From 6fd592daae2182adc47f405e20d07f34f52d07dd Mon Sep 17 00:00:00 2001
From: "Carlos R. Mafra" <crmafra2@gmail.com>
Date: Mon, 5 May 2008 20:11:22 -0300
Subject: x86: clean up computation of HPET .mult variables

While reading through the HPET code I realized that the
computation of .mult variables could be done with less
lines of code, resulting in a 1.6% text size saving
for hpet.o

So I propose the following patch, which applies against
today's Linus -git tree.

>From 0c6507e400e9ca5f7f14331e18f8c12baf75a9d3 Mon Sep 17 00:00:00 2001
From: Carlos R. Mafra <crmafra@ift.unesp.br>
Date: Mon, 5 May 2008 19:38:53 -0300

The computation of clocksource_hpet.mult

       tmp = (u64)hpet_period << HPET_SHIFT;
       do_div(tmp, FSEC_PER_NSEC);
       clocksource_hpet.mult = (u32)tmp;

can be streamlined if we note that it is equal to

       clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT);

Furthermore, the computation of hpet_clockevent.mult

       uint64_t hpet_freq;

       hpet_freq = 1000000000000000ULL;
       do_div(hpet_freq, hpet_period);
       hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
                                     NSEC_PER_SEC, hpet_clockevent.shift);

can also be streamlined with the observation that hpet_period and hpet_freq are
inverse to each other (in proper units).

So instead of computing hpet_freq and using (schematically)
div_sc(hpet_freq, 10^9, shift) we use the trick of calling with the
arguments in reverse order, div_sc(10^6, hpet_period, shift).

The different power of ten is due to frequency being in Hertz (1/sec)
and the period being in units of femtosecond. Explicitly,

mult = (hpet_freq * 2^shift)/10^9    (before)
mult = (10^6 * 2^shift)/hpet_period  (after)

because hpet_freq = 10^15/hpet_period.

The comments in the code are also updated to reflect the changes.

As a result,

   text    data     bss     dec     hex filename
   2957     425      92    3474     d92 arch/x86/kernel/hpet.o
   3006     425      92    3523     dc3 arch/x86/kernel/hpet.o.old

a 1.6% reduction in text size.

Signed-off-by: Carlos R. Mafra <crmafra@ift.unesp.br>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/hpet.c | 43 ++++++++++++++++++-------------------------
 1 file changed, 18 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 9b5cfcdfc426..ea230ec69057 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -17,7 +17,7 @@
 
 /* FSEC = 10^-15
    NSEC = 10^-9 */
-#define FSEC_PER_NSEC	1000000
+#define FSEC_PER_NSEC	1000000L
 
 /*
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
@@ -206,20 +206,19 @@ static void hpet_enable_legacy_int(void)
 
 static void hpet_legacy_clockevent_register(void)
 {
-	uint64_t hpet_freq;
-
 	/* Start HPET legacy interrupts */
 	hpet_enable_legacy_int();
 
 	/*
-	 * The period is a femto seconds value. We need to calculate the
-	 * scaled math multiplication factor for nanosecond to hpet tick
-	 * conversion.
+	 * The mult factor is defined as (include/linux/clockchips.h)
+	 *  mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h)
+	 * hpet_period is in units of femtoseconds (per cycle), so
+	 *  mult/2^shift = cyc/ns = 10^6/hpet_period
+	 *  mult = (10^6 * 2^shift)/hpet_period
+	 *  mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period
 	 */
-	hpet_freq = 1000000000000000ULL;
-	do_div(hpet_freq, hpet_period);
-	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
-				      NSEC_PER_SEC, hpet_clockevent.shift);
+	hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC,
+				      hpet_period, hpet_clockevent.shift);
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
@@ -324,7 +323,7 @@ static struct clocksource clocksource_hpet = {
 
 static int hpet_clocksource_register(void)
 {
-	u64 tmp, start, now;
+	u64 start, now;
 	cycle_t t1;
 
 	/* Start the counter */
@@ -351,21 +350,15 @@ static int hpet_clocksource_register(void)
 		return -ENODEV;
 	}
 
-	/* Initialize and register HPET clocksource
-	 *
-	 * hpet period is in femto seconds per cycle
-	 * so we need to convert this to ns/cyc units
-	 * approximated by mult/2^shift
-	 *
-	 *  fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
-	 *  fsec/cyc * 1ns/1000000fsec * 2^shift = mult
-	 *  fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
-	 *  (fsec/cyc << shift)/1000000 = mult
-	 *  (hpet_period << shift)/FSEC_PER_NSEC = mult
+	/*
+	 * The definition of mult is (include/linux/clocksource.h)
+	 * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc
+	 * so we first need to convert hpet_period to ns/cyc units:
+	 *  mult/2^shift = ns/cyc = hpet_period/10^6
+	 *  mult = (hpet_period * 2^shift)/10^6
+	 *  mult = (hpet_period << shift)/FSEC_PER_NSEC
 	 */
-	tmp = (u64)hpet_period << HPET_SHIFT;
-	do_div(tmp, FSEC_PER_NSEC);
-	clocksource_hpet.mult = (u32)tmp;
+	clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT);
 
 	clocksource_register(&clocksource_hpet);
 
-- 
cgit v1.2.2


From e8aa4667baf74dfd85fbaab86861465acb811085 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 9 May 2008 11:49:11 +0200
Subject: x86: enable hpet=force for AMD SB400

Add quirk to allow forced usage of HPET on ATI SB400.
I stumbled over machines where HPET is enabled but not reported
by BIOS. This patch configures the HPET base address and makes
it known to the OS.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/quirks.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index d89a648fe710..5fe6bd5cc4c7 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -65,6 +65,7 @@ static enum {
 	ICH_FORCE_HPET_RESUME,
 	VT8237_FORCE_HPET_RESUME,
 	NVIDIA_FORCE_HPET_RESUME,
+	ATI_FORCE_HPET_RESUME,
 } force_hpet_resume_type;
 
 static void __iomem *rcba_base;
@@ -330,6 +331,31 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
 			 vt8237_force_enable_hpet);
 
+static void ati_force_hpet_resume(void)
+{
+	pci_write_config_dword(cached_dev, 0x14, 0xfed00000);
+	printk(KERN_DEBUG "Force enabled HPET at resume\n");
+}
+
+static void ati_force_enable_hpet(struct pci_dev *dev)
+{
+	u32 uninitialized_var(val);
+
+	if (!hpet_force_user || hpet_address || force_hpet_address)
+		return;
+
+	pci_write_config_dword(dev, 0x14, 0xfed00000);
+	pci_read_config_dword(dev, 0x14, &val);
+	force_hpet_address = val;
+	force_hpet_resume_type = ATI_FORCE_HPET_RESUME;
+	dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n",
+		   force_hpet_address);
+	cached_dev = dev;
+	return;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS,
+			 ati_force_enable_hpet);
+
 /*
  * Undocumented chipset feature taken from LinuxBIOS.
  */
@@ -397,6 +423,9 @@ void force_hpet_resume(void)
 	case NVIDIA_FORCE_HPET_RESUME:
 		nvidia_force_hpet_resume();
 		return;
+	case ATI_FORCE_HPET_RESUME:
+		ati_force_hpet_resume();
+		return;
 	default:
 		break;
 	}
-- 
cgit v1.2.2


From 7c4728f4a865067d96fb84f1d9c65e0ccd1f355d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 10 May 2008 21:42:14 +0200
Subject: x86: print info about available HPET quirk

We have a lot of HPET quirks available which might force enable HPET
even when the BIOS does not enable it. Some of those quirks depend on
the command line option "hpet=force".

Andrew pointed out that hoping that the user will find out about this
boot option is not really helpful.

Emit a kernel info which informs the user about the "hpet=force" boot
option when we enter a quirk which depends on this option and the user
did not provide it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/quirks.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 5fe6bd5cc4c7..ddbf34d16a01 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -175,6 +175,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7,
 
 static struct pci_dev *cached_dev;
 
+static void hpet_print_force_info(void)
+{
+	printk(KERN_INFO "HPET not enabled in BIOS. "
+	       "You might try hpet=force boot option\n");
+}
+
 static void old_ich_force_hpet_resume(void)
 {
 	u32 val;
@@ -254,6 +260,8 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
 {
 	if (hpet_force_user)
 		old_ich_force_enable_hpet(dev);
+	else
+		hpet_print_force_info();
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0,
@@ -291,8 +299,13 @@ static void vt8237_force_enable_hpet(struct pci_dev *dev)
 {
 	u32 uninitialized_var(val);
 
-	if (!hpet_force_user || hpet_address || force_hpet_address)
+	if (hpet_address || force_hpet_address)
+		return;
+
+	if (!hpet_force_user) {
+		hpet_print_force_info();
 		return;
+	}
 
 	pci_read_config_dword(dev, 0x68, &val);
 	/*
@@ -341,8 +354,13 @@ static void ati_force_enable_hpet(struct pci_dev *dev)
 {
 	u32 uninitialized_var(val);
 
-	if (!hpet_force_user || hpet_address || force_hpet_address)
+	if (hpet_address || force_hpet_address)
+		return;
+
+	if (!hpet_force_user) {
+		hpet_print_force_info();
 		return;
+	}
 
 	pci_write_config_dword(dev, 0x14, 0xfed00000);
 	pci_read_config_dword(dev, 0x14, &val);
@@ -369,8 +387,13 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev)
 {
 	u32 uninitialized_var(val);
 
-	if (!hpet_force_user || hpet_address || force_hpet_address)
+	if (hpet_address || force_hpet_address)
+		return;
+
+	if (!hpet_force_user) {
+		hpet_print_force_info();
 		return;
+	}
 
 	pci_write_config_dword(dev, 0x44, 0xfed00001);
 	pci_read_config_dword(dev, 0x44, &val);
-- 
cgit v1.2.2


From 8edc5cc5ec880c96de8e6686fb0d7a5231e91c05 Mon Sep 17 00:00:00 2001
From: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Date: Mon, 12 May 2008 15:43:34 +0200
Subject: x86: remove 6 bank limitation in 64 bit MCE reporting code

Eliminate the 6 bank restriction in 64 bit mce reporting code. This
restriction is artificial (due to static creation of sysfs files) and 32
bit code does not have any such restriction.

This change helps in reporting the details of machine checks on a
machine check exception with errors in bank 6 and above on CPUs that
support those banks. Without the patch, machine check errors in those
banks are not reported.

We still have 128 (MCE_EXTENDED_BANK) bank restriction instead of max
256 supported in hardware. That is not changed in the patch below as it
will have some user level mcelog utility dependency, with bank 128 being
used for thermal reporting currently.

The patch below does not create sysfs control (bankNctl) for banks
higher than 6 as well. That needs some pre-cleanup in /sysfs mce layout,
removal of per cpu /sysfs entries for bankctl as they are really global
system level control today. That change will follow. This basic change
is critical to report the detailed errors on banks higher than 6.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mcheck/mce_64.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index e07e8c068ae0..f1f3f5e163b7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -31,7 +31,7 @@
 #include <asm/idle.h>
 
 #define MISC_MCELOG_MINOR 227
-#define NR_BANKS 6
+#define NR_SYSFS_BANKS 6
 
 atomic_t mce_entry;
 
@@ -46,7 +46,7 @@ static int mce_dont_init;
  */
 static int tolerant = 1;
 static int banks;
-static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
+static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL };
 static unsigned long notify_user;
 static int rip_msr;
 static int mce_bootlog = -1;
@@ -209,7 +209,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 	barrier();
 
 	for (i = 0; i < banks; i++) {
-		if (!bank[i])
+		if (i < NR_SYSFS_BANKS && !bank[i])
 			continue;
 
 		m.misc = 0;
@@ -444,9 +444,10 @@ static void mce_init(void *dummy)
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	banks = cap & 0xff;
-	if (banks > NR_BANKS) {
-		printk(KERN_INFO "MCE: warning: using only %d banks\n", banks);
-		banks = NR_BANKS;
+	if (banks > MCE_EXTENDED_BANK) {
+		printk(KERN_INFO "MCE: warning: using only %d banks\n",
+		       MCE_EXTENDED_BANK);
+		banks = MCE_EXTENDED_BANK;
 	}
 	/* Use accurate RIP reporting if available. */
 	if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
@@ -462,7 +463,7 @@ static void mce_init(void *dummy)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 
 	for (i = 0; i < banks; i++) {
-		wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+		wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
 		wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
 	}
 }
@@ -766,7 +767,10 @@ DEFINE_PER_CPU(struct sys_device, device_mce);
 	}								\
 	static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name);
 
-/* TBD should generate these dynamically based on number of available banks */
+/*
+ * TBD should generate these dynamically based on number of available banks.
+ * Have only 6 contol banks in /sysfs until then.
+ */
 ACCESSOR(bank0ctl,bank[0],mce_restart())
 ACCESSOR(bank1ctl,bank[1],mce_restart())
 ACCESSOR(bank2ctl,bank[2],mce_restart())
-- 
cgit v1.2.2


From 41b3eae669fb1ef6ae4acaa937b4e4617a1aa078 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Tue, 22 Apr 2008 16:29:26 +0100
Subject: x86: minor polishing to top-level arch Makefile

Use build target when creating compatibility link, and use $(boot)
where possible.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 3cff3c894cf3..5df0d1e330b1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -210,12 +210,12 @@ all: bzImage
 
 # KBUILD_IMAGE specify target image being built
                     KBUILD_IMAGE := $(boot)/bzImage
-zImage zlilo zdisk: KBUILD_IMAGE := arch/x86/boot/zImage
+zImage zlilo zdisk: KBUILD_IMAGE := $(boot)/zImage
 
 zImage bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
 	$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
-	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/bzImage
+	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@
 
 compressed: zImage
 
-- 
cgit v1.2.2


From 77b52b4c5c66175553ee59eb43f74366f1e54bde Mon Sep 17 00:00:00 2001
From: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Date: Mon, 5 May 2008 19:09:10 -0700
Subject: x86: add "debugpat" boot option

enable debug messages by a boot option "debugpat".

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/pat.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 60adbe22efa0..1a82f4db8a46 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -42,6 +42,19 @@ static int nopat(char *str)
 early_param("nopat", nopat);
 #endif
 
+
+static int debug_enable;
+static int __init pat_debug_setup(char *str)
+{
+	debug_enable = 1;
+	return 0;
+}
+__setup("debugpat", pat_debug_setup);
+
+#define dprintk(fmt, arg...) \
+	do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+
+
 static u64 __read_mostly boot_pat_state;
 
 enum {
@@ -279,7 +292,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		struct memtype *saved_ptr;
 
 		if (parse->start >= end) {
-			pr_debug("New Entry\n");
+			dprintk("New Entry\n");
 			list_add(&new_entry->nd, parse->nd.prev);
 			new_entry = NULL;
 			break;
@@ -329,7 +342,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				break;
 			}
 
-			pr_debug("Overlap at 0x%Lx-0x%Lx\n",
+			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 			       saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
 			list_add(&new_entry->nd, saved_ptr->nd.prev);
@@ -381,7 +394,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				break;
 			}
 
-			pr_debug(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n",
+			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 				 saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
 			list_add(&new_entry->nd, &saved_ptr->nd);
@@ -403,16 +416,16 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	if (new_entry) {
 		/* No conflict. Not yet added to the list. Add to the tail */
 		list_add_tail(&new_entry->nd, &memtype_list);
-		pr_debug("New Entry\n");
+		dprintk("New Entry\n");
 	}
 
 	if (ret_type) {
-		pr_debug(
+		dprintk(
 	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
 			start, end, cattr_name(actual_type),
 			cattr_name(req_type), cattr_name(*ret_type));
 	} else {
-		pr_debug(
+		dprintk(
 	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n",
 			start, end, cattr_name(actual_type),
 			cattr_name(req_type));
@@ -453,7 +466,7 @@ int free_memtype(u64 start, u64 end)
 			current->comm, current->pid, start, end);
 	}
 
-	pr_debug("free_memtype request 0x%Lx-0x%Lx\n", start, end);
+	dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
 	return err;
 }
 
-- 
cgit v1.2.2


From f8096f92b87d81c55ed63964d27baa9ce5ffe508 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Tue, 22 Apr 2008 16:27:29 +0100
Subject: x86: separate cmpxchg8b checking from PAE checking

.. allowing the former to be use in non-PAE kernels, too.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig.cpu | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2ad6301849a1..3d22bb8175b4 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -399,6 +399,10 @@ config X86_TSC
 	def_bool y
 	depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64
 
+config X86_CMPXCHG64
+	def_bool y
+	depends on X86_PAE || X86_64
+
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV
-- 
cgit v1.2.2


From aa134f1b09df6beaa4d031a50d5fda1f3cebce6c Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 8 Apr 2008 10:49:03 +0200
Subject: x86: iommu: use symbolic constants, not hardcoded numbers

Move symbolic constants into gart.h, and use them instead of hardcoded
constant.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/pci-gart_64.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c07455d1695f..bffcf455c857 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -598,13 +598,13 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 		dev = k8_northbridges[i];
 		gatt_reg = __pa(gatt) >> 12;
 		gatt_reg <<= 4;
-		pci_write_config_dword(dev, 0x98, gatt_reg);
-		pci_read_config_dword(dev, 0x90, &ctl);
+		pci_write_config_dword(dev, AMD64_GARTTABLEBASE, gatt_reg);
+		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
-		ctl |= 1;
-		ctl &= ~((1<<4) | (1<<5));
+		ctl |= GARTEN;
+		ctl &= ~(DISGARTCPU | DISGARTIO);
 
-		pci_write_config_dword(dev, 0x90, ctl);
+		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 	}
 	flush_gart();
 
-- 
cgit v1.2.2


From 1edc1ab3f68168ec6815e6d630f38948a6da005a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel.send@gmail.com>
Date: Sun, 13 Apr 2008 01:11:41 -0700
Subject: x86: agp_gart size checking for buggy device

while looking at Rafael J. Wysocki's system boot log,

I found a funny printout:

	Node 0: aperture @ de000000 size 32 MB
	Aperture too small (32 MB)
	AGP bridge at 00:04:00
	Aperture from AGP @ de000000 size 4096 MB (APSIZE 0)
	Aperture too small (0 MB)
	Your BIOS doesn't leave a aperture memory hole
	Please enable the IOMMU option in the BIOS setup
	This costs you 64 MB of RAM
	Mapping aperture over 65536 KB of RAM @ 4000000

	...

	agpgart: Detected AGP bridge 20
	agpgart: Aperture pointing to RAM
	agpgart: Aperture from AGP @ de000000 size 4096 MB
	agpgart: Aperture too small (0 MB)
	agpgart: No usable aperture found.
	agpgart: Consider rebooting with iommu=memaper=2 to get a good aperture.

it means BIOS allocated the correct gart on the NB and AGP bridge, but
because a bug in the silicon (the agp bridge reports the wrong order,
it wants 4G instead) the kernel will reject that allocation.

Also, because the size is only 32MB, and we try to get another 64M for gart,
late fix_northbridge can not revert that change because it still reads
the wrong size from agp bridge.

So try to double check the order value from the agp bridge, before calling
aperture_valid().

[ mingo@elte.hu: 32-bit fix. ]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 479926d9e004..2e93b3132dff 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -138,6 +138,7 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	int nbits;
 	u32 aper_low, aper_hi;
 	u64 aper;
+	u32 old_order;
 
 	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
 	apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
@@ -146,6 +147,9 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 		return 0;
 	}
 
+	/* old_order could be the value from NB gart setting */
+	old_order = *order;
+
 	apsize = apsizereg & 0xfff;
 	/* Some BIOS use weird encodings not in the AGPv3 table. */
 	if (apsize & 0xff)
@@ -159,6 +163,16 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	aper_hi = read_pci_config(num, slot, func, 0x14);
 	aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
 
+	/*
+	 * On some sick chips, APSIZE is 0. It means it wants 4G
+	 * so let double check that order, and lets trust AMD NB settings:
+	 */
+	if (aper + (32UL<<(20 + *order)) > 0x100000000UL) {
+		printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n",
+				32 << *order, apsizereg);
+		*order = old_order;
+	}
+
 	printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
 			aper, 32 << *order, apsizereg);
 
-- 
cgit v1.2.2


From 8c9fd91a0dc503f085169d44f4360be025f75224 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Sun, 13 Apr 2008 18:42:31 -0700
Subject: x86: checking aperture size order

some systems are using 32M for gart and agp when memory is less than 4G.
Kernel will reject and try to allcate another 64M that is not needed,
and we will waste 64M of perfectly good RAM.

this patch adds a workaround by checking aper_base/order between NB and
agp bridge. If they are the same, and memory size is less than 4G, it
will allow it.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 47 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 12 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 2e93b3132dff..8c325b7f2d9b 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -83,7 +83,7 @@ static u32 __init allocate_aperture(void)
 	return (u32)__pa(p);
 }
 
-static int __init aperture_valid(u64 aper_base, u32 aper_size)
+static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 {
 	if (!aper_base)
 		return 0;
@@ -96,8 +96,9 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size)
 		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0;
 	}
-	if (aper_size < 64*1024*1024) {
-		printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20);
+	if (aper_size < min_size) {
+		printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+				 aper_size>>20, min_size>>20);
 		return 0;
 	}
 
@@ -167,7 +168,9 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	 * On some sick chips, APSIZE is 0. It means it wants 4G
 	 * so let double check that order, and lets trust AMD NB settings:
 	 */
-	if (aper + (32UL<<(20 + *order)) > 0x100000000UL) {
+	printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n",
+			aper, 32 << old_order);
+	if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) {
 		printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n",
 				32 << *order, apsizereg);
 		*order = old_order;
@@ -176,7 +179,7 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
 			aper, 32 << *order, apsizereg);
 
-	if (!aperture_valid(aper, (32*1024*1024) << *order))
+	if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20))
 		return 0;
 	return (u32)aper;
 }
@@ -302,8 +305,8 @@ void __init early_gart_iommu_check(void)
 		fix = 1;
 
 	if (gart_fix_e820 && !fix && aper_enabled) {
-		if (e820_any_mapped(aper_base, aper_base + aper_size,
-				    E820_RAM)) {
+		if (!e820_all_mapped(aper_base, aper_base + aper_size,
+				    E820_RESERVED)) {
 			/* reserved it, so we can resuse it in second kernel */
 			printk(KERN_INFO "update e820 for GART\n");
 			add_memory_region(aper_base, aper_size, E820_RESERVED);
@@ -324,8 +327,11 @@ void __init early_gart_iommu_check(void)
 
 }
 
+static int __initdata printed_gart_size_msg;
+
 void __init gart_iommu_hole_init(void)
 {
+	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base, last_aper_base = 0;
 	int fix, num, valid_agp = 0;
@@ -337,6 +343,9 @@ void __init gart_iommu_hole_init(void)
 
 	printk(KERN_INFO  "Checking aperture...\n");
 
+	if (!fallback_aper_force)
+		agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp);
+
 	fix = 0;
 	node = 0;
 	for (num = 24; num < 32; num++) {
@@ -355,9 +364,21 @@ void __init gart_iommu_hole_init(void)
 				node, aper_base, aper_size >> 20);
 		node++;
 
-		if (!aperture_valid(aper_base, aper_size)) {
-			fix = 1;
-			break;
+		if (!aperture_valid(aper_base, aper_size, 64<<20)) {
+			if (valid_agp && agp_aper_base &&
+			    agp_aper_base == aper_base &&
+			    agp_aper_order == aper_order) {
+				/* the same between two setting from NB and agp */
+				if (!no_iommu && end_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) {
+					printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
+					printk(KERN_ERR "please increase GART size in your BIOS setup\n");
+					printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
+					printed_gart_size_msg = 1;
+				}
+			} else {
+				fix = 1;
+				break;
+			}
 		}
 
 		if ((last_aper_order && aper_order != last_aper_order) ||
@@ -378,8 +399,10 @@ void __init gart_iommu_hole_init(void)
 		return;
 	}
 
-	if (!fallback_aper_force)
-		aper_alloc = search_agp_bridge(&aper_order, &valid_agp);
+	if (!fallback_aper_force) {
+		aper_alloc = agp_aper_base;
+		aper_order = agp_aper_order;
+	}
 
 	if (aper_alloc) {
 		/* Got the aperture from the AGP bridge */
-- 
cgit v1.2.2


From 7677b2ef6c0c4fddc84f6473f3863f40eb71821b Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel.send@gmail.com>
Date: Mon, 14 Apr 2008 20:40:37 -0700
Subject: x86_64: allocate gart aperture from 512M

because we try to reserve dma32 early, so we have chance to get aperture
from 64M.

with some sequence aperture allocated from RAM, could become E820_RESERVED.

and then if doing a kexec with a big kernel that uncompressed size is above
64M we could have a range conflict with still using gart.

So allocate gart aperture from 512M instead.

Also change the fallback_aper_order to 5, because we don't have chance to get
2G or 4G aperture.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 20 +++++++++++++++++---
 arch/x86/kernel/pci-dma.c     |  6 +++++-
 2 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 8c325b7f2d9b..c63f8d9fad3e 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -55,8 +55,9 @@ static u32 __init allocate_aperture(void)
 	u32 aper_size;
 	void *p;
 
-	if (fallback_aper_order > 7)
-		fallback_aper_order = 7;
+	/* aper_size should <= 1G */
+	if (fallback_aper_order > 5)
+		fallback_aper_order = 5;
 	aper_size = (32 * 1024 * 1024) << fallback_aper_order;
 
 	/*
@@ -65,7 +66,20 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
+	/*
+	 * using 512M as goal, in case kexec will load kernel_big
+	 * that will do the on position decompress, and  could overlap with
+	 * that positon with gart that is used.
+	 * sequende:
+	 * kernel_small
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kernel_small(gart area become e820_reserved)
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+	 * so don't use 512M below as gart iommu, leave the space for kernel
+	 * code for safe
+	 */
+	p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
 	if (!p || __pa(p)+aper_size > 0xffffffff) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%p,%uK)\n",
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 0c37f16b6950..1a017f00e867 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -77,10 +77,14 @@ void __init dma32_reserve_bootmem(void)
 	if (end_pfn <= MAX_DMA32_PFN)
 		return;
 
+	/*
+	 * check aperture_64.c allocate_aperture() for reason about
+	 * using 512M as goal
+	 */
 	align = 64ULL<<20;
 	size = round_up(dma32_bootmem_size, align);
 	dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
-				 __pa(MAX_DMA_ADDRESS));
+				 512ULL<<20);
 	if (dma32_bootmem_ptr)
 		dma32_bootmem_size = size;
 	else
-- 
cgit v1.2.2


From 55c0d721df80dcc505dc888e85d4ca51ea150ce9 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel.send@gmail.com>
Date: Sat, 19 Apr 2008 01:31:11 -0700
Subject: x86: clean up aperture_64.c

1. use symbolic register names where appropriate.
2. num to bus or slot changing
3. handle for new opteron for bus other than 0

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/aperture_64.c | 230 +++++++++++++++++++++++++-----------------
 1 file changed, 139 insertions(+), 91 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index c63f8d9fad3e..02f4dbaa4df4 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -35,6 +35,18 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+struct bus_dev_range {
+	int bus;
+	int dev_base;
+	int dev_limit;
+};
+
+static struct bus_dev_range bus_dev_ranges[] __initdata = {
+	{ 0x00, 0x18, 0x20},
+	{ 0xff, 0x00, 0x20},
+	{ 0xfe, 0x00, 0x20}
+};
+
 static struct resource gart_resource = {
 	.name	= "GART",
 	.flags	= IORESOURCE_MEM,
@@ -120,33 +132,33 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 }
 
 /* Find a PCI capability */
-static __u32 __init find_cap(int num, int slot, int func, int cap)
+static __u32 __init find_cap(int bus, int slot, int func, int cap)
 {
 	int bytes;
 	u8 pos;
 
-	if (!(read_pci_config_16(num, slot, func, PCI_STATUS) &
+	if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) &
 						PCI_STATUS_CAP_LIST))
 		return 0;
 
-	pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST);
+	pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST);
 	for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
 		u8 id;
 
 		pos &= ~3;
-		id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID);
+		id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID);
 		if (id == 0xff)
 			break;
 		if (id == cap)
 			return pos;
-		pos = read_pci_config_byte(num, slot, func,
+		pos = read_pci_config_byte(bus, slot, func,
 						pos+PCI_CAP_LIST_NEXT);
 	}
 	return 0;
 }
 
 /* Read a standard AGPv3 bridge header */
-static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
+static __u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
 {
 	u32 apsize;
 	u32 apsizereg;
@@ -155,8 +167,8 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	u64 aper;
 	u32 old_order;
 
-	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
-	apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
+	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func);
+	apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14);
 	if (apsizereg == 0xffffffff) {
 		printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
 		return 0;
@@ -174,8 +186,8 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	if ((int)*order < 0) /* < 32MB */
 		*order = 0;
 
-	aper_low = read_pci_config(num, slot, func, 0x10);
-	aper_hi = read_pci_config(num, slot, func, 0x14);
+	aper_low = read_pci_config(bus, slot, func, 0x10);
+	aper_hi = read_pci_config(bus, slot, func, 0x14);
 	aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
 
 	/*
@@ -213,15 +225,15 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
  */
 static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 {
-	int num, slot, func;
+	int bus, slot, func;
 
 	/* Poor man's PCI discovery */
-	for (num = 0; num < 256; num++) {
+	for (bus = 0; bus < 256; bus++) {
 		for (slot = 0; slot < 32; slot++) {
 			for (func = 0; func < 8; func++) {
 				u32 class, cap;
 				u8 type;
-				class = read_pci_config(num, slot, func,
+				class = read_pci_config(bus, slot, func,
 							PCI_CLASS_REVISION);
 				if (class == 0xffffffff)
 					break;
@@ -230,17 +242,17 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 				case PCI_CLASS_BRIDGE_HOST:
 				case PCI_CLASS_BRIDGE_OTHER: /* needed? */
 					/* AGP bridge? */
-					cap = find_cap(num, slot, func,
+					cap = find_cap(bus, slot, func,
 							PCI_CAP_ID_AGP);
 					if (!cap)
 						break;
 					*valid_agp = 1;
-					return read_agp(num, slot, func, cap,
+					return read_agp(bus, slot, func, cap,
 							order);
 				}
 
 				/* No multi-function device? */
-				type = read_pci_config_byte(num, slot, func,
+				type = read_pci_config_byte(bus, slot, func,
 							       PCI_HEADER_TYPE);
 				if (!(type & 0x80))
 					break;
@@ -280,38 +292,49 @@ void __init early_gart_iommu_check(void)
 	 * or BIOS forget to put that in reserved.
 	 * try to update e820 to make that region as reserved.
 	 */
-	int fix, num;
+	int fix, slot;
 	u32 ctl;
 	u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base = 0, last_aper_base = 0;
 	int aper_enabled = 0, last_aper_enabled = 0;
+	int i;
 
 	if (!early_pci_allowed())
 		return;
 
 	fix = 0;
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		ctl = read_pci_config(0, num, 3, 0x90);
-		aper_enabled = ctl & 1;
-		aper_order = (ctl >> 1) & 7;
-		aper_size = (32 * 1024 * 1024) << aper_order;
-		aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
-		aper_base <<= 25;
-
-		if ((last_aper_order && aper_order != last_aper_order) ||
-		    (last_aper_base && aper_base != last_aper_base) ||
-		    (last_aper_enabled && aper_enabled != last_aper_enabled)) {
-			fix = 1;
-			break;
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+			aper_enabled = ctl & AMD64_GARTEN;
+			aper_order = (ctl >> 1) & 7;
+			aper_size = (32 * 1024 * 1024) << aper_order;
+			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+			aper_base <<= 25;
+
+			if ((last_aper_order && aper_order != last_aper_order) ||
+			    (last_aper_base && aper_base != last_aper_base) ||
+			    (last_aper_enabled && aper_enabled != last_aper_enabled)) {
+				fix = 1;
+				goto out;
+			}
+			last_aper_order = aper_order;
+			last_aper_base = aper_base;
+			last_aper_enabled = aper_enabled;
 		}
-		last_aper_order = aper_order;
-		last_aper_base = aper_base;
-		last_aper_enabled = aper_enabled;
 	}
 
+out:
 	if (!fix && !aper_enabled)
 		return;
 
@@ -330,13 +353,22 @@ void __init early_gart_iommu_check(void)
 	}
 
 	/* different nodes have different setting, disable them all at first*/
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
 
-		ctl = read_pci_config(0, num, 3, 0x90);
-		ctl &= ~1;
-		write_pci_config(0, num, 3, 0x90, ctl);
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+			ctl &= ~AMD64_GARTEN;
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+		}
 	}
 
 }
@@ -348,8 +380,8 @@ void __init gart_iommu_hole_init(void)
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base, last_aper_base = 0;
-	int fix, num, valid_agp = 0;
-	int node;
+	int fix, slot, valid_agp = 0;
+	int i, node;
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
@@ -362,48 +394,58 @@ void __init gart_iommu_hole_init(void)
 
 	fix = 0;
 	node = 0;
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		iommu_detected = 1;
-		gart_iommu_aperture = 1;
-
-		aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7;
-		aper_size = (32 * 1024 * 1024) << aper_order;
-		aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
-		aper_base <<= 25;
-
-		printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
-				node, aper_base, aper_size >> 20);
-		node++;
-
-		if (!aperture_valid(aper_base, aper_size, 64<<20)) {
-			if (valid_agp && agp_aper_base &&
-			    agp_aper_base == aper_base &&
-			    agp_aper_order == aper_order) {
-				/* the same between two setting from NB and agp */
-				if (!no_iommu && end_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) {
-					printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
-					printk(KERN_ERR "please increase GART size in your BIOS setup\n");
-					printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
-					printed_gart_size_msg = 1;
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			iommu_detected = 1;
+			gart_iommu_aperture = 1;
+
+			aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+			aper_size = (32 * 1024 * 1024) << aper_order;
+			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+			aper_base <<= 25;
+
+			printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
+					node, aper_base, aper_size >> 20);
+			node++;
+
+			if (!aperture_valid(aper_base, aper_size, 64<<20)) {
+				if (valid_agp && agp_aper_base &&
+				    agp_aper_base == aper_base &&
+				    agp_aper_order == aper_order) {
+					/* the same between two setting from NB and agp */
+					if (!no_iommu && end_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) {
+						printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
+						printk(KERN_ERR "please increase GART size in your BIOS setup\n");
+						printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
+						printed_gart_size_msg = 1;
+					}
+				} else {
+					fix = 1;
+					goto out;
 				}
-			} else {
-				fix = 1;
-				break;
 			}
-		}
 
-		if ((last_aper_order && aper_order != last_aper_order) ||
-		    (last_aper_base && aper_base != last_aper_base)) {
-			fix = 1;
-			break;
+			if ((last_aper_order && aper_order != last_aper_order) ||
+			    (last_aper_base && aper_base != last_aper_base)) {
+				fix = 1;
+				goto out;
+			}
+			last_aper_order = aper_order;
+			last_aper_base = aper_base;
 		}
-		last_aper_order = aper_order;
-		last_aper_base = aper_base;
 	}
 
+out:
 	if (!fix && !fallback_aper_force) {
 		if (last_aper_base) {
 			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
@@ -452,16 +494,22 @@ void __init gart_iommu_hole_init(void)
 	}
 
 	/* Fix up the north bridges */
-	for (num = 24; num < 32; num++) {
-		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
-			continue;
-
-		/*
-		 * Don't enable translation yet. That is done later.
-		 * Assume this BIOS didn't initialise the GART so
-		 * just overwrite all previous bits
-		 */
-		write_pci_config(0, num, 3, 0x90, aper_order<<1);
-		write_pci_config(0, num, 3, 0x94, aper_alloc>>25);
+	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+		int bus;
+		int dev_base, dev_limit;
+
+		bus = bus_dev_ranges[i].bus;
+		dev_base = bus_dev_ranges[i].dev_base;
+		dev_limit = bus_dev_ranges[i].dev_limit;
+		for (slot = dev_base; slot < dev_limit; slot++) {
+			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+				continue;
+
+			/* Don't enable translation yet. That is done later.
+			   Assume this BIOS didn't initialise the GART so
+			   just overwrite all previous bits */
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
+		}
 	}
 }
-- 
cgit v1.2.2


From 330fce23dab6e6a3d1979e55f27aba4c0c301331 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel.send@gmail.com>
Date: Sat, 19 Apr 2008 01:31:45 -0700
Subject: x86: reserve dma32 early for gart fix

we can use free_bootmem() directly.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-dma.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1a017f00e867..81862d0c7a9a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -92,7 +92,6 @@ void __init dma32_reserve_bootmem(void)
 }
 static void __init dma32_free_bootmem(void)
 {
-	int node;
 
 	if (end_pfn <= MAX_DMA32_PFN)
 		return;
@@ -100,9 +99,7 @@ static void __init dma32_free_bootmem(void)
 	if (!dma32_bootmem_ptr)
 		return;
 
-	for_each_online_node(node)
-		free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr),
-				  dma32_bootmem_size);
+	free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size);
 
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;
-- 
cgit v1.2.2


From 3bb6fbf9969a8bbe4892968659239273d092e78a Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 15 Apr 2008 12:43:57 +0200
Subject: x86 gart: factor out common code

Cleanup gart handling on amd64 a bit: move common code into
enable_gart_translation , and use symbolic register names where
appropriate.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/pci-gart_64.c | 23 ++++++-----------------
 1 file changed, 6 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index bffcf455c857..1f99b62ff616 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -533,8 +533,8 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
 	unsigned aper_size = 0, aper_base_32, aper_order;
 	u64 aper_base;
 
-	pci_read_config_dword(dev, 0x94, &aper_base_32);
-	pci_read_config_dword(dev, 0x90, &aper_order);
+	pci_read_config_dword(dev, AMD64_GARTAPERTUREBASE, &aper_base_32);
+	pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &aper_order);
 	aper_order = (aper_order >> 1) & 7;
 
 	aper_base = aper_base_32 & 0x7fff;
@@ -592,19 +592,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	agp_gatt_table = gatt;
 
 	for (i = 0; i < num_k8_northbridges; i++) {
-		u32 gatt_reg;
-		u32 ctl;
-
 		dev = k8_northbridges[i];
-		gatt_reg = __pa(gatt) >> 12;
-		gatt_reg <<= 4;
-		pci_write_config_dword(dev, AMD64_GARTTABLEBASE, gatt_reg);
-		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-
-		ctl |= GARTEN;
-		ctl &= ~(DISGARTCPU | DISGARTIO);
-
-		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+		enable_gart_translation(dev, __pa(gatt));
 	}
 	flush_gart();
 
@@ -648,11 +637,11 @@ void gart_iommu_shutdown(void)
 		u32 ctl;
 
 		dev = k8_northbridges[i];
-		pci_read_config_dword(dev, 0x90, &ctl);
+		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
-		ctl &= ~1;
+		ctl &= ~GARTEN;
 
-		pci_write_config_dword(dev, 0x90, ctl);
+		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 	}
 }
 
-- 
cgit v1.2.2


From 622e3f28e50fe30cc199c735440cd7c75e0033b0 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Sun, 4 May 2008 19:57:19 +0400
Subject: x86: 64-bit defconfig remake

The current x86_64_defconfig contains a number of nonexistent
symbols. Lets fix it.

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/configs/x86_64_defconfig | 627 ++++++++++++++++++++------------------
 1 file changed, 328 insertions(+), 299 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 2d6f5b2809d2..2f1b35664998 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,48 +1,65 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-git14
-# Fri Jul 20 09:53:15 2007
+# Linux kernel version: 2.6.26-rc1
+# Sun May  4 19:27:29 2008
 #
-CONFIG_X86_64=y
 CONFIG_64BIT=y
+# CONFIG_X86_32 is not set
+CONFIG_X86_64=y
 CONFIG_X86=y
+CONFIG_DEFCONFIG_LIST="arch/x86/configs/x86_64_defconfig"
+# CONFIG_GENERIC_LOCKBREAK is not set
 CONFIG_GENERIC_TIME=y
-CONFIG_GENERIC_TIME_VSYSCALL=y
 CONFIG_GENERIC_CMOS_UPDATE=y
-CONFIG_ZONE_DMA32=y
+CONFIG_CLOCKSOURCE_WATCHDOG=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
-CONFIG_SEMAPHORE_SLEEPERS=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_FAST_CMPXCHG_LOCAL=y
 CONFIG_MMU=y
 CONFIG_ZONE_DMA=y
-CONFIG_QUICKLIST=y
-CONFIG_NR_QUICK=2
-CONFIG_RWSEM_GENERIC_SPINLOCK=y
-CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_X86_CMPXCHG=y
-CONFIG_EARLY_PRINTK=y
 CONFIG_GENERIC_ISA_DMA=y
 CONFIG_GENERIC_IOMAP=y
-CONFIG_ARCH_MAY_HAVE_PC_FDC=y
-CONFIG_ARCH_POPULATES_NODE_MAP=y
-CONFIG_DMI=y
-CONFIG_AUDIT_ARCH=y
 CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_HWEIGHT=y
+# CONFIG_GENERIC_GPIO is not set
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
-CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_ARCH_HAS_CPU_IDLE_WAIT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_TIME_VSYSCALL=y
+CONFIG_ARCH_HAS_CPU_RELAX=y
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+CONFIG_ZONE_DMA32=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_AUDIT_ARCH=y
+CONFIG_ARCH_SUPPORTS_AOUT=y
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_PENDING_IRQ=y
+CONFIG_X86_SMP=y
+CONFIG_X86_64_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_BIOS_REBOOT=y
+CONFIG_X86_TRAMPOLINE=y
+# CONFIG_KTIME_SCALAR is not set
 
 #
-# Code maturity level options
+# General setup
 #
 CONFIG_EXPERIMENTAL=y
 CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
 CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
@@ -51,14 +68,21 @@ CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=18
-# CONFIG_CPUSETS is not set
-CONFIG_SYSFS_DEPRECATED=y
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
+# CONFIG_USER_SCHED is not set
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
 CONFIG_RELAY=y
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+# CONFIG_USER_NS is not set
+CONFIG_PID_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -66,6 +90,7 @@ CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -73,6 +98,7 @@ CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 CONFIG_ANON_INODES=y
@@ -85,6 +111,17 @@ CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
+CONFIG_OPROFILE=y
+CONFIG_HAVE_OPROFILE=y
+CONFIG_KPROBES=y
+CONFIG_KRETPROBES=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+# CONFIG_HAVE_DMA_ATTRS is not set
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
@@ -98,6 +135,7 @@ CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_BLOCK_COMPAT=y
 
 #
 # IO Schedulers
@@ -111,107 +149,169 @@ CONFIG_IOSCHED_CFQ=y
 CONFIG_DEFAULT_CFQ=y
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_CLASSIC_RCU=y
 
 #
 # Processor type and features
 #
+CONFIG_TICK_ONESHOT=y
+# CONFIG_NO_HZ is not set
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+CONFIG_SMP=y
 CONFIG_X86_PC=y
+# CONFIG_X86_ELAN is not set
+# CONFIG_X86_VOYAGER is not set
+# CONFIG_X86_NUMAQ is not set
+# CONFIG_X86_SUMMIT is not set
+# CONFIG_X86_BIGSMP is not set
+# CONFIG_X86_VISWS is not set
+# CONFIG_X86_GENERICARCH is not set
+# CONFIG_X86_ES7000 is not set
+# CONFIG_X86_RDC321X is not set
 # CONFIG_X86_VSMP is not set
+# CONFIG_PARAVIRT_GUEST is not set
+# CONFIG_MEMTEST_BOOTPARAM is not set
+# CONFIG_M386 is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMII is not set
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUMM is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
 # CONFIG_MK8 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MEFFICEON is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP2 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MGEODEGX1 is not set
+# CONFIG_MGEODE_LX is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+# CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
 # CONFIG_MCORE2 is not set
 CONFIG_GENERIC_CPU=y
+CONFIG_X86_CPU=y
 CONFIG_X86_L1_CACHE_BYTES=128
-CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_INTERNODE_CACHE_BYTES=128
-CONFIG_X86_TSC=y
+CONFIG_X86_CMPXCHG=y
+CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_X86_GOOD_APIC=y
-# CONFIG_MICROCODE is not set
-CONFIG_X86_MSR=y
-CONFIG_X86_CPUID=y
-CONFIG_X86_HT=y
-CONFIG_X86_IO_APIC=y
-CONFIG_X86_LOCAL_APIC=y
-CONFIG_MTRR=y
-CONFIG_SMP=y
+CONFIG_X86_TSC=y
+CONFIG_X86_CMOV=y
+CONFIG_X86_MINIMUM_CPU_FAMILY=64
+CONFIG_X86_DEBUGCTLMSR=y
+CONFIG_HPET_TIMER=y
+CONFIG_HPET_EMULATE_RTC=y
+CONFIG_DMI=y
+CONFIG_GART_IOMMU=y
+# CONFIG_CALGARY_IOMMU is not set
+CONFIG_SWIOTLB=y
+CONFIG_IOMMU_HELPER=y
+CONFIG_NR_CPUS=32
 CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_PREEMPT is not set
-CONFIG_PREEMPT_BKL=y
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_INTEL=y
+CONFIG_X86_MCE_AMD=y
+# CONFIG_I8K is not set
+# CONFIG_MICROCODE is not set
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
 CONFIG_NUMA=y
 CONFIG_K8_NUMA=y
-CONFIG_NODES_SHIFT=6
 CONFIG_X86_64_ACPI_NUMA=y
+CONFIG_NODES_SPAN_OTHER_NODES=y
 CONFIG_NUMA_EMU=y
+CONFIG_NODES_SHIFT=6
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_SELECT_MEMORY_MODEL=y
+# CONFIG_FLATMEM_MANUAL is not set
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
 CONFIG_NEED_MULTIPLE_NODES=y
+CONFIG_HAVE_MEMORY_PRESENT=y
 # CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPARSEMEM_EXTREME=y
+CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
+# CONFIG_SPARSEMEM_VMEMMAP is not set
+
+#
+# Memory hotplug is currently incompatible with Software Suspend
+#
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
-CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
-CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y
-CONFIG_NR_CPUS=32
-CONFIG_PHYSICAL_ALIGN=0x200000
-CONFIG_HOTPLUG_CPU=y
-CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
-CONFIG_HPET_TIMER=y
-CONFIG_HPET_EMULATE_RTC=y
-CONFIG_GART_IOMMU=y
-# CONFIG_CALGARY_IOMMU is not set
-CONFIG_SWIOTLB=y
-CONFIG_X86_MCE=y
-CONFIG_X86_MCE_INTEL=y
-CONFIG_X86_MCE_AMD=y
-# CONFIG_KEXEC is not set
-# CONFIG_CRASH_DUMP is not set
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_START=0x200000
+CONFIG_MTRR=y
+# CONFIG_X86_PAT is not set
+# CONFIG_EFI is not set
 CONFIG_SECCOMP=y
-# CONFIG_CC_STACKPROTECTOR is not set
 # CONFIG_HZ_100 is not set
 CONFIG_HZ_250=y
 # CONFIG_HZ_300 is not set
 # CONFIG_HZ_1000 is not set
 CONFIG_HZ=250
-CONFIG_K8_NB=y
-CONFIG_GENERIC_HARDIRQS=y
-CONFIG_GENERIC_IRQ_PROBE=y
-CONFIG_ISA_DMA_API=y
-CONFIG_GENERIC_PENDING_IRQ=y
+CONFIG_SCHED_HRTICK=y
+# CONFIG_KEXEC is not set
+# CONFIG_CRASH_DUMP is not set
+CONFIG_PHYSICAL_START=0x200000
+# CONFIG_RELOCATABLE is not set
+CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_HOTPLUG_CPU=y
+# CONFIG_COMPAT_VDSO is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
 
 #
 # Power management options
 #
+CONFIG_ARCH_HIBERNATION_HEADER=y
 CONFIG_PM=y
-# CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
+CONFIG_PM_SLEEP_SMP=y
+CONFIG_PM_SLEEP=y
+# CONFIG_SUSPEND is not set
 CONFIG_HIBERNATION=y
 CONFIG_PM_STD_PARTITION=""
-
-#
-# ACPI (Advanced Configuration and Power Interface) Support
-#
 CONFIG_ACPI=y
 CONFIG_ACPI_SLEEP=y
-CONFIG_ACPI_SLEEP_PROC_FS=y
-CONFIG_ACPI_SLEEP_PROC_SLEEP=y
 CONFIG_ACPI_PROCFS=y
+CONFIG_ACPI_PROCFS_POWER=y
+CONFIG_ACPI_SYSFS_POWER=y
+CONFIG_ACPI_PROC_EVENT=y
 CONFIG_ACPI_AC=y
 CONFIG_ACPI_BATTERY=y
 CONFIG_ACPI_BUTTON=y
 CONFIG_ACPI_FAN=y
-# CONFIG_ACPI_DOCK is not set
+CONFIG_ACPI_DOCK=y
+# CONFIG_ACPI_BAY is not set
 CONFIG_ACPI_PROCESSOR=y
 CONFIG_ACPI_HOTPLUG_CPU=y
 CONFIG_ACPI_THERMAL=y
 CONFIG_ACPI_NUMA=y
+# CONFIG_ACPI_WMI is not set
 # CONFIG_ACPI_ASUS is not set
 # CONFIG_ACPI_TOSHIBA is not set
+# CONFIG_ACPI_CUSTOM_DSDT is not set
 CONFIG_ACPI_BLACKLIST_YEAR=0
 # CONFIG_ACPI_DEBUG is not set
 CONFIG_ACPI_EC=y
@@ -230,7 +330,10 @@ CONFIG_CPU_FREQ_DEBUG=y
 CONFIG_CPU_FREQ_STAT=y
 # CONFIG_CPU_FREQ_STAT_DETAILS is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
 # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
@@ -240,16 +343,19 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 #
 # CPUFreq processor drivers
 #
+CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_X86_POWERNOW_K8=y
 CONFIG_X86_POWERNOW_K8_ACPI=y
 # CONFIG_X86_SPEEDSTEP_CENTRINO is not set
-CONFIG_X86_ACPI_CPUFREQ=y
+CONFIG_X86_P4_CLOCKMOD=y
 
 #
 # shared options
 #
 CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y
-# CONFIG_X86_SPEEDSTEP_LIB is not set
+CONFIG_X86_SPEEDSTEP_LIB=y
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_LADDER=y
 
 #
 # Bus options (PCI etc.)
@@ -257,16 +363,18 @@ CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y
 CONFIG_PCI=y
 CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
+CONFIG_PCI_DOMAINS=y
+# CONFIG_DMAR is not set
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCIEAER=y
+# CONFIG_PCIEASPM is not set
 CONFIG_ARCH_SUPPORTS_MSI=y
 CONFIG_PCI_MSI=y
+CONFIG_PCI_LEGACY=y
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_HT_IRQ is not set
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
+CONFIG_ISA_DMA_API=y
+CONFIG_K8_NB=y
 # CONFIG_PCCARD is not set
 # CONFIG_HOTPLUG_PCI is not set
 
@@ -274,10 +382,12 @@ CONFIG_PCI_MSI=y
 # Executable file formats / Emulations
 #
 CONFIG_BINFMT_ELF=y
+CONFIG_COMPAT_BINFMT_ELF=y
 # CONFIG_BINFMT_MISC is not set
 CONFIG_IA32_EMULATION=y
 CONFIG_IA32_AOUT=y
 CONFIG_COMPAT=y
+CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
 CONFIG_SYSVIPC_COMPAT=y
 
 #
@@ -313,6 +423,7 @@ CONFIG_INET_TUNNEL=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
@@ -334,8 +445,10 @@ CONFIG_IPV6=y
 # CONFIG_INET6_XFRM_MODE_BEET is not set
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_SIT=y
+CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_IPV6_TUNNEL is not set
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
+# CONFIG_IPV6_MROUTE is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
 # CONFIG_IP_DCCP is not set
@@ -352,10 +465,6 @@ CONFIG_IPV6_SIT=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
 # CONFIG_NET_SCHED is not set
 
 #
@@ -364,6 +473,7 @@ CONFIG_IPV6_SIT=y
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
@@ -385,6 +495,7 @@ CONFIG_IPV6_SIT=y
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
@@ -416,7 +527,7 @@ CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=16
 CONFIG_BLK_DEV_RAM_SIZE=4096
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+# CONFIG_BLK_DEV_XIP is not set
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
 CONFIG_MISC_DEVICES=y
@@ -427,17 +538,20 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_TIFM_CORE is not set
 # CONFIG_SONY_LAPTOP is not set
 # CONFIG_THINKPAD_ACPI is not set
+# CONFIG_INTEL_MENLOW is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDE=y
 
 #
-# Please see Documentation/ide.txt for help/info on IDE drives
+# Please see Documentation/ide/ide.txt for help/info on IDE drives
 #
 # CONFIG_BLK_DEV_IDE_SATA is not set
-# CONFIG_BLK_DEV_HD_IDE is not set
 CONFIG_BLK_DEV_IDEDISK=y
 CONFIG_IDEDISK_MULTI_MODE=y
 CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
 # CONFIG_BLK_DEV_IDETAPE is not set
 # CONFIG_BLK_DEV_IDEFLOPPY is not set
 # CONFIG_BLK_DEV_IDESCSI is not set
@@ -449,18 +563,21 @@ CONFIG_IDE_PROC_FS=y
 # IDE chipset support/bugfixes
 #
 CONFIG_IDE_GENERIC=y
+# CONFIG_BLK_DEV_PLATFORM is not set
 # CONFIG_BLK_DEV_CMD640 is not set
 # CONFIG_BLK_DEV_IDEPNP is not set
+CONFIG_BLK_DEV_IDEDMA_SFF=y
+
+#
+# PCI IDE chipsets support
+#
 CONFIG_BLK_DEV_IDEPCI=y
-# CONFIG_IDEPCI_SHARE_IRQ is not set
 CONFIG_IDEPCI_PCIBUS_ORDER=y
 # CONFIG_BLK_DEV_OFFBOARD is not set
 # CONFIG_BLK_DEV_GENERIC is not set
 # CONFIG_BLK_DEV_OPTI621 is not set
 # CONFIG_BLK_DEV_RZ1000 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
-# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-# CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
 CONFIG_BLK_DEV_AMD74XX=y
@@ -487,9 +604,8 @@ CONFIG_BLK_DEV_PDC202XX_NEW=y
 # CONFIG_BLK_DEV_TRM290 is not set
 # CONFIG_BLK_DEV_VIA82CXXX is not set
 # CONFIG_BLK_DEV_TC86C001 is not set
-# CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
-# CONFIG_IDEDMA_IVB is not set
+# CONFIG_BLK_DEV_HD_ONLY is not set
 # CONFIG_BLK_DEV_HD is not set
 
 #
@@ -528,105 +644,16 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_SPI_ATTRS=y
 CONFIG_SCSI_FC_ATTRS=y
 # CONFIG_SCSI_ISCSI_ATTRS is not set
-CONFIG_SCSI_SAS_ATTRS=y
 # CONFIG_SCSI_SAS_LIBSAS is not set
-
-#
-# SCSI low-level drivers
-#
-# CONFIG_ISCSI_TCP is not set
-# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
-# CONFIG_SCSI_3W_9XXX is not set
-# CONFIG_SCSI_ACARD is not set
-# CONFIG_SCSI_AACRAID is not set
-# CONFIG_SCSI_AIC7XXX is not set
-# CONFIG_SCSI_AIC7XXX_OLD is not set
-CONFIG_SCSI_AIC79XX=y
-CONFIG_AIC79XX_CMDS_PER_DEVICE=32
-CONFIG_AIC79XX_RESET_DELAY_MS=4000
-# CONFIG_AIC79XX_DEBUG_ENABLE is not set
-CONFIG_AIC79XX_DEBUG_MASK=0
-# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set
-# CONFIG_SCSI_AIC94XX is not set
-# CONFIG_SCSI_ARCMSR is not set
-# CONFIG_MEGARAID_NEWGEN is not set
-# CONFIG_MEGARAID_LEGACY is not set
-# CONFIG_MEGARAID_SAS is not set
-# CONFIG_SCSI_HPTIOP is not set
-# CONFIG_SCSI_BUSLOGIC is not set
-# CONFIG_SCSI_DMX3191D is not set
-# CONFIG_SCSI_EATA is not set
-# CONFIG_SCSI_FUTURE_DOMAIN is not set
-# CONFIG_SCSI_GDTH is not set
-# CONFIG_SCSI_IPS is not set
-# CONFIG_SCSI_INITIO is not set
-# CONFIG_SCSI_INIA100 is not set
-# CONFIG_SCSI_STEX is not set
-# CONFIG_SCSI_SYM53C8XX_2 is not set
-# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_1280 is not set
-# CONFIG_SCSI_QLA_FC is not set
-# CONFIG_SCSI_QLA_ISCSI is not set
-# CONFIG_SCSI_LPFC is not set
-# CONFIG_SCSI_DC395x is not set
-# CONFIG_SCSI_DC390T is not set
-# CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+# CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
+# CONFIG_SATA_PMP is not set
 CONFIG_SATA_AHCI=y
-CONFIG_SATA_SVW=y
-CONFIG_ATA_PIIX=y
-# CONFIG_SATA_MV is not set
-CONFIG_SATA_NV=y
-# CONFIG_PDC_ADMA is not set
-# CONFIG_SATA_QSTOR is not set
-# CONFIG_SATA_PROMISE is not set
-# CONFIG_SATA_SX4 is not set
-CONFIG_SATA_SIL=y
 # CONFIG_SATA_SIL24 is not set
-# CONFIG_SATA_SIS is not set
-# CONFIG_SATA_ULI is not set
-CONFIG_SATA_VIA=y
-# CONFIG_SATA_VITESSE is not set
-# CONFIG_SATA_INIC162X is not set
-# CONFIG_PATA_ALI is not set
-# CONFIG_PATA_AMD is not set
-# CONFIG_PATA_ARTOP is not set
-# CONFIG_PATA_ATIIXP is not set
-# CONFIG_PATA_CMD640_PCI is not set
-# CONFIG_PATA_CMD64X is not set
-# CONFIG_PATA_CS5520 is not set
-# CONFIG_PATA_CS5530 is not set
-# CONFIG_PATA_CYPRESS is not set
-# CONFIG_PATA_EFAR is not set
-# CONFIG_ATA_GENERIC is not set
-# CONFIG_PATA_HPT366 is not set
-# CONFIG_PATA_HPT37X is not set
-# CONFIG_PATA_HPT3X2N is not set
-# CONFIG_PATA_HPT3X3 is not set
-# CONFIG_PATA_IT821X is not set
-# CONFIG_PATA_IT8213 is not set
-# CONFIG_PATA_JMICRON is not set
-# CONFIG_PATA_TRIFLEX is not set
-# CONFIG_PATA_MARVELL is not set
-# CONFIG_PATA_MPIIX is not set
-# CONFIG_PATA_OLDPIIX is not set
-# CONFIG_PATA_NETCELL is not set
-# CONFIG_PATA_NS87410 is not set
-# CONFIG_PATA_OPTI is not set
-# CONFIG_PATA_OPTIDMA is not set
-# CONFIG_PATA_PDC_OLD is not set
-# CONFIG_PATA_RADISYS is not set
-# CONFIG_PATA_RZ1000 is not set
-# CONFIG_PATA_SC1200 is not set
-# CONFIG_PATA_SERVERWORKS is not set
-# CONFIG_PATA_PDC2027X is not set
-# CONFIG_PATA_SIL680 is not set
-# CONFIG_PATA_SIS is not set
-# CONFIG_PATA_VIA is not set
-# CONFIG_PATA_WINBOND is not set
+# CONFIG_ATA_SFF is not set
 CONFIG_MD=y
 # CONFIG_BLK_DEV_MD is not set
 CONFIG_BLK_DEV_DM=y
@@ -637,16 +664,14 @@ CONFIG_BLK_DEV_DM=y
 # CONFIG_DM_ZERO is not set
 # CONFIG_DM_MULTIPATH is not set
 # CONFIG_DM_DELAY is not set
-
-#
-# Fusion MPT device support
-#
+# CONFIG_DM_UEVENT is not set
 CONFIG_FUSION=y
 CONFIG_FUSION_SPI=y
 # CONFIG_FUSION_FC is not set
 # CONFIG_FUSION_SAS is not set
 CONFIG_FUSION_MAX_SGE=128
 # CONFIG_FUSION_CTL is not set
+# CONFIG_FUSION_LOGGING is not set
 
 #
 # IEEE 1394 (FireWire) support
@@ -687,6 +712,7 @@ CONFIG_NETDEVICES_MULTIQUEUE=y
 # CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 CONFIG_TUN=y
+# CONFIG_VETH is not set
 # CONFIG_NET_SB1000 is not set
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
@@ -709,15 +735,21 @@ CONFIG_TULIP=y
 # CONFIG_DM9102 is not set
 # CONFIG_ULI526X is not set
 # CONFIG_HP100 is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
 CONFIG_AMD8111_ETH=y
 # CONFIG_AMD8111E_NAPI is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
 CONFIG_B44=y
+CONFIG_B44_PCI_AUTOSELECT=y
+CONFIG_B44_PCICORE_AUTOSELECT=y
+CONFIG_B44_PCI=y
 CONFIG_FORCEDETH=y
 # CONFIG_FORCEDETH_NAPI is not set
-# CONFIG_DGRS is not set
 # CONFIG_EEPRO100 is not set
 CONFIG_E100=y
 # CONFIG_FEALNX is not set
@@ -729,6 +761,7 @@ CONFIG_8139TOO=y
 # CONFIG_8139TOO_TUNE_TWISTER is not set
 # CONFIG_8139TOO_8129 is not set
 # CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_R6040 is not set
 # CONFIG_SIS900 is not set
 # CONFIG_EPIC100 is not set
 # CONFIG_SUNDANCE is not set
@@ -740,6 +773,10 @@ CONFIG_NETDEV_1000=y
 CONFIG_E1000=y
 # CONFIG_E1000_NAPI is not set
 # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set
+# CONFIG_E1000E is not set
+# CONFIG_E1000E_ENABLED is not set
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -755,12 +792,17 @@ CONFIG_BNX2=y
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 # CONFIG_CHELSIO_T3 is not set
+# CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 CONFIG_S2IO=m
 # CONFIG_S2IO_NAPI is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
+# CONFIG_NIU is not set
 # CONFIG_MLX4_CORE is not set
+# CONFIG_TEHUTI is not set
+# CONFIG_BNX2X is not set
+# CONFIG_SFC is not set
 # CONFIG_TR is not set
 
 #
@@ -768,6 +810,8 @@ CONFIG_S2IO=m
 #
 # CONFIG_WLAN_PRE80211 is not set
 # CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI is not set
+# CONFIG_IWLWIFI_LEDS is not set
 
 #
 # USB Network Adapters
@@ -776,7 +820,6 @@ CONFIG_S2IO=m
 # CONFIG_USB_KAWETH is not set
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
 # CONFIG_USB_USBNET is not set
 # CONFIG_WAN is not set
 # CONFIG_FDDI is not set
@@ -784,8 +827,8 @@ CONFIG_S2IO=m
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
 # CONFIG_NET_FC is not set
-# CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
+# CONFIG_NETCONSOLE_DYNAMIC is not set
 CONFIG_NETPOLL=y
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
@@ -807,7 +850,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_EVBUG is not set
 
@@ -856,7 +898,9 @@ CONFIG_VT=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 # CONFIG_VT_HW_CONSOLE_BINDING is not set
+# CONFIG_DEVKMEM is not set
 # CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_NOZOMI is not set
 
 #
 # Serial drivers
@@ -880,7 +924,6 @@ CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
 # CONFIG_IPMI_HANDLER is not set
-# CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_INTEL=y
 CONFIG_HW_RANDOM_AMD=y
@@ -888,12 +931,6 @@ CONFIG_HW_RANDOM_AMD=y
 CONFIG_RTC=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
-CONFIG_AGP=y
-CONFIG_AGP_AMD64=y
-CONFIG_AGP_INTEL=y
-# CONFIG_AGP_SIS is not set
-# CONFIG_AGP_VIA is not set
-# CONFIG_DRM is not set
 # CONFIG_MWAVE is not set
 # CONFIG_PC8736x_GPIO is not set
 CONFIG_RAW_DRIVER=y
@@ -906,40 +943,69 @@ CONFIG_HPET_MMAP=y
 # CONFIG_TELCLOCK is not set
 CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
-
-#
-# SPI support
-#
 # CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
 # CONFIG_W1 is not set
-# CONFIG_POWER_SUPPLY is not set
+CONFIG_POWER_SUPPLY=y
+# CONFIG_POWER_SUPPLY_DEBUG is not set
+# CONFIG_PDA_POWER is not set
+# CONFIG_BATTERY_DS2760 is not set
 # CONFIG_HWMON is not set
+CONFIG_THERMAL=y
+# CONFIG_WATCHDOG is not set
+
+#
+# Sonics Silicon Backplane
+#
+CONFIG_SSB_POSSIBLE=y
+CONFIG_SSB=y
+CONFIG_SSB_SPROM=y
+CONFIG_SSB_PCIHOST_POSSIBLE=y
+CONFIG_SSB_PCIHOST=y
+# CONFIG_SSB_B43_PCI_BRIDGE is not set
+# CONFIG_SSB_DEBUG is not set
+CONFIG_SSB_DRIVER_PCICORE_POSSIBLE=y
+CONFIG_SSB_DRIVER_PCICORE=y
 
 #
 # Multifunction device drivers
 #
 # CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
 
 #
 # Multimedia devices
 #
+
+#
+# Multimedia core support
+#
 # CONFIG_VIDEO_DEV is not set
 # CONFIG_DVB_CORE is not set
+
+#
+# Multimedia drivers
+#
 CONFIG_DAB=y
 # CONFIG_USB_DABUSB is not set
 
 #
 # Graphics support
 #
+CONFIG_AGP=y
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+# CONFIG_AGP_SIS is not set
+# CONFIG_AGP_VIA is not set
+# CONFIG_DRM is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
 
 #
 # Display device support
 #
 # CONFIG_DISPLAY_SUPPORT is not set
-# CONFIG_VGASTATE is not set
-# CONFIG_FB is not set
 
 #
 # Console display driver support
@@ -971,6 +1037,7 @@ CONFIG_SOUND_PRIME=y
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
+CONFIG_HIDRAW=y
 
 #
 # USB Input Devices
@@ -985,6 +1052,7 @@ CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
 CONFIG_USB=y
 # CONFIG_USB_DEBUG is not set
+# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
 
 #
 # Miscellaneous USB options
@@ -993,18 +1061,19 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
-# CONFIG_USB_PERSIST is not set
 # CONFIG_USB_OTG is not set
 
 #
 # USB Host Controller Drivers
 #
+# CONFIG_USB_C67X00_HCD is not set
 CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
 # CONFIG_USB_ISP116X_HCD is not set
+# CONFIG_USB_ISP1760_HCD is not set
 CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_HCD_SSB is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
@@ -1036,7 +1105,9 @@ CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_SDDR55 is not set
 # CONFIG_USB_STORAGE_JUMPSHOT is not set
 # CONFIG_USB_STORAGE_ALAUDA is not set
+# CONFIG_USB_STORAGE_ONETOUCH is not set
 # CONFIG_USB_STORAGE_KARMA is not set
+# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
 # CONFIG_USB_LIBUSUAL is not set
 
 #
@@ -1049,10 +1120,6 @@ CONFIG_USB_MON=y
 #
 # USB port drivers
 #
-
-#
-# USB Serial Converter support
-#
 # CONFIG_USB_SERIAL is not set
 
 #
@@ -1078,55 +1145,20 @@ CONFIG_USB_MON=y
 # CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
-
-#
-# USB DSL modem support
-#
-
-#
-# USB Gadget Support
-#
 # CONFIG_USB_GADGET is not set
 # CONFIG_MMC is not set
-
-#
-# LED devices
-#
+# CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
-
-#
-# LED drivers
-#
-
-#
-# LED Triggers
-#
+# CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 # CONFIG_EDAC is not set
-
-#
-# Real Time Clock
-#
 # CONFIG_RTC_CLASS is not set
-
-#
-# DMA Engine support
-#
-# CONFIG_DMA_ENGINE is not set
-
-#
-# DMA Clients
-#
+CONFIG_DMADEVICES=y
 
 #
 # DMA Devices
 #
-CONFIG_VIRTUALIZATION=y
-# CONFIG_KVM is not set
-
-#
-# Userspace I/O
-#
+# CONFIG_INTEL_IOATDMA is not set
 # CONFIG_UIO is not set
 
 #
@@ -1136,6 +1168,7 @@ CONFIG_VIRTUALIZATION=y
 # CONFIG_DELL_RBU is not set
 # CONFIG_DCDBAS is not set
 CONFIG_DMIID=y
+# CONFIG_ISCSI_IBFT_FIND is not set
 
 #
 # File systems
@@ -1164,12 +1197,10 @@ CONFIG_FS_POSIX_ACL=y
 # CONFIG_XFS_FS is not set
 # CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
 # CONFIG_AUTOFS_FS is not set
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
@@ -1204,7 +1235,6 @@ CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
-CONFIG_RAMFS=y
 # CONFIG_CONFIGFS_FS is not set
 
 #
@@ -1219,48 +1249,19 @@ CONFIG_RAMFS=y
 # CONFIG_EFS_FS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-# CONFIG_NFS_V3_ACL is not set
-# CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
-CONFIG_NFSD=y
-CONFIG_NFSD_V3=y
-# CONFIG_NFSD_V3_ACL is not set
-# CONFIG_NFSD_V4 is not set
-CONFIG_NFSD_TCP=y
-CONFIG_ROOT_NFS=y
-CONFIG_LOCKD=y
-CONFIG_LOCKD_V4=y
-CONFIG_EXPORTFS=y
-CONFIG_NFS_COMMON=y
-CONFIG_SUNRPC=y
-# CONFIG_SUNRPC_BIND34 is not set
-# CONFIG_RPCSEC_GSS_KRB5 is not set
-# CONFIG_RPCSEC_GSS_SPKM3 is not set
-# CONFIG_SMB_FS is not set
-# CONFIG_CIFS is not set
-# CONFIG_NCP_FS is not set
-# CONFIG_CODA_FS is not set
-# CONFIG_AFS_FS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
 
 #
 # Partition Types
 #
 # CONFIG_PARTITION_ADVANCED is not set
 CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
 CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="iso8859-1"
 CONFIG_NLS_CODEPAGE_437=y
@@ -1301,25 +1302,16 @@ CONFIG_NLS_ISO8859_15=y
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 CONFIG_NLS_UTF8=y
-
-#
-# Distributed Lock Manager
-#
 # CONFIG_DLM is not set
 
-#
-# Instrumentation Support
-#
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
-
 #
 # Kernel hacking
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
 # CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=2048
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_UNUSED_SYMBOLS=y
 CONFIG_DEBUG_FS=y
@@ -1330,6 +1322,7 @@ CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 CONFIG_TIMER_STATS=y
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
@@ -1344,28 +1337,64 @@ CONFIG_TIMER_STATS=y
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
 # CONFIG_FRAME_POINTER is not set
-CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
 # CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_KPROBES_SANITY_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_LKDTM is not set
 # CONFIG_FAULT_INJECTION is not set
-# CONFIG_DEBUG_RODATA is not set
-# CONFIG_IOMMU_DEBUG is not set
+# CONFIG_LATENCYTOP is not set
+# CONFIG_PROVIDE_OHCI1394_DMA_INIT is not set
+# CONFIG_SAMPLES is not set
+# CONFIG_KGDB is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_NONPROMISC_DEVMEM is not set
+CONFIG_EARLY_PRINTK=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 # CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_DEBUG_PER_CPU_MAPS is not set
+# CONFIG_X86_PTDUMP is not set
+# CONFIG_DEBUG_RODATA is not set
+# CONFIG_DIRECT_GBPAGES is not set
+# CONFIG_DEBUG_NX_TEST is not set
+CONFIG_X86_MPPARSE=y
+# CONFIG_IOMMU_DEBUG is not set
+CONFIG_IO_DELAY_TYPE_0X80=0
+CONFIG_IO_DELAY_TYPE_0XED=1
+CONFIG_IO_DELAY_TYPE_UDELAY=2
+CONFIG_IO_DELAY_TYPE_NONE=3
+CONFIG_IO_DELAY_0X80=y
+# CONFIG_IO_DELAY_0XED is not set
+# CONFIG_IO_DELAY_UDELAY is not set
+# CONFIG_IO_DELAY_NONE is not set
+CONFIG_DEFAULT_IO_DELAY_TYPE=0
+# CONFIG_DEBUG_BOOT_PARAMS is not set
+# CONFIG_CPA_DEBUG is not set
 
 #
 # Security options
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_HAVE_KVM is not set
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_KVM is not set
+# CONFIG_VIRTIO_PCI is not set
+# CONFIG_VIRTIO_BALLOON is not set
 
 #
 # Library routines
 #
 CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
 # CONFIG_CRC_ITU_T is not set
-- 
cgit v1.2.2


From b5d958ea66ac11b1190c24f042f517adf9229a98 Mon Sep 17 00:00:00 2001
From: Auke Kok <auke-jan.h.kok@intel.com>
Date: Wed, 9 Apr 2008 13:17:39 -0700
Subject: e1000e: set CONFIG_E1000E=y in x86 defconfigs

This adds to the already default CONFIG_E1000=y in these files.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/configs/i386_defconfig | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index ad7ddaaff588..73f2c3cb7cda 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -814,6 +814,10 @@ CONFIG_NETDEV_1000=y
 CONFIG_E1000=y
 # CONFIG_E1000_NAPI is not set
 # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set
+CONFIG_E1000E=y
+CONFIG_E1000E_ENABLED=y
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
-- 
cgit v1.2.2


From 5cb04df8d3f03e37a19f2502591a84156be71772 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 4 May 2008 19:49:04 +0200
Subject: x86: defconfig updates

refresh 32-bit defconfig too, and update the 64-bit configs as well,
the defconfig should be much more useful by default, so most of the
updates are the enabling of various options.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/configs/i386_defconfig   | 1711 ++++++++++++++++++++++++++-----------
 arch/x86/configs/x86_64_defconfig | 1378 ++++++++++++++++++++++-------
 2 files changed, 2291 insertions(+), 798 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 73f2c3cb7cda..9bc34e2033ec 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,54 +1,103 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-git14
-# Fri Jul 20 09:53:15 2007
+# Linux kernel version: 2.6.26-rc1
+# Sun May  4 19:59:02 2008
 #
+# CONFIG_64BIT is not set
 CONFIG_X86_32=y
+# CONFIG_X86_64 is not set
+CONFIG_X86=y
+CONFIG_DEFCONFIG_LIST="arch/x86/configs/i386_defconfig"
+# CONFIG_GENERIC_LOCKBREAK is not set
 CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_CLOCKSOURCE_WATCHDOG=y
 CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
-CONFIG_SEMAPHORE_SLEEPERS=y
-CONFIG_X86=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_FAST_CMPXCHG_LOCAL=y
 CONFIG_MMU=y
 CONFIG_ZONE_DMA=y
-CONFIG_QUICKLIST=y
 CONFIG_GENERIC_ISA_DMA=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_GENERIC_BUG=y
 CONFIG_GENERIC_HWEIGHT=y
+# CONFIG_GENERIC_GPIO is not set
 CONFIG_ARCH_MAY_HAVE_PC_FDC=y
-CONFIG_DMI=y
-CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_HAS_CPU_IDLE_WAIT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+# CONFIG_GENERIC_TIME_VSYSCALL is not set
+CONFIG_ARCH_HAS_CPU_RELAX=y
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+# CONFIG_HAVE_CPUMASK_OF_CPU_MAP is not set
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+# CONFIG_ZONE_DMA32 is not set
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+# CONFIG_AUDIT_ARCH is not set
+CONFIG_ARCH_SUPPORTS_AOUT=y
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_PENDING_IRQ=y
+CONFIG_X86_SMP=y
+CONFIG_X86_32_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_BIOS_REBOOT=y
+CONFIG_X86_TRAMPOLINE=y
+CONFIG_KTIME_SCALAR=y
 
 #
-# Code maturity level options
+# General setup
 #
 CONFIG_EXPERIMENTAL=y
 CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
 CONFIG_LOCALVERSION=""
-CONFIG_LOCALVERSION_AUTO=y
+# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
-# CONFIG_BSD_PROCESS_ACCT is not set
-# CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_AUDIT is not set
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=18
-# CONFIG_CPUSETS is not set
-CONFIG_SYSFS_DEPRECATED=y
+CONFIG_BSD_PROCESS_ACCT=y
+# CONFIG_BSD_PROCESS_ACCT_V3 is not set
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_AUDIT_TREE=y
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+CONFIG_CGROUPS=y
+# CONFIG_CGROUP_DEBUG is not set
+CONFIG_CGROUP_NS=y
+# CONFIG_CGROUP_DEVICE is not set
+CONFIG_CPUSETS=y
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+# CONFIG_RT_GROUP_SCHED is not set
+# CONFIG_USER_SCHED is not set
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+# CONFIG_CGROUP_MEM_RES_CTLR is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
+CONFIG_PROC_PID_CPUSET=y
 CONFIG_RELAY=y
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
@@ -56,13 +105,15 @@ CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
-# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 CONFIG_ANON_INODES=y
@@ -76,6 +127,17 @@ CONFIG_SLUB_DEBUG=y
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+CONFIG_MARKERS=y
+# CONFIG_OPROFILE is not set
+CONFIG_HAVE_OPROFILE=y
+CONFIG_KPROBES=y
+CONFIG_KRETPROBES=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+# CONFIG_HAVE_DMA_ATTRS is not set
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
@@ -87,10 +149,10 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_KMOD is not set
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
-CONFIG_LBD=y
-# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LBD is not set
+CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_LSF is not set
-# CONFIG_BLK_DEV_BSG is not set
+CONFIG_BLK_DEV_BSG=y
 
 #
 # IO Schedulers
@@ -103,7 +165,8 @@ CONFIG_IOSCHED_CFQ=y
 # CONFIG_DEFAULT_DEADLINE is not set
 CONFIG_DEFAULT_CFQ=y
 # CONFIG_DEFAULT_NOOP is not set
-CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_CLASSIC_RCU=y
 
 #
 # Processor type and features
@@ -111,18 +174,21 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
 CONFIG_TICK_ONESHOT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
-# CONFIG_X86_PC is not set
+CONFIG_X86_PC=y
 # CONFIG_X86_ELAN is not set
 # CONFIG_X86_VOYAGER is not set
 # CONFIG_X86_NUMAQ is not set
 # CONFIG_X86_SUMMIT is not set
 # CONFIG_X86_BIGSMP is not set
 # CONFIG_X86_VISWS is not set
-CONFIG_X86_GENERICARCH=y
+# CONFIG_X86_GENERICARCH is not set
 # CONFIG_X86_ES7000 is not set
-# CONFIG_PARAVIRT is not set
-CONFIG_X86_CYCLONE_TIMER=y
+# CONFIG_X86_RDC321X is not set
+# CONFIG_X86_VSMP is not set
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+# CONFIG_PARAVIRT_GUEST is not set
 # CONFIG_M386 is not set
 # CONFIG_M486 is not set
 # CONFIG_M586 is not set
@@ -130,9 +196,8 @@ CONFIG_X86_CYCLONE_TIMER=y
 # CONFIG_M586MMX is not set
 # CONFIG_M686 is not set
 # CONFIG_MPENTIUMII is not set
-CONFIG_MPENTIUMIII=y
+# CONFIG_MPENTIUMIII is not set
 # CONFIG_MPENTIUMM is not set
-# CONFIG_MCORE2 is not set
 # CONFIG_MPENTIUM4 is not set
 # CONFIG_MK6 is not set
 # CONFIG_MK7 is not set
@@ -147,14 +212,14 @@ CONFIG_MPENTIUMIII=y
 # CONFIG_MCYRIXIII is not set
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
-CONFIG_X86_GENERIC=y
+# CONFIG_MPSC is not set
+CONFIG_MCORE2=y
+# CONFIG_GENERIC_CPU is not set
+# CONFIG_X86_GENERIC is not set
+CONFIG_X86_CPU=y
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=6
 CONFIG_X86_XADD=y
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
-# CONFIG_ARCH_HAS_ILOG2_U32 is not set
-# CONFIG_ARCH_HAS_ILOG2_U64 is not set
-CONFIG_GENERIC_CALIBRATE_DELAY=y
 CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_INVLPG=y
 CONFIG_X86_BSWAP=y
@@ -162,106 +227,120 @@ CONFIG_X86_POPAD_OK=y
 CONFIG_X86_GOOD_APIC=y
 CONFIG_X86_INTEL_USERCOPY=y
 CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_P6_NOP=y
 CONFIG_X86_TSC=y
-CONFIG_X86_CMOV=y
-CONFIG_X86_MINIMUM_CPU_FAMILY=4
+CONFIG_X86_MINIMUM_CPU_FAMILY=6
+CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
-CONFIG_NR_CPUS=32
-CONFIG_SCHED_SMT=y
+CONFIG_DMI=y
+# CONFIG_IOMMU_HELPER is not set
+CONFIG_NR_CPUS=4
+# CONFIG_SCHED_SMT is not set
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_PREEMPT is not set
-CONFIG_PREEMPT_BKL=y
 CONFIG_X86_LOCAL_APIC=y
 CONFIG_X86_IO_APIC=y
-CONFIG_X86_MCE=y
-CONFIG_X86_MCE_NONFATAL=y
-CONFIG_X86_MCE_P4THERMAL=y
+# CONFIG_X86_MCE is not set
 CONFIG_VM86=y
 # CONFIG_TOSHIBA is not set
 # CONFIG_I8K is not set
 # CONFIG_X86_REBOOTFIXUPS is not set
-CONFIG_MICROCODE=y
-CONFIG_MICROCODE_OLD_INTERFACE=y
+# CONFIG_MICROCODE is not set
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
-
-#
-# Firmware Drivers
-#
-# CONFIG_EDD is not set
-# CONFIG_DELL_RBU is not set
-# CONFIG_DCDBAS is not set
-CONFIG_DMIID=y
 # CONFIG_NOHIGHMEM is not set
 CONFIG_HIGHMEM4G=y
 # CONFIG_HIGHMEM64G is not set
 CONFIG_PAGE_OFFSET=0xC0000000
 CONFIG_HIGHMEM=y
-CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_NEED_NODE_MEMMAP_SIZE=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_SELECT_MEMORY_MODEL=y
-CONFIG_FLATMEM_MANUAL=y
+# CONFIG_FLATMEM_MANUAL is not set
 # CONFIG_DISCONTIGMEM_MANUAL is not set
-# CONFIG_SPARSEMEM_MANUAL is not set
-CONFIG_FLATMEM=y
-CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
+CONFIG_HAVE_MEMORY_PRESENT=y
+CONFIG_SPARSEMEM_STATIC=y
+# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set
+
+#
+# Memory hotplug is currently incompatible with Software Suspend
+#
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
-CONFIG_NR_QUICK=1
 CONFIG_VIRT_TO_BUS=y
 # CONFIG_HIGHPTE is not set
 # CONFIG_MATH_EMULATION is not set
 CONFIG_MTRR=y
-# CONFIG_EFI is not set
+# CONFIG_X86_PAT is not set
+CONFIG_EFI=y
 # CONFIG_IRQBALANCE is not set
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
-CONFIG_HZ_250=y
+# CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
-# CONFIG_HZ_1000 is not set
-CONFIG_HZ=250
-# CONFIG_KEXEC is not set
-# CONFIG_CRASH_DUMP is not set
-CONFIG_PHYSICAL_START=0x100000
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_ALIGN=0x100000
-# CONFIG_HOTPLUG_CPU is not set
-CONFIG_COMPAT_VDSO=y
+CONFIG_HZ_1000=y
+CONFIG_HZ=1000
+CONFIG_SCHED_HRTICK=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+CONFIG_PHYSICAL_START=0x1000000
+CONFIG_RELOCATABLE=y
+CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_HOTPLUG_CPU=y
+# CONFIG_COMPAT_VDSO is not set
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 
 #
-# Power management options (ACPI, APM)
+# Power management options
 #
 CONFIG_PM=y
-CONFIG_PM_LEGACY=y
-# CONFIG_PM_DEBUG is not set
-
-#
-# ACPI (Advanced Configuration and Power Interface) Support
-#
+CONFIG_PM_DEBUG=y
+# CONFIG_PM_VERBOSE is not set
+CONFIG_CAN_PM_TRACE=y
+CONFIG_PM_TRACE=y
+CONFIG_PM_TRACE_RTC=y
+CONFIG_PM_SLEEP_SMP=y
+CONFIG_PM_SLEEP=y
+CONFIG_SUSPEND=y
+CONFIG_SUSPEND_FREEZER=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_STD_PARTITION=""
 CONFIG_ACPI=y
+CONFIG_ACPI_SLEEP=y
 CONFIG_ACPI_PROCFS=y
+CONFIG_ACPI_PROCFS_POWER=y
+CONFIG_ACPI_SYSFS_POWER=y
+CONFIG_ACPI_PROC_EVENT=y
 CONFIG_ACPI_AC=y
 CONFIG_ACPI_BATTERY=y
 CONFIG_ACPI_BUTTON=y
 CONFIG_ACPI_FAN=y
-# CONFIG_ACPI_DOCK is not set
+CONFIG_ACPI_DOCK=y
+# CONFIG_ACPI_BAY is not set
 CONFIG_ACPI_PROCESSOR=y
+CONFIG_ACPI_HOTPLUG_CPU=y
 CONFIG_ACPI_THERMAL=y
+# CONFIG_ACPI_WMI is not set
 # CONFIG_ACPI_ASUS is not set
 # CONFIG_ACPI_TOSHIBA is not set
-CONFIG_ACPI_BLACKLIST_YEAR=2001
-CONFIG_ACPI_DEBUG=y
+# CONFIG_ACPI_CUSTOM_DSDT is not set
+CONFIG_ACPI_BLACKLIST_YEAR=0
+# CONFIG_ACPI_DEBUG is not set
 CONFIG_ACPI_EC=y
 CONFIG_ACPI_POWER=y
 CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
-# CONFIG_ACPI_CONTAINER is not set
+CONFIG_ACPI_CONTAINER=y
 # CONFIG_ACPI_SBS is not set
 # CONFIG_APM is not set
 
@@ -271,15 +350,17 @@ CONFIG_X86_PM_TIMER=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_TABLE=y
 CONFIG_CPU_FREQ_DEBUG=y
-CONFIG_CPU_FREQ_STAT=y
-# CONFIG_CPU_FREQ_STAT_DETAILS is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
-# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_STAT is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
 
 #
 # CPUFreq processor drivers
@@ -287,8 +368,7 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_X86_ACPI_CPUFREQ=y
 # CONFIG_X86_POWERNOW_K6 is not set
 # CONFIG_X86_POWERNOW_K7 is not set
-CONFIG_X86_POWERNOW_K8=y
-CONFIG_X86_POWERNOW_K8_ACPI=y
+# CONFIG_X86_POWERNOW_K8 is not set
 # CONFIG_X86_GX_SUSPMOD is not set
 # CONFIG_X86_SPEEDSTEP_CENTRINO is not set
 # CONFIG_X86_SPEEDSTEP_ICH is not set
@@ -302,43 +382,72 @@ CONFIG_X86_POWERNOW_K8_ACPI=y
 #
 # shared options
 #
-CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y
+# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set
 # CONFIG_X86_SPEEDSTEP_LIB is not set
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
 
 #
-# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
+# Bus options (PCI etc.)
 #
 CONFIG_PCI=y
 # CONFIG_PCI_GOBIOS is not set
 # CONFIG_PCI_GOMMCONFIG is not set
 # CONFIG_PCI_GODIRECT is not set
 CONFIG_PCI_GOANY=y
+# CONFIG_PCI_GOOLPC is not set
 CONFIG_PCI_BIOS=y
 CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
-# CONFIG_PCIEPORTBUS is not set
+CONFIG_PCI_DOMAINS=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_HOTPLUG_PCI_PCIE is not set
+CONFIG_PCIEAER=y
+# CONFIG_PCIEASPM is not set
 CONFIG_ARCH_SUPPORTS_MSI=y
 CONFIG_PCI_MSI=y
+# CONFIG_PCI_LEGACY is not set
 # CONFIG_PCI_DEBUG is not set
-# CONFIG_HT_IRQ is not set
+CONFIG_HT_IRQ=y
 CONFIG_ISA_DMA_API=y
 # CONFIG_ISA is not set
 # CONFIG_MCA is not set
 # CONFIG_SCx200 is not set
+# CONFIG_OLPC is not set
 CONFIG_K8_NB=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
-# CONFIG_PCCARD is not set
-# CONFIG_HOTPLUG_PCI is not set
-
-#
-# Executable file formats
+CONFIG_PCCARD=y
+# CONFIG_PCMCIA_DEBUG is not set
+CONFIG_PCMCIA=y
+CONFIG_PCMCIA_LOAD_CIS=y
+CONFIG_PCMCIA_IOCTL=y
+CONFIG_CARDBUS=y
+
+#
+# PC-card bridges
+#
+CONFIG_YENTA=y
+CONFIG_YENTA_O2=y
+CONFIG_YENTA_RICOH=y
+CONFIG_YENTA_TI=y
+CONFIG_YENTA_ENE_TUNE=y
+CONFIG_YENTA_TOSHIBA=y
+# CONFIG_PD6729 is not set
+# CONFIG_I82092 is not set
+CONFIG_PCCARD_NONSTATIC=y
+CONFIG_HOTPLUG_PCI=y
+# CONFIG_HOTPLUG_PCI_FAKE is not set
+# CONFIG_HOTPLUG_PCI_IBM is not set
+# CONFIG_HOTPLUG_PCI_ACPI is not set
+# CONFIG_HOTPLUG_PCI_CPCI is not set
+# CONFIG_HOTPLUG_PCI_SHPC is not set
+
+#
+# Executable file formats / Emulations
 #
 CONFIG_BINFMT_ELF=y
 # CONFIG_BINFMT_AOUT is not set
-# CONFIG_BINFMT_MISC is not set
+CONFIG_BINFMT_MISC=y
 
 #
 # Networking
@@ -349,59 +458,142 @@ CONFIG_NET=y
 # Networking options
 #
 CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
+CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
 CONFIG_XFRM=y
-# CONFIG_XFRM_USER is not set
+CONFIG_XFRM_USER=y
 # CONFIG_XFRM_SUB_POLICY is not set
 # CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
-# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_ASK_IP_FIB_HASH=y
+# CONFIG_IP_FIB_TRIE is not set
 CONFIG_IP_FIB_HASH=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IP_PNP_BOOTP is not set
-# CONFIG_IP_PNP_RARP is not set
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
 # CONFIG_NET_IPIP is not set
 # CONFIG_NET_IPGRE is not set
-# CONFIG_IP_MROUTE is not set
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
 # CONFIG_ARPD is not set
-# CONFIG_SYN_COOKIES is not set
+CONFIG_SYN_COOKIES=y
 # CONFIG_INET_AH is not set
 # CONFIG_INET_ESP is not set
 # CONFIG_INET_IPCOMP is not set
 # CONFIG_INET_XFRM_TUNNEL is not set
 CONFIG_INET_TUNNEL=y
-CONFIG_INET_XFRM_MODE_TRANSPORT=y
-CONFIG_INET_XFRM_MODE_TUNNEL=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-CONFIG_INET_DIAG=y
-CONFIG_INET_TCP_DIAG=y
-# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_INET_LRO=y
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
 CONFIG_TCP_CONG_CUBIC=y
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_TCP_CONG_HSTCP is not set
+# CONFIG_TCP_CONG_HYBLA is not set
+# CONFIG_TCP_CONG_VEGAS is not set
+# CONFIG_TCP_CONG_SCALABLE is not set
+# CONFIG_TCP_CONG_LP is not set
+# CONFIG_TCP_CONG_VENO is not set
+# CONFIG_TCP_CONG_YEAH is not set
+# CONFIG_TCP_CONG_ILLINOIS is not set
+# CONFIG_DEFAULT_BIC is not set
+CONFIG_DEFAULT_CUBIC=y
+# CONFIG_DEFAULT_HTCP is not set
+# CONFIG_DEFAULT_VEGAS is not set
+# CONFIG_DEFAULT_WESTWOOD is not set
+# CONFIG_DEFAULT_RENO is not set
 CONFIG_DEFAULT_TCP_CONG="cubic"
-# CONFIG_TCP_MD5SIG is not set
+CONFIG_TCP_MD5SIG=y
+# CONFIG_IP_VS is not set
 CONFIG_IPV6=y
 # CONFIG_IPV6_PRIVACY is not set
 # CONFIG_IPV6_ROUTER_PREF is not set
 # CONFIG_IPV6_OPTIMISTIC_DAD is not set
-# CONFIG_INET6_AH is not set
-# CONFIG_INET6_ESP is not set
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
 # CONFIG_INET6_IPCOMP is not set
 # CONFIG_IPV6_MIP6 is not set
 # CONFIG_INET6_XFRM_TUNNEL is not set
 # CONFIG_INET6_TUNNEL is not set
 CONFIG_INET6_XFRM_MODE_TRANSPORT=y
 CONFIG_INET6_XFRM_MODE_TUNNEL=y
-# CONFIG_INET6_XFRM_MODE_BEET is not set
+CONFIG_INET6_XFRM_MODE_BEET=y
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_SIT=y
+CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_IPV6_TUNNEL is not set
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
-# CONFIG_NETWORK_SECMARK is not set
-# CONFIG_NETFILTER is not set
+# CONFIG_IPV6_MROUTE is not set
+CONFIG_NETLABEL=y
+CONFIG_NETWORK_SECMARK=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+# CONFIG_NETFILTER_ADVANCED is not set
+
+#
+# Core Netfilter Configuration
+#
+CONFIG_NETFILTER_NETLINK=y
+CONFIG_NETFILTER_NETLINK_LOG=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_SIP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XTABLES=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_PROC_COMPAT=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_NF_NAT=y
+CONFIG_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_NF_NAT_FTP=y
+CONFIG_NF_NAT_IRC=y
+# CONFIG_NF_NAT_TFTP is not set
+# CONFIG_NF_NAT_AMANDA is not set
+# CONFIG_NF_NAT_PPTP is not set
+# CONFIG_NF_NAT_H323 is not set
+CONFIG_NF_NAT_SIP=y
+CONFIG_IP_NF_MANGLE=y
+
+#
+# IPv6: Netfilter Configuration
+#
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_LOG=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
 # CONFIG_IP_DCCP is not set
 # CONFIG_IP_SCTP is not set
 # CONFIG_TIPC is not set
@@ -409,6 +601,7 @@ CONFIG_IPV6_SIT=y
 # CONFIG_BRIDGE is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
+CONFIG_LLC=y
 # CONFIG_LLC2 is not set
 # CONFIG_IPX is not set
 # CONFIG_ATALK is not set
@@ -416,28 +609,99 @@ CONFIG_IPV6_SIT=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
-# CONFIG_NET_SCHED is not set
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+# CONFIG_NET_SCH_CBQ is not set
+# CONFIG_NET_SCH_HTB is not set
+# CONFIG_NET_SCH_HFSC is not set
+# CONFIG_NET_SCH_PRIO is not set
+# CONFIG_NET_SCH_RR is not set
+# CONFIG_NET_SCH_RED is not set
+# CONFIG_NET_SCH_SFQ is not set
+# CONFIG_NET_SCH_TEQL is not set
+# CONFIG_NET_SCH_TBF is not set
+# CONFIG_NET_SCH_GRED is not set
+# CONFIG_NET_SCH_DSMARK is not set
+# CONFIG_NET_SCH_NETEM is not set
+# CONFIG_NET_SCH_INGRESS is not set
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+# CONFIG_NET_CLS_BASIC is not set
+# CONFIG_NET_CLS_TCINDEX is not set
+# CONFIG_NET_CLS_ROUTE4 is not set
+# CONFIG_NET_CLS_FW is not set
+# CONFIG_NET_CLS_U32 is not set
+# CONFIG_NET_CLS_RSVP is not set
+# CONFIG_NET_CLS_RSVP6 is not set
+# CONFIG_NET_CLS_FLOW is not set
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+# CONFIG_NET_EMATCH_CMP is not set
+# CONFIG_NET_EMATCH_NBYTE is not set
+# CONFIG_NET_EMATCH_U32 is not set
+# CONFIG_NET_EMATCH_META is not set
+# CONFIG_NET_EMATCH_TEXT is not set
+CONFIG_NET_CLS_ACT=y
+# CONFIG_NET_ACT_POLICE is not set
+# CONFIG_NET_ACT_GACT is not set
+# CONFIG_NET_ACT_MIRRED is not set
+# CONFIG_NET_ACT_IPT is not set
+# CONFIG_NET_ACT_NAT is not set
+# CONFIG_NET_ACT_PEDIT is not set
+# CONFIG_NET_ACT_SIMP is not set
+CONFIG_NET_SCH_FIFO=y
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
-# CONFIG_HAMRADIO is not set
+CONFIG_HAMRADIO=y
+
+#
+# Packet Radio protocols
+#
+# CONFIG_AX25 is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_FIB_RULES=y
 
 #
 # Wireless
 #
-# CONFIG_CFG80211 is not set
-# CONFIG_WIRELESS_EXT is not set
-# CONFIG_MAC80211 is not set
+CONFIG_CFG80211=y
+CONFIG_NL80211=y
+CONFIG_WIRELESS_EXT=y
+CONFIG_MAC80211=y
+
+#
+# Rate control algorithm selection
+#
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+# CONFIG_MAC80211_RC_DEFAULT_NONE is not set
+
+#
+# Selecting 'y' for an algorithm will
+#
+
+#
+# build the algorithm into mac80211.
+#
+CONFIG_MAC80211_RC_DEFAULT="pid"
+CONFIG_MAC80211_RC_PID=y
+# CONFIG_MAC80211_MESH is not set
+CONFIG_MAC80211_LEDS=y
+# CONFIG_MAC80211_DEBUGFS is not set
+# CONFIG_MAC80211_DEBUG_PACKET_ALIGNMENT is not set
+# CONFIG_MAC80211_DEBUG is not set
 # CONFIG_IEEE80211 is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
@@ -449,13 +713,15 @@ CONFIG_IPV6_SIT=y
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
-# CONFIG_DEBUG_DEVRES is not set
+CONFIG_DEBUG_DEVRES=y
 # CONFIG_SYS_HYPERVISOR is not set
-# CONFIG_CONNECTOR is not set
+CONFIG_CONNECTOR=y
+CONFIG_PROC_EVENTS=y
 # CONFIG_MTD is not set
 # CONFIG_PARPORT is not set
 CONFIG_PNP=y
@@ -466,7 +732,7 @@ CONFIG_PNP=y
 #
 CONFIG_PNPACPI=y
 CONFIG_BLK_DEV=y
-CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_DEV_FD is not set
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -479,8 +745,8 @@ CONFIG_BLK_DEV_LOOP=y
 # CONFIG_BLK_DEV_UB is not set
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=16
-CONFIG_BLK_DEV_RAM_SIZE=4096
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_BLK_DEV_XIP is not set
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
 CONFIG_MISC_DEVICES=y
@@ -489,73 +755,17 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
+# CONFIG_ACER_WMI is not set
+# CONFIG_ASUS_LAPTOP is not set
+# CONFIG_FUJITSU_LAPTOP is not set
+# CONFIG_TC1100_WMI is not set
+# CONFIG_MSI_LAPTOP is not set
 # CONFIG_SONY_LAPTOP is not set
 # CONFIG_THINKPAD_ACPI is not set
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDE=y
-
-#
-# Please see Documentation/ide.txt for help/info on IDE drives
-#
-# CONFIG_BLK_DEV_IDE_SATA is not set
-# CONFIG_BLK_DEV_HD_IDE is not set
-CONFIG_BLK_DEV_IDEDISK=y
-CONFIG_IDEDISK_MULTI_MODE=y
-CONFIG_BLK_DEV_IDECD=y
-# CONFIG_BLK_DEV_IDETAPE is not set
-# CONFIG_BLK_DEV_IDEFLOPPY is not set
-# CONFIG_BLK_DEV_IDESCSI is not set
-CONFIG_BLK_DEV_IDEACPI=y
-# CONFIG_IDE_TASK_IOCTL is not set
-CONFIG_IDE_PROC_FS=y
-
-#
-# IDE chipset support/bugfixes
-#
-CONFIG_IDE_GENERIC=y
-# CONFIG_BLK_DEV_CMD640 is not set
-# CONFIG_BLK_DEV_IDEPNP is not set
-CONFIG_BLK_DEV_IDEPCI=y
-# CONFIG_IDEPCI_SHARE_IRQ is not set
-CONFIG_IDEPCI_PCIBUS_ORDER=y
-# CONFIG_BLK_DEV_OFFBOARD is not set
-# CONFIG_BLK_DEV_GENERIC is not set
-# CONFIG_BLK_DEV_OPTI621 is not set
-# CONFIG_BLK_DEV_RZ1000 is not set
-CONFIG_BLK_DEV_IDEDMA_PCI=y
-# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-# CONFIG_IDEDMA_ONLYDISK is not set
-# CONFIG_BLK_DEV_AEC62XX is not set
-# CONFIG_BLK_DEV_ALI15X3 is not set
-CONFIG_BLK_DEV_AMD74XX=y
-# CONFIG_BLK_DEV_ATIIXP is not set
-# CONFIG_BLK_DEV_CMD64X is not set
-# CONFIG_BLK_DEV_TRIFLEX is not set
-# CONFIG_BLK_DEV_CY82C693 is not set
-# CONFIG_BLK_DEV_CS5520 is not set
-# CONFIG_BLK_DEV_CS5530 is not set
-# CONFIG_BLK_DEV_CS5535 is not set
-# CONFIG_BLK_DEV_HPT34X is not set
-# CONFIG_BLK_DEV_HPT366 is not set
-# CONFIG_BLK_DEV_JMICRON is not set
-# CONFIG_BLK_DEV_SC1200 is not set
-CONFIG_BLK_DEV_PIIX=y
-# CONFIG_BLK_DEV_IT8213 is not set
-# CONFIG_BLK_DEV_IT821X is not set
-# CONFIG_BLK_DEV_NS87415 is not set
-# CONFIG_BLK_DEV_PDC202XX_OLD is not set
-# CONFIG_BLK_DEV_PDC202XX_NEW is not set
-# CONFIG_BLK_DEV_SVWKS is not set
-# CONFIG_BLK_DEV_SIIMAGE is not set
-# CONFIG_BLK_DEV_SIS5513 is not set
-# CONFIG_BLK_DEV_SLC90E66 is not set
-# CONFIG_BLK_DEV_TRM290 is not set
-# CONFIG_BLK_DEV_VIA82CXXX is not set
-# CONFIG_BLK_DEV_TC86C001 is not set
-# CONFIG_IDE_ARM is not set
-CONFIG_BLK_DEV_IDEDMA=y
-# CONFIG_IDEDMA_IVB is not set
-# CONFIG_BLK_DEV_HD is not set
+# CONFIG_INTEL_MENLOW is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
 
 #
 # SCSI device support
@@ -564,8 +774,8 @@ CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_SCSI=y
 CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
-CONFIG_SCSI_NETLINK=y
-# CONFIG_SCSI_PROC_FS is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
 
