9 files changed, 257 insertions, 48 deletions

diff --git a/include/xen/balloon.h b/include/xen/balloon.h
new file mode 100644
index 000000000000..a2b22f01a51d
--- /dev/null
+++ b/include/xen/balloon.h
@@ -0,0 +1,25 @@
+/******************************************************************************
+ * Xen balloon functionality
+ */
+
+#define RETRY_UNLIMITED 0
+
+struct balloon_stats {
+        /* We aim for 'current allocation' == 'target allocation'. */
+        unsigned long current_pages;
+        unsigned long target_pages;
+        /* Number of pages in high- and low-memory balloons. */
+        unsigned long balloon_low;
+        unsigned long balloon_high;
+        unsigned long schedule_delay;
+        unsigned long max_schedule_delay;
+        unsigned long retry_count;
+        unsigned long max_retry_count;
+};
+
+extern struct balloon_stats balloon_stats;
+
+void balloon_set_new_target(unsigned long target);
+
+int alloc_xenballooned_pages(int nr_pages, struct page** pages);
+void free_xenballooned_pages(int nr_pages, struct page** pages);
diff --git a/include/xen/events.h b/include/xen/events.h
index 32ebebacee7f..f1b87ad48ac7 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -23,6 +23,12 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
                            unsigned long irqflags,
                            const char *devname,
                            void *dev_id);
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+                                          unsigned int remote_port,
+                                          irq_handler_t handler,
+                                          unsigned long irqflags,
+                                          const char *devname,
+                                          void *dev_id);
 
 /*
  * Common unbind function for all event sources. Takes IRQ to unbind from.
diff --git a/include/xen/gntalloc.h b/include/xen/gntalloc.h
new file mode 100644
index 000000000000..76bd58065f4f
--- /dev/null
+++ b/include/xen/gntalloc.h
@@ -0,0 +1,82 @@
+/******************************************************************************
+ * gntalloc.h
+ *
+ * Interface to /dev/xen/gntalloc.
+ *
+ * Author: Daniel De Graaf <dgdegra@tycho.nsa.gov>
+ *
+ * This file is in the public domain.
+ */
+
+#ifndef __LINUX_PUBLIC_GNTALLOC_H__
+#define __LINUX_PUBLIC_GNTALLOC_H__
+
+/*
+ * Allocates a new page and creates a new grant reference.
+ */
+#define IOCTL_GNTALLOC_ALLOC_GREF \
+_IOC(_IOC_NONE, 'G', 5, sizeof(struct ioctl_gntalloc_alloc_gref))
+struct ioctl_gntalloc_alloc_gref {
+        /* IN parameters */
+        /* The ID of the domain to be given access to the grants. */
+        uint16_t domid;
+        /* Flags for this mapping */
+        uint16_t flags;
+        /* Number of pages to map */
+        uint32_t count;
+        /* OUT parameters */
+        /* The offset to be used on a subsequent call to mmap(). */
+        uint64_t index;
+        /* The grant references of the newly created grant, one per page */
+        /* Variable size, depending on count */
+        uint32_t gref_ids[1];
+};
+
+#define GNTALLOC_FLAG_WRITABLE 1
+
+/*
+ * Deallocates the grant reference, allowing the associated page to be freed if
+ * no other domains are using it.
+ */
+#define IOCTL_GNTALLOC_DEALLOC_GREF \
+_IOC(_IOC_NONE, 'G', 6, sizeof(struct ioctl_gntalloc_dealloc_gref))
+struct ioctl_gntalloc_dealloc_gref {
+        /* IN parameters */
+        /* The offset returned in the map operation */
+        uint64_t index;
+        /* Number of references to unmap */
+        uint32_t count;
+};
+
+/*
+ * Sets up an unmap notification within the page, so that the other side can do
+ * cleanup if this side crashes. Required to implement cross-domain robust
+ * mutexes or close notification on communication channels.
+ *
+ * Each mapped page only supports one notification; multiple calls referring to
+ * the same page overwrite the previous notification. You must clear the
+ * notification prior to the IOCTL_GNTALLOC_DEALLOC_GREF if you do not want it
+ * to occur.
+ */
+#define IOCTL_GNTALLOC_SET_UNMAP_NOTIFY \
+_IOC(_IOC_NONE, 'G', 7, sizeof(struct ioctl_gntalloc_unmap_notify))
+struct ioctl_gntalloc_unmap_notify {
+        /* IN parameters */
+        /* Offset in the file descriptor for a byte within the page (same as
+         * used in mmap). If using UNMAP_NOTIFY_CLEAR_BYTE, this is the byte to
+         * be cleared. Otherwise, it can be any byte in the page whose
+         * notification we are adjusting.
+         */
+        uint64_t index;
+        /* Action(s) to take on unmap */
+        uint32_t action;
+        /* Event channel to notify */
+        uint32_t event_channel_port;
+};
+
+/* Clear (set to zero) the byte specified by index */
+#define UNMAP_NOTIFY_CLEAR_BYTE 0x1
+/* Send an interrupt on the indicated event channel */
+#define UNMAP_NOTIFY_SEND_EVENT 0x2
+
+#endif /* __LINUX_PUBLIC_GNTALLOC_H__ */
diff --git a/include/xen/gntdev.h b/include/xen/gntdev.h
index eb23f4188f5a..5304bd3c84c5 100644
--- a/include/xen/gntdev.h
+++ b/include/xen/gntdev.h
@@ -116,4 +116,35 @@ struct ioctl_gntdev_set_max_grants {
         uint32_t count;
 };
 
