[PATCH for-v4.2 0/4] arm64: EFI minimal FDT and Image placement fixes

[PATCH for-v4.2 0/4] arm64: EFI minimal FDT and Image placement fixes

[Ard Biesheuvel]

The EFI stub may place the Image or FDT in a memory location that is
not allowed by the arm64/Linux boot protocol. Instead of fixing the stub,
these patches relax the placement rules for Image and FDT so that the
placement logic employed by the EFI stub is guaranteed to produce correct
values.

These 4 patches have been split off from these series

http://thread.gmane.org/gmane.linux.kernel.efi/5736 (8 patches)
http://thread.gmane.org/gmane.linux.ports.arm.kernel/411718 (10 patches)

so that they may still be considered for inclusion in v4.2.

Changes since previous versions:
- added acks/R-b/T-b from Catalin and Mark Rutland
- improved Documentation text in patch #2

Ard Biesheuvel (4):
  of/fdt: split off FDT self reservation from memreserve processing
  arm64: use fixmap region for permanent FDT mapping
  arm64: reduce ID map to a single page
  arm64: drop sleep_idmap_phys and clean up cpu_resume()

 Documentation/arm64/booting.txt | 10 ++++---
 arch/arm/mm/init.c              |  1 +
 arch/arm64/include/asm/boot.h   | 14 +++++++++
 arch/arm64/include/asm/fixmap.h | 15 ++++++++++
 arch/arm64/include/asm/mmu.h    |  1 +
 arch/arm64/kernel/head.S        | 52 +++++---------------------------
 arch/arm64/kernel/setup.c       | 30 +++++++------------
 arch/arm64/kernel/sleep.S       |  9 +++---
 arch/arm64/kernel/suspend.c     |  3 --
 arch/arm64/kernel/vmlinux.lds.S | 11 ++++++-
 arch/arm64/mm/Makefile          |  2 ++
 arch/arm64/mm/mmu.c             | 66 +++++++++++++++++++++++++++++++++++++++++
 arch/arm64/mm/proc.S            |  3 +-
 arch/powerpc/kernel/prom.c      |  1 +
 drivers/of/fdt.c                | 19 ++++++++----
 include/linux/of_fdt.h          |  2 ++
 16 files changed, 156 insertions(+), 83 deletions(-)
 create mode 100644 arch/arm64/include/asm/boot.h

-- 
1.9.1

[PATCH for-v4.2 1/4] of/fdt: split off FDT self reservation from memreserve processing

[Ard Biesheuvel]

This splits off the reservation of the memory occupied by the FDT
binary itself from the processing of the memory reservations it
contains. This is necessary because the physical address of the FDT,
which is needed to perform the reservation, may not be known to the
FDT driver core, i.e., it may be mapped outside the linear direct
mapping, in which case __pa() returns a bogus value.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/mm/init.c         |  1 +
 arch/arm64/mm/init.c       |  1 +
 arch/powerpc/kernel/prom.c |  1 +
 drivers/of/fdt.c           | 19 ++++++++++++++-----
 include/linux/of_fdt.h     |  2 ++
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index be92fa0f2f35..8a63b4cdc0f2 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -268,6 +268,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 	if (mdesc->reserve)
 		mdesc->reserve();
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* reserve memory for DMA contiguous allocations */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 597831bdddf3..89a05f467ffb 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -170,6 +170,7 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* 4GB maximum for 32-bit only capable devices */
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 308c5e15676b..51ea36f79307 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -573,6 +573,7 @@ static void __init early_reserve_mem_dt(void)
 	int len;
 	const __be32 *prop;
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	dt_root = of_get_flat_dt_root();
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index cde35c5d0191..f2dd23a32267 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -580,11 +580,6 @@ void __init early_init_fdt_scan_reserved_mem(void)
 	if (!initial_boot_params)
 		return;
 
