[PATCH] x86-64 update

Add accumulated bug fixes for x86-64 and some minor cleanups.

 - Add ptep_set_access_flags from i386
 - Change memory text mapping to 10MB from 40MB to make alias window
   smaller
 - Disable change_page_attr for kernel mapoing for now (wrong, but the
   other code also doesn't work)
 - Add .bss.page_aligned and align interrupt/exception stacks (idea from
   Matt Mackall)
 - Protect sysenter MSR setup against missing registers. 
 - Set mce tolerance level to 1 (panic instead of deadlock)
 - Fix cross 4GB bug in find_first_bit (Michael Matz)
 - Add missing memory clobbers in bitops.h (Suresh B.  Siddha)
 - Check kernel size at boot up
 - Set boot cpu online at boot to fix early printk
 - Fix EFER bit definitions (Dave Jones)
 - Fix comments in 32bit syscall table.
 - Quieten all 32bit syscalls that are unimplemented in 32bit. 
 - Various MCE fixes suggested by Eric Morton, David Boles et.al.
   More to come.
 - Quieten some printks
 - Fix cpu online check in msr driver
 - Lower polling interval for machine checks to 5 minutes to avoid
   overrunning the registers. 
 - Make memcpy_{from,to}io more compatible with i386 (Roland Dreier)

arch/x86_64/ia32/ia32_signal.c

@@ -306,7 +306,6 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs regs)
 {
 	struct rt_sigframe *frame = (struct rt_sigframe *)(regs.rsp - 4);
 	sigset_t set;
-	stack_t st;
 	unsigned int eax;
 
 	if (verify_area(VERIFY_READ, frame, sizeof(*frame)))
@@ -323,8 +322,8 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs regs)
 	if (ia32_restore_sigcontext(&regs, &frame->uc.uc_mcontext, &eax))
 		goto badframe;
 
-	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, regs) == -EFAULT)
-		goto badframe;
+ 	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, regs) == -EFAULT)
+  		goto badframe;
 
 	return eax;
 

