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

Merge reason: Pick up latest fixes.

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

412 files changed, 2474 insertions, 1329 deletions

diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index 4d4ce0e61e4..b4665b9c40b 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -16,7 +16,7 @@
         </orgname>
 
         <address>
-           <email>hjk@linutronix.de</email>
+           <email>hjk@hansjkoch.de</email>
         </address>
     </affiliation>
 </author>
@@ -114,7 +114,7 @@ GPL version 2.
 
 <para>If you know of any translations for this document, or you are
 interested in translating it, please email me
-<email>hjk@linutronix.de</email>.
+<email>hjk@hansjkoch.de</email>.
 </para>
 </sect1>
 
@@ -171,7 +171,7 @@ interested in translating it, please email me
 <title>Feedback</title>
         <para>Find something wrong with this document? (Or perhaps something
         right?) I would love to hear from you. Please email me at
-        <email>hjk@linutronix.de</email>.</para>
+        <email>hjk@hansjkoch.de</email>.</para>
 </sect1>
 </chapter>
 
diff --git a/Documentation/development-process/2.Process b/Documentation/development-process/2.Process
index 97726eba610..911a4518634 100644
--- a/Documentation/development-process/2.Process
+++ b/Documentation/development-process/2.Process
@@ -154,7 +154,7 @@ The stages that a patch goes through are, generally:
    inclusion, it should be accepted by a relevant subsystem maintainer -
    though this acceptance is not a guarantee that the patch will make it
    all the way to the mainline.  The patch will show up in the maintainer's
-   subsystem tree and into the staging trees (described below).  When the
+   subsystem tree and into the -next trees (described below).  When the
    process works, this step leads to more extensive review of the patch and
    the discovery of any problems resulting from the integration of this
    patch with work being done by others.
@@ -236,7 +236,7 @@ finding the right maintainer.  Sending patches directly to Linus is not
 normally the right way to go.
 
 
-2.4: STAGING TREES
+2.4: NEXT TREES
 
 The chain of subsystem trees guides the flow of patches into the kernel,
 but it also raises an interesting question: what if somebody wants to look
@@ -250,7 +250,7 @@ changes land in the mainline kernel.  One could pull changes from all of
 the interesting subsystem trees, but that would be a big and error-prone
 job.
 
-The answer comes in the form of staging trees, where subsystem trees are
+The answer comes in the form of -next trees, where subsystem trees are
 collected for testing and review.  The older of these trees, maintained by
 Andrew Morton, is called "-mm" (for memory management, which is how it got
 started).  The -mm tree integrates patches from a long list of subsystem
@@ -275,7 +275,7 @@ directory at:
 Use of the MMOTM tree is likely to be a frustrating experience, though;
 there is a definite chance that it will not even compile.
 
-The other staging tree, started more recently, is linux-next, maintained by
+The other -next tree, started more recently, is linux-next, maintained by
 Stephen Rothwell.  The linux-next tree is, by design, a snapshot of what
 the mainline is expected to look like after the next merge window closes.
 Linux-next trees are announced on the linux-kernel and linux-next mailing
@@ -303,12 +303,25 @@ volatility of linux-next tends to make it a difficult development target.
 See http://lwn.net/Articles/289013/ for more information on this topic, and
 stay tuned; much is still in flux where linux-next is involved.
 
-Besides the mmotm and linux-next trees, the kernel source tree now contains
-the drivers/staging/ directory and many sub-directories for drivers or
-filesystems that are on their way to being added to the kernel tree
-proper, but they remain in drivers/staging/ while they still need more
-work.
-
+2.4.1: STAGING TREES
+
+The kernel source tree now contains the drivers/staging/ directory, where
+many sub-directories for drivers or filesystems that are on their way to
+being added to the kernel tree live.  They remain in drivers/staging while
+they still need more work; once complete, they can be moved into the
+kernel proper.  This is a way to keep track of drivers that aren't
+up to Linux kernel coding or quality standards, but people may want to use
+them and track development.
+
+Greg Kroah-Hartman currently (as of 2.6.36) maintains the staging tree.
+Drivers that still need work are sent to him, with each driver having
+its own subdirectory in drivers/staging/.  Along with the driver source
+files, a TODO file should be present in the directory as well.  The TODO
+file lists the pending work that the driver needs for acceptance into
+the kernel proper, as well as a list of people that should be Cc'd for any
+patches to the driver.  Staging drivers that don't currently build should
+have their config entries depend upon CONFIG_BROKEN.  Once they can
+be successfully built without outside patches, CONFIG_BROKEN can be removed.
 
 2.5: TOOLS
 
diff --git a/Documentation/filesystems/configfs/configfs_example_explicit.c b/Documentation/filesystems/configfs/configfs_example_explicit.c
index d428cc9f07f..fd53869f563 100644
--- a/Documentation/filesystems/configfs/configfs_example_explicit.c
+++ b/Documentation/filesystems/configfs/configfs_example_explicit.c
@@ -89,7 +89,7 @@ static ssize_t childless_storeme_write(struct childless *childless,
         char *p = (char *) page;
 
         tmp = simple_strtoul(p, &p, 10);
-        if (!p || (*p && (*p != '\n')))
+        if ((*p != '\0') && (*p != '\n'))
                 return -EINVAL;
 
         if (tmp > INT_MAX)
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 9633da01ff4..792faa3c06c 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -617,6 +617,16 @@ and have the following read/write attributes:
                 is configured as an output, this value may be written;
                 any nonzero value is treated as high.
 
+                If the pin can be configured as interrupt-generating interrupt
+                and if it has been configured to generate interrupts (see the
+                description of "edge"), you can poll(2) on that file and
+                poll(2) will return whenever the interrupt was triggered. If
+                you use poll(2), set the events POLLPRI and POLLERR. If you
+                use select(2), set the file descriptor in exceptfds. After
+                poll(2) returns, either lseek(2) to the beginning of the sysfs
+                file and read the new value or close the file and re-open it
+                to read the value.
+
         "edge" ... reads as either "none", "rising", "falling", or
                 "both". Write these strings to select the signal edge(s)
                 that will make poll(2) on the "value" file return.
diff --git a/Documentation/hwmon/lm93 b/Documentation/hwmon/lm93
index ac711f357fa..7a10616d0b4 100644
--- a/Documentation/hwmon/lm93
+++ b/Documentation/hwmon/lm93
@@ -11,7 +11,7 @@ Authors:
         Mark M. Hoffman <mhoffman@lightlink.com>
         Ported to 2.6 by Eric J. Bowersox <ericb@aspsys.com>
         Adapted to 2.6.20 by Carsten Emde <ce@osadl.org>
-        Modified for mainline integration by Hans J. Koch <hjk@linutronix.de>
+        Modified for mainline integration by Hans J. Koch <hjk@hansjkoch.de>
 
 Module Parameters
 -----------------
diff --git a/Documentation/hwmon/max6650 b/Documentation/hwmon/max6650
index 8be7beb9e3e..c565650fcfc 100644
--- a/Documentation/hwmon/max6650
+++ b/Documentation/hwmon/max6650
@@ -8,7 +8,7 @@ Supported chips:
     Datasheet: http://pdfserv.maxim-ic.com/en/ds/MAX6650-MAX6651.pdf
 
 Authors:
-    Hans J. Koch <hjk@linutronix.de>
+    Hans J. Koch <hjk@hansjkoch.de>
     John Morris <john.morris@spirentcom.com>
     Claus Gindhart <claus.gindhart@kontron.com>
 
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index 44d87ad3cea..cd445582d1f 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -37,6 +37,9 @@ Typical usage of the OPP library is as follows:
 SoC framework   -> modifies on required cases certain OPPs      -> OPP layer
                 -> queries to search/retrieve information       ->
 
+Architectures that provide a SoC framework for OPP should select ARCH_HAS_OPP
+to make the OPP layer available.
+
 OPP layer expects each domain to be represented by a unique device pointer. SoC
 framework registers a set of initial OPPs per device with the OPP layer. This
 list is expected to be an optimally small number typically around 5 per device.
diff --git a/MAINTAINERS b/MAINTAINERS
index 8e6548dbd5d..a92c994ba93 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1829,6 +1829,13 @@ W:	http://www.chelsio.com
 S:      Supported
 F:      drivers/net/cxgb4vf/
 
+STMMAC ETHERNET DRIVER
+M:      Giuseppe Cavallaro <peppe.cavallaro@st.com>
+L:      netdev@vger.kernel.org
+W:      http://www.stlinux.com
+S:      Supported
+F:      drivers/net/stmmac/
+
 CYBERPRO FB DRIVER
 M:      Russell King <linux@arm.linux.org.uk>
 L:      linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2008,6 +2015,7 @@ F:	drivers/hwmon/dme1737.c
 DOCBOOK FOR DOCUMENTATION
 M:      Randy Dunlap <rdunlap@xenotime.net>
 S:      Maintained
+F:      scripts/kernel-doc
 
 DOCKING STATION DRIVER
 M:      Shaohua Li <shaohua.li@intel.com>
@@ -2018,6 +2026,7 @@ F:	drivers/acpi/dock.c
 DOCUMENTATION
 M:      Randy Dunlap <rdunlap@xenotime.net>
 L:      linux-doc@vger.kernel.org
+T:      quilt oss.oracle.com/~rdunlap/kernel-doc-patches/current/
 S:      Maintained
 F:      Documentation/
 
diff --git a/Makefile b/Makefile
index ab5359db3d1..b31d21377e4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 37
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
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();
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 58c6ee5b010..cc3eb78e333 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -8,7 +8,6 @@
 #include <linux/hdreg.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
 
diff --git a/block/ioctl.c b/block/ioctl.c
index 3d866d0037f..a9a302eba01 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -5,7 +5,6 @@
 #include <linux/hdreg.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
 #include <linux/blktrace_api.h>
 #include <asm/uaccess.h>
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 3f91c01c217..66aa4bee80a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3166,8 +3166,8 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
 
 /**
  *      ata_scsi_queuecmd - Issue SCSI cdb to libata-managed device
+ *      @shost: SCSI host of command to be sent
  *      @cmd: SCSI command to be sent
- *      @done: Completion function, called when command is complete
  *
  *      In some cases, this function translates SCSI commands into
  *      ATA taskfiles, and queues the taskfiles to be sent to
@@ -3177,37 +3177,36 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
  *      ATA and ATAPI devices appearing as SCSI devices.
  *
  *      LOCKING:
- *      Releases scsi-layer-held lock, and obtains host lock.
+ *      ATA host lock
  *
  *      RETURNS:
  *      Return value from __ata_scsi_queuecmd() if @cmd can be queued,
  *      0 otherwise.
  */
-int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 {
         struct ata_port *ap;
         struct ata_device *dev;
         struct scsi_device *scsidev = cmd->device;
-        struct Scsi_Host *shost = scsidev->host;
         int rc = 0;
+        unsigned long irq_flags;
 
         ap = ata_shost_to_port(shost);
 
-        spin_unlock(shost->host_lock);
-        spin_lock(ap->lock);
+        spin_lock_irqsave(ap->lock, irq_flags);
 
         ata_scsi_dump_cdb(ap, cmd);
 
         dev = ata_scsi_find_dev(ap, scsidev);
         if (likely(dev))
-                rc = __ata_scsi_queuecmd(cmd, done, dev);
+                rc = __ata_scsi_queuecmd(cmd, cmd->scsi_done, dev);
         else {
                 cmd->result = (DID_BAD_TARGET << 16);
-                done(cmd);
+                cmd->scsi_done(cmd);
         }
 
-        spin_unlock(ap->lock);
-        spin_lock(shost->host_lock);
+        spin_unlock_irqrestore(ap->lock, irq_flags);
+
         return rc;
 }
 
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index c21589986c6..8b677bbf2d3 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -538,7 +538,7 @@ static int vt8251_prepare_host(struct pci_dev *pdev, struct ata_host **r_host)
         return 0;
 }
 
-static void svia_configure(struct pci_dev *pdev)
+static void svia_configure(struct pci_dev *pdev, int board_id)
 {
         u8 tmp8;
 
@@ -577,7 +577,7 @@ static void svia_configure(struct pci_dev *pdev)
         }
 
         /*
-         * vt6421 has problems talking to some drives.  The following
+         * vt6420/1 has problems talking to some drives.  The following
          * is the fix from Joseph Chan <JosephChan@via.com.tw>.
          *
          * When host issues HOLD, device may send up to 20DW of data
@@ -596,8 +596,9 @@ static void svia_configure(struct pci_dev *pdev)
          *
          * https://bugzilla.kernel.org/show_bug.cgi?id=15173
          * http://article.gmane.org/gmane.linux.ide/46352
+         * http://thread.gmane.org/gmane.linux.kernel/1062139
          */
-        if (pdev->device == 0x3249) {
+        if (board_id == vt6420 || board_id == vt6421) {
                 pci_read_config_byte(pdev, 0x52, &tmp8);
                 tmp8 |= 1 << 2;
                 pci_write_config_byte(pdev, 0x52, tmp8);
@@ -652,7 +653,7 @@ static int svia_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
         if (rc)
                 return rc;
 
-        svia_configure(pdev);
+        svia_configure(pdev, board_id);
 
         pci_set_master(pdev);
         return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 31b526661ec..ead3e79d6fc 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -475,20 +475,33 @@ End:
  */
 void dpm_resume_noirq(pm_message_t state)
 {
-        struct device *dev;
+        struct list_head list;
         ktime_t starttime = ktime_get();
 
+        INIT_LIST_HEAD(&list);
         mutex_lock(&dpm_list_mtx);
         transition_started = false;
-        list_for_each_entry(dev, &dpm_list, power.entry)
+        while (!list_empty(&dpm_list)) {
+                struct device *dev = to_device(dpm_list.next);
+
+                get_device(dev);
                 if (dev->power.status > DPM_OFF) {
                         int error;
 
                         dev->power.status = DPM_OFF;
+                        mutex_unlock(&dpm_list_mtx);
+
                         error = device_resume_noirq(dev, state);
+
+                        mutex_lock(&dpm_list_mtx);
                         if (error)
                                 pm_dev_err(dev, state, " early", error);
                 }
+                if (!list_empty(&dev->power.entry))
+                        list_move_tail(&dev->power.entry, &list);
+                put_device(dev);
+        }
+        list_splice(&list, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
         dpm_show_time(starttime, state, "early");
         resume_device_irqs();
@@ -789,20 +802,33 @@ End:
  */
 int dpm_suspend_noirq(pm_message_t state)
 {
-        struct device *dev;
+        struct list_head list;
         ktime_t starttime = ktime_get();
         int error = 0;
 
+        INIT_LIST_HEAD(&list);
         suspend_device_irqs();
         mutex_lock(&dpm_list_mtx);
-        list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
+        while (!list_empty(&dpm_list)) {
+                struct device *dev = to_device(dpm_list.prev);
+
+                get_device(dev);
+                mutex_unlock(&dpm_list_mtx);
+
                 error = device_suspend_noirq(dev, state);
+
+                mutex_lock(&dpm_list_mtx);
                 if (error) {
                         pm_dev_err(dev, state, " late", error);
+                        put_device(dev);
                         break;
                 }
                 dev->power.status = DPM_OFF_IRQ;
+                if (!list_empty(&dev->power.entry))
+                        list_move(&dev->power.entry, &list);
+                put_device(dev);
         }
+        list_splice_tail(&list, &dpm_list);
         mutex_unlock(&dpm_list_mtx);
         if (error)
                 dpm_resume_noirq(resume_event(state));
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index 575495f3c4b..727d0225b7d 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -62,8 +62,8 @@ static int cciss_scsi_proc_info(
                 int length,        /* length of data in buffer */
                 int func);         /* 0 == read, 1 == write */
 
-static int cciss_scsi_queue_command (struct scsi_cmnd *cmd,
-                void (* done)(struct scsi_cmnd *));
+static int cciss_scsi_queue_command (struct Scsi_Host *h,
+                                     struct scsi_cmnd *cmd);
 static int cciss_eh_device_reset_handler(struct scsi_cmnd *);
 static int cciss_eh_abort_handler(struct scsi_cmnd *);
 
@@ -1406,7 +1406,7 @@ static void cciss_scatter_gather(ctlr_info_t *h, CommandList_struct *c,
 
 
 static int
-cciss_scsi_queue_command (struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd *))
+cciss_scsi_queue_command_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         ctlr_info_t *h;
         int rc;
@@ -1504,6 +1504,8 @@ cciss_scsi_queue_command (struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd
         return 0;
 }
 
+static DEF_SCSI_QCMD(cciss_scsi_queue_command)
+
 static void cciss_unregister_scsi(ctlr_info_t *h)
 {
         struct cciss_scsi_adapter_data_t *sa;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index d299fe9e78c..89d8a7cc405 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -36,7 +36,6 @@
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/pkt_sched.h>
 #define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index b0551ba7ad0..47d223c2409 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -26,7 +26,6 @@
 #include <linux/module.h>
 #include <linux/drbd.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index 43412c03969..3cb4539a98b 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -39,7 +39,6 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include "agp.h"
diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c
index c0bd6f472c5..6ee3348bc3e 100644
--- a/drivers/char/amiserial.c
+++ b/drivers/char/amiserial.c
@@ -81,7 +81,6 @@ static char *serial_version = "4.30";
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/platform_device.h>
diff --git a/drivers/char/briq_panel.c b/drivers/char/briq_panel.c
index f6718f05dad..095ab90535c 100644
--- a/drivers/char/briq_panel.c
+++ b/drivers/char/briq_panel.c
@@ -6,7 +6,6 @@
 
 #include <linux/module.h>
 
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/tty.h>
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 55b8667f739..7066e801b9d 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
 #include <linux/major.h>
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 788da05190c..2016aad8520 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -37,7 +37,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 667abd23ad6..7c6de4c9245 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -21,7 +21,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index f646725bd56..748c3b0ecd8 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -52,7 +52,6 @@
 #include <linux/interrupt.h>
 #include <linux/serial.h>
 #include <linux/serialP.h>
-#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c
index 9f8495b4fc8..a7616d226a4 100644
--- a/drivers/char/specialix.c
+++ b/drivers/char/specialix.c
@@ -87,7 +87,6 @@
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
 #include <linux/serial.h>
-#include <linux/smp_lock.h>
 #include <linux/fcntl.h>
 #include <linux/major.h>
 #include <linux/delay.h>
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index 4bef6ab8362..461a5a04551 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -40,7 +40,6 @@
 #include <linux/stallion.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/ctype.h>
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index e53f1686539..a786326cea2 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -216,7 +216,6 @@
 #include <linux/eisa.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/bitops.h>
diff --git a/drivers/char/uv_mmtimer.c b/drivers/char/uv_mmtimer.c
index 493b47a0d51..956ebe2080a 100644
--- a/drivers/char/uv_mmtimer.c
+++ b/drivers/char/uv_mmtimer.c
@@ -23,7 +23,6 @@
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/math64.h>
-#include <linux/smp_lock.h>
 
 #include <asm/genapic.h>
 #include <asm/uv/uv_hub.h>
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index bfae4b30979..afa576a75a8 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1468,7 +1468,7 @@ static int sbp2_map_scatterlist(struct sbp2_command_orb *orb,
 
 /* SCSI stack integration */
 
-static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
+static int sbp2_scsi_queuecommand_lck(struct scsi_cmnd *cmd, scsi_done_fn_t done)
 {
         struct sbp2_logical_unit *lu = cmd->device->hostdata;
         struct fw_device *device = target_device(lu->tgt);
@@ -1534,6 +1534,8 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
         return retval;
 }
 
+static DEF_SCSI_QCMD(sbp2_scsi_queuecommand)
+
 static int sbp2_scsi_slave_alloc(struct scsi_device *sdev)
 {
         struct sbp2_logical_unit *lu = sdev->hostdata;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index b744dad5c23..a39794bac04 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -37,7 +37,6 @@
 #include "drmP.h"
 #include <linux/poll.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 
 /* from BKL pushdown: note that nothing else serializes idr_find() */
 DEFINE_MUTEX(drm_global_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 80745f85902..f737960712e 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -150,7 +150,8 @@ static const struct intel_device_info intel_ironlake_d_info = {
 
 static const struct intel_device_info intel_ironlake_m_info = {
         .gen = 5, .is_mobile = 1,
-        .need_gfx_hws = 1, .has_fbc = 1, .has_rc6 = 1, .has_hotplug = 1,
+        .need_gfx_hws = 1, .has_rc6 = 1, .has_hotplug = 1,
+        .has_fbc = 0, /* disabled due to buggy hardware */
         .has_bsd_ring = 1,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 90414ae86af..409826da309 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1045,6 +1045,8 @@ void i915_gem_clflush_object(struct drm_gem_object *obj);
 int i915_gem_object_set_domain(struct drm_gem_object *obj,
                                uint32_t read_domains,
                                uint32_t write_domain);
+int i915_gem_object_flush_gpu(struct drm_i915_gem_object *obj,
+                              bool interruptible);
 int i915_gem_init_ringbuffer(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int i915_gem_do_init(struct drm_device *dev, unsigned long start,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ef188e39140..17b1cba3b5f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -547,6 +547,19 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
         struct drm_i915_gem_object *obj_priv;
         int ret = 0;
 
+        if (args->size == 0)
+                return 0;
+
+        if (!access_ok(VERIFY_WRITE,
+                       (char __user *)(uintptr_t)args->data_ptr,
+                       args->size))
+                return -EFAULT;
+
+        ret = fault_in_pages_writeable((char __user *)(uintptr_t)args->data_ptr,
+                                       args->size);
+        if (ret)
+                return -EFAULT;
+
         ret = i915_mutex_lock_interruptible(dev);
         if (ret)
                 return ret;
@@ -564,23 +577,6 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
                 goto out;
         }
 
-        if (args->size == 0)
-                goto out;
-
-        if (!access_ok(VERIFY_WRITE,
-                       (char __user *)(uintptr_t)args->data_ptr,
-                       args->size)) {
-                ret = -EFAULT;
-                goto out;
-        }
-
-        ret = fault_in_pages_writeable((char __user *)(uintptr_t)args->data_ptr,
-                                       args->size);
-        if (ret) {
-                ret = -EFAULT;
-                goto out;
-        }
-
         ret = i915_gem_object_get_pages_or_evict(obj);
         if (ret)
                 goto out;
@@ -981,7 +977,20 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
         struct drm_i915_gem_pwrite *args = data;
         struct drm_gem_object *obj;
         struct drm_i915_gem_object *obj_priv;
-        int ret = 0;
+        int ret;
+
+        if (args->size == 0)
+                return 0;
+
+        if (!access_ok(VERIFY_READ,
+                       (char __user *)(uintptr_t)args->data_ptr,
+                       args->size))
+                return -EFAULT;
+
+        ret = fault_in_pages_readable((char __user *)(uintptr_t)args->data_ptr,
+                                      args->size);
+        if (ret)
+                return -EFAULT;
 
         ret = i915_mutex_lock_interruptible(dev);
         if (ret)
@@ -994,30 +1003,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
         }
         obj_priv = to_intel_bo(obj);
 
-
         /* Bounds check destination. */
         if (args->offset > obj->size || args->size > obj->size - args->offset) {
                 ret = -EINVAL;
                 goto out;
         }
 
-        if (args->size == 0)
-                goto out;
-
-        if (!access_ok(VERIFY_READ,
-                       (char __user *)(uintptr_t)args->data_ptr,
-                       args->size)) {
-                ret = -EFAULT;
-                goto out;
-        }
-
-        ret = fault_in_pages_readable((char __user *)(uintptr_t)args->data_ptr,
-                                      args->size);
-        if (ret) {
-                ret = -EFAULT;
-                goto out;
-        }
-
         /* We can only do the GTT pwrite on untiled buffers, as otherwise
          * it would end up going through the fenced access, and we'll get
          * different detiling behavior between reading and writing.
@@ -2907,6 +2898,20 @@ i915_gem_object_set_to_display_plane(struct drm_gem_object *obj,
         return 0;
 }
 
+int
+i915_gem_object_flush_gpu(struct drm_i915_gem_object *obj,
+                          bool interruptible)
+{
+        if (!obj->active)
+                return 0;
+
+        if (obj->base.write_domain & I915_GEM_GPU_DOMAINS)
+                i915_gem_flush_ring(obj->base.dev, NULL, obj->ring,
+                                    0, obj->base.write_domain);
+
+        return i915_gem_object_wait_rendering(&obj->base, interruptible);
+}
+
 /**
  * Moves a single object to the CPU read, and possibly write domain.
  *
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index c55c7704335..8df57431606 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -34,6 +34,25 @@
 #include "i915_drm.h"
 #include "i915_drv.h"
 
+/* Here's the desired hotplug mode */
+#define ADPA_HOTPLUG_BITS (ADPA_CRT_HOTPLUG_PERIOD_128 |                \
+                           ADPA_CRT_HOTPLUG_WARMUP_10MS |               \
+                           ADPA_CRT_HOTPLUG_SAMPLE_4S |                 \
+                           ADPA_CRT_HOTPLUG_VOLTAGE_50 |                \
+                           ADPA_CRT_HOTPLUG_VOLREF_325MV |              \
+                           ADPA_CRT_HOTPLUG_ENABLE)
+
+struct intel_crt {
+        struct intel_encoder base;
+        bool force_hotplug_required;
+};
+
+static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
+{
+        return container_of(intel_attached_encoder(connector),
+                            struct intel_crt, base);
+}
+
 static void intel_crt_dpms(struct drm_encoder *encoder, int mode)
 {
         struct drm_device *dev = encoder->dev;
@@ -129,7 +148,7 @@ static void intel_crt_mode_set(struct drm_encoder *encoder,
                            dpll_md & ~DPLL_MD_UDI_MULTIPLIER_MASK);
         }
 
-        adpa = 0;
+        adpa = ADPA_HOTPLUG_BITS;
         if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
                 adpa |= ADPA_HSYNC_ACTIVE_HIGH;
         if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
@@ -157,53 +176,44 @@ static void intel_crt_mode_set(struct drm_encoder *encoder,
 static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 {
         struct drm_device *dev = connector->dev;
+        struct intel_crt *crt = intel_attached_crt(connector);
         struct drm_i915_private *dev_priv = dev->dev_private;
-        u32 adpa, temp;
+        u32 adpa;
         bool ret;
-        bool turn_off_dac = false;
 
-        temp = adpa = I915_READ(PCH_ADPA);
+        /* The first time through, trigger an explicit detection cycle */
+        if (crt->force_hotplug_required) {
+                bool turn_off_dac = HAS_PCH_SPLIT(dev);
+                u32 save_adpa;
 
-        if (HAS_PCH_SPLIT(dev))
-                turn_off_dac = true;
-
-        adpa &= ~ADPA_CRT_HOTPLUG_MASK;
-        if (turn_off_dac)
-                adpa &= ~ADPA_DAC_ENABLE;
-
-        /* disable HPD first */
-        I915_WRITE(PCH_ADPA, adpa);
-        (void)I915_READ(PCH_ADPA);
-
-        adpa |= (ADPA_CRT_HOTPLUG_PERIOD_128 |
-                        ADPA_CRT_HOTPLUG_WARMUP_10MS |
-                        ADPA_CRT_HOTPLUG_SAMPLE_4S |
-                        ADPA_CRT_HOTPLUG_VOLTAGE_50 | /* default */
-                        ADPA_CRT_HOTPLUG_VOLREF_325MV |
-                        ADPA_CRT_HOTPLUG_ENABLE |
-                        ADPA_CRT_HOTPLUG_FORCE_TRIGGER);
-
-        DRM_DEBUG_KMS("pch crt adpa 0x%x", adpa);
-        I915_WRITE(PCH_ADPA, adpa);
-
-        if (wait_for((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0,
-                     1000))
-                DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER");
-
-        if (turn_off_dac) {
-                /* Make sure hotplug is enabled */
-                I915_WRITE(PCH_ADPA, temp | ADPA_CRT_HOTPLUG_ENABLE);
-                (void)I915_READ(PCH_ADPA);
+                crt->force_hotplug_required = 0;
+
+                save_adpa = adpa = I915_READ(PCH_ADPA);
+                DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa);
+
+                adpa |= ADPA_CRT_HOTPLUG_FORCE_TRIGGER;
+                if (turn_off_dac)
+                        adpa &= ~ADPA_DAC_ENABLE;
+
+                I915_WRITE(PCH_ADPA, adpa);
+
+                if (wait_for((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0,
+                             1000))
+                        DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER");
+
+                if (turn_off_dac) {
+                        I915_WRITE(PCH_ADPA, save_adpa);
+                        POSTING_READ(PCH_ADPA);
+                }
         }
 
         /* Check the status to see if both blue and green are on now */
         adpa = I915_READ(PCH_ADPA);
-        adpa &= ADPA_CRT_HOTPLUG_MONITOR_MASK;
-        if ((adpa == ADPA_CRT_HOTPLUG_MONITOR_COLOR) ||
-                (adpa == ADPA_CRT_HOTPLUG_MONITOR_MONO))
+        if ((adpa & ADPA_CRT_HOTPLUG_MONITOR_MASK) != 0)
                 ret = true;
         else
                 ret = false;
+        DRM_DEBUG_KMS("ironlake hotplug adpa=0x%x, result %d\n", adpa, ret);
 
         return ret;
 }
@@ -277,13 +287,12 @@ static bool intel_crt_ddc_probe(struct drm_i915_private *dev_priv, int ddc_bus)
         return i2c_transfer(&dev_priv->gmbus[ddc_bus].adapter, msgs, 1) == 1;
 }
 
-static bool intel_crt_detect_ddc(struct drm_encoder *encoder)
+static bool intel_crt_detect_ddc(struct intel_crt *crt)
 {
-        struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
-        struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+        struct drm_i915_private *dev_priv = crt->base.base.dev->dev_private;
 
         /* CRT should always be at 0, but check anyway */
-        if (intel_encoder->type != INTEL_OUTPUT_ANALOG)
+        if (crt->base.type != INTEL_OUTPUT_ANALOG)
                 return false;
 
         if (intel_crt_ddc_probe(dev_priv, dev_priv->crt_ddc_pin)) {
@@ -291,7 +300,7 @@ static bool intel_crt_detect_ddc(struct drm_encoder *encoder)
                 return true;
         }
 
-        if (intel_ddc_probe(intel_encoder, dev_priv->crt_ddc_pin)) {
+        if (intel_ddc_probe(&crt->base, dev_priv->crt_ddc_pin)) {
                 DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
                 return true;
         }
@@ -300,9 +309,9 @@ static bool intel_crt_detect_ddc(struct drm_encoder *encoder)
 }
 
 static enum drm_connector_status
-intel_crt_load_detect(struct drm_crtc *crtc, struct intel_encoder *intel_encoder)
+intel_crt_load_detect(struct drm_crtc *crtc, struct intel_crt *crt)
 {
-        struct drm_encoder *encoder = &intel_encoder->base;
+        struct drm_encoder *encoder = &crt->base.base;
         struct drm_device *dev = encoder->dev;
         struct drm_i915_private *dev_priv = dev->dev_private;
         struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -434,7 +443,7 @@ static enum drm_connector_status
 intel_crt_detect(struct drm_connector *connector, bool force)
 {
         struct drm_device *dev = connector->dev;
-        struct intel_encoder *encoder = intel_attached_encoder(connector);
+        struct intel_crt *crt = intel_attached_crt(connector);
         struct drm_crtc *crtc;
         int dpms_mode;
         enum drm_connector_status status;
@@ -443,28 +452,31 @@ intel_crt_detect(struct drm_connector *connector, bool force)
                 if (intel_crt_detect_hotplug(connector)) {
                         DRM_DEBUG_KMS("CRT detected via hotplug\n");
                         return connector_status_connected;
-                } else
+                } else {
+                        DRM_DEBUG_KMS("CRT not detected via hotplug\n");
                         return connector_status_disconnected;
+                }
         }
 
-        if (intel_crt_detect_ddc(&encoder->base))
+        if (intel_crt_detect_ddc(crt))
                 return connector_status_connected;
 
         if (!force)
                 return connector->status;
 
         /* for pre-945g platforms use load detect */
-        if (encoder->base.crtc && encoder->base.crtc->enabled) {
-                status = intel_crt_load_detect(encoder->base.crtc, encoder);
+        crtc = crt->base.base.crtc;
+        if (crtc && crtc->enabled) {
+                status = intel_crt_load_detect(crtc, crt);
         } else {
-                crtc = intel_get_load_detect_pipe(encoder, connector,
+                crtc = intel_get_load_detect_pipe(&crt->base, connector,
                                                   NULL, &dpms_mode);
                 if (crtc) {
-                        if (intel_crt_detect_ddc(&encoder->base))
+                        if (intel_crt_detect_ddc(crt))
                                 status = connector_status_connected;
                         else
-                                status = intel_crt_load_detect(crtc, encoder);
-                        intel_release_load_detect_pipe(encoder,
+                                status = intel_crt_load_detect(crtc, crt);
+                        intel_release_load_detect_pipe(&crt->base,
                                                        connector, dpms_mode);
                 } else
                         status = connector_status_unknown;
@@ -536,17 +548,17 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = {
 void intel_crt_init(struct drm_device *dev)
 {
         struct drm_connector *connector;
-        struct intel_encoder *intel_encoder;
+        struct intel_crt *crt;
         struct intel_connector *intel_connector;
         struct drm_i915_private *dev_priv = dev->dev_private;
 
-        intel_encoder = kzalloc(sizeof(struct intel_encoder), GFP_KERNEL);
-        if (!intel_encoder)
+        crt = kzalloc(sizeof(struct intel_crt), GFP_KERNEL);
+        if (!crt)
                 return;
 
         intel_connector = kzalloc(sizeof(struct intel_connector), GFP_KERNEL);
         if (!intel_connector) {
-                kfree(intel_encoder);
+                kfree(crt);
                 return;
         }
 
@@ -554,20 +566,20 @@ void intel_crt_init(struct drm_device *dev)
         drm_connector_init(dev, &intel_connector->base,
                            &intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
 
-        drm_encoder_init(dev, &intel_encoder->base, &intel_crt_enc_funcs,
+        drm_encoder_init(dev, &crt->base.base, &intel_crt_enc_funcs,
                          DRM_MODE_ENCODER_DAC);
 
-        intel_connector_attach_encoder(intel_connector, intel_encoder);
+        intel_connector_attach_encoder(intel_connector, &crt->base);
 
-        intel_encoder->type = INTEL_OUTPUT_ANALOG;
-        intel_encoder->clone_mask = (1 << INTEL_SDVO_NON_TV_CLONE_BIT) |
-                                   (1 << INTEL_ANALOG_CLONE_BIT) |
-                                   (1 << INTEL_SDVO_LVDS_CLONE_BIT);
-        intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+        crt->base.type = INTEL_OUTPUT_ANALOG;
+        crt->base.clone_mask = (1 << INTEL_SDVO_NON_TV_CLONE_BIT |
+                                1 << INTEL_ANALOG_CLONE_BIT |
+                                1 << INTEL_SDVO_LVDS_CLONE_BIT);
+        crt->base.crtc_mask = (1 << 0) | (1 << 1);
         connector->interlace_allowed = 1;
         connector->doublescan_allowed = 0;
 
-        drm_encoder_helper_add(&intel_encoder->base, &intel_crt_helper_funcs);
+        drm_encoder_helper_add(&crt->base.base, &intel_crt_helper_funcs);
         drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 
         drm_sysfs_connector_add(connector);
@@ -577,5 +589,22 @@ void intel_crt_init(struct drm_device *dev)
         else
                 connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
+        /*
+         * Configure the automatic hotplug detection stuff
+         */
+        crt->force_hotplug_required = 0;
+        if (HAS_PCH_SPLIT(dev)) {
+                u32 adpa;
+
+                adpa = I915_READ(PCH_ADPA);
+                adpa &= ~ADPA_CRT_HOTPLUG_MASK;
+                adpa |= ADPA_HOTPLUG_BITS;
+                I915_WRITE(PCH_ADPA, adpa);
+                POSTING_READ(PCH_ADPA);
+
+                DRM_DEBUG_KMS("pch crt adpa set to 0x%x\n", adpa);
+                crt->force_hotplug_required = 1;
+        }
+
         dev_priv->hotplug_supported_mask |= CRT_HOTPLUG_INT_STATUS;
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 48d8fd686ea..bee24b1a58e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1611,6 +1611,18 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 
                 wait_event(dev_priv->pending_flip_queue,
                            atomic_read(&obj_priv->pending_flip) == 0);
+
+                /* Big Hammer, we also need to ensure that any pending
+                 * MI_WAIT_FOR_EVENT inside a user batch buffer on the
+                 * current scanout is retired before unpinning the old
+                 * framebuffer.
+                 */
+                ret = i915_gem_object_flush_gpu(obj_priv, false);
+                if (ret) {
+                        i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
+                        mutex_unlock(&dev->struct_mutex);
+                        return ret;
+                }
         }
 
         ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y,
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 2be4f728ed0..3dba086e7ee 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -160,7 +160,7 @@ intel_gpio_create(struct drm_i915_private *dev_priv, u32 pin)
         };
         struct intel_gpio *gpio;
 
-        if (pin < 1 || pin > 7)
+        if (pin >= ARRAY_SIZE(map_pin_to_reg) || !map_pin_to_reg[pin])
                 return NULL;
 
         gpio = kzalloc(sizeof(struct intel_gpio), GFP_KERNEL);
@@ -172,7 +172,8 @@ intel_gpio_create(struct drm_i915_private *dev_priv, u32 pin)
                 gpio->reg += PCH_GPIOA - GPIOA;
         gpio->dev_priv = dev_priv;
 
-        snprintf(gpio->adapter.name, I2C_NAME_SIZE, "GPIO%c", "?BACDEF?"[pin]);
+        snprintf(gpio->adapter.name, sizeof(gpio->adapter.name),
+                 "i915 GPIO%c", "?BACDE?F"[pin]);
         gpio->adapter.owner = THIS_MODULE;
         gpio->adapter.algo_data = &gpio->algo;
         gpio->adapter.dev.parent = &dev_priv->dev->pdev->dev;
@@ -349,7 +350,7 @@ int intel_setup_gmbus(struct drm_device *dev)
                 "panel",
                 "dpc",
                 "dpb",
-                "reserved"
+                "reserved",
                 "dpd",
         };
         struct drm_i915_private *dev_priv = dev->dev_private;
@@ -366,8 +367,8 @@ int intel_setup_gmbus(struct drm_device *dev)
                 bus->adapter.owner = THIS_MODULE;
                 bus->adapter.class = I2C_CLASS_DDC;
                 snprintf(bus->adapter.name,
-                         I2C_NAME_SIZE,
-                         "gmbus %s",
+                         sizeof(bus->adapter.name),
+                         "i915 gmbus %s",
                          names[i]);
 
                 bus->adapter.dev.parent = &dev->pdev->dev;
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 406228f4a2a..b14c8111057 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/backlight.h>
+#include <linux/acpi.h>
 
 #include "drmP.h"
 #include "nouveau_drv.h"
@@ -136,6 +137,14 @@ int nouveau_backlight_init(struct drm_device *dev)
 {
         struct drm_nouveau_private *dev_priv = dev->dev_private;
 
+#ifdef CONFIG_ACPI
+        if (acpi_video_backlight_support()) {
+                NV_INFO(dev, "ACPI backlight interface available, "
+                             "not registering our own\n");
+                return 0;
+        }
+#endif
+
         switch (dev_priv->card_type) {
         case NV_40:
                 return nouveau_nv40_backlight_init(dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 5f21030a293..b2293576f27 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -6829,7 +6829,7 @@ nouveau_bios_posted(struct drm_device *dev)
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         unsigned htotal;
 
-        if (dev_priv->chipset >= NV_50) {
+        if (dev_priv->card_type >= NV_50) {
                 if (NVReadVgaCrtc(dev, 0, 0x00) == 0 &&
                     NVReadVgaCrtc(dev, 0, 0x1a) == 0)
                         return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 80353e2b840..c41e1c200ef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -143,8 +143,10 @@ nouveau_bo_new(struct drm_device *dev, struct nouveau_channel *chan,
         nvbo->no_vm = no_vm;
         nvbo->tile_mode = tile_mode;
         nvbo->tile_flags = tile_flags;
+        nvbo->bo.bdev = &dev_priv->ttm.bdev;
 
-        nouveau_bo_fixup_align(dev, tile_mode, tile_flags, &align, &size);
+        nouveau_bo_fixup_align(dev, tile_mode, nouveau_bo_tile_layout(nvbo),
+                               &align, &size);
         align >>= PAGE_SHIFT;
 
         nouveau_bo_placement_set(nvbo, flags, 0);
@@ -176,6 +178,31 @@ set_placement_list(uint32_t *pl, unsigned *n, uint32_t type, uint32_t flags)
                 pl[(*n)++] = TTM_PL_FLAG_SYSTEM | flags;
 }
 
+static void
+set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
+{
+        struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev);
+
+        if (dev_priv->card_type == NV_10 &&
+            nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM)) {
+                /*
+                 * Make sure that the color and depth buffers are handled
+                 * by independent memory controller units. Up to a 9x
+                 * speed up when alpha-blending and depth-test are enabled
+                 * at the same time.
+                 */
+                int vram_pages = dev_priv->vram_size >> PAGE_SHIFT;
+
+                if (nvbo->tile_flags & NOUVEAU_GEM_TILE_ZETA) {
+                        nvbo->placement.fpfn = vram_pages / 2;
+                        nvbo->placement.lpfn = ~0;
+                } else {
+                        nvbo->placement.fpfn = 0;
+                        nvbo->placement.lpfn = vram_pages / 2;
+                }
+        }
+}
+
 void
 nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t type, uint32_t busy)
 {
@@ -190,6 +217,8 @@ nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t type, uint32_t busy)
         pl->busy_placement = nvbo->busy_placements;
         set_placement_list(nvbo->busy_placements, &pl->num_busy_placement,
                            type | busy, flags);
+
+        set_placement_range(nvbo, type);
 }
 
 int
@@ -525,7 +554,8 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
                 stride  = 16 * 4;
                 height  = amount / stride;
 
-                if (new_mem->mem_type == TTM_PL_VRAM && nvbo->tile_flags) {
+                if (new_mem->mem_type == TTM_PL_VRAM &&
+                    nouveau_bo_tile_layout(nvbo)) {
                         ret = RING_SPACE(chan, 8);
                         if (ret)
                                 return ret;
@@ -546,7 +576,8 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
                         BEGIN_RING(chan, NvSubM2MF, 0x0200, 1);
                         OUT_RING  (chan, 1);
                 }
-                if (old_mem->mem_type == TTM_PL_VRAM && nvbo->tile_flags) {
+                if (old_mem->mem_type == TTM_PL_VRAM &&
+                    nouveau_bo_tile_layout(nvbo)) {
                         ret = RING_SPACE(chan, 8);
                         if (ret)
                                 return ret;
@@ -753,7 +784,8 @@ nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem,
         if (dev_priv->card_type == NV_50) {
                 ret = nv50_mem_vm_bind_linear(dev,
                                               offset + dev_priv->vm_vram_base,
-                                              new_mem->size, nvbo->tile_flags,
+                                              new_mem->size,
+                                              nouveau_bo_tile_layout(nvbo),
                                               offset);
                 if (ret)
                         return ret;
@@ -894,7 +926,8 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
          * nothing to do here.
          */
         if (bo->mem.mem_type != TTM_PL_VRAM) {
-                if (dev_priv->card_type < NV_50 || !nvbo->tile_flags)
+                if (dev_priv->card_type < NV_50 ||
+                    !nouveau_bo_tile_layout(nvbo))
                         return 0;
         }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 0871495096f..52c356e9a3d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -281,7 +281,7 @@ detect_analog:
         nv_encoder = find_encoder_by_type(connector, OUTPUT_ANALOG);
         if (!nv_encoder && !nouveau_tv_disable)
                 nv_encoder = find_encoder_by_type(connector, OUTPUT_TV);
-        if (nv_encoder) {
+        if (nv_encoder && force) {
                 struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
                 struct drm_encoder_helper_funcs *helper =
                                                 encoder->helper_private;
@@ -641,11 +641,28 @@ nouveau_connector_get_modes(struct drm_connector *connector)
         return ret;
 }
 
+static unsigned
+get_tmds_link_bandwidth(struct drm_connector *connector)
+{
+        struct nouveau_connector *nv_connector = nouveau_connector(connector);
+        struct drm_nouveau_private *dev_priv = connector->dev->dev_private;
+        struct dcb_entry *dcb = nv_connector->detected_encoder->dcb;
+
+        if (dcb->location != DCB_LOC_ON_CHIP ||
+            dev_priv->chipset >= 0x46)
+                return 165000;
+        else if (dev_priv->chipset >= 0x40)
+                return 155000;
+        else if (dev_priv->chipset >= 0x18)
+                return 135000;
+        else
+                return 112000;
+}
+
 static int
 nouveau_connector_mode_valid(struct drm_connector *connector,
                              struct drm_display_mode *mode)
 {
-        struct drm_nouveau_private *dev_priv = connector->dev->dev_private;
         struct nouveau_connector *nv_connector = nouveau_connector(connector);
         struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
         struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
@@ -663,11 +680,9 @@ nouveau_connector_mode_valid(struct drm_connector *connector,
                 max_clock = 400000;
                 break;
         case OUTPUT_TMDS:
-                if ((dev_priv->card_type >= NV_50 && !nouveau_duallink) ||
-                    !nv_encoder->dcb->duallink_possible)
-                        max_clock = 165000;
-                else
-                        max_clock = 330000;
+                max_clock = get_tmds_link_bandwidth(connector);
+                if (nouveau_duallink && nv_encoder->dcb->duallink_possible)
+                        max_clock *= 2;
                 break;
         case OUTPUT_ANALOG:
                 max_clock = nv_encoder->dcb->crtconf.maxfreq;
@@ -709,44 +724,6 @@ nouveau_connector_best_encoder(struct drm_connector *connector)
         return NULL;
 }
 
