Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1621012 > unrolled thread

[tip:x86/mm] x86/boot/64: Rewrite startup_64() in C

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [tip:x86/mm] x86/boot/64: Rewrite startup_64() in C "tip-bot for Kirill A. Shutemov" <tipbot@zytor.com> - 2017-04-11 10:20 +0200
    Re: [tip:x86/mm] x86/boot/64: Rewrite startup_64() in C "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-04-11 14:40 +0200

#1621012 — [tip:x86/mm] x86/boot/64: Rewrite startup_64() in C

Commit-ID:  10ee822ec8c53f3987d969ce98b2686323a7fc2a
Gitweb:     http://git.kernel.org/tip/10ee822ec8c53f3987d969ce98b2686323a7fc2a
Author:     Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
AuthorDate: Thu, 6 Apr 2017 17:00:59 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 11 Apr 2017 08:57:37 +0200

x86/boot/64: Rewrite startup_64() in C

The patch converts most of the startup_64 logic from assembly to C.

This is preparation for 5-level paging enabling.

No change in functionality.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20170406140106.78087-2-kirill.shutemov@linux.intel.com
[ Small typo fixes. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/head64.c  | 81 ++++++++++++++++++++++++++++++++++++++++-
 arch/x86/kernel/head_64.S | 93 +----------------------------------------------
 2 files changed, 81 insertions(+), 93 deletions(-)

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 43b7002..079b382 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -35,9 +35,88 @@
  */
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
-static unsigned int __initdata next_early_pgt = 2;
+static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
+static void __init *fixup_pointer(void *ptr, unsigned long physaddr)
+{
+	return ptr - (void *)_text + (void *)physaddr;
+}
+
+void __init __startup_64(unsigned long physaddr)
+{
+	unsigned long load_delta, *p;
+	pgdval_t *pgd;
+	pudval_t *pud;
+	pmdval_t *pmd, pmd_entry;
+	int i;
+
+	/* Is the address too large? */
+	if (physaddr >> MAX_PHYSMEM_BITS)
+		for (;;);
+
+	/*
+	 * Compute the delta between the address I am compiled to run at
+	 * and the address I am actually running at.
+	 */
+	load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map);
+
+	/* Is the address not 2M aligned? */
+	if (load_delta & ~PMD_PAGE_MASK)
+		for (;;);
+
+	/* Fixup the physical addresses in the page table */
+
+	pgd = fixup_pointer(&early_level4_pgt, physaddr);
+	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
+
+	pud = fixup_pointer(&level3_kernel_pgt, physaddr);
+	pud[510] += load_delta;
+	pud[511] += load_delta;
+
+	pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
+	pmd[506] += load_delta;
+
+	/*
+	 * Set up the identity mapping for the switchover.  These
+	 * entries should *NOT* have the global bit set!  This also
+	 * creates a bunch of nonsense entries but that is fine --
+	 * it avoids problems around wraparound.
+	 */
+
+	pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+	pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+
+	pgd[0] = (pgdval_t)pud + _KERNPG_TABLE;
+	pgd[1] = (pgdval_t)pud + _KERNPG_TABLE;
+
+	pud[0] = (pudval_t)pmd + _KERNPG_TABLE;
+	pud[1] = (pudval_t)pmd + _KERNPG_TABLE;
+
+	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	pmd_entry +=  physaddr;
+
+	for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++)
+		pmd[i + (physaddr >> PMD_SHIFT)] = pmd_entry + i * PMD_SIZE;
+
+	/*
+	 * Fix up the kernel text+data virtual addresses. Note that
+	 * we might write invalid pmds, when the kernel is relocated
+	 * cleanup_highmap() fixes this up along with the mappings
+	 * beyond _end.
+	 */
+
+	pmd = fixup_pointer(level2_kernel_pgt, physaddr);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (pmd[i] & _PAGE_PRESENT)
+			pmd[i] += load_delta;
+	}
+
+	/* Fix up phys_base */
+	p = fixup_pointer(&phys_base, physaddr);
+	*p += load_delta;
+}
+
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
 {
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ac9d327..9656c59 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -72,100 +72,9 @@ startup_64:
 	/* Sanitize CPU configuration */
 	call verify_cpu
 
