52 files changed, 1208 insertions, 467 deletions

diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
index ea5a827395dd..9cc4d685dde5 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/ftrace.txt
@@ -8,7 +8,7 @@ Copyright 2008 Red Hat Inc.
 Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
              John Kacur, and David Teigland.
 
-Written for: 2.6.27-rc1
+Written for: 2.6.28-rc2
 
 Introduction
 ------------
@@ -50,26 +50,26 @@ of ftrace. Here is a list of some of the key files:
 
  Note: all time values are in microseconds.
 
-  current_tracer : This is used to set or display the current tracer
+  current_tracer: This is used to set or display the current tracer
                 that is configured.
 
-  available_tracers : This holds the different types of tracers that
+  available_tracers: This holds the different types of tracers that
                 have been compiled into the kernel. The tracers
                 listed here can be configured by echoing their name
                 into current_tracer.
 
-  tracing_enabled : This sets or displays whether the current_tracer
+  tracing_enabled: This sets or displays whether the current_tracer
                 is activated and tracing or not. Echo 0 into this
                 file to disable the tracer or 1 to enable it.
 
-  trace : This file holds the output of the trace in a human readable
+  trace: This file holds the output of the trace in a human readable
                 format (described below).
 
-  latency_trace : This file shows the same trace but the information
+  latency_trace: This file shows the same trace but the information
                 is organized more to display possible latencies
                 in the system (described below).
 
-  trace_pipe : The output is the same as the "trace" file but this
+  trace_pipe: The output is the same as the "trace" file but this
                 file is meant to be streamed with live tracing.
                 Reads from this file will block until new data
                 is retrieved. Unlike the "trace" and "latency_trace"
@@ -82,11 +82,11 @@ of ftrace. Here is a list of some of the key files:
                 tracer is not adding more data, they will display
                 the same information every time they are read.
 
-  iter_ctrl : This file lets the user control the amount of data
+  iter_ctrl: This file lets the user control the amount of data
                 that is displayed in one of the above output
                 files.
 
-  trace_max_latency : Some of the tracers record the max latency.
+  trace_max_latency: Some of the tracers record the max latency.
                 For example, the time interrupts are disabled.
                 This time is saved in this file. The max trace
                 will also be stored, and displayed by either
@@ -94,29 +94,26 @@ of ftrace. Here is a list of some of the key files:
                 only be recorded if the latency is greater than
                 the value in this file. (in microseconds)
 
-  trace_entries : This sets or displays the number of trace
-                entries each CPU buffer can hold. The tracer buffers
-                are the same size for each CPU. The displayed number
-                is the size of the CPU buffer and not total size. The
+  trace_entries: This sets or displays the number of bytes each CPU
+                buffer can hold. The tracer buffers are the same size
+                for each CPU. The displayed number is the size of the
+                 CPU buffer and not total size of all buffers. The
                 trace buffers are allocated in pages (blocks of memory
                 that the kernel uses for allocation, usually 4 KB in size).
-                Since each entry is smaller than a page, if the last
-                allocated page has room for more entries than were
-                requested, the rest of the page is used to allocate
-                entries.
+                If the last page allocated has room for more bytes
+                than requested, the rest of the page will be used,
+                making the actual allocation bigger than requested.
+                (Note, the size may not be a multiple of the page size due
+                to buffer managment overhead.)
 
                 This can only be updated when the current_tracer
-                is set to "none".
+                is set to "nop".
 
-                NOTE: It is planned on changing the allocated buffers
-                      from being the number of possible CPUS to
-                      the number of online CPUS.
-
-  tracing_cpumask : This is a mask that lets the user only trace
+  tracing_cpumask: This is a mask that lets the user only trace
                 on specified CPUS. The format is a hex string
                 representing the CPUS.
 
-  set_ftrace_filter : When dynamic ftrace is configured in (see the
+  set_ftrace_filter: When dynamic ftrace is configured in (see the
                 section below "dynamic ftrace"), the code is dynamically
                 modified (code text rewrite) to disable calling of the
                 function profiler (mcount). This lets tracing be configured
@@ -130,14 +127,11 @@ of ftrace. Here is a list of some of the key files:
                 be traced. If a function exists in both set_ftrace_filter
                 and set_ftrace_notrace, the function will _not_ be traced.
 
-  available_filter_functions : When a function is encountered the first
-                time by the dynamic tracer, it is recorded and
-                later the call is converted into a nop. This file
-                lists the functions that have been recorded
-                by the dynamic tracer and these functions can
-                be used to set the ftrace filter by the above
-                "set_ftrace_filter" file. (See the section "dynamic ftrace"
-                below for more details).
+  available_filter_functions: This lists the functions that ftrace
+                has processed and can trace. These are the function
+                names that you can pass to "set_ftrace_filter" or
+                "set_ftrace_notrace". (See the section "dynamic ftrace"
+                below for more details.)
 
 
 The Tracers
@@ -145,7 +139,7 @@ The Tracers
 
 Here is the list of current tracers that may be configured.
 
-  ftrace - function tracer that uses mcount to trace all functions.
+  function - function tracer that uses mcount to trace all functions.
 
   sched_switch - traces the context switches between tasks.
 
@@ -166,8 +160,8 @@ Here is the list of current tracers that may be configured.
                 the highest priority task to get scheduled after
                 it has been woken up.
 
-  none - This is not a tracer. To remove all tracers from tracing
-                simply echo "none" into current_tracer.
+  nop - This is not a tracer. To remove all tracers from tracing
+                simply echo "nop" into current_tracer.
 
 
 Examples of using the tracer
@@ -182,7 +176,7 @@ Output format:
 Here is an example of the output format of the file "trace"
 
                              --------
-# tracer: ftrace
+# tracer: function
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
 #              | |      |          |         |
@@ -192,7 +186,7 @@ Here is an example of the output format of the file "trace"
                              --------
 
 A header is printed with the tracer name that is represented by the trace.
-In this case the tracer is "ftrace". Then a header showing the format. Task
+In this case the tracer is "function". Then a header showing the format. Task
 name "bash", the task PID "4251", the CPU that it was running on
 "01", the timestamp in <secs>.<usecs> format, the function name that was
 traced "path_put" and the parent function that called this function
@@ -1003,22 +997,20 @@ is the stack for the hard interrupt. This hides the fact that NEED_RESCHED
 has been set. We do not see the 'N' until we switch back to the task's
 assigned stack.
 
-ftrace
-------
+function
+--------
 
-ftrace is not only the name of the tracing infrastructure, but it
-is also a name of one of the tracers. The tracer is the function
-tracer. Enabling the function tracer can be done from the
-debug file system. Make sure the ftrace_enabled is set otherwise
-this tracer is a nop.
+This tracer is the function tracer. Enabling the function tracer
+can be done from the debug file system. Make sure the ftrace_enabled is
+set; otherwise this tracer is a nop.
 
  # sysctl kernel.ftrace_enabled=1
- # echo ftrace > /debug/tracing/current_tracer
+ # echo function > /debug/tracing/current_tracer
  # echo 1 > /debug/tracing/tracing_enabled
  # usleep 1
  # echo 0 > /debug/tracing/tracing_enabled
  # cat /debug/tracing/trace
-# tracer: ftrace
+# tracer: function
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
 #              | |      |          |         |
@@ -1040,10 +1032,10 @@ this tracer is a nop.
 [...]
 
 
-Note: ftrace uses ring buffers to store the above entries. The newest data
-may overwrite the oldest data. Sometimes using echo to stop the trace
-is not sufficient because the tracing could have overwritten the data
-that you wanted to record. For this reason, it is sometimes better to
+Note: function tracer uses ring buffers to store the above entries.
+The newest data may overwrite the oldest data. Sometimes using echo to
+stop the trace is not sufficient because the tracing could have overwritten
+the data that you wanted to record. For this reason, it is sometimes better to
 disable tracing directly from a program. This allows you to stop the
 tracing at the point that you hit the part that you are interested in.
 To disable the tracing directly from a C program, something like following
@@ -1077,18 +1069,31 @@ every kernel function, produced by the -pg switch in gcc), starts
 of pointing to a simple return. (Enabling FTRACE will include the
 -pg switch in the compiling of the kernel.)
 
-When dynamic ftrace is initialized, it calls kstop_machine to make
-the machine act like a uniprocessor so that it can freely modify code
-without worrying about other processors executing that same code.  At
-initialization, the mcount calls are changed to call a "record_ip"
-function.  After this, the first time a kernel function is called,
-it has the calling address saved in a hash table.
-
-Later on the ftraced kernel thread is awoken and will again call
-kstop_machine if new functions have been recorded. The ftraced thread
-will change all calls to mcount to "nop".  Just calling mcount
-and having mcount return has shown a 10% overhead. By converting
-it to a nop, there is no measurable overhead to the system.
+At compile time every C file object is run through the
+recordmcount.pl script (located in the scripts directory). This
+script will process the C object using objdump to find all the
+locations in the .text section that call mcount. (Note, only
+the .text section is processed, since processing other sections
+like .init.text may cause races due to those sections being freed).
+
+A new section called "__mcount_loc" is created that holds references
+to all the mcount call sites in the .text section. This section is
+compiled back into the original object. The final linker will add
+all these references into a single table.
+
+On boot up, before SMP is initialized, the dynamic ftrace code
+scans this table and updates all the locations into nops. It also
+records the locations, which are added to the available_filter_functions
+list.  Modules are processed as they are loaded and before they are
+executed.  When a module is unloaded, it also removes its functions from
+the ftrace function list. This is automatic in the module unload
+code, and the module author does not need to worry about it.
+
+When tracing is enabled, kstop_machine is called to prevent races
+with the CPUS executing code being modified (which can cause the
+CPU to do undesireable things), and the nops are patched back
+to calls. But this time, they do not call mcount (which is just
+a function stub). They now call into the ftrace infrastructure.
 
 One special side-effect to the recording of the functions being
 traced is that we can now selectively choose which functions we
@@ -1251,36 +1256,6 @@ Produces:
 
 We can see that there's no more lock or preempt tracing.
 
-ftraced
--------
-
-As mentioned above, when dynamic ftrace is configured in, a kernel
-thread wakes up once a second and checks to see if there are mcount
-calls that need to be converted into nops. If there are not any, then
-it simply goes back to sleep. But if there are some, it will call
-kstop_machine to convert the calls to nops.
-
-There may be a case in which you do not want this added latency.
-Perhaps you are doing some audio recording and this activity might
-cause skips in the playback. There is an interface to disable
-and enable the "ftraced" kernel thread.
-
- # echo 0 > /debug/tracing/ftraced_enabled
-
-This will disable the calling of kstop_machine to update the
-mcount calls to nops. Remember that there is a large overhead
-to calling mcount. Without this kernel thread, that overhead will
-exist.
-
-If there are recorded calls to mcount, any write to the ftraced_enabled
-file will cause the kstop_machine to run. This means that a
-user can manually perform the updates when they want to by simply
-echoing a '0' into the ftraced_enabled file.
-
-The updates are also done at the beginning of enabling a tracer
-that uses ftrace function recording.
-
-
 trace_pipe
 ----------
 
@@ -1289,14 +1264,14 @@ on the tracing is different. Every read from trace_pipe is consumed.
 This means that subsequent reads will be different. The trace
 is live.
 
- # echo ftrace > /debug/tracing/current_tracer
+ # echo function > /debug/tracing/current_tracer
  # cat /debug/tracing/trace_pipe > /tmp/trace.out &
 [1] 4153
  # echo 1 > /debug/tracing/tracing_enabled
  # usleep 1
  # echo 0 > /debug/tracing/tracing_enabled
  # cat /debug/tracing/trace
-# tracer: ftrace
+# tracer: function
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
 #              | |      |          |         |
@@ -1317,7 +1292,7 @@ is live.
 
 Note, reading the trace_pipe file will block until more input is added.
 By changing the tracer, trace_pipe will issue an EOF. We needed
-to set the ftrace tracer _before_ cating the trace_pipe file.
+to set the function tracer _before_ we "cat" the trace_pipe file.
 
 
 trace entries
@@ -1334,10 +1309,10 @@ number of entries.
 65620
 
 Note, to modify this, you must have tracing completely disabled. To do that,
-echo "none" into the current_tracer. If the current_tracer is not set
-to "none", an EINVAL error will be returned.
+echo "nop" into the current_tracer. If the current_tracer is not set
+to "nop", an EINVAL error will be returned.
 
