diff mbox

[v3,5/7] arm64: move kernel mapping out of linear region

Message ID 1447672998-20981-6-git-send-email-ard.biesheuvel@linaro.org
State New
Headers show

Commit Message

Ard Biesheuvel Nov. 16, 2015, 11:23 a.m. UTC 
This moves the primary mapping of the kernel Image out of
the linear region. This is a preparatory step towards allowing
the kernel Image to reside anywhere in physical memory without
affecting the ability to map all of it efficiently.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

---
 arch/arm64/include/asm/boot.h           |  7 +++++++
 arch/arm64/include/asm/kernel-pgtable.h |  5 +++--
 arch/arm64/include/asm/memory.h         | 20 +++++++++++++++++---
 arch/arm64/kernel/head.S                | 18 +++++++++++++-----
 arch/arm64/kernel/vmlinux.lds.S         | 11 +++++++++--
 arch/arm64/mm/dump.c                    |  3 ++-
 arch/arm64/mm/mmu.c                     | 19 ++++++++++++++-----
 7 files changed, 65 insertions(+), 18 deletions(-)

-- 
1.9.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Comments

Catalin Marinas Dec. 7, 2015, 12:26 p.m. UTC | #1 
On Mon, Nov 16, 2015 at 12:23:16PM +0100, Ard Biesheuvel wrote:
> diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S

> index 23cfc08fc8ba..d3e4b5d6a8d2 100644

> --- a/arch/arm64/kernel/head.S

> +++ b/arch/arm64/kernel/head.S

[...]
> @@ -210,7 +210,15 @@ section_table:

>  ENTRY(stext)

>  	bl	preserve_boot_args

>  	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode

> -	adrp	x24, __PHYS_OFFSET

> +

> +	/*

> +	 * Before the linear mapping has been set up, __va() translations will

> +	 * not produce usable virtual addresses unless we tweak PHYS_OFFSET to

> +	 * compensate for the offset between the kernel mapping and the base of

> +	 * the linear mapping. We will undo this in map_mem().

> +	 */


Minor typo in comment: I guess you meant "__pa() translations will not
produce usable...".

> diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c

> index 5a22a119a74c..f6272f450688 100644

> --- a/arch/arm64/mm/dump.c

> +++ b/arch/arm64/mm/dump.c

> @@ -63,7 +63,8 @@ static struct addr_marker address_markers[] = {

>  	{ PCI_IO_END,		"PCI I/O end" },

>  	{ MODULES_VADDR,	"Modules start" },

>  	{ MODULES_END,		"Modules end" },

> -	{ PAGE_OFFSET,		"Kernel Mapping" },

> +	{ KIMAGE_VADDR,		"Kernel Mapping" },

> +	{ PAGE_OFFSET,		"Linear Mapping" },

>  	{ -1,			NULL },

>  };


Apart from this, please change the pr_notice() in mem_init() to show the
linear mapping at the end (keep them in ascending order).

-- 
Catalin

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Ard Biesheuvel Dec. 7, 2015, 12:33 p.m. UTC | #2 
On 7 December 2015 at 13:26, Catalin Marinas <catalin.marinas@arm.com> wrote:
> On Mon, Nov 16, 2015 at 12:23:16PM +0100, Ard Biesheuvel wrote:

>> diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S

>> index 23cfc08fc8ba..d3e4b5d6a8d2 100644

>> --- a/arch/arm64/kernel/head.S

>> +++ b/arch/arm64/kernel/head.S

> [...]

>> @@ -210,7 +210,15 @@ section_table:

>>  ENTRY(stext)

>>       bl      preserve_boot_args

>>       bl      el2_setup                       // Drop to EL1, w20=cpu_boot_mode

>> -     adrp    x24, __PHYS_OFFSET

>> +

>> +     /*

>> +      * Before the linear mapping has been set up, __va() translations will

>> +      * not produce usable virtual addresses unless we tweak PHYS_OFFSET to

>> +      * compensate for the offset between the kernel mapping and the base of

>> +      * the linear mapping. We will undo this in map_mem().

>> +      */

>

> Minor typo in comment: I guess you meant "__pa() translations will not

> produce usable...".

>


No, not quite. __va() translations will normally produce addresses in
the linear mapping, which will not be set up when we first start using
it in create_mapping(). So until that time, we have to redirect __va()
translations into the kernel mapping, where swapper_pg_dir is
shadowed. I am hoping that Mark's planned changes to create_mapping()
will make this unnecessary, but I haven't seen any of his code yet.

As far as __pa() is concerned, that translation is actually tweaked so
it will always produce usable addresses, regardless of whether the
bias is still set or not. The reason is that va-to-pa translations are
always unambiguous.

>> diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c

>> index 5a22a119a74c..f6272f450688 100644

>> --- a/arch/arm64/mm/dump.c

>> +++ b/arch/arm64/mm/dump.c

>> @@ -63,7 +63,8 @@ static struct addr_marker address_markers[] = {

>>       { PCI_IO_END,           "PCI I/O end" },

>>       { MODULES_VADDR,        "Modules start" },

>>       { MODULES_END,          "Modules end" },

>> -     { PAGE_OFFSET,          "Kernel Mapping" },

>> +     { KIMAGE_VADDR,         "Kernel Mapping" },

>> +     { PAGE_OFFSET,          "Linear Mapping" },

>>       { -1,                   NULL },

>>  };

>

> Apart from this, please change the pr_notice() in mem_init() to show the

> linear mapping at the end (keep them in ascending order).

>


OK

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Ard Biesheuvel Dec. 7, 2015, 12:34 p.m. UTC | #3 
On 7 December 2015 at 13:33, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> On 7 December 2015 at 13:26, Catalin Marinas <catalin.marinas@arm.com> wrote:

>> On Mon, Nov 16, 2015 at 12:23:16PM +0100, Ard Biesheuvel wrote:

>>> diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S

>>> index 23cfc08fc8ba..d3e4b5d6a8d2 100644

>>> --- a/arch/arm64/kernel/head.S

>>> +++ b/arch/arm64/kernel/head.S

>> [...]

>>> @@ -210,7 +210,15 @@ section_table:

>>>  ENTRY(stext)

>>>       bl      preserve_boot_args

>>>       bl      el2_setup                       // Drop to EL1, w20=cpu_boot_mode

>>> -     adrp    x24, __PHYS_OFFSET

>>> +

>>> +     /*

>>> +      * Before the linear mapping has been set up, __va() translations will

>>> +      * not produce usable virtual addresses unless we tweak PHYS_OFFSET to

>>> +      * compensate for the offset between the kernel mapping and the base of

>>> +      * the linear mapping. We will undo this in map_mem().

>>> +      */

>>

>> Minor typo in comment: I guess you meant "__pa() translations will not

>> produce usable...".

>>

>

> No, not quite. __va() translations will normally produce addresses in

> the linear mapping, which will not be set up when we first start using

> it in create_mapping(). So until that time, we have to redirect __va()

> translations into the kernel mapping, where swapper_pg_dir is

> shadowed. I am hoping that Mark's planned changes to create_mapping()

> will make this unnecessary, but I haven't seen any of his code yet.

>

> As far as __pa() is concerned, that translation is actually tweaked so

> it will always produce usable addresses, regardless of whether the

> bias is still set or not. The reason is that va-to-pa translations are

> always unambiguous.

>


... so of course, the comment is still wrong, -> s/virtual/physical/ addresses


>>> diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c

>>> index 5a22a119a74c..f6272f450688 100644

>>> --- a/arch/arm64/mm/dump.c

>>> +++ b/arch/arm64/mm/dump.c

>>> @@ -63,7 +63,8 @@ static struct addr_marker address_markers[] = {

>>>       { PCI_IO_END,           "PCI I/O end" },

>>>       { MODULES_VADDR,        "Modules start" },

>>>       { MODULES_END,          "Modules end" },

>>> -     { PAGE_OFFSET,          "Kernel Mapping" },

>>> +     { KIMAGE_VADDR,         "Kernel Mapping" },

>>> +     { PAGE_OFFSET,          "Linear Mapping" },

>>>       { -1,                   NULL },

>>>  };

>>

>> Apart from this, please change the pr_notice() in mem_init() to show the

>> linear mapping at the end (keep them in ascending order).

>>

>

> OK


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Catalin Marinas Dec. 7, 2015, 3:37 p.m. UTC | #4 
On Mon, Dec 07, 2015 at 01:34:19PM +0100, Ard Biesheuvel wrote:
> On 7 December 2015 at 13:33, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:

> > On 7 December 2015 at 13:26, Catalin Marinas <catalin.marinas@arm.com> wrote:

> >> On Mon, Nov 16, 2015 at 12:23:16PM +0100, Ard Biesheuvel wrote:

> >>> diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S

> >>> index 23cfc08fc8ba..d3e4b5d6a8d2 100644

> >>> --- a/arch/arm64/kernel/head.S

> >>> +++ b/arch/arm64/kernel/head.S

> >> [...]

> >>> @@ -210,7 +210,15 @@ section_table:

> >>>  ENTRY(stext)

> >>>       bl      preserve_boot_args

> >>>       bl      el2_setup                       // Drop to EL1, w20=cpu_boot_mode

> >>> -     adrp    x24, __PHYS_OFFSET

> >>> +

> >>> +     /*

> >>> +      * Before the linear mapping has been set up, __va() translations will

> >>> +      * not produce usable virtual addresses unless we tweak PHYS_OFFSET to

> >>> +      * compensate for the offset between the kernel mapping and the base of

> >>> +      * the linear mapping. We will undo this in map_mem().