-	/* Reserve the dtb region */
-	early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
-					  fdt_totalsize(initial_boot_params),
-					  0);
-
 	/* Process header /memreserve/ fields */
 	for (n = 0; ; n++) {
 		fdt_get_mem_rsv(initial_boot_params, n, &base, &size);
@@ -598,6 +593,20 @@ void __init early_init_fdt_scan_reserved_mem(void)
 }
 
 /**
+ * early_init_fdt_reserve_self() - reserve the memory used by the FDT blob
+ */
+void __init early_init_fdt_reserve_self(void)
+{
+	if (!initial_boot_params)
+		return;
+
+	/* Reserve the dtb region */
+	early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
+					  fdt_totalsize(initial_boot_params),
+					  0);
+}
+
+/**
  * of_scan_flat_dt - scan flattened tree blob and call callback on each.
  * @it: callback function
  * @data: context data pointer
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 587ee507965d..fd627a58068f 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -64,6 +64,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern void early_init_fdt_scan_reserved_mem(void);
+extern void early_init_fdt_reserve_self(void);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
 extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
 					     bool no_map);
@@ -91,6 +92,7 @@ extern u64 fdt_translate_address(const void *blob, int node_offset);
 extern void of_fdt_limit_memory(int limit);
 #else /* CONFIG_OF_FLATTREE */
 static inline void early_init_fdt_scan_reserved_mem(void) {}
+static inline void early_init_fdt_reserve_self(void) {}
 static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
 static inline void unflatten_device_tree(void) {}
 static inline void unflatten_and_copy_device_tree(void) {}
-- 
1.9.1

[PATCH for-v4.2 2/4] arm64: use fixmap region for permanent FDT mapping

[Ard Biesheuvel]

Currently, the FDT blob needs to be in the same 512 MB region as
the kernel, so that it can be mapped into the kernel virtual memory
space very early on using a minimal set of statically allocated
translation tables.

Now that we have early fixmap support, we can relax this restriction,
by moving the permanent FDT mapping to the fixmap region instead.
This way, the FDT blob may be anywhere in memory.

This also moves the vetting of the FDT to mmu.c, since the early
init code in head.S does not handle mapping of the FDT anymore.
At the same time, fix up some comments in head.S that have gone stale.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 Documentation/arm64/booting.txt | 10 ++++---
 arch/arm64/include/asm/boot.h   | 14 +++++++++
 arch/arm64/include/asm/fixmap.h | 15 ++++++++++
 arch/arm64/include/asm/mmu.h    |  1 +
 arch/arm64/kernel/head.S        | 39 +-----------------------
 arch/arm64/kernel/setup.c       | 30 +++++++------------
 arch/arm64/mm/Makefile          |  2 ++
 arch/arm64/mm/init.c            |  1 -
 arch/arm64/mm/mmu.c             | 66 +++++++++++++++++++++++++++++++++++++++++
 9 files changed, 115 insertions(+), 63 deletions(-)
 create mode 100644 arch/arm64/include/asm/boot.h

diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index f3c05b5f9f08..1690350f16e7 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -45,11 +45,13 @@ sees fit.)
 
 Requirement: MANDATORY
 
-The device tree blob (dtb) must be placed on an 8-byte boundary within
-the first 512 megabytes from the start of the kernel image and must not
-cross a 2-megabyte boundary. This is to allow the kernel to map the
-blob using a single section mapping in the initial page tables.
+The device tree blob (dtb) must be placed on an 8-byte boundary and must
+not exceed 2 megabytes in size. Since the dtb will be mapped cacheable
+using blocks of up to 2 megabytes in size, it must not be placed within
+any 2M region which must be mapped with any specific attributes.
 
+NOTE: versions prior to v4.2 also require that the DTB be placed within
+the 512 MB region starting at text_offset bytes below the kernel Image.
 
