy
+ * available to them (particularly common in the embedded world).
+ *
  * add_input_randomness() uses the input layer interrupt timing, as well as
  * the event type information from the hardware.
  *
- * add_interrupt_randomness() uses the inter-interrupt timing as random
- * inputs to the entropy pool.  Note that not all interrupts are good
- * sources of randomness!  For example, the timer interrupts is not a
- * good choice, because the periodicity of the interrupts is too
- * regular, and hence predictable to an attacker.  Network Interface
- * Controller interrupts are a better measure, since the timing of the
- * NIC interrupts are more unpredictable.
+ * add_interrupt_randomness() uses the interrupt timing as random
+ * inputs to the entropy pool. Using the cycle counters and the irq source
+ * as inputs, it feeds the randomness roughly once a second.
  *
  * add_disk_randomness() uses what amounts to the seek time of block
  * layer request events, on a per-disk_devt basis, as input to the
@@ -248,6 +253,8 @@
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
+#include <linux/ptrace.h>
+#include <linux/kmemcheck.h>
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 # include <linux/irq.h>
@@ -256,8 +263,12 @@
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
+#include <asm/irq_regs.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/random.h>
+
 /*
  * Configuration information
  */
@@ -266,6 +277,8 @@
 #define SEC_XFER_SIZE 512
 #define EXTRACT_SIZE 10
 
+#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long))
+
 /*
  * The minimum number of bits of entropy before we wake up a read on
  * /dev/random.  Should be enough to do a significant reseed.
@@ -420,8 +433,10 @@ struct entropy_store {
 	/* read-write data: */
 	spinlock_t lock;
 	unsigned add_ptr;
+	unsigned input_rotate;
 	int entropy_count;
-	int input_rotate;
+	int entropy_total;
+	unsigned int initialized:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
 
@@ -454,6 +469,10 @@ static struct entropy_store nonblocking_pool = {
 	.pool = nonblocking_pool_data
 };
 
+static __u32 const twist_table[8] = {
+	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
+	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
+
 /*
  * This function adds bytes into the entropy "pool".  It does not
  * update the entropy estimate.  The caller should call
@@ -464,29 +483,24 @@ static struct entropy_store nonblocking_pool = {
  * it's cheap to do so and helps slightly in the expected case where
  * the entropy is concentrated in the low-order bits.
  */
-static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
-				   int nbytes, __u8 out[64])
+static void _mix_pool_bytes(struct entropy_store *r, const void *in,
+			    int nbytes, __u8 out[64])
 {
-	static __u32 const twist_table[8] = {
-		0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
-		0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
 	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;
 	const char *bytes = in;
 	__u32 w;
-	unsigned long flags;
 
-	/* Taps are constant, so we can load them without holding r->lock.  */
 	tap1 = r->poolinfo->tap1;
 	tap2 = r->poolinfo->tap2;
 	tap3 = r->poolinfo->tap3;
 	tap4 = r->poolinfo->tap4;
 	tap5 = r->poolinfo->tap5;
 
-	spin_lock_irqsave(&r->lock, flags);
-	input_rotate = r->input_rotate;
-	i = r->add_ptr;
+	smp_rmb();
+	input_rotate = ACCESS_ONCE(r->input_rotate);
+	i = ACCESS_ONCE(r->add_ptr);
 
 	/* mix one byte at a time to simplify size handling and churn faster */
 	while (nbytes--) {
@@ -513,19 +527,61 @@ static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
 		input_rotate += i ? 7 : 14;
 	}
 
-	r->input_rotate = input_rotate;
-	r->add_ptr = i;
+	ACCESS_ONCE(r->input_rotate) = input_rotate;
+	ACCESS_ONCE(r->add_ptr) = i;
+	smp_wmb();
 
 	if (out)
 		for (j = 0; j < 16; j++)
 			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
+}
 
+static void __mix_pool_bytes(struct entropy_store *r, const void *in,
+			     int nbytes, __u8 out[64])
+{
+	trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
+	_mix_pool_bytes(r, in, nbytes, out);
+}
+
+static void mix_pool_bytes(struct entropy_store *r, const void *in,
+			   int nbytes, __u8 out[64])
+{
+	unsigned long flags;
+
+	trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
+	spin_lock_irqsave(&r->lock, flags);
+	_mix_pool_bytes(r, in, nbytes, out);
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 
-static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
+struct fast_pool {
+	__u32		pool[4];
+	unsigned long	last;
+	unsigned short	count;
+	unsigned char	rotate;
+	unsigned char	last_timer_intr;
+};
+
+/*
+ * This is a fast mixing routine used by the interrupt randomness
+ * collector.  It's hardcoded for an 128 bit pool and assumes that any
+ * locks that might be needed are taken by the caller.
+ */
+static void fast_mix(struct fast_pool *f, const void *in, int nbytes)
 {
-       mix_pool_bytes_extract(r, in, bytes, NULL);
+	const char	*bytes = in;
+	__u32		w;
+	unsigned	i = f->count;
+	unsigned	input_rotate = f->rotate;
+
+	while (nbytes--) {
+		w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^
+			f->pool[(i + 1) & 3];
+		f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7];
+		input_rotate += (i++ & 3) ? 7 : 14;
+	}
+	f->count = i;
+	f->rotate = input_rotate;
 }
 
