Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu into core/rcu
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index ed64d22..d7884b1 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1916,9 +1916,12 @@
       <function>mutex_lock()</function>
       </para>
       <para>
-       There is a <function>mutex_trylock()</function> which can be
-       used inside interrupt context, as it will not sleep.
+       There is a <function>mutex_trylock()</function> which does not
+       sleep.  Still, it must not be used inside interrupt context since
+       its implementation is not safe for that.
        <function>mutex_unlock()</function> will also never sleep.
+       It cannot be used in interrupt context either since a mutex
+       must be released by the same task that acquired it.
       </para>
      </listitem>
     </itemizedlist>
diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg
index 1a07fd6..a7952c2 100644
--- a/Documentation/hwmon/f71882fg
+++ b/Documentation/hwmon/f71882fg
@@ -2,10 +2,6 @@
 ======================
 
 Supported chips:
-  * Fintek F71808E
-    Prefix: 'f71808fg'
-    Addresses scanned: none, address read from Super I/O config space
-    Datasheet: Not public
   * Fintek F71858FG
     Prefix: 'f71858fg'
     Addresses scanned: none, address read from Super I/O config space
diff --git a/Documentation/powerpc/hvcs.txt b/Documentation/powerpc/hvcs.txt
index f93462c..6d8be34 100644
--- a/Documentation/powerpc/hvcs.txt
+++ b/Documentation/powerpc/hvcs.txt
@@ -560,7 +560,7 @@
 distribution company that provided your OS or by posting issues to the
 PowerPC development mailing list at:
 
-linuxppc-dev@ozlabs.org
+linuxppc-dev@lists.ozlabs.org
 
 This request is to provide a documented and searchable public exchange
 of the problems and solutions surrounding this driver for the benefit of
diff --git a/MAINTAINERS b/MAINTAINERS
index b5b8baa..433f353 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -456,7 +456,7 @@
 
 AOA (Apple Onboard Audio) ALSA DRIVER
 M:	Johannes Berg <johannes@sipsolutions.net>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	sound/aoa/
@@ -1472,8 +1472,8 @@
 
 CELL BROADBAND ENGINE ARCHITECTURE
 M:	Arnd Bergmann <arnd@arndb.de>
-L:	linuxppc-dev@ozlabs.org
-L:	cbe-oss-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
+L:	cbe-oss-dev@lists.ozlabs.org
 W:	http://www.ibm.com/developerworks/power/cell/
 S:	Supported
 F:	arch/powerpc/include/asm/cell*.h
@@ -2371,13 +2371,13 @@
 FREESCALE DMA DRIVER
 M:	Li Yang <leoli@freescale.com>
 M:	Zhang Wei <zw@zh-kernel.org>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/dma/fsldma.*
 
 FREESCALE I2C CPM DRIVER
 M:	Jochen Friedrich <jochen@scram.de>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-cpm.c
@@ -2393,7 +2393,7 @@
 FREESCALE SOC FS_ENET DRIVER
 M:	Pantelis Antoniou <pantelis.antoniou@gmail.com>
 M:	Vitaly Bordug <vbordug@ru.mvista.com>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/fs_enet/
@@ -2401,7 +2401,7 @@
 
 FREESCALE QUICC ENGINE LIBRARY
 M:	Timur Tabi <timur@freescale.com>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 F:	arch/powerpc/sysdev/qe_lib/
 F:	arch/powerpc/include/asm/*qe.h
@@ -2409,27 +2409,27 @@
 FREESCALE USB PERIPHERAL DRIVERS
 M:	Li Yang <leoli@freescale.com>
 L:	linux-usb@vger.kernel.org
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/usb/gadget/fsl*
 
 FREESCALE QUICC ENGINE UCC ETHERNET DRIVER
 M:	Li Yang <leoli@freescale.com>
 L:	netdev@vger.kernel.org
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/net/ucc_geth*
 
 FREESCALE QUICC ENGINE UCC UART DRIVER
 M:	Timur Tabi <timur@freescale.com>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 F:	drivers/serial/ucc_uart.c
 
 FREESCALE SOC SOUND DRIVERS
 M:	Timur Tabi <timur@freescale.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 F:	sound/soc/fsl/fsl*
 F:	sound/soc/fsl/mpc8610_hpcd.c
@@ -2564,7 +2564,7 @@
 F:	mm/hwpoison-inject.c
 
 HYPERVISOR VIRTUAL CONSOLE DRIVER
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Odd Fixes
 F:	drivers/char/hvc_*
 
@@ -3476,7 +3476,7 @@
 
 LGUEST
 M:	Rusty Russell <rusty@rustcorp.com.au>
-L:	lguest@ozlabs.org
+L:	lguest@lists.ozlabs.org
 W:	http://lguest.ozlabs.org/
 S:	Maintained
 F:	Documentation/lguest/
@@ -3495,7 +3495,7 @@
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 M:	Paul Mackerras <paulus@samba.org>
 W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 Q:	http://patchwork.ozlabs.org/project/linuxppc-dev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
 S:	Supported
@@ -3505,14 +3505,14 @@
 LINUX FOR POWER MACINTOSH
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/platforms/powermac/
 F:	drivers/macintosh/
 
 LINUX FOR POWERPC EMBEDDED MPC5XXX
 M:	Grant Likely <grant.likely@secretlab.ca>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
 F:	arch/powerpc/platforms/512x/
@@ -3522,7 +3522,7 @@
 M:	Josh Boyer <jwboyer@linux.vnet.ibm.com>
 M:	Matt Porter <mporter@kernel.crashing.org>
 W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jwboyer/powerpc-4xx.git
 S:	Maintained
 F:	arch/powerpc/platforms/40x/
@@ -3531,7 +3531,7 @@
 LINUX FOR POWERPC EMBEDDED XILINX VIRTEX
 M:	Grant Likely <grant.likely@secretlab.ca>
 W:	http://wiki.secretlab.ca/index.php/Linux_on_Xilinx_Virtex
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
 F:	arch/powerpc/*/*virtex*
@@ -3541,20 +3541,20 @@
 M:	Vitaly Bordug <vitb@kernel.crashing.org>
 M:	Marcelo Tosatti <marcelo@kvack.org>
 W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/platforms/8xx/
 
 LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
 M:	Kumar Gala <galak@kernel.crashing.org>
 W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/platforms/83xx/
 
 LINUX FOR POWERPC PA SEMI PWRFICIENT
 M:	Olof Johansson <olof@lixom.net>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/platforms/pasemi/
 F:	drivers/*/*pasemi*
@@ -4601,14 +4601,14 @@
 PS3 NETWORK SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
 L:	netdev@vger.kernel.org
-L:	cbe-oss-dev@ozlabs.org
+L:	cbe-oss-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/net/ps3_gelic_net.*
 
 PS3 PLATFORM SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
-L:	linuxppc-dev@ozlabs.org
-L:	cbe-oss-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
+L:	cbe-oss-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/boot/ps3*
 F:	arch/powerpc/include/asm/lv1call.h
@@ -4622,7 +4622,7 @@
 
 PS3VRAM DRIVER
 M:	Jim Paris <jim@jtan.com>
-L:	cbe-oss-dev@ozlabs.org
+L:	cbe-oss-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/block/ps3vram.c
 
@@ -5068,7 +5068,7 @@
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)
 M:	Anton Vorontsov <avorontsov@ru.mvista.com>
-L:	linuxppc-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-of.*
@@ -5485,8 +5485,8 @@
 
