aboutsummaryrefslogtreecommitdiffstats
path: root/mm/Kconfig
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2005-11-23 16:37:37 -0500
committerLinus Torvalds <torvalds@g5.osdl.org>2005-11-23 19:08:38 -0500
commit7b6ac9dffe6f4dd8776908b234ac1410ed15f112 (patch)
tree1e30fde299519eb964899be79560599e04a32a66 /mm/Kconfig
parentc101e77301877086e6f977fcfb140d1cbbe23fd5 (diff)
[PATCH] mm: update split ptlock Kconfig
Closer attention to the arithmetic shows that neither ppc64 nor sparc really uses one page for multiple page tables: how on earth could they, while pte_alloc_one returns just a struct page pointer, with no offset? Well, arm26 manages it by returning a pte_t pointer cast to a struct page pointer, harumph, then compensating in its pmd_populate. But arm26 is never SMP, so it's not a problem for split ptlock either. And the PA-RISC situation has been recently improved: CONFIG_PA20 works without the 16-byte alignment which inflated its spinlock_t. But the current union of spinlock_t with private does make the 7xxx struct page significantly larger, even without debug, so disable its split ptlock. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm/Kconfig')
-rw-r--r--mm/Kconfig6
1 files changed, 2 insertions, 4 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index ae9ce6b73e8a..21eb51d4da8f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -125,12 +125,10 @@ comment "Memory hotplug is currently incompatible with Software Suspend"
125# space can be handled with less contention: split it at this NR_CPUS. 125# space can be handled with less contention: split it at this NR_CPUS.
126# Default to 4 for wider testing, though 8 might be more appropriate. 126# Default to 4 for wider testing, though 8 might be more appropriate.
127# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 127# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
128# PA-RISC's debug spinlock_t is too large for the 32-bit struct page. 128# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
129# ARM26 and SPARC32 and PPC64 may use one page for multiple page tables.
130# 129#
131config SPLIT_PTLOCK_CPUS 130config SPLIT_PTLOCK_CPUS
132 int 131 int
133 default "4096" if ARM && !CPU_CACHE_VIPT 132 default "4096" if ARM && !CPU_CACHE_VIPT
134 default "4096" if PARISC && DEBUG_SPINLOCK && !64BIT 133 default "4096" if PARISC && !PA20
135 default "4096" if ARM26 || SPARC32 || PPC64
136 default "4" 134 default "4"