 /*
@@ -533,30 +589,38 @@ static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
  */
 static void credit_entropy_bits(struct entropy_store *r, int nbits)
 {
-	unsigned long flags;
-	int entropy_count;
+	int entropy_count, orig;
 
 	if (!nbits)
 		return;
 
-	spin_lock_irqsave(&r->lock, flags);
-
 	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
-	entropy_count = r->entropy_count;
+retry:
+	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	entropy_count += nbits;
+
 	if (entropy_count < 0) {
 		DEBUG_ENT("negative entropy/overflow\n");
 		entropy_count = 0;
 	} else if (entropy_count > r->poolinfo->POOLBITS)
 		entropy_count = r->poolinfo->POOLBITS;
-	r->entropy_count = entropy_count;
+	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+		goto retry;
+
+	if (!r->initialized && nbits > 0) {
+		r->entropy_total += nbits;
+		if (r->entropy_total > 128)
+			r->initialized = 1;
+	}
+
+	trace_credit_entropy_bits(r->name, nbits, entropy_count,
+				  r->entropy_total, _RET_IP_);
 
 	/* should we wake readers? */
 	if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
 		wake_up_interruptible(&random_read_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 	}
-	spin_unlock_irqrestore(&r->lock, flags);
 }
 
 /*********************************************************************
@@ -572,42 +636,24 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
-#ifndef CONFIG_GENERIC_HARDIRQS
-
-static struct timer_rand_state *irq_timer_state[NR_IRQS];
-
-static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
+/*
+ * Add device- or boot-specific data to the input and nonblocking
+ * pools to help initialize them to unique values.
+ *
+ * None of this adds any entropy, it is meant to avoid the
+ * problem of the nonblocking pool having similar initial state
+ * across largely identical devices.
+ */
+void add_device_randomness(const void *buf, unsigned int size)
 {
-	return irq_timer_state[irq];
+	unsigned long time = get_cycles() ^ jiffies;
+
+	mix_pool_bytes(&input_pool, buf, size, NULL);
+	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
+	mix_pool_bytes(&nonblocking_pool, buf, size, NULL);
+	mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL);
 }
-
-static void set_timer_rand_state(unsigned int irq,
-				 struct timer_rand_state *state)
-{
-	irq_timer_state[irq] = state;
-}
-
-#else
-
-static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return desc->timer_rand_state;
-}
-
-static void set_timer_rand_state(unsigned int irq,
-				 struct timer_rand_state *state)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	desc->timer_rand_state = state;
-}
-#endif
+EXPORT_SYMBOL(add_device_randomness);
 
 static struct timer_rand_state input_timer_state;
 
@@ -637,13 +683,9 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		goto out;
 
 	sample.jiffies = jiffies;
-
-	/* Use arch random value, fall back to cycles */
-	if (!arch_get_random_int(&sample.cycles))
-		sample.cycles = get_cycles();
-
+	sample.cycles = get_cycles();
 	sample.num = num;
-	mix_pool_bytes(&input_pool, &sample, sizeof(sample));
+	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 
 	/*
 	 * Calculate number of bits of randomness we probably added.
@@ -700,17 +742,48 @@ void add_input_randomness(unsigned int type, unsigned int code,
 }
 EXPORT_SYMBOL_GPL(add_input_randomness);
 
-void add_interrupt_randomness(int irq)
+static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
+
+void add_interrupt_randomness(int irq, int irq_flags)
 {
-	struct timer_rand_state *state;
+	struct entropy_store	*r;
+	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct pt_regs		*regs = get_irq_regs();
+	unsigned long		now = jiffies;
+	__u32			input[4], cycles = get_cycles();
 
-	state = get_timer_rand_state(irq);
+	input[0] = cycles ^ jiffies;
+	input[1] = irq;
+	if (regs) {
+		__u64 ip = instruction_pointer(regs);
+		input[2] = ip;
+		input[3] = ip >> 32;
+	}
 
-	if (state == NULL)
+	fast_mix(fast_pool, input, sizeof(input));
+
+	if ((fast_pool->count & 1023) &&
+	    !time_after(now, fast_pool->last + HZ))
 		return;
 
-	DEBUG_ENT("irq event %d\n", irq);
-	add_timer_randomness(state, 0x100 + irq);
+	fast_pool->last = now;
+
+	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
+	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
+	/*
+	 * If we don't have a valid cycle counter, and we see
+	 * back-to-back timer interrupts, then skip giving credit for
+	 * any entropy.
+	 */
+	if (cycles == 0) {
+		if (irq_flags & __IRQF_TIMER) {
+			if (fast_pool->last_timer_intr)
+				return;
+			fast_pool->last_timer_intr = 1;
+		} else
+			fast_pool->last_timer_intr = 0;
+	}
+	credit_entropy_bits(r, 1);
 }
 
 #ifdef CONFIG_BLOCK
@@ -742,7 +815,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
  */
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	__u32 tmp[OUTPUT_POOL_WORDS];
+	__u32	tmp[OUTPUT_POOL_WORDS];
 
 	if (r->pull && r->entropy_count < nbytes * 8 &&
 	    r->entropy_count < r->poolinfo->POOLBITS) {
@@ -761,7 +834,7 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 
 		bytes = extract_entropy(r->pull, tmp, bytes,
 					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes);
+		mix_pool_bytes(r, tmp, bytes, NULL);
 		credit_entropy_bits(r, bytes*8);
 	}
 }
@@ -820,13 +893,19 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 static void extract_buf(struct entropy_store *r, __u8 *out)
 {
 	int i;
-	__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
+	union {
+		__u32 w[5];
+		unsigned long l[LONGS(EXTRACT_SIZE)];
+	} hash;
+	__u32 workspace[SHA_WORKSPACE_WORDS];
 	__u8 extract[64];
+	unsigned long flags;
 