 SPU FILE SYSTEM
 M:	Jeremy Kerr <jk@ozlabs.org>
-L:	linuxppc-dev@ozlabs.org
-L:	cbe-oss-dev@ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
+L:	cbe-oss-dev@lists.ozlabs.org
 W:	http://www.ibm.com/developerworks/power/cell/
 S:	Supported
 F:	Documentation/filesystems/spufs.txt
diff --git a/arch/arm/plat-samsung/dev-hsmmc.c b/arch/arm/plat-samsung/dev-hsmmc.c
index b0f93f1..9d2be09 100644
--- a/arch/arm/plat-samsung/dev-hsmmc.c
+++ b/arch/arm/plat-samsung/dev-hsmmc.c
@@ -70,4 +70,6 @@
 		set->cfg_gpio = pd->cfg_gpio;
 	if (pd->cfg_card)
 		set->cfg_card = pd->cfg_card;
+	if (pd->host_caps)
+		set->host_caps = pd->host_caps;
 }
diff --git a/arch/arm/plat-samsung/dev-hsmmc1.c b/arch/arm/plat-samsung/dev-hsmmc1.c
index 1504fd8..a6c8295 100644
--- a/arch/arm/plat-samsung/dev-hsmmc1.c
+++ b/arch/arm/plat-samsung/dev-hsmmc1.c
@@ -70,4 +70,6 @@
 		set->cfg_gpio = pd->cfg_gpio;
 	if (pd->cfg_card)
 		set->cfg_card = pd->cfg_card;
+	if (pd->host_caps)
+		set->host_caps = pd->host_caps;
 }
diff --git a/arch/arm/plat-samsung/dev-hsmmc2.c b/arch/arm/plat-samsung/dev-hsmmc2.c
index b28ef17..cb0d714 100644
--- a/arch/arm/plat-samsung/dev-hsmmc2.c
+++ b/arch/arm/plat-samsung/dev-hsmmc2.c
@@ -71,4 +71,6 @@
 		set->cfg_gpio = pd->cfg_gpio;
 	if (pd->cfg_card)
 		set->cfg_card = pd->cfg_card;
+	if (pd->host_caps)
+		set->host_caps = pd->host_caps;
 }
diff --git a/arch/um/include/asm/dma-mapping.h b/arch/um/include/asm/dma-mapping.h
index 17a2cb5..1f469e80 100644
--- a/arch/um/include/asm/dma-mapping.h
+++ b/arch/um/include/asm/dma-mapping.h
@@ -95,13 +95,6 @@
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
-static inline int
-dma_get_cache_alignment(void)
-{
-	BUG();
-	return(0);
-}
-
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a84fc34..cea0cd9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -245,6 +245,11 @@
 
 config KTIME_SCALAR
 	def_bool X86_32
+
+config ARCH_CPU_PROBE_RELEASE
+	def_bool y
+	depends on HOTPLUG_CPU
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 
@@ -749,11 +754,11 @@
 	def_bool (AMD_IOMMU || DMAR)
 
 config MAXSMP
-	bool "Configure Maximum number of SMP Processors and NUMA Nodes"
+	bool "Enable Maximum number of SMP Processors and NUMA Nodes"
 	depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL
 	select CPUMASK_OFFSTACK
 	---help---
-	  Configure maximum number of CPUS and NUMA Nodes for this architecture.
+	  Enable maximum number of CPUS and NUMA Nodes for this architecture.
 	  If unsure, say N.
 
 config NR_CPUS
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 2984a25..f686f49 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -26,6 +26,7 @@
 struct vm_area_struct;
 
 extern pgd_t swapper_pg_dir[1024];
+extern pgd_t trampoline_pg_dir[1024];
 
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index cb507bb..4dde797 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,14 +13,17 @@
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+extern unsigned long initial_page_table;
 extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 
 extern unsigned long setup_trampoline(void);
+extern void __init setup_trampoline_page_table(void);
 extern void __init reserve_trampoline_memory(void);
 #else
-static inline void reserve_trampoline_memory(void) {};
+static inline void setup_trampoline_page_table(void) {}
+static inline void reserve_trampoline_memory(void) {}
 #endif /* CONFIG_X86_TRAMPOLINE */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 4dc0084..f1efeba 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1728,6 +1728,8 @@
 		struct irq_pin_list *entry;
 
 		cfg = desc->chip_data;
+		if (!cfg)
+			continue;
 		entry = cfg->irq_2_pin;
 		if (!entry)
 			continue;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 60a57b1..ba5f62f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -669,7 +669,7 @@
 	}
 
 	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 8) | cpu->x86_mask;
+	ms = (cpu->x86_model << 4) | cpu->x86_mask;
 	while ((range = *erratum++))
 		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
 		    (ms >= AMD_MODEL_RANGE_START(range)) &&
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 214ac86..d8d86d0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -491,33 +491,78 @@
  *   Intel Errata AAP53  (model 30)
  *   Intel Errata BD53   (model 44)
  *
- * These chips need to be 'reset' when adding counters by programming
- * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
- * either in sequence on the same PMC or on different PMCs.
+ * The official story:
+ *   These chips need to be 'reset' when adding counters by programming the
+ *   magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either
+ *   in sequence on the same PMC or on different PMCs.
+ *
+ * In practise it appears some of these events do in fact count, and
+ * we need to programm all 4 events.
  */
+static void intel_pmu_nhm_workaround(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	static const unsigned long nhm_magic[4] = {
+		0x4300B5,
+		0x4300D2,
+		0x4300B1,
+		0x4300B1
+	};
+	struct perf_event *event;
+	int i;
+
+	/*
+	 * The Errata requires below steps:
+	 * 1) Clear MSR_IA32_PEBS_ENABLE and MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 2) Configure 4 PERFEVTSELx with the magic events and clear
+	 *    the corresponding PMCx;
+	 * 3) set bit0~bit3 of MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 4) Clear MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 5) Clear 4 pairs of ERFEVTSELx and PMCx;
+	 */
+
+	/*
+	 * The real steps we choose are a little different from above.
+	 * A) To reduce MSR operations, we don't run step 1) as they
+	 *    are already cleared before this function is called;
+	 * B) Call x86_perf_event_update to save PMCx before configuring
+	 *    PERFEVTSELx with magic number;
+	 * C) With step 5), we do clear only when the PERFEVTSELx is
+	 *    not used currently.
+	 * D) Call x86_perf_event_set_period to restore PMCx;
+	 */
+
+	/* We always operate 4 pairs of PERF Counters */
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
+		if (event)
+			x86_perf_event_update(event);
+	}
+
+	for (i = 0; i < 4; i++) {
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
+		wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
+	}
+
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
+
+		if (event) {
+			x86_perf_event_set_period(event);
+			__x86_pmu_enable_event(&event->hw,
+					ARCH_PERFMON_EVENTSEL_ENABLE);
+		} else
+			wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
+	}
+}
+
 static void intel_pmu_nhm_enable_all(int added)
 {
-	if (added) {
-		struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-		int i;
-
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
-
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
-
-		for (i = 0; i < 3; i++) {
-			struct perf_event *event = cpuc->events[i];
-
-			if (!event)
-				continue;
-
-			__x86_pmu_enable_event(&event->hw,
-					       ARCH_PERFMON_EVENTSEL_ENABLE);
-		}
-	}
+	if (added)
+		intel_pmu_nhm_workaround();
 	intel_pmu_enable_all(added);
 }
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index ff4c453..fa8c1b8 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -334,7 +334,7 @@
 /*
  * Enable paging
  */
-	movl $pa(swapper_pg_dir),%eax
+	movl pa(initial_page_table), %eax
 	movl %eax,%cr3		/* set the page table pointer.. */
 	movl %cr0,%eax
 	orl  $X86_CR0_PG,%eax
@@ -614,6 +614,8 @@
 .align 4
 ENTRY(initial_code)
 	.long i386_start_kernel
+ENTRY(initial_page_table)
+	.long pa(swapper_pg_dir)
 
