Merge branch 'staging' of ssh://xenbits.xen.org/home/xen/git/xen into staging

4 files changed, 68 insertions, 26 deletions

diff --git a/xen/arch/x86/acpi/lib.c b/xen/arch/x86/acpi/lib.c
index e8e69d1cb4..1f98c316c3 100644
--- a/xen/arch/x86/acpi/lib.c
+++ b/xen/arch/x86/acpi/lib.c
@@ -39,7 +39,7 @@ u32 __read_mostly x86_acpiid_to_apicid[MAX_MADT_ENTRIES] =
  * from the fixed base.  That's why we start at FIX_ACPI_END and
  * count idx down while incrementing the phys address.
  */
-char *__acpi_map_table(unsigned long phys, unsigned long size)
+char *__acpi_map_table(paddr_t phys, unsigned long size)
 {
 	unsigned long base, offset, mapped_size;
 	int idx;
diff --git a/xen/arch/x86/hvm/vmsi.c b/xen/arch/x86/hvm/vmsi.c
index 36de312ef0..0244b133fe 100644
--- a/xen/arch/x86/hvm/vmsi.c
+++ b/xen/arch/x86/hvm/vmsi.c
@@ -169,6 +169,7 @@ struct msixtbl_entry
         uint32_t msi_ad[3];	/* Shadow of address low, high and data */
     } gentries[MAX_MSIX_ACC_ENTRIES];
     struct rcu_head rcu;
+    const struct pirq *pirq;
 };
 
 static DEFINE_RCU_READ_LOCK(msixtbl_rcu_lock);
@@ -254,6 +255,8 @@ static int msixtbl_write(struct vcpu *v, unsigned long address,
     void *virt;
     unsigned int nr_entry, index;
     int r = X86EMUL_UNHANDLEABLE;
+    unsigned long flags, orig;
+    struct irq_desc *desc;
 
     if ( len != 4 || (address & 3) )
         return r;
@@ -283,22 +286,49 @@ static int msixtbl_write(struct vcpu *v, unsigned long address,
     if ( !virt )
         goto out;
 
-    /* Do not allow the mask bit to be changed. */
-#if 0 /* XXX
-       * As the mask bit is the only defined bit in the word, and as the
-       * host MSI-X code doesn't preserve the other bits anyway, doing
-       * this is pointless. So for now just discard the write (also
-       * saving us from having to determine the matching irq_desc).
-       */
-    spin_lock_irqsave(&desc->lock, flags);
+    desc = pirq_spin_lock_irq_desc(entry->pirq, &flags);
+    if ( !desc )
+        goto out;
+
+    if ( !desc->msi_desc )
+        goto unlock;
+
     orig = readl(virt);
-    val &= ~PCI_MSIX_VECTOR_BITMASK;
-    val |= orig & PCI_MSIX_VECTOR_BITMASK;
+
+    /*
+     * Do not allow guest to modify MSI-X control bit if it is masked
+     * by Xen. We'll only handle the case where Xen thinks that
+     * bit is unmasked, but hardware has silently masked the bit
+     * (in case of SR-IOV VF reset, etc). On the other hand, if Xen
+     * thinks that the bit is masked, but it's really not,
+     * we log a warning.
+     */
+    if ( desc->msi_desc->msi_attrib.masked )
+    {
+        if ( !(orig & PCI_MSIX_VECTOR_BITMASK) )
+            printk(XENLOG_WARNING "MSI-X control bit is unmasked when"
+                   " it is expected to be masked [%04x:%02x:%02x.%01x]\n",
+                   entry->pdev->seg, entry->pdev->bus,
+                   PCI_SLOT(entry->pdev->devfn),
+                   PCI_FUNC(entry->pdev->devfn));
+
+        goto unlock;
+    }
+
+    /*
+     * The mask bit is the only defined bit in the word. But we
+     * ought to preserve the reserved bits. Clearing the reserved
+     * bits can result in undefined behaviour (see PCI Local Bus
+     * Specification revision 2.3).
+     */
+    val &= PCI_MSIX_VECTOR_BITMASK;
+    val |= (orig & ~PCI_MSIX_VECTOR_BITMASK);
     writel(val, virt);
-    spin_unlock_irqrestore(&desc->lock, flags);
-#endif
 
+unlock:
+    spin_unlock_irqrestore(&desc->lock, flags);
     r = X86EMUL_OKAY;
+
 out:
     rcu_read_unlock(&msixtbl_rcu_lock);
     return r;
@@ -328,7 +358,8 @@ const struct hvm_mmio_handler msixtbl_mmio_handler = {
 static void add_msixtbl_entry(struct domain *d,
                               struct pci_dev *pdev,
                               uint64_t gtable,
-                              struct msixtbl_entry *entry)
+                              struct msixtbl_entry *entry,
+                              const struct pirq *pirq)
 {
     u32 len;
 