 	/* Generate a hash across the pool, 16 words (512 bits) at a time */
-	sha_init(hash);
+	sha_init(hash.w);
+	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
-		sha_transform(hash, (__u8 *)(r->pool + i), workspace);
+		sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
 
 	/*
 	 * We mix the hash back into the pool to prevent backtracking
@@ -837,13 +916,14 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * brute-forcing the feedback as hard as brute-forcing the
 	 * hash.
 	 */
-	mix_pool_bytes_extract(r, hash, sizeof(hash), extract);
+	__mix_pool_bytes(r, hash.w, sizeof(hash.w), extract);
+	spin_unlock_irqrestore(&r->lock, flags);
 
 	/*
 	 * To avoid duplicates, we atomically extract a portion of the
 	 * pool while mixing, and hash one final time.
 	 */
-	sha_transform(hash, extract, workspace);
+	sha_transform(hash.w, extract, workspace);
 	memset(extract, 0, sizeof(extract));
 	memset(workspace, 0, sizeof(workspace));
 
@@ -852,20 +932,32 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * pattern, we fold it in half. Thus, we always feed back
 	 * twice as much data as we output.
 	 */
-	hash[0] ^= hash[3];
-	hash[1] ^= hash[4];
-	hash[2] ^= rol32(hash[2], 16);
-	memcpy(out, hash, EXTRACT_SIZE);
-	memset(hash, 0, sizeof(hash));
+	hash.w[0] ^= hash.w[3];
+	hash.w[1] ^= hash.w[4];
+	hash.w[2] ^= rol32(hash.w[2], 16);
+
+	/*
+	 * If we have a architectural hardware random number
+	 * generator, mix that in, too.
+	 */
+	for (i = 0; i < LONGS(EXTRACT_SIZE); i++) {
+		unsigned long v;
+		if (!arch_get_random_long(&v))
+			break;
+		hash.l[i] ^= v;
+	}
+
+	memcpy(out, &hash, EXTRACT_SIZE);
+	memset(&hash, 0, sizeof(hash));
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,
-			       size_t nbytes, int min, int reserved)
+				 size_t nbytes, int min, int reserved)
 {
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
-	unsigned long flags;
 
+	trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, min, reserved);
 
@@ -873,6 +965,8 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 		extract_buf(r, tmp);
 
 		if (fips_enabled) {
+			unsigned long flags;
+
 			spin_lock_irqsave(&r->lock, flags);
 			if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
 				panic("Hardware RNG duplicated output!\n");
@@ -898,6 +992,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
 
+	trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, 0, 0);
 
@@ -931,17 +1026,35 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 
 /*
  * This function is the exported kernel interface.  It returns some
- * number of good random numbers, suitable for seeding TCP sequence
- * numbers, etc.
+ * number of good random numbers, suitable for key generation, seeding
+ * TCP sequence numbers, etc.  It does not use the hw random number
+ * generator, if available; use get_random_bytes_arch() for that.
  */
 void get_random_bytes(void *buf, int nbytes)
+{
+	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
+}
+EXPORT_SYMBOL(get_random_bytes);
+
+/*
+ * This function will use the architecture-specific hardware random
+ * number generator if it is available.  The arch-specific hw RNG will
+ * almost certainly be faster than what we can do in software, but it
+ * is impossible to verify that it is implemented securely (as
+ * opposed, to, say, the AES encryption of a sequence number using a
+ * key known by the NSA).  So it's useful if we need the speed, but
+ * only if we're willing to trust the hardware manufacturer not to
+ * have put in a back door.
+ */
+void get_random_bytes_arch(void *buf, int nbytes)
 {
 	char *p = buf;
 
+	trace_get_random_bytes(nbytes, _RET_IP_);
 	while (nbytes) {
 		unsigned long v;
 		int chunk = min(nbytes, (int)sizeof(unsigned long));
-		
+
 		if (!arch_get_random_long(&v))
 			break;
 		
@@ -950,9 +1063,11 @@ void get_random_bytes(void *buf, int nbytes)
 		nbytes -= chunk;
 	}
 
-	extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
+	if (nbytes)
+		extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
 }
-EXPORT_SYMBOL(get_random_bytes);
+EXPORT_SYMBOL(get_random_bytes_arch);
+
 
 /*
  * init_std_data - initialize pool with system data
@@ -966,23 +1081,30 @@ EXPORT_SYMBOL(get_random_bytes);
 static void init_std_data(struct entropy_store *r)
 {
 	int i;
-	ktime_t now;
-	unsigned long flags;
+	ktime_t now = ktime_get_real();
+	unsigned long rv;
 
-	spin_lock_irqsave(&r->lock, flags);
 	r->entropy_count = 0;
-	spin_unlock_irqrestore(&r->lock, flags);
-
-	now = ktime_get_real();
-	mix_pool_bytes(r, &now, sizeof(now));
-	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof flags) {
-		if (!arch_get_random_long(&flags))
+	r->entropy_total = 0;
+	mix_pool_bytes(r, &now, sizeof(now), NULL);
+	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) {
+		if (!arch_get_random_long(&rv))
 			break;
-		mix_pool_bytes(r, &flags, sizeof(flags));
+		mix_pool_bytes(r, &rv, sizeof(rv), NULL);
 	}
-	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
+	mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL);
 }
 
