Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761532AbXJaXB0 (ORCPT ); Wed, 31 Oct 2007 19:01:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761506AbXJaXAw (ORCPT ); Wed, 31 Oct 2007 19:00:52 -0400 Received: from mx1.redhat.com ([66.187.233.31]:32899 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761011AbXJaXAu (ORCPT ); Wed, 31 Oct 2007 19:00:50 -0400 From: Glauber de Oliveira Costa To: linux-kernel@vger.kernel.org Cc: akpm@linux-foundation.org, rusty@rustcorp.com.au, ak@suse.de, mingo@elte.hu, chrisw@sous-sol.org, jeremy@goop.org, avi@qumranet.com, anthony@codemonkey.ws, virtualization@lists.linux-foundation.org, lguest@ozlabs.org, kvm-devel@lists.sourceforge.net, zach@vmware.com, tglx@linutronix.de, jun.nakajima@intel.com, glommer@gmail.com, Glauber de Oliveira Costa , Steven Rostedt Subject: [PATCH 8/16] add native functions for descriptors handling Date: Wed, 31 Oct 2007 16:14:53 -0300 Message-Id: <11938581451804-git-send-email-gcosta@redhat.com> X-Mailer: git-send-email 1.4.4.2 In-Reply-To: <11938581403478-git-send-email-gcosta@redhat.com> References: <1193858101367-git-send-email-gcosta@redhat.com> <11938581073775-git-send-email-gcosta@redhat.com> <11938581133479-git-send-email-gcosta@redhat.com> <1193858118284-git-send-email-gcosta@redhat.com> <11938581242810-git-send-email-gcosta@redhat.com> <1193858130443-git-send-email-gcosta@redhat.com> <11938581351064-git-send-email-gcosta@redhat.com> <11938581403478-git-send-email-gcosta@redhat.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11176 Lines: 365 This patch turns the basic descriptor handling into native_ functions. It is basically write_idt, load_idt, write_gdt, load_gdt, set_ldt, store_tr, load_tls, and the ones for updating a single entry. In the process of doing that, we change the definition of load_LDT_nolock, and caller sites have to be patched. We also patch call sites that now needs a typecast. Signed-off-by: Glauber de Oliveira Costa Signed-off-by: Steven Rostedt Acked-by: Jeremy Fitzhardinge --- arch/x86/kernel/ldt_64.c | 7 +- include/asm-x86/desc_64.h | 172 +++++++++++++++++++++++++------------- include/asm-x86/mmu_context_64.h | 23 ++++-- 3 files changed, 132 insertions(+), 70 deletions(-) diff --git a/arch/x86/kernel/ldt_64.c b/arch/x86/kernel/ldt_64.c index 60e57ab..ab1ff6e 100644 --- a/arch/x86/kernel/ldt_64.c +++ b/arch/x86/kernel/ldt_64.c @@ -171,7 +171,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) { struct task_struct *me = current; struct mm_struct * mm = me->mm; - __u32 entry_1, entry_2, *lp; + __u32 entry_1, entry_2; int error; struct user_desc ldt_info; @@ -200,7 +200,6 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) goto out_unlock; } - lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *) mm->context.ldt); /* Allow LDTs to be cleared by the user. */ if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { @@ -218,8 +217,8 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) /* Install the new entry ... */ install: - *lp = entry_1; - *(lp+1) = entry_2; + write_ldt_entry(mm->context.ldt, ldt_info.entry_number, + entry_1, entry_2); error = 0; out_unlock: diff --git a/include/asm-x86/desc_64.h b/include/asm-x86/desc_64.h index 7d9c938..f7008bb 100644 --- a/include/asm-x86/desc_64.h +++ b/include/asm-x86/desc_64.h @@ -16,20 +16,18 @@ extern struct desc_struct cpu_gdt_table[GDT_ENTRIES]; -#define load_TR_desc() asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8)) -#define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8)) -#define clear_LDT() asm volatile("lldt %w0"::"r" (0)) +static inline void native_load_tr_desc(void) +{ + asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8)); +} -static inline unsigned long __store_tr(void) +static inline unsigned long native_store_tr(void) { unsigned long tr; - asm volatile ("str %w0":"=r" (tr)); return tr; } -#define