 3. Decompress the kernel image
 ------------------------------
diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
new file mode 100644
index 000000000000..81151b67b26b
--- /dev/null
+++ b/arch/arm64/include/asm/boot.h
@@ -0,0 +1,14 @@
+
+#ifndef __ASM_BOOT_H
+#define __ASM_BOOT_H
+
+#include <asm/sizes.h>
+
+/*
+ * arm64 requires the DTB to be 8 byte aligned and
+ * not exceed 2MB in size.
+ */
+#define MIN_FDT_ALIGN		8
+#define MAX_FDT_SIZE		SZ_2M
+
+#endif
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 95e6b6dcbe37..c0739187a920 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
+#include <asm/boot.h>
 #include <asm/page.h>
 
 /*
@@ -32,6 +33,20 @@
  */
 enum fixed_addresses {
 	FIX_HOLE,
+
+	/*
+	 * Reserve a virtual window for the FDT that is 2 MB larger than the
+	 * maximum supported size, and put it at the top of the fixmap region.
+	 * The additional space ensures that any FDT that does not exceed
+	 * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
+	 * 2 MB alignment boundaries.
+	 *
+	 * Keep this at the top so it remains 2 MB aligned.
+	 */
+#define FIX_FDT_SIZE		(MAX_FDT_SIZE + SZ_2M)
+	FIX_FDT_END,
+	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
 	FIX_EARLYCON_MEM_BASE,
 	FIX_TEXT_POKE0,
 	__end_of_permanent_fixed_addresses,
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 3d311761e3c2..79fcfb048884 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -34,5 +34,6 @@ extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot);
+extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 
 #endif
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 19f915e8f6e0..30cffc5e7402 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -237,8 +237,6 @@ ENTRY(stext)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
-
-	bl	__vet_fdt
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -270,24 +268,6 @@ preserve_boot_args:
 ENDPROC(preserve_boot_args)
 
 /*
- * Determine validity of the x21 FDT pointer.
- * The dtb must be 8-byte aligned and live in the first 512M of memory.
- */
-__vet_fdt:
-	tst	x21, #0x7
-	b.ne	1f
-	cmp	x21, x24
-	b.lt	1f
-	mov	x0, #(1 << 29)
-	add	x0, x0, x24
-	cmp	x21, x0
-	b.ge	1f
-	ret
-1:
-	mov	x21, #0
-	ret
-ENDPROC(__vet_fdt)
-/*
  * Macro to create a table entry to the next page.
  *
  *	tbl:	page table address
@@ -348,8 +328,7 @@ ENDPROC(__vet_fdt)
  * required to get the kernel running. The following sections are required:
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
- *     been enabled, including the FDT blob (TTBR1)
- *   - pgd entry for fixed mappings (TTBR1)
+ *     been enabled
  */
 __create_page_tables:
 	adrp	x25, idmap_pg_dir
@@ -439,22 +418,6 @@ __create_page_tables:
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
-	 * Map the FDT blob (maximum 2MB; must be within 512MB of
-	 * PHYS_OFFSET).
-	 */
-	mov	x3, x21				// FDT phys address
-	and	x3, x3, #~((1 << 21) - 1)	// 2MB aligned
-	mov	x6, #PAGE_OFFSET
-	sub	x5, x3, x24			// subtract PHYS_OFFSET
-	tst	x5, #~((1 << 29) - 1)		// within 512MB?
-	csel	x21, xzr, x21, ne		// zero the FDT pointer
-	b.ne	1f
-	add	x5, x5, x6			// __va(FDT blob)
-	add	x6, x5, #1 << 21		// 2MB for the FDT blob
-	sub	x6, x6, #1			// inclusive range
-	create_block_map x0, x7, x3, x5, x6
-1:
-	/*
 	 * Since the page tables have been populated with non-cacheable
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 74753132c3ac..770ae9dc5a75 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -105,18 +105,6 @@ static struct resource mem_res[] = {
 #define kernel_code mem_res[0]
 #define kernel_data mem_res[1]
 
