Merge branch 'fixes' into for-linus

42 files changed, 508 insertions, 292 deletions

diff --git a/Makefile b/Makefile
index a3c11d589681..bb9fff26f078 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Terrified Chipmunk
 
 # *DOCUMENTATION*
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 47486a41c56e..9fdded6b1089 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -8,6 +8,7 @@
 #define _ASM_ARM_SYSCALL_H
 
 #include <linux/err.h>
+#include <linux/sched.h>
 
 #include <asm/unistd.h>
 
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 69f1c57a8d0d..33a6a2423bd2 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -20,14 +20,6 @@ struct mm_struct;
 
 struct thread_struct {
 	struct task_struct *saved_task;
-	/*
-	 * This flag is set to 1 before calling do_fork (and analyzed in
-	 * copy_thread) to mark that we are begin called from userspace (fork /
-	 * vfork / clone), and reset to 0 after. It is left to 0 when called
-	 * from kernelspace (i.e. kernel_thread() or fork_idle(),
-	 * as of 2.6.11).
-	 */
-	int forking;
 	struct pt_regs regs;
 	int singlestep_syscall;
 	void *fault_addr;
@@ -58,7 +50,6 @@ struct thread_struct {
 
 #define INIT_THREAD \
 { \
-	.forking		= 0, \
 	.regs		   	= EMPTY_REGS,	\
 	.fault_addr		= NULL, \
 	.prev_sched		= NULL, \
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index 40db8f71deae..2df313b6a586 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -7,16 +7,6 @@ DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK);
 DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT);
 DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
 
-DEFINE_STR(UM_KERN_EMERG, KERN_EMERG);
-DEFINE_STR(UM_KERN_ALERT, KERN_ALERT);
-DEFINE_STR(UM_KERN_CRIT, KERN_CRIT);
-DEFINE_STR(UM_KERN_ERR, KERN_ERR);
-DEFINE_STR(UM_KERN_WARNING, KERN_WARNING);
-DEFINE_STR(UM_KERN_NOTICE, KERN_NOTICE);
-DEFINE_STR(UM_KERN_INFO, KERN_INFO);
-DEFINE_STR(UM_KERN_DEBUG, KERN_DEBUG);
-DEFINE_STR(UM_KERN_CONT, KERN_CONT);
-
 DEFINE(UM_ELF_CLASS, ELF_CLASS);
 DEFINE(UM_ELFCLASS32, ELFCLASS32);
 DEFINE(UM_ELFCLASS64, ELFCLASS64);
diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h
index 4fa82c055aab..cef068563336 100644
--- a/arch/um/include/shared/user.h
+++ b/arch/um/include/shared/user.h
@@ -26,6 +26,17 @@
 extern void panic(const char *fmt, ...)
 	__attribute__ ((format (printf, 1, 2)));
 
+/* Requires preincluding include/linux/kern_levels.h */
+#define UM_KERN_EMERG	KERN_EMERG
+#define UM_KERN_ALERT	KERN_ALERT
+#define UM_KERN_CRIT	KERN_CRIT
+#define UM_KERN_ERR	KERN_ERR
+#define UM_KERN_WARNING	KERN_WARNING
+#define UM_KERN_NOTICE	KERN_NOTICE
+#define UM_KERN_INFO	KERN_INFO
+#define UM_KERN_DEBUG	KERN_DEBUG
+#define UM_KERN_CONT	KERN_CONT
+
 #ifdef UML_CONFIG_PRINTK
 extern int printk(const char *fmt, ...)
 	__attribute__ ((format (printf, 1, 2)));
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 6cade9366364..8c82786da823 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -39,34 +39,21 @@ void flush_thread(void)
 
 void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
 {
+	get_safe_registers(regs->regs.gp, regs->regs.fp);
 	PT_REGS_IP(regs) = eip;
 	PT_REGS_SP(regs) = esp;
-}
-EXPORT_SYMBOL(start_thread);
-
-static long execve1(const char *file,
-		    const char __user *const __user *argv,
-		    const char __user *const __user *env)
-{
-	long error;
-
-	error = do_execve(file, argv, env, &current->thread.regs);
-	if (error == 0) {
-		task_lock(current);
-		current->ptrace &= ~PT_DTRACE;
+	current->ptrace &= ~PT_DTRACE;
 #ifdef SUBARCH_EXECVE1
-		SUBARCH_EXECVE1(&current->thread.regs.regs);
+	SUBARCH_EXECVE1(regs->regs);
 #endif
-		task_unlock(current);
-	}
-	return error;
 }
+EXPORT_SYMBOL(start_thread);
 
 long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env)
 {
 	long err;
 
