This is a note to let you know that I've just added the patch titled arm64: mm: use single quantity to represent the PA to VA translation to the 5.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: arm64-mm-use-single-quantity-to-represent-the-pa-to-.patch and it can be found in the queue-5.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit 46d4f33931add03028b82247afbd24dae091aa89 Author: Ard Biesheuvel <ardb@xxxxxxxxxx> Date: Thu Oct 8 17:35:59 2020 +0200 arm64: mm: use single quantity to represent the PA to VA translation [ Upstream commit 7bc1a0f9e1765830e945669c99c59c35cf9bca82 ] On arm64, the global variable memstart_addr represents the physical address of PAGE_OFFSET, and so physical to virtual translations or vice versa used to come down to simple additions or subtractions involving the values of PAGE_OFFSET and memstart_addr. When support for 52-bit virtual addressing was introduced, we had to deal with PAGE_OFFSET potentially being outside of the region that can be covered by the virtual range (as the 52-bit VA capable build needs to be able to run on systems that are only 48-bit VA capable), and for this reason, another translation was introduced, and recorded in the global variable physvirt_offset. However, if we go back to the original definition of memstart_addr, i.e., the physical address of PAGE_OFFSET, it turns out that there is no need for two separate translations: instead, we can simply subtract the size of the unaddressable VA space from memstart_addr to make the available physical memory appear in the 48-bit addressable VA region. This simplifies things, but also fixes a bug on KASLR builds, which may update memstart_addr later on in arm64_memblock_init(), but fails to update vmemmap and physvirt_offset accordingly. Fixes: 5383cc6efed1 ("arm64: mm: Introduce vabits_actual") Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx> Reviewed-by: Steve Capper <steve.capper@xxxxxxx> Link: https://lore.kernel.org/r/20201008153602.9467-2-ardb@xxxxxxxxxx Signed-off-by: Will Deacon <will@xxxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index afa722504bfde..1ded73189874d 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -164,7 +164,6 @@ extern u64 vabits_actual; #define PAGE_END (_PAGE_END(vabits_actual)) -extern s64 physvirt_offset; extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) @@ -240,7 +239,7 @@ static inline const void *__tag_set(const void *addr, u8 tag) */ #define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) -#define __lm_to_phys(addr) (((addr) + physvirt_offset)) +#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ @@ -258,7 +257,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) #endif /* CONFIG_DEBUG_VIRTUAL */ -#define __phys_to_virt(x) ((unsigned long)((x) - physvirt_offset)) +#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index d5d3fbe739534..88233d42d9c29 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -23,6 +23,8 @@ #define VMALLOC_START (MODULES_END) #define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) + #define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ @@ -33,8 +35,6 @@ #include <linux/mm_types.h> #include <linux/sched.h> -extern struct page *vmemmap; - extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 481d22c32a2e7..324f0e0894f6e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -54,12 +54,6 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -s64 physvirt_offset __ro_after_init; -EXPORT_SYMBOL(physvirt_offset); - -struct page *vmemmap __ro_after_init; -EXPORT_SYMBOL(vmemmap); - /* * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of * memory as some devices, namely the Raspberry Pi 4, have peripherals with @@ -290,20 +284,6 @@ void __init arm64_memblock_init(void) memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); - physvirt_offset = PHYS_OFFSET - PAGE_OFFSET; - - vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)); - - /* - * If we are running with a 52-bit kernel VA config on a system that - * does not support it, we have to offset our vmemmap and physvirt_offset - * s.t. we avoid the 52-bit portion of the direct linear map - */ - if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) { - vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT; - physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48); - } - /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be @@ -318,6 +298,16 @@ void __init arm64_memblock_init(void) memblock_remove(0, memstart_addr); } + /* + * If we are running with a 52-bit kernel VA config on a system that + * does not support it, we have to place the available physical + * memory in the 48-bit addressable part of the linear region, i.e., + * we have to move it upward. Since memstart_addr represents the + * physical address of PAGE_OFFSET, we have to *subtract* from it. + */ + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) + memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible