x86 fixes
Subsystems (5)
Linus,
Please pull the latest x86-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus
# HEAD: 37868fe113ff2ba814b3b4eb12df214df555f8dc x86/ldt: Make modify_ldt synchronous
Fallout from the recent NMI fixes: make x86 LDT handling more robust. Also some EFI fixes.
out-of-topic modifications in x86-urgent-for-linus:
-----------------------------------------------------
drivers/firmware/efi/efi.c # 9115c7589b11: efi: Check for NULL efi kern
Thanks,
Ingo
------------------>
Andy Lutomirski (2):
x86/xen: Probe target addresses in set_aliased_prot() before the hypercall x86/ldt: Make modify_ldt synchronous
Dmitry Skorodumov (1):
x86/efi: Use all 64 bit of efi_memmap in setup_e820()
Jiang Liu (1):
x86/irq: Use the caller provided polarity setting in mp_check_pin_attr()
Ricardo Neri (1):
efi: Check for NULL efi kernel parameters
arch/x86/boot/compressed/eboot.c | 4 + arch/x86/include/asm/desc.h | 15 --- arch/x86/include/asm/mmu.h | 3 +- arch/x86/include/asm/mmu_context.h | 54 +++++++- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/common.c | 4 +- arch/x86/kernel/cpu/perf_event.c | 12 +- arch/x86/kernel/ldt.c | 262 ++++++++++++++++++++----------------- arch/x86/kernel/process_64.c | 4 +- arch/x86/kernel/step.c | 6 +- arch/x86/platform/efi/efi.c | 5 + arch/x86/power/cpu.c | 3 +- arch/x86/xen/enlighten.c | 40 ++++++ drivers/firmware/efi/efi.c | 5 + 14 files changed, 265 insertions(+), 154 deletions(-)
arch/x86/boot/compressed/eboot.c +4 -0
@@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params,unsigned int e820_type =0 ;unsigned long m = efi->efi_memmap; +#ifdef CONFIG_X86_64 + m |= (u64 )efi->efi_memmap_hi <<32 ; +#endif + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));switch (d->type) {case EFI_RESERVED_TYPE :
arch/x86/include/asm/desc.h +0 -15
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)set_ldt (NULL ,0 ); } -/* -* load one particular LDT into the current CPU -*/ -static inline void load_LDT_nolock (mm_context_t *pc) -{ -set_ldt (pc->ldt, pc->size); -} - -static inline void load_LDT (mm_context_t *pc) -{ -preempt_disable (); -load_LDT_nolock (pc); -preempt_enable (); -} -static inline unsigned long get_desc_base (const struct desc_struct *desc) {return (unsigned )(desc->base0 | ((desc->base1) <<16 ) | ((desc->base2) <<24 ));
arch/x86/include/asm/mmu.h +1 -2
@@ -9,8 +9,7 @@* we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */
arch/x86/include/asm/mmu_context.h +49 -5
74 lines not on this page · raw message
arch/x86/kernel/apic/io_apic.c +1 -1
@@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)*/ if (irq <nr_legacy_irqs () && data->count ==1 ) {if (info->ioapic_trigger != data->trigger) -mp_register_handler (irq, data->trigger); +mp_register_handler (irq, info->ioapic_trigger); data->entry.trigger = data->trigger = info->ioapic_trigger; data->entry.polarity = data->polarity = info->ioapic_polarity; }
arch/x86/kernel/cpu/common.c +2 -2
@@ -1410,7 +1410,7 @@ void cpu_init(void)load_sp0 (t, ¤t->thread);set_tss_desc (cpu, t);load_TR_desc (); -load_LDT (&init_mm.context); +load_mm_ldt (&init_mm);clear_all_debug_regs ();dbg_restore_debug_regs ();
@@ -1459,7 +1459,7 @@ void cpu_init(void)load_sp0 (t, thread);set_tss_desc (cpu, t);load_TR_desc (); -load_LDT (&init_mm.context); +load_mm_ldt (&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct , io_bitmap);
arch/x86/kernel/cpu/perf_event.c +8 -4
@@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment)int idx = segment >>3 ;if ((segment &SEGMENT_TI_MASK ) ==SEGMENT_LDT ) { +struct ldt_struct *ldt; +if (idx >LDT_ENTRIES )return 0 ; -if (idx > current->active_mm->context.size) +/* IRQs are off, so this synchronizes with smp_store_release */ + ldt =lockless_dereference (current->active_mm->context.ldt); +if (!ldt || idx > ldt->size)return 0 ; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; }else {if (idx >GDT_ENTRIES )return 0 ; - desc =raw_cpu_ptr (gdt_page.gdt); + desc =raw_cpu_ptr (gdt_page.gdt) + idx; } -return get_desc_base (desc + idx); +return get_desc_base (desc); }#ifdef CONFIG_COMPAT
arch/x86/kernel/ldt.c +142 -120
340 lines not on this page · raw message
arch/x86/kernel/process_64.c +2 -2