+/*
+ * Note that setup_arch() may call add_device_randomness()
+ * long before we get here. This allows seeding of the pools
+ * with some platform dependent data very early in the boot
+ * process. But it limits our options here. We must use
+ * statically allocated structures that already have all
+ * initializations complete at compile time. We should also
+ * take care not to overwrite the precious per platform data
+ * we were given.
+ */
 static int rand_initialize(void)
 {
 	init_std_data(&input_pool);
@@ -992,24 +1114,6 @@ static int rand_initialize(void)
 }
 module_init(rand_initialize);
 
-void rand_initialize_irq(int irq)
-{
-	struct timer_rand_state *state;
-
-	state = get_timer_rand_state(irq);
-
-	if (state)
-		return;
-
-	/*
-	 * If kzalloc returns null, we just won't use that entropy
-	 * source.
-	 */
-	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
-	if (state)
-		set_timer_rand_state(irq, state);
-}
-
 #ifdef CONFIG_BLOCK
 void rand_initialize_disk(struct gendisk *disk)
 {
@@ -1117,7 +1221,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 		count -= bytes;
 		p += bytes;
 
-		mix_pool_bytes(r, buf, bytes);
+		mix_pool_bytes(r, buf, bytes, NULL);
 		cond_resched();
 	}
 

drivers/char/tpm/tpm.c

@@ -827,10 +827,10 @@ EXPORT_SYMBOL_GPL(tpm_pcr_extend);
 int tpm_do_selftest(struct tpm_chip *chip)
 {
 	int rc;
-	u8 digest[TPM_DIGEST_SIZE];
 	unsigned int loops;
 	unsigned int delay_msec = 1000;
 	unsigned long duration;
+	struct tpm_cmd_t cmd;
 
 	duration = tpm_calc_ordinal_duration(chip,
 	                                     TPM_ORD_CONTINUE_SELFTEST);
@@ -845,7 +845,15 @@ int tpm_do_selftest(struct tpm_chip *chip)
 		return rc;
 
 	do {
-		rc = __tpm_pcr_read(chip, 0, digest);
+		/* Attempt to read a PCR value */
+		cmd.header.in = pcrread_header;
+		cmd.params.pcrread_in.pcr_idx = cpu_to_be32(0);
+		rc = tpm_transmit(chip, (u8 *) &cmd, READ_PCR_RESULT_SIZE);
+
+		if (rc < TPM_HEADER_SIZE)
+			return -EFAULT;
+
+		rc = be32_to_cpu(cmd.header.out.return_code);
 		if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
 			dev_info(chip->dev,
 				 "TPM is disabled/deactivated (0x%X)\n", rc);

drivers/dma/imx-dma.c

@@ -172,7 +172,8 @@ struct imxdma_engine {
 	struct device_dma_parameters	dma_parms;
 	struct dma_device		dma_device;
 	void __iomem			*base;
-	struct clk			*dma_clk;
+	struct clk			*dma_ahb;
+	struct clk			*dma_ipg;
 	spinlock_t			lock;
 	struct imx_dma_2d_config	slots_2d[IMX_DMA_2D_SLOTS];
 	struct imxdma_channel		channel[IMX_DMA_CHANNELS];
@@ -976,10 +977,20 @@ static int __init imxdma_probe(struct platform_device *pdev)
 		return 0;
 	}
 
-	imxdma->dma_clk = clk_get(NULL, "dma");
-	if (IS_ERR(imxdma->dma_clk))
-		return PTR_ERR(imxdma->dma_clk);
-	clk_enable(imxdma->dma_clk);
+	imxdma->dma_ipg = devm_clk_get(&pdev->dev, "ipg");
+	if (IS_ERR(imxdma->dma_ipg)) {
+		ret = PTR_ERR(imxdma->dma_ipg);
+		goto err_clk;
+	}
+
+	imxdma->dma_ahb = devm_clk_get(&pdev->dev, "ahb");
+	if (IS_ERR(imxdma->dma_ahb)) {
+		ret = PTR_ERR(imxdma->dma_ahb);
+		goto err_clk;
+	}
+
+	clk_prepare_enable(imxdma->dma_ipg);
+	clk_prepare_enable(imxdma->dma_ahb);
 
 	/* reset DMA module */
 	imx_dmav1_writel(imxdma, DCR_DRST, DMA_DCR);
@@ -988,16 +999,14 @@ static int __init imxdma_probe(struct platform_device *pdev)
 		ret = request_irq(MX1_DMA_INT, dma_irq_handler, 0, "DMA", imxdma);
 		if (ret) {
 			dev_warn(imxdma->dev, "Can't register IRQ for DMA\n");
-			kfree(imxdma);
-			return ret;
+			goto err_enable;
 		}
 
 		ret = request_irq(MX1_DMA_ERR, imxdma_err_handler, 0, "DMA", imxdma);
 		if (ret) {
 			dev_warn(imxdma->dev, "Can't register ERRIRQ for DMA\n");
 			free_irq(MX1_DMA_INT, NULL);
-			kfree(imxdma);
-			return ret;
+			goto err_enable;
 		}
 	}
 