 /*
  * BSS section
@@ -629,6 +631,10 @@
 #endif
 swapper_pg_fixmap:
 	.fill 1024,4,0
+#ifdef CONFIG_X86_TRAMPOLINE
+ENTRY(trampoline_pg_dir)
+	.fill 1024,4,0
+#endif
 ENTRY(empty_zero_page)
 	.fill 4096,1,0
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1bfb6cf..770ebfb 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -709,6 +709,7 @@
 	struct hlist_node *node, *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -740,15 +741,7 @@
 			/* another task is sharing our hash bucket */
 			continue;
 
-		if (ri->rp && ri->rp->handler) {
-			__get_cpu_var(current_kprobe) = &ri->rp->kp;
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
-			ri->rp->handler(ri, regs);
-			__get_cpu_var(current_kprobe) = NULL;
-		}
-
 		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -761,6 +754,32 @@
 
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (ri->rp && ri->rp->handler) {
+			__get_cpu_var(current_kprobe) = &ri->rp->kp;
+			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__get_cpu_var(current_kprobe) = NULL;
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b008e78..c3a4fbb 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1014,6 +1014,8 @@
 	paging_init();
 	x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
+	setup_trampoline_page_table();
+
 	tboot_probe();
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a5e928b..8b3bfc4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -73,7 +73,6 @@
 
 #ifdef CONFIG_X86_32
 u8 apicid_2_node[MAX_APICID];
-static int low_mappings;
 #endif
 
 /* State of each CPU */
@@ -91,6 +90,25 @@
 static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
+
+/*
+ * We need this for trampoline_base protection from concurrent accesses when
+ * off- and onlining cores wildly.
+ */
+static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
+
+void cpu_hotplug_driver_lock()
+{
+        mutex_lock(&x86_cpu_hotplug_driver_mutex);
+}
+
+void cpu_hotplug_driver_unlock()
+{
+        mutex_unlock(&x86_cpu_hotplug_driver_mutex);
+}
+
+ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
+ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
 #else
 static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
@@ -281,6 +299,18 @@
 	 * fragile that we want to limit the things done here to the
 	 * most necessary things.
 	 */
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Switch away from the trampoline page-table
+	 *
+	 * Do this before cpu_init() because it needs to access per-cpu
+	 * data which may not be mapped in the trampoline page-table.
+	 */
+	load_cr3(swapper_pg_dir);
+	__flush_tlb_all();
+#endif
+
 	vmi_bringup();
 	cpu_init();
 	preempt_disable();
@@ -299,12 +329,6 @@
 		legacy_pic->chip->unmask(0);
 	}
 
-#ifdef CONFIG_X86_32
-	while (low_mappings)
-		cpu_relax();
-	__flush_tlb_all();
-#endif
-
 	/* This must be done before setting cpu_online_mask */
 	set_cpu_sibling_map(raw_smp_processor_id());
 	wmb();
@@ -750,6 +774,7 @@
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	irq_ctx_init(cpu);
+	initial_page_table = __pa(&trampoline_pg_dir);
 #else
 	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
@@ -897,20 +922,8 @@
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
-#ifdef CONFIG_X86_32
-	/* init low mem mapping */
-	clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-		min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-	flush_tlb_all();
-	low_mappings = 1;
-
 	err = do_boot_cpu(apicid, cpu);
 
-	zap_low_mappings(false);
-	low_mappings = 0;
-#else
-	err = do_boot_cpu(apicid, cpu);
-#endif
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
 		return -EIO;
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index c652ef6..a874495 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,6 +1,7 @@
 #include <linux/io.h>
 
 #include <asm/trampoline.h>
+#include <asm/pgtable.h>
 #include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
@@ -37,3 +38,20 @@
 	memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
 	return virt_to_phys(trampoline_base);
 }
+
+void __init setup_trampoline_page_table(void)
+{
+#ifdef CONFIG_X86_32
+	/* Copy kernel address range */
+	clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+			min_t(unsigned long, KERNEL_PGD_PTRS,
+			      KERNEL_PGD_BOUNDARY));
+
+	/* Initialize low mappings */
+	clone_pgd_range(trampoline_pg_dir,
+			swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+			min_t(unsigned long, KERNEL_PGD_PTRS,
+			      KERNEL_PGD_BOUNDARY));
+#endif
+}
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 0fba829..4d4d09b 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -332,11 +332,11 @@
 	  will be called f71805f.
 
 config SENSORS_F71882FG
-	tristate "Fintek F71808E, F71858FG, F71862FG, F71882FG, F71889FG and F8000"
+	tristate "Fintek F71858FG, F71862FG, F71882FG, F71889FG and F8000"
 	depends on EXPERIMENTAL
 	help
-	  If you say yes here you get support for hardware monitoring features
-	  of the Fintek F71808E, F71858FG, F71862FG/71863FG, F71882FG/F71883FG,
+	  If you say yes here you get support for hardware monitoring
+	  features of the Fintek F71858FG, F71862FG/71863FG, F71882FG/F71883FG,
 	  F71889FG and F8000 Super-I/O chips.
 
 	  This driver can also be built as a module.  If so, the module
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index 6207120..537841e 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -45,7 +45,6 @@
 #define SIO_REG_ADDR		0x60	/* Logical device address (2 bytes) */
 
 #define SIO_FINTEK_ID		0x1934	/* Manufacturers ID */
-#define SIO_F71808_ID		0x0901  /* Chipset ID */
 #define SIO_F71858_ID		0x0507  /* Chipset ID */
 #define SIO_F71862_ID		0x0601	/* Chipset ID */
 #define SIO_F71882_ID		0x0541	/* Chipset ID */
@@ -97,10 +96,9 @@
 module_param(force_id, ushort, 0);
 MODULE_PARM_DESC(force_id, "Override the detected device ID");
 
-enum chips { f71808fg, f71858fg, f71862fg, f71882fg, f71889fg, f8000 };
+enum chips { f71858fg, f71862fg, f71882fg, f71889fg, f8000 };
 
 static const char *f71882fg_names[] = {
-	"f71808fg",
 	"f71858fg",
 	"f71862fg",
 	"f71882fg",
@@ -308,8 +306,8 @@
 	SENSOR_ATTR_2(temp3_fault, S_IRUGO, show_temp_fault, NULL, 0, 2),
 };
 
