|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [win-pv-devel] [PATCH 1/4] Update Xen headers to 4.7.0-rc2
This pulls in the recent changes to netif.h which are required by
subsequent patches.
Signed-off-by: Paul Durrant <paul.durrant@xxxxxxxxxx>
---
include/xen/public/arch-x86/xen-x86_32.h | 21 +-
include/xen/public/arch-x86/xen-x86_64.h | 8 +-
include/xen/public/arch-x86/xen.h | 37 +-
include/xen/public/errno.h | 63 ++-
include/xen/public/grant_table.h | 10 +-
include/xen/public/io/netif.h | 659 ++++++++++++++++++++++++++++---
include/xen/public/io/ring.h | 18 +-
include/xen/public/trace.h | 8 +-
include/xen/public/xen-compat.h | 2 +-
include/xen/public/xen.h | 153 +++++--
include/xen/xen/errno.h | 6 +-
11 files changed, 841 insertions(+), 144 deletions(-)
diff --git a/include/xen/public/arch-x86/xen-x86_32.h
b/include/xen/public/arch-x86/xen-x86_32.h
index 73688b8..d23340b 100644
--- a/include/xen/public/arch-x86/xen-x86_32.h
+++ b/include/xen/public/arch-x86/xen-x86_32.h
@@ -58,34 +58,31 @@
#define __HYPERVISOR_VIRT_START_PAE 0xF5800000
#define __MACH2PHYS_VIRT_START_PAE 0xF5800000
#define __MACH2PHYS_VIRT_END_PAE 0xF6800000
-#define HYPERVISOR_VIRT_START_PAE \
- mk_unsigned_long(__HYPERVISOR_VIRT_START_PAE)
-#define MACH2PHYS_VIRT_START_PAE \
- mk_unsigned_long(__MACH2PHYS_VIRT_START_PAE)
-#define MACH2PHYS_VIRT_END_PAE \
- mk_unsigned_long(__MACH2PHYS_VIRT_END_PAE)
+#define HYPERVISOR_VIRT_START_PAE
xen_mk_ulong(__HYPERVISOR_VIRT_START_PAE)
+#define MACH2PHYS_VIRT_START_PAE xen_mk_ulong(__MACH2PHYS_VIRT_START_PAE)
+#define MACH2PHYS_VIRT_END_PAE xen_mk_ulong(__MACH2PHYS_VIRT_END_PAE)
/* Non-PAE bounds are obsolete. */
#define __HYPERVISOR_VIRT_START_NONPAE 0xFC000000
#define __MACH2PHYS_VIRT_START_NONPAE 0xFC000000
#define __MACH2PHYS_VIRT_END_NONPAE 0xFC400000
#define HYPERVISOR_VIRT_START_NONPAE \
- mk_unsigned_long(__HYPERVISOR_VIRT_START_NONPAE)
+ xen_mk_ulong(__HYPERVISOR_VIRT_START_NONPAE)
#define MACH2PHYS_VIRT_START_NONPAE \
- mk_unsigned_long(__MACH2PHYS_VIRT_START_NONPAE)
+ xen_mk_ulong(__MACH2PHYS_VIRT_START_NONPAE)
#define MACH2PHYS_VIRT_END_NONPAE \
- mk_unsigned_long(__MACH2PHYS_VIRT_END_NONPAE)
+ xen_mk_ulong(__MACH2PHYS_VIRT_END_NONPAE)
#define __HYPERVISOR_VIRT_START __HYPERVISOR_VIRT_START_PAE
#define __MACH2PHYS_VIRT_START __MACH2PHYS_VIRT_START_PAE
#define __MACH2PHYS_VIRT_END __MACH2PHYS_VIRT_END_PAE
#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#define HYPERVISOR_VIRT_START xen_mk_ulong(__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_VIRT_START xen_mk_ulong(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END xen_mk_ulong(__MACH2PHYS_VIRT_END)
#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>2)
#ifndef machine_to_phys_mapping
#define machine_to_phys_mapping ((ULONG_PTR *)MACH2PHYS_VIRT_START)
