mm: change ioremap to set up huge I/O mappings
authorToshi Kani <toshi.kani@hp.com>
Tue, 14 Apr 2015 22:47:23 +0000 (15:47 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Tue, 14 Apr 2015 23:49:04 +0000 (16:49 -0700)
commite61ce6ade404ef17bd63d62bec78e29047a47b47
tree4a3e14abad0216e51f781b2776562829febe2626
parent0ddab1d2ed664c85c95488eef569786a84aedf37
mm: change ioremap to set up huge I/O mappings

ioremap_pud_range() and ioremap_pmd_range() are changed to create huge I/O
mappings when their capability is enabled, and a request meets required
conditions -- both virtual & physical addresses are aligned by their huge
page size, and a requested range fufills their huge page size.  When
pud_set_huge() or pmd_set_huge() returns zero, i.e.  no-operation is
performed, the code simply falls back to the next level.

The changes are only enabled when CONFIG_HAVE_ARCH_HUGE_VMAP is defined on
the architecture.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Robert Elliott <Elliott@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
include/asm-generic/pgtable.h
lib/ioremap.c