-void
-nouveau_connector_set_polling(struct drm_connector *connector)
-{
-        struct drm_device *dev = connector->dev;
-        struct drm_nouveau_private *dev_priv = dev->dev_private;
-        struct drm_crtc *crtc;
-        bool spare_crtc = false;
-
-        list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-                spare_crtc |= !crtc->enabled;
-
-        connector->polled = 0;
-
-        switch (connector->connector_type) {
-        case DRM_MODE_CONNECTOR_VGA:
-        case DRM_MODE_CONNECTOR_TV:
-                if (dev_priv->card_type >= NV_50 ||
-                    (nv_gf4_disp_arch(dev) && spare_crtc))
-                        connector->polled = DRM_CONNECTOR_POLL_CONNECT;
-                break;
-
-        case DRM_MODE_CONNECTOR_DVII:
-        case DRM_MODE_CONNECTOR_DVID:
-        case DRM_MODE_CONNECTOR_HDMIA:
-        case DRM_MODE_CONNECTOR_DisplayPort:
-        case DRM_MODE_CONNECTOR_eDP:
-                if (dev_priv->card_type >= NV_50)
-                        connector->polled = DRM_CONNECTOR_POLL_HPD;
-                else if (connector->connector_type == DRM_MODE_CONNECTOR_DVID ||
-                         spare_crtc)
-                        connector->polled = DRM_CONNECTOR_POLL_CONNECT;
-                break;
-
-        default:
-                break;
-        }
-}
-
 static const struct drm_connector_helper_funcs
 nouveau_connector_helper_funcs = {
         .get_modes = nouveau_connector_get_modes,
@@ -872,6 +849,7 @@ nouveau_connector_create(struct drm_device *dev, int index)
                                         dev->mode_config.scaling_mode_property,
                                         nv_connector->scaling_mode);
                 }
+                connector->polled = DRM_CONNECTOR_POLL_CONNECT;
                 /* fall-through */
         case DCB_CONNECTOR_TV_0:
         case DCB_CONNECTOR_TV_1:
@@ -888,11 +866,16 @@ nouveau_connector_create(struct drm_device *dev, int index)
                                 dev->mode_config.dithering_mode_property,
                                 nv_connector->use_dithering ?
                                 DRM_MODE_DITHERING_ON : DRM_MODE_DITHERING_OFF);
+
+                if (dcb->type != DCB_CONNECTOR_LVDS) {
+                        if (dev_priv->card_type >= NV_50)
+                                connector->polled = DRM_CONNECTOR_POLL_HPD;
+                        else
+                                connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+                }
                 break;
         }
 
-        nouveau_connector_set_polling(connector);
-
         drm_sysfs_connector_add(connector);
         dcb->drm = connector;
         return dcb->drm;
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index c21ed6b16f8..711b1e9203a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -52,9 +52,6 @@ static inline struct nouveau_connector *nouveau_connector(
 struct drm_connector *
 nouveau_connector_create(struct drm_device *, int index);
 
-void
-nouveau_connector_set_polling(struct drm_connector *);
-
 int
 nouveau_connector_bpp(struct drm_connector *);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 3a07e580d27..1c7db64c03b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -100,6 +100,9 @@ struct nouveau_bo {
         int pin_refcnt;
 };
 
+#define nouveau_bo_tile_layout(nvbo)                            \
+        ((nvbo)->tile_flags & NOUVEAU_GEM_TILE_LAYOUT_MASK)
+
 static inline struct nouveau_bo *
 nouveau_bo(struct ttm_buffer_object *bo)
 {
@@ -304,6 +307,7 @@ struct nouveau_fifo_engine {
         void (*destroy_context)(struct nouveau_channel *);
         int  (*load_context)(struct nouveau_channel *);
         int  (*unload_context)(struct drm_device *);
+        void (*tlb_flush)(struct drm_device *dev);
 };
 
 struct nouveau_pgraph_object_method {
@@ -336,6 +340,7 @@ struct nouveau_pgraph_engine {
         void (*destroy_context)(struct nouveau_channel *);
         int  (*load_context)(struct nouveau_channel *);
         int  (*unload_context)(struct drm_device *);
+        void (*tlb_flush)(struct drm_device *dev);
 
         void (*set_region_tiling)(struct drm_device *dev, int i, uint32_t addr,
                                   uint32_t size, uint32_t pitch);
@@ -485,13 +490,13 @@ enum nv04_fp_display_regs {
 };
 
 struct nv04_crtc_reg {
-        unsigned char MiscOutReg;     /* */
+        unsigned char MiscOutReg;
         uint8_t CRTC[0xa0];
         uint8_t CR58[0x10];
         uint8_t Sequencer[5];
         uint8_t Graphics[9];
         uint8_t Attribute[21];
-        unsigned char DAC[768];       /* Internal Colorlookuptable */
+        unsigned char DAC[768];
 
         /* PCRTC regs */
         uint32_t fb_start;
@@ -539,43 +544,9 @@ struct nv04_output_reg {
 };
 
 struct nv04_mode_state {
-        uint32_t bpp;
-        uint32_t width;
-        uint32_t height;
-        uint32_t interlace;
-        uint32_t repaint0;
-        uint32_t repaint1;
-        uint32_t screen;
-        uint32_t scale;
-        uint32_t dither;
-        uint32_t extra;
-        uint32_t fifo;
-        uint32_t pixel;
-        uint32_t horiz;
-        int arbitration0;
-        int arbitration1;
-        uint32_t pll;
-        uint32_t pllB;
-        uint32_t vpll;
-        uint32_t vpll2;
-        uint32_t vpllB;
-        uint32_t vpll2B;
+        struct nv04_crtc_reg crtc_reg[2];
         uint32_t pllsel;
         uint32_t sel_clk;
-        uint32_t general;
-        uint32_t crtcOwner;
-        uint32_t head;
-        uint32_t head2;
-        uint32_t cursorConfig;
-        uint32_t cursor0;
-        uint32_t cursor1;
-        uint32_t cursor2;
-        uint32_t timingH;
-        uint32_t timingV;
-        uint32_t displayV;
-        uint32_t crtcSync;
-
-        struct nv04_crtc_reg crtc_reg[2];
 };
 
 enum nouveau_card_type {
@@ -613,6 +584,12 @@ struct drm_nouveau_private {
         struct work_struct irq_work;
         struct work_struct hpd_work;
 
+        struct {
+                spinlock_t lock;
+                uint32_t hpd0_bits;
+                uint32_t hpd1_bits;
+        } hpd_state;
+
         struct list_head vbl_waiting;
 
         struct {
@@ -1045,6 +1022,7 @@ extern int  nv50_fifo_create_context(struct nouveau_channel *);
 extern void nv50_fifo_destroy_context(struct nouveau_channel *);
 extern int  nv50_fifo_load_context(struct nouveau_channel *);
 extern int  nv50_fifo_unload_context(struct drm_device *);
+extern void nv50_fifo_tlb_flush(struct drm_device *dev);
 
 /* nvc0_fifo.c */
 extern int  nvc0_fifo_init(struct drm_device *);
@@ -1122,6 +1100,8 @@ extern int  nv50_graph_load_context(struct nouveau_channel *);
 extern int  nv50_graph_unload_context(struct drm_device *);
 extern void nv50_graph_context_switch(struct drm_device *);
 extern int  nv50_grctx_init(struct nouveau_grctx *);
+extern void nv50_graph_tlb_flush(struct drm_device *dev);
+extern void nv86_graph_tlb_flush(struct drm_device *dev);
 
 /* nvc0_graph.c */
 extern int  nvc0_graph_init(struct drm_device *);
@@ -1239,7 +1219,6 @@ extern u16 nouveau_bo_rd16(struct nouveau_bo *nvbo, unsigned index);
 extern void nouveau_bo_wr16(struct nouveau_bo *nvbo, unsigned index, u16 val);
 extern u32 nouveau_bo_rd32(struct nouveau_bo *nvbo, unsigned index);
 extern void nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val);
-extern int nouveau_bo_sync_gpu(struct nouveau_bo *, struct nouveau_channel *);
 
 /* nouveau_fence.c */
 struct nouveau_fence;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 441b12420bb..ab1bbfbf266 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -249,6 +249,7 @@ alloc_semaphore(struct drm_device *dev)
 {
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         struct nouveau_semaphore *sema;
+        int ret;
 
         if (!USE_SEMA(dev))
                 return NULL;
@@ -257,10 +258,14 @@ alloc_semaphore(struct drm_device *dev)
         if (!sema)
                 goto fail;
 
+        ret = drm_mm_pre_get(&dev_priv->fence.heap);
+        if (ret)
+                goto fail;
+
         spin_lock(&dev_priv->fence.lock);
         sema->mem = drm_mm_search_free(&dev_priv->fence.heap, 4, 0, 0);
         if (sema->mem)
-                sema->mem = drm_mm_get_block(sema->mem, 4, 0);
+                sema->mem = drm_mm_get_block_atomic(sema->mem, 4, 0);
         spin_unlock(&dev_priv->fence.lock);
 
         if (!sema->mem)
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 5c4c929d7f7..9a1fdcf400c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -107,23 +107,29 @@ nouveau_gem_info(struct drm_gem_object *gem, struct drm_nouveau_gem_info *rep)
 }
 
 static bool
-nouveau_gem_tile_flags_valid(struct drm_device *dev, uint32_t tile_flags) {
-        switch (tile_flags) {
-        case 0x0000:
-        case 0x1800:
-        case 0x2800:
-        case 0x4800:
-        case 0x7000:
-        case 0x7400:
-        case 0x7a00:
-        case 0xe000:
-                break;
-        default:
-                NV_ERROR(dev, "bad page flags: 0x%08x\n", tile_flags);
-                return false;
+nouveau_gem_tile_flags_valid(struct drm_device *dev, uint32_t tile_flags)
+{
+        struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+        if (dev_priv->card_type >= NV_50) {
+                switch (tile_flags & NOUVEAU_GEM_TILE_LAYOUT_MASK) {
+                case 0x0000:
+                case 0x1800:
+                case 0x2800:
+                case 0x4800:
+                case 0x7000:
+                case 0x7400:
+                case 0x7a00:
+                case 0xe000:
+                        return true;
+                }
+        } else {
+                if (!(tile_flags & NOUVEAU_GEM_TILE_LAYOUT_MASK))
+                        return true;
         }
 
-        return true;
+        NV_ERROR(dev, "bad page flags: 0x%08x\n", tile_flags);
+        return false;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nouveau_hw.c b/drivers/gpu/drm/nouveau/nouveau_hw.c
index bed669a54a2..b9672a05c41 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hw.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hw.c
@@ -519,11 +519,11 @@ nouveau_hw_fix_bad_vpll(struct drm_device *dev, int head)
 
         struct pll_lims pll_lim;
         struct nouveau_pll_vals pv;
-        uint32_t pllreg = head ? NV_RAMDAC_VPLL2 : NV_PRAMDAC_VPLL_COEFF;
+        enum pll_types pll = head ? PLL_VPLL1 : PLL_VPLL0;
 
-        if (get_pll_limits(dev, pllreg, &pll_lim))
+        if (get_pll_limits(dev, pll, &pll_lim))
                 return;
-        nouveau_hw_get_pllvals(dev, pllreg, &pv);
+        nouveau_hw_get_pllvals(dev, pll, &pv);
 
         if (pv.M1 >= pll_lim.vco1.min_m && pv.M1 <= pll_lim.vco1.max_m &&
             pv.N1 >= pll_lim.vco1.min_n && pv.N1 <= pll_lim.vco1.max_n &&
@@ -536,7 +536,7 @@ nouveau_hw_fix_bad_vpll(struct drm_device *dev, int head)
         pv.M1 = pll_lim.vco1.max_m;
         pv.N1 = pll_lim.vco1.min_n;
         pv.log2P = pll_lim.max_usable_log2p;
-        nouveau_hw_setpll(dev, pllreg, &pv);
+        nouveau_hw_setpll(dev, pll_lim.reg, &pv);
 }
 
 /*
diff --git a/drivers/gpu/drm/nouveau/nouveau_hw.h b/drivers/gpu/drm/nouveau/nouveau_hw.h
index 869130f8360..2989090b943 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hw.h
+++ b/drivers/gpu/drm/nouveau/nouveau_hw.h
@@ -416,6 +416,25 @@ nv_fix_nv40_hw_cursor(struct drm_device *dev, int head)
 }
 
 static inline void
+nv_set_crtc_base(struct drm_device *dev, int head, uint32_t offset)
+{
+        struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+        NVWriteCRTC(dev, head, NV_PCRTC_START, offset);
+
+        if (dev_priv->card_type == NV_04) {
+                /*
+                 * Hilarious, the 24th bit doesn't want to stick to
+                 * PCRTC_START...
+                 */
+                int cre_heb = NVReadVgaCrtc(dev, head, NV_CIO_CRE_HEB__INDEX);
+
+                NVWriteVgaCrtc(dev, head, NV_CIO_CRE_HEB__INDEX,
+                               (cre_heb & ~0x40) | ((offset >> 18) & 0x40));
+        }
+}
+
+static inline void
 nv_show_cursor(struct drm_device *dev, int head, bool show)
 {
         struct drm_nouveau_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
index fdd7e3de79c..cb389d01432 100644
--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
+++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
@@ -256,7 +256,7 @@ nouveau_i2c_find(struct drm_device *dev, int index)
         if (index >= DCB_MAX_NUM_I2C_ENTRIES)
                 return NULL;
 
-        if (dev_priv->chipset >= NV_50 && (i2c->entry & 0x00000100)) {
+        if (dev_priv->card_type >= NV_50 && (i2c->entry & 0x00000100)) {
                 uint32_t reg = 0xe500, val;
 
                 if (i2c->port_type == 6) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_irq.c b/drivers/gpu/drm/nouveau/nouveau_irq.c
index 6fd51a51c60..7bfd9e6c9d6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_irq.c
+++ b/drivers/gpu/drm/nouveau/nouveau_irq.c
@@ -42,6 +42,13 @@
 #include "nouveau_connector.h"
 #include "nv50_display.h"
 
+static DEFINE_RATELIMIT_STATE(nouveau_ratelimit_state, 3 * HZ, 20);
+
+static int nouveau_ratelimit(void)
+{
+        return __ratelimit(&nouveau_ratelimit_state);
+}
+
 void
 nouveau_irq_preinstall(struct drm_device *dev)
 {
@@ -53,6 +60,7 @@ nouveau_irq_preinstall(struct drm_device *dev)
         if (dev_priv->card_type >= NV_50) {
                 INIT_WORK(&dev_priv->irq_work, nv50_display_irq_handler_bh);
                 INIT_WORK(&dev_priv->hpd_work, nv50_display_irq_hotplug_bh);
+                spin_lock_init(&dev_priv->hpd_state.lock);
                 INIT_LIST_HEAD(&dev_priv->vbl_waiting);
         }
 }
@@ -202,8 +210,8 @@ nouveau_fifo_irq_handler(struct drm_device *dev)
                 }
 
                 if (status & NV_PFIFO_INTR_DMA_PUSHER) {
-                        u32 get = nv_rd32(dev, 0x003244);
-                        u32 put = nv_rd32(dev, 0x003240);
+                        u32 dma_get = nv_rd32(dev, 0x003244);
+                        u32 dma_put = nv_rd32(dev, 0x003240);
                         u32 push = nv_rd32(dev, 0x003220);
                         u32 state = nv_rd32(dev, 0x003228);
 
@@ -213,16 +221,18 @@ nouveau_fifo_irq_handler(struct drm_device *dev)
                                 u32 ib_get = nv_rd32(dev, 0x003334);
                                 u32 ib_put = nv_rd32(dev, 0x003330);
 
-                                NV_INFO(dev, "PFIFO_DMA_PUSHER - Ch %d Get 0x%02x%08x "
+                                if (nouveau_ratelimit())
+                                        NV_INFO(dev, "PFIFO_DMA_PUSHER - Ch %d Get 0x%02x%08x "
                                              "Put 0x%02x%08x IbGet 0x%08x IbPut 0x%08x "
                                              "State 0x%08x Push 0x%08x\n",
-                                        chid, ho_get, get, ho_put, put, ib_get, ib_put,
-                                        state, push);
+                                                chid, ho_get, dma_get, ho_put,
+                                                dma_put, ib_get, ib_put, state,
+                                                push);
 
                                 /* METHOD_COUNT, in DMA_STATE on earlier chipsets */
                                 nv_wr32(dev, 0x003364, 0x00000000);
-                                if (get != put || ho_get != ho_put) {
-                                        nv_wr32(dev, 0x003244, put);
+                                if (dma_get != dma_put || ho_get != ho_put) {
+                                        nv_wr32(dev, 0x003244, dma_put);
                                         nv_wr32(dev, 0x003328, ho_put);
                                 } else
                                 if (ib_get != ib_put) {
@@ -231,10 +241,10 @@ nouveau_fifo_irq_handler(struct drm_device *dev)
                         } else {
                                 NV_INFO(dev, "PFIFO_DMA_PUSHER - Ch %d Get 0x%08x "
                                              "Put 0x%08x State 0x%08x Push 0x%08x\n",
-                                        chid, get, put, state, push);
+                                        chid, dma_get, dma_put, state, push);
 
-                                if (get != put)
-                                        nv_wr32(dev, 0x003244, put);
+                                if (dma_get != dma_put)
+                                        nv_wr32(dev, 0x003244, dma_put);
                         }
 
                         nv_wr32(dev, 0x003228, 0x00000000);
@@ -266,8 +276,9 @@ nouveau_fifo_irq_handler(struct drm_device *dev)
                 }
 
                 if (status) {
-                        NV_INFO(dev, "PFIFO_INTR 0x%08x - Ch %d\n",
-                                status, chid);
+                        if (nouveau_ratelimit())
+                                NV_INFO(dev, "PFIFO_INTR 0x%08x - Ch %d\n",
+                                        status, chid);
                         nv_wr32(dev, NV03_PFIFO_INTR_0, status);
                         status = 0;
                 }
@@ -544,13 +555,6 @@ nouveau_pgraph_intr_notify(struct drm_device *dev, uint32_t nsource)
                 nouveau_graph_dump_trap_info(dev, "PGRAPH_NOTIFY", &trap);
 }
 
-static DEFINE_RATELIMIT_STATE(nouveau_ratelimit_state, 3 * HZ, 20);
-
-static int nouveau_ratelimit(void)
-{
-        return __ratelimit(&nouveau_ratelimit_state);
-}
-
 
 static inline void
 nouveau_pgraph_intr_error(struct drm_device *dev, uint32_t nsource)
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index a163c7c612e..fe4a30dc4b4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -33,9 +33,9 @@
 #include "drmP.h"
 #include "drm.h"
 #include "drm_sarea.h"
-#include "nouveau_drv.h"
 
-#define MIN(a,b) a < b ? a : b
+#include "nouveau_drv.h"
+#include "nouveau_pm.h"
 
 /*
  * NV10-NV40 tiling helpers
@@ -175,11 +175,10 @@ nv50_mem_vm_bind_linear(struct drm_device *dev, uint64_t virt, uint32_t size,
                         }
                 }
         }
-        dev_priv->engine.instmem.flush(dev);
 
-        nv50_vm_flush(dev, 5);
-        nv50_vm_flush(dev, 0);
-        nv50_vm_flush(dev, 4);
+        dev_priv->engine.instmem.flush(dev);
+        dev_priv->engine.fifo.tlb_flush(dev);
+        dev_priv->engine.graph.tlb_flush(dev);
         nv50_vm_flush(dev, 6);
         return 0;
 }
@@ -209,11 +208,10 @@ nv50_mem_vm_unbind(struct drm_device *dev, uint64_t virt, uint32_t size)
                         pte++;
                 }
         }
-        dev_priv->engine.instmem.flush(dev);
 
-        nv50_vm_flush(dev, 5);
-        nv50_vm_flush(dev, 0);
-        nv50_vm_flush(dev, 4);
+        dev_priv->engine.instmem.flush(dev);
+        dev_priv->engine.fifo.tlb_flush(dev);
+        dev_priv->engine.graph.tlb_flush(dev);
         nv50_vm_flush(dev, 6);
 }
 
@@ -653,6 +651,7 @@ nouveau_mem_gart_init(struct drm_device *dev)
 void
 nouveau_mem_timing_init(struct drm_device *dev)
 {
+        /* cards < NVC0 only */
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         struct nouveau_pm_engine *pm = &dev_priv->engine.pm;
         struct nouveau_pm_memtimings *memtimings = &pm->memtimings;
@@ -719,14 +718,14 @@ nouveau_mem_timing_init(struct drm_device *dev)
                 tUNK_19 = 1;
                 tUNK_20 = 0;
                 tUNK_21 = 0;
-                switch (MIN(recordlen,21)) {
-                case 21:
+                switch (min(recordlen, 22)) {
+                case 22:
                         tUNK_21 = entry[21];
-                case 20:
+                case 21:
                         tUNK_20 = entry[20];
-                case 19:
+                case 20:
                         tUNK_19 = entry[19];
-                case 18:
+                case 19:
                         tUNK_18 = entry[18];
                 default:
                         tUNK_0  = entry[0];
@@ -756,24 +755,30 @@ nouveau_mem_timing_init(struct drm_device *dev)
                 timing->reg_100228 = (tUNK_12 << 16 | tUNK_11 << 8 | tUNK_10);
                 if(recordlen > 19) {
                         timing->reg_100228 += (tUNK_19 - 1) << 24;
-                } else {
+                }/* I cannot back-up this else-statement right now
+                         else {
                         timing->reg_100228 += tUNK_12 << 24;
-                }
+                }*/
 
                 /* XXX: reg_10022c */
+                timing->reg_10022c = tUNK_2 - 1;
 
                 timing->reg_100230 = (tUNK_20 << 24 | tUNK_21 << 16 |
                                       tUNK_13 << 8  | tUNK_13);
 
                 /* XXX: +6? */
                 timing->reg_100234 = (tRAS << 24 | (tUNK_19 + 6) << 8 | tRC);
-                if(tUNK_10 > tUNK_11) {
-                        timing->reg_100234 += tUNK_10 << 16;
-                } else {
-                        timing->reg_100234 += tUNK_11 << 16;
+                timing->reg_100234 += max(tUNK_10,tUNK_11) << 16;
+
+                /* XXX; reg_100238, reg_10023c
+                 * reg: 0x00??????
+                 * reg_10023c:
+                 *      0 for pre-NV50 cards
+                 *      0x????0202 for NV50+ cards (empirical evidence) */
+                if(dev_priv->card_type >= NV_50) {
+                        timing->reg_10023c = 0x202;
                 }
 
-                /* XXX; reg_100238, reg_10023c */
                 NV_DEBUG(dev, "Entry %d: 220: %08x %08x %08x %08x\n", i,
                          timing->reg_100220, timing->reg_100224,
                          timing->reg_100228, timing->reg_10022c);
diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_object.c
index 896cf863414..dd572adca02 100644
--- a/drivers/gpu/drm/nouveau/nouveau_object.c
+++ b/drivers/gpu/drm/nouveau/nouveau_object.c
@@ -129,7 +129,7 @@ nouveau_gpuobj_new(struct drm_device *dev, struct nouveau_channel *chan,
                         if (ramin == NULL) {
                                 spin_unlock(&dev_priv->ramin_lock);
                                 nouveau_gpuobj_ref(NULL, &gpuobj);
-                                return ret;
+                                return -ENOMEM;
                         }
 
                         ramin = drm_mm_get_block_atomic(ramin, size, align);
diff --git a/drivers/gpu/drm/nouveau/nouveau_pm.c b/drivers/gpu/drm/nouveau/nouveau_pm.c
index 1c99c55d6d4..9f7b158f582 100644
--- a/drivers/gpu/drm/nouveau/nouveau_pm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_pm.c
@@ -284,6 +284,7 @@ nouveau_sysfs_fini(struct drm_device *dev)
         }
 }
 
+#ifdef CONFIG_HWMON
 static ssize_t
 nouveau_hwmon_show_temp(struct device *d, struct device_attribute *a, char *buf)
 {
@@ -395,10 +396,12 @@ static struct attribute *hwmon_attributes[] = {
 static const struct attribute_group hwmon_attrgroup = {
         .attrs = hwmon_attributes,
 };
+#endif
 
 static int
 nouveau_hwmon_init(struct drm_device *dev)
 {
+#ifdef CONFIG_HWMON
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         struct nouveau_pm_engine *pm = &dev_priv->engine.pm;
         struct device *hwmon_dev;
@@ -425,13 +428,14 @@ nouveau_hwmon_init(struct drm_device *dev)
         }
 
         pm->hwmon = hwmon_dev;
-
+#endif
         return 0;
 }
 
 static void
 nouveau_hwmon_fini(struct drm_device *dev)
 {
+#ifdef CONFIG_HWMON
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         struct nouveau_pm_engine *pm = &dev_priv->engine.pm;
 
@@ -439,6 +443,7 @@ nouveau_hwmon_fini(struct drm_device *dev)
                 sysfs_remove_group(&pm->hwmon->kobj, &hwmon_attrgroup);
                 hwmon_device_unregister(pm->hwmon);
         }
+#endif
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nouveau_ramht.c b/drivers/gpu/drm/nouveau/nouveau_ramht.c
index 7f16697cc96..2d8580927ca 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ramht.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ramht.c
@@ -153,26 +153,42 @@ nouveau_ramht_insert(struct nouveau_channel *chan, u32 handle,
         return -ENOMEM;
 }
 
+static struct nouveau_ramht_entry *
+nouveau_ramht_remove_entry(struct nouveau_channel *chan, u32 handle)
+{
+        struct nouveau_ramht *ramht = chan ? chan->ramht : NULL;
+        struct nouveau_ramht_entry *entry;
+        unsigned long flags;
+
+        if (!ramht)
+                return NULL;
+
+        spin_lock_irqsave(&ramht->lock, flags);
+        list_for_each_entry(entry, &ramht->entries, head) {
+                if (entry->channel == chan &&
+                    (!handle || entry->handle == handle)) {
+                        list_del(&entry->head);
+                        spin_unlock_irqrestore(&ramht->lock, flags);
+
+                        return entry;
+                }
+        }
+        spin_unlock_irqrestore(&ramht->lock, flags);
+
+        return NULL;
+}
+
 static void
-nouveau_ramht_remove_locked(struct nouveau_channel *chan, u32 handle)
+nouveau_ramht_remove_hash(struct nouveau_channel *chan, u32 handle)
 {
         struct drm_device *dev = chan->dev;
         struct drm_nouveau_private *dev_priv = dev->dev_private;
         struct nouveau_instmem_engine *instmem = &dev_priv->engine.instmem;
         struct nouveau_gpuobj *ramht = chan->ramht->gpuobj;
-        struct nouveau_ramht_entry *entry, *tmp;
+        unsigned long flags;
         u32 co, ho;
 
-        list_for_each_entry_safe(entry, tmp, &chan->ramht->entries, head) {
-                if (entry->channel != chan || entry->handle != handle)
-                        continue;
-
-                nouveau_gpuobj_ref(NULL, &entry->gpuobj);
-                list_del(&entry->head);
-                kfree(entry);
-                break;
-        }
-
+        spin_lock_irqsave(&chan->ramht->lock, flags);
         co = ho = nouveau_ramht_hash_handle(chan, handle);
         do {
                 if (nouveau_ramht_entry_valid(dev, ramht, co) &&
@@ -184,7 +200,7 @@ nouveau_ramht_remove_locked(struct nouveau_channel *chan, u32 handle)
                         nv_wo32(ramht, co + 0, 0x00000000);
                         nv_wo32(ramht, co + 4, 0x00000000);
                         instmem->flush(dev);
-                        return;
+                        goto out;
                 }
 
                 co += 8;
@@ -194,17 +210,22 @@ nouveau_ramht_remove_locked(struct nouveau_channel *chan, u32 handle)
 
         NV_ERROR(dev, "RAMHT entry not found. ch=%d, handle=0x%08x\n",
                  chan->id, handle);
+out:
+        spin_unlock_irqrestore(&chan->ramht->lock, flags);
 }
 
 void
 nouveau_ramht_remove(struct nouveau_channel *chan, u32 handle)
 {
-        struct nouveau_ramht *ramht = chan->ramht;
-        unsigned long flags;
+        struct nouveau_ramht_entry *entry;
 
-        spin_lock_irqsave(&ramht->lock, flags);
-        nouveau_ramht_remove_locked(chan, handle);
-        spin_unlock_irqrestore(&ramht->lock, flags);
+        entry = nouveau_ramht_remove_entry(chan, handle);
+        if (!entry)
+                return;
+
+        nouveau_ramht_remove_hash(chan, entry->handle);
+        nouveau_gpuobj_ref(NULL, &entry->gpuobj);
+        kfree(entry);
 }
 
 struct nouveau_gpuobj *
@@ -265,23 +286,19 @@ void
 nouveau_ramht_ref(struct nouveau_ramht *ref, struct nouveau_ramht **ptr,
                   struct nouveau_channel *chan)
 {
-        struct nouveau_ramht_entry *entry, *tmp;
+        struct nouveau_ramht_entry *entry;
         struct nouveau_ramht *ramht;
-        unsigned long flags;
 
         if (ref)
                 kref_get(&ref->refcount);
 
         ramht = *ptr;
         if (ramht) {
-                spin_lock_irqsave(&ramht->lock, flags);
-                list_for_each_entry_safe(entry, tmp, &ramht->entries, head) {
-                        if (entry->channel != chan)
-                                continue;
-
-                        nouveau_ramht_remove_locked(chan, entry->handle);
+                while ((entry = nouveau_ramht_remove_entry(chan, 0))) {
+                        nouveau_ramht_remove_hash(chan, entry->handle);
+                        nouveau_gpuobj_ref(NULL, &entry->gpuobj);
+                        kfree(entry);
                 }
-                spin_unlock_irqrestore(&ramht->lock, flags);
 
                 kref_put(&ramht->refcount, nouveau_ramht_del);
         }
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 288bacac7e5..d4ac9700703 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -120,8 +120,8 @@ nouveau_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem)
         dev_priv->engine.instmem.flush(nvbe->dev);
 
         if (dev_priv->card_type == NV_50) {
-                nv50_vm_flush(dev, 5); /* PGRAPH */
-                nv50_vm_flush(dev, 0); /* PFIFO */
+                dev_priv->engine.fifo.tlb_flush(dev);
+                dev_priv->engine.graph.tlb_flush(dev);
         }
 
         nvbe->bound = true;
@@ -162,8 +162,8 @@ nouveau_sgdma_unbind(struct ttm_backend *be)
         dev_priv->engine.instmem.flush(nvbe->dev);
 
         if (dev_priv->card_type == NV_50) {
-                nv50_vm_flush(dev, 5);
-                nv50_vm_flush(dev, 0);
+                dev_priv->engine.fifo.tlb_flush(dev);
+                dev_priv->engine.graph.tlb_flush(dev);
         }
 
         nvbe->bound = false;
@@ -224,7 +224,11 @@ nouveau_sgdma_init(struct drm_device *dev)
         int i, ret;
 
         if (dev_priv->card_type < NV_50) {
-                aper_size = (64 * 1024 * 1024);
+                if(dev_priv->ramin_rsvd_vram < 2 * 1024 * 1024)
+                        aper_size = 64 * 1024 * 1024;
+                else
+                        aper_size = 512 * 1024 * 1024;
+
                 obj_size  = (aper_size >> NV_CTXDMA_PAGE_SHIFT) * 4;
                 obj_size += 8; /* ctxdma header */
         } else {
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index ed7757f1408..049f755567e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -354,6 +354,15 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev)
                 engine->graph.destroy_context   = nv50_graph_destroy_context;
                 engine->graph.load_context      = nv50_graph_load_context;
                 engine->graph.unload_context    = nv50_graph_unload_context;
+                if (dev_priv->chipset != 0x86)
+                        engine->graph.tlb_flush = nv50_graph_tlb_flush;
+                else {
+                        /* from what i can see nvidia do this on every
+                         * pre-NVA3 board except NVAC, but, we've only
+                         * ever seen problems on NV86
+                         */
+                        engine->graph.tlb_flush = nv86_graph_tlb_flush;
+                }
                 engine->fifo.channels           = 128;
                 engine->fifo.init               = nv50_fifo_init;
                 engine->fifo.takedown           = nv50_fifo_takedown;
@@ -365,6 +374,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev)
                 engine->fifo.destroy_context    = nv50_fifo_destroy_context;
                 engine->fifo.load_context       = nv50_fifo_load_context;
                 engine->fifo.unload_context     = nv50_fifo_unload_context;
+                engine->fifo.tlb_flush          = nv50_fifo_tlb_flush;
                 engine->display.early_init      = nv50_display_early_init;
                 engine->display.late_takedown   = nv50_display_late_takedown;
                 engine->display.create          = nv50_display_create;
@@ -1041,6 +1051,9 @@ int nouveau_ioctl_getparam(struct drm_device *dev, void *data,
         case NOUVEAU_GETPARAM_PTIMER_TIME:
                 getparam->value = dev_priv->engine.timer.read(dev);
                 break;
+        case NOUVEAU_GETPARAM_HAS_BO_USAGE:
+                getparam->value = 1;
+                break;
         case NOUVEAU_GETPARAM_GRAPH_UNITS:
                 /* NV40 and NV50 versions are quite different, but register
                  * address is the same. User is supposed to know the card
@@ -1051,7 +1064,7 @@ int nouveau_ioctl_getparam(struct drm_device *dev, void *data,
                 }
                 /* FALLTHRU */
         default:
-                NV_ERROR(dev, "unknown parameter %lld\n", getparam->param);
+                NV_DEBUG(dev, "unknown parameter %lld\n", getparam->param);
                 return -EINVAL;
         }
 
@@ -1066,7 +1079,7 @@ nouveau_ioctl_setparam(struct drm_device *dev, void *data,
 
         switch (setparam->param) {
         default:
-                NV_ERROR(dev, "unknown parameter %lld\n", setparam->param);
+                NV_DEBUG(dev, "unknown parameter %lld\n", setparam->param);
                 return -EINVAL;
         }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_temp.c b/drivers/gpu/drm/nouveau/nouveau_temp.c
index 16bbbf1eff6..7ecc4adc1e4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_temp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_temp.c
@@ -191,7 +191,7 @@ nv40_temp_get(struct drm_device *dev)
         int offset = sensor->offset_mult / sensor->offset_div;
         int core_temp;
 
-        if (dev_priv->chipset >= 0x50) {
+        if (dev_priv->card_type >= NV_50) {
                 core_temp = nv_rd32(dev, 0x20008);
         } else {
                 core_temp = nv_rd32(dev, 0x0015b4) & 0x1fff;
diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c
index c71abc2a34d..40e18074162 100644
--- a/drivers/gpu/drm/nouveau/nv04_crtc.c
+++ b/drivers/gpu/drm/nouveau/nv04_crtc.c
@@ -158,7 +158,6 @@ nv_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
         struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
         struct drm_device *dev = crtc->dev;
-        struct drm_connector *connector;
         unsigned char seq1 = 0, crtc17 = 0;
         unsigned char crtc1A;
 
@@ -213,10 +212,6 @@ nv_crtc_dpms(struct drm_crtc *crtc, int mode)
         NVVgaSeqReset(dev, nv_crtc->index, false);
 
         NVWriteVgaCrtc(dev, nv_crtc->index, NV_CIO_CRE_RPC1_INDEX, crtc1A);
-
-        /* Update connector polling modes */
-        list_for_each_entry(connector, &dev->mode_config.connector_list, head)
-                nouveau_connector_set_polling(connector);
 }
 
 static bool
@@ -831,7 +826,7 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
         /* Update the framebuffer location. */
         regp->fb_start = nv_crtc->fb.offset & ~3;
         regp->fb_start += (y * drm_fb->pitch) + (x * drm_fb->bits_per_pixel / 8);
-        NVWriteCRTC(dev, nv_crtc->index, NV_PCRTC_START, regp->fb_start);
+        nv_set_crtc_base(dev, nv_crtc->index, regp->fb_start);
 
         /* Update the arbitration parameters. */
         nouveau_calc_arb(dev, crtc->mode.clock, drm_fb->bits_per_pixel,
diff --git a/drivers/gpu/drm/nouveau/nv04_dfp.c b/drivers/gpu/drm/nouveau/nv04_dfp.c
index c936403b26e..ef23550407b 100644
--- a/drivers/gpu/drm/nouveau/nv04_dfp.c
+++ b/drivers/gpu/drm/nouveau/nv04_dfp.c
@@ -185,14 +185,15 @@ static bool nv04_dfp_mode_fixup(struct drm_encoder *encoder,
         struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
         struct nouveau_connector *nv_connector = nouveau_encoder_connector_get(nv_encoder);
 
-        /* For internal panels and gpu scaling on DVI we need the native mode */
-        if (nv_connector->scaling_mode != DRM_MODE_SCALE_NONE) {
-                if (!nv_connector->native_mode)
-                        return false;
+        if (!nv_connector->native_mode ||
+            nv_connector->scaling_mode == DRM_MODE_SCALE_NONE ||
+            mode->hdisplay > nv_connector->native_mode->hdisplay ||
+            mode->vdisplay > nv_connector->native_mode->vdisplay) {
+                nv_encoder->mode = *adjusted_mode;
+
+        } else {
                 nv_encoder->mode = *nv_connector->native_mode;
                 adjusted_mode->clock = nv_connector->native_mode->clock;
-        } else {
-                nv_encoder->mode = *adjusted_mode;
         }
 
         return true;
diff --git a/drivers/gpu/drm/nouveau/nv04_pm.c b/drivers/gpu/drm/nouveau/nv04_pm.c
index 6a6eb697d38..eb1c70dd82e 100644
--- a/drivers/gpu/drm/nouveau/nv04_pm.c
+++ b/drivers/gpu/drm/nouveau/nv04_pm.c
@@ -76,6 +76,15 @@ nv04_pm_clock_set(struct drm_device *dev, void *pre_state)
                 reg += 4;
 
         nouveau_hw_setpll(dev, reg, &state->calc);
+
+        if (dev_priv->card_type < NV_30 && reg == NV_PRAMDAC_MPLL_COEFF) {
+                if (dev_priv->card_type == NV_20)
+                        nv_mask(dev, 0x1002c4, 0, 1 << 20);
+
+                /* Reset the DLLs */
+                nv_mask(dev, 0x1002c0, 0, 1 << 8);
+        }
+
         kfree(state);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nv50_calc.c b/drivers/gpu/drm/nouveau/nv50_calc.c
index 2cdc2bfe717..de81151648f 100644
--- a/drivers/gpu/drm/nouveau/nv50_calc.c
+++ b/drivers/gpu/drm/nouveau/nv50_calc.c
@@ -51,24 +51,28 @@ nv50_calc_pll2(struct drm_device *dev, struct pll_lims *pll, int clk,
                int *N, int *fN, int *M, int *P)
 {
         fixed20_12 fb_div, a, b;
+        u32 refclk = pll->refclk / 10;
+        u32 max_vco_freq = pll->vco1.maxfreq / 10;
+        u32 max_vco_inputfreq = pll->vco1.max_inputfreq / 10;
+        clk /= 10;
 
-        *P = pll->vco1.maxfreq / clk;
+        *P = max_vco_freq / clk;
         if (*P > pll->max_p)
                 *P = pll->max_p;
         if (*P < pll->min_p)
                 *P = pll->min_p;
 
-        /* *M = ceil(refclk / pll->vco.max_inputfreq); */
-        a.full = dfixed_const(pll->refclk);
-        b.full = dfixed_const(pll->vco1.max_inputfreq);
+        /* *M = floor((refclk + max_vco_inputfreq) / max_vco_inputfreq); */
+        a.full = dfixed_const(refclk + max_vco_inputfreq);
+        b.full = dfixed_const(max_vco_inputfreq);
         a.full = dfixed_div(a, b);
-        a.full = dfixed_ceil(a);
+        a.full = dfixed_floor(a);
         *M = dfixed_trunc(a);
 
         /* fb_div = (vco * *M) / refclk; */
         fb_div.full = dfixed_const(clk * *P);
         fb_div.full = dfixed_mul(fb_div, a);
-        a.full = dfixed_const(pll->refclk);
+        a.full = dfixed_const(refclk);
         fb_div.full = dfixed_div(fb_div, a);
 
         /* *N = floor(fb_div); */
diff --git a/drivers/gpu/drm/nouveau/nv50_crtc.c b/drivers/gpu/drm/nouveau/nv50_crtc.c
index 16380d52cd8..56476d0c6de 100644
--- a/drivers/gpu/drm/nouveau/nv50_crtc.c
+++ b/drivers/gpu/drm/nouveau/nv50_crtc.c
@@ -546,7 +546,7 @@ nv50_crtc_do_mode_set_base(struct drm_crtc *crtc,
         }
 
         nv_crtc->fb.offset = fb->nvbo->bo.offset - dev_priv->vm_vram_base;
-        nv_crtc->fb.tile_flags = fb->nvbo->tile_flags;
+        nv_crtc->fb.tile_flags = nouveau_bo_tile_layout(fb->nvbo);
         nv_crtc->fb.cpp = drm_fb->bits_per_pixel / 8;
         if (!nv_crtc->fb.blanked && dev_priv->chipset != 0x50) {
                 ret = RING_SPACE(evo, 2);
@@ -578,7 +578,7 @@ nv50_crtc_do_mode_set_base(struct drm_crtc *crtc,
                                   fb->nvbo->tile_mode);
         }
         if (dev_priv->chipset == 0x50)
-                OUT_RING(evo, (fb->nvbo->tile_flags << 8) | format);
+                OUT_RING(evo, (nv_crtc->fb.tile_flags << 8) | format);
         else
                 OUT_RING(evo, format);
 
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 55c9663ef2b..f624c611dde 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -1032,11 +1032,18 @@ nv50_display_irq_hotplug_bh(struct work_struct *work)
         struct drm_connector *connector;
         const uint32_t gpio_reg[4] = { 0xe104, 0xe108, 0xe280, 0xe284 };
         uint32_t unplug_mask, plug_mask, change_mask;
-        uint32_t hpd0, hpd1 = 0;
+        uint32_t hpd0, hpd1;
 
-        hpd0 = nv_rd32(dev, 0xe054) & nv_rd32(dev, 0xe050);
+        spin_lock_irq(&dev_priv->hpd_state.lock);
+        hpd0 = dev_priv->hpd_state.hpd0_bits;
+        dev_priv->hpd_state.hpd0_bits = 0;
+        hpd1 = dev_priv->hpd_state.hpd1_bits;
+        dev_priv->hpd_state.hpd1_bits = 0;
+        spin_unlock_irq(&dev_priv->hpd_state.lock);
+
+        hpd0 &= nv_rd32(dev, 0xe050);
         if (dev_priv->chipset >= 0x90)
-                hpd1 = nv_rd32(dev, 0xe074) & nv_rd32(dev, 0xe070);
+                hpd1 &= nv_rd32(dev, 0xe070);
 
         plug_mask   = (hpd0 & 0x0000ffff) | (hpd1 << 16);
         unplug_mask = (hpd0 >> 16) | (hpd1 & 0xffff0000);
@@ -1078,10 +1085,6 @@ nv50_display_irq_hotplug_bh(struct work_struct *work)
                         helper->dpms(connector->encoder, DRM_MODE_DPMS_OFF);
         }
 
-        nv_wr32(dev, 0xe054, nv_rd32(dev, 0xe054));
-        if (dev_priv->chipset >= 0x90)
-                nv_wr32(dev, 0xe074, nv_rd32(dev, 0xe074));
-
         drm_helper_hpd_irq_event(dev);
 }
 
@@ -1092,8 +1095,22 @@ nv50_display_irq_handler(struct drm_device *dev)
         uint32_t delayed = 0;
 
         if (nv_rd32(dev, NV50_PMC_INTR_0) & NV50_PMC_INTR_0_HOTPLUG) {
-                if (!work_pending(&dev_priv->hpd_work))
-                        queue_work(dev_priv->wq, &dev_priv->hpd_work);
+                uint32_t hpd0_bits, hpd1_bits = 0;
+
+                hpd0_bits = nv_rd32(dev, 0xe054);
+                nv_wr32(dev, 0xe054, hpd0_bits);
+
+                if (dev_priv->chipset >= 0x90) {
+                        hpd1_bits = nv_rd32(dev, 0xe074);
+                        nv_wr32(dev, 0xe074, hpd1_bits);
+                }
+
+                spin_lock(&dev_priv->hpd_state.lock);
+                dev_priv->hpd_state.hpd0_bits |= hpd0_bits;
+                dev_priv->hpd_state.hpd1_bits |= hpd1_bits;
+                spin_unlock(&dev_priv->hpd_state.lock);
+
+                queue_work(dev_priv->wq, &dev_priv->hpd_work);
         }
 
         while (nv_rd32(dev, NV50_PMC_INTR_0) & NV50_PMC_INTR_0_DISPLAY) {
diff --git a/drivers/gpu/drm/nouveau/nv50_fifo.c b/drivers/gpu/drm/nouveau/nv50_fifo.c
index a46a961102f..1da65bd60c1 100644
--- a/drivers/gpu/drm/nouveau/nv50_fifo.c
+++ b/drivers/gpu/drm/nouveau/nv50_fifo.c
@@ -464,3 +464,8 @@ nv50_fifo_unload_context(struct drm_device *dev)
         return 0;
 }
 
+void
+nv50_fifo_tlb_flush(struct drm_device *dev)
+{
+        nv50_vm_flush(dev, 5);
+}
diff --git a/drivers/gpu/drm/nouveau/nv50_graph.c b/drivers/gpu/drm/nouveau/nv50_graph.c
index cbf5ae2f67d..8b669d0af61 100644
--- a/drivers/gpu/drm/nouveau/nv50_graph.c
+++ b/drivers/gpu/drm/nouveau/nv50_graph.c
@@ -402,3 +402,55 @@ struct nouveau_pgraph_object_class nv50_graph_grclass[] = {
         { 0x8597, false, NULL }, /* tesla (nva3, nva5, nva8) */
         {}
 };
+
+void
+nv50_graph_tlb_flush(struct drm_device *dev)
+{
+        nv50_vm_flush(dev, 0);
+}
+
+void
+nv86_graph_tlb_flush(struct drm_device *dev)
+{
+        struct drm_nouveau_private *dev_priv = dev->dev_private;
+        struct nouveau_timer_engine *ptimer = &dev_priv->engine.timer;
+        bool idle, timeout = false;
+        unsigned long flags;
+        u64 start;
+        u32 tmp;
+
+        spin_lock_irqsave(&dev_priv->context_switch_lock, flags);
+        nv_mask(dev, 0x400500, 0x00000001, 0x00000000);
+
+        start = ptimer->read(dev);
+        do {
+                idle = true;
+
+                for (tmp = nv_rd32(dev, 0x400380); tmp && idle; tmp >>= 3) {
+                        if ((tmp & 7) == 1)
+                                idle = false;
+                }
+
+                for (tmp = nv_rd32(dev, 0x400384); tmp && idle; tmp >>= 3) {
+                        if ((tmp & 7) == 1)
+                                idle = false;
+                }
+
+                for (tmp = nv_rd32(dev, 0x400388); tmp && idle; tmp >>= 3) {
+                        if ((tmp & 7) == 1)
+                                idle = false;
+                }
+        } while (!idle && !(timeout = ptimer->read(dev) - start > 2000000000));
+
+        if (timeout) {
+                NV_ERROR(dev, "PGRAPH TLB flush idle timeout fail: "
+                              "0x%08x 0x%08x 0x%08x 0x%08x\n",
+                         nv_rd32(dev, 0x400700), nv_rd32(dev, 0x400380),
+                         nv_rd32(dev, 0x400384), nv_rd32(dev, 0x400388));
+        }
+
+        nv50_vm_flush(dev, 0);
+
+        nv_mask(dev, 0x400500, 0x00000001, 0x00000001);
+        spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags);
+}
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index a53fc974332..b773229b764 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -402,7 +402,6 @@ nv50_instmem_bind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj)
         }
         dev_priv->engine.instmem.flush(dev);
 