arch/x86_64/ia32/ia32entry.S

@@ -322,7 +322,7 @@ ia32_sys_call_table:
 	.quad sys_mknod
 	.quad sys_chmod		/* 15 */
 	.quad sys_lchown16
-	.quad ni_syscall			/* old break syscall holder */
+	.quad quiet_ni_syscall			/* old break syscall holder */
 	.quad sys_stat
 	.quad sys32_lseek
 	.quad sys_getpid		/* 20 */
@@ -336,11 +336,11 @@ ia32_sys_call_table:
 	.quad sys_fstat	/* (old)fstat */
 	.quad sys_pause
 	.quad compat_sys_utime	/* 30 */
-	.quad ni_syscall	/* old stty syscall holder */
-	.quad ni_syscall	/* old gtty syscall holder */
+	.quad quiet_ni_syscall	/* old stty syscall holder */
+	.quad quiet_ni_syscall	/* old gtty syscall holder */
 	.quad sys_access
 	.quad sys_nice	
-	.quad ni_syscall	/* 35 */	/* old ftime syscall holder */
+	.quad quiet_ni_syscall	/* 35 */	/* old ftime syscall holder */
 	.quad sys_sync
 	.quad sys32_kill
 	.quad sys_rename
@@ -349,7 +349,7 @@ ia32_sys_call_table:
 	.quad sys_dup
 	.quad sys32_pipe
 	.quad compat_sys_times
-	.quad ni_syscall			/* old prof syscall holder */
+	.quad quiet_ni_syscall			/* old prof syscall holder */
 	.quad sys_brk		/* 45 */
 	.quad sys_setgid16
 	.quad sys_getgid16
@@ -358,12 +358,12 @@ ia32_sys_call_table:
 	.quad sys_getegid16	/* 50 */
 	.quad sys_acct
 	.quad sys_umount			/* new_umount */
-	.quad ni_syscall			/* old lock syscall holder */
+	.quad quiet_ni_syscall			/* old lock syscall holder */
 	.quad compat_sys_ioctl
 	.quad compat_sys_fcntl64		/* 55 */
-	.quad ni_syscall			/* old mpx syscall holder */
+	.quad quiet_ni_syscall			/* old mpx syscall holder */
 	.quad sys_setpgid
-	.quad ni_syscall			/* old ulimit syscall holder */
+	.quad quiet_ni_syscall			/* old ulimit syscall holder */
 	.quad sys32_olduname
 	.quad sys_umask		/* 60 */
 	.quad sys_chroot
@@ -403,7 +403,7 @@ ia32_sys_call_table:
 	.quad sys_fchown16		/* 95 */
 	.quad sys_getpriority
 	.quad sys_setpriority
-	.quad ni_syscall			/* old profil syscall holder */
+	.quad quiet_ni_syscall			/* old profil syscall holder */
 	.quad compat_sys_statfs
 	.quad compat_sys_fstatfs		/* 100 */
 	.quad sys_ioperm
@@ -417,7 +417,7 @@ ia32_sys_call_table:
 	.quad sys32_uname
 	.quad stub32_iopl		/* 110 */
 	.quad sys_vhangup
-	.quad ni_syscall	/* old "idle" system call */
+	.quad quiet_ni_syscall	/* old "idle" system call */
 	.quad sys32_vm86_warning	/* vm86old */ 
 	.quad compat_sys_wait4
 	.quad sys_swapoff		/* 115 */
@@ -442,7 +442,7 @@ ia32_sys_call_table:
 	.quad quiet_ni_syscall	/* bdflush */
 	.quad sys_sysfs		/* 135 */
 	.quad sys_personality
-	.quad ni_syscall	/* for afs_syscall */
+	.quad quiet_ni_syscall	/* for afs_syscall */
 	.quad sys_setfsuid16
 	.quad sys_setfsgid16
 	.quad sys_llseek		/* 140 */
@@ -493,8 +493,8 @@ ia32_sys_call_table:
 	.quad sys_capset
 	.quad stub32_sigaltstack
 	.quad sys32_sendfile
-	.quad ni_syscall		/* streams1 */
-	.quad ni_syscall		/* streams2 */
+	.quad quiet_ni_syscall		/* streams1 */
+	.quad quiet_ni_syscall		/* streams2 */
 	.quad stub32_vfork            /* 190 */
 	.quad compat_sys_getrlimit
 	.quad sys32_mmap2
@@ -543,51 +543,52 @@ ia32_sys_call_table:
 	.quad sys_removexattr	/* 235 */
 	.quad sys_lremovexattr
 	.quad sys_fremovexattr
-	.quad sys_tkill		/* 238 */ 
+	.quad sys_tkill
 	.quad sys_sendfile64 
 	.quad compat_sys_futex		/* 240 */
-        .quad compat_sys_sched_setaffinity
-        .quad compat_sys_sched_getaffinity
+	.quad compat_sys_sched_setaffinity
+	.quad compat_sys_sched_getaffinity
 	.quad sys32_set_thread_area
 	.quad sys32_get_thread_area
-	.quad sys32_io_setup
+	.quad sys32_io_setup		/* 245 */
 	.quad sys_io_destroy
 	.quad sys32_io_getevents
 	.quad sys32_io_submit
 	.quad sys_io_cancel
-	.quad sys_fadvise64
-	.quad quiet_ni_syscall /* free_huge_pages */
-	.quad sys_exit_group /* exit_group */
+	.quad sys_fadvise64		/* 250 */
+	.quad quiet_ni_syscall 	/* free_huge_pages */
+	.quad sys_exit_group
 	.quad sys_lookup_dcookie
 	.quad sys_epoll_create
-	.quad sys_epoll_ctl
+	.quad sys_epoll_ctl		/* 255 */
 	.quad sys_epoll_wait
 	.quad sys_remap_file_pages
 	.quad sys_set_tid_address
 	.quad sys32_timer_create
-	.quad compat_timer_settime
+	.quad compat_timer_settime	/* 260 */
 	.quad compat_timer_gettime
 	.quad sys_timer_getoverrun
 	.quad sys_timer_delete
 	.quad compat_clock_settime
-	.quad compat_clock_gettime
+	.quad compat_clock_gettime	/* 265 */
 	.quad compat_clock_getres
 	.quad compat_clock_nanosleep
-	.quad compat_statfs64   /* statfs64 */
-	.quad compat_fstatfs64  /* fstatfs64 */
-	.quad sys_tgkill
+	.quad compat_statfs64
+	.quad compat_fstatfs64
+	.quad sys_tgkill		/* 270 */
 	.quad compat_sys_utimes
 	.quad sys32_fadvise64_64
-	.quad sys_ni_syscall	/* sys_vserver */
-	.quad sys_ni_syscall	/* sys_mbind */
-	.quad sys_ni_syscall	/* 275 sys_get_mempolicy */
-	.quad sys_ni_syscall	/* sys_set_mempolicy */
+	.quad quiet_ni_syscall	/* sys_vserver */
+	.quad sys_mbind
+	.quad compat_get_mempolicy	/* 275 */
+	.quad sys_set_mempolicy
 	.quad compat_sys_mq_open
 	.quad sys_mq_unlink
 	.quad compat_sys_mq_timedsend
 	.quad compat_sys_mq_timedreceive	/* 280 */
 	.quad compat_sys_mq_notify
 	.quad compat_sys_mq_getsetattr
+	.quad quiet_ni_syscall		/* reserved for kexec */
 	/* don't forget to change IA32_NR_syscalls */
 ia32_syscall_end:		
 	.rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8