- # echo none > /debug/tracing/current_tracer
+ # echo nop > /debug/tracing/current_tracer
  # echo 100000 > /debug/tracing/trace_entries
  # cat /debug/tracing/trace_entries
 100045
diff --git a/Documentation/io-mapping.txt b/Documentation/io-mapping.txt
new file mode 100644
index 000000000000..473e43b2d588
--- /dev/null
+++ b/Documentation/io-mapping.txt
@@ -0,0 +1,82 @@
+The io_mapping functions in linux/io-mapping.h provide an abstraction for
+efficiently mapping small regions of an I/O device to the CPU. The initial
+usage is to support the large graphics aperture on 32-bit processors where
+ioremap_wc cannot be used to statically map the entire aperture to the CPU
+as it would consume too much of the kernel address space.
+
+A mapping object is created during driver initialization using
+
+        struct io_mapping *io_mapping_create_wc(unsigned long base,
+                                                unsigned long size)
+
+                'base' is the bus address of the region to be made
+                mappable, while 'size' indicates how large a mapping region to
+                enable. Both are in bytes.
+
+                This _wc variant provides a mapping which may only be used
+                with the io_mapping_map_atomic_wc or io_mapping_map_wc.
+
+With this mapping object, individual pages can be mapped either atomically
+or not, depending on the necessary scheduling environment. Of course, atomic
+maps are more efficient:
+
+        void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
+                                       unsigned long offset)
+
+                'offset' is the offset within the defined mapping region.
+                Accessing addresses beyond the region specified in the
+                creation function yields undefined results. Using an offset
+                which is not page aligned yields an undefined result. The
+                return value points to a single page in CPU address space.
+
+                This _wc variant returns a write-combining map to the
+                page and may only be used with mappings created by
+                io_mapping_create_wc
+
+                Note that the task may not sleep while holding this page
+                mapped.
+
+        void io_mapping_unmap_atomic(void *vaddr)
+
+                'vaddr' must be the the value returned by the last
+                io_mapping_map_atomic_wc call. This unmaps the specified
+                page and allows the task to sleep once again.
+
+If you need to sleep while holding the lock, you can use the non-atomic
+variant, although they may be significantly slower.
+
+        void *io_mapping_map_wc(struct io_mapping *mapping,
+                                unsigned long offset)
+
+                This works like io_mapping_map_atomic_wc except it allows
+                the task to sleep while holding the page mapped.
+
+        void io_mapping_unmap(void *vaddr)
+
+                This works like io_mapping_unmap_atomic, except it is used
+                for pages mapped with io_mapping_map_wc.
+
+At driver close time, the io_mapping object must be freed:
+
+        void io_mapping_free(struct io_mapping *mapping)
+
+Current Implementation:
+
+The initial implementation of these functions uses existing mapping
+mechanisms and so provides only an abstraction layer and no new
+functionality.
+
+On 64-bit processors, io_mapping_create_wc calls ioremap_wc for the whole
+range, creating a permanent kernel-visible mapping to the resource. The
+map_atomic and map functions add the requested offset to the base of the
+virtual address returned by ioremap_wc.
+
+On 32-bit processors with HIGHMEM defined, io_mapping_map_atomic_wc uses
+kmap_atomic_pfn to map the specified page in an atomic fashion;
+kmap_atomic_pfn isn't really supposed to be used with device pages, but it
+provides an efficient mapping for this usage.
+
+On 32-bit processors without HIGHMEM defined, io_mapping_map_atomic_wc and
+io_mapping_map_wc both use ioremap_wc, a terribly inefficient function which
+performs an IPI to inform all processors about the new mapping. This results
+in a significant performance penalty.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6f20718d3156..d03e91762f61 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
         select HAVE_FTRACE_MCOUNT_RECORD
         select HAVE_DYNAMIC_FTRACE
         select HAVE_FUNCTION_TRACER
+        select HAVE_FUNCTION_TRACE_MCOUNT_TEST
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
         select HAVE_ARCH_TRACEHOOK
@@ -1894,6 +1895,10 @@ config SYSVIPC_COMPAT
 endmenu
 
 
+config HAVE_ATOMIC_IOMAP
+        def_bool y
+        depends on X86_32
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 8668a94f850e..23696d44a0af 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -9,6 +9,10 @@
 
 extern int fixmaps_set;
 
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
 void native_set_fixmap(enum fixed_addresses idx,
                        unsigned long phys, pgprot_t flags);
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
index 09f29ab5c139..c7115c1d7217 100644
--- a/arch/x86/include/asm/fixmap_32.h
+++ b/arch/x86/include/asm/fixmap_32.h
@@ -28,10 +28,8 @@ extern unsigned long __FIXADDR_TOP;
 #include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
-#endif
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -75,10 +73,8 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_CYCLONE_TIMER
         FIX_CYCLONE_TIMER, /*cyclone timer register*/
 #endif
-#ifdef CONFIG_HIGHMEM
         FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
         FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
 #ifdef CONFIG_PCI_MMCONFIG
         FIX_PCIE_MCFG,
 #endif
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index a3b3b7c3027b..bf9276bea660 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -25,14 +25,11 @@
 #include <asm/kmap_types.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
+#include <asm/fixmap.h>
 
 /* declarations for highmem.c */
 extern unsigned long highstart_pfn, highend_pfn;
 
-extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
-extern pte_t *pkmap_page_table;
-
 /*
  * Right now we initialize only a single pte table. It can be extended
  * easily, subsequent pte tables have to be allocated in one physical
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 28b597ef9ca1..9134de814c97 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1157,6 +1157,9 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+        cmpl $0, function_trace_stop
+        jne  ftrace_stub
+
         pushl %eax
         pushl %ecx
         pushl %edx
@@ -1180,6 +1183,9 @@ END(ftrace_caller)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
+        cmpl $0, function_trace_stop
+        jne  ftrace_stub
+
         cmpl $ftrace_stub, ftrace_trace_function
         jnz trace
 .globl ftrace_stub
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b86f332c96a6..08aa6b10933c 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -68,6 +68,8 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+        cmpl $0, function_trace_stop
+        jne  ftrace_stub
 
         /* taken from glibc */
         subq $0x38, %rsp
@@ -103,6 +105,9 @@ END(ftrace_caller)
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
+        cmpl $0, function_trace_stop
+        jne  ftrace_stub
+
         cmpq $ftrace_stub, ftrace_trace_function
         jnz trace
 .globl ftrace_stub
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 0a21b7aab9dc..d8cc96a2738f 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
             pat.o pgtable.o gup.o
 
-obj-$(CONFIG_X86_32)            += pgtable_32.o
+obj-$(CONFIG_X86_32)            += pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP)        += dump_pagetables.o
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c5..c483f4242079 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -334,7 +334,6 @@ int devmem_is_allowed(unsigned long pagenr)
         return 0;
 }
 
-#ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 pgprot_t kmap_prot;
 
@@ -357,6 +356,7 @@ static void __init kmap_init(void)
         kmap_prot = PAGE_KERNEL;
 }
 
+#ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
         unsigned long vaddr;
@@ -436,7 +436,6 @@ static void __init set_highmem_pages_init(void)
 #endif /* !CONFIG_NUMA */
 
 #else
-# define kmap_init()                            do { } while (0)
 # define permanent_kmaps_init(pgd_base)         do { } while (0)
 # define set_highmem_pages_init()       do { } while (0)
 #endif /* CONFIG_HIGHMEM */
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 000000000000..d0151d8ce452
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+        enum fixed_addresses idx;
+        unsigned long vaddr;
+
+        pagefault_disable();
+
+        idx = type + KM_TYPE_NR*smp_processor_id();
+        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+        set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+        arch_flush_lazy_mmu_mode();
+
+        return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+        unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+        enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+        /*
+         * Force other mappings to Oops if they'll try to access this pte
+         * without first remap it.  Keeping stale mappings around is a bad idea
+         * also, in case the page changes cacheability attributes or becomes
+         * a protected page in a hypervisor.
+         */
+        if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+                kpte_clear_flush(kmap_pte-idx, vaddr);
+
+        arch_flush_lazy_mmu_mode();
+        pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index ce0d9da52a8a..94966edfb44d 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -274,6 +274,22 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = {
         .enable_mask    = SYSRQ_ENABLE_DUMP,
 };
 
+#ifdef CONFIG_TRACING
+#include <linux/ftrace.h>
+
+static void sysrq_ftrace_dump(int key, struct tty_struct *tty)
+{
+        ftrace_dump();
+}
+static struct sysrq_key_op sysrq_ftrace_dump_op = {
+        .handler        = sysrq_ftrace_dump,
+        .help_msg       = "dumpZ-ftrace-buffer",
+        .action_msg     = "Dump ftrace buffer",
+        .enable_mask    = SYSRQ_ENABLE_DUMP,
+};
+#else
+#define sysrq_ftrace_dump_op (*(struct sysrq_key_op *)0)
+#endif
 
 static void sysrq_handle_showmem(int key, struct tty_struct *tty)
 {
@@ -406,7 +422,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
         NULL,                           /* x */
         /* y: May be registered on sparc64 for global register dump */
         NULL,                           /* y */
-        NULL                            /* z */
+        &sysrq_ftrace_dump_op,          /* z */
 };
 
 /* key2index calculation, -1 on invalid index */
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 5ba78e4fd2b5..d8fb5d8ee7ea 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -3,13 +3,14 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 ccflags-y := -Iinclude/drm
-i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o i915_opregion.o \
+i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o \
           i915_suspend.o \
           i915_gem.o \
           i915_gem_debug.o \
           i915_gem_proc.o \
           i915_gem_tiling.o
 
+i915-$(CONFIG_ACPI)     += i915_opregion.o
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o
 
 obj-$(CONFIG_DRM_I915)  += i915.o
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 01de536e0211..256e22963ae4 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -960,6 +960,7 @@ struct drm_ioctl_desc i915_ioctls[] = {
         DRM_IOCTL_DEF(DRM_I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, 0),
         DRM_IOCTL_DEF(DRM_I915_GEM_SET_TILING, i915_gem_set_tiling, 0),
         DRM_IOCTL_DEF(DRM_I915_GEM_GET_TILING, i915_gem_get_tiling, 0),
+        DRM_IOCTL_DEF(DRM_I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, 0),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f20ffe17df71..572dcd0e3e0d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -31,6 +31,7 @@
 #define _I915_DRV_H_
 
 #include "i915_reg.h"
+#include <linux/io-mapping.h>
 
 /* General customization:
  */
@@ -246,6 +247,8 @@ typedef struct drm_i915_private {
         struct {
                 struct drm_mm gtt_space;
 
+                struct io_mapping *gtt_mapping;
+
                 /**
                  * List of objects currently involved in rendering from the
                  * ringbuffer.
@@ -502,6 +505,8 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data,
                         struct drm_file *file_priv);
 int i915_gem_get_tiling(struct drm_device *dev, void *data,
                         struct drm_file *file_priv);
+int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
+                                struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
 int i915_gem_proc_init(struct drm_minor *minor);
 void i915_gem_proc_cleanup(struct drm_minor *minor);
@@ -539,11 +544,18 @@ extern int i915_restore_state(struct drm_device *dev);
 extern int i915_save_state(struct drm_device *dev);
 extern int i915_restore_state(struct drm_device *dev);
 
+#ifdef CONFIG_ACPI
 /* i915_opregion.c */
 extern int intel_opregion_init(struct drm_device *dev);
 extern void intel_opregion_free(struct drm_device *dev);
 extern void opregion_asle_intr(struct drm_device *dev);
 extern void opregion_enable_asle(struct drm_device *dev);
+#else
+static inline int intel_opregion_init(struct drm_device *dev) { return 0; }
+static inline void intel_opregion_free(struct drm_device *dev) { return; }
+static inline void opregion_asle_intr(struct drm_device *dev) { return; }
+static inline void opregion_enable_asle(struct drm_device *dev) { return; }
+#endif
 
 /**
  * Lock test for when it's just for synchronization of ring access.
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 17ae330ff269..b0ec73fa6a93 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -79,6 +79,28 @@ i915_gem_init_ioctl(struct drm_device *dev, void *data,
         return 0;
 }
 
+int
+i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
+                            struct drm_file *file_priv)
+{
+        drm_i915_private_t *dev_priv = dev->dev_private;
+        struct drm_i915_gem_get_aperture *args = data;
+        struct drm_i915_gem_object *obj_priv;
+
+        if (!(dev->driver->driver_features & DRIVER_GEM))
+                return -ENODEV;
+
+        args->aper_size = dev->gtt_total;
+        args->aper_available_size = args->aper_size;
+
+        list_for_each_entry(obj_priv, &dev_priv->mm.active_list, list) {
+                if (obj_priv->pin_count > 0)
+                        args->aper_available_size -= obj_priv->obj->size;
+        }
+
+        return 0;
+}
+
 
 /**
  * Creates a new mm object and returns a handle to it.
@@ -171,35 +193,50 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
         return 0;
 }
 
-/*
- * Try to write quickly with an atomic kmap. Return true on success.
- *
- * If this fails (which includes a partial write), we'll redo the whole
- * thing with the slow version.
- *
- * This is a workaround for the low performance of iounmap (approximate
- * 10% cpu cost on normal 3D workloads).  kmap_atomic on HIGHMEM kernels
- * happens to let us map card memory without taking IPIs.  When the vmap
- * rework lands we should be able to dump this hack.
+/* This is the fast write path which cannot handle
+ * page faults in the source data
  */
-static inline int fast_user_write(unsigned long pfn, char __user *user_data,
-                                  int l, int o)
+
+static inline int
+fast_user_write(struct io_mapping *mapping,
+                loff_t page_base, int page_offset,
+                char __user *user_data,
+                int length)
 {
-#ifdef CONFIG_HIGHMEM
-        unsigned long unwritten;
         char *vaddr_atomic;
+        unsigned long unwritten;
 