-        nv50_vm_flush(dev, 4);
         nv50_vm_flush(dev, 6);
 
         gpuobj->im_bound = 1;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 488c36c8f5e..4dc5b4714c5 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1650,7 +1650,36 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
                 }
         }
 
-        rdev->config.evergreen.tile_config = gb_addr_config;
+        /* setup tiling info dword.  gb_addr_config is not adequate since it does
+         * not have bank info, so create a custom tiling dword.
+         * bits 3:0   num_pipes
+         * bits 7:4   num_banks
+         * bits 11:8  group_size
+         * bits 15:12 row_size
+         */
+        rdev->config.evergreen.tile_config = 0;
+        switch (rdev->config.evergreen.max_tile_pipes) {
+        case 1:
+        default:
+                rdev->config.evergreen.tile_config |= (0 << 0);
+                break;
+        case 2:
+                rdev->config.evergreen.tile_config |= (1 << 0);
+                break;
+        case 4:
+                rdev->config.evergreen.tile_config |= (2 << 0);
+                break;
+        case 8:
+                rdev->config.evergreen.tile_config |= (3 << 0);
+                break;
+        }
+        rdev->config.evergreen.tile_config |=
+                ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
+        rdev->config.evergreen.tile_config |=
+                ((mc_arb_ramcfg & BURSTLENGTH_MASK) >> BURSTLENGTH_SHIFT) << 8;
+        rdev->config.evergreen.tile_config |=
+                ((gb_addr_config & 0x30000000) >> 28) << 12;
+
         WREG32(GB_BACKEND_MAP, gb_backend_map);
         WREG32(GB_ADDR_CONFIG, gb_addr_config);
         WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index ac3b6dde23d..e0e590110dd 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -459,7 +459,7 @@ int evergreen_blit_init(struct radeon_device *rdev)
         obj_size += evergreen_ps_size * 4;
         obj_size = ALIGN(obj_size, 256);
 
-        r = radeon_bo_create(rdev, NULL, obj_size, true, RADEON_GEM_DOMAIN_VRAM,
+        r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
                                 &rdev->r600_blit.shader_obj);
         if (r) {
                 DRM_ERROR("evergreen failed to allocate shader\n");
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 0f806cc7dc7..a3552594ccc 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2718,7 +2718,7 @@ static int r600_ih_ring_alloc(struct radeon_device *rdev)
         /* Allocate ring buffer */
         if (rdev->ih.ring_obj == NULL) {
                 r = radeon_bo_create(rdev, NULL, rdev->ih.ring_size,
-                                     true,
+                                     PAGE_SIZE, true,
                                      RADEON_GEM_DOMAIN_GTT,
                                      &rdev->ih.ring_obj);
                 if (r) {
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index 8362974ef41..86e5aa07f0d 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -501,7 +501,7 @@ int r600_blit_init(struct radeon_device *rdev)
         obj_size += r6xx_ps_size * 4;
         obj_size = ALIGN(obj_size, 256);
 
-        r = radeon_bo_create(rdev, NULL, obj_size, true, RADEON_GEM_DOMAIN_VRAM,
+        r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
                                 &rdev->r600_blit.shader_obj);
         if (r) {
                 DRM_ERROR("r600 failed to allocate shader\n");
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 37cc2aa9f92..9bebac1ec00 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -50,6 +50,7 @@ struct r600_cs_track {
         u32                     nsamples;
         u32                     cb_color_base_last[8];
         struct radeon_bo        *cb_color_bo[8];
+        u64                     cb_color_bo_mc[8];
         u32                     cb_color_bo_offset[8];
         struct radeon_bo        *cb_color_frag_bo[8];
         struct radeon_bo        *cb_color_tile_bo[8];
@@ -67,6 +68,7 @@ struct r600_cs_track {
         u32                     db_depth_size;
         u32                     db_offset;
         struct radeon_bo        *db_bo;
+        u64                     db_bo_mc;
 };
 
 static inline int r600_bpe_from_format(u32 *bpe, u32 format)
@@ -140,6 +142,68 @@ static inline int r600_bpe_from_format(u32 *bpe, u32 format)
         return 0;
 }
 
+struct array_mode_checker {
+        int array_mode;
+        u32 group_size;
+        u32 nbanks;
+        u32 npipes;
+        u32 nsamples;
+        u32 bpe;
+};
+
+/* returns alignment in pixels for pitch/height/depth and bytes for base */
+static inline int r600_get_array_mode_alignment(struct array_mode_checker *values,
+                                                u32 *pitch_align,
+                                                u32 *height_align,
+                                                u32 *depth_align,
+                                                u64 *base_align)
+{
+        u32 tile_width = 8;
+        u32 tile_height = 8;
+        u32 macro_tile_width = values->nbanks;
+        u32 macro_tile_height = values->npipes;
+        u32 tile_bytes = tile_width * tile_height * values->bpe * values->nsamples;
+        u32 macro_tile_bytes = macro_tile_width * macro_tile_height * tile_bytes;
+
+        switch (values->array_mode) {
+        case ARRAY_LINEAR_GENERAL:
+                /* technically tile_width/_height for pitch/height */
+                *pitch_align = 1; /* tile_width */
+                *height_align = 1; /* tile_height */
+                *depth_align = 1;
+                *base_align = 1;
+                break;
+        case ARRAY_LINEAR_ALIGNED:
+                *pitch_align = max((u32)64, (u32)(values->group_size / values->bpe));
+                *height_align = tile_height;
+                *depth_align = 1;
+                *base_align = values->group_size;
+                break;
+        case ARRAY_1D_TILED_THIN1:
+                *pitch_align = max((u32)tile_width,
+                                   (u32)(values->group_size /
+                                         (tile_height * values->bpe * values->nsamples)));
+                *height_align = tile_height;
+                *depth_align = 1;
+                *base_align = values->group_size;
+                break;
+        case ARRAY_2D_TILED_THIN1:
+                *pitch_align = max((u32)macro_tile_width,
+                                  (u32)(((values->group_size / tile_height) /
+                                         (values->bpe * values->nsamples)) *
+                                        values->nbanks)) * tile_width;
+                *height_align = macro_tile_height * tile_height;
+                *depth_align = 1;
+                *base_align = max(macro_tile_bytes,
+                                  (*pitch_align) * values->bpe * (*height_align) * values->nsamples);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
 static void r600_cs_track_init(struct r600_cs_track *track)
 {
         int i;
@@ -153,10 +217,12 @@ static void r600_cs_track_init(struct r600_cs_track *track)
                 track->cb_color_info[i] = 0;
                 track->cb_color_bo[i] = NULL;
                 track->cb_color_bo_offset[i] = 0xFFFFFFFF;
+                track->cb_color_bo_mc[i] = 0xFFFFFFFF;
         }
         track->cb_target_mask = 0xFFFFFFFF;
         track->cb_shader_mask = 0xFFFFFFFF;
         track->db_bo = NULL;
+        track->db_bo_mc = 0xFFFFFFFF;
         /* assume the biggest format and that htile is enabled */
         track->db_depth_info = 7 | (1 << 25);
         track->db_depth_view = 0xFFFFC000;
@@ -168,7 +234,10 @@ static void r600_cs_track_init(struct r600_cs_track *track)
 static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 {
         struct r600_cs_track *track = p->track;
-        u32 bpe = 0, pitch, slice_tile_max, size, tmp, height, pitch_align;
+        u32 bpe = 0, slice_tile_max, size, tmp;
+        u32 height, height_align, pitch, pitch_align, depth_align;
+        u64 base_offset, base_align;
+        struct array_mode_checker array_check;
         volatile u32 *ib = p->ib->ptr;
         unsigned array_mode;
 
@@ -183,60 +252,40 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
                         i, track->cb_color_info[i]);
                 return -EINVAL;
         }
-        /* pitch is the number of 8x8 tiles per row */
-        pitch = G_028060_PITCH_TILE_MAX(track->cb_color_size[i]) + 1;
+        /* pitch in pixels */
+        pitch = (G_028060_PITCH_TILE_MAX(track->cb_color_size[i]) + 1) * 8;
         slice_tile_max = G_028060_SLICE_TILE_MAX(track->cb_color_size[i]) + 1;
         slice_tile_max *= 64;
-        height = slice_tile_max / (pitch * 8);
+        height = slice_tile_max / pitch;
         if (height > 8192)
                 height = 8192;
         array_mode = G_0280A0_ARRAY_MODE(track->cb_color_info[i]);
+
+        base_offset = track->cb_color_bo_mc[i] + track->cb_color_bo_offset[i];
+        array_check.array_mode = array_mode;
+        array_check.group_size = track->group_size;
+        array_check.nbanks = track->nbanks;
+        array_check.npipes = track->npipes;
+        array_check.nsamples = track->nsamples;
+        array_check.bpe = bpe;
+        if (r600_get_array_mode_alignment(&array_check,
+                                          &pitch_align, &height_align, &depth_align, &base_align)) {
+                dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
+                         G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
+                         track->cb_color_info[i]);
+                return -EINVAL;
+        }
         switch (array_mode) {
         case V_0280A0_ARRAY_LINEAR_GENERAL:
-                /* technically height & 0x7 */
                 break;
         case V_0280A0_ARRAY_LINEAR_ALIGNED:
-                pitch_align = max((u32)64, (u32)(track->group_size / bpe)) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n",
-                                 __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
-                if (!IS_ALIGNED(height, 8)) {
-                        dev_warn(p->dev, "%s:%d cb height (%d) invalid\n",
-                                 __func__, __LINE__, height);
-                        return -EINVAL;
-                }
                 break;
         case V_0280A0_ARRAY_1D_TILED_THIN1:
-                pitch_align = max((u32)8, (u32)(track->group_size / (8 * bpe * track->nsamples))) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n",
-                                 __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
                 /* avoid breaking userspace */
                 if (height > 7)
                         height &= ~0x7;
-                if (!IS_ALIGNED(height, 8)) {
-                        dev_warn(p->dev, "%s:%d cb height (%d) invalid\n",
-                                 __func__, __LINE__, height);
-                        return -EINVAL;
-                }
                 break;
         case V_0280A0_ARRAY_2D_TILED_THIN1:
-                pitch_align = max((u32)track->nbanks,
-                                  (u32)(((track->group_size / 8) / (bpe * track->nsamples)) * track->nbanks)) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n",
-                                __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
-                if (!IS_ALIGNED((height / 8), track->npipes)) {
-                        dev_warn(p->dev, "%s:%d cb height (%d) invalid\n",
-                                 __func__, __LINE__, height);
-                        return -EINVAL;
-                }
                 break;
         default:
                 dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
@@ -244,13 +293,29 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
                         track->cb_color_info[i]);
                 return -EINVAL;
         }
+
+        if (!IS_ALIGNED(pitch, pitch_align)) {
+                dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n",
+                         __func__, __LINE__, pitch);
+                return -EINVAL;
+        }
+        if (!IS_ALIGNED(height, height_align)) {
+                dev_warn(p->dev, "%s:%d cb height (%d) invalid\n",
+                         __func__, __LINE__, height);
+                return -EINVAL;
+        }
+        if (!IS_ALIGNED(base_offset, base_align)) {
+                dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset);
+                return -EINVAL;
+        }
+
         /* check offset */
-        tmp = height * pitch * 8 * bpe;
+        tmp = height * pitch * bpe;
         if ((tmp + track->cb_color_bo_offset[i]) > radeon_bo_size(track->cb_color_bo[i])) {
                 if (array_mode == V_0280A0_ARRAY_LINEAR_GENERAL) {
                         /* the initial DDX does bad things with the CB size occasionally */
                         /* it rounds up height too far for slice tile max but the BO is smaller */
-                        tmp = (height - 7) * 8 * bpe;
+                        tmp = (height - 7) * pitch * bpe;
                         if ((tmp + track->cb_color_bo_offset[i]) > radeon_bo_size(track->cb_color_bo[i])) {
                                 dev_warn(p->dev, "%s offset[%d] %d %d %lu too big\n", __func__, i, track->cb_color_bo_offset[i], tmp, radeon_bo_size(track->cb_color_bo[i]));
                                 return -EINVAL;
@@ -260,15 +325,11 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
                         return -EINVAL;
                 }
         }
-        if (!IS_ALIGNED(track->cb_color_bo_offset[i], track->group_size)) {
-                dev_warn(p->dev, "%s offset[%d] %d not aligned\n", __func__, i, track->cb_color_bo_offset[i]);
-                return -EINVAL;
-        }
         /* limit max tile */
-        tmp = (height * pitch * 8) >> 6;
+        tmp = (height * pitch) >> 6;
         if (tmp < slice_tile_max)
                 slice_tile_max = tmp;
-        tmp = S_028060_PITCH_TILE_MAX(pitch - 1) |
+        tmp = S_028060_PITCH_TILE_MAX((pitch / 8) - 1) |
                 S_028060_SLICE_TILE_MAX(slice_tile_max - 1);
         ib[track->cb_color_size_idx[i]] = tmp;
         return 0;
@@ -310,7 +371,12 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
         /* Check depth buffer */
         if (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
                 G_028800_Z_ENABLE(track->db_depth_control)) {
-                u32 nviews, bpe, ntiles, pitch, pitch_align, height, size, slice_tile_max;
+                u32 nviews, bpe, ntiles, size, slice_tile_max;
+                u32 height, height_align, pitch, pitch_align, depth_align;
+                u64 base_offset, base_align;
+                struct array_mode_checker array_check;
+                int array_mode;
+
                 if (track->db_bo == NULL) {
                         dev_warn(p->dev, "z/stencil with no depth buffer\n");
                         return -EINVAL;
@@ -353,41 +419,34 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
                         ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
                 } else {
                         size = radeon_bo_size(track->db_bo);
-                        pitch = G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1;
+                        /* pitch in pixels */
+                        pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
                         slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
                         slice_tile_max *= 64;
-                        height = slice_tile_max / (pitch * 8);
+                        height = slice_tile_max / pitch;
                         if (height > 8192)
                                 height = 8192;
-                        switch (G_028010_ARRAY_MODE(track->db_depth_info)) {
+                        base_offset = track->db_bo_mc + track->db_offset;
+                        array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
+                        array_check.array_mode = array_mode;
+                        array_check.group_size = track->group_size;
+                        array_check.nbanks = track->nbanks;
+                        array_check.npipes = track->npipes;
+                        array_check.nsamples = track->nsamples;
+                        array_check.bpe = bpe;
+                        if (r600_get_array_mode_alignment(&array_check,
+                                                          &pitch_align, &height_align, &depth_align, &base_align)) {
+                                dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+                                         G_028010_ARRAY_MODE(track->db_depth_info),
+                                         track->db_depth_info);
+                                return -EINVAL;
+                        }
+                        switch (array_mode) {
                         case V_028010_ARRAY_1D_TILED_THIN1:
-                                pitch_align = (max((u32)8, (u32)(track->group_size / (8 * bpe))) / 8);
-                                if (!IS_ALIGNED(pitch, pitch_align)) {
-                                        dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n",
-                                                 __func__, __LINE__, pitch);
-                                        return -EINVAL;
-                                }
                                 /* don't break userspace */
                                 height &= ~0x7;
-                                if (!IS_ALIGNED(height, 8)) {
-                                        dev_warn(p->dev, "%s:%d db height (%d) invalid\n",
-                                                 __func__, __LINE__, height);
-                                        return -EINVAL;
-                                }
                                 break;
                         case V_028010_ARRAY_2D_TILED_THIN1:
-                                pitch_align = max((u32)track->nbanks,
-                                                  (u32)(((track->group_size / 8) / bpe) * track->nbanks)) / 8;
-                                if (!IS_ALIGNED(pitch, pitch_align)) {
-                                        dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n",
-                                                 __func__, __LINE__, pitch);
-                                        return -EINVAL;
-                                }
-                                if (!IS_ALIGNED((height / 8), track->npipes)) {
-                                        dev_warn(p->dev, "%s:%d db height (%d) invalid\n",
-                                                 __func__, __LINE__, height);
-                                        return -EINVAL;
-                                }
                                 break;
                         default:
                                 dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
@@ -395,15 +454,27 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
                                          track->db_depth_info);
                                 return -EINVAL;
                         }
-                        if (!IS_ALIGNED(track->db_offset, track->group_size)) {
-                                dev_warn(p->dev, "%s offset[%d] %d not aligned\n", __func__, i, track->db_offset);
+
+                        if (!IS_ALIGNED(pitch, pitch_align)) {
+                                dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n",
+                                         __func__, __LINE__, pitch);
+                                return -EINVAL;
+                        }
+                        if (!IS_ALIGNED(height, height_align)) {
+                                dev_warn(p->dev, "%s:%d db height (%d) invalid\n",
+                                         __func__, __LINE__, height);
                                 return -EINVAL;
                         }
+                        if (!IS_ALIGNED(base_offset, base_align)) {
+                                dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset);
+                                return -EINVAL;
+                        }
+
                         ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
                         nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
                         tmp = ntiles * bpe * 64 * nviews;
                         if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
-                                dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %d -> %d have %ld)\n",
+                                dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %d -> %u have %lu)\n",
                                                 track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
                                                 radeon_bo_size(track->db_bo));
                                 return -EINVAL;
@@ -954,6 +1025,7 @@ static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx
                 ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
                 track->cb_color_base_last[tmp] = ib[idx];
                 track->cb_color_bo[tmp] = reloc->robj;
+                track->cb_color_bo_mc[tmp] = reloc->lobj.gpu_offset;
                 break;
         case DB_DEPTH_BASE:
                 r = r600_cs_packet_next_reloc(p, &reloc);
@@ -965,6 +1037,7 @@ static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx
                 track->db_offset = radeon_get_ib_value(p, idx) << 8;
                 ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
                 track->db_bo = reloc->robj;
+                track->db_bo_mc = reloc->lobj.gpu_offset;
                 break;
         case DB_HTILE_DATA_BASE:
         case SQ_PGM_START_FS:
@@ -1086,16 +1159,25 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned nlevels
 static inline int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
                                               struct radeon_bo *texture,
                                               struct radeon_bo *mipmap,
+                                              u64 base_offset,
+                                              u64 mip_offset,
                                               u32 tiling_flags)
 {
         struct r600_cs_track *track = p->track;
         u32 nfaces, nlevels, blevel, w0, h0, d0, bpe = 0;
-        u32 word0, word1, l0_size, mipmap_size, pitch, pitch_align;
+        u32 word0, word1, l0_size, mipmap_size;
+        u32 height_align, pitch, pitch_align, depth_align;
+        u64 base_align;
+        struct array_mode_checker array_check;
 
         /* on legacy kernel we don't perform advanced check */
         if (p->rdev == NULL)
                 return 0;
 
+        /* convert to bytes */
+        base_offset <<= 8;
+        mip_offset <<= 8;
+
         word0 = radeon_get_ib_value(p, idx + 0);
         if (tiling_flags & RADEON_TILING_MACRO)
                 word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
@@ -1128,46 +1210,38 @@ static inline int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 i
                 return -EINVAL;
         }
 
-        pitch = G_038000_PITCH(word0) + 1;
-        switch (G_038000_TILE_MODE(word0)) {
-        case V_038000_ARRAY_LINEAR_GENERAL:
-                pitch_align = 1;
-                /* XXX check height align */
-                break;
-        case V_038000_ARRAY_LINEAR_ALIGNED:
-                pitch_align = max((u32)64, (u32)(track->group_size / bpe)) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n",
-                                 __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
-                /* XXX check height align */
-                break;
-        case V_038000_ARRAY_1D_TILED_THIN1:
-                pitch_align = max((u32)8, (u32)(track->group_size / (8 * bpe))) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n",
-                                 __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
-                /* XXX check height align */
-                break;
-        case V_038000_ARRAY_2D_TILED_THIN1:
-                pitch_align = max((u32)track->nbanks,
-                                  (u32)(((track->group_size / 8) / bpe) * track->nbanks)) / 8;
-                if (!IS_ALIGNED(pitch, pitch_align)) {
-                        dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n",
-                                __func__, __LINE__, pitch);
-                        return -EINVAL;
-                }
-                /* XXX check height align */
-                break;
-        default:
-                dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-                         G_038000_TILE_MODE(word0), word0);
+        /* pitch in texels */
+        pitch = (G_038000_PITCH(word0) + 1) * 8;
+        array_check.array_mode = G_038000_TILE_MODE(word0);
+        array_check.group_size = track->group_size;
+        array_check.nbanks = track->nbanks;
+        array_check.npipes = track->npipes;
+        array_check.nsamples = 1;
+        array_check.bpe = bpe;
+        if (r600_get_array_mode_alignment(&array_check,
+                                          &pitch_align, &height_align, &depth_align, &base_align)) {
+                dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n",
+                         __func__, __LINE__, G_038000_TILE_MODE(word0));
+                return -EINVAL;
+        }
+
+        /* XXX check height as well... */
+
+        if (!IS_ALIGNED(pitch, pitch_align)) {
+                dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n",
+                         __func__, __LINE__, pitch);
+                return -EINVAL;
+        }
+        if (!IS_ALIGNED(base_offset, base_align)) {
+                dev_warn(p->dev, "%s:%d tex base offset (0x%llx) invalid\n",
+                         __func__, __LINE__, base_offset);
+                return -EINVAL;
+        }
+        if (!IS_ALIGNED(mip_offset, base_align)) {
+                dev_warn(p->dev, "%s:%d tex mip offset (0x%llx) invalid\n",
+                         __func__, __LINE__, mip_offset);
                 return -EINVAL;
         }
-        /* XXX check offset align */
 
         word0 = radeon_get_ib_value(p, idx + 4);
         word1 = radeon_get_ib_value(p, idx + 5);
@@ -1402,7 +1476,10 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
                                 mip_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
                                 mipmap = reloc->robj;
                                 r = r600_check_texture_resource(p,  idx+(i*7)+1,
-                                                                texture, mipmap, reloc->lobj.tiling_flags);
+                                                                texture, mipmap,
+                                                                base_offset + radeon_get_ib_value(p, idx+1+(i*7)+2),
+                                                                mip_offset + radeon_get_ib_value(p, idx+1+(i*7)+3),
+                                                                reloc->lobj.tiling_flags);
                                 if (r)
                                         return r;
                                 ib[idx+1+(i*7)+2] += base_offset;
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 966a793e225..bff4dc4f410 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -51,6 +51,12 @@
 #define PTE_READABLE                            (1 << 5)
 #define PTE_WRITEABLE                           (1 << 6)
 
+/* tiling bits */
+#define     ARRAY_LINEAR_GENERAL              0x00000000
+#define     ARRAY_LINEAR_ALIGNED              0x00000001
+#define     ARRAY_1D_TILED_THIN1              0x00000002
+#define     ARRAY_2D_TILED_THIN1              0x00000004
+
 /* Registers */
 #define ARB_POP                                         0x2418
 #define         ENABLE_TC128                                    (1 << 30)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 73f600d39ad..3a7095743d4 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1262,6 +1262,10 @@ void r100_pll_errata_after_index(struct radeon_device *rdev);
                 (rdev->family == CHIP_RS400) ||                 \
                 (rdev->family == CHIP_RS480))
 #define ASIC_IS_AVIVO(rdev) ((rdev->family >= CHIP_RS600))
+#define ASIC_IS_DCE2(rdev) ((rdev->family == CHIP_RS600)  ||    \
+                            (rdev->family == CHIP_RS690)  ||    \
+                            (rdev->family == CHIP_RS740)  ||    \
+                            (rdev->family >= CHIP_R600))
 #define ASIC_IS_DCE3(rdev) ((rdev->family >= CHIP_RV620))
 #define ASIC_IS_DCE32(rdev) ((rdev->family >= CHIP_RV730))
 #define ASIC_IS_DCE4(rdev) ((rdev->family >= CHIP_CEDAR))
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 7932dc4d6b9..c558685cc63 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -41,7 +41,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 
         size = bsize;
         n = 1024;
-        r = radeon_bo_create(rdev, NULL, size, true, sdomain, &sobj);
+        r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, sdomain, &sobj);
         if (r) {
                 goto out_cleanup;
         }
@@ -53,7 +53,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
         if (r) {
                 goto out_cleanup;
         }
-        r = radeon_bo_create(rdev, NULL, size, true, ddomain, &dobj);
+        r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, ddomain, &dobj);
         if (r) {
                 goto out_cleanup;
         }
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 7b7ea269549..3bddea5b529 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -571,6 +571,7 @@ static struct radeon_i2c_bus_rec combios_setup_i2c_bus(struct radeon_device *rde
         }
 
         if (clk_mask && data_mask) {
+                /* system specific masks */
                 i2c.mask_clk_mask = clk_mask;
                 i2c.mask_data_mask = data_mask;
                 i2c.a_clk_mask = clk_mask;
@@ -579,7 +580,19 @@ static struct radeon_i2c_bus_rec combios_setup_i2c_bus(struct radeon_device *rde
                 i2c.en_data_mask = data_mask;
                 i2c.y_clk_mask = clk_mask;
                 i2c.y_data_mask = data_mask;
+        } else if ((ddc_line == RADEON_GPIOPAD_MASK) ||
+                   (ddc_line == RADEON_MDGPIO_MASK)) {
+                /* default gpiopad masks */
+                i2c.mask_clk_mask = (0x20 << 8);
+                i2c.mask_data_mask = 0x80;
+                i2c.a_clk_mask = (0x20 << 8);
+                i2c.a_data_mask = 0x80;
+                i2c.en_clk_mask = (0x20 << 8);
+                i2c.en_data_mask = 0x80;
+                i2c.y_clk_mask = (0x20 << 8);
+                i2c.y_data_mask = 0x80;
         } else {
+                /* default masks for ddc pads */
                 i2c.mask_clk_mask = RADEON_GPIO_EN_1;
                 i2c.mask_data_mask = RADEON_GPIO_EN_0;
                 i2c.a_clk_mask = RADEON_GPIO_A_1;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index fe6c74780f1..3bef9f6d66f 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1008,9 +1008,21 @@ static void radeon_dp_connector_destroy(struct drm_connector *connector)
 static int radeon_dp_get_modes(struct drm_connector *connector)
 {
         struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+        struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
         int ret;
 
+        if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+                if (!radeon_dig_connector->edp_on)
+                        atombios_set_edp_panel_power(connector,
+                                                     ATOM_TRANSMITTER_ACTION_POWER_ON);
+        }
         ret = radeon_ddc_get_modes(radeon_connector);
+        if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+                if (!radeon_dig_connector->edp_on)
+                        atombios_set_edp_panel_power(connector,
+                                                     ATOM_TRANSMITTER_ACTION_POWER_OFF);
+        }
+
         return ret;
 }
 
@@ -1029,8 +1041,14 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
         if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
                 /* eDP is always DP */
                 radeon_dig_connector->dp_sink_type = CONNECTOR_OBJECT_ID_DISPLAYPORT;
+                if (!radeon_dig_connector->edp_on)
+                        atombios_set_edp_panel_power(connector,
+                                                     ATOM_TRANSMITTER_ACTION_POWER_ON);
                 if (radeon_dp_getdpcd(radeon_connector))
                         ret = connector_status_connected;
+                if (!radeon_dig_connector->edp_on)
+                        atombios_set_edp_panel_power(connector,
+                                                     ATOM_TRANSMITTER_ACTION_POWER_OFF);
         } else {
                 radeon_dig_connector->dp_sink_type = radeon_dp_getsinktype(radeon_connector);
                 if (radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) {
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 8adfedfe547..d8ac1849180 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -180,7 +180,7 @@ int radeon_wb_init(struct radeon_device *rdev)
         int r;
 
         if (rdev->wb.wb_obj == NULL) {
-                r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE, true,
+                r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
                                 RADEON_GEM_DOMAIN_GTT, &rdev->wb.wb_obj);
                 if (r) {
                         dev_warn(rdev->dev, "(%d) create WB bo failed\n", r);
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index f678257c42e..041943df966 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -176,6 +176,7 @@ static inline bool radeon_encoder_is_digital(struct drm_encoder *encoder)
                 return false;
         }
 }
+
 void
 radeon_link_encoder_connector(struct drm_device *dev)
 {
@@ -228,6 +229,27 @@ radeon_get_connector_for_encoder(struct drm_encoder *encoder)
         return NULL;
 }
 
+struct drm_encoder *radeon_atom_get_external_encoder(struct drm_encoder *encoder)
+{
+        struct drm_device *dev = encoder->dev;
+        struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+        struct drm_encoder *other_encoder;
+        struct radeon_encoder *other_radeon_encoder;
+
+        if (radeon_encoder->is_ext_encoder)
+                return NULL;
+
+        list_for_each_entry(other_encoder, &dev->mode_config.encoder_list, head) {
+                if (other_encoder == encoder)
+                        continue;
+                other_radeon_encoder = to_radeon_encoder(other_encoder);
+                if (other_radeon_encoder->is_ext_encoder &&
+                    (radeon_encoder->devices & other_radeon_encoder->devices))
+                        return other_encoder;
+        }
+        return NULL;
+}
+
 void radeon_panel_mode_fixup(struct drm_encoder *encoder,
                              struct drm_display_mode *adjusted_mode)
 {
@@ -426,52 +448,49 @@ atombios_tv_setup(struct drm_encoder *encoder, int action)
 
 }
 
-void
-atombios_external_tmds_setup(struct drm_encoder *encoder, int action)
-{
-        struct drm_device *dev = encoder->dev;
-        struct radeon_device *rdev = dev->dev_private;
-        struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-        ENABLE_EXTERNAL_TMDS_ENCODER_PS_ALLOCATION args;
-        int index = 0;
-
-        memset(&args, 0, sizeof(args));
-
-        index = GetIndexIntoMasterTable(COMMAND, DVOEncoderControl);
-
-        args.sXTmdsEncoder.ucEnable = action;
-
-        if (radeon_encoder->pixel_clock > 165000)
-                args.sXTmdsEncoder.ucMisc = PANEL_ENCODER_MISC_DUAL;
-
-        /*if (pScrn->rgbBits == 8)*/
-        args.sXTmdsEncoder.ucMisc |= (1 << 1);
-
-        atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
-
-}
+union dvo_encoder_control {
+        ENABLE_EXTERNAL_TMDS_ENCODER_PS_ALLOCATION ext_tmds;
+        DVO_ENCODER_CONTROL_PS_ALLOCATION dvo;
+        DVO_ENCODER_CONTROL_PS_ALLOCATION_V3 dvo_v3;
+};
 
-static void
-atombios_ddia_setup(struct drm_encoder *encoder, int action)
+void
+atombios_dvo_setup(struct drm_encoder *encoder, int action)
 {
         struct drm_device *dev = encoder->dev;
         struct radeon_device *rdev = dev->dev_private;
         struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-        DVO_ENCODER_CONTROL_PS_ALLOCATION args;
-        int index = 0;
+        union dvo_encoder_control args;
+        int index = GetIndexIntoMasterTable(COMMAND, DVOEncoderControl);
 
         memset(&args, 0, sizeof(args));
 
-        index = GetIndexIntoMasterTable(COMMAND, DVOEncoderControl);
+        if (ASIC_IS_DCE3(rdev)) {
+                /* DCE3+ */
+                args.dvo_v3.ucAction = action;
+                args.dvo_v3.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10);
+                args.dvo_v3.ucDVOConfig = 0; /* XXX */
+        } else if (ASIC_IS_DCE2(rdev)) {
+                /* DCE2 (pre-DCE3 R6xx, RS600/690/740 */
+                args.dvo.sDVOEncoder.ucAction = action;
+                args.dvo.sDVOEncoder.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10);
+                /* DFP1, CRT1, TV1 depending on the type of port */
+                args.dvo.sDVOEncoder.ucDeviceType = ATOM_DEVICE_DFP1_INDEX;
+
+                if (radeon_encoder->pixel_clock > 165000)
+                        args.dvo.sDVOEncoder.usDevAttr.sDigAttrib.ucAttribute |= PANEL_ENCODER_MISC_DUAL;
+        } else {
+                /* R4xx, R5xx */
+                args.ext_tmds.sXTmdsEncoder.ucEnable = action;
 
-        args.sDVOEncoder.ucAction = action;
-        args.sDVOEncoder.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10);
+                if (radeon_encoder->pixel_clock > 165000)
+                        args.ext_tmds.sXTmdsEncoder.ucMisc |= PANEL_ENCODER_MISC_DUAL;
 
-        if (radeon_encoder->pixel_clock > 165000)
-                args.sDVOEncoder.usDevAttr.sDigAttrib.ucAttribute = PANEL_ENCODER_MISC_DUAL;
+                /*if (pScrn->rgbBits == 8)*/
+                args.ext_tmds.sXTmdsEncoder.ucMisc |= ATOM_PANEL_MISC_888RGB;
+        }
 
         atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
-
 }
 
 union lvds_encoder_control {
@@ -532,14 +551,14 @@ atombios_digital_setup(struct drm_encoder *encoder, int action)
                                 if (dig->lcd_misc & ATOM_PANEL_MISC_DUAL)
                                         args.v1.ucMisc |= PANEL_ENCODER_MISC_DUAL;
                                 if (dig->lcd_misc & ATOM_PANEL_MISC_888RGB)
-                                        args.v1.ucMisc |= (1 << 1);
+                                        args.v1.ucMisc |= ATOM_PANEL_MISC_888RGB;
                         } else {
                                 if (dig->linkb)
                                         args.v1.ucMisc |= PANEL_ENCODER_MISC_TMDS_LINKB;
                                 if (radeon_encoder->pixel_clock > 165000)
                                         args.v1.ucMisc |= PANEL_ENCODER_MISC_DUAL;
                                 /*if (pScrn->rgbBits == 8) */
-                                args.v1.ucMisc |= (1 << 1);
+                                args.v1.ucMisc |= ATOM_PANEL_MISC_888RGB;
                         }
                         break;
                 case 2:
@@ -595,6 +614,7 @@ atombios_digital_setup(struct drm_encoder *encoder, int action)
 int
 atombios_get_encoder_mode(struct drm_encoder *encoder)
 {
+        struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
         struct drm_device *dev = encoder->dev;
         struct radeon_device *rdev = dev->dev_private;
         struct drm_connector *connector;
@@ -602,9 +622,20 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
         struct radeon_connector_atom_dig *dig_connector;
 
         connector = radeon_get_connector_for_encoder(encoder);
-        if (!connector)
-                return 0;
-
+        if (!connector) {
+                switch (radeon_encoder->encoder_id) {
+                case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
+                case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
+                case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+                case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
+                case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+                        return ATOM_ENCODER_MODE_DVI;
+                case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1:
+                case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2:
+                default:
+                        return ATOM_ENCODER_MODE_CRT;
+                }
+        }
         radeon_connector = to_radeon_connector(connector);
 
         switch (connector->connector_type) {
@@ -834,6 +865,9 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
         memset(&args, 0, sizeof(args));
 
         switch (radeon_encoder->encoder_id) {
+        case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+                index = GetIndexIntoMasterTable(COMMAND, DVOOutputControl);
+                break;
         case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
         case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
         case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
@@ -978,6 +1012,105 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
         atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 }
 
+void
+atombios_set_edp_panel_power(struct drm_connector *connector, int action)
+{
+        struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+        struct drm_device *dev = radeon_connector->base.dev;
+        struct radeon_device *rdev = dev->dev_private;
+        union dig_transmitter_control args;
+        int index = GetIndexIntoMasterTable(COMMAND, UNIPHYTransmitterControl);
+        uint8_t frev, crev;
+
+        if (connector->connector_type != DRM_MODE_CONNECTOR_eDP)
+                return;
+
+        if (!ASIC_IS_DCE4(rdev))
+                return;
+
+        if ((action != ATOM_TRANSMITTER_ACTION_POWER_ON) ||
+            (action != ATOM_TRANSMITTER_ACTION_POWER_OFF))
+                return;
+
+        if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev))
+                return;
+
+        memset(&args, 0, sizeof(args));
+
+        args.v1.ucAction = action;
+
+        atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+}
+
+union external_encoder_control {
+        EXTERNAL_ENCODER_CONTROL_PS_ALLOCATION v1;
+};
+
+static void
+atombios_external_encoder_setup(struct drm_encoder *encoder,
+                                struct drm_encoder *ext_encoder,
+                                int action)
+{
+        struct drm_device *dev = encoder->dev;
+        struct radeon_device *rdev = dev->dev_private;
+        struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+        union external_encoder_control args;
+        struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+        int index = GetIndexIntoMasterTable(COMMAND, ExternalEncoderControl);
+        u8 frev, crev;
+        int dp_clock = 0;
+        int dp_lane_count = 0;
+        int connector_object_id = 0;
+
+        if (connector) {
+                struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+                struct radeon_connector_atom_dig *dig_connector =
+                        radeon_connector->con_priv;
+
+                dp_clock = dig_connector->dp_clock;
+                dp_lane_count = dig_connector->dp_lane_count;
+                connector_object_id =
+                        (radeon_connector->connector_object_id & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
+        }
+
+        memset(&args, 0, sizeof(args));
+
+        if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev))
+                return;
+
+        switch (frev) {
+        case 1:
+                /* no params on frev 1 */
+                break;
+        case 2:
+                switch (crev) {
+                case 1:
+                case 2:
+                        args.v1.sDigEncoder.ucAction = action;
+                        args.v1.sDigEncoder.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10);
+                        args.v1.sDigEncoder.ucEncoderMode = atombios_get_encoder_mode(encoder);
+
+                        if (args.v1.sDigEncoder.ucEncoderMode == ATOM_ENCODER_MODE_DP) {
+                                if (dp_clock == 270000)
+                                        args.v1.sDigEncoder.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ;
+                                args.v1.sDigEncoder.ucLaneNum = dp_lane_count;
+                        } else if (radeon_encoder->pixel_clock > 165000)
+                                args.v1.sDigEncoder.ucLaneNum = 8;
+                        else
+                                args.v1.sDigEncoder.ucLaneNum = 4;
+                        break;
+                default:
+                        DRM_ERROR("Unknown table version: %d, %d\n", frev, crev);
+                        return;
+                }
+                break;
+        default:
+                DRM_ERROR("Unknown table version: %d, %d\n", frev, crev);
+                return;
+        }
+        atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+}
+
 static void
 atombios_yuv_setup(struct drm_encoder *encoder, bool enable)
 {
@@ -1021,6 +1154,7 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
         struct drm_device *dev = encoder->dev;
         struct radeon_device *rdev = dev->dev_private;
         struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+        struct drm_encoder *ext_encoder = radeon_atom_get_external_encoder(encoder);
         DISPLAY_DEVICE_OUTPUT_CONTROL_PS_ALLOCATION args;
         int index = 0;
         bool is_dig = false;
@@ -1043,9 +1177,14 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
                 break;
         case ENCODER_OBJECT_ID_INTERNAL_DVO1:
         case ENCODER_OBJECT_ID_INTERNAL_DDI:
-        case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
                 index = GetIndexIntoMasterTable(COMMAND, DVOOutputControl);
                 break;
+        case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+                if (ASIC_IS_DCE3(rdev))
+                        is_dig = true;
+                else
+                        index = GetIndexIntoMasterTable(COMMAND, DVOOutputControl);
+                break;
         case ENCODER_OBJECT_ID_INTERNAL_LVDS:
                 index = GetIndexIntoMasterTable(COMMAND, LCD1OutputControl);
                 break;
@@ -1082,34 +1221,85 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
                         if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP) {
                                 struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
+                                if (connector &&
+                                    (connector->connector_type == DRM_MODE_CONNECTOR_eDP)) {
+                                        struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+                                        struct radeon_connector_atom_dig *radeon_dig_connector =
+                                                radeon_connector->con_priv;
+                                        atombios_set_edp_panel_power(connector,
+                                                                     ATOM_TRANSMITTER_ACTION_POWER_ON);
+                                        radeon_dig_connector->edp_on = true;
+                                }
                                 dp_link_train(encoder, connector);
                                 if (ASIC_IS_DCE4(rdev))
                                         atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON);
                         }
+                        if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+                                atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
                         break;
                 case DRM_MODE_DPMS_STANDBY:
                 case DRM_MODE_DPMS_SUSPEND:
                 case DRM_MODE_DPMS_OFF:
                         atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
                         if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP) {
+                                struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+
                                 if (ASIC_IS_DCE4(rdev))
                                         atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_OFF);
+                                if (connector &&
+                                    (connector->connector_type == DRM_MODE_CONNECTOR_eDP)) {
+                                        struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+                                        struct radeon_connector_atom_dig *radeon_dig_connector =
+                                                radeon_connector->con_priv;
+                                        atombios_set_edp_panel_power(connector,
+                                                                     ATOM_TRANSMITTER_ACTION_POWER_OFF);
+                                        radeon_dig_connector->edp_on = false;
+                                }
                         }
+                        if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+                                atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
                         break;
                 }
         } else {
                 switch (mode) {
                 case DRM_MODE_DPMS_ON:
                         args.ucAction = ATOM_ENABLE;
+                        atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+                        if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+                                args.ucAction = ATOM_LCD_BLON;
+                                atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+                        }
                         break;
                 case DRM_MODE_DPMS_STANDBY:
                 case DRM_MODE_DPMS_SUSPEND:
                 case DRM_MODE_DPMS_OFF:
                         args.ucAction = ATOM_DISABLE;
+                        atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+                        if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+                                args.ucAction = ATOM_LCD_BLOFF;
+                                atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+                        }
                         break;
                 }
-                atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
         }
+
+        if (ext_encoder) {
+                int action;
+
+                switch (mode) {
+                case DRM_MODE_DPMS_ON:
+                default:
+                        action = ATOM_ENABLE;
+                        break;
+                case DRM_MODE_DPMS_STANDBY:
+                case DRM_MODE_DPMS_SUSPEND:
+                case DRM_MODE_DPMS_OFF:
+                        action = ATOM_DISABLE;
+                        break;
+                }
+                atombios_external_encoder_setup(encoder, ext_encoder, action);
+        }
+
         radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
 
 }
@@ -1242,7 +1432,7 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
                 break;
         default:
                 DRM_ERROR("Unknown table version: %d, %d\n", frev, crev);
-                break;
+                return;
         }
 
         atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
@@ -1357,6 +1547,7 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder,
         struct drm_device *dev = encoder->dev;
         struct radeon_device *rdev = dev->dev_private;
         struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+        struct drm_encoder *ext_encoder = radeon_atom_get_external_encoder(encoder);
 
         radeon_encoder->pixel_clock = adjusted_mode->clock;
 
@@ -1400,11 +1591,9 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder,
                 }
                 break;
         case ENCODER_OBJECT_ID_INTERNAL_DDI:
-                atombios_ddia_setup(encoder, ATOM_ENABLE);
-                break;
         case ENCODER_OBJECT_ID_INTERNAL_DVO1:
         case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
-                atombios_external_tmds_setup(encoder, ATOM_ENABLE);
+                atombios_dvo_setup(encoder, ATOM_ENABLE);
                 break;
         case ENCODER_OBJECT_ID_INTERNAL_DAC1:
         case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1:
@@ -1419,6 +1608,11 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder,
                 }
                 break;
         }
+
+        if (ext_encoder) {
+                atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE);
+        }
+
         atombios_apply_encoder_quirks(encoder, adjusted_mode);
 
         if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_HDMI) {
@@ -1595,11 +1789,9 @@ static void radeon_atom_encoder_disable(struct drm_encoder *encoder)
                 }
                 break;
         case ENCODER_OBJECT_ID_INTERNAL_DDI:
-                atombios_ddia_setup(encoder, ATOM_DISABLE);
-                break;
         case ENCODER_OBJECT_ID_INTERNAL_DVO1:
         case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
-                atombios_external_tmds_setup(encoder, ATOM_DISABLE);
+                atombios_dvo_setup(encoder, ATOM_DISABLE);
                 break;
         case ENCODER_OBJECT_ID_INTERNAL_DAC1:
         case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1:
@@ -1621,6 +1813,53 @@ disable_done:
         radeon_encoder->active_device = 0;
 }
 