> >>> +      */

> >>

> >> Minor typo in comment: I guess you meant "__pa() translations will not

> >> produce usable...".

> >

> > No, not quite. __va() translations will normally produce addresses in

> > the linear mapping, which will not be set up when we first start using

> > it in create_mapping(). So until that time, we have to redirect __va()

> > translations into the kernel mapping, where swapper_pg_dir is

> > shadowed.


I guessed what you meant and I remember the reason based on past
discussions, only that to me "linear mapping" sounds like something in
virtual space while __va() generates a linear mapping -> physical
translation (just some wording, nothing serious).

> > I am hoping that Mark's planned changes to create_mapping()

> > will make this unnecessary, but I haven't seen any of his code yet.


Not sure, I haven't seen the details yet.

> > As far as __pa() is concerned, that translation is actually tweaked so

> > it will always produce usable addresses, regardless of whether the

> > bias is still set or not. The reason is that va-to-pa translations are

> > always unambiguous.


Only that very early during boot memstart_addr is still based on the
kernel load address rather than memblock_start_of_DRAM(), that's why I
thought you meant __pa().

> ... so of course, the comment is still wrong, -> s/virtual/physical/

> addresses


This would do.

-- 
Catalin

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
diff mbox

Patch

diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
index 81151b67b26b..092d1096ce9a 100644
--- a/arch/arm64/include/asm/boot.h
+++ b/arch/arm64/include/asm/boot.h
@@ -11,4 +11,11 @@ 
 #define MIN_FDT_ALIGN		8
 #define MAX_FDT_SIZE		SZ_2M
 
+/*
+ * arm64 requires the kernel image to be 2 MB aligned and
+ * not exceed 64 MB in size.
+ */
+#define MIN_KIMG_ALIGN		SZ_2M
+#define MAX_KIMG_SIZE		SZ_64M
+
 #endif
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index a459714ee29e..daa8a7b9917a 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -70,8 +70,9 @@ 
 /*
  * Initial memory map attributes.
  */
-#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN)
+#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | \
+				 PMD_SECT_UXN)
 
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 853953cd1f08..3148691bc80a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -24,6 +24,7 @@ 
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/types.h>
+#include <asm/boot.h>
 #include <asm/sizes.h>
 
 /*
@@ -39,7 +40,12 @@ 
 #define PCI_IO_SIZE		SZ_16M
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * Offset below PAGE_OFFSET where to map the kernel Image.
+ */
+#define KIMAGE_OFFSET		MAX_KIMG_SIZE
+
+/*
+ * PAGE_OFFSET - the virtual address of the base of the linear mapping (top
  *		 (VA_BITS - 1))
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
@@ -51,7 +57,8 @@ 
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define VA_START		(UL(0xffffffffffffffff) << VA_BITS)
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
-#define MODULES_END		(PAGE_OFFSET)
+#define KIMAGE_VADDR		(PAGE_OFFSET - KIMAGE_OFFSET)
+#define MODULES_END		KIMAGE_VADDR
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
 #define PCI_IO_END		(MODULES_VADDR - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
@@ -75,7 +82,11 @@ 
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
  */
-#define __virt_to_phys(x)	(((phys_addr_t)(x) - PAGE_OFFSET + PHYS_OFFSET))
+#define __virt_to_phys(x) ({						\
+	long __x = (long)(x) - PAGE_OFFSET;				\
+	__x >= 0 ? (phys_addr_t)(__x + PHYS_OFFSET) : 			\
+		   (phys_addr_t)(__x + PHYS_OFFSET + kernel_va_offset); })
+
 #define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET + PAGE_OFFSET))
 
 /*
@@ -106,6 +117,8 @@  extern phys_addr_t		memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ memstart_addr; })
 
+extern u64 kernel_va_offset;
+
 /*
  * The maximum physical address that the linear direct mapping
  * of system RAM can cover. (PAGE_OFFSET can be interpreted as
@@ -113,6 +126,7 @@  extern phys_addr_t		memstart_addr;
  * maximum size of the linear mapping.)
  */
 #define MAX_MEMBLOCK_ADDR	({ memstart_addr - PAGE_OFFSET - 1; })
+#define MIN_MEMBLOCK_ADDR	__pa(KIMAGE_VADDR)
 
 /*
  * PFNs are used to describe any physical page; this means
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 23cfc08fc8ba..d3e4b5d6a8d2 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -38,8 +38,6 @@ 
 #include <asm/thread_info.h>
 #include <asm/virt.h>
 
-#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
-
 #if (TEXT_OFFSET & 0xfff) != 0
 #error TEXT_OFFSET must be at least 4KB aligned
 #elif (PAGE_OFFSET & 0x1fffff) != 0
@@ -50,6 +48,8 @@ 
 