-/* In attr common to the f71862fg, f71882fg and f71889fg */
-static struct sensor_device_attribute_2 fxxxx_in_attr[] = {
+/* Temp and in attr common to the f71862fg, f71882fg and f71889fg */
+static struct sensor_device_attribute_2 fxxxx_in_temp_attr[] = {
 	SENSOR_ATTR_2(in0_input, S_IRUGO, show_in, NULL, 0, 0),
 	SENSOR_ATTR_2(in1_input, S_IRUGO, show_in, NULL, 0, 1),
 	SENSOR_ATTR_2(in2_input, S_IRUGO, show_in, NULL, 0, 2),
@@ -319,22 +317,6 @@
 	SENSOR_ATTR_2(in6_input, S_IRUGO, show_in, NULL, 0, 6),
 	SENSOR_ATTR_2(in7_input, S_IRUGO, show_in, NULL, 0, 7),
 	SENSOR_ATTR_2(in8_input, S_IRUGO, show_in, NULL, 0, 8),
-};
-
-/* In attr for the f71808fg */
-static struct sensor_device_attribute_2 f71808_in_attr[] = {
-	SENSOR_ATTR_2(in0_input, S_IRUGO, show_in, NULL, 0, 0),
-	SENSOR_ATTR_2(in1_input, S_IRUGO, show_in, NULL, 0, 1),
-	SENSOR_ATTR_2(in2_input, S_IRUGO, show_in, NULL, 0, 2),
-	SENSOR_ATTR_2(in3_input, S_IRUGO, show_in, NULL, 0, 3),
-	SENSOR_ATTR_2(in4_input, S_IRUGO, show_in, NULL, 0, 4),
-	SENSOR_ATTR_2(in5_input, S_IRUGO, show_in, NULL, 0, 5),
-	SENSOR_ATTR_2(in6_input, S_IRUGO, show_in, NULL, 0, 7),
-	SENSOR_ATTR_2(in7_input, S_IRUGO, show_in, NULL, 0, 8),
-};
-
-/* Temp attr common to the f71808fg, f71862fg, f71882fg and f71889fg */
-static struct sensor_device_attribute_2 fxxxx_temp_attr[] = {
 	SENSOR_ATTR_2(temp1_input, S_IRUGO, show_temp, NULL, 0, 1),
 	SENSOR_ATTR_2(temp1_max, S_IRUGO|S_IWUSR, show_temp_max,
 		store_temp_max, 0, 1),
@@ -373,10 +355,6 @@
 		store_temp_beep, 0, 6),
 	SENSOR_ATTR_2(temp2_type, S_IRUGO, show_temp_type, NULL, 0, 2),
 	SENSOR_ATTR_2(temp2_fault, S_IRUGO, show_temp_fault, NULL, 0, 2),
-};
-
-/* Temp and in attr common to the f71862fg, f71882fg and f71889fg */
-static struct sensor_device_attribute_2 f71862_temp_attr[] = {
 	SENSOR_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 0, 3),
 	SENSOR_ATTR_2(temp3_max, S_IRUGO|S_IWUSR, show_temp_max,
 		store_temp_max, 0, 3),
@@ -1011,11 +989,6 @@
 				data->temp_type[1] = 6;
 				break;
 			}
-		} else if (data->type == f71808fg) {
-			reg  = f71882fg_read8(data, F71882FG_REG_TEMP_TYPE);
-			data->temp_type[1] = (reg & 0x02) ? 2 : 4;
-			data->temp_type[2] = (reg & 0x04) ? 2 : 4;
-
 		} else {
 			reg2 = f71882fg_read8(data, F71882FG_REG_PECI);
 			if ((reg2 & 0x03) == 0x01)
@@ -1898,8 +1871,7 @@
 
 	val /= 1000;
 
-	if (data->type == f71889fg
-	 || data->type == f71808fg)
+	if (data->type == f71889fg)
 		val = SENSORS_LIMIT(val, -128, 127);
 	else
 		val = SENSORS_LIMIT(val, 0, 127);
@@ -2002,28 +1974,8 @@
 			/* fall through! */
 		case f71862fg:
 			err = f71882fg_create_sysfs_files(pdev,
-					f71862_temp_attr,
-					ARRAY_SIZE(f71862_temp_attr));
-			if (err)
-				goto exit_unregister_sysfs;
-			err = f71882fg_create_sysfs_files(pdev,
-					fxxxx_in_attr,
-					ARRAY_SIZE(fxxxx_in_attr));
-			if (err)
-				goto exit_unregister_sysfs;
-			err = f71882fg_create_sysfs_files(pdev,
-					fxxxx_temp_attr,
-					ARRAY_SIZE(fxxxx_temp_attr));
-			break;
-		case f71808fg:
-			err = f71882fg_create_sysfs_files(pdev,
-					f71808_in_attr,
-					ARRAY_SIZE(f71808_in_attr));
-			if (err)
-				goto exit_unregister_sysfs;
-			err = f71882fg_create_sysfs_files(pdev,
-					fxxxx_temp_attr,
-					ARRAY_SIZE(fxxxx_temp_attr));
+					fxxxx_in_temp_attr,
+					ARRAY_SIZE(fxxxx_in_temp_attr));
 			break;
 		case f8000:
 			err = f71882fg_create_sysfs_files(pdev,
@@ -2050,7 +2002,6 @@
 		case f71862fg:
 			err = (data->pwm_enable & 0x15) != 0x15;
 			break;
-		case f71808fg:
 		case f71882fg:
 		case f71889fg:
 			err = 0;
@@ -2096,7 +2047,6 @@
 					f8000_auto_pwm_attr,
 					ARRAY_SIZE(f8000_auto_pwm_attr));
 			break;
-		case f71808fg:
 		case f71889fg:
 			for (i = 0; i < nr_fans; i++) {
 				data->pwm_auto_point_mapping[i] =
@@ -2176,22 +2126,8 @@
 			/* fall through! */
 		case f71862fg:
 			f71882fg_remove_sysfs_files(pdev,
-					f71862_temp_attr,
-					ARRAY_SIZE(f71862_temp_attr));
-			f71882fg_remove_sysfs_files(pdev,
-					fxxxx_in_attr,
-					ARRAY_SIZE(fxxxx_in_attr));
-			f71882fg_remove_sysfs_files(pdev,
-					fxxxx_temp_attr,
-					ARRAY_SIZE(fxxxx_temp_attr));
-			break;
-		case f71808fg:
-			f71882fg_remove_sysfs_files(pdev,
-					f71808_in_attr,
-					ARRAY_SIZE(f71808_in_attr));
-			f71882fg_remove_sysfs_files(pdev,
-					fxxxx_temp_attr,
-					ARRAY_SIZE(fxxxx_temp_attr));
+					fxxxx_in_temp_attr,
+					ARRAY_SIZE(fxxxx_in_temp_attr));
 			break;
 		case f8000:
 			f71882fg_remove_sysfs_files(pdev,
@@ -2259,9 +2195,6 @@
 
 	devid = force_id ? force_id : superio_inw(sioaddr, SIO_REG_DEVID);
 	switch (devid) {
-	case SIO_F71808_ID:
-		sio_data->type = f71808fg;
-		break;
 	case SIO_F71858_ID:
 		sio_data->type = f71858fg;
 		break;
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 283190b..68d1279 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -132,7 +132,7 @@
 
 config MMC_SDHCI_S3C
 	tristate "SDHCI support on Samsung S3C SoC"
-	depends on MMC_SDHCI && (PLAT_S3C24XX || PLAT_S3C64XX)
+	depends on MMC_SDHCI && PLAT_SAMSUNG
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
 	  often referrered to as the HSMMC block in some of the Samsung S3C
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 0a7f261..71ad416 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -242,7 +242,7 @@
 {
 	struct sdhci_host *host = platform_get_drvdata(dev);
 	if (host) {
-		mutex_lock(&host->lock);
+		spin_lock(&host->lock);
 		if (state) {
 			dev_dbg(&dev->dev, "card inserted.\n");
 			host->flags &= ~SDHCI_DEVICE_DEAD;
@@ -252,8 +252,8 @@
 			host->flags |= SDHCI_DEVICE_DEAD;
 			host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 		}
-		sdhci_card_detect(host);
-		mutex_unlock(&host->lock);
+		tasklet_schedule(&host->card_tasklet);
+		spin_unlock(&host->lock);
 	}
 }
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 7855121..401527d 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1180,7 +1180,8 @@
 	else
 		ctrl &= ~SDHCI_CTRL_4BITBUS;
 