-	err = execve1(file, argv, env);
+	err = do_execve(file, argv, env, &current->thread.regs);
 	if (!err)
 		UML_LONGJMP(current->thread.exec_buf, 1);
 	return err;
@@ -81,7 +68,7 @@ long sys_execve(const char __user *file, const char __user *const __user *argv,
 	filename = getname(file);
 	error = PTR_ERR(filename);
 	if (IS_ERR(filename)) goto out;
-	error = execve1(filename, argv, env);
+	error = do_execve(filename, argv, env, &current->thread.regs);
 	putname(filename);
  out:
 	return error;
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 57fc7028714a..c5f5afa50745 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -181,11 +181,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		struct pt_regs *regs)
 {
 	void (*handler)(void);
+	int kthread = current->flags & PF_KTHREAD;
 	int ret = 0;
 
 	p->thread = (struct thread_struct) INIT_THREAD;
 
-	if (current->thread.forking) {
+	if (!kthread) {
 	  	memcpy(&p->thread.regs.regs, &regs->regs,
 		       sizeof(p->thread.regs.regs));
 		PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0);
@@ -195,8 +196,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		handler = fork_handler;
 
 		arch_copy_thread(&current->thread.arch, &p->thread.arch);
-	}
-	else {
+	} else {
 		get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp);
 		p->thread.request.u.thread = current->thread.request.u.thread;
 		handler = new_thread_handler;
@@ -204,7 +204,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	new_thread(task_stack_page(p), &p->thread.switch_buf, handler);
 
-	if (current->thread.forking) {
+	if (!kthread) {
 		clear_flushed_tls(p);
 
 		/*
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 7362d58efc29..cc9c2350e417 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -22,9 +22,13 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr,
 			 struct k_sigaction *ka, siginfo_t *info)
 {
 	sigset_t *oldset = sigmask_to_save();
+	int singlestep = 0;
 	unsigned long sp;
 	int err;
 
+	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
+		singlestep = 1;
+
 	/* Did we come from a system call? */
 	if (PT_REGS_SYSCALL_NR(regs) >= 0) {
 		/* If so, check system call restarting.. */
@@ -61,7 +65,7 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr,
 	if (err)
 		force_sigsegv(signr, current);
 	else
-		signal_delivered(signr, info, ka, regs, 0);
+		signal_delivered(signr, info, ka, regs, singlestep);
 }
 
 static int kern_do_signal(struct pt_regs *regs)
diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c
index f958cb876ee3..a4c6d8eee74c 100644
--- a/arch/um/kernel/syscall.c
+++ b/arch/um/kernel/syscall.c
@@ -17,25 +17,25 @@
 
 long sys_fork(void)
 {
-	long ret;
-
-	current->thread.forking = 1;
-	ret = do_fork(SIGCHLD, UPT_SP(&current->thread.regs.regs),
+	return do_fork(SIGCHLD, UPT_SP(&current->thread.regs.regs),
 		      &current->thread.regs, 0, NULL, NULL);
-	current->thread.forking = 0;
-	return ret;
 }
 
 long sys_vfork(void)
 {
-	long ret;
-
-	current->thread.forking = 1;
-	ret = do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD,
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD,
 		      UPT_SP(&current->thread.regs.regs),
 		      &current->thread.regs, 0, NULL, NULL);
-	current->thread.forking = 0;
-	return ret;
+}
+
+long sys_clone(unsigned long clone_flags, unsigned long newsp,
+	       void __user *parent_tid, void __user *child_tid)
+{
+	if (!newsp)
+		newsp = UPT_SP(&current->thread.regs.regs);
+
+	return do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
+		      child_tid);
 }
 
 long old_mmap(unsigned long addr, unsigned long len,
diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules
index d50270d26b42..15889df9b466 100644
--- a/arch/um/scripts/Makefile.rules
+++ b/arch/um/scripts/Makefile.rules
@@ -8,7 +8,7 @@ USER_OBJS += $(filter %_user.o,$(obj-y) $(obj-m)  $(USER_SINGLE_OBJS))
 USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file))
 
 $(USER_OBJS:.o=.%): \
-	c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o)
+	c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include $(srctree)/include/linux/kern_levels.h -include user.h $(CFLAGS_$(basetarget).o)
 