@@ -1094,7 +1103,10 @@ err_init:
 		free_irq(MX1_DMA_INT, NULL);
 		free_irq(MX1_DMA_ERR, NULL);
 	}
-
+err_enable:
+	clk_disable_unprepare(imxdma->dma_ipg);
+	clk_disable_unprepare(imxdma->dma_ahb);
+err_clk:
 	kfree(imxdma);
 	return ret;
 }
@@ -1114,7 +1126,9 @@ static int __exit imxdma_remove(struct platform_device *pdev)
 		free_irq(MX1_DMA_ERR, NULL);
 	}
 
-        kfree(imxdma);
+	clk_disable_unprepare(imxdma->dma_ipg);
+	clk_disable_unprepare(imxdma->dma_ahb);
+	kfree(imxdma);
 
         return 0;
 }

drivers/firmware/dmi_scan.c

@@ -6,6 +6,7 @@
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/random.h>
 #include <asm/dmi.h>
 
 /*
@@ -111,6 +112,8 @@ static int __init dmi_walk_early(void (*decode)(const struct dmi_header *,
 
 	dmi_table(buf, dmi_len, dmi_num, decode, NULL);
 
+	add_device_randomness(buf, dmi_len);
+
 	dmi_iounmap(buf, dmi_len);
 	return 0;
 }

drivers/firmware/pcdp.c

@@ -95,7 +95,7 @@ efi_setup_pcdp_console(char *cmdline)
 	if (efi.hcdp == EFI_INVALID_TABLE_ADDR)
 		return -ENODEV;
 
-	pcdp = ioremap(efi.hcdp, 4096);
+	pcdp = early_ioremap(efi.hcdp, 4096);
 	printk(KERN_INFO "PCDP: v%d at 0x%lx\n", pcdp->rev, efi.hcdp);
 
 	if (strstr(cmdline, "console=hcdp")) {
@@ -131,6 +131,6 @@ efi_setup_pcdp_console(char *cmdline)
 	}
 
 out:
-	iounmap(pcdp);
+	early_iounmap(pcdp, 4096);
 	return rc;
 }

drivers/gpu/drm/gma500/psb_intel_display.c

@@ -1362,6 +1362,9 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe,
 	    (struct drm_connector **) (psb_intel_crtc + 1);
 	psb_intel_crtc->mode_set.num_connectors = 0;
 	psb_intel_cursor_init(dev, psb_intel_crtc);
+
+	/* Set to true so that the pipe is forced off on initial config. */
+	psb_intel_crtc->active = true;
 }
 
 int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,

drivers/gpu/drm/i915/i915_sysfs.c

@@ -31,6 +31,7 @@
 #include <linux/sysfs.h>
 #include "i915_drv.h"
 
+#ifdef CONFIG_PM
 static u32 calc_residency(struct drm_device *dev, const u32 reg)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -109,3 +110,14 @@ void i915_teardown_sysfs(struct drm_device *dev)
 {
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
 }
+#else
+void i915_setup_sysfs(struct drm_device *dev)
+{
+	return;
+}
+
+void i915_teardown_sysfs(struct drm_device *dev)
+{
+	return;
+}
+#endif /* CONFIG_PM */

drivers/gpu/drm/i915/intel_display.c

@@ -3581,17 +3581,6 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			continue;
 		}
 
-		if (intel_encoder->type == INTEL_OUTPUT_EDP) {
-			/* Use VBT settings if we have an eDP panel */
-			unsigned int edp_bpc = dev_priv->edp.bpp / 3;
-
-			if (edp_bpc < display_bpc) {
-				DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
-				display_bpc = edp_bpc;
-			}
-			continue;
-		}
-
 		/* Not one of the known troublemakers, check the EDID */
 		list_for_each_entry(connector, &dev->mode_config.connector_list,
 				    head) {

drivers/gpu/drm/i915/intel_dp.c

@@ -726,8 +726,8 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode,
 	bpp = adjusted_mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 24;
 	mode_rate = intel_dp_link_required(mode->clock, bpp);
 
-	for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
-		for (clock = 0; clock <= max_clock; clock++) {
+	for (clock = 0; clock <= max_clock; clock++) {
+		for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
 			int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count);
 
 			if (mode_rate <= link_avail) {
@@ -1171,10 +1171,14 @@ static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
 
 	pp = ironlake_get_pp_control(dev_priv);
-	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	/* We need to switch off panel power _and_ force vdd, for otherwise some
+	 * panels get very unhappy and cease to work. */
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
 
+	intel_dp->want_panel_vdd = false;
+
 	ironlake_wait_panel_off(intel_dp);
 }
 
@@ -1284,11 +1288,9 @@ static void intel_dp_prepare(struct drm_encoder *encoder)
 	 * ensure that we have vdd while we switch off the panel. */
 	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
-	ironlake_edp_panel_off(intel_dp);
-
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	ironlake_edp_panel_off(intel_dp);
 	intel_dp_link_down(intel_dp);
-	ironlake_edp_panel_vdd_off(intel_dp, false);
 }
 
 static void intel_dp_commit(struct drm_encoder *encoder)
@@ -1323,11 +1325,9 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 		/* Switching the panel off requires vdd. */
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_backlight_off(intel_dp);
-		ironlake_edp_panel_off(intel_dp);
-
 		intel_dp_sink_dpms(intel_dp, mode);
+		ironlake_edp_panel_off(intel_dp);
 		intel_dp_link_down(intel_dp);
-		ironlake_edp_panel_vdd_off(intel_dp, false);
 
 		if (is_cpu_edp(intel_dp))
 			ironlake_edp_pll_off(encoder);