-	if (ios->timing == MMC_TIMING_SD_HS)
+	if (ios->timing == MMC_TIMING_SD_HS &&
+	    !(host->quirks & SDHCI_QUIRK_NO_HISPD_BIT))
 		ctrl |= SDHCI_CTRL_HISPD;
 	else
 		ctrl &= ~SDHCI_CTRL_HISPD;
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 036cfae..d316bc7 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -245,6 +245,8 @@
 #define SDHCI_QUIRK_MISSING_CAPS			(1<<27)
 /* Controller uses Auto CMD12 command to stop the transfer */
 #define SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12		(1<<28)
+/* Controller doesn't have HISPD bit field in HI-SPEED SD card */
+#define SDHCI_QUIRK_NO_HISPD_BIT			(1<<29)
 
 	int			irq;		/* Device IRQ */
 	void __iomem *		ioaddr;		/* Mapped address */
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index a3c7473..d551ddd 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2866,6 +2866,7 @@
 		 */
 		if (id_data[0] == id_data[6] && id_data[1] == id_data[7] &&
 				id_data[0] == NAND_MFR_SAMSUNG &&
+				(chip->cellinfo & NAND_CI_CELLTYPE_MSK) &&
 				id_data[5] != 0x00) {
 			/* Calc pagesize */
 			mtd->writesize = 2048 << (extid & 0x03);
@@ -2934,14 +2935,10 @@
 		chip->chip_shift = ffs((unsigned)(chip->chipsize >> 32)) + 32 - 1;
 
 	/* Set the bad block position */
-	if (!(busw & NAND_BUSWIDTH_16) && (*maf_id == NAND_MFR_STMICRO ||
-				(*maf_id == NAND_MFR_SAMSUNG &&
-				 mtd->writesize == 512) ||
-				*maf_id == NAND_MFR_AMD))
-		chip->badblockpos = NAND_SMALL_BADBLOCK_POS;
-	else
+	if (mtd->writesize > 512 || (busw & NAND_BUSWIDTH_16))
 		chip->badblockpos = NAND_LARGE_BADBLOCK_POS;
-
+	else
+		chip->badblockpos = NAND_SMALL_BADBLOCK_POS;
 
 	/* Get chip options, preserve non chip based options */
 	chip->options &= ~NAND_CHIPOPTIONS_MSK;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index e02fa4f..4d89f37 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -363,7 +363,7 @@
 #define tAR_NDTR1(r)	(((r) >> 0) & 0xf)
 
 /* convert nano-seconds to nand flash controller clock cycles */
-#define ns2cycle(ns, clk)	(int)(((ns) * (clk / 1000000) / 1000) - 1)
+#define ns2cycle(ns, clk)	(int)((ns) * (clk / 1000000) / 1000)
 
 /* convert nand flash controller clock cycles to nano-seconds */
 #define cycle2ns(c, clk)	((((c) + 1) * 1000000 + clk / 500) / (clk / 1000))
diff --git a/drivers/scsi/qla4xxx/ql4_glbl.h b/drivers/scsi/qla4xxx/ql4_glbl.h
index f065204..95a26fb 100644
--- a/drivers/scsi/qla4xxx/ql4_glbl.h
+++ b/drivers/scsi/qla4xxx/ql4_glbl.h
@@ -132,7 +132,7 @@
 int qla4_8xxx_device_state_handler(struct scsi_qla_host *ha);
 void qla4_8xxx_need_qsnt_handler(struct scsi_qla_host *ha);
 void qla4_8xxx_clear_drv_active(struct scsi_qla_host *ha);
-inline void qla4_8xxx_set_drv_active(struct scsi_qla_host *ha);
+void qla4_8xxx_set_drv_active(struct scsi_qla_host *ha);
 
 extern int ql4xextended_error_logging;
 extern int ql4xdiscoverywait;
diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c
index e031a73..5d4a382 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.c
+++ b/drivers/scsi/qla4xxx/ql4_nx.c
@@ -1418,7 +1418,7 @@
 	return QLA_SUCCESS;
 }
 
-inline void
+void
 qla4_8xxx_set_drv_active(struct scsi_qla_host *ha)
 {
 	uint32_t drv_active;
diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h
index f3a4e15..f96a471 100644
--- a/drivers/video/matrox/matroxfb_base.h
+++ b/drivers/video/matrox/matroxfb_base.h
@@ -151,13 +151,13 @@
 static inline void mga_memcpy_toio(vaddr_t va, const void* src, int len) {
 #if defined(__alpha__) || defined(__i386__) || defined(__x86_64__)
 	/*
-	 * memcpy_toio works for us if:
+	 * iowrite32_rep works for us if:
 	 *  (1) Copies data as 32bit quantities, not byte after byte,
 	 *  (2) Performs LE ordered stores, and
 	 *  (3) It copes with unaligned source (destination is guaranteed to be page
 	 *      aligned and length is guaranteed to be multiple of 4).
 	 */
-	memcpy_toio(va.vaddr, src, len);
+	iowrite32_rep(va.vaddr, src, len >> 2);
 #else
         u_int32_t __iomem* addr = va.vaddr;
 
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 311f875..4aa95f2 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -836,6 +836,8 @@
 
 extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize);
 
+extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize);
+
 extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo,
 	void *buf, unsigned int len, size_t recsize);
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 05537a5..cb57d65 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -134,7 +134,7 @@
 					   within vm_mm. */
 
 	/* linked list of VM areas per task, sorted by address */
-	struct vm_area_struct *vm_next;
+	struct vm_area_struct *vm_next, *vm_prev;
 
 	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
 	unsigned long vm_flags;		/* Flags, see mm.h. */
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
new file mode 100644
index 0000000..49682d7
--- /dev/null
+++ b/include/trace/events/workqueue.h
@@ -0,0 +1,62 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/tracepoint.h>
+#include <linux/workqueue.h>
+
+/**
+ * workqueue_execute_start - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+TRACE_EVENT(workqueue_execute_start,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+		__field( void *,	function)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+		__entry->function	= work->func;
+	),
+
+	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
+);
+
+/**
+ * workqueue_execute_end - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+TRACE_EVENT(workqueue_execute_end,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+	),
+
+	TP_printk("work struct %p", __entry->work)
+);
+
+
+#endif /*  _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 856eac3..b7e9d60 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -300,7 +300,7 @@
 #ifdef CONFIG_MMU
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	struct vm_area_struct *mpnt, *tmp, **pprev;
+	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge;
@@ -328,6 +328,7 @@
 	if (retval)
 		goto out;
 
+	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
 		struct file *file;
 
@@ -359,7 +360,7 @@
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
 		tmp->vm_mm = mm;
-		tmp->vm_next = NULL;
+		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -392,6 +393,8 @@
 		 */
 		*pprev = tmp;
 		pprev = &tmp->vm_next;
+		tmp->vm_prev = prev;
+		prev = tmp;
 
