Merge tag 'stable/for-linus-3.5-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull five Xen bug-fixes from Konrad Rzeszutek Wilk:

 - When booting as PVHVM we would try to use PV console - but would not validate
   the parameters causing us to crash during restore b/c we re-use the wrong event
   channel.
 - When booting on machines with SR-IOV PCI bridge we didn't check for the bridge
   and tried to use it.
 - Under AMD machines would advertise the APERFMPERF resulting in needless amount
   of MSRs from the guest.
 - A global value (xen_released_pages) was not subtracted at bootup when pages
   were added back in. This resulted in the balloon worker having the wrong
   account of how many pages were truly released.
 - Fix dead-lock when xen-blkfront is run in the same domain as xen-blkback.

* tag 'stable/for-linus-3.5-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen: mark local pages as FOREIGN in the m2p_override
  xen/setup: filter APERFMPERF cpuid feature out
  xen/balloon: Subtract from xen_released_pages the count that is populated.
  xen/pci: Check for PCI bridge before using it.
  xen/events: Add WARN_ON when quick lookup found invalid type.
  xen/hvc: Check HVM_PARAM_CONSOLE_[EVTCHN|PFN] for correctness.
  xen/hvc: Fix error cases around HVM_PARAM_CONSOLE_PFN
  xen/hvc: Collapse error logic.

6 files changed, 73 insertions, 16 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e74df95..ff962d4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -209,6 +209,9 @@ static void __init xen_banner(void)
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 
+#define CPUID_THERM_POWER_LEAF 6
+#define APERFMPERF_PRESENT 0
+
 static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
 static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
 
@@ -242,6 +245,11 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		*dx = cpuid_leaf5_edx_val;
 		return;
 
+	case CPUID_THERM_POWER_LEAF:
+		/* Disabling APERFMPERF for kernel usage */
+		maskecx = ~(1 << APERFMPERF_PRESENT);
+		break;
+
 	case 0xb:
 		/* Suppress extended topology stuff */
 		maskebx = 0;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index ffd08c4..64effdc6 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -706,6 +706,7 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
+	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -741,6 +742,24 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
 
+	/* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
+	 * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
+	 * pfn so that the following mfn_to_pfn(mfn) calls will return the
+	 * pfn from the m2p_override (the backend pfn) instead.
+	 * We need to do this because the pages shared by the frontend
+	 * (xen-blkfront) can be already locked (lock_page, called by
+	 * do_read_cache_page); when the userspace backend tries to use them
+	 * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
+	 * do_blockdev_direct_IO is going to try to lock the same pages
+	 * again resulting in a deadlock.
+	 * As a side effect get_user_pages_fast might not be safe on the
+	 * frontend pages while they are being shared with the backend,
+	 * because mfn_to_pfn (that ends up being called by GUPF) will
+	 * return the backend pfn rather than the frontend pfn. */
+	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+	if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
@@ -752,6 +771,7 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
+	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	mfn = get_phys_to_machine(pfn);
@@ -821,6 +841,22 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	} else
 		set_phys_to_machine(pfn, page->index);
 
+	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
+	 * somewhere in this domain, even before being added to the
+	 * m2p_override (see comment above in m2p_add_override).
+	 * If there are no other entries in the m2p_override corresponding
+	 * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
+	 * the original pfn (the one shared by the frontend): the backend
+	 * cannot do any IO on this page anymore because it has been
+	 * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
+	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
+	 * pfn again. */
+	mfn &= ~FOREIGN_FRAME_BIT;
+	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+	if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+			m2p_find_override(mfn) == NULL)
+		set_phys_to_machine(pfn, mfn);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_remove_override);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 3ebba07..a4790bf 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -371,7 +371,8 @@ char * __init xen_memory_setup(void)
 	populated = xen_populate_chunk(map, memmap.nr_entries,
 			max_pfn, &last_pfn, xen_released_pages);
 
-	extra_pages += (xen_released_pages - populated);
+	xen_released_pages -= populated;
+	extra_pages += xen_released_pages;
 
 	if (last_pfn > max_pfn) {
 		max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index d3d91da..944eaeb 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -214,24 +214,24 @@ static int xen_hvm_console_init(void)
 	/* already configured */
 	if (info->intf != NULL)
 		return 0;
-
+	/*
+	 * If the toolstack (or the hypervisor) hasn't set these values, the
+	 * default value is 0. Even though mfn = 0 and evtchn = 0 are
+	 * theoretically correct values, in practice they never are and they
+	 * mean that a legacy toolstack hasn't initialized the pv console correctly.
+	 */
 	r = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v);
-	if (r < 0) {
-		kfree(info);
-		return -ENODEV;
-	}
+	if (r < 0 || v == 0)
+		goto err;
 	info->evtchn = v;
-	hvm_get_parameter(HVM_PARAM_CONSOLE_PFN, &v);
-	if (r < 0) {
-		kfree(info);
-		return -ENODEV;
-	}
+	v = 0;
+	r = hvm_get_parameter(HVM_PARAM_CONSOLE_PFN, &v);
+	if (r < 0 || v == 0)
+		goto err;
 	mfn = v;
 	info->intf = ioremap(mfn << PAGE_SHIFT, PAGE_SIZE);
-	if (info->intf == NULL) {
-		kfree(info);
-		return -ENODEV;
-	}
+	if (info->intf == NULL)
+		goto err;
 	info->vtermno = HVC_COOKIE;
 
 	spin_lock(&xencons_lock);
@@ -239,6 +239,9 @@ static int xen_hvm_console_init(void)
 	spin_unlock(&xencons_lock);
 
 	return 0;
+err:
+	kfree(info);
+	return -ENODEV;
 }
 
 static int xen_pv_console_init(void)
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 6908e4c..7595581 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -827,6 +827,9 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 					      handle_edge_irq, "event");
 
 		xen_irq_info_evtchn_init(irq, evtchn);
+	} else {
+		struct irq_info *info = info_for_irq(irq);
+		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
 	}
 
 out:
@@ -862,6 +865,9 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
 
 		bind_evtchn_to_cpu(evtchn, cpu);
+	} else {
+		struct irq_info *info = info_for_irq(irq);
+		WARN_ON(info == NULL || info->type != IRQT_IPI);
 	}
 
  out:
@@ -939,6 +945,9 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
 
 		bind_evtchn_to_cpu(evtchn, cpu);
+	} else {
+		struct irq_info *info = info_for_irq(irq);
+		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
 	}
 
 out:
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index b84bf0b..18fff88 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -59,7 +59,7 @@ static int xen_add_device(struct device *dev)
 
 #ifdef CONFIG_ACPI
 		handle = DEVICE_ACPI_HANDLE(&pci_dev->dev);
-		if (!handle)
+		if (!handle && pci_dev->bus->bridge)
 			handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge);
 #ifdef CONFIG_PCI_IOV
 		if (!handle && pci_dev->is_virtfn)