store_tr(tr) (tr) = __store_tr() - /* * This is the ldt that every process will get unless we need * something other than this. @@ -41,62 +39,51 @@ extern struct desc_ptr cpu_gdt_descr[]; /* the cpu gdt accessor */ #define cpu_gdt(_cpu) ((struct desc_struct *)cpu_gdt_descr[_cpu].address) -static inline void load_gdt(const struct desc_ptr *ptr) +static inline void native_load_gdt(const struct desc_ptr *ptr) { asm volatile("lgdt %w0"::"m" (*ptr)); } -static inline void store_gdt(struct desc_ptr *ptr) +static inline void native_store_gdt(struct desc_ptr *ptr) { - asm("sgdt %w0":"=m" (*ptr)); + asm volatile ("sgdt %w0":"=m" (*ptr)); } -static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist) +static inline void native_write_idt_entry(void *adr, struct gate_struct *s) { - struct gate_struct s; - s.offset_low = PTR_LOW(func); - s.segment = __KERNEL_CS; - s.ist = ist; - s.p = 1; - s.dpl = dpl; - s.zero0 = 0; - s.zero1 = 0; - s.type = type; - s.offset_middle = PTR_MIDDLE(func); - s.offset_high = PTR_HIGH(func); - /* does not need to be atomic because it is only done once at setup time */ - memcpy(adr, &s, 16); -} - -static inline void set_intr_gate(int nr, void *func) -{ - BUG_ON((unsigned)nr > 0xFF); - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0); -} + /* does not need to be atomic because + * it is only done once at setup time */ + memcpy(adr, s, 16); +} -static inline void set_intr_gate_ist(int nr, void *func, unsigned ist) -{ - BUG_ON((unsigned)nr > 0xFF); - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); -} +static inline void native_write_gdt_entry(void *ptr, void *entry, + unsigned type, unsigned size) +{ + memcpy(ptr, entry, size); +} -static inline void set_system_gate(int nr, void *func) -{ - BUG_ON((unsigned)nr > 0xFF); - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); -} +/* + * This one unfortunately can't go with the others, in below, because it has + * an user anxious for its definition: set_tssldt_descriptor + */ +#ifndef CONFIG_PARAVIRT +#define write_gdt_entry(_ptr, _e, _type, _size) \ + native_write_gdt_entry((_ptr), (_e), (_type), (_size)) +#endif -static inline void set_system_gate_ist(int nr, void *func, unsigned ist) +static inline void write_dt_entry(struct desc_struct *dt, + int entry, u32 entry_low, u32 entry_high) { - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, ist); + ((struct n_desc_struct *)dt)[entry].a = entry_low; + ((struct n_desc_struct *)dt)[entry].b = entry_high; } -static inline void load_idt(const struct desc_ptr *ptr) +static inline void native_load_idt(const struct desc_ptr *ptr) { asm volatile("lidt %w0"::"m" (*ptr)); } -static inline void store_idt(struct desc_ptr *dtr) +static inline void native_store_idt(struct desc_ptr *dtr) { asm("sidt %w0":"=m" (*dtr)); } @@ -114,7 +101,7 @@ static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned d.limit1 = (size >> 16) & 0xF; d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF; d.base3 = PTR_HIGH(tss); - memcpy(ptr, &d, 16); + write_gdt_entry(ptr, &d, type, 16); } static inline void set_tss_desc(unsigned cpu, void *addr) @@ -165,7 +152,7 @@ static inline void set_ldt_desc(unsigned cpu, void *addr, int size) (info)->useable == 0 && \ (info)->lm == 0) -static inline void load_TLS(struct thread_struct *t, unsigned int cpu) +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { unsigned int i; u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN); @@ -173,28 +160,93 @@ static inline void load_TLS(struct thread_struct *t, unsigned int cpu) for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) gdt[i] = t->tls_array[i]; } +static inline void native_set_ldt(const void *addr, + unsigned int entries) +{ + if (likely(entries == 0)) + __asm__ __volatile__ ("lldt %w0" :: "r" (0)); + else { + unsigned cpu = smp_processor_id(); + + set_tssldt_descriptor(&cpu_gdt(cpu)[GDT_ENTRY_LDT], + (unsigned