diff --git a/include/xen/public/arch-x86/xen-x86_64.h
b/include/xen/public/arch-x86/xen-x86_64.h
index b99eaab..2f53f69 100644
--- a/include/xen/public/arch-x86/xen-x86_64.h
+++ b/include/xen/public/arch-x86/xen-x86_64.h
@@ -76,12 +76,12 @@
#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)
+#define HYPERVISOR_VIRT_START xen_mk_ulong(__HYPERVISOR_VIRT_START)
+#define HYPERVISOR_VIRT_END xen_mk_ulong(__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_VIRT_START xen_mk_ulong(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END xen_mk_ulong(__MACH2PHYS_VIRT_END)
#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
#ifndef machine_to_phys_mapping
#define machine_to_phys_mapping ((ULONG_PTR *)HYPERVISOR_VIRT_START)
diff --git a/include/xen/public/arch-x86/xen.h
b/include/xen/public/arch-x86/xen.h
index 58c617f..05db77f 100644
--- a/include/xen/public/arch-x86/xen.h
+++ b/include/xen/public/arch-x86/xen.h
@@ -54,9 +54,6 @@
#define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name)
#define XEN_GUEST_HANDLE_PARAM(name) XEN_GUEST_HANDLE(name)
#define set_xen_guest_handle_raw(hnd, val) do { (hnd).p = val; } while (0)
-#ifdef __XEN_TOOLS__
-#define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0)
-#endif
#define set_xen_guest_handle(hnd, val) set_xen_guest_handle_raw(hnd, val)
#if defined(__i386__)
@@ -262,6 +259,40 @@ struct arch_shared_info {
};
typedef struct arch_shared_info arch_shared_info_t;
+#if defined(__XEN__) || defined(__XEN_TOOLS__)
+/*
+ * struct xen_arch_domainconfig's ABI is covered by
+ * XEN_DOMCTL_INTERFACE_VERSION.
+ */
+struct xen_arch_domainconfig {
+#define _XEN_X86_EMU_LAPIC 0
+#define XEN_X86_EMU_LAPIC (1U<<_XEN_X86_EMU_LAPIC)
+#define _XEN_X86_EMU_HPET 1
+#define XEN_X86_EMU_HPET (1U<<_XEN_X86_EMU_HPET)
+#define _XEN_X86_EMU_PM 2
+#define XEN_X86_EMU_PM (1U<<_XEN_X86_EMU_PM)
+#define _XEN_X86_EMU_RTC 3
+#define XEN_X86_EMU_RTC (1U<<_XEN_X86_EMU_RTC)
+#define _XEN_X86_EMU_IOAPIC 4
+#define XEN_X86_EMU_IOAPIC (1U<<_XEN_X86_EMU_IOAPIC)
+#define _XEN_X86_EMU_PIC 5
+#define XEN_X86_EMU_PIC (1U<<_XEN_X86_EMU_PIC)
+#define _XEN_X86_EMU_VGA 6
+#define XEN_X86_EMU_VGA (1U<<_XEN_X86_EMU_VGA)
+#define _XEN_X86_EMU_IOMMU 7
+#define XEN_X86_EMU_IOMMU (1U<<_XEN_X86_EMU_IOMMU)
+#define _XEN_X86_EMU_PIT 8
+#define XEN_X86_EMU_PIT (1U<<_XEN_X86_EMU_PIT)
+
+#define XEN_X86_EMU_ALL (XEN_X86_EMU_LAPIC | XEN_X86_EMU_HPET | \
+ XEN_X86_EMU_PM | XEN_X86_EMU_RTC | \
+ XEN_X86_EMU_IOAPIC | XEN_X86_EMU_PIC | \
+ XEN_X86_EMU_VGA | XEN_X86_EMU_IOMMU | \
+ XEN_X86_EMU_PIT)
+ uint32_t emulation_flags;
+};
+#endif
+
#endif /* !__ASSEMBLY__ */
/*
diff --git a/include/xen/public/errno.h b/include/xen/public/errno.h
index c644633..e440237 100644
--- a/include/xen/public/errno.h
+++ b/include/xen/public/errno.h
@@ -1,26 +1,60 @@
+/*
+ * There are two expected ways of including this header.