+/* these are handled by the primary encoders */
+static void radeon_atom_ext_prepare(struct drm_encoder *encoder)
+{
+
+}
+
+static void radeon_atom_ext_commit(struct drm_encoder *encoder)
+{
+
+}
+
+static void
+radeon_atom_ext_mode_set(struct drm_encoder *encoder,
+                         struct drm_display_mode *mode,
+                         struct drm_display_mode *adjusted_mode)
+{
+
+}
+
+static void radeon_atom_ext_disable(struct drm_encoder *encoder)
+{
+
+}
+
+static void
+radeon_atom_ext_dpms(struct drm_encoder *encoder, int mode)
+{
+
+}
+
+static bool radeon_atom_ext_mode_fixup(struct drm_encoder *encoder,
+                                       struct drm_display_mode *mode,
+                                       struct drm_display_mode *adjusted_mode)
+{
+        return true;
+}
+
+static const struct drm_encoder_helper_funcs radeon_atom_ext_helper_funcs = {
+        .dpms = radeon_atom_ext_dpms,
+        .mode_fixup = radeon_atom_ext_mode_fixup,
+        .prepare = radeon_atom_ext_prepare,
+        .mode_set = radeon_atom_ext_mode_set,
+        .commit = radeon_atom_ext_commit,
+        .disable = radeon_atom_ext_disable,
+        /* no detect for TMDS/LVDS yet */
+};
+
 static const struct drm_encoder_helper_funcs radeon_atom_dig_helper_funcs = {
         .dpms = radeon_atom_encoder_dpms,
         .mode_fixup = radeon_atom_mode_fixup,
@@ -1730,6 +1969,7 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_enum, uint32_t
         radeon_encoder->devices = supported_device;
         radeon_encoder->rmx_type = RMX_OFF;
         radeon_encoder->underscan_type = UNDERSCAN_OFF;
+        radeon_encoder->is_ext_encoder = false;
 
         switch (radeon_encoder->encoder_id) {
         case ENCODER_OBJECT_ID_INTERNAL_LVDS:
@@ -1771,6 +2011,9 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_enum, uint32_t
                         radeon_encoder->rmx_type = RMX_FULL;
                         drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_LVDS);
                         radeon_encoder->enc_priv = radeon_atombios_get_lvds_info(radeon_encoder);
+                } else if (radeon_encoder->devices & (ATOM_DEVICE_CRT_SUPPORT)) {
+                        drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_DAC);
+                        radeon_encoder->enc_priv = radeon_atombios_set_dig_info(radeon_encoder);
                 } else {
                         drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_TMDS);
                         radeon_encoder->enc_priv = radeon_atombios_set_dig_info(radeon_encoder);
@@ -1779,5 +2022,22 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_enum, uint32_t
                 }
                 drm_encoder_helper_add(encoder, &radeon_atom_dig_helper_funcs);
                 break;
+        case ENCODER_OBJECT_ID_SI170B:
+        case ENCODER_OBJECT_ID_CH7303:
+        case ENCODER_OBJECT_ID_EXTERNAL_SDVOA:
+        case ENCODER_OBJECT_ID_EXTERNAL_SDVOB:
+        case ENCODER_OBJECT_ID_TITFP513:
+        case ENCODER_OBJECT_ID_VT1623:
+        case ENCODER_OBJECT_ID_HDMI_SI1930:
+                /* these are handled by the primary encoders */
+                radeon_encoder->is_ext_encoder = true;
+                if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+                        drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_LVDS);
+                else if (radeon_encoder->devices & (ATOM_DEVICE_CRT_SUPPORT))
+                        drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_DAC);
+                else
+                        drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_TMDS);
+                drm_encoder_helper_add(encoder, &radeon_atom_ext_helper_funcs);
+                break;
         }
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index e65b90317fa..65016117d95 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -79,8 +79,8 @@ int radeon_gart_table_vram_alloc(struct radeon_device *rdev)
 
         if (rdev->gart.table.vram.robj == NULL) {
                 r = radeon_bo_create(rdev, NULL, rdev->gart.table_size,
-                                        true, RADEON_GEM_DOMAIN_VRAM,
-                                        &rdev->gart.table.vram.robj);
+                                     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+                                     &rdev->gart.table.vram.robj);
                 if (r) {
                         return r;
                 }
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index d1e595d9172..df95eb83dac 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -67,7 +67,7 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size,
         if (alignment < PAGE_SIZE) {
                 alignment = PAGE_SIZE;
         }
-        r = radeon_bo_create(rdev, gobj, size, kernel, initial_domain, &robj);
+        r = radeon_bo_create(rdev, gobj, size, alignment, kernel, initial_domain, &robj);
         if (r) {
                 if (r != -ERESTARTSYS)
                         DRM_ERROR("Failed to allocate GEM object (%d, %d, %u, %d)\n",
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index 0cfbba02c4d..ded2a45bc95 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -896,7 +896,8 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev,
              ((rdev->family <= CHIP_RS480) ||
               ((rdev->family >= CHIP_RV515) && (rdev->family <= CHIP_R580))))) {
                 /* set the radeon hw i2c adapter */
-                sprintf(i2c->adapter.name, "Radeon i2c hw bus %s", name);
+                snprintf(i2c->adapter.name, sizeof(i2c->adapter.name),
+                         "Radeon i2c hw bus %s", name);
                 i2c->adapter.algo = &radeon_i2c_algo;
                 ret = i2c_add_adapter(&i2c->adapter);
                 if (ret) {
@@ -905,7 +906,8 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev,
                 }
         } else {
                 /* set the radeon bit adapter */
-                sprintf(i2c->adapter.name, "Radeon i2c bit bus %s", name);
+                snprintf(i2c->adapter.name, sizeof(i2c->adapter.name),
+                         "Radeon i2c bit bus %s", name);
                 i2c->adapter.algo_data = &i2c->algo.bit;
                 i2c->algo.bit.pre_xfer = pre_xfer;
                 i2c->algo.bit.post_xfer = post_xfer;
@@ -946,6 +948,8 @@ struct radeon_i2c_chan *radeon_i2c_create_dp(struct drm_device *dev,
         i2c->rec = *rec;
         i2c->adapter.owner = THIS_MODULE;
         i2c->dev = dev;
+        snprintf(i2c->adapter.name, sizeof(i2c->adapter.name),
+                 "Radeon aux bus %s", name);
         i2c_set_adapdata(&i2c->adapter, i2c);
         i2c->adapter.algo_data = &i2c->algo.dp;
         i2c->algo.dp.aux_ch = radeon_dp_i2c_aux_ch;
diff --git a/drivers/gpu/drm/radeon/radeon_irq.c b/drivers/gpu/drm/radeon/radeon_irq.c
index 2f349a30019..465746bd51b 100644
--- a/drivers/gpu/drm/radeon/radeon_irq.c
+++ b/drivers/gpu/drm/radeon/radeon_irq.c
@@ -76,7 +76,7 @@ int radeon_enable_vblank(struct drm_device *dev, int crtc)
                 default:
                         DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
                                   crtc);
-                        return EINVAL;
+                        return -EINVAL;
                 }
         } else {
                 switch (crtc) {
@@ -89,7 +89,7 @@ int radeon_enable_vblank(struct drm_device *dev, int crtc)
                 default:
                         DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
                                   crtc);
-                        return EINVAL;
+                        return -EINVAL;
                 }
         }
 
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 0b8397000f4..59f834ba283 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -670,7 +670,7 @@ static void radeon_legacy_tmds_ext_mode_set(struct drm_encoder *encoder,
 
         if (rdev->is_atom_bios) {
                 radeon_encoder->pixel_clock = adjusted_mode->clock;
-                atombios_external_tmds_setup(encoder, ATOM_ENABLE);
+                atombios_dvo_setup(encoder, ATOM_ENABLE);
                 fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL);
         } else {
                 fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 680f57644e8..e301c6f9e05 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -375,6 +375,7 @@ struct radeon_encoder {
         int hdmi_config_offset;
         int hdmi_audio_workaround;
         int hdmi_buffer_status;
+        bool is_ext_encoder;
 };
 
 struct radeon_connector_atom_dig {
@@ -385,6 +386,7 @@ struct radeon_connector_atom_dig {
         u8 dp_sink_type;
         int dp_clock;
         int dp_lane_count;
+        bool edp_on;
 };
 
 struct radeon_gpio_rec {
@@ -523,9 +525,10 @@ struct drm_encoder *radeon_encoder_legacy_primary_dac_add(struct drm_device *dev
 struct drm_encoder *radeon_encoder_legacy_tv_dac_add(struct drm_device *dev, int bios_index, int with_tv);
 struct drm_encoder *radeon_encoder_legacy_tmds_int_add(struct drm_device *dev, int bios_index);
 struct drm_encoder *radeon_encoder_legacy_tmds_ext_add(struct drm_device *dev, int bios_index);
-extern void atombios_external_tmds_setup(struct drm_encoder *encoder, int action);
+extern void atombios_dvo_setup(struct drm_encoder *encoder, int action);
 extern void atombios_digital_setup(struct drm_encoder *encoder, int action);
 extern int atombios_get_encoder_mode(struct drm_encoder *encoder);
+extern void atombios_set_edp_panel_power(struct drm_connector *connector, int action);
 extern void radeon_encoder_set_active_device(struct drm_encoder *encoder);
 
 extern void radeon_crtc_load_lut(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 8eb18346601..1d067743fee 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -86,11 +86,12 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 }
 
 int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj,
-                        unsigned long size, bool kernel, u32 domain,
-                        struct radeon_bo **bo_ptr)
+                     unsigned long size, int byte_align, bool kernel, u32 domain,
+                     struct radeon_bo **bo_ptr)
 {
         struct radeon_bo *bo;
         enum ttm_bo_type type;
+        int page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
         int r;
 
         if (unlikely(rdev->mman.bdev.dev_mapping == NULL)) {
@@ -115,7 +116,7 @@ retry:
         /* Kernel allocation are uninterruptible */
         mutex_lock(&rdev->vram_mutex);
         r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
-                        &bo->placement, 0, 0, !kernel, NULL, size,
+                        &bo->placement, page_align, 0, !kernel, NULL, size,
                         &radeon_ttm_bo_destroy);
         mutex_unlock(&rdev->vram_mutex);
         if (unlikely(r != 0)) {
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 3481bc7f6f5..d143702b244 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -137,9 +137,10 @@ static inline int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
 }
 
 extern int radeon_bo_create(struct radeon_device *rdev,
-                                struct drm_gem_object *gobj, unsigned long size,
-                                bool kernel, u32 domain,
-                                struct radeon_bo **bo_ptr);
+                            struct drm_gem_object *gobj, unsigned long size,
+                            int byte_align,
+                            bool kernel, u32 domain,
+                            struct radeon_bo **bo_ptr);
 extern int radeon_bo_kmap(struct radeon_bo *bo, void **ptr);
 extern void radeon_bo_kunmap(struct radeon_bo *bo);
 extern void radeon_bo_unref(struct radeon_bo **bo);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 6ea798ce821..06e79822a2b 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -176,8 +176,8 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
         INIT_LIST_HEAD(&rdev->ib_pool.bogus_ib);
         /* Allocate 1M object buffer */
         r = radeon_bo_create(rdev, NULL,  RADEON_IB_POOL_SIZE*64*1024,
-                                true, RADEON_GEM_DOMAIN_GTT,
-                                &rdev->ib_pool.robj);
+                             PAGE_SIZE, true, RADEON_GEM_DOMAIN_GTT,
+                             &rdev->ib_pool.robj);
         if (r) {
                 DRM_ERROR("radeon: failed to ib pool (%d).\n", r);
                 return r;
@@ -332,7 +332,7 @@ int radeon_ring_init(struct radeon_device *rdev, unsigned ring_size)
         rdev->cp.ring_size = ring_size;
         /* Allocate ring buffer */
         if (rdev->cp.ring_obj == NULL) {
-                r = radeon_bo_create(rdev, NULL, rdev->cp.ring_size, true,
+                r = radeon_bo_create(rdev, NULL, rdev->cp.ring_size, PAGE_SIZE, true,
                                         RADEON_GEM_DOMAIN_GTT,
                                         &rdev->cp.ring_obj);
                 if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 313c96bc09d..5b44f652145 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -52,7 +52,7 @@ void radeon_test_moves(struct radeon_device *rdev)
                 goto out_cleanup;
         }
 
-        r = radeon_bo_create(rdev, NULL, size, true, RADEON_GEM_DOMAIN_VRAM,
+        r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
                                 &vram_obj);
         if (r) {
                 DRM_ERROR("Failed to create VRAM object\n");
@@ -71,7 +71,7 @@ void radeon_test_moves(struct radeon_device *rdev)
                 void **gtt_start, **gtt_end;
                 void **vram_start, **vram_end;
 
-                r = radeon_bo_create(rdev, NULL, size, true,
+                r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true,
                                          RADEON_GEM_DOMAIN_GTT, gtt_obj + i);
                 if (r) {
                         DRM_ERROR("Failed to create GTT object %d\n", i);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 01c2c736a1d..1272e4b6a1d 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -529,7 +529,7 @@ int radeon_ttm_init(struct radeon_device *rdev)
                 DRM_ERROR("Failed initializing VRAM heap.\n");
                 return r;
         }
-        r = radeon_bo_create(rdev, NULL, 256 * 1024, true,
+        r = radeon_bo_create(rdev, NULL, 256 * 1024, PAGE_SIZE, true,
                                 RADEON_GEM_DOMAIN_VRAM,
                                 &rdev->stollen_vga_memory);
         if (r) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 245374e2b77..4dfead8cee3 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -915,8 +915,8 @@ static int rv770_vram_scratch_init(struct radeon_device *rdev)
 
         if (rdev->vram_scratch.robj == NULL) {
                 r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE,
-                                        true, RADEON_GEM_DOMAIN_VRAM,
-                                        &rdev->vram_scratch.robj);
+                                     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+                                     &rdev->vram_scratch.robj);
                 if (r) {
                         return r;
                 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3ca77dc0391..148a322d8f5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -224,6 +224,9 @@ int ttm_bo_reserve_locked(struct ttm_buffer_object *bo,
         int ret;
 
         while (unlikely(atomic_cmpxchg(&bo->reserved, 0, 1) != 0)) {
+                /**
+                 * Deadlock avoidance for multi-bo reserving.
+                 */
                 if (use_sequence && bo->seq_valid &&
                         (sequence - bo->val_seq < (1 << 31))) {
                         return -EAGAIN;
@@ -241,6 +244,14 @@ int ttm_bo_reserve_locked(struct ttm_buffer_object *bo,
         }
 
         if (use_sequence) {
+                /**
+                 * Wake up waiters that may need to recheck for deadlock,
+                 * if we decreased the sequence number.
+                 */
+                if (unlikely((bo->val_seq - sequence < (1 << 31))
+                             || !bo->seq_valid))
+                        wake_up_all(&bo->event_queue);
+
                 bo->val_seq = sequence;
                 bo->seq_valid = true;
         } else {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 36e129f0023..5408b1b7996 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -862,7 +862,7 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
                               &vmw_vram_sys_placement, true,
                               &vmw_user_dmabuf_destroy);
         if (unlikely(ret != 0))
-                return ret;
+                goto out_no_dmabuf;
 
         tmp = ttm_bo_reference(&vmw_user_bo->dma.base);
         ret = ttm_base_object_init(vmw_fpriv(file_priv)->tfile,
@@ -870,19 +870,21 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
                                    false,
                                    ttm_buffer_type,
                                    &vmw_user_dmabuf_release, NULL);
-        if (unlikely(ret != 0)) {
-                ttm_bo_unref(&tmp);
-        } else {
+        if (unlikely(ret != 0))
+                goto out_no_base_object;
+        else {
                 rep->handle = vmw_user_bo->base.hash.key;
                 rep->map_handle = vmw_user_bo->dma.base.addr_space_offset;
                 rep->cur_gmr_id = vmw_user_bo->base.hash.key;
                 rep->cur_gmr_offset = 0;
         }
-        ttm_bo_unref(&tmp);
 
+out_no_base_object:
+        ttm_bo_unref(&tmp);
+out_no_dmabuf:
         ttm_read_unlock(&vmaster->lock);
 
-        return 0;
+        return ret;
 }
 
 int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 8a4b32dca9f..e1f07483691 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -32,7 +32,6 @@
 #include <linux/hid.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 
 #include <linux/hidraw.h>
 
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index fedd88df9a1..984feb351a5 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/input.h>
 #include <linux/usb.h>
 #include <linux/hid.h>
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 6078992da3f..9292a15ad7c 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -40,7 +40,6 @@
 #include <linux/highmem.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
 #include <asm/pgtable.h>
 
 #include "ipath_kernel.h"
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index cfc1d65c457..1e1e347a771 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1123,7 +1123,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
         }
 }
 
-static int srp_queuecommand(struct scsi_cmnd *scmnd,
+static int srp_queuecommand_lck(struct scsi_cmnd *scmnd,
                             void (*done)(struct scsi_cmnd *))
 {
         struct srp_target_port *target = host_to_target(scmnd->device->host);
@@ -1196,6 +1196,8 @@ err:
         return SCSI_MLQUEUE_HOST_BUSY;
 }
 
+static DEF_SCSI_QCMD(srp_queuecommand)
+
 static int srp_alloc_iu_bufs(struct srp_target_port *target)
 {
         int i;
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 7f26ca6ecf7..db409d6bd5d 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -24,7 +24,6 @@
 #include <linux/device.h>
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
-#include <linux/smp_lock.h>
 #include "input-compat.h"
 
 MODULE_AUTHOR("Vojtech Pavlik <vojtech@suse.cz>");
@@ -753,7 +752,7 @@ static int input_default_setkeycode(struct input_dev *dev,
         if (index >= dev->keycodemax)
                 return -EINVAL;
 
-        if (dev->keycodesize < sizeof(dev->keycode) &&
+        if (dev->keycodesize < sizeof(ke->keycode) &&
                         (ke->keycode >> (dev->keycodesize * 8)))
                 return -EINVAL;
 
diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index cd82bb12591..b7ba4597f7f 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -11,7 +11,6 @@
 
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/poll.h>
 #include <linux/module.h>
 #include <linux/serio.h>
diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c
index 57b25b84d1f..0a619c558bf 100644
--- a/drivers/input/tablet/aiptek.c
+++ b/drivers/input/tablet/aiptek.c
@@ -1097,7 +1097,7 @@ store_tabletPointerMode(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(pointer_mode,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletPointerMode, store_tabletPointerMode);
 
 /***********************************************************************
@@ -1134,7 +1134,7 @@ store_tabletCoordinateMode(struct device *dev, struct device_attribute *attr, co
 }
 
 static DEVICE_ATTR(coordinate_mode,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletCoordinateMode, store_tabletCoordinateMode);
 
 /***********************************************************************
@@ -1176,7 +1176,7 @@ store_tabletToolMode(struct device *dev, struct device_attribute *attr, const ch
 }
 
 static DEVICE_ATTR(tool_mode,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletToolMode, store_tabletToolMode);
 
 /***********************************************************************
@@ -1219,7 +1219,7 @@ store_tabletXtilt(struct device *dev, struct device_attribute *attr, const char
 }
 
 static DEVICE_ATTR(xtilt,
-                   S_IRUGO | S_IWUGO, show_tabletXtilt, store_tabletXtilt);
+                   S_IRUGO | S_IWUSR, show_tabletXtilt, store_tabletXtilt);
 
 /***********************************************************************
  * support routines for the 'ytilt' file. Note that this file
@@ -1261,7 +1261,7 @@ store_tabletYtilt(struct device *dev, struct device_attribute *attr, const char
 }
 
 static DEVICE_ATTR(ytilt,
-                   S_IRUGO | S_IWUGO, show_tabletYtilt, store_tabletYtilt);
+                   S_IRUGO | S_IWUSR, show_tabletYtilt, store_tabletYtilt);
 
 /***********************************************************************
  * support routines for the 'jitter' file. Note that this file
@@ -1288,7 +1288,7 @@ store_tabletJitterDelay(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(jitter,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletJitterDelay, store_tabletJitterDelay);
 
 /***********************************************************************
@@ -1317,7 +1317,7 @@ store_tabletProgrammableDelay(struct device *dev, struct device_attribute *attr,
 }
 
 static DEVICE_ATTR(delay,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletProgrammableDelay, store_tabletProgrammableDelay);
 
 /***********************************************************************
@@ -1406,7 +1406,7 @@ store_tabletStylusUpper(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(stylus_upper,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletStylusUpper, store_tabletStylusUpper);
 
 /***********************************************************************
@@ -1437,7 +1437,7 @@ store_tabletStylusLower(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(stylus_lower,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletStylusLower, store_tabletStylusLower);
 
 /***********************************************************************
@@ -1475,7 +1475,7 @@ store_tabletMouseLeft(struct device *dev, struct device_attribute *attr, const c
 }
 
 static DEVICE_ATTR(mouse_left,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletMouseLeft, store_tabletMouseLeft);
 
 /***********************************************************************
@@ -1505,7 +1505,7 @@ store_tabletMouseMiddle(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(mouse_middle,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletMouseMiddle, store_tabletMouseMiddle);
 
 /***********************************************************************
@@ -1535,7 +1535,7 @@ store_tabletMouseRight(struct device *dev, struct device_attribute *attr, const
 }
 
 static DEVICE_ATTR(mouse_right,
-                   S_IRUGO | S_IWUGO,
+                   S_IRUGO | S_IWUSR,
                    show_tabletMouseRight, store_tabletMouseRight);
 
 /***********************************************************************
@@ -1567,7 +1567,7 @@ store_tabletWheel(struct device *dev, struct device_attribute *attr, const char
 }
 
 static DEVICE_ATTR(wheel,
-                   S_IRUGO | S_IWUGO, show_tabletWheel, store_tabletWheel);
+                   S_IRUGO | S_IWUSR, show_tabletWheel, store_tabletWheel);
 
 /***********************************************************************
  * support routines for the 'execute' file. Note that this file
@@ -1600,7 +1600,7 @@ store_tabletExecute(struct device *dev, struct device_attribute *attr, const cha
 }
 
 static DEVICE_ATTR(execute,
-                   S_IRUGO | S_IWUGO, show_tabletExecute, store_tabletExecute);
+                   S_IRUGO | S_IWUSR, show_tabletExecute, store_tabletExecute);
 
 /***********************************************************************
  * support routines for the 'odm_code' file. Note that this file
diff --git a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
index 4d0646da608..7ea517b7e18 100644
--- a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
@@ -36,7 +36,6 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/kthread.h>
 
 #include "dvb_ca_en50221.h"
diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c
index 1589d5a5cb4..cad6634610e 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.c
@@ -36,7 +36,6 @@
 #include <linux/list.h>
 #include <linux/freezer.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
 #include <linux/kthread.h>
 #include <asm/processor.h>
 
diff --git a/drivers/media/dvb/ngene/ngene-core.c b/drivers/media/dvb/ngene/ngene-core.c
index 4caeb163a66..3a7ef71087b 100644
--- a/drivers/media/dvb/ngene/ngene-core.c
+++ b/drivers/media/dvb/ngene/ngene-core.c
@@ -34,7 +34,6 @@
 #include <linux/io.h>
 #include <asm/div64.h>
 #include <linux/pci.h>
-#include <linux/smp_lock.h>
 #include <linux/timer.h>
 #include <linux/byteorder/generic.h>
 #include <linux/firmware.h>
diff --git a/drivers/media/dvb/ngene/ngene-dvb.c b/drivers/media/dvb/ngene/ngene-dvb.c
index 48f980b21d6..3832e5983c1 100644
--- a/drivers/media/dvb/ngene/ngene-dvb.c
+++ b/drivers/media/dvb/ngene/ngene-dvb.c
@@ -35,7 +35,6 @@
 #include <linux/io.h>
 #include <asm/div64.h>
 #include <linux/pci.h>
-#include <linux/smp_lock.h>
 #include <linux/timer.h>
 #include <linux/byteorder/generic.h>
 #include <linux/firmware.h>
diff --git a/drivers/media/dvb/ngene/ngene-i2c.c b/drivers/media/dvb/ngene/ngene-i2c.c
index c3ae956714e..d28554f8ce9 100644
--- a/drivers/media/dvb/ngene/ngene-i2c.c
+++ b/drivers/media/dvb/ngene/ngene-i2c.c
@@ -37,7 +37,6 @@
 #include <asm/div64.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
-#include <linux/smp_lock.h>
 #include <linux/timer.h>
 #include <linux/byteorder/generic.h>
 #include <linux/firmware.h>
diff --git a/drivers/media/radio/radio-mr800.c b/drivers/media/radio/radio-mr800.c
index b540e8072e9..e6b2d085a44 100644
--- a/drivers/media/radio/radio-mr800.c
+++ b/drivers/media/radio/radio-mr800.c
@@ -58,7 +58,6 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/input.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/radio/si470x/radio-si470x.h b/drivers/media/radio/si470x/radio-si470x.h
index ea12782359a..b9914d7a0c9 100644
--- a/drivers/media/radio/si470x/radio-si470x.h
+++ b/drivers/media/radio/si470x/radio-si470x.h
@@ -31,7 +31,6 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/input.h>
 #include <linux/version.h>
 #include <linux/videodev2.h>
diff --git a/drivers/media/video/bt8xx/bttv-driver.c b/drivers/media/video/bt8xx/bttv-driver.c
index 3da6e80e104..a529619e51f 100644
--- a/drivers/media/video/bt8xx/bttv-driver.c
+++ b/drivers/media/video/bt8xx/bttv-driver.c
@@ -42,7 +42,6 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/kdev_t.h>
 #include "bttvp.h"
diff --git a/drivers/media/video/cx88/cx88-blackbird.c b/drivers/media/video/cx88/cx88-blackbird.c
index 417d1d5c73c..d7c94848249 100644
--- a/drivers/media/video/cx88/cx88-blackbird.c
+++ b/drivers/media/video/cx88/cx88-blackbird.c
@@ -33,7 +33,6 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/firmware.h>
-#include <linux/smp_lock.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/cx2341x.h>
diff --git a/drivers/media/video/cx88/cx88-video.c b/drivers/media/video/cx88/cx88-video.c
index d2f159daa8b..88b51194f91 100644
--- a/drivers/media/video/cx88/cx88-video.c
+++ b/drivers/media/video/cx88/cx88-video.c
@@ -31,7 +31,6 @@
 #include <linux/kmod.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
diff --git a/drivers/media/video/pwc/pwc-if.c b/drivers/media/video/pwc/pwc-if.c
index e62beb4efdb..f3dc89da4c4 100644
--- a/drivers/media/video/pwc/pwc-if.c
+++ b/drivers/media/video/pwc/pwc-if.c
@@ -62,7 +62,6 @@
 #include <linux/module.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #ifdef CONFIG_USB_PWC_INPUT_EVDEV
 #include <linux/usb/input.h>
 #endif
diff --git a/drivers/media/video/s2255drv.c b/drivers/media/video/s2255drv.c
index f5a46c45871..a845753665c 100644
--- a/drivers/media/video/s2255drv.c
+++ b/drivers/media/video/s2255drv.c
@@ -49,7 +49,6 @@
 #include <linux/videodev2.h>
 #include <linux/version.h>
 #include <linux/mm.h>
-#include <linux/smp_lock.h>
 #include <media/videobuf-vmalloc.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/video/saa7134/saa7134-empress.c b/drivers/media/video/saa7134/saa7134-empress.c
index 1467a30a434..b890aafe7d6 100644
--- a/drivers/media/video/saa7134/saa7134-empress.c
+++ b/drivers/media/video/saa7134/saa7134-empress.c
@@ -21,7 +21,6 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/smp_lock.h>
 #include <linux/delay.h>
 
 #include "saa7134-reg.h"
diff --git a/drivers/media/video/saa7164/saa7164.h b/drivers/media/video/saa7164/saa7164.h
index 1d9c5cbbbc5..041ae8e20f6 100644
--- a/drivers/media/video/saa7164/saa7164.h
+++ b/drivers/media/video/saa7164/saa7164.h
@@ -58,7 +58,6 @@
 #include <media/tveeprom.h>
 #include <media/videobuf-dma-sg.h>
 #include <media/videobuf-dvb.h>
-#include <linux/smp_lock.h>
 #include <dvb_demux.h>
 #include <dvb_frontend.h>
 #include <dvb_net.h>
diff --git a/drivers/media/video/usbvision/usbvision-video.c b/drivers/media/video/usbvision/usbvision-video.c
index db6b828594f..011c0c38699 100644
--- a/drivers/media/video/usbvision/usbvision-video.c
+++ b/drivers/media/video/usbvision/usbvision-video.c
@@ -50,7 +50,6 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/media/video/v4l2-compat-ioctl32.c b/drivers/media/video/v4l2-compat-ioctl32.c
index 86294ed35c9..e30e8dfb620 100644
--- a/drivers/media/video/v4l2-compat-ioctl32.c
+++ b/drivers/media/video/v4l2-compat-ioctl32.c
@@ -18,7 +18,6 @@
 #include <linux/videodev.h>
 #include <linux/videodev2.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <media/v4l2-ioctl.h>
 
 #ifdef CONFIG_COMPAT
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index e15220ff52f..d784c36707c 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -97,8 +97,7 @@ static u8	mptfcInternalCtx = MPT_MAX_PROTOCOL_DRIVERS;
 
 static int mptfc_target_alloc(struct scsi_target *starget);
 static int mptfc_slave_alloc(struct scsi_device *sdev);
-static int mptfc_qcmd(struct scsi_cmnd *SCpnt,
-                      void (*done)(struct scsi_cmnd *));
+static int mptfc_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt);
 static void mptfc_target_destroy(struct scsi_target *starget);
 static void mptfc_set_rport_loss_tmo(struct fc_rport *rport, uint32_t timeout);
 static void __devexit mptfc_remove(struct pci_dev *pdev);
@@ -650,7 +649,7 @@ mptfc_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-mptfc_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptfc_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         struct mptfc_rport_info *ri;
         struct fc_rport *rport = starget_to_rport(scsi_target(SCpnt->device));
@@ -681,6 +680,8 @@ mptfc_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
         return mptscsih_qcmd(SCpnt,done);
 }
 
+static DEF_SCSI_QCMD(mptfc_qcmd)
+
 /*
  *      mptfc_display_port_link_speed - displaying link speed
  *      @ioc: Pointer to MPT_ADAPTER structure
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 83a5115f025..d48c2c6058e 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1889,7 +1889,7 @@ mptsas_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-mptsas_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptsas_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         MPT_SCSI_HOST   *hd;
         MPT_ADAPTER     *ioc;
@@ -1913,6 +1913,8 @@ mptsas_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
         return mptscsih_qcmd(SCpnt,done);
 }
 
+static DEF_SCSI_QCMD(mptsas_qcmd)
+
 /**
  *      mptsas_mptsas_eh_timed_out - resets the scsi_cmnd timeout
  *              if the device under question is currently in the
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 0e2803155ae..6d9568d2ec5 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -780,7 +780,7 @@ static int mptspi_slave_configure(struct scsi_device *sdev)
 }
 
 static int
-mptspi_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptspi_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         struct _MPT_SCSI_HOST *hd = shost_priv(SCpnt->device->host);
         VirtDevice      *vdevice = SCpnt->device->hostdata;
@@ -805,6 +805,8 @@ mptspi_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
         return mptscsih_qcmd(SCpnt,done);
 }
 
+static DEF_SCSI_QCMD(mptspi_qcmd)
+
 static void mptspi_slave_destroy(struct scsi_device *sdev)
 {
         struct scsi_target *starget = scsi_target(sdev);
diff --git a/drivers/message/i2o/i2o_scsi.c b/drivers/message/i2o/i2o_scsi.c
index ea6b2197da8..97bdf82ec90 100644
--- a/drivers/message/i2o/i2o_scsi.c
+++ b/drivers/message/i2o/i2o_scsi.c
@@ -506,7 +506,7 @@ static struct i2o_driver i2o_scsi_driver = {
  *      Locks: takes the controller lock on error path only
  */
 
-static int i2o_scsi_queuecommand(struct scsi_cmnd *SCpnt,
+static int i2o_scsi_queuecommand_lck(struct scsi_cmnd *SCpnt,
                                  void (*done) (struct scsi_cmnd *))
 {
         struct i2o_controller *c;
@@ -688,7 +688,9 @@ static int i2o_scsi_queuecommand(struct scsi_cmnd *SCpnt,
 
       exit:
         return rc;
-};
+}
+
+static DEF_SCSI_QCMD(i2o_scsi_queuecommand)
 
 /**
  *      i2o_scsi_abort - abort a running command
diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index e1da258bbfb..0a92436f053 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -699,7 +699,8 @@ DEFINE_WINDOW_IO(32)
 #define DEVICE_PCI(dev) NULL
 #endif
 
-#define VORTEX_PCI(vp) (((vp)->gendev) ? DEVICE_PCI((vp)->gendev) : NULL)
+#define VORTEX_PCI(vp)                                                  \
+        ((struct pci_dev *) (((vp)->gendev) ? DEVICE_PCI((vp)->gendev) : NULL))
 
 #ifdef CONFIG_EISA
 #define DEVICE_EISA(dev) (((dev)->bus == &eisa_bus_type) ? to_eisa_device((dev)) : NULL)
@@ -707,7 +708,8 @@ DEFINE_WINDOW_IO(32)
 #define DEVICE_EISA(dev) NULL
 #endif
 
-#define VORTEX_EISA(vp) (((vp)->gendev) ? DEVICE_EISA((vp)->gendev) : NULL)
+#define VORTEX_EISA(vp)                                                 \
+        ((struct eisa_device *) (((vp)->gendev) ? DEVICE_EISA((vp)->gendev) : NULL))
 
 /* The action to take with a media selection timer tick.
    Note that we deviate from the 3Com order by checking 10base2 before AUI.
diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c
index ac422cd332e..dd16e83933a 100644
--- a/drivers/net/8139cp.c
+++ b/drivers/net/8139cp.c
@@ -490,13 +490,11 @@ static inline unsigned int cp_rx_csum_ok (u32 status)
 {
         unsigned int protocol = (status >> 16) & 0x3;
 
-        if (likely((protocol == RxProtoTCP) && (!(status & TCPFail))))
+        if (((protocol == RxProtoTCP) && !(status & TCPFail)) ||
+            ((protocol == RxProtoUDP) && !(status & UDPFail)))
                 return 1;
-        else if ((protocol == RxProtoUDP) && (!(status & UDPFail)))
-                return 1;
-        else if ((protocol == RxProtoIP) && (!(status & IPFail)))
-                return 1;
-        return 0;
+        else
+                return 0;
 }
 
 static int cp_rx_poll(struct napi_struct *napi, int budget)
diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c
index c36cd2ffbad..93354eee2cf 100644
--- a/drivers/net/benet/be_main.c
+++ b/drivers/net/benet/be_main.c
@@ -2458,6 +2458,12 @@ int be_load_fw(struct be_adapter *adapter, u8 *func)
         int status, i = 0, num_imgs = 0;
         const u8 *p;
 
+        if (!netif_running(adapter->netdev)) {
+                dev_err(&adapter->pdev->dev,
+                        "Firmware load not allowed (interface is down)\n");
+                return -EPERM;
+        }
+
         strcpy(fw_file, func);
 
         status = request_firmware(&fw, fw_file, &adapter->pdev->dev);
diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c
index e9ad16f00b5..9709b856966 100644
--- a/drivers/net/bnx2x/bnx2x_main.c
+++ b/drivers/net/bnx2x/bnx2x_main.c
@@ -9064,7 +9064,7 @@ static int __devinit bnx2x_init_one(struct pci_dev *pdev,
         default:
                 pr_err("Unknown board_type (%ld), aborting\n",
                            ent->driver_data);
-                return ENODEV;
+                return -ENODEV;
         }
 
         cid_count += CNIC_CONTEXT_USE;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bdb68a60038..71a169740d0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -878,8 +878,10 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev)
         rcu_read_lock();
         in_dev = __in_dev_get_rcu(dev);
         if (in_dev) {
+                read_lock(&in_dev->mc_list_lock);
                 for (im = in_dev->mc_list; im; im = im->next)
                         ip_mc_rejoin_group(im);
+                read_unlock(&in_dev->mc_list_lock);
         }
 
         rcu_read_unlock();
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index 8b4cea57a6c..20da1996d35 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -635,8 +635,8 @@ int cfspi_spi_probe(struct platform_device *pdev)
 
         ndev = alloc_netdev(sizeof(struct cfspi),
                         "cfspi%d", cfspi_setup);
-        if (!dev)
-                return -ENODEV;
+        if (!ndev)
+                return -ENOMEM;
 
         cfspi = netdev_priv(ndev);
         netif_stop_queue(ndev);
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 49e4ce1246a..d1bec626917 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -577,11 +577,10 @@ static int gfar_parse_group(struct device_node *np,
                         irq_of_parse_and_map(np, 1);
                 priv->gfargrp[priv->num_grps].interruptError =
                         irq_of_parse_and_map(np,2);
-                if (priv->gfargrp[priv->num_grps].interruptTransmit < 0 ||
-                        priv->gfargrp[priv->num_grps].interruptReceive < 0 ||
-                        priv->gfargrp[priv->num_grps].interruptError < 0) {
+                if (priv->gfargrp[priv->num_grps].interruptTransmit == NO_IRQ ||
+                    priv->gfargrp[priv->num_grps].interruptReceive  == NO_IRQ ||
+                    priv->gfargrp[priv->num_grps].interruptError    == NO_IRQ)
                         return -EINVAL;
-                }
         }
 
         priv->gfargrp[priv->num_grps].grp_id = priv->num_grps;
diff --git a/drivers/net/ipg.c b/drivers/net/ipg.c
index dc019809234..aa93655c3aa 100644
--- a/drivers/net/ipg.c
+++ b/drivers/net/ipg.c
@@ -88,16 +88,14 @@ static const char *ipg_brand_name[] = {
         "IC PLUS IP1000 1000/100/10 based NIC",
         "Sundance Technology ST2021 based NIC",
         "Tamarack Microelectronics TC9020/9021 based NIC",
-        "Tamarack Microelectronics TC9020/9021 based NIC",
         "D-Link NIC IP1000A"
 };
 
 static DEFINE_PCI_DEVICE_TABLE(ipg_pci_tbl) = {
         { PCI_VDEVICE(SUNDANCE, 0x1023), 0 },
         { PCI_VDEVICE(SUNDANCE, 0x2021), 1 },
-        { PCI_VDEVICE(SUNDANCE, 0x1021), 2 },
-        { PCI_VDEVICE(DLINK,    0x9021), 3 },
-        { PCI_VDEVICE(DLINK,    0x4020), 4 },
+        { PCI_VDEVICE(DLINK,    0x9021), 2 },
+        { PCI_VDEVICE(DLINK,    0x4020), 3 },
         { 0, }
 };
 
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 4c4d16905ef..7d33ef4bcb4 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -4440,8 +4440,7 @@ static inline void rtl8169_rx_csum(struct sk_buff *skb, u32 opts1)
         u32 status = opts1 & RxProtoMask;
 
         if (((status == RxProtoTCP) && !(opts1 & TCPFail)) ||
-            ((status == RxProtoUDP) && !(opts1 & UDPFail)) ||
-            ((status == RxProtoIP) && !(opts1 & IPFail)))
+            ((status == RxProtoUDP) && !(opts1 & UDPFail)))
                 skb->ip_summed = CHECKSUM_UNNECESSARY;
         else
                 skb_checksum_none_assert(skb);
diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
index 966b9496a9d..195406db3bd 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
@@ -37,7 +37,7 @@ static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah)
         int addr, eep_start_loc;
         eep_data = (u16 *)eep;
 
-        if (ah->hw_version.devid == 0x7015)
+        if (AR9287_HTC_DEVID(ah))
                 eep_start_loc = AR9287_HTC_EEP_START_LOC;
         else
                 eep_start_loc = AR9287_EEP_START_LOC;
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index f7ec31b4ddd..dfb6560dab9 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -36,8 +36,13 @@ static struct usb_device_id ath9k_hif_usb_ids[] = {
         { USB_DEVICE(0x13D3, 0x3327) }, /* Azurewave */
         { USB_DEVICE(0x13D3, 0x3328) }, /* Azurewave */
         { USB_DEVICE(0x13D3, 0x3346) }, /* IMC Networks */
+        { USB_DEVICE(0x13D3, 0x3348) }, /* Azurewave */
+        { USB_DEVICE(0x13D3, 0x3349) }, /* Azurewave */
+        { USB_DEVICE(0x13D3, 0x3350) }, /* Azurewave */
         { USB_DEVICE(0x04CA, 0x4605) }, /* Liteon */
         { USB_DEVICE(0x083A, 0xA704) }, /* SMC Networks */
+        { USB_DEVICE(0x040D, 0x3801) }, /* VIA */
+        { USB_DEVICE(0x1668, 0x1200) }, /* Verizon */
         { },
 };
 
@@ -806,6 +811,8 @@ static int ath9k_hif_usb_download_fw(struct hif_device_usb *hif_dev)
         case 0x7010:
         case 0x7015:
         case 0x9018:
+        case 0xA704:
+        case 0x1200:
                 firm_offset = AR7010_FIRMWARE_TEXT;
                 break;
         default:
@@ -928,6 +935,8 @@ static int ath9k_hif_usb_probe(struct usb_interface *interface,
         case 0x7010:
         case 0x7015:
         case 0x9018:
+        case 0xA704:
+        case 0x1200:
                 if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x0202)
                         hif_dev->fw_name = FIRMWARE_AR7010_1_1;
                 else
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index 3d7b97f1b3a..7c8a38d0456 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -249,6 +249,8 @@ static int ath9k_init_htc_services(struct ath9k_htc_priv *priv, u16 devid)
         case 0x7010:
         case 0x7015:
         case 0x9018:
+        case 0xA704:
+        case 0x1200:
                 priv->htc->credits = 45;
                 break;
         default:
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 3d19b5bc937..29d80ca7839 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -121,7 +121,7 @@ int ath9k_htc_tx_start(struct ath9k_htc_priv *priv, struct sk_buff *skb)
                         tx_hdr.data_type = ATH9K_HTC_NORMAL;
                 }
 
-                if (ieee80211_is_data(fc)) {
+                if (ieee80211_is_data_qos(fc)) {
                         qc = ieee80211_get_qos_ctl(hdr);
                         tx_hdr.tidno = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
                 }
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 6a0d99eff40..92bc5c5f487 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -817,8 +817,6 @@ void ath9k_deinit_device(struct ath_softc *sc)
 
         ath9k_ps_wakeup(sc);
 
-        pm_qos_remove_request(&ath9k_pm_qos_req);
-
         wiphy_rfkill_stop_polling(sc->hw->wiphy);
         ath_deinit_leds(sc);
 
@@ -832,6 +830,7 @@ void ath9k_deinit_device(struct ath_softc *sc)
         }
 
         ieee80211_unregister_hw(hw);
+        pm_qos_remove_request(&ath9k_pm_qos_req);
         ath_rx_cleanup(sc);
         ath_tx_cleanup(sc);
         ath9k_deinit_softc(sc);
diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h
index fa05b711e5c..dddf579aacf 100644
--- a/drivers/net/wireless/ath/ath9k/reg.h
+++ b/drivers/net/wireless/ath/ath9k/reg.h
@@ -866,7 +866,13 @@
 #define AR_DEVID_7010(_ah) \
         (((_ah)->hw_version.devid == 0x7010) || \
          ((_ah)->hw_version.devid == 0x7015) || \
-         ((_ah)->hw_version.devid == 0x9018))
+         ((_ah)->hw_version.devid == 0x9018) || \
+         ((_ah)->hw_version.devid == 0xA704) || \
+         ((_ah)->hw_version.devid == 0x1200))
+
+#define AR9287_HTC_DEVID(_ah) \
+        (((_ah)->hw_version.devid == 0x7015) || \
+         ((_ah)->hw_version.devid == 0x1200))
 
 #define AR_RADIO_SREV_MAJOR                   0xf0
 #define AR_RAD5133_SREV_MAJOR                 0xc0
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index 3317039cd28..7504ed14c72 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -553,12 +553,12 @@ static int carl9170_usb_flush(struct ar9170 *ar)
                 usb_free_urb(urb);
         }
 
-        ret = usb_wait_anchor_empty_timeout(&ar->tx_cmd, HZ);
+        ret = usb_wait_anchor_empty_timeout(&ar->tx_cmd, 1000);
         if (ret == 0)
                 err = -ETIMEDOUT;
 
         /* lets wait a while until the tx - queues are dried out */
-        ret = usb_wait_anchor_empty_timeout(&ar->tx_anch, HZ);
+        ret = usb_wait_anchor_empty_timeout(&ar->tx_anch, 1000);
         if (ret == 0)
                 err = -ETIMEDOUT;
 
diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index a38a7bd25f1..b9aedf18a04 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -57,7 +57,6 @@
 #include <linux/fcntl.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
-#include <linux/smp_lock.h>
 #include <linux/usb.h>
 #include <linux/timer.h>
 
diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c
index cce00ed81f3..af212c6a615 100644
--- a/drivers/parisc/eisa_eeprom.c
+++ b/drivers/parisc/eisa_eeprom.c
@@ -24,7 +24,6 @@
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/fs.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 95712a375cd..63d5042f207 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -715,7 +715,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
         nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
         start = vma->vm_pgoff;
         size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
-        pci_start = (mmap_api == PCI_MMAP_SYSFS) ?
+        pci_start = (mmap_api == PCI_MMAP_PROCFS) ?
                         pci_resource_start(pdev, resno) >> PAGE_SHIFT : 0;
         if (start >= pci_start && start < pci_start + size &&
                         start + nr <= pci_start + size)
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index ea00647f473..27911b55c2a 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/capability.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c
index e73ebefdf3e..315b3112aca 100644
--- a/drivers/pnp/isapnp/proc.c
+++ b/drivers/pnp/isapnp/proc.c
@@ -21,7 +21,6 @@
 #include <linux/isapnp.h>
 #include <linux/proc_fs.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 
 extern struct pnp_protocol isapnp_protocol;
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index c71d89dba30..83b4615a3b6 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -17,7 +17,6 @@
 #include <linux/device.h>
 #include <linux/poll.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index eb28fb01a38..f6489eb7e97 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -14,7 +14,6 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/smp_lock.h>
 
 #include <asm/compat.h>
 #include <asm/ccwdev.h>
diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c
index 883e2db02bd..e090a307fde 100644
--- a/drivers/s390/char/tape_char.c
+++ b/drivers/s390/char/tape_char.c
@@ -17,7 +17,6 @@
 #include <linux/types.h>
 #include <linux/proc_fs.h>
 #include <linux/mtio.h>
-#include <linux/smp_lock.h>
 #include <linux/compat.h>
 
 #include <asm/uaccess.h>
diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c
index 6c408670e08..b3a3e8e8656 100644
--- a/drivers/s390/char/tape_core.c
+++ b/drivers/s390/char/tape_core.c
@@ -209,29 +209,79 @@ tape_state_set(struct tape_device *device, enum tape_state newstate)
         wake_up(&device->state_change_wq);
 }
 
+struct tape_med_state_work_data {
+        struct tape_device *device;
+        enum tape_medium_state state;
+        struct work_struct  work;
+};
+
+static void
+tape_med_state_work_handler(struct work_struct *work)
+{
+        static char env_state_loaded[] = "MEDIUM_STATE=LOADED";
+        static char env_state_unloaded[] = "MEDIUM_STATE=UNLOADED";
+        struct tape_med_state_work_data *p =
+                container_of(work, struct tape_med_state_work_data, work);
+        struct tape_device *device = p->device;
+        char *envp[] = { NULL, NULL };
+
+        switch (p->state) {
+        case MS_UNLOADED:
+                pr_info("%s: The tape cartridge has been successfully "
+                        "unloaded\n", dev_name(&device->cdev->dev));
+                envp[0] = env_state_unloaded;
+                kobject_uevent_env(&device->cdev->dev.kobj, KOBJ_CHANGE, envp);
+                break;
+        case MS_LOADED:
+                pr_info("%s: A tape cartridge has been mounted\n",
+                        dev_name(&device->cdev->dev));
+                envp[0] = env_state_loaded;
+                kobject_uevent_env(&device->cdev->dev.kobj, KOBJ_CHANGE, envp);
+                break;
+        default:
+                break;
+        }
+        tape_put_device(device);
+        kfree(p);
+}
+
+static void
+tape_med_state_work(struct tape_device *device, enum tape_medium_state state)
+{
+        struct tape_med_state_work_data *p;
+
+        p = kzalloc(sizeof(*p), GFP_ATOMIC);
+        if (p) {
+                INIT_WORK(&p->work, tape_med_state_work_handler);
+                p->device = tape_get_device(device);
+                p->state = state;
+                schedule_work(&p->work);
+        }
+}
+
 void
 tape_med_state_set(struct tape_device *device, enum tape_medium_state newstate)
 {
-        if (device->medium_state == newstate)
+        enum tape_medium_state oldstate;
+
+        oldstate = device->medium_state;
+        if (oldstate == newstate)
                 return;
+        device->medium_state = newstate;
         switch(newstate){
         case MS_UNLOADED:
                 device->tape_generic_status |= GMT_DR_OPEN(~0);
-                if (device->medium_state == MS_LOADED)
-                        pr_info("%s: The tape cartridge has been successfully "
-                                "unloaded\n", dev_name(&device->cdev->dev));
+                if (oldstate == MS_LOADED)
+                        tape_med_state_work(device, MS_UNLOADED);
                 break;
         case MS_LOADED:
                 device->tape_generic_status &= ~GMT_DR_OPEN(~0);
-                if (device->medium_state == MS_UNLOADED)
-                        pr_info("%s: A tape cartridge has been mounted\n",
-                                dev_name(&device->cdev->dev));
+                if (oldstate == MS_UNLOADED)
+                        tape_med_state_work(device, MS_LOADED);
                 break;
         default:
-                // print nothing
                 break;
         }
-        device->medium_state = newstate;
         wake_up(&device->state_change_wq);
 }
 