-        vaddr_atomic = kmap_atomic_pfn(pfn, KM_USER0);
-#if WATCH_PWRITE
-        DRM_INFO("pwrite i %d o %d l %d pfn %ld vaddr %p\n",
-                 i, o, l, pfn, vaddr_atomic);
-#endif
-        unwritten = __copy_from_user_inatomic_nocache(vaddr_atomic + o, user_data, l);
-        kunmap_atomic(vaddr_atomic, KM_USER0);
-        return !unwritten;
-#else
+        vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base);
+        unwritten = __copy_from_user_inatomic_nocache(vaddr_atomic + page_offset,
+                                                      user_data, length);
+        io_mapping_unmap_atomic(vaddr_atomic);
+        if (unwritten)
+                return -EFAULT;
+        return 0;
+}
+
+/* Here's the write path which can sleep for
+ * page faults
+ */
+
+static inline int
+slow_user_write(struct io_mapping *mapping,
+                loff_t page_base, int page_offset,
+                char __user *user_data,
+                int length)
+{
+        char __iomem *vaddr;
+        unsigned long unwritten;
+
+        vaddr = io_mapping_map_wc(mapping, page_base);
+        if (vaddr == NULL)
+                return -EFAULT;
+        unwritten = __copy_from_user(vaddr + page_offset,
+                                     user_data, length);
+        io_mapping_unmap(vaddr);
+        if (unwritten)
+                return -EFAULT;
         return 0;
-#endif
 }
 
 static int
@@ -208,10 +245,12 @@ i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
                     struct drm_file *file_priv)
 {
         struct drm_i915_gem_object *obj_priv = obj->driver_private;
+        drm_i915_private_t *dev_priv = dev->dev_private;
         ssize_t remain;
-        loff_t offset;
+        loff_t offset, page_base;
         char __user *user_data;
-        int ret = 0;
+        int page_offset, page_length;
+        int ret;
 
         user_data = (char __user *) (uintptr_t) args->data_ptr;
         remain = args->size;
@@ -235,57 +274,37 @@ i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
         obj_priv->dirty = 1;
 
         while (remain > 0) {
-                unsigned long pfn;
-                int i, o, l;
-
                 /* Operation in this page
                  *
-                 * i = page number
-                 * o = offset within page
-                 * l = bytes to copy
+                 * page_base = page offset within aperture
+                 * page_offset = offset within page
+                 * page_length = bytes to copy for this page
                  */
-                i = offset >> PAGE_SHIFT;
-                o = offset & (PAGE_SIZE-1);
-                l = remain;
-                if ((o + l) > PAGE_SIZE)
-                        l = PAGE_SIZE - o;
-
-                pfn = (dev->agp->base >> PAGE_SHIFT) + i;
-
-                if (!fast_user_write(pfn, user_data, l, o)) {
-                        unsigned long unwritten;
-                        char __iomem *vaddr;
-
-                        vaddr = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE);
-#if WATCH_PWRITE
-                        DRM_INFO("pwrite slow i %d o %d l %d "
-                                 "pfn %ld vaddr %p\n",
-                                 i, o, l, pfn, vaddr);
-#endif
-                        if (vaddr == NULL) {
-                                ret = -EFAULT;
-                                goto fail;
-                        }
-                        unwritten = __copy_from_user(vaddr + o, user_data, l);
-#if WATCH_PWRITE
-                        DRM_INFO("unwritten %ld\n", unwritten);
-#endif
-                        iounmap(vaddr);
-                        if (unwritten) {
-                                ret = -EFAULT;
+                page_base = (offset & ~(PAGE_SIZE-1));
+                page_offset = offset & (PAGE_SIZE-1);
+                page_length = remain;
+                if ((page_offset + remain) > PAGE_SIZE)
+                        page_length = PAGE_SIZE - page_offset;
+
+                ret = fast_user_write (dev_priv->mm.gtt_mapping, page_base,
+                                       page_offset, user_data, page_length);
+
+                /* If we get a fault while copying data, then (presumably) our
+                 * source page isn't available. In this case, use the
+                 * non-atomic function
+                 */
+                if (ret) {
+                        ret = slow_user_write (dev_priv->mm.gtt_mapping,
+                                               page_base, page_offset,
+                                               user_data, page_length);
+                        if (ret)
                                 goto fail;
-                        }
                 }
 
-                remain -= l;
-                user_data += l;
-                offset += l;
+                remain -= page_length;
+                user_data += page_length;
+                offset += page_length;
         }
-#if WATCH_PWRITE && 1
-        i915_gem_clflush_object(obj);
-        i915_gem_dump_object(obj, args->offset + args->size, __func__, ~0);
-        i915_gem_clflush_object(obj);
-#endif
 
 fail:
         i915_gem_object_unpin(obj);
@@ -1503,12 +1522,12 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
                                  struct drm_i915_gem_exec_object *entry)
 {
         struct drm_device *dev = obj->dev;
+        drm_i915_private_t *dev_priv = dev->dev_private;
         struct drm_i915_gem_relocation_entry reloc;
         struct drm_i915_gem_relocation_entry __user *relocs;
         struct drm_i915_gem_object *obj_priv = obj->driver_private;
         int i, ret;
-        uint32_t last_reloc_offset = -1;
-        void __iomem *reloc_page = NULL;
+        void __iomem *reloc_page;
 
         /* Choose the GTT offset for our buffer and put it there. */
         ret = i915_gem_object_pin(obj, (uint32_t) entry->alignment);
@@ -1631,26 +1650,11 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
                  * perform.
                  */
                 reloc_offset = obj_priv->gtt_offset + reloc.offset;
-                if (reloc_page == NULL ||
-                    (last_reloc_offset & ~(PAGE_SIZE - 1)) !=
-                    (reloc_offset & ~(PAGE_SIZE - 1))) {
-                        if (reloc_page != NULL)
-                                iounmap(reloc_page);
-
-                        reloc_page = ioremap_wc(dev->agp->base +
-                                                (reloc_offset &
-                                                 ~(PAGE_SIZE - 1)),
-                                                PAGE_SIZE);
-                        last_reloc_offset = reloc_offset;
-                        if (reloc_page == NULL) {
-                                drm_gem_object_unreference(target_obj);
-                                i915_gem_object_unpin(obj);
-                                return -ENOMEM;
-                        }
-                }
-
+                reloc_page = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping,
+                                                      (reloc_offset &
+                                                       ~(PAGE_SIZE - 1)));
                 reloc_entry = (uint32_t __iomem *)(reloc_page +
-                                           (reloc_offset & (PAGE_SIZE - 1)));
+                                                   (reloc_offset & (PAGE_SIZE - 1)));
                 reloc_val = target_obj_priv->gtt_offset + reloc.delta;
 
 #if WATCH_BUF
@@ -1659,6 +1663,7 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
                           readl(reloc_entry), reloc_val);
 #endif
                 writel(reloc_val, reloc_entry);
+                io_mapping_unmap_atomic(reloc_page);
 
                 /* Write the updated presumed offset for this entry back out
                  * to the user.
@@ -1674,9 +1679,6 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
                 drm_gem_object_unreference(target_obj);
         }
 
-        if (reloc_page != NULL)
-                iounmap(reloc_page);
-
 #if WATCH_BUF
         if (0)
                 i915_gem_dump_object(obj, 128, __func__, ~0);
@@ -2518,6 +2520,10 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
         if (ret != 0)
                 return ret;
 
+        dev_priv->mm.gtt_mapping = io_mapping_create_wc(dev->agp->base,
+                                                        dev->agp->agp_info.aper_size
+                                                        * 1024 * 1024);
+
         mutex_lock(&dev->struct_mutex);
         BUG_ON(!list_empty(&dev_priv->mm.active_list));
         BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
@@ -2535,11 +2541,13 @@ int
 i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
                        struct drm_file *file_priv)
 {
+        drm_i915_private_t *dev_priv = dev->dev_private;
         int ret;
 
         ret = i915_gem_idle(dev);
         drm_irq_uninstall(dev);
 
+        io_mapping_free(dev_priv->mm.gtt_mapping);
         return ret;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index 59a2132a8f57..073894824e6b 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -653,15 +653,16 @@ static void radeon_cp_init_ring_buffer(struct drm_device * dev,
         RADEON_WRITE(RADEON_SCRATCH_UMSK, 0x7);
 
         /* Turn on bus mastering */
-        if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS400) ||
-            ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+        if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
             ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740)) {
-                /* rs400, rs690/rs740 */
-                tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RS400_BUS_MASTER_DIS;
+                /* rs600/rs690/rs740 */
+                tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RS600_BUS_MASTER_DIS;
                 RADEON_WRITE(RADEON_BUS_CNTL, tmp);
-        } else if (!(((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV380) ||
-                    ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_R423))) {
-                /* r1xx, r2xx, r300, r(v)350, r420/r481, rs480 */
+        } else if (((dev_priv->flags & RADEON_FAMILY_MASK) <= CHIP_RV350) ||
+                   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_R420) ||
+                   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS400) ||
+                   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS480)) {
+                /* r1xx, r2xx, r300, r(v)350, r420/r481, rs400/rs480 */
                 tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
                 RADEON_WRITE(RADEON_BUS_CNTL, tmp);
         } /* PCIE cards appears to not need this */
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 4dbb813910c3..02f5575ba395 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -447,12 +447,12 @@ extern int r300_do_cp_cmdbuf(struct drm_device *dev,
  * handling, not bus mastering itself.
  */
 #define RADEON_BUS_CNTL                 0x0030
-/* r1xx, r2xx, r300, r(v)350, r420/r481, rs480 */
+/* r1xx, r2xx, r300, r(v)350, r420/r481, rs400/rs480 */
 #       define RADEON_BUS_MASTER_DIS            (1 << 6)
-/* rs400, rs690/rs740 */
-#       define RS400_BUS_MASTER_DIS             (1 << 14)
-#       define RS400_MSI_REARM                  (1 << 20)
-/* see RS480_MSI_REARM in AIC_CNTL for rs480 */
+/* rs600/rs690/rs740 */
+#       define RS600_BUS_MASTER_DIS             (1 << 14)
+#       define RS600_MSI_REARM                  (1 << 20)
+/* see RS400_MSI_REARM in AIC_CNTL for rs480 */
 
 #define RADEON_BUS_CNTL1                0x0034
 #       define RADEON_PMI_BM_DIS                (1 << 2)
@@ -937,7 +937,7 @@ extern int r300_do_cp_cmdbuf(struct drm_device *dev,
 
 #define RADEON_AIC_CNTL                 0x01d0
 #       define RADEON_PCIGART_TRANSLATE_EN      (1 << 0)
-#       define RS480_MSI_REARM                  (1 << 3)
+#       define RS400_MSI_REARM                  (1 << 3)
 #define RADEON_AIC_STAT                 0x01d4
 #define RADEON_AIC_PT_BASE              0x01d8
 #define RADEON_AIC_LO_ADDR              0x01dc
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 0c10a0b3f146..df26aa88fa47 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -1,43 +1,45 @@
-#include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
-#include <linux/seq_file.h>
 #include <linux/time.h>
 #include <asm/cputime.h>
 
-static int uptime_proc_show(struct seq_file *m, void *v)
+static int proc_calc_metrics(char *page, char **start, off_t off,
+                                 int count, int *eof, int len)
+{
+        if (len <= off + count)
+                *eof = 1;
+        *start = page + off;
+        len -= off;
+        if (len > count)
+                len = count;
+        if (len < 0)
+                len = 0;
+        return len;
+}
+
+static int uptime_read_proc(char *page, char **start, off_t off, int count,
+                            int *eof, void *data)
 {
         struct timespec uptime;
         struct timespec idle;
+        int len;
         cputime_t idletime = cputime_add(init_task.utime, init_task.stime);
 
         do_posix_clock_monotonic_gettime(&uptime);
         monotonic_to_bootbased(&uptime);
         cputime_to_timespec(idletime, &idle);
-        seq_printf(m, "%lu.%02lu %lu.%02lu\n",
+        len = sprintf(page, "%lu.%02lu %lu.%02lu\n",
                         (unsigned long) uptime.tv_sec,
                         (uptime.tv_nsec / (NSEC_PER_SEC / 100)),
                         (unsigned long) idle.tv_sec,
                         (idle.tv_nsec / (NSEC_PER_SEC / 100)));
-        return 0;
+        return proc_calc_metrics(page, start, off, count, eof, len);
 }
 
-static int uptime_proc_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, uptime_proc_show, NULL);
-}
-
-static const struct file_operations uptime_proc_fops = {
-        .open           = uptime_proc_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
 static int __init proc_uptime_init(void)
 {
-        proc_create("uptime", 0, NULL, &uptime_proc_fops);
+        create_proc_read_entry("uptime", 0, NULL, uptime_read_proc, NULL);
         return 0;
 }
 module_init(proc_uptime_init);
diff --git a/include/asm-x86/iomap.h b/include/asm-x86/iomap.h
new file mode 100644
index 000000000000..c1f06289b14b
--- /dev/null
+++ b/include/asm-x86/iomap.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type);
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index eb4b35031a55..152b34da927c 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -159,6 +159,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_SW_FINISH  0x20
 #define DRM_I915_GEM_SET_TILING 0x21
 #define DRM_I915_GEM_GET_TILING 0x22
+#define DRM_I915_GEM_GET_APERTURE 0x23
 
 #define DRM_IOCTL_I915_INIT             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH            DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -190,6 +191,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_SW_FINISH    DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
 #define DRM_IOCTL_I915_GEM_SET_TILING   DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
 #define DRM_IOCTL_I915_GEM_GET_TILING   DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
+#define DRM_IOCTL_I915_GEM_GET_APERTURE DRM_IOR  (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -600,4 +602,15 @@ struct drm_i915_gem_get_tiling {
         uint32_t swizzle_mode;
 };
 
+struct drm_i915_gem_get_aperture {
+        /** Total size of the aperture used by i915_gem_execbuffer, in bytes */
+        uint64_t aper_size;
+
+        /**
+         * Available space in the aperture used by i915_gem_execbuffer, in
+         * bytes
+         */
+        uint64_t aper_available_size;
+};
+
 #endif                          /* _I915_DRM_H_ */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1b340e3fa249..1f5608c11023 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -23,6 +23,34 @@ struct ftrace_ops {
         struct ftrace_ops *next;
 };
 
