Merge branch 'linus' into x86/core

4 files changed, 198 insertions, 156 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0a80d6a5e9f..21ef9dd3618 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -577,35 +577,29 @@ config SWIOTLB
 
 config IOMMU_HELPER
 	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
+
 config MAXSMP
 	bool "Configure Maximum number of SMP Processors and NUMA Nodes"
-	depends on X86_64 && SMP
+	depends on X86_64 && SMP && BROKEN
 	default n
 	help
 	  Configure maximum number of CPUS and NUMA Nodes for this architecture.
 	  If unsure, say N.
 
-if MAXSMP
-config NR_CPUS
-	int
-	default "4096"
-endif
-
-if !MAXSMP
 config NR_CPUS
-	int "Maximum number of CPUs (2-4096)"
-	range 2 4096
+	int "Maximum number of CPUs (2-512)" if !MAXSMP
+	range 2 512
 	depends on SMP
+	default "4096" if MAXSMP
 	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 4096 and the
+	  kernel will support.  The maximum supported value is 512 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.
-endif
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -996,17 +990,10 @@ config NUMA_EMU
 	  into virtual nodes when booted with "numa=fake=N", where N is the
 	  number of nodes. This is only useful for debugging.
 
-if MAXSMP
-
 config NODES_SHIFT
-	int
-	default "9"
-endif
-
-if !MAXSMP
-config NODES_SHIFT
-	int "Maximum NUMA Nodes (as a power of 2)"
+	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 9   if X86_64
+	default "9" if MAXSMP
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
@@ -1014,7 +1001,6 @@ config NODES_SHIFT
 	help
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accomodate various tables.
-endif
 
 config HAVE_ARCH_BOOTMEM_NODE
 	def_bool y
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8e786b0d665..346cae5ac42 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -122,80 +122,217 @@ static u64 tsc_read_refs(u64 *pm, u64 *hpet)
 	return ULLONG_MAX;
 }
 
-/**
- * native_calibrate_tsc - calibrate the tsc on boot
+/*
+ * Try to calibrate the TSC against the Programmable
+ * Interrupt Timer and return the frequency of the TSC
+ * in kHz.
+ *
+ * Return ULONG_MAX on failure to calibrate.
  */
-unsigned long native_calibrate_tsc(void)
+static unsigned long pit_calibrate_tsc(void)
 {
-	unsigned long flags;
-	u64 tsc1, tsc2, tr1, tr2, delta, pm1, pm2, hpet1, hpet2;
-	int hpet = is_hpet_enabled();
-	unsigned int tsc_khz_val = 0;
-
-	local_irq_save(flags);
-
-	tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+	u64 tsc, t1, t2, delta;
+	unsigned long tscmin, tscmax;
+	int pitcnt;
 
+	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
+	/*
+	 * Setup CTC channel 2* for mode 0, (interrupt on terminal
+	 * count mode), binary count. Set the latch register to 50ms
+	 * (LSB then MSB) to begin countdown.
+	 */
 	outb(0xb0, 0x43);
 	outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
 	outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
-	tr1 = get_cycles();
-	while ((inb(0x61) & 0x20) == 0);
-	tr2 = get_cycles();
 
-	tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+	tsc = t1 = t2 = get_cycles();
 
-	local_irq_restore(flags);
+	pitcnt = 0;
+	tscmax = 0;
+	tscmin = ULONG_MAX;
+	while ((inb(0x61) & 0x20) == 0) {
+		t2 = get_cycles();
+		delta = t2 - tsc;
+		tsc = t2;
+		if ((unsigned long) delta < tscmin)
+			tscmin = (unsigned int) delta;
+		if ((unsigned long) delta > tscmax)
+			tscmax = (unsigned int) delta;
+		pitcnt++;
+	}
 
 	/*
-	 * Preset the result with the raw and inaccurate PIT
-	 * calibration value
+	 * Sanity checks:
+	 *
+	 * If we were not able to read the PIT more than 5000
+	 * times, then we have been hit by a massive SMI
+	 *
+	 * If the maximum is 10 times larger than the minimum,
+	 * then we got hit by an SMI as well.
 	 */
-	delta = (tr2 - tr1);
+	if (pitcnt < 5000 || tscmax > 10 * tscmin)
+		return ULONG_MAX;
+
+	/* Calculate the PIT value */
+	delta = t2 - t1;
 	do_div(delta, 50);
-	tsc_khz_val = delta;
+	return delta;
+}
+
+
+/**
+ * native_calibrate_tsc - calibrate the tsc on boot
+ */
+unsigned long native_calibrate_tsc(void)
+{
+	u64 tsc1, tsc2, delta, pm1, pm2, hpet1, hpet2;
+	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
+	unsigned long flags;
+	int hpet = is_hpet_enabled(), i;
 