+ *
+ * 1) The "default" case (expected from tools etc).
+ *
+ * Simply #include <public/errno.h>
+ *
+ * In this circumstance, normal header guards apply and the includer shall get
+ * an enumeration in the XEN_xxx namespace, appropriate for C or assembly.
+ *
+ * 2) The special case where the includer provides a XEN_ERRNO() in scope.
+ *
+ * In this case, no inclusion guards apply and the caller is responsible for
+ * their XEN_ERRNO() being appropriate in the included context. The header
+ * will unilaterally #undef XEN_ERRNO().
+ */
+
+#ifndef XEN_ERRNO
+
+/*
+ * Includer has not provided a custom XEN_ERRNO(). Arrange for normal header
+ * guards, an automatic enum (for C code) and constants in the XEN_xxx
+ * namespace.
+ */
#ifndef __XEN_PUBLIC_ERRNO_H__
+#define __XEN_PUBLIC_ERRNO_H__
+
+#define XEN_ERRNO_DEFAULT_INCLUDE
#ifndef __ASSEMBLY__
#define XEN_ERRNO(name, value) XEN_##name = value,
enum xen_errno {
-#else /* !__ASSEMBLY__ */
+#elif __XEN_INTERFACE_VERSION__ < 0x00040700
#define XEN_ERRNO(name, value) .equ XEN_##name, value
#endif /* __ASSEMBLY__ */
+#endif /* __XEN_PUBLIC_ERRNO_H__ */
+#endif /* !XEN_ERRNO */
+
/* ` enum neg_errnoval { [ -Efoo for each Efoo in the list below ] } */
/* ` enum errnoval { */
-#endif /* __XEN_PUBLIC_ERRNO_H__ */
-
#ifdef XEN_ERRNO
/*
* Values originating from x86 Linux. Please consider using respective
* values when adding new definitions here.
+ *
+ * The set of identifiers to be added here shouldn't extend beyond what
+ * POSIX mandates (see e.g.
+ * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html)
+ * with the exception that we support some optional (XSR) values
+ * specified there (but no new ones should be added).
*/
XEN_ERRNO(EPERM, 1) /* Operation not permitted */
@@ -36,6 +70,7 @@ XEN_ERRNO(ENOEXEC, 8) /* Exec format error */
XEN_ERRNO(EBADF, 9) /* Bad file number */
XEN_ERRNO(ECHILD, 10) /* No child processes */
XEN_ERRNO(EAGAIN, 11) /* Try again */
+XEN_ERRNO(EWOULDBLOCK, 11) /* Operation would block. Aliases EAGAIN */
XEN_ERRNO(ENOMEM, 12) /* Out of memory */
XEN_ERRNO(EACCES, 13) /* Permission denied */
XEN_ERRNO(EFAULT, 14) /* Bad address */
@@ -43,19 +78,21 @@ XEN_ERRNO(EBUSY, 16) /* Device or resource busy */
XEN_ERRNO(EEXIST, 17) /* File exists */
XEN_ERRNO(EXDEV, 18) /* Cross-device link */
XEN_ERRNO(ENODEV, 19) /* No such device */
+XEN_ERRNO(EISDIR, 21) /* Is a directory */
XEN_ERRNO(EINVAL, 22) /* Invalid argument */
XEN_ERRNO(ENFILE, 23) /* File table overflow */
XEN_ERRNO(EMFILE, 24) /* Too many open files */
XEN_ERRNO(ENOSPC, 28) /* No space left on device */
+XEN_ERRNO(EROFS, 30) /* Read-only file system */
XEN_ERRNO(EMLINK, 31) /* Too many links */
XEN_ERRNO(EDOM, 33) /* Math argument out of domain of func
*/
XEN_ERRNO(ERANGE, 34) /* Math result not representable */
XEN_ERRNO(EDEADLK, 35) /* Resource deadlock would occur */
+XEN_ERRNO(EDEADLOCK, 35) /* Resource deadlock would occur. Aliases
EDEADLK */
XEN_ERRNO(ENAMETOOLONG, 36) /* File name too LONG_PTR */
