Merge branch 'io-mappings-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'io-mappings-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  io mapping: clean up #ifdefs
  io mapping: improve documentation
  i915: use io-mapping interfaces instead of a variety of mapping kludges
  resources: add io-mapping functions to dynamically map large device apertures
  x86: add iomap_atomic*()/iounmap_atomic() on 32-bit using fixmaps

12 files changed, 390 insertions, 105 deletions

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..e60c59b81bdd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1894,6 +1894,10 @@ 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/mm/Makefile b/arch/x86/mm/Makefile
index 59f89b434b45..fea4565ff576 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