-	/* hpet or pmtimer available ? */
+	/*
+	 * Run 5 calibration loops to get the lowest frequency value
+	 * (the best estimate). We use two different calibration modes
+	 * here:
+	 *
+	 * 1) PIT loop. We set the PIT Channel 2 to oneshot mode and
+	 * load a timeout of 50ms. We read the time right after we
+	 * started the timer and wait until the PIT count down reaches
+	 * zero. In each wait loop iteration we read the TSC and check
+	 * the delta to the previous read. We keep track of the min
+	 * and max values of that delta. The delta is mostly defined
+	 * by the IO time of the PIT access, so we can detect when a
+	 * SMI/SMM disturbance happend between the two reads. If the
+	 * maximum time is significantly larger than the minimum time,
+	 * then we discard the result and have another try.
+	 *
+	 * 2) Reference counter. If available we use the HPET or the
+	 * PMTIMER as a reference to check the sanity of that value.
+	 * We use separate TSC readouts and check inside of the
+	 * reference read for a SMI/SMM disturbance. We dicard
+	 * disturbed values here as well. We do that around the PIT
+	 * calibration delay loop as we have to wait for a certain
+	 * amount of time anyway.
+	 */
+	for (i = 0; i < 5; i++) {
+		unsigned long tsc_pit_khz;
+
+		/*
+		 * Read the start value and the reference count of
+		 * hpet/pmtimer when available. Then do the PIT
+		 * calibration, which will take at least 50ms, and
+		 * read the end value.
+		 */
+		local_irq_save(flags);
+		tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+		tsc_pit_khz = pit_calibrate_tsc();
+		tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+		local_irq_restore(flags);
+
+		/* Pick the lowest PIT TSC calibration so far */
+		tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
+
+		/* hpet or pmtimer available ? */
+		if (!hpet && !pm1 && !pm2)
+			continue;
+
+		/* Check, whether the sampling was disturbed by an SMI */
+		if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
+			continue;
+
+		tsc2 = (tsc2 - tsc1) * 1000000LL;
+
+		if (hpet) {
+			if (hpet2 < hpet1)
+				hpet2 += 0x100000000ULL;
+			hpet2 -= hpet1;
+			tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
+			do_div(tsc1, 1000000);
+		} else {
+			if (pm2 < pm1)
+				pm2 += (u64)ACPI_PM_OVRRUN;
+			pm2 -= pm1;
+			tsc1 = pm2 * 1000000000LL;
+			do_div(tsc1, PMTMR_TICKS_PER_SEC);
+		}
+
+		do_div(tsc2, tsc1);
+		tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+	}
+
+	/*
+	 * Now check the results.
+	 */
+	if (tsc_pit_min == ULONG_MAX) {
+		/* PIT gave no useful value */
+		printk(KERN_WARNING "TSC: PIT calibration failed due to "
+		       "SMI disturbance.\n");
+
+		/* We don't have an alternative source, disable TSC */
+		if (!hpet && !pm1 && !pm2) {
+			printk("TSC: No reference (HPET/PMTIMER) available\n");
+			return 0;
+		}
+
+		/* The alternative source failed as well, disable TSC */
+		if (tsc_ref_min == ULONG_MAX) {
+			printk(KERN_WARNING "TSC: HPET/PMTIMER calibration "
+			       "failed due to SMI disturbance.\n");
+			return 0;
+		}
+
+		/* Use the alternative source */
+		printk(KERN_INFO "TSC: using %s reference calibration\n",
+		       hpet ? "HPET" : "PMTIMER");
+
+		return tsc_ref_min;
+	}
+
+	/* We don't have an alternative source, use the PIT calibration value */
 	if (!hpet && !pm1 && !pm2) {
-		printk(KERN_INFO "TSC calibrated against PIT\n");
-		goto out;
+		printk(KERN_INFO "TSC: Using PIT calibration value\n");
+		return tsc_pit_min;
 	}
 
-	/* Check, whether the sampling was disturbed by an SMI */
-	if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) {
-		printk(KERN_WARNING "TSC calibration disturbed by SMI, "
-				"using PIT calibration result\n");
-		goto out;
+	/* The alternative source failed, use the PIT calibration value */
+	if (tsc_ref_min == ULONG_MAX) {
+		printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed due "
+		       "to SMI disturbance. Using PIT calibration\n");
+		return tsc_pit_min;
 	}
 
-	tsc2 = (tsc2 - tsc1) * 1000000LL;
-
-	if (hpet) {
-		printk(KERN_INFO "TSC calibrated against HPET\n");
-		if (hpet2 < hpet1)
-			hpet2 += 0x100000000ULL;
-		hpet2 -= hpet1;
-		tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
-		do_div(tsc1, 1000000);
-	} else {
-		printk(KERN_INFO "TSC calibrated against PM_TIMER\n");
-		if (pm2 < pm1)
-			pm2 += (u64)ACPI_PM_OVRRUN;
-		pm2 -= pm1;
-		tsc1 = pm2 * 1000000000LL;
-		do_div(tsc1, PMTMR_TICKS_PER_SEC);
+	/* Check the reference deviation */
+	delta = ((u64) tsc_pit_min) * 100;
+	do_div(delta, tsc_ref_min);
+
+	/*
+	 * If both calibration results are inside a 5% window, the we
+	 * use the lower frequency of those as it is probably the
+	 * closest estimate.
+	 */
+	if (delta >= 95 && delta <= 105) {
+		printk(KERN_INFO "TSC: PIT calibration confirmed by %s.\n",
+		       hpet ? "HPET" : "PMTIMER");
+		printk(KERN_INFO "TSC: using %s calibration value\n",
+		       tsc_pit_min <= tsc_ref_min ? "PIT" :
+		       hpet ? "HPET" : "PMTIMER");
+		return tsc_pit_min <= tsc_ref_min ? tsc_pit_min : tsc_ref_min;
 	}
 
