Merge remote-tracking branch 'linus/master' into x86/urgent

4 files changed, 200 insertions, 12 deletions

diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h
index 39e571796e3..a17d84433e6 100644
--- a/include/xen/interface/grant_table.h
+++ b/include/xen/interface/grant_table.h
@@ -85,12 +85,22 @@
  */
 
 /*
+ * Reference to a grant entry in a specified domain's grant table.
+ */
+typedef uint32_t grant_ref_t;
+
+/*
  * A grant table comprises a packed array of grant entries in one or more
  * page frames shared between Xen and a guest.
  * [XEN]: This field is written by Xen and read by the sharing guest.
  * [GST]: This field is written by the guest and read by Xen.
  */
-struct grant_entry {
+
+/*
+ * Version 1 of the grant table entry structure is maintained purely
+ * for backwards compatibility.  New guests should use version 2.
+ */
+struct grant_entry_v1 {
     /* GTF_xxx: various type and flag information.  [XEN,GST] */
     uint16_t flags;
     /* The domain being granted foreign privileges. [GST] */
@@ -108,10 +118,13 @@ struct grant_entry {
  *  GTF_permit_access: Allow @domid to map/access @frame.
  *  GTF_accept_transfer: Allow @domid to transfer ownership of one page frame
  *                       to this guest. Xen writes the page number to @frame.
+ *  GTF_transitive: Allow @domid to transitively access a subrange of
+ *                  @trans_grant in @trans_domid.  No mappings are allowed.
  */
 #define GTF_invalid         (0U<<0)
 #define GTF_permit_access   (1U<<0)
 #define GTF_accept_transfer (2U<<0)
+#define GTF_transitive      (3U<<0)
 #define GTF_type_mask       (3U<<0)
 
 /*
@@ -119,6 +132,9 @@ struct grant_entry {
  *  GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST]
  *  GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN]
  *  GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN]
+ *  GTF_sub_page: Grant access to only a subrange of the page.  @domid
+ *                will only be allowed to copy from the grant, and not
+ *                map it. [GST]
  */
 #define _GTF_readonly       (2)
 #define GTF_readonly        (1U<<_GTF_readonly)
@@ -126,6 +142,8 @@ struct grant_entry {
 #define GTF_reading         (1U<<_GTF_reading)
 #define _GTF_writing        (4)
 #define GTF_writing         (1U<<_GTF_writing)
+#define _GTF_sub_page       (8)
+#define GTF_sub_page        (1U<<_GTF_sub_page)
 
 /*
  * Subflags for GTF_accept_transfer:
@@ -142,15 +160,81 @@ struct grant_entry {
 #define _GTF_transfer_completed (3)
 #define GTF_transfer_completed  (1U<<_GTF_transfer_completed)
 
+/*
+ * Version 2 grant table entries.  These fulfil the same role as
+ * version 1 entries, but can represent more complicated operations.
+ * Any given domain will have either a version 1 or a version 2 table,
+ * and every entry in the table will be the same version.
+ *
+ * The interface by which domains use grant references does not depend
+ * on the grant table version in use by the other domain.
+ */
 
-/***********************************
- * GRANT TABLE QUERIES AND USES
+/*
+ * Version 1 and version 2 grant entries share a common prefix.  The
+ * fields of the prefix are documented as part of struct
+ * grant_entry_v1.
  */
+struct grant_entry_header {
+    uint16_t flags;
+    domid_t  domid;
+};
 
 /*
- * Reference to a grant entry in a specified domain's grant table.
+ * Version 2 of the grant entry structure, here is an union because three
+ * different types are suppotted: full_page, sub_page and transitive.
+ */
+union grant_entry_v2 {
+    struct grant_entry_header hdr;
+
+    /*
+     * This member is used for V1-style full page grants, where either:
+     *
+     * -- hdr.type is GTF_accept_transfer, or
+     * -- hdr.type is GTF_permit_access and GTF_sub_page is not set.
+     *
+     * In that case, the frame field has the same semantics as the
+     * field of the same name in the V1 entry structure.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	uint32_t pad0;
+	uint64_t frame;
+    } full_page;
+
+    /*
+     * If the grant type is GTF_grant_access and GTF_sub_page is set,
+     * @domid is allowed to access bytes [@page_off,@page_off+@length)
+     * in frame @frame.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	uint16_t page_off;
+	uint16_t length;
+	uint64_t frame;
+    } sub_page;
+
+    /*
+     * If the grant is GTF_transitive, @domid is allowed to use the
+     * grant @gref in domain @trans_domid, as if it was the local
+     * domain.  Obviously, the transitive access must be compatible
+     * with the original grant.
+     */
+    struct {
+	struct grant_entry_header hdr;
+	domid_t trans_domid;
+	uint16_t pad0;
+	grant_ref_t gref;
+    } transitive;
+
+    uint32_t __spacer[4]; /* Pad to a power of two */
+};
+
+typedef uint16_t grant_status_t;
+
+/***********************************
+ * GRANT TABLE QUERIES AND USES
  */
-typedef uint32_t grant_ref_t;
 
 /*
  * Handle to track a mapping created via a grant reference.
@@ -322,6 +406,79 @@ struct gnttab_query_size {
 DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size);
 