+extern int function_trace_stop;
+
+/**
+ * ftrace_stop - stop function tracer.
+ *
+ * A quick way to stop the function tracer. Note this an on off switch,
+ * it is not something that is recursive like preempt_disable.
+ * This does not disable the calling of mcount, it only stops the
+ * calling of functions from mcount.
+ */
+static inline void ftrace_stop(void)
+{
+        function_trace_stop = 1;
+}
+
+/**
+ * ftrace_start - start the function tracer.
+ *
+ * This function is the inverse of ftrace_stop. This does not enable
+ * the function tracing if the function tracer is disabled. This only
+ * sets the function tracer flag to continue calling the functions
+ * from mcount.
+ */
+static inline void ftrace_start(void)
+{
+        function_trace_stop = 0;
+}
+
 /*
  * The ftrace_ops must be a static and should also
  * be read_mostly.  These functions do modify read_mostly variables
@@ -41,6 +69,8 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
 static inline void ftrace_kill(void) { }
+static inline void ftrace_stop(void) { }
+static inline void ftrace_start(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -184,6 +214,9 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern int ftrace_dump_on_oops;
 
+extern void tracing_start(void);
+extern void tracing_stop(void);
+
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
 
@@ -214,6 +247,8 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 static inline int
 ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
 
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
 static inline int
 ftrace_printk(const char *fmt, ...)
 {
@@ -232,6 +267,11 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 #endif
 
 
+/*
+ * Structure which defines the trace of an initcall.
+ * You don't have to fill the func field since it is
+ * only used internally by the tracer.
+ */
 struct boot_trace {
         pid_t                   caller;
         char                    func[KSYM_NAME_LEN];
@@ -242,13 +282,28 @@ struct boot_trace {
 };
 
 #ifdef CONFIG_BOOT_TRACER
+/* Append the trace on the ring-buffer */
 extern void trace_boot(struct boot_trace *it, initcall_t fn);
+
+/* Tells the tracer that smp_pre_initcall is finished.
+ * So we can start the tracing
+ */
 extern void start_boot_trace(void);
-extern void stop_boot_trace(void);
+
+/* Resume the tracing of other necessary events
+ * such as sched switches
+ */
+extern void enable_boot_trace(void);
+
+/* Suspend this tracing. Actually, only sched_switches tracing have
+ * to be suspended. Initcalls doesn't need it.)
+ */
+extern void disable_boot_trace(void);
 #else
 static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
 static inline void start_boot_trace(void) { }
-static inline void stop_boot_trace(void) { }
+static inline void enable_boot_trace(void) { }
+static inline void disable_boot_trace(void) { }
 #endif
 
 
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
new file mode 100644
index 000000000000..82df31726a54
--- /dev/null
+++ b/include/linux/io-mapping.h
@@ -0,0 +1,125 @@
+/*
+ * Copyright © 2008 Keith Packard <keithp@keithp.com>
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef _LINUX_IO_MAPPING_H
+#define _LINUX_IO_MAPPING_H
+
+#include <linux/types.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/iomap.h>
+
+/*
+ * The io_mapping mechanism provides an abstraction for mapping
+ * individual pages from an io device to the CPU in an efficient fashion.
+ *
+ * See Documentation/io_mapping.txt
+ */
+
+/* this struct isn't actually defined anywhere */
+struct io_mapping;
+
+#ifdef CONFIG_HAVE_ATOMIC_IOMAP
+
+/*
+ * For small address space machines, mapping large objects
+ * into the kernel virtual space isn't practical. Where
+ * available, use fixmap support to dynamically map pages
+ * of the object at run time.
+ */
+
+static inline struct io_mapping *
+io_mapping_create_wc(unsigned long base, unsigned long size)
+{
+        return (struct io_mapping *) base;
+}
+
+static inline void
+io_mapping_free(struct io_mapping *mapping)
+{
+}
+
+/* Atomic map/unmap */
+static inline void *
+io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset)
+{
+        offset += (unsigned long) mapping;
+        return iomap_atomic_prot_pfn(offset >> PAGE_SHIFT, KM_USER0,
+                                     __pgprot(__PAGE_KERNEL_WC));
+}
+
+static inline void
+io_mapping_unmap_atomic(void *vaddr)
+{
+        iounmap_atomic(vaddr, KM_USER0);
+}
+
+static inline void *
+io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
+{
+        offset += (unsigned long) mapping;
+        return ioremap_wc(offset, PAGE_SIZE);
+}
+
+static inline void
+io_mapping_unmap(void *vaddr)
+{
+        iounmap(vaddr);
+}
+
+#else
+
+/* Create the io_mapping object*/
+static inline struct io_mapping *
+io_mapping_create_wc(unsigned long base, unsigned long size)
+{
+        return (struct io_mapping *) ioremap_wc(base, size);
+}
+
+static inline void
+io_mapping_free(struct io_mapping *mapping)
+{
+        iounmap(mapping);
+}
+
+/* Atomic map/unmap */
+static inline void *
+io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset)
+{
+        return ((char *) mapping) + offset;
+}
+
+static inline void
+io_mapping_unmap_atomic(void *vaddr)
+{
+}
+
+/* Non-atomic map/unmap */
+static inline void *
+io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
+{
+        return ((char *) mapping) + offset;
+}
+
+static inline void
+io_mapping_unmap(void *vaddr)
+{
+}
+
+#endif /* HAVE_ATOMIC_IOMAP */
+
+#endif /* _LINUX_IO_MAPPING_H */
diff --git a/init/main.c b/init/main.c
index 7e117a231af1..4b03cd5656ca 100644
--- a/init/main.c
+++ b/init/main.c
@@ -711,6 +711,7 @@ int do_one_initcall(initcall_t fn)
                 it.caller = task_pid_nr(current);
                 printk("calling  %pF @ %i\n", fn, it.caller);
                 it.calltime = ktime_get();
+                enable_boot_trace();
         }
 
         it.result = fn();
@@ -722,6 +723,7 @@ int do_one_initcall(initcall_t fn)
                 printk("initcall %pF returned %d after %Ld usecs\n", fn,
                         it.result, it.duration);
                 trace_boot(&it, fn);
+                disable_boot_trace();
         }
 
         msgbuf[0] = 0;
@@ -882,7 +884,7 @@ static int __init kernel_init(void * unused)
          * we're essentially up and running. Get rid of the
          * initmem segments and start the user-mode stuff..
          */
-        stop_boot_trace();
+
         init_post();
         return 0;
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6b6b727258b5..65d4a9ba79e4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -487,7 +487,7 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_TRACING
         {
                 .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "ftrace_dump_on_opps",
+                .procname       = "ftrace_dump_on_oops",
                 .data           = &ftrace_dump_on_oops,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 33dbefd471e8..fc4febc3334a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -9,6 +9,13 @@ config NOP_TRACER
 config HAVE_FUNCTION_TRACER
         bool
 
+config HAVE_FUNCTION_TRACE_MCOUNT_TEST
+        bool
+        help
+         This gets selected when the arch tests the function_trace_stop
+         variable at the mcount call site. Otherwise, this variable
+         is tested by the called function.
+
 config HAVE_DYNAMIC_FTRACE
         bool
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4a39d24568c8..896c71f0f4c4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -47,6 +47,9 @@
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
+/* Quick disabling of function tracer. */
+int function_trace_stop;
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -63,6 +66,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
 
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
@@ -88,8 +92,23 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 void clear_ftrace_function(void)
 {
         ftrace_trace_function = ftrace_stub;
+        __ftrace_trace_function = ftrace_stub;
 }
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+/*
+ * For those archs that do not test ftrace_trace_stop in their
+ * mcount call site, we need to do it from C.
+ */
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+{
+        if (function_trace_stop)
+                return;
+
+        __ftrace_trace_function(ip, parent_ip);
+}
+#endif
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
         /* should not be called from interrupt context */
@@ -110,10 +129,18 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
                  * For one func, simply call it directly.
                  * For more than one func, call the chain.
                  */
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
                 if (ops->next == &ftrace_list_end)
                         ftrace_trace_function = ops->func;
                 else
                         ftrace_trace_function = ftrace_list_func;
+#else
+                if (ops->next == &ftrace_list_end)
+                        __ftrace_trace_function = ops->func;
+                else
+                        __ftrace_trace_function = ftrace_list_func;
+                ftrace_trace_function = ftrace_test_stop_func;
+#endif
         }
 
         spin_unlock(&ftrace_lock);
@@ -526,7 +553,7 @@ static void ftrace_run_update_code(int command)
 }
 
 static ftrace_func_t saved_ftrace_func;
-static int ftrace_start;
+static int ftrace_start_up;
 static DEFINE_MUTEX(ftrace_start_lock);
 
 static void ftrace_startup(void)
@@ -537,8 +564,8 @@ static void ftrace_startup(void)
                 return;
 
         mutex_lock(&ftrace_start_lock);
-        ftrace_start++;
-        if (ftrace_start == 1)
+        ftrace_start_up++;
+        if (ftrace_start_up == 1)
                 command |= FTRACE_ENABLE_CALLS;
 
         if (saved_ftrace_func != ftrace_trace_function) {
@@ -562,8 +589,8 @@ static void ftrace_shutdown(void)
                 return;
 
         mutex_lock(&ftrace_start_lock);
-        ftrace_start--;
-        if (!ftrace_start)
+        ftrace_start_up--;
+        if (!ftrace_start_up)
                 command |= FTRACE_DISABLE_CALLS;
 
         if (saved_ftrace_func != ftrace_trace_function) {
@@ -589,8 +616,8 @@ static void ftrace_startup_sysctl(void)
         mutex_lock(&ftrace_start_lock);
         /* Force update next time */
         saved_ftrace_func = NULL;
-        /* ftrace_start is true if we want ftrace running */
-        if (ftrace_start)
+        /* ftrace_start_up is true if we want ftrace running */
+        if (ftrace_start_up)
                 command |= FTRACE_ENABLE_CALLS;
 
         ftrace_run_update_code(command);
@@ -605,8 +632,8 @@ static void ftrace_shutdown_sysctl(void)
                 return;
 
         mutex_lock(&ftrace_start_lock);
-        /* ftrace_start is true if ftrace is running */
-        if (ftrace_start)
+        /* ftrace_start_up is true if ftrace is running */
+        if (ftrace_start_up)
                 command |= FTRACE_DISABLE_CALLS;
 
         ftrace_run_update_code(command);
@@ -1186,7 +1213,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 
         mutex_lock(&ftrace_sysctl_lock);
         mutex_lock(&ftrace_start_lock);
-        if (iter->filtered && ftrace_start && ftrace_enabled)
+        if (iter->filtered && ftrace_start_up && ftrace_enabled)
                 ftrace_run_update_code(FTRACE_ENABLE_CALLS);
         mutex_unlock(&ftrace_start_lock);
         mutex_unlock(&ftrace_sysctl_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cedf4e268285..6781e9aab2c0 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -16,6 +16,8 @@
 #include <linux/list.h>
 #include <linux/fs.h>
 
+#include "trace.h"
+
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
@@ -152,7 +154,7 @@ static inline int test_time_stamp(u64 delta)
 struct ring_buffer_per_cpu {
         int                             cpu;
         struct ring_buffer              *buffer;
-        spinlock_t                      lock;
+        raw_spinlock_t                  lock;
         struct lock_class_key           lock_key;
         struct list_head                pages;
         struct buffer_page              *head_page;     /* read from head */
@@ -289,7 +291,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
         cpu_buffer->cpu = cpu;
         cpu_buffer->buffer = buffer;
-        spin_lock_init(&cpu_buffer->lock);
+        cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
         INIT_LIST_HEAD(&cpu_buffer->pages);
 
         page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
@@ -852,7 +854,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         if (write > BUF_PAGE_SIZE) {
                 struct buffer_page *next_page = tail_page;
 
-                spin_lock_irqsave(&cpu_buffer->lock, flags);
+                local_irq_save(flags);
+                __raw_spin_lock(&cpu_buffer->lock);
 
                 rb_inc_page(cpu_buffer, &next_page);
 
@@ -928,7 +931,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                         rb_set_commit_to_write(cpu_buffer);
                 }
 
-                spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+                __raw_spin_unlock(&cpu_buffer->lock);
+                local_irq_restore(flags);
 
                 /* fail and let the caller try again */
                 return ERR_PTR(-EAGAIN);
@@ -951,7 +955,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         return event;
 
  out_unlock:
-        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+        __raw_spin_unlock(&cpu_buffer->lock);
+        local_irq_restore(flags);
         return NULL;
 }
 
@@ -1022,8 +1027,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
         struct ring_buffer_event *event;
         u64 ts, delta;
         int commit = 0;
+        int nr_loops = 0;
 
  again:
+        /*
+         * We allow for interrupts to reenter here and do a trace.
+         * If one does, it will cause this original code to loop
+         * back here. Even with heavy interrupts happening, this
+         * should only happen a few times in a row. If this happens
+         * 1000 times in a row, there must be either an interrupt
+         * storm or we have something buggy.
+         * Bail!
+         */
+        if (unlikely(++nr_loops > 1000)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
         ts = ring_buffer_time_stamp(cpu_buffer->cpu);
 
         /*
@@ -1122,8 +1142,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
                 return NULL;
 
         /* If we are tracing schedule, we don't want to recurse */
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
 
@@ -1154,10 +1173,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
         return event;
 
  out:
-        if (resched)
-                preempt_enable_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
         return NULL;
 }
 
@@ -1199,12 +1215,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
         /*
          * Only the last preempt count needs to restore preemption.
          */
-        if (preempt_count() == 1) {
-                if (per_cpu(rb_need_resched, cpu))
-                        preempt_enable_no_resched_notrace();
-                else
-                        preempt_enable_notrace();
-        } else
+        if (preempt_count() == 1)
+                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+        else
                 preempt_enable_no_resched_notrace();
 
         return 0;
@@ -1237,8 +1250,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (atomic_read(&buffer->record_disabled))
                 return -EBUSY;
 
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
 
@@ -1264,10 +1276,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         ret = 0;
  out:
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 
         return ret;
 }
@@ -1532,10 +1541,24 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
         struct buffer_page *reader = NULL;
         unsigned long flags;
+        int nr_loops = 0;
 