-void __init early_print(const char *str, ...)
-{
-	char buf[256];
-	va_list ap;
-
-	va_start(ap, str);
-	vsnprintf(buf, sizeof(buf), str, ap);
-	va_end(ap);
-
-	printk("%s", buf);
-}
-
 /*
  * The recorded values of x0 .. x3 upon kernel entry.
  */
@@ -326,12 +314,14 @@ static void __init setup_processor(void)
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) {
-		early_print("\n"
-			"Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n"
-			"The dtb must be 8-byte aligned and passed in the first 512MB of memory\n"
-			"\nPlease check your bootloader.\n",
-			dt_phys, phys_to_virt(dt_phys));
+	void *dt_virt = fixmap_remap_fdt(dt_phys);
+
+	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
+		pr_crit("\n"
+			"Error: invalid device tree blob@physical address %pa (virtual address 0x%p)\n"
+			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
+			"\nPlease check your bootloader.",
+			&dt_phys, dt_virt);
 
 		while (true)
 			cpu_relax();
@@ -374,8 +364,6 @@ void __init setup_arch(char **cmdline_p)
 {
 	setup_processor();
 
-	setup_machine_fdt(__fdt_pointer);
-
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -386,6 +374,8 @@ void __init setup_arch(char **cmdline_p)
 	early_fixmap_init();
 	early_ioremap_init();
 
+	setup_machine_fdt(__fdt_pointer);
+
 	parse_early_param();
 
 	/*
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 773d37a14039..9d84feb41a16 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,3 +4,5 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+
+CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 89a05f467ffb..597831bdddf3 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -170,7 +170,6 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
-	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* 4GB maximum for 32-bit only capable devices */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5b8b664422d3..82d3435bf14f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
@@ -643,3 +644,68 @@ void __set_fixmap(enum fixed_addresses idx,
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
+{
+	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+	pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
+	int granularity, size, offset;
+	void *dt_virt;
+
+	/*
+	 * Check whether the physical FDT address is set and meets the minimum
+	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
+	 * at least 8 bytes so that we can always access the size field of the
+	 * FDT header after mapping the first chunk, double check here if that
+	 * is indeed the case.
+	 */
+	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+		return NULL;
+
+	/*
+	 * Make sure that the FDT region can be mapped without the need to
+	 * allocate additional translation table pages, so that it is safe
+	 * to call create_mapping() this early.
+	 *
+	 * On 64k pages, the FDT will be mapped using PTEs, so we need to
+	 * be in the same PMD as the rest of the fixmap.
+	 * On 4k pages, we'll use section mappings for the FDT so we only
+	 * have to be in the same PUD.
+	 */
+	BUILD_BUG_ON(dt_virt_base % SZ_2M);
+
+	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT);
+
+		granularity = PAGE_SIZE;
+	} else {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT);
+
+		granularity = PMD_SIZE;
+	}
+
+	offset = dt_phys % granularity;
+	dt_virt = (void *)dt_virt_base + offset;
+
+	/* map the first chunk so we can read the size from the header */
+	create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+		       granularity, prot);
+
+	if (fdt_check_header(dt_virt) != 0)
+		return NULL;
+
+	size = fdt_totalsize(dt_virt);
+	if (size > MAX_FDT_SIZE)
+		return NULL;
+
+	if (offset + size > granularity)
+		create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+			       round_up(offset + size, granularity), prot);
+
+	memblock_reserve(dt_phys, size);
+
+	return dt_virt;
+}
-- 
1.9.1

[PATCH for-v4.2 3/4] arm64: reduce ID map to a single page

[Ard Biesheuvel]

Commit ea8c2e112445 ("arm64: Extend the idmap to the whole kernel
image") changed the early page table code so that the entire kernel
Image is covered by the identity map. This allows functions that
need to enable or disable the MMU to reside anywhere in the kernel
Image.

However, this change has the unfortunate side effect that the Image
cannot cross a physical 512 MB alignment boundary anymore, since the
early page table code cannot deal with the Image crossing a /virtual/
512 MB alignment boundary.

