Merge commit 'v2.6.37-rc3' into perf/core

Merge reason: Pick up latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

44 files changed, 116 insertions, 76 deletions

diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index cd0c090ebc5..b407bc8ad91 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/uaccess.h>
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 2b63b0191f5..efad12071c2 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 97478138e36..933bd388efb 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c
index 3a078ad3aa4..331de723c67 100644
--- a/arch/ia64/hp/sim/simscsi.c
+++ b/arch/ia64/hp/sim/simscsi.c
@@ -202,7 +202,7 @@ simscsi_readwrite10 (struct scsi_cmnd *sc, int mode)
 }
 
 static int
-simscsi_queuecommand (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
+simscsi_queuecommand_lck (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
 {
 	unsigned int target_id = sc->device->id;
 	char fname[MAX_ROOT_LEN+16];
@@ -326,6 +326,8 @@ simscsi_queuecommand (struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
 	return 0;
 }
 
+static DEF_SCSI_QCMD(simscsi_queuecommand)
+
 static int
 simscsi_host_reset (struct scsi_cmnd *sc)
 {
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 18732ab2329..c2a1fc23dd7 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -18,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c
index 6d3390590e5..e2a63af5d51 100644
--- a/arch/m68knommu/kernel/process.c
+++ b/arch/m68knommu/kernel/process.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 0d0f8049a17..e1b14a6ed54 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c
index ba430a03bc7..30394081d9b 100644
--- a/arch/parisc/hpux/sys_hpux.c
+++ b/arch/parisc/hpux/sys_hpux.c
@@ -28,7 +28,6 @@
 #include <linux/namei.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/utsname.h>
 #include <linux/vfs.h>
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index 9779ece2b07..88a0ad14a9c 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -20,7 +20,6 @@
 #include <linux/times.h>
 #include <linux/time.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b6447190e1a..e625e9e034a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -4,6 +4,10 @@ config PPC32
 	bool
 	default y if !PPC64
 
+config 32BIT
+	bool
+	default y if PPC32
+
 config 64BIT
 	bool
 	default y if PPC64
diff --git a/arch/powerpc/boot/div64.S b/arch/powerpc/boot/div64.S
index 722f360a32a..d271ab54267 100644
--- a/arch/powerpc/boot/div64.S
+++ b/arch/powerpc/boot/div64.S
@@ -33,9 +33,10 @@ __div64_32:
 	cntlzw	r0,r5		# we are shifting the dividend right
 	li	r10,-1		# to make it < 2^32, and shifting
 	srw	r10,r10,r0	# the divisor right the same amount,
-	add	r9,r4,r10	# rounding up (so the estimate cannot
+	addc	r9,r4,r10	# rounding up (so the estimate cannot
 	andc	r11,r6,r10	# ever be too large, only too small)
 	andc	r9,r9,r10
+	addze	r9,r9
 	or	r11,r5,r11
 	rotlw	r9,r9,r0
 	rotlw	r11,r11,r0
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 7a9db64f3f0..42850ee00ad 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -337,7 +337,7 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
 		/* FP registers 32 -> 63 */
 #if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE)
 		if (current)
-			memcpy(mem, current->thread.evr[regno-32],
+			memcpy(mem, &current->thread.evr[regno-32],
 					dbg_reg_def[regno].size);
 #else
 		/* fp registers not used by kernel, leave zero */
@@ -362,7 +362,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
 	if (regno >= 32 && regno < 64) {
 		/* FP registers 32 -> 63 */
 #if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE)
-		memcpy(current->thread.evr[regno-32], mem,
+		memcpy(&current->thread.evr[regno-32], mem,
 				dbg_reg_def[regno].size);
 #else
 		/* fp registers not used by kernel, leave zero */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2a178b0ebcd..ce6f61c6f87 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -497,9 +497,8 @@ static void __init emergency_stack_init(void)
 }
 
