Merge branch 'upstream-fixes'

11 files changed, 188 insertions, 43 deletions

diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index d16520da455..9ed449af8e9 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -1338,8 +1338,7 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
-	/* We enable the timer again on the exit path of the death loop */
-	disable_APIC_timer();
+	clear_local_APIC();
 	/* Allow any queued timer interrupts to get serviced */
 	local_irq_enable();
 	mdelay(1);
diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c
index 5d09de8d1c6..8498b5ac395 100644
--- a/arch/i386/mm/ioremap.c
+++ b/arch/i386/mm/ioremap.c
@@ -223,9 +223,15 @@ void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap_nocache);
 
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
 void iounmap(volatile void __iomem *addr)
 {
-	struct vm_struct *p;
+	struct vm_struct *p, *o;
 
 	if ((void __force *)addr <= high_memory)
 		return;
@@ -239,22 +245,37 @@ void iounmap(volatile void __iomem *addr)
 			addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
-	write_lock(&vmlist_lock);
-	p = __remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
-	if (!p) { 
-		printk(KERN_WARNING "iounmap: bad address %p\n", addr);
+	addr = (volatile void *)(PAGE_MASK & (unsigned long __force)addr);
+
+	/* Use the vm area unlocked, assuming the caller
+	   ensures there isn't another iounmap for the same address
+	   in parallel. Reuse of the virtual address is prevented by
+	   leaving it in the global lists until we're done with it.
+	   cpa takes care of the direct mappings. */
+	read_lock(&vmlist_lock);
+	for (p = vmlist; p; p = p->next) {
+		if (p->addr == addr)
+			break;
+	}
+	read_unlock(&vmlist_lock);
+
+	if (!p) {
+		printk("iounmap: bad address %p\n", addr);
 		dump_stack();
-		goto out_unlock;
+		return;
 	}
 
+	/* Reset the direct mapping. Can block */
 	if ((p->flags >> 20) && p->phys_addr < virt_to_phys(high_memory) - 1) {
 		change_page_attr(virt_to_page(__va(p->phys_addr)),
 				 p->size >> PAGE_SHIFT,
 				 PAGE_KERNEL);
 		global_flush_tlb();
 	} 
-out_unlock:
-	write_unlock(&vmlist_lock);
+
+	/* Finally remove it */
+	o = remove_vm_area((void *)addr);
+	BUG_ON(p != o || o == NULL);
 	kfree(p); 
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/i386/pci/direct.c b/arch/i386/pci/direct.c
index 94331d6be7a..e3ac502bf2f 100644
--- a/arch/i386/pci/direct.c
+++ b/arch/i386/pci/direct.c
@@ -13,7 +13,7 @@
 #define PCI_CONF1_ADDRESS(bus, devfn, reg) \
 	(0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3))
 
-static int pci_conf1_read(unsigned int seg, unsigned int bus,
+int pci_conf1_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
 	unsigned long flags;
@@ -42,7 +42,7 @@ static int pci_conf1_read(unsigned int seg, unsigned int bus,
 	return 0;
 }
 
-static int pci_conf1_write(unsigned int seg, unsigned int bus,
+int pci_conf1_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
 	unsigned long flags;
diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c
index dfbf80cff83..08a08490121 100644
--- a/arch/i386/pci/mmconfig.c
+++ b/arch/i386/pci/mmconfig.c
@@ -19,21 +19,25 @@
 /* The base address of the last MMCONFIG device accessed */
 static u32 mmcfg_last_accessed_device;
 
+static DECLARE_BITMAP(fallback_slots, 32);
+
 /*
  * Functions for accessing PCI configuration space with MMCONFIG accesses
  */
-static u32 get_base_addr(unsigned int seg, int bus)
+static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn)
 {
 	int cfg_num = -1;
 	struct acpi_table_mcfg_config *cfg;
 
+	if (seg == 0 && bus == 0 &&
+	    test_bit(PCI_SLOT(devfn), fallback_slots))
+		return 0;
+
 	while (1) {
 		++cfg_num;
 		if (cfg_num >= pci_mmcfg_config_num) {
-			/* something bad is going on, no cfg table is found. */
-			/* so we fall back to the old way we used to do this */
-			/* and just rely on the first entry to be correct. */
-			return pci_mmcfg_config[0].base_address;
+			/* Not found - fallback to type 1 */
+			return 0;
 		}
 		cfg = &pci_mmcfg_config[cfg_num];
 		if (cfg->pci_segment_group_number != seg)
@@ -44,9 +48,9 @@ static u32 get_base_addr(unsigned int seg, int bus)
 	}
 }
 
