[PATCH] uml: TLB operation batching
This adds VM op batching to skas0. Rather than having a context switch to and
from the userspace stub for each address space change, we write a number of
operations to the stub data page and invoke a different stub which loops over
them and executes them all in one go.
The operations are stored as [ system call number, arg1, arg2, ... ] tuples.
The set is terminated by a system call number of 0. Single operations, i.e.
page faults, are handled in the old way, since that is slightly more
efficient.
For a kernel build, a minority (~1/4) of the operations are part of a set.
These sets averaged ~100 in length, so for this quarter, the context switching
overhead is greatly reduced.
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Cc: Paolo Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/um/kernel/tt/tlb.c b/arch/um/kernel/tt/tlb.c
index 2eefb43..16fc6a2 100644
--- a/arch/um/kernel/tt/tlb.c
+++ b/arch/um/kernel/tt/tlb.c
@@ -17,7 +17,8 @@
#include "os.h"
#include "tlb.h"
-static void do_ops(union mm_context *mmu, struct host_vm_op *ops, int last)
+static void *do_ops(union mm_context *mmu, struct host_vm_op *ops, int last,
+ int finished, void *flush)
{
struct host_vm_op *op;
int i;
@@ -45,6 +46,8 @@
break;
}
}
+
+ return NULL;
}
static void fix_range(struct mm_struct *mm, unsigned long start_addr,