From: David Woodhouse dwmw@amazon.co.uk
[ Upstream commit 4b5bc2ec9a239bce261ffeafdd63571134102323 ]
Now that the following fix:
d0ceea662d45 ("x86/mm: Add _PAGE_NOPTISHADOW bit to avoid updating userspace page tables")
stops kernel_ident_mapping_init() from scribbling over the end of a 4KiB PGD by assuming the following 4KiB will be a userspace PGD, there's no good reason for the kexec PGD to be part of a single 8KiB allocation with the control_code_page.
( It's not clear that that was the reason for x86_64 kexec doing it that way in the first place either; there were no comments to that effect and it seems to have been the case even before PTI came along. It looks like it was just a happy accident which prevented memory corruption on kexec. )
Either way, it definitely isn't needed now. Just allocate the PGD separately on x86_64, like i386 already does.
Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Baoquan He bhe@redhat.com Cc: Vivek Goyal vgoyal@redhat.com Cc: Dave Young dyoung@redhat.com Cc: Eric Biederman ebiederm@xmission.com Cc: Ard Biesheuvel ardb@kernel.org Cc: "H. Peter Anvin" hpa@zytor.com Link: https://lore.kernel.org/r/20241205153343.3275139-6-dwmw2@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kexec.h | 18 +++++++++--- arch/x86/kernel/machine_kexec_64.c | 45 ++++++++++++++++-------------- 2 files changed, 38 insertions(+), 25 deletions(-)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 256eee99afc8f..e2e1ec99c9998 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -16,6 +16,7 @@ # define PAGES_NR 4 #endif
+# define KEXEC_CONTROL_PAGE_SIZE 4096 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048
#ifndef __ASSEMBLY__ @@ -44,7 +45,6 @@ struct kimage; /* Maximum address we can use for the control code buffer */ # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
-# define KEXEC_CONTROL_PAGE_SIZE 4096
/* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_386 @@ -59,9 +59,6 @@ struct kimage; /* Maximum address we can use for the control pages */ # define KEXEC_CONTROL_MEMORY_LIMIT (MAXMEM-1)
-/* Allocate one page for the pdp and the second for the code */ -# define KEXEC_CONTROL_PAGE_SIZE (4096UL + 4096UL) - /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_X86_64 #endif @@ -146,6 +143,19 @@ struct kimage_arch { }; #else struct kimage_arch { + /* + * This is a kimage control page, as it must not overlap with either + * source or destination address ranges. + */ + pgd_t *pgd; + /* + * The virtual mapping of the control code page itself is used only + * during the transition, while the current kernel's pages are all + * in place. Thus the intermediate page table pages used to map it + * are not control pages, but instead just normal pages obtained + * with get_zeroed_page(). And have to be tracked (below) so that + * they can be freed. + */ p4d_t *p4d; pud_t *pud; pmd_t *pmd; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 24b6eaacc81eb..5d61a342871b5 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -149,7 +149,8 @@ static void free_transition_pgtable(struct kimage *image) image->arch.pte = NULL; }
-static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) +static int init_transition_pgtable(struct kimage *image, pgd_t *pgd, + unsigned long control_page) { pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; unsigned long vaddr, paddr; @@ -160,7 +161,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) pte_t *pte;
vaddr = (unsigned long)relocate_kernel; - paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); + paddr = control_page; pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); @@ -219,7 +220,7 @@ static void *alloc_pgt_page(void *data) return p; }
-static int init_pgtable(struct kimage *image, unsigned long start_pgtable) +static int init_pgtable(struct kimage *image, unsigned long control_page) { struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, @@ -228,12 +229,12 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; - pgd_t *level4p; int result; int i;
- level4p = (pgd_t *)__va(start_pgtable); - clear_page(level4p); + image->arch.pgd = alloc_pgt_page(image); + if (!image->arch.pgd) + return -ENOMEM;
if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { info.page_flag |= _PAGE_ENC; @@ -247,8 +248,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = pfn_mapped[i].start << PAGE_SHIFT; mend = pfn_mapped[i].end << PAGE_SHIFT;
- result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; } @@ -263,8 +264,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz;
- result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend);
if (result) return result; @@ -274,15 +275,19 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) * Prepare EFI systab and ACPI tables for kexec kernel since they are * not covered by pfn_mapped. */ - result = map_efi_systab(&info, level4p); + result = map_efi_systab(&info, image->arch.pgd); if (result) return result;
- result = map_acpi_tables(&info, level4p); + result = map_acpi_tables(&info, image->arch.pgd); if (result) return result;
- return init_transition_pgtable(image, level4p); + /* + * This must be last because the intermediate page table pages it + * allocates will not be control pages and may overlap the image. + */ + return init_transition_pgtable(image, image->arch.pgd, control_page); }
static void load_segments(void) @@ -299,14 +304,14 @@ static void load_segments(void)
int machine_kexec_prepare(struct kimage *image) { - unsigned long start_pgtable; + unsigned long control_page; int result;
/* Calculate the offsets */ - start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; + control_page = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
/* Setup the identity mapped 64bit page table */ - result = init_pgtable(image, start_pgtable); + result = init_pgtable(image, control_page); if (result) return result;
@@ -353,13 +358,12 @@ void machine_kexec(struct kimage *image) #endif }
- control_page = page_address(image->control_code_page) + PAGE_SIZE; + control_page = page_address(image->control_code_page); __memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; - page_list[PA_TABLE_PAGE] = - (unsigned long)__pa(page_address(image->control_code_page)); + page_list[PA_TABLE_PAGE] = (unsigned long)__pa(image->arch.pgd);
if (image->type == KEXEC_TYPE_DEFAULT) page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) @@ -578,8 +582,7 @@ static void kexec_mark_crashkres(bool protect)
/* Don't touch the control code page used in crash_kexec().*/ control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page)); - /* Control code page is located in the 2nd page. */ - kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect); + kexec_mark_range(crashk_res.start, control - 1, protect); control += KEXEC_CONTROL_PAGE_SIZE; kexec_mark_range(control, crashk_res.end, protect); }