From: Mike Rapoport <[email protected]> The early reservations of memory areas used by the firmware, bootloader, kernel text and data are spread over setup_arch(). Moreover, some of them happen *after* memblock allocations, e.g trim_platform_memory_ranges() and trim_low_memory_range() are called after reserve_real_mode() that allocates memory.
We did not observe corruption of these memory regions because memblock always allocates memory either from the end of memory (in top-down mode) or above the kernel image (in bottom-up mode). However, the bottom up mode is going to be updated to span the entire memory [1] to avoid limitations caused by KASLR. Consolidate early memory reservations in a dedicated function to improve robustness against future changes. Having the early reservations in one place also makes it clearer what memory must be reserved before we allow memblock allocations. [1] https://lore.kernel.org/lkml/[email protected] Signed-off-by: Mike Rapoport <[email protected]> --- arch/x86/kernel/setup.c | 80 ++++++++++++++++++++++------------------- 1 file changed, 44 insertions(+), 36 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3412c4595efd..32cd2e790a0a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -728,7 +728,38 @@ static void __init trim_low_memory_range(void) */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } - + +static void __init early_reserve_memory(void) +{ + /* + * Reserve the memory occupied by the kernel between _text and + * __end_of_kernel_reserve symbols. Any kernel sections after the + * __end_of_kernel_reserve symbol must be explicitly reserved with a + * separate memblock_reserve() or they will be discarded. + */ + memblock_reserve(__pa_symbol(_text), + (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); + + /* + * Make sure page 0 is always reserved because on systems with + * L1TF its contents can be leaked to user processes. + */ + memblock_reserve(0, PAGE_SIZE); + + early_reserve_initrd(); + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); + + memblock_x86_reserve_range_setup_data(); + + reserve_ibft_region(); + reserve_bios_regions(); + + trim_platform_memory_ranges(); + trim_low_memory_range(); +} + /* * Dump out kernel offset information on panic. */ @@ -763,29 +794,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) void __init setup_arch(char **cmdline_p) { - /* - * Reserve the memory occupied by the kernel between _text and - * __end_of_kernel_reserve symbols. Any kernel sections after the - * __end_of_kernel_reserve symbol must be explicitly reserved with a - * separate memblock_reserve() or they will be discarded. - */ - memblock_reserve(__pa_symbol(_text), - (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); - - /* - * Make sure page 0 is always reserved because on systems with - * L1TF its contents can be leaked to user processes. - */ - memblock_reserve(0, PAGE_SIZE); - - early_reserve_initrd(); - - /* - * At this point everything still needed from the boot loader - * or BIOS or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); @@ -909,8 +917,18 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - if (efi_enabled(EFI_BOOT)) - efi_memblock_x86_reserve_range(); + /* + * Do some memory reservations *before* memory is added to + * memblock, so memblock allocations won't overwrite it. + * Do it after early param, so we could get (unlikely) panic from + * serial. + * + * After this point everything still needed from the boot loader or + * firmware or kernel text should be early reserved or marked not + * RAM in e820. All other memory is free game. + */ + early_reserve_memory(); + #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux @@ -937,9 +955,6 @@ void __init setup_arch(char **cmdline_p) x86_report_nx(); - /* after early param, so could get panic from serial */ - memblock_x86_reserve_range_setup_data(); - if (acpi_mps_check()) { #ifdef CONFIG_X86_LOCAL_APIC disable_apic = 1; @@ -1031,8 +1046,6 @@ void __init setup_arch(char **cmdline_p) */ find_smp_config(); - reserve_ibft_region(); - early_alloc_pgt_buf(); /* @@ -1053,8 +1066,6 @@ void __init setup_arch(char **cmdline_p) */ sev_setup_arch(); - reserve_bios_regions(); - efi_fake_memmap(); efi_find_mirror(); efi_esrt_init(); @@ -1080,9 +1091,6 @@ void __init setup_arch(char **cmdline_p) reserve_real_mode(); - trim_platform_memory_ranges(); - trim_low_memory_range(); - init_mem_mapping(); idt_setup_early_pf(); -- 2.28.0