 /*
+ * GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings
+ * tracked by <handle> but atomically replace the page table entry with one
+ * pointing to the machine address under <new_addr>.  <new_addr> will be
+ * redirected to the null entry.
+ * NOTES:
+ *  1. The call may fail in an undefined manner if either mapping is not
+ *     tracked by <handle>.
+ *  2. After executing a batch of unmaps, it is guaranteed that no stale
+ *     mappings will remain in the device or host TLBs.
+ */
+#define GNTTABOP_unmap_and_replace    7
+struct gnttab_unmap_and_replace {
+    /* IN parameters. */
+    uint64_t host_addr;
+    uint64_t new_addr;
+    grant_handle_t handle;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace);
+
+/*
+ * GNTTABOP_set_version: Request a particular version of the grant
+ * table shared table structure.  This operation can only be performed
+ * once in any given domain.  It must be performed before any grants
+ * are activated; otherwise, the domain will be stuck with version 1.
+ * The only defined versions are 1 and 2.
+ */
+#define GNTTABOP_set_version          8
+struct gnttab_set_version {
+    /* IN parameters */
+    uint32_t version;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version);
+
+/*
+ * GNTTABOP_get_status_frames: Get the list of frames used to store grant
+ * status for <dom>. In grant format version 2, the status is separated
+ * from the other shared grant fields to allow more efficient synchronization
+ * using barriers instead of atomic cmpexch operations.
+ * <nr_frames> specify the size of vector <frame_list>.
+ * The frame addresses are returned in the <frame_list>.
+ * Only <nr_frames> addresses are returned, even if the table is larger.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
+ */
+#define GNTTABOP_get_status_frames     9
+struct gnttab_get_status_frames {
+    /* IN parameters. */
+    uint32_t nr_frames;
+    domid_t  dom;
+    /* OUT parameters. */
+    int16_t  status;              /* GNTST_* */
+    GUEST_HANDLE(uint64_t) frame_list;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames);
+
+/*
+ * GNTTABOP_get_version: Get the grant table version which is in
+ * effect for domain <dom>.
+ */
+#define GNTTABOP_get_version          10
+struct gnttab_get_version {
+    /* IN parameters */
+    domid_t dom;
+    uint16_t pad;
+    /* OUT parameters */
+    uint32_t version;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version);
+
+/*
  * Bitfield values for update_pin_status.flags.
  */
  /* Map the grant entry for access by I/O devices. */
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index 9324488f23f..ee338bfde18 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -84,6 +84,21 @@ typedef uint64_t blkif_sector_t;
  *     e07154r6-Data_Set_Management_Proposal_for_ATA-ACS2.doc
  * http://www.seagate.com/staticfiles/support/disc/manuals/
  *     Interface%20manuals/100293068c.pdf
+ * The backend can optionally provide three extra XenBus attributes to
+ * further optimize the discard functionality:
+ * 'discard-aligment' - Devices that support discard functionality may
+ * internally allocate space in units that are bigger than the exported
+ * logical block size. The discard-alignment parameter indicates how many bytes
+ * the beginning of the partition is offset from the internal allocation unit's
+ * natural alignment.
+ * 'discard-granularity'  - Devices that support discard functionality may
+ * internally allocate space using units that are bigger than the logical block
+ * size. The discard-granularity parameter indicates the size of the internal
+ * allocation unit in bytes if reported by the device. Otherwise the
+ * discard-granularity will be set to match the device's physical block size.
+ * 'discard-secure' - All copies of the discarded sectors (potentially created
+ * by garbage collection) must also be erased.  To use this feature, the flag
+ * BLKIF_DISCARD_SECURE must be set in the blkif_request_trim.
  */
 #define BLKIF_OP_DISCARD           5
 
@@ -95,6 +110,12 @@ typedef uint64_t blkif_sector_t;
 #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
 
 struct blkif_request_rw {
+	uint8_t        nr_segments;  /* number of segments                   */
+	blkif_vdev_t   handle;       /* only for read/write requests         */
+#ifdef CONFIG_X86_64
+	uint32_t       _pad1;	     /* offsetof(blkif_request,u.rw.id) == 8 */
+#endif
+	uint64_t       id;           /* private guest value, echoed in resp  */
 	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        */
@@ -102,23 +123,28 @@ struct blkif_request_rw {
 		/* @last_sect: last sector in frame to transfer (inclusive).     */
 		uint8_t     first_sect, last_sect;
 	} seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
-};
+} __attribute__((__packed__));
 
 struct blkif_request_discard {
+	uint8_t        flag;         /* BLKIF_DISCARD_SECURE or zero.        */
+#define BLKIF_DISCARD_SECURE (1<<0)  /* ignored if discard-secure=0          */
+	blkif_vdev_t   _pad1;        /* only for read/write requests         */
+#ifdef CONFIG_X86_64
+	uint32_t       _pad2;        /* offsetof(blkif_req..,u.discard.id)==8*/
+#endif
+	uint64_t       id;           /* private guest value, echoed in resp  */
 	blkif_sector_t sector_number;
-	uint64_t nr_sectors;
-};
+	uint64_t       nr_sectors;
+	uint8_t        _pad3;
+} __attribute__((__packed__));
 
 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;
 		struct blkif_request_discard discard;
 	} u;
-};
+} __attribute__((__packed__));
 
 struct blkif_response {
 	uint64_t        id;              /* copied from request */
diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h
index f6f07aa35af..7cdfca24eaf 100644
--- a/include/xen/interface/io/xs_wire.h
+++ b/include/xen/interface/io/xs_wire.h
@@ -87,4 +87,7 @@ struct xenstore_domain_interface {
     XENSTORE_RING_IDX rsp_cons, rsp_prod;
 };
 
+/* Violating this is very bad.  See docs/misc/xenstore.txt. */
+#define XENSTORE_PAYLOAD_MAX 4096
+
 #endif /* _XS_WIRE_H */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 6a6e9144934..a890804945e 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -523,6 +523,8 @@ struct tmem_op {
 	} u;
 };
 
+DEFINE_GUEST_HANDLE(u64);
+
 #else /* __ASSEMBLY__ */
 
 /* In assembly code we cannot use C numeric constant suffixes. */