long)addr, DESC_LDT, + entries * 8 - 1); + __asm__ __volatile__ ("lldt %w0"::"r" (GDT_ENTRY_LDT*8)); + } +} + +#ifdef CONFIG_PARAVIRT +#include +#else +#define load_TR_desc() native_load_tr_desc() +#define load_gdt(ptr) native_load_gdt(ptr) +#define load_idt(ptr) native_load_idt(ptr) +#define load_TLS(t, cpu) native_load_tls(t, cpu) +#define set_ldt(addr, entries) native_set_ldt(addr, entries) +#define store_tr(tr) (tr) = native_store_tr() +#define store_gdt(ptr) native_store_gdt(ptr) +#define store_idt(ptr) native_store_idt(ptr) + +#define write_idt_entry(_adr, _s) native_write_idt_entry((_adr), (_s)) +#define write_ldt_entry(_ldt, _number, _entry1, _entry2) \ + write_dt_entry((_ldt), (_number), (_entry1), (_entry2)) +#endif + +static inline void _set_gate(void *adr, unsigned type, unsigned long func, + unsigned dpl, unsigned ist) +{ + struct gate_struct s; + s.offset_low = PTR_LOW(func); + s.segment = __KERNEL_CS; + s.ist = ist; + s.p = 1; + s.dpl = dpl; + s.zero0 = 0; + s.zero1 = 0; + s.type = type; + s.offset_middle = PTR_MIDDLE(func); + s.offset_high = PTR_HIGH(func); + write_idt_entry(adr, &s); +} + +static inline void set_intr_gate(int nr, void *func) +{ + BUG_ON((unsigned)nr > 0xFF); + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0); +} + +static inline void set_intr_gate_ist(int nr, void *func, unsigned ist) +{ + BUG_ON((unsigned)nr > 0xFF); + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); +} + +static inline void set_system_gate(int nr, void *func) +{ + BUG_ON((unsigned)nr > 0xFF); + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); +} + +static inline void set_system_gate_ist(int nr, void *func, unsigned ist) +{ + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, ist); +} + +#define clear_LDT() set_ldt(NULL, 0) /* * load one particular LDT into the current CPU */ -static inline void load_LDT_nolock (mm_context_t *pc, int cpu) +static inline void load_LDT_nolock(mm_context_t *pc) { - int count = pc->size; - - if (likely(!count)) { - clear_LDT(); - return; - } - - set_ldt_desc(cpu, pc->ldt, count); - load_LDT_desc(); + set_ldt(pc->ldt, pc->size); } static inline void load_LDT(mm_context_t *pc) { - int cpu = get_cpu(); - load_LDT_nolock(pc, cpu); - put_cpu(); + preempt_disable(); + load_LDT_nolock(pc); + preempt_enable(); } extern struct desc_ptr idt_descr; diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h index 0cce83a..841ee33 100644 --- a/include/asm-x86/mmu_context_64.h +++ b/include/asm-x86/mmu_context_64.h @@ -7,7 +7,16 @@ #include #include #include + +#ifdef CONFIG_PARAVIRT +#include +#else #include +static inline void paravirt_activate_mm(struct mm_struct *prev, + struct mm_struct *next) +{ +} +#endif /* CONFIG_PARAVIRT */ /* * possibly do the LDT unload here? @@ -25,7 +34,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline void load_cr3(pgd_t *pgd) { - asm volatile("movq %0,%%cr3" :: "r" (__pa(pgd)) : "memory"); + write_cr3(__pa(pgd)); } static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, @@ -43,7 +52,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, load_cr3(next->pgd); if (unlikely(next->context.ldt != prev->context.ldt)) - load_LDT_nolock(&next->context, cpu); + load_LDT_nolock(&next->context); } #ifdef CONFIG_SMP else { @@ -56,7 +65,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * to make sure to use no freed page tables. */ load_cr3(next->pgd); - load_LDT_nolock(&next->context, cpu); + load_LDT_nolock(&next->context); } } #endif @@ -67,8 +76,10 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, asm volatile("movl %0,%%fs"::"r"(0)); \ } while(0) -#define activate_mm(prev, next) \ - switch_mm((prev),(next),NULL) - +#define activate_mm(prev, next) \ +do { \ + paravirt_activate_mm(prev, next); \ + switch_mm((prev), (next), NULL); \ +} while (0) #endif -- 1.4.4.2 - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/