 /*
- * Called into from start_kernel, after lock_kernel has been called.
- * Initializes bootmem, which is unsed to manage page allocation until
- * mem_init is called.
+ * Called into from start_kernel this initializes bootmem, which is used
+ * to manage page allocation until mem_init is called.
  */
 void __init setup_arch(char **cmdline_p)
 {
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index b1b6043a56c..4e5bf1edc0f 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -23,7 +23,6 @@
 #include <linux/resource.h>
 #include <linux/times.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 83f534d862d..5e9584405c4 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1123,7 +1123,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 		rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
-				    subpage_protection(pgdir, ea));
+				    subpage_protection(mm, ea));
 
 	/* Dump some info in case of hash insertion failure, they should
 	 * never happen so it is really useful to know if/when they do
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 8b04c54e596..8526bd9d2aa 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -138,8 +138,11 @@
 	cmpldi	cr0,r15,0			/* Check for user region */
 	std	r14,EX_TLB_ESR(r12)		/* write crazy -1 to frame */
 	beq	normal_tlb_miss
+
+	li	r11,_PAGE_PRESENT|_PAGE_BAP_SX	/* Base perm */
+	oris	r11,r11,_PAGE_ACCESSED@h
 	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
+	mfspr	r10,SPRN_MAS1
 	cmpldi	cr0,r15,8			/* Check for vmalloc region */
 	rlwinm	r10,r10,0,16,1			/* Clear TID */
 	mtspr	SPRN_MAS1,r10
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 36c0c449a89..2a030d89bbc 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -585,6 +585,6 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
 
 	/* Finally limit subsequent allocations */
-	memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
 }
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index c667f0f02c3..3139814f643 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -47,6 +47,12 @@ config LPARCFG
 config PPC_PSERIES_DEBUG
 	depends on PPC_PSERIES && PPC_EARLY_DEBUG
 	bool "Enable extra debug logging in platforms/pseries"
+        help
+	  Say Y here if you want the pseries core to produce a bunch of
+	  debug messages to the system log. Select this if you are having a
+	  problem with the pseries core and want to see more of what is
+	  going on. This does not enable debugging in lpar.c, which must
+	  be manually done due to its verbosity.
 	default y
 
 config PPC_SMLPAR
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 34b7dc12e73..17a11c82e6f 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -21,8 +21,6 @@
  * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
  */
 
-#undef DEBUG
-
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/list.h>
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4b7a062dee1..5fcc92a12d3 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -25,8 +25,6 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#undef DEBUG
-
 #include <linux/pci.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 45e0c6199f3..05221b13ffb 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -6,6 +6,18 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
+config STRICT_DEVMEM
+	def_bool y
+	prompt "Filter access to /dev/mem"
+	---help---
+	  This option restricts access to /dev/mem.  If this option is
+	  disabled, you allow userspace access to all memory, including
+	  kernel and userspace memory. Accidental memory access is likely
+	  to be disastrous.
+	  Memory access is required for experts who want to debug the kernel.
+
+	  If you are unsure, say Y.
+
 config DEBUG_STRICT_USER_COPY_CHECKS
 	bool "Strict user copy size checks"
 	---help---
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index a8729ea7e9a..3c987e9ec8d 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -130,6 +130,11 @@ struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
 
+static inline int devmem_is_allowed(unsigned long pfn)
+{
+	return 0;
+}
+
 #define HAVE_ARCH_FREE_PAGE
 #define HAVE_ARCH_ALLOC_PAGE
 
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 1e6449c79ab..53acaa86dd9 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -25,7 +25,6 @@
 #include <linux/resource.h>
 #include <linux/times.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index d60fc439851..2564793ec2b 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -30,6 +30,7 @@
 #include <asm/sections.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/hardirq.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
@@ -212,7 +213,7 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 	/* Set the PER control regs, turns on single step for this address */
 	__ctl_load(kprobe_per_regs, 9, 11);
 	regs->psw.mask |= PSW_MASK_PER;
-	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK);
+	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 }
 
 static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
@@ -239,7 +240,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 	__get_cpu_var(current_kprobe) = p;
 	/* Save the interrupt and per flags */
 	kcb->kprobe_saved_imask = regs->psw.mask &
-	    (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK);
+		(PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT);
 	/* Save the control regs that govern PER */
 	__ctl_store(kcb->kprobe_saved_ctl, 9, 11);
 }
@@ -316,8 +317,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		return 1;
 
 ss_probe:
-	if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-		local_irq_disable();
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -350,6 +349,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	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);
@@ -372,10 +372,32 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 			/* another task is sharing our hash bucket */
 			continue;
 