So instead, reduce the ID map to a single page, that is populated by
the contents of the .idmap.text section. Only three functions reside
there at the moment: __enable_mmu(), cpu_resume_mmu() and cpu_reset().
If new code is introduced that needs to manipulate the MMU state, it
should be added to this section as well.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/kernel/head.S        | 13 +++++++------
 arch/arm64/kernel/sleep.S       |  2 ++
 arch/arm64/kernel/vmlinux.lds.S | 11 ++++++++++-
 arch/arm64/mm/proc.S            |  3 ++-
 4 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 30cffc5e7402..c0ff3ce4299e 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -361,7 +361,7 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	mov	x0, x25				// idmap_pg_dir
-	adrp	x3, KERNEL_START		// __pa(KERNEL_START)
+	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
 #ifndef CONFIG_ARM64_VA_BITS_48
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
@@ -384,11 +384,11 @@ __create_page_tables:
 
 	/*
 	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
-	 * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used),
+	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
 	 * this number conveniently equals the number of leading zeroes in
-	 * the physical address of KERNEL_END.
+	 * the physical address of __idmap_text_end.
 	 */
-	adrp	x5, KERNEL_END
+	adrp	x5, __idmap_text_end
 	clz	x5, x5
 	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
 	b.ge	1f			// .. then skip additional level
@@ -403,8 +403,8 @@ __create_page_tables:
 #endif
 
 	create_pgd_entry x0, x3, x5, x6
-	mov	x5, x3				// __pa(KERNEL_START)
-	adr_l	x6, KERNEL_END			// __pa(KERNEL_END)
+	mov	x5, x3				// __pa(__idmap_text_start)
+	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
@@ -632,6 +632,7 @@ ENDPROC(__secondary_switched)
  *
  * other registers depend on the function called upon completion
  */
+	.section	".idmap.text", "ax"
 __enable_mmu:
 	ldr	x5, =vectors
 	msr	vbar_el1, x5
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ede186cdd452..811e61a2d847 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -130,12 +130,14 @@ ENDPROC(__cpu_suspend_enter)
 /*
  * x0 must contain the sctlr value retrieved from restored context
  */
+	.pushsection	".idmap.text", "ax"
 ENTRY(cpu_resume_mmu)
 	ldr	x3, =cpu_resume_after_mmu
 	msr	sctlr_el1, x0		// restore sctlr_el1
 	isb
 	br	x3			// global jump to virtual address
 ENDPROC(cpu_resume_mmu)
+	.popsection
 cpu_resume_after_mmu:
 	mov	x0, #0			// return zero on success
 	ldp	x19, x20, [sp, #16]
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index a2c29865c3fe..98073332e2d0 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -38,6 +38,12 @@ jiffies = jiffies_64;
 	*(.hyp.text)					\
 	VMLINUX_SYMBOL(__hyp_text_end) = .;
 
+#define IDMAP_TEXT					\
+	. = ALIGN(SZ_4K);				\
+	VMLINUX_SYMBOL(__idmap_text_start) = .;		\
+	*(.idmap.text)					\
+	VMLINUX_SYMBOL(__idmap_text_end) = .;
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -95,6 +101,7 @@ SECTIONS
 			SCHED_TEXT
 			LOCK_TEXT
 			HYPERVISOR_TEXT
+			IDMAP_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
@@ -167,11 +174,13 @@ SECTIONS
 }
 
 /*
- * The HYP init code can't be more than a page long,
+ * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.
  */
 ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
 	"HYP init code too big or misaligned")
+ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
+	"ID map text too big or misaligned")
 
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cdd754e19b9b..a265934ab0af 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -67,7 +67,7 @@ ENDPROC(cpu_cache_off)
  *
  *	- loc   - location to jump to for soft reset
  */
-	.align	5
+	.pushsection	".idmap.text", "ax"
 ENTRY(cpu_reset)
 	mrs	x1, sctlr_el1
 	bic	x1, x1, #1
@@ -75,6 +75,7 @@ ENTRY(cpu_reset)
 	isb
 	ret	x0
 ENDPROC(cpu_reset)
+	.popsection
 