 #
 # SCSI support type (disk, tape, CD-ROM)
@@ -574,7 +784,7 @@ CONFIG_BLK_DEV_SD=y
 # CONFIG_CHR_DEV_ST is not set
 # CONFIG_CHR_DEV_OSST is not set
 CONFIG_BLK_DEV_SR=y
-# CONFIG_BLK_DEV_SR_VENDOR is not set
+CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_CHR_DEV_SCH is not set
 
@@ -582,7 +792,7 @@ CONFIG_CHR_DEV_SG=y
 # Some SCSI devices (e.g. CD jukebox) support multiple LUNs
 #
 # CONFIG_SCSI_MULTI_LUN is not set
-# CONFIG_SCSI_CONSTANTS is not set
+CONFIG_SCSI_CONSTANTS=y
 # CONFIG_SCSI_LOGGING is not set
 # CONFIG_SCSI_SCAN_ASYNC is not set
 CONFIG_SCSI_WAIT_SCAN=m
@@ -591,81 +801,37 @@ CONFIG_SCSI_WAIT_SCAN=m
 # SCSI Transports
 #
 CONFIG_SCSI_SPI_ATTRS=y
-CONFIG_SCSI_FC_ATTRS=y
+# CONFIG_SCSI_FC_ATTRS is not set
 # CONFIG_SCSI_ISCSI_ATTRS is not set
 # CONFIG_SCSI_SAS_ATTRS is not set
 # CONFIG_SCSI_SAS_LIBSAS is not set
-
-#
-# SCSI low-level drivers
-#
-# CONFIG_ISCSI_TCP is not set
-CONFIG_BLK_DEV_3W_XXXX_RAID=y
-# CONFIG_SCSI_3W_9XXX is not set
-# CONFIG_SCSI_ACARD is not set
-# CONFIG_SCSI_AACRAID is not set
-CONFIG_SCSI_AIC7XXX=y
-CONFIG_AIC7XXX_CMDS_PER_DEVICE=32
-CONFIG_AIC7XXX_RESET_DELAY_MS=5000
-CONFIG_AIC7XXX_DEBUG_ENABLE=y
-CONFIG_AIC7XXX_DEBUG_MASK=0
-CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
-# CONFIG_SCSI_AIC7XXX_OLD is not set
-CONFIG_SCSI_AIC79XX=y
-CONFIG_AIC79XX_CMDS_PER_DEVICE=32
-CONFIG_AIC79XX_RESET_DELAY_MS=4000
-# CONFIG_AIC79XX_DEBUG_ENABLE is not set
-CONFIG_AIC79XX_DEBUG_MASK=0
-# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set
-# CONFIG_SCSI_AIC94XX is not set
-# CONFIG_SCSI_DPT_I2O is not set
-# CONFIG_SCSI_ADVANSYS is not set
-# CONFIG_SCSI_ARCMSR is not set
-# CONFIG_MEGARAID_NEWGEN is not set
-# CONFIG_MEGARAID_LEGACY is not set
-# CONFIG_MEGARAID_SAS is not set
-# CONFIG_SCSI_HPTIOP is not set
-# CONFIG_SCSI_BUSLOGIC is not set
-# CONFIG_SCSI_DMX3191D is not set
-# CONFIG_SCSI_EATA is not set
-# CONFIG_SCSI_FUTURE_DOMAIN is not set
-# CONFIG_SCSI_GDTH is not set
-# CONFIG_SCSI_IPS is not set
-# CONFIG_SCSI_INITIO is not set
-# CONFIG_SCSI_INIA100 is not set
-# CONFIG_SCSI_STEX is not set
-# CONFIG_SCSI_SYM53C8XX_2 is not set
-# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_1280 is not set
-# CONFIG_SCSI_QLA_FC is not set
-# CONFIG_SCSI_QLA_ISCSI is not set
-# CONFIG_SCSI_LPFC is not set
-# CONFIG_SCSI_DC395x is not set
-# CONFIG_SCSI_DC390T is not set
-# CONFIG_SCSI_NSP32 is not set
-# CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+# CONFIG_SCSI_LOWLEVEL is not set
+# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
+CONFIG_SATA_PMP=y
 CONFIG_SATA_AHCI=y
-CONFIG_SATA_SVW=y
+# CONFIG_SATA_SIL24 is not set
+CONFIG_ATA_SFF=y
+# CONFIG_SATA_SVW is not set
 CONFIG_ATA_PIIX=y
 # CONFIG_SATA_MV is not set
-CONFIG_SATA_NV=y
+# CONFIG_SATA_NV is not set
 # CONFIG_PDC_ADMA is not set
 # CONFIG_SATA_QSTOR is not set
 # CONFIG_SATA_PROMISE is not set
 # CONFIG_SATA_SX4 is not set
-CONFIG_SATA_SIL=y
-# CONFIG_SATA_SIL24 is not set
+# CONFIG_SATA_SIL is not set
 # CONFIG_SATA_SIS is not set
 # CONFIG_SATA_ULI is not set
-CONFIG_SATA_VIA=y
+# CONFIG_SATA_VIA is not set
 # CONFIG_SATA_VITESSE is not set
 # CONFIG_SATA_INIC162X is not set
+# CONFIG_PATA_ACPI is not set
 # CONFIG_PATA_ALI is not set
-# CONFIG_PATA_AMD is not set
+CONFIG_PATA_AMD=y
 # CONFIG_PATA_ARTOP is not set
 # CONFIG_PATA_ATIIXP is not set
 # CONFIG_PATA_CMD640_PCI is not set
@@ -673,6 +839,7 @@ CONFIG_SATA_VIA=y
 # CONFIG_PATA_CS5520 is not set
 # CONFIG_PATA_CS5530 is not set
 # CONFIG_PATA_CS5535 is not set
+# CONFIG_PATA_CS5536 is not set
 # CONFIG_PATA_CYPRESS is not set
 # CONFIG_PATA_EFAR is not set
 # CONFIG_ATA_GENERIC is not set
@@ -686,11 +853,14 @@ CONFIG_SATA_VIA=y
 # CONFIG_PATA_TRIFLEX is not set
 # CONFIG_PATA_MARVELL is not set
 # CONFIG_PATA_MPIIX is not set
-# CONFIG_PATA_OLDPIIX is not set
+CONFIG_PATA_OLDPIIX=y
 # CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NINJA32 is not set
 # CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_NS87415 is not set
 # CONFIG_PATA_OPTI is not set
 # CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PCMCIA is not set
 # CONFIG_PATA_PDC_OLD is not set
 # CONFIG_PATA_RADISYS is not set
 # CONFIG_PATA_RZ1000 is not set
@@ -702,65 +872,42 @@ CONFIG_SATA_VIA=y
 # CONFIG_PATA_VIA is not set
 # CONFIG_PATA_WINBOND is not set
 CONFIG_MD=y
-# CONFIG_BLK_DEV_MD is not set
+CONFIG_BLK_DEV_MD=y
+# CONFIG_MD_LINEAR is not set
+# CONFIG_MD_RAID0 is not set
+# CONFIG_MD_RAID1 is not set
+# CONFIG_MD_RAID10 is not set
+# CONFIG_MD_RAID456 is not set
+# CONFIG_MD_MULTIPATH is not set
+# CONFIG_MD_FAULTY is not set
 CONFIG_BLK_DEV_DM=y
 # CONFIG_DM_DEBUG is not set
 # CONFIG_DM_CRYPT is not set
 # CONFIG_DM_SNAPSHOT is not set
-# CONFIG_DM_MIRROR is not set
-# CONFIG_DM_ZERO is not set
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
 # CONFIG_DM_MULTIPATH is not set
 # CONFIG_DM_DELAY is not set
-
-#
-# Fusion MPT device support
-#
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=y
-# CONFIG_FUSION_FC is not set
-# CONFIG_FUSION_SAS is not set
-CONFIG_FUSION_MAX_SGE=128
-# CONFIG_FUSION_CTL is not set
+# CONFIG_DM_UEVENT is not set
+# CONFIG_FUSION is not set
 
 #
 # IEEE 1394 (FireWire) support
 #
 # CONFIG_FIREWIRE is not set
-CONFIG_IEEE1394=y
-
-#
-# Subsystem Options
-#
-# CONFIG_IEEE1394_VERBOSEDEBUG is not set
-
-#
-# Controllers
-#
-
-#
-# Texas Instruments PCILynx requires I2C
-#
-CONFIG_IEEE1394_OHCI1394=y
-
-#
-# Protocols
-#
-# CONFIG_IEEE1394_VIDEO1394 is not set
-# CONFIG_IEEE1394_SBP2 is not set
-# CONFIG_IEEE1394_ETH1394_ROM_ENTRY is not set
-# CONFIG_IEEE1394_ETH1394 is not set
-# CONFIG_IEEE1394_DV1394 is not set
-CONFIG_IEEE1394_RAWIO=y
+# CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 CONFIG_MACINTOSH_DRIVERS=y
-# CONFIG_MAC_EMUMOUSEBTN is not set
+CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NETDEVICES_MULTIQUEUE=y
+# CONFIG_NETDEVICES_MULTIQUEUE is not set
+# CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
+# CONFIG_VETH is not set
 # CONFIG_NET_SB1000 is not set
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
@@ -770,38 +917,40 @@ CONFIG_MII=y
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 CONFIG_NET_VENDOR_3COM=y
-CONFIG_VORTEX=y
+# CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
-CONFIG_TULIP=y
-# CONFIG_TULIP_MWI is not set
-# CONFIG_TULIP_MMIO is not set
-# CONFIG_TULIP_NAPI is not set
+# CONFIG_TULIP is not set
 # CONFIG_DE4X5 is not set
 # CONFIG_WINBOND_840 is not set
 # CONFIG_DM9102 is not set
 # CONFIG_ULI526X is not set
+# CONFIG_PCMCIA_XIRCOM is not set
 # CONFIG_HP100 is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
 # CONFIG_AMD8111_ETH is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
-CONFIG_B44=y
+# CONFIG_B44 is not set
 CONFIG_FORCEDETH=y
 # CONFIG_FORCEDETH_NAPI is not set
-# CONFIG_DGRS is not set
 # CONFIG_EEPRO100 is not set
 CONFIG_E100=y
 # CONFIG_FEALNX is not set
 # CONFIG_NATSEMI is not set
 # CONFIG_NE2K_PCI is not set
-CONFIG_8139CP=y
+# CONFIG_8139CP is not set
 CONFIG_8139TOO=y
-# CONFIG_8139TOO_PIO is not set
+CONFIG_8139TOO_PIO=y
 # CONFIG_8139TOO_TUNE_TWISTER is not set
 # CONFIG_8139TOO_8129 is not set
 # CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_R6040 is not set
 # CONFIG_SIS900 is not set
 # CONFIG_EPIC100 is not set
 # CONFIG_SUNDANCE is not set
@@ -814,38 +963,75 @@ CONFIG_NETDEV_1000=y
 CONFIG_E1000=y
 # CONFIG_E1000_NAPI is not set
 # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set
-CONFIG_E1000E=y
-CONFIG_E1000E_ENABLED=y
+# CONFIG_E1000E is not set
+# CONFIG_E1000E_ENABLED is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
-CONFIG_R8169=y
-# CONFIG_R8169_NAPI is not set
+# CONFIG_R8169 is not set
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 CONFIG_SKY2=y
+# CONFIG_SKY2_DEBUG is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
-CONFIG_BNX2=y
+# CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 # CONFIG_CHELSIO_T3 is not set
+# CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
+# CONFIG_NIU is not set
 # CONFIG_MLX4_CORE is not set
-# CONFIG_TR is not set
+# CONFIG_TEHUTI is not set
+# CONFIG_BNX2X is not set
+# CONFIG_SFC is not set
+CONFIG_TR=y
+# CONFIG_IBMOL is not set
+# CONFIG_IBMLS is not set
+# CONFIG_3C359 is not set
+# CONFIG_TMS380TR is not set
 
 #
 # Wireless LAN
 #
 # CONFIG_WLAN_PRE80211 is not set
-# CONFIG_WLAN_80211 is not set
+CONFIG_WLAN_80211=y
+# CONFIG_PCMCIA_RAYCS is not set
+# CONFIG_IPW2100 is not set
+# CONFIG_IPW2200 is not set
+# CONFIG_LIBERTAS is not set
+# CONFIG_AIRO is not set
+# CONFIG_HERMES is not set
+# CONFIG_ATMEL is not set
+# CONFIG_AIRO_CS is not set
+# CONFIG_PCMCIA_WL3501 is not set
+# CONFIG_PRISM54 is not set
+# CONFIG_USB_ZD1201 is not set
+# CONFIG_USB_NET_RNDIS_WLAN is not set
+# CONFIG_RTL8180 is not set
+# CONFIG_RTL8187 is not set
+# CONFIG_ADM8211 is not set
+# CONFIG_P54_COMMON is not set
+CONFIG_ATH5K=y
+# CONFIG_ATH5K_DEBUG is not set
+# CONFIG_IWLWIFI is not set
+# CONFIG_IWLCORE is not set
+# CONFIG_IWLWIFI_LEDS is not set
+# CONFIG_IWL4965 is not set
+# CONFIG_IWL3945 is not set
+# CONFIG_HOSTAP is not set
+# CONFIG_B43 is not set
+# CONFIG_B43LEGACY is not set
+# CONFIG_ZD1211RW is not set
+# CONFIG_RT2X00 is not set
 
 #
 # USB Network Adapters
@@ -854,16 +1040,27 @@ CONFIG_NETDEV_10000=y
 # CONFIG_USB_KAWETH is not set
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
 # CONFIG_USB_USBNET is not set
+CONFIG_NET_PCMCIA=y
+# CONFIG_PCMCIA_3C589 is not set
+# CONFIG_PCMCIA_3C574 is not set
+# CONFIG_PCMCIA_FMVJ18X is not set
+# CONFIG_PCMCIA_PCNET is not set
+# CONFIG_PCMCIA_NMCLAN is not set
+# CONFIG_PCMCIA_SMC91C92 is not set
+# CONFIG_PCMCIA_XIRC2PS is not set
+# CONFIG_PCMCIA_AXNET is not set
+# CONFIG_PCMCIA_IBMTR is not set
 # CONFIG_WAN is not set
-# CONFIG_FDDI is not set
+CONFIG_FDDI=y
+# CONFIG_DEFXX is not set
+# CONFIG_SKFP is not set
 # CONFIG_HIPPI is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
 # CONFIG_NET_FC is not set
-# CONFIG_SHAPER is not set
 CONFIG_NETCONSOLE=y
+# CONFIG_NETCONSOLE_DYNAMIC is not set
 CONFIG_NETPOLL=y
 # CONFIG_NETPOLL_TRAP is not set
 CONFIG_NET_POLL_CONTROLLER=y
@@ -874,18 +1071,17 @@ CONFIG_NET_POLL_CONTROLLER=y
 # Input device support
 #
 CONFIG_INPUT=y
-# CONFIG_INPUT_FF_MEMLESS is not set
-# CONFIG_INPUT_POLLDEV is not set
+CONFIG_INPUT_FF_MEMLESS=y
+CONFIG_INPUT_POLLDEV=y
 
 #
 # Userland interfaces
 #
 CONFIG_INPUT_MOUSEDEV=y
-CONFIG_INPUT_MOUSEDEV_PSAUX=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_EVBUG is not set
 
@@ -910,17 +1106,63 @@ CONFIG_MOUSE_PS2_TRACKPOINT=y
 # CONFIG_MOUSE_SERIAL is not set
 # CONFIG_MOUSE_APPLETOUCH is not set
 # CONFIG_MOUSE_VSXXXAA is not set
-# CONFIG_INPUT_JOYSTICK is not set
-# CONFIG_INPUT_TABLET is not set
-# CONFIG_INPUT_TOUCHSCREEN is not set
-# CONFIG_INPUT_MISC is not set
+CONFIG_INPUT_JOYSTICK=y
+# CONFIG_JOYSTICK_ANALOG is not set
+# CONFIG_JOYSTICK_A3D is not set
+# CONFIG_JOYSTICK_ADI is not set
+# CONFIG_JOYSTICK_COBRA is not set
+# CONFIG_JOYSTICK_GF2K is not set
+# CONFIG_JOYSTICK_GRIP is not set
+# CONFIG_JOYSTICK_GRIP_MP is not set
+# CONFIG_JOYSTICK_GUILLEMOT is not set
+# CONFIG_JOYSTICK_INTERACT is not set
+# CONFIG_JOYSTICK_SIDEWINDER is not set
+# CONFIG_JOYSTICK_TMDC is not set
+# CONFIG_JOYSTICK_IFORCE is not set
+# CONFIG_JOYSTICK_WARRIOR is not set
+# CONFIG_JOYSTICK_MAGELLAN is not set
+# CONFIG_JOYSTICK_SPACEORB is not set
+# CONFIG_JOYSTICK_SPACEBALL is not set
+# CONFIG_JOYSTICK_STINGER is not set
+# CONFIG_JOYSTICK_TWIDJOY is not set
+# CONFIG_JOYSTICK_ZHENHUA is not set
+# CONFIG_JOYSTICK_JOYDUMP is not set
+# CONFIG_JOYSTICK_XPAD is not set
+CONFIG_INPUT_TABLET=y
+# CONFIG_TABLET_USB_ACECAD is not set
+# CONFIG_TABLET_USB_AIPTEK is not set
+# CONFIG_TABLET_USB_GTCO is not set
+# CONFIG_TABLET_USB_KBTAB is not set
+# CONFIG_TABLET_USB_WACOM is not set
+CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_FUJITSU is not set
+# CONFIG_TOUCHSCREEN_GUNZE is not set
+# CONFIG_TOUCHSCREEN_ELO is not set
+# CONFIG_TOUCHSCREEN_MTOUCH is not set
+# CONFIG_TOUCHSCREEN_MK712 is not set
+# CONFIG_TOUCHSCREEN_PENMOUNT is not set
+# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
+# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
+# CONFIG_TOUCHSCREEN_UCB1400 is not set
+# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
+CONFIG_INPUT_MISC=y
+# CONFIG_INPUT_PCSPKR is not set
+# CONFIG_INPUT_APANEL is not set
+# CONFIG_INPUT_WISTRON_BTNS is not set
+# CONFIG_INPUT_ATLAS_BTNS is not set
+# CONFIG_INPUT_ATI_REMOTE is not set
+# CONFIG_INPUT_ATI_REMOTE2 is not set
+# CONFIG_INPUT_KEYSPAN_REMOTE is not set
+# CONFIG_INPUT_POWERMATE is not set
+# CONFIG_INPUT_YEALINK is not set
+# CONFIG_INPUT_UINPUT is not set
 
 #
 # Hardware I/O ports
 #
 CONFIG_SERIO=y
 CONFIG_SERIO_I8042=y
-# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_SERPORT=y
 # CONFIG_SERIO_CT82C710 is not set
 # CONFIG_SERIO_PCIPS2 is not set
 CONFIG_SERIO_LIBPS2=y
@@ -933,8 +1175,26 @@ CONFIG_SERIO_LIBPS2=y
 CONFIG_VT=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
-# CONFIG_VT_HW_CONSOLE_BINDING is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVKMEM=y
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_COMPUTONE is not set
+# CONFIG_ROCKETPORT is not set
+# CONFIG_CYCLADES is not set
+# CONFIG_DIGIEPCA is not set
+# CONFIG_MOXA_INTELLIO is not set
+# CONFIG_MOXA_SMARTIO is not set
+# CONFIG_ISI is not set
+# CONFIG_SYNCLINK is not set
+# CONFIG_SYNCLINKMP is not set
+# CONFIG_SYNCLINK_GT is not set
+# CONFIG_N_HDLC is not set
+# CONFIG_RISCOM8 is not set
+# CONFIG_SPECIALIX is not set
+# CONFIG_SX is not set
+# CONFIG_RIO is not set
+# CONFIG_STALDRV is not set
+# CONFIG_NOZOMI is not set
 
 #
 # Serial drivers
@@ -944,9 +1204,14 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_FIX_EARLYCON_MEM=y
 CONFIG_SERIAL_8250_PCI=y
 CONFIG_SERIAL_8250_PNP=y
-CONFIG_SERIAL_8250_NR_UARTS=4
+# CONFIG_SERIAL_8250_CS is not set
+CONFIG_SERIAL_8250_NR_UARTS=32
 CONFIG_SERIAL_8250_RUNTIME_UARTS=4
-# CONFIG_SERIAL_8250_EXTENDED is not set
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
 
 #
 # Non-8250 serial port support
@@ -955,89 +1220,275 @@ CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
 CONFIG_UNIX98_PTYS=y
-CONFIG_LEGACY_PTYS=y
-CONFIG_LEGACY_PTY_COUNT=256
+# CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
-# CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_INTEL=y
-CONFIG_HW_RANDOM_AMD=y
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
 CONFIG_HW_RANDOM_GEODE=y
 CONFIG_HW_RANDOM_VIA=y
-# CONFIG_NVRAM is not set
-CONFIG_RTC=y
+CONFIG_NVRAM=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 # CONFIG_SONYPI is not set
-CONFIG_AGP=y
-# CONFIG_AGP_ALI is not set
-# CONFIG_AGP_ATI is not set
-# CONFIG_AGP_AMD is not set
-CONFIG_AGP_AMD64=y
-CONFIG_AGP_INTEL=y
-# CONFIG_AGP_NVIDIA is not set
-# CONFIG_AGP_SIS is not set
-# CONFIG_AGP_SWORKS is not set
-# CONFIG_AGP_VIA is not set
-# CONFIG_AGP_EFFICEON is not set
-# CONFIG_DRM is not set
+
+#
+# PCMCIA character devices
+#
+# CONFIG_SYNCLINK_CS is not set
+# CONFIG_CARDMAN_4000 is not set
+# CONFIG_CARDMAN_4040 is not set
+# CONFIG_IPWIRELESS is not set
 # CONFIG_MWAVE is not set
 # CONFIG_PC8736x_GPIO is not set
 # CONFIG_NSC_GPIO is not set
 # CONFIG_CS5535_GPIO is not set
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=256
+# CONFIG_RAW_DRIVER is not set
 CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
-CONFIG_HPET_MMAP=y
+# CONFIG_HPET_MMAP is not set
 # CONFIG_HANGCHECK_TIMER is not set
 # CONFIG_TCG_TPM is not set
 # CONFIG_TELCLOCK is not set
 CONFIG_DEVPORT=y
-# CONFIG_I2C is not set
-
-#
-# SPI support
-#
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+# CONFIG_I2C_CHARDEV is not set
+
+#
+# I2C Hardware Bus support
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+CONFIG_I2C_I801=y
+# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_I2C_SIMTEC is not set
+# CONFIG_SCx200_ACB is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_TINY_USB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
 # CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
 # CONFIG_W1 is not set
-# CONFIG_POWER_SUPPLY is not set
+CONFIG_POWER_SUPPLY=y
+# CONFIG_POWER_SUPPLY_DEBUG is not set
+# CONFIG_PDA_POWER is not set
+# CONFIG_BATTERY_DS2760 is not set
 # CONFIG_HWMON is not set
+CONFIG_THERMAL=y
+CONFIG_WATCHDOG=y
+# CONFIG_WATCHDOG_NOWAYOUT is not set
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+# CONFIG_ACQUIRE_WDT is not set
+# CONFIG_ADVANTECH_WDT is not set
+# CONFIG_ALIM1535_WDT is not set
+# CONFIG_ALIM7101_WDT is not set
+# CONFIG_SC520_WDT is not set
+# CONFIG_EUROTECH_WDT is not set
+# CONFIG_IB700_WDT is not set
+# CONFIG_IBMASR is not set
+# CONFIG_WAFER_WDT is not set
+# CONFIG_I6300ESB_WDT is not set
+# CONFIG_ITCO_WDT is not set
+# CONFIG_IT8712F_WDT is not set
+# CONFIG_HP_WATCHDOG is not set
+# CONFIG_SC1200_WDT is not set
+# CONFIG_PC87413_WDT is not set
+# CONFIG_60XX_WDT is not set
+# CONFIG_SBC8360_WDT is not set
+# CONFIG_SBC7240_WDT is not set
+# CONFIG_CPU5_WDT is not set
+# CONFIG_SMSC37B787_WDT is not set
+# CONFIG_W83627HF_WDT is not set
+# CONFIG_W83697HF_WDT is not set
+# CONFIG_W83877F_WDT is not set
+# CONFIG_W83977F_WDT is not set
+# CONFIG_MACHZ_WDT is not set
+# CONFIG_SBC_EPX_C3_WATCHDOG is not set
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
+
+#
+# USB-based Watchdog Cards
+#
+# CONFIG_USBPCWATCHDOG is not set
+
+#
+# Sonics Silicon Backplane
+#
+CONFIG_SSB_POSSIBLE=y
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
 #
 # CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
 
 #
 # Multimedia devices
 #
+
+#
+# Multimedia core support
+#
 # CONFIG_VIDEO_DEV is not set
 # CONFIG_DVB_CORE is not set
+
+#
+# Multimedia drivers
+#
 CONFIG_DAB=y
 # CONFIG_USB_DABUSB is not set
 
 #
 # Graphics support
 #
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+CONFIG_AGP=y
+# CONFIG_AGP_ALI is not set
+# CONFIG_AGP_ATI is not set
+# CONFIG_AGP_AMD is not set
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+# CONFIG_AGP_NVIDIA is not set
+# CONFIG_AGP_SIS is not set
+# CONFIG_AGP_SWORKS is not set
+# CONFIG_AGP_VIA is not set
+# CONFIG_AGP_EFFICEON is not set
+CONFIG_DRM=y
+# CONFIG_DRM_TDFX is not set
+# CONFIG_DRM_R128 is not set
+# CONFIG_DRM_RADEON is not set
+# CONFIG_DRM_I810 is not set
+# CONFIG_DRM_I830 is not set
+CONFIG_DRM_I915=y
+# CONFIG_DRM_MGA is not set
+# CONFIG_DRM_SIS is not set
+# CONFIG_DRM_VIA is not set
+# CONFIG_DRM_SAVAGE is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+CONFIG_FB_CFB_FILLRECT=y
+CONFIG_FB_CFB_COPYAREA=y
+CONFIG_FB_CFB_IMAGEBLIT=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+# CONFIG_FB_SYS_FILLRECT is not set
+# CONFIG_FB_SYS_COPYAREA is not set
+# CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+# CONFIG_FB_SYS_FOPS is not set
+CONFIG_FB_DEFERRED_IO=y
+# CONFIG_FB_SVGALIB is not set
+# CONFIG_FB_MACMODES is not set
+# CONFIG_FB_BACKLIGHT is not set
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+
+#
+# Frame buffer hardware drivers
+#
+# CONFIG_FB_CIRRUS is not set
+# CONFIG_FB_PM2 is not set
+# CONFIG_FB_CYBER2000 is not set
+# CONFIG_FB_ARC is not set
+# CONFIG_FB_ASILIANT is not set
+# CONFIG_FB_IMSTT is not set
+# CONFIG_FB_VGA16 is not set
+# CONFIG_FB_UVESA is not set
+# CONFIG_FB_VESA is not set
+CONFIG_FB_EFI=y
+# CONFIG_FB_IMAC is not set
+# CONFIG_FB_N411 is not set
+# CONFIG_FB_HGA is not set
+# CONFIG_FB_S1D13XXX is not set
+# CONFIG_FB_NVIDIA is not set
+# CONFIG_FB_RIVA is not set
+# CONFIG_FB_I810 is not set
+# CONFIG_FB_LE80578 is not set
+# CONFIG_FB_INTEL is not set
+# CONFIG_FB_MATROX is not set
+# CONFIG_FB_RADEON is not set
+# CONFIG_FB_ATY128 is not set
+# CONFIG_FB_ATY is not set
+# CONFIG_FB_S3 is not set
+# CONFIG_FB_SAVAGE is not set
+# CONFIG_FB_SIS is not set
+# CONFIG_FB_NEOMAGIC is not set
+# CONFIG_FB_KYRO is not set
+# CONFIG_FB_3DFX is not set
+# CONFIG_FB_VOODOO1 is not set
+# CONFIG_FB_VT8623 is not set
+# CONFIG_FB_CYBLA is not set
+# CONFIG_FB_TRIDENT is not set
+# CONFIG_FB_ARK is not set
+# CONFIG_FB_PM3 is not set
+# CONFIG_FB_GEODE is not set
+# CONFIG_FB_VIRTUAL is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+# CONFIG_BACKLIGHT_CORGI is not set
+# CONFIG_BACKLIGHT_PROGEAR is not set
 
 #
 # Display device support
 #
 # CONFIG_DISPLAY_SUPPORT is not set
-# CONFIG_VGASTATE is not set
-# CONFIG_FB is not set
 
 #
 # Console display driver support
 #
 CONFIG_VGA_CONSOLE=y
 CONFIG_VGACON_SOFT_SCROLLBACK=y
-CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=128
+CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
 CONFIG_VIDEO_SELECT=y
 CONFIG_DUMMY_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_LOGO_LINUX_CLUT224=y
 
 #
 # Sound
@@ -1047,33 +1498,167 @@ CONFIG_SOUND=y
 #
 # Advanced Linux Sound Architecture
 #
-# CONFIG_SND is not set
+CONFIG_SND=y
+CONFIG_SND_TIMER=y
+CONFIG_SND_PCM=y
+CONFIG_SND_HWDEP=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQ_DUMMY=y
+CONFIG_SND_OSSEMUL=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_PCM_OSS_PLUGINS=y
+CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_DYNAMIC_MINORS=y
+CONFIG_SND_SUPPORT_OLD_API=y
+CONFIG_SND_VERBOSE_PROCFS=y
+# CONFIG_SND_VERBOSE_PRINTK is not set
+# CONFIG_SND_DEBUG is not set
+CONFIG_SND_VMASTER=y
+
+#
+# Generic devices
+#
+# CONFIG_SND_PCSP is not set
+# CONFIG_SND_DUMMY is not set
+# CONFIG_SND_VIRMIDI is not set
+# CONFIG_SND_MTPAV is not set
+# CONFIG_SND_SERIAL_U16550 is not set
+# CONFIG_SND_MPU401 is not set
+
+#
+# PCI devices
+#
+# CONFIG_SND_AD1889 is not set
+# CONFIG_SND_ALS300 is not set
+# CONFIG_SND_ALS4000 is not set
+# CONFIG_SND_ALI5451 is not set
+# CONFIG_SND_ATIIXP is not set
+# CONFIG_SND_ATIIXP_MODEM is not set
+# CONFIG_SND_AU8810 is not set
+# CONFIG_SND_AU8820 is not set
+# CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AW2 is not set
+# CONFIG_SND_AZT3328 is not set
+# CONFIG_SND_BT87X is not set
+# CONFIG_SND_CA0106 is not set
+# CONFIG_SND_CMIPCI is not set
+# CONFIG_SND_OXYGEN is not set
+# CONFIG_SND_CS4281 is not set
+# CONFIG_SND_CS46XX is not set
+# CONFIG_SND_CS5530 is not set
+# CONFIG_SND_CS5535AUDIO is not set
+# CONFIG_SND_DARLA20 is not set
+# CONFIG_SND_GINA20 is not set
+# CONFIG_SND_LAYLA20 is not set
+# CONFIG_SND_DARLA24 is not set
+# CONFIG_SND_GINA24 is not set
+# CONFIG_SND_LAYLA24 is not set
+# CONFIG_SND_MONA is not set
+# CONFIG_SND_MIA is not set
+# CONFIG_SND_ECHO3G is not set
+# CONFIG_SND_INDIGO is not set
+# CONFIG_SND_INDIGOIO is not set
+# CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_EMU10K1 is not set
+# CONFIG_SND_EMU10K1X is not set
+# CONFIG_SND_ENS1370 is not set
+# CONFIG_SND_ENS1371 is not set
+# CONFIG_SND_ES1938 is not set
+# CONFIG_SND_ES1968 is not set
+# CONFIG_SND_FM801 is not set
+CONFIG_SND_HDA_INTEL=y
+CONFIG_SND_HDA_HWDEP=y
+CONFIG_SND_HDA_CODEC_REALTEK=y
+CONFIG_SND_HDA_CODEC_ANALOG=y
+CONFIG_SND_HDA_CODEC_SIGMATEL=y
+CONFIG_SND_HDA_CODEC_VIA=y
+CONFIG_SND_HDA_CODEC_ATIHDMI=y
+CONFIG_SND_HDA_CODEC_CONEXANT=y
+CONFIG_SND_HDA_CODEC_CMEDIA=y
+CONFIG_SND_HDA_CODEC_SI3054=y
+CONFIG_SND_HDA_GENERIC=y
+# CONFIG_SND_HDA_POWER_SAVE is not set
+# CONFIG_SND_HDSP is not set
+# CONFIG_SND_HDSPM is not set
+# CONFIG_SND_HIFIER is not set
+# CONFIG_SND_ICE1712 is not set
+# CONFIG_SND_ICE1724 is not set
+# CONFIG_SND_INTEL8X0 is not set
+# CONFIG_SND_INTEL8X0M is not set
+# CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_MAESTRO3 is not set
+# CONFIG_SND_MIXART is not set
+# CONFIG_SND_NM256 is not set
+# CONFIG_SND_PCXHR is not set
+# CONFIG_SND_RIPTIDE is not set
+# CONFIG_SND_RME32 is not set
+# CONFIG_SND_RME96 is not set
+# CONFIG_SND_RME9652 is not set
+# CONFIG_SND_SIS7019 is not set
+# CONFIG_SND_SONICVIBES is not set
+# CONFIG_SND_TRIDENT is not set
+# CONFIG_SND_VIA82XX is not set
+# CONFIG_SND_VIA82XX_MODEM is not set
+# CONFIG_SND_VIRTUOSO is not set
+# CONFIG_SND_VX222 is not set
+# CONFIG_SND_YMFPCI is not set
+
+#
+# USB devices
+#
+# CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_USX2Y is not set
+# CONFIG_SND_USB_CAIAQ is not set
+
+#
+# PCMCIA devices
+#
+# CONFIG_SND_VXPOCKET is not set
+# CONFIG_SND_PDAUDIOCF is not set
+
+#
+# System on Chip audio support
+#
+# CONFIG_SND_SOC is not set
+
+#
+# ALSA SoC audio for Freescale SOCs
+#
+
+#
+# SoC Audio for the Texas Instruments OMAP
+#
 
 #
 # Open Sound System
 #
-CONFIG_SOUND_PRIME=y
-# CONFIG_SOUND_TRIDENT is not set
-# CONFIG_SOUND_MSNDCLAS is not set
-# CONFIG_SOUND_MSNDPIN is not set
-# CONFIG_SOUND_OSS is not set
+# CONFIG_SOUND_PRIME is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
-# CONFIG_HID_DEBUG is not set
+CONFIG_HID_DEBUG=y
+CONFIG_HIDRAW=y
 
 #
 # USB Input Devices
 #
 CONFIG_USB_HID=y
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
-# CONFIG_USB_HIDDEV is not set
+CONFIG_USB_HIDINPUT_POWERBOOK=y
+CONFIG_HID_FF=y
+CONFIG_HID_PID=y
+CONFIG_LOGITECH_FF=y
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+CONFIG_PANTHERLORD_FF=y
+CONFIG_THRUSTMASTER_FF=y
+CONFIG_ZEROPLUS_FF=y
+CONFIG_USB_HIDDEV=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
 CONFIG_USB=y
-# CONFIG_USB_DEBUG is not set
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 
 #
 # Miscellaneous USB options
@@ -1081,18 +1666,18 @@ CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
-# CONFIG_USB_SUSPEND is not set
-# CONFIG_USB_PERSIST is not set
+CONFIG_USB_SUSPEND=y
 # CONFIG_USB_OTG is not set
 
 #
 # USB Host Controller Drivers
 #
+# CONFIG_USB_C67X00_HCD is not set
 CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
 # CONFIG_USB_ISP116X_HCD is not set
+# CONFIG_USB_ISP1760_HCD is not set
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
@@ -1125,8 +1710,10 @@ CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_SDDR55 is not set
 # CONFIG_USB_STORAGE_JUMPSHOT is not set
 # CONFIG_USB_STORAGE_ALAUDA is not set
+# CONFIG_USB_STORAGE_ONETOUCH is not set
 # CONFIG_USB_STORAGE_KARMA is not set
-# CONFIG_USB_LIBUSUAL is not set
+# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
+CONFIG_USB_LIBUSUAL=y
 
 #
 # USB Imaging devices
@@ -1138,10 +1725,6 @@ CONFIG_USB_MON=y
 #
 # USB port drivers
 #
-
-#
-# USB Serial Converter support
-#
 # CONFIG_USB_SERIAL is not set
 
 #
@@ -1167,90 +1750,125 @@ CONFIG_USB_MON=y
 # CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
+# CONFIG_USB_GADGET is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
 
 #
-# USB DSL modem support
+# LED drivers
 #
+# CONFIG_LEDS_CLEVO_MAIL is not set
 
 #
-# USB Gadget Support
+# LED Triggers
 #
-# CONFIG_USB_GADGET is not set
-# CONFIG_MMC is not set
+CONFIG_LEDS_TRIGGERS=y
+# CONFIG_LEDS_TRIGGER_TIMER is not set
+# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
+# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_INFINIBAND is not set
+CONFIG_EDAC=y
 
 #
-# LED devices
+# Reporting subsystems
 #
-# CONFIG_NEW_LEDS is not set
+# CONFIG_EDAC_DEBUG is not set
+# CONFIG_EDAC_MM_EDAC is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+# CONFIG_RTC_DEBUG is not set
 
 #
-# LED drivers
+# RTC interfaces
 #
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
 
 #
-# LED Triggers
+# I2C RTC drivers
 #
-# CONFIG_INFINIBAND is not set
-# CONFIG_EDAC is not set
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
 
 #
-# Real Time Clock
+# SPI RTC drivers
 #
-# CONFIG_RTC_CLASS is not set
 
 #
-# DMA Engine support
+# Platform RTC drivers
 #
-# CONFIG_DMA_ENGINE is not set
+CONFIG_RTC_DRV_CMOS=y
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_V3020 is not set
 
 #
-# DMA Clients
+# on-CPU RTC drivers
 #
+CONFIG_DMADEVICES=y
 
 #
 # DMA Devices
 #
-CONFIG_VIRTUALIZATION=y
-# CONFIG_KVM is not set
+# CONFIG_INTEL_IOATDMA is not set
+# CONFIG_UIO is not set
 
 #
-# Userspace I/O
+# Firmware Drivers
 #
-# CONFIG_UIO is not set
+# CONFIG_EDD is not set
+CONFIG_EFI_VARS=y
+# CONFIG_DELL_RBU is not set
+# CONFIG_DCDBAS is not set
+CONFIG_DMIID=y
+# CONFIG_ISCSI_IBFT_FIND is not set
 
 #
 # File systems
 #
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-# CONFIG_EXT2_FS_SECURITY is not set
-# CONFIG_EXT2_FS_XIP is not set
+# CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
-# CONFIG_EXT3_FS_SECURITY is not set
+CONFIG_EXT3_FS_SECURITY=y
 # CONFIG_EXT4DEV_FS is not set
 CONFIG_JBD=y
 # CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=y
-CONFIG_REISERFS_FS=y
-# CONFIG_REISERFS_CHECK is not set
-# CONFIG_REISERFS_PROC_INFO is not set
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-# CONFIG_REISERFS_FS_SECURITY is not set
+# CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 CONFIG_FS_POSIX_ACL=y
 # CONFIG_XFS_FS is not set
-# CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
-# CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+# CONFIG_QFMT_V1 is not set
+CONFIG_QFMT_V2=y
+CONFIG_QUOTACTL=y
 # CONFIG_AUTOFS_FS is not set
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
@@ -1260,8 +1878,8 @@ CONFIG_GENERIC_ACL=y
 # CD-ROM/DVD Filesystems
 #
 CONFIG_ISO9660_FS=y
-# CONFIG_JOLIET is not set
-# CONFIG_ZISOFS is not set
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
 # CONFIG_UDF_FS is not set
 
 #
@@ -1279,13 +1897,13 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 #
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_VMCORE=y
 CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
-CONFIG_RAMFS=y
 # CONFIG_CONFIGFS_FS is not set
 
 #
@@ -1293,6 +1911,7 @@ CONFIG_RAMFS=y
 #
 # CONFIG_ADFS_FS is not set
 # CONFIG_AFFS_FS is not set
+# CONFIG_ECRYPT_FS is not set
 # CONFIG_HFS_FS is not set
 # CONFIG_HFSPLUS_FS is not set
 # CONFIG_BEFS_FS is not set
@@ -1300,33 +1919,15 @@ CONFIG_RAMFS=y
 # CONFIG_EFS_FS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-# CONFIG_NFS_V3_ACL is not set
-# CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
-CONFIG_NFSD=y
-CONFIG_NFSD_V3=y
-# CONFIG_NFSD_V3_ACL is not set
-# CONFIG_NFSD_V4 is not set
-CONFIG_NFSD_TCP=y
-CONFIG_ROOT_NFS=y
-CONFIG_LOCKD=y
-CONFIG_LOCKD_V4=y
-CONFIG_EXPORTFS=y
-CONFIG_NFS_COMMON=y
-CONFIG_SUNRPC=y
-# CONFIG_SUNRPC_BIND34 is not set
-# CONFIG_RPCSEC_GSS_KRB5 is not set
-# CONFIG_RPCSEC_GSS_SPKM3 is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+# CONFIG_NFS_FS is not set
+# CONFIG_NFSD is not set
 # CONFIG_SMB_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
@@ -1336,14 +1937,26 @@ CONFIG_SUNRPC=y
 #
 # Partition Types
 #
-# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+# CONFIG_ATARI_PARTITION is not set
+CONFIG_MAC_PARTITION=y
 CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+# CONFIG_LDM_PARTITION is not set
+CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
 CONFIG_NLS=y
-CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 # CONFIG_NLS_CODEPAGE_737 is not set
 # CONFIG_NLS_CODEPAGE_775 is not set
@@ -1378,37 +1991,33 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_ISO8859_9 is not set
 # CONFIG_NLS_ISO8859_13 is not set
 # CONFIG_NLS_ISO8859_14 is not set
-CONFIG_NLS_ISO8859_15=y
+# CONFIG_NLS_ISO8859_15 is not set
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 CONFIG_NLS_UTF8=y
-
-#
-# Distributed Lock Manager
-#
 # CONFIG_DLM is not set
-CONFIG_INSTRUMENTATION=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
 
 #
 # Kernel hacking
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=2048
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_UNUSED_SYMBOLS=y
-# CONFIG_DEBUG_FS is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
-CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
-# CONFIG_SCHEDSTATS is not set
+CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_SLUB_DEBUG_ON is not set
+# CONFIG_SLUB_STATS is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
@@ -1423,48 +2032,174 @@ CONFIG_TIMER_STATS=y
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_LIST is not set
-# CONFIG_FRAME_POINTER is not set
-CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_DEBUG_SG is not set
+CONFIG_FRAME_POINTER=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
 # CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_KPROBES_SANITY_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
 # CONFIG_LKDTM is not set
 # CONFIG_FAULT_INJECTION is not set
+# CONFIG_LATENCYTOP is not set
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+# CONFIG_SAMPLES is not set
+# CONFIG_KGDB is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_NONPROMISC_DEVMEM is not set
 CONFIG_EARLY_PRINTK=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-# CONFIG_DEBUG_STACK_USAGE is not set
-# CONFIG_DEBUG_RODATA is not set
+CONFIG_DEBUG_STACK_USAGE=y
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_X86_PTDUMP is not set
+CONFIG_DEBUG_RODATA=y
+# CONFIG_DEBUG_RODATA_TEST is not set
+CONFIG_DEBUG_NX_TEST=m
 # CONFIG_4KSTACKS is not set
 CONFIG_X86_FIND_SMP_CONFIG=y
 CONFIG_X86_MPPARSE=y
 CONFIG_DOUBLEFAULT=y
+CONFIG_IO_DELAY_TYPE_0X80=0
+CONFIG_IO_DELAY_TYPE_0XED=1
+CONFIG_IO_DELAY_TYPE_UDELAY=2
+CONFIG_IO_DELAY_TYPE_NONE=3
+CONFIG_IO_DELAY_0X80=y
+# CONFIG_IO_DELAY_0XED is not set
+# CONFIG_IO_DELAY_UDELAY is not set
+# CONFIG_IO_DELAY_NONE is not set
+CONFIG_DEFAULT_IO_DELAY_TYPE=0
+CONFIG_DEBUG_BOOT_PARAMS=y
+# CONFIG_CPA_DEBUG is not set
 
 #
 # Security options
 #
-# CONFIG_KEYS is not set
-# CONFIG_SECURITY is not set
-# CONFIG_CRYPTO is not set
+CONFIG_KEYS=y
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+# CONFIG_SECURITY_NETWORK_XFRM is not set
+CONFIG_SECURITY_CAPABILITIES=y
+CONFIG_SECURITY_FILE_CAPABILITIES=y
+# CONFIG_SECURITY_ROOTPLUG is not set
+CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR=65536
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+CONFIG_SECURITY_SELINUX_AVC_STATS=y
+CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
+# CONFIG_SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT is not set
+# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
+# CONFIG_SECURITY_SMACK is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_MANAGER=y
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+CONFIG_CRYPTO_AUTHENC=y
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=y
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=y
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+CONFIG_CRYPTO_HMAC=y
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=y
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+CONFIG_CRYPTO_SHA1=y
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=y
+# CONFIG_CRYPTO_AES_586 is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=y
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SALSA20_586 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+# CONFIG_CRYPTO_TWOFISH_586 is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
+CONFIG_CRYPTO_HW=y
+# CONFIG_CRYPTO_DEV_PADLOCK is not set
+# CONFIG_CRYPTO_DEV_GEODE is not set
+# CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_HAVE_KVM=y
+CONFIG_VIRTUALIZATION=y
+# CONFIG_KVM is not set
+# CONFIG_LGUEST is not set
+# CONFIG_VIRTIO_PCI is not set
+# CONFIG_VIRTIO_BALLOON is not set
 
 #
 # Library routines
 #
 CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
 # CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
+CONFIG_AUDIT_GENERIC=y
 CONFIG_ZLIB_INFLATE=y
 CONFIG_PLIST=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
-CONFIG_GENERIC_HARDIRQS=y
-CONFIG_GENERIC_IRQ_PROBE=y
-CONFIG_GENERIC_PENDING_IRQ=y
-CONFIG_X86_SMP=y
-CONFIG_X86_HT=y
-CONFIG_X86_BIOS_REBOOT=y
-CONFIG_X86_TRAMPOLINE=y
-CONFIG_KTIME_SCALAR=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 2f1b35664998..ae5124e064d4 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
 # Linux kernel version: 2.6.26-rc1
-# Sun May  4 19:27:29 2008
+# Sun May  4 19:59:57 2008
 #
 CONFIG_64BIT=y
 # CONFIG_X86_32 is not set
@@ -61,27 +61,42 @@ CONFIG_EXPERIMENTAL=y
 CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
 CONFIG_LOCALVERSION=""
-CONFIG_LOCALVERSION_AUTO=y
+# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
-# CONFIG_BSD_PROCESS_ACCT is not set
-# CONFIG_TASKSTATS is not set
-# CONFIG_AUDIT is not set
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=18
-# CONFIG_CGROUPS is not set
-# CONFIG_GROUP_SCHED is not set
+CONFIG_BSD_PROCESS_ACCT=y
+# CONFIG_BSD_PROCESS_ACCT_V3 is not set
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_AUDIT_TREE=y
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+CONFIG_CGROUPS=y
+# CONFIG_CGROUP_DEBUG is not set
+CONFIG_CGROUP_NS=y
+# CONFIG_CGROUP_DEVICE is not set
+CONFIG_CPUSETS=y
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+# CONFIG_RT_GROUP_SCHED is not set
 # CONFIG_USER_SCHED is not set
-# CONFIG_CGROUP_SCHED is not set
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+# CONFIG_CGROUP_MEM_RES_CTLR is not set
 # CONFIG_SYSFS_DEPRECATED_V2 is not set
+CONFIG_PROC_PID_CPUSET=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
 CONFIG_IPC_NS=y
-# CONFIG_USER_NS is not set
+CONFIG_USER_NS=y
 CONFIG_PID_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
@@ -93,7 +108,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
-# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -108,12 +123,13 @@ CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
 CONFIG_VM_EVENT_COUNTERS=y
-CONFIG_SLAB=y
-# CONFIG_SLUB is not set
+CONFIG_SLUB_DEBUG=y
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
-# CONFIG_MARKERS is not set
-CONFIG_OPROFILE=y
+CONFIG_MARKERS=y
+# CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_KRETPROBES=y
@@ -133,15 +149,15 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_KMOD is not set
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
-# CONFIG_BLK_DEV_IO_TRACE is not set
-# CONFIG_BLK_DEV_BSG is not set
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_BLK_DEV_BSG=y
 CONFIG_BLOCK_COMPAT=y
 
 #
 # IO Schedulers
 #
 CONFIG_IOSCHED_NOOP=y
-# CONFIG_IOSCHED_AS is not set
+CONFIG_IOSCHED_AS=y
 CONFIG_IOSCHED_DEADLINE=y
 CONFIG_IOSCHED_CFQ=y
 # CONFIG_DEFAULT_AS is not set
@@ -155,7 +171,7 @@ CONFIG_CLASSIC_RCU=y
 # Processor type and features
 #
 CONFIG_TICK_ONESHOT=y
-# CONFIG_NO_HZ is not set
+CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
@@ -171,7 +187,8 @@ CONFIG_X86_PC=y
 # CONFIG_X86_RDC321X is not set
 # CONFIG_X86_VSMP is not set
 # CONFIG_PARAVIRT_GUEST is not set
-# CONFIG_MEMTEST_BOOTPARAM is not set
+CONFIG_MEMTEST_BOOTPARAM=y
+CONFIG_MEMTEST_BOOTPARAM_VALUE=0
 # CONFIG_M386 is not set
 # CONFIG_M486 is not set
 # CONFIG_M586 is not set
@@ -196,14 +213,17 @@ CONFIG_X86_PC=y
 # CONFIG_MVIAC3_2 is not set
 # CONFIG_MVIAC7 is not set
 # CONFIG_MPSC is not set
-# CONFIG_MCORE2 is not set
-CONFIG_GENERIC_CPU=y
+CONFIG_MCORE2=y
+# CONFIG_GENERIC_CPU is not set
 CONFIG_X86_CPU=y
-CONFIG_X86_L1_CACHE_BYTES=128
-CONFIG_X86_INTERNODE_CACHE_BYTES=128
+CONFIG_X86_L1_CACHE_BYTES=64
+CONFIG_X86_INTERNODE_CACHE_BYTES=64
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=6
 CONFIG_X86_GOOD_APIC=y
+CONFIG_X86_INTEL_USERCOPY=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_P6_NOP=y
 CONFIG_X86_TSC=y
 CONFIG_X86_CMOV=y
 CONFIG_X86_MINIMUM_CPU_FAMILY=64
@@ -212,20 +232,19 @@ CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
 CONFIG_DMI=y
 CONFIG_GART_IOMMU=y
-# CONFIG_CALGARY_IOMMU is not set
+CONFIG_CALGARY_IOMMU=y
+CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y
 CONFIG_SWIOTLB=y
 CONFIG_IOMMU_HELPER=y
-CONFIG_NR_CPUS=32
-CONFIG_SCHED_SMT=y
+CONFIG_NR_CPUS=4
+# CONFIG_SCHED_SMT is not set
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_PREEMPT is not set
 CONFIG_X86_LOCAL_APIC=y
 CONFIG_X86_IO_APIC=y
-CONFIG_X86_MCE=y
-CONFIG_X86_MCE_INTEL=y
-CONFIG_X86_MCE_AMD=y
+# CONFIG_X86_MCE is not set
 # CONFIG_I8K is not set
 # CONFIG_MICROCODE is not set
 CONFIG_X86_MSR=y
@@ -234,7 +253,7 @@ CONFIG_NUMA=y
 CONFIG_K8_NUMA=y
 CONFIG_X86_64_ACPI_NUMA=y
 CONFIG_NODES_SPAN_OTHER_NODES=y
-CONFIG_NUMA_EMU=y
+# CONFIG_NUMA_EMU is not set
 CONFIG_NODES_SHIFT=6
 CONFIG_ARCH_SPARSEMEM_DEFAULT=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
@@ -249,7 +268,7 @@ CONFIG_HAVE_MEMORY_PRESENT=y
 # CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
-# CONFIG_SPARSEMEM_VMEMMAP is not set
+CONFIG_SPARSEMEM_VMEMMAP=y
 
 #
 # Memory hotplug is currently incompatible with Software Suspend
@@ -263,18 +282,18 @@ CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_MTRR=y
 # CONFIG_X86_PAT is not set
-# CONFIG_EFI is not set
+CONFIG_EFI=y
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
-CONFIG_HZ_250=y
+# CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
-# CONFIG_HZ_1000 is not set
-CONFIG_HZ=250
+CONFIG_HZ_1000=y
+CONFIG_HZ=1000
 CONFIG_SCHED_HRTICK=y
-# CONFIG_KEXEC is not set
-# CONFIG_CRASH_DUMP is not set
-CONFIG_PHYSICAL_START=0x200000
-# CONFIG_RELOCATABLE is not set
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+CONFIG_PHYSICAL_START=0x1000000
+CONFIG_RELOCATABLE=y
 CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
@@ -286,10 +305,15 @@ CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
 #
 CONFIG_ARCH_HIBERNATION_HEADER=y
 CONFIG_PM=y
-# CONFIG_PM_DEBUG is not set
+CONFIG_PM_DEBUG=y
+# CONFIG_PM_VERBOSE is not set
+CONFIG_CAN_PM_TRACE=y
+CONFIG_PM_TRACE=y
+CONFIG_PM_TRACE_RTC=y
 CONFIG_PM_SLEEP_SMP=y
 CONFIG_PM_SLEEP=y
-# CONFIG_SUSPEND is not set
+CONFIG_SUSPEND=y
+CONFIG_SUSPEND_FREEZER=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_STD_PARTITION=""
 CONFIG_ACPI=y
@@ -327,35 +351,34 @@ CONFIG_ACPI_CONTAINER=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_TABLE=y
 CONFIG_CPU_FREQ_DEBUG=y
-CONFIG_CPU_FREQ_STAT=y
-# CONFIG_CPU_FREQ_STAT_DETAILS is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_STAT is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
 # CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
-# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 # CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
 # CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
 
 #
 # CPUFreq processor drivers
 #
 CONFIG_X86_ACPI_CPUFREQ=y
-CONFIG_X86_POWERNOW_K8=y
-CONFIG_X86_POWERNOW_K8_ACPI=y
+# CONFIG_X86_POWERNOW_K8 is not set
 # CONFIG_X86_SPEEDSTEP_CENTRINO is not set
-CONFIG_X86_P4_CLOCKMOD=y
+# CONFIG_X86_P4_CLOCKMOD is not set
 
 #
 # shared options
 #
-CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y
-CONFIG_X86_SPEEDSTEP_LIB=y
+# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set
+# CONFIG_X86_SPEEDSTEP_LIB is not set
 CONFIG_CPU_IDLE=y
 CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
 
 #
 # Bus options (PCI etc.)
@@ -364,28 +387,53 @@ CONFIG_PCI=y
 CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
 CONFIG_PCI_DOMAINS=y
-# CONFIG_DMAR is not set
+CONFIG_DMAR=y
+CONFIG_DMAR_GFX_WA=y
+CONFIG_DMAR_FLOPPY_WA=y
 CONFIG_PCIEPORTBUS=y
+# CONFIG_HOTPLUG_PCI_PCIE is not set
 CONFIG_PCIEAER=y
 # CONFIG_PCIEASPM is not set
 CONFIG_ARCH_SUPPORTS_MSI=y
 CONFIG_PCI_MSI=y
-CONFIG_PCI_LEGACY=y
+# CONFIG_PCI_LEGACY is not set
 # CONFIG_PCI_DEBUG is not set
-# CONFIG_HT_IRQ is not set
+CONFIG_HT_IRQ=y
 CONFIG_ISA_DMA_API=y
 CONFIG_K8_NB=y
-# CONFIG_PCCARD is not set
-# CONFIG_HOTPLUG_PCI is not set
+CONFIG_PCCARD=y
+# CONFIG_PCMCIA_DEBUG is not set
+CONFIG_PCMCIA=y
+CONFIG_PCMCIA_LOAD_CIS=y
+CONFIG_PCMCIA_IOCTL=y
+CONFIG_CARDBUS=y
+
+#
+# PC-card bridges
+#
+CONFIG_YENTA=y
+CONFIG_YENTA_O2=y
+CONFIG_YENTA_RICOH=y
+CONFIG_YENTA_TI=y
+CONFIG_YENTA_ENE_TUNE=y
+CONFIG_YENTA_TOSHIBA=y
+# CONFIG_PD6729 is not set
+# CONFIG_I82092 is not set
+CONFIG_PCCARD_NONSTATIC=y
+CONFIG_HOTPLUG_PCI=y
+# CONFIG_HOTPLUG_PCI_FAKE is not set
+# CONFIG_HOTPLUG_PCI_ACPI is not set
+# CONFIG_HOTPLUG_PCI_CPCI is not set
+# CONFIG_HOTPLUG_PCI_SHPC is not set
 
 #
 # Executable file formats / Emulations
 #
 CONFIG_BINFMT_ELF=y
 CONFIG_COMPAT_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
+CONFIG_BINFMT_MISC=y
 CONFIG_IA32_EMULATION=y
-CONFIG_IA32_AOUT=y
+# CONFIG_IA32_AOUT is not set
 CONFIG_COMPAT=y
 CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
 CONFIG_SYSVIPC_COMPAT=y
@@ -399,22 +447,31 @@ CONFIG_NET=y
 # Networking options
 #
 CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
+CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=y
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
-# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_ASK_IP_FIB_HASH=y
+# CONFIG_IP_FIB_TRIE is not set
 CONFIG_IP_FIB_HASH=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IP_PNP_BOOTP is not set
-# CONFIG_IP_PNP_RARP is not set
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
 # CONFIG_NET_IPIP is not set
 # CONFIG_NET_IPGRE is not set
-# CONFIG_IP_MROUTE is not set
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
 # CONFIG_ARPD is not set
-# CONFIG_SYN_COOKIES is not set
+CONFIG_SYN_COOKIES=y
 # CONFIG_INET_AH is not set
 # CONFIG_INET_ESP is not set
 # CONFIG_INET_IPCOMP is not set
@@ -423,34 +480,109 @@ CONFIG_INET_TUNNEL=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-CONFIG_INET_DIAG=y
-CONFIG_INET_TCP_DIAG=y
-# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_INET_LRO=y
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
 CONFIG_TCP_CONG_CUBIC=y
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_TCP_CONG_HSTCP is not set
+# CONFIG_TCP_CONG_HYBLA is not set
+# CONFIG_TCP_CONG_VEGAS is not set
+# CONFIG_TCP_CONG_SCALABLE is not set
+# CONFIG_TCP_CONG_LP is not set
+# CONFIG_TCP_CONG_VENO is not set
+# CONFIG_TCP_CONG_YEAH is not set
+# CONFIG_TCP_CONG_ILLINOIS is not set
+# CONFIG_DEFAULT_BIC is not set
+CONFIG_DEFAULT_CUBIC=y
+# CONFIG_DEFAULT_HTCP is not set
+# CONFIG_DEFAULT_VEGAS is not set
+# CONFIG_DEFAULT_WESTWOOD is not set
+# CONFIG_DEFAULT_RENO is not set
 CONFIG_DEFAULT_TCP_CONG="cubic"
-# CONFIG_TCP_MD5SIG is not set
+CONFIG_TCP_MD5SIG=y
+# CONFIG_IP_VS is not set
 CONFIG_IPV6=y
 # CONFIG_IPV6_PRIVACY is not set
 # CONFIG_IPV6_ROUTER_PREF is not set
 # CONFIG_IPV6_OPTIMISTIC_DAD is not set
-# CONFIG_INET6_AH is not set
-# CONFIG_INET6_ESP is not set
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
 # CONFIG_INET6_IPCOMP is not set
 # CONFIG_IPV6_MIP6 is not set
 # CONFIG_INET6_XFRM_TUNNEL is not set
 # CONFIG_INET6_TUNNEL is not set
-# CONFIG_INET6_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET6_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET6_XFRM_MODE_BEET is not set
+CONFIG_INET6_XFRM_MODE_TRANSPORT=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_INET6_XFRM_MODE_BEET=y
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_SIT=y
 CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_IPV6_TUNNEL is not set
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
 # CONFIG_IPV6_MROUTE is not set
-# CONFIG_NETWORK_SECMARK is not set
-# CONFIG_NETFILTER is not set
+CONFIG_NETLABEL=y
+CONFIG_NETWORK_SECMARK=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+# CONFIG_NETFILTER_ADVANCED is not set
+
+#
+# Core Netfilter Configuration
+#
+CONFIG_NETFILTER_NETLINK=y
+CONFIG_NETFILTER_NETLINK_LOG=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_SIP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XTABLES=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_PROC_COMPAT=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_LOG=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_NF_NAT=y
+CONFIG_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_NF_NAT_FTP=y
+CONFIG_NF_NAT_IRC=y
+# CONFIG_NF_NAT_TFTP is not set
+# CONFIG_NF_NAT_AMANDA is not set
+# CONFIG_NF_NAT_PPTP is not set
+# CONFIG_NF_NAT_H323 is not set
+CONFIG_NF_NAT_SIP=y
+CONFIG_IP_NF_MANGLE=y
+
+#
+# IPv6: Netfilter Configuration
+#
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_LOG=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
 # CONFIG_IP_DCCP is not set
 # CONFIG_IP_SCTP is not set
 # CONFIG_TIPC is not set
@@ -458,6 +590,7 @@ CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_BRIDGE is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
+CONFIG_LLC=y
 # CONFIG_LLC2 is not set
 # CONFIG_IPX is not set
 # CONFIG_ATALK is not set
@@ -465,25 +598,99 @@ CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-# CONFIG_NET_SCHED is not set
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+# CONFIG_NET_SCH_CBQ is not set
+# CONFIG_NET_SCH_HTB is not set
+# CONFIG_NET_SCH_HFSC is not set
+# CONFIG_NET_SCH_PRIO is not set
+# CONFIG_NET_SCH_RR is not set
+# CONFIG_NET_SCH_RED is not set
+# CONFIG_NET_SCH_SFQ is not set
+# CONFIG_NET_SCH_TEQL is not set
+# CONFIG_NET_SCH_TBF is not set
+# CONFIG_NET_SCH_GRED is not set
+# CONFIG_NET_SCH_DSMARK is not set
+# CONFIG_NET_SCH_NETEM is not set
+# CONFIG_NET_SCH_INGRESS is not set
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+# CONFIG_NET_CLS_BASIC is not set
+# CONFIG_NET_CLS_TCINDEX is not set
+# CONFIG_NET_CLS_ROUTE4 is not set
+# CONFIG_NET_CLS_FW is not set
+# CONFIG_NET_CLS_U32 is not set
+# CONFIG_NET_CLS_RSVP is not set
+# CONFIG_NET_CLS_RSVP6 is not set
+# CONFIG_NET_CLS_FLOW is not set
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+# CONFIG_NET_EMATCH_CMP is not set
+# CONFIG_NET_EMATCH_NBYTE is not set
+# CONFIG_NET_EMATCH_U32 is not set
+# CONFIG_NET_EMATCH_META is not set
+# CONFIG_NET_EMATCH_TEXT is not set
+CONFIG_NET_CLS_ACT=y
+# CONFIG_NET_ACT_POLICE is not set
+# CONFIG_NET_ACT_GACT is not set
+# CONFIG_NET_ACT_MIRRED is not set
+# CONFIG_NET_ACT_IPT is not set
+# CONFIG_NET_ACT_NAT is not set
+# CONFIG_NET_ACT_PEDIT is not set
+# CONFIG_NET_ACT_SIMP is not set
+CONFIG_NET_SCH_FIFO=y
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
-# CONFIG_HAMRADIO is not set
+CONFIG_HAMRADIO=y
+
+#
+# Packet Radio protocols
+#
+# CONFIG_AX25 is not set
 # CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_FIB_RULES=y
 
 #
 # Wireless
 #
-# CONFIG_CFG80211 is not set
-# CONFIG_WIRELESS_EXT is not set
-# CONFIG_MAC80211 is not set
+CONFIG_CFG80211=y
+CONFIG_NL80211=y
+CONFIG_WIRELESS_EXT=y
+CONFIG_MAC80211=y
+
+#
+# Rate control algorithm selection
+#
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+# CONFIG_MAC80211_RC_DEFAULT_NONE is not set
+
+#
+# Selecting 'y' for an algorithm will
+#
+
+#
+# build the algorithm into mac80211.
+#
+CONFIG_MAC80211_RC_DEFAULT="pid"
+CONFIG_MAC80211_RC_PID=y
+# CONFIG_MAC80211_MESH is not set
+CONFIG_MAC80211_LEDS=y
+# CONFIG_MAC80211_DEBUGFS is not set
+# CONFIG_MAC80211_DEBUG_PACKET_ALIGNMENT is not set
+# CONFIG_MAC80211_DEBUG is not set
 # CONFIG_IEEE80211 is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
@@ -500,9 +707,10 @@ CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
-# CONFIG_DEBUG_DEVRES is not set
+CONFIG_DEBUG_DEVRES=y
 # CONFIG_SYS_HYPERVISOR is not set
-# CONFIG_CONNECTOR is not set
+CONFIG_CONNECTOR=y
+CONFIG_PROC_EVENTS=y
 # CONFIG_MTD is not set
 # CONFIG_PARPORT is not set
 CONFIG_PNP=y
@@ -513,7 +721,7 @@ CONFIG_PNP=y
 #
 CONFIG_PNPACPI=y
 CONFIG_BLK_DEV=y
-CONFIG_BLK_DEV_FD=y
+# CONFIG_BLK_DEV_FD is not set
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -526,7 +734,7 @@ CONFIG_BLK_DEV_LOOP=y
 # CONFIG_BLK_DEV_UB is not set
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=16
-CONFIG_BLK_DEV_RAM_SIZE=4096
+CONFIG_BLK_DEV_RAM_SIZE=16384
 # CONFIG_BLK_DEV_XIP is not set
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
@@ -536,77 +744,16 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
+# CONFIG_ACER_WMI is not set
+# CONFIG_ASUS_LAPTOP is not set
+# CONFIG_FUJITSU_LAPTOP is not set
+# CONFIG_MSI_LAPTOP is not set
 # CONFIG_SONY_LAPTOP is not set
 # CONFIG_THINKPAD_ACPI is not set
 # CONFIG_INTEL_MENLOW is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
 CONFIG_HAVE_IDE=y
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDE=y
-
-#
-# Please see Documentation/ide/ide.txt for help/info on IDE drives
-#
-# CONFIG_BLK_DEV_IDE_SATA is not set
-CONFIG_BLK_DEV_IDEDISK=y
-CONFIG_IDEDISK_MULTI_MODE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
-# CONFIG_BLK_DEV_IDETAPE is not set
-# CONFIG_BLK_DEV_IDEFLOPPY is not set
-# CONFIG_BLK_DEV_IDESCSI is not set
-CONFIG_BLK_DEV_IDEACPI=y
-# CONFIG_IDE_TASK_IOCTL is not set
-CONFIG_IDE_PROC_FS=y
-
-#
-# IDE chipset support/bugfixes
-#
-CONFIG_IDE_GENERIC=y
-# CONFIG_BLK_DEV_PLATFORM is not set
-# CONFIG_BLK_DEV_CMD640 is not set
-# CONFIG_BLK_DEV_IDEPNP is not set
-CONFIG_BLK_DEV_IDEDMA_SFF=y
-
-#
-# PCI IDE chipsets support
-#
-CONFIG_BLK_DEV_IDEPCI=y
-CONFIG_IDEPCI_PCIBUS_ORDER=y
-# CONFIG_BLK_DEV_OFFBOARD is not set
-# CONFIG_BLK_DEV_GENERIC is not set
-# CONFIG_BLK_DEV_OPTI621 is not set
-# CONFIG_BLK_DEV_RZ1000 is not set
-CONFIG_BLK_DEV_IDEDMA_PCI=y
-# CONFIG_BLK_DEV_AEC62XX is not set
-# CONFIG_BLK_DEV_ALI15X3 is not set
-CONFIG_BLK_DEV_AMD74XX=y
-CONFIG_BLK_DEV_ATIIXP=y
-# CONFIG_BLK_DEV_CMD64X is not set
-# CONFIG_BLK_DEV_TRIFLEX is not set
-# CONFIG_BLK_DEV_CY82C693 is not set
-# CONFIG_BLK_DEV_CS5520 is not set
-# CONFIG_BLK_DEV_CS5530 is not set
-# CONFIG_BLK_DEV_HPT34X is not set
-# CONFIG_BLK_DEV_HPT366 is not set
-# CONFIG_BLK_DEV_JMICRON is not set
-# CONFIG_BLK_DEV_SC1200 is not set
-CONFIG_BLK_DEV_PIIX=y
-# CONFIG_BLK_DEV_IT8213 is not set
-# CONFIG_BLK_DEV_IT821X is not set
-# CONFIG_BLK_DEV_NS87415 is not set
-# CONFIG_BLK_DEV_PDC202XX_OLD is not set
-CONFIG_BLK_DEV_PDC202XX_NEW=y
-# CONFIG_BLK_DEV_SVWKS is not set
-# CONFIG_BLK_DEV_SIIMAGE is not set
-# CONFIG_BLK_DEV_SIS5513 is not set
-# CONFIG_BLK_DEV_SLC90E66 is not set
-# CONFIG_BLK_DEV_TRM290 is not set
-# CONFIG_BLK_DEV_VIA82CXXX is not set
-# CONFIG_BLK_DEV_TC86C001 is not set
-CONFIG_BLK_DEV_IDEDMA=y
-# CONFIG_BLK_DEV_HD_ONLY is not set
-# CONFIG_BLK_DEV_HD is not set
+# CONFIG_IDE is not set
 
 #
 # SCSI device support
@@ -615,8 +762,8 @@ CONFIG_BLK_DEV_IDEDMA=y
 CONFIG_SCSI=y
 CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
-CONFIG_SCSI_NETLINK=y
-# CONFIG_SCSI_PROC_FS is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
 
 #
 # SCSI support type (disk, tape, CD-ROM)
@@ -625,7 +772,7 @@ CONFIG_BLK_DEV_SD=y
 # CONFIG_CHR_DEV_ST is not set
 # CONFIG_CHR_DEV_OSST is not set
 CONFIG_BLK_DEV_SR=y
-# CONFIG_BLK_DEV_SR_VENDOR is not set
+CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_CHR_DEV_SCH is not set
 
@@ -642,76 +789,110 @@ CONFIG_SCSI_WAIT_SCAN=m
 # SCSI Transports
 #
 CONFIG_SCSI_SPI_ATTRS=y
-CONFIG_SCSI_FC_ATTRS=y
+# CONFIG_SCSI_FC_ATTRS is not set
 # CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_ATTRS is not set
 # CONFIG_SCSI_SAS_LIBSAS is not set
 # CONFIG_SCSI_SRP_ATTRS is not set
 # CONFIG_SCSI_LOWLEVEL is not set
+# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
-# CONFIG_SATA_PMP is not set
+CONFIG_SATA_PMP=y
 CONFIG_SATA_AHCI=y
 # CONFIG_SATA_SIL24 is not set
-# CONFIG_ATA_SFF is not set
+CONFIG_ATA_SFF=y
+# CONFIG_SATA_SVW is not set
+CONFIG_ATA_PIIX=y
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SX4 is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+# CONFIG_SATA_INIC162X is not set
+# CONFIG_PATA_ACPI is not set
+# CONFIG_PATA_ALI is not set
+CONFIG_PATA_AMD=y
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD640_PCI is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_ATA_GENERIC is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_IT8213 is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_MPIIX is not set
+CONFIG_PATA_OLDPIIX=y
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NINJA32 is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_NS87415 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PCMCIA is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
 CONFIG_MD=y
-# CONFIG_BLK_DEV_MD is not set
+CONFIG_BLK_DEV_MD=y
+# CONFIG_MD_LINEAR is not set
+# CONFIG_MD_RAID0 is not set
+# CONFIG_MD_RAID1 is not set
+# CONFIG_MD_RAID10 is not set
+# CONFIG_MD_RAID456 is not set
+# CONFIG_MD_MULTIPATH is not set
+# CONFIG_MD_FAULTY is not set
 CONFIG_BLK_DEV_DM=y
 # CONFIG_DM_DEBUG is not set
 # CONFIG_DM_CRYPT is not set
 # CONFIG_DM_SNAPSHOT is not set
-# CONFIG_DM_MIRROR is not set
-# CONFIG_DM_ZERO is not set
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
 # CONFIG_DM_MULTIPATH is not set
 # CONFIG_DM_DELAY is not set
 # CONFIG_DM_UEVENT is not set
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=y
-# CONFIG_FUSION_FC is not set
-# CONFIG_FUSION_SAS is not set
-CONFIG_FUSION_MAX_SGE=128
-# CONFIG_FUSION_CTL is not set
-# CONFIG_FUSION_LOGGING is not set
+# CONFIG_FUSION is not set
 
 #
 # IEEE 1394 (FireWire) support
 #
 # CONFIG_FIREWIRE is not set
-CONFIG_IEEE1394=y
-
-#
-# Subsystem Options
-#
-# CONFIG_IEEE1394_VERBOSEDEBUG is not set
-
-#
-# Controllers
-#
-
-#
-# Texas Instruments PCILynx requires I2C
-#
-CONFIG_IEEE1394_OHCI1394=y
-
-#
-# Protocols
-#
-# CONFIG_IEEE1394_VIDEO1394 is not set
-# CONFIG_IEEE1394_SBP2 is not set
-# CONFIG_IEEE1394_ETH1394_ROM_ENTRY is not set
-# CONFIG_IEEE1394_ETH1394 is not set
-# CONFIG_IEEE1394_DV1394 is not set
-CONFIG_IEEE1394_RAWIO=y
+# CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 CONFIG_MACINTOSH_DRIVERS=y
-# CONFIG_MAC_EMUMOUSEBTN is not set
+CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
-CONFIG_NETDEVICES_MULTIQUEUE=y
+# CONFIG_NETDEVICES_MULTIQUEUE is not set
+# CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
-CONFIG_TUN=y
+# CONFIG_TUN is not set
 # CONFIG_VETH is not set
 # CONFIG_NET_SB1000 is not set
 # CONFIG_ARCNET is not set
@@ -722,18 +903,16 @@ CONFIG_MII=y
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 CONFIG_NET_VENDOR_3COM=y
-CONFIG_VORTEX=y
+# CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
-CONFIG_TULIP=y
-# CONFIG_TULIP_MWI is not set
-# CONFIG_TULIP_MMIO is not set
-# CONFIG_TULIP_NAPI is not set
+# CONFIG_TULIP is not set
 # CONFIG_DE4X5 is not set
 # CONFIG_WINBOND_840 is not set
 # CONFIG_DM9102 is not set
 # CONFIG_ULI526X is not set
+# CONFIG_PCMCIA_XIRCOM is not set
 # CONFIG_HP100 is not set
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
@@ -741,13 +920,9 @@ CONFIG_TULIP=y
 # CONFIG_IBM_NEW_EMAC_EMAC4 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
-CONFIG_AMD8111_ETH=y
-# CONFIG_AMD8111E_NAPI is not set
+# CONFIG_AMD8111_ETH is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
-CONFIG_B44=y
-CONFIG_B44_PCI_AUTOSELECT=y
-CONFIG_B44_PCICORE_AUTOSELECT=y
-CONFIG_B44_PCI=y
+# CONFIG_B44 is not set
 CONFIG_FORCEDETH=y
 # CONFIG_FORCEDETH_NAPI is not set
 # CONFIG_EEPRO100 is not set
@@ -755,9 +930,9 @@ CONFIG_E100=y
 # CONFIG_FEALNX is not set
 # CONFIG_NATSEMI is not set
 # CONFIG_NE2K_PCI is not set
-CONFIG_8139CP=y
+# CONFIG_8139CP is not set
 CONFIG_8139TOO=y
-# CONFIG_8139TOO_PIO is not set
+CONFIG_8139TOO_PIO=y
 # CONFIG_8139TOO_TUNE_TWISTER is not set
 # CONFIG_8139TOO_8129 is not set
 # CONFIG_8139_OLD_RX_RESET is not set
@@ -783,10 +958,11 @@ CONFIG_E1000=y
 # CONFIG_R8169 is not set
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
-# CONFIG_SKY2 is not set
+CONFIG_SKY2=y
+# CONFIG_SKY2_DEBUG is not set
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
-CONFIG_BNX2=y
+# CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 CONFIG_NETDEV_10000=y
@@ -794,8 +970,7 @@ CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T3 is not set
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
-CONFIG_S2IO=m
-# CONFIG_S2IO_NAPI is not set
+# CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -803,15 +978,44 @@ CONFIG_S2IO=m
 # CONFIG_TEHUTI is not set
 # CONFIG_BNX2X is not set
 # CONFIG_SFC is not set
-# CONFIG_TR is not set
+CONFIG_TR=y
+# CONFIG_IBMOL is not set
+# CONFIG_3C359 is not set
+# CONFIG_TMS380TR is not set
 
 #
 # Wireless LAN
 #
 # CONFIG_WLAN_PRE80211 is not set
-# CONFIG_WLAN_80211 is not set
+CONFIG_WLAN_80211=y
+# CONFIG_PCMCIA_RAYCS is not set
+# CONFIG_IPW2100 is not set
+# CONFIG_IPW2200 is not set
+# CONFIG_LIBERTAS is not set
+# CONFIG_AIRO is not set
+# CONFIG_HERMES is not set
+# CONFIG_ATMEL is not set
+# CONFIG_AIRO_CS is not set
+# CONFIG_PCMCIA_WL3501 is not set
+# CONFIG_PRISM54 is not set
+# CONFIG_USB_ZD1201 is not set
+# CONFIG_USB_NET_RNDIS_WLAN is not set
+# CONFIG_RTL8180 is not set
+# CONFIG_RTL8187 is not set
+# CONFIG_ADM8211 is not set
+# CONFIG_P54_COMMON is not set
+CONFIG_ATH5K=y
+# CONFIG_ATH5K_DEBUG is not set
 # CONFIG_IWLWIFI is not set
+# CONFIG_IWLCORE is not set
 # CONFIG_IWLWIFI_LEDS is not set
+# CONFIG_IWL4965 is not set
+# CONFIG_IWL3945 is not set
+# CONFIG_HOSTAP is not set
+# CONFIG_B43 is not set
+# CONFIG_B43LEGACY is not set
+# CONFIG_ZD1211RW is not set
+# CONFIG_RT2X00 is not set
 
 #
 # USB Network Adapters
@@ -821,8 +1025,19 @@ CONFIG_S2IO=m
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
 # CONFIG_USB_USBNET is not set
+CONFIG_NET_PCMCIA=y
+# CONFIG_PCMCIA_3C589 is not set
+# CONFIG_PCMCIA_3C574 is not set
+# CONFIG_PCMCIA_FMVJ18X is not set
+# CONFIG_PCMCIA_PCNET is not set
+# CONFIG_PCMCIA_NMCLAN is not set
+# CONFIG_PCMCIA_SMC91C92 is not set
+# CONFIG_PCMCIA_XIRC2PS is not set
+# CONFIG_PCMCIA_AXNET is not set
 # CONFIG_WAN is not set
-# CONFIG_FDDI is not set
+CONFIG_FDDI=y
+# CONFIG_DEFXX is not set
+# CONFIG_SKFP is not set
 # CONFIG_HIPPI is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
@@ -839,14 +1054,14 @@ CONFIG_NET_POLL_CONTROLLER=y
 # Input device support
 #
 CONFIG_INPUT=y
-# CONFIG_INPUT_FF_MEMLESS is not set
-# CONFIG_INPUT_POLLDEV is not set
+CONFIG_INPUT_FF_MEMLESS=y
+CONFIG_INPUT_POLLDEV=y
 
 #
 # Userland interfaces
 #
 CONFIG_INPUT_MOUSEDEV=y
-CONFIG_INPUT_MOUSEDEV_PSAUX=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
@@ -874,17 +1089,62 @@ CONFIG_MOUSE_PS2_TRACKPOINT=y
 # CONFIG_MOUSE_SERIAL is not set
 # CONFIG_MOUSE_APPLETOUCH is not set
 # CONFIG_MOUSE_VSXXXAA is not set
-# CONFIG_INPUT_JOYSTICK is not set
-# CONFIG_INPUT_TABLET is not set
-# CONFIG_INPUT_TOUCHSCREEN is not set
-# CONFIG_INPUT_MISC is not set
+CONFIG_INPUT_JOYSTICK=y
+# CONFIG_JOYSTICK_ANALOG is not set
+# CONFIG_JOYSTICK_A3D is not set
+# CONFIG_JOYSTICK_ADI is not set
+# CONFIG_JOYSTICK_COBRA is not set
+# CONFIG_JOYSTICK_GF2K is not set
+# CONFIG_JOYSTICK_GRIP is not set
+# CONFIG_JOYSTICK_GRIP_MP is not set
+# CONFIG_JOYSTICK_GUILLEMOT is not set
+# CONFIG_JOYSTICK_INTERACT is not set
+# CONFIG_JOYSTICK_SIDEWINDER is not set
+# CONFIG_JOYSTICK_TMDC is not set
+# CONFIG_JOYSTICK_IFORCE is not set
+# CONFIG_JOYSTICK_WARRIOR is not set
+# CONFIG_JOYSTICK_MAGELLAN is not set
+# CONFIG_JOYSTICK_SPACEORB is not set
+# CONFIG_JOYSTICK_SPACEBALL is not set
+# CONFIG_JOYSTICK_STINGER is not set
+# CONFIG_JOYSTICK_TWIDJOY is not set
+# CONFIG_JOYSTICK_ZHENHUA is not set
+# CONFIG_JOYSTICK_JOYDUMP is not set
+# CONFIG_JOYSTICK_XPAD is not set
+CONFIG_INPUT_TABLET=y
+# CONFIG_TABLET_USB_ACECAD is not set
+# CONFIG_TABLET_USB_AIPTEK is not set
+# CONFIG_TABLET_USB_GTCO is not set
+# CONFIG_TABLET_USB_KBTAB is not set
+# CONFIG_TABLET_USB_WACOM is not set
+CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_FUJITSU is not set
+# CONFIG_TOUCHSCREEN_GUNZE is not set
+# CONFIG_TOUCHSCREEN_ELO is not set
+# CONFIG_TOUCHSCREEN_MTOUCH is not set
+# CONFIG_TOUCHSCREEN_MK712 is not set
+# CONFIG_TOUCHSCREEN_PENMOUNT is not set
+# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
+# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
+# CONFIG_TOUCHSCREEN_UCB1400 is not set
+# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
+CONFIG_INPUT_MISC=y
+# CONFIG_INPUT_PCSPKR is not set
+# CONFIG_INPUT_APANEL is not set
+# CONFIG_INPUT_ATLAS_BTNS is not set
+# CONFIG_INPUT_ATI_REMOTE is not set
+# CONFIG_INPUT_ATI_REMOTE2 is not set
+# CONFIG_INPUT_KEYSPAN_REMOTE is not set
+# CONFIG_INPUT_POWERMATE is not set
+# CONFIG_INPUT_YEALINK is not set
+# CONFIG_INPUT_UINPUT is not set
 
 #
 # Hardware I/O ports
 #
 CONFIG_SERIO=y
 CONFIG_SERIO_I8042=y
-# CONFIG_SERIO_SERPORT is not set
+CONFIG_SERIO_SERPORT=y
 # CONFIG_SERIO_CT82C710 is not set
 # CONFIG_SERIO_PCIPS2 is not set
 CONFIG_SERIO_LIBPS2=y
@@ -897,9 +1157,25 @@ CONFIG_SERIO_LIBPS2=y
 CONFIG_VT=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
-# CONFIG_VT_HW_CONSOLE_BINDING is not set
-# CONFIG_DEVKMEM is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVKMEM=y
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_COMPUTONE is not set
+# CONFIG_ROCKETPORT is not set
+# CONFIG_CYCLADES is not set
+# CONFIG_DIGIEPCA is not set
+# CONFIG_MOXA_INTELLIO is not set
+# CONFIG_MOXA_SMARTIO is not set
+# CONFIG_ISI is not set
+# CONFIG_SYNCLINK is not set
+# CONFIG_SYNCLINKMP is not set
+# CONFIG_SYNCLINK_GT is not set
+# CONFIG_N_HDLC is not set
+# CONFIG_RISCOM8 is not set
+# CONFIG_SPECIALIX is not set
+# CONFIG_SX is not set
+# CONFIG_RIO is not set
+# CONFIG_STALDRV is not set
 # CONFIG_NOZOMI is not set
 
 #
@@ -910,9 +1186,14 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_FIX_EARLYCON_MEM=y
 CONFIG_SERIAL_8250_PCI=y
 CONFIG_SERIAL_8250_PNP=y
-CONFIG_SERIAL_8250_NR_UARTS=4
+# CONFIG_SERIAL_8250_CS is not set
+CONFIG_SERIAL_8250_NR_UARTS=32
 CONFIG_SERIAL_8250_RUNTIME_UARTS=4
-# CONFIG_SERIAL_8250_EXTENDED is not set
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
 
 #
 # Non-8250 serial port support
@@ -921,28 +1202,78 @@ CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
 CONFIG_UNIX98_PTYS=y
-CONFIG_LEGACY_PTYS=y
-CONFIG_LEGACY_PTY_COUNT=256
+# CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
-CONFIG_HW_RANDOM_INTEL=y
-CONFIG_HW_RANDOM_AMD=y
-# CONFIG_NVRAM is not set
-CONFIG_RTC=y
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
+CONFIG_NVRAM=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
+
+#
+# PCMCIA character devices
+#
+# CONFIG_SYNCLINK_CS is not set
+# CONFIG_CARDMAN_4000 is not set
+# CONFIG_CARDMAN_4040 is not set
+# CONFIG_IPWIRELESS is not set
 # CONFIG_MWAVE is not set
 # CONFIG_PC8736x_GPIO is not set
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=256
+# CONFIG_RAW_DRIVER is not set
 CONFIG_HPET=y
 # CONFIG_HPET_RTC_IRQ is not set
-CONFIG_HPET_MMAP=y
+# CONFIG_HPET_MMAP is not set
 # CONFIG_HANGCHECK_TIMER is not set
 # CONFIG_TCG_TPM is not set
 # CONFIG_TELCLOCK is not set
 CONFIG_DEVPORT=y
-# CONFIG_I2C is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+# CONFIG_I2C_CHARDEV is not set
+
+#
+# I2C Hardware Bus support
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+CONFIG_I2C_I801=y
+# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_TINY_USB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
 # CONFIG_SPI is not set
 # CONFIG_W1 is not set
 CONFIG_POWER_SUPPLY=y
@@ -951,20 +1282,55 @@ CONFIG_POWER_SUPPLY=y
 # CONFIG_BATTERY_DS2760 is not set
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
-# CONFIG_WATCHDOG is not set
+CONFIG_WATCHDOG=y
+# CONFIG_WATCHDOG_NOWAYOUT is not set
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+# CONFIG_ACQUIRE_WDT is not set
+# CONFIG_ADVANTECH_WDT is not set
+# CONFIG_ALIM1535_WDT is not set
+# CONFIG_ALIM7101_WDT is not set
+# CONFIG_SC520_WDT is not set
+# CONFIG_EUROTECH_WDT is not set
+# CONFIG_IB700_WDT is not set
+# CONFIG_IBMASR is not set
+# CONFIG_WAFER_WDT is not set
+# CONFIG_I6300ESB_WDT is not set
+# CONFIG_ITCO_WDT is not set
+# CONFIG_IT8712F_WDT is not set
+# CONFIG_HP_WATCHDOG is not set
+# CONFIG_SC1200_WDT is not set
+# CONFIG_PC87413_WDT is not set
+# CONFIG_60XX_WDT is not set
+# CONFIG_SBC8360_WDT is not set
+# CONFIG_CPU5_WDT is not set
+# CONFIG_SMSC37B787_WDT is not set
+# CONFIG_W83627HF_WDT is not set
+# CONFIG_W83697HF_WDT is not set
+# CONFIG_W83877F_WDT is not set
+# CONFIG_W83977F_WDT is not set
+# CONFIG_MACHZ_WDT is not set
+# CONFIG_SBC_EPX_C3_WATCHDOG is not set
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
+
+#
+# USB-based Watchdog Cards
+#
+# CONFIG_USBPCWATCHDOG is not set
 
 #
 # Sonics Silicon Backplane
 #
 CONFIG_SSB_POSSIBLE=y
-CONFIG_SSB=y
-CONFIG_SSB_SPROM=y
-CONFIG_SSB_PCIHOST_POSSIBLE=y
-CONFIG_SSB_PCIHOST=y
-# CONFIG_SSB_B43_PCI_BRIDGE is not set
-# CONFIG_SSB_DEBUG is not set
-CONFIG_SSB_DRIVER_PCICORE_POSSIBLE=y
-CONFIG_SSB_DRIVER_PCICORE=y
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
@@ -996,11 +1362,81 @@ CONFIG_AGP_AMD64=y
 CONFIG_AGP_INTEL=y
 # CONFIG_AGP_SIS is not set
 # CONFIG_AGP_VIA is not set
-# CONFIG_DRM is not set
+CONFIG_DRM=y
+# CONFIG_DRM_TDFX is not set
+# CONFIG_DRM_R128 is not set
+# CONFIG_DRM_RADEON is not set
+# CONFIG_DRM_I810 is not set
+# CONFIG_DRM_I830 is not set
+CONFIG_DRM_I915=y
+# CONFIG_DRM_MGA is not set
+# CONFIG_DRM_SIS is not set
+# CONFIG_DRM_VIA is not set
+# CONFIG_DRM_SAVAGE is not set
 # CONFIG_VGASTATE is not set
 # CONFIG_VIDEO_OUTPUT_CONTROL is not set
-# CONFIG_FB is not set
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+CONFIG_FB_CFB_FILLRECT=y
+CONFIG_FB_CFB_COPYAREA=y
+CONFIG_FB_CFB_IMAGEBLIT=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+# CONFIG_FB_SYS_FILLRECT is not set
+# CONFIG_FB_SYS_COPYAREA is not set
+# CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+# CONFIG_FB_SYS_FOPS is not set
+CONFIG_FB_DEFERRED_IO=y
+# CONFIG_FB_SVGALIB is not set
+# CONFIG_FB_MACMODES is not set
+# CONFIG_FB_BACKLIGHT is not set
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+
+#
+# Frame buffer hardware drivers
+#
+# CONFIG_FB_CIRRUS is not set
+# CONFIG_FB_PM2 is not set
+# CONFIG_FB_CYBER2000 is not set
+# CONFIG_FB_ARC is not set
+# CONFIG_FB_ASILIANT is not set
+# CONFIG_FB_IMSTT is not set
+# CONFIG_FB_VGA16 is not set
+# CONFIG_FB_UVESA is not set
+# CONFIG_FB_VESA is not set
+CONFIG_FB_EFI=y
+# CONFIG_FB_IMAC is not set
+# CONFIG_FB_N411 is not set
+# CONFIG_FB_HGA is not set
+# CONFIG_FB_S1D13XXX is not set
+# CONFIG_FB_NVIDIA is not set
+# CONFIG_FB_RIVA is not set
+# CONFIG_FB_LE80578 is not set
+# CONFIG_FB_INTEL is not set
+# CONFIG_FB_MATROX is not set
+# CONFIG_FB_RADEON is not set
+# CONFIG_FB_ATY128 is not set
+# CONFIG_FB_ATY is not set
+# CONFIG_FB_S3 is not set
+# CONFIG_FB_SAVAGE is not set
+# CONFIG_FB_SIS is not set
+# CONFIG_FB_NEOMAGIC is not set
+# CONFIG_FB_KYRO is not set
+# CONFIG_FB_3DFX is not set
+# CONFIG_FB_VOODOO1 is not set
+# CONFIG_FB_VT8623 is not set
+# CONFIG_FB_TRIDENT is not set
+# CONFIG_FB_ARK is not set
+# CONFIG_FB_PM3 is not set
+# CONFIG_FB_GEODE is not set
+# CONFIG_FB_VIRTUAL is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+# CONFIG_BACKLIGHT_CORGI is not set
+# CONFIG_BACKLIGHT_PROGEAR is not set
 
 #
 # Display device support
@@ -1012,9 +1448,14 @@ CONFIG_AGP_INTEL=y
 #
 CONFIG_VGA_CONSOLE=y
 CONFIG_VGACON_SOFT_SCROLLBACK=y
-CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256
+CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
 CONFIG_VIDEO_SELECT=y
 CONFIG_DUMMY_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_LOGO_LINUX_CLUT224=y
 
 #
 # Sound
@@ -1024,35 +1465,165 @@ CONFIG_SOUND=y
 #
 # Advanced Linux Sound Architecture
 #
-# CONFIG_SND is not set
+CONFIG_SND=y
+CONFIG_SND_TIMER=y
+CONFIG_SND_PCM=y
+CONFIG_SND_HWDEP=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQ_DUMMY=y
+CONFIG_SND_OSSEMUL=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_PCM_OSS_PLUGINS=y
+CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_DYNAMIC_MINORS=y
+CONFIG_SND_SUPPORT_OLD_API=y
+CONFIG_SND_VERBOSE_PROCFS=y
+# CONFIG_SND_VERBOSE_PRINTK is not set
+# CONFIG_SND_DEBUG is not set
+CONFIG_SND_VMASTER=y
+
+#
+# Generic devices
+#
+# CONFIG_SND_PCSP is not set
+# CONFIG_SND_DUMMY is not set
+# CONFIG_SND_VIRMIDI is not set
+# CONFIG_SND_MTPAV is not set
+# CONFIG_SND_SERIAL_U16550 is not set
+# CONFIG_SND_MPU401 is not set
+
+#
+# PCI devices
+#
+# CONFIG_SND_AD1889 is not set
+# CONFIG_SND_ALS300 is not set
+# CONFIG_SND_ALS4000 is not set
+# CONFIG_SND_ALI5451 is not set
+# CONFIG_SND_ATIIXP is not set
+# CONFIG_SND_ATIIXP_MODEM is not set
+# CONFIG_SND_AU8810 is not set
+# CONFIG_SND_AU8820 is not set
+# CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AW2 is not set
+# CONFIG_SND_AZT3328 is not set
+# CONFIG_SND_BT87X is not set
+# CONFIG_SND_CA0106 is not set
+# CONFIG_SND_CMIPCI is not set
+# CONFIG_SND_OXYGEN is not set
+# CONFIG_SND_CS4281 is not set
+# CONFIG_SND_CS46XX is not set
+# CONFIG_SND_CS5530 is not set
+# CONFIG_SND_DARLA20 is not set
+# CONFIG_SND_GINA20 is not set
+# CONFIG_SND_LAYLA20 is not set
+# CONFIG_SND_DARLA24 is not set
+# CONFIG_SND_GINA24 is not set
+# CONFIG_SND_LAYLA24 is not set
+# CONFIG_SND_MONA is not set
+# CONFIG_SND_MIA is not set
+# CONFIG_SND_ECHO3G is not set
+# CONFIG_SND_INDIGO is not set
+# CONFIG_SND_INDIGOIO is not set
+# CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_EMU10K1 is not set
+# CONFIG_SND_EMU10K1X is not set
+# CONFIG_SND_ENS1370 is not set
+# CONFIG_SND_ENS1371 is not set
+# CONFIG_SND_ES1938 is not set
+# CONFIG_SND_ES1968 is not set
+# CONFIG_SND_FM801 is not set
+CONFIG_SND_HDA_INTEL=y
+CONFIG_SND_HDA_HWDEP=y
+CONFIG_SND_HDA_CODEC_REALTEK=y
+CONFIG_SND_HDA_CODEC_ANALOG=y
+CONFIG_SND_HDA_CODEC_SIGMATEL=y
+CONFIG_SND_HDA_CODEC_VIA=y
+CONFIG_SND_HDA_CODEC_ATIHDMI=y
+CONFIG_SND_HDA_CODEC_CONEXANT=y
+CONFIG_SND_HDA_CODEC_CMEDIA=y
+CONFIG_SND_HDA_CODEC_SI3054=y
+CONFIG_SND_HDA_GENERIC=y
+# CONFIG_SND_HDA_POWER_SAVE is not set
+# CONFIG_SND_HDSP is not set
+# CONFIG_SND_HDSPM is not set
+# CONFIG_SND_HIFIER is not set
+# CONFIG_SND_ICE1712 is not set
+# CONFIG_SND_ICE1724 is not set
+# CONFIG_SND_INTEL8X0 is not set
+# CONFIG_SND_INTEL8X0M is not set
+# CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_MAESTRO3 is not set
+# CONFIG_SND_MIXART is not set
+# CONFIG_SND_NM256 is not set
+# CONFIG_SND_PCXHR is not set
+# CONFIG_SND_RIPTIDE is not set
+# CONFIG_SND_RME32 is not set
+# CONFIG_SND_RME96 is not set
+# CONFIG_SND_RME9652 is not set
+# CONFIG_SND_SONICVIBES is not set
+# CONFIG_SND_TRIDENT is not set
+# CONFIG_SND_VIA82XX is not set
+# CONFIG_SND_VIA82XX_MODEM is not set
+# CONFIG_SND_VIRTUOSO is not set
+# CONFIG_SND_VX222 is not set
+# CONFIG_SND_YMFPCI is not set
+
+#
+# USB devices
+#
+# CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_USX2Y is not set
+# CONFIG_SND_USB_CAIAQ is not set
+
+#
+# PCMCIA devices
+#
+# CONFIG_SND_VXPOCKET is not set
+# CONFIG_SND_PDAUDIOCF is not set
+
+#
+# System on Chip audio support
+#
+# CONFIG_SND_SOC is not set
+
+#
+# ALSA SoC audio for Freescale SOCs
+#
+
+#
+# SoC Audio for the Texas Instruments OMAP
+#
 
 #
 # Open Sound System
 #
-CONFIG_SOUND_PRIME=y
-# CONFIG_SOUND_TRIDENT is not set
-# CONFIG_SOUND_MSNDCLAS is not set
-# CONFIG_SOUND_MSNDPIN is not set
-# CONFIG_SOUND_OSS is not set
+# CONFIG_SOUND_PRIME is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
-# CONFIG_HID_DEBUG is not set
+CONFIG_HID_DEBUG=y
 CONFIG_HIDRAW=y
 
 #
 # USB Input Devices
 #
 CONFIG_USB_HID=y
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
-# CONFIG_USB_HIDDEV is not set
+CONFIG_USB_HIDINPUT_POWERBOOK=y
+CONFIG_HID_FF=y
+CONFIG_HID_PID=y
+CONFIG_LOGITECH_FF=y
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+CONFIG_PANTHERLORD_FF=y
+CONFIG_THRUSTMASTER_FF=y
+CONFIG_ZEROPLUS_FF=y
+CONFIG_USB_HIDDEV=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
 CONFIG_USB=y
-# CONFIG_USB_DEBUG is not set
-# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 
 #
 # Miscellaneous USB options
@@ -1060,7 +1631,7 @@ CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
-# CONFIG_USB_SUSPEND is not set
+CONFIG_USB_SUSPEND=y
 # CONFIG_USB_OTG is not set
 
 #
@@ -1073,7 +1644,6 @@ CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_ISP116X_HCD is not set
 # CONFIG_USB_ISP1760_HCD is not set
 CONFIG_USB_OHCI_HCD=y
-# CONFIG_USB_OHCI_HCD_SSB is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
@@ -1108,7 +1678,7 @@ CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_ONETOUCH is not set
 # CONFIG_USB_STORAGE_KARMA is not set
 # CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
-# CONFIG_USB_LIBUSUAL is not set
+CONFIG_USB_LIBUSUAL=y
 
 #
 # USB Imaging devices
@@ -1148,11 +1718,78 @@ CONFIG_USB_MON=y
 # CONFIG_USB_GADGET is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
-# CONFIG_NEW_LEDS is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+
+#
+# LED drivers
+#
+# CONFIG_LEDS_CLEVO_MAIL is not set
+
+#
+# LED Triggers
+#
+CONFIG_LEDS_TRIGGERS=y
+# CONFIG_LEDS_TRIGGER_TIMER is not set
+# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
+# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
-# CONFIG_EDAC is not set
-# CONFIG_RTC_CLASS is not set
+CONFIG_EDAC=y
+
+#
+# Reporting subsystems
+#
+# CONFIG_EDAC_DEBUG is not set
+# CONFIG_EDAC_MM_EDAC is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# I2C RTC drivers
+#
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+CONFIG_RTC_DRV_CMOS=y
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
 CONFIG_DMADEVICES=y
 
 #
@@ -1165,6 +1802,7 @@ CONFIG_DMADEVICES=y
 # Firmware Drivers
 #
 # CONFIG_EDD is not set
+CONFIG_EFI_VARS=y
 # CONFIG_DELL_RBU is not set
 # CONFIG_DCDBAS is not set
 CONFIG_DMIID=y
@@ -1173,25 +1811,16 @@ CONFIG_DMIID=y
 #
 # File systems
 #
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-# CONFIG_EXT2_FS_SECURITY is not set
-# CONFIG_EXT2_FS_XIP is not set
+# CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
-# CONFIG_EXT3_FS_SECURITY is not set
+CONFIG_EXT3_FS_SECURITY=y
 # CONFIG_EXT4DEV_FS is not set
 CONFIG_JBD=y
 # CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=y
-CONFIG_REISERFS_FS=y
-# CONFIG_REISERFS_CHECK is not set
-# CONFIG_REISERFS_PROC_INFO is not set
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-# CONFIG_REISERFS_FS_SECURITY is not set
+# CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 CONFIG_FS_POSIX_ACL=y
 # CONFIG_XFS_FS is not set
@@ -1200,7 +1829,12 @@ CONFIG_FS_POSIX_ACL=y
 CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
-# CONFIG_QUOTA is not set
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+# CONFIG_QFMT_V1 is not set
+CONFIG_QFMT_V2=y
+CONFIG_QUOTACTL=y
 # CONFIG_AUTOFS_FS is not set
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
@@ -1211,7 +1845,7 @@ CONFIG_GENERIC_ACL=y
 #
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
-# CONFIG_ZISOFS is not set
+CONFIG_ZISOFS=y
 # CONFIG_UDF_FS is not set
 
 #
@@ -1229,6 +1863,7 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 #
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_VMCORE=y
 CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
@@ -1242,6 +1877,7 @@ CONFIG_HUGETLB_PAGE=y
 #
 # CONFIG_ADFS_FS is not set
 # CONFIG_AFFS_FS is not set
+# CONFIG_ECRYPT_FS is not set
 # CONFIG_HFS_FS is not set
 # CONFIG_HFSPLUS_FS is not set
 # CONFIG_BEFS_FS is not set
@@ -1255,15 +1891,38 @@ CONFIG_HUGETLB_PAGE=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+# CONFIG_NFS_FS is not set
+# CONFIG_NFSD is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
 
 #
 # Partition Types
 #
-# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+# CONFIG_ATARI_PARTITION is not set
+CONFIG_MAC_PARTITION=y
 CONFIG_MSDOS_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+# CONFIG_LDM_PARTITION is not set
+CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
 CONFIG_NLS=y
-CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 # CONFIG_NLS_CODEPAGE_737 is not set
 # CONFIG_NLS_CODEPAGE_775 is not set
@@ -1298,7 +1957,7 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_ISO8859_9 is not set
 # CONFIG_NLS_ISO8859_13 is not set
 # CONFIG_NLS_ISO8859_14 is not set
-CONFIG_NLS_ISO8859_15=y
+# CONFIG_NLS_ISO8859_15 is not set
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 CONFIG_NLS_UTF8=y
@@ -1309,21 +1968,22 @@ CONFIG_NLS_UTF8=y
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
-CONFIG_ENABLE_WARN_DEPRECATED=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_FRAME_WARN=2048
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_UNUSED_SYMBOLS=y
+# CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_FS=y
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
-CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
-# CONFIG_SCHEDSTATS is not set
+CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_OBJECTS is not set
-# CONFIG_DEBUG_SLAB is not set
+# CONFIG_SLUB_DEBUG_ON is not set
+# CONFIG_SLUB_STATS is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
@@ -1340,7 +2000,7 @@ CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set
-# CONFIG_FRAME_POINTER is not set
+CONFIG_FRAME_POINTER=y
 # CONFIG_BOOT_PRINTK_DELAY is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_KPROBES_SANITY_TEST is not set
@@ -1348,20 +2008,21 @@ CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_LKDTM is not set
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
-# CONFIG_PROVIDE_OHCI1394_DMA_INIT is not set
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
 # CONFIG_SAMPLES is not set
 # CONFIG_KGDB is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_NONPROMISC_DEVMEM is not set
 CONFIG_EARLY_PRINTK=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-# CONFIG_DEBUG_STACK_USAGE is not set
+CONFIG_DEBUG_STACK_USAGE=y
 # CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 # CONFIG_X86_PTDUMP is not set
-# CONFIG_DEBUG_RODATA is not set
+CONFIG_DEBUG_RODATA=y
 # CONFIG_DIRECT_GBPAGES is not set
-# CONFIG_DEBUG_NX_TEST is not set
+# CONFIG_DEBUG_RODATA_TEST is not set
+CONFIG_DEBUG_NX_TEST=m
 CONFIG_X86_MPPARSE=y
 # CONFIG_IOMMU_DEBUG is not set
 CONFIG_IO_DELAY_TYPE_0X80=0
@@ -1373,18 +2034,115 @@ CONFIG_IO_DELAY_0X80=y
 # CONFIG_IO_DELAY_UDELAY is not set
 # CONFIG_IO_DELAY_NONE is not set
 CONFIG_DEFAULT_IO_DELAY_TYPE=0
-# CONFIG_DEBUG_BOOT_PARAMS is not set
+CONFIG_DEBUG_BOOT_PARAMS=y
 # CONFIG_CPA_DEBUG is not set
 
 #
 # Security options
 #
-# CONFIG_KEYS is not set
-# CONFIG_SECURITY is not set
-# CONFIG_SECURITY_FILE_CAPABILITIES is not set
-# CONFIG_CRYPTO is not set
-# CONFIG_HAVE_KVM is not set
-# CONFIG_VIRTUALIZATION is not set
+CONFIG_KEYS=y
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+# CONFIG_SECURITY_NETWORK_XFRM is not set
+CONFIG_SECURITY_CAPABILITIES=y
+CONFIG_SECURITY_FILE_CAPABILITIES=y
+# CONFIG_SECURITY_ROOTPLUG is not set
+CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR=65536
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+CONFIG_SECURITY_SELINUX_AVC_STATS=y
+CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
+# CONFIG_SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT is not set
+# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
+# CONFIG_SECURITY_SMACK is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_MANAGER=y
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+CONFIG_CRYPTO_AUTHENC=y
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=y
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=y
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+CONFIG_CRYPTO_HMAC=y
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=y
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+CONFIG_CRYPTO_SHA1=y
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=y
+# CONFIG_CRYPTO_AES_X86_64 is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=y
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SALSA20_X86_64 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+# CONFIG_CRYPTO_TWOFISH_X86_64 is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
+CONFIG_CRYPTO_HW=y
+# CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_HAVE_KVM=y
+CONFIG_VIRTUALIZATION=y
 # CONFIG_KVM is not set
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
-- 
cgit v1.2.2


From 205f93288093df69f9ab5f6981aef27b91088b28 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@codemonkey.org.uk>
Date: Mon, 5 May 2008 17:52:52 -0400
Subject: x86: add new cache descriptor

The latest rev of Intel doc AP-485 details a new cache
descriptor that we don't yet support.
A 6MB 24-way assoc L2 cache.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/intel_cacheinfo.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 26d615dcb149..2c8afafa18e8 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -62,6 +62,7 @@ static struct _cache_table cache_table[] __cpuinitdata =
 	{ 0x4b, LVL_3,      8192 },	/* 16-way set assoc, 64 byte line size */
 	{ 0x4c, LVL_3,     12288 },	/* 12-way set assoc, 64 byte line size */
 	{ 0x4d, LVL_3,     16384 },	/* 16-way set assoc, 64 byte line size */
+	{ 0x4e, LVL_2,      6144 },	/* 24-way set assoc, 64 byte line size */
 	{ 0x60, LVL_1_DATA, 16 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-- 
cgit v1.2.2


From 0327318445d55808991a63137cfb698a90ab6adf Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel.send@gmail.com>
Date: Fri, 18 Apr 2008 17:49:15 -0700
Subject: x86_64: simplify the memtest parameter setting

use CONFIG_MEMTEST only. if it is set, will have memtest=0 (disabled)

need to have memtest=4 in command line to test more patterns.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig      | 30 +++++++-----------------------
 arch/x86/mm/init_64.c |  5 +++--
 2 files changed, 10 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe361ae7ef2f..a1a9021146bc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -419,35 +419,19 @@ config PARAVIRT
 
 endif
 
-config MEMTEST_BOOTPARAM
-	bool "Memtest boot parameter"
+config MEMTEST
+	bool "Memtest"
 	depends on X86_64
 	default y
 	help
 	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be disabled at boot.  If this option is selected, memtest
-	  functionality can be disabled with memtest=0 on the kernel
-	  command line.  The purpose of this option is to allow a single
-	  kernel image to be distributed with memtest built in, but not
-	  necessarily enabled.
-
+	  to be set.
+		memtest=0, mean disabled; -- default
+		memtest=1, mean do 1 test pattern;
+		...
+		memtest=4, mean do 4 test patterns.
 	  If you are unsure how to answer this question, answer Y.
 
-config MEMTEST_BOOTPARAM_VALUE
-	int "Memtest boot parameter default value (0-4)"
-	depends on MEMTEST_BOOTPARAM
-	range 0 4
-	default 0
-	help
-	  This option sets the default value for the kernel parameter
-	  'memtest', which allows memtest to be disabled at boot.  If this
-	  option is set to 0 (zero), the memtest kernel parameter will
-	  default to 0, disabling memtest at bootup.  If this option is
-	  set to 4, the memtest kernel parameter will default to 4,
-	  enabling memtest at bootup, and use that as pattern number.
-
-	  If you are unsure how to answer this question, answer 0.
-
 config ACPI_SRAT
 	def_bool y
 	depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 32ba13b0f818..c6d81316db65 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -431,7 +431,7 @@ static void __init init_gbpages(void)
 		direct_gbpages = 0;
 }
 
-#ifdef CONFIG_MEMTEST_BOOTPARAM
+#ifdef CONFIG_MEMTEST
 
 static void __init memtest(unsigned long start_phys, unsigned long size,
 				 unsigned pattern)
@@ -493,7 +493,8 @@ static void __init memtest(unsigned long start_phys, unsigned long size,
 
 }
 
-static int memtest_pattern __initdata = CONFIG_MEMTEST_BOOTPARAM_VALUE;
+/* default is disabled */
+static int memtest_pattern __initdata;
 
 static int __init parse_memtest(char *arg)
 {
-- 
cgit v1.2.2


From 8d64c781f0c5fbfdf8016bd1634506ff2ad1376a Mon Sep 17 00:00:00 2001
From: Tony Camuso <tcamuso@redhat.com>
Date: Thu, 15 May 2008 14:40:14 -0400
Subject: PCI: Correct last two HP entries in the bfsort whitelist

Replace Redundant Whitelist Entries with the Correct Ones

The ProLiant DL585 G2 and the DL585 G2 are entered reundantly in the
dmi_system_id table. What should have been there are the DL360 and DL380. This
patch simply replaces the redundant entries with the correct entries.

Signed-off-by: Tony Camuso <tony.camuso@hp.com>
Signed-off-by: Pat Schoeller <patrick.schoeller@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/pci/common.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8545c8a9d107..6e64aaf00d1d 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -302,18 +302,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 #ifdef __i386__
-- 
cgit v1.2.2


From eba9fe93a2959ec7f195c47c9db6ce7b5114ce1f Mon Sep 17 00:00:00 2001
From: Mark Langsdorf <mark.langsdorf@amd.com>
Date: Tue, 18 Mar 2008 15:24:32 -0500
Subject: [CPUFREQ] powernow-k8: improve error messages

The most common error with powernow-k8 is an ACPI _PSS error
caused either by failure to load the ACPI processor module
or a bad parse of the _PSS object.  Make the error message
returned to the user in these situations more straightforward
and easier to understand.

-Mark Langsdorf
Operating System Research Center
AMD

Signed-off-by: Mark Langsdorf <mark.langsdorf@amd.com>
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Dave Jones <davej@redhat.com>
---
 arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 46d4034d9f37..206791eb46e3 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1127,12 +1127,23 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		 * an UP version, and is deprecated by AMD.
 		 */
 		if (num_online_cpus() != 1) {
-			printk(KERN_ERR PFX "MP systems not supported by PSB BIOS structure\n");
+#ifndef CONFIG_ACPI_PROCESSOR
+			printk(KERN_ERR PFX "ACPI Processor support is required "
+			       "for SMP systems but is absent. Please load the "
+			       "ACPI Processor module before starting this "
+			       "driver.\n");
+#else
+			printk(KERN_ERR PFX "Your BIOS does not provide ACPI "
+			       "_PSS objects in a way that Linux understands. "
+			       "Please report this to the Linux ACPI maintainers"
+			       " and complain to your BIOS vendor.\n");
+#endif
 			kfree(data);
 			return -ENODEV;
 		}
 		if (pol->cpu != 0) {
-			printk(KERN_ERR PFX "No _PSS objects for CPU other than CPU0\n");
+			printk(KERN_ERR PFX "No ACPI _PSS objects for CPU other than "
+			       "CPU0. Complain to your BIOS vendor.\n");
 			kfree(data);
 			return -ENODEV;
 		}
-- 
cgit v1.2.2


From 667ad4f70110357e8f024e81741c7bd1d7906e7d Mon Sep 17 00:00:00 2001
From: maximilian attems <max@stro.at>
Date: Thu, 8 May 2008 22:10:01 +0200
Subject: [CPUFREQ] Crusoe: longrun cpufreq module reports false min freq

The longrun cpufreq module reports a false minimum frequency 3MHz on
300-600MHz Crusoe processor.  This may be due to a calculation bug
in the module.

Original patch from Kaz Sasayama <kazssym@hypercore.co.jp>
submitted as http://bugs.debian.org/468149 patch ported to x86

Cc: Kaz Sasayama <kazssym@hypercore.co.jp>
Signed-off-by: maximilian attems <max@stro.at>
Signed-off-by: Dave Jones <davej@redhat.com>
---
 arch/x86/kernel/cpu/cpufreq/longrun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index af4a867a097c..777a7ff075de 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -245,7 +245,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq,
 	if ((ecx > 95) || (ecx == 0) || (eax < ebx))
 		return -EIO;
 
-	edx = (eax - ebx) / (100 - ecx);
+	edx = ((eax - ebx) * 100) / (100 - ecx);
 	*low_freq = edx * 1000; /* back to kHz */
 
 	dprintk("low frequency is %u kHz\n", *low_freq);
-- 
cgit v1.2.2


From 0abbc78a0137fee60ef092f0b20a3d3d7e7e0cc2 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 20 May 2008 16:27:17 +0200
Subject: x86, aperture_64: use symbolic constants

Factor-out common aperture_valid code.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 23 +----------------------
 1 file changed, 1 insertion(+), 22 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 02f4dbaa4df4..5373f7834d8a 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -109,27 +109,6 @@ static u32 __init allocate_aperture(void)
 	return (u32)__pa(p);
 }
 
-static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
-{
-	if (!aper_base)
-		return 0;
-
-	if (aper_base + aper_size > 0x100000000UL) {
-		printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
-		return 0;
-	}
-	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
-		return 0;
-	}
-	if (aper_size < min_size) {
-		printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
-				 aper_size>>20, min_size>>20);
-		return 0;
-	}
-
-	return 1;
-}
 
 /* Find a PCI capability */
 static __u32 __init find_cap(int bus, int slot, int func, int cap)
@@ -344,7 +323,7 @@ out:
 	if (gart_fix_e820 && !fix && aper_enabled) {
 		if (!e820_all_mapped(aper_base, aper_base + aper_size,
 				    E820_RESERVED)) {
-			/* reserved it, so we can resuse it in second kernel */
+			/* reserve it, so we can reuse it in second kernel */
 			printk(KERN_INFO "update e820 for GART\n");
 			add_memory_region(aper_base, aper_size, E820_RESERVED);
 			update_e820();
-- 
cgit v1.2.2


From a1676072558854b95336c8f7db76b0504e909a0a Mon Sep 17 00:00:00 2001
From: Tony Camuso <tcamuso@redhat.com>
Date: Thu, 15 May 2008 14:40:14 -0400
Subject: PCI: Correct last two HP entries in the bfsort whitelist

Greetings.

There is a code flaw in the bfsort whitelist, where there are redundant
entries for the same two HP systems, DL385 G2 and DL585 G2. This patch
replaces those redundant entries with the correct ones. The correct
entries are for large-volume systems, the DL360 and DL380.

-----------------------------------------------------------------------

commit ec69f0374c3b0ad7ea991b0e9ac00377acfe5b1a
Author: Tony Camuso <tony.camuso@hp.com>
Date:   Wed May 14 07:09:28 2008 -0400

     Replace Redundant Whitelist Entries with the Correct Ones

     The ProLiant DL585 G2 and the DL585 G2 are entered reundantly
     in the dmi_system_id table. What should have been there are the
     DL360 and DL380. This patch simply replaces the redundant
     entries with the correct entries.

 arch/x86/pci/common.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

     Signed-off-by: Tony Camuso <tony.camuso@hp.com>
     Signed-off-by: Pat Schoeller <patrick.schoeller@hp.com>

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/pci/common.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 6e64aaf00d1d..940185ecaeda 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 #endif
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 	{}
-- 
cgit v1.2.2


From 0748aca6f0af917591dcfd70dccac770a25d4f71 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 13 May 2008 10:34:20 +0200
Subject: x86: remove useless static current_tsc_khz variable

current_tsc_khz is just written by the init code and never used
again. Remove it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/tsc_32.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index e4790728b224..d53b1040cbb7 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -283,7 +283,6 @@ core_initcall(cpufreq_tsc);
 
 /* clock source code */
 
-static unsigned long current_tsc_khz;
 static struct clocksource clocksource_tsc;
 
 /*
@@ -434,9 +433,8 @@ void __init tsc_init(void)
 
 	unsynchronized_tsc();
 	check_geode_tsc_reliable();
-	current_tsc_khz = tsc_khz;
-	clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz,
-							clocksource_tsc.shift);
+	clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
+						    clocksource_tsc.shift);
 	/* lower the rating if we already know its unstable: */
 	if (check_tsc_unstable()) {
 		clocksource_tsc.rating = 0;
-- 
cgit v1.2.2


From 3843fc2575e3389f4f0ad0420a720240a5746a5d Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Fri, 9 May 2008 12:05:57 +0100
Subject: xen: remove support for non-PAE 32-bit

Non-PAE operation has been deprecated in Xen for a while, and is
rarely tested or used.  xen-unstable has now officially dropped
non-PAE support.  Since Xen/pvops' non-PAE support has also been
broken for a while, we may as well completely drop it altogether.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/Kconfig     |  2 +-
 arch/x86/xen/enlighten.c | 51 +++++++++++++++++-------------------------------
 arch/x86/xen/mmu.c       | 19 ++----------------
 arch/x86/xen/mmu.h       | 24 ++++++-----------------
 arch/x86/xen/xen-head.S  |  4 ----
 5 files changed, 27 insertions(+), 73 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 2e641be2737e..525b108411bd 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -6,7 +6,7 @@ config XEN
 	bool "Xen guest support"
 	select PARAVIRT
 	depends on X86_32
-	depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
+	depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER)
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c8a56e457d61..a05b7721bc81 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -785,38 +785,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 	pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+	int i;
 
 	/* special set_pte for pagetable initialization */
 	pv_mmu_ops.set_pte = xen_set_pte_init;
 
 	init_mm.pgd = base;
 	/*
-	 * copy top-level of Xen-supplied pagetable into place.	 For
-	 * !PAE we can use this as-is, but for PAE it is a stand-in
-	 * while we copy the pmd pages.
+	 * copy top-level of Xen-supplied pagetable into place.  This
+	 * is a stand-in while we copy the pmd pages.
 	 */
 	memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
-	if (PTRS_PER_PMD > 1) {
-		int i;
-		/*
-		 * For PAE, need to allocate new pmds, rather than
-		 * share Xen's, since Xen doesn't like pmd's being
-		 * shared between address spaces.
-		 */
-		for (i = 0; i < PTRS_PER_PGD; i++) {
-			if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
-				pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+	/*
+	 * For PAE, need to allocate new pmds, rather than
+	 * share Xen's, since Xen doesn't like pmd's being
+	 * shared between address spaces.
+	 */
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
+			pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 
-				memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
-				       PAGE_SIZE);
+			memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
+			       PAGE_SIZE);
 
-				make_lowmem_page_readonly(pmd);
+			make_lowmem_page_readonly(pmd);
 
-				set_pgd(&base[i], __pgd(1 + __pa(pmd)));
-			} else
-				pgd_clear(&base[i]);
-		}
+			set_pgd(&base[i], __pgd(1 + __pa(pmd)));
+		} else
+			pgd_clear(&base[i]);
 	}
 
 	/* make sure zero_page is mapped RO so we can use it in pagetables */
@@ -873,17 +870,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 
 	/* Actually pin the pagetable down, but we can't set PG_pinned
 	   yet because the page structures don't exist yet. */
-	{
-		unsigned level;
-
-#ifdef CONFIG_X86_PAE
-		level = MMUEXT_PIN_L3_TABLE;
-#else
-		level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-		pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
-	}
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
 }
 
 /* This is called once we have the cpu_possible_map */
@@ -1093,7 +1080,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.make_pte = xen_make_pte,
 	.make_pgd = xen_make_pgd,
 
-#ifdef CONFIG_X86_PAE
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
 	.set_pud = xen_set_pud,
@@ -1102,7 +1088,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.make_pmd = xen_make_pmd,
 	.pmd_val = xen_pmd_val,
-#endif	/* PAE */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 126766d43aea..07c2653ec335 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -222,7 +222,7 @@ pmdval_t xen_pmd_val(pmd_t pmd)
 		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
 	return ret;
 }
-#ifdef CONFIG_X86_PAE
+
 void xen_set_pud(pud_t *ptr, pud_t val)
 {
 	struct multicall_space mcs;
@@ -272,12 +272,6 @@ pmd_t xen_make_pmd(pmdval_t pmd)
 
 	return native_make_pmd(pmd);
 }
-#else  /* !PAE */
-void xen_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
-}
-#endif	/* CONFIG_X86_PAE */
 
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
@@ -430,8 +424,6 @@ static int pin_page(struct page *page, enum pt_level level)
    read-only, and can be pinned. */
 void xen_pgd_pin(pgd_t *pgd)
 {
-	unsigned level;
-
 	xen_mc_batch();
 
 	if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
@@ -441,14 +433,7 @@ void xen_pgd_pin(pgd_t *pgd)
 		xen_mc_batch();
 	}
 
-#ifdef CONFIG_X86_PAE
-	level = MMUEXT_PIN_L3_TABLE;
-#else
-	level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-	xen_do_pin(level, PFN_DOWN(__pa(pgd)));
-
+	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
 	xen_mc_issue(0);
 }
 
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index b5e189b1519d..5fe961caffd4 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -37,14 +37,13 @@ void xen_exit_mmap(struct mm_struct *mm);
 void xen_pgd_pin(pgd_t *pgd);
 //void xen_pgd_unpin(pgd_t *pgd);
 
-#ifdef CONFIG_X86_PAE
-unsigned long long xen_pte_val(pte_t);
-unsigned long long xen_pmd_val(pmd_t);
-unsigned long long xen_pgd_val(pgd_t);
+pteval_t xen_pte_val(pte_t);
+pmdval_t xen_pmd_val(pmd_t);
+pgdval_t xen_pgd_val(pgd_t);
 
-pte_t xen_make_pte(unsigned long long);
-pmd_t xen_make_pmd(unsigned long long);
-pgd_t xen_make_pgd(unsigned long long);
+pte_t xen_make_pte(pteval_t);
+pmd_t xen_make_pmd(pmdval_t);
+pgd_t xen_make_pgd(pgdval_t);
 
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval);
@@ -53,15 +52,4 @@ void xen_set_pud(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
-
-#else
-unsigned long xen_pte_val(pte_t);
-unsigned long xen_pmd_val(pmd_t);
-unsigned long xen_pgd_val(pgd_t);
-
-pte_t xen_make_pte(unsigned long);
-pmd_t xen_make_pmd(unsigned long);
-pgd_t xen_make_pgd(unsigned long);
-#endif
-
 #endif	/* _XEN_MMU_H */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 288d587ce73c..2ab5f42f34d8 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -30,11 +30,7 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          .long  startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long  hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
-#ifdef CONFIG_X86_PAE
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
-#else
-	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "no")
-#endif
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 
 #endif /*CONFIG_XEN */
-- 
cgit v1.2.2


From b478458aeebfc55fe409abec43794ac72a623c79 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:44:39 +0200
Subject: x86: avoid re-loading LDT in unrelated address spaces

Performance optimization.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/ldt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 0224c3637c73..21f2bae98c15 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,9 +20,9 @@
 #include <asm/mmu_context.h>
 
 #ifdef CONFIG_SMP
-static void flush_ldt(void *null)
+static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm)
+	if (current->active_mm == current_mm)
 		load_LDT(&current->active_mm->context);
 }
 #endif
@@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 		load_LDT(pc);
 		mask = cpumask_of_cpu(smp_processor_id());
 		if (!cpus_equal(current->mm->cpu_vm_mask, mask))
-			smp_call_function(flush_ldt, NULL, 1, 1);
+			smp_call_function(flush_ldt, current->mm, 1, 1);
 		preempt_enable();
 #else
 		load_LDT(pc);
-- 
cgit v1.2.2


From 873b274a41c0cfe58b2eb0a7722424eb367b905b Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Thu, 22 May 2008 13:02:23 -0400
Subject: x86: Add Centaur and Transmeta CPUs to PAT whitelist

Unconditionally enable PAT support on Centaur and Transmeta CPUs.
All known models that advertise PAT have no known errata.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/addon_cpuid_features.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index c2e1ce33c7cb..d8b3e4a9d663 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -62,6 +62,9 @@ void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
 			return;
 		break;
+	case X86_VENDOR_CENTAUR:
+	case X86_VENDOR_TRANSMETA:
+		return;
 	}
 
 	pat_disable(cpu_has_pat ?
-- 
cgit v1.2.2


From c3ed64295f0fed9131b42122234b1ce4a4a266cf Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Fri, 16 May 2008 10:44:39 -0700
Subject: x86: change maximum NR_CPUS to 4096 and MAX_NUMNODES to 512

  * Change the range of NR_CPUS from 2-255 to 2-4096 and change the
    range of MAX_NUMNODES (NODES_SHIFT) from 1-32768 to 1-512.

  * Alter comment about how much each increment of NR_CPUS consumes.
    (This was found by configuring for 256 cpus and then 512 cpus
     and dividing the difference by 256.)

Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe361ae7ef2f..bbafeac89116 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -565,18 +565,18 @@ config IOMMU_HELPER
 	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB)
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-255)"
-	range 2 255
+	int "Maximum number of CPUs (2-4096)"
+	range 2 4096
 	depends on SMP
 	default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
 	default "8"
 	help
 	  This allows you to specify the maximum number of CPUs which this
-	  kernel will support.  The maximum supported value is 255 and the
+	  kernel will support.  The maximum supported value is 4096 and the
 	  minimum value which makes sense is 2.
 
 	  This is purely to save memory - each supported CPU adds
-	  approximately eight kilobytes to the kernel image.
+	  approximately one kilobyte to the kernel image.
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -968,8 +968,8 @@ config NUMA_EMU
 	  number of nodes. This is only useful for debugging.
 
 config NODES_SHIFT
-	int "Max num nodes shift(1-15)"
-	range 1 15  if X86_64
+	int "Max num nodes shift(1-9)"
+	range 1 9  if X86_64
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
-- 
cgit v1.2.2


From b6db80ee1331e7beaeb91b4b3d946dd16c72e388 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 18 May 2008 19:27:48 +0200
Subject: x86: fix setup of cyc2ns in tsc_64.c

When the TSC is calibrated against the PIT due to the nonavailability
of PMTIMER/HPET or due to SMI interference then the setup of the per
CPU cyc2ns variables is skipped. This is unlikely to happen but it
would definitely render sched_clock() unusable.

This was introduced with commit 53d517cdbaac704352b3d0c10fecb99e0b54572e

    x86: scale cyc_2_nsec according to CPU frequency

Update the per CPU cyc2ns variables in all exit pathes of tsc_calibrate.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
---
 arch/x86/kernel/tsc_64.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index fcc16e58609e..1784b8077a12 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -227,14 +227,14 @@ void __init tsc_calibrate(void)
 	/* hpet or pmtimer available ? */
 	if (!hpet && !pm1 && !pm2) {
 		printk(KERN_INFO "TSC calibrated against PIT\n");
-		return;
+		goto out;
 	}
 
 	/* Check, whether the sampling was disturbed by an SMI */
 	if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) {
 		printk(KERN_WARNING "TSC calibration disturbed by SMI, "
 		       "using PIT calibration result\n");
-		return;
+		goto out;
 	}
 
 	tsc2 = (tsc2 - tsc1) * 1000000L;
@@ -255,6 +255,7 @@ void __init tsc_calibrate(void)
 
 	tsc_khz = tsc2 / tsc1;
 
+out:
 	for_each_possible_cpu(cpu)
 		set_cyc2ns_scale(tsc_khz, cpu);
 }
-- 
cgit v1.2.2


From 9ccc906c97e34fd91dc6aaf5b69b52d824386910 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 13 May 2008 12:31:00 +0200
Subject: x86: distangle user disabled TSC from unstable

tsc_enabled is set to 0 from the command line switch "notsc" and from
the mark_tsc_unstable code. Seperate those functionalities and replace
tsc_enable with tsc_disable. This makes also the native_sched_clock()
decision when to use TSC understandable.

Preparatory patch to solve the sched_clock() issue on 32 bit.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/tsc_32.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index e4790728b224..b087d691f165 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -14,7 +14,7 @@
 
 #include "mach_timer.h"
 
-static int tsc_enabled;
+static int tsc_disabled;
 
 /*
  * On some systems the TSC frequency does not
@@ -28,8 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz);
 static int __init tsc_setup(char *str)
 {
 	printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, "
-				"cannot disable TSC completely.\n");
-	mark_tsc_unstable("user disabled TSC");
+	       "cannot disable TSC completely.\n");
+	tsc_disabled = 1;
 	return 1;
 }
 #else
@@ -120,7 +120,7 @@ unsigned long long native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achive it. )
 	 */
-	if (unlikely(!tsc_enabled && !tsc_unstable))
+	if (unlikely(tsc_disabled))
 		/* No locking but a rare wrong value is not a big deal: */
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
@@ -322,7 +322,6 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
-		tsc_enabled = 0;
 		printk("Marking TSC unstable due to: %s.\n", reason);
 		/* Can be called before registration */
 		if (clocksource_tsc.mult)
@@ -336,7 +335,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
-		       d->ident);
+	       d->ident);
 	tsc_unstable = 1;
 	return 0;
 }
@@ -403,8 +402,11 @@ void __init tsc_init(void)
 {
 	int cpu;
 
-	if (!cpu_has_tsc)
+	if (!cpu_has_tsc || tsc_disabled) {
+		/* Disable the TSC in case of !cpu_has_tsc */
+		tsc_disabled = 1;
 		return;
+	}
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
@@ -441,8 +443,6 @@ void __init tsc_init(void)
 	if (check_tsc_unstable()) {
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
-	} else
-		tsc_enabled = 1;
-
+	}
 	clocksource_register(&clocksource_tsc);
 }
-- 
cgit v1.2.2


From 74dc51a3de06aa516e3b9fdc4017b2aeb38bf44b Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 18 May 2008 22:17:59 +0200
Subject: x86: disable TSC for sched_clock() when calibration failed

When the TSC calibration fails then TSC is still used in
sched_clock(). Disable it completely in that case.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
---
 arch/x86/kernel/tsc_32.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index b087d691f165..068759db63dd 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -413,6 +413,11 @@ void __init tsc_init(void)
 
 	if (!cpu_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
+		/*
+		 * We need to disable the TSC completely in this case
+		 * to prevent sched_clock() from using it.
+		 */
+		tsc_disabled = 1;
 		return;
 	}
 
-- 
cgit v1.2.2


From 2584a82deed7196f48066f1b1a7fad4ec5bea961 Mon Sep 17 00:00:00 2001
From: Chuck Ebbert <cebbert@redhat.com>
Date: Tue, 20 May 2008 18:18:12 -0400
Subject: x86: don't read maxlvt before checking if APIC is mapped

A check for unmapped apic was added before reading maxlvt but the early
read of maxlvt wasn't removed.

Signed-off-by: Chuck Ebbert <cebbert@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
---
 arch/x86/kernel/apic_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 5910020c3f24..0633cfd0dc29 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -534,7 +534,7 @@ int setup_profiling_timer(unsigned int multiplier)
  */
 void clear_local_APIC(void)
 {
-	int maxlvt = lapic_get_maxlvt();
+	int maxlvt;
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
-- 
cgit v1.2.2


From de067814d6b69030d0030e1c5b3dbaf0385aae41 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Thu, 15 May 2008 13:24:52 +0100
Subject: x86/xen: fix arbitrary_virt_to_machine()

While I realize that the function isn't currently being used, I still
think an obvious mistake like this should be corrected.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 126766d43aea..3525ef523a74 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -60,7 +60,7 @@ xmaddr_t arbitrary_virt_to_machine(unsigned long address)
 {
 	unsigned int level;
 	pte_t *pte = lookup_address(address, &level);
-	unsigned offset = address & PAGE_MASK;
+	unsigned offset = address & ~PAGE_MASK;
 
 	BUG_ON(pte == NULL);
 
-- 
cgit v1.2.2


From 2ddfd20e7c55421435cbf95a5ed3dd6e423cf934 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Thu, 22 May 2008 10:37:48 +0200
Subject: namespacecheck: automated fixes

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/kvmclock.c | 4 ++--
 arch/x86/kvm/mmu.c         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 4bc1be5d5472..08a30986d472 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -53,7 +53,7 @@ static cycle_t kvm_clock_read(void);
  * have elapsed since the hypervisor wrote the data. So we try to account for
  * that with system time
  */
-unsigned long kvm_get_wallclock(void)
+static unsigned long kvm_get_wallclock(void)
 {
 	u32 wc_sec, wc_nsec;
 	u64 delta;
@@ -86,7 +86,7 @@ unsigned long kvm_get_wallclock(void)
 	return ts.tv_sec + 1;
 }
 
-int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(unsigned long now)
 {
 	return 0;
 }
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 36c5406b1813..7246b60afb96 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1996,7 +1996,7 @@ static struct shrinker mmu_shrinker = {
 	.seeks = DEFAULT_SEEKS * 10,
 };
 
-void mmu_destroy_caches(void)
+static void mmu_destroy_caches(void)
 {
 	if (pte_chain_cache)
 		kmem_cache_destroy(pte_chain_cache);
-- 
cgit v1.2.2


From a1289643adb6272c04db9399653ae195072c482a Mon Sep 17 00:00:00 2001
From: Andi Kleen <andi@firstfloor.org>
Date: Wed, 14 May 2008 16:10:42 -0700
Subject: x86: use explicit copy in vdso_gettimeofday()

Jeremy's gcc 3.4 seems to be unable to inline a 8 byte memcpy.  But the
vdso doesn't support external references.  Copy the structure members
of struct timezone explicitely instead.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/vdso/vclock_gettime.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 23476c2ebfc4..efa2ba7c6005 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -106,9 +106,9 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 		do_realtime((struct timespec *)tv);
 		tv->tv_usec /= 1000;
 		if (unlikely(tz != NULL)) {
-			/* This relies on gcc inlining the memcpy. We'll notice
-			   if it ever fails to do so. */
-			memcpy(tz, &gtod->sys_tz, sizeof(struct timezone));
+			/* Avoid memcpy. Some old compilers fail to inline it */
+			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
+			tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
 		}
 		return 0;
 	}
-- 
cgit v1.2.2


From 7fafd91d85181e946207bed18c44addc47e36c63 Mon Sep 17 00:00:00 2001
From: Harvey Harrison <harvey.harrison@gmail.com>
Date: Thu, 22 May 2008 15:45:06 -0700
Subject: x86: fix integer as NULL pointer warning

arch/x86/boot/printf.c:59:10: warning: Using plain integer as NULL pointer

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/boot/printf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index c1d00c0274c4..50e47cdbdddd 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -56,7 +56,7 @@ static char *number(char *str, long num, int base, int size, int precision,
 	if (type & LEFT)
 		type &= ~ZEROPAD;
 	if (base < 2 || base > 36)
-		return 0;
+		return NULL;
 	c = (type & ZEROPAD) ? '0' : ' ';
 	sign = 0;
 	if (type & SIGN) {
-- 
cgit v1.2.2


From 40bd21740012132afb62d78ac3e6b82372b2fbc2 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Wed, 21 May 2008 11:44:02 +0200
Subject: x86: automatical unification of i8259.c

Make conversion of i8259 very mechanical -- i8259 was generated by
---
 arch/x86/kernel/Makefile   |   2 +-
 arch/x86/kernel/i8259.c    | 368 +++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/i8259_32.c | 295 ------------------------------------
 arch/x86/kernel/i8259_64.c | 309 -------------------------------------
 4 files changed, 369 insertions(+), 605 deletions(-)
 create mode 100644 arch/x86/kernel/i8259.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5e618c3b4720..f71a76ef2596 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -18,7 +18,7 @@ CFLAGS_tsc_64.o		:= $(nostackp)
 obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
 obj-y			+= traps_$(BITS).o irq_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o
-obj-y			+= setup_$(BITS).o i8259_$(BITS).o setup.o
+obj-y			+= setup_$(BITS).o i8259.o i8259_$(BITS).o setup.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
new file mode 100644
index 000000000000..2decba6b0101
--- /dev/null
+++ b/arch/x86/kernel/i8259.c
@@ -0,0 +1,368 @@
+#ifdef CONFIG_X86_64
+#include <linux/linkage.h>
+#endif /* CONFIG_X86_64 */
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#ifdef CONFIG_X86_64
+#include <linux/timex.h>
+#endif /* CONFIG_X86_64 */
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#ifdef CONFIG_X86_64
+#include <asm/acpi.h>
+#endif /* CONFIG_X86_64 */
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#ifndef CONFIG_X86_64
+#include <asm/timer.h>
+#else /* CONFIG_X86_64 */
+#include <asm/hw_irq.h>
+#endif /* CONFIG_X86_64 */
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#ifndef CONFIG_X86_64
+#include <asm/arch_hooks.h>
+#endif /* ! CONFIG_X86_64 */
+#include <asm/i8259.h>
+
+/*
+ * This is the 'legacy' 8259A Programmable Interrupt Controller,
+ * present in the majority of PC/AT boxes.
+ * plus some generic x86 specific things if generic specifics makes
+ * any sense at all.
+ */
+
+static int i8259A_auto_eoi;
+DEFINE_SPINLOCK(i8259A_lock);
+static void mask_and_ack_8259A(unsigned int);
+
+struct irq_chip i8259A_chip = {
+	.name		= "XT-PIC",
+	.mask		= disable_8259A_irq,
+	.disable	= disable_8259A_irq,
+	.unmask		= enable_8259A_irq,
+	.mask_ack	= mask_and_ack_8259A,
+};
+
+/*
+ * 8259A PIC functions to handle ISA devices:
+ */
+
+/*
+ * This contains the irq mask for both 8259A irq controllers,
+ */
+unsigned int cached_irq_mask = 0xffff;
+
+/*
+ * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
+ * boards the timer interrupt is not really connected to any IO-APIC pin,
+ * it's fed to the master 8259A's IR0 line only.
+ *
+ * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
+ * this 'mixed mode' IRQ handling costs nothing because it's only used
+ * at IRQ setup time.
+ */
+unsigned long io_apic_irqs;
+
+void disable_8259A_irq(unsigned int irq)
+{
+	unsigned int mask = 1 << irq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+	cached_irq_mask |= mask;
+	if (irq & 8)
+		outb(cached_slave_mask, PIC_SLAVE_IMR);
+	else
+		outb(cached_master_mask, PIC_MASTER_IMR);
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
+void enable_8259A_irq(unsigned int irq)
+{
+	unsigned int mask = ~(1 << irq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+	cached_irq_mask &= mask;
+	if (irq & 8)
+		outb(cached_slave_mask, PIC_SLAVE_IMR);
+	else
+		outb(cached_master_mask, PIC_MASTER_IMR);
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+
+int i8259A_irq_pending(unsigned int irq)
+{
+	unsigned int mask = 1<<irq;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+	if (irq < 8)
+		ret = inb(PIC_MASTER_CMD) & mask;
+	else
+		ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+
+	return ret;
+}
+
+void make_8259A_irq(unsigned int irq)
+{
+	disable_irq_nosync(irq);
+	io_apic_irqs &= ~(1<<irq);
+	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+				      "XT");
+	enable_irq(irq);
+}
+
+/*
+ * This function assumes to be called rarely. Switching between
+ * 8259A registers is slow.
+ * This has to be protected by the irq controller spinlock
+ * before being called.
+ */
+static inline int i8259A_irq_real(unsigned int irq)
+{
+	int value;
+	int irqmask = 1<<irq;
+
+	if (irq < 8) {
+		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
+		value = inb(PIC_MASTER_CMD) & irqmask;
+		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
+		return value;
+	}
+	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
+	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
+	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
+	return value;
+}
+
+/*
+ * Careful! The 8259A is a fragile beast, it pretty
+ * much _has_ to be done exactly like this (mask it
+ * first, _then_ send the EOI, and the order of EOI
+ * to the two 8259s is important!
+ */
+static void mask_and_ack_8259A(unsigned int irq)
+{
+	unsigned int irqmask = 1 << irq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+	/*
+	 * Lightweight spurious IRQ detection. We do not want
+	 * to overdo spurious IRQ handling - it's usually a sign
+	 * of hardware problems, so we only do the checks we can
+	 * do without slowing down good hardware unnecessarily.
+	 *
+	 * Note that IRQ7 and IRQ15 (the two spurious IRQs
+	 * usually resulting from the 8259A-1|2 PICs) occur
+	 * even if the IRQ is masked in the 8259A. Thus we
+	 * can check spurious 8259A IRQs without doing the
+	 * quite slow i8259A_irq_real() call for every IRQ.
+	 * This does not cover 100% of spurious interrupts,
+	 * but should be enough to warn the user that there
+	 * is something bad going on ...
+	 */
+	if (cached_irq_mask & irqmask)
+		goto spurious_8259A_irq;
+	cached_irq_mask |= irqmask;
+
+handle_real_irq:
+	if (irq & 8) {
+		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
+		outb(cached_slave_mask, PIC_SLAVE_IMR);
+#ifndef CONFIG_X86_64
+		outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
+		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
+#else /* CONFIG_X86_64 */
+		/* 'Specific EOI' to slave */
+		outb(0x60+(irq&7),PIC_SLAVE_CMD);
+		 /* 'Specific EOI' to master-IRQ2 */
+		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD);
+#endif /* CONFIG_X86_64 */
+	} else {
+		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
+		outb(cached_master_mask, PIC_MASTER_IMR);
+#ifndef CONFIG_X86_64
+		outb(0x60+irq,PIC_MASTER_CMD);	/* 'Specific EOI to master */
+#else /* CONFIG_X86_64 */
+		/* 'Specific EOI' to master */
+		outb(0x60+irq,PIC_MASTER_CMD);
+#endif /* CONFIG_X86_64 */
+	}
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+	return;
+
+spurious_8259A_irq:
+	/*
+	 * this is the slow path - should happen rarely.
+	 */
+	if (i8259A_irq_real(irq))
+		/*
+		 * oops, the IRQ _is_ in service according to the
+		 * 8259A - not spurious, go handle it.
+		 */
+		goto handle_real_irq;
+
+	{
+		static int spurious_irq_mask;
+		/*
+		 * At this point we can be sure the IRQ is spurious,
+		 * lets ACK and report it. [once per IRQ]
+		 */
+		if (!(spurious_irq_mask & irqmask)) {
+#ifndef CONFIG_X86_64
+			printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
+#else /* CONFIG_X86_64 */
+			printk(KERN_DEBUG
+			       "spurious 8259A interrupt: IRQ%d.\n", irq);
+#endif /* CONFIG_X86_64 */
+			spurious_irq_mask |= irqmask;
+		}
+		atomic_inc(&irq_err_count);
+		/*
+		 * Theoretically we do not have to handle this IRQ,
+		 * but in Linux this does not cause problems and is
+		 * simpler for us.
+		 */
+		goto handle_real_irq;
+	}
+}
+
+static char irq_trigger[2];
+/**
+ * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
+ */
+static void restore_ELCR(char *trigger)
+{
+	outb(trigger[0], 0x4d0);
+	outb(trigger[1], 0x4d1);
+}
+
+static void save_ELCR(char *trigger)
+{
+	/* IRQ 0,1,2,8,13 are marked as reserved */
+	trigger[0] = inb(0x4d0) & 0xF8;
+	trigger[1] = inb(0x4d1) & 0xDE;
+}
+
+static int i8259A_resume(struct sys_device *dev)
+{
+	init_8259A(i8259A_auto_eoi);
+	restore_ELCR(irq_trigger);
+	return 0;
+}
+
+static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
+{
+	save_ELCR(irq_trigger);
+	return 0;
+}
+
+static int i8259A_shutdown(struct sys_device *dev)
+{
+	/* Put the i8259A into a quiescent state that
+	 * the kernel initialization code can get it
+	 * out of.
+	 */
+	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
+	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-1 */
+	return 0;
+}
+
+static struct sysdev_class i8259_sysdev_class = {
+	.name = "i8259",
+	.suspend = i8259A_suspend,
+	.resume = i8259A_resume,
+	.shutdown = i8259A_shutdown,
+};
+
+static struct sys_device device_i8259A = {
+	.id	= 0,
+	.cls	= &i8259_sysdev_class,
+};
+
+static int __init i8259A_init_sysfs(void)
+{
+	int error = sysdev_class_register(&i8259_sysdev_class);
+	if (!error)
+		error = sysdev_register(&device_i8259A);
+	return error;
+}
+
+device_initcall(i8259A_init_sysfs);
+
+void init_8259A(int auto_eoi)
+{
+	unsigned long flags;
+
+	i8259A_auto_eoi = auto_eoi;
+
+	spin_lock_irqsave(&i8259A_lock, flags);
+
+	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
+	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
+
+	/*
+	 * outb_pic - this has to work on a wide range of PC hardware.
+	 */
+	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
+#ifndef CONFIG_X86_64
+	outb_pic(0x20 + 0, PIC_MASTER_IMR);	/* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
+	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);	/* 8259A-1 (the master) has a slave on IR2 */
+#else /* CONFIG_X86_64 */
+	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
+	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+	/* 8259A-1 (the master) has a slave on IR2 */
+	outb_pic(0x04, PIC_MASTER_IMR);
+#endif /* CONFIG_X86_64 */
+	if (auto_eoi)	/* master does Auto EOI */
+		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
+	else		/* master expects normal EOI */
+		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
+
+	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
+#ifndef CONFIG_X86_64
+	outb_pic(0x20 + 8, PIC_SLAVE_IMR);	/* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
+	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);	/* 8259A-2 is a slave on master's IR2 */
+	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
+#else /* CONFIG_X86_64 */
+	/* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
+	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+	/* 8259A-2 is a slave on master's IR2 */
+	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
+	/* (slave's support for AEOI in flat mode is to be investigated) */
+	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
+
+#endif /* CONFIG_X86_64 */
+	if (auto_eoi)
+		/*
+		 * In AEOI mode we just have to mask the interrupt
+		 * when acking.
+		 */
+		i8259A_chip.mask_ack = disable_8259A_irq;
+	else
+		i8259A_chip.mask_ack = mask_and_ack_8259A;
+
+	udelay(100);		/* wait for 8259A to initialize */
+
+	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
+	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
+
+	spin_unlock_irqrestore(&i8259A_lock, flags);
+}
diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c
index fe631967d625..d66914287ee1 100644
--- a/arch/x86/kernel/i8259_32.c
+++ b/arch/x86/kernel/i8259_32.c
@@ -21,302 +21,7 @@
 #include <asm/arch_hooks.h>
 #include <asm/i8259.h>
 
-/*
- * This is the 'legacy' 8259A Programmable Interrupt Controller,
- * present in the majority of PC/AT boxes.
- * plus some generic x86 specific things if generic specifics makes
- * any sense at all.
- */
-
-static int i8259A_auto_eoi;
-DEFINE_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-
-static struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
-
-/*
- * 8259A PIC functions to handle ISA devices:
- */
-
-/*
- * This contains the irq mask for both 8259A irq controllers,
- */
-unsigned int cached_irq_mask = 0xffff;
-
-/*
- * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
- * boards the timer interrupt is not really connected to any IO-APIC pin,
- * it's fed to the master 8259A's IR0 line only.
- *
- * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
- * this 'mixed mode' IRQ handling costs nothing because it's only used
- * at IRQ setup time.
- */
-unsigned long io_apic_irqs;
-
-void disable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask |= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-void enable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = ~(1 << irq);
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask &= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-int i8259A_irq_pending(unsigned int irq)
-{
-	unsigned int mask = 1<<irq;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	if (irq < 8)
-		ret = inb(PIC_MASTER_CMD) & mask;
-	else
-		ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-
-	return ret;
-}
-
-void make_8259A_irq(unsigned int irq)
-{
-	disable_irq_nosync(irq);
-	io_apic_irqs &= ~(1<<irq);
-	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
-	enable_irq(irq);
-}
-
-/*
- * This function assumes to be called rarely. Switching between
- * 8259A registers is slow.
- * This has to be protected by the irq controller spinlock
- * before being called.
- */
-static inline int i8259A_irq_real(unsigned int irq)
-{
-	int value;
-	int irqmask = 1<<irq;
-
-	if (irq < 8) {
-		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
-		value = inb(PIC_MASTER_CMD) & irqmask;
-		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
-		return value;
-	}
-	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
-	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
-	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
-	return value;
-}
-
-/*
- * Careful! The 8259A is a fragile beast, it pretty
- * much _has_ to be done exactly like this (mask it
- * first, _then_ send the EOI, and the order of EOI
- * to the two 8259s is important!
- */
-static void mask_and_ack_8259A(unsigned int irq)
-{
-	unsigned int irqmask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	/*
-	 * Lightweight spurious IRQ detection. We do not want
-	 * to overdo spurious IRQ handling - it's usually a sign
-	 * of hardware problems, so we only do the checks we can
-	 * do without slowing down good hardware unnecessarily.
-	 *
-	 * Note that IRQ7 and IRQ15 (the two spurious IRQs
-	 * usually resulting from the 8259A-1|2 PICs) occur
-	 * even if the IRQ is masked in the 8259A. Thus we
-	 * can check spurious 8259A IRQs without doing the
-	 * quite slow i8259A_irq_real() call for every IRQ.
-	 * This does not cover 100% of spurious interrupts,
-	 * but should be enough to warn the user that there
-	 * is something bad going on ...
-	 */
-	if (cached_irq_mask & irqmask)
-		goto spurious_8259A_irq;
-	cached_irq_mask |= irqmask;
 
-handle_real_irq:
-	if (irq & 8) {
-		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
-	} else {
-		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_master_mask, PIC_MASTER_IMR);
-		outb(0x60+irq,PIC_MASTER_CMD);	/* 'Specific EOI to master */
-	}
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-	return;
-
-spurious_8259A_irq:
-	/*
-	 * this is the slow path - should happen rarely.
-	 */
-	if (i8259A_irq_real(irq))
-		/*
-		 * oops, the IRQ _is_ in service according to the
-		 * 8259A - not spurious, go handle it.
-		 */
-		goto handle_real_irq;
-
-	{
-		static int spurious_irq_mask;
-		/*
-		 * At this point we can be sure the IRQ is spurious,
-		 * lets ACK and report it. [once per IRQ]
-		 */
-		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
-			spurious_irq_mask |= irqmask;
-		}
-		atomic_inc(&irq_err_count);
-		/*
-		 * Theoretically we do not have to handle this IRQ,
-		 * but in Linux this does not cause problems and is
-		 * simpler for us.
-		 */
-		goto handle_real_irq;
-	}
-}
-
-static char irq_trigger[2];
-/**
- * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
- */
-static void restore_ELCR(char *trigger)
-{
-	outb(trigger[0], 0x4d0);
-	outb(trigger[1], 0x4d1);
-}
-
-static void save_ELCR(char *trigger)
-{
-	/* IRQ 0,1,2,8,13 are marked as reserved */
-	trigger[0] = inb(0x4d0) & 0xF8;
-	trigger[1] = inb(0x4d1) & 0xDE;
-}
-
-static int i8259A_resume(struct sys_device *dev)
-{
-	init_8259A(i8259A_auto_eoi);
-	restore_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
-{
-	save_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_shutdown(struct sys_device *dev)
-{
-	/* Put the i8259A into a quiescent state that
-	 * the kernel initialization code can get it
-	 * out of.
-	 */
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-1 */
-	return 0;
-}
-
-static struct sysdev_class i8259_sysdev_class = {
-	.name = "i8259",
-	.suspend = i8259A_suspend,
-	.resume = i8259A_resume,
-	.shutdown = i8259A_shutdown,
-};
-
-static struct sys_device device_i8259A = {
-	.id	= 0,
-	.cls	= &i8259_sysdev_class,
-};
-
-static int __init i8259A_init_sysfs(void)
-{
-	int error = sysdev_class_register(&i8259_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_i8259A);
-	return error;
-}
-
-device_initcall(i8259A_init_sysfs);
-
-void init_8259A(int auto_eoi)
-{
-	unsigned long flags;
-
-	i8259A_auto_eoi = auto_eoi;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
-
-	/*
-	 * outb_pic - this has to work on a wide range of PC hardware.
-	 */
-	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
-	outb_pic(0x20 + 0, PIC_MASTER_IMR);	/* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
-	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);	/* 8259A-1 (the master) has a slave on IR2 */
-	if (auto_eoi)	/* master does Auto EOI */
-		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
-	else		/* master expects normal EOI */
-		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
-
-	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
-	outb_pic(0x20 + 8, PIC_SLAVE_IMR);	/* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
-	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);	/* 8259A-2 is a slave on master's IR2 */
-	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
-	if (auto_eoi)
-		/*
-		 * In AEOI mode we just have to mask the interrupt
-		 * when acking.
-		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
-	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
-
-	udelay(100);		/* wait for 8259A to initialize */
-
-	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
-	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
-
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
 
 /*
  * Note that on a 486, we don't want to do a SIGFPE on an irq13
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
index fa57a1568508..a95d2bd27e9d 100644
--- a/arch/x86/kernel/i8259_64.c
+++ b/arch/x86/kernel/i8259_64.c
@@ -87,315 +87,6 @@ static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) =
 #undef IRQ
 #undef IRQLIST_16
 
-/*
- * This is the 'legacy' 8259A Programmable Interrupt Controller,
- * present in the majority of PC/AT boxes.
- * plus some generic x86 specific things if generic specifics makes
- * any sense at all.
- * this file should become arch/i386/kernel/irq.c when the old irq.c
- * moves to arch independent land
- */
-
-static int i8259A_auto_eoi;
-DEFINE_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-
-static struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
-
-/*
- * 8259A PIC functions to handle ISA devices:
- */
-
-/*
- * This contains the irq mask for both 8259A irq controllers,
- */
-unsigned int cached_irq_mask = 0xffff;
-
-/*
- * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
- * boards the timer interrupt is not really connected to any IO-APIC pin,
- * it's fed to the master 8259A's IR0 line only.
- *
- * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
- * this 'mixed mode' IRQ handling costs nothing because it's only used
- * at IRQ setup time.
- */
-unsigned long io_apic_irqs;
-
-void disable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask |= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-void enable_8259A_irq(unsigned int irq)
-{
-	unsigned int mask = ~(1 << irq);
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	cached_irq_mask &= mask;
-	if (irq & 8)
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-	else
-		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-int i8259A_irq_pending(unsigned int irq)
-{
-	unsigned int mask = 1<<irq;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	if (irq < 8)
-		ret = inb(PIC_MASTER_CMD) & mask;
-	else
-		ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-
-	return ret;
-}
-
-void make_8259A_irq(unsigned int irq)
-{
-	disable_irq_nosync(irq);
-	io_apic_irqs &= ~(1<<irq);
-	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
-	enable_irq(irq);
-}
-
-/*
- * This function assumes to be called rarely. Switching between
- * 8259A registers is slow.
- * This has to be protected by the irq controller spinlock
- * before being called.
- */
-static inline int i8259A_irq_real(unsigned int irq)
-{
-	int value;
-	int irqmask = 1<<irq;
-
-	if (irq < 8) {
-		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
-		value = inb(PIC_MASTER_CMD) & irqmask;
-		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
-		return value;
-	}
-	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
-	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
-	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
-	return value;
-}
-
-/*
- * Careful! The 8259A is a fragile beast, it pretty
- * much _has_ to be done exactly like this (mask it
- * first, _then_ send the EOI, and the order of EOI
- * to the two 8259s is important!
- */
-static void mask_and_ack_8259A(unsigned int irq)
-{
-	unsigned int irqmask = 1 << irq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-	/*
-	 * Lightweight spurious IRQ detection. We do not want
-	 * to overdo spurious IRQ handling - it's usually a sign
-	 * of hardware problems, so we only do the checks we can
-	 * do without slowing down good hardware unnecessarily.
-	 *
-	 * Note that IRQ7 and IRQ15 (the two spurious IRQs
-	 * usually resulting from the 8259A-1|2 PICs) occur
-	 * even if the IRQ is masked in the 8259A. Thus we
-	 * can check spurious 8259A IRQs without doing the
-	 * quite slow i8259A_irq_real() call for every IRQ.
-	 * This does not cover 100% of spurious interrupts,
-	 * but should be enough to warn the user that there
-	 * is something bad going on ...
-	 */
-	if (cached_irq_mask & irqmask)
-		goto spurious_8259A_irq;
-	cached_irq_mask |= irqmask;
-
-handle_real_irq:
-	if (irq & 8) {
-		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_slave_mask, PIC_SLAVE_IMR);
-		/* 'Specific EOI' to slave */
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);
-		 /* 'Specific EOI' to master-IRQ2 */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD);
-	} else {
-		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
-		outb(cached_master_mask, PIC_MASTER_IMR);
-		/* 'Specific EOI' to master */
-		outb(0x60+irq,PIC_MASTER_CMD);
-	}
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-	return;
-
-spurious_8259A_irq:
-	/*
-	 * this is the slow path - should happen rarely.
-	 */
-	if (i8259A_irq_real(irq))
-		/*
-		 * oops, the IRQ _is_ in service according to the
-		 * 8259A - not spurious, go handle it.
-		 */
-		goto handle_real_irq;
-
-	{
-		static int spurious_irq_mask;
-		/*
-		 * At this point we can be sure the IRQ is spurious,
-		 * lets ACK and report it. [once per IRQ]
-		 */
-		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
-			       "spurious 8259A interrupt: IRQ%d.\n", irq);
-			spurious_irq_mask |= irqmask;
-		}
-		atomic_inc(&irq_err_count);
-		/*
-		 * Theoretically we do not have to handle this IRQ,
-		 * but in Linux this does not cause problems and is
-		 * simpler for us.
-		 */
-		goto handle_real_irq;
-	}
-}
-
-static char irq_trigger[2];
-/**
- * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
- */
-static void restore_ELCR(char *trigger)
-{
-	outb(trigger[0], 0x4d0);
-	outb(trigger[1], 0x4d1);
-}
-
-static void save_ELCR(char *trigger)
-{
-	/* IRQ 0,1,2,8,13 are marked as reserved */
-	trigger[0] = inb(0x4d0) & 0xF8;
-	trigger[1] = inb(0x4d1) & 0xDE;
-}
-
-static int i8259A_resume(struct sys_device *dev)
-{
-	init_8259A(i8259A_auto_eoi);
-	restore_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
-{
-	save_ELCR(irq_trigger);
-	return 0;
-}
-
-static int i8259A_shutdown(struct sys_device *dev)
-{
-	/* Put the i8259A into a quiescent state that
-	 * the kernel initialization code can get it
-	 * out of.
-	 */
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-1 */
-	return 0;
-}
-
-static struct sysdev_class i8259_sysdev_class = {
-	.name = "i8259",
-	.suspend = i8259A_suspend,
-	.resume = i8259A_resume,
-	.shutdown = i8259A_shutdown,
-};
-
-static struct sys_device device_i8259A = {
-	.id	= 0,
-	.cls	= &i8259_sysdev_class,
-};
-
-static int __init i8259A_init_sysfs(void)
-{
-	int error = sysdev_class_register(&i8259_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_i8259A);
-	return error;
-}
-
-device_initcall(i8259A_init_sysfs);
-
-void init_8259A(int auto_eoi)
-{
-	unsigned long flags;
-
-	i8259A_auto_eoi = auto_eoi;
-
-	spin_lock_irqsave(&i8259A_lock, flags);
-
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
-	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
-
-	/*
-	 * outb_pic - this has to work on a wide range of PC hardware.
-	 */
-	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
-	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
-	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
-	/* 8259A-1 (the master) has a slave on IR2 */
-	outb_pic(0x04, PIC_MASTER_IMR);
-	if (auto_eoi)	/* master does Auto EOI */
-		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
-	else		/* master expects normal EOI */
-		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
-
-	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
-	/* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
-	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
-	/* 8259A-2 is a slave on master's IR2 */
-	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
-	/* (slave's support for AEOI in flat mode is to be investigated) */
-	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
-
-	if (auto_eoi)
-		/*
-		 * In AEOI mode we just have to mask the interrupt
-		 * when acking.
-		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
-	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
-
-	udelay(100);		/* wait for 8259A to initialize */
-
-	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
-	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
-
-	spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
 
 
 
-- 
cgit v1.2.2


From 6b4d3afbe722ee71b8da346c2c4393938440c471 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Wed, 21 May 2008 11:47:24 +0200
Subject: x86: i8259.c: remove #ifdefs around includes

Remove #ifdefs around includes; including too much should be always
safe.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: macro@ds2.pg.gda.pl
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/i8259.c | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 2decba6b0101..8b7eb0cb2e7e 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -1,14 +1,10 @@
-#ifdef CONFIG_X86_64
 #include <linux/linkage.h>
-#endif /* CONFIG_X86_64 */
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
-#ifdef CONFIG_X86_64
 #include <linux/timex.h>
-#endif /* CONFIG_X86_64 */
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/init.h>
@@ -16,24 +12,17 @@
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
 
-#ifdef CONFIG_X86_64
 #include <asm/acpi.h>
-#endif /* CONFIG_X86_64 */
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/io.h>
-#ifndef CONFIG_X86_64
 #include <asm/timer.h>
-#else /* CONFIG_X86_64 */
 #include <asm/hw_irq.h>
-#endif /* CONFIG_X86_64 */
 #include <asm/pgtable.h>
 #include <asm/delay.h>
 #include <asm/desc.h>
 #include <asm/apic.h>
-#ifndef CONFIG_X86_64
 #include <asm/arch_hooks.h>
-#endif /* ! CONFIG_X86_64 */
 #include <asm/i8259.h>
 
 /*
-- 
cgit v1.2.2


From 4f6f3bac18c80ff6cf072d90796755c69cc4c748 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Wed, 21 May 2008 11:52:52 +0200
Subject: x86: i8259.c: remove trivial ifdefs

Remove #ifdefs where the only difference is formatting of comments.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: macro@ds2.pg.gda.pl
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/i8259.c | 20 +++-----------------
 1 file changed, 3 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 8b7eb0cb2e7e..433e49edfd4f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -175,24 +175,14 @@ handle_real_irq:
 	if (irq & 8) {
 		inb(PIC_SLAVE_IMR);	/* DUMMY - (do we need this?) */
 		outb(cached_slave_mask, PIC_SLAVE_IMR);
-#ifndef CONFIG_X86_64
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
-#else /* CONFIG_X86_64 */
 		/* 'Specific EOI' to slave */
-		outb(0x60+(irq&7),PIC_SLAVE_CMD);
+		outb(0x60+(irq&7), PIC_SLAVE_CMD);
 		 /* 'Specific EOI' to master-IRQ2 */
-		outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD);
-#endif /* CONFIG_X86_64 */
+		outb(0x60+PIC_CASCADE_IR, PIC_MASTER_CMD);
 	} else {
 		inb(PIC_MASTER_IMR);	/* DUMMY - (do we need this?) */
 		outb(cached_master_mask, PIC_MASTER_IMR);
-#ifndef CONFIG_X86_64
-		outb(0x60+irq,PIC_MASTER_CMD);	/* 'Specific EOI to master */
-#else /* CONFIG_X86_64 */
-		/* 'Specific EOI' to master */
-		outb(0x60+irq,PIC_MASTER_CMD);
-#endif /* CONFIG_X86_64 */
+		outb(0x60+irq, PIC_MASTER_CMD);	/* 'Specific EOI to master */
 	}
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 	return;
@@ -215,12 +205,8 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-#ifndef CONFIG_X86_64
-			printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
-#else /* CONFIG_X86_64 */
 			printk(KERN_DEBUG
 			       "spurious 8259A interrupt: IRQ%d.\n", irq);
-#endif /* CONFIG_X86_64 */
 			spurious_irq_mask |= irqmask;
 		}
 		atomic_inc(&irq_err_count);
-- 
cgit v1.2.2


From 4d9a6e6128dd8ada0d2feed2a9bb6506043e4655 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Wed, 21 May 2008 11:57:52 +0200
Subject: x86: i8259: cleanup codingstyle

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: macro@ds2.pg.gda.pl
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/i8259.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 433e49edfd4f..7a0fda8f01b5 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -129,14 +129,14 @@ static inline int i8259A_irq_real(unsigned int irq)
 	int irqmask = 1<<irq;
 
 	if (irq < 8) {
-		outb(0x0B,PIC_MASTER_CMD);	/* ISR register */
+		outb(0x0B, PIC_MASTER_CMD);	/* ISR register */
 		value = inb(PIC_MASTER_CMD) & irqmask;
-		outb(0x0A,PIC_MASTER_CMD);	/* back to the IRR register */
+		outb(0x0A, PIC_MASTER_CMD);	/* back to the IRR register */
 		return value;
 	}
-	outb(0x0B,PIC_SLAVE_CMD);	/* ISR register */
+	outb(0x0B, PIC_SLAVE_CMD);	/* ISR register */
 	value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
-	outb(0x0A,PIC_SLAVE_CMD);	/* back to the IRR register */
+	outb(0x0A, PIC_SLAVE_CMD);	/* back to the IRR register */
 	return value;
 }
 
-- 
cgit v1.2.2


From f20b11e716936f85850654c49e06a1f955b9e5fc Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 24 May 2008 15:59:58 +0200
Subject: x86: rename the i8259_32/64.c leftovers to initirq_32/64.c

The leftovers of the i8259 unification have nothing to do with i8259
at all. They contain interrupt init code and the i8259_xx name is just
misleading now.

Rename them to initirq_32/64.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/Makefile     |   2 +-
 arch/x86/kernel/i8259_32.c   | 114 ------------------------
 arch/x86/kernel/i8259_64.c   | 203 -------------------------------------------
 arch/x86/kernel/irqinit_32.c | 114 ++++++++++++++++++++++++
 arch/x86/kernel/irqinit_64.c | 203 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 318 insertions(+), 318 deletions(-)
 delete mode 100644 arch/x86/kernel/i8259_32.c
 delete mode 100644 arch/x86/kernel/i8259_64.c
 create mode 100644 arch/x86/kernel/irqinit_32.c
 create mode 100644 arch/x86/kernel/irqinit_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f71a76ef2596..2a53ad2cb450 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -18,7 +18,7 @@ CFLAGS_tsc_64.o		:= $(nostackp)
 obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
 obj-y			+= traps_$(BITS).o irq_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o
-obj-y			+= setup_$(BITS).o i8259.o i8259_$(BITS).o setup.o
+obj-y			+= setup_$(BITS).o i8259.o irqinit_$(BITS).o setup.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c
deleted file mode 100644
index d66914287ee1..000000000000
--- a/arch/x86/kernel/i8259_32.c
+++ /dev/null
@@ -1,114 +0,0 @@
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/timer.h>
-#include <asm/pgtable.h>
-#include <asm/delay.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/arch_hooks.h>
-#include <asm/i8259.h>
-
-
-
-/*
- * Note that on a 486, we don't want to do a SIGFPE on an irq13
- * as the irq is unreliable, and exception 16 works correctly
- * (ie as explained in the intel literature). On a 386, you
- * can't use exception 16 due to bad IBM design, so we have to
- * rely on the less exact irq13.
- *
- * Careful.. Not only is IRQ13 unreliable, but it is also
- * leads to races. IBM designers who came up with it should
- * be shot.
- */
- 
-
-static irqreturn_t math_error_irq(int cpl, void *dev_id)
-{
-	extern void math_error(void __user *);
-	outb(0,0xF0);
-	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
-		return IRQ_NONE;
-	math_error((void __user *)get_irq_regs()->ip);
-	return IRQ_HANDLED;
-}
-
-/*
- * New motherboards sometimes make IRQ 13 be a PCI interrupt,
- * so allow interrupt sharing.
- */
-static struct irqaction fpu_irq = {
-	.handler = math_error_irq,
-	.mask = CPU_MASK_NONE,
-	.name = "fpu",
-};
-
-void __init init_ISA_irqs (void)
-{
-	int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	init_bsp_APIC();
-#endif
-	init_8259A(0);
-
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < 16; i++) {
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
-}
-
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	/* all the set up before the call gates are initialised */
-	pre_intr_init_hook();
-
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (i >= NR_IRQS)
-			break;
-		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (!test_bit(vector, used_vectors))
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-	/* setup after call gates are initialised (usually add in
-	 * the architecture specific gates)
-	 */
-	intr_init_hook();
-
-	/*
-	 * External FPU? Set up irq13 if so, for
-	 * original braindamaged IBM FERR coupling.
-	 */
-	if (boot_cpu_data.hard_math && !cpu_has_fpu)
-		setup_irq(FPU_IRQ, &fpu_irq);
-
-	irq_ctx_init(smp_processor_id());
-}
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
deleted file mode 100644
index a95d2bd27e9d..000000000000
--- a/arch/x86/kernel/i8259_64.c
+++ /dev/null
@@ -1,203 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-
-#include <asm/acpi.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/delay.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * Common place to define all x86 IRQ vectors
- *
- * This builds up the IRQ handler stubs using some ugly macros in irq.h
- *
- * These macros create the low-level assembly IRQ routines that save
- * register context and call do_IRQ(). do_IRQ() then does all the
- * operations that are needed to keep the AT (or SMP IOAPIC)
- * interrupt-controller happy.
- */
-
-#define BI(x,y) \
-	BUILD_IRQ(x##y)
-
-#define BUILD_16_IRQS(x) \
-	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
-	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
-	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
-	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-				      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
-BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
-BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
-BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
-
-#undef BUILD_16_IRQS
-#undef BI
-
-
-#define IRQ(x,y) \
-	IRQ##x##y##_interrupt
-
-#define IRQLIST_16(x) \
-	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
-	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
-	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
-	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
-
-/* for the irq vectors */
-static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
-					  IRQLIST_16(0x2), IRQLIST_16(0x3),
-	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
-	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
-	IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
-};
-
-#undef IRQ
-#undef IRQLIST_16
-
-
-
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-void __init init_ISA_irqs (void)
-{
-	int i;
-
-	init_bsp_APIC();
-	init_8259A(0);
-
-	for (i = 0; i < NR_IRQS; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = NULL;
-		irq_desc[i].depth = 1;
-
-		if (i < 16) {
-			/*
-			 * 16 old-style INTA-cycle interrupts:
-			 */
-			set_irq_chip_and_handler_name(i, &i8259A_chip,
-						      handle_level_irq, "XT");
-		} else {
-			/*
-			 * 'high' PCI IRQs filled in on demand
-			 */
-			irq_desc[i].chip = &no_irq_chip;
-		}
-	}
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	init_ISA_irqs();
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (vector != IA32_SYSCALL_VECTOR)
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-#ifdef CONFIG_SMP
-	/*
-	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-	 * IPI, driven by wakeup.
-	 */
-	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
-	/* IPIs for invalidation */
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
-	/* IPI for generic function call */
-	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
-	/* Low priority IPI to cleanup after moving an irq */
-	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-#endif
-	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
-	/* self generated IPI for local APIC timer */
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
-	/* IPI vectors for APIC spurious and error interrupts */
-	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-}
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
new file mode 100644
index 000000000000..d66914287ee1
--- /dev/null
+++ b/arch/x86/kernel/irqinit_32.c
@@ -0,0 +1,114 @@
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/timer.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/arch_hooks.h>
+#include <asm/i8259.h>
+
+
+
+/*
+ * Note that on a 486, we don't want to do a SIGFPE on an irq13
+ * as the irq is unreliable, and exception 16 works correctly
+ * (ie as explained in the intel literature). On a 386, you
+ * can't use exception 16 due to bad IBM design, so we have to
+ * rely on the less exact irq13.
+ *
+ * Careful.. Not only is IRQ13 unreliable, but it is also
+ * leads to races. IBM designers who came up with it should
+ * be shot.
+ */
+ 
+
+static irqreturn_t math_error_irq(int cpl, void *dev_id)
+{
+	extern void math_error(void __user *);
+	outb(0,0xF0);
+	if (ignore_fpu_irq || !boot_cpu_data.hard_math)
+		return IRQ_NONE;
+	math_error((void __user *)get_irq_regs()->ip);
+	return IRQ_HANDLED;
+}
+
+/*
+ * New motherboards sometimes make IRQ 13 be a PCI interrupt,
+ * so allow interrupt sharing.
+ */
+static struct irqaction fpu_irq = {
+	.handler = math_error_irq,
+	.mask = CPU_MASK_NONE,
+	.name = "fpu",
+};
+
+void __init init_ISA_irqs (void)
+{
+	int i;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	init_bsp_APIC();
+#endif
+	init_8259A(0);
+
+	/*
+	 * 16 old-style INTA-cycle interrupts:
+	 */
+	for (i = 0; i < 16; i++) {
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
+					      handle_level_irq, "XT");
+	}
+}
+
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	/* all the set up before the call gates are initialised */
+	pre_intr_init_hook();
+
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+		int vector = FIRST_EXTERNAL_VECTOR + i;
+		if (i >= NR_IRQS)
+			break;
+		/* SYSCALL_VECTOR was reserved in trap_init. */
+		if (!test_bit(vector, used_vectors))
+			set_intr_gate(vector, interrupt[i]);
+	}
+
+	/* setup after call gates are initialised (usually add in
+	 * the architecture specific gates)
+	 */
+	intr_init_hook();
+
+	/*
+	 * External FPU? Set up irq13 if so, for
+	 * original braindamaged IBM FERR coupling.
+	 */
+	if (boot_cpu_data.hard_math && !cpu_has_fpu)
+		setup_irq(FPU_IRQ, &fpu_irq);
+
+	irq_ctx_init(smp_processor_id());
+}
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
new file mode 100644
index 000000000000..a95d2bd27e9d
--- /dev/null
+++ b/arch/x86/kernel/irqinit_64.c
@@ -0,0 +1,203 @@
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/acpi.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+
+/*
+ * Common place to define all x86 IRQ vectors
+ *
+ * This builds up the IRQ handler stubs using some ugly macros in irq.h
+ *
+ * These macros create the low-level assembly IRQ routines that save
+ * register context and call do_IRQ(). do_IRQ() then does all the
+ * operations that are needed to keep the AT (or SMP IOAPIC)
+ * interrupt-controller happy.
+ */
+
+#define BI(x,y) \
+	BUILD_IRQ(x##y)
+
+#define BUILD_16_IRQS(x) \
+	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
+	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
+	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
+	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
+
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+				      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
+BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
+BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
+BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
+
+#undef BUILD_16_IRQS
+#undef BI
+
+
+#define IRQ(x,y) \
+	IRQ##x##y##_interrupt
+
+#define IRQLIST_16(x) \
+	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
+	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
+	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
+	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
+
+/* for the irq vectors */
+static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
+					  IRQLIST_16(0x2), IRQLIST_16(0x3),
+	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
+	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
+	IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
+};
+
+#undef IRQ
+#undef IRQLIST_16
+
+
+
+
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
+DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+	[0 ... IRQ0_VECTOR - 1] = -1,
+	[IRQ0_VECTOR] = 0,
+	[IRQ1_VECTOR] = 1,
+	[IRQ2_VECTOR] = 2,
+	[IRQ3_VECTOR] = 3,
+	[IRQ4_VECTOR] = 4,
+	[IRQ5_VECTOR] = 5,
+	[IRQ6_VECTOR] = 6,
+	[IRQ7_VECTOR] = 7,
+	[IRQ8_VECTOR] = 8,
+	[IRQ9_VECTOR] = 9,
+	[IRQ10_VECTOR] = 10,
+	[IRQ11_VECTOR] = 11,
+	[IRQ12_VECTOR] = 12,
+	[IRQ13_VECTOR] = 13,
+	[IRQ14_VECTOR] = 14,
+	[IRQ15_VECTOR] = 15,
+	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
+void __init init_ISA_irqs (void)
+{
+	int i;
+
+	init_bsp_APIC();
+	init_8259A(0);
+
+	for (i = 0; i < NR_IRQS; i++) {
+		irq_desc[i].status = IRQ_DISABLED;
+		irq_desc[i].action = NULL;
+		irq_desc[i].depth = 1;
+
+		if (i < 16) {
+			/*
+			 * 16 old-style INTA-cycle interrupts:
+			 */
+			set_irq_chip_and_handler_name(i, &i8259A_chip,
+						      handle_level_irq, "XT");
+		} else {
+			/*
+			 * 'high' PCI IRQs filled in on demand
+			 */
+			irq_desc[i].chip = &no_irq_chip;
+		}
+	}
+}
+
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	init_ISA_irqs();
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+		int vector = FIRST_EXTERNAL_VECTOR + i;
+		if (vector != IA32_SYSCALL_VECTOR)
+			set_intr_gate(vector, interrupt[i]);
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
+	 * IPI, driven by wakeup.
+	 */
+	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+
+	/* IPIs for invalidation */
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+	set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+
+	/* IPI for generic function call */
+	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+	/* Low priority IPI to cleanup after moving an irq */
+	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
+#endif
+	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+
+	/* self generated IPI for local APIC timer */
+	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+
+	/* IPI vectors for APIC spurious and error interrupts */
+	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+	if (!acpi_ioapic)
+		setup_irq(2, &irq2);
+}
-- 
cgit v1.2.2


From fce39665abb71d01d74ac74eb13dd69a799dfc2f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:36 +0200
Subject: x86: make init_ISA_irqs() static

Moved to i8259 branch to avoid conflicts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/irqinit_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index a95d2bd27e9d..64bc0f14285f 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -120,7 +120,7 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
 	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
 };
 
-void __init init_ISA_irqs (void)
+static void __init init_ISA_irqs (void)
 {
 	int i;
 
-- 
cgit v1.2.2


From 63687a528c39a67c1a213cdffa09feb0e6af9dbe Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:44:41 +0200
Subject: x86: move tracedata to RODATA

.. allowing it to be write-protected just as other read-only data
under CONFIG_DEBUG_RODATA.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/vmlinux_32.lds.S | 7 -------
 arch/x86/kernel/vmlinux_64.lds.S | 7 -------
 2 files changed, 14 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index ce5ed083a1e9..2674f5796275 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -60,13 +60,6 @@ SECTIONS
 
   BUG_TABLE :text
 
-  . = ALIGN(4);
-  .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
-  	__tracedata_start = .;
-	*(.tracedata)
-  	__tracedata_end = .;
-  }
-
   RODATA
 
   /* writeable */
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index fad3674b06a5..687041bfbae5 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -53,13 +53,6 @@ SECTIONS
 
   RODATA
 
-  . = ALIGN(4);
-  .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
-  	__tracedata_start = .;
-	*(.tracedata)
-  	__tracedata_end = .;
-  }
-
   . = ALIGN(PAGE_SIZE);		/* Align data segment to page size boundary */
 				/* Data */
   .data : AT(ADDR(.data) - LOAD_OFFSET) {
-- 
cgit v1.2.2


From a2eddfa95919a730e0e5ed17e9c303fe5ba249cd Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:44:41 +0200
Subject: x86: make /proc/stat account for all interrupts

LAPIC interrupts, which don't go through the generic interrupt handling
code, aren't accounted for in /proc/stat. Hence this patch adds a
mechanism architectures can use to accordingly adjust the statistics.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/irq_32.c | 38 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/irq_64.c | 28 ++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 147352df28b9..468acd04aa2e 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -313,16 +313,20 @@ skip:
 				per_cpu(irq_stat,j).irq_tlb_count);
 		seq_printf(p, "  TLB shootdowns\n");
 #endif
+#ifdef CONFIG_X86_MCE
 		seq_printf(p, "TRM: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).irq_thermal_count);
 		seq_printf(p, "  Thermal event interrupts\n");
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
 		seq_printf(p, "SPU: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).irq_spurious_count);
 		seq_printf(p, "  Spurious interrupts\n");
+#endif
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 		seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
@@ -331,6 +335,40 @@ skip:
 	return 0;
 }
 
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+	u64 sum = nmi_count(cpu);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+	sum += per_cpu(irq_stat, cpu).irq_resched_count;
+	sum += per_cpu(irq_stat, cpu).irq_call_count;
+	sum += per_cpu(irq_stat, cpu).irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	sum += per_cpu(irq_stat, cpu).irq_thermal_count;
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+	sum += per_cpu(irq_stat, cpu).irq_spurious_count;
+#endif
+	return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+	u64 sum = atomic_read(&irq_err_count);
+
+#ifdef CONFIG_X86_IO_APIC
+	sum += atomic_read(&irq_mis_count);
+#endif
+	return sum;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <mach_apic.h>
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 3aac15466a91..1f78b238d8d2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -135,6 +135,7 @@ skip:
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
 		seq_printf(p, "  TLB shootdowns\n");
 #endif
+#ifdef CONFIG_X86_MCE
 		seq_printf(p, "TRM: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
@@ -143,6 +144,7 @@ skip:
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
 		seq_printf(p, "  Threshold APIC interrupts\n");
+#endif
 		seq_printf(p, "SPU: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
@@ -152,6 +154,32 @@ skip:
 	return 0;
 }
 
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+	u64 sum = cpu_pda(cpu)->__nmi_count;
+
+	sum += cpu_pda(cpu)->apic_timer_irqs;
+#ifdef CONFIG_SMP
+	sum += cpu_pda(cpu)->irq_resched_count;
+	sum += cpu_pda(cpu)->irq_call_count;
+	sum += cpu_pda(cpu)->irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	sum += cpu_pda(cpu)->irq_thermal_count;
+	sum += cpu_pda(cpu)->irq_threshold_count;
+#endif
+	sum += cpu_pda(cpu)->irq_spurious_count;
+	return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+	return atomic_read(&irq_err_count);
+}
+
 /*
  * do_IRQ handles all normal device IRQ's (the special
  * SMP cross-CPU interrupts have their own specific
-- 
cgit v1.2.2


From c2c14fb7afcc67b48724571506e095fccc65a670 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:36 +0200
Subject: x86: tsc_64.c make constant UL

arch/x86/kernel/tsc_64.c:245:13: warning: constant 0x100000000 is so big it is long

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/tsc_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index fcc16e58609e..c19b0e273ef1 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -242,7 +242,7 @@ void __init tsc_calibrate(void)
 	if (hpet) {
 		printk(KERN_INFO "TSC calibrated against HPET\n");
 		if (hpet2 < hpet1)
-			hpet2 += 0x100000000;
+			hpet2 += 0x100000000UL;
 		hpet2 -= hpet1;
 		tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000;
 	} else {
-- 
cgit v1.2.2


From e6b0edef3453677b13e175a104a83eb36d062dd3 Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Mon, 12 May 2008 15:43:38 +0200
Subject: x86: clean up vdso_enabled type on x86_64

This fixes type of "vdso_enabled" on X86_64 to match extern in asm/elf.h.

Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/vdso/vma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 3fdd51497a83..19a6cfaf5db9 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -16,7 +16,7 @@
 #include "vextern.h"		/* Just for VMAGIC.  */
 #undef VEXTERN
 
-int vdso_enabled = 1;
+unsigned int __read_mostly vdso_enabled = 1;
 
 extern char vdso_start[], vdso_end[];
 extern unsigned short vdso_sync_cpuid;
-- 
cgit v1.2.2


From 46dd98a5c0b907f94742579ab605be1933a37abd Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Wed, 14 May 2008 16:10:39 -0700
Subject: arch/x86/mm/pat.c: use boot_cpu_has()

arch/x86/mm/pat.c: In function 'phys_mem_access_prot_allowed':
arch/x86/mm/pat.c:526: warning: passing argument 2 of 'constant_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:526: warning: passing argument 2 of 'variable_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:527: warning: passing argument 2 of 'constant_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:527: warning: passing argument 2 of 'variable_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:528: warning: passing argument 2 of 'constant_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:528: warning: passing argument 2 of 'variable_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:529: warning: passing argument 2 of 'constant_test_bit' from incompatible pointer type
arch/x86/mm/pat.c:529: warning: passing argument 2 of 'variable_test_bit' from incompatible pointer type

Don't open-code test_bit() on a __u32

Cc: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index a1cbea0b79b1..e83b770676d5 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -536,10 +536,10 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	 * we maintain the tradition of paranoia in this code.
 	 */
 	if (!pat_wc_enabled &&
-	    ! ( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) ||
-		test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) ||
-		test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) ||
-		test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability)) &&
+	    ! ( boot_cpu_has(X86_FEATURE_MTRR) ||
+		boot_cpu_has(X86_FEATURE_K6_MTRR) ||
+		boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
+		boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
 	   (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
 		flags = _PAGE_CACHE_UC;
 	}
-- 
cgit v1.2.2


From eef8f871d84b5df1a24902a4e4700188be1aff2c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:34 +0200
Subject: x86: vsmp_64 add missing includes

sparse mutters:
arch/x86/kernel/vsmp_64.c:126:5: warning: symbol 'is_vsmp_box' was not declared. Should it be static?
arch/x86/kernel/vsmp_64.c:145:13: warning: symbol 'vsmp_init' was not declared. Should it be static?

Include the appropriate headers.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/vsmp_64.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index ba8c0b75ab0a..0c029e8959c7 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -15,9 +15,12 @@
 #include <linux/init.h>
 #include <linux/pci_ids.h>
 #include <linux/pci_regs.h>
+
+#include <asm/apic.h>
 #include <asm/pci-direct.h>
 #include <asm/io.h>
 #include <asm/paravirt.h>
+#include <asm/setup.h>
 
 #if defined CONFIG_PCI && defined CONFIG_PARAVIRT
 /*
-- 
cgit v1.2.2


From 535694f361419ca195fd915dd5038c926334e1be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: boot/printfc use NULL instead 0

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/boot/printf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index c1d00c0274c4..50e47cdbdddd 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -56,7 +56,7 @@ static char *number(char *str, long num, int base, int size, int precision,
 	if (type & LEFT)
 		type &= ~ZEROPAD;
 	if (base < 2 || base > 36)
-		return 0;
+		return NULL;
 	c = (type & ZEROPAD) ? '0' : ' ';
 	sign = 0;
 	if (type & SIGN) {
-- 
cgit v1.2.2


From 0eafe234a2571f51ef9f7e8baddb58c828750771 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: k8topology add missing header

k8_scan_nodes is global and needs a prototype. Add the header file
which contains it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/k8topology_64.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 1f476e477844..48471199887d 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -22,6 +22,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
+#include <asm/k8.h>
 
 static __init int find_northbridge(void)
 {
-- 
cgit v1.2.2


From d34c08958fa36c7a8c3f8d9c0ebe6ec1ab744a68 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: k8topology fix shadow variable

sparse mutters:
arch/x86/mm/k8topology_64.c:108:7: warning: symbol 'nodeid' shadows an earlier one

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/k8topology_64.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 48471199887d..36c6c4a91353 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -76,10 +76,10 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 {
 	unsigned long prevbase;
 	struct bootnode nodes[8];
-	int nodeid, i, nb;
+	int i, nb;
 	unsigned char nodeids[8];
 	int found = 0;
-	u32 reg;
+	u32 nodeid, reg;
 	unsigned numnodes;
 	unsigned cores;
 	unsigned bits;
@@ -106,7 +106,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 	prevbase = 0;
 	for (i = 0; i < 8; i++) {
 		unsigned long base, limit;
-		u32 nodeid;
 
 		base = read_pci_config(0, nb, 1, 0x40 + i*8);
 		limit = read_pci_config(0, nb, 1, 0x44 + i*8);
-- 
cgit v1.2.2


From 55d4f22abc9f011c5db982f83377cdd38bb9a2a3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: k8topology cleanup variable declarations

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/k8topology_64.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 36c6c4a91353..0ea66b532c35 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -74,17 +74,12 @@ static __init void early_get_boot_cpu_id(void)
 
 int __init k8_scan_nodes(unsigned long start, unsigned long end)
 {
+	unsigned numnodes, cores, bits, apicid_base;
 	unsigned long prevbase;
 	struct bootnode nodes[8];
-	int i, nb;
 	unsigned char nodeids[8];
-	int found = 0;
+	int i, j, nb, found = 0;
 	u32 nodeid, reg;
-	unsigned numnodes;
-	unsigned cores;
-	unsigned bits;
-	int j;
-	unsigned apicid_base;
 
 	if (!early_pci_allowed())
 		return -1;
-- 
cgit v1.2.2


From d1097635deed7196c2a859f285c29267779ca45a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 2 May 2008 23:42:01 +0200
Subject: x86: move mmconfig declarations to header

arch/x86/kernel/mmconf-fam10h_64.c is missing the prototypes, which
are decalred in arch/x86/kernel/setup_64.c. Move the prototypes and
the inline stubs to the appropriate header file.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/mmconf-fam10h_64.c |  1 +
 arch/x86/kernel/setup_64.c         | 13 +------------
 2 files changed, 2 insertions(+), 12 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index edc5fbfe85c0..fdfdc550b366 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -12,6 +12,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/acpi.h>
+#include <asm/mmconfig.h>
 
 #include "../pci/pci.h"
 
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6dff1286ad8a..341230db74e1 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -71,6 +71,7 @@
 #include <asm/topology.h>
 #include <asm/trampoline.h>
 #include <asm/pat.h>
+#include <asm/mmconfig.h>
 
 #include <mach_apic.h>
 #ifdef CONFIG_PARAVIRT
@@ -293,18 +294,6 @@ static void __init parse_setup_data(void)
 	}
 }
 
-#ifdef CONFIG_PCI_MMCONFIG
-extern void __cpuinit fam10h_check_enable_mmcfg(void);
-extern void __init check_enable_amd_mmconf_dmi(void);
-#else
-void __cpuinit fam10h_check_enable_mmcfg(void)
-{
-}
-void __init check_enable_amd_mmconf_dmi(void)
-{
-}
-#endif
-
 /*
  * setup_arch - architecture-specific boot-time initializations
  *
-- 
cgit v1.2.2


From 11034d55975be6d8b955a6eb11e87fc67ec086c2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:36 +0200
Subject: x86: init64.c include initrd.h

free_initrd_mem needs a prototype, which is in linux/initrd.h

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 32ba13b0f818..18123096cdb9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
-- 
cgit v1.2.2


From e0b32d768cad17af07af3aced67498bde98296c9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:37 +0200
Subject: x86: make command_line static in setup_64.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/setup_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 341230db74e1..78c1be69c6d3 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(edid_info);
 
 extern int root_mountflags;
 
-char __initdata command_line[COMMAND_LINE_SIZE];
+static char __initdata command_line[COMMAND_LINE_SIZE];
 
 static struct resource standard_io_resources[] = {
 	{ .name = "dma1", .start = 0x00, .end = 0x1f,
-- 
cgit v1.2.2


From 968cbfad1a727b5689ae620f4d970abf6ce73340 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:37 +0200
Subject: x86: make __pci_mmcfg_init static in mmconfig-shared.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/pci/mmconfig-shared.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 0cfebecf2a8f..23faaa890ffc 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -374,7 +374,7 @@ reject:
 
 static int __initdata known_bridge;
 
-void __init __pci_mmcfg_init(int early)
+static void __init __pci_mmcfg_init(int early)
 {
 	/* MMCONFIG disabled */
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
-- 
cgit v1.2.2


From 311f83494830fec17f086401a5b43984bb447cd2 Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Mon, 12 May 2008 15:43:37 +0200
Subject: x86: kernel/pci-dma.c cleanups

This patch contains the following cleanups:
- make the following needlessly global code static:
  - dma_alloc_pages()

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/pci-dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index c5ef1af8e79d..5bc29ca4196e 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -357,7 +357,7 @@ int dma_supported(struct device *dev, u64 mask)
 EXPORT_SYMBOL(dma_supported);
 
 /* Allocate DMA memory on node near device */
-noinline struct page *
+static noinline struct page *
 dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
 {
 	int node;
-- 
cgit v1.2.2


From 6a1673ae2201931ce34bf7ba9f90928c864d8334 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:38 +0200
Subject: x86: make memory_add_physaddr_to_nid depend on MEMORY_HOTPLUG

memory_add_physaddr_to_nid() is only used in the
CONFIG_MEMORY_HOTPLUG_SPARSE || CONFIG_ACPI_HOTPLUG_MEMORY case.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/srat_64.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 3890234e5b26..f6d0584cbf38 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -522,6 +522,7 @@ int __node_distance(int a, int b)
 
 EXPORT_SYMBOL(__node_distance);
 
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY)
 int memory_add_physaddr_to_nid(u64 start)
 {
 	int i, ret = 0;
@@ -533,4 +534,4 @@ int memory_add_physaddr_to_nid(u64 start)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
+#endif
-- 
cgit v1.2.2


From 4e50e62ce52f39b5f45e82f68b18254458b429bb Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:43:38 +0200
Subject: x86: eliminate duplicate consistency checks in init_32.c

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/init_32.c | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ec30d10154b6..4834c0fcb6b7 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -571,17 +571,6 @@ void __init mem_init(void)
 #endif
 	bad_ppro = ppro_with_ram_bug();
 
-#ifdef CONFIG_HIGHMEM
-	/* check that fixmap and pkmap do not overlap */
-	if (PKMAP_BASE + LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) {
-		printk(KERN_ERR
-			"fixmap and kmap areas overlap - this will crash\n");
-		printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n",
-				PKMAP_BASE, PKMAP_BASE + LAST_PKMAP*PAGE_SIZE,
-				FIXADDR_START);
-		BUG();
-	}
-#endif
 	/* this will put all low memory onto the freelists */
 	totalram_pages += free_all_bootmem();
 
@@ -614,7 +603,6 @@ void __init mem_init(void)
 		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
 	       );
 
-#if 1 /* double-sanity-check paranoia */
 	printk(KERN_INFO "virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #ifdef CONFIG_HIGHMEM
@@ -655,7 +643,6 @@ void __init mem_init(void)
 #endif
 	BUG_ON(VMALLOC_START				> VMALLOC_END);
 	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
-#endif /* double-sanity-check paranoia */
 
 	if (boot_cpu_data.wp_works_ok < 0)
 		test_wp_bit();
-- 
cgit v1.2.2


From ebdd561a19d7917ac49fff9c355aa4833c504bf1 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:43:38 +0200
Subject: x86: constify data in reboot.c

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/reboot.c           | 18 +++++++++---------
 arch/x86/kernel/reboot_fixups_32.c |  4 ++--
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f6be7d5f82f8..f8a62160e151 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -27,7 +27,7 @@
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-static long no_idt[3];
+static const struct desc_ptr no_idt = {};
 static int reboot_mode;
 enum reboot_type reboot_type = BOOT_KBD;
 int reboot_force;
@@ -201,15 +201,15 @@ core_initcall(reboot_init);
    controller to pulse the CPU reset line, which is more thorough, but
    doesn't work with at least one type of 486 motherboard.  It is easy
    to stop this code working; hence the copious comments. */
-static unsigned long long
+static const unsigned long long
 real_mode_gdt_entries [3] =
 {
 	0x0000000000000000ULL,	/* Null descriptor */
-	0x00009a000000ffffULL,	/* 16-bit real-mode 64k code at 0x00000000 */
-	0x000092000100ffffULL	/* 16-bit real-mode 64k data at 0x00000100 */
+	0x00009b000000ffffULL,	/* 16-bit real-mode 64k code at 0x00000000 */
+	0x000093000100ffffULL	/* 16-bit real-mode 64k data at 0x00000100 */
 };
 
-static struct desc_ptr
+static const struct desc_ptr
 real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries },
 real_mode_idt = { 0x3ff, 0 };
 
@@ -231,7 +231,7 @@ real_mode_idt = { 0x3ff, 0 };
 
    More could be done here to set up the registers as if a CPU reset had
    occurred; hopefully real BIOSs don't assume much. */
-static unsigned char real_mode_switch [] =
+static const unsigned char real_mode_switch [] =
 {
 	0x66, 0x0f, 0x20, 0xc0,			/*    movl  %cr0,%eax        */
 	0x66, 0x83, 0xe0, 0x11,			/*    andl  $0x00000011,%eax */
@@ -245,7 +245,7 @@ static unsigned char real_mode_switch [] =
 	0x24, 0x10,				/* f: andb  $0x10,al         */
 	0x66, 0x0f, 0x22, 0xc0			/*    movl  %eax,%cr0        */
 };
-static unsigned char jump_to_bios [] =
+static const unsigned char jump_to_bios [] =
 {
 	0xea, 0x00, 0x00, 0xff, 0xff		/*    ljmp  $0xffff,$0x0000  */
 };
@@ -255,7 +255,7 @@ static unsigned char jump_to_bios [] =
  * specified by the code and length parameters.
  * We assume that length will aways be less that 100!
  */
-void machine_real_restart(unsigned char *code, int length)
+void machine_real_restart(const unsigned char *code, int length)
 {
 	local_irq_disable();
 
@@ -368,7 +368,7 @@ static void native_machine_emergency_restart(void)
 			}
 
 		case BOOT_TRIPLE:
-			load_idt((const struct desc_ptr *)&no_idt);
+			load_idt(&no_idt);
 			__asm__ __volatile__("int3");
 
 			reboot_type = BOOT_KBD;
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index dec0b5ec25c2..61a837743fe5 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -49,7 +49,7 @@ struct device_fixup {
 	void (*reboot_fixup)(struct pci_dev *);
 };
 
-static struct device_fixup fixups_table[] = {
+static const struct device_fixup fixups_table[] = {
 { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset },
 { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset },
 { PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset },
@@ -64,7 +64,7 @@ static struct device_fixup fixups_table[] = {
  */
 void mach_reboot_fixups(void)
 {
-	struct device_fixup *cur;
+	const struct device_fixup *cur;
 	struct pci_dev *dev;
 	int i;
 
-- 
cgit v1.2.2


From 369101da7e3f6f971b7303922d2978b8483241c6 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Mon, 12 May 2008 15:43:38 +0200
Subject: x86: head_64.S cleanup - use predefined flags from processor-flags.h

We should better use already defined flags from processor-flags.h instead
of defining own ones

[>>> object code check >>>]

original
md5sum: 9cfa6dbf045a046bb5dfb85f8bcfe8c4  arch/x86/kernel/head_64.o
   text    data     bss     dec     hex filename
  37361    4432    8192   49985    c341 arch/x86/kernel/head_64.o

patched
md5sum: 9cfa6dbf045a046bb5dfb85f8bcfe8c4  arch/x86/kernel/head_64.o
   text    data     bss     dec     hex filename
  37361    4432    8192   49985    c341 arch/x86/kernel/head_64.o

[<<< object code check <<<]

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/head_64.S | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 10a1955bb1d1..2f59ca8bd16c 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/msr.h>
 #include <asm/cache.h>
+#include <asm/processor-flags.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -184,14 +185,10 @@ ENTRY(secondary_startup_64)
 1:	wrmsr				/* Make changes effective */
 
 	/* Setup cr0 */
-#define CR0_PM				1		/* protected mode */
-#define CR0_MP				(1<<1)
-#define CR0_ET				(1<<4)
-#define CR0_NE				(1<<5)
-#define CR0_WP				(1<<16)
-#define CR0_AM				(1<<18)
-#define CR0_PAGING 			(1<<31)
-	movl $CR0_PM|CR0_MP|CR0_ET|CR0_NE|CR0_WP|CR0_AM|CR0_PAGING,%eax
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
+	movl	$CR0_STATE, %eax
 	/* Make changes effective */
 	movq	%rax, %cr0
 
-- 
cgit v1.2.2


From e83e31f41a623262714d9c56dde7dfc51ac078f7 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Mon, 12 May 2008 15:43:39 +0200
Subject: x86: compressed/head_64.S cleanup - use predefined flags from
 processor-flags.h

We should better use already defined flags from processor-flags.h instead
of defining own ones

[>>> object code check >>>]

original
md5sum: 129f24be6df396fb7d8bf998c01fc716  arch/x86/boot/compressed/head_64.o
   text    data     bss     dec     hex filename
    705      48   45056   45809    b2f1 arch/x86/boot/compressed/head_64.o

patched
md5sum: 129f24be6df396fb7d8bf998c01fc716  arch/x86/boot/compressed/head_64-new.o
   text    data     bss     dec     hex filename
    705      48   45056   45809    b2f1 arch/x86/boot/compressed/head_64-new.o

[<<< object code check <<<]

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/boot/compressed/head_64.S | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index d8819efac81d..1d5dff4123e1 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -30,6 +30,7 @@
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/msr.h>
+#include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
 .section ".text.head"
@@ -109,7 +110,7 @@ startup_32:
 
 	/* Enable PAE mode */
 	xorl	%eax, %eax
-	orl	$(1 << 5), %eax
+	orl	$(X86_CR4_PAE), %eax
 	movl	%eax, %cr4
 
  /*
@@ -170,7 +171,7 @@ startup_32:
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
-	movl	$0x80000001, %eax /* Enable Paging and Protected mode */
+	movl	$(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
 	movl	%eax, %cr0
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */
-- 
cgit v1.2.2


From 2cc74111c78dbc7b26c41b4e87cfebfc3aed49c4 Mon Sep 17 00:00:00 2001
From: Huang Weiyi <weiyi.huang@gmail.com>
Date: Sun, 11 May 2008 19:35:54 +0800
Subject: x86: ipi.c: removed duplicated include

Removed duplicated include <linux/interrupt.h> in
arch/x86/kernel/ipi.c.

Signed-off-by: Huang Weiyi <weiyi.huang@gmail.com>
Cc: mingo@redhat.com
Cc: hpa@zytor.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/ipi.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index c0df7b89ca23..9d98cda39ad9 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -8,7 +8,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/cache.h>
-#include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 
-- 
cgit v1.2.2


From 883b7af932b4435eb4798cfa4fec0848639c2a87 Mon Sep 17 00:00:00 2001
From: Huang Weiyi <weiyi.huang@gmail.com>
Date: Sun, 11 May 2008 19:36:57 +0800
Subject: x86: smpboot.c: removed duplicated include

Removed duplicated include <asm/nmi.h> in
arch/x86/kernel/smpboot.c.

Signed-off-by: Huang Weiyi <weiyi.huang@gmail.com>
Cc: mingo@redhat.com
Cc: hpa@zytor.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/smpboot.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 38988491c622..0974fc0997b9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -59,7 +59,6 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
-#include <asm/nmi.h>
 #include <asm/vmi.h>
 #include <asm/genapic.h>
 #include <linux/mc146818rtc.h>
-- 
cgit v1.2.2


From 05139d8fb445d9a3569071af1c5920fc46191b7b Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Tue, 13 May 2008 21:14:22 +0400
Subject: x86: head_64.S cleanup - use straight move to CR4 register

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/head_64.S | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 2f59ca8bd16c..7475b4c91f05 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -155,9 +155,7 @@ ENTRY(secondary_startup_64)
 	 */
 
 	/* Enable PAE mode and PGE */
-	xorq	%rax, %rax
-	btsq	$5, %rax
-	btsq	$7, %rax
+	movl	$(X86_CR4_PAE | X86_CR4_PGE), %eax
 	movq	%rax, %cr4
 
 	/* Setup early boot stage 4 level pagetables. */
-- 
cgit v1.2.2


From 0e192b99d7d09f08b445c31ee7c7f3d0bfb27345 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Tue, 13 May 2008 20:55:40 +0400
Subject: x86: head_64.S cleanup - use PMD_SHIFT instead of numeric constant

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/head_64.S | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7475b4c91f05..d8ed3259e6e4 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -322,11 +322,11 @@ early_idt_ripmsg:
 ENTRY(name)
 
 /* Automate the creation of 1 to 1 mapping pmd entries */
-#define PMDS(START, PERM, COUNT)		\
-	i = 0 ;					\
-	.rept (COUNT) ;				\
-	.quad	(START) + (i << 21) + (PERM) ;	\
-	i = i + 1 ;				\
+#define PMDS(START, PERM, COUNT)			\
+	i = 0 ;						\
+	.rept (COUNT) ;					\
+	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
+	i = i + 1 ;					\
 	.endr
 
 	/*
-- 
cgit v1.2.2


From bfe4bb1526945e446d2912bef2e1e2cbd2c7349e Mon Sep 17 00:00:00 2001
From: Miklos Vajna <vmiklos@frugalware.org>
Date: Sat, 17 May 2008 22:48:13 +0200
Subject: x86: janitor work in bugs.c

Just moved trailing statements to the next line, removed space before
open/close parenthesis, wrapped long lines.