 		__vma_link_rb(mm, tmp, rb_link, rb_parent);
 		rb_link = &tmp->vm_rb.rb_right;
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 4502604..6b5580c 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -503,6 +503,15 @@
 }
 EXPORT_SYMBOL(__kfifo_out_r);
 
+void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize)
+{
+	unsigned int n;
+
+	n = __kfifo_peek_n(fifo, recsize);
+	fifo->out += n + recsize;
+}
+EXPORT_SYMBOL(__kfifo_skip_r);
+
 int __kfifo_from_user_r(struct __kfifo *fifo, const void __user *from,
 	unsigned long len, unsigned int *copied, size_t recsize)
 {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2994a0e..8bd600c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -35,6 +35,9 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #include "workqueue_sched.h"
 
 enum {
@@ -1790,7 +1793,13 @@
 	work_clear_pending(work);
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
+	trace_workqueue_execute_start(work);
 	f(work);
+	/*
+	 * While we must be careful to not use "work" after this, the trace
+	 * point will only record its address.
+	 */
+	trace_workqueue_execute_end(work);
 	lock_map_release(&lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 899fb75..0ccbcdf 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -625,6 +625,8 @@
  *
  * The function returns number of leaves where the tag was set and sets
  * *first_indexp to the first unscanned index.
+ * WARNING! *first_indexp can wrap if last_index is ULONG_MAX. Caller must
+ * be prepared to handle that.
  */
 unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
 		unsigned long *first_indexp, unsigned long last_index,
@@ -675,7 +677,8 @@
 next:
 		/* Go to next item at level determined by 'shift' */
 		index = ((index >> shift) + 1) << shift;
-		if (index > last_index)
+		/* Overflow can happen when last_index is ~0UL... */
+		if (index > last_index || !index)
 			break;
 		if (tagged >= nr_to_tag)
 			break;
diff --git a/mm/memory.c b/mm/memory.c
index b6e5fd2..2ed2267 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2770,11 +2770,18 @@
 {
 	address &= PAGE_MASK;
 	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-		address -= PAGE_SIZE;
-		if (find_vma(vma->vm_mm, address) != vma)
-			return -ENOMEM;
+		struct vm_area_struct *prev = vma->vm_prev;
 
-		expand_stack(vma, address);
+		/*
+		 * Is there a mapping abutting this one below?
+		 *
+		 * That's only ok if it's the same stack mapping
+		 * that has gotten split..
+		 */
+		if (prev && prev->vm_end == address)
+			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
+
+		expand_stack(vma, address - PAGE_SIZE);
 	}
 	return 0;
 }
diff --git a/mm/mlock.c b/mm/mlock.c
index 49e5e4c..cbae7c5 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -135,6 +135,19 @@
 	}
 }
 
+/* Is the vma a continuation of the stack vma above it? */
+static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr)
+{
+	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
+}
+
+static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	return (vma->vm_flags & VM_GROWSDOWN) &&
+		(vma->vm_start == addr) &&
+		!vma_stack_continue(vma->vm_prev, addr);
+}
+
 /**
  * __mlock_vma_pages_range() -  mlock a range of pages in the vma.
  * @vma:   target vma
@@ -168,11 +181,9 @@
 		gup_flags |= FOLL_WRITE;
 
 	/* We don't try to access the guard page of a stack vma */
-	if (vma->vm_flags & VM_GROWSDOWN) {
-		if (start == vma->vm_start) {
-			start += PAGE_SIZE;
-			nr_pages--;
-		}
+	if (stack_guard_page(vma, start)) {
+		addr += PAGE_SIZE;
+		nr_pages--;
 	}
 
 	while (nr_pages > 0) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 3100333..331e51a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -388,17 +388,23 @@
 __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent)
 {
+	struct vm_area_struct *next;
+
+	vma->vm_prev = prev;
 	if (prev) {
-		vma->vm_next = prev->vm_next;
+		next = prev->vm_next;
 		prev->vm_next = vma;
 	} else {
 		mm->mmap = vma;
 		if (rb_parent)
-			vma->vm_next = rb_entry(rb_parent,
+			next = rb_entry(rb_parent,
 					struct vm_area_struct, vm_rb);
 		else
-			vma->vm_next = NULL;
+			next = NULL;
 	}
+	vma->vm_next = next;
+	if (next)
+		next->vm_prev = vma;
 }
 
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -483,7 +489,11 @@
 __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev)
 {
-	prev->vm_next = vma->vm_next;
+	struct vm_area_struct *next = vma->vm_next;
+
+	prev->vm_next = next;
+	if (next)
+		next->vm_prev = prev;
 	rb_erase(&vma->vm_rb, &mm->mm_rb);
 	if (mm->mmap_cache == vma)
 		mm->mmap_cache = prev;
@@ -1915,6 +1925,7 @@
 	unsigned long addr;
 
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
+	vma->vm_prev = NULL;
 	do {
 		rb_erase(&vma->vm_rb, &mm->mm_rb);
 		mm->map_count--;
@@ -1922,6 +1933,8 @@
 		vma = vma->vm_next;
 	} while (vma && vma->vm_start < end);
 	*insertion_point = vma;
+	if (vma)
+		vma->vm_prev = prev;
 	tail_vma->vm_next = NULL;
 	if (mm->unmap_area == arch_unmap_area)
 		addr = prev ? prev->vm_end : mm->mmap_base;
diff --git a/mm/nommu.c b/mm/nommu.c
index efa9a38..88ff091 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -604,7 +604,7 @@
  */
 static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct *pvma, **pp;
+	struct vm_area_struct *pvma, **pp, *next;
 	struct address_space *mapping;
 	struct rb_node **p, *parent;
 
@@ -664,8 +664,11 @@
 			break;
 	}
 
-	vma->vm_next = *pp;
+	next = *pp;
 	*pp = vma;
+	vma->vm_next = next;
+	if (next)
+		next->vm_prev = vma;
 }
 
 /*
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5014e50..fc81cb2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -372,7 +372,7 @@
 		}
 
 		pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
-			task->pid, __task_cred(task)->uid, task->tgid,
+			task->pid, task_uid(task), task->tgid,
 			task->mm->total_vm, get_mm_rss(task->mm),
 			task_cpu(task), task->signal->oom_adj,
 			task->signal->oom_score_adj, task->comm);
@@ -401,10 +401,9 @@
 static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
 {
 	p = find_lock_task_mm(p);
-	if (!p) {
-		task_unlock(p);
+	if (!p)
 		return 1;
-	}
+
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
 		task_pid_nr(p), p->comm, K(p->mm->total_vm),
 		K(get_mm_counter(p->mm, MM_ANONPAGES)),
@@ -647,6 +646,7 @@
 	unsigned long freed = 0;
 	unsigned int points;
 	enum oom_constraint constraint = CONSTRAINT_NONE;
+	int killed = 0;
 
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
 	if (freed > 0)
@@ -684,7 +684,7 @@
 		if (!oom_kill_process(current, gfp_mask, order, 0, totalpages,
 				NULL, nodemask,
 				"Out of memory (oom_kill_allocating_task)"))
-			return;
+			goto out;
 	}
 
 retry:
@@ -692,7 +692,7 @@
 			constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
 								 NULL);
 	if (PTR_ERR(p) == -1UL)
-		return;
+		goto out;
 
