From: Andy Lutomirski SYSENTER_stack should have reliable overflow detection, which means that it needs to be at the bottom of a page, not the top. Move it to the beginning of struct tss_struct and page-align it. Also add an assertion to make sure that the fixed hardware TSS doesn't cross a page boundary. Signed-off-by: Andy Lutomirski Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Rik van Riel Cc: Denys Vlasenko Cc: Peter Zijlstra Cc: Brian Gerst Cc: Dave Hansen Cc: Josh Poimboeuf Cc: Linus Torvalds Link: https://lkml.kernel.org/r/8de9901e7c3a6aa8fac95b37b9c7b96f1900f11a.1511497875.git.luto@kernel.org --- arch/x86/include/asm/processor.h | 21 ++++++++++++--------- arch/x86/kernel/cpu/common.c | 21 +++++++++++++++++++++ 2 files changed, 33 insertions(+), 9 deletions(-) --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -333,7 +333,16 @@ struct x86_hw_tss { struct tss_struct { /* - * The hardware state: + * Space for the temporary SYSENTER stack, used for SYSENTER + * and the entry trampoline as well. + */ + unsigned long SYSENTER_stack_canary; + unsigned long SYSENTER_stack[64]; + + /* + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. */ struct x86_hw_tss x86_tss; @@ -344,15 +353,9 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __aligned(PAGE_SIZE); - /* - * Space for the temporary SYSENTER stack. - */ - unsigned long SYSENTER_stack_canary; - unsigned long SYSENTER_stack[64]; -} ____cacheline_aligned; - -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss); /* * sizeof(unsigned long) coming from an extra "long" at the end --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -511,6 +511,27 @@ static inline void setup_cpu_entry_area( #endif __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); + + /* + * The Intel SDM says (Volume 3, 7.2.1): + * + * Avoid placing a page boundary in the part of the TSS that the + * processor reads during a task switch (the first 104 bytes). The + * processor may not correctly perform address translations if a + * boundary occurs in this area. During a task switch, the processor + * reads and writes into the first 104 bytes of each TSS (using + * contiguous physical addresses beginning with the physical address + * of the first byte of the TSS). So, after TSS access begins, if + * part of the 104 bytes is not physically contiguous, the processor + * will access incorrect information without generating a page-fault + * exception. + * + * There are also a lot of errata involving the TSS spanning a page + * boundary. Assert that we're not doing that. + */ + BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ + offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); + } /* Load the original GDT from the per-cpu structure */