-        spin_lock_irqsave(&cpu_buffer->lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&cpu_buffer->lock);
 
  again:
+        /*
+         * This should normally only loop twice. But because the
+         * start of the reader inserts an empty page, it causes
+         * a case where we will loop three times. There should be no
+         * reason to loop four times (that I know of).
+         */
+        if (unlikely(++nr_loops > 3)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                reader = NULL;
+                goto out;
+        }
+
         reader = cpu_buffer->reader_page;
 
         /* If there's more to read, return this page */
@@ -1583,7 +1606,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         goto again;
 
  out:
-        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+        __raw_spin_unlock(&cpu_buffer->lock);
+        local_irq_restore(flags);
 
         return reader;
 }
@@ -1665,6 +1689,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
         struct buffer_page *reader;
+        int nr_loops = 0;
 
         if (!cpu_isset(cpu, buffer->cpumask))
                 return NULL;
@@ -1672,6 +1697,19 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         cpu_buffer = buffer->buffers[cpu];
 
  again:
+        /*
+         * We repeat when a timestamp is encountered. It is possible
+         * to get multiple timestamps from an interrupt entering just
+         * as one timestamp is about to be written. The max times
+         * that this can happen is the number of nested interrupts we
+         * can have.  Nesting 10 deep of interrupts is clearly
+         * an anomaly.
+         */
+        if (unlikely(++nr_loops > 10)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
         reader = rb_get_reader_page(cpu_buffer);
         if (!reader)
                 return NULL;
@@ -1722,6 +1760,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         struct ring_buffer *buffer;
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
+        int nr_loops = 0;
 
         if (ring_buffer_iter_empty(iter))
                 return NULL;
@@ -1730,6 +1769,19 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         buffer = cpu_buffer->buffer;
 
  again:
+        /*
+         * We repeat when a timestamp is encountered. It is possible
+         * to get multiple timestamps from an interrupt entering just
+         * as one timestamp is about to be written. The max times
+         * that this can happen is the number of nested interrupts we
+         * can have. Nesting 10 deep of interrupts is clearly
+         * an anomaly.
+         */
+        if (unlikely(++nr_loops > 10)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
         if (rb_per_cpu_empty(cpu_buffer))
                 return NULL;
 
@@ -1824,9 +1876,11 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         atomic_inc(&cpu_buffer->record_disabled);
         synchronize_sched();
 
-        spin_lock_irqsave(&cpu_buffer->lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&cpu_buffer->lock);
         ring_buffer_iter_reset(iter);
-        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+        __raw_spin_unlock(&cpu_buffer->lock);
+        local_irq_restore(flags);
 
         return iter;
 }
@@ -1912,11 +1966,13 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
         if (!cpu_isset(cpu, buffer->cpumask))
                 return;
 
-        spin_lock_irqsave(&cpu_buffer->lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&cpu_buffer->lock);
 
         rb_reset_cpu(cpu_buffer);
 
-        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+        __raw_spin_unlock(&cpu_buffer->lock);
+        local_irq_restore(flags);
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e4c40c868d67..d55ccfc8d674 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -43,6 +43,15 @@
 unsigned long __read_mostly     tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly     tracing_thresh;
 
+
+/*
+ * Kill all tracing for good (never come back).
+ * It is initialized to 1 but will turn to zero if the initialization
+ * of the tracer is successful. But that is the only place that sets
+ * this back to zero.
+ */
+int tracing_disabled = 1;
+
 static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
@@ -62,8 +71,6 @@ static cpumask_t __read_mostly		tracing_buffer_mask;
 #define for_each_tracing_cpu(cpu)       \
         for_each_cpu_mask(cpu, tracing_buffer_mask)
 
-static int tracing_disabled = 1;
-
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
  *
@@ -143,6 +150,19 @@ static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 /* tracer_enabled is used to toggle activation of a tracer */
 static int                      tracer_enabled = 1;
 
+/**
+ * tracing_is_enabled - return tracer_enabled status
+ *
+ * This function is used by other tracers to know the status
+ * of the tracer_enabled flag.  Tracers may use this function
+ * to know if it should enable their features when starting
+ * up. See irqsoff tracer for an example (start_irqsoff_tracer).
+ */
+int tracing_is_enabled(void)
+{
+        return tracer_enabled;
+}
+
 /* function tracing enabled */
 int                             ftrace_function_enabled;
 
@@ -244,6 +264,7 @@ static const char *trace_options[] = {
         "stacktrace",
         "sched-tree",
         "ftrace_printk",
+        "ftrace_preempt",
         NULL
 };
 
@@ -612,6 +633,76 @@ static void trace_init_cmdlines(void)
         cmdline_idx = 0;
 }
 
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
+/**
+ * tracing_start - quick start of the tracer
+ *
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
+ */
+void tracing_start(void)
+{
+        struct ring_buffer *buffer;
+        unsigned long flags;
+
+        if (tracing_disabled)
+                return;
+
+        spin_lock_irqsave(&tracing_start_lock, flags);
+        if (--trace_stop_count)
+                goto out;
+
+        if (trace_stop_count < 0) {
+                /* Someone screwed up their debugging */
+                WARN_ON_ONCE(1);
+                trace_stop_count = 0;
+                goto out;
+        }
+
+
+        buffer = global_trace.buffer;
+        if (buffer)
+                ring_buffer_record_enable(buffer);
+
+        buffer = max_tr.buffer;
+        if (buffer)
+                ring_buffer_record_enable(buffer);
+
+        ftrace_start();
+ out:
+        spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
+{
+        struct ring_buffer *buffer;
+        unsigned long flags;
+
+        ftrace_stop();
+        spin_lock_irqsave(&tracing_start_lock, flags);
+        if (trace_stop_count++)
+                goto out;
+
+        buffer = global_trace.buffer;
+        if (buffer)
+                ring_buffer_record_disable(buffer);
+
+        buffer = max_tr.buffer;
+        if (buffer)
+                ring_buffer_record_disable(buffer);
+
+ out:
+        spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
 void trace_stop_cmdline_recording(void);
 
 static void trace_save_cmdline(struct task_struct *tsk)
@@ -891,7 +982,7 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
 {
         struct trace_array *tr = &global_trace;
         struct trace_array_cpu *data;
@@ -904,8 +995,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
                 return;
 
         pc = preempt_count();
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
         local_save_flags(flags);
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -915,10 +1005,38 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
                 trace_function(tr, data, ip, parent_ip, flags, pc);
 
         atomic_dec(&data->disabled);
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
+}
+
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = &global_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int cpu;
+        int pc;
+
+        if (unlikely(!ftrace_function_enabled))
+                return;
+
+        /*
+         * Need to use raw, since this must be called before the
+         * recursive protection is performed.
+         */
+        raw_local_irq_save(flags);
+        cpu = raw_smp_processor_id();
+        data = tr->data[cpu];
+        disabled = atomic_inc_return(&data->disabled);
+
+        if (likely(disabled == 1)) {
+                pc = preempt_count();
+                trace_function(tr, data, ip, parent_ip, flags, pc);
+        }
+
+        atomic_dec(&data->disabled);
+        raw_local_irq_restore(flags);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -929,9 +1047,14 @@ static struct ftrace_ops trace_ops __read_mostly =
 void tracing_start_function_trace(void)
 {
         ftrace_function_enabled = 0;
+
+        if (trace_flags & TRACE_ITER_PREEMPTONLY)
+                trace_ops.func = function_trace_call_preempt_only;
+        else
+                trace_ops.func = function_trace_call;
+
         register_ftrace_function(&trace_ops);
-        if (tracer_enabled)
-                ftrace_function_enabled = 1;
+        ftrace_function_enabled = 1;
 }
 
 void tracing_stop_function_trace(void)
@@ -1078,10 +1201,6 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
         atomic_inc(&trace_record_cmdline_disabled);
 
-        /* let the tracer grab locks here if needed */
-        if (current_trace->start)
-                current_trace->start(iter);
-
         if (*pos != iter->pos) {
                 iter->ent = NULL;
                 iter->cpu = 0;
@@ -1108,28 +1227,24 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 static void s_stop(struct seq_file *m, void *p)
 {
-        struct trace_iterator *iter = m->private;
-
         atomic_dec(&trace_record_cmdline_disabled);
-
-        /* let the tracer release locks here if needed */
-        if (current_trace && current_trace == iter->trace && iter->trace->stop)
-                iter->trace->stop(iter);
-
         mutex_unlock(&trace_types_lock);
 }
 
-#define KRETPROBE_MSG "[unknown/kretprobe'd]"
-
 #ifdef CONFIG_KRETPROBES
-static inline int kretprobed(unsigned long addr)
+static inline const char *kretprobed(const char *name)
 {
-        return addr == (unsigned long)kretprobe_trampoline;
+        static const char tramp_name[] = "kretprobe_trampoline";
+        int size = sizeof(tramp_name);
+
+        if (strncmp(tramp_name, name, size) == 0)
+                return "[unknown/kretprobe'd]";
+        return name;
 }
 #else
-static inline int kretprobed(unsigned long addr)
+static inline const char *kretprobed(const char *name)
 {
-        return 0;
+        return name;
 }
 #endif /* CONFIG_KRETPROBES */
 
@@ -1138,10 +1253,13 @@ seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
 {
 #ifdef CONFIG_KALLSYMS
         char str[KSYM_SYMBOL_LEN];
+        const char *name;
 
         kallsyms_lookup(address, NULL, NULL, NULL, str);
 
-        return trace_seq_printf(s, fmt, str);
+        name = kretprobed(str);
+
+        return trace_seq_printf(s, fmt, name);
 #endif
         return 1;
 }
@@ -1152,9 +1270,12 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 {
 #ifdef CONFIG_KALLSYMS
         char str[KSYM_SYMBOL_LEN];
+        const char *name;
 
         sprint_symbol(str, address);
-        return trace_seq_printf(s, fmt, str);
+        name = kretprobed(str);
+
+        return trace_seq_printf(s, fmt, name);
 #endif
         return 1;
 }
@@ -1408,10 +1529,7 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 
                 seq_print_ip_sym(s, field->ip, sym_flags);
                 trace_seq_puts(s, " (");
-                if (kretprobed(field->parent_ip))
-                        trace_seq_puts(s, KRETPROBE_MSG);
-                else
-                        seq_print_ip_sym(s, field->parent_ip, sym_flags);
+                seq_print_ip_sym(s, field->parent_ip, sym_flags);
                 trace_seq_puts(s, ")\n");
                 break;
         }
@@ -1527,12 +1645,9 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
                         ret = trace_seq_printf(s, " <-");
                         if (!ret)
                                 return TRACE_TYPE_PARTIAL_LINE;
-                        if (kretprobed(field->parent_ip))
-                                ret = trace_seq_puts(s, KRETPROBE_MSG);
-                        else
-                                ret = seq_print_ip_sym(s,
-                                                       field->parent_ip,
-                                                       sym_flags);
+                        ret = seq_print_ip_sym(s,
+                                               field->parent_ip,
+                                               sym_flags);
                         if (!ret)
                                 return TRACE_TYPE_PARTIAL_LINE;
                 }
@@ -1783,7 +1898,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
                 return TRACE_TYPE_HANDLED;
 
         SEQ_PUT_FIELD_RET(s, entry->pid);
-        SEQ_PUT_FIELD_RET(s, iter->cpu);
+        SEQ_PUT_FIELD_RET(s, entry->cpu);
         SEQ_PUT_FIELD_RET(s, iter->ts);
 
         switch (entry->type) {
@@ -1945,10 +2060,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
         m->private = iter;
 
         /* stop the trace while dumping */
-        if (iter->tr->ctrl) {
-                tracer_enabled = 0;
-                ftrace_function_enabled = 0;
-        }
+        tracing_stop();
 
         if (iter->trace && iter->trace->open)
                         iter->trace->open(iter);
@@ -1993,14 +2105,7 @@ int tracing_release(struct inode *inode, struct file *file)
                 iter->trace->close(iter);
 
         /* reenable tracing if it was previously enabled */
-        if (iter->tr->ctrl) {
-                tracer_enabled = 1;
-                /*
-                 * It is safe to enable function tracing even if it
-                 * isn't used
-                 */
-                ftrace_function_enabled = 1;
-        }
+        tracing_start();
         mutex_unlock(&trace_types_lock);
 
         seq_release(inode, file);
@@ -2338,11 +2443,10 @@ static ssize_t
 tracing_ctrl_read(struct file *filp, char __user *ubuf,
                   size_t cnt, loff_t *ppos)
 {
-        struct trace_array *tr = filp->private_data;
         char buf[64];
         int r;
 
-        r = sprintf(buf, "%ld\n", tr->ctrl);
+        r = sprintf(buf, "%u\n", tracer_enabled);
         return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -2370,16 +2474,18 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
         val = !!val;
 
         mutex_lock(&trace_types_lock);
-        if (tr->ctrl ^ val) {
-                if (val)
+        if (tracer_enabled ^ val) {
+                if (val) {
                         tracer_enabled = 1;
-                else
+                        if (current_trace->start)
+                                current_trace->start(tr);
+                        tracing_start();
+                } else {
                         tracer_enabled = 0;
-
-                tr->ctrl = val;
-
-                if (current_trace && current_trace->ctrl_update)
-                        current_trace->ctrl_update(tr);
+                        tracing_stop();
+                        if (current_trace->stop)
+                                current_trace->stop(tr);
+                }
         }
         mutex_unlock(&trace_types_lock);
 