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
@@ -704,13 +704,15 @@
 	if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
 				nodemask, "Out of memory"))
 		goto retry;
+	killed = 1;
+out:
 	read_unlock(&tasklist_lock);
 
 	/*
 	 * Give "p" a good chance of killing itself before we
 	 * retry to allocate memory unless "p" is current
 	 */
-	if (!test_thread_flag(TIF_MEMDIE))
+	if (killed && !test_thread_flag(TIF_MEMDIE))
 		schedule_timeout_uninterruptible(1);
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7262aac..c09ef52 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -836,7 +836,8 @@
 		spin_unlock_irq(&mapping->tree_lock);
 		WARN_ON_ONCE(tagged > WRITEBACK_TAG_BATCH);
 		cond_resched();
-	} while (tagged >= WRITEBACK_TAG_BATCH);
+		/* We check 'start' to handle wrapping when end == ~0UL */
+	} while (tagged >= WRITEBACK_TAG_BATCH && start);
 }
 EXPORT_SYMBOL(tag_pages_for_writeback);
 
diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c
index 642eef3..178061e 100644
--- a/samples/kfifo/bytestream-example.c
+++ b/samples/kfifo/bytestream-example.c
@@ -44,10 +44,17 @@
 static DECLARE_KFIFO(test, unsigned char, FIFO_SIZE);
 #endif
 
+static const unsigned char expected_result[FIFO_SIZE] = {
+	 3,  4,  5,  6,  7,  8,  9,  0,
+	 1, 20, 21, 22, 23, 24, 25, 26,
+	27, 28, 29, 30, 31, 32, 33, 34,
+	35, 36, 37, 38, 39, 40, 41, 42,
+};
+
 static int __init testfunc(void)
 {
 	unsigned char	buf[6];
-	unsigned char	i;
+	unsigned char	i, j;
 	unsigned int	ret;
 
 	printk(KERN_INFO "byte stream fifo test start\n");
@@ -73,16 +80,34 @@
 	ret = kfifo_in(&test, buf, ret);
 	printk(KERN_INFO "ret: %d\n", ret);
 
+	/* skip first element of the fifo */
+	printk(KERN_INFO "skip 1st element\n");
+	kfifo_skip(&test);
+
 	/* put values into the fifo until is full */
 	for (i = 20; kfifo_put(&test, &i); i++)
 		;
 
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&test));
 
-	/* print out all values in the fifo */
-	while (kfifo_get(&test, &i))
-		printk("%d ", i);
-	printk("\n");
+	/* show the first value without removing from the fifo */
+	if (kfifo_peek(&test, &i))
+		printk(KERN_INFO "%d\n", i);
+
+	/* check the correctness of all values in the fifo */
+	j = 0;
+	while (kfifo_get(&test, &i)) {
+		printk(KERN_INFO "item = %d\n", i);
+		if (i != expected_result[j++]) {
+			printk(KERN_WARNING "value mismatch: test failed\n");
+			return -EIO;
+		}
+	}
+	if (j != ARRAY_SIZE(expected_result)) {
+		printk(KERN_WARNING "size mismatch: test failed\n");
+		return -EIO;
+	}
+	printk(KERN_INFO "test passed\n");
 
 	return 0;
 }
@@ -138,7 +163,12 @@
 #else
 	INIT_KFIFO(test);
 #endif
-	testfunc();
+	if (testfunc() < 0) {
+#ifdef DYNAMIC
+		kfifo_free(&test);
+#endif
+		return -EIO;
+	}
 
 	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
 #ifdef DYNAMIC
diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c
index b9482c2..ee03a4f 100644
--- a/samples/kfifo/dma-example.c
+++ b/samples/kfifo/dma-example.c
@@ -29,8 +29,8 @@
 	printk(KERN_INFO "DMA fifo test start\n");
 
 	if (kfifo_alloc(&fifo, FIFO_SIZE, GFP_KERNEL)) {
-		printk(KERN_ERR "error kfifo_alloc\n");
-		return 1;
+		printk(KERN_WARNING "error kfifo_alloc\n");
+		return -ENOMEM;
 	}
 
 	printk(KERN_INFO "queue size: %u\n", kfifo_size(&fifo));
@@ -41,72 +41,99 @@
 		kfifo_put(&fifo, &i);
 
 	/* kick away first byte */
-	ret = kfifo_get(&fifo, &i);
+	kfifo_skip(&fifo);
 
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&fifo));
 
+	/*
+	 * Configure the kfifo buffer to receive data from DMA input.
+	 *
+	 *  .--------------------------------------.
+	 *  | 0 | 1 | 2 | ... | 12 | 13 | ... | 31 |
+	 *  |---|------------------|---------------|
+	 *   \_/ \________________/ \_____________/
+	 *    \          \                  \
+	 *     \          \_allocated data   \
+	 *      \_*free space*                \_*free space*
+	 *
+	 * We need two different SG entries: one for the free space area at the
+	 * end of the kfifo buffer (19 bytes) and another for the first free
+	 * byte at the beginning, after the kfifo_skip().
+	 */
+	sg_init_table(sg, ARRAY_SIZE(sg));
 	ret = kfifo_dma_in_prepare(&fifo, sg, ARRAY_SIZE(sg), FIFO_SIZE);
 	printk(KERN_INFO "DMA sgl entries: %d\n", ret);
-
-	/* if 0 was returned, fifo is full and no sgl was created */
-	if (ret) {
-		printk(KERN_INFO "scatterlist for receive:\n");
-		for (i = 0; i < ARRAY_SIZE(sg); i++) {
-			printk(KERN_INFO
-			"sg[%d] -> "
-			"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
-				i, sg[i].page_link, sg[i].offset, sg[i].length);
-
-			if (sg_is_last(&sg[i]))
-				break;
-		}
-
-		/* but here your code to setup and exectute the dma operation */
-		/* ... */
-
-		/* example: zero bytes received */
-		ret = 0;
-
-		/* finish the dma operation and update the received data */
-		kfifo_dma_in_finish(&fifo, ret);
+	if (!ret) {
+		/* fifo is full and no sgl was created */
+		printk(KERN_WARNING "error kfifo_dma_in_prepare\n");
+		return -EIO;
 	}
 
+	/* receive data */
+	printk(KERN_INFO "scatterlist for receive:\n");
+	for (i = 0; i < ARRAY_SIZE(sg); i++) {
+		printk(KERN_INFO
+		"sg[%d] -> "
+		"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
+			i, sg[i].page_link, sg[i].offset, sg[i].length);
+
+		if (sg_is_last(&sg[i]))
+			break;
+	}
+
+	/* put here your code to setup and exectute the dma operation */
+	/* ... */
+
+	/* example: zero bytes received */
+	ret = 0;
+
+	/* finish the dma operation and update the received data */
+	kfifo_dma_in_finish(&fifo, ret);
+
+	/* Prepare to transmit data, example: 8 bytes */
 	ret = kfifo_dma_out_prepare(&fifo, sg, ARRAY_SIZE(sg), 8);
 	printk(KERN_INFO "DMA sgl entries: %d\n", ret);
-
-	/* if 0 was returned, no data was available and no sgl was created */
-	if (ret) {
-		printk(KERN_INFO "scatterlist for transmit:\n");
-		for (i = 0; i < ARRAY_SIZE(sg); i++) {
-			printk(KERN_INFO
-			"sg[%d] -> "
-			"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
-				i, sg[i].page_link, sg[i].offset, sg[i].length);
-
-			if (sg_is_last(&sg[i]))
-				break;
-		}
-
-		/* but here your code to setup and exectute the dma operation */
-		/* ... */
-
-		/* example: 5 bytes transmitted */
-		ret = 5;
-
-		/* finish the dma operation and update the transmitted data */
-		kfifo_dma_out_finish(&fifo, ret);
+	if (!ret) {
+		/* no data was available and no sgl was created */
+		printk(KERN_WARNING "error kfifo_dma_out_prepare\n");
+		return -EIO;
 	}
 