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -280,8 +280,6 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	I915_WRITE_HEAD(ring, 0);
 	ring->write_tail(ring, 0);
 
-	/* Initialize the ring. */
-	I915_WRITE_START(ring, obj->gtt_offset);
 	head = I915_READ_HEAD(ring) & HEAD_ADDR;
 
 	/* G45 ring initialization fails to reset head to zero */
@@ -307,6 +305,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		}
 	}
 
+	/* Initialize the ring. This must happen _after_ we've cleared the ring
+	 * registers with the above sequence (the readback of the HEAD registers
+	 * also enforces ordering), otherwise the hw might lose the new ring
+	 * register values. */
+	I915_WRITE_START(ring, obj->gtt_offset);
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);

drivers/gpu/drm/mgag200/mgag200_mode.c

@@ -468,10 +468,11 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 {
 	unsigned int vcomax, vcomin, pllreffreq;
 	unsigned int delta, tmpdelta;
-	unsigned int testr, testn, testm, testo;
+	int testr, testn, testm, testo;
 	unsigned int p, m, n;
-	unsigned int computed;
+	unsigned int computed, vco;
 	int tmp;
+	const unsigned int m_div_val[] = { 1, 2, 4, 8 };
 
 	m = n = p = 0;
 	vcomax = 1488000;
@@ -490,12 +491,13 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 				if (delta == 0)
 					break;
 				for (testo = 5; testo < 33; testo++) {
-					computed = pllreffreq * (testn + 1) /
+					vco = pllreffreq * (testn + 1) /
 						(testr + 1);
-					if (computed < vcomin)
+					if (vco < vcomin)
 						continue;
-					if (computed > vcomax)
+					if (vco > vcomax)
 						continue;
+					computed = vco / (m_div_val[testm] * (testo + 1));
 					if (computed > clock)
 						tmpdelta = computed - clock;
 					else

drivers/gpu/drm/nouveau/nouveau_drv.h

@@ -689,8 +689,6 @@ struct drm_nouveau_private {
 	void (*irq_handler[32])(struct drm_device *);
 	bool msi_enabled;
 
-	struct list_head vbl_waiting;
-
 	struct {
 		struct drm_global_reference mem_global_ref;
 		struct ttm_bo_global_ref bo_global_ref;

drivers/gpu/drm/nouveau/nouveau_irq.c

@@ -41,12 +41,8 @@
 void
 nouveau_irq_preinstall(struct drm_device *dev)
 {
-	struct drm_nouveau_private *dev_priv = dev->dev_private;
-
 	/* Master disable */
 	nv_wr32(dev, NV03_PMC_INTR_EN_0, 0);
-
-	INIT_LIST_HEAD(&dev_priv->vbl_waiting);
 }
 
 int

drivers/gpu/drm/nouveau/nouveau_software.h

@@ -38,6 +38,7 @@ static inline void
 nouveau_software_context_new(struct nouveau_software_chan *pch)
 {
 	INIT_LIST_HEAD(&pch->flip);
+	INIT_LIST_HEAD(&pch->vblank.list);
 }
 
 static inline void

drivers/gpu/drm/nouveau/nva3_copy.fuc

@@ -119,9 +119,9 @@ dispatch_dma:
 // mthd 0x030c-0x0340, various stuff
 .b16 0xc3 14
 .b32 #ctx_src_address_high           ~0x000000ff
-.b32 #ctx_src_address_low            ~0xfffffff0
+.b32 #ctx_src_address_low            ~0xffffffff
 .b32 #ctx_dst_address_high           ~0x000000ff
-.b32 #ctx_dst_address_low            ~0xfffffff0
+.b32 #ctx_dst_address_low            ~0xffffffff
 .b32 #ctx_src_pitch                  ~0x0007ffff
 .b32 #ctx_dst_pitch                  ~0x0007ffff
 .b32 #ctx_xcnt                       ~0x0000ffff