Signed-off-by: Miklos Vajna <vmiklos@frugalware.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/bugs.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 170d2f5523b2..1b1c56bb338f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -59,8 +59,12 @@ static void __init check_fpu(void)
 		return;
 	}
 
-/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */
-	/* Test for the divl bug.. */
+	/*
+	 * trap_init() enabled FXSR and company _before_ testing for FP
+	 * problems here.
+	 *
+	 * Test for the divl bug..
+	 */
 	__asm__("fninit\n\t"
 		"fldl %1\n\t"
 		"fdivl %2\n\t"
@@ -108,10 +112,15 @@ static void __init check_popad(void)
 	  "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
 	  : "=&a" (res)
 	  : "d" (inp)
-	  : "ecx", "edi" );
-	/* If this fails, it means that any user program may lock the CPU hard. Too bad. */
-	if (res != 12345678) printk( "Buggy.\n" );
-		        else printk( "OK.\n" );
+	  : "ecx", "edi");
+	/*
+	 * If this fails, it means that any user program may lock the
+	 * CPU hard. Too bad.
+	 */
+	if (res != 12345678)
+		printk("Buggy.\n");
+	else
+		printk("OK.\n");
 #endif
 }
 
@@ -137,7 +146,8 @@ static void __init check_config(void)
  * i486+ only features! (WP works in supervisor mode and the
  * new "invlpg" and "bswap" instructions)
  */
-#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP)
+#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \
+	defined(CONFIG_X86_BSWAP)
 	if (boot_cpu_data.x86 == 3)
 		panic("Kernel requires i486+ for 'invlpg' and other features");
 #endif
@@ -170,6 +180,7 @@ void __init check_bugs(void)
 	check_fpu();
 	check_hlt();
 	check_popad();
-	init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	init_utsname()->machine[1] =
+		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
 }
-- 
cgit v1.2.2


From 2141261a11524acbfce86a5a213bbaea08794bbb Mon Sep 17 00:00:00 2001
From: Miklos Vajna <vmiklos@frugalware.org>
Date: Tue, 13 May 2008 13:35:25 +0200
Subject: x86: janitor work in video-vga.c

Just moved an open brace to the previous line.

Signed-off-by: Miklos Vajna <vmiklos@frugalware.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/boot/video-vga.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index 40ecb8d7688c..b939cb476dec 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -259,8 +259,7 @@ static int vga_probe(void)
 	return mode_count[adapter];
 }
 
-__videocard video_vga =
-{
+__videocard video_vga = {
 	.card_name	= "VGA",
 	.probe		= vga_probe,
 	.set_mode	= vga_set_mode,
-- 
cgit v1.2.2


From 83cd1daa1dc3400e5ca2255818641233ebb30680 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Mon, 12 May 2008 15:44:39 +0200
Subject: x86: eliminate dead code in x86_64 entry.S

Remove the not longer used handlers for reserved vectors.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/entry_64.S | 4 ----
 arch/x86/kernel/traps_64.c | 3 ---
 2 files changed, 7 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 556a8df522a7..1f1751dfb2f3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1120,10 +1120,6 @@ ENTRY(coprocessor_segment_overrun)
 	zeroentry do_coprocessor_segment_overrun
 END(coprocessor_segment_overrun)
 
-ENTRY(reserved)
-	zeroentry do_reserved
-END(reserved)
-
 	/* runs on exception stack */
 ENTRY(double_fault)
 	XCPT_FRAME
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index adff76ea97c4..ec6d3b2130c4 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -71,7 +71,6 @@ asmlinkage void general_protection(void);
 asmlinkage void page_fault(void);
 asmlinkage void coprocessor_error(void);
 asmlinkage void simd_coprocessor_error(void);
-asmlinkage void reserved(void);
 asmlinkage void alignment_check(void);
 asmlinkage void machine_check(void);
 asmlinkage void spurious_interrupt_bug(void);
@@ -702,12 +701,10 @@ DO_ERROR_INFO( 0, SIGFPE,  "divide error", divide_error, FPE_INTDIV, regs->ip)
 DO_ERROR( 4, SIGSEGV, "overflow", overflow)
 DO_ERROR( 5, SIGSEGV, "bounds", bounds)
 DO_ERROR_INFO( 6, SIGILL,  "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
 DO_ERROR( 9, SIGFPE,  "coprocessor segment overrun", coprocessor_segment_overrun)
 DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
 DO_ERROR(11, SIGBUS,  "segment not present", segment_not_present)
 DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
-DO_ERROR(18, SIGSEGV, "reserved", reserved)
 
 /* Runs on IST stack */
 asmlinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-- 
cgit v1.2.2


From 48e239572271cf79412d90753a721242a765f7d9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 24 May 2008 17:24:34 +0200
Subject: x86: fixup the fallout of the bitops changes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/pgtable.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 50159764f694..ee1d6d39edd4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -255,7 +255,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
 
 	if (pte_young(*ptep))
 		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
-					 &ptep->pte);
+					 (unsigned long *) &ptep->pte);
 
 	if (ret)
 		pte_update(vma->vm_mm, addr, ptep);
-- 
cgit v1.2.2


From c9fea78dc9775981bed2da379568c8a8fddd1fb6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 19 May 2008 13:53:39 +0200
Subject: x86: make NUMAQ depend on PCI

NUMAQ depends on the existence of PCI hardware, and requiring PCI
makes this subarch simpler and avoids build failures if PCI is
disabled.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bbafeac89116..029372813ae2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -270,7 +270,7 @@ config X86_VOYAGER
 
 config X86_NUMAQ
 	bool "NUMAQ (IBM/Sequent)"
-	depends on SMP && X86_32
+	depends on SMP && X86_32 && PCI
 	select NUMA
 	help
 	  This option is used for getting Linux to run on a (IBM/Sequent) NUMA
-- 
cgit v1.2.2


From 1ac97018169c5a13feaa90d9671f2d6ba2d9e86e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 19 May 2008 14:10:14 +0200
Subject: x86: untangle pci dependencies

make PCI-less subarches not build with PCI - instead of complicating
the PCI dependencies.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 029372813ae2..78700f5faf62 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -258,7 +258,7 @@ config X86_ELAN
 
 config X86_VOYAGER
 	bool "Voyager (NCR)"
-	depends on X86_32 && (SMP || BROKEN)
+	depends on X86_32 && (SMP || BROKEN) && !PCI
 	help
 	  Voyager is an MCA-based 32-way capable SMP architecture proprietary
 	  to NCR Corp.  Machine classes 345x/35xx/4100/51xx are Voyager-based.
@@ -300,7 +300,7 @@ config X86_BIGSMP
 
 config X86_VISWS
 	bool "SGI 320/540 (Visual Workstation)"
-	depends on X86_32
+	depends on X86_32 && !PCI
 	help
 	  The SGI Visual Workstation series is an IA32-based workstation
 	  based on SGI systems chips with some legacy PC hardware attached.
@@ -344,7 +344,7 @@ config X86_RDC321X
 config X86_VSMP
 	bool "Support for ScaleMP vSMP"
 	select PARAVIRT
-	depends on X86_64
+	depends on X86_64 && !PCI
 	help
 	  Support for ScaleMP vSMP systems.  Say 'Y' here if this kernel is
 	  supposed to run on these EM64T-based machines.  Only choose this option
@@ -1477,8 +1477,7 @@ endmenu
 menu "Bus options (PCI etc.)"
 
 config PCI
-	bool "PCI support" if !X86_VISWS && !X86_VSMP
-	depends on !X86_VOYAGER
+	bool "PCI support"
 	default y
 	select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
 	help
-- 
cgit v1.2.2


From b764a15f679942a7bc9d4f9645299e1defcc5b43 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@lxorguk.ukuu.org.uk>
Date: Thu, 22 May 2008 21:22:04 +0100
Subject: x86: Switch apm to unlocked_kernel

This pushes the lock a fair way down and the final kill looks like it
should be an easy project for someone who wants to have a shot at it.

Signed-off-by: Alan Cox <alan@redhat.com>
Cc: mingo@redhat.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/apm_32.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index bf9290e29013..00e6d1370954 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
+#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -1149,7 +1150,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender)
 				as->event_tail = 0;
 		}
 		as->events[as->event_head] = event;
-		if ((!as->suser) || (!as->writer))
+		if (!as->suser || !as->writer)
 			continue;
 		switch (event) {
 		case APM_SYS_SUSPEND:
@@ -1396,7 +1397,7 @@ static void apm_mainloop(void)
 
 static int check_apm_user(struct apm_user *as, const char *func)
 {
-	if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) {
+	if (as == NULL || as->magic != APM_BIOS_MAGIC) {
 		printk(KERN_ERR "apm: %s passed bad filp\n", func);
 		return 1;
 	}
@@ -1459,18 +1460,19 @@ static unsigned int do_poll(struct file *fp, poll_table *wait)
 	return 0;
 }
 
-static int do_ioctl(struct inode *inode, struct file *filp,
-		    u_int cmd, u_long arg)
+static long do_ioctl(struct file *filp, u_int cmd, u_long arg)
 {
 	struct apm_user *as;
+	int ret;
 
 	as = filp->private_data;
 	if (check_apm_user(as, "ioctl"))
 		return -EIO;
-	if ((!as->suser) || (!as->writer))
+	if (!as->suser || !as->writer)
 		return -EPERM;
 	switch (cmd) {
 	case APM_IOC_STANDBY:
+		lock_kernel();
 		if (as->standbys_read > 0) {
 			as->standbys_read--;
 			as->standbys_pending--;
@@ -1479,8 +1481,10 @@ static int do_ioctl(struct inode *inode, struct file *filp,
 			queue_event(APM_USER_STANDBY, as);
 		if (standbys_pending <= 0)
 			standby();
+		unlock_kernel();
 		break;
 	case APM_IOC_SUSPEND:
+		lock_kernel();
 		if (as->suspends_read > 0) {
 			as->suspends_read--;
 			as->suspends_pending--;
@@ -1488,16 +1492,17 @@ static int do_ioctl(struct inode *inode, struct file *filp,
 		} else
 			queue_event(APM_USER_SUSPEND, as);
 		if (suspends_pending <= 0) {
-			return suspend(1);
+			ret = suspend(1);
 		} else {
 			as->suspend_wait = 1;
 			wait_event_interruptible(apm_suspend_waitqueue,
 					as->suspend_wait == 0);
-			return as->suspend_result;
+			ret = as->suspend_result;
 		}
-		break;
+		unlock_kernel();
+		return ret;
 	default:
-		return -EINVAL;
+		return -ENOTTY;
 	}
 	return 0;
 }
@@ -1860,7 +1865,7 @@ static const struct file_operations apm_bios_fops = {
 	.owner		= THIS_MODULE,
 	.read		= do_read,
 	.poll		= do_poll,
-	.ioctl		= do_ioctl,
+	.unlocked_ioctl	= do_ioctl,
 	.open		= do_open,
 	.release	= do_release,
 };
-- 
cgit v1.2.2


From 73531905ed53576d9e8707659a761e7046a60497 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Sun, 25 May 2008 23:03:18 +0200
Subject: Kconfig: introduce ARCH_DEFCONFIG to DEFCONFIG_LIST

init/Kconfig contains a list of configs that are searched
for if 'make *config' are used with no .config present.
Extend this list to look at the config identified by
ARCH_DEFCONFIG.

With this change we now try the defconfig targets last.

This fixes a regression reported
by: Linus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
---
 arch/x86/Kconfig | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe361ae7ef2f..dcbec34154cf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,17 +26,10 @@ config X86
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 
-config DEFCONFIG_LIST
+config ARCH_DEFCONFIG
 	string
-	depends on X86_32
-	option defconfig_list
-	default "arch/x86/configs/i386_defconfig"
-
-config DEFCONFIG_LIST
-	string
-	depends on X86_64
-	option defconfig_list
-	default "arch/x86/configs/x86_64_defconfig"
+	default "arch/x86/configs/i386_defconfig" if X86_32
+	default "arch/x86/configs/x86_64_defconfig" if X86_64
 
 
 config GENERIC_LOCKBREAK
-- 
cgit v1.2.2


From 7b1333aa4cb546ddeb9c05098a53d9a777623a05 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:01 +0100
Subject: xen: use hypercall rather than clts

Xen will trap and emulate clts, but its better to use a hypercall.
Also, xenner doesn't handle clts.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a05b7721bc81..446f4cd649e6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -607,6 +607,30 @@ static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 
+static void xen_clts(void)
+{
+	struct multicall_space mcs;
+
+	mcs = xen_mc_entry(0);
+
+	MULTI_fpu_taskswitch(mcs.mc, 0);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_write_cr0(unsigned long cr0)
+{
+	struct multicall_space mcs;
+
+	/* Only pay attention to cr0.TS; everything else is
+	   ignored. */
+	mcs = xen_mc_entry(0);
+
+	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
 static void xen_write_cr2(unsigned long cr2)
 {
 	x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
@@ -978,10 +1002,10 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.set_debugreg = xen_set_debugreg,
 	.get_debugreg = xen_get_debugreg,
 
-	.clts = native_clts,
+	.clts = xen_clts,
 
 	.read_cr0 = native_read_cr0,
-	.write_cr0 = native_write_cr0,
+	.write_cr0 = xen_write_cr0,
 
 	.read_cr4 = native_read_cr4,
 	.read_cr4_safe = native_read_cr4_safe,
-- 
cgit v1.2.2


From 349c709f42453707f74bece0d9d35ee5b3842893 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:02 +0100
Subject: xen: use new sched_op

Use the new sched_op hypercall, mainly because xenner doesn't support
the old one.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 446f4cd649e6..35ddaf50180a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -254,7 +254,7 @@ static void xen_irq_enable(void)
 static void xen_safe_halt(void)
 {
 	/* Blocking includes an implicit local_irq_enable(). */
-	if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0)
+	if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)
 		BUG();
 }
 
@@ -1138,11 +1138,13 @@ static const struct smp_ops xen_smp_ops __initdata = {
 
 static void xen_reboot(int reason)
 {
+	struct sched_shutdown r = { .reason = reason };
+
 #ifdef CONFIG_SMP
 	smp_send_stop();
 #endif
 
-	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, reason))
+	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
 }
 
-- 
cgit v1.2.2


From 2956a3511c8c5dccb1d4739ead17c7c3c23a24b7 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:04 +0100
Subject: xen: allow some cr4 updates

The guest can legitimately change things like cr4.OSFXSR and
OSXMMEXCPT, so let it.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 35ddaf50180a..f6876485ee7d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -648,8 +648,10 @@ static unsigned long xen_read_cr2_direct(void)
 
 static void xen_write_cr4(unsigned long cr4)
 {
-	/* Just ignore cr4 changes; Xen doesn't allow us to do
-	   anything anyway. */
+	cr4 &= ~X86_CR4_PGE;
+	cr4 &= ~X86_CR4_PSE;
+
+	native_write_cr4(cr4);
 }
 
 static unsigned long xen_read_cr3(void)
-- 
cgit v1.2.2


From 239d1fc04ed0b58d638096b12a7f6d50269d30c9 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:05 +0100
Subject: xen: don't worry about preempt during xen_irq_enable()

When enabling interrupts, we don't need to worry about preemption,
because we either enter with interrupts disabled - so no preemption -
or the caller is confused and is re-enabling interrupts on some
indeterminate processor.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f6876485ee7d..4a372b71239d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -235,13 +235,13 @@ static void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
-	/* There's a one instruction preempt window here.  We need to
-	   make sure we're don't switch CPUs between getting the vcpu
-	   pointer and updating the mask. */
-	preempt_disable();
+	/* We don't need to worry about being preempted here, since
+	   either a) interrupts are disabled, so no preemption, or b)
+	   the caller is confused and is trying to re-enable interrupts
+	   on an indeterminate processor. */
+
 	vcpu = x86_read_percpu(xen_vcpu);
 	vcpu->evtchn_upcall_mask = 0;
-	preempt_enable_no_resched();
 
 	/* Doesn't matter if we get preempted here, because any
 	   pending event will get dealt with anyway. */
-- 
cgit v1.2.2


From a15af1c9ea2750a9ff01e51615c45950bad8221b Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:06 +0100
Subject: x86/paravirt: add pte_flags to just get pte flags

Add pte_flags() to extract the flags from a pte.  This is a special
case of pte_val() which is only guaranteed to return the pte's flags
correctly; the page number may be corrupted or missing.

The intent is to allow paravirt implementations to return pte flags
without having to do any translation of the page number (most notably,
Xen).

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/paravirt.c | 1 +
 arch/x86/xen/enlighten.c   | 1 +
 2 files changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 74f0c5ea2a03..c98d54688180 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -403,6 +403,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 #endif /* PAGETABLE_LEVELS >= 3 */
 
 	.pte_val = native_pte_val,
+	.pte_flags = native_pte_val,
 	.pgd_val = native_pgd_val,
 
 	.make_pte = native_make_pte,
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 4a372b71239d..1b4b5fa498b3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1101,6 +1101,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.set_pmd = xen_set_pmd,
 
 	.pte_val = xen_pte_val,
+	.pte_flags = native_pte_val,
 	.pgd_val = xen_pgd_val,
 
 	.make_pte = xen_make_pte,
-- 
cgit v1.2.2


From 9e124fe16ff24746d6de5a2ad685266d7bce0e08 Mon Sep 17 00:00:00 2001
From: Markus Armbruster <armbru@redhat.com>
Date: Mon, 26 May 2008 23:31:07 +0100
Subject: xen: Enable console tty by default in domU if it's not a dummy

Without console= arguments on the kernel command line, the first
console to register becomes enabled and the preferred console (the one
behind /dev/console).  This is normally tty (assuming
CONFIG_VT_CONSOLE is enabled, which it commonly is).

This is okay as long tty is a useful console.  But unless we have the
PV framebuffer, and it is enabled for this domain, tty0 in domU is
merely a dummy.  In that case, we want the preferred console to be the
Xen console hvc0, and we want it without having to fiddle with the
kernel command line.  Commit b8c2d3dfbc117dff26058fbac316b8acfc2cb5f7
did that for us.

Since we now have the PV framebuffer, we want to enable and prefer tty
again, but only when PVFB is enabled.  But even then we still want to
enable the Xen console as well.

Problem: when tty registers, we can't yet know whether the PVFB is
enabled.  By the time we can know (xenstore is up), the console setup
game is over.

Solution: enable console tty by default, but keep hvc as the preferred
console.  Change the preferred console to tty when PVFB probes
successfully, unless we've been given console kernel parameters.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1b4b5fa498b3..6cfb708408e9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1256,8 +1256,10 @@ asmlinkage void __init xen_start_kernel(void)
 		? __pa(xen_start_info->mod_start) : 0;
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 
-	if (!is_initial_xendomain())
+	if (!is_initial_xendomain()) {
+		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
+	}
 
 	/* Start the world */
 	start_kernel();
-- 
cgit v1.2.2


From 83abc70a4c6e306f4c1672e25884322f797e4fcb Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:12 +0100
Subject: xen: make earlyprintk=xen work again

For some perverse reason, if you call add_preferred_console() it prevents
setup_early_printk() from successfully enabling the boot console -
unless you make it a preferred console too...

Also, make xenboot console output distinct from normal console output,
since it gets repeated when the console handover happens, and the
duplicated output is confusing without disambiguation.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Markus Armbruster <armbru@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
---
 arch/x86/xen/enlighten.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 6cfb708408e9..5c0635a8bffd 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1257,6 +1257,7 @@ asmlinkage void __init xen_start_kernel(void)
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 
 	if (!is_initial_xendomain()) {
+		add_preferred_console("xenboot", 0, NULL);
 		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
 	}
-- 
cgit v1.2.2


From ec9b2065d4d3b797604c09a569083dd9ff951b1b Mon Sep 17 00:00:00 2001
From: Isaku Yamahata <yamahata@valinux.co.jp>
Date: Mon, 26 May 2008 23:31:13 +0100
Subject: xen: Move manage.c to drivers/xen for ia64/xen support

move arch/x86/xen/manage.c under drivers/xen/to share codes
with x86 and ia64.
ia64/xen also uses manage.c

Signed-off-by: Isaku Yamahata <yamahata@valinux.co.jp>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/Makefile |   2 +-
 arch/x86/xen/manage.c | 143 --------------------------------------------------
 2 files changed, 1 insertion(+), 144 deletions(-)
 delete mode 100644 arch/x86/xen/manage.c

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3d8df981d5fd..40b119b6b103 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o \
-			time.o manage.o xen-asm.o grant-table.o
+			time.o xen-asm.o grant-table.o
 
 obj-$(CONFIG_SMP)	+= smp.o
diff --git a/arch/x86/xen/manage.c b/arch/x86/xen/manage.c
deleted file mode 100644
index aa7af9e6abc0..000000000000
--- a/arch/x86/xen/manage.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * Handle extern requests for shutdown, reboot and sysrq
- */
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/reboot.h>
-#include <linux/sysrq.h>
-
-#include <xen/xenbus.h>
-
-#define SHUTDOWN_INVALID  -1
-#define SHUTDOWN_POWEROFF  0
-#define SHUTDOWN_SUSPEND   2
-/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
- * report a crash, not be instructed to crash!
- * HALT is the same as POWEROFF, as far as we're concerned.  The tools use
- * the distinction when we return the reason code to them.
- */
-#define SHUTDOWN_HALT      4
-
-/* Ignore multiple shutdown requests. */
-static int shutting_down = SHUTDOWN_INVALID;
-
-static void shutdown_handler(struct xenbus_watch *watch,
-			     const char **vec, unsigned int len)
-{
-	char *str;
-	struct xenbus_transaction xbt;
-	int err;
-
-	if (shutting_down != SHUTDOWN_INVALID)
-		return;
-
- again:
-	err = xenbus_transaction_start(&xbt);
-	if (err)
-		return;
-
-	str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
-	/* Ignore read errors and empty reads. */
-	if (XENBUS_IS_ERR_READ(str)) {
-		xenbus_transaction_end(xbt, 1);
-		return;
-	}
-
-	xenbus_write(xbt, "control", "shutdown", "");
-
-	err = xenbus_transaction_end(xbt, 0);
-	if (err == -EAGAIN) {
-		kfree(str);
-		goto again;
-	}
-
-	if (strcmp(str, "poweroff") == 0 ||
-	    strcmp(str, "halt") == 0)
-		orderly_poweroff(false);
-	else if (strcmp(str, "reboot") == 0)
-		ctrl_alt_del();
-	else {
-		printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
-		shutting_down = SHUTDOWN_INVALID;
-	}
-
-	kfree(str);
-}
-
-static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
-			  unsigned int len)
-{
-	char sysrq_key = '\0';
-	struct xenbus_transaction xbt;
-	int err;
-
- again:
-	err = xenbus_transaction_start(&xbt);
-	if (err)
-		return;
-	if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) {
-		printk(KERN_ERR "Unable to read sysrq code in "
-		       "control/sysrq\n");
-		xenbus_transaction_end(xbt, 1);
-		return;
-	}
-
-	if (sysrq_key != '\0')
-		xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
-
-	err = xenbus_transaction_end(xbt, 0);
-	if (err == -EAGAIN)
-		goto again;
-
-	if (sysrq_key != '\0')
-		handle_sysrq(sysrq_key, NULL);
-}
-
-static struct xenbus_watch shutdown_watch = {
-	.node = "control/shutdown",
-	.callback = shutdown_handler
-};
-
-static struct xenbus_watch sysrq_watch = {
-	.node = "control/sysrq",
-	.callback = sysrq_handler
-};
-
-static int setup_shutdown_watcher(void)
-{
-	int err;
-
-	err = register_xenbus_watch(&shutdown_watch);
-	if (err) {
-		printk(KERN_ERR "Failed to set shutdown watcher\n");
-		return err;
-	}
-
-	err = register_xenbus_watch(&sysrq_watch);
-	if (err) {
-		printk(KERN_ERR "Failed to set sysrq watcher\n");
-		return err;
-	}
-
-	return 0;
-}
-
-static int shutdown_event(struct notifier_block *notifier,
-			  unsigned long event,
-			  void *data)
-{
-	setup_shutdown_watcher();
-	return NOTIFY_DONE;
-}
-
-static int __init setup_shutdown_event(void)
-{
-	static struct notifier_block xenstore_notifier = {
-		.notifier_call = shutdown_event
-	};
-	register_xenstore_notifier(&xenstore_notifier);
-
-	return 0;
-}
-
-subsys_initcall(setup_shutdown_event);
-- 
cgit v1.2.2


From 38bb5ab4179572f4d24d3ca7188172a31ca51a69 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:16 +0100
Subject: xen: count resched interrupts properly

Make sure resched interrupts appear in /proc/interrupts in the proper
place.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/smp.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 94e69000f982..74ab8968c525 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,12 @@ static struct call_data_struct *call_data;
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
+#ifdef CONFIG_X86_32
+	__get_cpu_var(irq_stat).irq_resched_count++;
+#else
+	add_pda(irq_resched_count, 1);
+#endif
+
 	return IRQ_HANDLED;
 }
 
-- 
cgit v1.2.2


From d451bb7aa852627bdf7be7937dc3d9d9f261b235 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:18 +0100
Subject: xen: make phys_to_machine structure dynamic

We now support the use of memory hotplug, so the physical to machine
page mapping structure must be dynamic.  This is implemented as a
two-level radix tree structure, which allows us to efficiently
incrementally allocate memory for the p2m table as new pages are
added.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c |  2 +-
 arch/x86/xen/mmu.c       | 85 ++++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/setup.c     |  2 --
 arch/x86/xen/xen-ops.h   |  2 ++
 4 files changed, 88 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5c0635a8bffd..73d3c84a3495 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1221,7 +1221,7 @@ asmlinkage void __init xen_start_kernel(void)
 
 	/* Get mfn list */
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list;
+		xen_build_dynamic_phys_to_machine();
 
 	pgd = (pgd_t *)xen_start_info->pt_base;
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 07c2653ec335..c3b27dec6f03 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -56,6 +56,91 @@
 #include "multicalls.h"
 #include "mmu.h"
 
+/*
+ * This should probably be a config option.  On 32-bit, it costs 1
+ * page/gig of memory; on 64-bit its 2 pages/gig.  If we want it to be
+ * completely unbounded we can add another level to the p2m structure.
+ */
+#define MAX_GUEST_PAGES		(16ull * 1024*1024*1024 / PAGE_SIZE)
+#define P2M_ENTRIES_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long))
+
+static unsigned long *p2m_top[MAX_GUEST_PAGES / P2M_ENTRIES_PER_PAGE];
+
+static inline unsigned p2m_top_index(unsigned long pfn)
+{
+	BUG_ON(pfn >= MAX_GUEST_PAGES);
+	return pfn / P2M_ENTRIES_PER_PAGE;
+}
+
+static inline unsigned p2m_index(unsigned long pfn)
+{
+	return pfn % P2M_ENTRIES_PER_PAGE;
+}
+
+void __init xen_build_dynamic_phys_to_machine(void)
+{
+	unsigned pfn;
+	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
+
+	BUG_ON(xen_start_info->nr_pages >= MAX_GUEST_PAGES);
+
+	for(pfn = 0;
+	    pfn < xen_start_info->nr_pages;
+	    pfn += P2M_ENTRIES_PER_PAGE) {
+		unsigned topidx = p2m_top_index(pfn);
+
+		p2m_top[topidx] = &mfn_list[pfn];
+	}
+}
+
+unsigned long get_phys_to_machine(unsigned long pfn)
+{
+	unsigned topidx, idx;
+
+	topidx = p2m_top_index(pfn);
+	if (p2m_top[topidx] == NULL)
+		return INVALID_P2M_ENTRY;
+
+	idx = p2m_index(pfn);
+	return p2m_top[topidx][idx];
+}
+
+static void alloc_p2m(unsigned long **pp)
+{
+	unsigned long *p;
+	unsigned i;
+
+	p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
+	BUG_ON(p == NULL);
+
+	for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+		p[i] = INVALID_P2M_ENTRY;
+
+	if (cmpxchg(pp, NULL, p) != NULL)
+		free_page((unsigned long)p);
+}
+
+void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	unsigned topidx, idx;
+
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+		return;
+	}
+
+	topidx = p2m_top_index(pfn);
+	if (p2m_top[topidx] == NULL) {
+		/* no need to allocate a page to store an invalid entry */
+		if (mfn == INVALID_P2M_ENTRY)
+			return;
+		alloc_p2m(&p2m_top[topidx]);
+	}
+
+	idx = p2m_index(pfn);
+	p2m_top[topidx][idx] = mfn;
+}
+
 xmaddr_t arbitrary_virt_to_machine(unsigned long address)
 {
 	unsigned int level;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 82517e4a752a..37f8f0b8f743 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -27,8 +27,6 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
-unsigned long *phys_to_machine_mapping;
-EXPORT_SYMBOL(phys_to_machine_mapping);
 
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index f1063ae08037..7bdc8c5c9244 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -22,6 +22,8 @@ void __init xen_arch_setup(void);
 void __init xen_init_IRQ(void);
 void xen_enable_sysenter(void);
 
+void __init xen_build_dynamic_phys_to_machine(void);
+
 void xen_setup_timer(int cpu);
 void xen_setup_cpu_clockevents(void);
 unsigned long xen_cpu_khz(void);
-- 
cgit v1.2.2


From 8006ec3e911f93d702e1d4a4e387e244ab434924 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:19 +0100
Subject: xen: add configurable max domain size

Add a config option to set the max size of a Xen domain.  This is used
to scale the size of the physical-to-machine array; it ends up using
around 1 page/GByte, so there's no reason to be very restrictive.

For a 32-bit guest, the default value of 8GB is probably sufficient;
there's not much point in giving a 32-bit machine much more memory
than that.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/Kconfig | 10 ++++++++++
 arch/x86/xen/mmu.c   | 25 ++++++++++++-------------
 arch/x86/xen/setup.c |  3 +++
 3 files changed, 25 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 525b108411bd..d0f1c7c5dc3d 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -11,3 +11,13 @@ config XEN
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
 	  Xen hypervisor.
+
+config XEN_MAX_DOMAIN_MEMORY
+       int "Maximum allowed size of a domain in gigabytes"
+       default 8
+       depends on XEN
+       help
+         The pseudo-physical to machine address array is sized
+         according to the maximum possible memory size of a Xen
+         domain.  This array uses 1 page per gigabyte, so there's no
+         need to be too stingy here.
\ No newline at end of file
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index c3b27dec6f03..644232aa7bfb 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -56,19 +56,13 @@
 #include "multicalls.h"
 #include "mmu.h"
 
-/*
- * This should probably be a config option.  On 32-bit, it costs 1
- * page/gig of memory; on 64-bit its 2 pages/gig.  If we want it to be
- * completely unbounded we can add another level to the p2m structure.
- */
-#define MAX_GUEST_PAGES		(16ull * 1024*1024*1024 / PAGE_SIZE)
 #define P2M_ENTRIES_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long))
 
-static unsigned long *p2m_top[MAX_GUEST_PAGES / P2M_ENTRIES_PER_PAGE];
+static unsigned long *p2m_top[MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE];
 
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
-	BUG_ON(pfn >= MAX_GUEST_PAGES);
+	BUG_ON(pfn >= MAX_DOMAIN_PAGES);
 	return pfn / P2M_ENTRIES_PER_PAGE;
 }
 
@@ -81,12 +75,9 @@ void __init xen_build_dynamic_phys_to_machine(void)
 {
 	unsigned pfn;
 	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
+	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
 
-	BUG_ON(xen_start_info->nr_pages >= MAX_GUEST_PAGES);
-
-	for(pfn = 0;
-	    pfn < xen_start_info->nr_pages;
-	    pfn += P2M_ENTRIES_PER_PAGE) {
+	for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
 		unsigned topidx = p2m_top_index(pfn);
 
 		p2m_top[topidx] = &mfn_list[pfn];
@@ -97,6 +88,9 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 {
 	unsigned topidx, idx;
 
+	if (unlikely(pfn >= MAX_DOMAIN_PAGES))
+		return INVALID_P2M_ENTRY;
+
 	topidx = p2m_top_index(pfn);
 	if (p2m_top[topidx] == NULL)
 		return INVALID_P2M_ENTRY;
@@ -129,6 +123,11 @@ void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 		return;
 	}
 
+	if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
+		BUG_ON(mfn != INVALID_P2M_ENTRY);
+		return;
+	}
+
 	topidx = p2m_top_index(pfn);
 	if (p2m_top[topidx] == NULL) {
 		/* no need to allocate a page to store an invalid entry */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 37f8f0b8f743..488447878a9d 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -16,6 +16,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include <xen/page.h>
 #include <xen/interface/callback.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
@@ -36,6 +37,8 @@ char * __init xen_memory_setup(void)
 {
 	unsigned long max_pfn = xen_start_info->nr_pages;
 
+	max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+
 	e820.nr_map = 0;
 	add_memory_region(0, LOWMEMSIZE(), E820_RAM);
 	add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM);
-- 
cgit v1.2.2


From cf0923ea295ba08ae656ef04164a43cb6553ba99 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:20 +0100
Subject: xen: efficiently support a holey p2m table

When using sparsemem and memory hotplug, the kernel's pseudo-physical
address space can be discontigious.  Previously this was dealt with by
having the upper parts of the radix tree stubbed off.  Unfortunately,
this is incompatible with save/restore, which requires a complete p2m
table.

The solution is to have a special distinguished all-invalid p2m leaf
page, which we can point all the hole areas at.  This allows the tools
to see a complete p2m table, but it only costs a page for all memory
holes.

It also simplifies the code since it removes a few special cases.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/mmu.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 644232aa7bfb..da7b45b05066 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -57,8 +57,17 @@
 #include "mmu.h"
 
 #define P2M_ENTRIES_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long))
+#define TOP_ENTRIES		(MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE)
 
-static unsigned long *p2m_top[MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE];
+/* Placeholder for holes in the address space */
+static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE]
+	__attribute__((section(".data.page_aligned"))) =
+		{ [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };
+
+ /* Array of pointers to pages containing p2m entries */
+static unsigned long *p2m_top[TOP_ENTRIES]
+	__attribute__((section(".data.page_aligned"))) =
+		{ [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
 
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
@@ -92,9 +101,6 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 		return INVALID_P2M_ENTRY;
 
 	topidx = p2m_top_index(pfn);
-	if (p2m_top[topidx] == NULL)
-		return INVALID_P2M_ENTRY;
-
 	idx = p2m_index(pfn);
 	return p2m_top[topidx][idx];
 }
@@ -110,7 +116,7 @@ static void alloc_p2m(unsigned long **pp)
 	for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
 		p[i] = INVALID_P2M_ENTRY;
 
-	if (cmpxchg(pp, NULL, p) != NULL)
+	if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
 		free_page((unsigned long)p);
 }
 
@@ -129,7 +135,7 @@ void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 	}
 
 	topidx = p2m_top_index(pfn);
-	if (p2m_top[topidx] == NULL) {
+	if (p2m_top[topidx] == p2m_missing) {
 		/* no need to allocate a page to store an invalid entry */
 		if (mfn == INVALID_P2M_ENTRY)
 			return;
-- 
cgit v1.2.2


From a0d695c821544947342a2d372ec4108bc813b979 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:21 +0100
Subject: xen: make dummy_shared_info non-static

Rename dummy_shared_info to xen_dummy_shared_info and make it
non-static, in anticipation of users outside of enlighten.c

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c | 6 +++---
 arch/x86/xen/xen-ops.h   | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 73d3c84a3495..d9faaa26c104 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,13 +75,13 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
 
-static /* __initdata */ struct shared_info dummy_shared_info;
+struct shared_info xen_dummy_shared_info;
 
 /*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
  */
-struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
 
 /*
  * Flag to determine whether vcpu info placement is available on all
@@ -104,7 +104,7 @@ static void __init xen_vcpu_setup(int cpu)
 	int err;
 	struct vcpu_info *vcpup;
 
-	BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info);
+	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 	per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 
 	if (!have_vcpu_info_placement)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 7bdc8c5c9244..826d6e4c3dac 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -15,6 +15,7 @@ DECLARE_PER_CPU(unsigned long, xen_cr3);
 DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
 extern struct start_info *xen_start_info;
+extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 char * __init xen_memory_setup(void);
-- 
cgit v1.2.2


From d5edbc1f75420935b1ec7e65df10c8f81cea82de Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:22 +0100
Subject: xen: add p2m mfn_list_list

When saving a domain, the Xen tools need to remap all our mfns to
portable pfns.  In order to remap our p2m table, it needs to know
where all its pages are, so maintain the references to the p2m table
for it to use.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/enlighten.c |  2 ++
 arch/x86/xen/mmu.c       | 39 ++++++++++++++++++++++++++++++++++++---
 arch/x86/xen/xen-ops.h   |  2 ++
 3 files changed, 40 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d9faaa26c104..ce67dc8f36af 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -880,6 +880,8 @@ static __init void setup_shared_info(void)
 	/* In UP this is as good a place as any to set up shared info */
 	xen_setup_vcpu_info_placement();
 #endif
+
+	xen_setup_mfn_list_list();
 }
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index da7b45b05066..4740cda36563 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -69,6 +69,13 @@ static unsigned long *p2m_top[TOP_ENTRIES]
 	__attribute__((section(".data.page_aligned"))) =
 		{ [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
 
+/* Arrays of p2m arrays expressed in mfns used for save/restore */
+static unsigned long p2m_top_mfn[TOP_ENTRIES]
+	__attribute__((section(".bss.page_aligned")));
+
+static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
+	__attribute__((section(".bss.page_aligned")));
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_DOMAIN_PAGES);
@@ -80,11 +87,35 @@ static inline unsigned p2m_index(unsigned long pfn)
 	return pfn % P2M_ENTRIES_PER_PAGE;
 }
 
+/* Build the parallel p2m_top_mfn structures */
+void xen_setup_mfn_list_list(void)
+{
+	unsigned pfn, idx;
+
+	for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+		unsigned topidx = p2m_top_index(pfn);
+
+		p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
+	}
+
+	for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+		unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
+		p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
+	}
+
+	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
+
+	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
+		virt_to_mfn(p2m_top_mfn_list);
+	HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages;
+}
+
+/* Set up p2m_top to point to the domain-builder provided p2m pages */
 void __init xen_build_dynamic_phys_to_machine(void)
 {
-	unsigned pfn;
 	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
 	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
+	unsigned pfn;
 
 	for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
 		unsigned topidx = p2m_top_index(pfn);
@@ -105,7 +136,7 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 	return p2m_top[topidx][idx];
 }
 
-static void alloc_p2m(unsigned long **pp)
+static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
 {
 	unsigned long *p;
 	unsigned i;
@@ -118,6 +149,8 @@ static void alloc_p2m(unsigned long **pp)
 
 	if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
 		free_page((unsigned long)p);
+	else
+		*mfnp = virt_to_mfn(p);
 }
 
 void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
@@ -139,7 +172,7 @@ void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 		/* no need to allocate a page to store an invalid entry */
 		if (mfn == INVALID_P2M_ENTRY)
 			return;
-		alloc_p2m(&p2m_top[topidx]);
+		alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]);
 	}
 
 	idx = p2m_index(pfn);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 826d6e4c3dac..a1bc89a8f169 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -18,6 +18,8 @@ extern struct start_info *xen_start_info;
 extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
+void xen_setup_mfn_list_list(void);
+
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
 void __init xen_init_IRQ(void);
-- 
cgit v1.2.2


From 0e91398f2a5d4eb6b07df8115917d0d1cf3e9b58 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:27 +0100
Subject: xen: implement save/restore

This patch implements Xen save/restore and migration.

Saving is triggered via xenbus, which is polled in
drivers/xen/manage.c.  When a suspend request comes in, the kernel
prepares itself for saving by:

1 - Freeze all processes.  This is primarily to prevent any
    partially-completed pagetable updates from confusing the suspend
    process.  If CONFIG_PREEMPT isn't defined, then this isn't necessary.

2 - Suspend xenbus and other devices

3 - Stop_machine, to make sure all the other vcpus are quiescent.  The
    Xen tools require the domain to run its save off vcpu0.

4 - Within the stop_machine state, it pins any unpinned pgds (under
    construction or destruction), performs canonicalizes various other
    pieces of state (mostly converting mfns to pfns), and finally

5 - Suspend the domain

Restore reverses the steps used to save the domain, ending when all
the frozen processes are thawed.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/Makefile    |  2 +-
 arch/x86/xen/enlighten.c |  6 +++---
 arch/x86/xen/mmu.c       | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/smp.c       |  2 +-
 arch/x86/xen/suspend.c   | 42 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/time.c      |  8 ++++++++
 arch/x86/xen/xen-ops.h   |  4 ++++
 7 files changed, 105 insertions(+), 5 deletions(-)
 create mode 100644 arch/x86/xen/suspend.c

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 40b119b6b103..2ba2d1649131 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o \
-			time.o xen-asm.o grant-table.o
+			time.o xen-asm.o grant-table.o suspend.o
 
 obj-$(CONFIG_SMP)	+= smp.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ce67dc8f36af..b94f63ac228b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -857,7 +857,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 			  PFN_DOWN(__pa(xen_start_info->pt_base)));
 }
 
-static __init void setup_shared_info(void)
+void xen_setup_shared_info(void)
 {
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
@@ -894,7 +894,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 	pv_mmu_ops.release_pmd = xen_release_pmd;
 	pv_mmu_ops.set_pte = xen_set_pte;
 
-	setup_shared_info();
+	xen_setup_shared_info();
 
 	/* Actually pin the pagetable down, but we can't set PG_pinned
 	   yet because the page structures don't exist yet. */
@@ -902,7 +902,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 }
 
 /* This is called once we have the cpu_possible_map */
-void __init xen_setup_vcpu_info_placement(void)
+void xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 4740cda36563..e95955968ba3 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -560,6 +560,29 @@ void xen_pgd_pin(pgd_t *pgd)
 	xen_mc_issue(0);
 }
 
+/*
+ * On save, we need to pin all pagetables to make sure they get their
+ * mfns turned into pfns.  Search the list for any unpinned pgds and pin
+ * them (unpinned pgds are not currently in use, probably because the
+ * process is under construction or destruction).
+ */
+void xen_mm_pin_all(void)
+{
+	unsigned long flags;
+	struct page *page;
+
+	spin_lock_irqsave(&pgd_lock, flags);
+
+	list_for_each_entry(page, &pgd_list, lru) {
+		if (!PagePinned(page)) {
+			xen_pgd_pin((pgd_t *)page_address(page));
+			SetPageSavePinned(page);
+		}
+	}
+
+	spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 /* The init_mm pagetable is really pinned as soon as its created, but
    that's before we have page structures to store the bits.  So do all
    the book-keeping now. */
@@ -617,6 +640,29 @@ static void xen_pgd_unpin(pgd_t *pgd)
 	xen_mc_issue(0);
 }
 
+/*
+ * On resume, undo any pinning done at save, so that the rest of the
+ * kernel doesn't see any unexpected pinned pagetables.
+ */
+void xen_mm_unpin_all(void)
+{
+	unsigned long flags;
+	struct page *page;
+
+	spin_lock_irqsave(&pgd_lock, flags);
+
+	list_for_each_entry(page, &pgd_list, lru) {
+		if (PageSavePinned(page)) {
+			BUG_ON(!PagePinned(page));
+			printk("unpinning pinned %p\n", page_address(page));
+			xen_pgd_unpin((pgd_t *)page_address(page));
+			ClearPageSavePinned(page);
+		}
+	}
+
+	spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
 {
 	spin_lock(&next->page_table_lock);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 74ab8968c525..d2e3c20127d7 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -35,7 +35,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-static cpumask_t xen_cpu_initialized_map;
+cpumask_t xen_cpu_initialized_map;
 static DEFINE_PER_CPU(int, resched_irq) = -1;
 static DEFINE_PER_CPU(int, callfunc_irq) = -1;
 static DEFINE_PER_CPU(int, debug_irq) = -1;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
new file mode 100644
index 000000000000..7620a16fe535
--- /dev/null
+++ b/arch/x86/xen/suspend.c
@@ -0,0 +1,42 @@
+#include <linux/types.h>
+
+#include <xen/interface/xen.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+#include "xen-ops.h"
+#include "mmu.h"
+
+void xen_pre_suspend(void)
+{
+	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
+	xen_start_info->console.domU.mfn =
+		mfn_to_pfn(xen_start_info->console.domU.mfn);
+
+	BUG_ON(!irqs_disabled());
+
+	HYPERVISOR_shared_info = &xen_dummy_shared_info;
+	if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP),
+					 __pte_ma(0), 0))
+		BUG();
+}
+
+void xen_post_suspend(int suspend_cancelled)
+{
+	if (suspend_cancelled) {
+		xen_start_info->store_mfn =
+			pfn_to_mfn(xen_start_info->store_mfn);
+		xen_start_info->console.domU.mfn =
+			pfn_to_mfn(xen_start_info->console.domU.mfn);
+	} else {
+#ifdef CONFIG_SMP
+		xen_cpu_initialized_map = cpu_online_map;
+#endif
+	}
+
+	xen_setup_shared_info();
+}
+
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c39e1a5aa241..0bef256e5f2d 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -572,6 +572,14 @@ void xen_setup_cpu_clockevents(void)
 	clockevents_register_device(&__get_cpu_var(xen_clock_events));
 }
 
+void xen_time_suspend(void)
+{
+}
+
+void xen_time_resume(void)
+{
+}
+
 __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a1bc89a8f169..a0503acad664 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -9,6 +9,7 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
+struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
 DECLARE_PER_CPU(unsigned long, xen_cr3);
@@ -19,6 +20,7 @@ extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
+void xen_setup_shared_info(void);
 
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
@@ -59,6 +61,8 @@ int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
 			       void *info, int wait);
 
+extern cpumask_t xen_cpu_initialized_map;
+
 
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
-- 
cgit v1.2.2


From 359cdd3f866b6219a6729e313faf2221397f3278 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 26 May 2008 23:31:28 +0100
Subject: xen: maintain clock offset over save/restore

Hook into the device model to make sure that timekeeping's resume handler
is called.  This deals with our clocksource's non-monotonicity over the
save/restore.  Explicitly call clock_has_changed() to make sure that
all the timers get retriggered properly.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/time.c | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0bef256e5f2d..c39e1a5aa241 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -572,14 +572,6 @@ void xen_setup_cpu_clockevents(void)
 	clockevents_register_device(&__get_cpu_var(xen_clock_events));
 }
 
-void xen_time_suspend(void)
-{
-}
-
-void xen_time_resume(void)
-{
-}
-
 __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
-- 
cgit v1.2.2


From dd564d0cf08686cf0cc332bf9d48cba5b26a8171 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 27 May 2008 18:03:56 +0200
Subject: x86: aperture_64.c: cleanups

Some small cleanups for aperture_64.c; they should not really change
any code.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 5373f7834d8a..6eea42eb287b 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -111,7 +111,7 @@ static u32 __init allocate_aperture(void)
 
 
 /* Find a PCI capability */
-static __u32 __init find_cap(int bus, int slot, int func, int cap)
+static u32 __init find_cap(int bus, int slot, int func, int cap)
 {
 	int bytes;
 	u8 pos;
@@ -137,7 +137,7 @@ static __u32 __init find_cap(int bus, int slot, int func, int cap)
 }
 
 /* Read a standard AGPv3 bridge header */
-static __u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
+static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
 {
 	u32 apsize;
 	u32 apsizereg;
@@ -202,7 +202,7 @@ static __u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
  * the AGP bridges should be always an own bus on the HT hierarchy,
  * but do it here for future safety.
  */
-static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
+static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 {
 	int bus, slot, func;
 
-- 
cgit v1.2.2


From b20aeccd6ad42ccb6be1b3d1d32618ddd2b31bf0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 28 May 2008 14:24:38 +0200
Subject: xen: fix early bootup crash on native hardware

-tip tree auto-testing found the following early bootup hang:

-------------->
get_memcfg_from_srat: assigning address to rsdp
RSD PTR  v0 [Nvidia]
BUG: Int 14: CR2 ffd00040
     EDI 8092fbfe  ESI ffd00040  EBP 80b0aee8  ESP 80b0aed0
     EBX 000f76f0  EDX 0000000e  ECX 00000003  EAX ffd00040
     err 00000000  EIP 802c055a   CS 00000060  flg 00010006
Stack: ffd00040 80bc78d0 80b0af6c 80b1dbfe 8093d8ba 00000008 80b42810 80b4ddb4
       80b42842 00000000 80b0af1c 801079c8 808e724e 00000000 80b42871 802c0531
       00000100 00000000 0003fff0 80b0af40 80129999 00040100 00040100 00000000
Pid: 0, comm: swapper Not tainted 2.6.26-rc4-sched-devel.git #570
 [<802c055a>] ? strncmp+0x11/0x25
 [<80b1dbfe>] ? get_memcfg_from_srat+0xb4/0x568
 [<801079c8>] ? mcount_call+0x5/0x9
 [<802c0531>] ? strcmp+0xa/0x22
 [<80129999>] ? printk+0x38/0x3a
 [<80129999>] ? printk+0x38/0x3a
 [<8011b122>] ? memory_present+0x66/0x6f
 [<80b216b4>] ? setup_memory+0x13/0x40c
 [<80b16b47>] ? propagate_e820_map+0x80/0x97
 [<80b1622a>] ? setup_arch+0x248/0x477
 [<80129999>] ? printk+0x38/0x3a
 [<80b11759>] ? start_kernel+0x6e/0x2eb
 [<80b110fc>] ? i386_start_kernel+0xeb/0xf2
 =======================
<------

with this config:

   http://redhat.com/~mingo/misc/config-Wed_May_28_01_33_33_CEST_2008.bad

The thing is, the crash makes little sense at first sight. We crash on a
benign-looking printk. The code around it got changed in -tip but
checking those topic branches individually did not reproduce the bug.

Bisection led to this commit:

|   d5edbc1f75420935b1ec7e65df10c8f81cea82de is first bad commit
|   commit d5edbc1f75420935b1ec7e65df10c8f81cea82de
|   Author: Jeremy Fitzhardinge <jeremy@goop.org>
|   Date:   Mon May 26 23:31:22 2008 +0100
|
|   xen: add p2m mfn_list_list

Which is somewhat surprising, as on native hardware Xen client side
should have little to no side-effects.

After some head scratching, it turns out the following happened:
randconfig enabled the following Xen options:

  CONFIG_XEN=y
  CONFIG_XEN_MAX_DOMAIN_MEMORY=8
  # CONFIG_XEN_BLKDEV_FRONTEND is not set
  # CONFIG_XEN_NETDEV_FRONTEND is not set
  CONFIG_HVC_XEN=y
  # CONFIG_XEN_BALLOON is not set

which activated this piece of code in arch/x86/xen/mmu.c:

> @@ -69,6 +69,13 @@
>  	__attribute__((section(".data.page_aligned"))) =
>  		{ [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
>
> +/* Arrays of p2m arrays expressed in mfns used for save/restore */
> +static unsigned long p2m_top_mfn[TOP_ENTRIES]
> +	__attribute__((section(".bss.page_aligned")));
> +
> +static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
> +	__attribute__((section(".bss.page_aligned")));

The problem is, you must only put variables into .bss.page_aligned that
have a _size_ that is _exactly_ page aligned. In this case the size of
p2m_top_mfn_list is not page aligned:

 80b8d000 b p2m_top_mfn
 80b8f000 b p2m_top_mfn_list
 80b8f008 b softirq_stack
 80b97008 b hardirq_stack
 80b9f008 b bm_pte

So all subsequent variables get unaligned which, depending on luck,
breaks the kernel in various funny ways. In this case what killed the
kernel first was the misaligned bootmap pte page, resulting in that
creative crash above.

Anyway, this was a fun bug to track down :-)

I think the moral is that .bss.page_aligned is a dangerous construct in
its current form, and the symptoms of breakage are very non-trivial, so
i think we need build-time checks to make sure all symbols in
.bss.page_aligned are truly page aligned.

The Xen fix below gets the kernel booting again.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/mmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e95955968ba3..eef3b5c6e2fe 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -73,7 +73,8 @@ static unsigned long *p2m_top[TOP_ENTRIES]
 static unsigned long p2m_top_mfn[TOP_ENTRIES]
 	__attribute__((section(".bss.page_aligned")));
 
-static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
+static unsigned long p2m_top_mfn_list[
+			PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)]
 	__attribute__((section(".bss.page_aligned")));
 
 static inline unsigned p2m_top_index(unsigned long pfn)
-- 
cgit v1.2.2


From a16ffe93c46dfca211434d00453ebb695025978b Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Fri, 30 May 2008 15:09:42 -0500
Subject: lguest: fix ugly <NULL> in /proc/interrupts

Before:
	root@ubuntu:~# cat /proc/interrupts
	           CPU0
	  1:       1672    lguest-<NULL>    virtio0
	  2:          1    lguest-<NULL>    virtio1
	  ...
After:
	root@ubuntu:~# cat /proc/interrupts
	           CPU0
	  1:       2889    lguest-level     virtio0
	  2:          9    lguest-level     virtio1

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 arch/x86/lguest/boot.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index af65b2da3ba0..5c7e2fd52075 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -582,8 +582,9 @@ static void __init lguest_init_IRQ(void)
 		int vector = FIRST_EXTERNAL_VECTOR + i;
 		if (vector != SYSCALL_VECTOR) {
 			set_intr_gate(vector, interrupt[i]);
-			set_irq_chip_and_handler(i, &lguest_irq_controller,
-						 handle_level_irq);
+			set_irq_chip_and_handler_name(i, &lguest_irq_controller,
+						      handle_level_irq,
+						      "level");
 		}
 	}
 	/* This call is required to set up for 4k stacks, where we have
-- 
cgit v1.2.2


From d364319b989967b74e57fef5c8017fd56a16c392 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 2 May 2008 23:42:01 +0200
Subject: x86: move mmconfig declarations to header

arch/x86/kernel/mmconf-fam10h_64.c is missing the prototypes, which
are decalred in arch/x86/kernel/setup_64.c. Move the prototypes and
the inline stubs to the appropriate header file.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/mmconf-fam10h_64.c |  1 +
 arch/x86/kernel/setup_64.c         | 13 +------------
 2 files changed, 2 insertions(+), 12 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index edc5fbfe85c0..fdfdc550b366 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -12,6 +12,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/acpi.h>
+#include <asm/mmconfig.h>
 
 #include "../pci/pci.h"
 
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6dff1286ad8a..341230db74e1 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -71,6 +71,7 @@
 #include <asm/topology.h>
 #include <asm/trampoline.h>
 #include <asm/pat.h>
+#include <asm/mmconfig.h>
 
 #include <mach_apic.h>
 #ifdef CONFIG_PARAVIRT
@@ -293,18 +294,6 @@ static void __init parse_setup_data(void)
 	}
 }
 
-#ifdef CONFIG_PCI_MMCONFIG
-extern void __cpuinit fam10h_check_enable_mmcfg(void);
-extern void __init check_enable_amd_mmconf_dmi(void);
-#else
-void __cpuinit fam10h_check_enable_mmcfg(void)
-{
-}
-void __init check_enable_amd_mmconf_dmi(void)
-{
-}
-#endif
-
 /*
  * setup_arch - architecture-specific boot-time initializations
  *
-- 
cgit v1.2.2


From 4d285878564bb46cf64e54be18eeffe33ca583a0 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Thu, 22 May 2008 18:48:32 -0400
Subject: x86: Move the AMD64 specific parts out of setup_64.c

Create a separate amd_64.c file in the cpu/ dir for
the useful parts to live in.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/Makefile |   1 +
 arch/x86/kernel/cpu/amd_64.c | 235 +++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/setup_64.c   | 232 ++----------------------------------------
 3 files changed, 242 insertions(+), 226 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/amd_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a0c6f8190887..ef065c1a2e1a 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -7,6 +7,7 @@ obj-y			+= proc.o feature_names.o
 
 obj-$(CONFIG_X86_32)	+= common.o bugs.o
 obj-$(CONFIG_X86_32)	+= amd.o
+obj-$(CONFIG_X86_64)	+= amd_64.o
 obj-$(CONFIG_X86_32)	+= cyrix.o
 obj-$(CONFIG_X86_32)	+= centaur.o
 obj-$(CONFIG_X86_32)	+= transmeta.o
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
new file mode 100644
index 000000000000..1746f6f95726
--- /dev/null
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -0,0 +1,235 @@
+#include <linux/init.h>
+#include <linux/mm.h>
+
+#include <asm/numa_64.h>
+#include <asm/mmconfig.h>
+#include <asm/cacheflush.h>
+
+#include <mach_apic.h>
+
+extern int __cpuinit get_model_name(struct cpuinfo_x86 *c);
+extern void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c);
+
+int force_mwait __cpuinitdata;
+
+#ifdef CONFIG_NUMA
+static int __cpuinit nearby_node(int apicid)
+{
+	int i, node;
+
+	for (i = apicid - 1; i >= 0; i--) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+		node = apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+/*
+ * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned bits;
+#ifdef CONFIG_NUMA
+	int cpu = smp_processor_id();
+	int node = 0;
+	unsigned apicid = hard_smp_processor_id();
+#endif
+	bits = c->x86_coreid_bits;
+
+	/* Low order bits define the core id (index of core in socket) */
+	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+	/* Convert the initial APIC ID into the socket ID */
+	c->phys_proc_id = c->initial_apicid >> bits;
+
+#ifdef CONFIG_NUMA
+	node = c->phys_proc_id;
+	if (apicid_to_node[apicid] != NUMA_NO_NODE)
+		node = apicid_to_node[apicid];
+	if (!node_online(node)) {
+		/* Two possibilities here:
+		   - The CPU is missing memory and no node was created.
+		   In that case try picking one from a nearby CPU
+		   - The APIC IDs differ from the HyperTransport node IDs
+		   which the K8 northbridge parsing fills in.
+		   Assume they are all increased by a constant offset,
+		   but in the same order as the HT nodeids.
+		   If that doesn't result in a usable node fall back to the
+		   path for the previous case.  */
+
+		int ht_nodeid = c->initial_apicid;
+
+		if (ht_nodeid >= 0 &&
+		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = apicid_to_node[ht_nodeid];
+		/* Pick a nearby node */
+		if (!node_online(node))
+			node = nearby_node(apicid);
+	}
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+#endif
+}
+
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned bits, ecx;
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level < 0x80000008)
+		return;
+
+	ecx = cpuid_ecx(0x80000008);
+
+	c->x86_max_cores = (ecx & 0xff) + 1;
+
+	/* CPU telling us the core id bits shift? */
+	bits = (ecx >> 12) & 0xF;
+
+	/* Otherwise recompute */
+	if (bits == 0) {
+		while ((1 << bits) < c->x86_max_cores)
+			bits++;
+	}
+
+	c->x86_coreid_bits = bits;
+
+#endif
+}
+
+#define ENABLE_C1E_MASK		0x18000000
+#define CPUID_PROCESSOR_SIGNATURE	1
+#define CPUID_XFAM		0x0ff00000
+#define CPUID_XFAM_K8		0x00000000
+#define CPUID_XFAM_10H		0x00100000
+#define CPUID_XFAM_11H		0x00200000
+#define CPUID_XMOD		0x000f0000
+#define CPUID_XMOD_REV_F	0x00040000
+
+/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
+static __cpuinit int amd_apic_timer_broken(void)
+{
+	u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
+
+	switch (eax & CPUID_XFAM) {
+	case CPUID_XFAM_K8:
+		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
+			break;
+	case CPUID_XFAM_10H:
+	case CPUID_XFAM_11H:
+		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
+		if (lo & ENABLE_C1E_MASK)
+			return 1;
+		break;
+	default:
+		/* err on the side of caution */
+		return 1;
+	}
+	return 0;
+}
+
+void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+	early_init_amd_mc(c);
+
+	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+	if (c->x86_power & (1<<8))
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+void __cpuinit init_amd(struct cpuinfo_x86 *c)
+{
+	unsigned level;
+
+#ifdef CONFIG_SMP
+	unsigned long value;
+
+	/*
+	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
+	 * bit 6 of msr C001_0015
+	 *
+	 * Errata 63 for SH-B3 steppings
+	 * Errata 122 for all steppings (F+ have it disabled by default)
+	 */
+	if (c->x86 == 15) {
+		rdmsrl(MSR_K8_HWCR, value);
+		value |= 1 << 6;
+		wrmsrl(MSR_K8_HWCR, value);
+	}
+#endif
+
+	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+	clear_cpu_cap(c, 0*32+31);
+
+	/* On C+ stepping K8 rep microcode works well for copy/memset */
+	level = cpuid_eax(1);
+	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
+			     level >= 0x0f58))
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	if (c->x86 == 0x10 || c->x86 == 0x11)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* Enable workaround for FXSAVE leak */
+	if (c->x86 >= 6)
+		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
+
+	level = get_model_name(c);
+	if (!level) {
+		switch (c->x86) {
+		case 15:
+			/* Should distinguish Models here, but this is only
+			   a fallback anyways. */
+			strcpy(c->x86_model_id, "Hammer");
+			break;
+		}
+	}
+	display_cacheinfo(c);
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level >= 0x80000008)
+		amd_detect_cmp(c);
+
+	if (c->extended_cpuid_level >= 0x80000006 &&
+		(cpuid_edx(0x80000006) & 0xf000))
+		num_cache_leaves = 4;
+	else
+		num_cache_leaves = 3;
+
+	if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
+		set_cpu_cap(c, X86_FEATURE_K8);
+
+	/* MFENCE stops RDTSC speculation */
+	set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+
+	if (c->x86 == 0x10)
+		fam10h_check_enable_mmcfg();
+
+	if (amd_apic_timer_broken())
+		disable_apic_timer = 1;
+
+	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+		unsigned long long tseg;
+
+		/*
+		 * Split up direct mapping around the TSEG SMM area.
+		 * Don't do it for gbpages because there seems very little
+		 * benefit in doing so.
+		 */
+		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
+		(tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
+			set_memory_4k((unsigned long)__va(tseg), 1);
+	}
+}
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 341230db74e1..b07b1997ed97 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -96,8 +96,6 @@ int bootloader_type;
 
 unsigned long saved_video_mode;
 
-int force_mwait __cpuinitdata;
-
 /*
  * Early DMI memory
  */
@@ -526,7 +524,7 @@ void __init setup_arch(char **cmdline_p)
 	check_enable_amd_mmconf_dmi();
 }
 
-static int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
 
@@ -542,7 +540,7 @@ static int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 }
 
 
-static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
+void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, eax, ebx, ecx, edx;
 
@@ -574,228 +572,6 @@ static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 	}
 }
 
-#ifdef CONFIG_NUMA
-static int __cpuinit nearby_node(int apicid)
-{
-	int i, node;
-
-	for (i = apicid - 1; i >= 0; i--) {
-		node = apicid_to_node[i];
-		if (node != NUMA_NO_NODE && node_online(node))
-			return node;
-	}
-	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-		node = apicid_to_node[i];
-		if (node != NUMA_NO_NODE && node_online(node))
-			return node;
-	}
-	return first_node(node_online_map); /* Shouldn't happen */
-}
-#endif
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
- * Assumes number of cores is a power of two.
- */
-static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned bits;
-#ifdef CONFIG_NUMA
-	int cpu = smp_processor_id();
-	int node = 0;
-	unsigned apicid = hard_smp_processor_id();
-#endif
-	bits = c->x86_coreid_bits;
-
-	/* Low order bits define the core id (index of core in socket) */
-	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
-	/* Convert the initial APIC ID into the socket ID */
-	c->phys_proc_id = c->initial_apicid >> bits;
-
-#ifdef CONFIG_NUMA
-	node = c->phys_proc_id;
-	if (apicid_to_node[apicid] != NUMA_NO_NODE)
-		node = apicid_to_node[apicid];
-	if (!node_online(node)) {
-		/* Two possibilities here:
-		   - The CPU is missing memory and no node was created.
-		   In that case try picking one from a nearby CPU
-		   - The APIC IDs differ from the HyperTransport node IDs
-		   which the K8 northbridge parsing fills in.
-		   Assume they are all increased by a constant offset,
-		   but in the same order as the HT nodeids.
-		   If that doesn't result in a usable node fall back to the
-		   path for the previous case.  */
-
-		int ht_nodeid = c->initial_apicid;
-
-		if (ht_nodeid >= 0 &&
-		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-			node = apicid_to_node[ht_nodeid];
-		/* Pick a nearby node */
-		if (!node_online(node))
-			node = nearby_node(apicid);
-	}
-	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-#endif
-}
-
-static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned bits, ecx;
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level < 0x80000008)
-		return;
-
-	ecx = cpuid_ecx(0x80000008);
-
-	c->x86_max_cores = (ecx & 0xff) + 1;
-
-	/* CPU telling us the core id bits shift? */
-	bits = (ecx >> 12) & 0xF;
-
-	/* Otherwise recompute */
-	if (bits == 0) {
-		while ((1 << bits) < c->x86_max_cores)
-			bits++;
-	}
-
-	c->x86_coreid_bits = bits;
-
-#endif
-}
-
-#define ENABLE_C1E_MASK		0x18000000
-#define CPUID_PROCESSOR_SIGNATURE	1
-#define CPUID_XFAM		0x0ff00000
-#define CPUID_XFAM_K8		0x00000000
-#define CPUID_XFAM_10H		0x00100000
-#define CPUID_XFAM_11H		0x00200000
-#define CPUID_XMOD		0x000f0000
-#define CPUID_XMOD_REV_F	0x00040000
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
-{
-	u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
-
-	switch (eax & CPUID_XFAM) {
-	case CPUID_XFAM_K8:
-		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
-			break;
-	case CPUID_XFAM_10H:
-	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-		if (lo & ENABLE_C1E_MASK)
-			return 1;
-		break;
-	default:
-		/* err on the side of caution */
-		return 1;
-	}
-	return 0;
-}
-
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
-{
-	early_init_amd_mc(c);
-
- 	/* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
-	if (c->x86_power & (1<<8))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-}
-
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
-{
-	unsigned level;
-
-#ifdef CONFIG_SMP
-	unsigned long value;
-
-	/*
-	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
-	 * bit 6 of msr C001_0015
-	 *
-	 * Errata 63 for SH-B3 steppings
-	 * Errata 122 for all steppings (F+ have it disabled by default)
-	 */
-	if (c->x86 == 15) {
-		rdmsrl(MSR_K8_HWCR, value);
-		value |= 1 << 6;
-		wrmsrl(MSR_K8_HWCR, value);
-	}
-#endif
-
-	/* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
-	   3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
-	clear_cpu_cap(c, 0*32+31);
-
-	/* On C+ stepping K8 rep microcode works well for copy/memset */
-	level = cpuid_eax(1);
-	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
-			     level >= 0x0f58))
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-	if (c->x86 == 0x10 || c->x86 == 0x11)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
-		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-
-	level = get_model_name(c);
-	if (!level) {
-		switch (c->x86) {
-		case 15:
-			/* Should distinguish Models here, but this is only
-			   a fallback anyways. */
-			strcpy(c->x86_model_id, "Hammer");
-			break;
-		}
-	}
-	display_cacheinfo(c);
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008)
-		amd_detect_cmp(c);
-
-	if (c->extended_cpuid_level >= 0x80000006 &&
-		(cpuid_edx(0x80000006) & 0xf000))
-		num_cache_leaves = 4;
-	else
-		num_cache_leaves = 3;
-
-	if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
-		set_cpu_cap(c, X86_FEATURE_K8);
-
-	/* MFENCE stops RDTSC speculation */
-	set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-
-	if (c->x86 == 0x10)
-		fam10h_check_enable_mmcfg();
-
-	if (amd_apic_timer_broken())
-		disable_apic_timer = 1;
-
-	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
-		unsigned long long tseg;
-
-		/*
-		 * Split up direct mapping around the TSEG SMM area.
-		 * Don't do it for gbpages because there seems very little
-		 * benefit in doing so.
-		 */
-		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
-		(tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
-			set_memory_4k((unsigned long)__va(tseg), 1);
-	}
-}
-
 void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
@@ -977,6 +753,10 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 		c->x86_vendor = X86_VENDOR_UNKNOWN;
 }
 
+// FIXME: Needs to use cpu_vendor_dev_register
+extern void __cpuinit early_init_amd(struct cpuinfo_x86 *c);
+extern void __cpuinit init_amd(struct cpuinfo_x86 *c);
+
 /* Do some early cpuid on the boot CPU to get some parameter that are
    needed before check_bugs. Everything advanced is in identify_cpu
    below. */
-- 
cgit v1.2.2


From a82fbe31cb387bb246e2d3b3c177f551bb991135 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Thu, 22 May 2008 18:54:32 -0400
Subject: x86: Move the 64-bit Intel specific parts out of setup_64.c

Create a separate intel_64.c file in the cpu/ dir for
the useful parts to live in.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/Makefile   |  1 +
 arch/x86/kernel/cpu/intel_64.c | 97 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/setup_64.c     | 93 +---------------------------------------
 3 files changed, 100 insertions(+), 91 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/intel_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index ef065c1a2e1a..b7a11924fed7 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_X86_32)	+= cyrix.o
 obj-$(CONFIG_X86_32)	+= centaur.o
 obj-$(CONFIG_X86_32)	+= transmeta.o
 obj-$(CONFIG_X86_32)	+= intel.o
+obj-$(CONFIG_X86_64)	+= intel_64.o
 obj-$(CONFIG_X86_32)	+= umc.o
 
 obj-$(CONFIG_X86_MCE)	+= mcheck/
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
new file mode 100644
index 000000000000..e5f929f6c3d4
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -0,0 +1,97 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/topology.h>
+#include <asm/numa_64.h>
+
+void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+{
+	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
+	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+/*
+ * find out the number of processor cores on the die
+ */
+static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+	unsigned int eax, t;
+
+	if (c->cpuid_level < 4)
+		return 1;
+
+	cpuid_count(4, 0, &eax, &t, &t, &t);
+
+	if (eax & 0x1f)
+		return ((eax >> 26) + 1);
+	else
+		return 1;
+}
+
+static void __cpuinit srat_detect_node(void)
+{
+#ifdef CONFIG_NUMA
+	unsigned node;
+	int cpu = smp_processor_id();
+	int apicid = hard_smp_processor_id();
+
+	/* Don't do the funky fallback heuristics the AMD version employs
+	   for now. */
+	node = apicid_to_node[apicid];
+	if (node == NUMA_NO_NODE || !node_online(node))
+		node = first_node(node_online_map);
+	numa_set_node(cpu, node);
+
+	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
+
+void __cpuinit init_intel(struct cpuinfo_x86 *c)
+{
+	/* Cache sizes */
+	unsigned n;
+
+	init_intel_cacheinfo(c);
+	if (c->cpuid_level > 9) {
+		unsigned eax = cpuid_eax(10);
+		/* Check for version and the number of counters */
+		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
+	if (cpu_has_ds) {
+		unsigned int l1, l2;
+		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+		if (!(l1 & (1<<11)))
+			set_cpu_cap(c, X86_FEATURE_BTS);
+		if (!(l1 & (1<<12)))
+			set_cpu_cap(c, X86_FEATURE_PEBS);
+	}
+
+
+	if (cpu_has_bts)
+		ds_init_intel(c);
+
+	n = c->extended_cpuid_level;
+	if (n >= 0x80000008) {
+		unsigned eax = cpuid_eax(0x80000008);
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+		/* CPUID workaround for Intel 0F34 CPU */
+		if (c->x86_vendor == X86_VENDOR_INTEL &&
+		    c->x86 == 0xF && c->x86_model == 0x3 &&
+		    c->x86_mask == 0x4)
+			c->x86_phys_bits = 36;
+	}
+
+	if (c->x86 == 15)
+		c->x86_cache_alignment = c->x86_clflush_size * 2;
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+	c->x86_max_cores = intel_num_cpu_cores(c);
+
+	srat_detect_node();
+}
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index b07b1997ed97..c4e6a0b6c303 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -622,97 +622,6 @@ out:
 #endif
 }
 
-/*
- * find out the number of processor cores on the die
- */
-static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-	unsigned int eax, t;
-
-	if (c->cpuid_level < 4)
-		return 1;
-
-	cpuid_count(4, 0, &eax, &t, &t, &t);
-
-	if (eax & 0x1f)
-		return ((eax >> 26) + 1);
-	else
-		return 1;
-}
-
-static void __cpuinit srat_detect_node(void)
-{
-#ifdef CONFIG_NUMA
-	unsigned node;
-	int cpu = smp_processor_id();
-	int apicid = hard_smp_processor_id();
-
-	/* Don't do the funky fallback heuristics the AMD version employs
-	   for now. */
-	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
-		node = first_node(node_online_map);
-	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-}
-
-static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
-{
-	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
-	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-}
-
-static void __cpuinit init_intel(struct cpuinfo_x86 *c)
-{
-	/* Cache sizes */
-	unsigned n;
-
-	init_intel_cacheinfo(c);
-	if (c->cpuid_level > 9) {
-		unsigned eax = cpuid_eax(10);
-		/* Check for version and the number of counters */
-		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
-			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
-	}
-
-	if (cpu_has_ds) {
-		unsigned int l1, l2;
-		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
-		if (!(l1 & (1<<11)))
-			set_cpu_cap(c, X86_FEATURE_BTS);
-		if (!(l1 & (1<<12)))
-			set_cpu_cap(c, X86_FEATURE_PEBS);
-	}
-
-
-	if (cpu_has_bts)
-		ds_init_intel(c);
-
-	n = c->extended_cpuid_level;
-	if (n >= 0x80000008) {
-		unsigned eax = cpuid_eax(0x80000008);
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-		/* CPUID workaround for Intel 0F34 CPU */
-		if (c->x86_vendor == X86_VENDOR_INTEL &&
-		    c->x86 == 0xF && c->x86_model == 0x3 &&
-		    c->x86_mask == 0x4)
-			c->x86_phys_bits = 36;
-	}
-
-	if (c->x86 == 15)
-		c->x86_cache_alignment = c->x86_clflush_size * 2;
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-	c->x86_max_cores = intel_num_cpu_cores(c);
-
-	srat_detect_node();
-}
-
 static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 {
 	if (c->x86 == 0x6 && c->x86_model >= 0xf)
@@ -756,6 +665,8 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 // FIXME: Needs to use cpu_vendor_dev_register
 extern void __cpuinit early_init_amd(struct cpuinfo_x86 *c);
 extern void __cpuinit init_amd(struct cpuinfo_x86 *c);
+extern void __cpuinit early_init_intel(struct cpuinfo_x86 *c);
+extern void __cpuinit init_intel(struct cpuinfo_x86 *c);
 
 /* Do some early cpuid on the boot CPU to get some parameter that are
    needed before check_bugs. Everything advanced is in identify_cpu
-- 
cgit v1.2.2


From 7e2191127eb414d7d5a11df6552ab6e3845d17a1 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Thu, 22 May 2008 18:55:06 -0400
Subject: x86: Remove workaround for prescott (32bit P4) from 64-bit code.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/intel_64.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
index e5f929f6c3d4..b33912199484 100644
--- a/arch/x86/kernel/cpu/intel_64.c
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -79,11 +79,6 @@ void __cpuinit init_intel(struct cpuinfo_x86 *c)
 		unsigned eax = cpuid_eax(0x80000008);
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
-		/* CPUID workaround for Intel 0F34 CPU */
-		if (c->x86_vendor == X86_VENDOR_INTEL &&
-		    c->x86 == 0xF && c->x86_model == 0x3 &&
-		    c->x86_mask == 0x4)
-			c->x86_phys_bits = 36;
 	}
 
 	if (c->x86 == 15)
-- 
cgit v1.2.2


From 30a713180b3d08fdec5ca572e5a1cd35253c5d8e Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Thu, 22 May 2008 18:57:25 -0400
Subject: x86: Move the 64-bit Centaur specific parts out of setup_64.c

Create a separate centaur_64.c file in the cpu/ dir for
the useful parts to live in.

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/Makefile     |  1 +
 arch/x86/kernel/cpu/centaur_64.c | 31 +++++++++++++++++++++++++++++++
 arch/x86/kernel/setup_64.c       | 28 ++--------------------------
 3 files changed, 34 insertions(+), 26 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/centaur_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index b7a11924fed7..c77a1c50d944 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_X86_32)	+= amd.o
 obj-$(CONFIG_X86_64)	+= amd_64.o
 obj-$(CONFIG_X86_32)	+= cyrix.o
 obj-$(CONFIG_X86_32)	+= centaur.o
+obj-$(CONFIG_X86_64)	+= centaur_64.o
 obj-$(CONFIG_X86_32)	+= transmeta.o
 obj-$(CONFIG_X86_32)	+= intel.o
 obj-$(CONFIG_X86_64)	+= intel_64.o
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
new file mode 100644
index 000000000000..bac96d187d05
--- /dev/null
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -0,0 +1,31 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
+{
+	if (c->x86 == 0x6 && c->x86_model >= 0xf)
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+void __cpuinit init_centaur(struct cpuinfo_x86 *c)
+{
+	/* Cache sizes */
+	unsigned n;
+
+	n = c->extended_cpuid_level;
+	if (n >= 0x80000008) {
+		unsigned eax = cpuid_eax(0x80000008);
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+	}
+
+	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
+		c->x86_cache_alignment = c->x86_clflush_size * 2;
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+	}
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+}
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index c4e6a0b6c303..25afdd80a3cf 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -622,32 +622,6 @@ out:
 #endif
 }
 
-static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
-{
-	if (c->x86 == 0x6 && c->x86_model >= 0xf)
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-}
-
-static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
-{
-	/* Cache sizes */
-	unsigned n;
-
-	n = c->extended_cpuid_level;
-	if (n >= 0x80000008) {
-		unsigned eax = cpuid_eax(0x80000008);
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	}
-
-	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
-		c->x86_cache_alignment = c->x86_clflush_size * 2;
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-	}
-	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-}
-
 static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 {
 	char *v = c->x86_vendor_id;
@@ -667,6 +641,8 @@ extern void __cpuinit early_init_amd(struct cpuinfo_x86 *c);
 extern void __cpuinit init_amd(struct cpuinfo_x86 *c);
 extern void __cpuinit early_init_intel(struct cpuinfo_x86 *c);
 extern void __cpuinit init_intel(struct cpuinfo_x86 *c);
+extern void __cpuinit early_init_centaur(struct cpuinfo_x86 *c);
+extern void __cpuinit init_centaur(struct cpuinfo_x86 *c);
 
 /* Do some early cpuid on the boot CPU to get some parameter that are
    needed before check_bugs. Everything advanced is in identify_cpu
-- 
cgit v1.2.2


From 1c47cd638e8302bc38be1f6d81067950e038ebd3 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Fri, 30 May 2008 15:42:45 -0700
Subject: x86: fix overlong line in arch/x86/kernel/cpu/amd_64.c

Clean up an overlong line in arch/x86/kernel/cpu/amd_64.c.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/amd_64.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 1746f6f95726..c815c2c0484b 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -229,7 +229,8 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		 * benefit in doing so.
 		 */
 		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
-		(tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
+		    (tseg >> PMD_SHIFT) <
+			(max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
 			set_memory_4k((unsigned long)__va(tseg), 1);
 	}
 }
-- 
cgit v1.2.2


From 75b19b790bec3ebffbf513405b27500e22270cbc Mon Sep 17 00:00:00 2001
From: Bertram Felgenhauer <int-e@gmx.de>
Date: Fri, 30 May 2008 03:20:05 +0200
Subject: pci, x86: add workaround for bug in ASUS A7V600 BIOS (rev 1005)

This BIOS claims the VIA 8237 south bridge to be compatible with VIA 586,
which it is not.

Without this patch, I get the following warning while booting,
among others,

| PCI: Using IRQ router VIA [1106/3227] at 0000:00:11.0
| ------------[ cut here ]------------
| WARNING: at arch/x86/pci/irq.c:265 pirq_via586_get+0x4a/0x60()
| Modules linked in:
| Pid: 1, comm: swapper Not tainted 2.6.26-rc4-00015-g1ec7d99 #1
|  [<c0119fd4>] warn_on_slowpath+0x54/0x70
|  [<c02246e0>] ? vt_console_print+0x210/0x2b0
|  [<c02244d0>] ? vt_console_print+0x0/0x2b0
|  [<c011a413>] ? __call_console_drivers+0x43/0x60
|  [<c011a482>] ? _call_console_drivers+0x52/0x80
|  [<c011aa89>] ? release_console_sem+0x1c9/0x200
|  [<c0291d21>] ? raw_pci_read+0x41/0x70
|  [<c0291e8f>] ? pci_read+0x2f/0x40
|  [<c029151a>] pirq_via586_get+0x4a/0x60
|  [<c02914d0>] ? pirq_via586_get+0x0/0x60
|  [<c029178d>] pcibios_lookup_irq+0x15d/0x430
|  [<c03b895a>] pcibios_irq_init+0x17a/0x3e0
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c03a6763>] kernel_init+0x73/0x250
|  [<c03b87e0>] ? pcibios_irq_init+0x0/0x3e0
|  [<c0114d00>] ? schedule_tail+0x10/0x40
|  [<c0102dee>] ? ret_from_fork+0x6/0x1c
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c010324b>] kernel_thread_helper+0x7/0x1c
|  =======================
| ---[ end trace 4eaa2a86a8e2da22 ]---

and IRQ trouble later,

| irq 10: nobody cared (try booting with the "irqpoll" option)

Now that's an VIA 8237 chip, so pirq_via586_get shouldn't be called
at all; adding this workaround to via_router_probe() fixes the
problem for me.

Amazingly I have a 2.6.23.8 kernel that somehow works fine ... I'll
never understand why.

Signed-off-by: Bertram Felgenhauer <int-e@gmx.de>
Acked-by: Alan Cox <alan@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/pci/irq.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0908fca901bf..ca8df9c260bc 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -621,6 +621,13 @@ static __init int via_router_probe(struct irq_router *r,
 			 */
 			device = PCI_DEVICE_ID_VIA_8235;
 			break;
+		case PCI_DEVICE_ID_VIA_8237:
+			/**
+			 * Asus a7v600 bios wrongly reports 8237
+			 * as 586-compatible
+			 */
+			device = PCI_DEVICE_ID_VIA_8237;
+			break;
 		}
 	}
 
-- 
cgit v1.2.2


From 831d991821daedd4839073dbca55514432ef1768 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Mon, 3 Sep 2007 10:17:39 +0200
Subject: x86: add PCI extended config space access for AMD Barcelona

This patch implements PCI extended configuration space access for
AMD's Barcelona CPUs. It extends the method using CF8/CFC IO
addresses. An x86 capability bit has been introduced that is set for
CPUs supporting PCI extended config space accesses.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd.c    |  4 ++++
 arch/x86/kernel/cpu/amd_64.c |  3 +++
 arch/x86/kernel/setup.c      | 13 +++++++++++++
 arch/x86/kernel/setup.h      | 26 ++++++++++++++++++++++++++
 arch/x86/kernel/setup_64.c   |  2 ++
 arch/x86/pci/direct.c        | 21 +++++++++++++++------
 6 files changed, 63 insertions(+), 6 deletions(-)
 create mode 100644 arch/x86/kernel/setup.h

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 245866828294..99221f9834e4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -6,6 +6,7 @@
 #include <asm/apic.h>
 
 #include <mach_apic.h>
+#include "../setup.h"
 #include "cpu.h"
 
 /*
@@ -308,6 +309,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+
+	if (c->x86 == 0x10)
+		amd_enable_pci_ext_cfg(c);
 }
 
 static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index c815c2c0484b..180097e99219 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -217,6 +217,9 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		fam10h_check_enable_mmcfg();
 
+	if (c->x86 == 0x10)
+		amd_enable_pci_ext_cfg(c);
+
 	if (amd_apic_timer_broken())
 		disable_apic_timer = 1;
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6f80b852a196..d8f171234013 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -136,4 +136,17 @@ void __init setup_per_cpu_areas(void)
 	setup_cpumask_of_cpu();
 }
 
+#define ENABLE_CF8_EXT_CFG      (1ULL << 46)
+
+void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c)
+{
+	u64 reg;
+	rdmsrl(MSR_AMD64_NB_CFG, reg);
+	if (!(reg & ENABLE_CF8_EXT_CFG)) {
+		reg |= ENABLE_CF8_EXT_CFG;
+		wrmsrl(MSR_AMD64_NB_CFG, reg);
+	}
+	set_cpu_cap(c, X86_FEATURE_PCI_EXT_CFG);
+}
+
 #endif
diff --git a/arch/x86/kernel/setup.h b/arch/x86/kernel/setup.h
new file mode 100644
index 000000000000..66cc2c7f961d
--- /dev/null
+++ b/arch/x86/kernel/setup.h
@@ -0,0 +1,26 @@
+/*
+ * Internal declarations for shared x86 setup code.
+ *
+ * Copyright (c) 2008 Advanced Micro Devices, Inc.
+ * Contributed by Robert Richter <robert.richter@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307 USA
+ */
+
+#ifndef _ARCH_X86_KERNEL_SETUP_H
+
+extern void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c);
+
+#endif	/* _ARCH_X86_KERNEL_SETUP_H */
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 25afdd80a3cf..215bd67e5b6c 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -73,6 +73,8 @@
 #include <asm/pat.h>
 #include <asm/mmconfig.h>
 
+#include "setup.h"
+
 #include <mach_apic.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 21d1e0e0d535..27d61b63def6 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -8,18 +8,21 @@
 #include "pci.h"
 
 /*
- * Functions for accessing PCI configuration space with type 1 accesses
+ * Functions for accessing PCI base (first 256 bytes) and extended
+ * (4096 bytes per PCI function) configuration space with type 1
+ * accesses.
  */
 
 #define PCI_CONF1_ADDRESS(bus, devfn, reg) \
-	(0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3))
+	(0x80000000 | ((reg & 0xF00) << 16) | (bus << 16) \
+	| (devfn << 8) | (reg & 0xFC))
 
 static int pci_conf1_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
 	unsigned long flags;
 
-	if ((bus > 255) || (devfn > 255) || (reg > 255)) {
+	if ((bus > 255) || (devfn > 255) || (reg > 4095)) {
 		*value = -1;
 		return -EINVAL;
 	}
@@ -50,7 +53,7 @@ static int pci_conf1_write(unsigned int seg, unsigned int bus,
 {
 	unsigned long flags;
 
-	if ((bus > 255) || (devfn > 255) || (reg > 255)) 
+	if ((bus > 255) || (devfn > 255) || (reg > 4095))
 		return -EINVAL;
 
 	spin_lock_irqsave(&pci_config_lock, flags);
@@ -260,10 +263,16 @@ void __init pci_direct_init(int type)
 		return;
 	printk(KERN_INFO "PCI: Using configuration type %d for base access\n",
 		 type);
-	if (type == 1)
+	if (type == 1) {
 		raw_pci_ops = &pci_direct_conf1;
-	else
+		if (!raw_pci_ext_ops && cpu_has_pci_ext_cfg) {
+			printk(KERN_INFO "PCI: Using configuration type 1 "
+			       "for extended access\n");
+			raw_pci_ext_ops = &pci_direct_conf1;
+		}
+	} else {
 		raw_pci_ops = &pci_direct_conf2;
+	}
 }
 
 int __init pci_direct_probe(void)
-- 
cgit v1.2.2


From db9f600b96c16bb3c7f094e294fbdd370226ad86 Mon Sep 17 00:00:00 2001
From: Miquel van Smoorenburg <mikevs@xs4all.net>
Date: Wed, 28 May 2008 10:31:25 +0200
Subject: x86: pci-dma.c: use __GFP_NO_OOM instead of __GFP_NORETRY

On Wed, 2008-05-28 at 04:47 +0200, Andi Kleen wrote:
> > So...  why not just remove the setting of __GFP_NORETRY?  Why is it
> > wrong to oom-kill things in this case?
>
> When the 16MB zone overflows (which can be common in some workloads)
> calling the OOM killer is pretty useless because it has barely any
> real user data [only exception would be the "only 16MB" case Alan
> mentioned]. Killing random processes in this case is bad.
>
> I think for 16MB __GFP_NORETRY is ok because there should be
> nothing freeable in there so looping is useless. Only exception would be the
> "only 16MB total" case again but I'm not sure 2.6 supports that at all
> on x86.
>
> On the other hand d_a_c() does more allocations than just 16MB, especially
> on 64bit and the other zones need different strategies.

Okay, so how about this then ?

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-dma.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index c5ef1af8e79d..069e843f0b93 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -397,9 +397,6 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dev->dma_mask == NULL)
 		return NULL;
 
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
 #ifdef CONFIG_X86_64
 	/* Why <=? Even when the mask is smaller than 4GB it is often
 	   larger than 16MB and in this case we have a chance of
@@ -410,7 +407,9 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 #endif
 
  again:
-	page = dma_alloc_pages(dev, gfp, get_order(size));
+	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+	page = dma_alloc_pages(dev,
+		(gfp & GFP_DMA) ? gfp | __GFP_NORETRY : gfp, get_order(size));
 	if (page == NULL)
 		return NULL;
 
-- 
cgit v1.2.2


From 1a5726528a70bb239bdd149aef7f2155cd2b1699 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 2 Jun 2008 12:21:36 +0200
Subject: fix build bug in "x86: add PCI extended config space access for AMD
 Barcelona"

---
 arch/x86/kernel/cpu/amd.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 99221f9834e4..656b40aed647 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -4,6 +4,7 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#include <asm/mmconfig.h>
 
 #include <mach_apic.h>
 #include "../setup.h"
-- 
cgit v1.2.2


From f529626a86d61897862aa1bbbb4537773209238e Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Thu, 29 May 2008 00:30:21 -0700
Subject: suspend-vs-iommu: prevent suspend if we could not resume

iommu/gart support misses suspend/resume code, which can do bad stuff,
including memory corruption on resume.  Prevent system suspend in case we
would be unable to resume.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Tested-by: Patrick <ragamuffin@datacomm.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-gart_64.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c07455d1695f..aa8ec928caa8 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+#include <linux/sysdev.h>
 #include <asm/atomic.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
@@ -548,6 +549,28 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
 	return aper_base;
 }
 
+static int gart_resume(struct sys_device *dev)
+{
+	return 0;
+}
+
+static int gart_suspend(struct sys_device *dev, pm_message_t state)
+{
+	return -EINVAL;
+}
+
+static struct sysdev_class gart_sysdev_class = {
+	.name = "gart",
+	.suspend = gart_suspend,
+	.resume = gart_resume,
+
+};
+
+static struct sys_device device_gart = {
+	.id	= 0,
+	.cls	= &gart_sysdev_class,
+};
+
 /*
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
@@ -558,7 +581,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	unsigned aper_base, new_aper_base;
 	struct pci_dev *dev;
 	void *gatt;
-	int i;
+	int i, error;
 
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
@@ -606,6 +629,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 		pci_write_config_dword(dev, 0x90, ctl);
 	}
+
+	error = sysdev_class_register(&gart_sysdev_class);
+	if (!error)
+		error = sysdev_register(&device_gart);
+	if (error)
+		panic("Could not register gart_sysdev -- would corrupt data on next suspend");
 	flush_gart();
 
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
-- 
cgit v1.2.2


From 15ce60056b24a65b65e28de973a9fd8ac0750a2f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 2 Jun 2008 13:20:11 +0200
Subject: xen: export get_phys_to_machine

-tip testing found the following xen-console symbols trouble:

  ERROR: "get_phys_to_machine" [drivers/video/xen-fbfront.ko] undefined!
  ERROR: "get_phys_to_machine" [drivers/net/xen-netfront.ko] undefined!
  ERROR: "get_phys_to_machine" [drivers/input/xen-kbdfront.ko] undefined!

with:

  http://redhat.com/~mingo/misc/config-Mon_Jun__2_12_25_13_CEST_2008.bad
---
 arch/x86/xen/mmu.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index eef3b5c6e2fe..17f374eb1faa 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -136,6 +136,7 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 	idx = p2m_index(pfn);
 	return p2m_top[topidx][idx];
 }
+EXPORT_SYMBOL_GPL(get_phys_to_machine);
 
 static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
 {
-- 
cgit v1.2.2


From e2426cf85f8db5891fb5831323d2d0c176c4dadc Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Sat, 31 May 2008 01:24:27 +0100
Subject: xen: avoid hypercalls when updating unpinned pud/pmd

When operating on an unpinned pagetable (ie, one under construction or
destruction), it isn't necessary to use a hypercall to update a
pud/pmd entry.  Jan Beulich observed that a similar optimisation
avoided many thousands of hypercalls while doing a kernel build.

One tricky part is that early in the kernel boot there's no page
structure, so we can't check to see if the page is pinned.  In that
case, we just always use the hypercall.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/enlighten.c | 14 +++++++++++---
 arch/x86/xen/mmu.c       | 39 +++++++++++++++++++++++++++++++++++----
 arch/x86/xen/mmu.h       |  8 ++++----
 3 files changed, 50 insertions(+), 11 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b94f63ac228b..ed9f04b3836d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -901,6 +901,14 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
 }
 
+static __init void xen_post_allocator_init(void)
+{
+	pv_mmu_ops.set_pmd = xen_set_pmd;
+	pv_mmu_ops.set_pud = xen_set_pud;
+
+	xen_mark_init_mm_pinned();
+}
+
 /* This is called once we have the cpu_possible_map */
 void xen_setup_vcpu_info_placement(void)
 {
@@ -988,7 +996,7 @@ static const struct pv_init_ops xen_init_ops __initdata = {
 	.banner = xen_banner,
 	.memory_setup = xen_memory_setup,
 	.arch_setup = xen_arch_setup,
-	.post_allocator_init = xen_mark_init_mm_pinned,
+	.post_allocator_init = xen_post_allocator_init,
 };
 
 static const struct pv_time_ops xen_time_ops __initdata = {
@@ -1100,7 +1108,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.set_pte = NULL,	/* see xen_pagetable_setup_* */
 	.set_pte_at = xen_set_pte_at,
-	.set_pmd = xen_set_pmd,
+	.set_pmd = xen_set_pmd_hyper,
 
 	.pte_val = xen_pte_val,
 	.pte_flags = native_pte_val,
@@ -1111,7 +1119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
-	.set_pud = xen_set_pud,
+	.set_pud = xen_set_pud_hyper,
 	.pte_clear = xen_pte_clear,
 	.pmd_clear = xen_pmd_clear,
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 17f374eb1faa..4fa0934db925 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -223,7 +223,14 @@ void make_lowmem_page_readwrite(void *vaddr)
 }
 
 
-void xen_set_pmd(pmd_t *ptr, pmd_t val)
+static bool page_pinned(void *ptr)
+{
+	struct page *page = virt_to_page(ptr);
+
+	return PagePinned(page);
+}
+
+void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 {
 	struct multicall_space mcs;
 	struct mmu_update *u;
@@ -241,6 +248,18 @@ void xen_set_pmd(pmd_t *ptr, pmd_t val)
 	preempt_enable();
 }
 
+void xen_set_pmd(pmd_t *ptr, pmd_t val)
+{
+	/* If page is not pinned, we can just update the entry
+	   directly */
+	if (!page_pinned(ptr)) {
+		*ptr = val;
+		return;
+	}
+
+	xen_set_pmd_hyper(ptr, val);
+}
+
 /*
  * Associate a virtual page frame with a given physical page frame
  * and protection flags for that frame.
@@ -348,7 +367,7 @@ pmdval_t xen_pmd_val(pmd_t pmd)
 	return ret;
 }
 
-void xen_set_pud(pud_t *ptr, pud_t val)
+void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 {
 	struct multicall_space mcs;
 	struct mmu_update *u;
@@ -366,6 +385,18 @@ void xen_set_pud(pud_t *ptr, pud_t val)
 	preempt_enable();
 }
 
+void xen_set_pud(pud_t *ptr, pud_t val)
+{
+	/* If page is not pinned, we can just update the entry
+	   directly */
+	if (!page_pinned(ptr)) {
+		*ptr = val;
+		return;
+	}
+
+	xen_set_pud_hyper(ptr, val);
+}
+
 void xen_set_pte(pte_t *ptep, pte_t pte)
 {
 	ptep->pte_high = pte.pte_high;
@@ -387,7 +418,7 @@ void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 
 void xen_pmd_clear(pmd_t *pmdp)
 {
-	xen_set_pmd(pmdp, __pmd(0));
+	set_pmd(pmdp, __pmd(0));
 }
 
 pmd_t xen_make_pmd(pmdval_t pmd)
@@ -758,7 +789,7 @@ void xen_exit_mmap(struct mm_struct *mm)
 	spin_lock(&mm->page_table_lock);
 
 	/* pgd may not be pinned in the error exit path of execve */
-	if (PagePinned(virt_to_page(mm->pgd)))
+	if (page_pinned(mm->pgd))
 		xen_pgd_unpin(mm->pgd);
 
 	spin_unlock(&mm->page_table_lock);
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index 5fe961caffd4..e3dd09e25c63 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -25,10 +25,6 @@ enum pt_level {
 
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-void xen_set_pte(pte_t *ptep, pte_t pteval);
-void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
-		    pte_t *ptep, pte_t pteval);
-void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval);
 
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next);
 void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
@@ -45,10 +41,14 @@ pte_t xen_make_pte(pteval_t);
 pmd_t xen_make_pmd(pmdval_t);
 pgd_t xen_make_pgd(pgdval_t);
 
+void xen_set_pte(pte_t *ptep, pte_t pteval);
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval);
 void xen_set_pte_atomic(pte_t *ptep, pte_t pte);
+void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval);
 void xen_set_pud(pud_t *ptr, pud_t val);
+void xen_set_pmd_hyper(pmd_t *pmdp, pmd_t pmdval);
+void xen_set_pud_hyper(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
-- 
cgit v1.2.2


From 9c7a794209f8a91f47697c3be20597eb60531e6d Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Sat, 31 May 2008 01:33:02 +0100
Subject: xen: restore vcpu_info mapping

If we're using vcpu_info mapping, then make sure its restored on all
processors before relasing them from stop_machine.

The only complication is that if this fails, we can't continue because
we've already made assumptions that the mapping is available (baked in
calls to the _direct versions of the functions, for example).

Fortunately this can only happen with a 32-bit hypervisor, which may
possibly run out of mapping space.  On a 64-bit hypervisor, this is a
non-issue.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/enlighten.c | 30 +++++++++++++++++++++++++++++-
 arch/x86/xen/suspend.c   |  4 +++-
 arch/x86/xen/xen-ops.h   |  1 +
 3 files changed, 33 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ed9f04b3836d..8e6152e6ed88 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -98,7 +98,7 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
  */
 static int have_vcpu_info_placement = 1;
 
-static void __init xen_vcpu_setup(int cpu)
+static void xen_vcpu_setup(int cpu)
 {
 	struct vcpu_register_vcpu_info info;
 	int err;
@@ -136,6 +136,34 @@ static void __init xen_vcpu_setup(int cpu)
 	}
 }
 
+/*
+ * On restore, set the vcpu placement up again.
+ * If it fails, then we're in a bad state, since
+ * we can't back out from using it...
+ */
+void xen_vcpu_restore(void)
+{
+	if (have_vcpu_info_placement) {
+		int cpu;
+
+		for_each_online_cpu(cpu) {
+			bool other_cpu = (cpu != smp_processor_id());
+
+			if (other_cpu &&
+			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+				BUG();
+
+			xen_vcpu_setup(cpu);
+
+			if (other_cpu &&
+			    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+				BUG();
+		}
+
+		BUG_ON(!have_vcpu_info_placement);
+	}
+}
+
 static void __init xen_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 7620a16fe535..7ab10f6b39a5 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -26,6 +26,8 @@ void xen_pre_suspend(void)
 
 void xen_post_suspend(int suspend_cancelled)
 {
+	xen_setup_shared_info();
+
 	if (suspend_cancelled) {
 		xen_start_info->store_mfn =
 			pfn_to_mfn(xen_start_info->store_mfn);
@@ -35,8 +37,8 @@ void xen_post_suspend(int suspend_cancelled)
 #ifdef CONFIG_SMP
 		xen_cpu_initialized_map = cpu_online_map;
 #endif
+		xen_vcpu_restore();
 	}
 
-	xen_setup_shared_info();
 }
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a0503acad664..a457e03e1b21 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -26,6 +26,7 @@ char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
 void __init xen_init_IRQ(void);
 void xen_enable_sysenter(void);
+void xen_vcpu_restore(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
 
-- 
cgit v1.2.2


From d07af1f0e3a3e378074fc36322dd7b0e72d9a3e2 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Sat, 31 May 2008 01:33:03 +0100
Subject: xen: resume timers on all vcpus

On resume, the vcpu timer modes will not be restored.  The timer
infrastructure doesn't do this for us, since it assumes the cpus
are offline.  We can just poke the other vcpus into the right mode
directly though.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/suspend.c |  1 +
 arch/x86/xen/time.c    | 13 +++++++++++++
 arch/x86/xen/xen-ops.h |  1 +
 3 files changed, 15 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 7ab10f6b39a5..251669a932d4 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -38,6 +38,7 @@ void xen_post_suspend(int suspend_cancelled)
 		xen_cpu_initialized_map = cpu_online_map;
 #endif
 		xen_vcpu_restore();
+		xen_timer_resume();
 	}
 
 }
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c39e1a5aa241..ea137fb660c0 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -572,6 +572,19 @@ void xen_setup_cpu_clockevents(void)
 	clockevents_register_device(&__get_cpu_var(xen_clock_events));
 }
 
+void xen_timer_resume(void)
+{
+	int cpu;
+
+	if (xen_clockevent != &xen_vcpuop_clockevent)
+		return;
+
+	for_each_online_cpu(cpu) {
+		if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+			BUG();
+	}
+}
+
 __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a457e03e1b21..9a055592a307 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -37,6 +37,7 @@ void __init xen_time_init(void);
 unsigned long xen_get_wallclock(void);
 int xen_set_wallclock(unsigned long time);
 unsigned long long xen_sched_clock(void);
+void xen_timer_resume(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
-- 
cgit v1.2.2


From 7e0edc1bc343231029084761ebf59e522902eb49 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Sat, 31 May 2008 01:33:04 +0100
Subject: xen: add new Xen elfnote types and use them appropriately

Define recently added XEN_ELFNOTEs, and use them appropriately.
Most significantly, this enables domain checkpointing (xm save -c).

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/xen-head.S | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 2ab5f42f34d8..ef6c9e005f90 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <asm/boot.h>
 #include <xen/interface/elfnote.h>
+#include <asm/xen/interface.h>
 
 	__INIT
 ENTRY(startup_xen)
@@ -32,5 +33,9 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
+	ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
+		.quad _PAGE_PRESENT; .quad _PAGE_PRESENT)
+	ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1)
+	ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW,   .long __HYPERVISOR_VIRT_START)
 
 #endif /*CONFIG_XEN */
-- 
cgit v1.2.2


From d44b9d17faf7bca165ce73a1acb936b65a3f0cc6 Mon Sep 17 00:00:00 2001
From: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Date: Tue, 3 Jun 2008 13:06:07 -0700
Subject: x86: move bugs_64.c to cpu/bugs_64.c

It looks good to move bugs_64.c to cpu/bugs_64.c.

Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/Makefile      |  1 -
 arch/x86/kernel/bugs_64.c     | 33 ---------------------------------
 arch/x86/kernel/cpu/Makefile  |  1 +
 arch/x86/kernel/cpu/bugs_64.c | 33 +++++++++++++++++++++++++++++++++
 4 files changed, 34 insertions(+), 34 deletions(-)
 delete mode 100644 arch/x86/kernel/bugs_64.c
 create mode 100644 arch/x86/kernel/cpu/bugs_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5e618c3b4720..4934fec38c42 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -25,7 +25,6 @@ obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
 obj-y			+= bootflag.o e820_$(BITS).o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o
-obj-$(CONFIG_X86_64)	+= bugs_64.o
 obj-y			+= tsc_$(BITS).o io_delay.o rtc.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
diff --git a/arch/x86/kernel/bugs_64.c b/arch/x86/kernel/bugs_64.c
deleted file mode 100644
index 9a3ed0649d4e..000000000000
--- a/arch/x86/kernel/bugs_64.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- *  Copyright (C) 1994  Linus Torvalds
- *  Copyright (C) 2000  SuSE
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <asm/alternative.h>
-#include <asm/bugs.h>
-#include <asm/processor.h>
-#include <asm/mtrr.h>
-#include <asm/cacheflush.h>
-
-void __init check_bugs(void)
-{
-	identify_boot_cpu();
-#if !defined(CONFIG_SMP)
-	printk("CPU: ");
-	print_cpu_info(&boot_cpu_data);
-#endif
-	alternative_instructions();
-
-	/*
-	 * Make sure the first 2MB area is not mapped by huge pages
-	 * There are typically fixed size MTRRs in there and overlapping
-	 * MTRRs into large pages causes slow downs.
-	 *
-	 * Right now we don't do that with gbpages because there seems
-	 * very little benefit for that case.
-	 */
-	if (!direct_gbpages)
-		set_memory_4k((unsigned long)__va(0), 1);
-}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index c77a1c50d944..65b1be5fe9ce 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -6,6 +6,7 @@ obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o feature_names.o
 
 obj-$(CONFIG_X86_32)	+= common.o bugs.o
+obj-$(CONFIG_X86_64)	+= bugs_64.o
 obj-$(CONFIG_X86_32)	+= amd.o
 obj-$(CONFIG_X86_64)	+= amd_64.o
 obj-$(CONFIG_X86_32)	+= cyrix.o
diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c
new file mode 100644
index 000000000000..9a3ed0649d4e
--- /dev/null
+++ b/arch/x86/kernel/cpu/bugs_64.c
@@ -0,0 +1,33 @@
+/*
+ *  Copyright (C) 1994  Linus Torvalds
+ *  Copyright (C) 2000  SuSE
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/alternative.h>
+#include <asm/bugs.h>
+#include <asm/processor.h>
+#include <asm/mtrr.h>
+#include <asm/cacheflush.h>
+
+void __init check_bugs(void)
+{
+	identify_boot_cpu();
+#if !defined(CONFIG_SMP)
+	printk("CPU: ");
+	print_cpu_info(&boot_cpu_data);
+#endif
+	alternative_instructions();
+
+	/*
+	 * Make sure the first 2MB area is not mapped by huge pages
+	 * There are typically fixed size MTRRs in there and overlapping
+	 * MTRRs into large pages causes slow downs.
+	 *
+	 * Right now we don't do that with gbpages because there seems
+	 * very little benefit for that case.
+	 */
+	if (!direct_gbpages)
+		set_memory_4k((unsigned long)__va(0), 1);
+}
-- 
cgit v1.2.2


From fb3bbd6a663fe972611676381adc4c60ddfe61ac Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Thu, 22 May 2008 18:22:30 -0700
Subject: x86: fix APIC warning on 32bit v2

for http://bugzilla.kernel.org/show_bug.cgi?id=10613

BIOS bug, APIC version is 0 for CPU#0! fixing up to 0x10. (tell your hw vendor)

v2: fix 64 bit compilation

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Gabriel C <nix.or.die@googlemail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/acpi/boot.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index c49ebcc6c41e..33c5216fd3e1 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -242,12 +242,19 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 
 static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
+	unsigned int ver = 0;
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;
 	}
 
-	generic_processor_info(id, 0);
+#ifdef CONFIG_X86_32
+	if (boot_cpu_physical_apicid != -1U)
+		ver = apic_version[boot_cpu_physical_apicid];
+#endif
+
+	generic_processor_info(id, ver);
 }
 
 static int __init
@@ -767,8 +774,13 @@ static void __init acpi_register_lapic_address(unsigned long address)
 	mp_lapic_addr = address;
 
 	set_fixmap_nocache(FIX_APIC_BASE, address);
-	if (boot_cpu_physical_apicid == -1U)
+	if (boot_cpu_physical_apicid == -1U) {
 		boot_cpu_physical_apicid  = GET_APIC_ID(read_apic_id());
+#ifdef CONFIG_X86_32
+		apic_version[boot_cpu_physical_apicid] =
+			 GET_APIC_VERSION(apic_read(APIC_LVR));
+#endif
+	}
 }
 
 static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
-- 
cgit v1.2.2


From deef325086c3897393b8f7d6bccd03405244fe18 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 12 May 2008 15:44:38 +0200
Subject: x86: disable preemption in native_smp_prepare_cpus

Priit Laes reported the following warning:

Call Trace:
 [<ffffffff8022f1e1>] warn_on_slowpath+0x51/0x63
 [<ffffffff80282e48>] sys_ioctl+0x2d/0x5d
 [<ffffffff805185ff>] _spin_lock+0xe/0x24
 [<ffffffff80227459>] task_rq_lock+0x3d/0x73
 [<ffffffff805133c3>] set_cpu_sibling_map+0x336/0x350
 [<ffffffff8021c1b8>] read_apic_id+0x30/0x62
 [<ffffffff806d921d>] verify_local_APIC+0x90/0x138
 [<ffffffff806d84b5>] native_smp_prepare_cpus+0x1f9/0x305
 [<ffffffff806ce7b1>] kernel_init+0x59/0x2d9
 [<ffffffff80518a26>] _spin_unlock_irq+0x11/0x2b
 [<ffffffff8020bf48>] child_rip+0xa/0x12
 [<ffffffff806ce758>] kernel_init+0x0/0x2d9
 [<ffffffff8020bf3e>] child_rip+0x0/0x12

fix this by generally disabling preemption in native_smp_prepare_cpus().

Reported-and-bisected-by: Priit Laes <plaes@plaes.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/smpboot.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 38988491c622..56078d61c793 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1190,6 +1190,7 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	preempt_disable();
 	nmi_watchdog_default();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1206,7 +1207,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
 		disable_smp();
-		return;
+		goto out;
 	}
 
 	preempt_disable();
@@ -1246,6 +1247,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	printk(KERN_INFO "CPU%d: ", 0);
 	print_cpu_info(&cpu_data(0));
 	setup_boot_clock();
+out:
+	preempt_enable();
 }
 /*
  * Early setup to make printk work.
-- 
cgit v1.2.2


From 5c1ea08215f1f830dfaf4819a5f22efca41c3832 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Sun, 25 May 2008 11:13:32 -0400
Subject: x86: enable preemption in delay

The RT team has been searching for a nasty latency. This latency shows
up out of the blue and has been seen to be as big as 5ms!

Using ftrace I found the cause of the latency.

   pcscd-2995  3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt)
   pcscd-2995  3dN.2 52360301us : idle_cpu (irq_exit)
   pcscd-2995  3dN.2 52360301us : rcu_irq_exit (irq_exit)
   pcscd-2995  3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt
)
   pcscd-2995  3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt)

Here's an example of a 400 us latency. pcscd took a timer interrupt and
returned with "need resched" enabled, but did not reschedule until after
the next interrupt came in at 52360771us 400us later!

At first I thought we somehow missed a preemption check in entry.S. But
I also noticed that this always seemed to happen during a __delay call.

   pcscd-2995  3dN.2 52360836us : rcu_irq_exit (irq_exit)
   pcscd-2995  3.N.. 52361265us : preempt_schedule (__delay)

Looking at the x86 delay, I found my problem.

In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton
placed preempt_disable around the entire delay due to TSC's not working
nicely on SMP.  Unfortunately for those that care about latencies this
is devastating! Especially when we have callers to mdelay(8).

Here I enable preemption during the loop and account for anytime the task
migrates to a new CPU. The delay asked for may be extended a bit by
the migration, but delay only guarantees that it will delay for that minimum
time. Delaying longer should not be an issue.

[
  Thanks to Thomas Gleixner for spotting that cpu wasn't updated,
    and to place the rep_nop between preempt_enabled/disable.
]

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: akpm@osdl.org
Cc: Clark Williams <clark.williams@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org>
Cc: Gregory Haskins <ghaskins@novell.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andi Kleen <andi-suse@firstfloor.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/lib/delay_32.c | 31 +++++++++++++++++++++++++++----
 arch/x86/lib/delay_64.c | 30 ++++++++++++++++++++++++++----
 2 files changed, 53 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c
index 4535e6d147ad..d710f2d167bb 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay_32.c
@@ -44,13 +44,36 @@ static void delay_loop(unsigned long loops)
 static void delay_tsc(unsigned long loops)
 {
 	unsigned long bclock, now;
+	int cpu;
 
-	preempt_disable();		/* TSC's are per-cpu */
+	preempt_disable();
+	cpu = smp_processor_id();
 	rdtscl(bclock);
-	do {
-		rep_nop();
+	for (;;) {
 		rdtscl(now);
-	} while ((now-bclock) < loops);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
+	}
 	preempt_enable();
 }
 
diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c
index bbc610518516..4c441be92641 100644
--- a/arch/x86/lib/delay_64.c
+++ b/arch/x86/lib/delay_64.c
@@ -31,14 +31,36 @@ int __devinit read_current_timer(unsigned long *timer_value)
 void __delay(unsigned long loops)
 {
 	unsigned bclock, now;
+	int cpu;
 
-	preempt_disable();		/* TSC's are pre-cpu */
+	preempt_disable();
+	cpu = smp_processor_id();
 	rdtscl(bclock);
-	do {
-		rep_nop(); 
+	for (;;) {
 		rdtscl(now);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
 	}
-	while ((now-bclock) < loops);
 	preempt_enable();
 }
 EXPORT_SYMBOL(__delay);
-- 
cgit v1.2.2


From e8a496ac8cd00cabbdaa373db4818a9ad19a1c5a Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Fri, 23 May 2008 16:26:37 -0700
Subject: x86: fix broken math-emu with lazy allocation of fpu area

Fix the math emulation that got broken with the recent lazy allocation of FPU
area. init_fpu() need to be added for the math-emulation path aswell
for the FPU area allocation.

math emulation enabled kernel booted fine with this, in the presence
of "no387 nofxsr" boot param.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: hpa@zytor.com
Cc: mingo@elte.hu
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/i387.c        | 44 ++++++++++++++++++++++++++++---------------
 arch/x86/math-emu/fpu_entry.c | 13 ++++++++-----
 2 files changed, 37 insertions(+), 20 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e03cc952f233..eb9ddd8efb82 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void)
 
 void __init init_thread_xstate(void)
 {
+	if (!HAVE_HWFP) {
+		xstate_size = sizeof(struct i387_soft_struct);
+		return;
+	}
+
 	if (cpu_has_fxsr)
 		xstate_size = sizeof(struct i387_fxsave_struct);
 #ifdef CONFIG_X86_32
@@ -94,7 +99,7 @@ void __cpuinit fpu_init(void)
 int init_fpu(struct task_struct *tsk)
 {
 	if (tsk_used_math(tsk)) {
-		if (tsk == current)
+		if (HAVE_HWFP && tsk == current)
 			unlazy_fpu(tsk);
 		return 0;
 	}
@@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk)
 			return -ENOMEM;
 	}
 
+#ifdef CONFIG_X86_32
+	if (!HAVE_HWFP) {
+		memset(tsk->thread.xstate, 0, xstate_size);
+		finit();
+		set_stopped_child_used_math(tsk);
+		return 0;
+	}
+#endif
+
 	if (cpu_has_fxsr) {
 		struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
 
@@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	if (!HAVE_HWFP)
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
 	ret = init_fpu(target);
 	if (ret)
 		return ret;
 
+	if (!HAVE_HWFP)
+		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
 	if (!cpu_has_fxsr) {
 		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					   &target->thread.xstate->fsave, 0,
@@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	if (!HAVE_HWFP)
-		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
 	ret = init_fpu(target);
 	if (ret)
 		return ret;
 
 	set_stopped_child_used_math(target);
 
+	if (!HAVE_HWFP)
+		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
 	if (!cpu_has_fxsr) {
 		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					  &target->thread.xstate->fsave, 0, -1);
@@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf)
 int restore_i387_ia32(struct _fpstate_ia32 __user *buf)
 {
 	int err;
+	struct task_struct *tsk = current;
 
-	if (HAVE_HWFP) {
-		struct task_struct *tsk = current;
-
+	if (HAVE_HWFP)
 		clear_fpu(tsk);
 
-		if (!used_math()) {
-			err = init_fpu(tsk);
-			if (err)
-				return err;
-		}
+	if (!used_math()) {
+		err = init_fpu(tsk);
+		if (err)
+			return err;
+	}
 
+	if (HAVE_HWFP) {
 		if (cpu_has_fxsr)
 			err = restore_i387_fxsave(buf);
 		else
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 6e38d877ea77..c7b06feb139b 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -30,6 +30,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/user.h>
+#include <asm/i387.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
@@ -146,6 +147,13 @@ asmlinkage void math_emulate(long arg)
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
 
+	if (!used_math()) {
+		if (init_fpu(current)) {
+			do_group_exit(SIGKILL);
+			return;
+		}
+	}
+
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
 		printk("ERROR: wm-FPU-emu is not RE-ENTRANT!\n");
@@ -153,11 +161,6 @@ asmlinkage void math_emulate(long arg)
 	RE_ENTRANT_CHECK_ON;
 #endif /* RE_ENTRANT_CHECKING */
 
-	if (!used_math()) {
-		finit();
-		set_used_math();
-	}
-
 	SETUP_DATA_AREA(arg);
 
 	FPU_ORIG_EIP = FPU_EIP;
-- 
cgit v1.2.2


From 226e9a93a253b7d8811b5ed9ac671c6c5a728022 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Tue, 27 May 2008 09:56:49 +0200
Subject: x86: ioremap fix failing nesting check

Mika Kukkonen noticed that the nesting check in early_iounmap() is not
actually done.

Reported-by: Mika Kukkonen <mikukkon@srv1-m700-lanp.koti>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: torvalds@linux-foundation.org
Cc: arjan@linux.intel.com
Cc: mikukkon@iki.fi
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/ioremap.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 71bb3159031a..2b2bb3f9b683 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -593,10 +593,11 @@ void __init early_iounmap(void *addr, unsigned long size)
 	unsigned long offset;
 	unsigned int nrpages;
 	enum fixed_addresses idx;
-	unsigned int nesting;
+	int nesting;
 
 	nesting = --early_ioremap_nested;
-	WARN_ON(nesting < 0);
+	if (WARN_ON(nesting < 0))
+		return;
 
 	if (early_ioremap_debug) {
 		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr,
-- 
cgit v1.2.2


From 2884f110d5409714f3a04eeb6d2ecd77da66b242 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hugh@veritas.com>
Date: Wed, 28 May 2008 19:36:07 +0100
Subject: x86: fix bad pmd ffff810000207xxx(9090909090909090)

OGAWA Hirofumi and Fede have reported rare pmd_ERROR messages:
mm/memory.c:127: bad pmd ffff810000207xxx(9090909090909090).

Initialization's cleanup_highmap was leaving alignment filler
behind in the pmd for MODULES_VADDR: when vmalloc's guard page
would occupy a new page table, it's not allocated, and then
module unload's vfree hits the bad 9090 pmd entry left over.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 32ba13b0f818..998a06ea5f7d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -206,7 +206,7 @@ void __init cleanup_highmap(void)
 	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
 	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
-		if (!pmd_present(*pmd))
+		if (pmd_none(*pmd))
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)
 			set_pmd(pmd, __pmd(0));
-- 
cgit v1.2.2


From 511631011d39706ac81ee5e4c9084d61e5b4fd34 Mon Sep 17 00:00:00 2001
From: Kevin Winchester <kjwinchester@gmail.com>
Date: Thu, 29 May 2008 21:14:35 -0300
Subject: x86: fix pointer type warning in arch/x86/mm/init_64.c:early_memtest

Changed the call to find_e820_area_size to pass u64 instead of unsigned long.

Signed-off-by: Kevin Winchester <kjwinchester@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 998a06ea5f7d..156e6d7b0e32 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	unsigned long t_start, t_size;
+	u64 t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
+			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
 				t_start, t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
-- 
cgit v1.2.2


From 282c454cd3a7041f59a37112bb2f82263bc38f6c Mon Sep 17 00:00:00 2001
From: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Date: Thu, 29 May 2008 12:01:44 -0700
Subject: x86: fix Xorg crash with xf86MapVidMem error

Clarify the usage of mtrr_lookup() in PAT code, and to make PAT code
resilient to mtrr lookup problems.

Specifically, pat_x_mtrr_type() is restructured to highlight, under what
conditions we look for mtrr hint. pat_x_mtrr_type() uses a default type
when there are any errors in mtrr lookup (still maintaining the pat
consistency). And, reserve_memtype() highlights its usage ot mtrr_lookup
for request type of '-1' and also defaults in a sane way on any mtrr
lookup failure.

pat.c looks at mtrr type of a range to get a hint on what mapping type
to request when user/API: (1) hasn't specified any type (/dev/mem
mapping) and we do not want to take performance hit by always mapping
UC_MINUS. This will be the case for /dev/mem mappings used to map BIOS
area or ACPI region which are WB'able. In this case, as long as MTRR is
not WB, PAT will request UC_MINUS for such mappings.

(2) user/API requests WB mapping while in reality MTRR may have UC or
WC. In this case, PAT can map as WB (without checking MTRR) and still
effective type will be UC or WC. But, a subsequent request to map same
region as UC or WC may fail, as the region will get trackked as WB in
PAT list. Looking at MTRR hint helps us to track based on effective type
rather than what user requested. Again, here mtrr_lookup is only used as
hint and we fallback to WB mapping (as requested by user) as default.

In both cases, after using the mtrr hint, we still go through the
memtype list to make sure there are no inconsistencies among multiple
users.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Rufus & Azrael <rufus-azrael@numericable.fr>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 49 ++++++++++++++++++++++++-------------------------
 1 file changed, 24 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index de3a99812450..183fdd36d3bd 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -151,32 +151,33 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
 	unsigned long pat_type;
 	u8 mtrr_type;
 
-	mtrr_type = mtrr_type_lookup(start, end);
-	if (mtrr_type == 0xFF) {		/* MTRR not enabled */
-		*ret_prot = prot;
-		return 0;
-	}
-	if (mtrr_type == 0xFE) {		/* MTRR match error */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-	if (mtrr_type != MTRR_TYPE_UNCACHABLE &&
-	    mtrr_type != MTRR_TYPE_WRBACK &&
-	    mtrr_type != MTRR_TYPE_WRCOMB) {	/* MTRR type unhandled */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-
 	pat_type = prot & _PAGE_CACHE_MASK;
 	prot &= (~_PAGE_CACHE_MASK);
 
-	/* Currently doing intersection by hand. Optimize it later. */
+	/*
+	 * We return the PAT request directly for types where PAT takes
+	 * precedence with respect to MTRR and for UC_MINUS.
+	 * Consistency checks with other PAT requests is done later
+	 * while going through memtype list.
+	 */
 	if (pat_type == _PAGE_CACHE_WC) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
+		return 0;
 	} else if (pat_type == _PAGE_CACHE_UC_MINUS) {
 		*ret_prot = prot | _PAGE_CACHE_UC_MINUS;
-	} else if (pat_type == _PAGE_CACHE_UC ||
-	           mtrr_type == MTRR_TYPE_UNCACHABLE) {
+		return 0;
+	} else if (pat_type == _PAGE_CACHE_UC) {
+		*ret_prot = prot | _PAGE_CACHE_UC;
+		return 0;
+	}
+
+	/*
+	 * Look for MTRR hint to get the effective type in case where PAT
+	 * request is for WB.
+	 */
+	mtrr_type = mtrr_type_lookup(start, end);
+
+	if (mtrr_type == MTRR_TYPE_UNCACHABLE) {
 		*ret_prot = prot | _PAGE_CACHE_UC;
 	} else if (mtrr_type == MTRR_TYPE_WRCOMB) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
@@ -233,14 +234,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	if (req_type == -1) {
 		/*
-		 * Special case where caller wants to inherit from mtrr or
-		 * existing pat mapping, defaulting to UC_MINUS in case of
-		 * no match.
+		 * Call mtrr_lookup to get the type hint. This is an
+		 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+		 * tools and ACPI tools). Use WB request for WB memory and use
+		 * UC_MINUS otherwise.
 		 */
 		u8 mtrr_type = mtrr_type_lookup(start, end);
-		if (mtrr_type == 0xFE) { /* MTRR match error */
-			err = -1;
-		}
 
 		if (mtrr_type == MTRR_TYPE_WRBACK) {
 			req_type = _PAGE_CACHE_WB;
-- 
cgit v1.2.2


From be524fb96081e9e511d993ebf39b05a32b19476e Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Thu, 29 May 2008 00:01:28 -0700
Subject: x86: section mismatch fix

Fix this:

 WARNING: vmlinux.o(.text+0x114bb): Section mismatch in reference from
 the function nopat() to the function .cpuinit.text:pat_disable()
 The function nopat() references
 the function __cpuinit pat_disable().
 This is often because nopat lacks a __cpuinit
 annotation or the annotation of pat_disable is wrong.

Reported-by: "Fabio Comolli" <fabio.comolli@gmail.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 183fdd36d3bd..06b7a1c90fb8 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -34,7 +34,7 @@ void __cpuinit pat_disable(char *reason)
 	printk(KERN_INFO "%s\n", reason);
 }
 
-static int nopat(char *str)
+static int __init nopat(char *str)
 {
 	pat_disable("PAT support disabled.");
 	return 0;
-- 
cgit v1.2.2


From cd76374e9de4501acc74f833dc6cb5e7a5dca115 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Thu, 29 May 2008 00:30:21 -0700
Subject: suspend-vs-iommu: prevent suspend if we could not resume

iommu/gart support misses suspend/resume code, which can do bad stuff,
including memory corruption on resume.  Prevent system suspend in case we
would be unable to resume.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Tested-by: Patrick <ragamuffin@datacomm.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-gart_64.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c07455d1695f..aa8ec928caa8 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+#include <linux/sysdev.h>
 #include <asm/atomic.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
@@ -548,6 +549,28 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
 	return aper_base;
 }
 
+static int gart_resume(struct sys_device *dev)
+{
+	return 0;
+}
+
+static int gart_suspend(struct sys_device *dev, pm_message_t state)
+{
+	return -EINVAL;
+}
+
+static struct sysdev_class gart_sysdev_class = {
+	.name = "gart",
+	.suspend = gart_suspend,
+	.resume = gart_resume,
+
+};
+
+static struct sys_device device_gart = {
+	.id	= 0,
+	.cls	= &gart_sysdev_class,
+};
+
 /*
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
@@ -558,7 +581,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	unsigned aper_base, new_aper_base;
 	struct pci_dev *dev;
 	void *gatt;
-	int i;
+	int i, error;
 
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
@@ -606,6 +629,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 		pci_write_config_dword(dev, 0x90, ctl);
 	}
+
+	error = sysdev_class_register(&gart_sysdev_class);
+	if (!error)
+		error = sysdev_register(&device_gart);
+	if (error)
+		panic("Could not register gart_sysdev -- would corrupt data on next suspend");
 	flush_gart();
 
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
-- 
cgit v1.2.2


From 870568b39064cab2dd971fe57969916036982862 Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Mon, 2 Jun 2008 15:57:27 -0700
Subject: x86, fpu: fix CONFIG_PREEMPT=y corruption of application's FPU stack
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Jürgen Mell reported an FPU state corruption bug under CONFIG_PREEMPT,
and bisected it to commit v2.6.19-1363-gacc2076, "i386: add sleazy FPU
optimization".

Add tsk_used_math() checks to prevent calling math_state_restore()
which can sleep in the case of !tsk_used_math(). This prevents
making a blocking call in __switch_to().

Apparently "fpu_counter > 5" check is not enough, as in some signal handling
and fork/exec scenarios, fpu_counter > 5 and !tsk_used_math() is possible.

It's a side effect though. This is the failing scenario:

process 'A' in save_i387_ia32() just after clear_used_math()

Got an interrupt and pre-empted out.

At the next context switch to process 'A' again, kernel tries to restore
the math state proactively and sees a fpu_counter > 0 and !tsk_used_math()

This results in init_fpu() during the __switch_to()'s math_state_restore()

And resulting in fpu corruption which will be saved/restored
(save_i387_fxsave and restore_i387_fxsave) during the remaining
part of the signal handling after the context switch.

Bisected-by: Jürgen Mell <j.mell@t-online.de>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Jürgen Mell <j.mell@t-online.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
---
 arch/x86/kernel/process_32.c | 5 ++++-
 arch/x86/kernel/process_64.c | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f8476dfbb60d..6d5483356e74 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -649,8 +649,11 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
+	 *
+	 * tsk_used_math() checks prevent calling math_state_restore(),
+	 * which can sleep in the case of !tsk_used_math()
 	 */
-	if (next_p->fpu_counter > 5)
+	if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
 		math_state_restore();
 
 	/*
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e2319f39988b..ac54ff56df80 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -658,8 +658,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
+	 *
+	 * tsk_used_math() checks prevent calling math_state_restore(),
+	 * which can sleep in the case of !tsk_used_math()
 	 */
-	if (next_p->fpu_counter>5)
+	if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
 		math_state_restore();
 	return prev_p;
 }
-- 
cgit v1.2.2


From fa5b8a30cf03520737e9a0ee2ee03a61b2eccf05 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Mon, 26 May 2008 20:40:47 +0200
Subject: aperture_64.c: duplicated code, buggy?

Hi!

void __init early_gart_iommu_check(void)

contains

	for (num = 24; num < 32; num++) {
		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
			continue;

loop, with very similar loop duplicated in

void __init gart_iommu_hole_init(void)

. First copy of a loop seems to be buggy, too. It uses 0 as a "nothing
set" value, which may actually bite us in last_aper_enabled case
(because it may be often zero).

(Beware, it is hard to test this patch, because this code has about
2^8 different code paths, depending on hardware and cmdline settings).

Plus, the second loop does not check for consistency of
aper_enabled. Should it?

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6eea42eb287b..e5b17f910f8b 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -271,16 +271,16 @@ void __init early_gart_iommu_check(void)
 	 * or BIOS forget to put that in reserved.
 	 * try to update e820 to make that region as reserved.
 	 */
-	int fix, slot;
+	int i, fix, slot;
 	u32 ctl;
 	u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base = 0, last_aper_base = 0;
-	int aper_enabled = 0, last_aper_enabled = 0;
-	int i;
+	int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
 
 	if (!early_pci_allowed())
 		return;
 
+	/* This is mostly duplicate of iommu_hole_init */
 	fix = 0;
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
 		int bus;
@@ -301,19 +301,22 @@ void __init early_gart_iommu_check(void)
 			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
 			aper_base <<= 25;
 
-			if ((last_aper_order && aper_order != last_aper_order) ||
-			    (last_aper_base && aper_base != last_aper_base) ||
-			    (last_aper_enabled && aper_enabled != last_aper_enabled)) {
-				fix = 1;
-				goto out;
+			if (last_valid) {
+				if ((aper_order != last_aper_order) ||
+				    (aper_base != last_aper_base) ||
+				    (aper_enabled != last_aper_enabled)) {
+					fix = 1;
+					break;
+				}
 			}
+
 			last_aper_order = aper_order;
 			last_aper_base = aper_base;
 			last_aper_enabled = aper_enabled;
+			last_valid = 1;
 		}
 	}
 
-out:
 	if (!fix && !aper_enabled)
 		return;
 
-- 
cgit v1.2.2


From 4f384f8bcdb5d618a0a68fb84c809e602c798b8f Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Mon, 26 May 2008 21:17:30 +0200
Subject: x86: aperture_64.c: corner case wrong

If

fix == 0, aper_enabled == 1, gart_fix_e820 == 0

	if (!fix && !aper_enabled)
		return;

	if (gart_fix_e820 && !fix && aper_enabled) {
		if (e820_any_mapped(aper_base, aper_base + aper_size,
				    E820_RAM)) {
			/* reserve it, so we can reuse it in second kernel */
			printk(KERN_INFO "update e820 for GART\n");
			add_memory_region(aper_base, aper_size, E820_RESERVED);
			update_e820();
		}
		return;
	}

	/* different nodes have different setting, disable them all atfirst*/

we'll fall back here and disable all the settings, even when they were
all consistent.

What about this? (I hope it compiles...)

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/aperture_64.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index e5b17f910f8b..eb20f168c0fd 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -331,9 +331,11 @@ void __init early_gart_iommu_check(void)
 			add_memory_region(aper_base, aper_size, E820_RESERVED);
 			update_e820();
 		}
-		return;
 	}
 
+	if (!fix)
+		return;
+
 	/* different nodes have different setting, disable them all at first*/
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
 		int bus;
-- 
cgit v1.2.2


From 74e411cb6443d8bcb55fbe89fcc7a9ee574df91b Mon Sep 17 00:00:00 2001
From: Krzysztof Oledzki <ole@ans.pl>
Date: Wed, 4 Jun 2008 03:40:17 +0200
Subject: x86: add another PCI ID for ICH6 force hpet.

Tested on Asus P5GDC-V

$ lspci -n -n |grep ISA
00:1f.0 ISA bridge [0601]: Intel Corporation 82801FB/FR (ICH6/ICH6R) LPC Interface Bridge [8086:2640] (rev 03)

Force enabled HPET at base address 0xfed00000
hpet clockevent registered
hpet0: at MMIO 0xfed00000, IRQs 2, 8, 0
hpet0: 3 64-bit timers, 14318180 Hz

Signed-off-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Cc: mingo@elte.hu
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index ddbf34d16a01..79bdcd11c66e 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -159,6 +159,8 @@ static void ich_force_enable_hpet(struct pci_dev *dev)
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0,
 			 ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_0,
+			 ich_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1,
 			 ich_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0,
-- 
cgit v1.2.2


From 16104b5504fa8be130f7f127a5a1c7dd774efc44 Mon Sep 17 00:00:00 2001
From: Stefan Richter <stefanr@s5r6.in-berlin.de>
Date: Thu, 5 Jun 2008 22:47:13 +0200
Subject: x86: fix CONFIG_NONPROMISC_DEVMEM prompt and help text

Here is an attempt to translate the prompt and help text into something
which is legible and, as a bonus, correct.

Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/Kconfig.debug | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ac1e31ba4795..18363374d51a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -6,15 +6,19 @@ config TRACE_IRQFLAGS_SUPPORT
 source "lib/Kconfig.debug"
 
 config NONPROMISC_DEVMEM
-	bool "Disable promiscuous /dev/mem"
+	bool "Filter access to /dev/mem"
 	help
-	  The /dev/mem file by default only allows userspace access to PCI
-	  space and the BIOS code and data regions. This is sufficient for
-	  dosemu and X and all common users of /dev/mem. With this config
-	  option, you allow userspace access to all of memory, including
-	  kernel and userspace memory. Accidental access to this is
-	  obviously disasterous, but specific access can be used by people
-	  debugging the kernel.
+	  If this option is left off, you allow userspace access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to PCI space and the BIOS code and data regions.
+	  This is sufficient for dosemu and X and all common users of
+	  /dev/mem.
+
+	  If in doubt, say Y.
 
 config EARLY_PRINTK
 	bool "Early printk" if EMBEDDED
-- 
cgit v1.2.2


From 2bdd1b031b200d55c2512c8d7e0e9bdcf85d011f Mon Sep 17 00:00:00 2001
From: Andres Salomon <dilinger@queued.net>
Date: Thu, 5 Jun 2008 14:14:41 -0700
Subject: PCI/x86: fix up PCI stuff so that PCI_GOANY supports OLPC

Previously, one would have to specifically choose CONFIG_OLPC and
CONFIG_PCI_GOOLPC in order to enable PCI_OLPC.  That doesn't really work
for distro kernels, so this patch allows one to choose CONFIG_OLPC and
CONFIG_PCI_GOANY in order to build in OLPC support in a generic kernel (as
requested by Robert Millan).

This also moves GOOLPC before GOANY in the menuconfig list.

Finally, make pci_access_init return early if we detect OLPC hardware.
There's no need to continue probing stuff, and pci_pcbios_init
specifically trashes our settings (we didn't run into that before because
PCI_GOANY wasn't supported).

Signed-off-by: Andres Salomon <dilinger@debian.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/Kconfig    | 11 +++++------
 arch/x86/pci/init.c |  3 ++-
 arch/x86/pci/olpc.c |  5 +++--
 arch/x86/pci/pci.h  |  2 +-
 4 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dcbec34154cf..52e18e6d2ba0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1508,13 +1508,13 @@ config PCI_GOMMCONFIG
 config PCI_GODIRECT
 	bool "Direct"
 
-config PCI_GOANY
-	bool "Any"
-
 config PCI_GOOLPC
 	bool "OLPC"
 	depends on OLPC
 
+config PCI_GOANY
+	bool "Any"
+
 endchoice
 
 config PCI_BIOS
@@ -1531,9 +1531,8 @@ config PCI_MMCONFIG
 	depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY)
 
 config PCI_OLPC
-	bool
-	depends on PCI && PCI_GOOLPC
-	default y
+	def_bool y
+	depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY)
 
 config PCI_DOMAINS
 	def_bool y
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
index e70b9c57b88e..b821f4462d99 100644
--- a/arch/x86/pci/init.c
+++ b/arch/x86/pci/init.c
@@ -15,7 +15,8 @@ static __init int pci_access_init(void)
 	pci_mmcfg_early_init();
 
 #ifdef CONFIG_PCI_OLPC
-	pci_olpc_init();
+	if (!pci_olpc_init())
+		return 0;	/* skip additional checks if it's an XO */
 #endif
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index 5e7636558c02..e11e9e803d5f 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -302,12 +302,13 @@ static struct pci_raw_ops pci_olpc_conf = {
 	.write = pci_olpc_write,
 };
 
-void __init pci_olpc_init(void)
+int __init pci_olpc_init(void)
 {
 	if (!machine_is_olpc() || olpc_has_vsa())
-		return;
+		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using configuration type OLPC\n");
 	raw_pci_ops = &pci_olpc_conf;
 	is_lx = is_geode_lx();
+	return 0;
 }
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index f3972b12c60a..720c4c554534 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -101,7 +101,7 @@ extern struct pci_raw_ops pci_direct_conf1;
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
 extern void pci_pcbios_init(void);
-extern void pci_olpc_init(void);
+extern int pci_olpc_init(void);
 
 /* pci-mmconfig.c */
 
-- 
cgit v1.2.2


From 9f67fd5db50566728996b0115a08c83d4f902cb3 Mon Sep 17 00:00:00 2001
From: Bertram Felgenhauer <int-e@gmx.de>
Date: Thu, 5 Jun 2008 15:31:22 -0700
Subject: x86/PCI: add workaround for bug in ASUS A7V600 BIOS (rev 1005)

This BIOS claims the VIA 8237 south bridge to be compatible with VIA 586,
which it is not.

Without this patch, I get the following warning while booting,
among others,

| PCI: Using IRQ router VIA [1106/3227] at 0000:00:11.0
| ------------[ cut here ]------------
| WARNING: at arch/x86/pci/irq.c:265 pirq_via586_get+0x4a/0x60()
| Modules linked in:
| Pid: 1, comm: swapper Not tainted 2.6.26-rc4-00015-g1ec7d99 #1
|  [<c0119fd4>] warn_on_slowpath+0x54/0x70
|  [<c02246e0>] ? vt_console_print+0x210/0x2b0
|  [<c02244d0>] ? vt_console_print+0x0/0x2b0
|  [<c011a413>] ? __call_console_drivers+0x43/0x60
|  [<c011a482>] ? _call_console_drivers+0x52/0x80
|  [<c011aa89>] ? release_console_sem+0x1c9/0x200
|  [<c0291d21>] ? raw_pci_read+0x41/0x70
|  [<c0291e8f>] ? pci_read+0x2f/0x40
|  [<c029151a>] pirq_via586_get+0x4a/0x60
|  [<c02914d0>] ? pirq_via586_get+0x0/0x60
|  [<c029178d>] pcibios_lookup_irq+0x15d/0x430
|  [<c03b895a>] pcibios_irq_init+0x17a/0x3e0
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c03a6763>] kernel_init+0x73/0x250
|  [<c03b87e0>] ? pcibios_irq_init+0x0/0x3e0
|  [<c0114d00>] ? schedule_tail+0x10/0x40
|  [<c0102dee>] ? ret_from_fork+0x6/0x1c
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c03a66f0>] ? kernel_init+0x0/0x250
|  [<c010324b>] kernel_thread_helper+0x7/0x1c
|  =======================
| ---[ end trace 4eaa2a86a8e2da22 ]---

and IRQ trouble later,

| irq 10: nobody cared (try booting with the "irqpoll" option)

Now that's an VIA 8237 chip, so pirq_via586_get shouldn't be called
at all; adding this workaround to via_router_probe() fixes the
problem for me.

Amazingly I have a 2.6.23.8 kernel that somehow works fine ... I'll
never understand why.

Signed-off-by: Bertram Felgenhauer <int-e@gmx.de>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Acked-by: Alan Cox <alan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/pci/irq.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0908fca901bf..ca8df9c260bc 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -621,6 +621,13 @@ static __init int via_router_probe(struct irq_router *r,
 			 */
 			device = PCI_DEVICE_ID_VIA_8235;
 			break;
+		case PCI_DEVICE_ID_VIA_8237:
+			/**
+			 * Asus a7v600 bios wrongly reports 8237
+			 * as 586-compatible
+			 */
+			device = PCI_DEVICE_ID_VIA_8237;
+			break;
 		}
 	}
 
-- 
cgit v1.2.2


From 33e3885de25148e00595c4dd808d6eb15db2edcf Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Wed, 21 May 2008 15:34:25 +0300
Subject: KVM: x86 emulator: fix hypercall return value on AMD

The hypercall instructions on Intel and AMD are different.  KVM allows the
guest to choose one or the other (the default is Intel), and if the guest
chooses incorrectly, KVM will patch it at runtime to select the correct
instruction.  This allows live migration between Intel and AMD machines.

This patching occurs in the x86 emulator.  The current code also executes
the hypercall.  Unfortunately, the tail end of the x86 emulator code also
executes, overwriting the return value of the hypercall with the original
contents of rax (which happens to be the hypercall number).

Fix not by executing the hypercall in the emulator context; instead let the
guest reissue the patched instruction and execute the hypercall via the
normal path.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/x86_emulate.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 8a96320ab071..932f216d890c 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -1727,7 +1727,8 @@ twobyte_insn:
 			if (rc)
 				goto done;
 
-			kvm_emulate_hypercall(ctxt->vcpu);
+			/* Let the processor re-execute the fixed hypercall */
+			c->eip = ctxt->vcpu->arch.rip;
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
-- 
cgit v1.2.2


From 2f5997140f22f68f6390c49941150d3fa8a95cb7 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Tue, 27 May 2008 12:10:20 -0300
Subject: KVM: migrate PIT timer

Migrate the PIT timer to the physical CPU which vcpu0 is scheduled on,
similarly to what is done for the LAPIC timers, otherwise PIT interrupts
will be delayed until an unrelated event causes an exit.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/i8254.c | 14 +++++++++++++-
 arch/x86/kvm/irq.c   |  6 ++++++
 arch/x86/kvm/irq.h   |  2 ++
 arch/x86/kvm/svm.c   |  2 +-
 arch/x86/kvm/vmx.c   |  2 +-
 arch/x86/kvm/x86.c   |  2 +-
 6 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 7c077a9d9777..f2f5d260874e 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -200,7 +200,6 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
 	atomic_inc(&pt->pending);
 	smp_mb__after_atomic_inc();
-	/* FIXME: handle case where the guest is in guest mode */
 	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
 		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(&vcpu0->wq);
@@ -237,6 +236,19 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	struct hrtimer *timer;
+
+	if (vcpu->vcpu_id != 0 || !pit)
+		return;
+
+	timer = &pit->pit_state.pit_timer.timer;
+	if (hrtimer_cancel(timer))
+		hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+}
+
 static void destroy_pit_timer(struct kvm_kpit_timer *pt)
 {
 	pr_debug("pit: execute del timer!\n");
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index ce1f583459b1..76d736b5f664 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -94,3 +94,9 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
 	/* TODO: PIT, RTC etc. */
 }
 EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
+
+void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
+{
+	__kvm_migrate_apic_timer(vcpu);
+	__kvm_migrate_pit_timer(vcpu);
+}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 1802134b836f..2a15be2275c0 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -84,6 +84,8 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu);
+void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
 
 int pit_has_pending_timer(struct kvm_vcpu *vcpu);
 int apic_has_pending_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ab22615eee89..6b0d5fa5bab3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -688,7 +688,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		delta = vcpu->arch.host_tsc - tsc_this;
 		svm->vmcb->control.tsc_offset += delta;
 		vcpu->cpu = cpu;
-		kvm_migrate_apic_timer(vcpu);
+		kvm_migrate_timers(vcpu);
 	}
 
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe4db11989c..96445f341519 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -608,7 +608,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if (vcpu->cpu != cpu) {
 		vcpu_clear(vmx);
-		kvm_migrate_apic_timer(vcpu);
+		kvm_migrate_timers(vcpu);
 		vpid_sync_vcpu_all(vmx);
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 21338bdb28ff..00acf1301a15 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2758,7 +2758,7 @@ again:
 
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
-			__kvm_migrate_apic_timer(vcpu);
+			__kvm_migrate_timers(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
 			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
-- 
cgit v1.2.2


From e693d71b46e64536581bf4884434fc1b8797e96f Mon Sep 17 00:00:00 2001
From: Eli Collins <ecollins@vmware.com>
Date: Sun, 1 Jun 2008 20:24:40 -0700
Subject: KVM: VMX: Clear CR4.VMXE in hardware_disable

Clear CR4.VMXE in hardware_disable. There's no reason to leave it set
after doing a VMXOFF.

VMware Workstation 6.5 checks CR4.VMXE as a proxy for whether the CPU is
in VMX mode, so leaving VMXE set means we'll refuse to power on. With this
change the user can power on after unloading the kvm-intel module. I
tested on kvm-67 and kvm-69.

Signed-off-by: Eli Collins <ecollins@vmware.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/vmx.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 96445f341519..02efbe75f317 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1036,6 +1036,7 @@ static void hardware_enable(void *garbage)
 static void hardware_disable(void *garbage)
 {
 	asm volatile (ASM_VMX_VMXOFF : : : "cc");
+	write_cr4(read_cr4() & ~X86_CR4_VMXE);
 }
 
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
-- 
cgit v1.2.2


From 8d2d73b9a5c35f2c6abf427afba7888cfc4cc65d Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Wed, 4 Jun 2008 18:42:24 +0300
Subject: KVM: MMU: reschedule during shadow teardown

Shadows for large guests can take a long time to tear down, so reschedule
occasionally to avoid softlockup warnings.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/mmu.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7246b60afb96..c2fd6a4a58c3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1858,6 +1858,7 @@ static void free_mmu_pages(struct kvm_vcpu *vcpu)
 		sp = container_of(vcpu->kvm->arch.active_mmu_pages.next,
 				  struct kvm_mmu_page, link);
 		kvm_mmu_zap_page(vcpu->kvm, sp);
+		cond_resched();
 	}
 	free_page((unsigned long)vcpu->arch.mmu.pae_root);
 }
-- 
cgit v1.2.2


From ebb0e6264c7a65c51feb3575e9edb58eab0cf469 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Tue, 20 May 2008 16:21:58 +0300
Subject: KVM: MMU: Fix printk() format string

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/paging_tmpl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 156fe10288ae..934c7b619396 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -418,7 +418,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	/* mmio */
 	if (is_error_pfn(pfn)) {
-		pgprintk("gfn %x is mmio\n", walker.gfn);
+		pgprintk("gfn %lx is mmio\n", walker.gfn);
 		kvm_release_pfn_clean(pfn);
 		return 1;
 	}
-- 
cgit v1.2.2


From 3c9155106d589584f67b026ec444e69c4a68d7dc Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Tue, 20 May 2008 16:21:13 +0300
Subject: KVM: MMU: Fix is_empty_shadow_page() check

The check is only looking at one of two possible empty ptes.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index c2fd6a4a58c3..ee3f53098f0c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -658,7 +658,7 @@ static int is_empty_shadow_page(u64 *spt)
 	u64 *end;
 
 	for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
-		if (*pos != shadow_trap_nonpresent_pte) {
+		if (is_shadow_present_pte(*pos)) {
 			printk(KERN_ERR "%s: %p %llx\n", __func__,
 			       pos, *pos);
 			return 0;
-- 
cgit v1.2.2


From 668231141f307ffd81db075b34bddaedae0ec863 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Thu, 5 Jun 2008 16:35:10 +0200
Subject: x86: fix compile warning in io_apic_{32,64}.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 1 +
 arch/x86/kernel/io_apic_64.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a40d54fc1fdd..4fbf656b08b4 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1489,6 +1489,7 @@ void /*__init*/ print_local_APIC(void * dummy)
 
 	printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
 		smp_processor_id(), hard_smp_processor_id());
+	v = apic_read(APIC_ID);
 	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v,
 			GET_APIC_ID(read_apic_id()));
 	v = apic_read(APIC_LVR);
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index ef1a8dfcc529..c7c6b005f665 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1077,6 +1077,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
 
 	printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
 		smp_processor_id(), hard_smp_processor_id());
+	v = apic_read(APIC_ID);
 	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
-- 
cgit v1.2.2


From b7f09ae583c49d28b2796d2fa5893dcf822e3a10 Mon Sep 17 00:00:00 2001
From: Miquel van Smoorenburg <mikevs@xs4all.net>
Date: Thu, 5 Jun 2008 18:14:44 +0200
Subject: x86, pci-dma.c: don't always add __GFP_NORETRY to gfp

Currently arch/x86/kernel/pci-dma.c always adds __GFP_NORETRY
to the allocation flags, because it wants to be reasonably
sure not to deadlock when calling alloc_pages().

But really that should only be done in two cases:
- when allocating memory in the lower 16 MB DMA zone.
  If there's no free memory there, waiting or OOM killing is of no use
- when optimistically trying an allocation in the DMA32 zone
  when dma_mask < DMA_32BIT_MASK hoping that the allocation
  happens to fall within the limits of the dma_mask

Also blindly adding __GFP_NORETRY to the the gfp variable might
not be a good idea since we then also use it when calling
dma_ops->alloc_coherent(). Clearing it might also not be a
good idea, dma_alloc_coherent()'s caller might have set it
on purpose. The gfp variable should not be clobbered.

[ mingo@elte.hu: converted to delta patch ontop of previous version. ]

Signed-off-by: Miquel van Smoorenburg <miquels@cistron.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-dma.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 069e843f0b93..dc00a1331ace 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -378,6 +378,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	struct page *page;
 	unsigned long dma_mask = 0;
 	dma_addr_t bus;
+	int noretry = 0;
 
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -397,19 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dev->dma_mask == NULL)
 		return NULL;
 
+	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+	if (gfp & __GFP_DMA)
+		noretry = 1;
+
 #ifdef CONFIG_X86_64
 	/* Why <=? Even when the mask is smaller than 4GB it is often
 	   larger than 16MB and in this case we have a chance of
 	   finding fitting memory in the next higher zone first. If
 	   not retry with true GFP_DMA. -AK */
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
 		gfp |= GFP_DMA32;
+		if (dma_mask < DMA_32BIT_MASK)
+			noretry = 1;
+	}
 #endif
 
  again:
-	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
 	page = dma_alloc_pages(dev,
-		(gfp & GFP_DMA) ? gfp | __GFP_NORETRY : gfp, get_order(size));
+		noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
 	if (page == NULL)
 		return NULL;
 
-- 
cgit v1.2.2


From 9e26d84273541a8c6c2efb705457ca8e6245fb73 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Fri, 6 Jun 2008 12:01:13 +0200
Subject: fix build bug in "x86: add PCI extended config space access for AMD
 Barcelona"

Also much less code now.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd.c    |  2 --
 arch/x86/kernel/cpu/amd_64.c |  1 +
 arch/x86/kernel/cpu/cpu.h    |  5 +++++
 arch/x86/kernel/setup.c      |  2 +-
 arch/x86/kernel/setup.h      | 26 --------------------------
 arch/x86/kernel/setup_64.c   |  2 --
 6 files changed, 7 insertions(+), 31 deletions(-)
 delete mode 100644 arch/x86/kernel/setup.h

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 656b40aed647..a38d54f4ff25 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -4,10 +4,8 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
-#include <asm/mmconfig.h>
 
 #include <mach_apic.h>
-#include "../setup.h"
 #include "cpu.h"
 
 /*
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 180097e99219..626fc21f027d 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -6,6 +6,7 @@
 #include <asm/cacheflush.h>
 
 #include <mach_apic.h>
+#include "cpu.h"
 
 extern int __cpuinit get_model_name(struct cpuinfo_x86 *c);
 extern void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 783691b2a738..f5d5bb1b5541 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -1,3 +1,4 @@
+#ifdef CONFIG_X86_32
 
 struct cpu_model_info {
 	int vendor;
@@ -36,3 +37,7 @@ extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
 
 extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
+
+#endif /* CONFIG_X86_32 */
+
+extern void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d8f171234013..20e14dbef107 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -136,6 +136,7 @@ void __init setup_per_cpu_areas(void)
 	setup_cpumask_of_cpu();
 }
 
+#endif
 #define ENABLE_CF8_EXT_CFG      (1ULL << 46)
 
 void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c)
@@ -149,4 +150,3 @@ void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c)
 	set_cpu_cap(c, X86_FEATURE_PCI_EXT_CFG);
 }
 
-#endif
diff --git a/arch/x86/kernel/setup.h b/arch/x86/kernel/setup.h
deleted file mode 100644
index 66cc2c7f961d..000000000000
--- a/arch/x86/kernel/setup.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Internal declarations for shared x86 setup code.
- *
- * Copyright (c) 2008 Advanced Micro Devices, Inc.
- * Contributed by Robert Richter <robert.richter@amd.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
- * 02111-1307 USA
- */
-
-#ifndef _ARCH_X86_KERNEL_SETUP_H
-
-extern void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c);
-
-#endif	/* _ARCH_X86_KERNEL_SETUP_H */
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 215bd67e5b6c..25afdd80a3cf 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -73,8 +73,6 @@
 #include <asm/pat.h>
 #include <asm/mmconfig.h>
 
-#include "setup.h"
-
 #include <mach_apic.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
-- 
cgit v1.2.2


From 7058b06188232381c13ff05a3caf458bb892b834 Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 7 Jun 2008 14:14:35 +0200
Subject: x86: coding style fixes to arch/x86/pci/irq.

Before:
total: 60 errors, 85 warnings, 1237 lines checked

After:
total: 1 errors, 82 warnings, 1226 lines checked

WARNING: line over 80 characters

Compile tested.

paolo@paolo-desktop:/tmp$ size irq.o.*
   text    data     bss     dec     hex filename
   6128     440      76    6644    19f4 irq.o.after
   6128     440      76    6644    19f4 irq.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/pci/irq.c | 261 +++++++++++++++++++++++++----------------------------
 1 file changed, 125 insertions(+), 136 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0908fca901bf..7300567e480b 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -11,8 +11,8 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dmi.h>
-#include <asm/io.h>
-#include <asm/smp.h>
+#include <linux/io.h>
+#include <linux/smp.h>
 #include <asm/io_apic.h>
 #include <linux/irq.h>
 #include <linux/acpi.h>
@@ -61,7 +61,7 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL;
  *  and perform checksum verification.
  */
 
-static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr)
+static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr)
 {
 	struct irq_routing_table *rt;
 	int i;
@@ -74,7 +74,7 @@ static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr)
 	    rt->size < sizeof(struct irq_routing_table))
 		return NULL;
 	sum = 0;
-	for (i=0; i < rt->size; i++)
+	for (i = 0; i < rt->size; i++)
 		sum += addr[i];
 	if (!sum) {
 		DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", rt);
@@ -100,7 +100,7 @@ static struct irq_routing_table * __init pirq_find_routing_table(void)
 			return rt;
 		printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n");
 	}
-	for(addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) {
+	for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) {
 		rt = pirq_check_routing_table(addr);
 		if (rt)
 			return rt;
@@ -122,20 +122,20 @@ static void __init pirq_peer_trick(void)
 	struct irq_info *e;
 
 	memset(busmap, 0, sizeof(busmap));
-	for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) {
+	for (i = 0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) {
 		e = &rt->slots[i];
 #ifdef DEBUG
 		{
 			int j;
 			DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot);
-			for(j=0; j<4; j++)
+			for (j = 0; j < 4; j++)
 				DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap);
 			DBG("\n");
 		}
 #endif
 		busmap[e->bus] = 1;
 	}
-	for(i = 1; i < 256; i++) {
+	for (i = 1; i < 256; i++) {
 		int node;
 		if (!busmap[i] || pci_find_bus(0, i))
 			continue;
@@ -285,7 +285,7 @@ static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
 	static const unsigned char pirqmap[4] = { 1, 0, 2, 3 };
 
 	WARN_ON_ONCE(pirq > 4);
-	return read_config_nybble(router,0x43, pirqmap[pirq-1]);
+	return read_config_nybble(router, 0x43, pirqmap[pirq-1]);
 }
 
 static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
@@ -314,7 +314,7 @@ static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
 
 /*
  * Cyrix: nibble offset 0x5C
- * 0x5C bits 7:4 is INTB bits 3:0 is INTA 
+ * 0x5C bits 7:4 is INTB bits 3:0 is INTA
  * 0x5D bits 7:4 is INTD bits 3:0 is INTC
  */
 static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
@@ -350,7 +350,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
  *	Apparently there are systems implementing PCI routing table using
  *	link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D.
  *	We try our best to handle both link mappings.
- *	
+ *
  *	Currently (2003-05-21) it appears most SiS chipsets follow the
  *	definition of routing registers from the SiS-5595 southbridge.
  *	According to the SiS 5595 datasheets the revision id's of the
@@ -370,7 +370,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
  *
  *	0x62:	USBIRQ:
  *		bit 6 OHCI function disabled (0), enabled (1)
- *	
+ *
  *	0x6a:	ACPI/SCI IRQ: bits 4-6 reserved
  *
  *	0x7e:	Data Acq. Module IRQ - bits 4-6 reserved
@@ -487,9 +487,7 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq
 	u8 irq;
 	irq = 0;
 	if (pirq <= 4)
-	{
 		irq = read_config_nybble(router, 0x56, pirq - 1);
-	}
 	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n",
 		dev->vendor, dev->device, pirq, irq);
 	return irq;
@@ -497,12 +495,10 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq
 
 static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
 {
-	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", 
+	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n",
 		dev->vendor, dev->device, pirq, irq);
 	if (pirq <= 4)
-	{
 		write_config_nybble(router, 0x56, pirq - 1, irq);
-	}
 	return 1;
 }
 
@@ -549,50 +545,49 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
 	if (pci_dev_present(pirq_440gx))
 		return 0;
 
-	switch(device)
-	{
-		case PCI_DEVICE_ID_INTEL_82371FB_0:
-		case PCI_DEVICE_ID_INTEL_82371SB_0:
-		case PCI_DEVICE_ID_INTEL_82371AB_0:
-		case PCI_DEVICE_ID_INTEL_82371MX:
-		case PCI_DEVICE_ID_INTEL_82443MX_0:
-		case PCI_DEVICE_ID_INTEL_82801AA_0:
-		case PCI_DEVICE_ID_INTEL_82801AB_0:
-		case PCI_DEVICE_ID_INTEL_82801BA_0:
-		case PCI_DEVICE_ID_INTEL_82801BA_10:
-		case PCI_DEVICE_ID_INTEL_82801CA_0:
-		case PCI_DEVICE_ID_INTEL_82801CA_12:
-		case PCI_DEVICE_ID_INTEL_82801DB_0:
-		case PCI_DEVICE_ID_INTEL_82801E_0:
-		case PCI_DEVICE_ID_INTEL_82801EB_0:
-		case PCI_DEVICE_ID_INTEL_ESB_1:
-		case PCI_DEVICE_ID_INTEL_ICH6_0:
-		case PCI_DEVICE_ID_INTEL_ICH6_1:
-		case PCI_DEVICE_ID_INTEL_ICH7_0:
-		case PCI_DEVICE_ID_INTEL_ICH7_1:
-		case PCI_DEVICE_ID_INTEL_ICH7_30:
-		case PCI_DEVICE_ID_INTEL_ICH7_31:
-		case PCI_DEVICE_ID_INTEL_ESB2_0:
-		case PCI_DEVICE_ID_INTEL_ICH8_0:
-		case PCI_DEVICE_ID_INTEL_ICH8_1:
-		case PCI_DEVICE_ID_INTEL_ICH8_2:
-		case PCI_DEVICE_ID_INTEL_ICH8_3:
-		case PCI_DEVICE_ID_INTEL_ICH8_4:
-		case PCI_DEVICE_ID_INTEL_ICH9_0:
-		case PCI_DEVICE_ID_INTEL_ICH9_1:
-		case PCI_DEVICE_ID_INTEL_ICH9_2:
-		case PCI_DEVICE_ID_INTEL_ICH9_3:
-		case PCI_DEVICE_ID_INTEL_ICH9_4:
-		case PCI_DEVICE_ID_INTEL_ICH9_5:
-		case PCI_DEVICE_ID_INTEL_TOLAPAI_0:
-		case PCI_DEVICE_ID_INTEL_ICH10_0:
-		case PCI_DEVICE_ID_INTEL_ICH10_1:
-		case PCI_DEVICE_ID_INTEL_ICH10_2:
-		case PCI_DEVICE_ID_INTEL_ICH10_3:
-			r->name = "PIIX/ICH";
-			r->get = pirq_piix_get;
-			r->set = pirq_piix_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_INTEL_82371FB_0:
+	case PCI_DEVICE_ID_INTEL_82371SB_0:
+	case PCI_DEVICE_ID_INTEL_82371AB_0:
+	case PCI_DEVICE_ID_INTEL_82371MX:
+	case PCI_DEVICE_ID_INTEL_82443MX_0:
+	case PCI_DEVICE_ID_INTEL_82801AA_0:
+	case PCI_DEVICE_ID_INTEL_82801AB_0:
+	case PCI_DEVICE_ID_INTEL_82801BA_0:
+	case PCI_DEVICE_ID_INTEL_82801BA_10:
+	case PCI_DEVICE_ID_INTEL_82801CA_0:
+	case PCI_DEVICE_ID_INTEL_82801CA_12:
+	case PCI_DEVICE_ID_INTEL_82801DB_0:
+	case PCI_DEVICE_ID_INTEL_82801E_0:
+	case PCI_DEVICE_ID_INTEL_82801EB_0:
+	case PCI_DEVICE_ID_INTEL_ESB_1:
+	case PCI_DEVICE_ID_INTEL_ICH6_0:
+	case PCI_DEVICE_ID_INTEL_ICH6_1:
+	case PCI_DEVICE_ID_INTEL_ICH7_0:
+	case PCI_DEVICE_ID_INTEL_ICH7_1:
+	case PCI_DEVICE_ID_INTEL_ICH7_30:
+	case PCI_DEVICE_ID_INTEL_ICH7_31:
+	case PCI_DEVICE_ID_INTEL_ESB2_0:
+	case PCI_DEVICE_ID_INTEL_ICH8_0:
+	case PCI_DEVICE_ID_INTEL_ICH8_1:
+	case PCI_DEVICE_ID_INTEL_ICH8_2:
+	case PCI_DEVICE_ID_INTEL_ICH8_3:
+	case PCI_DEVICE_ID_INTEL_ICH8_4:
+	case PCI_DEVICE_ID_INTEL_ICH9_0:
+	case PCI_DEVICE_ID_INTEL_ICH9_1:
+	case PCI_DEVICE_ID_INTEL_ICH9_2:
+	case PCI_DEVICE_ID_INTEL_ICH9_3:
+	case PCI_DEVICE_ID_INTEL_ICH9_4:
+	case PCI_DEVICE_ID_INTEL_ICH9_5:
+	case PCI_DEVICE_ID_INTEL_TOLAPAI_0:
+	case PCI_DEVICE_ID_INTEL_ICH10_0:
+	case PCI_DEVICE_ID_INTEL_ICH10_1:
+	case PCI_DEVICE_ID_INTEL_ICH10_2:
+	case PCI_DEVICE_ID_INTEL_ICH10_3:
+		r->name = "PIIX/ICH";
+		r->get = pirq_piix_get;
+		r->set = pirq_piix_set;
+		return 1;
 	}
 	return 0;
 }
@@ -606,7 +601,7 @@ static __init int via_router_probe(struct irq_router *r,
 	 * workarounds for some buggy BIOSes
 	 */
 	if (device == PCI_DEVICE_ID_VIA_82C586_0) {
-		switch(router->device) {
+		switch (router->device) {
 		case PCI_DEVICE_ID_VIA_82C686:
 			/*
 			 * Asus k7m bios wrongly reports 82C686A
@@ -624,7 +619,7 @@ static __init int via_router_probe(struct irq_router *r,
 		}
 	}
 
-	switch(device) {
+	switch (device) {
 	case PCI_DEVICE_ID_VIA_82C586_0:
 		r->name = "VIA";
 		r->get = pirq_via586_get;
@@ -647,13 +642,12 @@ static __init int via_router_probe(struct irq_router *r,
 
 static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_VLSI_82C534:
-			r->name = "VLSI 82C534";
-			r->get = pirq_vlsi_get;
-			r->set = pirq_vlsi_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_VLSI_82C534:
+		r->name = "VLSI 82C534";
+		r->get = pirq_vlsi_get;
+		r->set = pirq_vlsi_set;
+		return 1;
 	}
 	return 0;
 }
@@ -661,14 +655,13 @@ static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router
 
 static __init int serverworks_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_SERVERWORKS_OSB4:
-		case PCI_DEVICE_ID_SERVERWORKS_CSB5:
-			r->name = "ServerWorks";
-			r->get = pirq_serverworks_get;
-			r->set = pirq_serverworks_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_SERVERWORKS_OSB4:
+	case PCI_DEVICE_ID_SERVERWORKS_CSB5:
+		r->name = "ServerWorks";
+		r->get = pirq_serverworks_get;
+		r->set = pirq_serverworks_set;
+		return 1;
 	}
 	return 0;
 }
@@ -677,7 +670,7 @@ static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router,
 {
 	if (device != PCI_DEVICE_ID_SI_503)
 		return 0;
-		
+
 	r->name = "SIS";
 	r->get = pirq_sis_get;
 	r->set = pirq_sis_set;
@@ -686,47 +679,43 @@ static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router,
 
 static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_CYRIX_5520:
-			r->name = "NatSemi";
-			r->get = pirq_cyrix_get;
-			r->set = pirq_cyrix_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_CYRIX_5520:
+		r->name = "NatSemi";
+		r->get = pirq_cyrix_get;
+		r->set = pirq_cyrix_set;
+		return 1;
 	}
 	return 0;
 }
 
 static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_OPTI_82C700:
-			r->name = "OPTI";
-			r->get = pirq_opti_get;
-			r->set = pirq_opti_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_OPTI_82C700:
+		r->name = "OPTI";
+		r->get = pirq_opti_get;
+		r->set = pirq_opti_set;
+		return 1;
 	}
 	return 0;
 }
 
 static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_ITE_IT8330G_0:
-			r->name = "ITE";
-			r->get = pirq_ite_get;
-			r->set = pirq_ite_set;
-			return 1;
+	switch (device) {
+	case PCI_DEVICE_ID_ITE_IT8330G_0:
+		r->name = "ITE";
+		r->get = pirq_ite_get;
+		r->set = pirq_ite_set;
+		return 1;
 	}
 	return 0;
 }
 
 static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
+	switch (device) {
 	case PCI_DEVICE_ID_AL_M1533:
 	case PCI_DEVICE_ID_AL_M1563:
 		printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n");
@@ -740,25 +729,24 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router,
 
 static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
-	switch(device)
-	{
-		case PCI_DEVICE_ID_AMD_VIPER_740B:
-			r->name = "AMD756";
-			break;
-		case PCI_DEVICE_ID_AMD_VIPER_7413:
-			r->name = "AMD766";
-			break;
-		case PCI_DEVICE_ID_AMD_VIPER_7443:
-			r->name = "AMD768";
-			break;
-		default:
-			return 0;
+	switch (device) {
+	case PCI_DEVICE_ID_AMD_VIPER_740B:
+		r->name = "AMD756";
+		break;
+	case PCI_DEVICE_ID_AMD_VIPER_7413:
+		r->name = "AMD766";
+		break;
+	case PCI_DEVICE_ID_AMD_VIPER_7443:
+		r->name = "AMD768";
+		break;
+	default:
+		return 0;
 	}
 	r->get = pirq_amd756_get;
 	r->set = pirq_amd756_set;
 	return 1;
 }
-		
+
 static __init int pico_router_probe(struct irq_router *r, struct pci_dev *router, u16 device)
 {
 	switch (device) {
@@ -800,7 +788,7 @@ static struct pci_dev *pirq_router_dev;
  *	FIXME: should we have an option to say "generic for
  *	chipset" ?
  */
- 
+
 static void __init pirq_find_router(struct irq_router *r)
 {
 	struct irq_routing_table *rt = pirq_table;
@@ -819,7 +807,7 @@ static void __init pirq_find_router(struct irq_router *r)
 	r->name = "default";
 	r->get = NULL;
 	r->set = NULL;
-	
+
 	DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for %04x:%04x\n",
 	    rt->rtr_vendor, rt->rtr_device);
 
@@ -830,7 +818,7 @@ static void __init pirq_find_router(struct irq_router *r)
 		return;
 	}
 
-	for( h = pirq_routers; h->vendor; h++) {
+	for (h = pirq_routers; h->vendor; h++) {
 		/* First look for a router match */
 		if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev, rt->rtr_device))
 			break;
@@ -882,7 +870,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 
 	if (!pirq_table)
 		return 0;
-	
+
 	DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin);
 	info = pirq_get_info(dev);
 	if (!info) {
@@ -921,8 +909,10 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	 */
 	newirq = dev->irq;
 	if (newirq && !((1 << newirq) & mask)) {
-		if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0;
-		else printk("\n" KERN_WARNING
+		if (pci_probe & PCI_USE_PIRQ_MASK)
+			newirq = 0;
+		else
+			printk("\n" KERN_WARNING
 			"PCI: IRQ %i for device %s doesn't match PIRQ mask "
 			"- try pci=usepirqmask\n" KERN_DEBUG, newirq,
 			pci_name(dev));
@@ -942,8 +932,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		irq = pirq & 0xf;
 		DBG(" -> hardcoded IRQ %d\n", irq);
 		msg = "Hardcoded";
-	} else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
-	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) {
+	} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
+	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
 		DBG(" -> got IRQ %d\n", irq);
 		msg = "Found";
 		eisa_set_level_irq(irq);
@@ -978,15 +968,15 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 			continue;
 		if (info->irq[pin].link == pirq) {
 			/* We refuse to override the dev->irq information. Give a warning! */
-		    	if ( dev2->irq && dev2->irq != irq && \
+			if (dev2->irq && dev2->irq != irq && \
 			(!(pci_probe & PCI_USE_PIRQ_MASK) || \
-			((1 << dev2->irq) & mask)) ) {
+			((1 << dev2->irq) & mask))) {
 #ifndef CONFIG_PCI_MSI
-		    		printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n",
+				printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n",
 				       pci_name(dev2), dev2->irq, irq);
 #endif
-		    		continue;
-		    	}
+				continue;
+			}
 			dev2->irq = irq;
 			pirq_penalty[irq]++;
 			if (dev != dev2)
@@ -1024,8 +1014,7 @@ static void __init pcibios_fixup_irqs(void)
 		/*
 		 * Recalculate IRQ numbers if we use the I/O APIC.
 		 */
-		if (io_apic_assign_pci_irqs)
-		{
+		if (io_apic_assign_pci_irqs) {
 			int irq;
 
 			if (pin) {
@@ -1038,10 +1027,10 @@ static void __init pcibios_fixup_irqs(void)
 	 * busses itself so we should get into this branch reliably.
 	 */
 				if (irq < 0 && dev->bus->parent) { /* go back to the bridge */
-					struct pci_dev * bridge = dev->bus->self;
+					struct pci_dev *bridge = dev->bus->self;
 
 					pin = (pin + PCI_SLOT(dev->devfn)) % 4;
-					irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, 
+					irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 							PCI_SLOT(bridge->devfn), pin);
 					if (irq >= 0)
 						printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n",
@@ -1131,7 +1120,7 @@ static int __init pcibios_irq_init(void)
 		pirq_find_router(&pirq_router);
 		if (pirq_table->exclusive_irqs) {
 			int i;
-			for (i=0; i<16; i++)
+			for (i = 0; i < 16; i++)
 				if (!(pirq_table->exclusive_irqs & (1 << i)))
 					pirq_penalty[i] += 100;
 		}
@@ -1196,10 +1185,10 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			 */
 			temp_dev = dev;
 			while (irq < 0 && dev->bus->parent) { /* go back to the bridge */
-				struct pci_dev * bridge = dev->bus->self;
+				struct pci_dev *bridge = dev->bus->self;
 
 				pin = (pin + PCI_SLOT(dev->devfn)) % 4;
-				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, 
+				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 						PCI_SLOT(bridge->devfn), pin);
 				if (irq >= 0)
 					printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n",
-- 
cgit v1.2.2


From 5b80fe8bd732b5dd442118a43e02db22e8fd93e2 Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 7 Jun 2008 14:34:42 +0200
Subject: x86: coding style fixes to arch/x86/kernel/sys_i386_32.c

Before:
total: 16 errors, 25 warnings, 246 lines checked

After:
total: 0 errors, 7 warnings, 246 lines checked

Compile tested.

paolo@paolo-desktop:/tmp$ size sys*
   text    data     bss     dec     hex filename
   1209       0       0    1209     4b9 sys_i386_32.o.after
   1209       0       0    1209     4b9 sys_i386_32.o.before

paolo@paolo-desktop:/tmp$ md5sum sys*
6144f6d6ce7342c3e192681a1ccaa1c1  sys_i386_32.o.after
6144f6d6ce7342c3e192681a1ccaa1c1  sys_i386_32.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/sys_i386_32.c | 64 +++++++++++++++++++++----------------------
 1 file changed, 32 insertions(+), 32 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index d2ab52cc1d6b..7066cb855a60 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -19,8 +19,8 @@
 #include <linux/utsname.h>
 #include <linux/ipc.h>
 
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
+#include <linux/uaccess.h>
+#include <linux/unistd.h>
 
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 			  unsigned long prot, unsigned long flags,
@@ -103,7 +103,7 @@ asmlinkage int old_select(struct sel_arg_struct __user *arg)
  *
  * This is really horribly ugly.
  */
-asmlinkage int sys_ipc (uint call, int first, int second,
+asmlinkage int sys_ipc(uint call, int first, int second,
 			int third, void __user *ptr, long fifth)
 {
 	int version, ret;
@@ -113,24 +113,24 @@ asmlinkage int sys_ipc (uint call, int first, int second,
 
 	switch (call) {
 	case SEMOP:
-		return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL);
+		return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL);
 	case SEMTIMEDOP:
 		return sys_semtimedop(first, (struct sembuf __user *)ptr, second,
 					(const struct timespec __user *)fifth);
 
 	case SEMGET:
-		return sys_semget (first, second, third);
+		return sys_semget(first, second, third);
 	case SEMCTL: {
 		union semun fourth;
 		if (!ptr)
 			return -EINVAL;
 		if (get_user(fourth.__pad, (void __user * __user *) ptr))
 			return -EFAULT;
-		return sys_semctl (first, second, third, fourth);
+		return sys_semctl(first, second, third, fourth);
 	}
 
 	case MSGSND:
-		return sys_msgsnd (first, (struct msgbuf __user *) ptr, 
+		return sys_msgsnd(first, (struct msgbuf __user *) ptr,
 				   second, third);
 	case MSGRCV:
 		switch (version) {
@@ -138,45 +138,45 @@ asmlinkage int sys_ipc (uint call, int first, int second,
 			struct ipc_kludge tmp;
 			if (!ptr)
 				return -EINVAL;
-			
+
 			if (copy_from_user(&tmp,
-					   (struct ipc_kludge __user *) ptr, 
-					   sizeof (tmp)))
+					   (struct ipc_kludge __user *) ptr,
+					   sizeof(tmp)))
 				return -EFAULT;
-			return sys_msgrcv (first, tmp.msgp, second,
+			return sys_msgrcv(first, tmp.msgp, second,
 					   tmp.msgtyp, third);
 		}
 		default:
-			return sys_msgrcv (first,
+			return sys_msgrcv(first,
 					   (struct msgbuf __user *) ptr,
 					   second, fifth, third);
 		}
 	case MSGGET:
-		return sys_msgget ((key_t) first, second);
+		return sys_msgget((key_t) first, second);
 	case MSGCTL:
-		return sys_msgctl (first, second, (struct msqid_ds __user *) ptr);
+		return sys_msgctl(first, second, (struct msqid_ds __user *) ptr);
 
 	case SHMAT:
 		switch (version) {
 		default: {
 			ulong raddr;
-			ret = do_shmat (first, (char __user *) ptr, second, &raddr);
+			ret = do_shmat(first, (char __user *) ptr, second, &raddr);
 			if (ret)
 				return ret;
-			return put_user (raddr, (ulong __user *) third);
+			return put_user(raddr, (ulong __user *) third);
 		}
 		case 1:	/* iBCS2 emulator entry point */
 			if (!segment_eq(get_fs(), get_ds()))
 				return -EINVAL;
 			/* The "(ulong *) third" is valid _only_ because of the kernel segment thing */
-			return do_shmat (first, (char __user *) ptr, second, (ulong *) third);
+			return do_shmat(first, (char __user *) ptr, second, (ulong *) third);
 		}
-	case SHMDT: 
-		return sys_shmdt ((char __user *)ptr);
+	case SHMDT:
+		return sys_shmdt((char __user *)ptr);
 	case SHMGET:
-		return sys_shmget (first, second, third);
+		return sys_shmget(first, second, third);
 	case SHMCTL:
-		return sys_shmctl (first, second,
+		return sys_shmctl(first, second,
 				   (struct shmid_ds __user *) ptr);
 	default:
 		return -ENOSYS;
@@ -186,28 +186,28 @@ asmlinkage int sys_ipc (uint call, int first, int second,
 /*
  * Old cruft
  */
-asmlinkage int sys_uname(struct old_utsname __user * name)
+asmlinkage int sys_uname(struct old_utsname __user *name)
 {
 	int err;
 	if (!name)
 		return -EFAULT;
 	down_read(&uts_sem);
-	err = copy_to_user(name, utsname(), sizeof (*name));
+	err = copy_to_user(name, utsname(), sizeof(*name));
 	up_read(&uts_sem);
-	return err?-EFAULT:0;
+	return err? -EFAULT:0;
 }
 
-asmlinkage int sys_olduname(struct oldold_utsname __user * name)
+asmlinkage int sys_olduname(struct oldold_utsname __user *name)
 {
 	int error;
 
 	if (!name)
 		return -EFAULT;
-	if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+	if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
 		return -EFAULT;
-  
-  	down_read(&uts_sem);
-	
+
+	down_read(&uts_sem);
+
 	error = __copy_to_user(&name->sysname, &utsname()->sysname,
 			       __OLD_UTS_LEN);
 	error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
@@ -223,9 +223,9 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name)
 	error |= __copy_to_user(&name->machine, &utsname()->machine,
 				__OLD_UTS_LEN);
 	error |= __put_user(0, name->machine + __OLD_UTS_LEN);
-	
+
 	up_read(&uts_sem);
-	
+
 	error = error ? -EFAULT : 0;
 
 	return error;
@@ -241,6 +241,6 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
 	long __res;
 	asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
 	: "=a" (__res)
-	: "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory");
+	: "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory");
 	return __res;
 }
-- 
cgit v1.2.2


From 6ddd2a27948f0bd02a2ad001e8a6816898eba0dc Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 16:59:53 +0200
Subject: x86: simplify idle selection

default_idle is selected in cpu_idle(), when no other idle routine is
selected. Select it in select_idle_routine() when mwait is not
selected.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process.c    | 18 +++++++-----------
 arch/x86/kernel/process_32.c |  7 +------
 arch/x86/kernel/process_64.c |  7 ++-----
 3 files changed, 10 insertions(+), 22 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ba370dc8685b..b3078f4ce25b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -139,27 +139,23 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
-	static int selected;
-
-	if (selected)
-		return;
 #ifdef CONFIG_X86_SMP
 	if (pm_idle == poll_idle && smp_num_siblings > 1) {
 		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
 			" performance may degrade.\n");
 	}
 #endif
+	if (pm_idle)
+		return;
+
 	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
 		/*
-		 * Skip, if setup has overridden idle.
 		 * One CPU supports mwait => All CPUs supports mwait
 		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
+		printk(KERN_INFO "using mwait in idle threads.\n");
+		pm_idle = mwait_idle;
+	} else
+		pm_idle = default_idle;
 }
 
 static int __init idle_setup(char *str)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f8476dfbb60d..ee4ab461c50d 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -168,24 +168,19 @@ void cpu_idle(void)
 	while (1) {
 		tick_nohz_stop_sched_tick();
 		while (!need_resched()) {
-			void (*idle)(void);
 
 			check_pgt_cache();
 			rmb();
-			idle = pm_idle;
 
 			if (rcu_pending(cpu))
 				rcu_check_callbacks(cpu, 0);
 
-			if (!idle)
-				idle = default_idle;
-
 			if (cpu_is_offline(cpu))
 				play_dead();
 
 			local_irq_disable();
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
-			idle();
+			pm_idle();
 		}
 		tick_nohz_restart_sched_tick();
 		preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e2319f39988b..db3d89a04399 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -150,12 +150,9 @@ void cpu_idle(void)
 	while (1) {
 		tick_nohz_stop_sched_tick();
 		while (!need_resched()) {
-			void (*idle)(void);
 
 			rmb();
-			idle = pm_idle;
-			if (!idle)
-				idle = default_idle;
+
 			if (cpu_is_offline(smp_processor_id()))
 				play_dead();
 			/*
@@ -165,7 +162,7 @@ void cpu_idle(void)
 			 */
 			local_irq_disable();
 			enter_idle();
-			idle();
+			pm_idle();
 			/* In many cases the interrupt that ended idle
 			   has already called exit_idle. But some idle
 			   loops can be woken up without interrupt. */
-- 
cgit v1.2.2


From aa83f3f2cfc74d66d01b1d2eb1485ea1103a0f4e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 17:11:13 +0200
Subject: x86: cleanup C1E enabled detection

Rename the "MSR_K8_ENABLE_C1E" MSR to INT_PENDING_MSG, which is the
name in the data sheet as well. Move the C1E mask to the header file.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd.c    | 5 ++---
 arch/x86/kernel/cpu/amd_64.c | 5 ++---
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a38d54f4ff25..30b5055be355 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -25,7 +25,6 @@ extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
 #ifdef CONFIG_X86_LOCAL_APIC
-#define ENABLE_C1E_MASK         0x18000000
 #define CPUID_PROCESSOR_SIGNATURE       1
 #define CPUID_XFAM              0x0ff00000
 #define CPUID_XFAM_K8           0x00000000
@@ -45,8 +44,8 @@ static __cpuinit int amd_apic_timer_broken(void)
 			break;
 	case CPUID_XFAM_10H:
 	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-		if (lo & ENABLE_C1E_MASK) {
+		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
 			if (smp_processor_id() != boot_cpu_physical_apicid)
 				printk(KERN_INFO "AMD C1E detected late. "
 				       "	Force timer broadcast.\n");
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 626fc21f027d..6eef3c79d151 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -110,7 +110,6 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define ENABLE_C1E_MASK		0x18000000
 #define CPUID_PROCESSOR_SIGNATURE	1
 #define CPUID_XFAM		0x0ff00000
 #define CPUID_XFAM_K8		0x00000000
@@ -130,8 +129,8 @@ static __cpuinit int amd_apic_timer_broken(void)
 			break;
 	case CPUID_XFAM_10H:
 	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-		if (lo & ENABLE_C1E_MASK)
+		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+		if (lo & K8_INTP_C1E_ACTIVE_MASK)
 			return 1;
 		break;
 	default:
-- 
cgit v1.2.2


From 732d7be17b98ebfd59e5864c3490f19856fa832c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 17:27:20 +0200
Subject: x86: use cpuinfo to check for interrupt pending message msr

Simplify code: no need to do a cpuid(1) again. The cpuinfo structure
has all necessary information already.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd.c    | 41 +++++++++++++++--------------------------
 arch/x86/kernel/cpu/amd_64.c | 38 +++++++++++++++-----------------------
 2 files changed, 30 insertions(+), 49 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 30b5055be355..e76b49e7a916 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -25,35 +25,24 @@ extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
 #ifdef CONFIG_X86_LOCAL_APIC
-#define CPUID_PROCESSOR_SIGNATURE       1
-#define CPUID_XFAM              0x0ff00000
-#define CPUID_XFAM_K8           0x00000000
-#define CPUID_XFAM_10H          0x00100000
-#define CPUID_XFAM_11H          0x00200000
-#define CPUID_XMOD              0x000f0000
-#define CPUID_XMOD_REV_F        0x00040000
 
 /* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
+static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
 {
 	u32 lo, hi;
-	u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
-	switch (eax & CPUID_XFAM) {
-	case CPUID_XFAM_K8:
-		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
-			break;
-	case CPUID_XFAM_10H:
-	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			if (smp_processor_id() != boot_cpu_physical_apicid)
-				printk(KERN_INFO "AMD C1E detected late. "
-				       "	Force timer broadcast.\n");
-			return 1;
-		}
-		break;
-	default:
-		/* err on the side of caution */
+
+	if (c->x86 < 0x0F)
+		return 0;
+
+	/* Family 0x0f models < rev F do not have this MSR */
+	if (c->x86 == 0x0f && c->x86_model < 0x40)
+		return 0;
+
+	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+		if (smp_processor_id() != boot_cpu_physical_apicid)
+			printk(KERN_INFO "AMD C1E detected late. "
+			       "Force timer broadcast.\n");
 		return 1;
 	}
 	return 0;
@@ -297,7 +286,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	}
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (amd_apic_timer_broken())
+	if (amd_apic_timer_broken(c))
 		local_apic_timer_disabled = 1;
 #endif
 
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 6eef3c79d151..f5fc161d8f2a 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -110,31 +110,23 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define CPUID_PROCESSOR_SIGNATURE	1
-#define CPUID_XFAM		0x0ff00000
-#define CPUID_XFAM_K8		0x00000000
-#define CPUID_XFAM_10H		0x00100000
-#define CPUID_XFAM_11H		0x00200000
-#define CPUID_XMOD		0x000f0000
-#define CPUID_XMOD_REV_F	0x00040000
-
 /* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
+static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
 {
-	u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
+	u32 lo, hi;
 
-	switch (eax & CPUID_XFAM) {
-	case CPUID_XFAM_K8:
-		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
-			break;
-	case CPUID_XFAM_10H:
-	case CPUID_XFAM_11H:
-		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-		if (lo & K8_INTP_C1E_ACTIVE_MASK)
-			return 1;
-		break;
-	default:
-		/* err on the side of caution */
+	if (c->x86 < 0x0F)
+		return 0;
+
+	/* Family 0x0f models < rev F do not have this MSR */
+	if (c->x86 == 0x0f && c->x86_model < 0x40)
+		return 0;
+
+	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+		if (smp_processor_id() != boot_cpu_physical_apicid)
+			printk(KERN_INFO "AMD C1E detected late. "
+			       "Force timer broadcast.\n");
 		return 1;
 	}
 	return 0;
@@ -220,7 +212,7 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		amd_enable_pci_ext_cfg(c);
 
-	if (amd_apic_timer_broken())
+	if (amd_apic_timer_broken(c))
 		disable_apic_timer = 1;
 
 	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
-- 
cgit v1.2.2


From 09fd4b4ef5bc7e5222c13acec1bee8cd252fb63f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 18:04:27 +0200
Subject: x86: use cpuid to check MWAIT support for C1

cpuid(0x05) provides extended information about MWAIT in EDX when bit
0 of ECX is set. Bit 4-7 of EDX determine whether MWAIT is supported
for C1. C1E enabled CPUs have these bits set to 0.

Based on an earlier patch from Andi Kleen.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process.c | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b3078f4ce25b..fe415ba606e0 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -122,19 +122,31 @@ static void poll_idle(void)
  *
  * idle=mwait overrides this decision and forces the usage of mwait.
  */
+
+#define MWAIT_INFO			0x05
+#define MWAIT_ECX_EXTENDED_INFO		0x01
+#define MWAIT_EDX_C1			0xf0
+
 static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 {
+	u32 eax, ebx, ecx, edx;
+
 	if (force_mwait)
 		return 1;
 
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		switch(c->x86) {
-		case 0x10:
-		case 0x11:
-			return 0;
-		}
-	}
-	return 1;
+	if (c->cpuid_level < MWAIT_INFO)
+		return 0;
+
+	cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx);
+	/* Check, whether EDX has extended info about MWAIT */
+	if (!(ecx & MWAIT_ECX_EXTENDED_INFO))
+		return 1;
+
+	/*
+	 * edx enumeratios MONITOR/MWAIT extensions. Check, whether
+	 * C1  supports MWAIT
+	 */
+	return (edx & MWAIT_EDX_C1);
 }
 
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-- 
cgit v1.2.2


From 00dba56465228825ea806e3a7fc0aa6bba7bdc6c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 18:35:28 +0200
Subject: x86: move more common idle functions/variables to process.c

more unification. Should cause no change in functionality.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process.c    | 70 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/process_32.c | 54 ----------------------------------
 arch/x86/kernel/process_64.c | 28 ------------------
 3 files changed, 70 insertions(+), 82 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index fe415ba606e0..9fea14607dfe 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -45,6 +45,76 @@ void arch_task_cache_init(void)
 				  SLAB_PANIC, NULL);
 }
 
+/*
+ * Idle related variables and functions
+ */
+unsigned long boot_option_idle_override = 0;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+EXPORT_SYMBOL(pm_idle);
+
+#ifdef CONFIG_X86_32
+/*
+ * This halt magic was a workaround for ancient floppy DMA
+ * wreckage. It should be safe to remove.
+ */
+static int hlt_counter;
+void disable_hlt(void)
+{
+	hlt_counter++;
+}
+EXPORT_SYMBOL(disable_hlt);
+
+void enable_hlt(void)
+{
+	hlt_counter--;
+}
+EXPORT_SYMBOL(enable_hlt);
+
+static inline int hlt_use_halt(void)
+{
+	return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+}
+#else
+static inline int hlt_use_halt(void)
+{
+	return 1;
+}
+#endif
+
+/*
+ * We use this if we don't have any better
+ * idle routine..
+ */
+void default_idle(void)
+{
+	if (hlt_use_halt()) {
+		current_thread_info()->status &= ~TS_POLLING;
+		/*
+		 * TS_POLLING-cleared state must be visible before we
+		 * test NEED_RESCHED:
+		 */
+		smp_mb();
+
+		if (!need_resched())
+			safe_halt();	/* enables interrupts racelessly */
+		else
+			local_irq_enable();
+		current_thread_info()->status |= TS_POLLING;
+	} else {
+		local_irq_enable();
+		/* loop is done by the caller */
+		cpu_relax();
+	}
+}
+#ifdef CONFIG_APM_MODULE
+EXPORT_SYMBOL(default_idle);
+#endif
+
 static void do_nothing(void *unused)
 {
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ee4ab461c50d..ae4020486a97 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -58,11 +58,6 @@
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-static int hlt_counter;
-
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
@@ -77,55 +72,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return ((unsigned long *)tsk->thread.sp)[3];
 }
 
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-
-void disable_hlt(void)
-{
-	hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-	hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
-	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we
-		 * test NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (!need_resched())
-			safe_halt();	/* enables interrupts racelessly */
-		else
-			local_irq_enable();
-		current_thread_info()->status |= TS_POLLING;
-	} else {
-		local_irq_enable();
-		/* loop is done by the caller */
-		cpu_relax();
-	}
-}
-#ifdef CONFIG_APM_MODULE
-EXPORT_SYMBOL(default_idle);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <asm/nmi.h>
 /* We don't actually take CPU down, just spin without interrupts. */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index db3d89a04399..9fb3a6fe863b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -56,15 +56,6 @@ asmlinkage extern void ret_from_fork(void);
 
 unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
 
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
 
 void idle_notifier_register(struct notifier_block *n)
@@ -94,25 +85,6 @@ void exit_idle(void)
 	__exit_idle();
 }
 
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
-	current_thread_info()->status &= ~TS_POLLING;
-	/*
-	 * TS_POLLING-cleared state must be visible before we
-	 * test NEED_RESCHED:
-	 */
-	smp_mb();
-	if (!need_resched())
-		safe_halt();	/* enables interrupts racelessly */
-	else
-		local_irq_enable();
-	current_thread_info()->status |= TS_POLLING;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 DECLARE_PER_CPU(int, cpu_state);
 
-- 
cgit v1.2.2


From 39b8931b5cad9a7cbcd2394a40a088311e783a82 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Mon, 9 Jun 2008 16:48:18 -0700
Subject: ACPI: handle invalid ACPI SLIT table

This is a SLIT sanity checking patch.  It moves slit_valid() function to
generic ACPI code and does sanity checking for both x86 and ia64.  It sets up
node_distance with LOCAL_DISTANCE and REMOTE_DISTANCE when hitting invalid
SLIT table on ia64.  It also cleans up unused variable localities in
acpi_parse_slit() on x86.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/mm/srat_64.c | 27 ---------------------------
 1 file changed, 27 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 3890234e5b26..99649dccad28 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -97,36 +97,9 @@ static __init inline int srat_disabled(void)
 	return numa_off || acpi_numa < 0;
 }
 
-/*
- * A lot of BIOS fill in 10 (= no distance) everywhere. This messes
- * up the NUMA heuristics which wants the local node to have a smaller
- * distance than the others.
- * Do some quick checks here and only use the SLIT if it passes.
- */
-static __init int slit_valid(struct acpi_table_slit *slit)
-{
-	int i, j;
-	int d = slit->locality_count;
-	for (i = 0; i < d; i++) {
-		for (j = 0; j < d; j++)  {
-			u8 val = slit->entry[d*i + j];
-			if (i == j) {
-				if (val != LOCAL_DISTANCE)
-					return 0;
-			} else if (val <= LOCAL_DISTANCE)
-				return 0;
-		}
-	}
-	return 1;
-}
-
 /* Callback for SLIT parsing */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
-	if (!slit_valid(slit)) {
-		printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n");
-		return;
-	}
 	acpi_slit = slit;
 }
 
-- 
cgit v1.2.2


From c26421d01986e1521043c8feb47256833df3bf31 Mon Sep 17 00:00:00 2001
From: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Date: Thu, 29 May 2008 12:01:44 -0700
Subject: x86: fix Xorg crash with xf86MapVidMem error

Clarify the usage of mtrr_lookup() in PAT code, and to make PAT code
resilient to mtrr lookup problems.

Specifically, pat_x_mtrr_type() is restructured to highlight, under what
conditions we look for mtrr hint. pat_x_mtrr_type() uses a default type
when there are any errors in mtrr lookup (still maintaining the pat
consistency). And, reserve_memtype() highlights its usage ot mtrr_lookup
for request type of '-1' and also defaults in a sane way on any mtrr
lookup failure.

pat.c looks at mtrr type of a range to get a hint on what mapping type
to request when user/API: (1) hasn't specified any type (/dev/mem
mapping) and we do not want to take performance hit by always mapping
UC_MINUS. This will be the case for /dev/mem mappings used to map BIOS
area or ACPI region which are WB'able. In this case, as long as MTRR is
not WB, PAT will request UC_MINUS for such mappings.

(2) user/API requests WB mapping while in reality MTRR may have UC or
WC. In this case, PAT can map as WB (without checking MTRR) and still
effective type will be UC or WC. But, a subsequent request to map same
region as UC or WC may fail, as the region will get trackked as WB in
PAT list. Looking at MTRR hint helps us to track based on effective type
rather than what user requested. Again, here mtrr_lookup is only used as
hint and we fallback to WB mapping (as requested by user) as default.

In both cases, after using the mtrr hint, we still go through the
memtype list to make sure there are no inconsistencies among multiple
users.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Rufus & Azrael <rufus-azrael@numericable.fr>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 49 ++++++++++++++++++++++++-------------------------
 1 file changed, 24 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index e83b770676d5..320d644a8107 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -164,32 +164,33 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
 	unsigned long pat_type;
 	u8 mtrr_type;
 
-	mtrr_type = mtrr_type_lookup(start, end);
-	if (mtrr_type == 0xFF) {		/* MTRR not enabled */
-		*ret_prot = prot;
-		return 0;
-	}
-	if (mtrr_type == 0xFE) {		/* MTRR match error */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-	if (mtrr_type != MTRR_TYPE_UNCACHABLE &&
-	    mtrr_type != MTRR_TYPE_WRBACK &&
-	    mtrr_type != MTRR_TYPE_WRCOMB) {	/* MTRR type unhandled */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-
 	pat_type = prot & _PAGE_CACHE_MASK;
 	prot &= (~_PAGE_CACHE_MASK);
 
-	/* Currently doing intersection by hand. Optimize it later. */
+	/*
+	 * We return the PAT request directly for types where PAT takes
+	 * precedence with respect to MTRR and for UC_MINUS.
+	 * Consistency checks with other PAT requests is done later
+	 * while going through memtype list.
+	 */
 	if (pat_type == _PAGE_CACHE_WC) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
+		return 0;
 	} else if (pat_type == _PAGE_CACHE_UC_MINUS) {
 		*ret_prot = prot | _PAGE_CACHE_UC_MINUS;
-	} else if (pat_type == _PAGE_CACHE_UC ||
-	           mtrr_type == MTRR_TYPE_UNCACHABLE) {
+		return 0;
+	} else if (pat_type == _PAGE_CACHE_UC) {
+		*ret_prot = prot | _PAGE_CACHE_UC;
+		return 0;
+	}
+
+	/*
+	 * Look for MTRR hint to get the effective type in case where PAT
+	 * request is for WB.
+	 */
+	mtrr_type = mtrr_type_lookup(start, end);
+
+	if (mtrr_type == MTRR_TYPE_UNCACHABLE) {
 		*ret_prot = prot | _PAGE_CACHE_UC;
 	} else if (mtrr_type == MTRR_TYPE_WRCOMB) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
@@ -246,14 +247,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	if (req_type == -1) {
 		/*
-		 * Special case where caller wants to inherit from mtrr or
-		 * existing pat mapping, defaulting to UC_MINUS in case of
-		 * no match.
+		 * Call mtrr_lookup to get the type hint. This is an
+		 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+		 * tools and ACPI tools). Use WB request for WB memory and use
+		 * UC_MINUS otherwise.
 		 */
 		u8 mtrr_type = mtrr_type_lookup(start, end);
-		if (mtrr_type == 0xFE) { /* MTRR match error */
-			err = -1;
-		}
 
 		if (mtrr_type == MTRR_TYPE_WRBACK) {
 			req_type = _PAGE_CACHE_WB;
-- 
cgit v1.2.2


From ee863ba7ab3d3ed8a9585d378aae69d1e3e9f1b4 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Tue, 10 Jun 2008 16:04:30 +0200
Subject: x86: unconditionally enable PAT for AMD CPUs

If PAT support is advertised it should just work. No errata known.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/addon_cpuid_features.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index d8b3e4a9d663..0fbd06241e07 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -54,14 +54,11 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0xf && c->x86 <= 0x11)
-			return;
-		break;
 	case X86_VENDOR_INTEL:
 		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
 			return;
 		break;
+	case X86_VENDOR_AMD:
 	case X86_VENDOR_CENTAUR:
 	case X86_VENDOR_TRANSMETA:
 		return;
-- 
cgit v1.2.2


From 97cfab6ac4ddfda0d722393bbf46cc40bc332107 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Tue, 10 Jun 2008 16:05:18 +0200
Subject: x86: PAT: fix ambiguous paranoia check in pat_init()

Starting with commit 8d4a4300854f3971502e81dacd930704cb88f606 (x86:
cleanup PAT cpu validation) the PAT CPU feature flag is not cleared
anymore. Now the error message

  "PAT enabled, but CPU feature cleared"

in pat_init() is misleading.

Furthermore the current code does not check for existence of the PAT
CPU feature flag if a CPU is whitelisted in validate_pat_support.

This patch clears pat_wc_enabled if boot CPU has no PAT feature flag
and adapts the paranoia check.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/addon_cpuid_features.c |  7 ++++---
 arch/x86/mm/pat.c                          | 11 ++++++-----
 2 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 0fbd06241e07..2df461f06a52 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -53,6 +53,9 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_PAT
 void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 {
+	if (!cpu_has_pat)
+		pat_disable("PAT not supported by CPU.");
+
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
@@ -64,8 +67,6 @@ void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	pat_disable(cpu_has_pat ?
-		    "PAT disabled. Not yet verified on this CPU type." :
-		    "PAT not supported by CPU.");
+	pat_disable("PAT disabled. Not yet verified on this CPU type.");
 }
 #endif
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 320d644a8107..65105b1195a3 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -76,14 +76,15 @@ void pat_init(void)
 		return;
 
 	/* Paranoia check. */
-	if (!cpu_has_pat) {
-		printk(KERN_ERR "PAT enabled, but CPU feature cleared\n");
+	if (!cpu_has_pat && boot_pat_state) {
 		/*
-		 * Panic if this happens on the secondary CPU, and we
+		 * If this happens we are on a secondary CPU, but
 		 * switched to PAT on the boot CPU. We have no way to
 		 * undo PAT.
-		*/
-		BUG_ON(boot_pat_state);
+		 */
+		printk(KERN_ERR "PAT enabled, "
+		       "but not supported by secondary CPU\n");
+		BUG();
 	}
 
 	/* Set PWT to Write-Combining. All other bits stay the same */
-- 
cgit v1.2.2


From cd7a4e936d345ab4cb49d68192d90bd4e4c58458 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Tue, 10 Jun 2008 16:05:39 +0200
Subject: x86: PAT: fixed checkpatch errors (and whitespaces)

x86: PAT: fixed checkpatch errors (and whitespaces)

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/addon_cpuid_features.c |  2 --
 arch/x86/mm/pat.c                          | 29 ++++++++++++++---------------
 2 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 2df461f06a52..84a8220a6072 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -1,9 +1,7 @@
-
 /*
  *	Routines to indentify additional cpu features that are scattered in
  *	cpuid space.
  */
-
 #include <linux/cpu.h>
 
 #include <asm/pat.h>
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 65105b1195a3..a8b69bb26972 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -66,7 +66,7 @@ enum {
 	PAT_UC_MINUS = 7,	/* UC, but can be overriden by MTRR */
 };
 
-#define PAT(x,y)	((u64)PAT_ ## y << ((x)*8))
+#define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
 
 void pat_init(void)
 {
@@ -100,8 +100,8 @@ void pat_init(void)
 	 *      011 UC		_PAGE_CACHE_UC
 	 * PAT bit unused
 	 */
-	pat = PAT(0,WB) | PAT(1,WC) | PAT(2,UC_MINUS) | PAT(3,UC) |
-	      PAT(4,WB) | PAT(5,WC) | PAT(6,UC_MINUS) | PAT(7,UC);
+	pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+	      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
 
 	/* Boot CPU check */
 	if (!boot_pat_state)
@@ -117,11 +117,11 @@ void pat_init(void)
 static char *cattr_name(unsigned long flags)
 {
 	switch (flags & _PAGE_CACHE_MASK) {
-		case _PAGE_CACHE_UC:		return "uncached";
-		case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
-		case _PAGE_CACHE_WB:		return "write-back";
-		case _PAGE_CACHE_WC:		return "write-combining";
-		default:			return "broken";
+	case _PAGE_CACHE_UC:		return "uncached";
+	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
+	case _PAGE_CACHE_WB:		return "write-back";
+	case _PAGE_CACHE_WC:		return "write-combining";
+	default:			return "broken";
 	}
 }
 
@@ -536,11 +536,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	 * we maintain the tradition of paranoia in this code.
 	 */
 	if (!pat_wc_enabled &&
-	    ! ( boot_cpu_has(X86_FEATURE_MTRR) ||
-		boot_cpu_has(X86_FEATURE_K6_MTRR) ||
-		boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
-		boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
-	   (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
+	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
+	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
+	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
+	      boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
+	    (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
 		flags = _PAGE_CACHE_UC;
 	}
 #endif
@@ -562,7 +562,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 		return 0;
 
 	if (pfn <= max_pfn_mapped &&
-            ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
+	    ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
 		free_memtype(offset, offset + size);
 		printk(KERN_INFO
 		"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
@@ -600,4 +600,3 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 
 	free_memtype(addr, addr + size);
 }
-
-- 
cgit v1.2.2


From 499f8f84b8324ba27d756e03f373fa16eeed9ccc Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Tue, 10 Jun 2008 16:06:21 +0200
Subject: x86: rename pat_wc_enabled to pat_enabled

BTW, what does pat_wc_enabled stand for? Does it mean
"write-combining"?

Currently it is used to globally switch on or off PAT support.
Thus I renamed it to pat_enabled.
I think this increases readability (and hope that I didn't miss
something).