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 9f661426e4a..c837d7419a6 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -30,7 +30,6 @@
 #include <linux/kmod.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
-#include <linux/smp_lock.h>
 #include <linux/string.h>
 
 MODULE_AUTHOR
@@ -249,27 +248,25 @@ static int vmlogrdr_recording(struct vmlogrdr_priv_t * logptr,
         char cp_command[80];
         char cp_response[160];
         char *onoff, *qid_string;
+        int rc;
 
-        memset(cp_command, 0x00, sizeof(cp_command));
-        memset(cp_response, 0x00, sizeof(cp_response));
-
-        onoff = ((action == 1) ? "ON" : "OFF");
+        onoff = ((action == 1) ? "ON" : "OFF");
         qid_string = ((recording_class_AB == 1) ? " QID * " : "");
 
-        /*
+        /*
          * The recording commands needs to be called with option QID
          * for guests that have previlege classes A or B.
          * Purging has to be done as separate step, because recording
          * can't be switched on as long as records are on the queue.
          * Doing both at the same time doesn't work.
          */
-
-        if (purge) {
+        if (purge && (action == 1)) {
+                memset(cp_command, 0x00, sizeof(cp_command));
+                memset(cp_response, 0x00, sizeof(cp_response));
                 snprintf(cp_command, sizeof(cp_command),
                          "RECORDING %s PURGE %s",
                          logptr->recording_name,
                          qid_string);
-
                 cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
         }
 
@@ -279,19 +276,33 @@ static int vmlogrdr_recording(struct vmlogrdr_priv_t * logptr,
                 logptr->recording_name,
                 onoff,
                 qid_string);
-
         cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
         /* The recording command will usually answer with 'Command complete'
          * on success, but when the specific service was never connected
          * before then there might be an additional informational message
          * 'HCPCRC8072I Recording entry not found' before the
-         * 'Command complete'. So I use strstr rather then the strncmp.
+         * 'Command complete'. So I use strstr rather then the strncmp.
          */
         if (strstr(cp_response,"Command complete"))
-                return 0;
+                rc = 0;
         else
-                return -EIO;
+                rc = -EIO;
+        /*
+         * If we turn recording off, we have to purge any remaining records
+         * afterwards, as a large number of queued records may impact z/VM
+         * performance.
+         */
+        if (purge && (action == 0)) {
+                memset(cp_command, 0x00, sizeof(cp_command));
+                memset(cp_response, 0x00, sizeof(cp_response));
+                snprintf(cp_command, sizeof(cp_command),
+                         "RECORDING %s PURGE %s",
+                         logptr->recording_name,
+                         qid_string);
+                cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
+        }
 
+        return rc;
 }
 
 
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index 1de672f2103..f7e4ae6bf15 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -13,7 +13,6 @@
 
 #include <linux/cdev.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 #include <asm/cio.h>
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 2ff8a22d425..e8391b89eff 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1455,7 +1455,16 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
                 break;
         case IO_SCH_UNREG_ATTACH:
         case IO_SCH_UNREG:
-                if (cdev)
+                if (!cdev)
+                        break;
+                if (cdev->private->state == DEV_STATE_SENSE_ID) {
+                        /*
+                         * Note: delayed work triggered by this event
+                         * and repeated calls to sch_event are synchronized
+                         * by the above check for work_pending(cdev).
+                         */
+                        dev_fsm_event(cdev, DEV_EVENT_NOTOPER);
+                } else
                         ccw_device_set_notoper(cdev);
                 break;
         case IO_SCH_NOP:
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index f5221749d18..7fca9c10ffc 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -35,7 +35,6 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 50286d8707f..6bd2dbc4c31 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -76,7 +76,7 @@ static void zfcp_scsi_command_fail(struct scsi_cmnd *scpnt, int result)
         scpnt->scsi_done(scpnt);
 }
 
-static int zfcp_scsi_queuecommand(struct scsi_cmnd *scpnt,
+static int zfcp_scsi_queuecommand_lck(struct scsi_cmnd *scpnt,
                                   void (*done) (struct scsi_cmnd *))
 {
         struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(scpnt->device);
@@ -127,6 +127,8 @@ static int zfcp_scsi_queuecommand(struct scsi_cmnd *scpnt,
         return ret;
 }
 
+static DEF_SCSI_QCMD(zfcp_scsi_queuecommand)
+
 static int zfcp_scsi_slave_alloc(struct scsi_device *sdev)
 {
         struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index fcf08b3f52c..b7bd5b0cc7a 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -1765,7 +1765,7 @@ out:
 } /* End twa_scsi_eh_reset() */
 
 /* This is the main scsi queue function to handle scsi opcodes */
-static int twa_scsi_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         int request_id, retval;
         TW_Device_Extension *tw_dev = (TW_Device_Extension *)SCpnt->device->host->hostdata;
@@ -1812,6 +1812,8 @@ out:
         return retval;
 } /* End twa_scsi_queue() */
 
+static DEF_SCSI_QCMD(twa_scsi_queue)
+
 /* This function hands scsi cdb's to the firmware */
 static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg)
 {
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index 6a95d111d20..13e39e1fdfe 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1501,7 +1501,7 @@ out:
 } /* End twl_scsi_eh_reset() */
 
 /* This is the main scsi queue function to handle scsi opcodes */
-static int twl_scsi_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+static int twl_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         int request_id, retval;
         TW_Device_Extension *tw_dev = (TW_Device_Extension *)SCpnt->device->host->hostdata;
@@ -1536,6 +1536,8 @@ out:
         return retval;
 } /* End twl_scsi_queue() */
 
+static DEF_SCSI_QCMD(twl_scsi_queue)
+
 /* This function tells the controller to shut down */
 static void __twl_shutdown(TW_Device_Extension *tw_dev)
 {
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index b1125341f4c..7fe96ff60c5 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1947,7 +1947,7 @@ static int tw_scsiop_test_unit_ready_complete(TW_Device_Extension *tw_dev, int r
 } /* End tw_scsiop_test_unit_ready_complete() */
 
 /* This is the main scsi queue function to handle scsi opcodes */
-static int tw_scsi_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *)) 
+static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         unsigned char *command = SCpnt->cmnd;
         int request_id = 0;
@@ -2023,6 +2023,8 @@ static int tw_scsi_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd
         return retval;
 } /* End tw_scsi_queue() */
 
+static DEF_SCSI_QCMD(tw_scsi_queue)
+
 /* This function is the interrupt service routine */
 static irqreturn_t tw_interrupt(int irq, void *dev_instance) 
 {
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 89fc1c8af86..f672491774e 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -167,7 +167,7 @@ MODULE_LICENSE("GPL");
 #include "53c700_d.h"
 
 
-STATIC int NCR_700_queuecommand(struct scsi_cmnd *, void (*done)(struct scsi_cmnd *));
+STATIC int NCR_700_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *);
 STATIC int NCR_700_abort(struct scsi_cmnd * SCpnt);
 STATIC int NCR_700_bus_reset(struct scsi_cmnd * SCpnt);
 STATIC int NCR_700_host_reset(struct scsi_cmnd * SCpnt);
@@ -1749,8 +1749,8 @@ NCR_700_intr(int irq, void *dev_id)
         return IRQ_RETVAL(handled);
 }
 
-STATIC int
-NCR_700_queuecommand(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *))
+static int
+NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *))
 {
         struct NCR_700_Host_Parameters *hostdata = 
                 (struct NCR_700_Host_Parameters *)SCp->device->host->hostdata[0];
@@ -1904,6 +1904,8 @@ NCR_700_queuecommand(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *))
         return 0;
 }
 
+STATIC DEF_SCSI_QCMD(NCR_700_queuecommand)
+
 STATIC int
 NCR_700_abort(struct scsi_cmnd * SCp)
 {
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index fc0b4b81d55..f66c33b9ab4 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -2807,7 +2807,7 @@ static int BusLogic_host_reset(struct scsi_cmnd * SCpnt)
   Outgoing Mailbox for execution by the associated Host Adapter.
 */
 
-static int BusLogic_QueueCommand(struct scsi_cmnd *Command, void (*CompletionRoutine) (struct scsi_cmnd *))
+static int BusLogic_QueueCommand_lck(struct scsi_cmnd *Command, void (*CompletionRoutine) (struct scsi_cmnd *))
 {
         struct BusLogic_HostAdapter *HostAdapter = (struct BusLogic_HostAdapter *) Command->device->host->hostdata;
         struct BusLogic_TargetFlags *TargetFlags = &HostAdapter->TargetFlags[Command->device->id];
@@ -2994,6 +2994,7 @@ static int BusLogic_QueueCommand(struct scsi_cmnd *Command, void (*CompletionRou
         return 0;
 }
 
+static DEF_SCSI_QCMD(BusLogic_QueueCommand)
 
 #if 0
 /*
diff --git a/drivers/scsi/BusLogic.h b/drivers/scsi/BusLogic.h
index 73f237a1ed9..649fcb31f26 100644
--- a/drivers/scsi/BusLogic.h
+++ b/drivers/scsi/BusLogic.h
@@ -1319,7 +1319,7 @@ static inline void BusLogic_IncrementSizeBucket(BusLogic_CommandSizeBuckets_T Co
 */
 
 static const char *BusLogic_DriverInfo(struct Scsi_Host *);
-static int BusLogic_QueueCommand(struct scsi_cmnd *, void (*CompletionRoutine) (struct scsi_cmnd *));
+static int BusLogic_QueueCommand(struct Scsi_Host *h, struct scsi_cmnd *);
 static int BusLogic_BIOSDiskParameters(struct scsi_device *, struct block_device *, sector_t, int *);
 static int BusLogic_ProcDirectoryInfo(struct Scsi_Host *, char *, char **, off_t, int, int);
 static int BusLogic_SlaveConfigure(struct scsi_device *);
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 5d2f148889a..9a5629f94f9 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -952,7 +952,7 @@ static void NCR5380_exit(struct Scsi_Host *instance)
  *      Locks: host lock taken by caller
  */
 
-static int NCR5380_queue_command(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *)) 
+static int NCR5380_queue_command_lck(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
 {
         struct Scsi_Host *instance = cmd->device->host;
         struct NCR5380_hostdata *hostdata = (struct NCR5380_hostdata *) instance->hostdata;
@@ -1021,6 +1021,7 @@ static int NCR5380_queue_command(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(NCR5380_queue_command)
 
 /**
  *      NCR5380_main    -       NCR state machines
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index bdc468c9e1d..fd40a32b1f6 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -313,7 +313,7 @@ static void NCR5380_print(struct Scsi_Host *instance);
 #endif
 static int NCR5380_abort(Scsi_Cmnd * cmd);
 static int NCR5380_bus_reset(Scsi_Cmnd * cmd);
-static int NCR5380_queue_command(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *));
+static int NCR5380_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int __maybe_unused NCR5380_proc_info(struct Scsi_Host *instance,
         char *buffer, char **start, off_t offset, int length, int inout);
 
diff --git a/drivers/scsi/NCR53c406a.c b/drivers/scsi/NCR53c406a.c
index 6961f78742a..c91888a0a23 100644
--- a/drivers/scsi/NCR53c406a.c
+++ b/drivers/scsi/NCR53c406a.c
@@ -693,7 +693,7 @@ static void wait_intr(void)
 }
 #endif
 
-static int NCR53c406a_queue(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
+static int NCR53c406a_queue_lck(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 {
         int i;
 
@@ -726,6 +726,8 @@ static int NCR53c406a_queue(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(NCR53c406a_queue)
+
 static int NCR53c406a_host_reset(Scsi_Cmnd * SCpnt)
 {
         DEB(printk("NCR53c406a_reset called\n"));
diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c
index dbbc601948e..dc5ac6e528c 100644
--- a/drivers/scsi/a100u2w.c
+++ b/drivers/scsi/a100u2w.c
@@ -911,7 +911,7 @@ static int inia100_build_scb(struct orc_host * host, struct orc_scb * scb, struc
  *      queue the command down to the controller
  */
 
-static int inia100_queue(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd *))
+static int inia100_queue_lck(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd *))
 {
         struct orc_scb *scb;
         struct orc_host *host;          /* Point to Host adapter control block */
@@ -930,6 +930,8 @@ static int inia100_queue(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd
         return 0;
 }
 
+static DEF_SCSI_QCMD(inia100_queue)
+
 /*****************************************************************************
  Function name  : inia100_abort
  Description    : Abort a queued command.
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 29c0ed1cf50..2c93d9496d6 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -248,7 +248,7 @@ static struct aac_driver_ident aac_drivers[] = {
  *      TODO: unify with aac_scsi_cmd().
  */
 
-static int aac_queuecommand(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int aac_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = cmd->device->host;
         struct aac_dev *dev = (struct aac_dev *)host->hostdata;
@@ -267,6 +267,8 @@ static int aac_queuecommand(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd
         return (aac_scsi_cmd(cmd) ? FAILED : 0);
 }
 
+static DEF_SCSI_QCMD(aac_queuecommand)
+
 /**
  *      aac_info                -       Returns the host adapter name
  *      @shost:         Scsi host to report on
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 0ec3da6f3e1..081c6de92bc 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -9500,7 +9500,7 @@ static int asc_execute_scsi_cmnd(struct scsi_cmnd *scp)
  * in the 'scp' result field.
  */
 static int
-advansys_queuecommand(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
+advansys_queuecommand_lck(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *shost = scp->device->host;
         int asc_res, result = 0;
@@ -9525,6 +9525,8 @@ advansys_queuecommand(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
         return result;
 }
 
+static DEF_SCSI_QCMD(advansys_queuecommand)
+
 static ushort __devinit AscGetEisaChipCfg(PortAddr iop_base)
 {
         PortAddr eisa_cfg_iop = (PortAddr) ASC_GET_EISA_SLOT(iop_base) |
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index 8eab8587ff2..c5169f01c1c 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -1056,7 +1056,7 @@ static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
  *  queue a command
  *
  */
-static int aha152x_queue(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha152x_queue_lck(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
 {
 #if 0
         if(*SCpnt->cmnd == REQUEST_SENSE) {
@@ -1070,6 +1070,8 @@ static int aha152x_queue(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
         return aha152x_internal_queue(SCpnt, NULL, 0, done);
 }
 
+static DEF_SCSI_QCMD(aha152x_queue)
+
 
 /*
  *  
diff --git a/drivers/scsi/aha1542.c b/drivers/scsi/aha1542.c
index 4f785f254c1..195823a51aa 100644
--- a/drivers/scsi/aha1542.c
+++ b/drivers/scsi/aha1542.c
@@ -558,7 +558,7 @@ static void aha1542_intr_handle(struct Scsi_Host *shost)
         };
 }
 
-static int aha1542_queuecommand(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
+static int aha1542_queuecommand_lck(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 {
         unchar ahacmd = CMD_START_SCSI;
         unchar direction;
@@ -718,6 +718,8 @@ static int aha1542_queuecommand(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(aha1542_queuecommand)
+
 /* Initialize mailboxes */
 static void setup_mailboxes(int bse, struct Scsi_Host *shpnt)
 {
diff --git a/drivers/scsi/aha1542.h b/drivers/scsi/aha1542.h
index 1db538552d5..b871d2b57f9 100644
--- a/drivers/scsi/aha1542.h
+++ b/drivers/scsi/aha1542.h
@@ -132,7 +132,7 @@ struct ccb {			/* Command Control Block 5.3 */
 };
 
 static int aha1542_detect(struct scsi_host_template *);
-static int aha1542_queuecommand(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int aha1542_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int aha1542_bus_reset(Scsi_Cmnd * SCpnt);
 static int aha1542_dev_reset(Scsi_Cmnd * SCpnt);
 static int aha1542_host_reset(Scsi_Cmnd * SCpnt);
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index 0107a4cc333..d058f1ab82b 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -331,7 +331,7 @@ static irqreturn_t aha1740_intr_handle(int irq, void *dev_id)
         return IRQ_RETVAL(handled);
 }
 
-static int aha1740_queuecommand(Scsi_Cmnd * SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha1740_queuecommand_lck(Scsi_Cmnd * SCpnt, void (*done)(Scsi_Cmnd *))
 {
         unchar direction;
         unchar *cmd = (unchar *) SCpnt->cmnd;
@@ -503,6 +503,8 @@ static int aha1740_queuecommand(Scsi_Cmnd * SCpnt, void (*done)(Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(aha1740_queuecommand)
+
 /* Query the board for its irq_level and irq_type.  Nothing else matters
    in enhanced mode on an EISA bus. */
 
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 88ad8482ef5..25d06662447 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -573,7 +573,7 @@ ahd_linux_info(struct Scsi_Host *host)
  * Queue an SCB to the controller.
  */
 static int
-ahd_linux_queue(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
+ahd_linux_queue_lck(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
 {
         struct   ahd_softc *ahd;
         struct   ahd_linux_device *dev = scsi_transport_device_data(cmd->device);
@@ -588,6 +588,8 @@ ahd_linux_queue(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
         return rtn;
 }
 
+static DEF_SCSI_QCMD(ahd_linux_queue)
+
 static struct scsi_target **
 ahd_linux_target_in_softc(struct scsi_target *starget)
 {
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index aeea7a61478..4a359bb307c 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -528,7 +528,7 @@ ahc_linux_info(struct Scsi_Host *host)
  * Queue an SCB to the controller.
  */
 static int
-ahc_linux_queue(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
+ahc_linux_queue_lck(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
 {
         struct   ahc_softc *ahc;
         struct   ahc_linux_device *dev = scsi_transport_device_data(cmd->device);
@@ -548,6 +548,8 @@ ahc_linux_queue(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
         return rtn;
 }
 
+static DEF_SCSI_QCMD(ahc_linux_queue)
+
 static inline struct scsi_target **
 ahc_linux_target_in_softc(struct scsi_target *starget)
 {
diff --git a/drivers/scsi/aic7xxx_old.c b/drivers/scsi/aic7xxx_old.c
index aee73fafccc..4ff60a08df0 100644
--- a/drivers/scsi/aic7xxx_old.c
+++ b/drivers/scsi/aic7xxx_old.c
@@ -10234,7 +10234,7 @@ static void aic7xxx_buildscb(struct aic7xxx_host *p, struct scsi_cmnd *cmd,
  * Description:
  *   Queue a SCB to the controller.
  *-F*************************************************************************/
-static int aic7xxx_queue(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
+static int aic7xxx_queue_lck(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
 {
   struct aic7xxx_host *p;
   struct aic7xxx_scb *scb;
@@ -10292,6 +10292,8 @@ static int aic7xxx_queue(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
   return (0);
 }
 
+static DEF_SCSI_QCMD(aic7xxx_queue)
+
 /*+F*************************************************************************
  * Function:
  *   aic7xxx_bus_device_reset
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 05a78e515a2..17e3df4f016 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -85,8 +85,7 @@ static int arcmsr_abort(struct scsi_cmnd *);
 static int arcmsr_bus_reset(struct scsi_cmnd *);
 static int arcmsr_bios_param(struct scsi_device *sdev,
                 struct block_device *bdev, sector_t capacity, int *info);
-static int arcmsr_queue_command(struct scsi_cmnd *cmd,
-                                        void (*done) (struct scsi_cmnd *));
+static int arcmsr_queue_command(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static int arcmsr_probe(struct pci_dev *pdev,
                                 const struct pci_device_id *id);
 static void arcmsr_remove(struct pci_dev *pdev);
@@ -2081,7 +2080,7 @@ static void arcmsr_handle_virtual_command(struct AdapterControlBlock *acb,
         }
 }
 
-static int arcmsr_queue_command(struct scsi_cmnd *cmd,
+static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd,
         void (* done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = cmd->device->host;
@@ -2124,6 +2123,8 @@ static int arcmsr_queue_command(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(arcmsr_queue_command)
+
 static bool arcmsr_get_hba_config(struct AdapterControlBlock *acb)
 {
         struct MessageUnit_A __iomem *reg = acb->pmuA;
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index 918ccf81875..ec166726b31 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -2511,7 +2511,7 @@ acornscsi_intr(int irq, void *dev_id)
  *            done - function called on completion, with pointer to command descriptor
  * Returns  : 0, or < 0 on error.
  */
-int acornscsi_queuecmd(struct scsi_cmnd *SCpnt,
+static int acornscsi_queuecmd_lck(struct scsi_cmnd *SCpnt,
                        void (*done)(struct scsi_cmnd *))
 {
     AS_Host *host = (AS_Host *)SCpnt->device->host->hostdata;
@@ -2561,6 +2561,8 @@ int acornscsi_queuecmd(struct scsi_cmnd *SCpnt,
     return 0;
 }
 
+DEF_SCSI_QCMD(acornscsi_queuecmd)
+
 /*
  * Prototype: void acornscsi_reportstatus(struct scsi_cmnd **SCpntp1, struct scsi_cmnd **SCpntp2, int result)
  * Purpose  : pass a result to *SCpntp1, and check if *SCpntp1 = *SCpntp2
diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index 9e71ac61114..2b2ce21e227 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -2198,7 +2198,7 @@ no_command:
  * Returns: 0 on success, else error.
  * Notes: io_request_lock is held, interrupts are disabled.
  */
-int fas216_queue_command(struct scsi_cmnd *SCpnt,
+static int fas216_queue_command_lck(struct scsi_cmnd *SCpnt,
                          void (*done)(struct scsi_cmnd *))
 {
         FAS216_Info *info = (FAS216_Info *)SCpnt->device->host->hostdata;
@@ -2240,6 +2240,8 @@ int fas216_queue_command(struct scsi_cmnd *SCpnt,
         return result;
 }
 
+DEF_SCSI_QCMD(fas216_queue_command)
+
 /**
  * fas216_internal_done - trigger restart of a waiting thread in fas216_noqueue_command
  * @SCpnt: Command to wake
@@ -2263,7 +2265,7 @@ static void fas216_internal_done(struct scsi_cmnd *SCpnt)
  * Returns: scsi result code.
  * Notes: io_request_lock is held, interrupts are disabled.
  */
-int fas216_noqueue_command(struct scsi_cmnd *SCpnt,
+static int fas216_noqueue_command_lck(struct scsi_cmnd *SCpnt,
                            void (*done)(struct scsi_cmnd *))
 {
         FAS216_Info *info = (FAS216_Info *)SCpnt->device->host->hostdata;
@@ -2277,7 +2279,7 @@ int fas216_noqueue_command(struct scsi_cmnd *SCpnt,
         BUG_ON(info->scsi.irq != NO_IRQ);
 
         info->internal_done = 0;
-        fas216_queue_command(SCpnt, fas216_internal_done);
+        fas216_queue_command_lck(SCpnt, fas216_internal_done);
 
         /*
          * This wastes time, since we can't return until the command is
@@ -2310,6 +2312,8 @@ int fas216_noqueue_command(struct scsi_cmnd *SCpnt,
         return 0;
 }
 
+DEF_SCSI_QCMD(fas216_noqueue_command)
+
 /*
  * Error handler timeout function.  Indicate that we timed out,
  * and wake up any error handler process so it can continue.
diff --git a/drivers/scsi/arm/fas216.h b/drivers/scsi/arm/fas216.h
index b65f4cf0eec..377cfb72cc6 100644
--- a/drivers/scsi/arm/fas216.h
+++ b/drivers/scsi/arm/fas216.h
@@ -331,23 +331,21 @@ extern int fas216_init (struct Scsi_Host *instance);
  */
 extern int fas216_add (struct Scsi_Host *instance, struct device *dev);
 
-/* Function: int fas216_queue_command(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+/* Function: int fas216_queue_command(struct Scsi_Host *h, struct scsi_cmnd *SCpnt)
  * Purpose : queue a command for adapter to process.
- * Params  : SCpnt - Command to queue
- *           done  - done function to call once command is complete
+ * Params  : h - host adapter
+ *         : SCpnt - Command to queue
  * Returns : 0 - success, else error
  */
-extern int fas216_queue_command(struct scsi_cmnd *,
-                                void (*done)(struct scsi_cmnd *));
+extern int fas216_queue_command(struct Scsi_Host *h, struct scsi_cmnd *SCpnt);
 
-/* Function: int fas216_noqueue_command(istruct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+/* Function: int fas216_noqueue_command(struct Scsi_Host *h, struct scsi_cmnd *SCpnt)
  * Purpose : queue a command for adapter to process, and process it to completion.
- * Params  : SCpnt - Command to queue
- *           done  - done function to call once command is complete
+ * Params  : h - host adapter
+ *         : SCpnt - Command to queue
  * Returns : 0 - success, else error
  */
-extern int fas216_noqueue_command(struct scsi_cmnd *,
-                                  void (*done)(struct scsi_cmnd *));
+extern int fas216_noqueue_command(struct Scsi_Host *, struct scsi_cmnd *)
 
 /* Function: irqreturn_t fas216_intr (FAS216_Info *info)
  * Purpose : handle interrupts from the interface to progress a command
diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
index 158ebc3644d..88b2928b4d3 100644
--- a/drivers/scsi/atari_NCR5380.c
+++ b/drivers/scsi/atari_NCR5380.c
@@ -910,7 +910,7 @@ static int __init NCR5380_init(struct Scsi_Host *instance, int flags)
  *
  */
 
-static int NCR5380_queue_command(Scsi_Cmnd *cmd, void (*done)(Scsi_Cmnd *))
+static int NCR5380_queue_command_lck(Scsi_Cmnd *cmd, void (*done)(Scsi_Cmnd *))
 {
         SETUP_HOSTDATA(cmd->device->host);
         Scsi_Cmnd *tmp;
@@ -1022,6 +1022,8 @@ static int NCR5380_queue_command(Scsi_Cmnd *cmd, void (*done)(Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(NCR5380_queue_command)
+
 /*
  * Function : NCR5380_main (void)
  *
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index ad7a23aef0e..3e8658e2f15 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -572,23 +572,6 @@ static void falcon_get_lock(void)
 }
 
 
-/* This is the wrapper function for NCR5380_queue_command(). It just
- * tries to get the lock on the ST-DMA (see above) and then calls the
- * original function.
- */
-
-#if 0
-int atari_queue_command(Scsi_Cmnd *cmd, void (*done)(Scsi_Cmnd *))
-{
-        /* falcon_get_lock();
-         * ++guenther: moved to NCR5380_queue_command() to prevent
-         * race condition, see there for an explanation.
-         */
-        return NCR5380_queue_command(cmd, done);
-}
-#endif
-
-
 int __init atari_scsi_detect(struct scsi_host_template *host)
 {
         static int called = 0;
diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index ab5bdda6903..76029d570be 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -605,7 +605,7 @@ handled:
  *
  *      Queue a command to the ATP queue. Called with the host lock held.
  */
-static int atp870u_queuecommand(struct scsi_cmnd * req_p, 
+static int atp870u_queuecommand_lck(struct scsi_cmnd *req_p,
                          void (*done) (struct scsi_cmnd *))
 {
         unsigned char c;
@@ -694,6 +694,8 @@ static int atp870u_queuecommand(struct scsi_cmnd * req_p,
         return 0;
 }
 
+static DEF_SCSI_QCMD(atp870u_queuecommand)
+
 /**
  *      send_s870       -       send a command to the controller
  *      @host: host
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 8daa716739d..8ca967dee66 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -30,8 +30,7 @@ DEFINE_IDR(bfad_im_port_index);
 struct scsi_transport_template *bfad_im_scsi_transport_template;
 struct scsi_transport_template *bfad_im_scsi_vport_transport_template;
 static void bfad_im_itnim_work_handler(struct work_struct *work);
-static int bfad_im_queuecommand(struct scsi_cmnd *cmnd,
-                                void (*done)(struct scsi_cmnd *));
+static int bfad_im_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmnd);
 static int bfad_im_slave_alloc(struct scsi_device *sdev);
 static void bfad_im_fc_rport_add(struct bfad_im_port_s  *im_port,
                                 struct bfad_itnim_s *itnim);
@@ -1120,7 +1119,7 @@ bfad_im_itnim_work_handler(struct work_struct *work)
  * Scsi_Host template entry, queue a SCSI command to the BFAD.
  */
 static int
-bfad_im_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
+bfad_im_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 {
         struct bfad_im_port_s *im_port =
                 (struct bfad_im_port_s *) cmnd->device->host->hostdata[0];
@@ -1187,6 +1186,8 @@ out_fail_cmd:
         return 0;
 }
 
+static DEF_SCSI_QCMD(bfad_im_queuecommand)
+
 void
 bfad_os_rport_online_wait(struct bfad_s *bfad)
 {
diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index 54f50b07dac..8f1b5c8bf90 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -1080,7 +1080,7 @@ static void build_srb(struct scsi_cmnd *cmd, struct DeviceCtlBlk *dcb,
  *        and is expected to be held on return.
  *
  **/
-static int dc395x_queue_command(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int dc395x_queue_command_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct DeviceCtlBlk *dcb;
         struct ScsiReqBlk *srb;
@@ -1154,6 +1154,7 @@ complete:
         return 0;
 }
 
+static DEF_SCSI_QCMD(dc395x_queue_command)
 
 /*
  * Return the disk geometry for the given SCSI device.
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 23dec006338..cffcb108ac9 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -423,7 +423,7 @@ static int adpt_slave_configure(struct scsi_device * device)
         return 0;
 }
 
-static int adpt_queue(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd *))
+static int adpt_queue_lck(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd *))
 {
         adpt_hba* pHba = NULL;
         struct adpt_device* pDev = NULL;        /* dpt per device information */
@@ -491,6 +491,8 @@ static int adpt_queue(struct scsi_cmnd * cmd, void (*done) (struct scsi_cmnd *))
         return adpt_scsi_to_i2o(pHba, cmd, pDev);
 }
 
+static DEF_SCSI_QCMD(adpt_queue)
+
 static int adpt_bios_param(struct scsi_device *sdev, struct block_device *dev,
                 sector_t capacity, int geom[])
 {
diff --git a/drivers/scsi/dpti.h b/drivers/scsi/dpti.h
index 337746d4604..beded716f93 100644
--- a/drivers/scsi/dpti.h
+++ b/drivers/scsi/dpti.h
@@ -29,7 +29,7 @@
  */
 
 static int adpt_detect(struct scsi_host_template * sht);
-static int adpt_queue(struct scsi_cmnd * cmd, void (*cmdcomplete) (struct scsi_cmnd *));
+static int adpt_queue(struct Scsi_Host *h, struct scsi_cmnd * cmd);
 static int adpt_abort(struct scsi_cmnd * cmd);
 static int adpt_reset(struct scsi_cmnd* cmd);
 static int adpt_release(struct Scsi_Host *host);
diff --git a/drivers/scsi/dtc.h b/drivers/scsi/dtc.h
index 0b205f8c732..cdc621204b6 100644
--- a/drivers/scsi/dtc.h
+++ b/drivers/scsi/dtc.h
@@ -36,7 +36,7 @@ static int dtc_abort(Scsi_Cmnd *);
 static int dtc_biosparam(struct scsi_device *, struct block_device *,
                          sector_t, int*);
 static int dtc_detect(struct scsi_host_template *);
-static int dtc_queue_command(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int dtc_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int dtc_bus_reset(Scsi_Cmnd *);
 
 #ifndef CMD_PER_LUN
diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c
index d1c31378f6d..53925ac178f 100644
--- a/drivers/scsi/eata.c
+++ b/drivers/scsi/eata.c
@@ -505,8 +505,7 @@
 
 static int eata2x_detect(struct scsi_host_template *);
 static int eata2x_release(struct Scsi_Host *);
-static int eata2x_queuecommand(struct scsi_cmnd *,
-                               void (*done) (struct scsi_cmnd *));
+static int eata2x_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int eata2x_eh_abort(struct scsi_cmnd *);
 static int eata2x_eh_host_reset(struct scsi_cmnd *);
 static int eata2x_bios_param(struct scsi_device *, struct block_device *,
@@ -1758,7 +1757,7 @@ static void scsi_to_dev_dir(unsigned int i, struct hostdata *ha)
 
 }
 
-static int eata2x_queuecommand(struct scsi_cmnd *SCpnt,
+static int eata2x_queuecommand_lck(struct scsi_cmnd *SCpnt,
                                void (*done) (struct scsi_cmnd *))
 {
         struct Scsi_Host *shost = SCpnt->device->host;
@@ -1843,6 +1842,8 @@ static int eata2x_queuecommand(struct scsi_cmnd *SCpnt,
         return 0;
 }
 
+static DEF_SCSI_QCMD(eata2x_queuecommand)
+
 static int eata2x_eh_abort(struct scsi_cmnd *SCarg)
 {
         struct Scsi_Host *shost = SCarg->device->host;
diff --git a/drivers/scsi/eata_pio.c b/drivers/scsi/eata_pio.c
index 60886c19065..4a9641e69f5 100644
--- a/drivers/scsi/eata_pio.c
+++ b/drivers/scsi/eata_pio.c
@@ -335,7 +335,7 @@ static inline unsigned int eata_pio_send_command(unsigned long base, unsigned ch
         return 0;
 }
 
-static int eata_pio_queue(struct scsi_cmnd *cmd,
+static int eata_pio_queue_lck(struct scsi_cmnd *cmd,
                 void (*done)(struct scsi_cmnd *))
 {
         unsigned int x, y;
@@ -438,6 +438,8 @@ static int eata_pio_queue(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(eata_pio_queue)
+
 static int eata_pio_abort(struct scsi_cmnd *cmd)
 {
         unsigned int loop = 100;
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index e2bc779f86c..57558523c1b 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -916,7 +916,7 @@ static void esp_event_queue_full(struct esp *esp, struct esp_cmd_entry *ent)
         scsi_track_queue_full(dev, lp->num_tagged - 1);
 }
 
-static int esp_queuecommand(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int esp_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct scsi_device *dev = cmd->device;
         struct esp *esp = shost_priv(dev->host);
@@ -941,6 +941,8 @@ static int esp_queuecommand(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd
         return 0;
 }
 
+static DEF_SCSI_QCMD(esp_queuecommand)
+
 static int esp_check_gross_error(struct esp *esp)
 {
         if (esp->sreg & ESP_STAT_SPAM) {
diff --git a/drivers/scsi/fd_mcs.c b/drivers/scsi/fd_mcs.c
index 2ad95aa8f58..a2c6135d337 100644
--- a/drivers/scsi/fd_mcs.c
+++ b/drivers/scsi/fd_mcs.c
@@ -1072,7 +1072,7 @@ static int fd_mcs_release(struct Scsi_Host *shpnt)
         return 0;
 }
 
-static int fd_mcs_queue(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
+static int fd_mcs_queue_lck(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
 {
         struct Scsi_Host *shpnt = SCpnt->device->host;
 
@@ -1122,6 +1122,8 @@ static int fd_mcs_queue(Scsi_Cmnd * SCpnt, void (*done) (Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(fd_mcs_queue)
+
 #if DEBUG_ABORT || DEBUG_RESET
 static void fd_mcs_print_info(Scsi_Cmnd * SCpnt)
 {
diff --git a/drivers/scsi/fdomain.c b/drivers/scsi/fdomain.c
index e296bcc57d5..69b7aa54f43 100644
--- a/drivers/scsi/fdomain.c
+++ b/drivers/scsi/fdomain.c
@@ -1419,7 +1419,7 @@ static irqreturn_t do_fdomain_16x0_intr(int irq, void *dev_id)
    return IRQ_HANDLED;
 }
 
-static int fdomain_16x0_queue(struct scsi_cmnd *SCpnt,
+static int fdomain_16x0_queue_lck(struct scsi_cmnd *SCpnt,
                 void (*done)(struct scsi_cmnd *))
 {
    if (in_command) {
@@ -1469,6 +1469,8 @@ static int fdomain_16x0_queue(struct scsi_cmnd *SCpnt,
    return 0;
 }
 
+static DEF_SCSI_QCMD(fdomain_16x0_queue)
+
 #if DEBUG_ABORT
 static void print_info(struct scsi_cmnd *SCpnt)
 {
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index cbb20b13b22..92f185081e6 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -246,7 +246,7 @@ void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *);
 void fnic_update_mac(struct fc_lport *, u8 *new);
 void fnic_update_mac_locked(struct fnic *, u8 *new);
 
-int fnic_queuecommand(struct scsi_cmnd *, void (*done)(struct scsi_cmnd *));
+int fnic_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 int fnic_abort_cmd(struct scsi_cmnd *);
 int fnic_device_reset(struct scsi_cmnd *);
 int fnic_host_reset(struct scsi_cmnd *);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 198cbab3e89..22d02404d15 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -349,7 +349,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
  * Routine to send a scsi cdb
  * Called with host_lock held and interrupts disabled.
  */
-int fnic_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
+static int fnic_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
 {
         struct fc_lport *lp;
         struct fc_rport *rport;
@@ -457,6 +457,8 @@ out:
         return ret;
 }
 
+DEF_SCSI_QCMD(fnic_queuecommand)
+
 /*
  * fnic_fcpio_fw_reset_cmpl_handler
  * Routine to handle fw reset completion
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
index 921764c9ab2..1bcdb7beb77 100644
--- a/drivers/scsi/g_NCR5380.h
+++ b/drivers/scsi/g_NCR5380.h
@@ -46,7 +46,7 @@
 static int generic_NCR5380_abort(Scsi_Cmnd *);
 static int generic_NCR5380_detect(struct scsi_host_template *);
 static int generic_NCR5380_release_resources(struct Scsi_Host *);
-static int generic_NCR5380_queue_command(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int generic_NCR5380_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int generic_NCR5380_bus_reset(Scsi_Cmnd *);
 static const char* generic_NCR5380_info(struct Scsi_Host *);
 
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 841101846b8..76365700e2d 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -185,7 +185,7 @@ static long gdth_unlocked_ioctl(struct file *filep, unsigned int cmd,
                                 unsigned long arg);
 
 static void gdth_flush(gdth_ha_str *ha);
-static int gdth_queuecommand(Scsi_Cmnd *scp,void (*done)(Scsi_Cmnd *));
+static int gdth_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static int __gdth_queuecommand(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                 struct gdth_cmndinfo *cmndinfo);
 static void gdth_scsi_done(struct scsi_cmnd *scp);
@@ -4004,7 +4004,7 @@ static int gdth_bios_param(struct scsi_device *sdev,struct block_device *bdev,se
 }
 
 
-static int gdth_queuecommand(struct scsi_cmnd *scp,
+static int gdth_queuecommand_lck(struct scsi_cmnd *scp,
                                 void (*done)(struct scsi_cmnd *))
 {
     gdth_ha_str *ha = shost_priv(scp->device->host);
@@ -4022,6 +4022,8 @@ static int gdth_queuecommand(struct scsi_cmnd *scp,
     return __gdth_queuecommand(ha, scp, cmndinfo);
 }
 
+static DEF_SCSI_QCMD(gdth_queuecommand)
+
 static int __gdth_queuecommand(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                 struct gdth_cmndinfo *cmndinfo)
 {
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index c5d0606ad09..b2fb2b2a6e7 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -31,7 +31,6 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
 #include <linux/compat.h>
 #include <linux/blktrace_api.h>
 #include <linux/uaccess.h>
@@ -143,8 +142,7 @@ static void fill_cmd(struct CommandList *c, u8 cmd, struct ctlr_info *h,
         void *buff, size_t size, u8 page_code, unsigned char *scsi3addr,
         int cmd_type);
 
-static int hpsa_scsi_queue_command(struct scsi_cmnd *cmd,
-                void (*done)(struct scsi_cmnd *));
+static int hpsa_scsi_queue_command(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static void hpsa_scan_start(struct Scsi_Host *);
 static int hpsa_scan_finished(struct Scsi_Host *sh,
         unsigned long elapsed_time);
@@ -1926,7 +1924,7 @@ sglist_finished:
 }
 
 
-static int hpsa_scsi_queue_command(struct scsi_cmnd *cmd,
+static int hpsa_scsi_queue_command_lck(struct scsi_cmnd *cmd,
         void (*done)(struct scsi_cmnd *))
 {
         struct ctlr_info *h;
@@ -2020,6 +2018,8 @@ static int hpsa_scsi_queue_command(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(hpsa_scsi_queue_command)
+
 static void hpsa_scan_start(struct Scsi_Host *sh)
 {
         struct ctlr_info *h = shost_to_hba(sh);
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index 0729f150b33..10b65556937 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -751,7 +751,7 @@ static void hptiop_post_req_mv(struct hptiop_hba *hba,
                 MVIOP_MU_QUEUE_ADDR_HOST_BIT | size_bit, hba);
 }
 
-static int hptiop_queuecommand(struct scsi_cmnd *scp,
+static int hptiop_queuecommand_lck(struct scsi_cmnd *scp,
                                 void (*done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = scp->device->host;
@@ -819,6 +819,8 @@ cmd_done:
         return 0;
 }
 
+static DEF_SCSI_QCMD(hptiop_queuecommand)
+
 static const char *hptiop_info(struct Scsi_Host *host)
 {
         return driver_name_long;
diff --git a/drivers/scsi/ibmmca.c b/drivers/scsi/ibmmca.c
index 9a4b69d4f4e..67fc8ffd52e 100644
--- a/drivers/scsi/ibmmca.c
+++ b/drivers/scsi/ibmmca.c
@@ -39,7 +39,7 @@
 #include <scsi/scsi_host.h>
 
 /* Common forward declarations for all Linux-versions: */
-static int ibmmca_queuecommand (Scsi_Cmnd *, void (*done) (Scsi_Cmnd *));
+static int ibmmca_queuecommand (struct Scsi_Host *, struct scsi_cmnd *);
 static int ibmmca_abort (Scsi_Cmnd *);
 static int ibmmca_host_reset (Scsi_Cmnd *);
 static int ibmmca_biosparam (struct scsi_device *, struct block_device *, sector_t, int *);
@@ -1691,7 +1691,7 @@ static int __devexit ibmmca_remove(struct device *dev)
 }
 
 /* The following routine is the SCSI command queue for the midlevel driver */
-static int ibmmca_queuecommand(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
+static int ibmmca_queuecommand_lck(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
 {
         unsigned int ldn;
         unsigned int scsi_cmd;
@@ -1996,6 +1996,8 @@ static int ibmmca_queuecommand(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(ibmmca_queuecommand)
+
 static int __ibmmca_abort(Scsi_Cmnd * cmd)
 {
         /* Abort does not work, as the adapter never generates an interrupt on
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 00d08b25425..57cad7e20ca 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1606,7 +1606,7 @@ static inline int ibmvfc_host_chkready(struct ibmvfc_host *vhost)
  * Returns:
  *      0 on success / other on failure
  **/
-static int ibmvfc_queuecommand(struct scsi_cmnd *cmnd,
+static int ibmvfc_queuecommand_lck(struct scsi_cmnd *cmnd,
                                void (*done) (struct scsi_cmnd *))
 {
         struct ibmvfc_host *vhost = shost_priv(cmnd->device->host);
@@ -1672,6 +1672,8 @@ static int ibmvfc_queuecommand(struct scsi_cmnd *cmnd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(ibmvfc_queuecommand)
+
 /**
  * ibmvfc_sync_completion - Signal that a synchronous command has completed
  * @evt:        ibmvfc event struct
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 67f78a470f5..041958453e2 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -713,7 +713,7 @@ static inline u16 lun_from_dev(struct scsi_device *dev)
  * @cmd:        struct scsi_cmnd to be executed
  * @done:       Callback function to be called when cmd is completed
 */
-static int ibmvscsi_queuecommand(struct scsi_cmnd *cmnd,
+static int ibmvscsi_queuecommand_lck(struct scsi_cmnd *cmnd,
                                  void (*done) (struct scsi_cmnd *))
 {
         struct srp_cmd *srp_cmd;
@@ -766,6 +766,8 @@ static int ibmvscsi_queuecommand(struct scsi_cmnd *cmnd,
         return ibmvscsi_send_srp_event(evt_struct, hostdata, 0);
 }
 
+static DEF_SCSI_QCMD(ibmvscsi_queuecommand)
+
 /* ------------------------------------------------------------
  * Routines for driver initialization
  */
diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c
index 4734ab0b3ff..99aa0e5699b 100644
--- a/drivers/scsi/imm.c
+++ b/drivers/scsi/imm.c
@@ -926,7 +926,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
         return 0;
 }
 
-static int imm_queuecommand(struct scsi_cmnd *cmd,
+static int imm_queuecommand_lck(struct scsi_cmnd *cmd,
                 void (*done)(struct scsi_cmnd *))
 {
         imm_struct *dev = imm_dev(cmd->device->host);
@@ -949,6 +949,8 @@ static int imm_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(imm_queuecommand)
+
 /*
  * Apparently the disk->capacity attribute is off by 1 sector 
  * for all disk drives.  We add the one here, but it should really
diff --git a/drivers/scsi/in2000.c b/drivers/scsi/in2000.c
index 52bdc6df6b9..6568aab745a 100644
--- a/drivers/scsi/in2000.c
+++ b/drivers/scsi/in2000.c
@@ -334,7 +334,7 @@ static uchar calc_sync_xfer(unsigned int period, unsigned int offset)
 
 static void in2000_execute(struct Scsi_Host *instance);
 
-static int in2000_queuecommand(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
+static int in2000_queuecommand_lck(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
 {
         struct Scsi_Host *instance;
         struct IN2000_hostdata *hostdata;
@@ -431,6 +431,8 @@ static int in2000_queuecommand(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *))
             return 0;
 }
 
+static DEF_SCSI_QCMD(in2000_queuecommand)
+
 
 
 /*
diff --git a/drivers/scsi/in2000.h b/drivers/scsi/in2000.h
index 0fb8b06b839..5821e1fbce0 100644
--- a/drivers/scsi/in2000.h
+++ b/drivers/scsi/in2000.h
@@ -396,7 +396,7 @@ struct IN2000_hostdata {
                                                            flags)
 
 static int in2000_detect(struct scsi_host_template *) in2000__INIT;
-static int in2000_queuecommand(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int in2000_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int in2000_abort(Scsi_Cmnd *);
 static void in2000_setup(char *, int *) in2000__INIT;
 static int in2000_biosparam(struct scsi_device *, struct block_device *,
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 108797761b9..9627d062e16 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -2639,7 +2639,7 @@ static void initio_build_scb(struct initio_host * host, struct scsi_ctrl_blk * c
  *      will cause the mid layer to call us again later with the command)
  */
 
