linux.git/arch/arm/include/asm/pgtable.h, branch v2.6.35 Linux kernel source tree ARM: Optionally allow ARMv6 to use 'normal, bufferable' memory for DMA 2010-05-17T10:52:11+00:00 Russell King rmk+kernel@arm.linux.org.uk 2010-05-15T10:02:43+00:00 47ab0dee661dbd5aca67abe44a333e471134fbf9 Provide a configuration option to allow the ARMv6 to use normal bufferable memory for coherent DMA. This option is forced to 'y' for ARMv7, and offered as a configuration option on ARMv6. Enabling this option requires drivers to have the necessary barriers to ensure that data in DMA coherent memory is visible prior to the DMA operation commencing. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
Provide a configuration option to allow the ARMv6 to use normal
bufferable memory for coherent DMA.  This option is forced to 'y'
for ARMv7, and offered as a configuration option on ARMv6.

Enabling this option requires drivers to have the necessary barriers
to ensure that data in DMA coherent memory is visible prior to the
DMA operation commencing.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
ARM: dma-mapping: switch ARMv7 DMA mappings to retain 'memory' attribute 2009-11-24T17:41:36+00:00 Russell King rmk+kernel@arm.linux.org.uk 2009-11-20T21:06:43+00:00 26a26d329688ab018e068b412b03d43d7c299f0a On ARMv7, it is invalid to map the same physical address multiple times with different memory types. Since system RAM is already mapped as 'memory', subsequent remapping of it must retain this attribute. However, DMA memory maps it as "strongly ordered". Fix this by introducing 'pgprot_dmacoherent()' which provides the necessary page table bits for DMA mappings. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Acked-by: Greg Ungerer <gerg@uclinux.org> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> 
On ARMv7, it is invalid to map the same physical address multiple times
with different memory types.  Since system RAM is already mapped as
'memory', subsequent remapping of it must retain this attribute.

However, DMA memory maps it as "strongly ordered".  Fix this by introducing
'pgprot_dmacoherent()' which provides the necessary page table bits for
DMA mappings.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Acked-by: Greg Ungerer <gerg@uclinux.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
ARM: implement highpte 2009-08-17T19:02:06+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-08-17T19:02:06+00:00 65cec8e3db606608fd1f8dfc4a1c7c37bfba9173 Add the ARM implementation of highpte, which allows PTE tables to be placed in highmem. Unfortunately, we do not offer highpte support when support for L2 cache is enabled. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
Add the ARM implementation of highpte, which allows PTE tables to be
placed in highmem.  Unfortunately, we do not offer highpte support
when support for L2 cache is enabled.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ARM] pgtable: rearrange file PTE bit allocation 2009-07-11T15:59:39+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-07-11T15:57:20+00:00 6a00cded91532f3d58e07729ba56269339281d8e For future compatibility, we need to ensure that swap and file Linux PTEs conform with the hardware PTEs "fault" encoding. Swap PTEs already fit in with this, but file PTEs do not. Shift them by one bit to ensure that they conform, using bit 2 to distinguish between swap and file PTEs. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
For future compatibility, we need to ensure that swap and file Linux
PTEs conform with the hardware PTEs "fault" encoding.  Swap PTEs
already fit in with this, but file PTEs do not.  Shift them by one
bit to ensure that they conform, using bit 2 to distinguish between
swap and file PTEs.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ARM] remove L_PTE_BUFFERABLE and L_PTE_CACHEABLE 2009-07-11T15:55:52+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-07-11T15:51:40+00:00 f7a55fa6ecef8be6d15bd79a803e44a3187ce9d6 These old symbols are meaningless now that we have memory type support implemented. The entire memory type field needs to be modified rather than just a few bits twiddled. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
These old symbols are meaningless now that we have memory type
support implemented.  The entire memory type field needs to be
modified rather than just a few bits twiddled.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ARM] pgtable: file pte layout documentation 2009-07-05T14:31:35+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-07-05T10:52:21+00:00 65b1bfc13e8f50034187e339aa12b81cd6785bd5 Document the layout of our file PTE entries. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
Document the layout of our file PTE entries.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ARM] pgtable: swp pte layout documentation, definitions, and check 2009-07-05T14:31:26+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-07-05T10:30:15+00:00 fb93a1c75eb646fde35985e9af23da936775ae52 Document the layout of our swp PTE entries, adding definitions for the bit masks/shifts/sizes, and implement MAX_SWAPFILES_CHECK() such that we fail to build if we are unable to properly encode the swp type field. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
Document the layout of our swp PTE entries, adding definitions for
the bit masks/shifts/sizes, and implement MAX_SWAPFILES_CHECK()
such that we fail to build if we are unable to properly encode the
swp type field.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ARM] Convert pmd_page() to be highmem safe 2009-04-26T12:14:52+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2009-04-26T12:14:52+00:00 924a158a12c7e732179dd85ddd20848039e7bd71 In the long run, we may want to place page tables in highmem. However, pmd_page() has traditionally been coded to convert the physical address to a virtual one, which won't work with highmem pages. Instead, translate the physical address to a PFN, and then convert the PFN to a struct page instead. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
In the long run, we may want to place page tables in highmem.  However,
pmd_page() has traditionally been coded to convert the physical address
to a virtual one, which won't work with highmem pages.  Instead,
translate the physical address to a PFN, and then convert the PFN to a
struct page instead.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Merge branch 'ptebits' into devel 2008-10-09T20:31:56+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2008-10-09T20:31:56+00:00 6a4690c22f5da1eb1c898b61b6a80da52fbd976f Conflicts: arch/arm/Kconfig 
Conflicts:

	arch/arm/Kconfig
[ARM] Improve non-executable support 2008-10-01T15:41:10+00:00 Russell King rmk@dyn-67.arm.linux.org.uk 2008-09-07T16:16:54+00:00 8ec53663d2698076468b3e1edc4e1b418bd54de3 Add support for detecting non-executable stack binaries, and adjust permissions to prevent execution from data and stack areas. Also, ensure that READ_IMPLIES_EXEC is enabled for older CPUs where that is true, and for any executable-stack binary. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> 
Add support for detecting non-executable stack binaries, and adjust
permissions to prevent execution from data and stack areas.  Also,
ensure that READ_IMPLIES_EXEC is enabled for older CPUs where that
is true, and for any executable-stack binary.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>