@@ -3251,6 +3357,8 @@ __init static int tracer_alloc_buffers(void)
 
         register_tracer(&nop_trace);
 #ifdef CONFIG_BOOT_TRACER
+        /* We don't want to launch sched_switch tracer yet */
+        global_trace.ctrl = 0;
         register_tracer(&boot_tracer);
         current_trace = &boot_tracer;
         current_trace->init(&global_trace);
@@ -3259,7 +3367,7 @@ __init static int tracer_alloc_buffers(void)
 #endif
 
         /* All seems OK, enable tracing */
-        global_trace.ctrl = tracer_enabled;
+        global_trace.ctrl = 1;
         tracing_disabled = 0;
 
         atomic_notifier_chain_register(&panic_notifier_list,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8465ad052707..3422489fad5e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -49,6 +49,7 @@ struct ftrace_entry {
         unsigned long           parent_ip;
 };
 extern struct tracer boot_tracer;
+extern struct tracer sched_switch_trace; /* Used by the boot tracer */
 
 /*
  * Context switch trace entry - which task (and prio) we switched from/to:
@@ -236,11 +237,11 @@ struct tracer {
         const char              *name;
         void                    (*init)(struct trace_array *tr);
         void                    (*reset)(struct trace_array *tr);
+        void                    (*start)(struct trace_array *tr);
+        void                    (*stop)(struct trace_array *tr);
         void                    (*open)(struct trace_iterator *iter);
         void                    (*pipe_open)(struct trace_iterator *iter);
         void                    (*close)(struct trace_iterator *iter);
-        void                    (*start)(struct trace_iterator *iter);
-        void                    (*stop)(struct trace_iterator *iter);
         ssize_t                 (*read)(struct trace_iterator *iter,
                                         struct file *filp, char __user *ubuf,
                                         size_t cnt, loff_t *ppos);
@@ -281,6 +282,7 @@ struct trace_iterator {
         long                    idx;
 };
 
+int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 int tracing_open_generic(struct inode *inode, struct file *filp);
@@ -415,8 +417,57 @@ enum trace_iterator_flags {
         TRACE_ITER_STACKTRACE           = 0x100,
         TRACE_ITER_SCHED_TREE           = 0x200,
         TRACE_ITER_PRINTK               = 0x400,
+        TRACE_ITER_PREEMPTONLY          = 0x800,
 };
 
 extern struct tracer nop_trace;
 
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_recshed flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+        int resched;
+
+        resched = need_resched();
+        preempt_disable_notrace();
+
+        return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we were either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+        if (resched)
+                preempt_enable_no_resched_notrace();
+        else
+                preempt_enable_notrace();
+}
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index d0a5e50eeff2..bd5046c9deb7 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -13,23 +13,33 @@
 #include "trace.h"
 
 static struct trace_array *boot_trace;
-static int trace_boot_enabled;
+static bool pre_initcalls_finished;
 
-
-/* Should be started after do_pre_smp_initcalls() in init/main.c */
+/* Tells the boot tracer that the pre_smp_initcalls are finished.
+ * So we are ready .
+ * It doesn't enable sched events tracing however.
+ * You have to call enable_boot_trace to do so.
+ */
 void start_boot_trace(void)
 {
-        trace_boot_enabled = 1;
+        pre_initcalls_finished = true;
 }
 
-void stop_boot_trace(void)
+void enable_boot_trace(void)
 {
-        trace_boot_enabled = 0;
+        if (pre_initcalls_finished)
+                tracing_start_cmdline_record();
 }
 
-void reset_boot_trace(struct trace_array *tr)
+void disable_boot_trace(void)
 {
-        stop_boot_trace();
+        if (pre_initcalls_finished)
+                tracing_stop_cmdline_record();
+}
+
+static void reset_boot_trace(struct trace_array *tr)
+{
+        sched_switch_trace.reset(tr);
 }
 
 static void boot_trace_init(struct trace_array *tr)
@@ -37,18 +47,18 @@ static void boot_trace_init(struct trace_array *tr)
         int cpu;
         boot_trace = tr;
 
-        trace_boot_enabled = 0;
-
         for_each_cpu_mask(cpu, cpu_possible_map)
                 tracing_reset(tr, cpu);
+
+        sched_switch_trace.init(tr);
 }
 
 static void boot_trace_ctrl_update(struct trace_array *tr)
 {
         if (tr->ctrl)
-                start_boot_trace();
+                enable_boot_trace();
         else
-                stop_boot_trace();
+                disable_boot_trace();
 }
 
 static enum print_line_t initcall_print_line(struct trace_iterator *iter)
@@ -99,7 +109,7 @@ void trace_boot(struct boot_trace *it, initcall_t fn)
         unsigned long irq_flags;
         struct trace_array *tr = boot_trace;
 
-        if (!trace_boot_enabled)
+        if (!pre_initcalls_finished)
                 return;
 
         /* Get its name now since this function could
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 0f85a64003d3..9f1b0de71284 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -62,11 +62,17 @@ static void function_trace_ctrl_update(struct trace_array *tr)
                 stop_function_trace(tr);
 }
 
+static void function_trace_start(struct trace_array *tr)
+{
+        function_reset(tr);
+}
+
 static struct tracer function_trace __read_mostly =
 {
         .name        = "function",
         .init        = function_trace_init,
         .reset       = function_trace_reset,
+        .start       = function_trace_start,
         .ctrl_update = function_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_function,
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 9c74071c10e0..a87a20fa3fc6 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -353,15 +353,28 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_irqsoff_tracer(struct trace_array *tr)
 {
         register_ftrace_function(&trace_ops);
-        tracer_enabled = 1;
+        if (tracing_is_enabled()) {
+                tracer_enabled = 1;
+                save_tracer_enabled = 1;
+        } else {
+                tracer_enabled = 0;
+                save_tracer_enabled = 0;
+        }
 }
 
 static void stop_irqsoff_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
+        save_tracer_enabled = 0;
         unregister_ftrace_function(&trace_ops);
 }
 
@@ -389,17 +402,29 @@ static void irqsoff_tracer_ctrl_update(struct trace_array *tr)
                 stop_irqsoff_tracer(tr);
 }
 
+static void irqsoff_tracer_start(struct trace_array *tr)
+{
+        irqsoff_tracer_reset(tr);
+        tracer_enabled = 1;
+        save_tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+        tracer_enabled = 0;
+        save_tracer_enabled = 0;
+}
+
 static void irqsoff_tracer_open(struct trace_iterator *iter)
 {
         /* stop the trace while dumping */
-        if (iter->tr->ctrl)
-                stop_irqsoff_tracer(iter->tr);
+        tracer_enabled = 0;
 }
 
 static void irqsoff_tracer_close(struct trace_iterator *iter)
 {
-        if (iter->tr->ctrl)
-                start_irqsoff_tracer(iter->tr);
+        /* restart tracing */
+        tracer_enabled = save_tracer_enabled;
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
@@ -414,6 +439,8 @@ static struct tracer irqsoff_tracer __read_mostly =
         .name           = "irqsoff",
         .init           = irqsoff_tracer_init,
         .reset          = irqsoff_tracer_reset,
+        .start          = irqsoff_tracer_start,
+        .stop           = irqsoff_tracer_stop,
         .open           = irqsoff_tracer_open,
         .close          = irqsoff_tracer_close,
         .ctrl_update    = irqsoff_tracer_ctrl_update,
@@ -440,6 +467,8 @@ static struct tracer preemptoff_tracer __read_mostly =
         .name           = "preemptoff",
         .init           = preemptoff_tracer_init,
         .reset          = irqsoff_tracer_reset,
+        .start          = irqsoff_tracer_start,
+        .stop           = irqsoff_tracer_stop,
         .open           = irqsoff_tracer_open,
         .close          = irqsoff_tracer_close,
         .ctrl_update    = irqsoff_tracer_ctrl_update,
@@ -468,6 +497,8 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
         .name           = "preemptirqsoff",
         .init           = preemptirqsoff_tracer_init,
         .reset          = irqsoff_tracer_reset,
+        .start          = irqsoff_tracer_start,
+        .stop           = irqsoff_tracer_stop,
         .open           = irqsoff_tracer_open,
         .close          = irqsoff_tracer_close,
         .ctrl_update    = irqsoff_tracer_ctrl_update,
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index b8f56beb1a62..91c699be8c87 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,7 +16,8 @@
 
 static struct trace_array       *ctx_trace;
 static int __read_mostly        tracer_enabled;
-static atomic_t                 sched_ref;
+static int                      sched_ref;
+static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
@@ -27,7 +28,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
         int cpu;
         int pc;
 
-        if (!atomic_read(&sched_ref))
+        if (!sched_ref)
                 return;
 
         tracing_record_cmdline(prev);
@@ -123,20 +124,22 @@ static void tracing_sched_unregister(void)
 
 static void tracing_start_sched_switch(void)
 {
-        long ref;
-
-        ref = atomic_inc_return(&sched_ref);
-        if (ref == 1)
+        mutex_lock(&sched_register_mutex);
+        if (!(sched_ref++)) {
+                tracer_enabled = 1;
                 tracing_sched_register();
+        }
+        mutex_unlock(&sched_register_mutex);
 }
 
 static void tracing_stop_sched_switch(void)
 {
-        long ref;
-
-        ref = atomic_dec_and_test(&sched_ref);
-        if (ref)
+        mutex_lock(&sched_register_mutex);
+        if (!(--sched_ref)) {
                 tracing_sched_unregister();
+                tracer_enabled = 0;
+        }
+        mutex_unlock(&sched_register_mutex);
 }
 
 void tracing_start_cmdline_record(void)
@@ -153,12 +156,10 @@ static void start_sched_trace(struct trace_array *tr)
 {
         sched_switch_reset(tr);
         tracing_start_cmdline_record();
-        tracer_enabled = 1;
 }
 
 static void stop_sched_trace(struct trace_array *tr)
 {
-        tracer_enabled = 0;
         tracing_stop_cmdline_record();
 }
 
@@ -172,7 +173,7 @@ static void sched_switch_trace_init(struct trace_array *tr)
 
 static void sched_switch_trace_reset(struct trace_array *tr)
 {
-        if (tr->ctrl)
+        if (tr->ctrl && sched_ref)
                 stop_sched_trace(tr);
 }
 
@@ -185,11 +186,24 @@ static void sched_switch_trace_ctrl_update(struct trace_array *tr)
                 stop_sched_trace(tr);
 }
 
-static struct tracer sched_switch_trace __read_mostly =
+static void sched_switch_trace_start(struct trace_array *tr)
+{
+        sched_switch_reset(tr);
+        tracing_start_sched_switch();
+}
+
+static void sched_switch_trace_stop(struct trace_array *tr)
+{
+        tracing_stop_sched_switch();
+}
+
+struct tracer sched_switch_trace __read_mostly =
 {
         .name           = "sched_switch",
         .init           = sched_switch_trace_init,
         .reset          = sched_switch_trace_reset,
+        .start          = sched_switch_trace_start,
+        .stop           = sched_switch_trace_stop,
         .ctrl_update    = sched_switch_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_sched_switch,
@@ -198,14 +212,6 @@ static struct tracer sched_switch_trace __read_mostly =
 
 __init static int init_sched_switch_trace(void)
 {
-        int ret = 0;
-
-        if (atomic_read(&sched_ref))
-                ret = tracing_sched_register();
-        if (ret) {
-                pr_info("error registering scheduler trace\n");
-                return ret;
-        }
         return register_tracer(&sched_switch_trace);
 }
 device_initcall(init_sched_switch_trace);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3ae93f16b565..240577bc8ba5 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
                 return;
 
         pc = preempt_count();
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
         atomic_dec(&data->disabled);
 
-        /*
-         * To prevent recursion from the scheduler, if the
-         * resched flag was set before we entered, then
-         * don't reschedule.
-         */
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -271,6 +262,12 @@ out:
         atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_wakeup_tracer(struct trace_array *tr)
 {
         int ret;
@@ -309,7 +306,13 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
         register_ftrace_function(&trace_ops);
 
-        tracer_enabled = 1;
+        if (tracing_is_enabled()) {
+                tracer_enabled = 1;
+                save_tracer_enabled = 1;
+        } else {
+                tracer_enabled = 0;
+                save_tracer_enabled = 0;
+        }
 
         return;
 fail_deprobe_wake_new:
@@ -321,6 +324,7 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
+        save_tracer_enabled = 0;
         unregister_ftrace_function(&trace_ops);
         unregister_trace_sched_switch(probe_wakeup_sched_switch);
         unregister_trace_sched_wakeup_new(probe_wakeup);
@@ -352,18 +356,32 @@ static void wakeup_tracer_ctrl_update(struct trace_array *tr)
                 stop_wakeup_tracer(tr);
 }
 
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+        wakeup_reset(tr);
+        tracer_enabled = 1;
+        save_tracer_enabled = 1;
+}
+
+static void wakeup_tracer_stop(struct trace_array *tr)
+{
+        tracer_enabled = 0;
+        save_tracer_enabled = 0;
+}
+
 static void wakeup_tracer_open(struct trace_iterator *iter)
 {
         /* stop the trace while dumping */
-        if (iter->tr->ctrl)
-                stop_wakeup_tracer(iter->tr);
+        tracer_enabled = 0;
 }
 
 static void wakeup_tracer_close(struct trace_iterator *iter)
 {
         /* forget about any processes we were recording */
-        if (iter->tr->ctrl)
-                start_wakeup_tracer(iter->tr);
+        if (save_tracer_enabled) {
+                wakeup_reset(iter->tr);
+                tracer_enabled = 1;
+        }
 }
 
 static struct tracer wakeup_tracer __read_mostly =
@@ -371,6 +389,8 @@ static struct tracer wakeup_tracer __read_mostly =
         .name           = "wakeup",
         .init           = wakeup_tracer_init,
         .reset          = wakeup_tracer_reset,
+        .start          = wakeup_tracer_start,
+        .stop           = wakeup_tracer_stop,
         .open           = wakeup_tracer_open,
         .close          = wakeup_tracer_close,
         .ctrl_update    = wakeup_tracer_ctrl_update,
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index be682b62fe58..d39e8b7de6a2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -107,8 +107,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
         if (unlikely(!ftrace_enabled || stack_trace_disabled))
                 return;
 
