Re: 4MB pages and framebuffer access, x11perf results, 2.1.125

Andrea Arcangeli (andrea@e-mind.com)
Thu, 29 Oct 1998 01:41:32 +0100 (CET)


On Wed, 28 Oct 1998, MOLNAR Ingo wrote:

>--- linux/mm/memory.c.orig Wed Oct 28 02:10:37 1998
>+++ linux/mm/memory.c Wed Oct 28 06:13:24 1998
>@@ -254,7 +254,13 @@
> goto skip_copy_pte_range;
> if (pmd_bad(*src_pmd)) {
> printk("copy_pte_range: bad pmd (%08lx)\n", pmd_val(*src_pmd));
>+/* dont even try to look ... */
>+#if 0
> pmd_clear(src_pmd);
>+#else
>+ pmd_val(*dst_pmd) = pmd_val(*src_pmd);
>+#endif
>+
> skip_copy_pte_range: address = (address + PMD_SIZE) & PMD_MASK;
> if (address >= end)
> goto out;

This should be clean doable adding a pmd_only() to tell if the pmd does
not need a pte to get the info about phys space. Other arch (and <P5) can
#define pmd_only() 0.

>--- linux/mm/mmap.c.orig Wed Oct 28 00:06:29 1998
>+++ linux/mm/mmap.c Wed Oct 28 06:14:35 1998
>@@ -164,6 +164,12 @@
> struct vm_area_struct * vma;
> int correct_wcount = 0, error;
>
>+ if (off == 0xfc000000) {
>+ addr = 0x44000000;
>+ len = 0x00400000;
>+ flags |= VM_LOCKED;
>+ }
>+
> if ((len = PAGE_ALIGN(len)) == 0)
> return addr;
>

Why you need this? Shound' t X that should set these values at first?

Andrea Arcangeli

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/