+/*
+ * Sets up an unmap notification within the page, so that the other side can do
+ * cleanup if this side crashes. Required to implement cross-domain robust
+ * mutexes or close notification on communication channels.
+ *
+ * Each mapped page only supports one notification; multiple calls referring to
+ * the same page overwrite the previous notification. You must clear the
+ * notification prior to the IOCTL_GNTALLOC_DEALLOC_GREF if you do not want it
+ * to occur.
+ */
+#define IOCTL_GNTDEV_SET_UNMAP_NOTIFY \
+_IOC(_IOC_NONE, 'G', 7, sizeof(struct ioctl_gntdev_unmap_notify))
+struct ioctl_gntdev_unmap_notify {
+        /* IN parameters */
+        /* Offset in the file descriptor for a byte within the page (same as
+         * used in mmap). If using UNMAP_NOTIFY_CLEAR_BYTE, this is the byte to
+         * be cleared. Otherwise, it can be any byte in the page whose
+         * notification we are adjusting.
+         */
+        uint64_t index;
+        /* Action(s) to take on unmap */
+        uint32_t action;
+        /* Event channel to notify */
+        uint32_t event_channel_port;
+};
+
+/* Clear (set to zero) the byte specified by index */
+#define UNMAP_NOTIFY_CLEAR_BYTE 0x1
+/* Send an interrupt on the indicated event channel */
+#define UNMAP_NOTIFY_SEND_EVENT 0x2
+
 #endif /* __LINUX_PUBLIC_GNTDEV_H__ */
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c2d1fa4dc1ee..61e523af3c46 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -51,11 +51,7 @@ typedef uint64_t blkif_sector_t;
  */
 #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
 
-struct blkif_request {
-        uint8_t        operation;    /* BLKIF_OP_???                         */
-        uint8_t        nr_segments;  /* number of segments                   */
-        blkif_vdev_t   handle;       /* only for read/write requests         */
-        uint64_t       id;           /* private guest value, echoed in resp  */
+struct blkif_request_rw {
         blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
         struct blkif_request_segment {
                 grant_ref_t gref;        /* reference to I/O buffer frame        */
@@ -65,6 +61,16 @@ struct blkif_request {
         } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 };
 