-	do_div(tsc2, tsc1);
-	tsc_khz_val = tsc2;
+	printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
+	       hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
 
-out:
-	return tsc_khz_val;
+	/*
+	 * The calibration values differ too much. In doubt, we use
+	 * the PIT value as we know that there are PMTIMERs around
+	 * running at double speed.
+	 */
+	printk(KERN_INFO "TSC: Using PIT calibration value\n");
+	return tsc_pit_min;
 }
 
-
 #ifdef CONFIG_X86_32
 /* Only called from the Powernow K7 cpu freq driver */
 int recalibrate_cpu_khz(void)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index f72ac1fa35f..4a814bff21f 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -345,7 +345,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		shadow_addr = __pa(shadow_page->spt);
 		shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
 			| PT_WRITABLE_MASK | PT_USER_MASK;
-		*shadow_ent = shadow_pte;
+		set_shadow_pte(shadow_ent, shadow_pte);
 	}
 
 	mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access,
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index d765da91384..8791fc55e71 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -31,11 +31,8 @@
 #include <linux/ioport.h>
 #include <linux/errno.h>
 #include <linux/bootmem.h>
-#include <linux/acpi.h>
 
 #include <asm/pat.h>
-#include <asm/hpet.h>
-#include <asm/io_apic.h>
 
 #include "pci.h"
 
@@ -80,77 +77,6 @@ pcibios_align_resource(void *data, struct resource *res,
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
-static int check_res_with_valid(struct pci_dev *dev, struct resource *res)
-{
-	unsigned long base;
-	unsigned long size;
-	int i;
-
-	base = res->start;
-	size = (res->start == 0 && res->end == res->start) ? 0 :
-		 (res->end - res->start + 1);
-
-	if (!base || !size)
-		return 0;
-
-#ifdef CONFIG_HPET_TIMER
-	/* for hpet */
-	if (base == hpet_address && (res->flags & IORESOURCE_MEM)) {
-		dev_info(&dev->dev, "BAR has HPET at %08lx-%08lx\n",
-				 base, base + size - 1);
-		return 1;
-	}
-#endif
-
-#ifdef CONFIG_X86_IO_APIC
-	for (i = 0; i < nr_ioapics; i++) {
-		unsigned long ioapic_phys = mp_ioapics[i].mp_apicaddr;
-
-		if (base == ioapic_phys && (res->flags & IORESOURCE_MEM)) {
-			dev_info(&dev->dev, "BAR has ioapic at %08lx-%08lx\n",
-					 base, base + size - 1);
-			return 1;
-		}
-	}
-#endif
-
-#ifdef CONFIG_PCI_MMCONFIG
-	for (i = 0; i < pci_mmcfg_config_num; i++) {
-		unsigned long addr;
-
-		addr = pci_mmcfg_config[i].address;
-		if (base == addr && (res->flags & IORESOURCE_MEM)) {
-			dev_info(&dev->dev, "BAR has MMCONFIG at %08lx-%08lx\n",
-					 base, base + size - 1);
-			return 1;
-		}
-	}
-#endif
-
-	return 0;
-}
-
-static int check_platform(struct pci_dev *dev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	/*
-	 * forcibly insert it into the
-	 * resource tree
-	 */
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-	else if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-
-	if (root && check_res_with_valid(dev, res)) {
-		insert_resource(root, res);
-
-		return 1;
-	}
-
-	return 0;
-}
 /*
  *  Handle resources of PCI devices.  If the world were perfect, we could
  *  just allocate all the resource regions and do nothing more.  It isn't.
@@ -202,10 +128,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				pr = pci_find_parent_resource(dev, r);
 				if (!r->start || !pr ||
 				    request_resource(pr, r) < 0) {
-					if (check_platform(dev, r))
-						continue;
-					dev_err(&dev->dev, "BAR %d: can't "
-						"allocate resource\n", idx);
+					dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -240,17 +163,13 @@ static void __init pcibios_allocate_resources(int pass)
 			else
 				disabled = !(command & PCI_COMMAND_MEMORY);
 			if (pass == disabled) {
-				dev_dbg(&dev->dev, "resource %#08llx-%#08llx "
-					"(f=%lx, d=%d, p=%d)\n",
+				dev_dbg(&dev->dev, "resource %#08llx-%#08llx (f=%lx, d=%d, p=%d)\n",
 					(unsigned long long) r->start,
 					(unsigned long long) r->end,
 					r->flags, disabled, pass);
 				pr = pci_find_parent_resource(dev, r);
 				if (!pr || request_resource(pr, r) < 0) {
-					if (check_platform(dev, r))
-						continue;
-					dev_err(&dev->dev, "BAR %d: can't "
-						"allocate resource\n", idx);
+					dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;