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
         /* no atomic needed, we only modify this variable by this cpu */
@@ -120,10 +119,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
         per_cpu(trace_active, cpu)--;
         /* prevent recursion in schedule */
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/sound/aoa/soundbus/core.c b/sound/aoa/soundbus/core.c
index f84f3e505788..fa8ab2815a98 100644
--- a/sound/aoa/soundbus/core.c
+++ b/sound/aoa/soundbus/core.c
@@ -176,7 +176,7 @@ int soundbus_add_one(struct soundbus_dev *dev)
                 return -EINVAL;
         }
 
-        snprintf(dev->ofdev.dev.bus_id, BUS_ID_SIZE, "soundbus:%x", ++devcount);
+        dev_set_name(&dev->ofdev.dev, "soundbus:%x", ++devcount);
         dev->ofdev.dev.bus = &soundbus_bus_type;
         return of_device_register(&dev->ofdev);
 }
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index c4995c9f5730..39672f68ce5d 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -148,6 +148,8 @@ static int snd_rawmidi_runtime_free(struct snd_rawmidi_substream *substream)
 
 static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *substream,int up)
 {
+        if (!substream->opened)
+                return;
         if (up) {
                 tasklet_hi_schedule(&substream->runtime->tasklet);
         } else {
@@ -158,6 +160,8 @@ static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *subs
 
 static void snd_rawmidi_input_trigger(struct snd_rawmidi_substream *substream, int up)
 {
+        if (!substream->opened)
+                return;
         substream->ops->trigger(substream, up);
         if (!up && substream->runtime->event)
                 tasklet_kill(&substream->runtime->tasklet);
@@ -857,6 +861,8 @@ int snd_rawmidi_receive(struct snd_rawmidi_substream *substream,
         int result = 0, count1;
         struct snd_rawmidi_runtime *runtime = substream->runtime;
 
+        if (!substream->opened)
+                return -EBADFD;
         if (runtime->buffer == NULL) {
                 snd_printd("snd_rawmidi_receive: input is not active!!!\n");
                 return -EINVAL;
@@ -1126,6 +1132,8 @@ int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count)
 int snd_rawmidi_transmit(struct snd_rawmidi_substream *substream,
                          unsigned char *buffer, int count)
 {
+        if (!substream->opened)
+                return -EBADFD;
         count = snd_rawmidi_transmit_peek(substream, buffer, count);
         if (count < 0)
                 return count;
diff --git a/sound/drivers/ml403-ac97cr.c b/sound/drivers/ml403-ac97cr.c
index ecdbeb6d3603..7783843ca9ae 100644
--- a/sound/drivers/ml403-ac97cr.c
+++ b/sound/drivers/ml403-ac97cr.c
@@ -1153,7 +1153,7 @@ snd_ml403_ac97cr_create(struct snd_card *card, struct platform_device *pfdev,
         /* get irq */
         irq = platform_get_irq(pfdev, 0);
         if (request_irq(irq, snd_ml403_ac97cr_irq, IRQF_DISABLED,
-                        pfdev->dev.bus_id, (void *)ml403_ac97cr)) {
+                        dev_name(&pfdev->dev), (void *)ml403_ac97cr)) {
                 snd_printk(KERN_ERR SND_ML403_AC97CR_DRIVER ": "
                            "unable to grab IRQ %d\n",
                            irq);
@@ -1166,7 +1166,7 @@ snd_ml403_ac97cr_create(struct snd_card *card, struct platform_device *pfdev,
                    ml403_ac97cr->irq);
         irq = platform_get_irq(pfdev, 1);
         if (request_irq(irq, snd_ml403_ac97cr_irq, IRQF_DISABLED,
-                        pfdev->dev.bus_id, (void *)ml403_ac97cr)) {
+                        dev_name(&pfdev->dev), (void *)ml403_ac97cr)) {
                 snd_printk(KERN_ERR SND_ML403_AC97CR_DRIVER ": "
                            "unable to grab IRQ %d\n",
                            irq);
diff --git a/sound/drivers/pcsp/pcsp_input.c b/sound/drivers/pcsp/pcsp_input.c
index cd9b83e7f7d1..0444cdeb4bec 100644
--- a/sound/drivers/pcsp/pcsp_input.c
+++ b/sound/drivers/pcsp/pcsp_input.c
@@ -24,13 +24,13 @@ static void pcspkr_do_sound(unsigned int count)
         spin_lock_irqsave(&i8253_lock, flags);
 
         if (count) {
-                /* enable counter 2 */
-                outb_p(inb_p(0x61) | 3, 0x61);
                 /* set command for counter 2, 2 byte write */
                 outb_p(0xB6, 0x43);
                 /* select desired HZ */
                 outb_p(count & 0xff, 0x42);
                 outb((count >> 8) & 0xff, 0x42);
+                /* enable counter 2 */
+                outb_p(inb_p(0x61) | 3, 0x61);
         } else {
                 /* disable counter 2 */
                 outb(inb_p(0x61) & 0xFC, 0x61);
diff --git a/sound/isa/ad1848/ad1848.c b/sound/isa/ad1848/ad1848.c
index b68d20edc20f..223a6c038819 100644
--- a/sound/isa/ad1848/ad1848.c
+++ b/sound/isa/ad1848/ad1848.c
@@ -70,15 +70,15 @@ static int __devinit snd_ad1848_match(struct device *dev, unsigned int n)
                 return 0;
 
         if (port[n] == SNDRV_AUTO_PORT) {
-                snd_printk(KERN_ERR "%s: please specify port\n", dev->bus_id);
+                dev_err(dev, "please specify port\n");
                 return 0;
         }
         if (irq[n] == SNDRV_AUTO_IRQ) {
-                snd_printk(KERN_ERR "%s: please specify irq\n", dev->bus_id);
+                dev_err(dev, "please specify irq\n");
                 return 0;       
         }
         if (dma1[n] == SNDRV_AUTO_DMA) {
-                snd_printk(KERN_ERR "%s: please specify dma1\n", dev->bus_id);
+                dev_err(dev, "please specify dma1\n");
                 return 0;
         }
         return 1;
diff --git a/sound/isa/adlib.c b/sound/isa/adlib.c
index efa8c80d05b6..374b7177e111 100644
--- a/sound/isa/adlib.c
+++ b/sound/isa/adlib.c
@@ -36,7 +36,7 @@ static int __devinit snd_adlib_match(struct device *dev, unsigned int n)
                 return 0;
 
         if (port[n] == SNDRV_AUTO_PORT) {
-                snd_printk(KERN_ERR "%s: please specify port\n", dev->bus_id);
+                dev_err(dev, "please specify port\n");
                 return 0;
         }
         return 1;
@@ -55,13 +55,13 @@ static int __devinit snd_adlib_probe(struct device *dev, unsigned int n)
 
         card = snd_card_new(index[n], id[n], THIS_MODULE, 0);
         if (!card) {
-                snd_printk(KERN_ERR "%s: could not create card\n", dev->bus_id);
+                dev_err(dev, "could not create card\n");
                 return -EINVAL;
         }
 
         card->private_data = request_region(port[n], 4, CRD_NAME);
         if (!card->private_data) {
-                snd_printk(KERN_ERR "%s: could not grab ports\n", dev->bus_id);
+                dev_err(dev, "could not grab ports\n");
                 error = -EBUSY;
                 goto out;
         }
@@ -73,13 +73,13 @@ static int __devinit snd_adlib_probe(struct device *dev, unsigned int n)
 
         error = snd_opl3_create(card, port[n], port[n] + 2, OPL3_HW_AUTO, 1, &opl3);
         if (error < 0) {
-                snd_printk(KERN_ERR "%s: could not create OPL\n", dev->bus_id);
+                dev_err(dev, "could not create OPL\n");
                 goto out;
         }
 
         error = snd_opl3_hwdep_new(opl3, 0, 0, NULL);
         if (error < 0) {
-                snd_printk(KERN_ERR "%s: could not create FM\n", dev->bus_id);
+                dev_err(dev, "could not create FM\n");
                 goto out;
         }
 
@@ -87,7 +87,7 @@ static int __devinit snd_adlib_probe(struct device *dev, unsigned int n)
 
         error = snd_card_register(card);
         if (error < 0) {
-                snd_printk(KERN_ERR "%s: could not register card\n", dev->bus_id);
+                dev_err(dev, "could not register card\n");
                 goto out;
         }
 
diff --git a/sound/isa/cs423x/cs4231.c b/sound/isa/cs423x/cs4231.c
index ddd289120aa8..f019d449e2d6 100644
--- a/sound/isa/cs423x/cs4231.c
+++ b/sound/isa/cs423x/cs4231.c
@@ -74,15 +74,15 @@ static int __devinit snd_cs4231_match(struct device *dev, unsigned int n)
                 return 0;
 
         if (port[n] == SNDRV_AUTO_PORT) {
-                snd_printk(KERN_ERR "%s: please specify port\n", dev->bus_id);
+                dev_err(dev, "please specify port\n");
                 return 0;
         }
         if (irq[n] == SNDRV_AUTO_IRQ) {
-                snd_printk(KERN_ERR "%s: please specify irq\n", dev->bus_id);
+                dev_err(dev, "please specify irq\n");
                 return 0;
         }
         if (dma1[n] == SNDRV_AUTO_DMA) {
-                snd_printk(KERN_ERR "%s: please specify dma1\n", dev->bus_id);
+                dev_err(dev, "please specify dma1\n");
                 return 0;
         }
         return 1;
@@ -133,7 +133,7 @@ static int __devinit snd_cs4231_probe(struct device *dev, unsigned int n)
                                         mpu_port[n], 0, mpu_irq[n],
                                         mpu_irq[n] >= 0 ? IRQF_DISABLED : 0,
                                         NULL) < 0)
-                        printk(KERN_WARNING "%s: MPU401 not detected\n", dev->bus_id);
+                        dev_warn(dev, "MPU401 not detected\n");
         }
 
         snd_card_set_dev(card, dev);
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 91f9c15d3e30..019c9401663e 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -488,19 +488,19 @@ static int __devinit snd_cs423x_isa_match(struct device *pdev,
                 return 0;
 
         if (port[dev] == SNDRV_AUTO_PORT) {
-                snd_printk(KERN_ERR "%s: please specify port\n", pdev->bus_id);
+                dev_err(pdev, "please specify port\n");
                 return 0;
         }
         if (cport[dev] == SNDRV_AUTO_PORT) {
-                snd_printk(KERN_ERR "%s: please specify cport\n", pdev->bus_id);
+                dev_err(pdev, "please specify cport\n");
                 return 0;
         }
         if (irq[dev] == SNDRV_AUTO_IRQ) {
-                snd_printk(KERN_ERR "%s: please specify irq\n", pdev->bus_id);
+                dev_err(pdev, "please specify irq\n");
                 return 0;
         }
         if (dma1[dev] == SNDRV_AUTO_DMA) {
-                snd_printk(KERN_ERR "%s: please specify dma1\n", pdev->bus_id);
+                dev_err(pdev, "please specify dma1\n");
                 return 0;
         }
         return 1;
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index f88639ea64b2..b46377139cf8 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -88,16 +88,14 @@ static int __devinit snd_es1688_legacy_create(struct snd_card *card,
         if (irq[n] == SNDRV_AUTO_IRQ) {
                 irq[n] = snd_legacy_find_free_irq(possible_irqs);
                 if (irq[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free IRQ\n",
-                                dev->bus_id);
+                        dev_err(dev, "unable to find a free IRQ\n");
                         return -EBUSY;
                 }
         }
         if (dma8[n] == SNDRV_AUTO_DMA) {
                 dma8[n] = snd_legacy_find_free_dma(possible_dmas);
                 if (dma8[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free DMA\n",
-                                dev->bus_id);
+                        dev_err(dev, "unable to find a free DMA\n");
                         return -EBUSY;
                 }
         }
@@ -147,8 +145,7 @@ static int __devinit snd_es1688_probe(struct device *dev, unsigned int n)
 
         if (snd_opl3_create(card, chip->port, chip->port + 2,
                         OPL3_HW_OPL3, 0, &opl3) < 0)
-                printk(KERN_WARNING "%s: opl3 not detected at 0x%lx\n",
-                        dev->bus_id, chip->port);
+                dev_warn(dev, "opl3 not detected at 0x%lx\n", chip->port);
         else {
                 error = snd_opl3_hwdep_new(opl3, 0, 1, NULL);
                 if (error < 0)
diff --git a/sound/isa/gus/gusclassic.c b/sound/isa/gus/gusclassic.c
index 8f914b37bf89..426532a4d730 100644
--- a/sound/isa/gus/gusclassic.c
+++ b/sound/isa/gus/gusclassic.c
@@ -90,24 +90,21 @@ static int __devinit snd_gusclassic_create(struct snd_card *card,
         if (irq[n] == SNDRV_AUTO_IRQ) {
                 irq[n] = snd_legacy_find_free_irq(possible_irqs);
                 if (irq[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free IRQ\n",
-                                dev->bus_id);
+                        dev_err(dev, "unable to find a free IRQ\n");
                         return -EBUSY;
                 }
         }
         if (dma1[n] == SNDRV_AUTO_DMA) {
                 dma1[n] = snd_legacy_find_free_dma(possible_dmas);
                 if (dma1[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free DMA1\n",
-                                dev->bus_id);
+                        dev_err(dev, "unable to find a free DMA1\n");
                         return -EBUSY;
                 }
         }
         if (dma2[n] == SNDRV_AUTO_DMA) {
                 dma2[n] = snd_legacy_find_free_dma(possible_dmas);
                 if (dma2[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free DMA2\n",
-                                dev->bus_id);
+                        dev_err(dev, "unable to find a free DMA2\n");
                         return -EBUSY;
                 }
         }
@@ -174,8 +171,8 @@ static int __devinit snd_gusclassic_probe(struct device *dev, unsigned int n)
 