-	/*
-	 * Compute the delta between the address I am compiled to run at and the
-	 * address I am actually running at.
-	 */
-	leaq	_text(%rip), %rbp
-	subq	$_text - __START_KERNEL_map, %rbp
-
-	/* Is the address not 2M aligned? */
-	testl	$~PMD_PAGE_MASK, %ebp
-	jnz	bad_address
-
-	/*
-	 * Is the address too large?
-	 */
-	leaq	_text(%rip), %rax
-	shrq	$MAX_PHYSMEM_BITS, %rax
-	jnz	bad_address
-
-	/*
-	 * Fixup the physical addresses in the page table
-	 */
-	addq	%rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip)
-
-	addq	%rbp, level3_kernel_pgt + (510*8)(%rip)
-	addq	%rbp, level3_kernel_pgt + (511*8)(%rip)
-
-	addq	%rbp, level2_fixmap_pgt + (506*8)(%rip)
-
-	/*
-	 * Set up the identity mapping for the switchover.  These
-	 * entries should *NOT* have the global bit set!  This also
-	 * creates a bunch of nonsense entries but that is fine --
-	 * it avoids problems around wraparound.
-	 */
 	leaq	_text(%rip), %rdi
-	leaq	early_level4_pgt(%rip), %rbx
-
-	movq	%rdi, %rax
-	shrq	$PGDIR_SHIFT, %rax
-
-	leaq	(PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx
-	movq	%rdx, 0(%rbx,%rax,8)
-	movq	%rdx, 8(%rbx,%rax,8)
-
-	addq	$PAGE_SIZE, %rdx
-	movq	%rdi, %rax
-	shrq	$PUD_SHIFT, %rax
-	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
-	incl	%eax
-	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
-
-	addq	$PAGE_SIZE * 2, %rbx
-	movq	%rdi, %rax
-	shrq	$PMD_SHIFT, %rdi
-	addq	$(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
-	leaq	(_end - 1)(%rip), %rcx
-	shrq	$PMD_SHIFT, %rcx
-	subq	%rdi, %rcx
-	incl	%ecx
+	call	__startup_64
 
-1:
-	andq	$(PTRS_PER_PMD - 1), %rdi
-	movq	%rax, (%rbx,%rdi,8)
-	incq	%rdi
-	addq	$PMD_SIZE, %rax
-	decl	%ecx
-	jnz	1b
-
-	test %rbp, %rbp
-	jz .Lskip_fixup
-
-	/*
-	 * Fixup the kernel text+data virtual addresses. Note that
-	 * we might write invalid pmds, when the kernel is relocated
-	 * cleanup_highmap() fixes this up along with the mappings
-	 * beyond _end.
-	 */
-	leaq	level2_kernel_pgt(%rip), %rdi
-	leaq	PAGE_SIZE(%rdi), %r8
-	/* See if it is a valid page table entry */
-1:	testb	$_PAGE_PRESENT, 0(%rdi)
-	jz	2f
-	addq	%rbp, 0(%rdi)
-	/* Go to the next page */
-2:	addq	$8, %rdi
-	cmp	%r8, %rdi
-	jne	1b
-
-	/* Fixup phys_base */
-	addq	%rbp, phys_base(%rip)
-
-.Lskip_fixup:
 	movq	$(early_level4_pgt - __START_KERNEL_map), %rax
 	jmp 1f
 ENTRY(secondary_startup_64)

[toc] | [next] | [standalone]

#1621228

On Tue, Apr 11, 2017 at 10:54:41AM +0200, Ingo Molnar wrote:
> 
> * tip-bot for Kirill A. Shutemov <tipbot@zytor.com> wrote:
> 
> > Commit-ID:  10ee822ec8c53f3987d969ce98b2686323a7fc2a
> > Gitweb:     http://git.kernel.org/tip/10ee822ec8c53f3987d969ce98b2686323a7fc2a
> > Author:     Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > AuthorDate: Thu, 6 Apr 2017 17:00:59 +0300
> > Committer:  Ingo Molnar <mingo@kernel.org>
> > CommitDate: Tue, 11 Apr 2017 08:57:37 +0200
> > 
> > x86/boot/64: Rewrite startup_64() in C
> > 
> > The patch converts most of the startup_64 logic from assembly to C.
> > 
> > This is preparation for 5-level paging enabling.
> > 
> > No change in functionality.
> > 
> > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > Cc: Andy Lutomirski <luto@amacapital.net>
> > Cc: Dave Hansen <dave.hansen@intel.com>
> > Cc: Linus Torvalds <torvalds@linux-foundation.org>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Thomas Gleixner <tglx@linutronix.de>
> > Cc: linux-arch@vger.kernel.org
> > Cc: linux-mm@kvack.org
> > Link: http://lkml.kernel.org/r/20170406140106.78087-2-kirill.shutemov@linux.intel.com
> > [ Small typo fixes. ]
> > Signed-off-by: Ingo Molnar <mingo@kernel.org>
> > ---
> >  arch/x86/kernel/head64.c  | 81 ++++++++++++++++++++++++++++++++++++++++-
> >  arch/x86/kernel/head_64.S | 93 +----------------------------------------------
> >  2 files changed, 81 insertions(+), 93 deletions(-)
> 
> Hm, so I had to zap this commit as it broke booting on a 64-bit Intel and an AMD 
> system as well, with defconfig-ish kernels.

The fixup is below. Maybe there's better more idiomatic way, but I'm not
really into assembly.

Basically, we need to preserve %rsi across call __startup_64.

I will post whole thing again once we sort out what to do with the reset
of assembly code I've touched. Or you can apply the fixup, if you feel to.

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 9656c5951b98..1432d530fa35 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -73,7 +73,9 @@ startup_64:
 	call verify_cpu
 
 	leaq	_text(%rip), %rdi
+	pushq	%rsi
 	call	__startup_64
+	popq	%rsi
 
 	movq	$(early_level4_pgt - __START_KERNEL_map), %rax
 	jmp 1f
-- 
 Kirill A. Shutemov

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web