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/ioremap.c  |  4 ++--
 arch/x86/mm/pageattr.c |  2 +-
 arch/x86/mm/pat.c      | 16 ++++++++--------
 arch/x86/pci/i386.c    |  4 ++--
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 71bb3159031a..ddeafed1171e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -261,7 +261,7 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
 	/*
 	 * Ideally, this should be:
-	 *	pat_wc_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
+	 *	pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
 	 *
 	 * Till we fix all X drivers to use ioremap_wc(), we will use
 	 * UC MINUS.
@@ -285,7 +285,7 @@ EXPORT_SYMBOL(ioremap_nocache);
  */
 void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size)
 {
-	if (pat_wc_enabled)
+	if (pat_enabled)
 		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
 					__builtin_return_address(0));
 	else
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 60bcb5b6a37e..6916fe4bf0cb 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -805,7 +805,7 @@ int _set_memory_wc(unsigned long addr, int numpages)
 
 int set_memory_wc(unsigned long addr, int numpages)
 {
-	if (!pat_wc_enabled)
+	if (!pat_enabled)
 		return set_memory_uc(addr, numpages);
 
 	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index a8b69bb26972..4beccea0897f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -26,11 +26,11 @@
 #include <asm/io.h>
 
 #ifdef CONFIG_X86_PAT
-int __read_mostly pat_wc_enabled = 1;
+int __read_mostly pat_enabled = 1;
 
 void __cpuinit pat_disable(char *reason)
 {
-	pat_wc_enabled = 0;
+	pat_enabled = 0;
 	printk(KERN_INFO "%s\n", reason);
 }
 
@@ -72,7 +72,7 @@ void pat_init(void)
 {
 	u64 pat;
 
-	if (!pat_wc_enabled)
+	if (!pat_enabled)
 		return;
 
 	/* Paranoia check. */
@@ -225,8 +225,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	unsigned long actual_type;
 	int err = 0;
 
-	/* Only track when pat_wc_enabled */
-	if (!pat_wc_enabled) {
+	/* Only track when pat_enabled */
+	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
 		if (ret_type) {
 			if (req_type == -1) {
@@ -440,8 +440,8 @@ int free_memtype(u64 start, u64 end)
 	struct memtype *ml;
 	int err = -EINVAL;
 
-	/* Only track when pat_wc_enabled */
-	if (!pat_wc_enabled) {
+	/* Only track when pat_enabled */
+	if (!pat_enabled) {
 		return 0;
 	}
 
@@ -535,7 +535,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	 * caching for the high addresses through the KEN pin, but
 	 * we maintain the tradition of paranoia in this code.
 	 */
-	if (!pat_wc_enabled &&
+	if (!pat_enabled &&
 	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 10fb308fded8..6ccd7a108cd4 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -299,9 +299,9 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	prot = pgprot_val(vma->vm_page_prot);
-	if (pat_wc_enabled && write_combine)
+	if (pat_enabled && write_combine)
 		prot |= _PAGE_CACHE_WC;
-	else if (pat_wc_enabled || boot_cpu_data.x86 > 3)
+	else if (pat_enabled || boot_cpu_data.x86 > 3)
 		/*
 		 * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
 		 * To avoid attribute conflicts, request UC MINUS here
-- 
cgit v1.2.2


From f595ec964daf7f99668039d7303ddedd09a75142 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Date: Thu, 12 Jun 2008 10:47:56 +0200
Subject: common implementation of iterative div/mod

We have a few instances of the open-coded iterative div/mod loop, used
when we don't expcet the dividend to be much bigger than the divisor.
Unfortunately modern gcc's have the tendency to strength "reduce" this
into a full mod operation, which isn't necessarily any faster, and
even if it were, doesn't exist if gcc implements it in libgcc.

The workaround is to put a dummy asm statement in the loop to prevent
gcc from performing the transformation.

This patch creates a single implementation of this loop, and uses it
to replace the open-coded versions I know about.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: Christian Kujau <lists@nerdbynature.de>
Cc: Robert Hancock <hancockr@shaw.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/time.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c39e1a5aa241..52b2e3856980 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -12,6 +12,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/kernel_stat.h>
+#include <linux/math64.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
@@ -150,11 +151,7 @@ static void do_stolen_accounting(void)
 	if (stolen < 0)
 		stolen = 0;
 
-	ticks = 0;
-	while (stolen >= NS_PER_TICK) {
-		ticks++;
-		stolen -= NS_PER_TICK;
-	}
+	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
 	__get_cpu_var(residual_stolen) = stolen;
 	account_steal_time(NULL, ticks);
 
@@ -166,11 +163,7 @@ static void do_stolen_accounting(void)
 	if (blocked < 0)
 		blocked = 0;
 
-	ticks = 0;
-	while (blocked >= NS_PER_TICK) {
-		ticks++;
-		blocked -= NS_PER_TICK;
-	}
+	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
 	__get_cpu_var(residual_blocked) = blocked;
 	account_steal_time(idle_task(smp_processor_id()), ticks);
 }
-- 
cgit v1.2.2


From 6703f6d10dcd3316e03641a5ecaa6c8a04374d98 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 10 Jun 2008 00:10:48 +0200
Subject: x86, gart: add resume handling

If GART IOMMU is used on an AMD64 system, the northbridge registers
related to it should be restored during resume so that memory is not
corrupted.  Make gart_resume() handle that as appropriate.

Ref. http://lkml.org/lkml/2008/5/25/96 and the following thread.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/aperture_64.c |  2 ++
 arch/x86/kernel/pci-gart_64.c | 57 +++++++++++++++++++++++++++++++++++++++----
 2 files changed, 54 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index eb20f168c0fd..3409abb231ac 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -496,4 +496,6 @@ out:
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
 		}
 	}
+
+	set_up_gart_resume(aper_order, aper_alloc);
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 3710097f02eb..f505c3890358 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -549,14 +549,63 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
 	return aper_base;
 }
 
+static void enable_gart_translations(void)
+{
+	int i;
+
+	for (i = 0; i < num_k8_northbridges; i++) {
+		struct pci_dev *dev = k8_northbridges[i];
+
+		enable_gart_translation(dev, __pa(agp_gatt_table));
+	}
+}
+
+/*
+ * If fix_up_north_bridges is set, the north bridges have to be fixed up on
+ * resume in the same way as they are handled in gart_iommu_hole_init().
+ */
+static bool fix_up_north_bridges;
+static u32 aperture_order;
+static u32 aperture_alloc;
+
+void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
+{
+	fix_up_north_bridges = true;
+	aperture_order = aper_order;
+	aperture_alloc = aper_alloc;
+}
+
 static int gart_resume(struct sys_device *dev)
 {
+	printk(KERN_INFO "PCI-DMA: Resuming GART IOMMU\n");
+
+	if (fix_up_north_bridges) {
+		int i;
+
+		printk(KERN_INFO "PCI-DMA: Restoring GART aperture settings\n");
+
+		for (i = 0; i < num_k8_northbridges; i++) {
+			struct pci_dev *dev = k8_northbridges[i];
+
+			/*
+			 * Don't enable translations just yet.  That is the next
+			 * step.  Restore the pre-suspend aperture settings.
+			 */
+			pci_write_config_dword(dev, AMD64_GARTAPERTURECTL,
+						aperture_order << 1);
+			pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE,
+						aperture_alloc >> 25);
+		}
+	}
+
+	enable_gart_translations();
+
 	return 0;
 }
 
 static int gart_suspend(struct sys_device *dev, pm_message_t state)
 {
-	return -EINVAL;
+	return 0;
 }
 
 static struct sysdev_class gart_sysdev_class = {
@@ -614,16 +663,14 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	memset(gatt, 0, gatt_size);
 	agp_gatt_table = gatt;
 
-	for (i = 0; i < num_k8_northbridges; i++) {
-		dev = k8_northbridges[i];
-		enable_gart_translation(dev, __pa(gatt));
-	}
+	enable_gart_translations();
 
 	error = sysdev_class_register(&gart_sysdev_class);
 	if (!error)
 		error = sysdev_register(&device_gart);
 	if (error)
 		panic("Could not register gart_sysdev -- would corrupt data on next suspend");
+
 	flush_gart();
 
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
-- 
cgit v1.2.2


From 3703f39965a197ebd91743fc38d0f640606b8da3 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 4 Jun 2008 18:13:37 +0200
Subject: geode: fix modular build

-tip testing found this build bug:

 MODPOST 331 modules
 ERROR: "geode_mfgpt_toggle_event" [drivers/watchdog/geodewdt.ko] undefined!
 ERROR: "geode_mfgpt_alloc_timer" [drivers/watchdog/geodewdt.ko] undefined!
 make[1]: *** [__modpost] Error 1
 make: *** [modules] Error 2

with this config:

  http://redhat.com/~mingo/misc/config-Wed_Jun__4_18_01_59_CEST_2008.bad

export those symbols.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/mfgpt_32.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 3cad17fe026b..07c0f828f488 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
 	wrmsr(msr, value, dummy);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event);
 
 int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
 {
@@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain)
 	/* No timers available - too bad */
 	return -1;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer);
 
 
 #ifdef CONFIG_GEODE_MFGPT_TIMER
-- 
cgit v1.2.2


From b29c701deacd5d24453127c37ed77ef851c53b8b Mon Sep 17 00:00:00 2001
From: Henry Nestler <henry.nestler@gmail.com>
Date: Mon, 12 May 2008 15:44:39 +0200
Subject: x86: fix endless page faults in mount_block_root for Linux 2.6

Page faults in kernel address space between PAGE_OFFSET up to
VMALLOC_START should not try to map as vmalloc.

Fix rarely endless page faults inside mount_block_root for root
filesystem at boot time.

All 32bit kernels up to 2.6.25 can fail into this hole.
I can not present this under native linux kernel. I see, that the 64bit
has fixed the problem. I copied the same lines into 32bit part.

Recorded debugs are from coLinux kernel 2.6.22.18 (virtualisation):
http://www.henrynestler.com/colinux/testing/pfn-check-0.7.3/20080410-antinx/bug16-recursive-page-fault-endless.txt
The physicaly memory was trimmed down to 192MB to better catch the bug.
More memory gets the bug more rarely.

Details, how every x86 32bit system can fail:

Start from "mount_block_root",
http://lxr.linux.no/linux/init/do_mounts.c#L297
There the variable "fs_names" got one memory page with 4096 bytes.
Variable "p" walks through the existing file system types. The first
string is no problem.
But, with the second loop in mount_block_root the offset of "p" is not
at beginning of page, the offset is for example +9, if "reiserfs" is the
first in list.
Than calls do_mount_root, and lands in sys_mount.
Remember: Variable "type_page" contains now "fs_type+9" and not contains
a full page.
The sys_mount copies 4096 bytes with function "exact_copy_from_user()":
http://lxr.linux.no/linux/fs/namespace.c#L1540

Mostly exist pages after the buffer "fs_names+4096+9" and the page fault
handler was not called. No problem.

In the case, if the page after "fs_names+4096" is not mapped, the page
fault handler was called from http://lxr.linux.no/linux/fs/namespace.c#L1320

The do_page_fault gots an address 0xc03b4000.
It's kernel address, address >= TASK_SIZE, but not from vmalloc! It's
from "__getname()" alias "kmem_cache_alloc".
The "error_code" is 0. "vmalloc_fault" will be call:
http://lxr.linux.no/linux/arch/i386/mm/fault.c#L332

"vmalloc_fault" tryed to find the physical page for a non existing
virtual memory area. The macro "pte_present" in vmalloc_fault()
got a next page fault for 0xc0000ed0 at:
http://lxr.linux.no/linux/arch/i386/mm/fault.c#L282

No PTE exist for such virtual address. The page fault handler was trying
to sync the physical page for the PTE lockup.

This called vmalloc_fault() again for address 0xc000000, and that also
was not existing. The endless began...

In normal case the cpu would still loop with disabled interrrupts. Under
coLinux this was catched by a stack overflow inside printk debugs.

Signed-off-by: Henry Nestler <henry.nestler@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/fault.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fd7e1798c75a..8bcb6f40ccb6 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -497,6 +497,11 @@ static int vmalloc_fault(unsigned long address)
 	unsigned long pgd_paddr;
 	pmd_t *pmd_k;
 	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
-- 
cgit v1.2.2


From 86b2b70e156203149c3861455feec54bc4906e6d Mon Sep 17 00:00:00 2001
From: Joe Korty <joe.korty@ccur.com>
Date: Mon, 2 Jun 2008 17:21:06 -0400
Subject: x86: fix asm warning in head_32.S

On Mon, May 19, 2008 at 04:10:02PM -0700, Linus Torvalds wrote:
> It also causes these warnings on 32-bit PAE:
>
> 	  AS      arch/x86/kernel/head_32.o
> 	arch/x86/kernel/head_32.S: Assembler messages:
> 	arch/x86/kernel/head_32.S:225: Warning: left operand is a bignum; integer 0 assumed
> 	arch/x86/kernel/head_32.S:609: Warning: left operand is a bignum; integer 0 assumed
>
> and I do not see why (the end result seems to be identical).

Fix head_32.S gcc bignum warnings when CONFIG_PAE=y.

    arch/x86/kernel/head_32.S: Assembler messages:
    arch/x86/kernel/head_32.S:225: Warning: left operand is a bignum; integer 0 assumed
    arch/x86/kernel/head_32.S:609: Warning: left operand is a bignum; integer 0 assumed

The assembler was stumbling over the 64-bit constant 0x100000000 in the
KPMDS #define.

Testing: a cmp(1) on head_32.o before and after shows the binary is unchanged.

Signed-off-by: Joe Korty <joe.korty@ccur.com
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Gabriel C <nix.or.die@googlemail.com>
Cc: Keith Packard <keithp@keithp.com>
Cc: "Pallipadi Venkatesh" <venkatesh.pallipadi@intel.com>
Cc: Eric Anholt <eric@anholt.net>
Cc: "Siddha Suresh B" <suresh.b.siddha@intel.com>
Cc: bugme-daemon@bugzilla.kernel.org
Cc: airlied@linux.ie
Cc: "Barnes Jesse" <jesse.barnes@intel.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/head_32.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b2cc73768a9d..f7357cc0162c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -189,7 +189,7 @@ default_entry:
 	 * this stage.
 	 */
 
-#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
 
 	xorl %ebx,%ebx				/* %ebx is kept at zero */
 
-- 
cgit v1.2.2


From 0b6a39f7ebcb1c82587ce35b401c513eed41ac5c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 9 Jun 2008 13:29:43 +0200
Subject: Revert "x86: fix ioapic bug again"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 6e908947b4995bc0e551a8257c586d5c3e428201.

Németh Márton reported:

| there is a problem in 2.6.26-rc3 which was not there in case of
| 2.6.25: the CPU wakes up ~90,000 times per sec instead of ~60 per sec.
|
| I also "git bisected" the problem, the result is:
|
| 6e908947b4995bc0e551a8257c586d5c3e428201 is first bad commit
| commit 6e908947b4995bc0e551a8257c586d5c3e428201
| Author: Ingo Molnar <mingo@elte.hu>
| Date:   Fri Mar 21 14:32:36 2008 +0100
|
|     x86: fix ioapic bug again

the original problem is fixed by Maciej W. Rozycki in the tip/x86/apic
branch (confirmed by Márton), but those changes are too intrusive for
v2.6.26 so we'll go for the less intrusive (repeated) revert now.

Reported-and-bisected-by: Németh Márton <nm127@freemail.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 12 ++----------
 arch/x86/kernel/nmi_32.c     |  9 ++-------
 2 files changed, 4 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a40d54fc1fdd..4dc8600d9d20 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2130,14 +2130,10 @@ static inline void __init check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
 	int vector;
-	unsigned int ver;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	ver = apic_read(APIC_LVR);
-	ver = GET_APIC_VERSION(ver);
-
 	/*
 	 * get/set the timer IRQ vector:
 	 */
@@ -2150,15 +2146,11 @@ static inline void __init check_timer(void)
 	 * mode for the 8259A whenever interrupts are routed
 	 * through I/O APICs.  Also IRQ0 has to be enabled in
 	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.  Finally timer interrupts
-	 * need to be acknowledged manually in the 8259A for
-	 * timer_interrupt() and for the i82489DX when using
-	 * the NMI watchdog.
+	 * disabled in the local APIC.
 	 */
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	timer_ack = !cpu_has_tsc;
-	timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+	timer_ack = 1;
 	if (timer_over_8254 > 0)
 		enable_8259A_irq(0);
 
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 11b14bbaa61e..84160f74eeb0 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -26,7 +26,6 @@
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
-#include <asm/timer.h>
 
 #include "mach_traps.h"
 
@@ -82,7 +81,7 @@ int __init check_nmi_watchdog(void)
 
 	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
-		goto error;
+		return -1;
 
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -119,7 +118,7 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active)) {
 		kfree(prev_nmi_count);
 		atomic_set(&nmi_active, -1);
-		goto error;
+		return -1;
 	}
 	printk("OK.\n");
 
@@ -130,10 +129,6 @@ int __init check_nmi_watchdog(void)
 
 	kfree(prev_nmi_count);
 	return 0;
-error:
-	timer_ack = !cpu_has_tsc;
-
-	return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
-- 
cgit v1.2.2


From 52aaa12fbe786c90396f1b11ec39c924ccdd8fd5 Mon Sep 17 00:00:00 2001
From: Manish Katiyar <mkatiyar@gmail.com>
Date: Thu, 5 Jun 2008 19:14:15 +0530
Subject: x86: fix unused variable 'loops' warning in arch/x86/boot/a20.c

Following patch fixes the below warning message :
arch/x86/boot/a20.c:118: warning: unused variable 'loops'

Signed-off-by : Manish Katiyar <mkatiyar@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/boot/a20.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c
index 90943f83e84d..e01aafd03bde 100644
--- a/arch/x86/boot/a20.c
+++ b/arch/x86/boot/a20.c
@@ -115,8 +115,6 @@ static void enable_a20_fast(void)
 
 int enable_a20(void)
 {
-	int loops = A20_ENABLE_LOOPS;
-
 #if defined(CONFIG_X86_ELAN)
 	/* Elan croaks if we try to touch the KBC */
 	enable_a20_fast();
@@ -128,6 +126,7 @@ int enable_a20(void)
 	enable_a20_kbc();
 	return 0;
 #else
+       int loops = A20_ENABLE_LOOPS;
 	while (loops--) {
 		/* First, check to see if A20 is already enabled
 		   (legacy free, etc.) */
-- 
cgit v1.2.2


From e32e58a96de4ac35a03349db2ab69f263ded958f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 6 Jun 2008 10:14:08 +0200
Subject: x86: fix lockdep warning during suspend-to-ram

Andrew Morton wrote:

> I've been seeing the below for a long time during suspend-to-ram on the Vaio.
>
>
> PM: Syncing filesystems ... done.
> PM: Preparing system for mem sleep
> Freezing user space processes ... <4>------------[ cut here ]------------
> WARNING: at kernel/lockdep.c:2658 check_flags+0x4c/0x127()
> Modules linked in: i915 drm ipw2200 sonypi ipv6 autofs4 hidp l2cap bluetooth sunrpc nf_conntrack_netbios_ns ipt_REJECT nf_conntrack_ipv4 xt_state nf_conntrack xt_tcpudp iptable_filter ip_tables x_tables acpi_cpufreq nvram ohci1394 ieee1394 ehci_hcd uhci_hcd sg joydev snd_hda_intel snd_seq_dummy sr_mod snd_seq_oss cdrom snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss ieee80211 pcspkr ieee80211_crypt snd_pcm i2c_i801 snd_timer i2c_core ide_pci_generic piix snd soundcore snd_page_alloc button ext3 jbd ide_disk ide_core [last unloaded: ipw2200]
> Pid: 3250, comm: zsh Not tainted 2.6.26-rc5 #1
>  [<c011c5f5>] warn_on_slowpath+0x41/0x6d
>  [<c01080e6>] ? native_sched_clock+0x82/0x96
>  [<c013789c>] ? mark_held_locks+0x41/0x5c
>  [<c0315688>] ? _spin_unlock_irqrestore+0x36/0x58
>  [<c0137a29>] ? trace_hardirqs_on+0xe6/0x10d
>  [<c0138637>] ? __lock_acquire+0xae3/0xb2b
>  [<c0313413>] ? schedule+0x39b/0x3b4
>  [<c0135596>] check_flags+0x4c/0x127
>  [<c01386b9>] lock_acquire+0x3a/0x86
>  [<c0315075>] _spin_lock+0x26/0x53
>  [<c0140660>] ? refrigerator+0x13/0xc3
>  [<c0140660>] refrigerator+0x13/0xc3
>  [<c012684a>] get_signal_to_deliver+0x3c/0x31e
>  [<c0102fe7>] do_notify_resume+0x91/0x6ee
>  [<c01359fd>] ? lock_release_holdtime+0x50/0x56
>  [<c0315688>] ? _spin_unlock_irqrestore+0x36/0x58
>  [<c0235d24>] ? read_chan+0x0/0x58c
>  [<c0137a29>] ? trace_hardirqs_on+0xe6/0x10d
>  [<c0315694>] ? _spin_unlock_irqrestore+0x42/0x58
>  [<c0230afa>] ? tty_ldisc_deref+0x5c/0x63
>  [<c0233104>] ? tty_read+0x66/0x98
>  [<c014b3f0>] ? audit_syscall_exit+0x2aa/0x2c5
>  [<c0109430>] ? do_syscall_trace+0x6b/0x16f
>  [<c0103a9c>] work_notifysig+0x13/0x1b
>  =======================
> ---[ end trace 25b49fe59a25afa5 ]---
> possible reason: unannotated irqs-off.
> irq event stamp: 58919
> hardirqs last  enabled at (58919): [<c0103afd>] syscall_exit_work+0x11/0x26

Joy - I so love entry.S

Best I can make of it:

syscall_exit_work
  resume_userspace
    DISABLE_INTERRUPTS
    (no TRACE_IRQS_OFF)
      work_pending
        work_notifysig
          do_notify_resume()
            do_signal()
              get_signal_to_deliver()
                try_to_freeze()
                  refrigerator()
                    task_lock() -> check_flags() -> BANG

The normal path is:

syscall_exit_work
  resume_userspace
    DISABLE_INTERRUPTS
    restore_all
      TRACE_IRQS_IRET
      iret

No idea why that would not warn..

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/entry_32.S | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2a609dc3271c..c778e4fa55a2 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -248,6 +248,7 @@ ENTRY(resume_userspace)
  	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
+	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
 					# int/exception return?
-- 
cgit v1.2.2


From eb53e9f3ea859a6d59c37b500593b970aa8562e6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 7 Jun 2008 17:18:40 +0100
Subject: x86: fix an incompatible pointer type warning on 64-bit compilations

Fix an incompatible pointer type warning on x86_64 compilations.
early_memtest() is passing a u64* to find_e820_area_size() which is expecting
an unsigned long.  Change t_start and t_size to unsigned long as those are
also 64-bit types on x88_64.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 156e6d7b0e32..998a06ea5f7d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	u64 t_start, t_size;
+	unsigned long t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
+			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
 				t_start, t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
-- 
cgit v1.2.2


From 4461145ef1be92851c230f858f6b6f457c99670f Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@gmail.com>
Date: Thu, 12 Jun 2008 08:55:59 +0200
Subject: x86, lockdep: fix "WARNING: at kernel/lockdep.c:2658
 check_flags+0x4c/0x128()"

Alessandro Suardi reported:
> Recently upgraded my FC6 desktop to Fedora 9; with the
>  latest nautilus RPM updates my VNC session went nuts
>  with nautilus pegging the CPU for everything that breathed.
>
> I now reverted to an earlier nautilus package, but during
>  the peak CPU period my kernel spat this:
>
> [314185.623294] ------------[ cut here ]------------
> [314185.623414] WARNING: at kernel/lockdep.c:2658 check_flags+0x4c/0x128()
> [314185.623514] Modules linked in: iptable_filter ip_tables x_tables
> sunrpc ipv6 fuse snd_via82xx snd_ac97_codec ac97_bus snd_mpu401_uart
> snd_rawmidi via686a hwmon parport_pc sg parport uhci_hcd ehci_hcd
> [314185.623924] Pid: 12314, comm: nautilus Not tainted 2.6.26-rc5-git2 #4
> [314185.624021]  [<c0115b95>] warn_on_slowpath+0x41/0x7b
> [314185.624021]  [<c010de70>] ? do_page_fault+0x2c1/0x5fd
> [314185.624021]  [<c0128396>] ? up_read+0x16/0x28
> [314185.624021]  [<c010de70>] ? do_page_fault+0x2c1/0x5fd
> [314185.624021]  [<c012fa33>] ? __lock_acquire+0xbb4/0xbc3
> [314185.624021]  [<c012d0a0>] check_flags+0x4c/0x128
> [314185.624021]  [<c012fa73>] lock_acquire+0x31/0x7d
> [314185.624021]  [<c0128cf6>] __atomic_notifier_call_chain+0x30/0x80
> [314185.624021]  [<c0128cc6>] ? __atomic_notifier_call_chain+0x0/0x80
> [314185.624021]  [<c0128d52>] atomic_notifier_call_chain+0xc/0xe
> [314185.624021]  [<c0128d81>] notify_die+0x2d/0x2f
> [314185.624021]  [<c01043b0>] do_int3+0x1f/0x4d
> [314185.624021]  [<c02f2d3b>] int3+0x27/0x2c
> [314185.624021]  =======================
> [314185.624021] ---[ end trace 1923f65a2d7bb246 ]---
> [314185.624021] possible reason: unannotated irqs-off.
> [314185.624021] irq event stamp: 488879
> [314185.624021] hardirqs last  enabled at (488879): [<c0102d67>]
> restore_nocheck+0x12/0x15
> [314185.624021] hardirqs last disabled at (488878): [<c0102dca>]
> work_resched+0x19/0x30
> [314185.624021] softirqs last  enabled at (488876): [<c011a1ba>]
> __do_softirq+0xa6/0xac
> [314185.624021] softirqs last disabled at (488865): [<c010476e>]
> do_softirq+0x57/0xa6
>
> I didn't seem to find it with some googling, so here it is.
>
> I was incidentally ltracing that process to try and find out
>  what was gulping down that much CPU (sorry, no idea
>  whether ltrace and the WARNING happened at the same
>  time or which came first) and:

Yeah, this is extremely likely to be the source of the warning.

The warning should be harmless, however.

> Box is my trusty noname K7-800, 512MB RAM; if there's
>  anything else useful I might be able to provide, just ask.

It would be interesting to see where the int3 comes from.  Too bad,
lockdep doesn't provide the register dump. The stacktrace also doesn't
go further than the int3(), I wonder if this int3 came from userspace?
The ltrace readme says "software breakpoints, like gdb", so I guess
this is the case. Yep, seems like it.

This looks relevant:

| commit fb1dac909d94ff807cd833d340c6827c3a957159
| Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
| Date:   Wed Jan 16 09:51:59 2008 +0100
|
|     lockdep: more hardirq annotations for notify_die()

I'm attaching a similarly-looking patch for this case (DO_VM86_ERROR),
though I suspect it might be missing for the other cases
(DO_ERROR/DO_ERROR_INFO) as well.

Reported-by: Alessandro Suardi <alessandro.suardi@gmail.com>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/traps_32.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index bde6f63e15d5..08d752de4eee 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -544,6 +544,7 @@ vm86_trap:
 #define DO_ERROR(trapnr, signr, str, name)				\
 void do_##name(struct pt_regs *regs, long error_code)			\
 {									\
+	trace_hardirqs_fixup();						\
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
 						== NOTIFY_STOP)		\
 		return;							\
-- 
cgit v1.2.2


From f8a45704f5bd5f037c8e4a75172cab1476fc0447 Mon Sep 17 00:00:00 2001
From: Kevin Winchester <kjwinchester@gmail.com>
Date: Thu, 29 May 2008 21:14:35 -0300
Subject: x86: fix pointer type warning in arch/x86/mm/init_64.c:early_memtest

Changed the call to find_e820_area_size to pass u64 instead of unsigned long.

Signed-off-by: Kevin Winchester <kjwinchester@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 998a06ea5f7d..156e6d7b0e32 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	unsigned long t_start, t_size;
+	u64 t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
+			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
 				t_start, t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
-- 
cgit v1.2.2


From 1da2e3d679a8ea2d9e82040359a706da0bd3bef6 Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@aknet.ru>
Date: Thu, 12 Jun 2008 15:21:54 -0700
Subject: provide rtc_cmos platform device

Recently (around 2.6.25) I've noticed that RTC no longer works for me.  It
turned out this is because I use pnpacpi=off kernel option to work around
the parport_pc bugs.  I always did so, but RTC used to work fine in the
past, and now it have regressed.

The patch fixes the problem by creating the platform device for the RTC
when PNP is disabled.  This may also help running the PNP-enabled kernel
on an older PCs.

Signed-off-by: Stas Sergeev <stsp@aknet.ru>
Cc: David Brownell <david-b@pacbell.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Adam Belay <ambx1@neo.rr.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/rtc.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 9615eee9b775..05191bbc68b8 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,6 +4,8 @@
 #include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/mc146818rtc.h>
+#include <linux/platform_device.h>
+#include <linux/pnp.h>
 
 #include <asm/time.h>
 #include <asm/vsyscall.h>
@@ -197,3 +199,35 @@ unsigned long long native_read_tsc(void)
 }
 EXPORT_SYMBOL(native_read_tsc);
 
+
+static struct resource rtc_resources[] = {
+	[0] = {
+		.start	= RTC_PORT(0),
+		.end	= RTC_PORT(1),
+		.flags	= IORESOURCE_IO,
+	},
+	[1] = {
+		.start	= RTC_IRQ,
+		.end	= RTC_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device rtc_device = {
+	.name		= "rtc_cmos",
+	.id		= -1,
+	.resource	= rtc_resources,
+	.num_resources	= ARRAY_SIZE(rtc_resources),
+};
+
+static __init int add_rtc_cmos(void)
+{
+#ifdef CONFIG_PNP
+	if (!pnp_platform_devices)
+		platform_device_register(&rtc_device);
+#else
+	platform_device_register(&rtc_device);
+#endif /* CONFIG_PNP */
+	return 0;
+}
+device_initcall(add_rtc_cmos);
-- 
cgit v1.2.2


From 42a886af728c089df8da1b0017b0e7e6c81b5335 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 17 Jun 2008 17:47:50 -0700
Subject: x86-64: Fix "bytes left to copy" return value for copy_from_user()

Most users by far do not care about the exact return value (they only
really care about whether the copy succeeded in its entirety or not),
but a few special core routines actually care deeply about exactly how
many bytes were copied from user space.

And the unrolled versions of the x86-64 user copy routines would
sometimes report that it had copied more bytes than it actually had.

Very few uses actually have partial copies to begin with, but to make
this bug even harder to trigger, most x86 CPU's use the "rep string"
instructions for normal user copies, and that version didn't have this
issue.

To make it even harder to hit, the one user of this that really cared
about the return value (and used the uncached version of the copy that
doesn't use the "rep string" instructions) was the generic write
routine, which pre-populated its source, once more hiding the problem by
avoiding the exception case that triggers the bug.

In other words, very special thanks to Bron Gondwana who not only
triggered this, but created a test-program to show it, and bisected the
behavior down to commit 08291429cfa6258c4cd95d8833beb40f828b194e ("mm:
fix pagecache write deadlocks") which changed the access pattern just
enough that you can now trigger it with 'writev()' with multiple
iovec's.

That commit itself was not the cause of the bug, it just allowed all the
stars to align just right that you could trigger the problem.

[ Side note: this is just the minimal fix to make the copy routines
  (with __copy_from_user_inatomic_nocache as the particular version that
  was involved in showing this) have the right return values.

  We really should improve on the exceptional case further - to make the
  copy do a byte-accurate copy up to the exact page limit that causes it
  to fail.  As it is, the callers have to do extra work to handle the
  limit case gracefully. ]

Reported-by: Bron Gondwana <brong@fastmail.fm>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

 (which didn't have this problem), and since
most users that do the carethis was very hard to trigger, but
---
 arch/x86/lib/copy_user_64.S         | 25 +++++++++++--------------
 arch/x86/lib/copy_user_nocache_64.S | 25 +++++++++++--------------
 2 files changed, 22 insertions(+), 28 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 70bebd310408..ee1c3f635157 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -217,19 +217,19 @@ ENTRY(copy_user_generic_unrolled)
 	/* table sorted by exception address */
 	.section __ex_table,"a"
 	.align 8
-	.quad .Ls1,.Ls1e
-	.quad .Ls2,.Ls2e
-	.quad .Ls3,.Ls3e
-	.quad .Ls4,.Ls4e
-	.quad .Ld1,.Ls1e
+	.quad .Ls1,.Ls1e	/* Ls1-Ls4 have copied zero bytes */
+	.quad .Ls2,.Ls1e
+	.quad .Ls3,.Ls1e
+	.quad .Ls4,.Ls1e
+	.quad .Ld1,.Ls1e	/* Ld1-Ld4 have copied 0-24 bytes */
 	.quad .Ld2,.Ls2e
 	.quad .Ld3,.Ls3e
 	.quad .Ld4,.Ls4e
-	.quad .Ls5,.Ls5e
-	.quad .Ls6,.Ls6e
-	.quad .Ls7,.Ls7e
-	.quad .Ls8,.Ls8e
-	.quad .Ld5,.Ls5e
+	.quad .Ls5,.Ls5e	/* Ls5-Ls8 have copied 32 bytes */
+	.quad .Ls6,.Ls5e
+	.quad .Ls7,.Ls5e
+	.quad .Ls8,.Ls5e
+	.quad .Ld5,.Ls5e	/* Ld5-Ld8 have copied 32-56 bytes */
 	.quad .Ld6,.Ls6e
 	.quad .Ld7,.Ls7e
 	.quad .Ld8,.Ls8e
@@ -244,11 +244,8 @@ ENTRY(copy_user_generic_unrolled)
 	.quad .Le5,.Le_zero
 	.previous
 
-	/* compute 64-offset for main loop. 8 bytes accuracy with error on the
-	   pessimistic side. this is gross. it would be better to fix the
-	   interface. */
 	/* eax: zero, ebx: 64 */
-.Ls1e: 	addl $8,%eax
+.Ls1e: 	addl $8,%eax		/* eax is bytes left uncopied within the loop (Ls1e: 64 .. Ls8e: 8) */
 .Ls2e: 	addl $8,%eax
 .Ls3e: 	addl $8,%eax
 .Ls4e: 	addl $8,%eax
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index 5196762b3b0e..9d3d1ab83763 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -145,19 +145,19 @@ ENTRY(__copy_user_nocache)
 	/* table sorted by exception address */
 	.section __ex_table,"a"
 	.align 8
-	.quad .Ls1,.Ls1e
-	.quad .Ls2,.Ls2e
-	.quad .Ls3,.Ls3e
-	.quad .Ls4,.Ls4e
-	.quad .Ld1,.Ls1e
+	.quad .Ls1,.Ls1e	/* .Ls[1-4] - 0 bytes copied */
+	.quad .Ls2,.Ls1e
+	.quad .Ls3,.Ls1e
+	.quad .Ls4,.Ls1e
+	.quad .Ld1,.Ls1e	/* .Ld[1-4] - 0..24 bytes coped */
 	.quad .Ld2,.Ls2e
 	.quad .Ld3,.Ls3e
 	.quad .Ld4,.Ls4e
-	.quad .Ls5,.Ls5e
-	.quad .Ls6,.Ls6e
-	.quad .Ls7,.Ls7e
-	.quad .Ls8,.Ls8e
-	.quad .Ld5,.Ls5e
+	.quad .Ls5,.Ls5e	/* .Ls[5-8] - 32 bytes copied */
+	.quad .Ls6,.Ls5e
+	.quad .Ls7,.Ls5e
+	.quad .Ls8,.Ls5e
+	.quad .Ld5,.Ls5e	/* .Ld[5-8] - 32..56 bytes copied */
 	.quad .Ld6,.Ls6e
 	.quad .Ld7,.Ls7e
 	.quad .Ld8,.Ls8e
@@ -172,11 +172,8 @@ ENTRY(__copy_user_nocache)
 	.quad .Le5,.Le_zero
 	.previous
 
-	/* compute 64-offset for main loop. 8 bytes accuracy with error on the
-	   pessimistic side. this is gross. it would be better to fix the
-	   interface. */
 	/* eax: zero, ebx: 64 */
-.Ls1e: 	addl $8,%eax
+.Ls1e: 	addl $8,%eax	/* eax: bytes left uncopied: Ls1e: 64 .. Ls8e: 8 */
 .Ls2e: 	addl $8,%eax
 .Ls3e: 	addl $8,%eax
 .Ls4e: 	addl $8,%eax
-- 
cgit v1.2.2


From b4b3bd96f26586e53ab5482f1869221dd1b5ac36 Mon Sep 17 00:00:00 2001
From: Daniel Rahn <Daniel.Rahn@novell.com>
Date: Fri, 6 Jun 2008 09:42:36 +0200
Subject: x86: correctly report NR_BANKS in mce_64.c

attached is a no-brainer that makes kernel correctly report
NR_BANKS for MCE. We are right now limited to NR_BANKS==6, but the
error message will use the available number of banks instead of the
defined maximum.

For a Nehalem based system it will print:

"MCE: warning: using only 9 banks"

while the correct message would be

"MCE: warning: using only 6 banks"

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mcheck/mce_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index f1f3f5e163b7..8c8299ce7ad4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -445,9 +445,9 @@ static void mce_init(void *dummy)
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	banks = cap & 0xff;
 	if (banks > MCE_EXTENDED_BANK) {
+		banks = MCE_EXTENDED_BANK;
 		printk(KERN_INFO "MCE: warning: using only %d banks\n",
 		       MCE_EXTENDED_BANK);
-		banks = MCE_EXTENDED_BANK;
 	}
 	/* Use accurate RIP reporting if available. */
 	if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
-- 
cgit v1.2.2


From 6cf514fce18589ea1e0521c5f2d7c2bb280fefc7 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hugh@veritas.com>
Date: Mon, 16 Jun 2008 18:42:43 +0100
Subject: x86: PAT: make pat_x_mtrr_type() more readable

Clean up over-complications in pat_x_mtrr_type().
And if reserve_memtype() ignores stray req_type bits when
pat_enabled, it's better to mask them off when not also.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 47 ++++++++++++-----------------------------------
 1 file changed, 12 insertions(+), 35 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 7c21572bbdda..ac3a2b11eb38 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -159,47 +159,31 @@ static DEFINE_SPINLOCK(memtype_lock); 	/* protects memtype list */
  * The intersection is based on "Effective Memory Type" tables in IA-32
  * SDM vol 3a
  */
-static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
-				unsigned long *ret_prot)
+static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 {
-	unsigned long pat_type;
 	u8 mtrr_type;
 
-	pat_type = prot & _PAGE_CACHE_MASK;
-	prot &= (~_PAGE_CACHE_MASK);
-
 	/*
 	 * We return the PAT request directly for types where PAT takes
 	 * precedence with respect to MTRR and for UC_MINUS.
 	 * Consistency checks with other PAT requests is done later
 	 * while going through memtype list.
 	 */
-	if (pat_type == _PAGE_CACHE_WC) {
-		*ret_prot = prot | _PAGE_CACHE_WC;
-		return 0;
-	} else if (pat_type == _PAGE_CACHE_UC_MINUS) {
-		*ret_prot = prot | _PAGE_CACHE_UC_MINUS;
-		return 0;
-	} else if (pat_type == _PAGE_CACHE_UC) {
-		*ret_prot = prot | _PAGE_CACHE_UC;
-		return 0;
-	}
+	if (req_type == _PAGE_CACHE_WC ||
+	    req_type == _PAGE_CACHE_UC_MINUS ||
+	    req_type == _PAGE_CACHE_UC)
+		return req_type;
 
 	/*
 	 * Look for MTRR hint to get the effective type in case where PAT
 	 * request is for WB.
 	 */
 	mtrr_type = mtrr_type_lookup(start, end);
-
-	if (mtrr_type == MTRR_TYPE_UNCACHABLE) {
-		*ret_prot = prot | _PAGE_CACHE_UC;
-	} else if (mtrr_type == MTRR_TYPE_WRCOMB) {
-		*ret_prot = prot | _PAGE_CACHE_WC;
-	} else {
-		*ret_prot = prot | _PAGE_CACHE_WB;
-	}
-
-	return 0;
+	if (mtrr_type == MTRR_TYPE_UNCACHABLE)
+		return _PAGE_CACHE_UC;
+	if (mtrr_type == MTRR_TYPE_WRCOMB)
+		return _PAGE_CACHE_WC;
+	return _PAGE_CACHE_WB;
 }
 
 /*
@@ -232,7 +216,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			if (req_type == -1) {
 				*ret_type = _PAGE_CACHE_WB;
 			} else {
-				*ret_type = req_type;
+				*ret_type = req_type & _PAGE_CACHE_MASK;
 			}
 		}
 		return 0;
@@ -264,14 +248,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		}
 	} else {
 		req_type &= _PAGE_CACHE_MASK;
-		err = pat_x_mtrr_type(start, end, req_type, &actual_type);
-	}
-
-	if (err) {
-		if (ret_type)
-			*ret_type = actual_type;
-
-		return -EINVAL;
+		actual_type = pat_x_mtrr_type(start, end, req_type);
 	}
 
 	new_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
-- 
cgit v1.2.2


From fe94ae995d33a4df35b6b9cd0504e87d7e37c8de Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 14 Jun 2008 14:06:19 +0200
Subject: x86: coding style fixes to arch/x86/kernel/cpu/mcheck/p4.c

Before:
total: 16 errors, 34 warnings, 257 lines checked

After:
total: 0 errors, 2 warnings, 257 lines checked

No changes in the compiled code:

paolo@paolo-desktop:~/linux.trees.git$ size /tmp/p4*
   text    data     bss     dec     hex filename
   2644       4       4    2652     a5c /tmp/p4.o.after
   2644       4       4    2652     a5c /tmp/p4.o.before

paolo@paolo-desktop:~/linux.trees.git$ md5sum /tmp/p4*
13f1b21c4246b31a28aaff38184586ca  /tmp/p4.o.after
13f1b21c4246b31a28aaff38184586ca  /tmp/p4.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mcheck/p4.c | 90 ++++++++++++++++++++---------------------
 1 file changed, 45 insertions(+), 45 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index cb03345554a5..eef001ad3bde 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 
-#include <asm/processor.h> 
+#include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -32,12 +32,12 @@ struct intel_mce_extended_msrs {
 	/* u32 *reserved[]; */
 };
 
-static int mce_num_extended_msrs = 0;
+static int mce_num_extended_msrs;
 
 
 #ifdef CONFIG_X86_MCE_P4THERMAL
 static void unexpected_thermal_interrupt(struct pt_regs *regs)
-{	
+{
 	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
 			smp_processor_id());
 	add_taint(TAINT_MACHINE_CHECK);
@@ -83,7 +83,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 	 * be some SMM goo which handles it, so we can't even put a handler
 	 * since it might be delivered via SMI already -zwanem.
 	 */
-	rdmsr (MSR_IA32_MISC_ENABLE, l, h);
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 	h = apic_read(APIC_LVTTHMR);
 	if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n",
@@ -91,7 +91,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 		return; /* -EBUSY */
 	}
 
-	/* check whether a vector already exists, temporarily masked? */	
+	/* check whether a vector already exists, temporarily masked? */
 	if (h & APIC_VECTOR_MASK) {
 		printk(KERN_DEBUG "CPU%d: Thermal LVT vector (%#x) already "
 				"installed\n",
@@ -104,18 +104,18 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
 	h |= (APIC_DM_FIXED | APIC_LVT_MASKED);	/* we'll mask till we're ready */
 	apic_write_around(APIC_LVTTHMR, h);
 
-	rdmsr (MSR_IA32_THERM_INTERRUPT, l, h);
-	wrmsr (MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
+	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
+	wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
 
 	/* ok we're good to go... */
 	vendor_thermal_interrupt = intel_thermal_interrupt;
-	
-	rdmsr (MSR_IA32_MISC_ENABLE, l, h);
-	wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h);
 
-	l = apic_read (APIC_LVTTHMR);
-	apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
-	printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+
+	l = apic_read(APIC_LVTTHMR);
+	apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+	printk(KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
 
 	/* enable thermal throttle processing */
 	atomic_set(&therm_throt_en, 1);
@@ -129,28 +129,28 @@ static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 {
 	u32 h;
 
-	rdmsr (MSR_IA32_MCG_EAX, r->eax, h);
-	rdmsr (MSR_IA32_MCG_EBX, r->ebx, h);
-	rdmsr (MSR_IA32_MCG_ECX, r->ecx, h);
-	rdmsr (MSR_IA32_MCG_EDX, r->edx, h);
-	rdmsr (MSR_IA32_MCG_ESI, r->esi, h);
-	rdmsr (MSR_IA32_MCG_EDI, r->edi, h);
-	rdmsr (MSR_IA32_MCG_EBP, r->ebp, h);
-	rdmsr (MSR_IA32_MCG_ESP, r->esp, h);
-	rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h);
-	rdmsr (MSR_IA32_MCG_EIP, r->eip, h);
+	rdmsr(MSR_IA32_MCG_EAX, r->eax, h);
+	rdmsr(MSR_IA32_MCG_EBX, r->ebx, h);
+	rdmsr(MSR_IA32_MCG_ECX, r->ecx, h);
+	rdmsr(MSR_IA32_MCG_EDX, r->edx, h);
+	rdmsr(MSR_IA32_MCG_ESI, r->esi, h);
+	rdmsr(MSR_IA32_MCG_EDI, r->edi, h);
+	rdmsr(MSR_IA32_MCG_EBP, r->ebp, h);
+	rdmsr(MSR_IA32_MCG_ESP, r->esp, h);
+	rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h);
+	rdmsr(MSR_IA32_MCG_EIP, r->eip, h);
 }
 
-static void intel_machine_check(struct pt_regs * regs, long error_code)
+static void intel_machine_check(struct pt_regs *regs, long error_code)
 {
-	int recover=1;
+	int recover = 1;
 	u32 alow, ahigh, high, low;
 	u32 mcgstl, mcgsth;
 	int i;
 
-	rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if (mcgstl & (1<<0))	/* Recoverable ? */
-		recover=0;
+		recover = 0;
 
 	printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
 		smp_processor_id(), mcgsth, mcgstl);
@@ -191,20 +191,20 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 	}
 
 	if (recover & 2)
-		panic ("CPU context corrupt");
+		panic("CPU context corrupt");
 	if (recover & 1)
-		panic ("Unable to continue");
+		panic("Unable to continue");
 
 	printk(KERN_EMERG "Attempting to continue.\n");
-	/* 
-	 * Do not clear the MSR_IA32_MCi_STATUS if the error is not 
+	/*
+	 * Do not clear the MSR_IA32_MCi_STATUS if the error is not
 	 * recoverable/continuable.This will allow BIOS to look at the MSRs
 	 * for errors if the OS could not log the error.
 	 */
-	for (i=0; i<nr_mce_banks; i++) {
+	for (i = 0; i < nr_mce_banks; i++) {
 		u32 msr;
 		msr = MSR_IA32_MC0_STATUS+i*4;
-		rdmsr (msr, low, high);
+		rdmsr(msr, low, high);
 		if (high&(1<<31)) {
 			/* Clear it */
 			wrmsr(msr, 0UL, 0UL);
@@ -214,7 +214,7 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 		}
 	}
 	mcgstl &= ~(1<<2);
-	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+	wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 }
 
 
@@ -222,30 +222,30 @@ void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int i;
-	
+
 	machine_check_vector = intel_machine_check;
 	wmb();
 
-	printk (KERN_INFO "Intel machine check architecture supported.\n");
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	printk(KERN_INFO "Intel machine check architecture supported.\n");
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<8))	/* Control register present ? */
-		wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 	nr_mce_banks = l & 0xff;
 
-	for (i=0; i<nr_mce_banks; i++) {
-		wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-		wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+	for (i = 0; i < nr_mce_banks; i++) {
+		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
 	}
 
-	set_in_cr4 (X86_CR4_MCE);
-	printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
 		smp_processor_id());
 
 	/* Check for P4/Xeon extended MCE MSRs */
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<9))	{/* MCG_EXT_P */
 		mce_num_extended_msrs = (l >> 16) & 0xff;
-		printk (KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
+		printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
 				" available\n",
 			smp_processor_id(), mce_num_extended_msrs);
 
-- 
cgit v1.2.2


From 5175676a2d012ca5e5ad5eaedbfc1da5d5660d2a Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 14 Jun 2008 14:37:14 +0200
Subject: x86: coding style fixes to arch/x86/kernel/cpu/mcheck/k7.c

Before:
total: 6 errors, 13 warnings, 105 lines checked

After:
total: 0 errors, 0 warnings, 105 lines checked

paolo@paolo-desktop:~/linux.trees.git$ size /tmp/k7*
   text    data     bss     dec     hex filename
   1135       0       0    1135     46f /tmp/k7.o.after
   1135       0       0    1135     46f /tmp/k7.o.before

paolo@paolo-desktop:~/linux.trees.git$ md5sum /tmp/k7*
87b14954045aa37dbaee6fb7e022ed9a  /tmp/k7.o.after
87b14954045aa37dbaee6fb7e022ed9a  /tmp/k7.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mcheck/k7.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mcheck/k7.c b/arch/x86/kernel/cpu/mcheck/k7.c
index e633c9c2b764..f390c9f66351 100644
--- a/arch/x86/kernel/cpu/mcheck/k7.c
+++ b/arch/x86/kernel/cpu/mcheck/k7.c
@@ -9,23 +9,23 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 
-#include <asm/processor.h> 
+#include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/msr.h>
 
 #include "mce.h"
 
 /* Machine Check Handler For AMD Athlon/Duron */
-static void k7_machine_check(struct pt_regs * regs, long error_code)
+static void k7_machine_check(struct pt_regs *regs, long error_code)
 {
-	int recover=1;
+	int recover = 1;
 	u32 alow, ahigh, high, low;
 	u32 mcgstl, mcgsth;
 	int i;
 
-	rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if (mcgstl & (1<<0))	/* Recoverable ? */
-		recover=0;
+		recover = 0;
 
 	printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
 		smp_processor_id(), mcgsth, mcgstl);
@@ -60,12 +60,12 @@ static void k7_machine_check(struct pt_regs * regs, long error_code)
 	}
 
 	if (recover&2)
-		panic ("CPU context corrupt");
+		panic("CPU context corrupt");
 	if (recover&1)
-		panic ("Unable to continue");
-	printk (KERN_EMERG "Attempting to continue.\n");
+		panic("Unable to continue");
+	printk(KERN_EMERG "Attempting to continue.\n");
 	mcgstl &= ~(1<<2);
-	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+	wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 }
 
 
@@ -81,25 +81,25 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
 	machine_check_vector = k7_machine_check;
 	wmb();
 
-	printk (KERN_INFO "Intel machine check architecture supported.\n");
-	rdmsr (MSR_IA32_MCG_CAP, l, h);
+	printk(KERN_INFO "Intel machine check architecture supported.\n");
+	rdmsr(MSR_IA32_MCG_CAP, l, h);
 	if (l & (1<<8))	/* Control register present ? */
-		wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 	nr_mce_banks = l & 0xff;
 
 	/* Clear status for MC index 0 separately, we don't touch CTL,
 	 * as some K7 Athlons cause spurious MCEs when its enabled. */
 	if (boot_cpu_data.x86 == 6) {
-		wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0);
+		wrmsr(MSR_IA32_MC0_STATUS, 0x0, 0x0);
 		i = 1;
 	} else
 		i = 0;
-	for (; i<nr_mce_banks; i++) {
-		wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-		wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+	for (; i < nr_mce_banks; i++) {
+		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
 	}
 
-	set_in_cr4 (X86_CR4_MCE);
-	printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
 		smp_processor_id());
 }
-- 
cgit v1.2.2


From f016e15c11ba8945ff8e1945445648722d6fadfb Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 14 Jun 2008 20:44:52 +0200
Subject: x86: coding style fixes to arch/x86/math-emu/reg_constant

Before:
total: 6 errors, 1 warnings, 117 lines checked

After:
total: 0 errors, 1 warnings, 117 lines checked

paolo@paolo-desktop:~/linux.trees.git$ md5sum /tmp/reg_constant.o.*
780388a3056d58fb759efaf190d5d3d1  /tmp/reg_constant.o.after
780388a3056d58fb759efaf190d5d3d1  /tmp/reg_constant.o.before

paolo@paolo-desktop:~/linux.trees.git$ size /tmp/reg_constant.o.*
   text    data     bss     dec     hex filename
    457       0       0     457     1c9 /tmp/reg_constant.o.after
    457       0       0     457     1c9 /tmp/reg_constant.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/math-emu/reg_constant.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c
index 04869e64b18e..00548354912f 100644
--- a/arch/x86/math-emu/reg_constant.c
+++ b/arch/x86/math-emu/reg_constant.c
@@ -16,8 +16,8 @@
 #include "reg_constant.h"
 #include "control_w.h"
 
-#define MAKE_REG(s,e,l,h) { l, h, \
-                            ((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) }
+#define MAKE_REG(s, e, l, h) { l, h, \
+		((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) }
 
 FPU_REG const CONST_1 = MAKE_REG(POS, 0, 0x00000000, 0x80000000);
 #if 0
@@ -40,7 +40,7 @@ FPU_REG const CONST_PI2extra = MAKE_REG(NEG, -66,
 FPU_REG const CONST_Z = MAKE_REG(POS, EXP_UNDER, 0x0, 0x0);
 
 /* Only the sign and significand (and tag) are used in internal NaNs */
-/* The 80486 never generates one of these 
+/* The 80486 never generates one of these
 FPU_REG const CONST_SNAN = MAKE_REG(POS, EXP_OVER, 0x00000001, 0x80000000);
  */
 /* This is the real indefinite QNaN */
@@ -49,7 +49,7 @@ FPU_REG const CONST_QNaN = MAKE_REG(NEG, EXP_OVER, 0x00000000, 0xC0000000);
 /* Only the sign (and tag) is used in internal infinities */
 FPU_REG const CONST_INF = MAKE_REG(POS, EXP_OVER, 0x00000000, 0x80000000);
 
-static void fld_const(FPU_REG const *c, int adj, u_char tag)
+static void fld_const(FPU_REG const * c, int adj, u_char tag)
 {
 	FPU_REG *st_new_ptr;
 
-- 
cgit v1.2.2


From 219835f10eaef19d2b976076f2bc4ad806856c55 Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sat, 14 Jun 2008 21:11:39 +0200
Subject: x86: coding style fixes to x86/kernel/cpu/cpufreq/cpufreq-nforce2.c

Before:
total: 22 errors, 8 warnings, 440 lines checked

After:
total: 0 errors, 8 warnings, 442 lines checked

paolo@paolo-desktop:~/linux.trees.git$ md5sum /tmp/cpufreq-nforce2.o.*
3d4330a5d188fe904446e5948a618b48  /tmp/cpufreq-nforce2.o.after
1477e6b0dcd6f59b1fb6b4490042eca6  /tmp/cpufreq-nforce2.o.before
^^^ I guess this is because I fixed a few "do not initialise statics to 0 or NULL"

paolo@paolo-desktop:~/linux.trees.git$ size /tmp/cpufreq-nforce2.o.*
   text    data     bss     dec     hex filename
   1923      72      16    2011     7db /tmp/cpufreq-nforce2.o.after
   1923      72      16    2011     7db /tmp/cpufreq-nforce2.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c | 44 ++++++++++++++-------------
 1 file changed, 23 insertions(+), 21 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
index f03e9153618e..965ea52767ac 100644
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
@@ -26,9 +26,10 @@
 #define NFORCE2_SAFE_DISTANCE 50
 
 /* Delay in ms between FSB changes */
-//#define NFORCE2_DELAY 10
+/* #define NFORCE2_DELAY 10 */
 
-/* nforce2_chipset:
+/*
+ * nforce2_chipset:
  * FSB is changed using the chipset
  */
 static struct pci_dev *nforce2_chipset_dev;
@@ -36,13 +37,13 @@ static struct pci_dev *nforce2_chipset_dev;
 /* fid:
  * multiplier * 10
  */
-static int fid = 0;
+static int fid;
 
 /* min_fsb, max_fsb:
  * minimum and maximum FSB (= FSB at boot time)
  */
-static int min_fsb = 0;
-static int max_fsb = 0;
+static int min_fsb;
+static int max_fsb;
 
 MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
 MODULE_DESCRIPTION("nForce2 FSB changing cpufreq driver");
@@ -53,7 +54,7 @@ module_param(min_fsb, int, 0444);
 
 MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)");
 MODULE_PARM_DESC(min_fsb,
-                 "Minimum FSB to use, if not defined: current FSB - 50");
+		"Minimum FSB to use, if not defined: current FSB - 50");
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg)
 
@@ -139,7 +140,7 @@ static unsigned int nforce2_fsb_read(int bootfsb)
 
 	/* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */
 	nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA,
-						0x01EF,PCI_ANY_ID,PCI_ANY_ID,NULL);
+						0x01EF, PCI_ANY_ID, PCI_ANY_ID, NULL);
 	if (!nforce2_sub5)
 		return 0;
 
@@ -147,13 +148,13 @@ static unsigned int nforce2_fsb_read(int bootfsb)
 	fsb /= 1000000;
 
 	/* Check if PLL register is already set */
-	pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+	pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
 
-	if(bootfsb || !temp)
+	if (bootfsb || !temp)
 		return fsb;
-		
+
 	/* Use PLL register FSB value */
-	pci_read_config_dword(nforce2_chipset_dev,NFORCE2_PLLREG, &temp);
+	pci_read_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, &temp);
 	fsb = nforce2_calc_fsb(temp);
 
 	return fsb;
@@ -184,7 +185,7 @@ static int nforce2_set_fsb(unsigned int fsb)
 	}
 
 	/* First write? Then set actual value */
-	pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+	pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
 	if (!temp) {
 		pll = nforce2_calc_pll(tfsb);
 
@@ -210,7 +211,8 @@ static int nforce2_set_fsb(unsigned int fsb)
 			tfsb--;
 
 		/* Calculate the PLL reg. value */
-		if ((pll = nforce2_calc_pll(tfsb)) == -1)
+		pll = nforce2_calc_pll(tfsb);
+		if (pll == -1)
 			return -EINVAL;
 
 		nforce2_write_pll(pll);
@@ -249,7 +251,7 @@ static unsigned int nforce2_get(unsigned int cpu)
 static int nforce2_target(struct cpufreq_policy *policy,
 			  unsigned int target_freq, unsigned int relation)
 {
-//        unsigned long         flags;
+/*        unsigned long         flags; */
 	struct cpufreq_freqs freqs;
 	unsigned int target_fsb;
 
@@ -271,17 +273,17 @@ static int nforce2_target(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
 	/* Disable IRQs */
-	//local_irq_save(flags);
+	/* local_irq_save(flags); */
 
 	if (nforce2_set_fsb(target_fsb) < 0)
 		printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n",
-                       target_fsb);
+			target_fsb);
 	else
 		dprintk("Changed FSB successfully to %d\n",
-                       target_fsb);
+			target_fsb);
 
 	/* Enable IRQs */
-	//local_irq_restore(flags);
+	/* local_irq_restore(flags); */
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
@@ -302,8 +304,8 @@ static int nforce2_verify(struct cpufreq_policy *policy)
 		policy->max = (fsb_pol_max + 1) * fid * 100;
 
 	cpufreq_verify_within_limits(policy,
-                                     policy->cpuinfo.min_freq,
-                                     policy->cpuinfo.max_freq);
+				     policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
 	return 0;
 }
 
@@ -347,7 +349,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 	/* Set maximum FSB to FSB at boot time */
 	max_fsb = nforce2_fsb_read(1);
 
-	if(!max_fsb)
+	if (!max_fsb)
 		return -EIO;
 
 	if (!min_fsb)
-- 
cgit v1.2.2


From 75118a82e21cafb4a82b53bb85d1c7689787e046 Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Fri, 13 Jun 2008 15:47:12 -0700
Subject: x86: fix NULL pointer deref in __switch_to

Patrick McHardy reported a crash:

> > I get this oops once a day, its apparently triggered by something
> > run by cron, but the process is a different one each time.
> >
> > Kernel is -git from yesterday shortly before the -rc6 release
> > (last commit is the usb-2.6 merge, the x86 patches are missing),
> > .config is attached.
> >
> > I'll retry with current -git, but the patches that have gone in
> > since I last updated don't look related.
> >
> > [62060.043009] BUG: unable to handle kernel NULL pointer dereference at
> > 000001ff
> > [62060.043009] IP: [<c0102a9b>] __switch_to+0x2f/0x118
> > [62060.043009] *pde = 00000000
> > [62060.043009] Oops: 0002 [#1] PREEMPT

Vegard Nossum analyzed it:

> This decodes to
>
>    0:   0f ae 00                fxsave (%eax)
>
> so it's related to the floating-point context. This is the exact
> location of the crash:
>
> $ addr2line -e arch/x86/kernel/process_32.o -i ab0
> include/asm/i387.h:232
> include/asm/i387.h:262
> arch/x86/kernel/process_32.c:595
>
> ...so it looks like prev_task->thread.xstate->fxsave has become NULL.
> Or maybe it never had any other value.

Somehow (as described below) TS_USEDFPU is set but the fpu is not
allocated or freed.

Another possible FPU pre-emption issue with the sleazy FPU optimization
which was benign before but not so anymore, with the dynamic FPU allocation
patch.

New task is getting exec'd and it is prempted at the below point.

flush_thread() {
	...
	/*
	* Forget coprocessor state..
	*/
	clear_fpu(tsk);
		<----- Preemption point
	clear_used_math();
	...
}

Now when it context switches in again, as the used_math() is still set
and fpu_counter can be > 5, we will do a math_state_restore() which sets
the task's TS_USEDFPU. After it continues from the above preemption point
it does clear_used_math() and much later free_thread_xstate().

Now, at the next context switch, it is quite possible that xstate is
null, used_math() is not set and TS_USEDFPU is still set. This will
trigger unlazy_fpu() causing kernel oops.

Fix this  by clearing tsk's fpu_counter before clearing task's fpu.

Reported-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process_32.c | 1 +
 arch/x86/kernel/process_64.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 6d5483356e74..e2db9ac5c61c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -333,6 +333,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ac54ff56df80..c6eb5c91e5f6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -294,6 +294,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }
-- 
cgit v1.2.2


From df17b1d990fc214f033c5588e58216ec941591e0 Mon Sep 17 00:00:00 2001
From: Mikael Pettersson <mikpe@it.uu.se>
Date: Sun, 15 Jun 2008 02:19:56 +0200
Subject: x86, 32-bit: fix boot failure on TSC-less processors

Booting 2.6.26-rc6 on my 486 DX/4 fails with a "BUG: Int 6"
(invalid opcode) and a kernel halt immediately after the
kernel has been uncompressed. The BUG shows EIP pointing
to an rdtsc instruction in native_read_tsc(), invoked from
native_sched_clock().

(This error occurs so early that not even the serial console
can capture it.)

A bisection showed that this bug first occurs in 2.6.26-rc3-git7,
via commit 9ccc906c97e34fd91dc6aaf5b69b52d824386910:

>x86: distangle user disabled TSC from unstable
>
>tsc_enabled is set to 0 from the command line switch "notsc" and from
>the mark_tsc_unstable code. Seperate those functionalities and replace
>tsc_enable with tsc_disable. This makes also the native_sched_clock()
>decision when to use TSC understandable.
>
>Preparatory patch to solve the sched_clock() issue on 32 bit.
>
>Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

The core reason for this bug is that native_sched_clock() gets
called before tsc_init().

Before the commit above, tsc_32.c used a "tsc_enabled" variable
which defaulted to 0 == disabled, and which only got enabled late
in tsc_init(). Thus early calls to native_sched_clock() would skip
the TSC and use jiffies instead.

After the commit above, tsc_32.c uses a "tsc_disabled" variable
which defaults to 0, meaning that the TSC is Ok to use. Early calls
to native_sched_clock() now erroneously try to use the TSC on
!cpu_has_tsc processors, leading to invalid opcode exceptions.

My proposed fix is to initialise tsc_disabled to a "soft disabled"
state distinct from the hard disabled state set up by the "notsc"
kernel option. This fixes the native_sched_clock() problem. It also
allows tsc_init() to be simplified: instead of setting tsc_disabled = 1
on every error return, we just set tsc_disabled = 0 once when all
checks have succeeded.

I've verified that this lets my 486 boot again. I've also verified
that a Core2 machine still uses the TSC as clocksource after the patch.

Signed-off-by: Mikael Pettersson <mikpe@it.uu.se>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/tsc_32.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 068759db63dd..65b70637ad97 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -14,7 +14,10 @@
 
 #include "mach_timer.h"
 
-static int tsc_disabled;
+/* native_sched_clock() is called before tsc_init(), so
+   we must start with the TSC soft disabled to prevent
+   erroneous rdtsc usage on !cpu_has_tsc processors */
+static int tsc_disabled = -1;
 
 /*
  * On some systems the TSC frequency does not
@@ -402,25 +405,20 @@ void __init tsc_init(void)
 {
 	int cpu;
 
-	if (!cpu_has_tsc || tsc_disabled) {
-		/* Disable the TSC in case of !cpu_has_tsc */
-		tsc_disabled = 1;
+	if (!cpu_has_tsc || tsc_disabled > 0)
 		return;
-	}
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
 
 	if (!cpu_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
-		/*
-		 * We need to disable the TSC completely in this case
-		 * to prevent sched_clock() from using it.
-		 */
-		tsc_disabled = 1;
 		return;
 	}
 
+	/* now allow native_sched_clock() to use rdtsc */
+	tsc_disabled = 0;
+
 	printk("Detected %lu.%03lu MHz processor.\n",
 				(unsigned long)cpu_khz / 1000,
 				(unsigned long)cpu_khz % 1000);
-- 
cgit v1.2.2


From d3942cff620bea073fc4e3c8ed878eb1e84615ce Mon Sep 17 00:00:00 2001
From: Bernhard Walle <bwalle@suse.de>
Date: Sun, 8 Jun 2008 16:16:07 +0200
Subject: x86: use BOOTMEM_EXCLUSIVE on 32-bit

This patch uses the BOOTMEM_EXCLUSIVE for crashkernel reservation also for
i386 and prints a error message on failure.

The patch is still for 2.6.26 since it is only bug fixing. The unification
of reserve_crashkernel() between i386 and x86_64 should be done for 2.6.27.

Signed-off-by: Bernhard Walle <bwalle@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
---
 arch/x86/kernel/setup_32.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 2c5f8b213e86..5a2f8e063887 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -532,10 +532,16 @@ static void __init reserve_crashkernel(void)
 					(unsigned long)(crash_size >> 20),
 					(unsigned long)(crash_base >> 20),
 					(unsigned long)(total_mem >> 20));
+
+			if (reserve_bootmem(crash_base, crash_size,
+					BOOTMEM_EXCLUSIVE) < 0) {
+				printk(KERN_INFO "crashkernel reservation "
+					"failed - memory is in use\n");
+				return;
+			}
+
 			crashk_res.start = crash_base;
 			crashk_res.end   = crash_base + crash_size - 1;
-			reserve_bootmem(crash_base, crash_size,
-					BOOTMEM_DEFAULT);
 		} else
 			printk(KERN_INFO "crashkernel reservation failed - "
 					"you have to specify a base address\n");
-- 
cgit v1.2.2


From dd0c7c4903c29da9aa3bf33deecf064d190a0d81 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Wed, 18 Jun 2008 15:38:57 +0200
Subject: x86: shrink pat_x_mtrr_type to its essentials

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ac3a2b11eb38..227df3ca9bfd 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -161,29 +161,21 @@ static DEFINE_SPINLOCK(memtype_lock); 	/* protects memtype list */
  */
 static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 {
-	u8 mtrr_type;
-
-	/*
-	 * We return the PAT request directly for types where PAT takes
-	 * precedence with respect to MTRR and for UC_MINUS.
-	 * Consistency checks with other PAT requests is done later
-	 * while going through memtype list.
-	 */
-	if (req_type == _PAGE_CACHE_WC ||
-	    req_type == _PAGE_CACHE_UC_MINUS ||
-	    req_type == _PAGE_CACHE_UC)
-		return req_type;
-
 	/*
 	 * Look for MTRR hint to get the effective type in case where PAT
 	 * request is for WB.
 	 */
-	mtrr_type = mtrr_type_lookup(start, end);
-	if (mtrr_type == MTRR_TYPE_UNCACHABLE)
-		return _PAGE_CACHE_UC;
-	if (mtrr_type == MTRR_TYPE_WRCOMB)
-		return _PAGE_CACHE_WC;
-	return _PAGE_CACHE_WB;
+	if (req_type == _PAGE_CACHE_WB) {
+		u8 mtrr_type;
+
+		mtrr_type = mtrr_type_lookup(start, end);
+		if (mtrr_type == MTRR_TYPE_UNCACHABLE)
+			return _PAGE_CACHE_UC;
+		if (mtrr_type == MTRR_TYPE_WRCOMB)
+			return _PAGE_CACHE_WC;
+	}
+
+	return req_type;
 }
 
 /*
-- 
cgit v1.2.2


From ffe6e1da86d21d7855495b5a772c93f050258f6e Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jordan.crouse@amd.com>
Date: Wed, 18 Jun 2008 11:34:38 -0600
Subject: x86, geode: add a VSA2 ID for General Software

General Software writes their own VSA2 module for their version
of the Geode BIOS, which returns a different ID then the standard
VSA2.  This was causing the framebuffer driver to break for most
GSW boards.

Signed-off-by: Jordan Crouse <jordan.crouse@amd.com>
Cc: tglx@linutronix.de
Cc: linux-geode@lists.infradead.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/geode_32.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c
index e8edd63ab000..9b08e852fd1a 100644
--- a/arch/x86/kernel/geode_32.c
+++ b/arch/x86/kernel/geode_32.c
@@ -166,6 +166,8 @@ int geode_has_vsa2(void)
 	static int has_vsa2 = -1;
 
 	if (has_vsa2 == -1) {
+		u16 val;
+
 		/*
 		 * The VSA has virtual registers that we can query for a
 		 * signature.
@@ -173,7 +175,8 @@ int geode_has_vsa2(void)
 		outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
 		outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX);
 
-		has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG);
+		val = inw(VSA_VRC_DATA);
+		has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG);
 	}
 
 	return has_vsa2;
-- 
cgit v1.2.2


From 5f0120b5786f5dbe097a946a2eb5d745ebc2b7ed Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Wed, 18 Jun 2008 12:42:11 +0100
Subject: x86-64: remove unnecessary ptregs call stubs

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Cc: "Andi Kleen" <andi@firstfloor.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/ia32/ia32entry.S  | 6 ++----
 arch/x86/kernel/entry_64.S | 1 -
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index b5e329da166c..3aefbce2de48 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -370,13 +370,11 @@ quiet_ni_syscall:
 	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
 	PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
 	PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
-	PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx
 	PTREGSCALL stub32_execve, sys32_execve, %rcx
 	PTREGSCALL stub32_fork, sys_fork, %rdi
 	PTREGSCALL stub32_clone, sys32_clone, %rdx
 	PTREGSCALL stub32_vfork, sys_vfork, %rdi
 	PTREGSCALL stub32_iopl, sys_iopl, %rsi
-	PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx
 
 ENTRY(ia32_ptregs_common)
 	popq %r11
@@ -476,7 +474,7 @@ ia32_sys_call_table:
 	.quad sys_ssetmask
 	.quad sys_setreuid16	/* 70 */
 	.quad sys_setregid16
-	.quad stub32_sigsuspend
+	.quad sys32_sigsuspend
 	.quad compat_sys_sigpending
 	.quad sys_sethostname
 	.quad compat_sys_setrlimit	/* 75 */
@@ -583,7 +581,7 @@ ia32_sys_call_table:
 	.quad sys32_rt_sigpending
 	.quad compat_sys_rt_sigtimedwait
 	.quad sys32_rt_sigqueueinfo
-	.quad stub32_rt_sigsuspend
+	.quad sys_rt_sigsuspend
 	.quad sys32_pread		/* 180 */
 	.quad sys32_pwrite
 	.quad sys_chown16
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1f1751dfb2f3..5cf0aa993f4f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -420,7 +420,6 @@ END(\label)
 	PTREGSCALL stub_clone, sys_clone, %r8
 	PTREGSCALL stub_fork, sys_fork, %rdi
 	PTREGSCALL stub_vfork, sys_vfork, %rdi
-	PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
 	PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
 	PTREGSCALL stub_iopl, sys_iopl, %rsi
 
-- 
cgit v1.2.2


From eb179e443deb0a5c81a62b4c157124a4b7ff1813 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 15:01:53 -0700
Subject: xen: mask unwanted pte bits in __supported_pte_mask

[ Stable: this isn't a bugfix in itself, but it's a pre-requiste
  for "xen: don't drop NX bit" ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/enlighten.c | 5 +++++
 arch/x86/xen/mmu.c       | 4 +---
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 8e6152e6ed88..73fb0c4c150a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1280,6 +1280,11 @@ asmlinkage void __init xen_start_kernel(void)
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 
+	/* Prevent unwanted bits from being set in PTEs. */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	if (!is_initial_xendomain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
 	/* set the limit of our address space */
 	xen_reserve_top();
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 7c9935858f92..f0078d9a5b78 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -343,10 +343,8 @@ pgdval_t xen_pgd_val(pgd_t pgd)
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT) {
+	if (pte & _PAGE_PRESENT)
 		pte = phys_to_machine(XPADDR(pte)).maddr;
-		pte &= ~(_PAGE_PCD | _PAGE_PWT);
-	}
 
 	return (pte_t){ .pte = pte };
 }
-- 
cgit v1.2.2


From a987b16cc6123af2c9414032701bab5f73c54c89 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 15:01:56 -0700
Subject: xen: don't drop NX bit

Because NX is now enforced properly, we must put the hypercall page
into the .text segment so that it is executable.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/mmu.c      | 54 +++++++++++++++++++++++++++----------------------
 arch/x86/xen/xen-head.S |  2 +-
 2 files changed, 31 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f0078d9a5b78..8132aa8c5d49 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -323,46 +323,54 @@ out:
 		preempt_enable();
 }
 
-pteval_t xen_pte_val(pte_t pte)
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-	pteval_t ret = pte.pte;
+	if (val & _PAGE_PRESENT) {
+		unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+	}
 
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+	return val;
+}
 
-	return ret;
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+pteval_t xen_pte_val(pte_t pte)
+{
+	return pte_mfn_to_pfn(pte.pte);
 }
 
 pgdval_t xen_pgd_val(pgd_t pgd)
 {
-	pgdval_t ret = pgd.pgd;
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pgd.pgd);
 }
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT)
-		pte = phys_to_machine(XPADDR(pte)).maddr;
-
-	return (pte_t){ .pte = pte };
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
 }
 
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
-	if (pgd & _PAGE_PRESENT)
-		pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
-	return (pgd_t){ pgd };
+	pgd = pte_pfn_to_mfn(pgd);
+	return native_make_pgd(pgd);
 }
 
 pmdval_t xen_pmd_val(pmd_t pmd)
 {
-	pmdval_t ret = native_pmd_val(pmd);
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pmd.pmd);
 }
 
 void xen_set_pud_hyper(pud_t *ptr, pud_t val)
@@ -421,9 +429,7 @@ void xen_pmd_clear(pmd_t *pmdp)
 
 pmd_t xen_make_pmd(pmdval_t pmd)
 {
-	if (pmd & _PAGE_PRESENT)
-		pmd = phys_to_machine(XPADDR(pmd)).maddr;
-
+	pmd = pte_pfn_to_mfn(pmd);
 	return native_make_pmd(pmd);
 }
 
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index ef6c9e005f90..7c0cf6320a0a 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -18,7 +18,7 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-.pushsection .bss.page_aligned
+.pushsection .text
 	.align PAGE_SIZE_asm
 ENTRY(hypercall_page)
 	.skip 0x1000
-- 
cgit v1.2.2


From 05345b0f006ac226d0d25d48fcb2d792ac44a071 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 15:01:53 -0700
Subject: xen: mask unwanted pte bits in __supported_pte_mask

[ Stable: this isn't a bugfix in itself, but it's a pre-requiste
  for "xen: don't drop NX bit" ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/enlighten.c | 5 +++++
 arch/x86/xen/mmu.c       | 4 +---
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c8a56e457d61..c048de34d6a1 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1228,6 +1228,11 @@ asmlinkage void __init xen_start_kernel(void)
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 
+	/* Prevent unwanted bits from being set in PTEs. */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	if (!is_initial_xendomain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
 	/* set the limit of our address space */
 	xen_reserve_top();
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3525ef523a74..3f2a67fe6ad6 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -199,10 +199,8 @@ pgdval_t xen_pgd_val(pgd_t pgd)
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT) {
+	if (pte & _PAGE_PRESENT)
 		pte = phys_to_machine(XPADDR(pte)).maddr;
-		pte &= ~(_PAGE_PCD | _PAGE_PWT);
-	}
 
 	return (pte_t){ .pte = pte };
 }
-- 
cgit v1.2.2


From ebb9cfe20fe167f29960a5e913193a684fac50bf Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 15:01:56 -0700
Subject: xen: don't drop NX bit

Because NX is now enforced properly, we must put the hypercall page
into the .text segment so that it is executable.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/mmu.c      | 54 +++++++++++++++++++++++++++----------------------
 arch/x86/xen/xen-head.S |  2 +-
 2 files changed, 31 insertions(+), 25 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3f2a67fe6ad6..265601d5a6ae 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -179,46 +179,54 @@ out:
 		preempt_enable();
 }
 
-pteval_t xen_pte_val(pte_t pte)
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-	pteval_t ret = pte.pte;
+	if (val & _PAGE_PRESENT) {
+		unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+	}
 
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+	return val;
+}
 
-	return ret;
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+pteval_t xen_pte_val(pte_t pte)
+{
+	return pte_mfn_to_pfn(pte.pte);
 }
 
 pgdval_t xen_pgd_val(pgd_t pgd)
 {
-	pgdval_t ret = pgd.pgd;
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pgd.pgd);
 }
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT)
-		pte = phys_to_machine(XPADDR(pte)).maddr;
-
-	return (pte_t){ .pte = pte };
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
 }
 
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
-	if (pgd & _PAGE_PRESENT)
-		pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
-	return (pgd_t){ pgd };
+	pgd = pte_pfn_to_mfn(pgd);
+	return native_make_pgd(pgd);
 }
 
 pmdval_t xen_pmd_val(pmd_t pmd)
 {
-	pmdval_t ret = native_pmd_val(pmd);
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pmd.pmd);
 }
 #ifdef CONFIG_X86_PAE
 void xen_set_pud(pud_t *ptr, pud_t val)
@@ -265,9 +273,7 @@ void xen_pmd_clear(pmd_t *pmdp)
 
 pmd_t xen_make_pmd(pmdval_t pmd)
 {
-	if (pmd & _PAGE_PRESENT)
-		pmd = phys_to_machine(XPADDR(pmd)).maddr;
-
+	pmd = pte_pfn_to_mfn(pmd);
 	return native_make_pmd(pmd);
 }
 #else  /* !PAE */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 288d587ce73c..3175e973fd0d 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -17,7 +17,7 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-.pushsection .bss.page_aligned
+.pushsection .text
 	.align PAGE_SIZE_asm
 ENTRY(hypercall_page)
 	.skip 0x1000
-- 
cgit v1.2.2


From 0754557d72c1fbfc5fcfd5235e7c23ae6f77248c Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Sat, 21 Jun 2008 03:50:47 -0700
Subject: x86: change early_gart_iommu_check() back to any_mapped

Kevin Winchester reported a GART related direct rendering failure against
linux-next-20080611, which shows up via these log entries:

 PCI: Using ACPI for IRQ routing
 PCI: Cannot allocate resource region 0 of device 0000:00:00.0
 agpgart: Detected AGP bridge 0
 agpgart: Aperture conflicts with PCI mapping.
 agpgart: Aperture from AGP @ e0000000 size 128 MB
 agpgart: Aperture conflicts with PCI mapping.
 agpgart: No usable aperture found.
 agpgart: Consider rebooting with iommu=memaper=2 to get a good aperture.

instead of the expected:

 PCI: Using ACPI for IRQ routing
 agpgart: Detected AGP bridge 0
 agpgart: Aperture from AGP @ e0000000 size 128 MB

Kevin bisected it down to this change in tip/x86/gart:
"x86: checking aperture size order".

agp check is using request_mem_region(), and could fail if e820 is reserved...

change it back to e820_any_mapped().

Reported-and-bisected-by: "Kevin Winchester" <kjwinchester@gmail.com>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Tested-by: Kevin Winchester <kjwinchester@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/aperture_64.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3409abb231ac..e819362c7068 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -324,8 +324,8 @@ void __init early_gart_iommu_check(void)
 		fix = 1;
 
 	if (gart_fix_e820 && !fix && aper_enabled) {
-		if (!e820_all_mapped(aper_base, aper_base + aper_size,
-				    E820_RESERVED)) {
+		if (e820_any_mapped(aper_base, aper_base + aper_size,
+				    E820_RAM)) {
 			/* reserve it, so we can reuse it in second kernel */
 			printk(KERN_INFO "update e820 for GART\n");
 			add_memory_region(aper_base, aper_size, E820_RESERVED);
-- 
cgit v1.2.2


From d4acf7e7abe45457e751525a2a4d5b693dfdd597 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Fri, 6 Jun 2008 16:37:35 -0300
Subject: KVM: Fix race between timer migration and vcpu migration

A guest vcpu instance can be scheduled to a different physical CPU
between the test for KVM_REQ_MIGRATE_TIMER and local_irq_disable().

If that happens, the timer will only be migrated to the current pCPU on
the next exit, meaning that guest LAPIC timer event can be delayed until
a host interrupt is triggered.

Fix it by cancelling guest entry if any vcpu request is pending.  This
has the side effect of nicely consolidating vcpu->requests checks.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/x86.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00acf1301a15..b90744a1dc3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2759,6 +2759,8 @@ again:
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
 			__kvm_migrate_timers(vcpu);
+		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+			kvm_x86_ops->tlb_flush(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
 			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -2781,21 +2783,13 @@ again:
 
 	local_irq_disable();
 
-	if (need_resched()) {
+	if (vcpu->requests || need_resched()) {
 		local_irq_enable();
 		preempt_enable();
 		r = 1;
 		goto out;
 	}
 
-	if (vcpu->requests)
-		if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
-			local_irq_enable();
-			preempt_enable();
-			r = 1;
-			goto out;
-		}
-
 	if (signal_pending(current)) {
 		local_irq_enable();
 		preempt_enable();
@@ -2825,9 +2819,6 @@ again:
 
 	kvm_guest_enter();
 
-	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
-			kvm_x86_ops->tlb_flush(vcpu);
 
 	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
 	kvm_x86_ops->run(vcpu, kvm_run);
-- 
cgit v1.2.2


From 06e05645661211b9eaadaf6344c335d2e80f0ba2 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Fri, 6 Jun 2008 16:37:36 -0300
Subject: KVM: close timer injection race window in __vcpu_run

If a timer fires after kvm_inject_pending_timer_irqs() but before
local_irq_disable() the code will enter guest mode and only inject such
timer interrupt the next time an unrelated event causes an exit.

It would be simpler if the timer->pending irq conversion could be done
with IRQ's disabled, so that the above problem cannot happen.

For now introduce a new vcpu requests bit to cancel guest entry.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/i8254.c | 9 ++++++---
 arch/x86/kvm/lapic.c | 1 +
 arch/x86/kvm/x86.c   | 1 +
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index f2f5d260874e..3829aa7b663f 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -200,9 +200,12 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
 	atomic_inc(&pt->pending);
 	smp_mb__after_atomic_inc();
-	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
-		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-		wake_up_interruptible(&vcpu0->wq);
+	if (vcpu0) {
+		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
+		if (waitqueue_active(&vcpu0->wq)) {
+			vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			wake_up_interruptible(&vcpu0->wq);
+		}
 	}
 
 	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c297c50eba63..ebc03f5ae162 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 	wait_queue_head_t *q = &apic->vcpu->wq;
 
 	atomic_inc(&apic->timer.pending);
+	set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
 	if (waitqueue_active(q)) {
 		apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(q);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b90744a1dc3a..b08812d6b34c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2774,6 +2774,7 @@ again:
 		}
 	}
 
+	clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
 	kvm_inject_pending_timer_irqs(vcpu);
 
 	preempt_disable();
-- 
cgit v1.2.2


From 6597ca09e6c0e5aec7ffd2b8ab48c671d3c28414 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Sun, 8 Jun 2008 01:48:53 -0300
Subject: KVM: MMU: Fix rmap_write_protect() hugepage iteration bug

rmap_next() does not work correctly after rmap_remove(), as it expects
the rmap chains not to change during iteration.  Fix (for now) by restarting
iteration from the beginning.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/mmu.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ee3f53098f0c..9628091c574d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -640,6 +640,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
 			rmap_remove(kvm, spte);
 			--kvm->stat.lpages;
 			set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+			spte = NULL;
 			write_protected = 1;
 		}
 		spte = rmap_next(kvm, rmapp, spte);
-- 
cgit v1.2.2


From 3094538739415a9225afd2a6c78cb0fe1c1f641b Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 11 Jun 2008 20:32:40 -0300
Subject: KVM: MMU: large page update_pte issue with non-PAE 32-bit guests
 (resend)

kvm_mmu_pte_write() does not handle 32-bit non-PAE large page backed
guests properly. It will instantiate two 2MB sptes pointing to the same
physical 2MB page when a guest large pte update is trapped.

Instead of duplicating code to handle this, disallow directory level
updates to happen through kvm_mmu_pte_write(), so the two 2MB sptes
emulating one guest 4MB pte can be correctly created by the page fault
handling path.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/mmu.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9628091c574d..baa6503894d3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1581,11 +1581,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
 				  u64 *spte,
 				  const void *new)
 {
-	if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
-	    && !vcpu->arch.update_pte.largepage) {
-		++vcpu->kvm->stat.mmu_pde_zapped;
-		return;
-	}
+	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+		if (!vcpu->arch.update_pte.largepage ||
+		    sp->role.glevels == PT32_ROOT_LEVEL) {
+			++vcpu->kvm->stat.mmu_pde_zapped;
+			return;
+		}
+        }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
 	if (sp->role.glevels == PT32_ROOT_LEVEL)
-- 
cgit v1.2.2


From 6bf6a9532fd03ad719f0c86654f16ef777b78fc6 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Thu, 12 Jun 2008 16:54:41 +0300
Subject: KVM: MMU: Fix oops on guest userspace access to guest pagetable

KVM has a heuristic to unshadow guest pagetables when userspace accesses
them, on the assumption that most guests do not allow userspace to access
pagetables directly. Unfortunately, in addition to unshadowing the pagetables,
it also oopses.

This never triggers on ordinary guests since sane OSes will clear the
pagetables before assigning them to userspace, which will trigger the flood
heuristic, unshadowing the pagetables before the first userspace access. One
particular guest, though (Xenner) will run the kernel in userspace, triggering
the oops.  Since the heuristic is incorrect in this case, we can simply
remove it.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/mmu.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index baa6503894d3..7e7c3969f7a2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1083,10 +1083,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		struct kvm_mmu_page *shadow;
 
 		spte |= PT_WRITABLE_MASK;
-		if (user_fault) {
-			mmu_unshadow(vcpu->kvm, gfn);
-			goto unshadowed;
-		}
 
 		shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
 		if (shadow ||
@@ -1103,8 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		}
 	}
 
-unshadowed:
-
 	if (pte_access & ACC_WRITE_MASK)
 		mark_page_dirty(vcpu->kvm, gfn);
 
-- 
cgit v1.2.2


From a9b21b622958afc3f3bc5a23d266dd9ed1171fd3 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Tue, 24 Jun 2008 11:48:49 +0300
Subject: KVM: VMX: Fix host msr corruption with preemption enabled

Switching msrs can occur either synchronously as a result of calls to
the msr management functions (usually in response to the guest touching
virtualized msrs), or asynchronously when preempting a kvm thread that has
guest state loaded.  If we're unlucky enough to have the two at the same
time, host msrs are corrupted and the machine goes kaput on the next syscall.

Most easily triggered by Windows Server 2008, as it does a lot of msr
switching during bootup.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/vmx.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 02efbe75f317..540e95179074 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -566,7 +566,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	load_transition_efer(vmx);
 }
 
-static void vmx_load_host_state(struct vcpu_vmx *vmx)
+static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 {
 	unsigned long flags;
 
@@ -596,6 +596,13 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx)
 	reload_host_efer(vmx);
 }
 
+static void vmx_load_host_state(struct vcpu_vmx *vmx)
+{
+	preempt_disable();
+	__vmx_load_host_state(vmx);
+	preempt_enable();
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -654,7 +661,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	vmx_load_host_state(to_vmx(vcpu));
+	__vmx_load_host_state(to_vmx(vcpu));
 }
 
 static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
@@ -884,11 +891,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 	switch (msr_index) {
 #ifdef CONFIG_X86_64
 	case MSR_EFER:
+		vmx_load_host_state(vmx);
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
-		if (vmx->host_state.loaded) {
-			reload_host_efer(vmx);
-			load_transition_efer(vmx);
-		}
 		break;
 	case MSR_FS_BASE:
 		vmcs_writel(GUEST_FS_BASE, data);
@@ -910,11 +914,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		guest_write_tsc(data);
 		break;
 	default:
+		vmx_load_host_state(vmx);
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (vmx->host_state.loaded)
-				load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
-- 
cgit v1.2.2


From bcc643dc287cb732e96a1685ac130c3ae8b1c960 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 21:58:46 +0200
Subject: x86: introduce macro to check whether an address range is in the ISA
 range

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/ioremap.c | 2 +-
 arch/x86/mm/pat.c     | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 7452eb31ed12..6d9960dd6f35 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -142,7 +142,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't remap the low PCI/ISA area, it's always mapped..
 	 */
-	if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS)
+	if (is_ISA_range(phys_addr, last_addr))
 		return (__force void __iomem *)phys_to_virt(phys_addr);
 
 	/*
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 227df3ca9bfd..5bbc22efe4e5 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -215,7 +215,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	}
 
 	/* Low ISA region is always mapped WB in page table. No need to track */
-	if (start >= ISA_START_ADDRESS && (end - 1) <= ISA_END_ADDRESS) {
+	if (is_ISA_range(start, end - 1)) {
 		if (ret_type)
 			*ret_type = _PAGE_CACHE_WB;
 
@@ -415,9 +415,8 @@ int free_memtype(u64 start, u64 end)
 	}
 
 	/* Low ISA region is always mapped WB. No need to track */
-	if (start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS) {
+	if (is_ISA_range(start, end - 1))
 		return 0;
-	}
 
 	spin_lock(&memtype_lock);
 	list_for_each_entry(ml, &memtype_list, nd) {
-- 
cgit v1.2.2


From ac97991ec9e0a05c8860f4a04f8477227b1c03f2 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:01:49 +0200
Subject: x86: pat.c choose more crisp variable names

 - parse/ml => entry (within list_for_each and friends)
 - new_entry => new
 - ret_type => new_type (to avoid confusion with req_type)

(... to make it more readable...)

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 127 ++++++++++++++++++++++++++----------------------------
 1 file changed, 62 insertions(+), 65 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 5bbc22efe4e5..a6507bfb12a7 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -188,37 +188,34 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
  * req_type will have a special case value '-1', when requester want to inherit
  * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS.
  *
- * If ret_type is NULL, function will return an error if it cannot reserve the
- * region with req_type. If ret_type is non-null, function will return
- * available type in ret_type in case of no error. In case of any error
+ * If new_type is NULL, function will return an error if it cannot reserve the
+ * region with req_type. If new_type is non-NULL, function will return
+ * available type in new_type in case of no error. In case of any error
  * it will return a negative return value.
  */
 int reserve_memtype(u64 start, u64 end, unsigned long req_type,
-			unsigned long *ret_type)
+			unsigned long *new_type)
 {
-	struct memtype *new_entry = NULL;
-	struct memtype *parse;
+	struct memtype *new, *entry;
 	unsigned long actual_type;
 	int err = 0;
 
 	/* Only track when pat_enabled */
 	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
-		if (ret_type) {
-			if (req_type == -1) {
-				*ret_type = _PAGE_CACHE_WB;
-			} else {
-				*ret_type = req_type & _PAGE_CACHE_MASK;
-			}
+		if (new_type) {
+			if (req_type == -1)
+				*new_type = _PAGE_CACHE_WB;
+			else
+				*new_type = req_type & _PAGE_CACHE_MASK;
 		}
 		return 0;
 	}
 
 	/* Low ISA region is always mapped WB in page table. No need to track */
 	if (is_ISA_range(start, end - 1)) {
-		if (ret_type)
-			*ret_type = _PAGE_CACHE_WB;
-
+		if (new_type)
+			*new_type = _PAGE_CACHE_WB;
 		return 0;
 	}
 
@@ -243,65 +240,65 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		actual_type = pat_x_mtrr_type(start, end, req_type);
 	}
 
-	new_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
-	if (!new_entry)
+	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+	if (!new)
 		return -ENOMEM;
 
-	new_entry->start = start;
-	new_entry->end = end;
-	new_entry->type = actual_type;
+	new->start = start;
+	new->end = end;
+	new->type = actual_type;
 
-	if (ret_type)
-		*ret_type = actual_type;
+	if (new_type)
+		*new_type = actual_type;
 
 	spin_lock(&memtype_lock);
 
 	/* Search for existing mapping that overlaps the current range */
-	list_for_each_entry(parse, &memtype_list, nd) {
+	list_for_each_entry(entry, &memtype_list, nd) {
 		struct memtype *saved_ptr;
 
-		if (parse->start >= end) {
+		if (entry->start >= end) {
 			dprintk("New Entry\n");
-			list_add(&new_entry->nd, parse->nd.prev);
-			new_entry = NULL;
+			list_add(&new->nd, entry->nd.prev);
+			new = NULL;
 			break;
 		}
 
-		if (start <= parse->start && end >= parse->start) {
-			if (actual_type != parse->type && ret_type) {
-				actual_type = parse->type;
-				*ret_type = actual_type;
-				new_entry->type = actual_type;
+		if (start <= entry->start && end >= entry->start) {
+			if (actual_type != entry->type && new_type) {
+				actual_type = entry->type;
+				*new_type = actual_type;
+				new->type = actual_type;
 			}
 
-			if (actual_type != parse->type) {
+			if (actual_type != entry->type) {
 				printk(
 		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
 					current->comm, current->pid,
 					start, end,
 					cattr_name(actual_type),
-					cattr_name(parse->type));
+					cattr_name(entry->type));
 				err = -EBUSY;
 				break;
 			}
 
-			saved_ptr = parse;
+			saved_ptr = entry;
 			/*
 			 * Check to see whether the request overlaps more
 			 * than one entry in the list
 			 */
-			list_for_each_entry_continue(parse, &memtype_list, nd) {
-				if (end <= parse->start) {
+			list_for_each_entry_continue(entry, &memtype_list, nd) {
+				if (end <= entry->start) {
 					break;
 				}
 
-				if (actual_type != parse->type) {
+				if (actual_type != entry->type) {
 					printk(
 		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
 						current->comm, current->pid,
 						start, end,
 						cattr_name(actual_type),
-						cattr_name(parse->type));
+						cattr_name(entry->type));
 					err = -EBUSY;
 					break;
 				}
@@ -314,46 +311,46 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 			       saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
-			list_add(&new_entry->nd, saved_ptr->nd.prev);
-			new_entry = NULL;
+			list_add(&new->nd, saved_ptr->nd.prev);
+			new = NULL;
 			break;
 		}
 
-		if (start < parse->end) {
-			if (actual_type != parse->type && ret_type) {
-				actual_type = parse->type;
-				*ret_type = actual_type;
-				new_entry->type = actual_type;
+		if (start < entry->end) {
+			if (actual_type != entry->type && new_type) {
+				actual_type = entry->type;
+				*new_type = actual_type;
+				new->type = actual_type;
 			}
 
-			if (actual_type != parse->type) {
+			if (actual_type != entry->type) {
 				printk(
 		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
 					current->comm, current->pid,
 					start, end,
 					cattr_name(actual_type),
-					cattr_name(parse->type));
+					cattr_name(entry->type));
 				err = -EBUSY;
 				break;
 			}
 
-			saved_ptr = parse;
+			saved_ptr = entry;
 			/*
 			 * Check to see whether the request overlaps more
 			 * than one entry in the list
 			 */
-			list_for_each_entry_continue(parse, &memtype_list, nd) {
-				if (end <= parse->start) {
+			list_for_each_entry_continue(entry, &memtype_list, nd) {
+				if (end <= entry->start) {
 					break;
 				}
 
-				if (actual_type != parse->type) {
+				if (actual_type != entry->type) {
 					printk(
 		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
 						current->comm, current->pid,
 						start, end,
 						cattr_name(actual_type),
-						cattr_name(parse->type));
+						cattr_name(entry->type));
 					err = -EBUSY;
 					break;
 				}
@@ -366,8 +363,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 				 saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
-			list_add(&new_entry->nd, &saved_ptr->nd);
-			new_entry = NULL;
+			list_add(&new->nd, &saved_ptr->nd);
+			new = NULL;
 			break;
 		}
 	}
@@ -375,24 +372,24 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	if (err) {
 		printk(KERN_INFO
 	"reserve_memtype failed 0x%Lx-0x%Lx, track %s, req %s\n",
-			start, end, cattr_name(new_entry->type),
+			start, end, cattr_name(new->type),
 			cattr_name(req_type));
-		kfree(new_entry);
+		kfree(new);
 		spin_unlock(&memtype_lock);
 		return err;
 	}
 
-	if (new_entry) {
+	if (new) {
 		/* No conflict. Not yet added to the list. Add to the tail */
-		list_add_tail(&new_entry->nd, &memtype_list);
+		list_add_tail(&new->nd, &memtype_list);
 		dprintk("New Entry\n");
 	}
 
-	if (ret_type) {
+	if (new_type) {
 		dprintk(
 	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
 			start, end, cattr_name(actual_type),
-			cattr_name(req_type), cattr_name(*ret_type));
+			cattr_name(req_type), cattr_name(*new_type));
 	} else {
 		dprintk(
 	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n",
@@ -406,7 +403,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 int free_memtype(u64 start, u64 end)
 {
-	struct memtype *ml;
+	struct memtype *entry;
 	int err = -EINVAL;
 
 	/* Only track when pat_enabled */
@@ -419,10 +416,10 @@ int free_memtype(u64 start, u64 end)
 		return 0;
 
 	spin_lock(&memtype_lock);
-	list_for_each_entry(ml, &memtype_list, nd) {
-		if (ml->start == start && ml->end == end) {
-			list_del(&ml->nd);
-			kfree(ml);
+	list_for_each_entry(entry, &memtype_list, nd) {
+		if (entry->start == start && entry->end == end) {
+			list_del(&entry->nd);
+			kfree(entry);
 			err = 0;
 			break;
 		}
-- 
cgit v1.2.2


From 69e26be9b1d0c83d3581475095ce2a1ccc578215 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:03:06 +0200
Subject: x86: pat.c more trivial changes

 - add BUG statement to catch invalid start and end parameters
 - No need to track the actual type in both req_type and actual_type --
   keep req_type unchanged.
 - removed (IMHO) superfluous comments

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index a6507bfb12a7..c996a3641200 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -200,7 +200,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	unsigned long actual_type;
 	int err = 0;
 
-	/* Only track when pat_enabled */
+ 	BUG_ON(start >= end); /* end is exclusive */
+
 	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
 		if (new_type) {
@@ -228,17 +229,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		 */
 		u8 mtrr_type = mtrr_type_lookup(start, end);
 
-		if (mtrr_type == MTRR_TYPE_WRBACK) {
-			req_type = _PAGE_CACHE_WB;
+		if (mtrr_type == MTRR_TYPE_WRBACK)
 			actual_type = _PAGE_CACHE_WB;
-		} else {
-			req_type = _PAGE_CACHE_UC_MINUS;
+		else
 			actual_type = _PAGE_CACHE_UC_MINUS;
-		}
-	} else {
-		req_type &= _PAGE_CACHE_MASK;
-		actual_type = pat_x_mtrr_type(start, end, req_type);
-	}
+	} else
+		actual_type = pat_x_mtrr_type(start, end,
+					      req_type & _PAGE_CACHE_MASK);
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
@@ -406,10 +403,8 @@ int free_memtype(u64 start, u64 end)
 	struct memtype *entry;
 	int err = -EINVAL;
 
-	/* Only track when pat_enabled */
-	if (!pat_enabled) {
+	if (!pat_enabled)
 		return 0;
-	}
 
 	/* Low ISA region is always mapped WB. No need to track */
 	if (is_ISA_range(start, end - 1))
-- 
cgit v1.2.2


From 3e9c83b309fd7cbf1d9b801d0d5877c040e30420 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:04:02 +0200
Subject: x86: pat.c consolidate error/debug messages in reserve_memtype

... and move last debug message out of locked section.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 51 +++++++++++----------------------------------------
 1 file changed, 11 insertions(+), 40 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index c996a3641200..1118288f8fe2 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -269,12 +269,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			}
 
 			if (actual_type != entry->type) {
-				printk(
-		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-					current->comm, current->pid,
-					start, end,
-					cattr_name(actual_type),
-					cattr_name(entry->type));
 				err = -EBUSY;
 				break;
 			}
@@ -290,12 +284,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				}
 
 				if (actual_type != entry->type) {
-					printk(
-		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-						current->comm, current->pid,
-						start, end,
-						cattr_name(actual_type),
-						cattr_name(entry->type));
 					err = -EBUSY;
 					break;
 				}
@@ -321,12 +309,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 			}
 
 			if (actual_type != entry->type) {
-				printk(
-		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-					current->comm, current->pid,
-					start, end,
-					cattr_name(actual_type),
-					cattr_name(entry->type));
 				err = -EBUSY;
 				break;
 			}
@@ -342,12 +324,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				}
 
 				if (actual_type != entry->type) {
-					printk(
-		KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-						current->comm, current->pid,
-						start, end,
-						cattr_name(actual_type),
-						cattr_name(entry->type));
 					err = -EBUSY;
 					break;
 				}
@@ -367,10 +343,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	}
 
 	if (err) {
-		printk(KERN_INFO
-	"reserve_memtype failed 0x%Lx-0x%Lx, track %s, req %s\n",
-			start, end, cattr_name(new->type),
-			cattr_name(req_type));
+		printk(KERN_INFO "%s:%d conflicting memory types "
+		       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
+		       end, cattr_name(new->type), cattr_name(entry->type));
+		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
+		       "track %s, req %s\n",
+		       start, end, cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
 		return err;
@@ -382,19 +360,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		dprintk("New Entry\n");
 	}
 
-	if (new_type) {
-		dprintk(
-	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
-			start, end, cattr_name(actual_type),
-			cattr_name(req_type), cattr_name(*new_type));
-	} else {
-		dprintk(
-	"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n",
-			start, end, cattr_name(actual_type),
-			cattr_name(req_type));
-	}
-
 	spin_unlock(&memtype_lock);
+
+	dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
+		start, end, cattr_name(new->type), cattr_name(req_type),
+		new_type ? cattr_name(*new_type) : "-");
+
 	return err;
 }
 
-- 
cgit v1.2.2


From f6887264deba4cd991f0ca006918dcff4c939021 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:05:37 +0200
Subject: x86: pat.c consolidate list_add handling in reserve_memtype

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 1118288f8fe2..49dcd9652ec8 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -198,6 +198,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 {
 	struct memtype *new, *entry;
 	unsigned long actual_type;
+	struct list_head *where;
 	int err = 0;
 
  	BUG_ON(start >= end); /* end is exclusive */
@@ -251,13 +252,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	spin_lock(&memtype_lock);
 
 	/* Search for existing mapping that overlaps the current range */
+	where = NULL;
 	list_for_each_entry(entry, &memtype_list, nd) {
 		struct memtype *saved_ptr;
 
 		if (entry->start >= end) {
-			dprintk("New Entry\n");
-			list_add(&new->nd, entry->nd.prev);
-			new = NULL;
+			where = entry->nd.prev;
 			break;
 		}
 
@@ -295,9 +295,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 			       saved_ptr->start, saved_ptr->end);
-			/* No conflict. Go ahead and add this new entry */
-			list_add(&new->nd, saved_ptr->nd.prev);
-			new = NULL;
+			where = saved_ptr->nd.prev;
 			break;
 		}
 
@@ -335,9 +333,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
 				 saved_ptr->start, saved_ptr->end);
-			/* No conflict. Go ahead and add this new entry */
-			list_add(&new->nd, &saved_ptr->nd);
-			new = NULL;
+			where = &saved_ptr->nd;
 			break;
 		}
 	}
@@ -354,11 +350,10 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		return err;
 	}
 
-	if (new) {
-		/* No conflict. Not yet added to the list. Add to the tail */
+	if (where)
+		list_add(&new->nd, where);
+	else
 		list_add_tail(&new->nd, &memtype_list);
-		dprintk("New Entry\n");
-	}
 
 	spin_unlock(&memtype_lock);
 
-- 
cgit v1.2.2


From 64fe44c38bbdfab4fe052029058ce5fe9804de68 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:07:09 +0200
Subject: x86: pat.c introduce function to check for conflicts with existing
 memtypes

... to strip down loop body in reserve_memtype.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 96 +++++++++++++++++++------------------------------------
 1 file changed, 33 insertions(+), 63 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 49dcd9652ec8..281ac6489c08 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -178,6 +178,33 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 	return req_type;
 }
 
+static int chk_conflict(struct memtype *new, struct memtype *entry,
+			unsigned long *type)
+{
+	if (new->type != entry->type) {
+		if (type) {
+			new->type = entry->type;
+			*type = entry->type;
+		} else
+			goto conflict;
+	}
+
+	 /* check overlaps with more than one entry in the list */
+	list_for_each_entry_continue(entry, &memtype_list, nd) {
+		if (new->end <= entry->start)
+			break;
+		else if (new->type != entry->type)
+			goto conflict;
+	}
+	return 0;
+
+ conflict:
+	printk(KERN_INFO "%s:%d conflicting memory types "
+	       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start,
+	       new->end, cattr_name(new->type), cattr_name(entry->type));
+	return -EBUSY;
+}
+
 /*
  * req_type typically has one of the:
  * - _PAGE_CACHE_WB
@@ -254,94 +281,37 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	/* Search for existing mapping that overlaps the current range */
 	where = NULL;
 	list_for_each_entry(entry, &memtype_list, nd) {
-		struct memtype *saved_ptr;
-
 		if (entry->start >= end) {
 			where = entry->nd.prev;
 			break;
 		}
 
 		if (start <= entry->start && end >= entry->start) {
-			if (actual_type != entry->type && new_type) {
-				actual_type = entry->type;
-				*new_type = actual_type;
-				new->type = actual_type;
-			}
-
-			if (actual_type != entry->type) {
-				err = -EBUSY;
-				break;
-			}
-
-			saved_ptr = entry;
-			/*
-			 * Check to see whether the request overlaps more
-			 * than one entry in the list
-			 */
-			list_for_each_entry_continue(entry, &memtype_list, nd) {
-				if (end <= entry->start) {
-					break;
-				}
-
-				if (actual_type != entry->type) {
-					err = -EBUSY;
-					break;
-				}
-			}
-
+			err = chk_conflict(new, entry, new_type);
 			if (err) {
 				break;
 			}
 
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
-			       saved_ptr->start, saved_ptr->end);
-			where = saved_ptr->nd.prev;
+			       entry->start, entry->end);
+			where = entry->nd.prev;
 			break;
 		}
 
 		if (start < entry->end) {
-			if (actual_type != entry->type && new_type) {
-				actual_type = entry->type;
-				*new_type = actual_type;
-				new->type = actual_type;
-			}
-
-			if (actual_type != entry->type) {
-				err = -EBUSY;
-				break;
-			}
-
-			saved_ptr = entry;
-			/*
-			 * Check to see whether the request overlaps more
-			 * than one entry in the list
-			 */
-			list_for_each_entry_continue(entry, &memtype_list, nd) {
-				if (end <= entry->start) {
-					break;
-				}
-
-				if (actual_type != entry->type) {
-					err = -EBUSY;
-					break;
-				}
-			}
-
+			err = chk_conflict(new, entry, new_type);
 			if (err) {
 				break;
 			}
 
 			dprintk("Overlap at 0x%Lx-0x%Lx\n",
-				 saved_ptr->start, saved_ptr->end);
-			where = &saved_ptr->nd;
+				 entry->start, entry->end);
+			where = &entry->nd;
 			break;
 		}
 	}
 
 	if (err) {
-		printk(KERN_INFO "%s:%d conflicting memory types "
-		       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
-		       end, cattr_name(new->type), cattr_name(entry->type));
 		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
 		       "track %s, req %s\n",
 		       start, end, cattr_name(new->type), cattr_name(req_type));
-- 
cgit v1.2.2


From 33af9039cbf629041da2bfa0cf451208391a1ec3 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann3@amd.com>
Date: Fri, 20 Jun 2008 22:08:37 +0200
Subject: x86: pat.c final cleanup of loop body in reserve_memtype

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pat.c | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 281ac6489c08..a885a1019b8a 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -281,32 +281,24 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	/* Search for existing mapping that overlaps the current range */
 	where = NULL;
 	list_for_each_entry(entry, &memtype_list, nd) {
-		if (entry->start >= end) {
+		if (end <= entry->start) {
 			where = entry->nd.prev;
 			break;
-		}
-
-		if (start <= entry->start && end >= entry->start) {
+		} else if (start <= entry->start) { /* end > entry->start */
 			err = chk_conflict(new, entry, new_type);
-			if (err) {
-				break;
+			if (!err) {
+				dprintk("Overlap at 0x%Lx-0x%Lx\n",
+					entry->start, entry->end);
+				where = entry->nd.prev;
 			}
-
-			dprintk("Overlap at 0x%Lx-0x%Lx\n",
-			       entry->start, entry->end);
-			where = entry->nd.prev;
 			break;
-		}
-
-		if (start < entry->end) {
+		} else if (start < entry->end) { /* start > entry->start */
 			err = chk_conflict(new, entry, new_type);
-			if (err) {
-				break;
+			if (!err) {
+				dprintk("Overlap at 0x%Lx-0x%Lx\n",
+					entry->start, entry->end);
+				where = &entry->nd;
 			}
-
-			dprintk("Overlap at 0x%Lx-0x%Lx\n",
-				 entry->start, entry->end);
-			where = &entry->nd;
 			break;
 		}
 	}
-- 
cgit v1.2.2


From 28499143933f19b28008a556ed59255d6009391a Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Fri, 9 May 2008 12:05:57 +0100
Subject: xen: remove support for non-PAE 32-bit

Non-PAE operation has been deprecated in Xen for a while, and is
rarely tested or used.  xen-unstable has now officially dropped
non-PAE support.  Since Xen/pvops' non-PAE support has also been
broken for a while, we may as well completely drop it altogether.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/Kconfig     |  2 +-
 arch/x86/xen/enlighten.c | 51 +++++++++++++++++-------------------------------
 arch/x86/xen/mmu.c       | 19 ++----------------
 arch/x86/xen/mmu.h       | 24 ++++++-----------------
 arch/x86/xen/xen-head.S  |  4 ----
 5 files changed, 27 insertions(+), 73 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 2e641be2737e..525b108411bd 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -6,7 +6,7 @@ config XEN
 	bool "Xen guest support"
 	select PARAVIRT
 	depends on X86_32
-	depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
+	depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER)
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c048de34d6a1..f09c1c69c37a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -785,38 +785,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 	pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+	int i;
 
 	/* special set_pte for pagetable initialization */
 	pv_mmu_ops.set_pte = xen_set_pte_init;
 
 	init_mm.pgd = base;
 	/*
-	 * copy top-level of Xen-supplied pagetable into place.	 For
-	 * !PAE we can use this as-is, but for PAE it is a stand-in
-	 * while we copy the pmd pages.
+	 * copy top-level of Xen-supplied pagetable into place.  This
+	 * is a stand-in while we copy the pmd pages.
 	 */
 	memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
-	if (PTRS_PER_PMD > 1) {
-		int i;
-		/*
-		 * For PAE, need to allocate new pmds, rather than
-		 * share Xen's, since Xen doesn't like pmd's being
-		 * shared between address spaces.
-		 */
-		for (i = 0; i < PTRS_PER_PGD; i++) {
-			if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
-				pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+	/*
+	 * For PAE, need to allocate new pmds, rather than
+	 * share Xen's, since Xen doesn't like pmd's being
+	 * shared between address spaces.
+	 */
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
+			pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 
-				memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
-				       PAGE_SIZE);
+			memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
+			       PAGE_SIZE);
 
-				make_lowmem_page_readonly(pmd);
+			make_lowmem_page_readonly(pmd);
 
-				set_pgd(&base[i], __pgd(1 + __pa(pmd)));
-			} else
-				pgd_clear(&base[i]);
-		}
+			set_pgd(&base[i], __pgd(1 + __pa(pmd)));
+		} else
+			pgd_clear(&base[i]);
 	}
 
 	/* make sure zero_page is mapped RO so we can use it in pagetables */
@@ -873,17 +870,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 
 	/* Actually pin the pagetable down, but we can't set PG_pinned
 	   yet because the page structures don't exist yet. */
-	{
-		unsigned level;
-
-#ifdef CONFIG_X86_PAE
-		level = MMUEXT_PIN_L3_TABLE;
-#else
-		level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-		pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
-	}
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
 }
 
 /* This is called once we have the cpu_possible_map */
@@ -1093,7 +1080,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.make_pte = xen_make_pte,
 	.make_pgd = xen_make_pgd,
 
-#ifdef CONFIG_X86_PAE
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
 	.set_pud = xen_set_pud,
@@ -1102,7 +1088,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.make_pmd = xen_make_pmd,
 	.pmd_val = xen_pmd_val,
-#endif	/* PAE */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 265601d5a6ae..df40bf74ea75 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -228,7 +228,7 @@ pmdval_t xen_pmd_val(pmd_t pmd)
 {
 	return pte_mfn_to_pfn(pmd.pmd);
 }
-#ifdef CONFIG_X86_PAE
+
 void xen_set_pud(pud_t *ptr, pud_t val)
 {
 	struct multicall_space mcs;
@@ -276,12 +276,6 @@ pmd_t xen_make_pmd(pmdval_t pmd)
 	pmd = pte_pfn_to_mfn(pmd);
 	return native_make_pmd(pmd);
 }
-#else  /* !PAE */
-void xen_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
-}
-#endif	/* CONFIG_X86_PAE */
 
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
@@ -434,8 +428,6 @@ static int pin_page(struct page *page, enum pt_level level)
    read-only, and can be pinned. */
 void xen_pgd_pin(pgd_t *pgd)
 {
-	unsigned level;
-
 	xen_mc_batch();
 
 	if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
@@ -445,14 +437,7 @@ void xen_pgd_pin(pgd_t *pgd)
 		xen_mc_batch();
 	}
 
-#ifdef CONFIG_X86_PAE
-	level = MMUEXT_PIN_L3_TABLE;
-#else
-	level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-	xen_do_pin(level, PFN_DOWN(__pa(pgd)));
-
+	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
 	xen_mc_issue(0);
 }
 
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index b5e189b1519d..5fe961caffd4 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -37,14 +37,13 @@ void xen_exit_mmap(struct mm_struct *mm);
 void xen_pgd_pin(pgd_t *pgd);
 //void xen_pgd_unpin(pgd_t *pgd);
 
-#ifdef CONFIG_X86_PAE
-unsigned long long xen_pte_val(pte_t);
-unsigned long long xen_pmd_val(pmd_t);
-unsigned long long xen_pgd_val(pgd_t);
+pteval_t xen_pte_val(pte_t);
+pmdval_t xen_pmd_val(pmd_t);
+pgdval_t xen_pgd_val(pgd_t);
 
-pte_t xen_make_pte(unsigned long long);
-pmd_t xen_make_pmd(unsigned long long);
-pgd_t xen_make_pgd(unsigned long long);
+pte_t xen_make_pte(pteval_t);
+pmd_t xen_make_pmd(pmdval_t);
+pgd_t xen_make_pgd(pgdval_t);
 
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval);
@@ -53,15 +52,4 @@ void xen_set_pud(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
-
-#else
-unsigned long xen_pte_val(pte_t);
-unsigned long xen_pmd_val(pmd_t);
-unsigned long xen_pgd_val(pgd_t);
-
-pte_t xen_make_pte(unsigned long);
-pmd_t xen_make_pmd(unsigned long);
-pgd_t xen_make_pgd(unsigned long);
-#endif
-
 #endif	/* _XEN_MMU_H */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 3175e973fd0d..6ec3b4f7719b 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -30,11 +30,7 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          .long  startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long  hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
-#ifdef CONFIG_X86_PAE
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
-#else
-	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "no")
-#endif
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 
 #endif /*CONFIG_XEN */
-- 
cgit v1.2.2


From 378fc6eedc0091cc5ba65b298b8967bd2d43df5d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 24 Jun 2008 16:21:18 +0100
Subject: x86: arch/x86/kernel/machine_kexec_32.c: remove extra semicolons

I can't see any reason to keep these semicolons.