drivers/gpu/drm/nouveau/nva3_copy.fuc.h

@@ -1,37 +1,72 @@
-uint32_t nva3_pcopy_data[] = {
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
+u32 nva3_pcopy_data[] = {
+/* 0x0000: ctx_object */
+	0x00000000,
+/* 0x0004: ctx_dma */
+/* 0x0004: ctx_dma_query */
+	0x00000000,
+/* 0x0008: ctx_dma_src */
+	0x00000000,
+/* 0x000c: ctx_dma_dst */
+	0x00000000,
+/* 0x0010: ctx_query_address_high */
+	0x00000000,
+/* 0x0014: ctx_query_address_low */
+	0x00000000,
+/* 0x0018: ctx_query_counter */
+	0x00000000,
+/* 0x001c: ctx_src_address_high */
+	0x00000000,
+/* 0x0020: ctx_src_address_low */
+	0x00000000,
+/* 0x0024: ctx_src_pitch */
+	0x00000000,
+/* 0x0028: ctx_src_tile_mode */
+	0x00000000,
+/* 0x002c: ctx_src_xsize */
+	0x00000000,
+/* 0x0030: ctx_src_ysize */
+	0x00000000,
+/* 0x0034: ctx_src_zsize */
+	0x00000000,
+/* 0x0038: ctx_src_zoff */
+	0x00000000,
+/* 0x003c: ctx_src_xoff */
+	0x00000000,
+/* 0x0040: ctx_src_yoff */
+	0x00000000,
+/* 0x0044: ctx_src_cpp */
+	0x00000000,
+/* 0x0048: ctx_dst_address_high */
+	0x00000000,
+/* 0x004c: ctx_dst_address_low */
+	0x00000000,
+/* 0x0050: ctx_dst_pitch */
+	0x00000000,
+/* 0x0054: ctx_dst_tile_mode */
+	0x00000000,
+/* 0x0058: ctx_dst_xsize */
+	0x00000000,
+/* 0x005c: ctx_dst_ysize */
+	0x00000000,
+/* 0x0060: ctx_dst_zsize */
+	0x00000000,
+/* 0x0064: ctx_dst_zoff */
+	0x00000000,
+/* 0x0068: ctx_dst_xoff */
+	0x00000000,
+/* 0x006c: ctx_dst_yoff */
+	0x00000000,
+/* 0x0070: ctx_dst_cpp */
+	0x00000000,
+/* 0x0074: ctx_format */
+	0x00000000,
+/* 0x0078: ctx_swz_const0 */
+	0x00000000,
+/* 0x007c: ctx_swz_const1 */
+	0x00000000,
+/* 0x0080: ctx_xcnt */
+	0x00000000,
+/* 0x0084: ctx_ycnt */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -63,6 +98,7 @@ uint32_t nva3_pcopy_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+/* 0x0100: dispatch_table */
 	0x00010000,
 	0x00000000,
 	0x00000000,
@@ -73,6 +109,7 @@ uint32_t nva3_pcopy_data[] = {
 	0x00010162,
 	0x00000000,
 	0x00030060,
+/* 0x0128: dispatch_dma */
 	0x00010170,
 	0x00000000,
 	0x00010170,
@@ -118,11 +155,11 @@ uint32_t nva3_pcopy_data[] = {
 	0x0000001c,
 	0xffffff00,
 	0x00000020,
-	0x0000000f,
+	0x00000000,
 	0x00000048,
 	0xffffff00,
 	0x0000004c,
-	0x0000000f,
+	0x00000000,
 	0x00000024,
 	0xfff80000,
 	0x00000050,
@@ -146,7 +183,8 @@ uint32_t nva3_pcopy_data[] = {
 	0x00000800,
 };
 