+struct blkif_request {
+        uint8_t        operation;    /* BLKIF_OP_???                         */
+        uint8_t        nr_segments;  /* number of segments                   */
+        blkif_vdev_t   handle;       /* only for read/write requests         */
+        uint64_t       id;           /* private guest value, echoed in resp  */
+        union {
+                struct blkif_request_rw rw;
+        } u;
+};
+
 struct blkif_response {
         uint64_t        id;              /* copied from request */
         uint8_t         operation;       /* copied from request */
@@ -91,4 +97,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
 #define VDISK_REMOVABLE    0x2
 #define VDISK_READONLY     0x4
 
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR  3
+#define XEN_IDE1_MAJOR  22
+#define XEN_SCSI_DISK0_MAJOR    8
+#define XEN_SCSI_DISK1_MAJOR    65
+#define XEN_SCSI_DISK2_MAJOR    66
+#define XEN_SCSI_DISK3_MAJOR    67
+#define XEN_SCSI_DISK4_MAJOR    68
+#define XEN_SCSI_DISK5_MAJOR    69
+#define XEN_SCSI_DISK6_MAJOR    70
+#define XEN_SCSI_DISK7_MAJOR    71
+#define XEN_SCSI_DISK8_MAJOR    128
+#define XEN_SCSI_DISK9_MAJOR    129
+#define XEN_SCSI_DISK10_MAJOR   130
+#define XEN_SCSI_DISK11_MAJOR   131
+#define XEN_SCSI_DISK12_MAJOR   132
+#define XEN_SCSI_DISK13_MAJOR   133
+#define XEN_SCSI_DISK14_MAJOR   134
+#define XEN_SCSI_DISK15_MAJOR   135
+
 #endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index 518481c95f18..cb94668f6e9f 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -22,50 +22,50 @@
 
 /*
  * This is the 'wire' format for packets:
- *  Request 1: netif_tx_request -- NETTXF_* (any flags)
- * [Request 2: netif_tx_extra]  (only if request 1 has NETTXF_extra_info)
- * [Request 3: netif_tx_extra]  (only if request 2 has XEN_NETIF_EXTRA_MORE)
- *  Request 4: netif_tx_request -- NETTXF_more_data
- *  Request 5: netif_tx_request -- NETTXF_more_data
+ *  Request 1: xen_netif_tx_request  -- XEN_NETTXF_* (any flags)
+ * [Request 2: xen_netif_extra_info]    (only if request 1 has XEN_NETTXF_extra_info)
+ * [Request 3: xen_netif_extra_info]    (only if request 2 has XEN_NETIF_EXTRA_MORE)
+ *  Request 4: xen_netif_tx_request  -- XEN_NETTXF_more_data
+ *  Request 5: xen_netif_tx_request  -- XEN_NETTXF_more_data
  *  ...
- *  Request N: netif_tx_request -- 0
+ *  Request N: xen_netif_tx_request  -- 0
  */
 
 /* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _NETTXF_csum_blank     (0)
-#define  NETTXF_csum_blank     (1U<<_NETTXF_csum_blank)
+#define _XEN_NETTXF_csum_blank          (0)
+#define  XEN_NETTXF_csum_blank          (1U<<_XEN_NETTXF_csum_blank)
 
 /* Packet data has been validated against protocol checksum. */
-#define _NETTXF_data_validated (1)
-#define  NETTXF_data_validated (1U<<_NETTXF_data_validated)
+#define _XEN_NETTXF_data_validated      (1)
+#define  XEN_NETTXF_data_validated      (1U<<_XEN_NETTXF_data_validated)
 
 /* Packet continues in the next request descriptor. */
-#define _NETTXF_more_data      (2)
-#define  NETTXF_more_data      (1U<<_NETTXF_more_data)
+#define _XEN_NETTXF_more_data           (2)
+#define  XEN_NETTXF_more_data           (1U<<_XEN_NETTXF_more_data)
 
 /* Packet to be followed by extra descriptor(s). */
-#define _NETTXF_extra_info     (3)
-#define  NETTXF_extra_info     (1U<<_NETTXF_extra_info)
+#define _XEN_NETTXF_extra_info          (3)
+#define  XEN_NETTXF_extra_info          (1U<<_XEN_NETTXF_extra_info)
 
 struct xen_netif_tx_request {
     grant_ref_t gref;      /* Reference to buffer page */
     uint16_t offset;       /* Offset within buffer page */
-    uint16_t flags;        /* NETTXF_* */
+    uint16_t flags;        /* XEN_NETTXF_* */
     uint16_t id;           /* Echoed in response message. */
     uint16_t size;         /* Packet size in bytes.       */
 };
 