 ENTRY(cpu_soft_restart)
 	/* Save address of cpu_reset() and reset address */
-- 
1.9.1

[PATCH for-v4.2 4/4] arm64: drop sleep_idmap_phys and clean up cpu_resume()

[Ard Biesheuvel]

Two cleanups of the asm function cpu_resume():
- The global variable sleep_idmap_phys always points to idmap_pg_dir,
  so we can just use that value directly in the CPU resume path.
- Unclutter the load of sleep_save_sp::save_ptr_stash_phys.

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/kernel/sleep.S   | 7 ++-----
 arch/arm64/kernel/suspend.c | 3 ---
 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 811e61a2d847..803cfea41962 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -164,15 +164,12 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adrp	x0, sleep_save_sp
-	add	x0, x0, #:lo12:sleep_save_sp
-	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
+	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
+	adrp	x1, idmap_pg_dir
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index d7daf45ae7a2..f6073c27d65f 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -118,7 +118,6 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 }
 
 struct sleep_save_sp sleep_save_sp;
-phys_addr_t sleep_idmap_phys;
 
 static int __init cpu_suspend_init(void)
 {
@@ -132,9 +131,7 @@ static int __init cpu_suspend_init(void)
 
 	sleep_save_sp.save_ptr_stash = ctx_ptr;
 	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
-	sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
 	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
-	__flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
 
 	return 0;
 }
-- 
1.9.1

[PATCH for-v4.2 1/4] of/fdt: split off FDT self reservation from memreserve processing

[Catalin Marinas]

On Mon, Jun 01, 2015 at 01:40:31PM +0200, Ard Biesheuvel wrote:
> This splits off the reservation of the memory occupied by the FDT
> binary itself from the processing of the memory reservations it
> contains. This is necessary because the physical address of the FDT,
> which is needed to perform the reservation, may not be known to the
> FDT driver core, i.e., it may be mapped outside the linear direct
> mapping, in which case __pa() returns a bogus value.
> 
> Cc: Russell King <linux@arm.linux.org.uk>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Acked-by: Rob Herring <robh@kernel.org>
> Acked-by: Mark Rutland <mark.rutland@arm.com>
> Acked-by: Catalin Marinas <catalin.marinas@arm.com>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
>  arch/arm/mm/init.c         |  1 +
>  arch/arm64/mm/init.c       |  1 +
>  arch/powerpc/kernel/prom.c |  1 +
>  drivers/of/fdt.c           | 19 ++++++++++++++-----
>  include/linux/of_fdt.h     |  2 ++
>  5 files changed, 19 insertions(+), 5 deletions(-)

I'm happy to take this patch (already acked by the DT maintainers)
through the arm64 tree but it would be good to have an ack from the arch
maintainers as well (i.e. Russell, Ben, Paul).

Thanks.

-- 
Catalin

[PATCH for-v4.2 1/4] of/fdt: split off FDT self reservation from memreserve processing

[Ard Biesheuvel]

On 1 June 2015 at 19:33, Catalin Marinas <catalin.marinas@arm.com> wrote:
> On Mon, Jun 01, 2015 at 01:40:31PM +0200, Ard Biesheuvel wrote:
>> This splits off the reservation of the memory occupied by the FDT
>> binary itself from the processing of the memory reservations it
>> contains. This is necessary because the physical address of the FDT,
>> which is needed to perform the reservation, may not be known to the
>> FDT driver core, i.e., it may be mapped outside the linear direct
>> mapping, in which case __pa() returns a bogus value.
>>
>> Cc: Russell King <linux@arm.linux.org.uk>
>> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> Cc: Paul Mackerras <paulus@samba.org>
>> Acked-by: Rob Herring <robh@kernel.org>
>> Acked-by: Mark Rutland <mark.rutland@arm.com>
>> Acked-by: Catalin Marinas <catalin.marinas@arm.com>
>> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
>> ---
>>  arch/arm/mm/init.c         |  1 +
>>  arch/arm64/mm/init.c       |  1 +
>>  arch/powerpc/kernel/prom.c |  1 +
>>  drivers/of/fdt.c           | 19 ++++++++++++++-----
>>  include/linux/of_fdt.h     |  2 ++
>>  5 files changed, 19 insertions(+), 5 deletions(-)
>
> I'm happy to take this patch (already acked by the DT maintainers)
> through the arm64 tree but it would be good to have an ack from the arch
> maintainers as well (i.e. Russell, Ben, Paul).
>

