Commit da32dac1 authored by Rusty Russell's avatar Rusty Russell
Browse files

lguest: populate initial_page_table 



Two x86 patches broke lguest:
1) v2.6.35-492-g72d7c3b, which changed x86 to use the memblock allocator.

In lguest, the host places linear page tables at the top of mem, which
used to be enough to get us up to the swapper_pg_dir page tables.  With
the first patch, the direct mapping tables used that memory:

Before: kernel direct mapping tables up to 4000000 @ 7000-1a000
After: kernel direct mapping tables up to 4000000 @ 3fed000-4000000

I initially fixed this by lying about the amount of memory we had, so
the kernel wouldn't blatt the lguest boot pagetables (yuk!), but then...

2) v2.6.36-rc8-54-gb40827f, which made x86 boot use initial_page_table.

This was initialized in a part of head_32.S which isn't executed by
lguest; it is then copied into swapper_pg_dir.  So we have to initialize
it; and anyway we switch to it before we blatt the old tables, so that
fixes the previous damage as well.

For the moment, I cut & pasted the code into lguest's boot code, but
next merge window I will merge them.

Signed-off-by: default avatarRusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: x86@kernel.org
parent bb4093de

arch/x86/kernel/head_32.S

+2 −2
Original line number Diff line number Diff line
@@ -620,13 +620,13 @@ ENTRY(initial_code) 
__PAGE_ALIGNED_BSS

	.align PAGE_SIZE_asm

#ifdef CONFIG_X86_PAE

initial_pg_pmd:

ENTRY(initial_pg_pmd)

	.fill 1024*KPMDS,4,0

#else

ENTRY(initial_page_table)

	.fill 1024,4,0

#endif

initial_pg_fixmap:

ENTRY(initial_pg_fixmap)

	.fill 1024,4,0

ENTRY(empty_zero_page)

	.fill 4096,1,0

arch/x86/lguest/boot.c

+0 −3
Original line number Diff line number Diff line
@@ -1352,9 +1352,6 @@ __init void lguest_init(void) 
	 */

	switch_to_new_gdt(0);



	/* We actually boot with all memory mapped, but let's say 128MB. */

	max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;



	/*

	 * The Host<->Guest Switcher lives at the top of our address space, and

	 * the Host told us how big it is when we made LGUEST_INIT hypercall:

arch/x86/lguest/i386_head.S

+105 −0
Original line number Diff line number Diff line
@@ -4,6 +4,7 @@ 
#include <asm/asm-offsets.h>

#include <asm/thread_info.h>

#include <asm/processor-flags.h>

#include <asm/pgtable.h>



/*G:020

 * Our story starts with the kernel booting into startup_32 in
@@ -37,9 +38,113 @@ ENTRY(lguest_entry) 
	/* Set up the initial stack so we can run C code. */

	movl $(init_thread_union+THREAD_SIZE),%esp



	call init_pagetables



	/* Jumps are relative: we're running __PAGE_OFFSET too low. */

	jmp lguest_init+__PAGE_OFFSET



/*

 * Initialize page tables.  This creates a PDE and a set of page

 * tables, which are located immediately beyond __brk_base.  The variable

 * _brk_end is set up to point to the first "safe" location.

 * Mappings are created both at virtual address 0 (identity mapping)

 * and PAGE_OFFSET for up to _end.

 *

 * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they

 * don't have a stack at this point, so we can't just use call and ret.

 */

init_pagetables:

#if PTRS_PER_PMD > 1

#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)

#else

#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)

#endif

#define pa(X) ((X) - __PAGE_OFFSET)



/* Enough space to fit pagetables for the low memory linear map */

MAPPING_BEYOND_END = \

	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT

#ifdef CONFIG_X86_PAE



	/*

	 * In PAE mode initial_page_table is statically defined to contain

	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3

	 * entries). The identity mapping is handled by pointing two PGD entries

	 * to the first kernel PMD.

	 *

	 * Note the upper half of each PMD or PTE are always zero at this stage.

	 */



#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */



	xorl %ebx,%ebx				/* %ebx is kept at zero */



	movl $pa(__brk_base), %edi

	movl $pa(initial_pg_pmd), %edx

	movl $PTE_IDENT_ATTR, %eax

10:

	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */

	movl %ecx,(%edx)			/* Store PMD entry */

						/* Upper half already zero */

	addl $8,%edx

	movl $512,%ecx

11:

	stosl

	xchgl %eax,%ebx

	stosl

	xchgl %eax,%ebx

	addl $0x1000,%eax

	loop 11b



	/*

	 * End condition: we must map up to the end + MAPPING_BEYOND_END.

	 */

	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp

	cmpl %ebp,%eax

	jb 10b

1:

	addl $__PAGE_OFFSET, %edi

	movl %edi, pa(_brk_end)

	shrl $12, %eax

	movl %eax, pa(max_pfn_mapped)



	/* Do early initialization of the fixmap area */

	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax

	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)

#else	/* Not PAE */



page_pde_offset = (__PAGE_OFFSET >> 20);



	movl $pa(__brk_base), %edi

	movl $pa(initial_page_table), %edx

	movl $PTE_IDENT_ATTR, %eax

10:

	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */

	movl %ecx,(%edx)			/* Store identity PDE entry */

	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */

	addl $4,%edx

	movl $1024, %ecx

11:

	stosl

	addl $0x1000,%eax

	loop 11b

	/*

	 * End condition: we must map up to the end + MAPPING_BEYOND_END.

	 */

	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp

	cmpl %ebp,%eax

	jb 10b

	addl $__PAGE_OFFSET, %edi

	movl %edi, pa(_brk_end)

	shrl $12, %eax

	movl %eax, pa(max_pfn_mapped)



	/* Do early initialization of the fixmap area */

	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax

	movl %eax,pa(initial_page_table+0xffc)

#endif

	ret



/*G:055

 * We create a macro which puts the assembler code between lgstart_ and lgend_

 * markers.  These templates are put in the .text section: they can't be

CRA Git | Maintained and supported by SUSTech CRA and CCSE