-/* Types of netif_extra_info descriptors. */
-#define XEN_NETIF_EXTRA_TYPE_NONE  (0)  /* Never used - invalid */
-#define XEN_NETIF_EXTRA_TYPE_GSO   (1)  /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MAX   (2)
+/* Types of xen_netif_extra_info descriptors. */
+#define XEN_NETIF_EXTRA_TYPE_NONE       (0)  /* Never used - invalid */
+#define XEN_NETIF_EXTRA_TYPE_GSO        (1)  /* u.gso */
+#define XEN_NETIF_EXTRA_TYPE_MAX        (2)
 
-/* netif_extra_info flags. */
-#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
-#define XEN_NETIF_EXTRA_FLAG_MORE  (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
+/* xen_netif_extra_info flags. */
+#define _XEN_NETIF_EXTRA_FLAG_MORE      (0)
+#define  XEN_NETIF_EXTRA_FLAG_MORE      (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
 
 /* GSO types - only TCPv4 currently supported. */
-#define XEN_NETIF_GSO_TYPE_TCPV4        (1)
+#define XEN_NETIF_GSO_TYPE_TCPV4        (1)
 
 /*
  * This structure needs to fit within both netif_tx_request and
@@ -107,7 +107,7 @@ struct xen_netif_extra_info {
 
 struct xen_netif_tx_response {
         uint16_t id;
-        int16_t  status;       /* NETIF_RSP_* */
+        int16_t  status;       /* XEN_NETIF_RSP_* */
 };
 
 struct xen_netif_rx_request {
@@ -116,25 +116,29 @@ struct xen_netif_rx_request {
 };
 
 /* Packet data has been validated against protocol checksum. */
-#define _NETRXF_data_validated (0)
-#define  NETRXF_data_validated (1U<<_NETRXF_data_validated)
+#define _XEN_NETRXF_data_validated      (0)
+#define  XEN_NETRXF_data_validated      (1U<<_XEN_NETRXF_data_validated)
 
 /* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _NETRXF_csum_blank     (1)
-#define  NETRXF_csum_blank     (1U<<_NETRXF_csum_blank)
+#define _XEN_NETRXF_csum_blank          (1)
+#define  XEN_NETRXF_csum_blank          (1U<<_XEN_NETRXF_csum_blank)
 
 /* Packet continues in the next request descriptor. */
-#define _NETRXF_more_data      (2)
-#define  NETRXF_more_data      (1U<<_NETRXF_more_data)
+#define _XEN_NETRXF_more_data           (2)
+#define  XEN_NETRXF_more_data           (1U<<_XEN_NETRXF_more_data)
 
 /* Packet to be followed by extra descriptor(s). */
-#define _NETRXF_extra_info     (3)
-#define  NETRXF_extra_info     (1U<<_NETRXF_extra_info)
+#define _XEN_NETRXF_extra_info          (3)
+#define  XEN_NETRXF_extra_info          (1U<<_XEN_NETRXF_extra_info)
+
+/* GSO Prefix descriptor. */
+#define _XEN_NETRXF_gso_prefix          (4)
+#define  XEN_NETRXF_gso_prefix          (1U<<_XEN_NETRXF_gso_prefix)
 
 struct xen_netif_rx_response {
     uint16_t id;
     uint16_t offset;       /* Offset in page of start of received packet  */
-    uint16_t flags;        /* NETRXF_* */
+    uint16_t flags;        /* XEN_NETRXF_* */
     int16_t  status;       /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
 };
 
@@ -149,10 +153,10 @@ DEFINE_RING_TYPES(xen_netif_rx,
                   struct xen_netif_rx_request,
                   struct xen_netif_rx_response);
 
