x86/vdso fixes for 3.1

index 7b439d9..41935fa 100644
@@ -27,8 +27,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->base2		= (info->base_addr & 0xff000000) >> 24;
 	/*
-	 * Don't allow setting of the lm bit. It is useless anyway
-	 * because 64bit system calls require __USER_CS:
+	 * Don't allow setting of the lm bit. It would confuse
+	 * user_64bit_mode and would get overridden by sysret anyway.
 	 */
 	desc->l			= 0;
 }

index f9a3209..7e50f06 100644
@@ -17,7 +17,6 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vector  204         : legacy x86_64 vsyscall emulation
  *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
  *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *

@@ -51,9 +50,6 @@
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
 #endif
-#ifdef CONFIG_X86_64
-# define VSYSCALL_EMU_VECTOR		0xcc
-#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.

index 2c76521..8e8b9a4 100644
@@ -41,6 +41,7 @@
 
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
+#include <asm/pgtable_types.h>
 
 struct page;
 struct thread_struct;

@@ -63,6 +64,11 @@ struct paravirt_callee_save {
 struct pv_info {
 	unsigned int kernel_rpl;
 	int shared_kernel_pmd;
+
+#ifdef CONFIG_X86_64
+	u16 extra_user_64bit_cs;  /* __USER_CS if none */
+#endif
+
 	int paravirt_enabled;
 	const char *name;
 };

index 94e7618..3566454 100644
@@ -131,6 +131,9 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #include <linux/init.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt_types.h>
+#endif
 
 struct cpuinfo_x86;
 struct task_struct;

@@ -187,6 +190,22 @@ static inline int v8086_mode(struct pt_regs *regs)
 #endif
 }
 
+#ifdef CONFIG_X86_64
+static inline bool user_64bit_mode(struct pt_regs *regs)
+{
+#ifndef CONFIG_PARAVIRT
+	/*
+	 * On non-paravirt systems, this is the only long mode CPL 3
+	 * selector.  We do not allow long mode selectors in the LDT.
+	 */
+	return regs->cs == __USER_CS;
+#else
+	/* Headers are too twisted for this to go in paravirt.h. */
+	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
+#endif
+}
+#endif
+
 /*
  * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
  * when it traps.  The previous stack will be directly underneath the saved

index 2bae0a5..0012d09 100644
@@ -40,7 +40,6 @@ asmlinkage void alignment_check(void);
 asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
-asmlinkage void emulate_vsyscall(void);
 
 dotraplinkage void do_divide_error(struct pt_regs *, long);
 dotraplinkage void do_debug(struct pt_regs *, long);

@@ -67,7 +66,6 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long);
 dotraplinkage void do_machine_check(struct pt_regs *, long);
 #endif
 dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif

index 705bf13..d92641c 100644
@@ -681,6 +681,8 @@ __SYSCALL(__NR_syncfs, sys_syncfs)
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
 #define __NR_setns				308
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_getcpu				309
+__SYSCALL(__NR_getcpu, sys_getcpu)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

index 6010707..eaea1d3 100644
@@ -27,6 +27,12 @@ extern struct timezone sys_tz;
 
 extern void map_vsyscall(void);
 
+/*
+ * Called on instruction fetch fault in vsyscall page.
+ * Returns true if handled.
+ */
+extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_VSYSCALL_H */

index 613a793..d90272e 100644
@@ -307,6 +307,10 @@ struct pv_info pv_info = {
 	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
+
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = __USER_CS,
+#endif
 };
 
 struct pv_init_ops pv_init_ops = {

index 7977f0c..c346d11 100644
@@ -74,7 +74,7 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs)
 
 #ifdef CONFIG_X86_64
 		case 0x40 ... 0x4f:
-			if (regs->cs != __USER_CS)
+			if (!user_64bit_mode(regs))
 				/* 32-bit mode: register increment */
 				return 0;
 			/* 64-bit mode: REX prefix */

index 9682ec5..6913369 100644
@@ -872,12 +872,6 @@ void __init trap_init(void)
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
 
-#ifdef CONFIG_X86_64
-	BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
-	set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
-	set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
-#endif
-
 	/*
 	 * Should be a barrier for any external CPU state:
 	 */

156 lines not on this page · raw message

new file mode 100644
index 0000000..a8b2ede
@@ -0,0 +1,29 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+	    TP_PROTO(int nr),
+
+	    TP_ARGS(nr),
+
+	    TP_STRUCT__entry(__field(int, nr)),
+
+	    TP_fast_assign(
+			   __entry->nr = nr;
+			   ),
+
+	    TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>

index 4d09df0..247aae3 100644
@@ -105,7 +105,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		 * but for now it's good enough to assume that long
 		 * mode only uses well known segments or kernel.
 		 */
-		return (!user_mode(regs)) || (regs->cs == __USER_CS);
+		return (!user_mode(regs) || user_64bit_mode(regs));
 #endif
 	case 0x60:
 		/* 0x64 thru 0x67 are valid prefixes in all modes. */

@@ -720,6 +720,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		if (is_errata100(regs, address))
 			return;
 
+#ifdef CONFIG_X86_64
+		/*
+		 * Instruction fetch faults in the vsyscall page might need
+		 * emulation.
+		 */
+		if (unlikely((error_code & PF_INSTR) &&
+			     ((address & ~0xfff) == VSYSCALL_START))) {
+			if (emulate_vsyscall(regs, address))
+				return;
+		}
+#endif
+
 		if (unlikely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 

index 974a528..e2345af 100644
@@ -951,6 +951,10 @@ static const struct pv_info xen_info __initconst = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+
 	.name = "Xen",
 };
 

index f987bde..8cce339 100644
@@ -1916,6 +1916,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # endif
 #else
 	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+	case VVAR_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:

@@ -1956,7 +1957,8 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+	    idx == VVAR_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}