 # These are like USER_OBJS but filter USER_CFLAGS through unprofile instead of
 # using it directly.
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 9926e11a772d..aeaff8bef2f1 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -21,6 +21,7 @@ config 64BIT
 config X86_32
 	def_bool !64BIT
 	select HAVE_AOUT
+	select ARCH_WANT_IPC_PARSE_VERSION
 
 config X86_64
 	def_bool 64BIT
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 5868526b5eef..46a9df99f3c5 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -7,9 +7,6 @@
 #define DEFINE(sym, val) \
 	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
 
-#define STR(x) #x
-#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " STR(val) " " #val: : )
-
 #define BLANK() asm volatile("\n->" : : )
 
 #define OFFSET(sym, str, mem) \
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
index bd9a89b67e41..ca255a805ed9 100644
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -1,3 +1,5 @@
+extern long sys_clone(unsigned long clone_flags, unsigned long newsp,
+	       void __user *parent_tid, void __user *child_tid);
 #ifdef __i386__
 #include "syscalls_32.h"
 #else
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index a508cea13503..ba7363ecf896 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
 	PT_REGS_AX(regs) = (unsigned long) sig;
 	PT_REGS_DX(regs) = (unsigned long) 0;
 	PT_REGS_CX(regs) = (unsigned long) 0;
-
-	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
-		ptrace_notify(SIGTRAP);
 	return 0;
 }
 
@@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
 	PT_REGS_AX(regs) = (unsigned long) sig;
 	PT_REGS_DX(regs) = (unsigned long) &frame->info;
 	PT_REGS_CX(regs) = (unsigned long) &frame->uc;
-
-	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
-		ptrace_notify(SIGTRAP);
 	return 0;
 }
 
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 68d1dc91b37b..b5408cecac6c 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -28,7 +28,7 @@
 #define ptregs_execve sys_execve
 #define ptregs_iopl sys_iopl
 #define ptregs_vm86old sys_vm86old
-#define ptregs_clone sys_clone
+#define ptregs_clone i386_clone
 #define ptregs_vm86 sys_vm86
 #define ptregs_sigaltstack sys_sigaltstack
 #define ptregs_vfork sys_vfork
diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c
index b853e8600b9d..db444c7218fe 100644
--- a/arch/x86/um/syscalls_32.c
+++ b/arch/x86/um/syscalls_32.c
@@ -3,37 +3,24 @@
  * Licensed under the GPL
  */
 
-#include "linux/sched.h"
-#include "linux/shm.h"
-#include "linux/ipc.h"
-#include "linux/syscalls.h"
-#include "asm/mman.h"
-#include "asm/uaccess.h"
-#include "asm/unistd.h"
+#include <linux/syscalls.h>
+#include <sysdep/syscalls.h>
 
 /*
  * The prototype on i386 is:
  *
- *     int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr)
+ *     int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls
  *
  * and the "newtls" arg. on i386 is read by copy_thread directly from the
  * register saved on the stack.
  */
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
-	       int __user *parent_tid, void *newtls, int __user *child_tid)
+long i386_clone(unsigned long clone_flags, unsigned long newsp,
+		int __user *parent_tid, void *newtls, int __user *child_tid)
 {
-	long ret;
-
-	if (!newsp)
-		newsp = UPT_SP(&current->thread.regs.regs);
-
-	current->thread.forking = 1;
-	ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
-		      child_tid);
-	current->thread.forking = 0;
-	return ret;
+	return sys_clone(clone_flags, newsp, parent_tid, child_tid);
 }
 
+
 long sys_sigaction(int sig, const struct old_sigaction __user *act,
 			 struct old_sigaction __user *oact)
 {
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index f3d82bb6e15a..adb08eb5c22a 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -5,12 +5,9 @@
  * Licensed under the GPL
  */
 
-#include "linux/linkage.h"
-#include "linux/personality.h"
-#include "linux/utsname.h"
-#include "asm/prctl.h" /* XXX This should get the constants from libc */
-#include "asm/uaccess.h"
-#include "os.h"
+#include <linux/sched.h>
+#include <asm/prctl.h> /* XXX This should get the constants from libc */
+#include <os.h>
 
 long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
 {
@@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr)
 	return arch_prctl(current, code, (unsigned long __user *) addr);
 }
 