-#define NETIF_RSP_DROPPED         -2
-#define NETIF_RSP_ERROR           -1
-#define NETIF_RSP_OKAY             0
-/* No response: used for auxiliary requests (e.g., netif_tx_extra). */
-#define NETIF_RSP_NULL             1
+#define XEN_NETIF_RSP_DROPPED   -2
+#define XEN_NETIF_RSP_ERROR     -1
+#define XEN_NETIF_RSP_OKAY       0
+/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
+#define XEN_NETIF_RSP_NULL       1
 
 #endif
diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h
index 5fec575a800a..dd55dac340de 100644
--- a/include/xen/interface/sched.h
+++ b/include/xen/interface/sched.h
@@ -65,6 +65,39 @@ struct sched_poll {
 DEFINE_GUEST_HANDLE_STRUCT(sched_poll);
 
 /*
+ * Declare a shutdown for another domain. The main use of this function is
+ * in interpreting shutdown requests and reasons for fully-virtualized
+ * domains.  A para-virtualized domain may use SCHEDOP_shutdown directly.
+ * @arg == pointer to sched_remote_shutdown structure.
+ */
+#define SCHEDOP_remote_shutdown        4
+struct sched_remote_shutdown {
+    domid_t domain_id;         /* Remote domain ID */
+    unsigned int reason;       /* SHUTDOWN_xxx reason */
+};
+
+/*
+ * Latch a shutdown code, so that when the domain later shuts down it
+ * reports this code to the control tools.
+ * @arg == as for SCHEDOP_shutdown.
+ */
+#define SCHEDOP_shutdown_code 5
+
+/*
+ * Setup, poke and destroy a domain watchdog timer.
+ * @arg == pointer to sched_watchdog structure.
+ * With id == 0, setup a domain watchdog timer to cause domain shutdown
+ *               after timeout, returns watchdog id.
+ * With id != 0 and timeout == 0, destroy domain watchdog timer.
+ * With id != 0 and timeout != 0, poke watchdog timer and set new timeout.
+ */
+#define SCHEDOP_watchdog    6
+struct sched_watchdog {
+    uint32_t id;                /* watchdog ID */
+    uint32_t timeout;           /* timeout */
+};
+
+/*
  * Reason codes for SCHEDOP_shutdown. These may be interpreted by control
  * software to determine the appropriate action. For the most part, Xen does
  * not care about the shutdown code.
@@ -73,5 +106,6 @@ DEFINE_GUEST_HANDLE_STRUCT(sched_poll);
 #define SHUTDOWN_reboot     1  /* Clean up, kill, and then restart.          */
 #define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
 #define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
+#define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
 
 #endif /* __XEN_PUBLIC_SCHED_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 2befa3e2f1bc..b33257bc7e83 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -30,7 +30,7 @@
 #define __HYPERVISOR_stack_switch          3
 #define __HYPERVISOR_set_callbacks         4
 #define __HYPERVISOR_fpu_taskswitch        5
-#define __HYPERVISOR_sched_op              6
+#define __HYPERVISOR_sched_op_compat       6
 #define __HYPERVISOR_dom0_op               7
 #define __HYPERVISOR_set_debugreg          8
 #define __HYPERVISOR_get_debugreg          9
@@ -52,7 +52,7 @@
 #define __HYPERVISOR_mmuext_op            26
 #define __HYPERVISOR_acm_op               27
 #define __HYPERVISOR_nmi_op               28
-#define __HYPERVISOR_sched_op_new         29
+#define __HYPERVISOR_sched_op             29
 #define __HYPERVISOR_callback_op          30
 #define __HYPERVISOR_xenoprof_op          31
 #define __HYPERVISOR_event_channel_op     32
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b92154a264..03c85d7387fb 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,9 +5,9 @@
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
-void xen_pre_suspend(void);
-void xen_post_suspend(int suspend_cancelled);
-void xen_hvm_post_suspend(int suspend_cancelled);
+void xen_arch_pre_suspend(void);
+void xen_arch_post_suspend(int suspend_cancelled);
+void xen_arch_hvm_post_suspend(int suspend_cancelled);
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);