-static int i91u_queuecommand(struct scsi_cmnd *cmd,
+static int i91u_queuecommand_lck(struct scsi_cmnd *cmd,
                 void (*done)(struct scsi_cmnd *))
 {
         struct initio_host *host = (struct initio_host *) cmd->device->host->hostdata;
@@ -2656,6 +2656,8 @@ static int i91u_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(i91u_queuecommand)
+
 /**
  *      i91u_bus_reset          -       reset the SCSI bus
  *      @cmnd: Command block we want to trigger the reset for
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index fa60d7df44b..5bbaee597e8 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5709,7 +5709,7 @@ static void ipr_scsi_done(struct ipr_cmnd *ipr_cmd)
  *      SCSI_MLQUEUE_DEVICE_BUSY if device is busy
  *      SCSI_MLQUEUE_HOST_BUSY if host is busy
  **/
-static int ipr_queuecommand(struct scsi_cmnd *scsi_cmd,
+static int ipr_queuecommand_lck(struct scsi_cmnd *scsi_cmd,
                             void (*done) (struct scsi_cmnd *))
 {
         struct ipr_ioa_cfg *ioa_cfg;
@@ -5792,6 +5792,8 @@ static int ipr_queuecommand(struct scsi_cmnd *scsi_cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(ipr_queuecommand)
+
 /**
  * ipr_ioctl - IOCTL handler
  * @sdev:       scsi device struct
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index f83a116955f..b2511acd39b 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -232,7 +232,7 @@ static int ips_detect(struct scsi_host_template *);
 static int ips_release(struct Scsi_Host *);
 static int ips_eh_abort(struct scsi_cmnd *);
 static int ips_eh_reset(struct scsi_cmnd *);
-static int ips_queue(struct scsi_cmnd *, void (*)(struct scsi_cmnd *));
+static int ips_queue(struct Scsi_Host *, struct scsi_cmnd *);
 static const char *ips_info(struct Scsi_Host *);
 static irqreturn_t do_ipsintr(int, void *);
 static int ips_hainit(ips_ha_t *);
@@ -1046,7 +1046,7 @@ static int ips_eh_reset(struct scsi_cmnd *SC)
 /*    Linux obtains io_request_lock before calling this function            */
 /*                                                                          */
 /****************************************************************************/
-static int ips_queue(struct scsi_cmnd *SC, void (*done) (struct scsi_cmnd *))
+static int ips_queue_lck(struct scsi_cmnd *SC, void (*done) (struct scsi_cmnd *))
 {
         ips_ha_t *ha;
         ips_passthru_t *pt;
@@ -1137,6 +1137,8 @@ static int ips_queue(struct scsi_cmnd *SC, void (*done) (struct scsi_cmnd *))
         return (0);
 }
 
+static DEF_SCSI_QCMD(ips_queue)
+
 /****************************************************************************/
 /*                                                                          */
 /* Routine Name: ips_biosparam                                              */
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index e340373b509..2924363d142 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -1753,7 +1753,7 @@ static inline int fc_fcp_lport_queue_ready(struct fc_lport *lport)
  * This is the i/o strategy routine, called by the SCSI layer. This routine
  * is called with the host_lock held.
  */
-int fc_queuecommand(struct scsi_cmnd *sc_cmd, void (*done)(struct scsi_cmnd *))
+static int fc_queuecommand_lck(struct scsi_cmnd *sc_cmd, void (*done)(struct scsi_cmnd *))
 {
         struct fc_lport *lport;
         struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
@@ -1851,6 +1851,8 @@ out:
         spin_lock_irq(lport->host->host_lock);
         return rc;
 }
+
+DEF_SCSI_QCMD(fc_queuecommand)
 EXPORT_SYMBOL(fc_queuecommand);
 
 /**
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 633e0903635..c15fde808c3 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1599,7 +1599,7 @@ enum {
         FAILURE_SESSION_NOT_READY,
 };
 
-int iscsi_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
+static int iscsi_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *))
 {
         struct iscsi_cls_session *cls_session;
         struct Scsi_Host *host;
@@ -1736,6 +1736,8 @@ fault:
         spin_lock(host->host_lock);
         return 0;
 }
+
+DEF_SCSI_QCMD(iscsi_queuecommand)
 EXPORT_SYMBOL_GPL(iscsi_queuecommand);
 
 int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 55f09e92ab5..29251fabecc 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -189,7 +189,7 @@ int sas_queue_up(struct sas_task *task)
  * Note: XXX: Remove the host unlock/lock pair when SCSI Core can
  * call us without holding an IRQ spinlock...
  */
-int sas_queuecommand(struct scsi_cmnd *cmd,
+static int sas_queuecommand_lck(struct scsi_cmnd *cmd,
                      void (*scsi_done)(struct scsi_cmnd *))
         __releases(host->host_lock)
         __acquires(dev->sata_dev.ap->lock)
@@ -254,6 +254,8 @@ out:
         return res;
 }
 
+DEF_SCSI_QCMD(sas_queuecommand)
+
 static void sas_eh_finish_cmd(struct scsi_cmnd *cmd)
 {
         struct sas_task *task = TO_SAS_TASK(cmd);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index f64b65a770b..581837b3c71 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -2899,7 +2899,7 @@ void lpfc_poll_timeout(unsigned long ptr)
  *   SCSI_MLQUEUE_HOST_BUSY - Block all devices served by this host temporarily.
  **/
 static int
-lpfc_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
+lpfc_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 {
         struct Scsi_Host  *shost = cmnd->device->host;
         struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
@@ -3060,6 +3060,8 @@ lpfc_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(lpfc_queuecommand)
+
 /**
  * lpfc_abort_handler - scsi_host_template eh_abort_handler entry point
  * @cmnd: Pointer to scsi_cmnd data structure.
diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c
index 3ddb4dc62d5..6c42dff0f4d 100644
--- a/drivers/scsi/mac53c94.c
+++ b/drivers/scsi/mac53c94.c
@@ -66,7 +66,7 @@ static void cmd_done(struct fsc_state *, int result);
 static void set_dma_cmds(struct fsc_state *, struct scsi_cmnd *);
 
 
-static int mac53c94_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int mac53c94_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct fsc_state *state;
 
@@ -99,6 +99,8 @@ static int mac53c94_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *
         return 0;
 }
 
+static DEF_SCSI_QCMD(mac53c94_queue)
+
 static int mac53c94_host_reset(struct scsi_cmnd *cmd)
 {
         struct fsc_state *state = (struct fsc_state *) cmd->device->host->hostdata;
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 7ceb5cf12c6..9aa048525eb 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -366,7 +366,7 @@ mega_runpendq(adapter_t *adapter)
  * The command queuing entry point for the mid-layer.
  */
 static int
-megaraid_queue(Scsi_Cmnd *scmd, void (*done)(Scsi_Cmnd *))
+megaraid_queue_lck(Scsi_Cmnd *scmd, void (*done)(Scsi_Cmnd *))
 {
         adapter_t       *adapter;
         scb_t   *scb;
@@ -409,6 +409,8 @@ megaraid_queue(Scsi_Cmnd *scmd, void (*done)(Scsi_Cmnd *))
         return busy;
 }
 
+static DEF_SCSI_QCMD(megaraid_queue)
+
 /**
  * mega_allocate_scb()
  * @adapter - pointer to our soft state
@@ -4456,7 +4458,7 @@ mega_internal_command(adapter_t *adapter, megacmd_t *mc, mega_passthru *pthru)
 
         scb->idx = CMDID_INT_CMDS;
 
-        megaraid_queue(scmd, mega_internal_done);
+        megaraid_queue_lck(scmd, mega_internal_done);
 
         wait_for_completion(&adapter->int_waitq);
 
diff --git a/drivers/scsi/megaraid.h b/drivers/scsi/megaraid.h
index 2b4a048cadf..f5644745e24 100644
--- a/drivers/scsi/megaraid.h
+++ b/drivers/scsi/megaraid.h
@@ -987,7 +987,7 @@ static int mega_query_adapter(adapter_t *);
 static int issue_scb(adapter_t *, scb_t *);
 static int mega_setup_mailbox(adapter_t *);
 
-static int megaraid_queue (Scsi_Cmnd *, void (*)(Scsi_Cmnd *));
+static int megaraid_queue (struct Scsi_Host *, struct scsi_cmnd *);
 static scb_t * mega_build_cmd(adapter_t *, Scsi_Cmnd *, int *);
 static void __mega_runpendq(adapter_t *);
 static int issue_scb_block(adapter_t *, u_char *);
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index a7810a106b3..5708cb27d07 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -113,8 +113,7 @@ static int megaraid_mbox_fire_sync_cmd(adapter_t *);
 static void megaraid_mbox_display_scb(adapter_t *, scb_t *);
 static void megaraid_mbox_setup_device_map(adapter_t *);
 
-static int megaraid_queue_command(struct scsi_cmnd *,
-                void (*)(struct scsi_cmnd *));
+static int megaraid_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static scb_t *megaraid_mbox_build_cmd(adapter_t *, struct scsi_cmnd *, int *);
 static void megaraid_mbox_runpendq(adapter_t *, scb_t *);
 static void megaraid_mbox_prepare_pthru(adapter_t *, scb_t *,
@@ -1484,7 +1483,7 @@ mbox_post_cmd(adapter_t *adapter, scb_t *scb)
  * Queue entry point for mailbox based controllers.
  */
 static int
-megaraid_queue_command(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
+megaraid_queue_command_lck(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
 {
         adapter_t       *adapter;
         scb_t           *scb;
@@ -1513,6 +1512,8 @@ megaraid_queue_command(struct scsi_cmnd *scp, void (*done)(struct scsi_cmnd *))
         return if_busy;
 }
 
+static DEF_SCSI_QCMD(megaraid_queue_command)
+
 /**
  * megaraid_mbox_build_cmd - transform the mid-layer scsi commands
  * @adapter     : controller's soft state
diff --git a/drivers/scsi/megaraid/megaraid_sas.c b/drivers/scsi/megaraid/megaraid_sas.c
index eb29d508513..7451bc096a0 100644
--- a/drivers/scsi/megaraid/megaraid_sas.c
+++ b/drivers/scsi/megaraid/megaraid_sas.c
@@ -1334,7 +1334,7 @@ megasas_dump_pending_frames(struct megasas_instance *instance)
  * @done:                       Callback entry point
  */
 static int
-megasas_queue_command(struct scsi_cmnd *scmd, void (*done) (struct scsi_cmnd *))
+megasas_queue_command_lck(struct scsi_cmnd *scmd, void (*done) (struct scsi_cmnd *))
 {
         u32 frame_count;
         struct megasas_cmd *cmd;
@@ -1417,6 +1417,8 @@ megasas_queue_command(struct scsi_cmnd *scmd, void (*done) (struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(megasas_queue_command)
+
 static struct megasas_instance *megasas_lookup_instance(u16 host_no)
 {
         int i;
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 1f784fde251..197aa1b3f0f 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -1627,7 +1627,7 @@ static void cmd_complete(struct mesh_state *ms)
  * Called by midlayer with host locked to queue a new
  * request
  */
-static int mesh_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int mesh_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct mesh_state *ms;
 
@@ -1648,6 +1648,8 @@ static int mesh_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(mesh_queue)
+
 /*
  * Called to handle interrupts, either call by the interrupt
  * handler (do_mesh_interrupt) or by other functions in
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 16e99b68635..1a96a00418a 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -3315,7 +3315,7 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
  * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full
  */
 static int
-_scsih_qcmd(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
+_scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 {
         struct MPT2SAS_ADAPTER *ioc = shost_priv(scmd->device->host);
         struct MPT2SAS_DEVICE *sas_device_priv_data;
@@ -3441,6 +3441,8 @@ _scsih_qcmd(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
         return SCSI_MLQUEUE_HOST_BUSY;
 }
 
+static DEF_SCSI_QCMD(_scsih_qcmd)
+
 /**
  * _scsih_normalize_sense - normalize descriptor and fixed format sense data
  * @sense_buffer: sense data returned by target
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index d013a2aa2fd..46cc3825638 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -8029,7 +8029,7 @@ static int ncr53c8xx_slave_configure(struct scsi_device *device)
         return 0;
 }
 
-static int ncr53c8xx_queue_command (struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd *))
+static int ncr53c8xx_queue_command_lck (struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
      struct ncb *np = ((struct host_data *) cmd->device->host->hostdata)->ncb;
      unsigned long flags;
@@ -8068,6 +8068,8 @@ printk("ncr53c8xx : command successfully queued\n");
      return sts;
 }
 
+static DEF_SCSI_QCMD(ncr53c8xx_queue_command)
+
 irqreturn_t ncr53c8xx_intr(int irq, void *dev_id)
 {
      unsigned long flags;
diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c
index 4c1e5454520..6b8b021400f 100644
--- a/drivers/scsi/nsp32.c
+++ b/drivers/scsi/nsp32.c
@@ -196,8 +196,7 @@ static void __exit    exit_nsp32  (void);
 static int         nsp32_proc_info   (struct Scsi_Host *, char *, char **, off_t, int, int);
 
 static int         nsp32_detect      (struct pci_dev *pdev);
-static int         nsp32_queuecommand(struct scsi_cmnd *,
-                void (*done)(struct scsi_cmnd *));
+static int         nsp32_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static const char *nsp32_info        (struct Scsi_Host *);
 static int         nsp32_release     (struct Scsi_Host *);
 
@@ -909,7 +908,7 @@ static int nsp32_setup_sg_table(struct scsi_cmnd *SCpnt)
         return TRUE;
 }
 
-static int nsp32_queuecommand(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+static int nsp32_queuecommand_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         nsp32_hw_data *data = (nsp32_hw_data *)SCpnt->device->host->hostdata;
         nsp32_target *target;
@@ -1050,6 +1049,8 @@ static int nsp32_queuecommand(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_
         return 0;
 }
 
+static DEF_SCSI_QCMD(nsp32_queuecommand)
+
 /* initialize asic */
 static int nsp32hw_init(nsp32_hw_data *data)
 {
diff --git a/drivers/scsi/pas16.h b/drivers/scsi/pas16.h
index 8dc5b1a5f5d..a04281cace2 100644
--- a/drivers/scsi/pas16.h
+++ b/drivers/scsi/pas16.h
@@ -118,7 +118,7 @@ static int pas16_abort(Scsi_Cmnd *);
 static int pas16_biosparam(struct scsi_device *, struct block_device *,
                            sector_t, int*);
 static int pas16_detect(struct scsi_host_template *);
-static int pas16_queue_command(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int pas16_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int pas16_bus_reset(Scsi_Cmnd *);
 
 #ifndef CMD_PER_LUN
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index 9326c2c1488..be3f33d31a9 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -184,7 +184,7 @@ static void nsp_scsi_done(struct scsi_cmnd *SCpnt)
         SCpnt->scsi_done(SCpnt);
 }
 
-static int nsp_queuecommand(struct scsi_cmnd *SCpnt,
+static int nsp_queuecommand_lck(struct scsi_cmnd *SCpnt,
                             void (*done)(struct scsi_cmnd *))
 {
 #ifdef NSP_DEBUG
@@ -264,6 +264,8 @@ static int nsp_queuecommand(struct scsi_cmnd *SCpnt,
         return 0;
 }
 
+static DEF_SCSI_QCMD(nsp_queuecommand)
+
 /*
  * setup PIO FIFO transfer mode and enable/disable to data out
  */
diff --git a/drivers/scsi/pcmcia/nsp_cs.h b/drivers/scsi/pcmcia/nsp_cs.h
index d68c9f267c5..7fc9a9d0a44 100644
--- a/drivers/scsi/pcmcia/nsp_cs.h
+++ b/drivers/scsi/pcmcia/nsp_cs.h
@@ -299,8 +299,7 @@ static        int        nsp_proc_info  (
                                          off_t   offset,
                                          int     length,
                                          int     inout);
-static int nsp_queuecommand(struct scsi_cmnd *SCpnt,
-                            void (* done)(struct scsi_cmnd *SCpnt));
+static int nsp_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *SCpnt);
 
 /* Error handler */
 /*static int nsp_eh_abort       (struct scsi_cmnd *SCpnt);*/
diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c
index 0ae27cb5cd6..8552296edaa 100644
--- a/drivers/scsi/pcmcia/sym53c500_cs.c
+++ b/drivers/scsi/pcmcia/sym53c500_cs.c
@@ -547,7 +547,7 @@ SYM53C500_info(struct Scsi_Host *SChost)
 }
 
 static int 
-SYM53C500_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+SYM53C500_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 {
         int i;
         int port_base = SCpnt->device->host->io_port;
@@ -583,6 +583,8 @@ SYM53C500_queue(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(SYM53C500_queue)
+
 static int 
 SYM53C500_host_reset(struct scsi_cmnd *SCpnt)
 {
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index 8e38ca8cd10..7f064f9ca82 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -50,7 +50,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
-#include <linux/smp_lock.h>
 #include <scsi/libsas.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/sas_ata.h>
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index cf89091e4c3..5e76a624cb0 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -3478,7 +3478,7 @@ static int pmcraid_copy_sglist(
  *        SCSI_MLQUEUE_DEVICE_BUSY if device is busy
  *        SCSI_MLQUEUE_HOST_BUSY if host is busy
  */
-static int pmcraid_queuecommand(
+static int pmcraid_queuecommand_lck(
         struct scsi_cmnd *scsi_cmd,
         void (*done) (struct scsi_cmnd *)
 )
@@ -3584,6 +3584,8 @@ static int pmcraid_queuecommand(
         return rc;
 }
 
+static DEF_SCSI_QCMD(pmcraid_queuecommand)
+
 /**
  * pmcraid_open -char node "open" entry, allowed only users with admin access
  */
diff --git a/drivers/scsi/ppa.c b/drivers/scsi/ppa.c
index 7bc2d796e40..d164c963936 100644
--- a/drivers/scsi/ppa.c
+++ b/drivers/scsi/ppa.c
@@ -798,7 +798,7 @@ static int ppa_engine(ppa_struct *dev, struct scsi_cmnd *cmd)
         return 0;
 }
 
-static int ppa_queuecommand(struct scsi_cmnd *cmd,
+static int ppa_queuecommand_lck(struct scsi_cmnd *cmd,
                 void (*done) (struct scsi_cmnd *))
 {
         ppa_struct *dev = ppa_dev(cmd->device->host);
@@ -821,6 +821,8 @@ static int ppa_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(ppa_queuecommand)
+
 /*
  * Apparently the disk->capacity attribute is off by 1 sector 
  * for all disk drives.  We add the one here, but it should really
diff --git a/drivers/scsi/ps3rom.c b/drivers/scsi/ps3rom.c
index 92ffbb51049..cd178b9e40c 100644
--- a/drivers/scsi/ps3rom.c
+++ b/drivers/scsi/ps3rom.c
@@ -211,7 +211,7 @@ static int ps3rom_write_request(struct ps3_storage_device *dev,
         return 0;
 }
 
-static int ps3rom_queuecommand(struct scsi_cmnd *cmd,
+static int ps3rom_queuecommand_lck(struct scsi_cmnd *cmd,
                                void (*done)(struct scsi_cmnd *))
 {
         struct ps3rom_private *priv = shost_priv(cmd->device->host);
@@ -260,6 +260,8 @@ static int ps3rom_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(ps3rom_queuecommand)
+
 static int decode_lv1_status(u64 status, unsigned char *sense_key,
                              unsigned char *asc, unsigned char *ascq)
 {
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index b8166ecfd0e..5dec684bf01 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -727,7 +727,7 @@ qla1280_info(struct Scsi_Host *host)
  * context which is a big NO! NO!.
  **************************************************************************/
 static int
-qla1280_queuecommand(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
+qla1280_queuecommand_lck(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = cmd->device->host;
         struct scsi_qla_host *ha = (struct scsi_qla_host *)host->hostdata;
@@ -756,6 +756,8 @@ qla1280_queuecommand(struct scsi_cmnd *cmd, void (*fn)(struct scsi_cmnd *))
         return status;
 }
 
+static DEF_SCSI_QCMD(qla1280_queuecommand)
+
 enum action {
         ABORT_COMMAND,
         DEVICE_RESET,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1830e6e9731..1644eabaafe 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -179,8 +179,7 @@ static int qla2xxx_slave_alloc(struct scsi_device *);
 static int qla2xxx_scan_finished(struct Scsi_Host *, unsigned long time);
 static void qla2xxx_scan_start(struct Scsi_Host *);
 static void qla2xxx_slave_destroy(struct scsi_device *);
-static int qla2xxx_queuecommand(struct scsi_cmnd *cmd,
-                void (*fn)(struct scsi_cmnd *));
+static int qla2xxx_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static int qla2xxx_eh_abort(struct scsi_cmnd *);
 static int qla2xxx_eh_device_reset(struct scsi_cmnd *);
 static int qla2xxx_eh_target_reset(struct scsi_cmnd *);
@@ -535,7 +534,7 @@ qla2x00_get_new_sp(scsi_qla_host_t *vha, fc_port_t *fcport,
 }
 
 static int
-qla2xxx_queuecommand(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+qla2xxx_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         scsi_qla_host_t *vha = shost_priv(cmd->device->host);
         fc_port_t *fcport = (struct fc_port *) cmd->device->hostdata;
@@ -609,6 +608,8 @@ qc24_fail_command:
         return 0;
 }
 
+static DEF_SCSI_QCMD(qla2xxx_queuecommand)
+
 
 /*
  * qla2x00_eh_wait_on_command
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index f4cd846abf6..0d48fb4d104 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -79,8 +79,7 @@ static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc);
 /*
  * SCSI host template entry points
  */
-static int qla4xxx_queuecommand(struct scsi_cmnd *cmd,
-                                void (*done) (struct scsi_cmnd *));
+static int qla4xxx_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static int qla4xxx_eh_abort(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd);
@@ -464,7 +463,7 @@ void qla4xxx_srb_compl(struct kref *ref)
  * completion handling).   Unfortunely, it sometimes calls the scheduler
  * in interrupt context which is a big NO! NO!.
  **/
-static int qla4xxx_queuecommand(struct scsi_cmnd *cmd,
+static int qla4xxx_queuecommand_lck(struct scsi_cmnd *cmd,
                                 void (*done)(struct scsi_cmnd *))
 {
         struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
@@ -538,6 +537,8 @@ qc_fail_command:
         return 0;
 }
 
+static DEF_SCSI_QCMD(qla4xxx_queuecommand)
+
 /**
  * qla4xxx_mem_free - frees memory allocated to adapter
  * @ha: Pointer to host adapter structure.
diff --git a/drivers/scsi/qlogicfas408.c b/drivers/scsi/qlogicfas408.c
index 1ad51552d6b..c3a9151ca82 100644
--- a/drivers/scsi/qlogicfas408.c
+++ b/drivers/scsi/qlogicfas408.c
@@ -439,7 +439,7 @@ irqreturn_t qlogicfas408_ihandl(int irq, void *dev_id)
  *      Queued command
  */
 
-int qlogicfas408_queuecommand(struct scsi_cmnd *cmd,
+static int qlogicfas408_queuecommand_lck(struct scsi_cmnd *cmd,
                               void (*done) (struct scsi_cmnd *))
 {
         struct qlogicfas408_priv *priv = get_priv_by_cmd(cmd);
@@ -459,6 +459,8 @@ int qlogicfas408_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+DEF_SCSI_QCMD(qlogicfas408_queuecommand)
+
 /* 
  *      Return bios parameters 
  */
diff --git a/drivers/scsi/qlogicfas408.h b/drivers/scsi/qlogicfas408.h
index 260626427a3..2f6c0a16620 100644
--- a/drivers/scsi/qlogicfas408.h
+++ b/drivers/scsi/qlogicfas408.h
@@ -103,8 +103,7 @@ struct qlogicfas408_priv {
 #define get_priv_by_host(x) (struct qlogicfas408_priv *)&((x)->hostdata[0])
 
 irqreturn_t qlogicfas408_ihandl(int irq, void *dev_id);
-int qlogicfas408_queuecommand(struct scsi_cmnd * cmd,
-                              void (*done) (struct scsi_cmnd *));
+int qlogicfas408_queuecommand(struct Scsi_Host *h, struct scsi_cmnd * cmd);
 int qlogicfas408_biosparam(struct scsi_device * disk,
                            struct block_device *dev,
                            sector_t capacity, int ip[]);
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index f8c561cf751..664c9572d0c 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -1003,7 +1003,7 @@ static int qlogicpti_slave_configure(struct scsi_device *sdev)
  *
  * "This code must fly." -davem
  */
-static int qlogicpti_queuecommand(struct scsi_cmnd *Cmnd, void (*done)(struct scsi_cmnd *))
+static int qlogicpti_queuecommand_lck(struct scsi_cmnd *Cmnd, void (*done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = Cmnd->device->host;
         struct qlogicpti *qpti = (struct qlogicpti *) host->hostdata;
@@ -1052,6 +1052,8 @@ toss_command:
         return 1;
 }
 
+static DEF_SCSI_QCMD(qlogicpti_queuecommand)
+
 static int qlogicpti_return_status(struct Status_Entry *sts, int id)
 {
         int host_status = DID_ERROR;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 348fba0a897..2aeb2e9c4d3 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -634,12 +634,13 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
  * Description: a serial number identifies a request for error recovery
  * and debugging purposes.  Protected by the Host_Lock of host.
  */
-static inline void scsi_cmd_get_serial(struct Scsi_Host *host, struct scsi_cmnd *cmd)
+void scsi_cmd_get_serial(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 {
         cmd->serial_number = host->cmd_serial_number++;
         if (cmd->serial_number == 0) 
                 cmd->serial_number = host->cmd_serial_number++;
 }
+EXPORT_SYMBOL(scsi_cmd_get_serial);
 
 /**
  * scsi_dispatch_command - Dispatch a command to the low-level driver.
@@ -651,7 +652,6 @@ static inline void scsi_cmd_get_serial(struct Scsi_Host *host, struct scsi_cmnd
 int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 {
         struct Scsi_Host *host = cmd->device->host;
-        unsigned long flags = 0;
         unsigned long timeout;
         int rtn = 0;
 
@@ -737,23 +737,15 @@ int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
                 goto out;
         }
 
-        spin_lock_irqsave(host->host_lock, flags);
-        /*
-         * AK: unlikely race here: for some reason the timer could
-         * expire before the serial number is set up below.
-         *
-         * TODO: kill serial or move to blk layer
-         */
-        scsi_cmd_get_serial(host, cmd); 
-
         if (unlikely(host->shost_state == SHOST_DEL)) {
                 cmd->result = (DID_NO_CONNECT << 16);
                 scsi_done(cmd);
         } else {
                 trace_scsi_dispatch_cmd_start(cmd);
-                rtn = host->hostt->queuecommand(cmd, scsi_done);
+                cmd->scsi_done = scsi_done;
+                rtn = host->hostt->queuecommand(host, cmd);
         }
-        spin_unlock_irqrestore(host->host_lock, flags);
+
         if (rtn) {
                 trace_scsi_dispatch_cmd_error(cmd, rtn);
                 if (rtn != SCSI_MLQUEUE_DEVICE_BUSY &&
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 2c36bae3bd4..2f1f9b079b1 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -3538,7 +3538,7 @@ static void sdebug_remove_adapter(void)
 }
 
 static
-int scsi_debug_queuecommand(struct scsi_cmnd *SCpnt, done_funct_t done)
+int scsi_debug_queuecommand_lck(struct scsi_cmnd *SCpnt, done_funct_t done)
 {
         unsigned char *cmd = (unsigned char *) SCpnt->cmnd;
         int len, k;
@@ -3884,6 +3884,8 @@ write:
                              (delay_override ? 0 : scsi_debug_delay));
 }
 
+static DEF_SCSI_QCMD(scsi_debug_queuecommand)
+
 static struct scsi_host_template sdebug_driver_template = {
         .proc_info =            scsi_debug_proc_info,
         .proc_name =            sdebug_proc_name,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f3cf924a2cd..824b8fc03ce 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -773,17 +773,15 @@ static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd,
         struct Scsi_Host *shost = sdev->host;
         DECLARE_COMPLETION_ONSTACK(done);
         unsigned long timeleft;
-        unsigned long flags;
         struct scsi_eh_save ses;
         int rtn;
 
         scsi_eh_prep_cmnd(scmd, &ses, cmnd, cmnd_size, sense_bytes);
         shost->eh_action = &done;
 
-        spin_lock_irqsave(shost->host_lock, flags);
         scsi_log_send(scmd);
-        shost->hostt->queuecommand(scmd, scsi_eh_done);
-        spin_unlock_irqrestore(shost->host_lock, flags);
+        scmd->scsi_done = scsi_eh_done;
+        shost->hostt->queuecommand(shost, scmd);
 
         timeleft = wait_for_completion_timeout(&done, timeout);
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index b9ab3a590e4..956496182c8 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -46,7 +46,6 @@
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
 #include <linux/delay.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/string_helpers.h>
 #include <linux/async.h>
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index 9c73dbda3bb..606215e54b8 100644
--- a/drivers/scsi/stex.c
+++ b/drivers/scsi/stex.c
@@ -572,7 +572,7 @@ stex_slave_destroy(struct scsi_device *sdev)
 }
 
 static int
-stex_queuecommand(struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd *))
+stex_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct st_hba *hba;
         struct Scsi_Host *host;
@@ -698,6 +698,8 @@ stex_queuecommand(struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(stex_queuecommand)
+
 static void stex_scsi_done(struct st_ccb *ccb)
 {
         struct scsi_cmnd *cmd = ccb->cmd;
diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c
index 713620ed70d..4f0e5485ffd 100644
--- a/drivers/scsi/sun3_NCR5380.c
+++ b/drivers/scsi/sun3_NCR5380.c
@@ -908,7 +908,7 @@ static int NCR5380_init (struct Scsi_Host *instance, int flags)
  */
 
 /* Only make static if a wrapper function is used */
-static int NCR5380_queue_command(struct scsi_cmnd *cmd,
+static int NCR5380_queue_command_lck(struct scsi_cmnd *cmd,
                                  void (*done)(struct scsi_cmnd *))
 {
     SETUP_HOSTDATA(cmd->device->host);
@@ -1019,6 +1019,8 @@ static int NCR5380_queue_command(struct scsi_cmnd *cmd,
     return 0;
 }
 
+static DEF_SCSI_QCMD(NCR5380_queue_command)
+
 /*
  * Function : NCR5380_main (void) 
  *
diff --git a/drivers/scsi/sun3_scsi.h b/drivers/scsi/sun3_scsi.h
index b29a9d661ca..bcefd8458e6 100644
--- a/drivers/scsi/sun3_scsi.h
+++ b/drivers/scsi/sun3_scsi.h
@@ -51,8 +51,7 @@ static int sun3scsi_abort(struct scsi_cmnd *);
 static int sun3scsi_detect (struct scsi_host_template *);
 static const char *sun3scsi_info (struct Scsi_Host *);
 static int sun3scsi_bus_reset(struct scsi_cmnd *);
-static int sun3scsi_queue_command(struct scsi_cmnd *,
-                                  void (*done)(struct scsi_cmnd *));
+static int sun3scsi_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int sun3scsi_release (struct Scsi_Host *);
 
 #ifndef CMD_PER_LUN
diff --git a/drivers/scsi/sym53c416.c b/drivers/scsi/sym53c416.c
index e5c369bb568..190107ae120 100644
--- a/drivers/scsi/sym53c416.c
+++ b/drivers/scsi/sym53c416.c
@@ -734,7 +734,7 @@ const char *sym53c416_info(struct Scsi_Host *SChost)
         return info;
 }
 
-int sym53c416_queuecommand(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
+static int sym53c416_queuecommand_lck(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
 {
         int base;
         unsigned long flags = 0;
@@ -761,6 +761,8 @@ int sym53c416_queuecommand(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
         return 0;
 }
 
+DEF_SCSI_QCMD(sym53c416_queuecommand)
+
 static int sym53c416_host_reset(Scsi_Cmnd *SCpnt)
 {
         int base;
diff --git a/drivers/scsi/sym53c416.h b/drivers/scsi/sym53c416.h
index 77860d0748f..387de5d80a7 100644
--- a/drivers/scsi/sym53c416.h
+++ b/drivers/scsi/sym53c416.h
@@ -25,7 +25,7 @@
 static int sym53c416_detect(struct scsi_host_template *);
 static const char *sym53c416_info(struct Scsi_Host *);
 static int sym53c416_release(struct Scsi_Host *);
-static int sym53c416_queuecommand(Scsi_Cmnd *, void (*done)(Scsi_Cmnd *));
+static int sym53c416_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int sym53c416_host_reset(Scsi_Cmnd *);
 static int sym53c416_bios_param(struct scsi_device *, struct block_device *,
                 sector_t, int *);
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index 8b955b534a3..6b97ded9d45 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -505,7 +505,7 @@ void sym_log_bus_error(struct Scsi_Host *shost)
  * queuecommand method.  Entered with the host adapter lock held and
  * interrupts disabled.
  */
-static int sym53c8xx_queue_command(struct scsi_cmnd *cmd,
+static int sym53c8xx_queue_command_lck(struct scsi_cmnd *cmd,
                                         void (*done)(struct scsi_cmnd *))
 {
         struct sym_hcb *np = SYM_SOFTC_PTR(cmd);
@@ -536,6 +536,8 @@ static int sym53c8xx_queue_command(struct scsi_cmnd *cmd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(sym53c8xx_queue_command)
+
 /*
  *  Linux entry point of the interrupt handler.
  */
diff --git a/drivers/scsi/t128.h b/drivers/scsi/t128.h
index 76a069b7ac0..ada1115079c 100644
--- a/drivers/scsi/t128.h
+++ b/drivers/scsi/t128.h
@@ -96,8 +96,7 @@ static int t128_abort(struct scsi_cmnd *);
 static int t128_biosparam(struct scsi_device *, struct block_device *,
                           sector_t, int*);
 static int t128_detect(struct scsi_host_template *);
-static int t128_queue_command(struct scsi_cmnd *,
-                              void (*done)(struct scsi_cmnd *));
+static int t128_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
 static int t128_bus_reset(struct scsi_cmnd *);
 
 #ifndef CMD_PER_LUN
diff --git a/drivers/scsi/tmscsim.c b/drivers/scsi/tmscsim.c
index 27866b0adfe..a124a28f2cc 100644
--- a/drivers/scsi/tmscsim.c
+++ b/drivers/scsi/tmscsim.c
@@ -1883,7 +1883,7 @@ dc390_ScsiRstDetect( struct dc390_acb* pACB )
     return;
 }
 
-static int DC390_queuecommand(struct scsi_cmnd *cmd,
+static int DC390_queuecommand_lck(struct scsi_cmnd *cmd,
                 void (*done)(struct scsi_cmnd *))
 {
         struct scsi_device *sdev = cmd->device;
@@ -1944,6 +1944,8 @@ static int DC390_queuecommand(struct scsi_cmnd *cmd,
         return SCSI_MLQUEUE_DEVICE_BUSY;
 }
 
+static DEF_SCSI_QCMD(DC390_queuecommand)
+
 static void dc390_dumpinfo (struct dc390_acb* pACB, struct dc390_dcb* pDCB, struct dc390_srb* pSRB)
 {
     struct pci_dev *pdev;
diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c
index 5d9fdeeb231..edfc5da8be4 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -433,7 +433,7 @@
 
 static int u14_34f_detect(struct scsi_host_template *);
 static int u14_34f_release(struct Scsi_Host *);
-static int u14_34f_queuecommand(struct scsi_cmnd *, void (*done)(struct scsi_cmnd *));
+static int u14_34f_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int u14_34f_eh_abort(struct scsi_cmnd *);
 static int u14_34f_eh_host_reset(struct scsi_cmnd *);
 static int u14_34f_bios_param(struct scsi_device *, struct block_device *,
@@ -1248,7 +1248,7 @@ static void scsi_to_dev_dir(unsigned int i, unsigned int j) {
 
 }
 
-static int u14_34f_queuecommand(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *)) {
+static int u14_34f_queuecommand_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *)) {
    unsigned int i, j, k;
    struct mscp *cpp;
 
@@ -1329,6 +1329,8 @@ static int u14_34f_queuecommand(struct scsi_cmnd *SCpnt, void (*done)(struct scs
    return 0;
 }
 
+static DEF_SCSI_QCMD(u14_34f_queuecommand)
+
 static int u14_34f_eh_abort(struct scsi_cmnd *SCarg) {
    unsigned int i, j;
 
diff --git a/drivers/scsi/ultrastor.c b/drivers/scsi/ultrastor.c
index 27aa40f3980..0571ef9639c 100644
--- a/drivers/scsi/ultrastor.c
+++ b/drivers/scsi/ultrastor.c
@@ -700,7 +700,7 @@ static inline void build_sg_list(struct mscp *mscp, struct scsi_cmnd *SCpnt)
         mscp->transfer_data_length = transfer_length;
 }
 
-static int ultrastor_queuecommand(struct scsi_cmnd *SCpnt,
+static int ultrastor_queuecommand_lck(struct scsi_cmnd *SCpnt,
                                 void (*done) (struct scsi_cmnd *))
 {
     struct mscp *my_mscp;
@@ -825,6 +825,8 @@ retry:
     return 0;
 }
 
+static DEF_SCSI_QCMD(ultrastor_queuecommand)
+
 /* This code must deal with 2 cases:
 
    1. The command has not been written to the OGM.  In this case, set
diff --git a/drivers/scsi/ultrastor.h b/drivers/scsi/ultrastor.h
index a692905f95f..165c18b5cf5 100644
--- a/drivers/scsi/ultrastor.h
+++ b/drivers/scsi/ultrastor.h
@@ -15,8 +15,7 @@
 
 static int ultrastor_detect(struct scsi_host_template *);
 static const char *ultrastor_info(struct Scsi_Host *shpnt);
-static int ultrastor_queuecommand(struct scsi_cmnd *,
-                                void (*done)(struct scsi_cmnd *));
+static int ultrastor_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 static int ultrastor_abort(struct scsi_cmnd *);
 static int ultrastor_host_reset(struct scsi_cmnd *);
 static int ultrastor_biosparam(struct scsi_device *, struct block_device *,
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 26894459c37..a18996d2446 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -690,7 +690,7 @@ static int pvscsi_queue_ring(struct pvscsi_adapter *adapter,
         return 0;
 }
 
-static int pvscsi_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
+static int pvscsi_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
         struct Scsi_Host *host = cmd->device->host;
         struct pvscsi_adapter *adapter = shost_priv(host);
@@ -719,6 +719,8 @@ static int pvscsi_queue(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(pvscsi_queue)
+
 static int pvscsi_abort(struct scsi_cmnd *cmd)
 {
         struct pvscsi_adapter *adapter = shost_priv(cmd->device->host);
diff --git a/drivers/scsi/wd33c93.c b/drivers/scsi/wd33c93.c
index b701bf2cc18..5f697e0bd00 100644
--- a/drivers/scsi/wd33c93.c
+++ b/drivers/scsi/wd33c93.c
@@ -371,8 +371,8 @@ calc_sync_msg(unsigned int period, unsigned int offset, unsigned int fast,
         msg[1] = offset;
 }
 
-int
-wd33c93_queuecommand(struct scsi_cmnd *cmd,
+static int
+wd33c93_queuecommand_lck(struct scsi_cmnd *cmd,
                 void (*done)(struct scsi_cmnd *))
 {
         struct WD33C93_hostdata *hostdata;
@@ -468,6 +468,8 @@ wd33c93_queuecommand(struct scsi_cmnd *cmd,
         return 0;
 }
 
+DEF_SCSI_QCMD(wd33c93_queuecommand)
+
 /*
  * This routine attempts to start a scsi command. If the host_card is
  * already connected, we give up immediately. Otherwise, look through
diff --git a/drivers/scsi/wd33c93.h b/drivers/scsi/wd33c93.h
index 1ed5f3bf388..3b463d7304d 100644
--- a/drivers/scsi/wd33c93.h
+++ b/drivers/scsi/wd33c93.h
@@ -343,8 +343,7 @@ struct WD33C93_hostdata {
 void wd33c93_init (struct Scsi_Host *instance, const wd33c93_regs regs,
          dma_setup_t setup, dma_stop_t stop, int clock_freq);
 int wd33c93_abort (struct scsi_cmnd *cmd);
-int wd33c93_queuecommand (struct scsi_cmnd *cmd,
-                void (*done)(struct scsi_cmnd *));
+int wd33c93_queuecommand (struct Scsi_Host *h, struct scsi_cmnd *cmd);
 void wd33c93_intr (struct Scsi_Host *instance);
 int wd33c93_proc_info(struct Scsi_Host *, char *, char **, off_t, int, int);
 int wd33c93_host_reset (struct scsi_cmnd *);
diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c
index 333580bf37c..db451ae0a36 100644
--- a/drivers/scsi/wd7000.c
+++ b/drivers/scsi/wd7000.c
@@ -1082,7 +1082,7 @@ static irqreturn_t wd7000_intr(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-static int wd7000_queuecommand(struct scsi_cmnd *SCpnt,
+static int wd7000_queuecommand_lck(struct scsi_cmnd *SCpnt,
                 void (*done)(struct scsi_cmnd *))
 {
         Scb *scb;
@@ -1139,6 +1139,8 @@ static int wd7000_queuecommand(struct scsi_cmnd *SCpnt,
         return 0;
 }
 
+static DEF_SCSI_QCMD(wd7000_queuecommand)
+
 static int wd7000_diagnostics(Adapter * host, int code)
 {
         static IcbDiag icb = { ICB_OP_DIAGNOSTICS };
diff --git a/drivers/serial/crisv10.c b/drivers/serial/crisv10.c
index fa62578fcd2..bcc31f2140a 100644
--- a/drivers/serial/crisv10.c
+++ b/drivers/serial/crisv10.c
@@ -18,7 +18,6 @@ static char *serial_version = "$Revision: 1.25 $";
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/major.h>
-#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c
index c4ea14670d4..9ffa5bee44a 100644
--- a/drivers/serial/serial_core.c
+++ b/drivers/serial/serial_core.c
@@ -29,7 +29,6 @@
 #include <linux/console.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/serial.h> /* for serial_state and serial_icounter_struct */
 #include <linux/serial_core.h>
diff --git a/drivers/staging/easycap/easycap.h b/drivers/staging/easycap/easycap.h
index f3c827eb0ab..25961c23dc0 100644
--- a/drivers/staging/easycap/easycap.h
+++ b/drivers/staging/easycap/easycap.h
@@ -77,7 +77,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/kref.h>
-#include <linux/smp_lock.h>
 #include <linux/usb.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/staging/hv/storvsc_drv.c b/drivers/staging/hv/storvsc_drv.c
index 41d9acf4cd6..6f8d67d0d64 100644
--- a/drivers/staging/hv/storvsc_drv.c
+++ b/drivers/staging/hv/storvsc_drv.c
@@ -72,8 +72,7 @@ struct storvsc_driver_context {
 
 /* Static decl */
 static int storvsc_probe(struct device *dev);
-static int storvsc_queuecommand(struct scsi_cmnd *scmnd,
-                                void (*done)(struct scsi_cmnd *));
+static int storvsc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd);
 static int storvsc_device_alloc(struct scsi_device *);
 static int storvsc_device_configure(struct scsi_device *);
 static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd);
@@ -595,7 +594,7 @@ static unsigned int copy_from_bounce_buffer(struct scatterlist *orig_sgl,
 /*
  * storvsc_queuecommand - Initiate command processing
  */
-static int storvsc_queuecommand(struct scsi_cmnd *scmnd,
+static int storvsc_queuecommand_lck(struct scsi_cmnd *scmnd,
                                 void (*done)(struct scsi_cmnd *))
 {
         int ret;
@@ -783,6 +782,8 @@ retry_request:
         return ret;
 }
 
+static DEF_SCSI_QCMD(storvsc_queuecommand)
+
 static int storvsc_merge_bvec(struct request_queue *q,
                               struct bvec_merge_data *bmd, struct bio_vec *bvec)
 {
diff --git a/drivers/staging/intel_sst/intel_sst_app_interface.c b/drivers/staging/intel_sst/intel_sst_app_interface.c
index 9618c799746..991440015e9 100644
--- a/drivers/staging/intel_sst/intel_sst_app_interface.c
+++ b/drivers/staging/intel_sst/intel_sst_app_interface.c
@@ -34,7 +34,6 @@
 #include <linux/uaccess.h>
 #include <linux/firmware.h>
 #include <linux/ioctl.h>
-#include <linux/smp_lock.h>
 #ifdef CONFIG_MRST_RAR_HANDLER
 #include <linux/rar_register.h>
 #include "../../../drivers/staging/memrar/memrar.h"
diff --git a/drivers/staging/keucr/scsiglue.c b/drivers/staging/keucr/scsiglue.c
index a2671404f7a..da4f42af383 100644
--- a/drivers/staging/keucr/scsiglue.c
+++ b/drivers/staging/keucr/scsiglue.c
@@ -87,7 +87,7 @@ static int slave_configure(struct scsi_device *sdev)
 
 /* This is always called with scsi_lock(host) held */
 //----- queuecommand() ---------------------
-static int queuecommand(struct scsi_cmnd *srb, void (*done)(struct scsi_cmnd *))
+static int queuecommand_lck(struct scsi_cmnd *srb, void (*done)(struct scsi_cmnd *))
 {
         struct us_data *us = host_to_us(srb->device->host);
 
@@ -117,6 +117,8 @@ static int queuecommand(struct scsi_cmnd *srb, void (*done)(struct scsi_cmnd *))
         return 0;
 }
 
+static DEF_SCSI_QCMD(queuecommand)
+
 /***********************************************************************
  * Error handling functions
  ***********************************************************************/
diff --git a/drivers/staging/rtl8712/osdep_service.h b/drivers/staging/rtl8712/osdep_service.h
index d1674cd282d..831d81e0e42 100644
--- a/drivers/staging/rtl8712/osdep_service.h
+++ b/drivers/staging/rtl8712/osdep_service.h
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kref.h>
-#include <linux/smp_lock.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/usb.h>
diff --git a/drivers/staging/speakup/buffers.c b/drivers/staging/speakup/buffers.c
index b7b60d5e866..a2db956edd5 100644
--- a/drivers/staging/speakup/buffers.c
+++ b/drivers/staging/speakup/buffers.c
@@ -1,5 +1,4 @@
 #include <linux/console.h>
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
diff --git a/drivers/staging/stradis/Kconfig b/drivers/staging/stradis/Kconfig
index 92e89114189..02f0fc504cf 100644
--- a/drivers/staging/stradis/Kconfig
+++ b/drivers/staging/stradis/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_STRADIS
         tristate "Stradis 4:2:2 MPEG-2 video driver (DEPRECATED)"
-        depends on EXPERIMENTAL && PCI && VIDEO_V4L1 && VIRT_TO_BUS
+        depends on EXPERIMENTAL && PCI && VIDEO_V4L1 && VIRT_TO_BUS && BKL
         help
           Say Y here to enable support for the Stradis 4:2:2 MPEG-2 video
           driver for PCI.  There is a product page at
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index eaa5d3efa79..c556ed9db13 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -554,7 +554,7 @@ EXPORT_SYMBOL(handle_sysrq);
 #ifdef CONFIG_INPUT
 