-static inline void pci_exp_set_dev_base(unsigned int seg, int bus, int devfn)
+static inline void pci_exp_set_dev_base(unsigned int base, int bus, int devfn)
 {
-	u32 dev_base = get_base_addr(seg, bus) | (bus << 20) | (devfn << 12);
+	u32 dev_base = base | (bus << 20) | (devfn << 12);
 	if (dev_base != mmcfg_last_accessed_device) {
 		mmcfg_last_accessed_device = dev_base;
 		set_fixmap_nocache(FIX_PCIE_MCFG, dev_base);
@@ -57,13 +61,18 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
 	unsigned long flags;
+	u32 base;
 
 	if (!value || (bus > 255) || (devfn > 255) || (reg > 4095))
 		return -EINVAL;
 
+	base = get_base_addr(seg, bus, devfn);
+	if (!base)
+		return pci_conf1_read(seg,bus,devfn,reg,len,value);
+
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(seg, bus, devfn);
+	pci_exp_set_dev_base(base, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -86,13 +95,18 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
 	unsigned long flags;
+	u32 base;
 
 	if ((bus > 255) || (devfn > 255) || (reg > 4095)) 
 		return -EINVAL;
 
+	base = get_base_addr(seg, bus, devfn);
+	if (!base)
+		return pci_conf1_write(seg,bus,devfn,reg,len,value);
+
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(seg, bus, devfn);
+	pci_exp_set_dev_base(base, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -116,6 +130,37 @@ static struct pci_raw_ops pci_mmcfg = {
 	.write =	pci_mmcfg_write,
 };
 
+/* K8 systems have some devices (typically in the builtin northbridge)
+   that are only accessible using type1
+   Normally this can be expressed in the MCFG by not listing them
+   and assigning suitable _SEGs, but this isn't implemented in some BIOS.
+   Instead try to discover all devices on bus 0 that are unreachable using MM
+   and fallback for them.
+   We only do this for bus 0/seg 0 */
+static __init void unreachable_devices(void)
+{
+	int i;
+	unsigned long flags;
+
+	for (i = 0; i < 32; i++) {
+		u32 val1;
+		u32 addr;
+
+		pci_conf1_read(0, 0, PCI_DEVFN(i, 0), 0, 4, &val1);
+		if (val1 == 0xffffffff)
+			continue;
+
+		/* Locking probably not needed, but safer */
+		spin_lock_irqsave(&pci_config_lock, flags);
+		addr = get_base_addr(0, 0, PCI_DEVFN(i, 0));
+		if (addr != 0)
+			pci_exp_set_dev_base(addr, 0, PCI_DEVFN(i, 0));
+		if (addr == 0 || readl((u32 *)addr) != val1)
+			set_bit(i, fallback_slots);
+		spin_unlock_irqrestore(&pci_config_lock, flags);
+	}
+}
+
 static int __init pci_mmcfg_init(void)
 {
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
@@ -131,6 +176,8 @@ static int __init pci_mmcfg_init(void)
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 
+	unreachable_devices();
+
  out:
 	return 0;
 }
diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h
index 127d53ad16b..f550781ec31 100644
--- a/arch/i386/pci/pci.h
+++ b/arch/i386/pci/pci.h
@@ -74,3 +74,10 @@ extern spinlock_t pci_config_lock;
 
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
+
+extern int pci_conf1_write(unsigned int seg, unsigned int bus,
+			   unsigned int devfn, int reg, int len, u32 value);
+extern int pci_conf1_read(unsigned int seg, unsigned int bus,
+			  unsigned int devfn, int reg, int len, u32 *value);
+
+
diff --git a/arch/x86_64/ia32/ia32_binfmt.c b/arch/x86_64/ia32/ia32_binfmt.c
index 830feb272ec..2b760d0d9ce 100644
--- a/arch/x86_64/ia32/ia32_binfmt.c
+++ b/arch/x86_64/ia32/ia32_binfmt.c
@@ -217,8 +217,7 @@ elf_core_copy_task_fpregs(struct task_struct *tsk, struct pt_regs *regs, elf_fpr
 	if (!tsk_used_math(tsk))
 		return 0;
 	if (!regs)
-		regs = (struct pt_regs *)tsk->thread.rsp0;
-	--regs;
+		regs = ((struct pt_regs *)tsk->thread.rsp0) - 1;
 	if (tsk == current)
 		unlazy_fpu(tsk);
 	set_fs(KERNEL_DS); 
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 683c33f7b96..ecbd7b83acc 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -1181,7 +1181,7 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
-	disable_APIC_timer();
+	clear_local_APIC();
 