OK, fair enough,

@Ben, Paul
@Russell

Could you please indicate whether or not you have any objections to this patch?

Kind regards,
Ard.

[PATCH for-v4.2 1/4] of/fdt: split off FDT self reservation from memreserve processing

[Catalin Marinas]

On Mon, Jun 01, 2015 at 09:36:28PM +0200, Ard Biesheuvel wrote:
> On 1 June 2015 at 19:33, Catalin Marinas <catalin.marinas@arm.com> wrote:
> > On Mon, Jun 01, 2015 at 01:40:31PM +0200, Ard Biesheuvel wrote:
> >> This splits off the reservation of the memory occupied by the FDT
> >> binary itself from the processing of the memory reservations it
> >> contains. This is necessary because the physical address of the FDT,
> >> which is needed to perform the reservation, may not be known to the
> >> FDT driver core, i.e., it may be mapped outside the linear direct
> >> mapping, in which case __pa() returns a bogus value.
> >>
> >> Cc: Russell King <linux@arm.linux.org.uk>
> >> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> >> Cc: Paul Mackerras <paulus@samba.org>
> >> Acked-by: Rob Herring <robh@kernel.org>
> >> Acked-by: Mark Rutland <mark.rutland@arm.com>
> >> Acked-by: Catalin Marinas <catalin.marinas@arm.com>
> >> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> >> ---
> >>  arch/arm/mm/init.c         |  1 +
> >>  arch/arm64/mm/init.c       |  1 +
> >>  arch/powerpc/kernel/prom.c |  1 +
> >>  drivers/of/fdt.c           | 19 ++++++++++++++-----
> >>  include/linux/of_fdt.h     |  2 ++
> >>  5 files changed, 19 insertions(+), 5 deletions(-)
> >
> > I'm happy to take this patch (already acked by the DT maintainers)
> > through the arm64 tree but it would be good to have an ack from the arch
> > maintainers as well (i.e. Russell, Ben, Paul).
> 
> OK, fair enough,
> 
> @Ben, Paul
> @Russell
> 
> Could you please indicate whether or not you have any objections to this patch?

I'm going to push this patch into -next via the arm64 tree. If there are
objections before the merging window, please let me know (looking at the
previous commits adding early_init_fdt_scan_reserved_mem(), they were
only acked by the DT maintainers).

I merged this series of 4 patches.

Thanks.

-- 
Catalin

[PATCH for-v4.2 1/4] of/fdt: split off FDT self reservation from memreserve processing

[Benjamin Herrenschmidt]

On Mon, 2015-06-01 at 13:40 +0200, Ard Biesheuvel wrote:
> This splits off the reservation of the memory occupied by the FDT
> binary itself from the processing of the memory reservations it
> contains. This is necessary because the physical address of the FDT,
> which is needed to perform the reservation, may not be known to the
> FDT driver core, i.e., it may be mapped outside the linear direct
> mapping, in which case __pa() returns a bogus value.
> 
> Cc: Russell King <linux@arm.linux.org.uk>

Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

> Cc: Paul Mackerras <paulus@samba.org>
> Acked-by: Rob Herring <robh@kernel.org>
> Acked-by: Mark Rutland <mark.rutland@arm.com>
> Acked-by: Catalin Marinas <catalin.marinas@arm.com>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
>  arch/arm/mm/init.c         |  1 +
>  arch/arm64/mm/init.c       |  1 +
>  arch/powerpc/kernel/prom.c |  1 +
>  drivers/of/fdt.c           | 19 ++++++++++++++-----
>  include/linux/of_fdt.h     |  2 ++
>  5 files changed, 19 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
> index be92fa0f2f35..8a63b4cdc0f2 100644
> --- a/arch/arm/mm/init.c
> +++ b/arch/arm/mm/init.c
> @@ -268,6 +268,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
>  	if (mdesc->reserve)
>  		mdesc->reserve();
>  
> +	early_init_fdt_reserve_self();
>  	early_init_fdt_scan_reserved_mem();
>  
>  	/* reserve memory for DMA contiguous allocations */
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 597831bdddf3..89a05f467ffb 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -170,6 +170,7 @@ void __init arm64_memblock_init(void)
>  		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
>  #endif
>  
> +	early_init_fdt_reserve_self();
>  	early_init_fdt_scan_reserved_mem();
>  
>  	/* 4GB maximum for 32-bit only capable devices */
> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
> index 308c5e15676b..51ea36f79307 100644
> --- a/arch/powerpc/kernel/prom.c
> +++ b/arch/powerpc/kernel/prom.c
> @@ -573,6 +573,7 @@ static void __init early_reserve_mem_dt(void)
>  	int len;
>  	const __be32 *prop;
>  
> +	early_init_fdt_reserve_self();
>  	early_init_fdt_scan_reserved_mem();
>  
>  	dt_root = of_get_flat_dt_root();
> diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
> index cde35c5d0191..f2dd23a32267 100644
> --- a/drivers/of/fdt.c
> +++ b/drivers/of/fdt.c
> @@ -580,11 +580,6 @@ void __init early_init_fdt_scan_reserved_mem(void)
>  	if (!initial_boot_params)
>  		return;
>  
> -	/* Reserve the dtb region */
> -	early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
> -					  fdt_totalsize(initial_boot_params),
> -					  0);
> -
>  	/* Process header /memreserve/ fields */
>  	for (n = 0; ; n++) {
>  		fdt_get_mem_rsv(initial_boot_params, n, &base, &size);
> @@ -598,6 +593,20 @@ void __init early_init_fdt_scan_reserved_mem(void)
>  }
>  
>  /**
> + * early_init_fdt_reserve_self() - reserve the memory used by the FDT blob
> + */
> +void __init early_init_fdt_reserve_self(void)
> +{
> +	if (!initial_boot_params)
> +		return;
> +
> +	/* Reserve the dtb region */
> +	early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
> +					  fdt_totalsize(initial_boot_params),
> +					  0);
> +}
> +
> +/**
>   * of_scan_flat_dt - scan flattened tree blob and call callback on each.
>   * @it: callback function
>   * @data: context data pointer
> diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
> index 587ee507965d..fd627a58068f 100644
> --- a/include/linux/of_fdt.h
> +++ b/include/linux/of_fdt.h
> @@ -64,6 +64,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
>  extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
>  				     int depth, void *data);
>  extern void early_init_fdt_scan_reserved_mem(void);
> +extern void early_init_fdt_reserve_self(void);
>  extern void early_init_dt_add_memory_arch(u64 base, u64 size);
>  extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
>  					     bool no_map);
> @@ -91,6 +92,7 @@ extern u64 fdt_translate_address(const void *blob, int node_offset);
>  extern void of_fdt_limit_memory(int limit);
>  #else /* CONFIG_OF_FLATTREE */
>  static inline void early_init_fdt_scan_reserved_mem(void) {}
> +static inline void early_init_fdt_reserve_self(void) {}
>  static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
>  static inline void unflatten_device_tree(void) {}
>  static inline void unflatten_and_copy_device_tree(void) {}