+	printk(KERN_INFO "scatterlist for transmit:\n");
+	for (i = 0; i < ARRAY_SIZE(sg); i++) {
+		printk(KERN_INFO
+		"sg[%d] -> "
+		"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
+			i, sg[i].page_link, sg[i].offset, sg[i].length);
+
+		if (sg_is_last(&sg[i]))
+			break;
+	}
+
+	/* put here your code to setup and exectute the dma operation */
+	/* ... */
+
+	/* example: 5 bytes transmitted */
+	ret = 5;
+
+	/* finish the dma operation and update the transmitted data */
+	kfifo_dma_out_finish(&fifo, ret);
+
+	ret = kfifo_len(&fifo);
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&fifo));
 
+	if (ret != 7) {
+		printk(KERN_WARNING "size mismatch: test failed");
+		return -EIO;
+	}
+	printk(KERN_INFO "test passed\n");
+
 	return 0;
 }
 
 static void __exit example_exit(void)
 {
-#ifdef DYNAMIC
-	kfifo_free(&test);
-#endif
+	kfifo_free(&fifo);
 }
 
 module_init(example_init);
diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c
index d6c5b7d..71b2aab 100644
--- a/samples/kfifo/inttype-example.c
+++ b/samples/kfifo/inttype-example.c
@@ -44,10 +44,17 @@
 static DEFINE_KFIFO(test, int, FIFO_SIZE);
 #endif
 
+static const int expected_result[FIFO_SIZE] = {
+	 3,  4,  5,  6,  7,  8,  9,  0,
+	 1, 20, 21, 22, 23, 24, 25, 26,
+	27, 28, 29, 30, 31, 32, 33, 34,
+	35, 36, 37, 38, 39, 40, 41, 42,
+};
+
 static int __init testfunc(void)
 {
 	int		buf[6];
-	int		i;
+	int		i, j;
 	unsigned int	ret;
 
 	printk(KERN_INFO "int fifo test start\n");
@@ -66,8 +73,13 @@
 	ret = kfifo_in(&test, buf, ret);
 	printk(KERN_INFO "ret: %d\n", ret);
 
-	for (i = 20; i != 30; i++)
-		kfifo_put(&test, &i);
+	/* skip first element of the fifo */
+	printk(KERN_INFO "skip 1st element\n");
+	kfifo_skip(&test);
+
+	/* put values into the fifo until is full */
+	for (i = 20; kfifo_put(&test, &i); i++)
+		;
 
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&test));
 
@@ -75,10 +87,20 @@
 	if (kfifo_peek(&test, &i))
 		printk(KERN_INFO "%d\n", i);
 
-	/* print out all values in the fifo */
-	while (kfifo_get(&test, &i))
-		printk("%d ", i);
-	printk("\n");
+	/* check the correctness of all values in the fifo */
+	j = 0;
+	while (kfifo_get(&test, &i)) {
+		printk(KERN_INFO "item = %d\n", i);
+		if (i != expected_result[j++]) {
+			printk(KERN_WARNING "value mismatch: test failed\n");
+			return -EIO;
+		}
+	}
+	if (j != ARRAY_SIZE(expected_result)) {
+		printk(KERN_WARNING "size mismatch: test failed\n");
+		return -EIO;
+	}
+	printk(KERN_INFO "test passed\n");
 
 	return 0;
 }
@@ -132,7 +154,12 @@
 		return ret;
 	}
 #endif
-	testfunc();
+	if (testfunc() < 0) {
+#ifdef DYNAMIC
+		kfifo_free(&test);
+#endif
+		return -EIO;
+	}
 
 	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
 #ifdef DYNAMIC
diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c
index 32c6e0b..e68bd16 100644
--- a/samples/kfifo/record-example.c
+++ b/samples/kfifo/record-example.c
@@ -55,6 +55,19 @@
 static mytest test;
 #endif
 
+static const char *expected_result[] = {
+	"a",
+	"bb",
+	"ccc",
+	"dddd",
+	"eeeee",
+	"ffffff",
+	"ggggggg",
+	"hhhhhhhh",
+	"iiiiiiiii",
+	"jjjjjjjjjj",
+};
+
 static int __init testfunc(void)
 {
 	char		buf[100];
@@ -75,6 +88,10 @@
 		kfifo_in(&test, buf, i + 1);
 	}
 
+	/* skip first element of the fifo */
+	printk(KERN_INFO "skip 1st element\n");
+	kfifo_skip(&test);
+
 	printk(KERN_INFO "fifo len: %u\n", kfifo_len(&test));
 
 	/* show the first record without removing from the fifo */
@@ -82,11 +99,22 @@
 	if (ret)
 		printk(KERN_INFO "%.*s\n", ret, buf);
 
-	/* print out all records in the fifo */
+	/* check the correctness of all values in the fifo */
+	i = 0;
 	while (!kfifo_is_empty(&test)) {
 		ret = kfifo_out(&test, buf, sizeof(buf));
-		printk(KERN_INFO "%.*s\n", ret, buf);
+		buf[ret] = '\0';
+		printk(KERN_INFO "item = %.*s\n", ret, buf);
+		if (strcmp(buf, expected_result[i++])) {
+			printk(KERN_WARNING "value mismatch: test failed\n");
+			return -EIO;
+		}
 	}
+	if (i != ARRAY_SIZE(expected_result)) {
+		printk(KERN_WARNING "size mismatch: test failed\n");
+		return -EIO;
+	}
+	printk(KERN_INFO "test passed\n");
 
 	return 0;
 }
@@ -142,7 +170,12 @@
 #else
 	INIT_KFIFO(test);
 #endif
-	testfunc();
+	if (testfunc() < 0) {
+#ifdef DYNAMIC
+		kfifo_free(&test);
+#endif
+		return -EIO;
+	}
 
 	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
 #ifdef DYNAMIC
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcb9700..4f1fa77 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -5,6 +5,12 @@
 # The default target of this Makefile is...
 all::
 
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
+
 # Define V=1 to have a more verbose compile.
 # Define V=2 to have an even more verbose compile.
 #
@@ -931,15 +937,15 @@
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-	$(QUIET_GEN)$(RM) $@ $@+ && \
+	$(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
 	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
 	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
 	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
 	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
 	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-	    $@.sh >$@+ && \
-	chmod +x $@+ && \
-	mv $@+ $(OUTPUT)$@
+	    $@.sh > $(OUTPUT)$@+ && \
+	chmod +x $(OUTPUT)$@+ && \
+	mv $(OUTPUT)$@+ $(OUTPUT)$@
 
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index ddb68e6..7a7b608 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -113,7 +113,7 @@
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options)
 try-cc = $(shell sh -c						  \
-	'TMP="$(TMPOUT).$$$$";			 		  \
+	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
 	 echo "$(1)" |						  \
 	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
 	 rm -f "$$TMP"')