-uint32_t nva3_pcopy_code[] = {
+u32 nva3_pcopy_code[] = {
+/* 0x0000: main */
 	0x04fe04bd,
 	0x3517f000,
 	0xf10010fe,
@@ -158,23 +196,31 @@ uint32_t nva3_pcopy_code[] = {
 	0x17f11031,
 	0x27f01200,
 	0x0012d003,
+/* 0x002f: spin */
 	0xf40031f4,
 	0x0ef40028,
+/* 0x0035: ih */
 	0x8001cffd,
 	0xf40812c4,
 	0x21f4060b,
+/* 0x0041: ih_no_chsw */
 	0x0412c472,
 	0xf4060bf4,
+/* 0x004a: ih_no_cmd */
 	0x11c4c321,
 	0x4001d00c,
+/* 0x0052: swctx */
 	0x47f101f8,
 	0x4bfe7700,
 	0x0007fe00,
 	0xf00204b9,
 	0x01f40643,
 	0x0604fa09,
+/* 0x006b: swctx_load */
 	0xfa060ef4,
+/* 0x006e: swctx_done */
 	0x03f80504,
+/* 0x0072: chsw */
 	0x27f100f8,
 	0x23cf1400,
 	0x1e3fc800,
@@ -183,18 +229,22 @@ uint32_t nva3_pcopy_code[] = {
 	0x1e3af052,
 	0xf00023d0,
 	0x24d00147,
+/* 0x0093: chsw_no_unload */
 	0xcf00f880,
 	0x3dc84023,
 	0x220bf41e,
 	0xf40131f4,
 	0x57f05221,
 	0x0367f004,
+/* 0x00a8: chsw_load_ctx_dma */
 	0xa07856bc,
 	0xb6018068,
 	0x87d00884,
 	0x0162b600,
+/* 0x00bb: chsw_finish_load */
 	0xf0f018f4,
 	0x23d00237,
+/* 0x00c3: dispatch */
 	0xf100f880,
 	0xcf190037,
 	0x33cf4032,
@@ -202,6 +252,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x1024b607,
 	0x010057f1,
 	0x74bd64bd,
+/* 0x00dc: dispatch_loop */
 	0x58005658,
 	0x50b60157,
 	0x0446b804,
@@ -211,6 +262,7 @@ uint32_t nva3_pcopy_code[] = {
 	0xb60276bb,
 	0x57bb0374,
 	0xdf0ef400,
+/* 0x0100: dispatch_valid_mthd */
 	0xb60246bb,
 	0x45bb0344,
 	0x01459800,
@@ -220,31 +272,41 @@ uint32_t nva3_pcopy_code[] = {
 	0xb0014658,
 	0x1bf40064,
 	0x00538009,
+/* 0x0127: dispatch_cmd */
 	0xf4300ef4,
 	0x55f90132,
 	0xf40c01f4,
+/* 0x0132: dispatch_invalid_bitfield */
 	0x25f0250e,
+/* 0x0135: dispatch_illegal_mthd */
 	0x0125f002,
+/* 0x0138: dispatch_error */
 	0x100047f1,
 	0xd00042d0,
 	0x27f04043,
 	0x0002d040,
+/* 0x0148: hostirq_wait */
 	0xf08002cf,
 	0x24b04024,
 	0xf71bf400,
+/* 0x0154: dispatch_done */
 	0x1d0027f1,
 	0xd00137f0,
 	0x00f80023,
+/* 0x0160: cmd_nop */
+/* 0x0162: cmd_pm_trigger */
 	0x27f100f8,
 	0x34bd2200,
 	0xd00233f0,
 	0x00f80023,
+/* 0x0170: cmd_dma */
 	0x012842b7,
 	0xf00145b6,
 	0x43801e39,
 	0x0040b701,
 	0x0644b606,
 	0xf80043d0,
+/* 0x0189: cmd_exec_set_format */
 	0xf030f400,
 	0xb00001b0,
 	0x01b00101,
@@ -256,20 +318,26 @@ uint32_t nva3_pcopy_code[] = {
 	0x70b63847,
 	0x0232f401,
 	0x94bd84bd,
+/* 0x01b4: ncomp_loop */
 	0xb60f4ac4,
 	0xb4bd0445,
+/* 0x01bc: bpc_loop */
 	0xf404a430,
 	0xa5ff0f18,
 	0x00cbbbc0,
 	0xf40231f4,
+/* 0x01ce: cmp_c0 */
 	0x1bf4220e,
 	0x10c7f00c,
 	0xf400cbbb,
+/* 0x01da: cmp_c1 */
 	0xa430160e,
 	0x0c18f406,
 	0xbb14c7f0,
 	0x0ef400cb,
+/* 0x01e9: cmp_zero */
 	0x80c7f107,
+/* 0x01ed: bpc_next */
 	0x01c83800,
 	0xb60180b6,
 	0xb5b801b0,
@@ -280,6 +348,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x98110680,
 	0x68fd2008,
 	0x0502f400,
+/* 0x0216: dst_xcnt */
 	0x75fd64bd,
 	0x1c078000,
 	0xf10078fd,
@@ -304,6 +373,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x980056d0,
 	0x56d01f06,
 	0x1030f440,
+/* 0x0276: cmd_exec_set_surface_tiled */
 	0x579800f8,
 	0x6879c70a,
 	0xb66478c7,
@@ -311,9 +381,11 @@ uint32_t nva3_pcopy_code[] = {
 	0x0e76b060,
 	0xf0091bf4,
 	0x0ef40477,
+/* 0x0291: xtile64 */
 	0x027cf00f,
 	0xfd1170b6,
 	0x77f00947,
+/* 0x029d: xtileok */
 	0x0f5a9806,
 	0xfd115b98,
 	0xb7f000ab,
@@ -371,6 +443,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x67d00600,
 	0x0060b700,
 	0x0068d004,
+/* 0x0382: cmd_exec_set_surface_linear */
 	0x6cf000f8,
 	0x0260b702,
 	0x0864b602,
@@ -381,13 +454,16 @@ uint32_t nva3_pcopy_code[] = {
 	0xb70067d0,
 	0x98040060,
 	0x67d00957,
+/* 0x03ab: cmd_exec_wait */
 	0xf900f800,
 	0xf110f900,
 	0xb6080007,
+/* 0x03b6: loop */
 	0x01cf0604,
 	0x0114f000,
 	0xfcfa1bf4,
 	0xf800fc10,
+/* 0x03c5: cmd_exec_query */
 	0x0d34c800,
 	0xf5701bf4,
 	0xf103ab21,
@@ -417,6 +493,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x47f10153,
 	0x44b60800,
 	0x0045d006,
+/* 0x0438: query_counter */
 	0x03ab21f5,
 	0x080c47f1,
 	0x980644b6,
@@ -439,11 +516,13 @@ uint32_t nva3_pcopy_code[] = {
 	0x47f10153,
 	0x44b60800,
 	0x0045d006,
+/* 0x0492: cmd_exec */
 	0x21f500f8,
 	0x3fc803ab,
 	0x0e0bf400,
 	0x018921f5,
 	0x020047f1,
+/* 0x04a7: cmd_exec_no_format */
 	0xf11e0ef4,
 	0xb6081067,
 	0x77f00664,
@@ -451,19 +530,24 @@ uint32_t nva3_pcopy_code[] = {
 	0x981c0780,
 	0x67d02007,
 	0x4067d000,
+/* 0x04c2: cmd_exec_init_src_surface */
 	0x32f444bd,
 	0xc854bd02,
 	0x0bf4043f,
 	0x8221f50a,
 	0x0a0ef403,
+/* 0x04d4: src_tiled */
 	0x027621f5,
+/* 0x04db: cmd_exec_init_dst_surface */
 	0xf40749f0,
 	0x57f00231,
 	0x083fc82c,
 	0xf50a0bf4,
 	0xf4038221,
+/* 0x04ee: dst_tiled */
 	0x21f50a0e,
 	0x49f00276,
+/* 0x04f5: cmd_exec_kick */
 	0x0057f108,
 	0x0654b608,
 	0xd0210698,
@@ -473,6 +557,8 @@ uint32_t nva3_pcopy_code[] = {
 	0xc80054d0,
 	0x0bf40c3f,
 	0xc521f507,
+/* 0x0519: cmd_exec_done */
+/* 0x051b: cmd_wrcache_flush */
 	0xf100f803,
 	0xbd220027,
 	0x0133f034,