 	/*
 	 * HACK:
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index fdaddc4e528..74102796e5c 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -59,7 +59,7 @@ static int notsc __initdata = 0;
 unsigned int cpu_khz;					/* TSC clocks / usec, not used here */
 static unsigned long hpet_period;			/* fsecs / HPET clock */
 unsigned long hpet_tick;				/* HPET clocks / interrupt */
-static int hpet_use_timer;
+static int hpet_use_timer;				/* Use counter of hpet for time keeping, otherwise PIT */
 unsigned long vxtime_hz = PIT_TICK_RATE;
 int report_lost_ticks;				/* command line option */
 unsigned long long monotonic_base;
@@ -908,12 +908,14 @@ void __init time_init(void)
 	if (!hpet_init())
                 vxtime_hz = (1000000000000000L + hpet_period / 2) /
 			hpet_period;
+	else
+		vxtime.hpet_address = 0;
 
 	if (hpet_use_timer) {
 		cpu_khz = hpet_calibrate_tsc();
 		timename = "HPET";
 #ifdef CONFIG_X86_PM_TIMER
-	} else if (pmtmr_ioport) {
+	} else if (pmtmr_ioport && !vxtime.hpet_address) {
 		vxtime_hz = PM_TIMER_FREQUENCY;
 		timename = "PM";
 		pit_init();
diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c
index ecf7acb5db9..0d260e4492f 100644
--- a/arch/x86_64/mm/ioremap.c
+++ b/arch/x86_64/mm/ioremap.c
@@ -247,9 +247,15 @@ void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
 	return __ioremap(phys_addr, size, _PAGE_PCD);
 }
 
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
 void iounmap(volatile void __iomem *addr)
 {
-	struct vm_struct *p;
+	struct vm_struct *p, *o;
 
 	if (addr <= high_memory) 
 		return; 
@@ -257,12 +263,31 @@ void iounmap(volatile void __iomem *addr)
 		addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
-	write_lock(&vmlist_lock);
-	p = __remove_vm_area((void *)((unsigned long)addr & PAGE_MASK));
-	if (!p)
+	addr = (volatile void *)(PAGE_MASK & (unsigned long __force)addr);
+	/* Use the vm area unlocked, assuming the caller
+	   ensures there isn't another iounmap for the same address
+	   in parallel. Reuse of the virtual address is prevented by
+	   leaving it in the global lists until we're done with it.
+	   cpa takes care of the direct mappings. */
+	read_lock(&vmlist_lock);
+	for (p = vmlist; p; p = p->next) {
+		if (p->addr == addr)
+			break;
+	}
+	read_unlock(&vmlist_lock);
+
+	if (!p) {
 		printk("iounmap: bad address %p\n", addr);
-	else if (p->flags >> 20)
+		dump_stack();
+		return;
+	}
+
+	/* Reset the direct mapping. Can block */
+	if (p->flags >> 20)
 		ioremap_change_attr(p->phys_addr, p->size, 0);
-	write_unlock(&vmlist_lock);
+
+	/* Finally remove it */
+	o = remove_vm_area((void *)addr);
+	BUG_ON(p != o || o == NULL);
 	kfree(p); 
 }
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index a828a01739c..15b67d2760c 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -53,6 +53,8 @@ static int __init populate_memnodemap(
 	int res = -1;
 	unsigned long addr, end;
 
+	if (shift >= 64)
+		return -1;
 	memset(memnodemap, 0xff, sizeof(memnodemap));
 	for (i = 0; i < numnodes; i++) {
 		addr = nodes[i].start;
@@ -65,7 +67,7 @@ static int __init populate_memnodemap(
 			if (memnodemap[addr >> shift] != 0xff)
 				return -1;
 			memnodemap[addr >> shift] = i;
-			addr += (1 << shift);
+                       addr += (1UL << shift);
 		} while (addr < end);
 		res = 1;
 	} 
diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c
index a0838c4a94e..9c4f907e301 100644
--- a/arch/x86_64/pci/mmconfig.c
+++ b/arch/x86_64/pci/mmconfig.c
@@ -8,10 +8,13 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/bitmap.h>
 #include "pci.h"
 
