From ecc7e37d4dadd16f6be125ca496feccd05454da4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 11 Nov 2019 23:03:20 +0100 Subject: x86/io: Speedup schedule out of I/O bitmap user There is no requirement to update the TSS I/O bitmap when a thread using it is scheduled out and the incoming thread does not use it. For the permission check based on the TSS I/O bitmap the CPU calculates the memory location of the I/O bitmap by the address of the TSS and the io_bitmap_base member of the tss_struct. The easiest way to invalidate the I/O bitmap is to switch the offset to an address outside of the TSS limit. If an I/O instruction is issued from user space the TSS limit causes #GP to be raised in the same was as valid I/O bitmap with all bits set to 1 would do. This removes the extra work when an I/O bitmap using task is scheduled out and puts the burden on the rare I/O bitmap users when they are scheduled in. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/process.c | 63 +++++++++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 27 deletions(-) (limited to 'arch/x86/kernel/process.c') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 7e07f0bb0def..2444fe296de5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -72,18 +72,9 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, #endif + .io_bitmap_base = IO_BITMAP_OFFSET_INVALID, }, -#ifdef CONFIG_X86_32 - /* - * Note that the .io_bitmap member must be extra-big. This is because - * the CPU will access an additional byte beyond the end of the IO - * permission bitmap. The extra byte must be all 1 bits, and must - * be within the limit. - */ - .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, -#endif }; EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); @@ -112,18 +103,18 @@ void exit_thread(struct task_struct *tsk) struct thread_struct *t = &tsk->thread; unsigned long *bp = t->io_bitmap_ptr; struct fpu *fpu = &t->fpu; + struct tss_struct *tss; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); + preempt_disable(); + tss = this_cpu_ptr(&cpu_tss_rw); t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); t->io_bitmap_max = 0; - put_cpu(); + clear_thread_flag(TIF_IO_BITMAP); + /* Invalidate the io bitmap base in the TSS */ + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; + preempt_enable(); kfree(bp); } @@ -369,29 +360,47 @@ void arch_setup_new_exec(void) } } -static inline void switch_to_bitmap(struct thread_struct *prev, - struct thread_struct *next, +static inline void switch_to_bitmap(struct thread_struct *next, unsigned long tifp, unsigned long tifn) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); if (tifn & _TIF_IO_BITMAP) { /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: + * Copy at least the size of the incoming tasks bitmap + * which covers the last permitted I/O port. + * + * If the previous task which used an io bitmap had more + * bits permitted, then the copy needs to cover those as + * well so they get turned off. */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); + max(tss->io_bitmap_prev_max, next->io_bitmap_max)); + + /* Store the new max and set io_bitmap_base valid */ + tss->io_bitmap_prev_max = next->io_bitmap_max; + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_VALID; + /* - * Make sure that the TSS limit is correct for the CPU - * to notice the IO bitmap. + * Make sure that the TSS limit is covering the io bitmap. + * It might have been cut down by a VMEXIT to 0x67 which + * would cause a subsequent I/O access from user space to + * trigger a #GP because tbe bitmap is outside the TSS + * limit. */ refresh_tss_limit(); } else if (tifp & _TIF_IO_BITMAP) { /* - * Clear any possible leftover bits: + * Do not touch the bitmap. Let the next bitmap using task + * deal with the mess. Just make the io_bitmap_base invalid + * by moving it outside the TSS limit so any subsequent I/O + * access from user space will trigger a #GP. + * + * This is correct even when VMEXIT rewrites the TSS limit + * to 0x67 as the only requirement is that the base points + * outside the limit. */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; } } @@ -605,7 +614,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) tifn = READ_ONCE(task_thread_info(next_p)->flags); tifp = READ_ONCE(task_thread_info(prev_p)->flags); - switch_to_bitmap(prev, next, tifp, tifn); + switch_to_bitmap(next, tifp, tifn); propagate_user_return_notify(prev_p, next_p); -- cgit v1.2.3