arch/x86_64/ia32/syscall32.c

@@ -83,9 +83,9 @@ void __init syscall32_cpu_init(void)
 
 	/* Load these always in case some future AMD CPU supports
 	   SYSENTER from compat mode too. */
-	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, 0, 0);
-	wrmsrl(MSR_IA32_SYSENTER_EIP, ia32_sysenter_target);
+	checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+	checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
+	checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
 
 	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }

arch/x86_64/kernel/Makefile-HEAD

+#
+# Makefile for the linux kernel.
+#
+
+extra-y 	:= head.o head64.o init_task.o vmlinux.lds.s
+EXTRA_AFLAGS	:= -traditional
+obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
+		ptrace.o i8259.o ioport.o ldt.o setup.o time.o sys_x86_64.o \
+		x8664_ksyms.o i387.o syscall.o vsyscall.o \
+		setup64.o bootflag.o e820.o reboot.o warmreboot.o
+obj-y += mce.o
+
+obj-$(CONFIG_MTRR)		+= ../../i386/kernel/cpu/mtrr/
+obj-$(CONFIG_ACPI_BOOT)		+= acpi/
+obj-$(CONFIG_X86_MSR)		+= msr.o
+obj-$(CONFIG_MICROCODE)		+= microcode.o
+obj-$(CONFIG_X86_CPUID)		+= cpuid.o
+obj-$(CONFIG_SMP)		+= smp.o smpboot.o trampoline.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o  nmi.o
+obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o mpparse.o
+obj-$(CONFIG_PM)		+= suspend.o
+obj-$(CONFIG_SOFTWARE_SUSPEND)	+= suspend_asm.o
+obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
+obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+obj-$(CONFIG_GART_IOMMU)	+= pci-gart.o aperture.o
+obj-$(CONFIG_DUMMY_IOMMU)	+= pci-nommu.o pci-dma.o
+obj-$(CONFIG_SWIOTLB)		+= swiotlb.o
+obj-$(CONFIG_SCHED_SMT)		+= domain.o
+
+obj-$(CONFIG_MODULES)		+= module.o
+
+obj-y				+= topology.o
+
+bootflag-y			+= ../../i386/kernel/bootflag.o
+cpuid-$(subst m,y,$(CONFIG_X86_CPUID))  += ../../i386/kernel/cpuid.o
+topology-y                     += ../../i386/mach-default/topology.o
+swiotlb-$(CONFIG_SWIOTLB)      += ../../ia64/lib/swiotlb.o
+microcode-$(subst m,y,$(CONFIG_MICROCODE))  += ../../i386/kernel/microcode.o

arch/x86_64/kernel/acpi/sleep.c

@@ -114,7 +114,7 @@ void __init acpi_reserve_bootmem(void)
 	acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE);
 	if ((&wakeup_end - &wakeup_start) > PAGE_SIZE)
 		printk(KERN_CRIT "ACPI: Wakeup code way too big, will crash on attempt to suspend\n");
-	printk(KERN_DEBUG "ACPI: have wakeup address 0x%8.8lx\n", acpi_wakeup_address);
+	Dprintk(KERN_DEBUG "ACPI: have wakeup address 0x%8.8lx\n", acpi_wakeup_address);
 }
 
 static int __init acpi_sleep_setup(char *str)

arch/x86_64/kernel/head.S

@@ -255,7 +255,7 @@ temp_boot_pmds:
 	