@@ -342,6 +373,7 @@ static void add_msixtbl_entry(struct domain *d,
     entry->table_len = len;
     entry->pdev = pdev;
     entry->gtable = (unsigned long) gtable;
+    entry->pirq = pirq;
 
     list_add_rcu(&entry->list, &d->arch.hvm_domain.msixtbl_list);
 }
@@ -404,9 +436,10 @@ int msixtbl_pt_register(struct domain *d, struct pirq *pirq, uint64_t gtable)
 
     entry = new_entry;
     new_entry = NULL;
-    add_msixtbl_entry(d, pdev, gtable, entry);
+    add_msixtbl_entry(d, pdev, gtable, entry, pirq);
 
 found:
+    ASSERT(entry->pirq == pirq);
     atomic_inc(&entry->refcnt);
     spin_unlock(&d->arch.hvm_domain.msixtbl_list_lock);
     r = 0;
diff --git a/xen/drivers/acpi/osl.c b/xen/drivers/acpi/osl.c
index 1b60be621c..93c983ca9d 100644
--- a/xen/drivers/acpi/osl.c
+++ b/xen/drivers/acpi/osl.c
@@ -38,6 +38,7 @@
 #include <xen/spinlock.h>
 #include <xen/domain_page.h>
 #include <xen/efi.h>
+#include <xen/vmap.h>
 
 #define _COMPONENT		ACPI_OS_SERVICES
 ACPI_MODULE_NAME("osl")
@@ -83,14 +84,25 @@ acpi_physical_address __init acpi_os_get_root_pointer(void)
 	}
 }
 
-void __iomem *__init
+void __iomem *
 acpi_os_map_memory(acpi_physical_address phys, acpi_size size)
 {
-	return __acpi_map_table((unsigned long)phys, size);
+	if (system_state >= SYS_STATE_active) {
+		unsigned long pfn = PFN_DOWN(phys);
+		unsigned int offs = phys & (PAGE_SIZE - 1);
+
+		/* The low first Mb is always mapped. */
+		if ( !((phys + size - 1) >> 20) )
+			return __va(phys);
+		return __vmap(&pfn, PFN_UP(offs + size), 1, 1, PAGE_HYPERVISOR_NOCACHE) + offs;
+	}
+	return __acpi_map_table(phys, size);
 }
 
-void __init acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
+void acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
 {
+	if (system_state >= SYS_STATE_active)
+		vunmap((void *)((unsigned long)virt & PAGE_MASK));
 }
 
 acpi_status acpi_os_read_port(acpi_io_address port, u32 * value, u32 width)
@@ -133,9 +145,8 @@ acpi_status
 acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width)
 {
 	u32 dummy;
-	void __iomem *virt_addr;
+	void __iomem *virt_addr = acpi_os_map_memory(phys_addr, width >> 3);
 
-	virt_addr = map_domain_page(phys_addr>>PAGE_SHIFT);
 	if (!value)
 		value = &dummy;
 
@@ -153,7 +164,7 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width)
 		BUG();
 	}
 
-	unmap_domain_page(virt_addr);
+	acpi_os_unmap_memory(virt_addr, width >> 3);
 
 	return AE_OK;
 }
@@ -161,9 +172,7 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width)
 acpi_status
 acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width)
 {
-	void __iomem *virt_addr;
-
-	virt_addr = map_domain_page(phys_addr>>PAGE_SHIFT);
+	void __iomem *virt_addr = acpi_os_map_memory(phys_addr, width >> 3);
 
 	switch (width) {
 	case 8:
@@ -179,7 +188,7 @@ acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width)
 		BUG();
 	}
 
-	unmap_domain_page(virt_addr);
+	acpi_os_unmap_memory(virt_addr, width >> 3);
 
 	return AE_OK;
 }
diff --git a/xen/include/xen/acpi.h b/xen/include/xen/acpi.h
index 8f3cdca314..aedec65a28 100644
--- a/xen/include/xen/acpi.h
+++ b/xen/include/xen/acpi.h
@@ -56,7 +56,7 @@ typedef int (*acpi_table_handler) (struct acpi_table_header *table);
 typedef int (*acpi_table_entry_handler) (struct acpi_subtable_header *header, const unsigned long end);
 
 unsigned int acpi_get_processor_id (unsigned int cpu);
-char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
+char * __acpi_map_table (paddr_t phys_addr, unsigned long size);
 int acpi_boot_init (void);
 int acpi_boot_table_init (void);
 int acpi_numa_init (void);