7 files changed, 218 insertions, 30 deletions

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7fda040a76cd..d240ea950519 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -200,6 +200,23 @@ extern struct { char _entry[32]; } hypercall_page[];
         (type)__res;                                                    \
 })
 
+static inline long
+privcmd_call(unsigned call,
+             unsigned long a1, unsigned long a2,
+             unsigned long a3, unsigned long a4,
+             unsigned long a5)
+{
+        __HYPERCALL_DECLS;
+        __HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+
+        asm volatile("call *%[call]"
+                     : __HYPERCALL_5PARAM
+                     : [call] "a" (&hypercall_page[call])
+                     : __HYPERCALL_CLOBBER5);
+
+        return (long)__res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
@@ -270,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
-        return _hypercall2(int, sched_op_new, cmd, arg);
+        return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
@@ -405,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value)
 #endif
 
 static inline int
-HYPERVISOR_suspend(unsigned long srec)
+HYPERVISOR_suspend(unsigned long start_info_mfn)
 {
-        return _hypercall3(int, sched_op, SCHEDOP_shutdown,
-                           SHUTDOWN_suspend, srec);
+        struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+        /*
+         * For a PV guest the tools require that the start_info mfn be
+         * present in rdx/edx when the hypercall is made. Per the
+         * hypercall calling convention this is the third hypercall
+         * argument, which is start_info_mfn here.
+         */
+        return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
 }
 
 static inline int
@@ -423,6 +447,13 @@ HYPERVISOR_hvm_op(int op, void *arg)
        return _hypercall2(unsigned long, hvm_op, op, arg);
 }
 
+static inline int
+HYPERVISOR_tmem_op(
+        struct tmem_op *op)
+{
+        return _hypercall1(int, tmem_op, op);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 396ff4cc8ed4..66d0fff1ee84 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,4 +37,39 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
+#include <asm/processor.h>
+
+static inline uint32_t xen_cpuid_base(void)
+{
+        uint32_t base, eax, ebx, ecx, edx;
+        char signature[13];
+
+        for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+                cpuid(base, &eax, &ebx, &ecx, &edx);
+                *(uint32_t *)(signature + 0) = ebx;
+                *(uint32_t *)(signature + 4) = ecx;
+                *(uint32_t *)(signature + 8) = edx;
+                signature[12] = 0;
+
+                if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
+                        return base;
+        }
+
+        return 0;
+}
+
+#ifdef CONFIG_XEN
+extern bool xen_hvm_need_lapic(void);
+
+static inline bool xen_x2apic_para_available(void)
+{
+        return xen_hvm_need_lapic();
+}
+#else
+static inline bool xen_x2apic_para_available(void)
+{
+        return (xen_cpuid_base() != 0);
+}
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index e8506c1f0c55..5d4922ad4b9b 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void);
 #define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
 #endif
 
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
 
 /* Maximum number of virtual CPUs in multi-processor guests. */
 #define MAX_VIRT_CPUS 32
@@ -86,7 +86,7 @@ DEFINE_GUEST_HANDLE(void);
  * The privilege level specifies which modes may enter a trap via a software
  * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
  * privilege levels as follows:
- *  Level == 0: Noone may enter
+ *  Level == 0: No one may enter
  *  Level == 1: Kernel may enter
  *  Level == 2: Kernel may enter
  *  Level == 3: Everyone may enter
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index 42a7e004ae5c..8413688b2571 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -32,6 +32,11 @@
 /* And the trap vector is... */
 #define TRAP_INSTR "int $0x82"
 
+#define __MACH2PHYS_VIRT_START 0xF5800000
+#define __MACH2PHYS_VIRT_END   0xF6800000
+
+#define __MACH2PHYS_SHIFT      2
+
 /*
  * Virtual addresses beyond this are not modifiable by guest OSes. The
  * machine->physical mapping table starts at this address, read-only.
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index 100d2662b97c..839a4811cf98 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -39,18 +39,7 @@
 #define __HYPERVISOR_VIRT_END   0xFFFF880000000000
 #define __MACH2PHYS_VIRT_START  0xFFFF800000000000
 #define __MACH2PHYS_VIRT_END    0xFFFF804000000000
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
-#endif
-
-#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define __MACH2PHYS_SHIFT       3
 
 /*
  * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index bf5f7d32bd08..64a619d47d34 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/pfn.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -28,23 +29,46 @@ typedef struct xpaddr {
 
 /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
 #define INVALID_P2M_ENTRY       (~0UL)
-#define FOREIGN_FRAME_BIT       (1UL<<31)
+#define FOREIGN_FRAME_BIT       (1UL<<(BITS_PER_LONG-1))
+#define IDENTITY_FRAME_BIT      (1UL<<(BITS_PER_LONG-2))
 #define FOREIGN_FRAME(m)        ((m) | FOREIGN_FRAME_BIT)
+#define IDENTITY_FRAME(m)       ((m) | IDENTITY_FRAME_BIT)
 