 /* Simple translation table for the SysRq keys */
-static const unsigned char sysrq_xlate[KEY_MAX + 1] =
+static const unsigned char sysrq_xlate[KEY_CNT] =
         "\000\0331234567890-=\177\t"                    /* 0x00 - 0x0f */
         "qwertyuiop[]\r\000as"                          /* 0x10 - 0x1f */
         "dfghjkl;'`\000\\zxcv"                          /* 0x20 - 0x2f */
@@ -563,53 +563,129 @@ static const unsigned char sysrq_xlate[KEY_MAX + 1] =
         "230\177\000\000\213\214\000\000\000\000\000\000\000\000\000\000" /* 0x50 - 0x5f */
         "\r\000/";                                      /* 0x60 - 0x6f */
 
-static bool sysrq_down;
-static int sysrq_alt_use;
-static int sysrq_alt;
-static DEFINE_SPINLOCK(sysrq_event_lock);
+struct sysrq_state {
+        struct input_handle handle;
+        struct work_struct reinject_work;
+        unsigned long key_down[BITS_TO_LONGS(KEY_CNT)];
+        unsigned int alt;
+        unsigned int alt_use;
+        bool active;
+        bool need_reinject;
+};
+
+static void sysrq_reinject_alt_sysrq(struct work_struct *work)
+{
+        struct sysrq_state *sysrq =
+                        container_of(work, struct sysrq_state, reinject_work);
+        struct input_handle *handle = &sysrq->handle;
+        unsigned int alt_code = sysrq->alt_use;
+
+        if (sysrq->need_reinject) {
+                /* Simulate press and release of Alt + SysRq */
+                input_inject_event(handle, EV_KEY, alt_code, 1);
+                input_inject_event(handle, EV_KEY, KEY_SYSRQ, 1);
+                input_inject_event(handle, EV_SYN, SYN_REPORT, 1);
+
+                input_inject_event(handle, EV_KEY, KEY_SYSRQ, 0);
+                input_inject_event(handle, EV_KEY, alt_code, 0);
+                input_inject_event(handle, EV_SYN, SYN_REPORT, 1);
+        }
+}
 
-static bool sysrq_filter(struct input_handle *handle, unsigned int type,
-                         unsigned int code, int value)
+static bool sysrq_filter(struct input_handle *handle,
+                         unsigned int type, unsigned int code, int value)
 {
+        struct sysrq_state *sysrq = handle->private;
+        bool was_active = sysrq->active;
         bool suppress;
 
-        /* We are called with interrupts disabled, just take the lock */
-        spin_lock(&sysrq_event_lock);
+        switch (type) {
 
-        if (type != EV_KEY)
-                goto out;
+        case EV_SYN:
+                suppress = false;
+                break;
 
-        switch (code) {
+        case EV_KEY:
+                switch (code) {
 
-        case KEY_LEFTALT:
-        case KEY_RIGHTALT:
-                if (value)
-                        sysrq_alt = code;
-                else {
-                        if (sysrq_down && code == sysrq_alt_use)
-                                sysrq_down = false;
+                case KEY_LEFTALT:
+                case KEY_RIGHTALT:
+                        if (!value) {
+                                /* One of ALTs is being released */
+                                if (sysrq->active && code == sysrq->alt_use)
+                                        sysrq->active = false;
 
-                        sysrq_alt = 0;
+                                sysrq->alt = KEY_RESERVED;
+
+                        } else if (value != 2) {
+                                sysrq->alt = code;
+                                sysrq->need_reinject = false;
+                        }
+                        break;
+
+                case KEY_SYSRQ:
+                        if (value == 1 && sysrq->alt != KEY_RESERVED) {
+                                sysrq->active = true;
+                                sysrq->alt_use = sysrq->alt;
+                                /*
+                                 * If nothing else will be pressed we'll need
+                                 * to * re-inject Alt-SysRq keysroke.
+                                 */
+                                sysrq->need_reinject = true;
+                        }
+
+                        /*
+                         * Pretend that sysrq was never pressed at all. This
+                         * is needed to properly handle KGDB which will try
+                         * to release all keys after exiting debugger. If we
+                         * do not clear key bit it KGDB will end up sending
+                         * release events for Alt and SysRq, potentially
+                         * triggering print screen function.
+                         */
+                        if (sysrq->active)
+                                clear_bit(KEY_SYSRQ, handle->dev->key);
+
+                        break;
+
+                default:
+                        if (sysrq->active && value && value != 2) {
+                                sysrq->need_reinject = false;
+                                __handle_sysrq(sysrq_xlate[code], true);
+                        }
+                        break;
                 }
-                break;
 
-        case KEY_SYSRQ:
-                if (value == 1 && sysrq_alt) {
-                        sysrq_down = true;
-                        sysrq_alt_use = sysrq_alt;
+                suppress = sysrq->active;
+
+                if (!sysrq->active) {
+                        /*
+                         * If we are not suppressing key presses keep track of
+                         * keyboard state so we can release keys that have been
+                         * pressed before entering SysRq mode.
+                         */
+                        if (value)
+                                set_bit(code, sysrq->key_down);
+                        else
+                                clear_bit(code, sysrq->key_down);
+
+                        if (was_active)
+                                schedule_work(&sysrq->reinject_work);
+
+                } else if (value == 0 &&
+                           test_and_clear_bit(code, sysrq->key_down)) {
+                        /*
+                         * Pass on release events for keys that was pressed before
+                         * entering SysRq mode.
+                         */
+                        suppress = false;
                 }
                 break;
 
         default:
-                if (sysrq_down && value && value != 2)
-                        __handle_sysrq(sysrq_xlate[code], true);
+                suppress = sysrq->active;
                 break;
         }
 
-out:
-        suppress = sysrq_down;
-        spin_unlock(&sysrq_event_lock);
-
         return suppress;
 }
 
@@ -617,28 +693,28 @@ static int sysrq_connect(struct input_handler *handler,
                          struct input_dev *dev,
                          const struct input_device_id *id)
 {
-        struct input_handle *handle;
+        struct sysrq_state *sysrq;
         int error;
 
-        sysrq_down = false;
-        sysrq_alt = 0;
-
-        handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL);
-        if (!handle)
+        sysrq = kzalloc(sizeof(struct sysrq_state), GFP_KERNEL);
+        if (!sysrq)
                 return -ENOMEM;
 
-        handle->dev = dev;
-        handle->handler = handler;
-        handle->name = "sysrq";
+        INIT_WORK(&sysrq->reinject_work, sysrq_reinject_alt_sysrq);
+
+        sysrq->handle.dev = dev;
+        sysrq->handle.handler = handler;
+        sysrq->handle.name = "sysrq";
+        sysrq->handle.private = sysrq;
 
-        error = input_register_handle(handle);
+        error = input_register_handle(&sysrq->handle);
         if (error) {
                 pr_err("Failed to register input sysrq handler, error %d\n",
                         error);
                 goto err_free;
         }
 
-        error = input_open_device(handle);
+        error = input_open_device(&sysrq->handle);
         if (error) {
                 pr_err("Failed to open input device, error %d\n", error);
                 goto err_unregister;
@@ -647,17 +723,20 @@ static int sysrq_connect(struct input_handler *handler,
         return 0;
 
  err_unregister:
-        input_unregister_handle(handle);
+        input_unregister_handle(&sysrq->handle);
  err_free:
-        kfree(handle);
+        kfree(sysrq);
         return error;
 }
 
 static void sysrq_disconnect(struct input_handle *handle)
 {
+        struct sysrq_state *sysrq = handle->private;
+
         input_close_device(handle);
+        cancel_work_sync(&sysrq->reinject_work);
         input_unregister_handle(handle);
-        kfree(handle);
+        kfree(sysrq);
 }
 
 /*
diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c
index ddb4dc98092..a3d2e239965 100644
--- a/drivers/usb/core/devices.c
+++ b/drivers/usb/core/devices.c
@@ -54,7 +54,6 @@
 #include <linux/gfp.h>
 #include <linux/poll.h>
 #include <linux/usb.h>
-#include <linux/smp_lock.h>
 #include <linux/usbdevice_fs.h>
 #include <linux/usb/hcd.h>
 #include <linux/mutex.h>
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 045bb4b823e..a7131ad630f 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -37,7 +37,6 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/signal.h>
 #include <linux/poll.h>
 #include <linux/module.h>
diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c
index 9fe34fb78ef..cf6a5423de0 100644
--- a/drivers/usb/core/file.c
+++ b/drivers/usb/core/file.c
@@ -19,7 +19,6 @@
 #include <linux/errno.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/usb.h>
 
 #include "usb.h"
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index 9819a4cc3b2..b690aa35df9 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -39,7 +39,6 @@
 #include <linux/parser.h>
 #include <linux/notifier.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/usb/hcd.h>
 #include <asm/byteorder.h>
 #include "usb.h"
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 4a830df4fc3..484c5ba5450 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -30,7 +30,6 @@
 #include <linux/blkdev.h>
 #include <linux/pagemap.h>
 #include <asm/unaligned.h>
-#include <linux/smp_lock.h>
 
 #include <linux/usb/composite.h>
 #include <linux/usb/functionfs.h>
diff --git a/drivers/usb/gadget/f_hid.c b/drivers/usb/gadget/f_hid.c
index 4f891eddd06..598e7e2ab80 100644
--- a/drivers/usb/gadget/f_hid.c
+++ b/drivers/usb/gadget/f_hid.c
@@ -25,7 +25,6 @@
 #include <linux/cdev.h>
 #include <linux/mutex.h>
 #include <linux/poll.h>
-#include <linux/smp_lock.h>
 #include <linux/uaccess.h>
 #include <linux/wait.h>
 #include <linux/usb/g_hid.h>
diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c
index 8196fa11fec..6c4fb4efb4b 100644
--- a/drivers/usb/host/isp1362-hcd.c
+++ b/drivers/usb/host/isp1362-hcd.c
@@ -70,7 +70,6 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/list.h>
diff --git a/drivers/usb/host/uhci-debug.c b/drivers/usb/host/uhci-debug.c
index 6e7fb5f38db..ee60cd3ea64 100644
--- a/drivers/usb/host/uhci-debug.c
+++ b/drivers/usb/host/uhci-debug.c
@@ -12,7 +12,6 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
-#include <linux/smp_lock.h>
 #include <asm/io.h>
 
 #include "uhci-hcd.h"
diff --git a/drivers/usb/image/microtek.c b/drivers/usb/image/microtek.c
index 5a47805d958..c90c89dc000 100644
--- a/drivers/usb/image/microtek.c
+++ b/drivers/usb/image/microtek.c
@@ -364,7 +364,7 @@ static int mts_scsi_host_reset(struct scsi_cmnd *srb)
 }
 
 static int
-mts_scsi_queuecommand(struct scsi_cmnd *srb, mts_scsi_cmnd_callback callback);
+mts_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *srb);
 
 static void mts_transfer_cleanup( struct urb *transfer );
 static void mts_do_sg(struct urb * transfer);
@@ -573,7 +573,7 @@ mts_build_transfer_context(struct scsi_cmnd *srb, struct mts_desc* desc)
 
 
 static int
-mts_scsi_queuecommand(struct scsi_cmnd *srb, mts_scsi_cmnd_callback callback)
+mts_scsi_queuecommand_lck(struct scsi_cmnd *srb, mts_scsi_cmnd_callback callback)
 {
         struct mts_desc* desc = (struct mts_desc*)(srb->device->host->hostdata[0]);
         int err = 0;
@@ -626,6 +626,8 @@ out:
         return err;
 }
 
+static DEF_SCSI_QCMD(mts_scsi_queuecommand)
+
 static struct scsi_host_template mts_scsi_host_template = {
         .module                 = THIS_MODULE,
         .name                   = "microtekX6",
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 44cb37b5a4d..c436e1e2c3b 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -15,7 +15,6 @@
 #include <linux/poll.h>
 #include <linux/compat.h>
 #include <linux/mm.h>
-#include <linux/smp_lock.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 
diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c
index 8ec94f15a73..e5ce42bd316 100644
--- a/drivers/usb/mon/mon_stat.c
+++ b/drivers/usb/mon/mon_stat.c
@@ -11,7 +11,6 @@
 #include <linux/slab.h>
 #include <linux/usb.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 
 #include "usb_mon.h"
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index e64da74bdcc..861223f2af6 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -21,7 +21,6 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index a688b1e686e..689ee1fb702 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -285,7 +285,7 @@ static int slave_configure(struct scsi_device *sdev)
 
 /* queue a command */
 /* This is always called with scsi_lock(host) held */
-static int queuecommand(struct scsi_cmnd *srb,
+static int queuecommand_lck(struct scsi_cmnd *srb,
                         void (*done)(struct scsi_cmnd *))
 {
         struct us_data *us = host_to_us(srb->device->host);
@@ -315,6 +315,8 @@ static int queuecommand(struct scsi_cmnd *srb,
         return 0;
 }
 
+static DEF_SCSI_QCMD(queuecommand)
+
 /***********************************************************************
  * Error handling functions
  ***********************************************************************/
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index d1268191acb..339fac3949d 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -430,7 +430,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
         return 0;
 }
 
-static int uas_queuecommand(struct scsi_cmnd *cmnd,
+static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
                                         void (*done)(struct scsi_cmnd *))
 {
         struct scsi_device *sdev = cmnd->device;
@@ -488,6 +488,8 @@ static int uas_queuecommand(struct scsi_cmnd *cmnd,
         return 0;
 }
 
+static DEF_SCSI_QCMD(uas_queuecommand)
+
 static int uas_eh_abort_handler(struct scsi_cmnd *cmnd)
 {
         struct scsi_device *sdev = cmnd->device;
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 54e32c51361..915448ec75b 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -47,7 +47,6 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/screen_info.h>
-#include <linux/smp_lock.h>
 #include <video/vga.h>
 #include <asm/io.h>
 
diff --git a/drivers/xen/xenfs/privcmd.c b/drivers/xen/xenfs/privcmd.c
index f80be7f6eb9..0f5d4162b22 100644
--- a/drivers/xen/xenfs/privcmd.c
+++ b/drivers/xen/xenfs/privcmd.c
@@ -15,7 +15,6 @@
 #include <linux/mman.h>
 #include <linux/uaccess.h>
 #include <linux/swap.h>
-#include <linux/smp_lock.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index cafc5045429..e0c84725d3e 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -13,7 +13,6 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/setup.h>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 06e8ff12b97..4230252fd68 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -11,7 +11,6 @@
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/major.h>
-#include <linux/smp_lock.h>
 #include <linux/device_cgroup.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e9c874abc9e..561438b6a50 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -204,7 +204,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
         err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
                                   page->index << PAGE_CACHE_SHIFT, &len,
                                   ci->i_truncate_seq, ci->i_truncate_size,
-                                  &page, 1);
+                                  &page, 1, 0);
         if (err == -ENOENT)
                 err = 0;
         if (err < 0) {
@@ -287,7 +287,7 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
         rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
                                  offset, &len,
                                  ci->i_truncate_seq, ci->i_truncate_size,
-                                 pages, nr_pages);
+                                 pages, nr_pages, 0);
         if (rc == -ENOENT)
                 rc = 0;
         if (rc < 0)
@@ -774,7 +774,7 @@ get_more_pages:
                                             snapc, do_sync,
                                             ci->i_truncate_seq,
                                             ci->i_truncate_size,
-                                            &inode->i_mtime, true, 1);
+                                            &inode->i_mtime, true, 1, 0);
                                 max_pages = req->r_num_pages;
 
                                 alloc_page_vec(fsc, req);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 98ab13e2b71..60d27bc9eb8 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1430,8 +1430,8 @@ static int try_nonblocking_invalidate(struct inode *inode)
             invalidating_gen == ci->i_rdcache_gen) {
                 /* success. */
                 dout("try_nonblocking_invalidate %p success\n", inode);
-                ci->i_rdcache_gen = 0;
-                ci->i_rdcache_revoking = 0;
+                /* save any racing async invalidate some trouble */
+                ci->i_rdcache_revoking = ci->i_rdcache_gen - 1;
                 return 0;
         }
         dout("try_nonblocking_invalidate %p failed\n", inode);
@@ -2273,8 +2273,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
         int mds = session->s_mds;
-        unsigned seq = le32_to_cpu(grant->seq);
-        unsigned issue_seq = le32_to_cpu(grant->issue_seq);
+        int seq = le32_to_cpu(grant->seq);
         int newcaps = le32_to_cpu(grant->caps);
         int issued, implemented, used, wanted, dirty;
         u64 size = le64_to_cpu(grant->size);
@@ -2286,8 +2285,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
         int revoked_rdcache = 0;
         int queue_invalidate = 0;
 
-        dout("handle_cap_grant inode %p cap %p mds%d seq %u/%u %s\n",
-             inode, cap, mds, seq, issue_seq, ceph_cap_string(newcaps));
+        dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
+             inode, cap, mds, seq, ceph_cap_string(newcaps));
         dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
                 inode->i_size);
 
@@ -2383,7 +2382,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
         }
 
         cap->seq = seq;
-        cap->issue_seq = issue_seq;
 
         /* file layout may have changed */
         ci->i_layout = grant->layout;
@@ -2691,6 +2689,11 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
                      NULL /* no caps context */);
         try_flush_caps(inode, session, NULL);
         up_read(&mdsc->snap_rwsem);
+
+        /* make sure we re-request max_size, if necessary */
+        spin_lock(&inode->i_lock);
+        ci->i_requested_max_size = 0;
+        spin_unlock(&inode->i_lock);
 }
 
 /*
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e0a2dc6fcaf..7d447af84ec 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -336,7 +336,10 @@ more:
                 if (req->r_reply_info.dir_end) {
                         kfree(fi->last_name);
                         fi->last_name = NULL;
-                        fi->next_offset = 2;
+                        if (ceph_frag_is_rightmost(frag))
+                                fi->next_offset = 2;
+                        else
+                                fi->next_offset = 0;
                 } else {
                         rinfo = &req->r_reply_info;
                         err = note_last_dentry(fi,
@@ -355,18 +358,22 @@ more:
                 u64 pos = ceph_make_fpos(frag, off);
                 struct ceph_mds_reply_inode *in =
                         rinfo->dir_in[off - fi->offset].in;
+                struct ceph_vino vino;
+                ino_t ino;
+
                 dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n",
                      off, off - fi->offset, rinfo->dir_nr, pos,
                      rinfo->dir_dname_len[off - fi->offset],
                      rinfo->dir_dname[off - fi->offset], in);
                 BUG_ON(!in);
                 ftype = le32_to_cpu(in->mode) >> 12;
+                vino.ino = le64_to_cpu(in->ino);
+                vino.snap = le64_to_cpu(in->snapid);
+                ino = ceph_vino_to_ino(vino);
                 if (filldir(dirent,
                             rinfo->dir_dname[off - fi->offset],
                             rinfo->dir_dname_len[off - fi->offset],
-                            pos,
-                            le64_to_cpu(in->ino),
-                            ftype) < 0) {
+                            pos, ino, ftype) < 0) {
                         dout("filldir stopping us...\n");
                         return 0;
                 }
@@ -414,6 +421,7 @@ static void reset_readdir(struct ceph_file_info *fi)
                 fi->last_readdir = NULL;
         }
         kfree(fi->last_name);
+        fi->last_name = NULL;
         fi->next_offset = 2;  /* compensate for . and .. */
         if (fi->dentry) {
                 dput(fi->dentry);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e77c28cf369..8d79b8912e3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -154,11 +154,13 @@ int ceph_open(struct inode *inode, struct file *file)
         }
 
         /*
-         * No need to block if we have any caps.  Update wanted set
+         * No need to block if we have caps on the auth MDS (for
+         * write) or any MDS (for read).  Update wanted set
          * asynchronously.
          */
         spin_lock(&inode->i_lock);
-        if (__ceph_is_any_real_caps(ci)) {
+        if (__ceph_is_any_real_caps(ci) &&
+            (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
                 int mds_wanted = __ceph_caps_mds_wanted(ci);
                 int issued = __ceph_caps_issued(ci, NULL);
 
@@ -280,11 +282,12 @@ int ceph_release(struct inode *inode, struct file *file)
 static int striped_read(struct inode *inode,
                         u64 off, u64 len,
                         struct page **pages, int num_pages,
-                        int *checkeof)
+                        int *checkeof, bool align_to_pages)
 {
         struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
         struct ceph_inode_info *ci = ceph_inode(inode);
         u64 pos, this_len;
+        int io_align, page_align;
         int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
         int left, pages_left;
         int read;
@@ -300,14 +303,19 @@ static int striped_read(struct inode *inode,
         page_pos = pages;
         pages_left = num_pages;
         read = 0;
+        io_align = off & ~PAGE_MASK;
 
 more:
+        if (align_to_pages)
+                page_align = (pos - io_align) & ~PAGE_MASK;
+        else
+                page_align = pos & ~PAGE_MASK;
         this_len = left;
         ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
                                   &ci->i_layout, pos, &this_len,
                                   ci->i_truncate_seq,
                                   ci->i_truncate_size,
-                                  page_pos, pages_left);
+                                  page_pos, pages_left, page_align);
         hit_stripe = this_len < left;
         was_short = ret >= 0 && ret < this_len;
         if (ret == -ENOENT)
@@ -374,26 +382,25 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
         dout("sync_read on file %p %llu~%u %s\n", file, off, len,
              (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
-        if (file->f_flags & O_DIRECT) {
-                pages = ceph_get_direct_page_vector(data, num_pages, off, len);
-
-                /*
-                 * flush any page cache pages in this range.  this
-                 * will make concurrent normal and O_DIRECT io slow,
-                 * but it will at least behave sensibly when they are
-                 * in sequence.
-                 */
-        } else {
+        if (file->f_flags & O_DIRECT)
+                pages = ceph_get_direct_page_vector(data, num_pages);
+        else
                 pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
-        }
         if (IS_ERR(pages))
                 return PTR_ERR(pages);
 
+        /*
+         * flush any page cache pages in this range.  this
+         * will make concurrent normal and sync io slow,
+         * but it will at least behave sensibly when they are
+         * in sequence.
+         */
         ret = filemap_write_and_wait(inode->i_mapping);
         if (ret < 0)
                 goto done;
 
-        ret = striped_read(inode, off, len, pages, num_pages, checkeof);
+        ret = striped_read(inode, off, len, pages, num_pages, checkeof,
+                           file->f_flags & O_DIRECT);
 
         if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
                 ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
@@ -448,6 +455,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
         int flags;
         int do_sync = 0;
         int check_caps = 0;
+        int page_align, io_align;
         int ret;
         struct timespec mtime = CURRENT_TIME;
 
@@ -462,6 +470,8 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
         else
                 pos = *offset;
 
+        io_align = pos & ~PAGE_MASK;
+
         ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
         if (ret < 0)
                 return ret;
@@ -486,20 +496,26 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
          */
 more:
         len = left;
+        if (file->f_flags & O_DIRECT)
+                /* write from beginning of first page, regardless of
+                   io alignment */
+                page_align = (pos - io_align) & ~PAGE_MASK;
+        else
+                page_align = pos & ~PAGE_MASK;
         req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
                                     ceph_vino(inode), pos, &len,
                                     CEPH_OSD_OP_WRITE, flags,
                                     ci->i_snap_realm->cached_context,
                                     do_sync,
                                     ci->i_truncate_seq, ci->i_truncate_size,
-                                    &mtime, false, 2);
+                                    &mtime, false, 2, page_align);
         if (!req)
                 return -ENOMEM;
 
         num_pages = calc_pages_for(pos, len);
 
         if (file->f_flags & O_DIRECT) {
-                pages = ceph_get_direct_page_vector(data, num_pages, pos, len);
+                pages = ceph_get_direct_page_vector(data, num_pages);
                 if (IS_ERR(pages)) {
                         ret = PTR_ERR(pages);
                         goto out;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1d6a45b5a04..bf1286588f2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2,7 +2,6 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
@@ -471,7 +470,9 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 
         if (issued & (CEPH_CAP_FILE_EXCL|
                       CEPH_CAP_FILE_WR|
-                      CEPH_CAP_FILE_BUFFER)) {
+                      CEPH_CAP_FILE_BUFFER|
+                      CEPH_CAP_AUTH_EXCL|
+                      CEPH_CAP_XATTR_EXCL)) {
                 if (timespec_compare(ctime, &inode->i_ctime) > 0) {
                         dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
                              inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
@@ -511,7 +512,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
                         warn = 1;
                 }
         } else {
-                /* we have no write caps; whatever the MDS says is true */
+                /* we have no write|excl caps; whatever the MDS says is true */
                 if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) {
                         inode->i_ctime = *ctime;
                         inode->i_mtime = *mtime;
@@ -567,12 +568,17 @@ static int fill_inode(struct inode *inode,
 
         /*
          * provided version will be odd if inode value is projected,
-         * even if stable.  skip the update if we have a newer info
-         * (e.g., due to inode info racing form multiple MDSs), or if
-         * we are getting projected (unstable) inode info.
+         * even if stable.  skip the update if we have newer stable
+         * info (ours>=theirs, e.g. due to racing mds replies), unless
+         * we are getting projected (unstable) info (in which case the
+         * version is odd, and we want ours>theirs).
+         *   us   them
+         *   2    2     skip
+         *   3    2     skip
+         *   3    3     update
          */
         if (le64_to_cpu(info->version) > 0 &&
-            (ci->i_version & ~1) > le64_to_cpu(info->version))
+            (ci->i_version & ~1) >= le64_to_cpu(info->version))
                 goto no_change;
 
         issued = __ceph_caps_issued(ci, &implemented);
@@ -606,7 +612,14 @@ static int fill_inode(struct inode *inode,
                             le32_to_cpu(info->time_warp_seq),
                             &ctime, &mtime, &atime);
 
-        ci->i_max_size = le64_to_cpu(info->max_size);
+        /* only update max_size on auth cap */
+        if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+            ci->i_max_size != le64_to_cpu(info->max_size)) {
+                dout("max_size %lld -> %llu\n", ci->i_max_size,
+                     le64_to_cpu(info->max_size));
+                ci->i_max_size = le64_to_cpu(info->max_size);
+        }
+
         ci->i_layout = info->layout;
         inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
@@ -1055,7 +1068,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                 ininfo = rinfo->targeti.in;
                 vino.ino = le64_to_cpu(ininfo->ino);
                 vino.snap = le64_to_cpu(ininfo->snapid);
-                if (!dn->d_inode) {
+                in = dn->d_inode;
+                if (!in) {
                         in = ceph_get_inode(sb, vino);
                         if (IS_ERR(in)) {
                                 pr_err("fill_trace bad get_inode "
@@ -1386,11 +1400,8 @@ static void ceph_invalidate_work(struct work_struct *work)
         spin_lock(&inode->i_lock);
         dout("invalidate_pages %p gen %d revoking %d\n", inode,
              ci->i_rdcache_gen, ci->i_rdcache_revoking);
-        if (ci->i_rdcache_gen == 0 ||
-            ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-                BUG_ON(ci->i_rdcache_revoking > ci->i_rdcache_gen);
+        if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
                 /* nevermind! */
-                ci->i_rdcache_revoking = 0;
                 spin_unlock(&inode->i_lock);
                 goto out;
         }
@@ -1400,15 +1411,16 @@ static void ceph_invalidate_work(struct work_struct *work)
         ceph_invalidate_nondirty_pages(inode->i_mapping);
 
         spin_lock(&inode->i_lock);
-        if (orig_gen == ci->i_rdcache_gen) {
+        if (orig_gen == ci->i_rdcache_gen &&
+            orig_gen == ci->i_rdcache_revoking) {
                 dout("invalidate_pages %p gen %d successful\n", inode,
                      ci->i_rdcache_gen);
-                ci->i_rdcache_gen = 0;
-                ci->i_rdcache_revoking = 0;
+                ci->i_rdcache_revoking--;
                 check = 1;
         } else {
-                dout("invalidate_pages %p gen %d raced, gen now %d\n",
-                     inode, orig_gen, ci->i_rdcache_gen);
+                dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
+                     inode, orig_gen, ci->i_rdcache_gen,
+                     ci->i_rdcache_revoking);
         }
         spin_unlock(&inode->i_lock);
 
@@ -1739,7 +1751,7 @@ int ceph_do_getattr(struct inode *inode, int mask)
                 return 0;
         }
 
-        dout("do_getattr inode %p mask %s\n", inode, ceph_cap_string(mask));
+        dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
         if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
                 return 0;
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3142b15940c..098b1850847 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -6,7 +6,6 @@
 #include <linux/sched.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -529,6 +528,9 @@ static void __register_request(struct ceph_mds_client *mdsc,
         ceph_mdsc_get_request(req);
         __insert_request(mdsc, req);
 
+        req->r_uid = current_fsuid();
+        req->r_gid = current_fsgid();
+
         if (dir) {
                 struct ceph_inode_info *ci = ceph_inode(dir);
 
@@ -1588,8 +1590,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
         head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
         head->op = cpu_to_le32(req->r_op);
-        head->caller_uid = cpu_to_le32(current_fsuid());
-        head->caller_gid = cpu_to_le32(current_fsgid());
+        head->caller_uid = cpu_to_le32(req->r_uid);
+        head->caller_gid = cpu_to_le32(req->r_gid);
         head->args = req->r_args;
 
         ceph_encode_filepath(&p, end, ino1, path1);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index d66d63c7235..9341fd4f143 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -170,6 +170,8 @@ struct ceph_mds_request {
 
         union ceph_mds_request_args r_args;
         int r_fmode;        /* file mode, if expecting cap */
+        uid_t r_uid;
+        gid_t r_gid;
 
         /* for choosing which mds to send this request to */
         int r_direct_mode;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1886294e12f..7f01728a465 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -293,9 +293,7 @@ struct ceph_inode_info {
         int i_rd_ref, i_rdcache_ref, i_wr_ref;
         int i_wrbuffer_ref, i_wrbuffer_ref_head;
         u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
-        u32 i_rdcache_gen;      /* we increment this each time we get
-                                   FILE_CACHE.  If it's non-zero, we
-                                   _may_ have cached pages. */
+        u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
         u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
 
         struct list_head i_unsafe_writes; /* uncommitted sync writes */
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 410ed188faa..a60579b007b 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -19,7 +19,6 @@
 #include <linux/compiler.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/ioctl.h>
 #include <linux/if.h>
 #include <linux/if_bridge.h>
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 253732382d3..2720178b771 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -28,7 +28,6 @@
 #include <linux/key.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/file.h>
 #include <linux/crypto.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 2fedaf8b501..acf8695fa8f 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -27,7 +27,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/vfs.h>
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bf5ae883b1b..eb3bc2fe647 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -331,6 +331,30 @@ mext_out:
                 return err;
         }
 
+        case FITRIM:
+        {
+                struct super_block *sb = inode->i_sb;
+                struct fstrim_range range;
+                int ret = 0;
+
+                if (!capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+
+                if (copy_from_user(&range, (struct fstrim_range *)arg,
+                    sizeof(range)))
+                        return -EFAULT;
+
+                ret = ext4_trim_fs(sb, &range);
+                if (ret < 0)
+                        return ret;
+
+                if (copy_to_user((struct fstrim_range *)arg, &range,
+                    sizeof(range)))
+                        return -EFAULT;
+
+                return 0;
+        }
+
         default:
                 return -ENOTTY;
         }
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7f5451cd1d3..beacce11ac5 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -237,8 +237,6 @@ static void ext4_end_bio(struct bio *bio, int error)
                         } while (bh != head);
                 }
 
-                put_io_page(io_end->pages[i]);
-
                 /*
                  * If this is a partial write which happened to make
                  * all buffers uptodate then we can optimize away a
@@ -248,6 +246,8 @@ static void ext4_end_bio(struct bio *bio, int error)
                  */
                 if (!partial_write)
                         SetPageUptodate(page);
+
+                put_io_page(io_end->pages[i]);
         }
         io_end->num_io_pages = 0;
         inode = io_end->inode;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 61182fe6254..e32195d6aac 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1197,7 +1197,6 @@ static const struct super_operations ext4_sops = {
         .quota_write    = ext4_quota_write,
 #endif
         .bdev_try_to_free_page = bdev_try_to_free_page,
-        .trim_fs        = ext4_trim_fs
 };
 
 static const struct super_operations ext4_nojournal_sops = {
@@ -2799,9 +2798,6 @@ static void ext4_clear_request_list(void)
         struct ext4_li_request *elr;
 
         mutex_lock(&ext4_li_info->li_list_mtx);
-        if (list_empty(&ext4_li_info->li_request_list))
-                return;
-
         list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
                 elr = list_entry(pos, struct ext4_li_request,
                                  lr_request);
@@ -3268,13 +3264,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
          * Test whether we have more sectors than will fit in sector_t,
          * and whether the max offset is addressable by the page cache.
          */
-        ret = generic_check_addressable(sb->s_blocksize_bits,
+        err = generic_check_addressable(sb->s_blocksize_bits,
                                         ext4_blocks_count(es));
-        if (ret) {
+        if (err) {
                 ext4_msg(sb, KERN_ERR, "filesystem"
                          " too large to mount safely on this system");
                 if (sizeof(sector_t) < 8)
                         ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
+                ret = err;
                 goto failed_mount;
         }
 
diff --git a/fs/ioctl.c b/fs/ioctl.c
index e92fdbb3bc3..d6cc1647662 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -6,7 +6,6 @@
 
 #include <linux/syscalls.h>
 #include <linux/mm.h>
-#include <linux/smp_lock.h>
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -530,41 +529,6 @@ static int ioctl_fsthaw(struct file *filp)
         return thaw_super(sb);
 }
 
-static int ioctl_fstrim(struct file *filp, void __user *argp)
-{
-        struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
-        struct fstrim_range range;
-        int ret = 0;
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-
-        /* If filesystem doesn't support trim feature, return. */
-        if (sb->s_op->trim_fs == NULL)
-                return -EOPNOTSUPP;
-
-        /* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
-        if (sb->s_bdev == NULL)
-                return -EINVAL;
-
-        if (argp == NULL) {
-                range.start = 0;
-                range.len = ULLONG_MAX;
-                range.minlen = 0;
-        } else if (copy_from_user(&range, argp, sizeof(range)))
-                return -EFAULT;
-
-        ret = sb->s_op->trim_fs(sb, &range);
-        if (ret < 0)
-                return ret;
-
-        if ((argp != NULL) &&
-            (copy_to_user(argp, &range, sizeof(range))))
-                return -EFAULT;
-
-        return 0;
-}
-
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -615,10 +579,6 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                 error = ioctl_fsthaw(filp);
                 break;
 
-        case FITRIM:
-                error = ioctl_fstrim(filp, argp);
-                break;
-
         case FS_IOC_FIEMAP:
                 return ioctl_fiemap(filp, arg);
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c590d155c09..f837ba95352 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -899,6 +899,14 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 
         /* journal descriptor can store up to n blocks -bzzz */
         journal->j_blocksize = blocksize;
+        journal->j_dev = bdev;
+        journal->j_fs_dev = fs_dev;
+        journal->j_blk_offset = start;
+        journal->j_maxlen = len;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
         jbd2_stats_proc_init(journal);
         n = journal->j_blocksize / sizeof(journal_block_tag_t);
         journal->j_wbufsize = n;
@@ -908,14 +916,6 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
                         __func__);
                 goto out_err;
         }
-        journal->j_dev = bdev;
-        journal->j_fs_dev = fs_dev;
-        journal->j_blk_offset = start;
-        journal->j_maxlen = len;
-        bdevname(journal->j_dev, journal->j_devname);
-        p = journal->j_devname;
-        while ((p = strchr(p, '/')))
-                *p = '!';
 
         bh = __getblk(journal->j_dev, start, journal->j_blocksize);
         if (!bh) {
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index d5bb86866e6..25509eb28fd 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -14,7 +14,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
-#include <linux/smp_lock.h>
 #include <linux/kthread.h>
 
 #define NLMDBG_FACILITY         NLMDBG_CLIENT
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 47ea1e1925b..332c54cf75e 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/errno.h>
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 25e21e4023b..ed0c59fe23c 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -124,7 +124,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
                         continue;
                 if (host->h_server != ni->server)
                         continue;
-                if (ni->server &&
+                if (ni->server && ni->src_len != 0 &&
                     !rpc_cmp_addr(nlm_srcaddr(host), ni->src_sap))
                         continue;
 
@@ -167,6 +167,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
         host->h_addrlen = ni->salen;
         rpc_set_port(nlm_addr(host), 0);
         memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len);
+        host->h_srcaddrlen = ni->src_len;
         host->h_version    = ni->version;
         host->h_proto      = ni->protocol;
         host->h_rpcclnt    = NULL;
@@ -238,9 +239,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
                                      const char *hostname,
                                      int noresvport)
 {
-        const struct sockaddr source = {
-                .sa_family      = AF_UNSPEC,
-        };
         struct nlm_lookup_host_info ni = {
                 .server         = 0,
                 .sap            = sap,
@@ -249,8 +247,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
                 .version        = version,
                 .hostname       = hostname,
                 .hostname_len   = strlen(hostname),
-                .src_sap        = &source,
-                .src_len        = sizeof(source),
                 .noresvport     = noresvport,
         };
 
@@ -357,7 +353,6 @@ nlm_bind_host(struct nlm_host *host)
                         .protocol       = host->h_proto,
                         .address        = nlm_addr(host),
                         .addrsize       = host->h_addrlen,
-                        .saddress       = nlm_srcaddr(host),
                         .timeout        = &timeparms,
                         .servername     = host->h_name,
                         .program        = &nlm_program,
@@ -376,6 +371,8 @@ nlm_bind_host(struct nlm_host *host)
                         args.flags |= RPC_CLNT_CREATE_HARDRTRY;
                 if (host->h_noresvport)
                         args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+                if (host->h_srcaddrlen)
+                        args.saddress = nlm_srcaddr(host);
 
                 clnt = rpc_create(&args);
                 if (!IS_ERR(clnt))
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index a336e832475..38d26119245 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -9,7 +9,6 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index c462d346acb..ef5659b211e 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -25,7 +25,6 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/nlm.h>
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index c3069f38d60..0caea5310ac 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -9,7 +9,6 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 
diff --git a/fs/locks.c b/fs/locks.c
index 0e62dd35d08..8729347bcd1 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -122,7 +122,6 @@
 #include <linux/module.h>
 #include <linux/security.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/time.h>
 #include <linux/rcupdate.h>
diff --git a/fs/namespace.c b/fs/namespace.c
index 8a415c9c5e5..3dbfc072ec7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -13,7 +13,6 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/percpu.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/acct.h>
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index aac8832e919..f22b12e7d33 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -19,7 +19,6 @@
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
-#include <linux/smp_lock.h>
 
 #include <linux/ncp_fs.h>
 
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 6c754f70c52..cb50aaf981d 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -17,7 +17,6 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 
 #include <linux/ncp_fs.h>
 #include "ncplib_kernel.h"
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index d290545aa0c..8fb93b604e7 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -26,7 +26,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index c2a1f9a155c..d40a547e337 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -17,7 +17,6 @@
 #include <linux/mount.h>
 #include <linux/slab.h>
 #include <linux/highuid.h>
-#include <linux/smp_lock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index aeec017fe81..93a8b3bd69e 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -9,7 +9,6 @@
 #include <linux/completion.h>
 #include <linux/ip.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 232a7eead33..1fd62fc49be 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 
 #include <linux/nfs4.h>
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 07ac3847e56..662df2a5fad 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -34,6 +34,7 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
 
 #include "delegation.h"
 #include "iostat.h"
@@ -194,9 +195,13 @@ typedef struct {
 static
 struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
 {
+        void *ptr;
         if (page == NULL)
                 return ERR_PTR(-EIO);
-        return (struct nfs_cache_array *)kmap(page);
+        ptr = kmap(page);
+        if (ptr == NULL)
+                return ERR_PTR(-ENOMEM);
+        return ptr;
 }
 
 static
@@ -213,6 +218,9 @@ int nfs_readdir_clear_array(struct page *page, gfp_t mask)
 {
         struct nfs_cache_array *array = nfs_readdir_get_array(page);
         int i;
+
+        if (IS_ERR(array))
+                return PTR_ERR(array);
         for (i = 0; i < array->size; i++)
                 kfree(array->array[i].string.name);
         nfs_readdir_release_array(page);
@@ -231,6 +239,11 @@ int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int le
         string->name = kmemdup(name, len, GFP_KERNEL);
         if (string->name == NULL)
                 return -ENOMEM;
+        /*
+         * Avoid a kmemleak false positive. The pointer to the name is stored
+         * in a page cache page which kmemleak does not scan.
+         */
+        kmemleak_not_leak(string->name);
         string->hash = full_name_hash(name, len);
         return 0;
 }
@@ -244,7 +257,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 
         if (IS_ERR(array))
                 return PTR_ERR(array);
-        ret = -EIO;
+        ret = -ENOSPC;
         if (array->size >= MAX_READDIR_ARRAY)
                 goto out;
 
@@ -255,9 +268,9 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
         if (ret)
                 goto out;
         array->last_cookie = entry->cookie;
+        array->size++;
         if (entry->eof == 1)
                 array->eof_index = array->size;
-        array->size++;
 out:
         nfs_readdir_release_array(page);
         return ret;
@@ -272,7 +285,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
         if (diff < 0)
                 goto out_eof;
         if (diff >= array->size) {
-                if (array->eof_index > 0)
+                if (array->eof_index >= 0)
                         goto out_eof;
                 desc->current_index += array->size;
                 return -EAGAIN;
@@ -281,8 +294,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
         index = (unsigned int)diff;
         *desc->dir_cookie = array->array[index].cookie;
         desc->cache_entry_index = index;
-        if (index == array->eof_index)
-                desc->eof = 1;
         return 0;
 out_eof:
         desc->eof = 1;
@@ -296,17 +307,17 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
         int status = -EAGAIN;
 
         for (i = 0; i < array->size; i++) {
-                if (i == array->eof_index) {
-                        desc->eof = 1;
-                        status = -EBADCOOKIE;
-                }
                 if (array->array[i].cookie == *desc->dir_cookie) {
                         desc->cache_entry_index = i;
                         status = 0;
-                        break;
+                        goto out;
                 }
         }
-
+        if (i == array->eof_index) {
+                desc->eof = 1;
+                status = -EBADCOOKIE;
+        }
+out:
         return status;
 }
 
@@ -449,7 +460,7 @@ out:
 
 /* Perform conversion from xdr to cache array */
 static
-void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
+int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
                                 void *xdr_page, struct page *page, unsigned int buflen)
 {
         struct xdr_stream stream;
@@ -471,21 +482,29 @@ void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *e
 
         do {
                 status = xdr_decode(desc, entry, &stream);
-                if (status != 0)
+                if (status != 0) {
+                        if (status == -EAGAIN)
+                                status = 0;
                         break;
+                }
 
-                if (nfs_readdir_add_to_array(entry, page) == -1)
-                        break;
                 if (desc->plus == 1)
                         nfs_prime_dcache(desc->file->f_path.dentry, entry);
+
+                status = nfs_readdir_add_to_array(entry, page);
+                if (status != 0)
+                        break;
         } while (!entry->eof);
 
         if (status == -EBADCOOKIE && entry->eof) {
                 array = nfs_readdir_get_array(page);
-                array->eof_index = array->size - 1;
-                status = 0;
-                nfs_readdir_release_array(page);
+                if (!IS_ERR(array)) {
+                        array->eof_index = array->size;
+                        status = 0;
+                        nfs_readdir_release_array(page);
+                }
         }
+        return status;
 }
 
 static
@@ -537,7 +556,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
         struct nfs_entry entry;
         struct file     *file = desc->file;
         struct nfs_cache_array *array;
-        int status = 0;
+        int status = -ENOMEM;
         unsigned int array_size = ARRAY_SIZE(pages);
 
         entry.prev_cookie = 0;
@@ -549,6 +568,10 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
                 goto out;
 
         array = nfs_readdir_get_array(page);
+        if (IS_ERR(array)) {
+                status = PTR_ERR(array);
+                goto out;
+        }
         memset(array, 0, sizeof(struct nfs_cache_array));
         array->eof_index = -1;
 
@@ -556,12 +579,19 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
         if (!pages_ptr)
                 goto out_release_array;
         do {
+                unsigned int pglen;
                 status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
 
                 if (status < 0)
                         break;
-                nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE);
-        } while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY);
+                pglen = status;
+                status = nfs_readdir_page_filler(desc, &entry, pages_ptr, page, pglen);
+                if (status < 0) {
+                        if (status == -ENOSPC)
+                                status = 0;
+                        break;
+                }
+        } while (array->eof_index < 0);
 
         nfs_readdir_free_large_page(pages_ptr, pages, array_size);
 out_release_array:
@@ -582,8 +612,10 @@ static
 int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 {
         struct inode    *inode = desc->file->f_path.dentry->d_inode;
+        int ret;
 
-        if (nfs_readdir_xdr_to_array(desc, page, inode) < 0)
+        ret = nfs_readdir_xdr_to_array(desc, page, inode);
+        if (ret < 0)
                 goto error;
         SetPageUptodate(page);
 
@@ -595,7 +627,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
         return 0;
  error:
         unlock_page(page);
-        return -EIO;
+        return ret;
 }
 
 static
@@ -608,12 +640,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
 static
 struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
 {
-        struct page *page;
-        page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
+        return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
                         desc->page_index, (filler_t *)nfs_readdir_filler, desc);
-        if (IS_ERR(page))
-                desc->eof = 1;
-        return page;
 }
 
 /*
@@ -639,8 +667,10 @@ int find_cache_page(nfs_readdir_descriptor_t *desc)
 static inline
 int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 {
-        int res = -EAGAIN;
+        int res;
 