Signed-off-by: WANG Cong <wangcong@zeuux.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/machine_kexec_32.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d0b234c9fc31..f4960171bc66 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -39,7 +39,7 @@ static void set_idt(void *newidt, __u16 limit)
 	curidt.address = (unsigned long)newidt;
 
 	load_idt(&curidt);
-};
+}
 
 
 static void set_gdt(void *newgdt, __u16 limit)
@@ -51,7 +51,7 @@ static void set_gdt(void *newgdt, __u16 limit)
 	curgdt.address = (unsigned long)newgdt;
 
 	load_gdt(&curgdt);
-};
+}
 
 static void load_segments(void)
 {
-- 
cgit v1.2.2


From 7af192c954017499ec163bc9dbaaee2e593d7ef2 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 3 Jun 2008 16:17:29 +0200
Subject: x86: Add structs and functions for paravirt clocksource

This patch adds structs for the paravirt clocksource ABI
used by both xen and kvm (pvclock-abi.h).

It also adds some helper functions to read system time and
wall clock time from a paravirtual clocksource (pvclock.[ch]).
They are based on the xen code.  They are enabled using
CONFIG_PARAVIRT_CLOCK.

Subsequent patches of this series will put the code in use.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/Kconfig          |   4 ++
 arch/x86/kernel/Makefile  |   1 +
 arch/x86/kernel/pvclock.c | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 146 insertions(+)
 create mode 100644 arch/x86/kernel/pvclock.c

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 52e18e6d2ba0..f94bca6ff47f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -410,6 +410,10 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_CLOCK
+	bool
+	default n
+
 endif
 
 config MEMTEST_BOOTPARAM
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5e618c3b4720..77807d4769c9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
new file mode 100644
index 000000000000..05fbe9a0325a
--- /dev/null
+++ b/arch/x86/kernel/pvclock.c
@@ -0,0 +1,141 @@
+/*  paravirtual clock -- common code used by kvm/xen
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <asm/pvclock.h>
+
+/*
+ * These are perodically updated
+ *    xen: magic shared_info page
+ *    kvm: gpa registered via msr
+ * and then copied here.
+ */
+struct pvclock_shadow_time {
+	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
+	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
+	u32 tsc_to_nsec_mul;
+	int tsc_shift;
+	u32 version;
+};
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif __x86_64__
+	__asm__ (
+		"mul %%rdx ; shrd $32,%%rdx,%%rax"
+		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
+static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
+{
+	u64 delta = native_read_tsc() - shadow->tsc_timestamp;
+	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+}
+
+/*
+ * Reads a consistent set of time-base values from hypervisor,
+ * into a shadow data area.
+ */
+static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
+					struct pvclock_vcpu_time_info *src)
+{
+	do {
+		dst->version = src->version;
+		rmb();		/* fetch version before data */
+		dst->tsc_timestamp     = src->tsc_timestamp;
+		dst->system_timestamp  = src->system_time;
+		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
+		dst->tsc_shift         = src->tsc_shift;
+		rmb();		/* test version after fetching data */
+	} while ((src->version & 1) || (dst->version != src->version));
+
+	return dst->version;
+}
+
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+	struct pvclock_shadow_time shadow;
+	unsigned version;
+	cycle_t ret, offset;
+
+	do {
+		version = pvclock_get_time_values(&shadow, src);
+		barrier();
+		offset = pvclock_get_nsec_offset(&shadow);
+		ret = shadow.system_timestamp + offset;
+		barrier();
+	} while (version != src->version);
+
+	return ret;
+}
+
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
+			    struct pvclock_vcpu_time_info *vcpu_time,
+			    struct timespec *ts)
+{
+	u32 version;
+	u64 delta;
+	struct timespec now;
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	delta = pvclock_clocksource_read(vcpu_time);	/* time since system boot */
+	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+
+	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
+	now.tv_sec = delta;
+
+	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+}
-- 
cgit v1.2.2


From 1c7b67f7576c4ca2a344379a4a29eec8fe8e7935 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 3 Jun 2008 16:17:30 +0200
Subject: x86: Make xen use the paravirt clocksource structs and functions

This patch updates the xen guest to use the pvclock structs
and helper functions.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/xen/Kconfig |   1 +
 arch/x86/xen/time.c  | 132 +++++----------------------------------------------
 2 files changed, 13 insertions(+), 120 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 2e641be2737e..3a4f16aea4bf 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -5,6 +5,7 @@
 config XEN
 	bool "Xen guest support"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on X86_32
 	depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
 	help
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 52b2e3856980..41e217503c96 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
 
+#include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -31,17 +32,6 @@
 
 static cycle_t xen_clocksource_read(void);
 
-/* These are perodically updated in shared_info, and then copied here. */
-struct shadow_time_info {
-	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
-	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
-	u32 tsc_to_nsec_mul;
-	int tsc_shift;
-	u32 version;
-};
-
-static DEFINE_PER_CPU(struct shadow_time_info, shadow_time);
-
 /* runstate info updated by Xen */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
 
@@ -211,7 +201,7 @@ unsigned long long xen_sched_clock(void)
 unsigned long xen_cpu_khz(void)
 {
 	u64 xen_khz = 1000000ULL << 32;
-	const struct vcpu_time_info *info =
+	const struct pvclock_vcpu_time_info *info =
 		&HYPERVISOR_shared_info->vcpu_info[0].time;
 
 	do_div(xen_khz, info->tsc_to_system_mul);
@@ -223,121 +213,26 @@ unsigned long xen_cpu_khz(void)
 	return xen_khz;
 }
 
-/*
- * Reads a consistent set of time-base values from Xen, into a shadow data
- * area.
- */
-static unsigned get_time_values_from_xen(void)
-{
-	struct vcpu_time_info   *src;
-	struct shadow_time_info *dst;
-
-	/* src is shared memory with the hypervisor, so we need to
-	   make sure we get a consistent snapshot, even in the face of
-	   being preempted. */
-	src = &__get_cpu_var(xen_vcpu)->time;
-	dst = &__get_cpu_var(shadow_time);
-
-	do {
-		dst->version = src->version;
-		rmb();		/* fetch version before data */
-		dst->tsc_timestamp     = src->tsc_timestamp;
-		dst->system_timestamp  = src->system_time;
-		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
-		dst->tsc_shift         = src->tsc_shift;
-		rmb();		/* test version after fetching data */
-	} while ((src->version & 1) | (dst->version ^ src->version));
-
-	return dst->version;
-}
-
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
-	u64 product;
-#ifdef __i386__
-	u32 tmp1, tmp2;
-#endif
-
-	if (shift < 0)
-		delta >>= -shift;
-	else
-		delta <<= shift;
-
-#ifdef __i386__
-	__asm__ (
-		"mul  %5       ; "
-		"mov  %4,%%eax ; "
-		"mov  %%edx,%4 ; "
-		"mul  %5       ; "
-		"xor  %5,%5    ; "
-		"add  %4,%%eax ; "
-		"adc  %5,%%edx ; "
-		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
-		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif __x86_64__
-	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
-	return product;
-}
-
-static u64 get_nsec_offset(struct shadow_time_info *shadow)
-{
-	u64 now, delta;
-	now = native_read_tsc();
-	delta = now - shadow->tsc_timestamp;
-	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
-}
-
 static cycle_t xen_clocksource_read(void)
 {
-	struct shadow_time_info *shadow = &get_cpu_var(shadow_time);
+        struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
-	unsigned version;
-
-	do {
-		version = get_time_values_from_xen();
-		barrier();
-		ret = shadow->system_timestamp + get_nsec_offset(shadow);
-		barrier();
-	} while (version != __get_cpu_var(xen_vcpu)->time.version);
-
-	put_cpu_var(shadow_time);
 
+	src = &get_cpu_var(xen_vcpu)->time;
+	ret = pvclock_clocksource_read(src);
+	put_cpu_var(xen_vcpu);
 	return ret;
 }
 
 static void xen_read_wallclock(struct timespec *ts)
 {
-	const struct shared_info *s = HYPERVISOR_shared_info;
-	u32 version;
-	u64 delta;
-	struct timespec now;
-
-	/* get wallclock at system boot */
-	do {
-		version = s->wc_version;
-		rmb();		/* fetch version before time */
-		now.tv_sec  = s->wc_sec;
-		now.tv_nsec = s->wc_nsec;
-		rmb();		/* fetch time before checking version */
-	} while ((s->wc_version & 1) | (version ^ s->wc_version));
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
+        struct pvclock_vcpu_time_info *vcpu_time;
 
-	delta = xen_clocksource_read();	/* time since system boot */
-	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
-
-	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
-	now.tv_sec = delta;
-
-	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+	vcpu_time = &get_cpu_var(xen_vcpu)->time;
+	pvclock_read_wallclock(wall_clock, vcpu_time, ts);
+	put_cpu_var(xen_vcpu);
 }
 
 unsigned long xen_get_wallclock(void)
@@ -345,7 +240,6 @@ unsigned long xen_get_wallclock(void)
 	struct timespec ts;
 
 	xen_read_wallclock(&ts);
-
 	return ts.tv_sec;
 }
 
@@ -569,8 +463,6 @@ __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
 
-	get_time_values_from_xen();
-
 	clocksource_register(&xen_clocksource);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
-- 
cgit v1.2.2


From 50d0a0f987b83a8dadb1134d834e35ec410392b5 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 3 Jun 2008 16:17:31 +0200
Subject: KVM: Make kvm host use the paravirt clocksource structs

This patch updates the kvm host code to use the pvclock structs.
It also makes the paravirt clock compatible with Xen.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/kvm/x86.c | 75 ++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 62 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b08812d6b34c..63a77caa59f1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -492,8 +492,8 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	static int version;
-	struct kvm_wall_clock wc;
-	struct timespec wc_ts;
+	struct pvclock_wall_clock wc;
+	struct timespec now, sys, boot;
 
 	if (!wall_clock)
 		return;
@@ -502,10 +502,19 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 
-	wc_ts = current_kernel_time();
-	wc.wc_sec = wc_ts.tv_sec;
-	wc.wc_nsec = wc_ts.tv_nsec;
-	wc.wc_version = version;
+	/*
+	 * The guest calculates current wall clock time by adding
+	 * system time (updated by kvm_write_guest_time below) to the
+	 * wall clock specified here.  guest system time equals host
+	 * system time for us, thus we must fill in host boot time here.
+	 */
+	now = current_kernel_time();
+	ktime_get_ts(&sys);
+	boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+
+	wc.sec = boot.tv_sec;
+	wc.nsec = boot.tv_nsec;
+	wc.version = version;
 
 	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
 
@@ -513,6 +522,45 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 }
 
+static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
+{
+	uint32_t quotient, remainder;
+
+	/* Don't try to replace with do_div(), this one calculates
+	 * "(dividend << 32) / divisor" */
+	__asm__ ( "divl %4"
+		  : "=a" (quotient), "=d" (remainder)
+		  : "0" (0), "1" (dividend), "r" (divisor) );
+	return quotient;
+}
+
+static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+{
+	uint64_t nsecs = 1000000000LL;
+	int32_t  shift = 0;
+	uint64_t tps64;
+	uint32_t tps32;
+
+	tps64 = tsc_khz * 1000LL;
+	while (tps64 > nsecs*2) {
+		tps64 >>= 1;
+		shift--;
+	}
+
+	tps32 = (uint32_t)tps64;
+	while (tps32 <= (uint32_t)nsecs) {
+		tps32 <<= 1;
+		shift++;
+	}
+
+	hv_clock->tsc_shift = shift;
+	hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+
+	pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
+		 __FUNCTION__, tsc_khz, hv_clock->tsc_shift,
+		 hv_clock->tsc_to_system_mul);
+}
+
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {
 	struct timespec ts;
@@ -523,6 +571,11 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	if ((!vcpu->time_page))
 		return;
 
+	if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
+		kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = tsc_khz;
+	}
+
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
 	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
@@ -537,14 +590,14 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
-	 * state, we just write "2" at the end
+	 * state, we just increase by 2 at the end.
 	 */
-	vcpu->hv_clock.version = 2;
+	vcpu->hv_clock.version += 2;
 
 	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
 
 	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-		sizeof(vcpu->hv_clock));
+	       sizeof(vcpu->hv_clock));
 
 	kunmap_atomic(shared_kaddr, KM_USER0);
 
@@ -599,10 +652,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		/* ...but clean it before doing the actual write */
 		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.hv_clock.tsc_to_system_mul =
-					clocksource_khz2mult(tsc_khz, 22);
-		vcpu->arch.hv_clock.tsc_shift = 22;
-
 		down_read(&current->mm->mmap_sem);
 		vcpu->arch.time_page =
 				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
-- 
cgit v1.2.2


From f6e16d5ad463d15f285666f588cfe49495c692d9 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 3 Jun 2008 16:17:32 +0200
Subject: x86: KVM guest: Use the paravirt clocksource structs and functions

This patch updates the kvm host code to use the pvclock structs
and functions, thereby making it compatible with Xen.

The patch also fixes an initialization bug: on SMP systems the
per-cpu has two different locations early at boot and after CPU
bringup.  kvmclock must take that in account when registering the
physical address within the host.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 arch/x86/Kconfig           |  1 +
 arch/x86/kernel/kvmclock.c | 89 +++++++++++++++++-----------------------------
 2 files changed, 34 insertions(+), 56 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f94bca6ff47f..e0edaaa6920a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -383,6 +383,7 @@ config VMI
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on !(X86_VISWS || X86_VOYAGER)
 	help
 	  Turning on this option will allow you to run a paravirtualized clock
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 08a30986d472..87edf1ceb1df 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -18,6 +18,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/kvm_para.h>
+#include <asm/pvclock.h>
 #include <asm/arch_hooks.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
+static struct pvclock_wall_clock wall_clock;
 
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
-	int cpu = smp_processor_id();
-	u64 delta = native_read_tsc() - last_tsc;
-	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
-
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
@@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void);
  */
 static unsigned long kvm_get_wallclock(void)
 {
-	u32 wc_sec, wc_nsec;
-	u64 delta;
+	struct pvclock_vcpu_time_info *vcpu_time;
 	struct timespec ts;
-	int version, nsec;
 	int low, high;
 
 	low = (int)__pa(&wall_clock);
 	high = ((u64)__pa(&wall_clock) >> 32);
+	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
 
-	delta = kvm_clock_read();
+	vcpu_time = &get_cpu_var(hv_clock);
+	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+	put_cpu_var(hv_clock);
 
-	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
-	do {
-		version = wall_clock.wc_version;
-		rmb();
-		wc_sec = wall_clock.wc_sec;
-		wc_nsec = wall_clock.wc_nsec;
-		rmb();
-	} while ((wall_clock.wc_version != version) || (version & 1));
-
-	delta = kvm_clock_read() - delta;
-	delta += wc_nsec;
-	nsec = do_div(delta, NSEC_PER_SEC);
-	set_normalized_timespec(&ts, wc_sec + delta, nsec);
-	/*
-	 * Of all mechanisms of time adjustment I've tested, this one
-	 * was the champion!
-	 */
-	return ts.tv_sec + 1;
+	return ts.tv_sec;
 }
 
 static int kvm_set_wallclock(unsigned long now)
 {
-	return 0;
+	return -1;
 }
 
-/*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
- */
 static cycle_t kvm_clock_read(void)
 {
-	u64 last_tsc, now;
-	int cpu;
+	struct pvclock_vcpu_time_info *src;
+	cycle_t ret;
 
-	preempt_disable();
-	cpu = smp_processor_id();
-
-	last_tsc = get_clock(cpu, tsc_timestamp);
-	now = get_clock(cpu, system_time);
-
-	now += kvm_get_delta(last_tsc);
-	preempt_enable();
-
-	return now;
+	src = &get_cpu_var(hv_clock);
+	ret = pvclock_clocksource_read(src);
+	put_cpu_var(hv_clock);
+	return ret;
 }
+
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_read,
@@ -123,13 +88,14 @@ static struct clocksource kvm_clock = {
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(void)
+static int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
 	int low, high;
 	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
-
+	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
+	       cpu, high, low, txt);
 	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
 }
 
@@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void)
 	 * Now that the first cpu already had this clocksource initialized,
 	 * we shouldn't fail.
 	 */
-	WARN_ON(kvm_register_clock());
+	WARN_ON(kvm_register_clock("secondary cpu clock"));
 	/* ok, done with our trickery, call native */
 	setup_secondary_APIC_clock();
 }
 #endif
 
+#ifdef CONFIG_SMP
+void __init kvm_smp_prepare_boot_cpu(void)
+{
+	WARN_ON(kvm_register_clock("primary cpu clock"));
+	native_smp_prepare_boot_cpu();
+}
+#endif
+
 /*
  * After the clock is registered, the host will keep writing to the
  * registered memory location. If the guest happens to shutdown, this memory
@@ -174,13 +148,16 @@ void __init kvmclock_init(void)
 		return;
 
 	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_clock())
+		if (kvm_register_clock("boot clock"))
 			return;
 		pv_time_ops.get_wallclock = kvm_get_wallclock;
 		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
 #ifdef CONFIG_X86_LOCAL_APIC
 		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+#endif
+#ifdef CONFIG_SMP
+		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
 		machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-- 
cgit v1.2.2


From 08b882c627aeeeb3cfd3c4354f0d360d7949549d Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 04:30:01 -0700
Subject: paravirt: add hooks for ptep_modify_prot_start/commit

This patch adds paravirt-ops hooks in pv_mmu_ops for ptep_modify_prot_start and
ptep_modify_prot_commit.  This allows the hypervisor-specific backends to
implement these in some more efficient way.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/paravirt.c | 3 +++
 arch/x86/xen/enlighten.c   | 3 +++
 2 files changed, 6 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c98d54688180..f1ab0f727007 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -380,6 +380,9 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.pte_update = paravirt_nop,
 	.pte_update_defer = paravirt_nop,
 
+	.ptep_modify_prot_start = __ptep_modify_prot_start,
+	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
+
 #ifdef CONFIG_HIGHPTE
 	.kmap_atomic_pte = kmap_atomic,
 #endif
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 73fb0c4c150a..0b7553cbc529 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1138,6 +1138,9 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.set_pte_at = xen_set_pte_at,
 	.set_pmd = xen_set_pmd_hyper,
 
+	.ptep_modify_prot_start = __ptep_modify_prot_start,
+	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
+
 	.pte_val = xen_pte_val,
 	.pte_flags = native_pte_val,
 	.pgd_val = xen_pgd_val,
-- 
cgit v1.2.2


From e57778a1e30470c9f5b79e370511b9af29b59c48 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 04:30:02 -0700
Subject: xen: implement ptep_modify_prot_start/commit

Xen has a pte update function which will update a pte while preserving
its accessed and dirty bits.  This means that ptep_modify_prot_start() can be
implemented as a simple read of the pte value.  The hardware may
update the pte in the meantime, but ptep_modify_prot_commit() updates it while
preserving any changes that may have happened in the meantime.

The updates in ptep_modify_prot_commit() are batched if we're currently in lazy
mmu mode.

The mmu_update hypercall can take a batch of updates to perform, but
this code doesn't make particular use of that feature, in favour of
using generic multicall batching to get them all into the hypervisor.

The net effect of this is that each mprotect pte update turns from two
expensive trap-and-emulate faults into they hypervisor into a single
hypercall whose cost is amortized in a batched multicall.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/enlighten.c | 13 ++++++++++---
 arch/x86/xen/mmu.c       | 21 +++++++++++++++++++++
 arch/x86/xen/mmu.h       |  4 ++++
 3 files changed, 35 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b7553cbc529..bd74229081c3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -168,7 +168,9 @@ static void __init xen_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
 	       pv_info.name);
-	printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
+	printk(KERN_INFO "Hypervisor signature: %s%s\n",
+	       xen_start_info->magic,
+	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
@@ -1243,6 +1245,8 @@ asmlinkage void __init xen_start_kernel(void)
 
 	BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
 
+	xen_setup_features();
+
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
@@ -1252,14 +1256,17 @@ asmlinkage void __init xen_start_kernel(void)
 	pv_apic_ops = xen_apic_ops;
 	pv_mmu_ops = xen_mmu_ops;
 
+	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
+		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
+		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+	}
+
 	machine_ops = xen_machine_ops;
 
 #ifdef CONFIG_SMP
 	smp_ops = xen_smp_ops;
 #endif
 
-	xen_setup_features();
-
 	/* Get mfn list */
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
 		xen_build_dynamic_phys_to_machine();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 8132aa8c5d49..846dad7d54a5 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -323,6 +323,27 @@ out:
 		preempt_enable();
 }
 
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	/* Just return the pte as-is.  We preserve the bits on commit */
+	return *ptep;
+}
+
+void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep, pte_t pte)
+{
+	struct multicall_space mcs;
+	struct mmu_update *u;
+
+	mcs = xen_mc_entry(sizeof(*u));
+	u = mcs.args;
+	u->ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+	u->val = pte_val_ma(pte);
+	MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index e3dd09e25c63..297bf9f5b8bc 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -52,4 +52,8 @@ void xen_set_pud_hyper(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+				  pte_t *ptep, pte_t pte);
+
 #endif	/* _XEN_MMU_H */
-- 
cgit v1.2.2


From 400d34944c4ad82a817c06e570bc93b1114aa596 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Mon, 16 Jun 2008 04:30:03 -0700
Subject: xen: add mechanism to extend existing multicalls

Some Xen hypercalls accept an array of operations to work on.  In
general this is because its more efficient for the hypercall to the
work all at once rather than as separate hypercalls (even batched as a
multicall).

This patch adds a mechanism (xen_mc_extend_args()) to allocate more
argument space to the last-issued multicall, in order to extend its
argument list.

The user of this mechanism is xen/mmu.c, which uses it to extend the
args array of mmu_update.  This is particularly valuable when doing
the update for a large mprotect, which goes via
ptep_modify_prot_commit(), but it also manages to batch updates to
pgd/pmds as well.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/mmu.c        | 55 ++++++++++++++++++++++++++++++-----------------
 arch/x86/xen/multicalls.c | 40 ++++++++++++++++++++++++++++------
 arch/x86/xen/multicalls.h | 12 +++++++++++
 3 files changed, 81 insertions(+), 26 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 846dad7d54a5..f6b8225c2a0b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -230,18 +230,35 @@ static bool page_pinned(void *ptr)
 	return PagePinned(page);
 }
 
-void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+static void extend_mmu_update(const struct mmu_update *update)
 {
 	struct multicall_space mcs;
 	struct mmu_update *u;
 
-	preempt_disable();
+	mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
+
+	if (mcs.mc != NULL)
+		mcs.mc->args[1]++;
+	else {
+		mcs = __xen_mc_entry(sizeof(*u));
+		MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+	}
 
-	mcs = xen_mc_entry(sizeof(*u));
 	u = mcs.args;
-	u->ptr = virt_to_machine(ptr).maddr;
-	u->val = pmd_val_ma(val);
-	MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+	*u = *update;
+}
+
+void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+{
+	struct mmu_update u;
+
+	preempt_disable();
+
+	xen_mc_batch();
+
+	u.ptr = virt_to_machine(ptr).maddr;
+	u.val = pmd_val_ma(val);
+	extend_mmu_update(&u);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 
@@ -332,14 +349,13 @@ pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t
 void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte)
 {
-	struct multicall_space mcs;
-	struct mmu_update *u;
+	struct mmu_update u;
 
-	mcs = xen_mc_entry(sizeof(*u));
-	u = mcs.args;
-	u->ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
-	u->val = pte_val_ma(pte);
-	MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+	xen_mc_batch();
+
+	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+	u.val = pte_val_ma(pte);
+	extend_mmu_update(&u);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
@@ -396,16 +412,15 @@ pmdval_t xen_pmd_val(pmd_t pmd)
 
 void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 {
-	struct multicall_space mcs;
-	struct mmu_update *u;
+	struct mmu_update u;
 
 	preempt_disable();
 
-	mcs = xen_mc_entry(sizeof(*u));
-	u = mcs.args;
-	u->ptr = virt_to_machine(ptr).maddr;
-	u->val = pud_val_ma(val);
-	MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+	xen_mc_batch();
+
+	u.ptr = virt_to_machine(ptr).maddr;
+	u.val = pud_val_ma(val);
+	extend_mmu_update(&u);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 5791eb2e3750..3c63c4da7ed1 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -29,14 +29,14 @@
 #define MC_DEBUG	1
 
 #define MC_BATCH	32
-#define MC_ARGS		(MC_BATCH * 16 / sizeof(u64))
+#define MC_ARGS		(MC_BATCH * 16)
 
 struct mc_buffer {
 	struct multicall_entry entries[MC_BATCH];
 #if MC_DEBUG
 	struct multicall_entry debug[MC_BATCH];
 #endif
-	u64 args[MC_ARGS];
+	unsigned char args[MC_ARGS];
 	struct callback {
 		void (*fn)(void *);
 		void *data;
@@ -107,20 +107,48 @@ struct multicall_space __xen_mc_entry(size_t args)
 {
 	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
 	struct multicall_space ret;
-	unsigned argspace = (args + sizeof(u64) - 1) / sizeof(u64);
+	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
 	BUG_ON(preemptible());
-	BUG_ON(argspace > MC_ARGS);
+	BUG_ON(b->argidx > MC_ARGS);
 
 	if (b->mcidx == MC_BATCH ||
-	    (b->argidx + argspace) > MC_ARGS)
+	    (argidx + args) > MC_ARGS) {
 		xen_mc_flush();
+		argidx = roundup(b->argidx, sizeof(u64));
+	}
 
 	ret.mc = &b->entries[b->mcidx];
 	b->mcidx++;
+	ret.args = &b->args[argidx];
+	b->argidx = argidx + args;
+
+	BUG_ON(b->argidx > MC_ARGS);
+	return ret;
+}
+
+struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
+{
+	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct multicall_space ret = { NULL, NULL };
+
+	BUG_ON(preemptible());
+	BUG_ON(b->argidx > MC_ARGS);
+
+	if (b->mcidx == 0)
+		return ret;
+
+	if (b->entries[b->mcidx - 1].op != op)
+		return ret;
+
+	if ((b->argidx + size) > MC_ARGS)
+		return ret;
+
+	ret.mc = &b->entries[b->mcidx - 1];
 	ret.args = &b->args[b->argidx];
-	b->argidx += argspace;
+	b->argidx += size;
 
+	BUG_ON(b->argidx > MC_ARGS);
 	return ret;
 }
 
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 8bae996d99a3..858938241616 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -45,4 +45,16 @@ static inline void xen_mc_issue(unsigned mode)
 /* Set up a callback to be called when the current batch is flushed */
 void xen_mc_callback(void (*fn)(void *), void *data);
 
+/*
+ * Try to extend the arguments of the previous multicall command.  The
+ * previous command's op must match.  If it does, then it attempts to
+ * extend the argument space allocated to the multicall entry by
+ * arg_size bytes.
+ *
+ * The returned multicall_space will return with mc pointing to the
+ * command on success, or NULL on failure, and args pointing to the
+ * newly allocated space.
+ */
+struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
+
 #endif /* _XEN_MULTICALLS_H */
-- 
cgit v1.2.2


From fa3d319ac6f648dc51cb672a31f482c80a8c2457 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Thu, 26 Jun 2008 00:25:43 +0200
Subject: pci-gart_64.c: could we get better explanation?

Add better explanation to pci-gart.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Trivial patch monkey <trivial@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-gart_64.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index f505c3890358..f20c20a7853d 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -824,10 +824,10 @@ void __init gart_iommu_init(void)
 	wbinvd();
 
 	/*
-	 * Try to workaround a bug (thanks to BenH)
+	 * Try to workaround a bug (thanks to BenH):
 	 * Set unmapped entries to a scratch page instead of 0.
 	 * Any prefetches that hit unmapped entries won't get an bus abort
-	 * then.
+	 * then. (P2P bridge may be prefetching on DMA reads).
 	 */
 	scratch = get_zeroed_page(GFP_KERNEL);
 	if (!scratch)
-- 
cgit v1.2.2


From 0b1faeef5f9243bb5fc5713a34bbf1ceab0de562 Mon Sep 17 00:00:00 2001
From: Daniel J Blueman <daniel.blueman@gmail.com>
Date: Sun, 15 Jun 2008 12:32:15 +0100
Subject: x86: section/warning fixes

WARNING: arch/x86/mm/built-in.o(.text+0x3a1): Section mismatch in
reference from the function set_pte_phys() to the function
.init.text:spp_getpage()
The function set_pte_phys() references
the function __init spp_getpage().
This is often because set_pte_phys lacks a __init
annotation or the annotation of spp_getpage is wrong.

arch/x86/mm/init_64.c: In function 'early_memtest':
arch/x86/mm/init_64.c:520: warning: passing argument 2 of
'find_e820_area_size' from incompatible pointer type

Signed-off-by: Daniel J Blueman <daniel.blueman@gmail.com>
Cc: "Linus Torvalds" <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 156e6d7b0e32..f6d20be7a8f4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -135,7 +135,7 @@ static __init void *spp_getpage(void)
 	return ptr;
 }
 
-static void
+static __init void
 set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
 {
 	pgd_t *pgd;
@@ -214,7 +214,7 @@ void __init cleanup_highmap(void)
 }
 
 /* NOTE: this is meant to be run only at boot */
-void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+void __init __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
 {
 	unsigned long address = __fix_to_virt(idx);
 
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	u64 t_start, t_size;
+	unsigned long t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
+			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
 				t_start, t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
-- 
cgit v1.2.2


From 44974c8fc1d7047abe414562e0782320f4c1f511 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Date: Mon, 30 Jun 2008 08:11:22 +0900
Subject: x86 gart: remove unnecessary set_bit_string

iommu_area_alloc internally calls set_bit_string and set bits
properly. This set_bit_string is unnecessary.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: joerg.roedel@amd.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/pci-gart_64.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index f20c20a7853d..021f3c684a62 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -104,7 +104,6 @@ static unsigned long alloc_iommu(struct device *dev, int size)
 					  size, base_index, boundary_size, 0);
 	}
 	if (offset != -1) {
-		set_bit_string(iommu_gart_bitmap, offset, size);
 		next_bit = offset+size;
 		if (next_bit >= iommu_pages) {
 			next_bit = 0;
-- 
cgit v1.2.2


From fcb43042ef55d2f46b0efa5d7746967cef38f056 Mon Sep 17 00:00:00 2001
From: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Date: Tue, 24 Jun 2008 16:06:23 +0800
Subject: x86: fix cpu hotplug crash

Vegard Nossum reported crashes during cpu hotplug tests:

  http://marc.info/?l=linux-kernel&m=121413950227884&w=4

In function _cpu_up, the panic happens when calling
__raw_notifier_call_chain at the second time. Kernel doesn't panic when
calling it at the first time. If just say because of nr_cpu_ids, that's
not right.

By checking the source code, I found that function do_boot_cpu is the culprit.
Consider below call chain:
 _cpu_up=>__cpu_up=>smp_ops.cpu_up=>native_cpu_up=>do_boot_cpu.

So do_boot_cpu is called in the end. In do_boot_cpu, if
boot_error==true, cpu_clear(cpu, cpu_possible_map) is executed. So later
on, when _cpu_up calls __raw_notifier_call_chain at the second time to
report CPU_UP_CANCELED, because this cpu is already cleared from
cpu_possible_map, get_cpu_sysdev returns NULL.

Many resources are related to cpu_possible_map, so it's better not to
change it.

Below patch against 2.6.26-rc7 fixes it by removing the bit clearing in
cpu_possible_map.

Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/smpboot.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 56078d61c793..3e1cecedde42 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -996,7 +996,6 @@ do_rest:
 #endif
 		cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
 		cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
-		cpu_clear(cpu, cpu_possible_map);
 		cpu_clear(cpu, cpu_present_map);
 		per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
 	}
-- 
cgit v1.2.2


From 11dbc963a8f6128595d0f6ecf138dc369e144997 Mon Sep 17 00:00:00 2001
From: TAKADA Yoshihito <takada@mbf.nifty.com>
Date: Mon, 30 Jun 2008 13:44:45 +0900
Subject: ptrace GET/SET FPXREGS broken

When I update kernel 2.6.25 from 2.6.24, gdb does not work.
On 2.6.25, ptrace(PTRACE_GETFPXREGS, ...) returns ENODEV.

But 2.6.24 kernel's ptrace() returns EIO.
It is issue of compatibility.

I attached test program as pt.c and patch for fix it.

#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <signal.h>
#include <errno.h>
#include <sys/ptrace.h>
#include <sys/types.h>

struct user_fxsr_struct {
	unsigned short	cwd;
	unsigned short	swd;
	unsigned short	twd;
	unsigned short	fop;
	long	fip;
	long	fcs;
	long	foo;
	long	fos;
	long	mxcsr;
	long	reserved;
	long	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
	long	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
	long	padding[56];
};

int main(void)
{
  pid_t pid;

  pid = fork();

  switch(pid){
  case -1:/*  error */
    break;
  case 0:/*  child */
    child();
    break;
  default:
    parent(pid);
    break;
  }
  return 0;
}

int child(void)
{
  ptrace(PTRACE_TRACEME);
  kill(getpid(), SIGSTOP);
  sleep(10);
  return 0;
}
int parent(pid_t pid)
{
  int ret;
  struct user_fxsr_struct fpxregs;

  ret = ptrace(PTRACE_GETFPXREGS, pid, 0, &fpxregs);
  if(ret < 0){
    printf("%d: %s.\n", errno, strerror(errno));
  }
  kill(pid, SIGCONT);
  wait(pid);
  return 0;
}

/* in the kerel, at kernel/i387.c get_fpxregs() */

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/i387.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index eb9ddd8efb82..95e80e5033c3 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -162,7 +162,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -ENODEV;
+		return -EIO;
 
 	ret = init_fpu(target);
 	if (ret)
@@ -179,7 +179,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -ENODEV;
+		return -EIO;
 
 	ret = init_fpu(target);
 	if (ret)
-- 
cgit v1.2.2


From efac41894df57d32b483ac622d03541b5b2692c0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Jul 2008 08:56:32 +0200
Subject: x86: fix NODES_SHIFT Kconfig range

commit 4323838215184f5a2f081e0d17b8d60731b03164
       x86: change size of node ids from u8 to s16

set the range for NODES_SHIFT to 1..15.

The possible range is 1..9

Fixes Bugzilla #10726

Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 52e18e6d2ba0..8a07f417f5f4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -961,8 +961,8 @@ config NUMA_EMU
 	  number of nodes. This is only useful for debugging.
 
 config NODES_SHIFT
-	int "Max num nodes shift(1-15)"
-	range 1 15  if X86_64
+	int "Max num nodes shift(1-9)"
+	range 1 9  if X86_64
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
-- 
cgit v1.2.2


From 216705d2720dedf630b55d641737f430ead0c228 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hugh@veritas.com>
Date: Wed, 2 Jul 2008 22:48:03 +0100
Subject: x86: fix Intel Mac booting with EFI

Fedora reports that mem_init()'s zap_low_mappings(), extended to SMP in
61165d7a035f6571c7576e7f51e7230157724c8d x86: fix app crashes after SMP
resume causes 32-bit Intel Mac machines to reboot very early when
booting with EFI.

The EFI code appears to manage low mappings for itself when needed; but
like many before it, confuses PSE with PAE.  So it has only been mapping
half the space it needed when PSE but not PAE.  This remained unnoticed
until we moved the SMP zap_low_mappings() before
efi_enter_virtual_mode().  Presumably could have been noticed years ago
if anyone ran a UP kernel on such machines?

Reported-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Glauber Costa <gcosta@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Peter Jones <pjones@redhat.com>
---
 arch/x86/kernel/efi_32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c
index 5d23d85624d4..4b63c8e1f13b 100644
--- a/arch/x86/kernel/efi_32.c
+++ b/arch/x86/kernel/efi_32.c
@@ -49,13 +49,13 @@ void efi_call_phys_prelog(void)
 	local_irq_save(efi_rt_eflags);
 
 	/*
-	 * If I don't have PSE, I should just duplicate two entries in page
-	 * directory. If I have PSE, I just need to duplicate one entry in
+	 * If I don't have PAE, I should just duplicate two entries in page
+	 * directory. If I have PAE, I just need to duplicate one entry in
 	 * page directory.
 	 */
 	cr4 = read_cr4();
 
-	if (cr4 & X86_CR4_PSE) {
+	if (cr4 & X86_CR4_PAE) {
 		efi_bak_pg_dir_pointer[0].pgd =
 		    swapper_pg_dir[pgd_index(0)].pgd;
 		swapper_pg_dir[0].pgd =
@@ -93,7 +93,7 @@ void efi_call_phys_epilog(void)
 
 	cr4 = read_cr4();
 
-	if (cr4 & X86_CR4_PSE) {
+	if (cr4 & X86_CR4_PAE) {
 		swapper_pg_dir[pgd_index(0)].pgd =
 		    efi_bak_pg_dir_pointer[0].pgd;
 	} else {
-- 
cgit v1.2.2


From 27df66a406a171308b138bd84938cb735392e15c Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Thu, 3 Jul 2008 10:14:10 +0200
Subject: arch/x86/mm/init_64.c: early_memtest(): fix types

fix this warning:

arch/x86/mm/init_64.c: In function 'early_memtest':
arch/x86/mm/init_64.c:524: warning: passing argument 2 of 'find_e820_area_size' from incompatible pointer type

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_64.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f6d20be7a8f4..819dad973b13 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	unsigned long t_start, t_size;
+	u64 t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,8 +525,9 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
-				t_start, t_start + t_size, pattern);
+			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
+				(unsigned long long)t_start,
+				(unsigned long long)t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
 
-- 
cgit v1.2.2


From bc4e0f9ae2b1b133d36c1392d0145d2997cff272 Mon Sep 17 00:00:00 2001
From: Ben Castricum <lk0806@bencastricum.nl>
Date: Tue, 10 Jun 2008 13:15:12 +0200
Subject: x86: microcode: cosmetic changes

First announce ourself, then start working. Currently this module reports
itself when all is completed which is not most modules do. Plus some
cosmetic/whitespace cleanups.

Signed-off-by: Ben Castricum <lk0806@bencastricum.nl>
Cc: trivial@kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/microcode.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 69729e38b78a..9758fea87c5b 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -5,13 +5,14 @@
  *		      2006	Shaohua Li <shaohua.li@intel.com>
  *
  *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II, 
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
  *	Pentium III, Xeon, Pentium 4, etc.
  *
- *	Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual, 
- *	Order Number 245472 or free download from:
- *		
- *	http://developer.intel.com/design/pentium4/manuals/245472.htm
+ *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ *	Software Developer's Manual
+ *	Order Number 253668 or free download from:
+ *
+ *	http://developer.intel.com/design/pentium4/manuals/253668.htm
  *
  *	For more information, go to http://www.urbanmyth.org/microcode
  *
@@ -58,12 +59,12 @@
  *		nature of implementation.
  *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
  *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, 
+ *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
  *		Jun Nakajima <jun.nakajima@intel.com>
  *		Support for the microcode updates in the new format.
  *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
  *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode 
+ *		because we no longer hold a copy of applied microcode
  *		in kernel memory.
  *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
@@ -320,11 +321,11 @@ static void apply_microcode(int cpu)
 		return;
 
 	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);          
+	spin_lock_irqsave(&microcode_update_lock, flags);
 
 	/* write microcode via MSR 0x79 */
 	wrmsr(MSR_IA32_UCODE_WRITE,
-		(unsigned long) uci->mc->bits, 
+		(unsigned long) uci->mc->bits,
 		(unsigned long) uci->mc->bits >> 16 >> 16);
 	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
 
@@ -341,7 +342,7 @@ static void apply_microcode(int cpu)
 		return;
 	}
 	printk(KERN_INFO "microcode: CPU%d updated from revision "
-	       "0x%x to 0x%x, date = %08x \n", 
+	       "0x%x to 0x%x, date = %08x \n",
 	       cpu_num, uci->rev, val[1], uci->mc->hdr.date);
 	uci->rev = val[1];
 }
@@ -534,7 +535,7 @@ static int cpu_request_microcode(int cpu)
 		c->x86, c->x86_model, c->x86_mask);
 	error = request_firmware(&firmware, name, &microcode_pdev->dev);
 	if (error) {
-		pr_debug("microcode: ucode data file %s load failed\n", name);
+		pr_debug("microcode: data file %s load failed\n", name);
 		return error;
 	}
 	buf = firmware->data;
@@ -805,6 +806,9 @@ static int __init microcode_init (void)
 {
 	int error;
 
+	printk(KERN_INFO
+		"IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
+
 	error = microcode_dev_init();
 	if (error)
 		return error;
@@ -825,9 +829,6 @@ static int __init microcode_init (void)
 	}
 
 	register_hotcpu_notifier(&mc_cpu_notifier);
-
-	printk(KERN_INFO 
-		"IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
 	return 0;
 }
 
-- 
cgit v1.2.2


From 2d144e63098be47c21ad59d68a4fd17bd73a3aaf Mon Sep 17 00:00:00 2001
From: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Date: Tue, 24 Jun 2008 17:12:56 -0700
Subject: x86, mce_64.c: mce_cpu_quirks being ignored

Quirks getting ignored was a bug. Below patch fixes the bug, until
we have the dynamic banks support.

Sysfs choice configuration should not have any issues with the earlier patch
as we look for NR_SYSFS_BANKS in do_machine_check().

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Max Asbock <masbock@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mcheck/mce_64.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 8c8299ce7ad4..501ca1cea27d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -463,7 +463,11 @@ static void mce_init(void *dummy)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 
 	for (i = 0; i < banks; i++) {
-		wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
+		if (i < NR_SYSFS_BANKS)
+			wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+		else
+			wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
+
 		wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
 	}
 }
-- 
cgit v1.2.2


From 95c60b08c6af6db2165837139da10f593462d51c Mon Sep 17 00:00:00 2001
From: Gustavo Fernando Padovan <gustavo@las.ic.unicamp.br>
Date: Wed, 25 Jun 2008 04:03:19 -0300
Subject: x86: remove unnecessary #ifdef CONFIG_X86_32...#else

Remove the #ifdef conditional because this comparison is already done in
user_mode_vm().

Signed-off-by: Gustavo F. Padovan <gustavo@las.ic.unicamp.br>
Cc: akpm@osdl.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/fault.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8bcb6f40ccb6..1e64795714c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -55,11 +55,7 @@ static inline int notify_page_fault(struct pt_regs *regs)
 	int ret = 0;
 
 	/* kprobe_running() needs smp_processor_id() */
-#ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
-#else
-	if (!user_mode(regs)) {
-#endif
 		preempt_disable();
 		if (kprobe_running() && kprobe_fault_handler(regs, 14))
 			ret = 1;
-- 
cgit v1.2.2


From d8355aca23863be659ec5b7e0393cfbfa91ec221 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Thu, 3 Jul 2008 22:10:18 -0700
Subject: xen: fix address truncation in pte mfn<->pfn conversion

When converting the page number in a pte/pmd/pud/pgd between
machine and pseudo-physical addresses, the converted result was
being truncated at 32-bits.  This caused failures on machines
with more than 4G of physical memory.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: "Christopher S. Aker" <caker@theshore.net>
Cc: Ian Campbell <Ian.Campbell@eu.citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/xen/mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index df40bf74ea75..4e527e7893a8 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -185,7 +185,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & ~PTE_MASK;
-		val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
 	}
 
 	return val;
@@ -196,7 +196,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 	if (val & _PAGE_PRESENT) {
 		unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & ~PTE_MASK;
-		val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+		val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
 	}
 
 	return val;
-- 
cgit v1.2.2


From 4b4f7280d7fd1feeff134c2cf2db32fd583b6c29 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Tue, 24 Jun 2008 23:03:48 +0200
Subject: x86 ACPI: normalize segment descriptor register on resume

Some Dell laptops enter resume with apparent garbage in the segment
descriptor registers (almost certainly the result of a botched
transition from protected to real mode.)  The only way to clean that
up is to enter protected mode ourselves and clean out the descriptor
registers.

This fixes resume on Dell XPS M1210 and Dell D620.

Reference: http://bugzilla.kernel.org/show_bug.cgi?id=10927

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: pm list <linux-pm@lists.linux-foundation.org>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/acpi/realmode/wakeup.S | 38 +++++++++++++++++++++++++++++++++-
 arch/x86/kernel/acpi/realmode/wakeup.h |  5 +++++
 arch/x86/kernel/acpi/sleep.c           | 16 +++++++++++++-
 3 files changed, 57 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index f9b77fb37e5b..3355973b12ac 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -5,6 +5,7 @@
 #include <asm/msr-index.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/processor-flags.h>
 
 	.code16
 	.section ".header", "a"
@@ -24,6 +25,11 @@ pmode_gdt:	.quad	0
 realmode_flags:	.long	0
 real_magic:	.long	0
 trampoline_segment:	.word 0
+_pad1:		.byte	0
+wakeup_jmp:	.byte	0xea	/* ljmpw */
+wakeup_jmp_off:	.word	3f
+wakeup_jmp_seg:	.word	0
+wakeup_gdt:	.quad	0, 0, 0
 signature:	.long	0x51ee1111
 
 	.text
@@ -34,11 +40,34 @@ _start:
 	cli
 	cld
 
+	/* Apparently some dimwit BIOS programmers don't know how to
+	   program a PM to RM transition, and we might end up here with
+	   junk in the data segment descriptor registers.  The only way
+	   to repair that is to go into PM and fix it ourselves... */
+	movw	$16, %cx
+	lgdtl	%cs:wakeup_gdt
+	movl	%cr0, %eax
+	orb	$X86_CR0_PE, %al
+	movl	%eax, %cr0
+	jmp	1f
+1:	ljmpw	$8, $2f
+2:
+	movw	%cx, %ds
+	movw	%cx, %es
+	movw	%cx, %ss
+	movw	%cx, %fs
+	movw	%cx, %gs
+
+	andb	$~X86_CR0_PE, %al
+	movl	%eax, %cr0
+	jmp	wakeup_jmp
+3:
 	/* Set up segments */
 	movw	%cs, %ax
 	movw	%ax, %ds
 	movw	%ax, %es
 	movw	%ax, %ss
+	lidtl	wakeup_idt
 
 	movl	$wakeup_stack_end, %esp
 
@@ -98,7 +127,14 @@ bogus_real_magic:
 	jmp	1b
 
 	.data
-	.balign	4
+	.balign	8
+
+	/* This is the standard real-mode IDT */
+wakeup_idt:
+	.word	0xffff		/* limit */
+	.long	0		/* address */
+	.word	0
+
 	.globl	HEAP, heap_end
 HEAP:
 	.long	wakeup_heap
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h
index ef8166fe8020..69d38d0b2b64 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/kernel/acpi/realmode/wakeup.h
@@ -24,6 +24,11 @@ struct wakeup_header {
 	u32 realmode_flags;
 	u32 real_magic;
 	u16 trampoline_segment;	/* segment with trampoline code, 64-bit only */
+	u8  _pad1;
+	u8  wakeup_jmp;
+	u16 wakeup_jmp_off;
+	u16 wakeup_jmp_seg;
+	u64 wakeup_gdt[3];
 	u32 signature;		/* To check we have correct structure */
 } __attribute__((__packed__));
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index afc25ee9964b..36af01f029ed 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -50,6 +50,20 @@ int acpi_save_state_mem(void)
 
 	header->video_mode = saved_video_mode;
 
+	header->wakeup_jmp_seg = acpi_wakeup_address >> 4;
+	/* GDT[0]: GDT self-pointer */
+	header->wakeup_gdt[0] =
+		(u64)(sizeof(header->wakeup_gdt) - 1) +
+		((u64)(acpi_wakeup_address +
+			((char *)&header->wakeup_gdt - (char *)acpi_realmode))
+				<< 16);
+	/* GDT[1]: real-mode-like code segment */
+	header->wakeup_gdt[1] = (0x009bULL << 40) +
+		((u64)acpi_wakeup_address << 16) + 0xffff;
+	/* GDT[2]: real-mode-like data segment */
+	header->wakeup_gdt[2] = (0x0093ULL << 40) +
+		((u64)acpi_wakeup_address << 16) + 0xffff;
+
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
@@ -111,7 +125,7 @@ void __init acpi_reserve_bootmem(void)
 		return;
 	}
 
-	acpi_wakeup_address = acpi_realmode;
+	acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
 }
 
 
-- 
cgit v1.2.2


From 64e83b5a919a65eb35b63dd7e07c188379ff8ce6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Sat, 5 Jul 2008 00:05:30 +0200
Subject: x86 ACPI: fix resume from suspend to RAM on uniprocessor x86-64

Since the trampoline code is now used for ACPI resume from suspend to RAM,
the trampoline page tables have to be fixed up during boot not only on SMP
systems, but also on UP systems that use the trampoline.

Reference: http://bugzilla.kernel.org/show_bug.cgi?id=10923

Reported-by: Dionisus Torimens <djtm@gmx.net>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: pm list <linux-pm@lists.linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/head_64.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 10a1955bb1d1..b817974ef942 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -128,7 +128,7 @@ ident_complete:
 	/* Fixup phys_base */
 	addq	%rbp, phys_base(%rip)
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_X86_TRAMPOLINE
 	addq	%rbp, trampoline_level4_pgt + 0(%rip)
 	addq	%rbp, trampoline_level4_pgt + (511*8)(%rip)
 #endif
-- 
cgit v1.2.2


From aa276e1cafb3ce9d01d1e837bcd67e92616013ac Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 19:15:00 +0200
Subject: x86, clockevents: add C1E aware idle function

C1E on AMD machines is like C3 but without control from the OS. Up to
now we disabled the local apic timer for those machines as it stops
when the CPU goes into C1E. This excludes those machines from high
resolution timers / dynamic ticks, which hurts especially X2 based
laptops.

The current boot time C1E detection has another, more serious flaw
as well: some BIOSes do not enable C1E until the ACPI processor module
is loaded. This causes systems to stop working after that point.

To work nicely with C1E enabled machines we use a separate idle
function, which checks on idle entry whether C1E was enabled in the
Interrupt Pending Message MSR. This allows us to do timer broadcasting
for C1E and covers the late enablement of C1E as well.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_32.c    |  5 ++--
 arch/x86/kernel/apic_64.c    | 26 +----------------
 arch/x86/kernel/cpu/amd.c    | 30 --------------------
 arch/x86/kernel/cpu/amd_64.c | 25 -----------------
 arch/x86/kernel/process.c    | 66 ++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 69 insertions(+), 83 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6c..c44206e731d4 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -64,9 +64,8 @@ static int enable_local_apic __initdata;
 
 /* Local APIC timer verification ok */
 static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
-   or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc29..a5cc8447cf4d 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -43,7 +43,7 @@
 #include <mach_ipi.h>
 #include <mach_apic.h>
 
-int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
 
@@ -422,32 +422,8 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-static void __cpuinit check_boot_apic_timer_broadcast(void)
-{
-	if (!disable_apic_timer ||
-	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
-		return;
-
-	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
-	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-			   &boot_cpu_physical_apicid);
-	local_irq_disable();
-}
-
 void __cpuinit setup_secondary_APIC_clock(void)
 {
-	check_boot_apic_timer_broadcast();
 	setup_APIC_timer();
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e76b49e7a916..acc891ae5901 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -24,31 +24,6 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
-#ifdef CONFIG_X86_LOCAL_APIC
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-#endif
-
 int force_mwait __cpuinitdata;
 
 static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
@@ -285,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			num_cache_leaves = 3;
 	}
 
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (amd_apic_timer_broken(c))
-		local_apic_timer_disabled = 1;
-#endif
-
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
 		clear_cpu_cap(c, X86_FEATURE_MCE);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index f5fc161d8f2a..f8d20588bde9 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -110,28 +110,6 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-
 void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd_mc(c);
@@ -212,9 +190,6 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		amd_enable_pci_ext_cfg(c);
 
-	if (amd_apic_timer_broken(c))
-		disable_apic_timer = 1;
-
 	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
 		unsigned long long tseg;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9fea14607dfe..68ad3539b143 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/pm.h>
+#include <linux/clockchips.h>
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -219,6 +220,68 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
+/*
+ * Check for AMD CPUs, which have potentially C1E support
+ */
+static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
+{
+	if (c->x86_vendor != X86_VENDOR_AMD)
+		return 0;
+
+	if (c->x86 < 0x0F)
+		return 0;
+
+	/* Family 0x0f models < rev F do not have C1E */
+	if (c->x86 == 0x0f && c->x86_model < 0x40)
+		return 0;
+
+	return 1;
+}
+
+/*
+ * C1E aware idle routine. We check for C1E active in the interrupt
+ * pending message MSR. If we detect C1E, then we handle it the same
+ * way as C3 power states (local apic timer and TSC stop)
+ */
+static void c1e_idle(void)
+{
+	static cpumask_t c1e_mask = CPU_MASK_NONE;
+	static int c1e_detected;
+
+	if (need_resched())
+		return;
+
+	if (!c1e_detected) {
+		u32 lo, hi;
+
+		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+			c1e_detected = 1;
+			mark_tsc_unstable("TSC halt in C1E");
+			printk(KERN_INFO "System has C1E enabled\n");
+		}
+	}
+
+	if (c1e_detected) {
+		int cpu = smp_processor_id();
+
+		if (!cpu_isset(cpu, c1e_mask)) {
+			cpu_set(cpu, c1e_mask);
+			/* Force broadcast so ACPI can not interfere */
+			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+					   &cpu);
+			printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
+			       cpu);
+		}
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+		default_idle();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
+	} else
+		default_idle();
+}
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_SMP
@@ -236,6 +299,9 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		 */
 		printk(KERN_INFO "using mwait in idle threads.\n");
 		pm_idle = mwait_idle;
+	} else if (check_c1e_idle(c)) {
+		printk(KERN_INFO "using C1E aware idle routine\n");
+		pm_idle = c1e_idle;
 	} else
 		pm_idle = default_idle;
 }
-- 
cgit v1.2.2


From 0beefa208bb3a9e581a60125703409ebe6f7fa53 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 17 Jun 2008 09:12:03 +0200
Subject: x86: add C1E aware idle function, fix

On Tue, 17 Jun 2008, Rafael J. Wysocki wrote:
>
> BTW, with the C1E patches reverted I don't get the
> WARNING: at /home/rafael/src/linux-next/kernel/smp.c:215 smp_call_function_single+0x3d/0xa2
> in the log.  Thomas?

The BROADCAST_FORCE notification uses smp_function_call and therefor
must be run with interrupts enabled.

While at it, add a comment for the BROADCAST_EXIT notifier as well.

Reported-and-bisected-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 68ad3539b143..4061d63aabe7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -267,17 +267,29 @@ static void c1e_idle(void)
 
 		if (!cpu_isset(cpu, c1e_mask)) {
 			cpu_set(cpu, c1e_mask);
-			/* Force broadcast so ACPI can not interfere */
+			/*
+			 * Force broadcast so ACPI can not interfere. Needs
+			 * to run with interrupts enabled as it uses
+			 * smp_function_call.
+			 */
+			local_irq_enable();
 			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
 					   &cpu);
 			printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
 			       cpu);
+			local_irq_disable();
 		}
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+
 		default_idle();
-		local_irq_disable();
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		local_irq_enable();
+
+		/*
+		 * The switch back from broadcast mode needs to be
+		 * called with interrupts disabled.
+		 */
+		 local_irq_disable();
+		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		 local_irq_enable();
 	} else
 		default_idle();
 }
-- 
cgit v1.2.2


From 24bfdca7b7da971ef9a483303a096ac6d4b3a02c Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Thu, 12 Jun 2008 20:19:22 +0200
Subject: x86/pci: Renaming k8-bus_64.c to amd_bus.c

The name fits better since this is code not only for K8.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/pci/Makefile_64 |   2 +-
 arch/x86/pci/amd_bus.c   | 528 +++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/pci/k8-bus_64.c | 528 -----------------------------------------------
 3 files changed, 529 insertions(+), 529 deletions(-)
 create mode 100644 arch/x86/pci/amd_bus.c
 delete mode 100644 arch/x86/pci/k8-bus_64.c

(limited to 'arch/x86')

diff --git a/arch/x86/pci/Makefile_64 b/arch/x86/pci/Makefile_64
index 8fbd19832cf6..fd47068c95de 100644
--- a/arch/x86/pci/Makefile_64
+++ b/arch/x86/pci/Makefile_64
@@ -13,5 +13,5 @@ obj-y			+= legacy.o irq.o common.o early.o
 # mmconfig has a 64bit special
 obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_64.o direct.o mmconfig-shared.o
 
-obj-y		+= k8-bus_64.o
+obj-y		+= amd_bus.o
 
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
new file mode 100644
index 000000000000..5c2799c20e47
--- /dev/null
+++ b/arch/x86/pci/amd_bus.c
@@ -0,0 +1,528 @@
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <asm/pci-direct.h>
+#include <asm/mpspec.h>
+#include <linux/cpumask.h>
+#include <linux/topology.h>
+
+/*
+ * This discovers the pcibus <-> node mapping on AMD K8.
+ * also get peer root bus resource for io,mmio
+ */
+
+
+/*
+ * sub bus (transparent) will use entres from 3 to store extra from root,
+ * so need to make sure have enought slot there, increase PCI_BUS_NUM_RESOURCES?
+ */
+#define RES_NUM 16
+struct pci_root_info {
+	char name[12];
+	unsigned int res_num;
+	struct resource res[RES_NUM];
+	int bus_min;
+	int bus_max;
+	int node;
+	int link;
+};
+
+/* 4 at this time, it may become to 32 */
+#define PCI_ROOT_NR 4
+static int pci_root_num;
+static struct pci_root_info pci_root_info[PCI_ROOT_NR];
+
+#ifdef CONFIG_NUMA
+
+#define BUS_NR 256
+
+static int mp_bus_to_node[BUS_NR];
+
+void set_mp_bus_to_node(int busnum, int node)
+{
+	if (busnum >= 0 &&  busnum < BUS_NR)
+		mp_bus_to_node[busnum] = node;
+}
+
+int get_mp_bus_to_node(int busnum)
+{
+	int node = -1;
+
+	if (busnum < 0 || busnum > (BUS_NR - 1))
+		return node;
+
+	node = mp_bus_to_node[busnum];
+
+	/*
+	 * let numa_node_id to decide it later in dma_alloc_pages
+	 * if there is no ram on that node
+	 */
+	if (node != -1 && !node_online(node))
+		node = -1;
+
+	return node;
+}
+#endif
+
+void set_pci_bus_resources_arch_default(struct pci_bus *b)
+{
+	int i;
+	int j;
+	struct pci_root_info *info;
+
+	/* if only one root bus, don't need to anything */
+	if (pci_root_num < 2)
+		return;
+
+	for (i = 0; i < pci_root_num; i++) {
+		if (pci_root_info[i].bus_min == b->number)
+			break;
+	}
+
+	if (i == pci_root_num)
+		return;
+
+	info = &pci_root_info[i];
+	for (j = 0; j < info->res_num; j++) {
+		struct resource *res;
+		struct resource *root;
+
+		res = &info->res[j];
+		b->resource[j] = res;
+		if (res->flags & IORESOURCE_IO)
+			root = &ioport_resource;
+		else
+			root = &iomem_resource;
+		insert_resource(root, res);
+	}
+}
+
+#define RANGE_NUM 16
+
+struct res_range {
+	size_t start;
+	size_t end;
+};
+
+static void __init update_range(struct res_range *range, size_t start,
+				size_t end)
+{
+	int i;
+	int j;
+
+	for (j = 0; j < RANGE_NUM; j++) {
+		if (!range[j].end)
+			continue;
+
+		if (start <= range[j].start && end >= range[j].end) {
+			range[j].start = 0;
+			range[j].end = 0;
+			continue;
+		}
+
+		if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
+			range[j].start = end + 1;
+			continue;
+		}
+
+
+		if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
+			range[j].end = start - 1;
+			continue;
+		}
+
+		if (start > range[j].start && end < range[j].end) {
+			/* find the new spare */
+			for (i = 0; i < RANGE_NUM; i++) {
+				if (range[i].end == 0)
+					break;
+			}
+			if (i < RANGE_NUM) {
+				range[i].end = range[j].end;
+				range[i].start = end + 1;
+			} else {
+				printk(KERN_ERR "run of slot in ranges\n");
+			}
+			range[j].end = start - 1;
+			continue;
+		}
+	}
+}
+
+static void __init update_res(struct pci_root_info *info, size_t start,
+			      size_t end, unsigned long flags, int merge)
+{
+	int i;
+	struct resource *res;
+
+	if (!merge)
+		goto addit;
+
+	/* try to merge it with old one */
+	for (i = 0; i < info->res_num; i++) {
+		size_t final_start, final_end;
+		size_t common_start, common_end;
+
+		res = &info->res[i];
+		if (res->flags != flags)
+			continue;
+
+		common_start = max((size_t)res->start, start);
+		common_end = min((size_t)res->end, end);
+		if (common_start > common_end + 1)
+			continue;
+
+		final_start = min((size_t)res->start, start);
+		final_end = max((size_t)res->end, end);
+
+		res->start = final_start;
+		res->end = final_end;
+		return;
+	}
+
+addit:
+
+	/* need to add that */
+	if (info->res_num >= RES_NUM)
+		return;
+
+	res = &info->res[info->res_num];
+	res->name = info->name;
+	res->flags = flags;
+	res->start = start;
+	res->end = end;
+	res->child = NULL;
+	info->res_num++;
+}
+
+struct pci_hostbridge_probe {
+	u32 bus;
+	u32 slot;
+	u32 vendor;
+	u32 device;
+};
+
+static struct pci_hostbridge_probe pci_probes[] __initdata = {
+	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1100 },
+	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 },
+	{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
+	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 },
+};
+
+static u64 __initdata fam10h_mmconf_start;
+static u64 __initdata fam10h_mmconf_end;
+static void __init get_pci_mmcfg_amd_fam10h_range(void)
+{
+	u32 address;
+	u64 base, msr;
+	unsigned segn_busn_bits;
+
+	/* assume all cpus from fam10h have mmconf */
+        if (boot_cpu_data.x86 < 0x10)
+		return;
+
+	address = MSR_FAM10H_MMIO_CONF_BASE;
+	rdmsrl(address, msr);
+
+	/* mmconfig is not enable */
+	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+		return;
+
+	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+	fam10h_mmconf_start = base;
+	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
+}
+
+/**
+ * early_fill_mp_bus_to_node()
+ * called before pcibios_scan_root and pci_scan_bus
+ * fills the mp_bus_to_cpumask array based according to the LDT Bus Number
+ * Registers found in the K8 northbridge
+ */
+static int __init early_fill_mp_bus_info(void)
+{
+	int i;
+	int j;
+	unsigned bus;
+	unsigned slot;
+	int found;
+	int node;
+	int link;
+	int def_node;
+	int def_link;
+	struct pci_root_info *info;
+	u32 reg;
+	struct resource *res;
+	size_t start;
+	size_t end;
+	struct res_range range[RANGE_NUM];
+	u64 val;
+	u32 address;
+
+#ifdef CONFIG_NUMA
+	for (i = 0; i < BUS_NR; i++)
+		mp_bus_to_node[i] = -1;
+#endif
+
+	if (!early_pci_allowed())
+		return -1;
+
+	found = 0;
+	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
+		u32 id;
+		u16 device;
+		u16 vendor;
+
+		bus = pci_probes[i].bus;
+		slot = pci_probes[i].slot;
+		id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID);
+
+		vendor = id & 0xffff;
+		device = (id>>16) & 0xffff;
+		if (pci_probes[i].vendor == vendor &&
+		    pci_probes[i].device == device) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return 0;
+
+	pci_root_num = 0;
+	for (i = 0; i < 4; i++) {
+		int min_bus;
+		int max_bus;
+		reg = read_pci_config(bus, slot, 1, 0xe0 + (i << 2));
+
+		/* Check if that register is enabled for bus range */
+		if ((reg & 7) != 3)
+			continue;
+
+		min_bus = (reg >> 16) & 0xff;
+		max_bus = (reg >> 24) & 0xff;
+		node = (reg >> 4) & 0x07;
+#ifdef CONFIG_NUMA
+		for (j = min_bus; j <= max_bus; j++)
+			mp_bus_to_node[j] = (unsigned char) node;
+#endif
+		link = (reg >> 8) & 0x03;
+
+		info = &pci_root_info[pci_root_num];
+		info->bus_min = min_bus;
+		info->bus_max = max_bus;
+		info->node = node;
+		info->link = link;
+		sprintf(info->name, "PCI Bus #%02x", min_bus);
+		pci_root_num++;
+	}
+
+	/* get the default node and link for left over res */
+	reg = read_pci_config(bus, slot, 0, 0x60);
+	def_node = (reg >> 8) & 0x07;
+	reg = read_pci_config(bus, slot, 0, 0x64);
+	def_link = (reg >> 8) & 0x03;
+
+	memset(range, 0, sizeof(range));
+	range[0].end = 0xffff;
+	/* io port resource */
+	for (i = 0; i < 4; i++) {
+		reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
+		if (!(reg & 3))
+			continue;
+
+		start = reg & 0xfff000;
+		reg = read_pci_config(bus, slot, 1, 0xc4 + (i << 3));
+		node = reg & 0x07;
+		link = (reg >> 4) & 0x03;
+		end = (reg & 0xfff000) | 0xfff;
+
+		/* find the position */
+		for (j = 0; j < pci_root_num; j++) {
+			info = &pci_root_info[j];
+			if (info->node == node && info->link == link)
+				break;
+		}
+		if (j == pci_root_num)
+			continue; /* not found */
+
+		info = &pci_root_info[j];
+		printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
+		       node, link, (u64)start, (u64)end);
+
+		/* kernel only handle 16 bit only */
+		if (end > 0xffff)
+			end = 0xffff;
+		update_res(info, start, end, IORESOURCE_IO, 1);
+		update_range(range, start, end);
+	}
+	/* add left over io port range to def node/link, [0, 0xffff] */
+	/* find the position */
+	for (j = 0; j < pci_root_num; j++) {
+		info = &pci_root_info[j];
+		if (info->node == def_node && info->link == def_link)
+			break;
+	}
+	if (j < pci_root_num) {
+		info = &pci_root_info[j];
+		for (i = 0; i < RANGE_NUM; i++) {
+			if (!range[i].end)
+				continue;
+
+			update_res(info, range[i].start, range[i].end,
+				   IORESOURCE_IO, 1);
+		}
+	}
+
+	memset(range, 0, sizeof(range));
+	/* 0xfd00000000-0xffffffffff for HT */
+	range[0].end = (0xfdULL<<32) - 1;
+
+	/* need to take out [0, TOM) for RAM*/
+	address = MSR_K8_TOP_MEM1;
+	rdmsrl(address, val);
+	end = (val & 0xffffff8000000ULL);
+	printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
+	if (end < (1ULL<<32))
+		update_range(range, 0, end - 1);
+
+	/* get mmconfig */
+	get_pci_mmcfg_amd_fam10h_range();
+	/* need to take out mmconf range */
+	if (fam10h_mmconf_end) {
+		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
+		update_range(range, fam10h_mmconf_start, fam10h_mmconf_end);
+	}
+
+	/* mmio resource */
+	for (i = 0; i < 8; i++) {
+		reg = read_pci_config(bus, slot, 1, 0x80 + (i << 3));
+		if (!(reg & 3))
+			continue;
+
+		start = reg & 0xffffff00; /* 39:16 on 31:8*/
+		start <<= 8;
+		reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3));
+		node = reg & 0x07;
+		link = (reg >> 4) & 0x03;
+		end = (reg & 0xffffff00);
+		end <<= 8;
+		end |= 0xffff;
+
+		/* find the position */
+		for (j = 0; j < pci_root_num; j++) {
+			info = &pci_root_info[j];
+			if (info->node == node && info->link == link)
+				break;
+		}
+		if (j == pci_root_num)
+			continue; /* not found */
+
+		info = &pci_root_info[j];
+
+		printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
+		       node, link, (u64)start, (u64)end);
+		/*
+		 * some sick allocation would have range overlap with fam10h
+		 * mmconf range, so need to update start and end.
+		 */
+		if (fam10h_mmconf_end) {
+			int changed = 0;
+			u64 endx = 0;
+			if (start >= fam10h_mmconf_start &&
+			    start <= fam10h_mmconf_end) {
+				start = fam10h_mmconf_end + 1;
+				changed = 1;
+			}
+
+			if (end >= fam10h_mmconf_start &&
+			    end <= fam10h_mmconf_end) {
+				end = fam10h_mmconf_start - 1;
+				changed = 1;
+			}
+
+			if (start < fam10h_mmconf_start &&
+			    end > fam10h_mmconf_end) {
+				/* we got a hole */
+				endx = fam10h_mmconf_start - 1;
+				update_res(info, start, endx, IORESOURCE_MEM, 0);
+				update_range(range, start, endx);
+				printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
+				start = fam10h_mmconf_end + 1;
+				changed = 1;
+			}
+			if (changed) {
+				if (start <= end) {
+					printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end);
+				} else {
+					printk(KERN_CONT "%s\n", endx?"":" ==> none");
+					continue;
+				}
+			}
+		}
+
+		update_res(info, start, end, IORESOURCE_MEM, 1);
+		update_range(range, start, end);
+		printk(KERN_CONT "\n");
+	}
+
+	/* need to take out [4G, TOM2) for RAM*/
+	/* SYS_CFG */
+	address = MSR_K8_SYSCFG;
+	rdmsrl(address, val);
+	/* TOP_MEM2 is enabled? */
+	if (val & (1<<21)) {
+		/* TOP_MEM2 */
+		address = MSR_K8_TOP_MEM2;
+		rdmsrl(address, val);
+		end = (val & 0xffffff8000000ULL);
+		printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
+		update_range(range, 1ULL<<32, end - 1);
+	}
+
+	/*
+	 * add left over mmio range to def node/link ?
+	 * that is tricky, just record range in from start_min to 4G
+	 */
+	for (j = 0; j < pci_root_num; j++) {
+		info = &pci_root_info[j];
+		if (info->node == def_node && info->link == def_link)
+			break;
+	}
+	if (j < pci_root_num) {
+		info = &pci_root_info[j];
+
+		for (i = 0; i < RANGE_NUM; i++) {
+			if (!range[i].end)
+				continue;
+
+			update_res(info, range[i].start, range[i].end,
+				   IORESOURCE_MEM, 1);
+		}
+	}
+
+	for (i = 0; i < pci_root_num; i++) {
+		int res_num;
+		int busnum;
+
+		info = &pci_root_info[i];
+		res_num = info->res_num;
+		busnum = info->bus_min;
+		printk(KERN_DEBUG "bus: [%02x,%02x] on node %x link %x\n",
+		       info->bus_min, info->bus_max, info->node, info->link);
+		for (j = 0; j < res_num; j++) {
+			res = &info->res[j];
+			printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n",
+			       busnum, j,
+			       (res->flags & IORESOURCE_IO)?"io port":"mmio",
+			       res->start, res->end);
+		}
+	}
+
+	return 0;
+}
+
+postcore_initcall(early_fill_mp_bus_info);
diff --git a/arch/x86/pci/k8-bus_64.c b/arch/x86/pci/k8-bus_64.c
deleted file mode 100644
index 5c2799c20e47..000000000000
--- a/arch/x86/pci/k8-bus_64.c
+++ /dev/null
@@ -1,528 +0,0 @@
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <asm/pci-direct.h>
-#include <asm/mpspec.h>
-#include <linux/cpumask.h>
-#include <linux/topology.h>
-
-/*
- * This discovers the pcibus <-> node mapping on AMD K8.
- * also get peer root bus resource for io,mmio
- */
-
-
-/*
- * sub bus (transparent) will use entres from 3 to store extra from root,
- * so need to make sure have enought slot there, increase PCI_BUS_NUM_RESOURCES?
- */
-#define RES_NUM 16
-struct pci_root_info {
-	char name[12];
-	unsigned int res_num;
-	struct resource res[RES_NUM];
-	int bus_min;
-	int bus_max;
-	int node;
-	int link;
-};
-
-/* 4 at this time, it may become to 32 */
-#define PCI_ROOT_NR 4
-static int pci_root_num;
-static struct pci_root_info pci_root_info[PCI_ROOT_NR];
-
-#ifdef CONFIG_NUMA
-
-#define BUS_NR 256
-
-static int mp_bus_to_node[BUS_NR];
-
-void set_mp_bus_to_node(int busnum, int node)
-{
-	if (busnum >= 0 &&  busnum < BUS_NR)
-		mp_bus_to_node[busnum] = node;
-}
-
-int get_mp_bus_to_node(int busnum)
-{
-	int node = -1;
-
-	if (busnum < 0 || busnum > (BUS_NR - 1))
-		return node;
-
-	node = mp_bus_to_node[busnum];
-
-	/*
-	 * let numa_node_id to decide it later in dma_alloc_pages
-	 * if there is no ram on that node
-	 */
-	if (node != -1 && !node_online(node))
-		node = -1;
-
-	return node;
-}
-#endif
-
-void set_pci_bus_resources_arch_default(struct pci_bus *b)
-{
-	int i;
-	int j;
-	struct pci_root_info *info;
-
-	/* if only one root bus, don't need to anything */
-	if (pci_root_num < 2)
-		return;
-
-	for (i = 0; i < pci_root_num; i++) {
-		if (pci_root_info[i].bus_min == b->number)
-			break;
-	}
-
-	if (i == pci_root_num)
-		return;
-
-	info = &pci_root_info[i];
-	for (j = 0; j < info->res_num; j++) {
-		struct resource *res;
-		struct resource *root;
-
-		res = &info->res[j];
-		b->resource[j] = res;
-		if (res->flags & IORESOURCE_IO)
-			root = &ioport_resource;
-		else
-			root = &iomem_resource;
-		insert_resource(root, res);
-	}
-}
-
-#define RANGE_NUM 16
-
-struct res_range {
-	size_t start;
-	size_t end;
-};
-
-static void __init update_range(struct res_range *range, size_t start,
-				size_t end)
-{
-	int i;
-	int j;
-
-	for (j = 0; j < RANGE_NUM; j++) {
-		if (!range[j].end)
-			continue;
-
-		if (start <= range[j].start && end >= range[j].end) {
-			range[j].start = 0;
-			range[j].end = 0;
-			continue;
-		}
-
-		if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
-			range[j].start = end + 1;
-			continue;
-		}
-
-
-		if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
-			range[j].end = start - 1;
-			continue;
-		}
-
-		if (start > range[j].start && end < range[j].end) {
-			/* find the new spare */
-			for (i = 0; i < RANGE_NUM; i++) {
-				if (range[i].end == 0)
-					break;
-			}
-			if (i < RANGE_NUM) {
-				range[i].end = range[j].end;
-				range[i].start = end + 1;
-			} else {
-				printk(KERN_ERR "run of slot in ranges\n");
-			}
-			range[j].end = start - 1;
-			continue;
-		}
-	}
-}
-
-static void __init update_res(struct pci_root_info *info, size_t start,
-			      size_t end, unsigned long flags, int merge)
-{
-	int i;
-	struct resource *res;
-
-	if (!merge)
-		goto addit;
-
-	/* try to merge it with old one */
-	for (i = 0; i < info->res_num; i++) {
-		size_t final_start, final_end;
-		size_t common_start, common_end;
-
-		res = &info->res[i];
-		if (res->flags != flags)
-			continue;
-
-		common_start = max((size_t)res->start, start);
-		common_end = min((size_t)res->end, end);
-		if (common_start > common_end + 1)
-			continue;
-
-		final_start = min((size_t)res->start, start);
-		final_end = max((size_t)res->end, end);
-
-		res->start = final_start;
-		res->end = final_end;
-		return;
-	}
-
-addit:
-
-	/* need to add that */
-	if (info->res_num >= RES_NUM)
-		return;
-
-	res = &info->res[info->res_num];
-	res->name = info->name;
-	res->flags = flags;
-	res->start = start;
-	res->end = end;
-	res->child = NULL;
-	info->res_num++;
-}
-
-struct pci_hostbridge_probe {
-	u32 bus;
-	u32 slot;
-	u32 vendor;
-	u32 device;
-};
-
-static struct pci_hostbridge_probe pci_probes[] __initdata = {
-	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1100 },
-	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 },
-	{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
-	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 },
-};
-
-static u64 __initdata fam10h_mmconf_start;
-static u64 __initdata fam10h_mmconf_end;
-static void __init get_pci_mmcfg_amd_fam10h_range(void)
-{
-	u32 address;
-	u64 base, msr;
-	unsigned segn_busn_bits;
-
-	/* assume all cpus from fam10h have mmconf */
-        if (boot_cpu_data.x86 < 0x10)
-		return;
-
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
-	/* mmconfig is not enable */
-	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
-		return;
-
-	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
-
-	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
-			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
-
-	fam10h_mmconf_start = base;
-	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
-}
-
-/**
- * early_fill_mp_bus_to_node()
- * called before pcibios_scan_root and pci_scan_bus
- * fills the mp_bus_to_cpumask array based according to the LDT Bus Number
- * Registers found in the K8 northbridge
- */
-static int __init early_fill_mp_bus_info(void)
-{
-	int i;
-	int j;
-	unsigned bus;
-	unsigned slot;
-	int found;
-	int node;
-	int link;
-	int def_node;
-	int def_link;
-	struct pci_root_info *info;
-	u32 reg;
-	struct resource *res;
-	size_t start;
-	size_t end;
-	struct res_range range[RANGE_NUM];
-	u64 val;
-	u32 address;
-
-#ifdef CONFIG_NUMA
-	for (i = 0; i < BUS_NR; i++)
-		mp_bus_to_node[i] = -1;
-#endif
-
-	if (!early_pci_allowed())
-		return -1;
-
-	found = 0;
-	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
-		u32 id;
-		u16 device;
-		u16 vendor;
-
-		bus = pci_probes[i].bus;
-		slot = pci_probes[i].slot;
-		id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID);
-
-		vendor = id & 0xffff;
-		device = (id>>16) & 0xffff;
-		if (pci_probes[i].vendor == vendor &&
-		    pci_probes[i].device == device) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (!found)
-		return 0;
-
-	pci_root_num = 0;
-	for (i = 0; i < 4; i++) {
-		int min_bus;
-		int max_bus;
-		reg = read_pci_config(bus, slot, 1, 0xe0 + (i << 2));
-
-		/* Check if that register is enabled for bus range */
-		if ((reg & 7) != 3)
-			continue;
-
-		min_bus = (reg >> 16) & 0xff;
-		max_bus = (reg >> 24) & 0xff;
-		node = (reg >> 4) & 0x07;
-#ifdef CONFIG_NUMA
-		for (j = min_bus; j <= max_bus; j++)
-			mp_bus_to_node[j] = (unsigned char) node;
-#endif
-		link = (reg >> 8) & 0x03;
-
-		info = &pci_root_info[pci_root_num];
-		info->bus_min = min_bus;
-		info->bus_max = max_bus;
-		info->node = node;
-		info->link = link;
-		sprintf(info->name, "PCI Bus #%02x", min_bus);
-		pci_root_num++;
-	}
-
-	/* get the default node and link for left over res */
-	reg = read_pci_config(bus, slot, 0, 0x60);
-	def_node = (reg >> 8) & 0x07;
-	reg = read_pci_config(bus, slot, 0, 0x64);
-	def_link = (reg >> 8) & 0x03;
-
-	memset(range, 0, sizeof(range));
-	range[0].end = 0xffff;
-	/* io port resource */
-	for (i = 0; i < 4; i++) {
-		reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
-		if (!(reg & 3))
-			continue;
-
-		start = reg & 0xfff000;
-		reg = read_pci_config(bus, slot, 1, 0xc4 + (i << 3));
-		node = reg & 0x07;
-		link = (reg >> 4) & 0x03;
-		end = (reg & 0xfff000) | 0xfff;
-
-		/* find the position */
-		for (j = 0; j < pci_root_num; j++) {
-			info = &pci_root_info[j];
-			if (info->node == node && info->link == link)
-				break;
-		}
-		if (j == pci_root_num)
-			continue; /* not found */
-
-		info = &pci_root_info[j];
-		printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
-		       node, link, (u64)start, (u64)end);
-
-		/* kernel only handle 16 bit only */
-		if (end > 0xffff)
-			end = 0xffff;
-		update_res(info, start, end, IORESOURCE_IO, 1);
-		update_range(range, start, end);
-	}
-	/* add left over io port range to def node/link, [0, 0xffff] */
-	/* find the position */
-	for (j = 0; j < pci_root_num; j++) {
-		info = &pci_root_info[j];
-		if (info->node == def_node && info->link == def_link)
-			break;
-	}
-	if (j < pci_root_num) {
-		info = &pci_root_info[j];
-		for (i = 0; i < RANGE_NUM; i++) {
-			if (!range[i].end)
-				continue;
-
-			update_res(info, range[i].start, range[i].end,
-				   IORESOURCE_IO, 1);
-		}
-	}
-
-	memset(range, 0, sizeof(range));
-	/* 0xfd00000000-0xffffffffff for HT */
-	range[0].end = (0xfdULL<<32) - 1;
-
-	/* need to take out [0, TOM) for RAM*/
-	address = MSR_K8_TOP_MEM1;
-	rdmsrl(address, val);
-	end = (val & 0xffffff8000000ULL);
-	printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
-	if (end < (1ULL<<32))
-		update_range(range, 0, end - 1);
-
-	/* get mmconfig */
-	get_pci_mmcfg_amd_fam10h_range();
-	/* need to take out mmconf range */
-	if (fam10h_mmconf_end) {
-		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
-		update_range(range, fam10h_mmconf_start, fam10h_mmconf_end);
-	}
-
-	/* mmio resource */
-	for (i = 0; i < 8; i++) {
-		reg = read_pci_config(bus, slot, 1, 0x80 + (i << 3));
-		if (!(reg & 3))
-			continue;
-
-		start = reg & 0xffffff00; /* 39:16 on 31:8*/
-		start <<= 8;
-		reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3));
-		node = reg & 0x07;
-		link = (reg >> 4) & 0x03;
-		end = (reg & 0xffffff00);
-		end <<= 8;
-		end |= 0xffff;
-
-		/* find the position */
-		for (j = 0; j < pci_root_num; j++) {
-			info = &pci_root_info[j];
-			if (info->node == node && info->link == link)
-				break;
-		}
-		if (j == pci_root_num)
-			continue; /* not found */
-
-		info = &pci_root_info[j];
-
-		printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
-		       node, link, (u64)start, (u64)end);
-		/*
-		 * some sick allocation would have range overlap with fam10h
-		 * mmconf range, so need to update start and end.
-		 */
-		if (fam10h_mmconf_end) {
-			int changed = 0;
-			u64 endx = 0;
-			if (start >= fam10h_mmconf_start &&
-			    start <= fam10h_mmconf_end) {
-				start = fam10h_mmconf_end + 1;
-				changed = 1;
-			}
-
-			if (end >= fam10h_mmconf_start &&
-			    end <= fam10h_mmconf_end) {
-				end = fam10h_mmconf_start - 1;
-				changed = 1;
-			}
-
-			if (start < fam10h_mmconf_start &&
-			    end > fam10h_mmconf_end) {
-				/* we got a hole */
-				endx = fam10h_mmconf_start - 1;
-				update_res(info, start, endx, IORESOURCE_MEM, 0);
-				update_range(range, start, endx);
-				printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
-				start = fam10h_mmconf_end + 1;
-				changed = 1;
-			}
-			if (changed) {
-				if (start <= end) {
-					printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end);
-				} else {
-					printk(KERN_CONT "%s\n", endx?"":" ==> none");
-					continue;
-				}
-			}
-		}
-
-		update_res(info, start, end, IORESOURCE_MEM, 1);
-		update_range(range, start, end);
-		printk(KERN_CONT "\n");
-	}
-
-	/* need to take out [4G, TOM2) for RAM*/
-	/* SYS_CFG */
-	address = MSR_K8_SYSCFG;
-	rdmsrl(address, val);
-	/* TOP_MEM2 is enabled? */
-	if (val & (1<<21)) {
-		/* TOP_MEM2 */
-		address = MSR_K8_TOP_MEM2;
-		rdmsrl(address, val);
-		end = (val & 0xffffff8000000ULL);
-		printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
-		update_range(range, 1ULL<<32, end - 1);
-	}
-
-	/*
-	 * add left over mmio range to def node/link ?
-	 * that is tricky, just record range in from start_min to 4G
-	 */
-	for (j = 0; j < pci_root_num; j++) {
-		info = &pci_root_info[j];
-		if (info->node == def_node && info->link == def_link)
-			break;
-	}
-	if (j < pci_root_num) {
-		info = &pci_root_info[j];
-
-		for (i = 0; i < RANGE_NUM; i++) {
-			if (!range[i].end)
-				continue;
-
-			update_res(info, range[i].start, range[i].end,
-				   IORESOURCE_MEM, 1);
-		}
-	}
-
-	for (i = 0; i < pci_root_num; i++) {
-		int res_num;
-		int busnum;
-
-		info = &pci_root_info[i];
-		res_num = info->res_num;
-		busnum = info->bus_min;
-		printk(KERN_DEBUG "bus: [%02x,%02x] on node %x link %x\n",
-		       info->bus_min, info->bus_max, info->node, info->link);
-		for (j = 0; j < res_num; j++) {
-			res = &info->res[j];
-			printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n",
-			       busnum, j,
-			       (res->flags & IORESOURCE_IO)?"io port":"mmio",
-			       res->start, res->end);
-		}
-	}
-
-	return 0;
-}
-
-postcore_initcall(early_fill_mp_bus_info);
-- 
cgit v1.2.2


From 3a27dd1ce5de08e21e0266ddf00e6f1f843bfe8b Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Thu, 12 Jun 2008 20:19:23 +0200
Subject: x86: Move PCI IO ECS code to x86/pci

"Form follows function". Code is now where it belongs to.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd.c    |  3 ---
 arch/x86/kernel/cpu/amd_64.c |  4 ----
 arch/x86/kernel/cpu/cpu.h    |  2 --
 arch/x86/kernel/setup.c      | 13 -------------
 arch/x86/pci/Makefile_32     |  1 +
 arch/x86/pci/amd_bus.c       | 32 ++++++++++++++++++++++++++++++++
 arch/x86/pci/direct.c        | 16 +++++++++-------
 arch/x86/pci/pci.h           |  1 +
 8 files changed, 43 insertions(+), 29 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index acc891ae5901..81a07ca65d44 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -266,9 +266,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-
-	if (c->x86 == 0x10)
-		amd_enable_pci_ext_cfg(c);
 }
 
 static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index f8d20588bde9..250bfe6064af 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -6,7 +6,6 @@
 #include <asm/cacheflush.h>
 
 #include <mach_apic.h>
-#include "cpu.h"
 
 extern int __cpuinit get_model_name(struct cpuinfo_x86 *c);
 extern void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c);
@@ -187,9 +186,6 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		fam10h_check_enable_mmcfg();
 
-	if (c->x86 == 0x10)
-		amd_enable_pci_ext_cfg(c);
-
 	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
 		unsigned long long tseg;
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index f5d5bb1b5541..40ad1893fe87 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -39,5 +39,3 @@ extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
 
 #endif /* CONFIG_X86_32 */
-
-extern void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 20e14dbef107..6f80b852a196 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -137,16 +137,3 @@ void __init setup_per_cpu_areas(void)
 }
 
 #endif
-#define ENABLE_CF8_EXT_CFG      (1ULL << 46)
-
-void __cpuinit amd_enable_pci_ext_cfg(struct cpuinfo_x86 *c)
-{
-	u64 reg;
-	rdmsrl(MSR_AMD64_NB_CFG, reg);
-	if (!(reg & ENABLE_CF8_EXT_CFG)) {
-		reg |= ENABLE_CF8_EXT_CFG;
-		wrmsrl(MSR_AMD64_NB_CFG, reg);
-	}
-	set_cpu_cap(c, X86_FEATURE_PCI_EXT_CFG);
-}
-
diff --git a/arch/x86/pci/Makefile_32 b/arch/x86/pci/Makefile_32
index 89ec35d00efd..f647e7e56da4 100644
--- a/arch/x86/pci/Makefile_32
+++ b/arch/x86/pci/Makefile_32
@@ -22,3 +22,4 @@ pci-$(CONFIG_X86_NUMAQ)		:= numa.o irq.o
 pci-$(CONFIG_NUMA)		+= mp_bus_to_node.o
 
 obj-y				+= $(pci-y) common.o early.o
+obj-y				+= amd_bus.o
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 5c2799c20e47..15f505d3a78e 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -1,5 +1,9 @@
 #include <linux/init.h>
 #include <linux/pci.h>
+#include "pci.h"
+
+#ifdef CONFIG_X86_64
+
 #include <asm/pci-direct.h>
 #include <asm/mpspec.h>
 #include <linux/cpumask.h>
@@ -526,3 +530,31 @@ static int __init early_fill_mp_bus_info(void)
 }
 
 postcore_initcall(early_fill_mp_bus_info);
+
+#endif
+
+/* common 32/64 bit code */
+
+#define ENABLE_CF8_EXT_CFG      (1ULL << 46)
+
+static void enable_pci_io_ecs_per_cpu(void *unused)
+{
+	u64 reg;
+	rdmsrl(MSR_AMD64_NB_CFG, reg);
+	if (!(reg & ENABLE_CF8_EXT_CFG)) {
+		reg |= ENABLE_CF8_EXT_CFG;
+		wrmsrl(MSR_AMD64_NB_CFG, reg);
+	}
+}
+
+static int __init enable_pci_io_ecs(void)
+{
+	/* assume all cpus from fam10h have IO ECS */
+        if (boot_cpu_data.x86 < 0x10)
+		return 0;
+	on_each_cpu(enable_pci_io_ecs_per_cpu, NULL, 1, 1);
+	pci_probe |= PCI_HAS_IO_ECS;
+	return 0;
+}
+
+postcore_initcall(enable_pci_io_ecs);
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 27d61b63def6..9915293500fb 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -265,14 +265,16 @@ void __init pci_direct_init(int type)
 		 type);
 	if (type == 1) {
 		raw_pci_ops = &pci_direct_conf1;
-		if (!raw_pci_ext_ops && cpu_has_pci_ext_cfg) {
-			printk(KERN_INFO "PCI: Using configuration type 1 "
-			       "for extended access\n");
-			raw_pci_ext_ops = &pci_direct_conf1;
-		}
-	} else {
-		raw_pci_ops = &pci_direct_conf2;
+		if (raw_pci_ext_ops)
+			return;
+		if (!(pci_probe & PCI_HAS_IO_ECS))
+			return;
+		printk(KERN_INFO "PCI: Using configuration type 1 "
+		       "for extended access\n");
+		raw_pci_ext_ops = &pci_direct_conf1;
+		return;
 	}
+	raw_pci_ops = &pci_direct_conf2;
 }
 
 int __init pci_direct_probe(void)
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index f3972b12c60a..fd53db50eeeb 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -27,6 +27,7 @@
 #define PCI_CAN_SKIP_ISA_ALIGN	0x8000
 #define PCI_USE__CRS		0x10000
 #define PCI_CHECK_ENABLE_AMD_MMCONF	0x20000
+#define PCI_HAS_IO_ECS		0x40000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;
-- 
cgit v1.2.2


From dcd32b6a1ffe6c040f8346f7fbaf4318bb8ae41c Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Fri, 20 Jun 2008 08:18:09 +0200
Subject: x86: make 64-bit identify_cpu use cpu_dev

we may need to move some functions to common.c later

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/amd_64.c     | 17 +++++--
 arch/x86/kernel/cpu/centaur_64.c | 16 ++++++-
 arch/x86/kernel/cpu/cpu.h        |  6 ++-
 arch/x86/kernel/cpu/intel_64.c   | 15 ++++++-
 arch/x86/kernel/setup_64.c       | 96 +++++++++++++++++++++-------------------
 5 files changed, 95 insertions(+), 55 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index 250bfe6064af..30b7557c9641 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -7,8 +7,7 @@
 
 #include <mach_apic.h>
 
-extern int __cpuinit get_model_name(struct cpuinfo_x86 *c);
-extern void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c);
+#include "cpu.h"
 
 int force_mwait __cpuinitdata;
 
@@ -109,7 +108,7 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd_mc(c);
 
@@ -118,7 +117,7 @@ void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 }
 
-void __cpuinit init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 {
 	unsigned level;
 
@@ -200,3 +199,13 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			set_memory_4k((unsigned long)__va(tseg), 1);
 	}
 }
+
+static struct cpu_dev amd_cpu_dev __cpuinitdata = {
+	.c_vendor	= "AMD",
+	.c_ident	= { "AuthenticAMD" },
+	.c_early_init   = early_init_amd,
+	.c_init		= init_amd,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
+
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index bac96d187d05..13526fd5cce1 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -4,13 +4,15 @@
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
 
-void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
+#include "cpu.h"
+
+static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 {
 	if (c->x86 == 0x6 && c->x86_model >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 }
 
-void __cpuinit init_centaur(struct cpuinfo_x86 *c)
+static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
 	unsigned n;
@@ -29,3 +31,13 @@ void __cpuinit init_centaur(struct cpuinfo_x86 *c)
 	}
 	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 }
+
+static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
+	.c_vendor	= "Centaur",
+	.c_ident	= { "CentaurHauls" },
+	.c_early_init	= early_init_centaur,
+	.c_init		= init_centaur,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 40ad1893fe87..4d894e8565fe 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -1,4 +1,6 @@
-#ifdef CONFIG_X86_32
+#ifndef ARCH_X86_CPU_H
+
+#define ARCH_X86_CPU_H
 
 struct cpu_model_info {
 	int vendor;
@@ -38,4 +40,4 @@ extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
 extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
 
-#endif /* CONFIG_X86_32 */
+#endif
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
index b33912199484..fcb1cc9d75ca 100644
--- a/arch/x86/kernel/cpu/intel_64.c
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -5,7 +5,9 @@
 #include <asm/topology.h>
 #include <asm/numa_64.h>
 
-void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+#include "cpu.h"
+
+static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 	    (c->x86 == 0x6 && c->x86_model >= 0x0e))
@@ -48,7 +50,7 @@ static void __cpuinit srat_detect_node(void)
 #endif
 }
 
-void __cpuinit init_intel(struct cpuinfo_x86 *c)
+static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
 	unsigned n;
@@ -90,3 +92,12 @@ void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 	srat_detect_node();
 }
+
+static struct cpu_dev intel_cpu_dev __cpuinitdata = {
+	.c_vendor	= "Intel",
+	.c_ident	= { "GenuineIntel" },
+	.c_early_init   = early_init_intel,
+	.c_init		= init_intel,
+};
+cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
+
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 25afdd80a3cf..0cebf953c25a 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -80,6 +80,8 @@
 #define ARCH_SETUP
 #endif
 
+#include "cpu/cpu.h"
+
 /*
  * Machine setup..
  */
@@ -163,6 +165,7 @@ static struct resource bss_resource = {
 	.flags = IORESOURCE_RAM,
 };
 
+static void __init early_cpu_init(void);
 static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);
 
 #ifdef CONFIG_PROC_VMCORE
@@ -339,6 +342,7 @@ void __init setup_arch(char **cmdline_p)
 	bss_resource.start = virt_to_phys(&__bss_start);
 	bss_resource.end = virt_to_phys(&__bss_stop)-1;
 
+	early_cpu_init();
 	early_identify_cpu(&boot_cpu_data);
 
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
@@ -524,6 +528,19 @@ void __init setup_arch(char **cmdline_p)
 	check_enable_amd_mmconf_dmi();
 }
 
+struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+
+static void __cpuinit default_init(struct cpuinfo_x86 *c)
+{
+	display_cacheinfo(c);
+}
+
+static struct cpu_dev __cpuinitdata default_cpu = {
+	.c_init	= default_init,
+	.c_vendor = "Unknown",
+};
+static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
+
 int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
@@ -625,24 +642,37 @@ out:
 static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 {
 	char *v = c->x86_vendor_id;
-
-	if (!strcmp(v, "AuthenticAMD"))
-		c->x86_vendor = X86_VENDOR_AMD;
-	else if (!strcmp(v, "GenuineIntel"))
-		c->x86_vendor = X86_VENDOR_INTEL;
-	else if (!strcmp(v, "CentaurHauls"))
-		c->x86_vendor = X86_VENDOR_CENTAUR;
-	else
-		c->x86_vendor = X86_VENDOR_UNKNOWN;
+	int i;
+	static int printed;
+
+	for (i = 0; i < X86_VENDOR_NUM; i++) {
+		if (cpu_devs[i]) {
+			if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+			    (cpu_devs[i]->c_ident[1] &&
+			    !strcmp(v, cpu_devs[i]->c_ident[1]))) {
+				c->x86_vendor = i;
+				this_cpu = cpu_devs[i];
+				return;
+			}
+		}
+	}
+	if (!printed) {
+		printed++;
+		printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+		printk(KERN_ERR "CPU: Your system may be unstable.\n");
+	}
+	c->x86_vendor = X86_VENDOR_UNKNOWN;
 }
 
-// FIXME: Needs to use cpu_vendor_dev_register
-extern void __cpuinit early_init_amd(struct cpuinfo_x86 *c);
-extern void __cpuinit init_amd(struct cpuinfo_x86 *c);
-extern void __cpuinit early_init_intel(struct cpuinfo_x86 *c);
-extern void __cpuinit init_intel(struct cpuinfo_x86 *c);
-extern void __cpuinit early_init_centaur(struct cpuinfo_x86 *c);
-extern void __cpuinit init_centaur(struct cpuinfo_x86 *c);
+static void __init early_cpu_init(void)
+{
+        struct cpu_vendor_dev *cvdev;
+
+        for (cvdev = __x86cpuvendor_start ;
+             cvdev < __x86cpuvendor_end   ;
+             cvdev++)
+                cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+}
 
 /* Do some early cpuid on the boot CPU to get some parameter that are
    needed before check_bugs. Everything advanced is in identify_cpu
@@ -722,17 +752,9 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
-	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		early_init_amd(c);
-		break;
-	case X86_VENDOR_INTEL:
-		early_init_intel(c);
-		break;
-	case X86_VENDOR_CENTAUR:
-		early_init_centaur(c);
-		break;
-	}
+	if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
+	    cpu_devs[c->x86_vendor]->c_early_init)
+		cpu_devs[c->x86_vendor]->c_early_init(c);
 
 	validate_pat_support(c);
 }
@@ -760,24 +782,8 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	 * At the end of this section, c->x86_capability better
 	 * indicate the features this CPU genuinely supports!
 	 */
-	switch (c->x86_vendor) {
-	case X86_VENDOR_AMD:
-		init_amd(c);
-		break;
-
-	case X86_VENDOR_INTEL:
-		init_intel(c);
-		break;
-
-	case X86_VENDOR_CENTAUR:
-		init_centaur(c);
-		break;
-
-	case X86_VENDOR_UNKNOWN:
-	default:
-		display_cacheinfo(c);
-		break;
-	}
+	if (this_cpu->c_init)
+		this_cpu->c_init(c);
 
 	detect_ht(c);
 
-- 
cgit v1.2.2


From c49c412a47b5102516d3313d4eba38cb1e968721 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Thu, 19 Jun 2008 15:30:31 -0700
Subject: x86: make 64bit identify_cpu use cpu_dev v2

v2: fix early_panic on this config:

  http://redhat.com/~mingo/misc/config-Thu_Jun_19_14_22_37_CEST_2008.bad

reason : struct cpu_vendor_dev size is 16, need to make table to be 16
         byte alignment

also print out the cpu supported...