 #define KERNEL_START	_text
 #define KERNEL_END	_end
+#define KERNEL_BASE	(KERNEL_START - TEXT_OFFSET)
+
 
 /*
  * Kernel startup entry point.
@@ -210,7 +210,15 @@  section_table:
 ENTRY(stext)
 	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
-	adrp	x24, __PHYS_OFFSET
+
+	/*
+	 * Before the linear mapping has been set up, __va() translations will
+	 * not produce usable virtual addresses unless we tweak PHYS_OFFSET to
+	 * compensate for the offset between the kernel mapping and the base of
+	 * the linear mapping. We will undo this in map_mem().
+	 */
+	adrp	x24, KERNEL_BASE + KIMAGE_OFFSET
+
 	bl	set_cpu_boot_mode_flag
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
@@ -389,10 +397,10 @@  __create_page_tables:
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
 	mov	x0, x26				// swapper_pg_dir
-	mov	x5, #PAGE_OFFSET
+	ldr	x5, =KERNEL_BASE
 	create_pgd_entry x0, x5, x3, x6
 	ldr	x6, =KERNEL_END			// __va(KERNEL_END)
-	mov	x3, x24				// phys offset
+	adrp	x3, KERNEL_BASE			// real PHYS_OFFSET
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 63fca196c09e..84f780e6b039 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -7,6 +7,7 @@ 
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
+#include <asm/boot.h>
 #include <asm/memory.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -99,7 +100,7 @@  SECTIONS
 		*(.discard.*)
 	}
 
-	. = PAGE_OFFSET + TEXT_OFFSET;
+	. = KIMAGE_VADDR + TEXT_OFFSET;
 
 	.head.text : {
 		_text = .;
@@ -207,4 +208,10 @@  ASSERT(SIZEOF(.pgdir) <= ALIGNOF(.pgdir), ".pgdir size exceeds its alignment")
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
  */
-ASSERT(_text == (PAGE_OFFSET + TEXT_OFFSET), "HEAD is misaligned")
+ASSERT(_text == (KIMAGE_VADDR + TEXT_OFFSET), "HEAD is misaligned")
+
+/*
+ * Make sure the memory footprint of the kernel Image does not exceed the limit.
+ */
+ASSERT(_end - _text + TEXT_OFFSET <= MAX_KIMG_SIZE,
+	"Kernel Image memory footprint exceeds MAX_KIMG_SIZE")
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 5a22a119a74c..f6272f450688 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -63,7 +63,8 @@  static struct addr_marker address_markers[] = {
 	{ PCI_IO_END,		"PCI I/O end" },
 	{ MODULES_VADDR,	"Modules start" },
 	{ MODULES_END,		"Modules end" },
-	{ PAGE_OFFSET,		"Kernel Mapping" },
+	{ KIMAGE_VADDR,		"Kernel Mapping" },
+	{ PAGE_OFFSET,		"Linear Mapping" },
 	{ -1,			NULL },
 };
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 81bb49eaa1a3..c7ba171951c8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -51,6 +51,9 @@  u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 struct page *empty_zero_page;
 EXPORT_SYMBOL(empty_zero_page);
 
+u64 kernel_va_offset __read_mostly;
+EXPORT_SYMBOL(kernel_va_offset);
+
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -479,6 +482,9 @@  static unsigned long __init bootstrap_region(struct bootstrap_pgtables *reg,
  * Bootstrap the linear ranges that cover the start of DRAM and swapper_pg_dir
  * so that the statically allocated page tables as well as newly allocated ones
  * are accessible via the linear mapping.
+ * Since at this point, PHYS_OFFSET is still biased to redirect __va()
+ * translations into the kernel text mapping, we need to apply an
+ * explicit va_offset to calculate linear virtual addresses.
  */
 static void __init bootstrap_linear_mapping(unsigned long va_offset)
 {
@@ -513,7 +519,10 @@  static void __init map_mem(void)
 {
 	struct memblock_region *reg;
 
-	bootstrap_linear_mapping(0);
+	bootstrap_linear_mapping(KIMAGE_OFFSET);
+
+	kernel_va_offset = KIMAGE_OFFSET;
+	memstart_addr -= KIMAGE_OFFSET;
 
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
@@ -535,12 +544,12 @@  static void __init fixup_executable(void)
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
 	if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) {
-		unsigned long aligned_start = round_down(__pa(_stext),
+		unsigned long aligned_start = round_down((unsigned long)_stext,
 							 SWAPPER_BLOCK_SIZE);
 
-		create_mapping(aligned_start, __phys_to_virt(aligned_start),
-				__pa(_stext) - aligned_start,
-				PAGE_KERNEL);
+		create_mapping(__pa(_stext), aligned_start,
+			       (unsigned long)_stext - aligned_start,
+			       PAGE_KERNEL);
 	}
 
 	if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) {