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		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_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) {
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+		}
+
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address) {
@@ -387,7 +409,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 			break;
 		}
 	}
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
 	regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
 
 	reset_current_kprobe();
@@ -465,8 +487,6 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs)
 		goto out;
 	}
 	reset_current_kprobe();
-	if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-		local_irq_enable();
 out:
 	preempt_enable_no_resched();
 
@@ -482,7 +502,7 @@ out:
 	return 1;
 }
 
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -508,8 +528,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else {
 			reset_current_kprobe();
-			if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-				local_irq_enable();
 		}
 		preempt_enable_no_resched();
 		break;
@@ -553,6 +571,18 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 	return 0;
 }
 
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+	int ret;
+
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_disable();
+	ret = kprobe_trap_handler(regs, trapnr);
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+	return ret;
+}
+
 /*
  * Wrapper routine to for handling exceptions.
  */
@@ -560,8 +590,12 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				       unsigned long val, void *data)
 {
 	struct die_args *args = (struct die_args *)data;
+	struct pt_regs *regs = args->regs;
 	int ret = NOTIFY_DONE;
 
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_disable();
+
 	switch (val) {
 	case DIE_BPT:
 		if (kprobe_handler(args->regs))
@@ -572,16 +606,17 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 			ret = NOTIFY_STOP;
 		break;
 	case DIE_TRAP:
-		/* kprobe_running() needs smp_processor_id() */
-		preempt_disable();
-		if (kprobe_running() &&
-		    kprobe_fault_handler(args->regs, args->trapnr))
+		if (!preemptible() && kprobe_running() &&
+		    kprobe_trap_handler(args->regs, args->trapnr))
 			ret = NOTIFY_STOP;
-		preempt_enable();
 		break;
 	default:
 		break;
 	}
+
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+
 	return ret;
 }
 
@@ -595,6 +630,7 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 
 	/* setup return addr to the jprobe handler routine */
 	regs->psw.addr = (unsigned long)(jp->entry) | PSW_ADDR_AMODE;
+	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 
 	/* r14 is the function return address */
 	kcb->jprobe_saved_r14 = (unsigned long)regs->gprs[14];
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 38e641cdd97..45b405ca256 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -20,18 +20,17 @@
 static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	unsigned long mask, result;
+	unsigned long mask;
 	pte_t *ptep, pte;
 	struct page *page;
 
-	result = write ? 0 : _PAGE_RO;
-	mask = result | _PAGE_INVALID | _PAGE_SPECIAL;
+	mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
 
 	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
 	do {
 		pte = *ptep;
 		barrier();
-		if ((pte_val(pte) & mask) != result)
+		if ((pte_val(pte) & mask) != 0)
 			return 0;
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 7524689b03d..16582d85368 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -12,7 +12,6 @@
 #include <linux/sched.h>
 #include <linux/threads.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/init.h>
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index e6375a750d9..6db18c6927f 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -17,7 +17,6 @@
 #include <linux/resource.h>
 #include <linux/times.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index 675c9e11ada..42b282fa611 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -19,7 +19,6 @@
 #include <linux/mman.h>
 #include <linux/utsname.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/ipc.h>
 