         error = -ENODEV;
         if (gus->max_flag || gus->ess_flag) {
-                snd_printk(KERN_ERR "%s: GUS Classic or ACE soundcard was "
-                        "not detected at 0x%lx\n", dev->bus_id, gus->gf1.port);
+                dev_err(dev, "GUS Classic or ACE soundcard was "
+                        "not detected at 0x%lx\n", gus->gf1.port);
                 goto out;
         }
 
diff --git a/sound/isa/gus/gusextreme.c b/sound/isa/gus/gusextreme.c
index da13185eb0a0..7ad4c3b41a84 100644
--- a/sound/isa/gus/gusextreme.c
+++ b/sound/isa/gus/gusextreme.c
@@ -106,16 +106,14 @@ static int __devinit snd_gusextreme_es1688_create(struct snd_card *card,
         if (irq[n] == SNDRV_AUTO_IRQ) {
                 irq[n] = snd_legacy_find_free_irq(possible_irqs);
                 if (irq[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free IRQ "
-                                "for ES1688\n", dev->bus_id);
+                        dev_err(dev, "unable to find a free IRQ for ES1688\n");
                         return -EBUSY;
                 }
         }
         if (dma8[n] == SNDRV_AUTO_DMA) {
                 dma8[n] = snd_legacy_find_free_dma(possible_dmas);
                 if (dma8[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free DMA "
-                                "for ES1688\n", dev->bus_id);
+                        dev_err(dev, "unable to find a free DMA for ES1688\n");
                         return -EBUSY;
                 }
         }
@@ -143,16 +141,14 @@ static int __devinit snd_gusextreme_gus_card_create(struct snd_card *card,
         if (gf1_irq[n] == SNDRV_AUTO_IRQ) {
                 gf1_irq[n] = snd_legacy_find_free_irq(possible_irqs);
                 if (gf1_irq[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free IRQ "
-                                "for GF1\n", dev->bus_id);
+                        dev_err(dev, "unable to find a free IRQ for GF1\n");
                         return -EBUSY;
                 }
         }
         if (dma1[n] == SNDRV_AUTO_DMA) {
                 dma1[n] = snd_legacy_find_free_dma(possible_dmas);
                 if (dma1[n] < 0) {
-                        snd_printk(KERN_ERR "%s: unable to find a free DMA "
-                                "for GF1\n", dev->bus_id);
+                        dev_err(dev, "unable to find a free DMA for GF1\n");
                         return -EBUSY;
                 }
         }
@@ -278,8 +274,8 @@ static int __devinit snd_gusextreme_probe(struct device *dev, unsigned int n)
 
         error = -ENODEV;
         if (!gus->ess_flag) {
-                snd_printk(KERN_ERR "%s: GUS Extreme soundcard was not "
-                        "detected at 0x%lx\n", dev->bus_id, gus->gf1.port);
+                dev_err(dev, "GUS Extreme soundcard was not "
+                        "detected at 0x%lx\n", gus->gf1.port);
                 goto out;
         }
         gus->codec_flag = 1;
@@ -310,8 +306,7 @@ static int __devinit snd_gusextreme_probe(struct device *dev, unsigned int n)
 
         if (snd_opl3_create(card, es1688->port, es1688->port + 2,
                         OPL3_HW_OPL3, 0, &opl3) < 0)
-                printk(KERN_ERR "%s: opl3 not detected at 0x%lx\n",
-                        dev->bus_id, es1688->port);
+                dev_warn(dev, "opl3 not detected at 0x%lx\n", es1688->port);
         else {
                 error = snd_opl3_hwdep_new(opl3, 0, 2, NULL);
                 if (error < 0)
diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c
index 336a34277907..667eccc676a4 100644
--- a/sound/isa/sb/sb8.c
+++ b/sound/isa/sb/sb8.c
@@ -85,11 +85,11 @@ static int __devinit snd_sb8_match(struct device *pdev, unsigned int dev)
         if (!enable[dev])
                 return 0;
         if (irq[dev] == SNDRV_AUTO_IRQ) {
-                snd_printk(KERN_ERR "%s: please specify irq\n", pdev->bus_id);
+                dev_err(pdev, "please specify irq\n");
                 return 0;
         }
         if (dma8[dev] == SNDRV_AUTO_DMA) {
-                snd_printk(KERN_ERR "%s: please specify dma8\n", pdev->bus_id);
+                dev_err(pdev, "please specify dma8\n");
                 return 0;
         }
         return 1;
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index 2f283ea6ad9a..de5ee8f097f6 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -1464,6 +1464,7 @@ static struct snd_emu_chip_details emu_chip_details[] = {
          .ca0151_chip = 1,
          .spk71 = 1,
          .spdif_bug = 1,
+         .invert_shared_spdif = 1,      /* digital/analog switch swapped */
          .ac97_chip = 1} ,
         {.vendor = 0x1102, .device = 0x0004, .subsystem = 0x20021102,
          .driver = "Audigy2", .name = "Audigy 2 ZS [SB0350]", 
@@ -1473,6 +1474,7 @@ static struct snd_emu_chip_details emu_chip_details[] = {
          .ca0151_chip = 1,
          .spk71 = 1,
          .spdif_bug = 1,
+         .invert_shared_spdif = 1,      /* digital/analog switch swapped */
          .ac97_chip = 1} ,
         {.vendor = 0x1102, .device = 0x0004, .subsystem = 0x20011102,
          .driver = "Audigy2", .name = "Audigy 2 ZS [2001]", 
@@ -1482,6 +1484,7 @@ static struct snd_emu_chip_details emu_chip_details[] = {
          .ca0151_chip = 1,
          .spk71 = 1,
          .spdif_bug = 1,
+         .invert_shared_spdif = 1,      /* digital/analog switch swapped */
          .ac97_chip = 1} ,
         /* Audigy 2 */
         /* Tested by James@superbug.co.uk 3rd July 2005 */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4eceab9bd109..a4666c96a44f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -829,6 +829,7 @@ static void alc_sku_automute(struct hda_codec *codec)
                             spec->jack_present ? 0 : PIN_OUT);
 }
 
+#if 0 /* it's broken in some acses -- temporarily disabled */
 static void alc_mic_automute(struct hda_codec *codec)
 {
         struct alc_spec *spec = codec->spec;
@@ -849,6 +850,9 @@ static void alc_mic_automute(struct hda_codec *codec)
         snd_hda_codec_amp_stereo(codec, 0x0b, HDA_INPUT, capsrc_idx_fmic,
                          HDA_AMP_MUTE, present ? HDA_AMP_MUTE : 0);
 }
+#else
+#define alc_mic_automute(codec) /* NOP */
+#endif /* disabled */
 
 /* unsolicited event for HP jack sensing */
 static void alc_sku_unsol_event(struct hda_codec *codec, unsigned int res)
@@ -1058,12 +1062,14 @@ do_sku:
                         AC_VERB_SET_UNSOLICITED_ENABLE,
                         AC_USRSP_EN | ALC880_HP_EVENT);
 
+#if 0 /* it's broken in some acses -- temporarily disabled */
         if (spec->autocfg.input_pins[AUTO_PIN_MIC] &&
                 spec->autocfg.input_pins[AUTO_PIN_FRONT_MIC])
                 snd_hda_codec_write(codec,
                         spec->autocfg.input_pins[AUTO_PIN_MIC], 0,
                         AC_VERB_SET_UNSOLICITED_ENABLE,
                         AC_USRSP_EN | ALC880_MIC_EVENT);
+#endif /* disabled */
 
         spec->unsol_event = alc_sku_unsol_event;
 }
@@ -8408,6 +8414,7 @@ static const char *alc883_models[ALC883_MODEL_LAST] = {
 static struct snd_pci_quirk alc883_cfg_tbl[] = {
         SND_PCI_QUIRK(0x1019, 0x6668, "ECS", ALC883_3ST_6ch_DIG),
         SND_PCI_QUIRK(0x1025, 0x006c, "Acer Aspire 9810", ALC883_ACER_ASPIRE),
+        SND_PCI_QUIRK(0x1025, 0x0090, "Acer Aspire", ALC883_ACER_ASPIRE),
         SND_PCI_QUIRK(0x1025, 0x0110, "Acer Aspire", ALC883_ACER_ASPIRE),
         SND_PCI_QUIRK(0x1025, 0x0112, "Acer Aspire 9303", ALC883_ACER_ASPIRE),
         SND_PCI_QUIRK(0x1025, 0x0121, "Acer Aspire 5920G", ALC883_ACER_ASPIRE),
@@ -12238,8 +12245,26 @@ static int alc269_auto_create_multi_out_ctls(struct alc_spec *spec,
         return 0;
 }
 
-#define alc269_auto_create_analog_input_ctls \
-        alc880_auto_create_analog_input_ctls
+static int alc269_auto_create_analog_input_ctls(struct alc_spec *spec,
+                                                const struct auto_pin_cfg *cfg)
+{
+        int err;
+
+        err = alc880_auto_create_analog_input_ctls(spec, cfg);
+        if (err < 0)
+                return err;
+        /* digital-mic input pin is excluded in alc880_auto_create..()
+         * because it's under 0x18
+         */
+        if (cfg->input_pins[AUTO_PIN_MIC] == 0x12 ||
+            cfg->input_pins[AUTO_PIN_FRONT_MIC] == 0x12) {
+                struct hda_input_mux *imux = &spec->private_imux;
+                imux->items[imux->num_items].label = "Int Mic";
+                imux->items[imux->num_items].index = 0x05;
+                imux->num_items++;
+        }
+        return 0;
+}
 
 #ifdef CONFIG_SND_HDA_POWER_SAVE
 #define alc269_loopbacks        alc880_loopbacks
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index df9b0bc7f878..e6085915d86d 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -69,6 +69,7 @@ enum {
 enum {
         STAC_92HD73XX_REF,
         STAC_DELL_M6,
+        STAC_DELL_EQ,
         STAC_92HD73XX_MODELS
 };
 
@@ -773,9 +774,7 @@ static struct hda_verb dell_eq_core_init[] = {
 };
 
 static struct hda_verb dell_m6_core_init[] = {
-        /* set master volume to max value without distortion
-         * and direct control */
-        { 0x1f, AC_VERB_SET_VOLUME_KNOB_CONTROL, 0xec},
+        { 0x1f, AC_VERB_SET_VOLUME_KNOB_CONTROL, 0xff},
         /* setup audio connections */
         { 0x0d, AC_VERB_SET_CONNECT_SEL, 0x00},
         { 0x0a, AC_VERB_SET_CONNECT_SEL, 0x01},
@@ -1600,11 +1599,13 @@ static unsigned int dell_m6_pin_configs[13] = {
 static unsigned int *stac92hd73xx_brd_tbl[STAC_92HD73XX_MODELS] = {
         [STAC_92HD73XX_REF]     = ref92hd73xx_pin_configs,
         [STAC_DELL_M6]  = dell_m6_pin_configs,
+        [STAC_DELL_EQ]  = dell_m6_pin_configs,
 };
 
 static const char *stac92hd73xx_models[STAC_92HD73XX_MODELS] = {
         [STAC_92HD73XX_REF] = "ref",
         [STAC_DELL_M6] = "dell-m6",
+        [STAC_DELL_EQ] = "dell-eq",
 };
 
 static struct snd_pci_quirk stac92hd73xx_cfg_tbl[] = {
@@ -4131,12 +4132,17 @@ again:
                         sizeof(stac92hd73xx_dmux));
 
         switch (spec->board_config) {
-        case STAC_DELL_M6:
+        case STAC_DELL_EQ:
                 spec->init = dell_eq_core_init;
+                /* fallthru */
+        case STAC_DELL_M6:
                 spec->num_smuxes = 0;
                 spec->mixer = &stac92hd73xx_6ch_mixer[DELL_M6_MIXER];
                 spec->amp_nids = &stac92hd73xx_amp_nids[DELL_M6_AMP];
                 spec->num_amps = 1;
+
+                if (!spec->init)
+                        spec->init = dell_m6_core_init;
                 switch (codec->subsystem_id) {
                 case 0x1028025e: /* Analog Mics */
                 case 0x1028025f:
@@ -4146,8 +4152,6 @@ again:
                         break;
                 case 0x10280271: /* Digital Mics */
                 case 0x10280272:
-                        spec->init = dell_m6_core_init;
-                        /* fall-through */
                 case 0x10280254:
                 case 0x10280255:
                         stac92xx_set_config_reg(codec, 0x13, 0x90A60160);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index a3adbf06b1e5..16c7453f4946 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -95,8 +95,8 @@ static int soc_ac97_dev_register(struct snd_soc_codec *codec)
         codec->ac97->dev.parent = NULL;
         codec->ac97->dev.release = soc_ac97_device_release;
 
-        snprintf(codec->ac97->dev.bus_id, BUS_ID_SIZE, "%d-%d:%s",
-                 codec->card->number, 0, codec->name);
+        dev_set_name(&codec->ac97->dev, "%d-%d:%s",
+                     codec->card->number, 0, codec->name);
         err = device_register(&codec->ac97->dev);
         if (err < 0) {
                 snd_printk(KERN_ERR "Can't register ac97 bus\n");