From 2074cb608cb538e242fb1d43c2de37b0962ea4ac Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Sep 2023 10:02:21 +0300 Subject: [PATCH] x86/boot/compressed: Reserve more memory for page tables [ Upstream commit f530ee95b72e77b09c141c4b1a4b94d1199ffbd9 ] The decompressor has a hard limit on the number of page tables it can allocate. This limit is defined at compile-time and will cause boot failure if it is reached. The kernel is very strict and calculates the limit precisely for the worst-case scenario based on the current configuration. However, it is easy to forget to adjust the limit when a new use-case arises. The worst-case scenario is rarely encountered during sanity checks. In the case of enabling 5-level paging, a use-case was overlooked. The limit needs to be increased by one to accommodate the additional level. This oversight went unnoticed until Aaron attempted to run the kernel via kexec with 5-level paging and unaccepted memory enabled. Update wost-case calculations to include 5-level paging. To address this issue, let's allocate some extra space for page tables. 128K should be sufficient for any use-case. The logic can be simplified by using a single value for all kernel configurations. [ Also add a warning, should this memory run low - by Dave Hansen. ] Fixes: 34bbb0009f3b ("x86/boot/compressed: Enable 5-level paging during decompression stage") Reported-by: Aaron Lu Signed-off-by: Kirill A. Shutemov Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915070221.10266-1-kirill.shutemov@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/boot/compressed/ident_map_64.c | 8 +++++ arch/x86/include/asm/boot.h | 45 +++++++++++++++++-------- 2 files changed, 39 insertions(+), 14 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 321a5011042d..b4155273df89 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -67,6 +67,14 @@ static void *alloc_pgt_page(void *context) return NULL; } + /* Consumed more tables than expected? */ + if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) { + debug_putstr("pgt_buf running low in " __FILE__ "\n"); + debug_putstr("Need to raise BOOT_PGT_SIZE?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + } + entry = pages->pgt_buf + pages->pgt_buf_offset; pages->pgt_buf_offset += PAGE_SIZE; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 9191280d9ea3..215d37f7dde8 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -40,23 +40,40 @@ #ifdef CONFIG_X86_64 # define BOOT_STACK_SIZE 0x4000 +/* + * Used by decompressor's startup_32() to allocate page tables for identity + * mapping of the 4G of RAM in 4-level paging mode: + * - 1 level4 table; + * - 1 level3 table; + * - 4 level2 table that maps everything with 2M pages; + * + * The additional level5 table needed for 5-level paging is allocated from + * trampoline_32bit memory. + */ # define BOOT_INIT_PGT_SIZE (6*4096) -# ifdef CONFIG_RANDOMIZE_BASE + /* - * Assuming all cross the 512GB boundary: - * 1 page for level4 - * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel - * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP). - * Total is 19 pages. + * Total number of page tables kernel_add_identity_map() can allocate, + * including page tables consumed by startup_32(). + * + * Worst-case scenario: + * - 5-level paging needs 1 level5 table; + * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel, + * assuming all of them cross 256T boundary: + * + 4*2 level4 table; + * + 4*2 level3 table; + * + 4*2 level2 table; + * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM): + * + 1 level4 table; + * + 1 level3 table; + * + 1 level2 table; + * Total: 28 tables + * + * Add 4 spare table in case decompressor touches anything beyond what is + * accounted above. Warn if it happens. */ -# ifdef CONFIG_X86_VERBOSE_BOOTUP -# define BOOT_PGT_SIZE (19*4096) -# else /* !CONFIG_X86_VERBOSE_BOOTUP */ -# define BOOT_PGT_SIZE (17*4096) -# endif -# else /* !CONFIG_RANDOMIZE_BASE */ -# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE -# endif +# define BOOT_PGT_SIZE_WARN (28*4096) +# define BOOT_PGT_SIZE (32*4096) #else /* !CONFIG_X86_64 */ # define BOOT_STACK_SIZE 0x1000 -- 2.34.1