 #include <asm/uaccess.h>
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 12b9f352595..4491f4cb269 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -16,7 +16,6 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/perf_event.h>
 
 enum direction {
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index b351770cbdd..3107381e576 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -9,7 +9,6 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index 67617a05e60..dbc213adf5e 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -21,7 +21,6 @@
 #include <linux/kdev_t.h>
 #include <linux/fs.h>
 #include <linux/fcntl.h>
-#include <linux/smp_lock.h>
 #include <linux/uaccess.h>
 #include <linux/signal.h>
 #include <asm/syscalls.h>
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index fb64b99959d..543d6a33aa2 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -15,7 +15,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 687719d4abd..757407e3669 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -16,7 +16,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 74d62d098ed..b949edcec20 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
-#include <linux/smp_lock.h>
 #include <linux/bootmem.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index 7e764669a02..e2187d24a9b 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -20,7 +20,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/mman.h>
 #include <linux/file.h>
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index f295b4ac941..dcebfc831cd 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -24,7 +24,6 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/tty.h>
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 24688b697a8..201a582c413 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -21,7 +21,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 340268be00b..09bd7b58572 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -5,7 +5,6 @@
 
 #include "linux/stddef.h"
 #include "linux/fs.h"
-#include "linux/smp_lock.h"
 #include "linux/ptrace.h"
 #include "linux/sched.h"
 #include "linux/slab.h"
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 849813f398e..5852519b2d0 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -28,7 +28,6 @@
 #include <linux/syscalls.h>
 #include <linux/times.h>
 #include <linux/utsname.h>
-#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/uio.h>
 #include <linux/poll.h>
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 1b7b31ab7d8..212a6a42527 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -33,7 +33,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index ec592caac4b..cd21b654dec 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void)
 		if (!breakinfo[i].enabled)
 			continue;
 		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
-		if (bp->attr.disabled == 1)
+		if (!bp->attr.disabled) {
+			arch_uninstall_hw_breakpoint(bp);
+			bp->attr.disabled = 1;
 			continue;
+		}
 		if (dbg_is_early)
 			early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
 						 breakinfo[i].type);
-		else
-			arch_uninstall_hw_breakpoint(bp);
-		bp->attr.disabled = 1;
+		else if (hw_break_release_slot(i))
+			printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n",
+			       breakinfo[i].addr);
+		breakinfo[i].enabled = 0;
 	}
 }
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7bf2dc4c8f7..12fcbe2c143 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -30,7 +30,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 82e144a4e51..1ca12298ffc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3395,6 +3395,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
 	load_host_msrs(vcpu);
+	kvm_load_ldt(ldt_selector);
 	loadsegment(fs, fs_selector);
 #ifdef CONFIG_X86_64
 	load_gs_index(gs_selector);
@@ -3402,7 +3403,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #else
 	loadsegment(gs, gs_selector);
 #endif
-	kvm_load_ldt(ldt_selector);
 
 	reload_tss(vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8da0e45ff7c..ff21fdda0c5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -821,10 +821,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 #endif
 
 #ifdef CONFIG_X86_64
-	if (is_long_mode(&vmx->vcpu)) {
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+	if (is_long_mode(&vmx->vcpu))
 		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-	}
 #endif
 	for (i = 0; i < vmx->save_nmsrs; ++i)
 		kvm_set_shared_msr(vmx->guest_msrs[i].index,
@@ -839,23 +838,23 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 
 	++vmx->vcpu.stat.host_state_reload;
 	vmx->host_state.loaded = 0;
-	if (vmx->host_state.fs_reload_needed)
-		loadsegment(fs, vmx->host_state.fs_sel);
+#ifdef CONFIG_X86_64
+	if (is_long_mode(&vmx->vcpu))
+		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+#endif
 	if (vmx->host_state.gs_ldt_reload_needed) {
 		kvm_load_ldt(vmx->host_state.ldt_sel);
 #ifdef CONFIG_X86_64
 		load_gs_index(vmx->host_state.gs_sel);
-		wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
 #else
 		loadsegment(gs, vmx->host_state.gs_sel);
 #endif
 	}
+	if (vmx->host_state.fs_reload_needed)
+		loadsegment(fs, vmx->host_state.fs_sel);
 	reload_tss();
 #ifdef CONFIG_X86_64
-	if (is_long_mode(&vmx->vcpu)) {
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
-	}
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
 	if (current_thread_info()->status & TS_USEDFPU)
 		clts();