 #define MMCONFIG_APER_SIZE (256*1024*1024)
 
+static DECLARE_BITMAP(fallback_slots, 32);
+
 /* Static virtual mapping of the MMCONFIG aperture */
 struct mmcfg_virt {
 	struct acpi_table_mcfg_config *cfg;
@@ -19,7 +22,7 @@ struct mmcfg_virt {
 };
 static struct mmcfg_virt *pci_mmcfg_virt;
 
-static char *get_virt(unsigned int seg, int bus)
+static char *get_virt(unsigned int seg, unsigned bus)
 {
 	int cfg_num = -1;
 	struct acpi_table_mcfg_config *cfg;
@@ -27,10 +30,9 @@ static char *get_virt(unsigned int seg, int bus)
 	while (1) {
 		++cfg_num;
 		if (cfg_num >= pci_mmcfg_config_num) {
-			/* something bad is going on, no cfg table is found. */
-			/* so we fall back to the old way we used to do this */
-			/* and just rely on the first entry to be correct. */
-			return pci_mmcfg_virt[0].virt;
+			/* Not found - fall back to type 1. This happens
+			   e.g. on the internal devices of a K8 northbridge. */
+			return NULL;
 		}
 		cfg = pci_mmcfg_virt[cfg_num].cfg;
 		if (cfg->pci_segment_group_number != seg)
@@ -41,20 +43,30 @@ static char *get_virt(unsigned int seg, int bus)
 	}
 }
 
-static inline char *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+static char *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
 {
-
-	return get_virt(seg, bus) + ((bus << 20) | (devfn << 12));
+	char *addr;
+	if (seg == 0 && bus == 0 && test_bit(PCI_SLOT(devfn), &fallback_slots))
+		return NULL;
+	addr = get_virt(seg, bus);
+	if (!addr)
+		return NULL;
+ 	return addr + ((bus << 20) | (devfn << 12));
 }
 
 static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
-	char *addr = pci_dev_base(seg, bus, devfn);
+	char *addr;
 
+	/* Why do we have this when nobody checks it. How about a BUG()!? -AK */
 	if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
 
+	addr = pci_dev_base(seg, bus, devfn);
+	if (!addr)
+		return pci_conf1_read(seg,bus,devfn,reg,len,value);
+
 	switch (len) {
 	case 1:
 		*value = readb(addr + reg);
@@ -73,11 +85,16 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
-	char *addr = pci_dev_base(seg, bus, devfn);
+	char *addr;
 
+	/* Why do we have this when nobody checks it. How about a BUG()!? -AK */
 	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
 
+	addr = pci_dev_base(seg, bus, devfn);
+	if (!addr)
+		return pci_conf1_write(seg,bus,devfn,reg,len,value);
+
 	switch (len) {
 	case 1:
 		writeb(value, addr + reg);
@@ -98,6 +115,30 @@ static struct pci_raw_ops pci_mmcfg = {
 	.write =	pci_mmcfg_write,
 };
 
+/* K8 systems have some devices (typically in the builtin northbridge)
+   that are only accessible using type1
+   Normally this can be expressed in the MCFG by not listing them
+   and assigning suitable _SEGs, but this isn't implemented in some BIOS.
+   Instead try to discover all devices on bus 0 that are unreachable using MM
+   and fallback for them.
+   We only do this for bus 0/seg 0 */
+static __init void unreachable_devices(void)
+{
+	int i;
+	for (i = 0; i < 32; i++) {
+		u32 val1;
+		char *addr;
+
+		pci_conf1_read(0, 0, PCI_DEVFN(i,0), 0, 4, &val1);
+		if (val1 == 0xffffffff)
+			continue;
+		addr = pci_dev_base(0, 0, PCI_DEVFN(i, 0));
+		if (addr == NULL|| readl(addr) != val1) {
+			set_bit(i, &fallback_slots);
+		}
+	}
+}
+
 static int __init pci_mmcfg_init(void)
 {
 	int i;
@@ -128,6 +169,8 @@ static int __init pci_mmcfg_init(void)
 		printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_config[i].base_address);
 	}
 
+	unreachable_devices();
+
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;