 .org 0x5000
 ENTRY(level2_kernel_pgt)
-	/* 40MB kernel mapping. The kernel code cannot be bigger than that.
+	/* 10MB kernel mapping. The kernel code cannot be bigger than that.
 	   When you change this change KERNEL_TEXT_SIZE in page.h too. */
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
 	.quad	0x0000000000000183
@@ -263,21 +263,8 @@ ENTRY(level2_kernel_pgt)
 	.quad	0x0000000000400183
 	.quad	0x0000000000600183
 	.quad	0x0000000000800183
-	.quad	0x0000000000A00183
-	.quad	0x0000000000C00183
-	.quad	0x0000000000E00183
-	.quad	0x0000000001000183
-	.quad	0x0000000001200183
-	.quad	0x0000000001400183
-	.quad	0x0000000001600183
-	.quad	0x0000000001800183
-	.quad	0x0000000001A00183
-	.quad	0x0000000001C00183
-	.quad	0x0000000001E00183
-	.quad	0x0000000002000183
-	.quad	0x0000000002200183
-	.quad	0x0000000002400183
-	.quad	0x0000000002600183
+	/* 10MB mapping for now to decrease the aliasing window */
+	.fill   15,8,0
 	/* Module mapping starts here */
 	.fill	492,8,0
 

arch/x86_64/kernel/head64.c

@@ -73,6 +73,8 @@ static void __init setup_boot_cpu_data(void)
 	boot_cpu_data.x86_mask = eax & 0xf;
 }
 
+extern char _end[];
+
 void __init x86_64_start_kernel(char * real_mode_data)
 {
 	char *s;
@@ -80,6 +82,9 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	clear_bss();
 	pda_init(0);
 	copy_bootdata(real_mode_data);
+#ifdef CONFIG_SMP
+	cpu_set(0, cpu_online_map);
+#endif
 	/* default console: */
 	if (!strstr(saved_command_line, "console="))
 		strcat(saved_command_line, " console=tty0"); 
@@ -95,6 +100,10 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	if (strstr(saved_command_line, "disableapic"))
 		disable_apic = 1;
 #endif
+	/* You need early console to see that */
+	if (__pa_symbol(&_end) >= KERNEL_TEXT_SIZE)
+		panic("Kernel too big for kernel mapping\n");
+
 	setup_boot_cpu_data();
 	start_kernel();
 }

arch/x86_64/kernel/mce.c

@@ -26,7 +26,7 @@
 
 static int mce_disabled __initdata;
 /* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic */ 
-static int tolerant = 2;
+static int tolerant = 1;
 static int banks;
 static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
 
@@ -96,7 +96,8 @@ static void mce_panic(char *msg, struct mce *backup, unsigned long start)
 	int i;
 	oops_begin();
 	for (i = 0; i < MCE_LOG_LEN; i++) {
-		if (mcelog.entry[i].tsc < start)
+		unsigned long tsc = mcelog.entry[i].tsc;
+		if (time_before(tsc, start))
 			continue;
 		print_mce(&mcelog.entry[i]); 
 		if (mcelog.entry[i].tsc == backup->tsc)
@@ -120,8 +121,8 @@ static int mce_available(struct cpuinfo_x86 *c)
 
 void do_machine_check(struct pt_regs * regs, long error_code)
 {
-	struct mce m;
-	int nowayout = 0;
+	struct mce m, panicm;
+	int nowayout = (tolerant < 1); 
 	int kill_it = 0;
 	u64 mcestart;
 	int i;
@@ -149,12 +150,23 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 	for (i = 0; i < banks; i++) {
 		if (!bank[i])
 			continue;
+		
+		/* Did this bank cause the exception? */ 
+		/* XXX: check more flags  */
+		if ((m.status & MCI_STATUS_PCC)) { 
+			panicm = m; 
+		} else {
+			m.rip = 0;
+			m.cs = 0;
+		}
+
+		m.misc = 0; 
+		m.addr = 0;
 
 		rdmsrl(MSR_IA32_MC0_STATUS + i*4, m.status);
 		if ((m.status & MCI_STATUS_VAL) == 0)
 			continue;
 
-		nowayout |= (tolerant < 1); 
 		nowayout |= !!(m.status & (MCI_STATUS_OVER|MCI_STATUS_PCC));
 		kill_it |= !!(m.status & MCI_STATUS_UC);
 		m.bank = i;
@@ -176,7 +188,10 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 	if (nowayout)
 		mce_panic("Machine check", &m, mcestart);
 	if (kill_it) {
-		int user_space = (m.rip && (m.cs & 3));
+		int user_space = 0;
+
+		if (m.mcgstatus & MCG_STATUS_RIPV)
+			user_space = m.rip && (m.cs & 3);
 		