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
-	       void __user *parent_tid, void __user *child_tid)
-{
-	long ret;
-
-	if (!newsp)
-		newsp = UPT_SP(&current->thread.regs.regs);
-	current->thread.forking = 1;
-	ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
-		      child_tid);
-	current->thread.forking = 0;
-	return ret;
-}
-
 void arch_switch_to(struct task_struct *to)
 {
 	if ((to->thread.arch.fs == 0) || (to->mm == NULL))
diff --git a/drivers/block/nvme.c b/drivers/block/nvme.c
index 38a2d0631882..ad16c68c8645 100644
--- a/drivers/block/nvme.c
+++ b/drivers/block/nvme.c
@@ -79,6 +79,7 @@ struct nvme_dev {
 	char serial[20];
 	char model[40];
 	char firmware_rev[8];
+	u32 max_hw_sectors;
 };
 
 /*
@@ -835,15 +836,15 @@ static int nvme_identify(struct nvme_dev *dev, unsigned nsid, unsigned cns,
 }
 
 static int nvme_get_features(struct nvme_dev *dev, unsigned fid,
-				unsigned dword11, dma_addr_t dma_addr)
+				unsigned nsid, dma_addr_t dma_addr)
 {
 	struct nvme_command c;
 
 	memset(&c, 0, sizeof(c));
 	c.features.opcode = nvme_admin_get_features;
+	c.features.nsid = cpu_to_le32(nsid);
 	c.features.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
-	c.features.dword11 = cpu_to_le32(dword11);
 
 	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
@@ -862,11 +863,51 @@ static int nvme_set_features(struct nvme_dev *dev, unsigned fid,
 	return nvme_submit_admin_cmd(dev, &c, result);
 }
 
+/**
+ * nvme_cancel_ios - Cancel outstanding I/Os
+ * @queue: The queue to cancel I/Os on
+ * @timeout: True to only cancel I/Os which have timed out
+ */
+static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
+{
+	int depth = nvmeq->q_depth - 1;
+	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
+	unsigned long now = jiffies;
+	int cmdid;
+
+	for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
+		void *ctx;
+		nvme_completion_fn fn;
+		static struct nvme_completion cqe = {
+			.status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1,
+		};
+
+		if (timeout && !time_after(now, info[cmdid].timeout))
+			continue;
+		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid);
+		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
+		fn(nvmeq->dev, ctx, &cqe);
+	}
+}
+
+static void nvme_free_queue_mem(struct nvme_queue *nvmeq)
+{
+	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
+				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
+	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
+					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+	kfree(nvmeq);
+}
+
 static void nvme_free_queue(struct nvme_dev *dev, int qid)
 {
 	struct nvme_queue *nvmeq = dev->queues[qid];
 	int vector = dev->entry[nvmeq->cq_vector].vector;
 
+	spin_lock_irq(&nvmeq->q_lock);
+	nvme_cancel_ios(nvmeq, false);
+	spin_unlock_irq(&nvmeq->q_lock);
+
 	irq_set_affinity_hint(vector, NULL);
 	free_irq(vector, nvmeq);
 
@@ -876,18 +917,15 @@ static void nvme_free_queue(struct nvme_dev *dev, int qid)
 		adapter_delete_cq(dev, qid);
 	}
 
-	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
-				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
-	kfree(nvmeq);
+	nvme_free_queue_mem(nvmeq);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
-	unsigned extra = (depth / 8) + (depth * sizeof(struct nvme_cmd_info));
+	unsigned extra = DIV_ROUND_UP(depth, 8) + (depth *
+						sizeof(struct nvme_cmd_info));
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
@@ -975,7 +1013,7 @@ static __devinit struct nvme_queue *nvme_create_queue(struct nvme_dev *dev,
 
 static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev)
 {
-	int result;
+	int result = 0;
 	u32 aqa;
 	u64 cap;
 	unsigned long timeout;
@@ -1005,17 +1043,22 @@ static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev)
 	timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
 	dev->db_stride = NVME_CAP_STRIDE(cap);
 
-	while (!(readl(&dev->bar->csts) & NVME_CSTS_RDY)) {
+	while (!result && !(readl(&dev->bar->csts) & NVME_CSTS_RDY)) {
 		msleep(100);
 		if (fatal_signal_pending(current))
-			return -EINTR;
+			result = -EINTR;
 		if (time_after(jiffies, timeout)) {
 			dev_err(&dev->pci_dev->dev,
 				"Device not ready; aborting initialisation\n");
-			return -ENODEV;
+			result = -ENODEV;
 		}
 	}
 