+        if (desc->page_index == 0)
+                desc->current_index = 0;
         while (1) {
                 res = find_cache_page(desc);
                 if (res != -EAGAIN)
@@ -670,6 +700,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
         struct dentry *dentry = NULL;
 
         array = nfs_readdir_get_array(desc->page);
+        if (IS_ERR(array))
+                return PTR_ERR(array);
 
         for (i = desc->cache_entry_index; i < array->size; i++) {
                 d_type = DT_UNKNOWN;
@@ -685,11 +717,9 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
                         *desc->dir_cookie = array->array[i+1].cookie;
                 else
                         *desc->dir_cookie = array->last_cookie;
-                if (i == array->eof_index) {
-                        desc->eof = 1;
-                        break;
-                }
         }
+        if (i == array->eof_index)
+                desc->eof = 1;
 
         nfs_readdir_release_array(desc->page);
         cache_page_release(desc);
@@ -1345,12 +1375,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                                 res = NULL;
                                 goto out;
                         /* This turned out not to be a regular file */
-                        case -EISDIR:
                         case -ENOTDIR:
                                 goto no_open;
                         case -ELOOP:
                                 if (!(nd->intent.open.flags & O_NOFOLLOW))
                                         goto no_open;
+                        /* case -EISDIR: */
                         /* case -EINVAL: */
                         default:
                                 res = ERR_CAST(inode);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index e6bf45710cc..2563f765c9b 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -423,7 +423,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
         struct page **page;
         size_t hdrlen;
         unsigned int pglen, recvd;
-        int status, nr = 0;
+        int status;
 
         if ((status = ntohl(*p++)))
                 return nfs_stat_to_errno(status);
@@ -443,7 +443,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
         if (pglen > recvd)
                 pglen = recvd;
         page = rcvbuf->pages;
-        return nr;
+        return pglen;
 }
 
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index d9a5e832c25..748dc91a4a1 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -555,7 +555,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
         struct page **page;
         size_t hdrlen;
         u32 recvd, pglen;
-        int status, nr = 0;
+        int status;
 
         status = ntohl(*p++);
         /* Decode post_op_attrs */
@@ -586,7 +586,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res
                 pglen = recvd;
         page = rcvbuf->pages;
 
-        return nr;
+        return pglen;
 }
 
 __be32 *
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0f24cdf2cb1..6a653ffd8e4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2852,8 +2852,10 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
         nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
         res.pgbase = args.pgbase;
         status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0);
-        if (status == 0)
+        if (status >= 0) {
                 memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+                status += args.pgbase;
+        }
 
         nfs_invalidate_atime(dir);
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f313c4cce7e..b7a204ff6fe 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4518,7 +4518,7 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
         xdr_read_pages(xdr, pglen);
 
 
-        return 0;
+        return pglen;
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0a42e8f4adc..3c045044fca 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -39,7 +39,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/mnt_namespace.h>
@@ -67,6 +66,12 @@
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
+#ifdef CONFIG_NFS_V3
+#define NFS_DEFAULT_VERSION 3
+#else
+#define NFS_DEFAULT_VERSION 2
+#endif
+
 enum {
         /* Mount options that take no arguments */
         Opt_soft, Opt_hard,
@@ -2277,7 +2282,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
         };
         int error = -ENOMEM;
 
-        data = nfs_alloc_parsed_mount_data(3);
+        data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
         mntfh = nfs_alloc_fhandle();
         if (data == NULL || mntfh == NULL)
                 goto out_free_fh;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ad2bfa68d53..116cab970e0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2262,7 +2262,7 @@ nfs4_file_downgrade(struct nfs4_file *fp, unsigned int share_access)
  * Spawn a thread to perform a recall on the delegation represented
  * by the lease (file_lock)
  *
- * Called from break_lease() with lock_kernel() held.
+ * Called from break_lease() with lock_flocks() held.
  * Note: we assume break_lease will only call this *once* for any given
  * lease.
  */
@@ -2286,7 +2286,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
         list_add_tail(&dp->dl_recall_lru, &del_recall_lru);
         spin_unlock(&recall_lock);
 
-        /* only place dl_time is set. protected by lock_kernel*/
+        /* only place dl_time is set. protected by lock_flocks*/
         dp->dl_time = get_seconds();
 
         /*
@@ -2303,7 +2303,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
 /*
  * The file_lock is being reapd.
  *
- * Called by locks_free_lock() with lock_kernel() held.
+ * Called by locks_free_lock() with lock_flocks() held.
  */
 static
 void nfsd_release_deleg_cb(struct file_lock *fl)
@@ -2318,7 +2318,7 @@ void nfsd_release_deleg_cb(struct file_lock *fl)
 }
 
 /*
- * Called from setlease() with lock_kernel() held
+ * Called from setlease() with lock_flocks() held
  */
 static
 int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index f02c0ef3157..cfeab7ce369 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -41,7 +41,6 @@
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
-#include <linux/smp_lock.h>
 
 #define MLOG_MASK_PREFIX ML_SUPER
 #include <cluster/masklog.h>
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 9c2b5f48487..3ddb6068177 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -16,7 +16,6 @@
 #include <linux/limits.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 431a0ed610c..5d431bacbea 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,7 +9,6 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
-#include <linux/smp_lock.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/module.h>
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 41656d40dc5..0bae036831e 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -8,7 +8,6 @@
 #include <linux/reiserfs_acl.h>
 #include <linux/reiserfs_xattr.h>
 #include <linux/exportfs.h>
-#include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index adf22b485ce..bd9763e76ba 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -9,7 +9,6 @@
 #include <linux/time.h>
 #include <asm/uaccess.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/compat.h>
 
 /*
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 076c8b19468..d31bce1a9f9 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -43,7 +43,6 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/workqueue.h>
 #include <linux/writeback.h>
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3bf7a6457f4..b243117b875 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -28,7 +28,6 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/crc32.h>
-#include <linux/smp_lock.h>
 
 struct file_system_type reiserfs_fs_type;
 
diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h
index 01a71411950..bc5590b1a1a 100644
--- a/include/drm/nouveau_drm.h
+++ b/include/drm/nouveau_drm.h
@@ -80,6 +80,7 @@ struct drm_nouveau_gpuobj_free {
 #define NOUVEAU_GETPARAM_VM_VRAM_BASE    12
 #define NOUVEAU_GETPARAM_GRAPH_UNITS     13
 #define NOUVEAU_GETPARAM_PTIMER_TIME     14
+#define NOUVEAU_GETPARAM_HAS_BO_USAGE    15
 struct drm_nouveau_getparam {
         uint64_t param;
         uint64_t value;
@@ -95,6 +96,12 @@ struct drm_nouveau_setparam {
 #define NOUVEAU_GEM_DOMAIN_GART      (1 << 2)
 #define NOUVEAU_GEM_DOMAIN_MAPPABLE  (1 << 3)
 
+#define NOUVEAU_GEM_TILE_LAYOUT_MASK 0x0000ff00
+#define NOUVEAU_GEM_TILE_16BPP       0x00000001
+#define NOUVEAU_GEM_TILE_32BPP       0x00000002
+#define NOUVEAU_GEM_TILE_ZETA        0x00000004
+#define NOUVEAU_GEM_TILE_NONCONTIG   0x00000008
+
 struct drm_nouveau_gem_info {
         uint32_t handle;
         uint32_t domain;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index f22b2e94168..9e76d35670d 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -227,8 +227,7 @@ extern int ceph_open_session(struct ceph_client *client);
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
 
 extern struct page **ceph_get_direct_page_vector(const char __user *data,
-                                            int num_pages,
-                                            loff_t off, size_t len);
+                                                 int num_pages);
 extern void ceph_put_page_vector(struct page **pages, int num_pages);
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 5956d62c305..a108b425fee 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -82,6 +82,7 @@ struct ceph_msg {
         struct ceph_buffer *middle;
         struct page **pages;            /* data payload.  NOT OWNER. */
         unsigned nr_pages;              /* size of page array */
+        unsigned page_alignment;        /* io offset in first page */
         struct ceph_pagelist *pagelist; /* instead of pages */
         struct list_head list_head;
         struct kref kref;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 6c91fb032c3..a1af29648fb 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -79,6 +79,7 @@ struct ceph_osd_request {
         struct ceph_file_layout r_file_layout;
         struct ceph_snap_context *r_snapc;    /* snap context for writes */
         unsigned          r_num_pages;        /* size of page array (follows) */
+        unsigned          r_page_alignment;   /* io offset in first page */
         struct page     **r_pages;            /* pages for data payload */
         int               r_pages_from_pool;
         int               r_own_pages;        /* if true, i own page list */
@@ -194,7 +195,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
                                       int do_sync, u32 truncate_seq,
                                       u64 truncate_size,
                                       struct timespec *mtime,
-                                      bool use_mempool, int num_reply);
+                                      bool use_mempool, int num_reply,
+                                      int page_align);
 
 static inline void ceph_osdc_get_request(struct ceph_osd_request *req)
 {
@@ -218,7 +220,8 @@ extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
                                struct ceph_file_layout *layout,
                                u64 off, u64 *plen,
                                u32 truncate_seq, u64 truncate_size,
-                               struct page **pages, int nr_pages);
+                               struct page **pages, int nr_pages,
+                               int page_align);
 
 extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
                                 struct ceph_vino vino,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 334d68a1710..eedc00b7b1e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1612,7 +1612,6 @@ struct super_operations {
         ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
         int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
-        int (*trim_fs) (struct super_block *, struct fstrim_range *);
 };
 
 /*
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 41cb31f14ee..32f9fd6619b 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -2,9 +2,6 @@
 #define LINUX_HARDIRQ_H
 
 #include <linux/preempt.h>
-#ifdef CONFIG_PREEMPT
-#include <linux/smp_lock.h>
-#endif
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <asm/hardirq.h>
@@ -97,7 +94,8 @@
 #define in_nmi()        (preempt_count() & NMI_MASK)
 
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_BKL)
-# define PREEMPT_INATOMIC_BASE kernel_locked()
+# include <linux/sched.h>
+# define PREEMPT_INATOMIC_BASE (current->lock_depth >= 0)
 #else
 # define PREEMPT_INATOMIC_BASE 0
 #endif
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 15b77b8dc7e..d947b123166 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -986,7 +986,7 @@ extern void ata_host_init(struct ata_host *, struct device *,
                           unsigned long, struct ata_port_operations *);
 extern int ata_scsi_detect(struct scsi_host_template *sht);
 extern int ata_scsi_ioctl(struct scsi_device *dev, int cmd, void __user *arg);
-extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *));
+extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
                             int cmd, void __user *arg);
 extern void ata_sas_port_destroy(struct ata_port *);
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index a34dea46b62..2dee05e5119 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -43,6 +43,7 @@ struct nlm_host {
         struct sockaddr_storage h_addr;         /* peer address */
         size_t                  h_addrlen;
         struct sockaddr_storage h_srcaddr;      /* our address (optional) */
+        size_t                  h_srcaddrlen;
         struct rpc_clnt         *h_rpcclnt;     /* RPC client to talk to peer */
         char                    *h_name;                /* remote hostname */
         u32                     h_version;      /* interface version */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bba26684acd..c66fdb7d699 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -593,12 +593,6 @@ nfs_fileid_to_ino_t(u64 fileid)
         return ino;
 }
 
-#define nfs_wait_event(clnt, wq, condition)                             \
-({                                                                      \
-        int __retval = wait_event_killable(wq, condition);              \
-        __retval;                                                       \
-})
-
 #define NFS_JUKEBOX_RETRY_TIME (5 * HZ)
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index 5ca47e59b72..c21072adbfa 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -22,7 +22,6 @@
 #include <asm/unaligned.h>
 #include <linux/bitops.h>
 #include <linux/proc_fs.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/reiserfs_fs_i.h>
 #include <linux/reiserfs_fs_sb.h>
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index d42f274418b..bbad657a372 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -6,7 +6,6 @@
 #include <linux/if_link.h>
 #include <linux/if_addr.h>
 #include <linux/neighbour.h>
-#include <linux/netdevice.h>
 
 /* rtnetlink families. Values up to 127 are reserved for real address
  * families, values above 128 may be used arbitrarily.
@@ -606,6 +605,7 @@ struct tcamsg {
 #ifdef __KERNEL__
 
 #include <linux/mutex.h>
+#include <linux/netdevice.h>
 
 static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 840f1277492..a5b92c70c73 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -862,6 +862,7 @@ struct sched_group {
          * single CPU.
          */
         unsigned int cpu_power, cpu_power_orig;
+        unsigned int group_weight;
 
         /*
          * The CPUs this group covers.
diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h
index 291f721144c..3a198820273 100644
--- a/include/linux/smp_lock.h
+++ b/include/linux/smp_lock.h
@@ -4,8 +4,6 @@
 #ifdef CONFIG_LOCK_KERNEL
 #include <linux/sched.h>
 
-#define kernel_locked()         (current->lock_depth >= 0)
-
 extern int __lockfunc __reacquire_kernel_lock(void);
 extern void __lockfunc __release_kernel_lock(void);
 
@@ -58,7 +56,6 @@ static inline void cycle_kernel_lock(void)
 #define lock_kernel()
 #define unlock_kernel()
 #define cycle_kernel_lock()                     do { } while(0)
-#define kernel_locked()                         1
 #endif /* CONFIG_BKL */
 
 #define release_kernel_lock(task)               do { } while(0)
diff --git a/include/linux/tty.h b/include/linux/tty.h
index c7ea9bc8897..032d79ff1d9 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -13,7 +13,6 @@
 #include <linux/tty_driver.h>
 #include <linux/tty_ldisc.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2a7936d7851..97b8b7c9b63 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1355,7 +1355,7 @@ enum wiphy_flags {
         WIPHY_FLAG_4ADDR_AP                     = BIT(5),
         WIPHY_FLAG_4ADDR_STATION                = BIT(6),
         WIPHY_FLAG_CONTROL_PORT_PROTOCOL        = BIT(7),
-        WIPHY_FLAG_IBSS_RSN                     = BIT(7),
+        WIPHY_FLAG_IBSS_RSN                     = BIT(8),
 };
 
 struct mac_address {
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 55590ab16b3..6beb1ffc2b7 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -303,7 +303,7 @@ static inline void neigh_confirm(struct neighbour *neigh)
 
 static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
-        unsigned long now = ACCESS_ONCE(jiffies);
+        unsigned long now = jiffies;
         
         if (neigh->used != now)
                 neigh->used = now;
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index f986ab7ffe6..5c4c1678f7b 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -1006,8 +1006,7 @@ void fc_fcp_destroy(struct fc_lport *);
 /*
  * SCSI INTERACTION LAYER
  *****************************/
-int fc_queuecommand(struct scsi_cmnd *,
-                    void (*done)(struct scsi_cmnd *));
+int fc_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 int fc_eh_abort(struct scsi_cmnd *);
 int fc_eh_device_reset(struct scsi_cmnd *);
 int fc_eh_host_reset(struct scsi_cmnd *);
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index ae5196aae1a..b81d969ddc6 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -341,8 +341,7 @@ extern int iscsi_eh_abort(struct scsi_cmnd *sc);
 extern int iscsi_eh_recover_target(struct scsi_cmnd *sc);
 extern int iscsi_eh_session_reset(struct scsi_cmnd *sc);
 extern int iscsi_eh_device_reset(struct scsi_cmnd *sc);
-extern int iscsi_queuecommand(struct scsi_cmnd *sc,
-                              void (*done)(struct scsi_cmnd *));
+extern int iscsi_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *sc);
 
 /*
  * iSCSI host helpers.
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 3dec1949f69..90ce527ecf3 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -621,8 +621,7 @@ int sas_set_phy_speed(struct sas_phy *phy,
 int sas_phy_enable(struct sas_phy *phy, int enabled);
 int sas_phy_reset(struct sas_phy *phy, int hard_reset);
 int sas_queue_up(struct sas_task *task);
-extern int sas_queuecommand(struct scsi_cmnd *,
-                     void (*scsi_done)(struct scsi_cmnd *));
+extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
 extern int sas_slave_alloc(struct scsi_device *);
 extern int sas_slave_configure(struct scsi_device *);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index d0a6a845f20..e7e385842a3 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -127,8 +127,7 @@ struct scsi_host_template {
          *
          * STATUS: REQUIRED
          */
-        int (* queuecommand)(struct scsi_cmnd *,
-                             void (*done)(struct scsi_cmnd *));
+        int (* queuecommand)(struct Scsi_Host *, struct scsi_cmnd *);
 
         /*
          * The transfer functions are used to queue a scsi command to
@@ -505,6 +504,25 @@ struct scsi_host_template {
 };
 
 /*
+ * Temporary #define for host lock push down. Can be removed when all
+ * drivers have been updated to take advantage of unlocked
+ * queuecommand.
+ *
+ */
+#define DEF_SCSI_QCMD(func_name) \
+        int func_name(struct Scsi_Host *shost, struct scsi_cmnd *cmd)   \
+        {                                                               \
+                unsigned long irq_flags;                                \
+                int rc;                                                 \
+                spin_lock_irqsave(shost->host_lock, irq_flags);         \
+                scsi_cmd_get_serial(shost, cmd);                        \
+                rc = func_name##_lck (cmd, cmd->scsi_done);                     \
+                spin_unlock_irqrestore(shost->host_lock, irq_flags);    \
+                return rc;                                              \
+        }
+
+
+/*
  * shost state: If you alter this, you also need to alter scsi_sysfs.c
  * (for the ascii descriptions) and the state model enforcer:
  * scsi_host_set_state()
@@ -752,6 +770,7 @@ extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *);
 extern void scsi_host_put(struct Scsi_Host *t);
 extern struct Scsi_Host *scsi_host_lookup(unsigned short);
 extern const char *scsi_host_state_name(enum scsi_host_state);
+extern void scsi_cmd_get_serial(struct Scsi_Host *, struct scsi_cmnd *);
 
 extern u64 scsi_calculate_bounce_limit(struct Scsi_Host *);
 
diff --git a/init/main.c b/init/main.c
index e59af24a0b7..8646401f7a0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -20,7 +20,6 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 37755d62192..a6e72976682 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -82,7 +82,7 @@ static kdbtab_t kdb_base_commands[50];
 #define for_each_kdbcmd(cmd, num)                                       \
         for ((cmd) = kdb_base_commands, (num) = 0;                      \
              num < kdb_max_commands;                                    \
-             num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+             num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++)
 
 typedef struct _kdbmsg {
         int     km_diag;        /* kdb diagnostic */
@@ -646,7 +646,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
         }
         if (!s->usable)
                 return KDB_NOTIMP;
-        s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+        s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
         if (!s->command) {
                 kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
                            cmdstr);
@@ -2361,7 +2361,7 @@ static int kdb_pid(int argc, const char **argv)
  */
 static int kdb_ll(int argc, const char **argv)
 {
-        int diag;
+        int diag = 0;
         unsigned long addr;
         long offset = 0;
         unsigned long va;
@@ -2400,20 +2400,21 @@ static int kdb_ll(int argc, const char **argv)
                 char buf[80];
 
                 if (KDB_FLAG(CMD_INTERRUPT))
-                        return 0;
+                        goto out;
 
                 sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
                 diag = kdb_parse(buf);
                 if (diag)
-                        return diag;
+                        goto out;
 
                 addr = va + linkoffset;
                 if (kdb_getword(&va, addr, sizeof(va)))
-                        return 0;
+                        goto out;
         }
-        kfree(command);
 
-        return 0;
+out:
+        kfree(command);
+        return diag;
 }
 
 static int kdb_kgdb(int argc, const char **argv)
@@ -2739,13 +2740,13 @@ int kdb_register_repeat(char *cmd,
                 }
                 if (kdb_commands) {
                         memcpy(new, kdb_commands,
-                               kdb_max_commands * sizeof(*new));
+                          (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new));
                         kfree(kdb_commands);
                 }
                 memset(new + kdb_max_commands, 0,
                        kdb_command_extend * sizeof(*new));
                 kdb_commands = new;
-                kp = kdb_commands + kdb_max_commands;
+                kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX;
                 kdb_max_commands += kdb_command_extend;
         }
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 6c683b37f2c..40a8777a27d 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2489,7 +2489,8 @@ void exit_robust_list(struct task_struct *curr)
 {
         struct robust_list_head __user *head = curr->robust_list;
         struct robust_list __user *entry, *next_entry, *pending;
-        unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+        unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+        unsigned int uninitialized_var(next_pi);
         unsigned long futex_offset;
         int rc;
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 06da4dfc339..a7934ac75e5 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -49,7 +49,8 @@ void compat_exit_robust_list(struct task_struct *curr)
 {
         struct compat_robust_list_head __user *head = curr->compat_robust_list;
         struct robust_list __user *entry, *next_entry, *pending;
-        unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+        unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+        unsigned int uninitialized_var(next_pi);
         compat_uptr_t uentry, next_uentry, upending;
         compat_long_t futex_offset;
         int rc;
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index c7a8f453919..aeaa7f84682 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -121,10 +121,10 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 
         switch (o->type) {
         case PM_QOS_MIN:
-                return plist_last(&o->requests)->prio;
+                return plist_first(&o->requests)->prio;
 
         case PM_QOS_MAX:
-                return plist_first(&o->requests)->prio;
+                return plist_last(&o->requests)->prio;
 
         default:
                 /* runtime check for not using enum */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 29bff6117ab..a5aff3ebad3 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -246,9 +246,13 @@ config PM_OPS
         depends on PM_SLEEP || PM_RUNTIME
         default y
 
+config ARCH_HAS_OPP
+        bool
+
 config PM_OPP
         bool "Operating Performance Point (OPP) Layer library"
         depends on PM
+        depends on ARCH_HAS_OPP
         ---help---
           SOCs have a standard set of tuples consisting of frequency and
           voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/sched.c b/kernel/sched.c
index 324afce0e22..3e8a7db951a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -557,18 +557,8 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-        rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 
-        /*
-         * A queue event has occurred, and we're going to schedule.  In
-         * this case, we can save a useless back to back clock update.
-         */
-        if (test_tsk_need_resched(p))
-                rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -1980,6 +1970,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                 p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+        const struct sched_class *class;
+
+        if (p->sched_class == rq->curr->sched_class) {
+                rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+        } else {
+                for_each_class(class) {
+                        if (class == rq->curr->sched_class)
+                                break;
+                        if (class == p->sched_class) {
+                                resched_task(rq->curr);
+                                break;
+                        }
+                }
+        }
+
+        /*
+         * A queue event has occurred, and we're going to schedule.  In
+         * this case, we can save a useless back to back clock update.
+         */
+        if (test_tsk_need_resched(rq->curr))
+                rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -6737,6 +6752,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
         if (cpu != group_first_cpu(sd->groups))
                 return;
 
+        sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
         child = sd->child;
 
         sd->groups->cpu_power = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 82fd884b4e3..fdbdb5084c4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1799,12 +1799,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         struct cfs_rq *cfs_rq = task_cfs_rq(curr);
         int scale = cfs_rq->nr_running >= sched_nr_latency;
 
-        if (unlikely(rt_prio(p->prio)))
-                goto preempt;
-
-        if (unlikely(p->sched_class != &fair_sched_class))
-                return;
-
         if (unlikely(se == pse))
                 return;
 
@@ -2226,13 +2220,16 @@ struct sd_lb_stats {
         unsigned long this_load_per_task;
         unsigned long this_nr_running;
         unsigned long this_has_capacity;
+        unsigned int  this_idle_cpus;
 
         /* Statistics of the busiest group */
+        unsigned int  busiest_idle_cpus;
         unsigned long max_load;
         unsigned long busiest_load_per_task;
         unsigned long busiest_nr_running;
         unsigned long busiest_group_capacity;
         unsigned long busiest_has_capacity;
+        unsigned int  busiest_group_weight;
 
         int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2254,6 +2251,8 @@ struct sg_lb_stats {
         unsigned long sum_nr_running; /* Nr tasks running in the group */
         unsigned long sum_weighted_load; /* Weighted load of group's tasks */
         unsigned long group_capacity;
+        unsigned long idle_cpus;
+        unsigned long group_weight;
         int group_imb; /* Is there an imbalance in the group ? */
         int group_has_capacity; /* Is there extra capacity in the group? */
 };
@@ -2622,7 +2621,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                 sgs->group_load += load;
                 sgs->sum_nr_running += rq->nr_running;
                 sgs->sum_weighted_load += weighted_cpuload(i);
-
+                if (idle_cpu(i))
+                        sgs->idle_cpus++;
         }
 
         /*
@@ -2660,6 +2660,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
         if (!sgs->group_capacity)
                 sgs->group_capacity = fix_small_capacity(sd, group);
+        sgs->group_weight = group->group_weight;
 
         if (sgs->group_capacity > sgs->sum_nr_running)
                 sgs->group_has_capacity = 1;
@@ -2767,13 +2768,16 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->this_nr_running = sgs.sum_nr_running;
                         sds->this_load_per_task = sgs.sum_weighted_load;
                         sds->this_has_capacity = sgs.group_has_capacity;
+                        sds->this_idle_cpus = sgs.idle_cpus;
                 } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
                         sds->max_load = sgs.avg_load;
                         sds->busiest = sg;
                         sds->busiest_nr_running = sgs.sum_nr_running;
+                        sds->busiest_idle_cpus = sgs.idle_cpus;
                         sds->busiest_group_capacity = sgs.group_capacity;
                         sds->busiest_load_per_task = sgs.sum_weighted_load;
                         sds->busiest_has_capacity = sgs.group_has_capacity;
+                        sds->busiest_group_weight = sgs.group_weight;
                         sds->group_imb = sgs.group_imb;
                 }
 
@@ -3051,8 +3055,26 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (sds.this_load >= sds.avg_load)
                 goto out_balanced;
 
-        if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-                goto out_balanced;
+        /*
+         * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
+         * And to check for busy balance use !idle_cpu instead of
+         * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
+         * even when they are idle.
+         */
+        if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
+                if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+                        goto out_balanced;
+        } else {
+                /*
+                 * This cpu is idle. If the busiest group load doesn't
+                 * have more tasks than the number of available cpu's and
+                 * there is no imbalance between this and busiest group
+                 * wrt to idle cpu's, it is balanced.
+                 */
+                if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+                    sds.busiest_nr_running <= sds.busiest_group_weight)
+                        goto out_balanced;
+        }
 
 force_balance:
         /* Looks like there is an imbalance. Compute it */
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 45bddc0c104..2bf6b47058c 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,14 +19,14 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
 static void
 check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-        resched_task(rq->curr); /* we preempt everything */
+        /* we're never preempted */
 }
 
 static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
         struct task_struct *stop = rq->stop;
 
-        if (stop && stop->state == TASK_RUNNING)
+        if (stop && stop->se.on_rq)
                 return stop;
 
         return NULL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9b520d74f05..a00fdefd24c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -690,7 +690,6 @@ static struct ctl_table kern_table[] = {
                 .extra1         = &zero,
                 .extra2         = &ten_thousand,
         },
-#endif
         {
                 .procname       = "dmesg_restrict",
                 .data           = &dmesg_restrict,
@@ -700,6 +699,7 @@ static struct ctl_table kern_table[] = {
                 .extra1         = &zero,
                 .extra2         = &one,
         },
+#endif
         {
                 .procname       = "ngroups_max",
                 .data           = &ngroups_max,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef8..ea37e2ff416 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -126,7 +126,7 @@ if FTRACE
 config FUNCTION_TRACER
         bool "Kernel Function Tracer"
         depends on HAVE_FUNCTION_TRACER
-        select FRAME_POINTER if (!ARM_UNWIND)
+        select FRAME_POINTER if !ARM_UNWIND && !S390
         select KALLSYMS
         select GENERIC_TRACER
         select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b8106cd..04208415798 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0e8157ee5d4..1c7a2ec4f3c 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -540,8 +540,7 @@ static void prepare_write_message(struct ceph_connection *con)
                 /* initialize page iterator */
                 con->out_msg_pos.page = 0;
                 if (m->pages)
-                        con->out_msg_pos.page_pos =
-                                le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+                        con->out_msg_pos.page_pos = m->page_alignment;
                 else
                         con->out_msg_pos.page_pos = 0;
                 con->out_msg_pos.data_pos = 0;
@@ -1491,7 +1490,7 @@ static int read_partial_message(struct ceph_connection *con)
         struct ceph_msg *m = con->in_msg;
         int ret;
         int to, left;
-        unsigned front_len, middle_len, data_len, data_off;
+        unsigned front_len, middle_len, data_len;
         int datacrc = con->msgr->nocrc;
         int skip;
         u64 seq;
@@ -1527,19 +1526,17 @@ static int read_partial_message(struct ceph_connection *con)
         data_len = le32_to_cpu(con->in_hdr.data_len);
         if (data_len > CEPH_MSG_MAX_DATA_LEN)
                 return -EIO;
-        data_off = le16_to_cpu(con->in_hdr.data_off);
 
         /* verify seq# */
         seq = le64_to_cpu(con->in_hdr.seq);
         if ((s64)seq - (s64)con->in_seq < 1) {
-                pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
+                pr_info("skipping %s%lld %s seq %lld expected %lld\n",
                         ENTITY_NAME(con->peer_name),
                         ceph_pr_addr(&con->peer_addr.in_addr),
                         seq, con->in_seq + 1);
                 con->in_base_pos = -front_len - middle_len - data_len -
                         sizeof(m->footer);
                 con->in_tag = CEPH_MSGR_TAG_READY;
-                con->in_seq++;
                 return 0;
         } else if ((s64)seq - (s64)con->in_seq > 1) {
                 pr_err("read_partial_message bad seq %lld expected %lld\n",
@@ -1576,7 +1573,7 @@ static int read_partial_message(struct ceph_connection *con)
 
                 con->in_msg_pos.page = 0;
                 if (m->pages)
-                        con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+                        con->in_msg_pos.page_pos = m->page_alignment;
                 else
                         con->in_msg_pos.page_pos = 0;
                 con->in_msg_pos.data_pos = 0;
@@ -2301,6 +2298,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
 
         /* data */
         m->nr_pages = 0;
+        m->page_alignment = 0;
         m->pages = NULL;
         m->pagelist = NULL;
         m->bio = NULL;
@@ -2370,6 +2368,7 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
                                type, front_len);
                         return NULL;
                 }
+                msg->page_alignment = le16_to_cpu(hdr->data_off);
         }
         memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 79391994b3e..3e20a122ffa 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -71,6 +71,7 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
                 op->extent.length = objlen;
         }
         req->r_num_pages = calc_pages_for(off, *plen);
+        req->r_page_alignment = off & ~PAGE_MASK;
         if (op->op == CEPH_OSD_OP_WRITE)
                 op->payload_len = *plen;
 
@@ -390,6 +391,8 @@ void ceph_osdc_build_request(struct ceph_osd_request *req,
                 req->r_request->hdr.data_len = cpu_to_le32(data_len);
         }
 
+        req->r_request->page_alignment = req->r_page_alignment;
+
         BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
         msg_size = p - msg->front.iov_base;
         msg->front.iov_len = msg_size;
@@ -419,7 +422,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
                                                u32 truncate_seq,
                                                u64 truncate_size,
                                                struct timespec *mtime,
-                                               bool use_mempool, int num_reply)
+                                               bool use_mempool, int num_reply,
+                                               int page_align)
 {
         struct ceph_osd_req_op ops[3];
         struct ceph_osd_request *req;
@@ -447,6 +451,10 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
         calc_layout(osdc, vino, layout, off, plen, req, ops);
         req->r_file_layout = *layout;  /* keep a copy */
 
+        /* in case it differs from natural alignment that calc_layout
+           filled in for us */
+        req->r_page_alignment = page_align;
+
         ceph_osdc_build_request(req, off, plen, ops,
                                 snapc,
                                 mtime,
@@ -1489,7 +1497,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
                         struct ceph_vino vino, struct ceph_file_layout *layout,
                         u64 off, u64 *plen,
                         u32 truncate_seq, u64 truncate_size,
-                        struct page **pages, int num_pages)
+                        struct page **pages, int num_pages, int page_align)
 {
         struct ceph_osd_request *req;
         int rc = 0;
@@ -1499,15 +1507,15 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
         req = ceph_osdc_new_request(osdc, layout, vino, off, plen,
                                     CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
                                     NULL, 0, truncate_seq, truncate_size, NULL,
-                                    false, 1);
+                                    false, 1, page_align);
         if (!req)
                 return -ENOMEM;
 
         /* it may be a short read due to an object boundary */
         req->r_pages = pages;
 
-        dout("readpages  final extent is %llu~%llu (%d pages)\n",
-             off, *plen, req->r_num_pages);
+        dout("readpages  final extent is %llu~%llu (%d pages align %d)\n",
+             off, *plen, req->r_num_pages, page_align);
 
         rc = ceph_osdc_start_request(osdc, req, false);
         if (!rc)
@@ -1533,6 +1541,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 {
         struct ceph_osd_request *req;
         int rc = 0;
+        int page_align = off & ~PAGE_MASK;
 
         BUG_ON(vino.snap != CEPH_NOSNAP);
         req = ceph_osdc_new_request(osdc, layout, vino, off, &len,
@@ -1541,7 +1550,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
                                             CEPH_OSD_FLAG_WRITE,
                                     snapc, do_sync,
                                     truncate_seq, truncate_size, mtime,
-                                    nofail, 1);
+                                    nofail, 1, page_align);
         if (!req)
                 return -ENOMEM;
 
@@ -1638,8 +1647,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
         m = ceph_msg_get(req->r_reply);
 
         if (data_len > 0) {
-                unsigned data_off = le16_to_cpu(hdr->data_off);
-                int want = calc_pages_for(data_off & ~PAGE_MASK, data_len);
+                int want = calc_pages_for(req->r_page_alignment, data_len);
 
                 if (unlikely(req->r_num_pages < want)) {
                         pr_warning("tid %lld reply %d > expected %d pages\n",
@@ -1651,6 +1659,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
                 }
                 m->pages = req->r_pages;
                 m->nr_pages = req->r_num_pages;
+                m->page_alignment = req->r_page_alignment;
 #ifdef CONFIG_BLOCK
                 m->bio = req->r_bio;
 #endif
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 54caf068715..ac34feeb2b3 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -13,8 +13,7 @@
  * build a vector of user pages
  */
 struct page **ceph_get_direct_page_vector(const char __user *data,
-                                                 int num_pages,
-                                                 loff_t off, size_t len)
+                                          int num_pages)
 {
         struct page **pages;
         int rc;
diff --git a/net/core/filter.c b/net/core/filter.c
index 23e9b2a6b4c..c1ee800bc08 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -589,7 +589,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
 EXPORT_SYMBOL(sk_chk_filter);
 
 /**
- *      sk_filter_rcu_release: Release a socket filter by rcu_head
+ *      sk_filter_rcu_release - Release a socket filter by rcu_head
  *      @rcu: rcu_head that contains the sk_filter to free
  */
 static void sk_filter_rcu_release(struct rcu_head *rcu)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a5ff5a89f37..7f902cad10f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -712,15 +712,21 @@ static void rx_queue_release(struct kobject *kobj)
 
 
         map = rcu_dereference_raw(queue->rps_map);
-        if (map)
+        if (map) {
+                RCU_INIT_POINTER(queue->rps_map, NULL);
                 call_rcu(&map->rcu, rps_map_release);
+        }
 
         flow_table = rcu_dereference_raw(queue->rps_flow_table);
-        if (flow_table)
+        if (flow_table) {
+                RCU_INIT_POINTER(queue->rps_flow_table, NULL);
                 call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
+        }
 
         if (atomic_dec_and_test(&first->count))
                 kfree(first);
+        else
+                memset(kobj, 0, sizeof(*kobj));
 }
 
 static struct kobj_type rx_queue_ktype = {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 96bc7f9475a..e5d1a44bcbd 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -569,6 +569,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
                 /* No need to clone since we're just using its address. */
                 rt2 = rt;
 
+                if (!fl.nl_u.ip4_u.saddr)
+                        fl.nl_u.ip4_u.saddr = rt->rt_src;
+
                 err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0);
                 switch (err) {
                 case 0:
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b41ce0f0d51..2fc35b32df9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -98,7 +98,11 @@
 #endif
 
 #define INFINITY_LIFE_TIME      0xFFFFFFFF
-#define TIME_DELTA(a, b) ((unsigned long)((long)(a) - (long)(b)))
+
+static inline u32 cstamp_delta(unsigned long cstamp)
+{
+        return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
+}
 
 #define ADDRCONF_TIMER_FUZZ_MINUS       (HZ > 50 ? HZ/50 : 1)
 #define ADDRCONF_TIMER_FUZZ             (HZ / 4)
@@ -3444,10 +3448,8 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp,
 {
         struct ifa_cacheinfo ci;
 
-        ci.cstamp = (u32)(TIME_DELTA(cstamp, INITIAL_JIFFIES) / HZ * 100
-                        + TIME_DELTA(cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
-        ci.tstamp = (u32)(TIME_DELTA(tstamp, INITIAL_JIFFIES) / HZ * 100
-                        + TIME_DELTA(tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
+        ci.cstamp = cstamp_delta(cstamp);
+        ci.tstamp = cstamp_delta(tstamp);
         ci.ifa_prefered = preferred;
         ci.ifa_valid = valid;
 
@@ -3798,8 +3800,10 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
         array[DEVCONF_AUTOCONF] = cnf->autoconf;
         array[DEVCONF_DAD_TRANSMITS] = cnf->dad_transmits;
         array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits;
-        array[DEVCONF_RTR_SOLICIT_INTERVAL] = cnf->rtr_solicit_interval;
-        array[DEVCONF_RTR_SOLICIT_DELAY] = cnf->rtr_solicit_delay;
+        array[DEVCONF_RTR_SOLICIT_INTERVAL] =
+                jiffies_to_msecs(cnf->rtr_solicit_interval);
+        array[DEVCONF_RTR_SOLICIT_DELAY] =
+                jiffies_to_msecs(cnf->rtr_solicit_delay);
         array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version;
 #ifdef CONFIG_IPV6_PRIVACY
         array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr;
@@ -3813,7 +3817,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
         array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
         array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
-        array[DEVCONF_RTR_PROBE_INTERVAL] = cnf->rtr_probe_interval;
+        array[DEVCONF_RTR_PROBE_INTERVAL] =
+                jiffies_to_msecs(cnf->rtr_probe_interval);
 #ifdef CONFIG_IPV6_ROUTE_INFO
         array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
 #endif
@@ -3929,10 +3934,9 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
         NLA_PUT_U32(skb, IFLA_INET6_FLAGS, idev->if_flags);
 
         ci.max_reasm_len = IPV6_MAXPLEN;
-        ci.tstamp = (__u32)(TIME_DELTA(idev->tstamp, INITIAL_JIFFIES) / HZ * 100
-                    + TIME_DELTA(idev->tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
-        ci.reachable_time = idev->nd_parms->reachable_time;
-        ci.retrans_time = idev->nd_parms->retrans_time;
+        ci.tstamp = cstamp_delta(idev->tstamp);
+        ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time);
+        ci.retrans_time = jiffies_to_msecs(idev->nd_parms->retrans_time);
         NLA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci);
 
         nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32));
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 7f097989cde..a6de3059746 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -45,7 +45,6 @@
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/smp_lock.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/slab.h>
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 7fa86373de4..7c567b8aa89 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -15,7 +15,6 @@
 
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include "irnet_ppp.h"          /* Private header */
 /* Please put other headers in irnet.h - Thanks */
 
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 285761e77d9..f6054f9ccbe 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -550,22 +550,30 @@ EXPORT_SYMBOL(irttp_close_tsap);
  */
 int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 {
+        int ret;
+
         IRDA_ASSERT(self != NULL, return -1;);
         IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
         IRDA_ASSERT(skb != NULL, return -1;);
 
         IRDA_DEBUG(4, "%s()\n", __func__);
 
+        /* Take shortcut on zero byte packets */
+        if (skb->len == 0) {
+                ret = 0;
+                goto err;
+        }
+
         /* Check that nothing bad happens */
-        if ((skb->len == 0) || (!self->connected)) {
-                IRDA_DEBUG(1, "%s(), No data, or not connected\n",
-                           __func__);
+        if (!self->connected) {
+                IRDA_WARNING("%s(), Not connected\n", __func__);
+                ret = -ENOTCONN;
                 goto err;
         }
 
         if (skb->len > self->max_seg_size) {
-                IRDA_DEBUG(1, "%s(), UData is too large for IrLAP!\n",
-                           __func__);
+                IRDA_ERROR("%s(), UData is too large for IrLAP!\n", __func__);
+                ret = -EMSGSIZE;
                 goto err;
         }
 
@@ -576,7 +584,7 @@ int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 
 err:
         dev_kfree_skb(skb);
-        return -1;
+        return ret;
 }
 EXPORT_SYMBOL(irttp_udata_request);
 
@@ -599,9 +607,15 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
         IRDA_DEBUG(2, "%s() : queue len = %d\n", __func__,
                    skb_queue_len(&self->tx_queue));
 
+        /* Take shortcut on zero byte packets */
+        if (skb->len == 0) {
+                ret = 0;
+                goto err;
+        }
+
         /* Check that nothing bad happens */
-        if ((skb->len == 0) || (!self->connected)) {
-                IRDA_WARNING("%s: No data, or not connected\n", __func__);
+        if (!self->connected) {
+                IRDA_WARNING("%s: Not connected\n", __func__);
                 ret = -ENOTCONN;
                 goto err;
         }
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index a22dac22705..70bd1d0774c 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -4,6 +4,7 @@
 menuconfig IP_VS
         tristate "IP virtual server support"
         depends on NET && INET && NETFILTER
+        depends on (NF_CONNTRACK || NF_CONNTRACK=n)
         ---help---
           IP Virtual Server support will let you build a high-performance
           virtual server based on cluster of two or more real servers. This
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 8920f2a8332..4e37c1cbe8b 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -567,7 +567,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                 goto out;
         }
 
-        if (args->nr_local > (u64)UINT_MAX) {
+        if (args->nr_local > UIO_MAXIOV) {
                 ret = -EMSGSIZE;
                 goto out;
         }
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index f71a73107ae..80df89d957b 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -115,9 +115,7 @@ EXPORT_SYMBOL_GPL(svc_seq_show);
  */
 struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt)
 {
-        struct rpc_iostats *new;
-        new = kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
-        return new;
+        return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(rpc_alloc_iostats);
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c82fe739fbd..ea2ff78dcf7 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -5,7 +5,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index d0c92dddb26..17cd0c04d13 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -44,6 +44,38 @@ rdev_freq_to_chan(struct cfg80211_registered_device *rdev,
         return chan;
 }
 
+static bool can_beacon_sec_chan(struct wiphy *wiphy,
+                                struct ieee80211_channel *chan,
+                                enum nl80211_channel_type channel_type)
+{
+        struct ieee80211_channel *sec_chan;
+        int diff;
+
+        switch (channel_type) {
+        case NL80211_CHAN_HT40PLUS:
+                diff = 20;
+                break;
+        case NL80211_CHAN_HT40MINUS:
+                diff = -20;
+                break;
+        default:
+                return false;
+        }
+
+        sec_chan = ieee80211_get_channel(wiphy, chan->center_freq + diff);
+        if (!sec_chan)
+                return false;
+
+        /* we'll need a DFS capability later */
+        if (sec_chan->flags & (IEEE80211_CHAN_DISABLED |
+                               IEEE80211_CHAN_PASSIVE_SCAN |
+                               IEEE80211_CHAN_NO_IBSS |
+                               IEEE80211_CHAN_RADAR))
+                return false;
+
+        return true;
+}
+
 int cfg80211_set_freq(struct cfg80211_registered_device *rdev,
                       struct wireless_dev *wdev, int freq,
                       enum nl80211_channel_type channel_type)
@@ -68,6 +100,28 @@ int cfg80211_set_freq(struct cfg80211_registered_device *rdev,
         if (!chan)
                 return -EINVAL;
 
+        /* Both channels should be able to initiate communication */
+        if (wdev && (wdev->iftype == NL80211_IFTYPE_ADHOC ||
+                     wdev->iftype == NL80211_IFTYPE_AP ||
+                     wdev->iftype == NL80211_IFTYPE_AP_VLAN ||
+                     wdev->iftype == NL80211_IFTYPE_MESH_POINT ||
+                     wdev->iftype == NL80211_IFTYPE_P2P_GO)) {
+                switch (channel_type) {
+                case NL80211_CHAN_HT40PLUS:
+                case NL80211_CHAN_HT40MINUS:
+                        if (!can_beacon_sec_chan(&rdev->wiphy, chan,
+                                                 channel_type)) {
+                                printk(KERN_DEBUG
+                                       "cfg80211: Secondary channel not "
+                                       "allowed to initiate communication\n");
+                                return -EINVAL;
+                        }
+                        break;
+                default:
+                        break;
+                }
+        }
+
         result = rdev->ops->set_channel(&rdev->wiphy,
                                         wdev ? wdev->netdev : NULL,
                                         chan, channel_type);
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index cdb6dc1f645..39580a5dc5d 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -5,7 +5,7 @@ use strict;
 ## Copyright (c) 1998 Michael Zucchi, All Rights Reserved        ##
 ## Copyright (C) 2000, 1  Tim Waugh <twaugh@redhat.com>          ##
 ## Copyright (C) 2001  Simon Huggins                             ##
-## Copyright (C) 2005-2009  Randy Dunlap                         ##
+## Copyright (C) 2005-2010  Randy Dunlap                         ##
 ##                                                               ##
 ## #define enhancements by Armin Kuster <akuster@mvista.com>     ##
 ## Copyright (c) 2000 MontaVista Software, Inc.                  ##
@@ -453,7 +453,7 @@ sub output_highlight {
     if ($output_mode eq "html" || $output_mode eq "xml") {
         $contents = local_unescape($contents);
         # convert data read & converted thru xml_escape() into &xyz; format:
-        $contents =~ s/\\\\\\/&/g;
+        $contents =~ s/\\\\\\/\&/g;
     }
 #   print STDERR "contents b4:$contents\n";
     eval $dohighlight;
@@ -770,7 +770,11 @@ sub output_struct_xml(%) {
     print $args{'type'} . " " . $args{'struct'} . " {\n";
     foreach $parameter (@{$args{'parameterlist'}}) {
         if ($parameter =~ /^#/) {
-            print "$parameter\n";
+            my $prm = $parameter;
+            # convert data read & converted thru xml_escape() into &xyz; format:
+            # This allows us to have #define macros interspersed in a struct.
+            $prm =~ s/\\\\\\/\&/g;
+            print "$prm\n";
             next;
         }
 
@@ -1701,6 +1705,8 @@ sub push_parameter($$$) {
         }
         }
 
+        $param = xml_escape($param);
+
         # strip spaces from $param so that it is one continous string
         # on @parameterlist;
         # this fixes a problem where check_sections() cannot find
diff --git a/sound/core/info.c b/sound/core/info.c
index b70564ed8b3..7077f601da5 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -23,7 +23,6 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <sound/core.h>
 #include <sound/minors.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 8bc7cb3db33..e82c1f97d99 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -22,7 +22,6 @@
 #include <linux/mm.h>
 #include <linux/file.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/pm_qos_params.h>
 #include <linux/uio.h>
diff --git a/sound/core/sound.c b/sound/core/sound.c
index 62a093efb45..66691fe437e 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -21,7 +21,6 @@
 
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/device.h>
 #include <linux/moduleparam.h>
diff --git a/sound/sound_core.c b/sound/sound_core.c
index c03bbaefdbc..5580aced873 100644
--- a/sound/sound_core.c
+++ b/sound/sound_core.c
@@ -104,7 +104,6 @@ module_exit(cleanup_soundcore);
 
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sound.h>