 		/* When the machine was in user space and the CPU didn't get
 		   confused it's normally not necessary to panic, unless you 
@@ -187,7 +202,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 		   it is best to just halt the machine. */
 		if ((!user_space && (panic_on_oops || tolerant < 2)) ||
 		    (unsigned)current->pid <= 1)
-			mce_panic("Uncorrected machine check", &m, mcestart);
+			mce_panic("Uncorrected machine check", &panicm, mcestart);
 
 		/* do_exit takes an awful lot of locks and has as slight risk 
 		   of deadlocking. If you don't want that don't set tolerant >= 2 */
@@ -207,7 +222,7 @@ static void mce_clear_all(void)
  * Periodic polling timer for "silent" machine check errors.
  */
 
-static int check_interval = 3600; /* one hour */
+static int check_interval = 5 * 60; /* 5 minutes */
 static void mcheck_timer(void *data);
 static DECLARE_WORK(mcheck_work, mcheck_timer, NULL);
 

arch/x86_64/kernel/mpparse.c

@@ -575,6 +575,7 @@ static int __init smp_scan_config (unsigned long base, unsigned long length)
 	extern void __bad_mpf_size(void); 
 	unsigned int *bp = phys_to_virt(base);
 	struct intel_mp_floating *mpf;
+	static int printed __initdata; 
 
 	Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length);
 	if (sizeof(*mpf) != 16)
@@ -598,7 +599,10 @@ static int __init smp_scan_config (unsigned long base, unsigned long length)
 		bp += 4;
 		length -= 16;
 	}
-	printk(KERN_INFO "No mptable found.\n");
+	if (!printed) {		
+		printk(KERN_INFO "No mptable found.\n");
+		printed = 1;
+	}
 	return 0;
 }
 

arch/x86_64/kernel/msr.c

@@ -241,7 +241,7 @@ static int msr_open(struct inode *inode, struct file *file)
   int cpu = iminor(file->f_dentry->d_inode);
   struct cpuinfo_x86 *c = &(cpu_data)[cpu];
   
-  if (!cpu_online(cpu))
+  if (cpu >= NR_CPUS || !cpu_online(cpu))
     return -ENXIO;		/* No such CPU */
   if ( !cpu_has(c, X86_FEATURE_MSR) )
     return -EIO;		/* MSR not supported */

arch/x86_64/kernel/setup.c

@@ -909,7 +909,7 @@ void __init early_identify_cpu(struct cpuinfo_x86 *c)
 			c->x86_model += ((tfms >> 16) & 0xF) << 4;
 		} 
 		if (c->x86_capability[0] & (1<<19)) 
-       		c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
 	} else {
 		/* Have CPUID level 0 only - unheard of */
 		c->x86 = 4;
@@ -967,7 +967,7 @@ void __init identify_cpu(struct cpuinfo_x86 *c)
 			display_cacheinfo(c);
 			break;
 	}
-	
+
 	select_idle_routine(c);
 	detect_ht(c); 
 		

arch/x86_64/kernel/setup64.c

@@ -39,7 +39,7 @@ extern unsigned char __per_cpu_start[], __per_cpu_end[];
 extern struct desc_ptr cpu_gdt_descr[];
 struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table }; 
 
-char boot_cpu_stack[IRQSTACKSIZE] __cacheline_aligned;
+char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned")));
 
 unsigned long __supported_pte_mask = ~0UL;
 static int do_not_nx __initdata = 0;
@@ -190,7 +190,8 @@ void pda_init(int cpu)
 	pda->irqstackptr += IRQSTACKSIZE-64;
 } 
 
-char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ];
+char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ] 
+__attribute__((section(".bss.page_aligned")));
 
 void __init syscall_init(void)
 {

arch/x86_64/kernel/smpboot.c

@@ -895,15 +895,17 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 					cpu_set(i, cpu_sibling_map[cpu]);
 				}
 			}
-		} else {
+		} else { 
 			siblings++;
 			cpu_set(cpu, cpu_sibling_map[cpu]);
 		}
 
-		if (siblings != smp_num_siblings)
-			printk(KERN_WARNING
-	       "WARNING: %d siblings found for CPU%d, should be %d\n",
+		if (siblings != smp_num_siblings) {
+			printk(KERN_WARNING 
+	       "WARNING: %d siblings found for CPU%d, should be %d\n", 
 			       siblings, cpu, smp_num_siblings);
+			smp_num_siblings = siblings;
+		}       
 	}
 