 /* Maximum amount of memory we can handle in a domain in pages */
 #define MAX_DOMAIN_PAGES                                                \
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
+extern unsigned long *machine_to_phys_mapping;
+extern unsigned int   machine_to_phys_order;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
-extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-
+extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern unsigned long set_phys_range_identity(unsigned long pfn_s,
+                                             unsigned long pfn_e);
+
+extern int m2p_add_override(unsigned long mfn, struct page *page,
+                            bool clear_pte);
+extern int m2p_remove_override(struct page *page, bool clear_pte);
+extern struct page *m2p_find_override(unsigned long mfn);
+extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+extern int p2m_dump_show(struct seq_file *m, void *v);
+#endif
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
+        unsigned long mfn;
+
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return pfn;
 
-        return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
+        mfn = get_phys_to_machine(pfn);
+
+        if (mfn != INVALID_P2M_ENTRY)
+                mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
+
+        return mfn;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -58,22 +82,44 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
 {
         unsigned long pfn;
+        int ret = 0;
 
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return mfn;
 
-#if 0
-        if (unlikely((mfn >> machine_to_phys_order) != 0))
-                return max_mapnr;
-#endif
-
+        if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+                pfn = ~0;
+                goto try_override;
+        }
         pfn = 0;
         /*
          * The array access can fail (e.g., device space beyond end of RAM).
          * In such cases it doesn't matter what we return (we return garbage),
          * but we must handle the fault without crashing!
          */
-        __get_user(pfn, &machine_to_phys_mapping[mfn]);
+        ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+try_override:
+        /* ret might be < 0 if there are no entries in the m2p for mfn */
+        if (ret < 0)
+                pfn = ~0;
+        else if (get_phys_to_machine(pfn) != mfn)
+                /*
+                 * If this appears to be a foreign mfn (because the pfn
+                 * doesn't map back to the mfn), then check the local override
+                 * table to see if there's a better pfn to use.
+                 *
+                 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
+                 */
+                pfn = m2p_find_override_pfn(mfn, ~0);
+
+        /* 
+         * pfn is ~0 if there are no entries in the m2p for mfn or if the
+         * entry doesn't map back to the mfn and m2p_override doesn't have a
+         * valid entry for it.
+         */
+        if (pfn == ~0 &&
+                        get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+                pfn = mfn;
 
         return pfn;
 }
@@ -159,6 +205,7 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pgd_val_ma(x)   ((x).pgd)
 
+void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 
 xmaddr_t arbitrary_virt_to_machine(void *address);
 unsigned long arbitrary_virt_to_mfn(void *vaddr);
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
new file mode 100644
index 000000000000..4fbda9a3f339
--- /dev/null
+++ b/arch/x86/include/asm/xen/pci.h
@@ -0,0 +1,81 @@
+#ifndef _ASM_X86_XEN_PCI_H
+#define _ASM_X86_XEN_PCI_H
+
+#if defined(CONFIG_PCI_XEN)
+extern int __init pci_xen_init(void);
+extern int __init pci_xen_hvm_init(void);
+#define pci_xen 1
+#else
+#define pci_xen 0
+#define pci_xen_init (0)
+static inline int pci_xen_hvm_init(void)
+{
+        return -1;
+}
+#endif
+#if defined(CONFIG_XEN_DOM0)
+void __init xen_setup_pirqs(void);
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
+#else
+static inline void __init xen_setup_pirqs(void)
+{
+}
+static inline int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
+static inline int xen_register_device_domain_owner(struct pci_dev *dev,
+                                                   uint16_t domain)
+{
+        return -1;
+}
+static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
+#endif
+
+#if defined(CONFIG_PCI_MSI)
+#if defined(CONFIG_PCI_XEN)
+/* The drivers/pci/xen-pcifront.c sets this structure to
+ * its own functions.
+ */
+struct xen_pci_frontend_ops {
+        int (*enable_msi)(struct pci_dev *dev, int vectors[]);
+        void (*disable_msi)(struct pci_dev *dev);
+        int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec);
+        void (*disable_msix)(struct pci_dev *dev);
+};
+
+extern struct xen_pci_frontend_ops *xen_pci_frontend;
+
+static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
+                                              int vectors[])
+{
+        if (xen_pci_frontend && xen_pci_frontend->enable_msi)
+                return xen_pci_frontend->enable_msi(dev, vectors);
+        return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
+{
+        if (xen_pci_frontend && xen_pci_frontend->disable_msi)
+                        xen_pci_frontend->disable_msi(dev);
+}
+static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
+                                               int vectors[], int nvec)
+{
+        if (xen_pci_frontend && xen_pci_frontend->enable_msix)
+                return xen_pci_frontend->enable_msix(dev, vectors, nvec);
+        return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
+{
+        if (xen_pci_frontend && xen_pci_frontend->disable_msix)
+                        xen_pci_frontend->disable_msix(dev);
+}
+#endif /* CONFIG_PCI_XEN */
+#endif /* CONFIG_PCI_MSI */
+
+#endif  /* _ASM_X86_XEN_PCI_H */