[RFC PATCH v3 06/20] x86/kexec: Allocate PGD for x86_64 transition page tables separately

David Woodhouse dwmw2 at infradead.org
Mon Nov 25 01:54:36 PST 2024


From: David Woodhouse <dwmw at amazon.co.uk>

There's no good reason for this to be part of the control_code_page; just
allocate it separately on x86_64 like i386 does.

Signed-off-by: David Woodhouse <dwmw at amazon.co.uk>
---
 arch/x86/include/asm/kexec.h       | 18 ++++++++---
 arch/x86/kernel/machine_kexec_64.c | 49 ++++++++++++++++--------------
 2 files changed, 40 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index ae5482a2f0ca..ccb8ff37fa9d 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__
@@ -43,7 +44,6 @@ 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
@@ -58,9 +58,6 @@ 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
@@ -145,6 +142,19 @@ 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 b9b6243ee223..c9ae65c9a27c 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -146,7 +146,8 @@ 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;
@@ -157,7 +158,7 @@ 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);
@@ -216,7 +217,7 @@ 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,
@@ -225,12 +226,12 @@ 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;
@@ -241,8 +242,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 		info.direct_gbpages = true;
 
 	/* Ensure the control code page itself is in the direct map */
-	result = kernel_ident_mapping_init(&info, level4p, start_pgtable + PAGE_SIZE,
-					   start_pgtable + KEXEC_CONTROL_CODE_MAX_SIZE);
+	result = kernel_ident_mapping_init(&info, image->arch.pgd, control_page,
+					   control_page + KEXEC_CONTROL_CODE_MAX_SIZE);
 	if (result)
 		return result;
 
@@ -250,8 +251,8 @@ 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;
 	}
@@ -266,8 +267,8 @@ 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;
@@ -277,15 +278,19 @@ 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)
@@ -302,14 +307,14 @@ 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;
 
@@ -363,13 +368,12 @@ 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)
@@ -579,8 +583,7 @@ 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);
 }
-- 
2.47.0




More information about the kexec mailing list