 	Dprintk("Boot done.\n");

arch/x86_64/kernel/vmlinux.lds.S

@@ -39,6 +39,7 @@ SECTIONS
 
   __bss_start = .;		/* BSS */
   .bss : {
+	*(.bss.page_aligned)	
 	*(.bss)
 	}
   __bss_end = .;
@@ -75,8 +76,8 @@ SECTIONS
   . = ALIGN(8192);		/* init_task */
   .data.init_task : { *(.data.init_task) }
 
-  . = ALIGN(4096); 
-  .data.boot_pgt : { *(.data.boot_pgt) }
+  . = ALIGN(4096);
+  .data.page_aligned : { *(.data.page_aligned) }
 
   . = ALIGN(4096);		/* Init code and data */
   __init_begin = .;

arch/x86_64/kernel/x8664_ksyms.c

@@ -219,6 +219,3 @@ EXPORT_SYMBOL_GPL(flush_tlb_all);
 #endif
 
 EXPORT_SYMBOL(sys_ioctl);
-
-EXPORT_SYMBOL(memcpy_toio);
-EXPORT_SYMBOL(memcpy_fromio);

arch/x86_64/lib/Makefile

@@ -4,9 +4,11 @@
 
 CFLAGS_csum-partial.o := -funroll-loops
 
+obj-y := io.o
+
 lib-y := csum-partial.o csum-copy.o csum-wrappers.o delay.o \
 	usercopy.o getuser.o putuser.o  \
-	thunk.o io.o clear_page.o copy_page.o bitstr.o
+	thunk.o clear_page.o copy_page.o bitstr.o
 lib-y += memcpy.o memmove.o memset.o copy_user.o
 
 lib-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o

arch/x86_64/lib/io.c

@@ -2,12 +2,14 @@
 #include <asm/io.h>
 #include <linux/module.h>
 
-void *memcpy_toio(void *dst,const void*src,unsigned len)
+void *__memcpy_toio(unsigned long dst,const void*src,unsigned len)
 {
-	return __inline_memcpy(dst,src,len);
+	return __inline_memcpy((void *) dst,src,len);
 }
+EXPORT_SYMBOL(__memcpy_toio);
 
-void *memcpy_fromio(void *dst,const void*src,unsigned len)
+void *__memcpy_fromio(void *dst,unsigned long src,unsigned len)
 {
-	return __inline_memcpy(dst,src,len);
+	return __inline_memcpy(dst,(const void *) src,len);
 }
+EXPORT_SYMBOL(__memcpy_fromio);

arch/x86_64/mm/init.c

@@ -512,9 +512,7 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 	/* Should check here against the e820 map to avoid double free */ 
 #ifdef CONFIG_DISCONTIGMEM
 	int nid = phys_to_nid(phys);
-	if (phys < HIGH_MEMORY && nid) 
-		panic("reserve of %lx at node %d", phys, nid);
-	reserve_bootmem_node(NODE_DATA(nid), phys, len);
+  	reserve_bootmem_node(NODE_DATA(nid), phys, len);
 #else       		
 	reserve_bootmem(phys, len);    
 #endif

arch/x86_64/mm/pageattr.c

@@ -96,8 +96,7 @@ static inline void save_page(unsigned long address, struct page *fpage)
  * No more special protections in this 2/4MB area - revert to a
  * large page again. 
  */
-static void revert_page(struct page *kpte_page, unsigned long address, 
-			pgprot_t ref_prot)
+static void revert_page(unsigned long address, pgprot_t ref_prot)
 {
        pgd_t *pgd;
        pmd_t *pmd; 
@@ -145,7 +144,7 @@ __change_page_attr(unsigned long address, struct page *page, pgprot_t prot,
 
 	if (page_count(kpte_page) == 1) {
 		save_page(address, kpte_page); 		     
-		revert_page(kpte_page, address, ref_prot);
+		revert_page(address, ref_prot);
 	} 
 	return 0;
 } 
@@ -176,9 +175,11 @@ int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 			break; 
 		/* Handle kernel mapping too which aliases part of the
 		 * lowmem */
-		if (page_to_phys(page) < KERNEL_TEXT_SIZE) {		
+		/* Disabled right now. Fixme */ 
+		if (0 && page_to_phys(page) < KERNEL_TEXT_SIZE) {		
 			unsigned long addr2;
 			addr2 = __START_KERNEL_map + page_to_phys(page);
+			__pgprot(prot) &= ~_PAGE_NX;
 			err = __change_page_attr(addr2, page, prot, 
 						 PAGE_KERNEL_EXECUTABLE);
 		} 

include/asm-x86_64/bitops.h

@@ -337,16 +337,15 @@ static __inline__ int find_first_bit(const unsigned long * addr, unsigned size)
 		"repe; scasl\n\t"
 		"jz 1f\n\t"
 		"leaq -4(%%rdi),%%rdi\n\t"
-		"bsfq (%%rdi),%%rax\n"
-		"1:\tsubl %%ebx,%%edi\n\t"
+		"bsfl (%%rdi),%%eax\n"
+		"1:\tsubq %%rbx,%%rdi\n\t"
 		"shll $3,%%edi\n\t"
 		"addl %%edi,%%eax"
 		:"=a" (res), "=&c" (d0), "=&D" (d1)
-		:"1" ((size + 31) >> 5), "2" (addr), "b" (addr));
+		:"1" ((size + 31) >> 5), "2" (addr), "b" (addr) : "memory");
 	return res;
 }
 
-
 /**
  * find_next_bit - find the first set bit in a memory region
  * @addr: The address to base the search on

include/asm-x86_64/ia32_unistd.h

@@ -288,7 +288,8 @@
 #define __NR_ia32_mq_timedreceive	(__NR_ia32_mq_open+3)
 #define __NR_ia32_mq_notify		(__NR_ia32_mq_open+4)
 #define __NR_ia32_mq_getsetattr	(__NR_ia32_mq_open+5)
+#define __NR_ia32_kexec		283
 
-#define IA32_NR_syscalls 285	/* must be > than biggest syscall! */
+#define IA32_NR_syscalls 287	/* must be > than biggest syscall! */
 
 #endif /* _ASM_X86_64_IA32_UNISTD_H_ */

include/asm-x86_64/io.h

@@ -195,8 +195,13 @@ extern void iounmap(void *addr);
 #define __raw_writel writel
 #define __raw_writeq writeq
 
-void *memcpy_fromio(void*,const void*,unsigned); 
-void *memcpy_toio(void*,const void*,unsigned); 
+void *__memcpy_fromio(void*,unsigned long,unsigned);
+void *__memcpy_toio(unsigned long,const void*,unsigned);
+
+#define memcpy_fromio(to,from,len) \
+  __memcpy_fromio((to),(unsigned long)(from),(len))
+#define memcpy_toio(to,from,len) \
+  __memcpy_toio((unsigned long)(to),(from),(len))
 #define memset_io(a,b,c)	memset((void *)(a),(b),(c))
 
 /*

include/asm-x86_64/msr.h

@@ -143,8 +143,8 @@ extern inline unsigned int cpuid_edx(unsigned int op)
 #define _EFER_NX 11  /* No execute enable */
 
 #define EFER_SCE (1<<_EFER_SCE)
-#define EFER_LME (1<<EFER_LME)
-#define EFER_LMA (1<<EFER_LMA)
+#define EFER_LME (1<<_EFER_LME)
+#define EFER_LMA (1<<_EFER_LMA)
 #define EFER_NX (1<<_EFER_NX)
 
 /* Intel MSRs. Some also available on other CPUs */

include/asm-x86_64/page.h

@@ -79,7 +79,7 @@ extern unsigned long vm_force_exec32;
 #define __VIRTUAL_MASK_SHIFT	48
 #define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
-#define KERNEL_TEXT_SIZE  (40UL*1024*1024)
+#define KERNEL_TEXT_SIZE  (10UL*1024*1024)
 #define KERNEL_TEXT_START 0xffffffff80000000UL 
 
 #ifndef __ASSEMBLY__

include/asm-x86_64/pgtable.h

@@ -383,6 +383,20 @@ extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 #define update_mmu_cache(vma,address,pte) do { } while (0)
 
+/* We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time. */
+#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+	do {								  \
+		if (__dirty) {						  \
+			set_pte(__ptep, __entry);			  \
+			flush_tlb_page(__vma, __address);		  \
+		}							  \
+	} while (0)
+
 /* Encode and de-code a swap entry */
 #define __swp_type(x)			(((x).val >> 1) & 0x3f)
 #define __swp_offset(x)			((x).val >> 8)