+	if (result) {
+		nvme_free_queue_mem(nvmeq);
+		return result;
+	}
+
 	result = queue_request_irq(dev, nvmeq, "nvme admin");
 	dev->queues[0] = nvmeq;
 	return result;
@@ -1037,6 +1080,8 @@ static struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	offset = offset_in_page(addr);
 	count = DIV_ROUND_UP(offset + length, PAGE_SIZE);
 	pages = kcalloc(count, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
 
 	err = get_user_pages_fast(addr, count, 1, pages);
 	if (err < count) {
@@ -1146,14 +1191,13 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	return status;
 }
 
-static int nvme_user_admin_cmd(struct nvme_ns *ns,
+static int nvme_user_admin_cmd(struct nvme_dev *dev,
 					struct nvme_admin_cmd __user *ucmd)
 {
-	struct nvme_dev *dev = ns->dev;
 	struct nvme_admin_cmd cmd;
 	struct nvme_command c;
 	int status, length;
-	struct nvme_iod *iod;
+	struct nvme_iod *uninitialized_var(iod);
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -1204,7 +1248,7 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 	case NVME_IOCTL_ID:
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_admin_cmd(ns, (void __user *)arg);
+		return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, (void __user *)arg);
 	default:
@@ -1218,26 +1262,6 @@ static const struct block_device_operations nvme_fops = {
 	.compat_ioctl	= nvme_ioctl,
 };
 
-static void nvme_timeout_ios(struct nvme_queue *nvmeq)
-{
-	int depth = nvmeq->q_depth - 1;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	unsigned long now = jiffies;
-	int cmdid;
-
-	for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
-		void *ctx;
-		nvme_completion_fn fn;
-		static struct nvme_completion cqe = { .status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1, };
-
-		if (!time_after(now, info[cmdid].timeout))
-			continue;
-		dev_warn(nvmeq->q_dmadev, "Timing out I/O %d\n", cmdid);
-		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
-		fn(nvmeq->dev, ctx, &cqe);
-	}
-}
-
 static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
 {
 	while (bio_list_peek(&nvmeq->sq_cong)) {
@@ -1269,7 +1293,7 @@ static int nvme_kthread(void *data)
 				spin_lock_irq(&nvmeq->q_lock);
 				if (nvme_process_cq(nvmeq))
 					printk("process_cq did something\n");
-				nvme_timeout_ios(nvmeq);
+				nvme_cancel_ios(nvmeq, true);
 				nvme_resubmit_bios(nvmeq);
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
@@ -1339,6 +1363,9 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, int nsid,
 	ns->disk = disk;
 	lbaf = id->flbas & 0xf;
 	ns->lba_shift = id->lbaf[lbaf].ds;
+	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
+	if (dev->max_hw_sectors)
+		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
 
 	disk->major = nvme_major;
 	disk->minors = NVME_MINORS;
@@ -1383,7 +1410,7 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 
 static int __devinit nvme_setup_io_queues(struct nvme_dev *dev)
 {
-	int result, cpu, i, nr_io_queues, db_bar_size;
+	int result, cpu, i, nr_io_queues, db_bar_size, q_depth;
 
 	nr_io_queues = num_online_cpus();
 	result = set_queue_count(dev, nr_io_queues);
@@ -1429,9 +1456,10 @@ static int __devinit nvme_setup_io_queues(struct nvme_dev *dev)
 		cpu = cpumask_next(cpu, cpu_online_mask);
 	}
 
+	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
+								NVME_Q_DEPTH);
 	for (i = 0; i < nr_io_queues; i++) {
-		dev->queues[i + 1] = nvme_create_queue(dev, i + 1,
-							NVME_Q_DEPTH, i);
+		dev->queues[i + 1] = nvme_create_queue(dev, i + 1, q_depth, i);
 		if (IS_ERR(dev->queues[i + 1]))
 			return PTR_ERR(dev->queues[i + 1]);
 		dev->queue_count++;
@@ -1480,6 +1508,10 @@ static int __devinit nvme_dev_add(struct nvme_dev *dev)
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
+	if (ctrl->mdts) {
+		int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
+		dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
+	}
 
 	id_ns = mem;
 	for (i = 1; i <= nn; i++) {
@@ -1523,8 +1555,6 @@ static int nvme_dev_remove(struct nvme_dev *dev)
 	list_del(&dev->node);
 	spin_unlock(&dev_list_lock);
 
-	/* TODO: wait all I/O finished or cancel them */
-
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
 		list_del(&ns->list);
 		del_gendisk(ns->disk);
@@ -1560,15 +1590,33 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)