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/setup_64.c       | 20 ++++++++++++++++++++
 arch/x86/kernel/vmlinux_64.lds.S |  1 +
 2 files changed, 21 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 0cebf953c25a..b789ec599923 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -664,6 +664,25 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
 }
 
+static void __init early_cpu_support_print(void)
+{
+	int i,j;
+	struct cpu_dev *cpu_devx;
+
+	printk("KERNEL supported cpus:\n");
+	for (i = 0; i < X86_VENDOR_NUM; i++) {
+		cpu_devx = cpu_devs[i];
+		if (!cpu_devx)
+			continue;
+		for (j = 0; j < 2; j++) {
+			if (!cpu_devx->c_ident[j])
+				continue;
+			printk("  %s %s\n", cpu_devx->c_vendor,
+				cpu_devx->c_ident[j]);
+		}
+	}
+}
+
 static void __init early_cpu_init(void)
 {
         struct cpu_vendor_dev *cvdev;
@@ -672,6 +691,7 @@ static void __init early_cpu_init(void)
              cvdev < __x86cpuvendor_end   ;
              cvdev++)
                 cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+	early_cpu_support_print();
 }
 
 /* Do some early cpuid on the boot CPU to get some parameter that are
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index fad3674b06a5..b29f63bdff5e 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -177,6 +177,7 @@ SECTIONS
 	*(.con_initcall.init)
   }
   __con_initcall_end = .;
+  . = ALIGN(16);
   __x86cpuvendor_start = .;
   .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) {
 	*(.x86cpuvendor.init)
-- 
cgit v1.2.2


From ce0c0e50f94e8c55b00a722e8c6e8d6c802be211 Mon Sep 17 00:00:00 2001
From: Andi Kleen <andi@firstfloor.org>
Date: Fri, 2 May 2008 11:46:49 +0200
Subject: x86, generic: CPA add statistics about state of direct mapping v4

Add information about the mapping state of the direct mapping to
/proc/meminfo. I chose /proc/meminfo because that is where all the other
memory statistics are too and it is a generally useful metric even
outside debugging situations. A lot of split kernel pages means the
kernel will run slower.

This way we can see how many large pages are really used for it and how
many are split.

Useful for general insight into the kernel.

v2: Add hotplug locking to 64bit to plug a very obscure theoretical race.
    32bit doesn't need it because it doesn't support hotadd for lowmem.
    Fix some typos
v3: Rename dpages_cnt
    Add CONFIG ifdef for count update as requested by tglx
    Expand description
v4: Fix stupid bugs added in v3
    Move update_page_count to pageattr.c

Signed-off-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_32.c  |  5 +++++
 arch/x86/mm/init_64.c  |  7 +++++++
 arch/x86/mm/pageattr.c | 35 +++++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ec30d10154b6..0269ac230bfa 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -162,6 +162,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	pgd_t *pgd;
 	pmd_t *pmd;
 	pte_t *pte;
+	unsigned pages_2m = 0, pages_4k = 0;
 
 	pgd_idx = pgd_index(PAGE_OFFSET);
 	pgd = pgd_base + pgd_idx;
@@ -197,6 +198,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 				    is_kernel_text(addr2))
 					prot = PAGE_KERNEL_LARGE_EXEC;
 
+				pages_2m++;
 				set_pmd(pmd, pfn_pmd(pfn, prot));
 
 				pfn += PTRS_PER_PTE;
@@ -213,11 +215,14 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 				if (is_kernel_text(addr))
 					prot = PAGE_KERNEL_EXEC;
 
+				pages_4k++;
 				set_pte(pte, pfn_pte(pfn, prot));
 			}
 			max_pfn_mapped = pfn;
 		}
 	}
+	update_page_count(PG_LEVEL_2M, pages_2m);
+	update_page_count(PG_LEVEL_4K, pages_4k);
 }
 
 static inline int page_kills_ppro(unsigned long pagenr)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 819dad973b13..5e4383859053 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -312,6 +312,8 @@ __meminit void early_iounmap(void *addr, unsigned long size)
 static unsigned long __meminit
 phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
 {
+	unsigned long pages = 0;
+
 	int i = pmd_index(address);
 
 	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
@@ -328,9 +330,11 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
 		if (pmd_val(*pmd))
 			continue;
 
+		pages++;
 		set_pte((pte_t *)pmd,
 			pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
 	}
+	update_page_count(PG_LEVEL_2M, pages);
 	return address;
 }
 
@@ -350,6 +354,7 @@ phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
 static unsigned long __meminit
 phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 {
+	unsigned long pages = 0;
 	unsigned long last_map_addr = end;
 	int i = pud_index(addr);
 
@@ -374,6 +379,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 		}
 
 		if (direct_gbpages) {
+			pages++;
 			set_pte((pte_t *)pud,
 				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
 			last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
@@ -390,6 +396,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 		unmap_low_page(pmd);
 	}
 	__flush_tlb_all();
+	update_page_count(PG_LEVEL_1G, pages);
 
 	return last_map_addr >> PAGE_SHIFT;
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 60bcb5b6a37e..668205bca15e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -34,6 +34,19 @@ struct cpa_data {
 	unsigned	force_split : 1;
 };
 
+static unsigned long direct_pages_count[PG_LEVEL_NUM];
+
+void __meminit update_page_count(int level, unsigned long pages)
+{
+#ifdef CONFIG_PROC_FS
+	unsigned long flags;
+	/* Protect against CPA */
+	spin_lock_irqsave(&pgd_lock, flags);
+	direct_pages_count[level] += pages;
+	spin_unlock_irqrestore(&pgd_lock, flags);
+#endif
+}
+
 #ifdef CONFIG_X86_64
 
 static inline unsigned long highmap_start_pfn(void)
@@ -500,6 +513,12 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
 		set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
 
+	if (address >= (unsigned long)__va(0) &&
+		address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT)) {
+		direct_pages_count[level]--;
+		direct_pages_count[level - 1] += PTRS_PER_PTE;
+	}
+
 	/*
 	 * Install the new, split up pagetable. Important details here:
 	 *
@@ -1029,6 +1048,22 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+#ifdef CONFIG_PROC_FS
+int arch_report_meminfo(char *page)
+{
+	int n;
+	n = sprintf(page, "DirectMap4k:  %8lu\n"
+			  "DirectMap2M:  %8lu\n",
+			direct_pages_count[PG_LEVEL_4K],
+			direct_pages_count[PG_LEVEL_2M]);
+#ifdef CONFIG_X86_64
+	n += sprintf(page + n, "DirectMap1G:  %8lu\n",
+			direct_pages_count[PG_LEVEL_1G]);
+#endif
+	return n;
+}
+#endif
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
-- 
cgit v1.2.2


From 65280e613fada41704f35709b6c8952ca4b8750c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 5 May 2008 16:35:21 +0200
Subject: x86: janitor CPA statistics patch

1) Remove __meminit from update_pages_count. It is used inside
split_pages()

2) Make the code depend on PROC_FS. Doing statistics for nothing is
useless and not adding useless code is nice to the Linux tiny folks.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/pageattr.c | 48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 668205bca15e..0a3f5e047f89 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -34,18 +34,40 @@ struct cpa_data {
 	unsigned	force_split : 1;
 };
 
+#ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
 
-void __meminit update_page_count(int level, unsigned long pages)
+void update_page_count(int level, unsigned long pages)
 {
-#ifdef CONFIG_PROC_FS
 	unsigned long flags;
+
 	/* Protect against CPA */
 	spin_lock_irqsave(&pgd_lock, flags);
 	direct_pages_count[level] += pages;
 	spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void split_page_count(int level)
+{
+	direct_pages_count[level]--;
+	direct_pages_count[level - 1] += PTRS_PER_PTE;
+}
+
+int arch_report_meminfo(char *page)
+{
+	int n = sprintf(page, "DirectMap4k:  %8lu\n"
+			"DirectMap2M:  %8lu\n",
+			direct_pages_count[PG_LEVEL_4K],
+			direct_pages_count[PG_LEVEL_2M]);
+#ifdef CONFIG_X86_64
+	n += sprintf(page + n, "DirectMap1G:  %8lu\n",
+		     direct_pages_count[PG_LEVEL_1G]);
 #endif
+	return n;
 }
+#else
+static inline void split_page_count(int level) { }
+#endif
 
 #ifdef CONFIG_X86_64
 
@@ -514,10 +536,8 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 		set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
 
 	if (address >= (unsigned long)__va(0) &&
-		address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT)) {
-		direct_pages_count[level]--;
-		direct_pages_count[level - 1] += PTRS_PER_PTE;
-	}
+		address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
+		split_page_count(level);
 
 	/*
 	 * Install the new, split up pagetable. Important details here:
@@ -1048,22 +1068,6 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
-#ifdef CONFIG_PROC_FS
-int arch_report_meminfo(char *page)
-{
-	int n;
-	n = sprintf(page, "DirectMap4k:  %8lu\n"
-			  "DirectMap2M:  %8lu\n",
-			direct_pages_count[PG_LEVEL_4K],
-			direct_pages_count[PG_LEVEL_2M]);
-#ifdef CONFIG_X86_64
-	n += sprintf(page + n, "DirectMap1G:  %8lu\n",
-			direct_pages_count[PG_LEVEL_1G]);
-#endif
-	return n;
-}
-#endif
-
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
-- 
cgit v1.2.2


From 6e92a5a6151f4a467b8c1bde9123c0a9d1a63339 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: add sparse annotations to ioremap

arch/x86/mm/ioremap.c:308:11: error: incompatible types in comparison expression (different address spaces)

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/ioremap.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 2b2bb3f9b683..01d76426971d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -318,8 +318,8 @@ void iounmap(volatile void __iomem *addr)
 	 * vm_area and by simply returning an address into the kernel mapping
 	 * of ISA space.   So handle that here.
 	 */
-	if (addr >= phys_to_virt(ISA_START_ADDRESS) &&
-	    addr < phys_to_virt(ISA_END_ADDRESS))
+	if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) &&
+	    (void __force *)addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
 	addr = (volatile void __iomem *)
@@ -332,7 +332,7 @@ void iounmap(volatile void __iomem *addr)
 	   cpa takes care of the direct mappings. */
 	read_lock(&vmlist_lock);
 	for (p = vmlist; p; p = p->next) {
-		if (p->addr == addr)
+		if (p->addr == (void __force *)addr)
 			break;
 	}
 	read_unlock(&vmlist_lock);
@@ -346,7 +346,7 @@ void iounmap(volatile void __iomem *addr)
 	free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p));
 
 	/* Finally remove it */
-	o = remove_vm_area((void *)addr);
+	o = remove_vm_area((void __force *)addr);
 	BUG_ON(p != o || o == NULL);
 	kfree(p);
 }
@@ -365,7 +365,7 @@ void *xlate_dev_mem_ptr(unsigned long phys)
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	addr = (void *)ioremap(start, PAGE_SIZE);
+	addr = (void __force *)ioremap(start, PAGE_SIZE);
 	if (addr)
 		addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
 
-- 
cgit v1.2.2


From 684eb0163a98bc329193b4aa4535cdd705a5dd58 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jirislaby@gmail.com>
Date: Mon, 12 May 2008 15:43:37 +0200
Subject: x86_64: use PAGE_OFFSET in dump_pagetables

Use PAGE_OFFSET macro instead of using 0xffff810000000000UL directly.

Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: hpa@zytor.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/dump_pagetables.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 2c24bea92c66..0bb0caed8971 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -42,7 +42,7 @@ static struct addr_marker address_markers[] = {
 	{ 0, "User Space" },
 #ifdef CONFIG_X86_64
 	{ 0x8000000000000000UL, "Kernel Space" },
-	{ 0xffff810000000000UL, "Low Kernel Mapping" },
+	{ PAGE_OFFSET,		"Low Kernel Mapping" },
 	{ VMALLOC_START,        "vmalloc() Area" },
 	{ VMEMMAP_START,        "Vmemmap" },
 	{ __START_KERNEL_map,   "High Kernel Mapping" },
-- 
cgit v1.2.2


From a0176e2485ce6468f9b74264a2fd6c19811f027a Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 16 Jun 2008 12:44:17 +0200
Subject: Revert "Revert "x86: fix ioapic bug again""

This reverts commit 0b6a39f7ebcb1c82587ce35b401c513eed41ac5c.

The changes in tip/x86/apic solve this better.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 12 ++++++++++--
 arch/x86/kernel/nmi_32.c     |  9 +++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 4dc8600d9d20..a40d54fc1fdd 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2130,10 +2130,14 @@ static inline void __init check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
 	int vector;
+	unsigned int ver;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
+	ver = apic_read(APIC_LVR);
+	ver = GET_APIC_VERSION(ver);
+
 	/*
 	 * get/set the timer IRQ vector:
 	 */
@@ -2146,11 +2150,15 @@ static inline void __init check_timer(void)
 	 * mode for the 8259A whenever interrupts are routed
 	 * through I/O APICs.  Also IRQ0 has to be enabled in
 	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.
+	 * disabled in the local APIC.  Finally timer interrupts
+	 * need to be acknowledged manually in the 8259A for
+	 * timer_interrupt() and for the i82489DX when using
+	 * the NMI watchdog.
 	 */
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	timer_ack = 1;
+	timer_ack = !cpu_has_tsc;
+	timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
 	if (timer_over_8254 > 0)
 		enable_8259A_irq(0);
 
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 84160f74eeb0..11b14bbaa61e 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -26,6 +26,7 @@
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
+#include <asm/timer.h>
 
 #include "mach_traps.h"
 
@@ -81,7 +82,7 @@ int __init check_nmi_watchdog(void)
 
 	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
-		return -1;
+		goto error;
 
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -118,7 +119,7 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active)) {
 		kfree(prev_nmi_count);
 		atomic_set(&nmi_active, -1);
-		return -1;
+		goto error;
 	}
 	printk("OK.\n");
 
@@ -129,6 +130,10 @@ int __init check_nmi_watchdog(void)
 
 	kfree(prev_nmi_count);
 	return 0;
+error:
+	timer_ack = !cpu_has_tsc;
+
+	return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
-- 
cgit v1.2.2


From d11d5794e0c21a1054e6cd57381050a999ad7232 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:09:11 +0100
Subject: x86: I/O APIC: AEOI timer acknowledgement clean-ups

The code that used to be in do_slow_gettimeoffset() that relied on the
IRR bit of the master 8259A PIC for IRQ0 to check the state of the output
timer 0 of the PIT is no longer there.  As a result, there is no need to
use the POLL command to acknowledge the timer interrupt in the "8259A
Virtual Wire", except for the NMI watchdog when the i82489DX APIC is used
(this is because this particular APIC treats NMIs as level-triggered and
keeping the input asserted would keep motherboard NMI sources held off for
too long).  Remove the unneeded bits and adjust comments accordingly.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 20 +++++++++-----------
 arch/x86/kernel/io_apic_64.c |  7 ++-----
 arch/x86/kernel/nmi_32.c     |  2 +-
 arch/x86/kernel/time_32.c    |  3 +--
 4 files changed, 13 insertions(+), 19 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a40d54fc1fdd..c64b3f5cc121 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2146,19 +2146,17 @@ static inline void __init check_timer(void)
 	set_intr_gate(vector, interrupt[0]);
 
 	/*
-	 * Subtle, code in do_timer_interrupt() expects an AEOI
-	 * mode for the 8259A whenever interrupts are routed
-	 * through I/O APICs.  Also IRQ0 has to be enabled in
-	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.  Finally timer interrupts
-	 * need to be acknowledged manually in the 8259A for
-	 * timer_interrupt() and for the i82489DX when using
-	 * the NMI watchdog.
+	 * As IRQ0 is to be enabled in the 8259A, the virtual
+	 * wire has to be disabled in the local APIC.  Also
+	 * timer interrupts need to be acknowledged manually in
+	 * the 8259A for the i82489DX when using the NMI
+	 * watchdog as that APIC treats NMIs as level-triggered.
+	 * The AEOI mode will finish them in the 8259A
+	 * automatically.
 	 */
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	timer_ack = !cpu_has_tsc;
-	timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+	timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
 	if (timer_over_8254 > 0)
 		enable_8259A_irq(0);
 
@@ -2219,6 +2217,7 @@ static inline void __init check_timer(void)
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
 		nmi_watchdog = 0;
 	}
+	timer_ack = 0;
 
 	printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
@@ -2237,7 +2236,6 @@ static inline void __init check_timer(void)
 
 	printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
 
-	timer_ack = 0;
 	init_8259A(0);
 	make_8259A_irq(0);
 	apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index ef1a8dfcc529..7c34e38e4219 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1669,11 +1669,8 @@ static inline void __init check_timer(void)
 	assign_irq_vector(0, TARGET_CPUS);
 
 	/*
-	 * Subtle, code in do_timer_interrupt() expects an AEOI
-	 * mode for the 8259A whenever interrupts are routed
-	 * through I/O APICs.  Also IRQ0 has to be enabled in
-	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.
+	 * As IRQ0 is to be enabled in the 8259A, the virtual
+	 * wire has to be disabled in the local APIC.
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 11b14bbaa61e..d322901c38e6 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -131,7 +131,7 @@ int __init check_nmi_watchdog(void)
 	kfree(prev_nmi_count);
 	return 0;
 error:
-	timer_ack = !cpu_has_tsc;
+	timer_ack = 0;
 
 	return -1;
 }
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index 2ff21f398934..5f29f12da50c 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -84,8 +84,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 	if (timer_ack) {
 		/*
 		 * Subtle, when I/O APICs are used we have to ack timer IRQ
-		 * manually to reset the IRR bit for do_slow_gettimeoffset().
-		 * This will also deassert NMI lines for the watchdog if run
+		 * manually to deassert NMI lines for the watchdog if run
 		 * on an 82489DX-based system.
 		 */
 		spin_lock(&i8259A_lock);
-- 
cgit v1.2.2


From ecd29476ae0143b1c3641edfa76c0fc3e9ad3021 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:09:19 +0100
Subject: x86: I/O APIC: remove parameters to fiddle with the 8259A

Remove the "disable_8254_timer" and "enable_8254_timer" kernel
parameters.  Now that AEOI acknowledgements are no longer needed for
correct timer operation, the 8259A can be kept disabled unconditionally
unless interrupts, either timer or watchdog ones, are actually passed
through it.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/early-quirks.c | 13 -------------
 arch/x86/kernel/io_apic_32.c   | 21 ++-------------------
 arch/x86/kernel/io_apic_64.c   | 21 ++-------------------
 3 files changed, 4 insertions(+), 51 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 9f51e1ea9e82..84fd9f2a28ff 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -98,17 +98,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
 
 }
 
-static void __init ati_bugs(int num, int slot, int func)
-{
-#ifdef CONFIG_X86_IO_APIC
-	if (timer_over_8254 == 1) {
-		timer_over_8254 = 0;
-		printk(KERN_INFO
-		"ATI board detected. Disabling timer routing over 8254.\n");
-	}
-#endif
-}
-
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -126,8 +115,6 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
 	{ PCI_VENDOR_ID_VIA, PCI_ANY_ID,
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
-	{ PCI_VENDOR_ID_ATI, PCI_ANY_ID,
-	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, ati_bugs },
 	{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
 	  PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
 	{}
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index c64b3f5cc121..61cf366d040f 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -58,7 +58,6 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 static DEFINE_SPINLOCK(ioapic_lock);
 static DEFINE_SPINLOCK(vector_lock);
 
-int timer_over_8254 __initdata = 1;
 
 /*
  *	Is the SiS APIC rmw bug present ?
@@ -2157,8 +2156,6 @@ static inline void __init check_timer(void)
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
 	timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
-	if (timer_over_8254 > 0)
-		enable_8259A_irq(0);
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2175,7 +2172,6 @@ static inline void __init check_timer(void)
 		unmask_IO_APIC_irq(0);
 		if (timer_irq_works()) {
 			if (nmi_watchdog == NMI_IO_APIC) {
-				disable_8259A_irq(0);
 				setup_nmi();
 				enable_8259A_irq(0);
 			}
@@ -2195,6 +2191,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			printk("works.\n");
 			if (pin1 != -1)
@@ -2209,6 +2206,7 @@ static inline void __init check_timer(void)
 		/*
 		 * Cleanup, just in case ...
 		 */
+		disable_8259A_irq(0);
 		clear_IO_APIC_pin(apic2, pin2);
 	}
 	printk(" failed.\n");
@@ -2221,7 +2219,6 @@ static inline void __init check_timer(void)
 
 	printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
-	disable_8259A_irq(0);
 	set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
 				      "fasteoi");
 	apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);	/* Fixed mode */
@@ -2292,20 +2289,6 @@ void __init setup_IO_APIC(void)
 		print_IO_APIC();
 }
 
-static int __init setup_disable_8254_timer(char *s)
-{
-	timer_over_8254 = -1;
-	return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
-	timer_over_8254 = 2;
-	return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
 /*
  *	Called after all the initialization is done. If we didnt find any
  *	APIC bugs then we can allow the modify fast path
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 7c34e38e4219..9f16ca4b5a24 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -90,7 +90,6 @@ static int no_timer_check;
 
 static int disable_timer_pin_1 __initdata;
 
-int timer_over_8254 __initdata = 1;
 
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -430,20 +429,6 @@ static int __init disable_timer_pin_setup(char *arg)
 }
 __setup("disable_timer_pin_1", disable_timer_pin_setup);
 
-static int __init setup_disable_8254_timer(char *s)
-{
-	timer_over_8254 = -1;
-	return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
-	timer_over_8254 = 2;
-	return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -1674,8 +1659,6 @@ static inline void __init check_timer(void)
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	if (timer_over_8254 > 0)
-		enable_8259A_irq(0);
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
@@ -1693,7 +1676,6 @@ static inline void __init check_timer(void)
 		if (!no_timer_check && timer_irq_works()) {
 			nmi_watchdog_default();
 			if (nmi_watchdog == NMI_IO_APIC) {
-				disable_8259A_irq(0);
 				setup_nmi();
 				enable_8259A_irq(0);
 			}
@@ -1715,6 +1697,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
 			nmi_watchdog_default();
@@ -1726,6 +1709,7 @@ static inline void __init check_timer(void)
 		/*
 		 * Cleanup, just in case ...
 		 */
+		disable_8259A_irq(0);
 		clear_IO_APIC_pin(apic2, pin2);
 	}
 	apic_printk(APIC_VERBOSE," failed.\n");
@@ -1737,7 +1721,6 @@ static inline void __init check_timer(void)
 
 	apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
-	disable_8259A_irq(0);
 	irq_desc[0].chip = &lapic_irq_type;
 	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
 	enable_8259A_irq(0);
-- 
cgit v1.2.2


From e67465f1298671266a8e824c1751afdb7c08c860 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:09:26 +0100
Subject: x86: I/O APIC: clean up after a fasteoi failure

Disable the 8259A when routing of the timer interrupt through the chip to
the local APIC of the primary processor has failed.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 1 +
 arch/x86/kernel/io_apic_64.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 61cf366d040f..e7b7655c4e94 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2228,6 +2228,7 @@ static inline void __init check_timer(void)
 		printk(" works.\n");
 		goto out;
 	}
+	disable_8259A_irq(0);
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
 	printk(" failed.\n");
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 9f16ca4b5a24..6433fc99f1f9 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1729,6 +1729,7 @@ static inline void __init check_timer(void)
 		apic_printk(APIC_VERBOSE," works.\n");
 		goto out;
 	}
+	disable_8259A_irq(0);
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_VERBOSE," failed.\n");
 
-- 
cgit v1.2.2


From 60134ebe795b728dbb960485a8e873c3250ada36 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:09:34 +0100
Subject: x86: I/O APIC: keep IRQ off when changing LVT registers

Disable the 8259A acting in the "virtual wire" mode to keep the interrupt
line inactive while fiddling with local APIC interrupt vector registers
associated with its destination inputs.  To be on the safe side,
especially concerning flipping the trigger mode.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 2 ++
 arch/x86/kernel/io_apic_64.c | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index e7b7655c4e94..41218ac75d10 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2199,7 +2199,9 @@ static inline void __init check_timer(void)
 			else
 				add_pin_to_irq(0, apic2, pin2);
 			if (nmi_watchdog == NMI_IO_APIC) {
+				disable_8259A_irq(0);
 				setup_nmi();
+				enable_8259A_irq(0);
 			}
 			goto out;
 		}
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 6433fc99f1f9..aa45a85c4d11 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1702,7 +1702,9 @@ static inline void __init check_timer(void)
 			apic_printk(APIC_VERBOSE," works.\n");
 			nmi_watchdog_default();
 			if (nmi_watchdog == NMI_IO_APIC) {
+				disable_8259A_irq(0);
 				setup_nmi();
+				enable_8259A_irq(0);
 			}
 			goto out;
 		}
-- 
cgit v1.2.2


From 73d08e636026bbcb413d4864ca5e917502f8a0f9 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:09:43 +0100
Subject: x86: APIC/SMP: correct the message for "nosmp"

The local APIC is no longer forced off when "nosmp" has been specified.
Correct the message printed.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/smpboot.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3e1cecedde42..8c53d86e3e86 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1157,8 +1157,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	 * If SMP should be disabled, then really disable it!
 	 */
 	if (!max_cpus) {
-		printk(KERN_INFO "SMP mode deactivated,"
-				 "forcing use of dummy APIC emulation.\n");
+		printk(KERN_INFO "SMP mode deactivated.\n");
 		smpboot_clear_io_apic();
 #ifdef CONFIG_X86_32
 		connect_bsp_APIC();
-- 
cgit v1.2.2


From a1133d8e4ffc2db751eb987a2f3cf8ead67927c3 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:10:16 +0100
Subject: x86: APIC/SMP: downgrade the NMI watchdog for "nosmp"

If configured to use the I/O APIC, the NMI watchdog is deemed to fail if
the chip has been deactivated as a result of "nosmp".  Downgrade to the
local APIC watchdog similarly to what is done for the UP case.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/smpboot.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8c53d86e3e86..df60bc7c9cb7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1159,6 +1159,10 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	if (!max_cpus) {
 		printk(KERN_INFO "SMP mode deactivated.\n");
 		smpboot_clear_io_apic();
+
+		if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
+			nmi_watchdog = NMI_LOCAL_APIC;
+
 #ifdef CONFIG_X86_32
 		connect_bsp_APIC();
 #endif
-- 
cgit v1.2.2


From 35542c5ebced864776d90d83d1e255016fd4c084 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Wed, 21 May 2008 22:10:22 +0100
Subject: x86: I/O APIC: clean up the 8259A on a NMI watchdog failure

There is no point in keeping the 8259A enabled if the I/O APIC NMI
watchdog has failed and the 8259A is not used to pass through regular
timer interrupts.  This fixes problems with some systems where some logic
gets confused.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c |  2 ++
 arch/x86/kernel/io_apic_64.c |  2 ++
 arch/x86/kernel/nmi_32.c     |  4 ++++
 arch/x86/kernel/nmi_64.c     | 11 +++++++++--
 4 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 41218ac75d10..7c7d88ebb966 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -58,6 +58,7 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 static DEFINE_SPINLOCK(ioapic_lock);
 static DEFINE_SPINLOCK(vector_lock);
 
+int timer_through_8259 __initdata;
 
 /*
  *	Is the SiS APIC rmw bug present ?
@@ -2194,6 +2195,7 @@ static inline void __init check_timer(void)
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			printk("works.\n");
+			timer_through_8259 = 1;
 			if (pin1 != -1)
 				replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
 			else
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index aa45a85c4d11..2a60bfb7446f 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -90,6 +90,7 @@ static int no_timer_check;
 
 static int disable_timer_pin_1 __initdata;
 
+int timer_through_8259 __initdata;
 
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -1700,6 +1701,7 @@ static inline void __init check_timer(void)
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
+			timer_through_8259 = 1;
 			nmi_watchdog_default();
 			if (nmi_watchdog == NMI_IO_APIC) {
 				disable_8259A_irq(0);
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index d322901c38e6..6580dae46277 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -24,6 +24,8 @@
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/nmi.h>
 #include <asm/timer.h>
@@ -131,6 +133,8 @@ int __init check_nmi_watchdog(void)
 	kfree(prev_nmi_count);
 	return 0;
 error:
+	if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+		disable_8259A_irq(0);
 	timer_ack = 0;
 
 	return -1;
diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c
index 5a29ded994fa..0060e44e8989 100644
--- a/arch/x86/kernel/nmi_64.c
+++ b/arch/x86/kernel/nmi_64.c
@@ -21,6 +21,8 @@
 #include <linux/cpumask.h>
 #include <linux/kdebug.h>
 
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/nmi.h>
 #include <asm/proto.h>
@@ -90,7 +92,7 @@ int __init check_nmi_watchdog(void)
 
 	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
-		return -1;
+		goto error;
 
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -121,7 +123,7 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active)) {
 		kfree(prev_nmi_count);
 		atomic_set(&nmi_active, -1);
-		return -1;
+		goto error;
 	}
 	printk("OK.\n");
 
@@ -132,6 +134,11 @@ int __init check_nmi_watchdog(void)
 
 	kfree(prev_nmi_count);
 	return 0;
+error:
+	if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+		disable_8259A_irq(0);
+
+	return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
-- 
cgit v1.2.2


From 9a1c61929121cbd597a5575f82711c0db8ee1778 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:09 +0100
Subject: x86: I/O APIC: fix the name of the L-APIC IRQ handler

The local APIC interrupt handler gets registered with
set_irq_chip_and_handler_name(), which results in
"local-APIC-edge-fasteoi" reported as the name of the handler.  Fix by
removing the type of the handler left over from before the generic
handlers were introduced.

The 64-bit variation should get fixed with the upcoming merge.

NB It should really use the "edge" handler and not the "fasteoi" one,
but that's a separate issue.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 7c7d88ebb966..7064500f00f2 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2037,7 +2037,7 @@ static void unmask_lapic_irq (unsigned int irq)
 }
 
 static struct irq_chip lapic_chip __read_mostly = {
-	.name		= "local-APIC-edge",
+	.name		= "local-APIC",
 	.mask		= mask_lapic_irq,
 	.unmask		= unmask_lapic_irq,
 	.eoi		= ack_apic,
-- 
cgit v1.2.2


From f08252623c7981f5cea70e4fab4983a94fc52212 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:16 +0100
Subject: x86: I/O APIC: fix the name of the through-8259A handler

When the through-8259A mode is used for the timer, the call to
set_irq_handler() will register a NULL handler name, resulting in
"IO-APIC-<NULL>" reported.  Fix by calling ioapic_register_intr() as done
for all the other I/O APIC interrupts.

The 64-bit variation calls set_irq_chip_and_handler_name() here
needlessly and should get fixed with the upcoming merge.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 7064500f00f2..c93c0d3c1a6b 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1331,8 +1331,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 	 * The timer IRQ doesn't have to know that behind the
 	 * scene we have a 8259A-master in AEOI mode ...
 	 */
-	irq_desc[0].chip = &ioapic_chip;
-	set_irq_handler(0, handle_edge_irq);
+	ioapic_register_intr(0, vector, IOAPIC_EDGE);
 
 	/*
 	 * Add it to the IO-APIC irq-routing table:
-- 
cgit v1.2.2


From 80d16bace63e057d30337e48d70aef0881656457 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:22 +0100
Subject: x86: I/O APIC: remove redundant 8259A {,un}masking

For a better control the masking and unmasking of the timer interrupt
line in the 8259A operating in the 'Virtual Wire' mode has been moved out
of setup_ExtINT_IRQ0_pin() now, so remove the redundant calls from the
function.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 4 ----
 arch/x86/kernel/io_apic_64.c | 4 ----
 2 files changed, 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index c93c0d3c1a6b..6e743ecf863b 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1310,8 +1310,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	memset(&entry,0,sizeof(entry));
 
-	disable_8259A_irq(0);
-
 	/* mask LVT0 */
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 
@@ -1337,8 +1335,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 	 * Add it to the IO-APIC irq-routing table:
 	 */
 	ioapic_write_entry(apic, pin, entry);
-
-	enable_8259A_irq(0);
 }
 
 void __init print_IO_APIC(void)
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 2a60bfb7446f..83d4e117746b 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -906,8 +906,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	memset(&entry, 0, sizeof(entry));
 
-	disable_8259A_irq(0);
-
 	/* mask LVT0 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 
@@ -933,8 +931,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 	 * Add it to the IO-APIC irq-routing table:
 	 */
 	ioapic_write_entry(apic, pin, entry);
-
-	enable_8259A_irq(0);
 }
 
 void __apicdebuginit print_IO_APIC(void)
-- 
cgit v1.2.2


From 6b4722a7779ebadcf016fd96ce3156b6acda8a31 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:28 +0100
Subject: x86: I/O APIC: remove redundant LVT0 masking

The LINT0 line of the local APIC is masked in the LVT0 entry in
check_timer() before this function is ever called.  Removed the
redundant unmasking for better control.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 3 ---
 arch/x86/kernel/io_apic_64.c | 3 ---
 2 files changed, 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 6e743ecf863b..51e5519ee1a7 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1310,9 +1310,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	memset(&entry,0,sizeof(entry));
 
-	/* mask LVT0 */
-	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
 	/*
 	 * We use logical delivery to get the timer IRQ
 	 * to the first CPU.
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 83d4e117746b..565f19b01bf4 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -906,9 +906,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	memset(&entry, 0, sizeof(entry));
 
-	/* mask LVT0 */
-	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
 	/*
 	 * We use logical delivery to get the timer IRQ
 	 * to the first CPU.
-- 
cgit v1.2.2


From f7633ce55b2ea2926a39d7ca9d0bb06c43edd2c2 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:34 +0100
Subject: x86: I/O APIC: rename setup_ExtINT_IRQ0_pin()

Rename setup_ExtINT_IRQ0_pin() to setup_timer_IRQ0_pin() to better
reflect the upcoming role of a function setting up a (semi-)arbitrary I/O
APIC pin appropriately for the 8254 timer.  By "appropriate" the following
settings are meant: edge-triggered, active-high, all the other settings
per-architecture.  Adjust comments to reflect code appropriately.  No
functional changes.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c |  9 +++++----
 arch/x86/kernel/io_apic_64.c | 10 +++++-----
 2 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 51e5519ee1a7..ce682e873aa7 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1302,9 +1302,10 @@ static void __init setup_IO_APIC_irqs(void)
 }
 
 /*
- * Set up the 8259A-master output pin:
+ * Set up the timer pin, possibly with the 8259A-master behind.
  */
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+					int vector)
 {
 	struct IO_APIC_route_entry entry;
 
@@ -1324,7 +1325,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	/*
 	 * The timer IRQ doesn't have to know that behind the
-	 * scene we have a 8259A-master in AEOI mode ...
+	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
 	ioapic_register_intr(0, vector, IOAPIC_EDGE);
 
@@ -2183,7 +2184,7 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+		setup_timer_IRQ0_pin(apic2, pin2, vector);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			printk("works.\n");
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 565f19b01bf4..6c4635fa97a6 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -897,10 +897,10 @@ static void __init setup_IO_APIC_irqs(void)
 }
 
 /*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
  */
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+					int vector)
 {
 	struct IO_APIC_route_entry entry;
 
@@ -920,7 +920,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
 
 	/*
 	 * The timer IRQ doesn't have to know that behind the
-	 * scene we have a 8259A-master in AEOI mode ...
+	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
 	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
@@ -1690,7 +1690,7 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
-- 
cgit v1.2.2


From 24742ece8eb01b5855059020ba1c09173fd9b732 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:40 +0100
Subject: x86: I/O APIC: unmask the second-chance timer interrupt

Unmask the timer interrupt line set up in the through-8259A mode
explicitly after setup_timer_IRQ0_pin() has set up the I/O APIC interrupt
redirection entry to let the two operations be unbound from each other.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 1 +
 arch/x86/kernel/io_apic_64.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index ce682e873aa7..b381f93b79ae 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2185,6 +2185,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		setup_timer_IRQ0_pin(apic2, pin2, vector);
+		unmask_IO_APIC_irq(0);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			printk("works.\n");
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 6c4635fa97a6..0e20b7d7c1c7 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1691,6 +1691,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+		unmask_IO_APIC_irq(0);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
-- 
cgit v1.2.2


From 03be750559b2fe20d85dd968e08d5fe1c3accf83 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:45 +0100
Subject: x86: I/O APIC: keep the timer IRQ masked during set-up

Keep the timer interrupt line masked when reconfiguring its interrupt
redirection entry in the I/O APIC.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 2 +-
 arch/x86/kernel/io_apic_64.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index b381f93b79ae..63a2f64c765b 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1316,7 +1316,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 	 * to the first CPU.
 	 */
 	entry.dest_mode = INT_DEST_MODE;
-	entry.mask = 0;					/* unmask IRQ now */
+	entry.mask = 1;					/* mask IRQ now */
 	entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
 	entry.delivery_mode = INT_DELIVERY_MODE;
 	entry.polarity = 0;
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 0e20b7d7c1c7..ae0ac990574f 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -911,7 +911,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 	 * to the first CPU.
 	 */
 	entry.dest_mode = INT_DEST_MODE;
-	entry.mask = 0;					/* unmask IRQ now */
+	entry.mask = 1;					/* mask IRQ now */
 	entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
 	entry.delivery_mode = INT_DELIVERY_MODE;
 	entry.polarity = 0;
-- 
cgit v1.2.2


From 691874fa96d6349a8b60f8ea9c2bae52ece79941 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Tue, 27 May 2008 21:19:51 +0100
Subject: x86: I/O APIC: timer through 8259A second-chance

Some systems incorrectly report the ExtINTA pin of the I/O APIC as the
genuine target of the timer interrupt.  Here is a change that copies timer
pin information found to the other pin if one has been found only.  This
way both a direct and a through-8259A route is tested with the pin letting
these problematic systems work well enough.  If no timer pin information
has been found for the I/O APIC, then local APIC variations are tried
only, similarly to what is done without the change (except without the
misleading messages).

Obviously if we try the first-chance path without being told by the BIOS
to do so, we should not complain either, so do not print the message in
this case.

The 64-bit variation should be updated with a call to
replace_pin_at_irq() which can be done with the upcoming merge.  Since
add_pin_to_irq() is now always called in the first-chance path, the
condition to require it in the second-chance path no longer happens.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 38 ++++++++++++++++++++++++++++----------
 arch/x86/kernel/io_apic_64.c | 36 +++++++++++++++++++++++++++++-------
 2 files changed, 57 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 63a2f64c765b..a69a59d19e18 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2122,6 +2122,7 @@ static inline void __init unlock_ExtINT_logic(void)
 static inline void __init check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
+	int no_pin1 = 0;
 	int vector;
 	unsigned int ver;
 	unsigned long flags;
@@ -2159,10 +2160,30 @@ static inline void __init check_timer(void)
 	printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
 		vector, apic1, pin1, apic2, pin2);
 
+	/*
+	 * Some BIOS writers are clueless and report the ExtINTA
+	 * I/O APIC input from the cascaded 8259A as the timer
+	 * interrupt input.  So just in case, if only one pin
+	 * was found above, try it both directly and through the
+	 * 8259A.
+	 */
+	if (pin1 == -1) {
+		pin1 = pin2;
+		apic1 = apic2;
+		no_pin1 = 1;
+	} else if (pin2 == -1) {
+		pin2 = pin1;
+		apic2 = apic1;
+	}
+
 	if (pin1 != -1) {
 		/*
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
+		if (no_pin1) {
+			add_pin_to_irq(0, apic1, pin1);
+			setup_timer_IRQ0_pin(apic1, pin1, vector);
+		}
 		unmask_IO_APIC_irq(0);
 		if (timer_irq_works()) {
 			if (nmi_watchdog == NMI_IO_APIC) {
@@ -2174,26 +2195,23 @@ static inline void __init check_timer(void)
 			goto out;
 		}
 		clear_IO_APIC_pin(apic1, pin1);
-		printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
-				"IO-APIC\n");
-	}
+		if (!no_pin1)
+			printk(KERN_ERR "..MP-BIOS bug: "
+			       "8254 timer not connected to IO-APIC\n");
 
-	printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... ");
-	if (pin2 != -1) {
+		printk(KERN_INFO "...trying to set up timer (IRQ0) "
+		       "through the 8259A ... ");
 		printk("\n..... (found pin %d) ...", pin2);
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
+		replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, vector);
 		unmask_IO_APIC_irq(0);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			printk("works.\n");
 			timer_through_8259 = 1;
-			if (pin1 != -1)
-				replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
-			else
-				add_pin_to_irq(0, apic2, pin2);
 			if (nmi_watchdog == NMI_IO_APIC) {
 				disable_8259A_irq(0);
 				setup_nmi();
@@ -2206,8 +2224,8 @@ static inline void __init check_timer(void)
 		 */
 		disable_8259A_irq(0);
 		clear_IO_APIC_pin(apic2, pin2);
+		printk(" failed.\n");
 	}
-	printk(" failed.\n");
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index ae0ac990574f..9a54b779abd4 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1638,6 +1638,7 @@ static inline void __init check_timer(void)
 	struct irq_cfg *cfg = irq_cfg + 0;
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
+	int no_pin1 = 0;
 
 	local_irq_save(flags);
 
@@ -1662,10 +1663,30 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
 		cfg->vector, apic1, pin1, apic2, pin2);
 
+	/*
+	 * Some BIOS writers are clueless and report the ExtINTA
+	 * I/O APIC input from the cascaded 8259A as the timer
+	 * interrupt input.  So just in case, if only one pin
+	 * was found above, try it both directly and through the
+	 * 8259A.
+	 */
+	if (pin1 == -1) {
+		pin1 = pin2;
+		apic1 = apic2;
+		no_pin1 = 1;
+	} else if (pin2 == -1) {
+		pin2 = pin1;
+		apic2 = apic1;
+	}
+
 	if (pin1 != -1) {
 		/*
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
+		if (no_pin1) {
+			add_pin_to_irq(0, apic1, pin1);
+			setup_timer_IRQ0_pin(apic1, pin1, vector);
+		}
 		unmask_IO_APIC_irq(0);
 		if (!no_timer_check && timer_irq_works()) {
 			nmi_watchdog_default();
@@ -1678,18 +1699,19 @@ static inline void __init check_timer(void)
 			goto out;
 		}
 		clear_IO_APIC_pin(apic1, pin1);
-		apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
-				"connected to IO-APIC\n");
-	}
+		if (!no_pin1)
+			apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+				    "8254 timer not connected to IO-APIC\n");
 
-	apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
-				"through the 8259A ... ");
-	if (pin2 != -1) {
+		apic_printk(APIC_VERBOSE,KERN_INFO
+			"...trying to set up timer (IRQ0) "
+			"through the 8259A ... ");
 		apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
 			apic2, pin2);
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
+		/* replace_pin_at_irq(0, apic1, pin1, apic2, pin2); */
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		unmask_IO_APIC_irq(0);
 		enable_8259A_irq(0);
@@ -1709,8 +1731,8 @@ static inline void __init check_timer(void)
 		 */
 		disable_8259A_irq(0);
 		clear_IO_APIC_pin(apic2, pin2);
+		apic_printk(APIC_VERBOSE," failed.\n");
 	}
-	apic_printk(APIC_VERBOSE," failed.\n");
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
-- 
cgit v1.2.2


From 071565095897dff9668cd4a2343160ae31538c27 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:37 +0200
Subject: x86: move pci_routirq declaration to pci.h

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/pci/acpi.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d95de2f199cd..464279da49c4 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -218,7 +218,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 	return bus;
 }
 
-extern int pci_routeirq;
 static int __init pci_acpi_init(void)
 {
 	struct pci_dev *dev = NULL;
-- 
cgit v1.2.2


From 7223daf5e1a6298e459db84442adc04d68a6a42d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:36 +0200
Subject: x86: make irq_cfg static

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 9a54b779abd4..bb3033f037c3 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -61,7 +61,7 @@ struct irq_cfg {
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
 	[0]  = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
 	[1]  = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
 	[2]  = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
-- 
cgit v1.2.2


From 431ee79db0a9552314d787446044973a8176b57d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 12 May 2008 15:43:35 +0200
Subject: x86: apic_64.c fix sparse warnings about shadowed variables

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_64.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc29..07fda23a9f76 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -875,7 +875,7 @@ static int __init detect_init_APIC(void)
 
 void __init early_init_lapic_mapping(void)
 {
-	unsigned long apic_phys;
+	unsigned long phys_addr;
 
 	/*
 	 * If no local APIC can be found then go out
@@ -884,11 +884,11 @@ void __init early_init_lapic_mapping(void)
 	if (!smp_found_config)
 		return;
 
-	apic_phys = mp_lapic_addr;
+	phys_addr = mp_lapic_addr;
 
-	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+	set_fixmap_nocache(FIX_APIC_BASE, phys_addr);
 	apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
-				 APIC_BASE, apic_phys);
+		    APIC_BASE, phys_addr);
 
 	/*
 	 * Fetch the APIC ID of the BSP in case we have a
-- 
cgit v1.2.2


From b1b57ee135ac7614184faa7d7345b5e7098cb81d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sat, 31 May 2008 12:20:10 +0200
Subject: x86 build fix:

  arch/x86/kernel/io_apic_64.c: In function 'check_timer':
  arch/x86/kernel/io_apic_64.c:1688: error: 'vector' undeclared (first use in this function)
  arch/x86/kernel/io_apic_64.c:1688: error: (Each undeclared identifier is reported only once
  arch/x86/kernel/io_apic_64.c:1688: error: for each function it appears in.)
---
 arch/x86/kernel/io_apic_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index bb3033f037c3..8991567c76b7 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1685,7 +1685,7 @@ static inline void __init check_timer(void)
 		 */
 		if (no_pin1) {
 			add_pin_to_irq(0, apic1, pin1);
-			setup_timer_IRQ0_pin(apic1, pin1, vector);
+			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		}
 		unmask_IO_APIC_irq(0);
 		if (!no_timer_check && timer_irq_works()) {
-- 
cgit v1.2.2


From 067fa0ff0c89d25c2136ed095c72213089d4bb4e Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Thu, 29 May 2008 22:32:30 +0400
Subject: x86: IO-APIC - use NMI_NONE instead of numeric constant

Not sure but maybe it is better to use NMI_DISABLED,
will take a look. But for now this patch is not change
anything in logic so it will not hurt/broke the kernel.
For most cases nmi_watchdog assignment is by one of NMI_*
macro so I think there it make sense too.

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 2 +-
 arch/x86/kernel/io_apic_64.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a69a59d19e18..5c0f8d6496a6 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2229,7 +2229,7 @@ static inline void __init check_timer(void)
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
-		nmi_watchdog = 0;
+		nmi_watchdog = NMI_NONE;
 	}
 	timer_ack = 0;
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8991567c76b7..40a184d4dff8 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1736,7 +1736,7 @@ static inline void __init check_timer(void)
 
 	if (nmi_watchdog == NMI_IO_APIC) {
 		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
-		nmi_watchdog = 0;
+		nmi_watchdog = NMI_NONE;
 	}
 
 	apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
-- 
cgit v1.2.2


From ff11571b25152edfb1eb0e6feb7e0009670fe4a5 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Thu, 5 Jun 2008 11:17:16 +0200
Subject: x86, io-apic: fix nmi_watchdog=1 bootup hang

nmi_watchdog=1 hangs on 64-bit:

[    0.250000] Detected 12.564 MHz APIC timer.
[    0.254178] APIC timer registered as dummy, due to nmi_watchdog=1!
[    0.260366] Testing NMI watchdog ... <4>WARNING: CPU#0: NMI appears to be stuck (0->0)!
[    ...     ]
[    0.470003] calling  genl_init+0x0/0xd0
[  hard hang ]

bisected it down to:

 git-bisect start
 git-bisect good 1beee8dc8cf58e3f605bd7b34d7a39939be7d8d2
 git-bisect bad 11582ece0aaa2d0f94f345c08a4ab9997078a083
 git-bisect bad 5479c623bb44089844022c03d4c0eb16d5b7a15f
 git-bisect bad cfb4c7fabeb499e1c29f9d1878968e37a938e28a
 git-bisect good 246dd412d31e4f5de1d43aa6422a325b785f36e4
 git-bisect bad 3f8237eaff7dc1e35fa791dae095574fd974e671
 git-bisect good 90e23b13ab849e2a11f00c655eb3a2011b4623be
 git-bisect bad 833526a34eeefc117df3191a594c3c3a4f15a9ac
 git-bisect good 791b93d3dfaf16c23e978bec0cc0a3dd9d855d63
 git-bisect bad 65767c64068f2c93e56a1accfed5c78230ac12d7
 git-bisect bad 2abc5c05dd82c188e3bdf6641a274f013348d14b
 git-bisect bad 317e1f2597ffb4d4db940577bbe56dc6e881ef07

| 317e1f2597ffb4d4db940577bbe56dc6e881ef07 is first bad commit
| commit 317e1f2597ffb4d4db940577bbe56dc6e881ef07
| Author: Maciej W. Rozycki <macro@linux-mips.org>
| Date:   Wed May 21 22:10:22 2008 +0100
|     x86: I/O APIC: clean up the 8259A on a NMI watchdog failure

the problem is that in the dummy-lapic branch we rely on the i8259A
but if the NMI watchdog fails we turn off IRQ 0 - which doesnt work
too well ;-)

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_32.c | 6 ++++--
 arch/x86/kernel/apic_64.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6c..3cebf91d500f 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -541,11 +541,13 @@ void __init setup_boot_APIC_clock(void)
 		 * PIT/HPET going.  Otherwise register lapic as a dummy
 		 * device.
 		 */
-		if (nmi_watchdog != NMI_IO_APIC)
+		if (nmi_watchdog != NMI_IO_APIC) {
 			lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-		else
+		} else {
 			printk(KERN_WARNING "APIC timer registered as dummy,"
 			       " due to nmi_watchdog=1!\n");
+			timer_through_8259 = 1;
+		}
 	}
 
 	/* Setup the lapic or request the broadcast */
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 07fda23a9f76..6cbc668a4c63 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -413,11 +413,13 @@ void __init setup_boot_APIC_clock(void)
 	 * PIT/HPET going.  Otherwise register lapic as a dummy
 	 * device.
 	 */
-	if (nmi_watchdog != NMI_IO_APIC)
+	if (nmi_watchdog != NMI_IO_APIC) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-	else
+	} else {
 		printk(KERN_WARNING "APIC timer registered as dummy,"
 		       " due to nmi_watchdog=1!\n");
+		timer_through_8259 = 1;
+	}
 
 	setup_APIC_timer();
 }
-- 
cgit v1.2.2


From ab5a5be099cb20a1c006bf0e211c48502d7ebc44 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 8 Jun 2008 10:13:33 +0200
Subject: Revert "x86, io-apic: fix nmi_watchdog=1 bootup hang"

This reverts commit 2229ff84f01746d02fb6b79e156fb5cce48c908f.

A better fix from Maciej will be merged.
---
 arch/x86/kernel/apic_32.c | 6 ++----
 arch/x86/kernel/apic_64.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 3cebf91d500f..4b99b1bdeb6c 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -541,13 +541,11 @@ void __init setup_boot_APIC_clock(void)
 		 * PIT/HPET going.  Otherwise register lapic as a dummy
 		 * device.
 		 */
-		if (nmi_watchdog != NMI_IO_APIC) {
+		if (nmi_watchdog != NMI_IO_APIC)
 			lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-		} else {
+		else
 			printk(KERN_WARNING "APIC timer registered as dummy,"
 			       " due to nmi_watchdog=1!\n");
-			timer_through_8259 = 1;
-		}
 	}
 
 	/* Setup the lapic or request the broadcast */
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 6cbc668a4c63..07fda23a9f76 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -413,13 +413,11 @@ void __init setup_boot_APIC_clock(void)
 	 * PIT/HPET going.  Otherwise register lapic as a dummy
 	 * device.
 	 */
-	if (nmi_watchdog != NMI_IO_APIC) {
+	if (nmi_watchdog != NMI_IO_APIC)
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-	} else {
+	else
 		printk(KERN_WARNING "APIC timer registered as dummy,"
 		       " due to nmi_watchdog=1!\n");
-		timer_through_8259 = 1;
-	}
 
 	setup_APIC_timer();
 }
-- 
cgit v1.2.2


From 6fe9fe875691e15eda61b992e03257e68aa5ba4f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 8 Jun 2008 10:14:40 +0200
Subject: Revert "x86: APIC/SMP: downgrade the NMI watchdog for "nosmp""

This reverts commit 791b93d3dfaf16c23e978bec0cc0a3dd9d855d63.

A better fix from Maciej will be merged.
---
 arch/x86/kernel/smpboot.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index df60bc7c9cb7..8c53d86e3e86 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1159,10 +1159,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	if (!max_cpus) {
 		printk(KERN_INFO "SMP mode deactivated.\n");
 		smpboot_clear_io_apic();
-
-		if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
-			nmi_watchdog = NMI_LOCAL_APIC;
-
 #ifdef CONFIG_X86_32
 		connect_bsp_APIC();
 #endif
-- 
cgit v1.2.2


From acae7d906f2f81d814e9c3730eeb19dfd3bf3bb4 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Fri, 6 Jun 2008 03:27:49 +0100
Subject: x86: APIC/UP: Downgrade the NMI watchdog for no I/O APIC

 If configured to use the I/O APIC, the NMI watchdog is deemed to fail if
the chip will not be used in the UP configuration, because "noapic" has
been specified or the chip is simply not there.  Downgrade to the local
APIC watchdog to rectify.

The new #ifdef is ugly, I know.  A proper solution is to provide suitable
definitions of smp_found_config, etc. for !CONFIG_X86_IO_APIC in a header.
Likewise the whole if () condition should be moved to a static inline
function.  Such clean-ups are beyond the scope of this change and can be
done once the whole issue of the timer has been sorted out.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_32.c | 4 ++++
 arch/x86/kernel/apic_64.c | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6c..26e7a62e9ab6 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1269,6 +1269,10 @@ int __init APIC_init_uniprocessor(void)
 
 	setup_local_APIC();
 
+#ifdef CONFIG_X86_IO_APIC
+	if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+#endif
+		localise_nmi_watchdog();
 	end_local_APIC_setup();
 #ifdef CONFIG_X86_IO_APIC
 	if (smp_found_config)
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 07fda23a9f76..13eac4f984c3 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -954,6 +954,8 @@ int __init APIC_init_uniprocessor(void)
 	if (!skip_ioapic_setup && nr_ioapics)
 		enable_IO_APIC();
 
+	if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+		localise_nmi_watchdog();
 	end_local_APIC_setup();
 
 	if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
-- 
cgit v1.2.2


From 19662027488946e34dd54d3bb408fa3307681d7d Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Fri, 6 Jun 2008 03:27:56 +0100
Subject: x86: APIC/UP: Remove redundant NMI watchdog downgrade

For the UP case the NMI watchdog downgrade is done consistently in
APIC_init_uniprocessor() now.  Remove redundant code used only when
BIOS-disabled local APIC is activated.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_32.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 26e7a62e9ab6..126e87153b39 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1154,9 +1154,6 @@ static int __init detect_init_APIC(void)
 	if (l & MSR_IA32_APICBASE_ENABLE)
 		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
 
-	if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
-		nmi_watchdog = NMI_LOCAL_APIC;
-
 	printk(KERN_INFO "Found and enabled local APIC!\n");
 
 	apic_pm_activate();
-- 
cgit v1.2.2


From d54db1ac9ecde9bcb8a561595b02c1d970d3a4d6 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Fri, 6 Jun 2008 03:28:02 +0100
Subject: x86: APIC/SMP: Downgrade the NMI watchdog for "nosmp"

 If configured to use the I/O APIC, the NMI watchdog is deemed to fail if
the chip has been deactivated as a result of "nosmp".  Downgrade to the
local APIC watchdog similarly to what is done for the UP case.

Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/smpboot.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8c53d86e3e86..f3760349c84f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1159,6 +1159,9 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	if (!max_cpus) {
 		printk(KERN_INFO "SMP mode deactivated.\n");
 		smpboot_clear_io_apic();
+
+		localise_nmi_watchdog();
+
 #ifdef CONFIG_X86_32
 		connect_bsp_APIC();
 #endif
-- 
cgit v1.2.2


From 46b3b4ef1ea2a0892b9b38b6a0c65a3f33b504aa Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Sat, 7 Jun 2008 19:53:57 +0400
Subject: x86, io-apic: use predefined names instead of numeric constants

This patch replaces some hard-coded numbers with predefined names.

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 10 ++++++----
 arch/x86/kernel/io_apic_64.c | 13 +++++++------
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 5c0f8d6496a6..40fbb229fe7d 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -261,25 +261,27 @@ static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsign
 /* mask = 1 */
 static void __mask_IO_APIC_irq (unsigned int irq)
 {
-	__modify_IO_APIC_irq(irq, 0x00010000, 0);
+	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0);
 }
 
 /* mask = 0 */
 static void __unmask_IO_APIC_irq (unsigned int irq)
 {
-	__modify_IO_APIC_irq(irq, 0, 0x00010000);
+	__modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED);
 }
 
 /* mask = 1, trigger = 0 */
 static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
 {
-	__modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED,
+				IO_APIC_REDIR_LEVEL_TRIGGER);
 }
 
 /* mask = 0, trigger = 1 */
 static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
 {
-	__modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER,
+				IO_APIC_REDIR_MASKED);
 }
 
 static void mask_IO_APIC_irq (unsigned int irq)
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 40a184d4dff8..60a022d6de5e 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -183,7 +183,7 @@ static bool io_apic_level_ack_pending(unsigned int irq)
 			break;
 		reg = io_apic_read(entry->apic, 0x10 + pin*2);
 		/* Is the remote IRR bit set? */
-		if ((reg >> 14) & 1) {
+		if (reg & IO_APIC_REDIR_REMOTE_IRR) {
 			spin_unlock_irqrestore(&ioapic_lock, flags);
 			return true;
 		}
@@ -298,7 +298,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 			break;
 		io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~0x000000ff;
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
 		reg |= vector;
 		io_apic_modify(apic, reg);
 		if (!entry->next)
@@ -366,10 +366,11 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	static void name##_IO_APIC_irq (unsigned int irq)		\
 	__DO_ACTION(R, ACTION, FINAL)
 
-DO_ACTION( __mask,             0, |= 0x00010000, io_apic_sync(entry->apic) )
-						/* mask = 1 */
-DO_ACTION( __unmask,           0, &= 0xfffeffff, )
-						/* mask = 0 */
+/* mask = 1 */
+DO_ACTION(__mask,	0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+/* mask = 0 */
+DO_ACTION(__unmask,	0, &= ~IO_APIC_REDIR_MASKED, )
 
 static void mask_IO_APIC_irq (unsigned int irq)
 {
-- 
cgit v1.2.2


From 360624484c81d55f88b1e5f48ce24c9243ce38e5 Mon Sep 17 00:00:00 2001
From: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Date: Sun, 8 Jun 2008 13:07:18 +0200
Subject: x86: coding style fixes to arch/x86/kernel/io_apic_32.c

Before:
total: 91 errors, 73 warnings, 2850 lines checked

After:
total: 1 errors, 47 warnings, 2848 lines checked

Compile tested:

paolo@paolo-desktop:/tmp$ size io*
   text    data     bss     dec     hex filename
  13836    1756   11104   26696    6848 io_apic_32.o.after
  13836    1756   11104   26696    6848 io_apic_32.o.before

Signed-off-by: Paolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 348 +++++++++++++++++++++----------------------
 1 file changed, 173 insertions(+), 175 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 40fbb229fe7d..9a924ebcd74c 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -239,7 +239,7 @@ static void __init replace_pin_at_irq(unsigned int irq,
 	}
 }
 
-static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable)
+static void __modify_IO_APIC_irq(unsigned int irq, unsigned long enable, unsigned long disable)
 {
 	struct irq_pin_list *entry = irq_2_pin + irq;
 	unsigned int pin, reg;
@@ -259,32 +259,32 @@ static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsign
 }
 
 /* mask = 1 */
-static void __mask_IO_APIC_irq (unsigned int irq)
+static void __mask_IO_APIC_irq(unsigned int irq)
 {
 	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0);
 }
 
 /* mask = 0 */
-static void __unmask_IO_APIC_irq (unsigned int irq)
+static void __unmask_IO_APIC_irq(unsigned int irq)
 {
 	__modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED);
 }
 
 /* mask = 1, trigger = 0 */
-static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+static void __mask_and_edge_IO_APIC_irq(unsigned int irq)
 {
 	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED,
 				IO_APIC_REDIR_LEVEL_TRIGGER);
 }
 
 /* mask = 0, trigger = 1 */
-static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
 {
 	__modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER,
 				IO_APIC_REDIR_MASKED);
 }
 
-static void mask_IO_APIC_irq (unsigned int irq)
+static void mask_IO_APIC_irq(unsigned int irq)
 {
 	unsigned long flags;
 
@@ -293,7 +293,7 @@ static void mask_IO_APIC_irq (unsigned int irq)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void unmask_IO_APIC_irq (unsigned int irq)
+static void unmask_IO_APIC_irq(unsigned int irq)
 {
 	unsigned long flags;
 
@@ -305,7 +305,7 @@ static void unmask_IO_APIC_irq (unsigned int irq)
 static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 {
 	struct IO_APIC_route_entry entry;
-	
+
 	/* Check delivery_mode to be sure we're not clearing an SMI pin */
 	entry = ioapic_read_entry(apic, pin);
 	if (entry.delivery_mode == dest_SMI)
@@ -317,7 +317,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 	ioapic_mask_entry(apic, pin);
 }
 
-static void clear_IO_APIC (void)
+static void clear_IO_APIC(void)
 {
 	int apic, pin;
 
@@ -334,7 +334,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 	struct irq_pin_list *entry = irq_2_pin + irq;
 	unsigned int apicid_value;
 	cpumask_t tmp;
-	
+
 	cpus_and(tmp, cpumask, cpu_online_map);
 	if (cpus_empty(tmp))
 		tmp = TARGET_CPUS;
@@ -363,7 +363,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 # include <linux/kernel_stat.h>	/* kstat */
 # include <linux/slab.h>		/* kmalloc() */
 # include <linux/timer.h>
- 
+
 #define IRQBALANCE_CHECK_ARCH -999
 #define MAX_BALANCED_IRQ_INTERVAL	(5*HZ)
 #define MIN_BALANCED_IRQ_INTERVAL	(HZ/2)
@@ -375,14 +375,14 @@ static int physical_balance __read_mostly;
 static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
 
 static struct irq_cpu_info {
-	unsigned long * last_irq;
-	unsigned long * irq_delta;
+	unsigned long *last_irq;
+	unsigned long *irq_delta;
 	unsigned long irq;
 } irq_cpu_data[NR_CPUS];
 
 #define CPU_IRQ(cpu)		(irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu,irq)   (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu,irq) 	(irq_cpu_data[cpu].irq_delta[irq])
+#define LAST_CPU_IRQ(cpu, irq)   (irq_cpu_data[cpu].last_irq[irq])
+#define IRQ_DELTA(cpu, irq) 	(irq_cpu_data[cpu].irq_delta[irq])
 
 #define IDLE_ENOUGH(cpu,now) \
 	(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
@@ -421,8 +421,8 @@ inside:
 			if (cpu == -1)
 				cpu = NR_CPUS-1;
 		}
-	} while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) ||
-			(search_idle && !IDLE_ENOUGH(cpu,now)));
+	} while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
+			(search_idle && !IDLE_ENOUGH(cpu, now)));
 
 	return cpu;
 }
@@ -432,15 +432,14 @@ static inline void balance_irq(int cpu, int irq)
 	unsigned long now = jiffies;
 	cpumask_t allowed_mask;
 	unsigned int new_cpu;
-		
+
 	if (irqbalance_disabled)
-		return; 
+		return;
 
 	cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
 	new_cpu = move(cpu, allowed_mask, now, 1);
-	if (cpu != new_cpu) {
+	if (cpu != new_cpu)
 		set_pending_irq(irq, cpumask_of_cpu(new_cpu));
-	}
 }
 
 static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
@@ -452,14 +451,14 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 			if (!irq_desc[j].action)
 				continue;
 			/* Is it a significant load ?  */
-			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) <
+			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
 						useful_load_threshold)
 				continue;
 			balance_irq(i, j);
 		}
 	}
 	balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);	
+		balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
 	return;
 }
 
@@ -488,22 +487,22 @@ static void do_irq_balance(void)
 			/* Is this an active IRQ or balancing disabled ? */
 			if (!irq_desc[j].action || irq_balancing_disabled(j))
 				continue;
-			if ( package_index == i )
-				IRQ_DELTA(package_index,j) = 0;
+			if (package_index == i)
+				IRQ_DELTA(package_index, j) = 0;
 			/* Determine the total count per processor per IRQ */
 			value_now = (unsigned long) kstat_cpu(i).irqs[j];
 
 			/* Determine the activity per processor per IRQ */
-			delta = value_now - LAST_CPU_IRQ(i,j);
+			delta = value_now - LAST_CPU_IRQ(i, j);
 
 			/* Update last_cpu_irq[][] for the next time */
-			LAST_CPU_IRQ(i,j) = value_now;
+			LAST_CPU_IRQ(i, j) = value_now;
 
 			/* Ignore IRQs whose rate is less than the clock */
 			if (delta < useful_load_threshold)
 				continue;
 			/* update the load for the processor or package total */
-			IRQ_DELTA(package_index,j) += delta;
+			IRQ_DELTA(package_index, j) += delta;
 
 			/* Keep track of the higher numbered sibling as well */
 			if (i != package_index)
@@ -529,7 +528,8 @@ static void do_irq_balance(void)
 	max_cpu_irq = ULONG_MAX;
 
 tryanothercpu:
-	/* Look for heaviest loaded processor.
+	/*
+	 * Look for heaviest loaded processor.
 	 * We may come back to get the next heaviest loaded processor.
 	 * Skip processors with trivial loads.
 	 */
@@ -538,7 +538,7 @@ tryanothercpu:
 	for_each_online_cpu(i) {
 		if (i != CPU_TO_PACKAGEINDEX(i))
 			continue;
-		if (max_cpu_irq <= CPU_IRQ(i)) 
+		if (max_cpu_irq <= CPU_IRQ(i))
 			continue;
 		if (tmp_cpu_irq < CPU_IRQ(i)) {
 			tmp_cpu_irq = CPU_IRQ(i);
@@ -547,8 +547,9 @@ tryanothercpu:
 	}
 
 	if (tmp_loaded == -1) {
- 	 /* In the case of small number of heavy interrupt sources, 
-	  * loading some of the cpus too much. We use Ingo's original 
+	 /*
+	  * In the case of small number of heavy interrupt sources,
+	  * loading some of the cpus too much. We use Ingo's original
 	  * approach to rotate them around.
 	  */
 		if (!first_attempt && imbalance >= useful_load_threshold) {
@@ -557,13 +558,14 @@ tryanothercpu:
 		}
 		goto not_worth_the_effort;
 	}
-	
+
 	first_attempt = 0;		/* heaviest search */
 	max_cpu_irq = tmp_cpu_irq;	/* load */
 	max_loaded = tmp_loaded;	/* processor */
 	imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-	
-	/* if imbalance is less than approx 10% of max load, then
+
+	/*
+	 * if imbalance is less than approx 10% of max load, then
 	 * observe diminishing returns action. - quit
 	 */
 	if (imbalance < (max_cpu_irq >> 3))
@@ -579,26 +581,25 @@ tryanotherirq:
 		/* Is this an active IRQ? */
 		if (!irq_desc[j].action)
 			continue;
-		if (imbalance <= IRQ_DELTA(max_loaded,j))
+		if (imbalance <= IRQ_DELTA(max_loaded, j))
 			continue;
 		/* Try to find the IRQ that is closest to the imbalance
 		 * without going over.
 		 */
-		if (move_this_load < IRQ_DELTA(max_loaded,j)) {
-			move_this_load = IRQ_DELTA(max_loaded,j);
+		if (move_this_load < IRQ_DELTA(max_loaded, j)) {
+			move_this_load = IRQ_DELTA(max_loaded, j);
 			selected_irq = j;
 		}
 	}
-	if (selected_irq == -1) {
+	if (selected_irq == -1)
 		goto tryanothercpu;
-	}
 
 	imbalance = move_this_load;
-	
+
 	/* For physical_balance case, we accumulated both load
 	 * values in the one of the siblings cpu_irq[],
 	 * to use the same code for physical and logical processors
-	 * as much as possible. 
+	 * as much as possible.
 	 *
 	 * NOTE: the cpu_irq[] array holds the sum of the load for
 	 * sibling A and sibling B in the slot for the lowest numbered
@@ -627,11 +628,11 @@ tryanotherirq:
 		/* mark for change destination */
 		set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
 
-		/* Since we made a change, come back sooner to 
+		/* Since we made a change, come back sooner to
 		 * check for more variation.
 		 */
 		balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-			balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);	
+			balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
 		return;
 	}
 	goto tryanotherirq;
@@ -642,7 +643,7 @@ not_worth_the_effort:
 	 * upward
 	 */
 	balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);	
+		balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
 	return;
 }
 
@@ -681,13 +682,13 @@ static int __init balanced_irq_init(void)
 	cpumask_t tmp;
 
 	cpus_shift_right(tmp, cpu_online_map, 2);
-        c = &boot_cpu_data;
+	c = &boot_cpu_data;
 	/* When not overwritten by the command line ask subarchitecture. */
 	if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
 		irqbalance_disabled = NO_BALANCE_IRQ;
 	if (irqbalance_disabled)
 		return 0;
-	
+
 	 /* disable irqbalance completely if there is only one processor online */
 	if (num_online_cpus() < 2) {
 		irqbalance_disabled = 1;
@@ -707,10 +708,10 @@ static int __init balanced_irq_init(void)
 			printk(KERN_ERR "balanced_irq_init: out of memory");
 			goto failed;
 		}
-		memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS);
-		memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS);
+		memset(irq_cpu_data[i].irq_delta, 0, sizeof(unsigned long) * NR_IRQS);
+		memset(irq_cpu_data[i].last_irq, 0, sizeof(unsigned long) * NR_IRQS);
 	}
-	
+
 	printk(KERN_INFO "Starting balanced_irq\n");
 	if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
 		return 0;
@@ -845,7 +846,7 @@ static int __init find_isa_irq_apic(int irq, int type)
 	}
 	if (i < mp_irq_entries) {
 		int apic;
-		for(apic = 0; apic < nr_ioapics; apic++) {
+		for (apic = 0; apic < nr_ioapics; apic++) {
 			if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
 				return apic;
 		}
@@ -882,7 +883,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 		    !mp_irqs[i].mpc_irqtype &&
 		    (bus == lbus) &&
 		    (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+			int irq = pin_2_irq(i, apic, mp_irqs[i].mpc_dstirq);
 
 			if (!(apic || IO_APIC_IRQ(irq)))
 				continue;
@@ -902,7 +903,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
 /*
- * This function currently is only a helper for the i386 smp boot process where 
+ * This function currently is only a helper for the i386 smp boot process where
  * we need to reprogram the ioredtbls to cater for the cpus which have come online
  * so mask in all cases should simply be TARGET_CPUS
  */
@@ -977,37 +978,36 @@ static int MPBIOS_polarity(int idx)
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].mpc_irqflag & 3)
+	switch (mp_irqs[idx].mpc_irqflag & 3) {
+	case 0: /* conforms, ie. bus-type dependent polarity */
 	{
-		case 0: /* conforms, ie. bus-type dependent polarity */
-		{
-			polarity = test_bit(bus, mp_bus_not_pci)?
-				default_ISA_polarity(idx):
-				default_PCI_polarity(idx);
-			break;
-		}
-		case 1: /* high active */
-		{
-			polarity = 0;
-			break;
-		}
-		case 2: /* reserved */
-		{
-			printk(KERN_WARNING "broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
-		case 3: /* low active */
-		{
-			polarity = 1;
-			break;
-		}
-		default: /* invalid */
-		{
-			printk(KERN_WARNING "broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
+		polarity = test_bit(bus, mp_bus_not_pci)?
+			default_ISA_polarity(idx):
+			default_PCI_polarity(idx);
+		break;
+	}
+	case 1: /* high active */
+	{
+		polarity = 0;
+		break;
+	}
+	case 2: /* reserved */
+	{
+		printk(KERN_WARNING "broken BIOS!!\n");
+		polarity = 1;
+		break;
+	}
+	case 3: /* low active */
+	{
+		polarity = 1;
+		break;
+	}
+	default: /* invalid */
+	{
+		printk(KERN_WARNING "broken BIOS!!\n");
+		polarity = 1;
+		break;
+	}
 	}
 	return polarity;
 }
@@ -1020,69 +1020,67 @@ static int MPBIOS_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+	switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) {
+	case 0: /* conforms, ie. bus-type dependent */
 	{
-		case 0: /* conforms, ie. bus-type dependent */
-		{
-			trigger = test_bit(bus, mp_bus_not_pci)?
-					default_ISA_trigger(idx):
-					default_PCI_trigger(idx);
+		trigger = test_bit(bus, mp_bus_not_pci)?
+				default_ISA_trigger(idx):
+				default_PCI_trigger(idx);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
-			switch (mp_bus_id_to_type[bus])
-			{
-				case MP_BUS_ISA: /* ISA pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				case MP_BUS_EISA: /* EISA pin */
-				{
-					trigger = default_EISA_trigger(idx);
-					break;
-				}
-				case MP_BUS_PCI: /* PCI pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				case MP_BUS_MCA: /* MCA pin */
-				{
-					trigger = default_MCA_trigger(idx);
-					break;
-				}
-				default:
-				{
-					printk(KERN_WARNING "broken BIOS!!\n");
-					trigger = 1;
-					break;
-				}
-			}
-#endif
+		switch (mp_bus_id_to_type[bus]) {
+		case MP_BUS_ISA: /* ISA pin */
+		{
+			/* set before the switch */
 			break;
 		}
-		case 1: /* edge */
+		case MP_BUS_EISA: /* EISA pin */
 		{
-			trigger = 0;
+			trigger = default_EISA_trigger(idx);
 			break;
 		}
-		case 2: /* reserved */
+		case MP_BUS_PCI: /* PCI pin */
 		{
-			printk(KERN_WARNING "broken BIOS!!\n");
-			trigger = 1;
+			/* set before the switch */
 			break;
 		}
-		case 3: /* level */
+		case MP_BUS_MCA: /* MCA pin */
 		{
-			trigger = 1;
+			trigger = default_MCA_trigger(idx);
 			break;
 		}
-		default: /* invalid */
+		default:
 		{
 			printk(KERN_WARNING "broken BIOS!!\n");
-			trigger = 0;
+			trigger = 1;
 			break;
 		}
 	}
+#endif
+		break;
+	}
+	case 1: /* edge */
+	{
+		trigger = 0;
+		break;
+	}
+	case 2: /* reserved */
+	{
+		printk(KERN_WARNING "broken BIOS!!\n");
+		trigger = 1;
+		break;
+	}
+	case 3: /* level */
+	{
+		trigger = 1;
+		break;
+	}
+	default: /* invalid */
+	{
+		printk(KERN_WARNING "broken BIOS!!\n");
+		trigger = 0;
+		break;
+	}
+	}
 	return trigger;
 }
 
@@ -1150,8 +1148,8 @@ static inline int IO_APIC_irq_trigger(int irq)
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
-			idx = find_irq_entry(apic,pin,mp_INT);
-			if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+			idx = find_irq_entry(apic, pin, mp_INT);
+			if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
 				return irq_trigger(idx);
 		}
 	}
@@ -1166,7 +1164,7 @@ static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 }
 
 static int __assign_irq_vector(int irq)
 {
-	static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+	static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
 	int vector, offset;
 
 	BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
@@ -1239,15 +1237,15 @@ static void __init setup_IO_APIC_irqs(void)
 		/*
 		 * add it to the IO-APIC irq-routing table:
 		 */
-		memset(&entry,0,sizeof(entry));
+		memset(&entry, 0, sizeof(entry));
 
 		entry.delivery_mode = INT_DELIVERY_MODE;
 		entry.dest_mode = INT_DEST_MODE;
 		entry.mask = 0;				/* enable IRQ */
-		entry.dest.logical.logical_dest = 
+		entry.dest.logical.logical_dest =
 					cpu_mask_to_apicid(TARGET_CPUS);
 
-		idx = find_irq_entry(apic,pin,mp_INT);
+		idx = find_irq_entry(apic, pin, mp_INT);
 		if (idx == -1) {
 			if (first_notcon) {
 				apic_printk(APIC_VERBOSE, KERN_DEBUG
@@ -1291,7 +1289,7 @@ static void __init setup_IO_APIC_irqs(void)
 			vector = assign_irq_vector(irq);
 			entry.vector = vector;
 			ioapic_register_intr(irq, vector, IOAPIC_AUTO);
-		
+
 			if (!apic && (irq < 16))
 				disable_8259A_irq(irq);
 		}
@@ -1311,7 +1309,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 {
 	struct IO_APIC_route_entry entry;
 
-	memset(&entry,0,sizeof(entry));
+	memset(&entry, 0, sizeof(entry));
 
 	/*
 	 * We use logical delivery to get the timer IRQ
@@ -1349,7 +1347,7 @@ void __init print_IO_APIC(void)
 	if (apic_verbosity == APIC_QUIET)
 		return;
 
- 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for (i = 0; i < nr_ioapics; i++)
 		printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
 		       mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
@@ -1454,7 +1452,7 @@ void __init print_IO_APIC(void)
 
 #if 0
 
-static void print_APIC_bitfield (int base)
+static void print_APIC_bitfield(int base)
 {
 	unsigned int v;
 	int i, j;
@@ -1475,7 +1473,7 @@ static void print_APIC_bitfield (int base)
 	}
 }
 
-void /*__init*/ print_local_APIC(void * dummy)
+void /*__init*/ print_local_APIC(void *dummy)
 {
 	unsigned int v, ver, maxlvt;
 
@@ -1558,7 +1556,7 @@ void /*__init*/ print_local_APIC(void * dummy)
 	printk("\n");
 }
 
-void print_all_local_APICs (void)
+void print_all_local_APICs(void)
 {
 	on_each_cpu(print_local_APIC, NULL, 1, 1);
 }
@@ -1581,11 +1579,11 @@ void /*__init*/ print_PIC(void)
 	v = inb(0xa0) << 8 | inb(0x20);
 	printk(KERN_DEBUG "... PIC  IRR: %04x\n", v);
 
-	outb(0x0b,0xa0);
-	outb(0x0b,0x20);
+	outb(0x0b, 0xa0);
+	outb(0x0b, 0x20);
 	v = inb(0xa0) << 8 | inb(0x20);
-	outb(0x0a,0xa0);
-	outb(0x0a,0x20);
+	outb(0x0a, 0xa0);
+	outb(0x0a, 0x20);
 
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 
@@ -1621,7 +1619,7 @@ static void __init enable_IO_APIC(void)
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
 	}
-	for(apic = 0; apic < nr_ioapics; apic++) {
+	for (apic = 0; apic < nr_ioapics; apic++) {
 		int pin;
 		/* See if any of the pins is in ExtINT mode */
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
@@ -1743,7 +1741,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
 		spin_lock_irqsave(&ioapic_lock, flags);
 		reg_00.raw = io_apic_read(apic, 0);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
-		
+
 		old_id = mp_ioapics[apic].mpc_apicid;
 
 		if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
@@ -1795,7 +1793,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
 		/*
 		 * Read the right value from the MPC table and
 		 * write it into the ID register.
-	 	 */
+		 */
 		apic_printk(APIC_VERBOSE, KERN_INFO
 			"...changing IO-APIC physical APIC ID to %d ...",
 			mp_ioapics[apic].mpc_apicid);
@@ -2015,7 +2013,7 @@ static void ack_apic(unsigned int irq)
 	ack_APIC_irq();
 }
 
-static void mask_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
 {
 	unsigned long v;
 
@@ -2023,7 +2021,7 @@ static void mask_lapic_irq (unsigned int irq)
 	apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void unmask_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
 {
 	unsigned long v;
 
@@ -2041,14 +2039,14 @@ static struct irq_chip lapic_chip __read_mostly = {
 static void __init setup_nmi(void)
 {
 	/*
- 	 * Dirty trick to enable the NMI watchdog ...
+	 * Dirty trick to enable the NMI watchdog ...
 	 * We put the 8259A master into AEOI mode and
 	 * unmask on all local APICs LVT0 as NMI.
 	 *
 	 * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
 	 * is from Maciej W. Rozycki - so we do not have to EOI from
 	 * the NMI handler or the timer interrupt.
-	 */ 
+	 */
 	apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
 
 	enable_NMI_through_LVT0();
@@ -2312,10 +2310,10 @@ void __init setup_IO_APIC(void)
  *	Called after all the initialization is done. If we didnt find any
  *	APIC bugs then we can allow the modify fast path
  */
- 
+
 static int __init io_apic_bug_finalize(void)
 {
-	if(sis_apic_bug == -1)
+	if (sis_apic_bug == -1)
 		sis_apic_bug = 0;
 	return 0;
 }
@@ -2326,17 +2324,17 @@ struct sysfs_ioapic_data {
 	struct sys_device dev;
 	struct IO_APIC_route_entry entry[0];
 };
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS];
 
 static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
 {
 	struct IO_APIC_route_entry *entry;
 	struct sysfs_ioapic_data *data;
 	int i;
-	
+
 	data = container_of(dev, struct sysfs_ioapic_data, dev);
 	entry = data->entry;
-	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+	for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
 		entry[i] = ioapic_read_entry(dev->id, i);
 
 	return 0;
@@ -2349,7 +2347,7 @@ static int ioapic_resume(struct sys_device *dev)
 	unsigned long flags;
 	union IO_APIC_reg_00 reg_00;
 	int i;
-	
+
 	data = container_of(dev, struct sysfs_ioapic_data, dev);
 	entry = data->entry;
 
@@ -2360,7 +2358,7 @@ static int ioapic_resume(struct sys_device *dev)
 		io_apic_write(dev->id, 0, reg_00.raw);
 	}
 	spin_unlock_irqrestore(&ioapic_lock, flags);
-	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+	for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
 		ioapic_write_entry(dev->id, i, entry[i]);
 
 	return 0;
@@ -2374,15 +2372,15 @@ static struct sysdev_class ioapic_sysdev_class = {
 
 static int __init ioapic_init_sysfs(void)
 {
-	struct sys_device * dev;
+	struct sys_device *dev;
 	int i, size, error = 0;
 
 	error = sysdev_class_register(&ioapic_sysdev_class);
 	if (error)
 		return error;
 
-	for (i = 0; i < nr_ioapics; i++ ) {
-		size = sizeof(struct sys_device) + nr_ioapic_registers[i] 
+	for (i = 0; i < nr_ioapics; i++) {
+		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
 		mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
 		if (!mp_ioapic_data[i]) {
@@ -2391,7 +2389,7 @@ static int __init ioapic_init_sysfs(void)
 		}
 		memset(mp_ioapic_data[i], 0, size);
 		dev = &mp_ioapic_data[i]->dev;
-		dev->id = i; 
+		dev->id = i;
 		dev->cls = &ioapic_sysdev_class;
 		error = sysdev_register(dev);
 		if (error) {
@@ -2466,7 +2464,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 		msg->address_lo =
 			MSI_ADDR_BASE_LO |
 			((INT_DEST_MODE == 0) ?
-				MSI_ADDR_DEST_MODE_PHYSICAL:
+MSI_ADDR_DEST_MODE_PHYSICAL:
 				MSI_ADDR_DEST_MODE_LOGICAL) |
 			((INT_DELIVERY_MODE != dest_LowestPrio) ?
 				MSI_ADDR_REDIRECTION_CPU:
@@ -2477,7 +2475,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 			MSI_DATA_TRIGGER_EDGE |
 			MSI_DATA_LEVEL_ASSERT |
 			((INT_DELIVERY_MODE != dest_LowestPrio) ?
-				MSI_DATA_DELIVERY_FIXED:
+MSI_DATA_DELIVERY_FIXED:
 				MSI_DATA_DELIVERY_LOWPRI) |
 			MSI_DATA_VECTOR(vector);
 	}
@@ -2648,12 +2646,12 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 #endif /* CONFIG_HT_IRQ */
 
 /* --------------------------------------------------------------------------
-                          ACPI-based IOAPIC Configuration
+			ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
 
 #ifdef CONFIG_ACPI
 
-int __init io_apic_get_unique_id (int ioapic, int apic_id)
+int __init io_apic_get_unique_id(int ioapic, int apic_id)
 {
 	union IO_APIC_reg_00 reg_00;
 	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -2662,10 +2660,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
 	int i = 0;
 
 	/*
-	 * The P4 platform supports up to 256 APIC IDs on two separate APIC 
-	 * buses (one for LAPICs, one for IOAPICs), where predecessors only 
+	 * The P4 platform supports up to 256 APIC IDs on two separate APIC
+	 * buses (one for LAPICs, one for IOAPICs), where predecessors only
 	 * supports up to 16 on one shared APIC bus.
-	 * 
+	 *
 	 * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
 	 *      advantage of new APIC bus architecture.
 	 */
@@ -2684,7 +2682,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
 	}
 
 	/*
-	 * Every APIC in a system must have a unique ID or we get lots of nice 
+	 * Every APIC in a system must have a unique ID or we get lots of nice
 	 * 'stuck on smp_invalidate_needed IPI wait' messages.
 	 */
 	if (check_apicid_used(apic_id_map, apic_id)) {
@@ -2701,7 +2699,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
 			"trying %d\n", ioapic, apic_id, i);
 
 		apic_id = i;
-	} 
+	}
 
 	tmp = apicid_to_cpu_present(apic_id);
 	physids_or(apic_id_map, apic_id_map, tmp);
@@ -2728,7 +2726,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
 }
 
 
-int __init io_apic_get_version (int ioapic)
+int __init io_apic_get_version(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -2741,7 +2739,7 @@ int __init io_apic_get_version (int ioapic)
 }
 
 
-int __init io_apic_get_redir_entries (int ioapic)
+int __init io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -2754,7 +2752,7 @@ int __init io_apic_get_redir_entries (int ioapic)
 }
 
 
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low)
+int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low)
 {
 	struct IO_APIC_route_entry entry;
 
@@ -2770,7 +2768,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
 	 * corresponding device driver registers for this IRQ.
 	 */
 
-	memset(&entry,0,sizeof(entry));
+	memset(&entry, 0, sizeof(entry));
 
 	entry.delivery_mode = INT_DELIVERY_MODE;
 	entry.dest_mode = INT_DEST_MODE;
-- 
cgit v1.2.2


From cd08d0754ecb0cb9293c8476cb33ded1d23d0d8f Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Thu, 19 Jun 2008 00:39:33 +0100
Subject: x86: fix IO APIC breakage on HP nx6325

On Thu, 19 Jun 2008, Rafael J. Wysocki wrote:

> >  With such a configuration the "x86: I/O APIC: timer through 8259A
> > second-chance" patch should not matter, because the only change it
> > introduces is an attempt to try the same I/O APIC pin again, but with the
> > IRQ0 line of the master 8259A enabled.  That's not a terribly unusual
> > configuration and nothing should get confused in the system.
>
> But it _does_ get confused, really.

 Something certainly gets confused, but so far I am not sure which bit
exactly it is, are you?

> >  Barring the unlikely possibility of the 8259A actually being wired to
> > INTIN2 of the I/O APIC I can see two possible explanations:
> >
> > 1. The 8259A interrupt actually escapes to the CPU somehow and is handled
> >    as an ExtINTA interrupt.  This would make the code in check_timer()
> >    decide it has found a working configuration, while actually it has been
> >    fooled.
[...]
> Here you go:
>
> [    0.108006] ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
> [    0.108006] ..MP-BIOS bug: 8254 timer not connected to IO-APIC
> [    0.108006] ...trying to set up timer (IRQ0) through the 8259A ... <3>
> [    0.108006] ..... (found apic 0 pin 2) ...<3> works.
>
> The full dmesg is at: http://www.sisk.pl/kernel/debug/20080618/dmesg-1.log

Thanks.  In this case I suspect the case #1 quoted above happens, that is
the 8259A manages to deliver its interrupt somehow.  Note at this stage it
is meant to be in the AEOI mode, so it can happily resubmit the interrupt
indefinitely with no additional handling as long as it receives INTA
cycles.

Can you please try the patch below on top of "x86: I/O APIC: timer
through 8259A second-chance" to see whether my hypothesis is true?  It
modifies the through-8259A setup path so that the APIC input gets masked,
but the 8259A has the timer interrupt still enabled.  Let me know how the
timer interrupt is routed in this case.

Bisected-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Tested-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 60a022d6de5e..f06f5b4fb35f 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1715,6 +1715,7 @@ static inline void __init check_timer(void)
 		/* replace_pin_at_irq(0, apic1, pin1, apic2, pin2); */
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		unmask_IO_APIC_irq(0);
+		clear_IO_APIC_pin(apic2, pin2);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
-- 
cgit v1.2.2


From 7f0dbbc08d80df7ea15d8da4f0d78255891c8812 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@linux-mips.org>
Date: Fri, 20 Jun 2008 01:35:07 +0100
Subject: x86: fix IO APIC breakage on HP nx6325, v2

> That helped a lot, the system seems to work normally now.
>
> Here's the relevant snippet from dmesg:
>
> [    0.108006] ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
> [    0.108006] ..MP-BIOS bug: 8254 timer not connected to IO-APIC
> [    0.108006] ...trying to set up timer (IRQ0) through the 8259A ... <3>
> [    0.108006] ..... (found apic 0 pin 2) ...<3> failed.
> [    0.108006] ...trying to set up timer as Virtual Wire IRQ...<3> works.
>
> and the whole thing is at: http://www.sisk.pl/kernel/debug/20080618/dmesg-2.log

 Hmm, that only proved the 8259A is indeed wired to the pin #2 of the I/O
APIC.

> I, personally, don't have any and AMD only has SB600 documentation on its
> web page (it's still marked as "AMD confidential" ;-)).

 Well, the IC block is most likely the same as that's not rocket science
and once done there is no need to fiddle with that.  That written, I am
afraid there is nothing useful about the IC in the document, except that
it's there and consists of an I/O APIC providing 24 inputs and the usual
pair of 8259A cores.  Thanks for the reference anyway.

> There is an interrupt controller in there, but I'm not sure if there's any
> 8259A.  The northbridge is on the CPU, actually.

 I will praise the day someone ships an x86 machine without an 8259A core!

 As expressed in another mail I suspect there may actually be a direct
route from the 8254 to INTIN0 in the southbridge -- this is what other
bootstrap logs seen in the Internet suggest.  This would mean this
particular BIOS is buggy (is it the latest version?) and provides an
incorrect IRQ override in its ACPI tables, for example because the
responsible block has been blindly copied from a machine using a commoner
wiring.  This could be moderately easily fixed up with a quirk based on
the PCI ID (after checking it again, we actually used to have a quirk for
ATI in this area, but the way it was done suggests the issue was not
understood well enough).

 Could you please remove the hack sent yesterday and test the patch
provided below?  I do hope it builds, but I have no immediate means to
check it.  Please report the output.  The intent is to test INTIN0
directly before testing INTIN2 through the 8259A.  Thanks.

 Aside of that, what I have gathered from your reports (please correct me
if I have got it wrong) is that when the through-8259A mode is used, then
after a while 8254 timer interrupts stop arriving.  What's interesting,
the "Virtual Wire IRQ" seems to work for you correctly (that's quite an
odd setup where a local APIC input is used in the native mode -- please
post /proc/interrupts for confirmation), which in turn implies the master
8259A drives its INT output as we expect.  Why would the I/O APIC input
have problems then?  Hmm...

[ mingo@elte.hu: revert the "x86: fix IO APIC breakage on HP nx6325"
  version. ]

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index f06f5b4fb35f..40aa041b2987 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -360,6 +360,26 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	entry->pin = pin;
 }
 
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+				      int oldapic, int oldpin,
+				      int newapic, int newpin)
+{
+	struct irq_pin_list *entry = irq_2_pin + irq;
+
+	while (1) {
+		if (entry->apic == oldapic && entry->pin == oldpin) {
+			entry->apic = newapic;
+			entry->pin = newpin;
+		}
+		if (!entry->next)
+			break;
+		entry = irq_2_pin + entry->next;
+	}
+}
+
 
 #define DO_ACTION(name,R,ACTION, FINAL)					\
 									\
@@ -1680,6 +1700,11 @@ static inline void __init check_timer(void)
 		apic2 = apic1;
 	}
 
+	replace_pin_at_irq(0, 0, 0, apic1, pin1);
+	apic1 = 0;
+	pin1 = 0;
+	setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+
 	if (pin1 != -1) {
 		/*
 		 * Ok, does IRQ0 through the IOAPIC work?
@@ -1712,10 +1737,9 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		/* replace_pin_at_irq(0, apic1, pin1, apic2, pin2); */
+		replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		unmask_IO_APIC_irq(0);
-		clear_IO_APIC_pin(apic2, pin2);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_VERBOSE," works.\n");
-- 
cgit v1.2.2


From 25556c1699ad84dd6077adf67c92eba362aa7dc2 Mon Sep 17 00:00:00 2001
From: Christophe Jaillet <jaillet.christophe@wanadoo.fr>
Date: Sun, 22 Jun 2008 22:13:48 +0200
Subject: x86, arch/x86/kernel/io_apic_32.c: use kzalloc instead of
 kmalloc/memset

1) replace kmalloc/memset with equivalent kzalloc.

Signed-off-by: Christophe Jaillet <jaillet.christophe@wanadoo.fr>
Cc: cj <jaillet.christophe@wanadoo.fr>
Cc: petero2@telia.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 9a924ebcd74c..e22cbfbce049 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -702,14 +702,12 @@ static int __init balanced_irq_init(void)
 		physical_balance = 1;
 
 	for_each_online_cpu(i) {
-		irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
-		irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
 		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
 			printk(KERN_ERR "balanced_irq_init: out of memory");
 			goto failed;
 		}
-		memset(irq_cpu_data[i].irq_delta, 0, sizeof(unsigned long) * NR_IRQS);
-		memset(irq_cpu_data[i].last_irq, 0, sizeof(unsigned long) * NR_IRQS);
 	}
 
 	printk(KERN_INFO "Starting balanced_irq\n");
@@ -2382,12 +2380,11 @@ static int __init ioapic_init_sysfs(void)
 	for (i = 0; i < nr_ioapics; i++) {
 		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
-		mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+		mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
 		if (!mp_ioapic_data[i]) {
 			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
 			continue;
 		}
-		memset(mp_ioapic_data[i], 0, size);
 		dev = &mp_ioapic_data[i]->dev;
 		dev->id = i;
 		dev->cls = &ioapic_sysdev_class;
-- 
cgit v1.2.2