@@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all)void release_thread (struct task_struct *dead_task) {if (dead_task->mm) { -if (dead_task->mm->context.size) { +if (dead_task->mm->context.ldt) {pr_warn ("WARNING: dead process %s still has LDT? <%p/%d>\n" , dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size);BUG (); } }
arch/x86/kernel/step.c +4 -2
@@ -5,6 +5,7 @@#include <linux/mm.h> #include <linux/ptrace.h> #include <asm/desc.h> +#include <asm/mmu_context.h> unsigned long convert_ip_to_linear (struct task_struct *child,struct pt_regs *regs) {
@@ -30,10 +31,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re seg &= ~7UL ;mutex_lock (&child->mm->context.lock); -if (unlikely ((seg >>3 ) >= child->mm->context.size)) +if (unlikely (!child->mm->context.ldt || + (seg >>3 ) >= child->mm->context.ldt->size)) addr =-1L ;/* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base =get_desc_base (desc);/* 16-bit code segment? */
arch/x86/platform/efi/efi.c +5 -0
@@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)static int __init arch_parse_efi_cmdline (char *str) { +if (!str) { +pr_warn ("need at least one option\n" ); +return -EINVAL ; + } +if (parse_option_str (str,"old_map" ))set_bit (EFI_OLD_MEMMAP , &efi.flags);if (parse_option_str (str,"debug" ))
arch/x86/power/cpu.c +2 -1
@@ -22,6 +22,7 @@#include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/cpu.h> +#include <asm/mmu_context.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@ static void fix_processor_context(void)syscall_init ();/* This sets MSR_*STAR and related */ #endif load_TR_desc ();/* This does ltr */ -load_LDT (¤t->active_mm->context);/* This does lldt */ +load_mm_ldt (current->active_mm);/* This does lldt */ fpu__resume_cpu (); }
arch/x86/xen/enlighten.c +40 -0
@@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)pte_t pte;unsigned long pfn;struct page *page; +unsigned char dummy; ptep =lookup_address ((unsigned long )v, &level);BUG_ON (ptep ==NULL );
@@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte =pfn_pte (pfn, prot); +/* +* Careful: update_va_mapping() will fail if the virtual address +* we're poking isn't populated in the page tables. We don't +* need to worry about the direct map (that's always in the page +* tables), but we need to be careful about vmap space. In +* particular, the top level page table can lazily propagate +* entries between processes, so if we've switched mms since we +* vmapped the target in the first place, we might not have the +* top-level page table entry populated. +* +* We disable preemption because we want the same mm active when +* we probe the target and when we issue the hypercall. We'll +* have the same nominal mm, but if we're a kernel thread, lazy +* mm dropping could change our pgd. +* +* Out of an abundance of caution, this uses __get_user() to fault +* in the target address just in case there's some obscure case +* in which the target address isn't readable. +*/ + +preempt_disable (); + +pagefault_disable ();/* Avoid warnings due to being atomic. */ +__get_user (dummy, (unsigned char __user __force *)v); +pagefault_enable (); +if (HYPERVISOR_update_va_mapping ((unsigned long )v, pte,0 ))BUG ();
@@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)BUG (); }else kmap_flush_unused (); + +preempt_enable (); }static void xen_alloc_ldt (struct desc_struct *ldt,unsigned entries)
@@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)const unsigned entries_per_page =PAGE_SIZE /LDT_ENTRY_SIZE ;int i; +/* +* We need to mark the all aliases of the LDT pages RO. We +* don't need to call vm_flush_aliases(), though, since that's +* only responsible for flushing aliases out the TLBs, not the +* page tables, and Xen will flush the TLB for us if needed. +* +* To avoid confusing future readers: none of this is necessary +* to load the LDT. The hypervisor only checks this when the +* LDT is faulted in due to subsequent descriptor access. +*/ +for (i =0 ; i < entries; i += entries_per_page)set_aliased_prot (ldt + i,PAGE_KERNEL_RO ); }
drivers/firmware/efi/efi.c +5 -0
@@ -58,6 +58,11 @@ bool efi_runtime_disabled(void)static int __init parse_efi_cmdline (char *str) { +if (!str) { +pr_warn ("need at least one option\n" ); +return -EINVAL ; + } +if (parse_option_str (str,"noruntime" )) disable_runtime = true;