XEN_ERRNO(ENOLCK, 37) /* No record locks available */
+XEN_ERRNO(ENOTEMPTY, 39) /* Directory not empty */
XEN_ERRNO(ENOSYS, 38) /* Function not implemented */
-XEN_ERRNO(EBADRQC, 56) /* Invalid request code */
-XEN_ERRNO(EBADSLT, 57) /* Invalid slot */
XEN_ERRNO(ENODATA, 61) /* No data available */
XEN_ERRNO(ETIME, 62) /* Timer expired */
XEN_ERRNO(EBADMSG, 74) /* Not a data message */
@@ -64,30 +101,24 @@ XEN_ERRNO(EILSEQ, 84) /* Illegal byte sequence */
#ifdef __XEN__ /* Internal only, should never be exposed to the guest. */
XEN_ERRNO(ERESTART, 85) /* Interrupted system call should be restarted
*/
#endif
-XEN_ERRNO(EUSERS, 87) /* Too many users */
+XEN_ERRNO(ENOTSOCK, 88) /* Socket operation on non-socket */
XEN_ERRNO(EOPNOTSUPP, 95) /* Operation not supported on transport
endpoint */
XEN_ERRNO(EADDRINUSE, 98) /* Address already in use */
XEN_ERRNO(EADDRNOTAVAIL, 99) /* Cannot assign requested address */
XEN_ERRNO(ENOBUFS, 105) /* No buffer space available */
XEN_ERRNO(EISCONN, 106) /* Transport endpoint is already connected */
XEN_ERRNO(ENOTCONN, 107) /* Transport endpoint is not connected */
-XEN_ERRNO(ESHUTDOWN, 108) /* Cannot send after transport endpoint
shutdown */
-XEN_ERRNO(ETOOMANYREFS, 109) /* Too many references: cannot splice */
XEN_ERRNO(ETIMEDOUT, 110) /* Connection timed out */
#undef XEN_ERRNO
#endif /* XEN_ERRNO */
-
-#ifndef __XEN_PUBLIC_ERRNO_H__
-#define __XEN_PUBLIC_ERRNO_H__
-
/* ` } */
+/* Clean up from a default include. Close the enum (for C). */
+#ifdef XEN_ERRNO_DEFAULT_INCLUDE
+#undef XEN_ERRNO_DEFAULT_INCLUDE
#ifndef __ASSEMBLY__
};
#endif
-#define XEN_EWOULDBLOCK XEN_EAGAIN /* Operation would block */
-#define XEN_EDEADLOCK XEN_EDEADLK /* Resource deadlock would
occur */
-
-#endif /* __XEN_PUBLIC_ERRNO_H__ */
+#endif /* XEN_ERRNO_DEFAULT_INCLUDE */
diff --git a/include/xen/public/grant_table.h b/include/xen/public/grant_table.h
index f1b7917..b68ffdd 100644
--- a/include/xen/public/grant_table.h
+++ b/include/xen/public/grant_table.h
@@ -43,7 +43,7 @@
* table are identified by grant references. A grant reference is an
* integer, which indexes into the grant table. It acts as a
* capability which the grantee can use to perform operations on the
- * granter’s memory.
+ * granter's memory.
*
* This capability-based system allows shared-memory communications
* between unprivileged domains. A grant reference also encapsulates
@@ -134,8 +134,10 @@ struct grant_entry_v1 {
/* The domain being granted foreign privileges. [GST] */
domid_t domid;
/*
- * GTF_permit_access: Frame that @domid is allowed to map and access. [GST]
- * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN]
+ * GTF_permit_access: GFN that @domid is allowed to map and access. [GST]
+ * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST]
+ * GTF_transfer_completed: MFN whose ownership transferred by @domid
+ * (non-translated guests only). [XEN]
*/
uint32_t frame;
};
@@ -321,7 +323,7 @@ typedef uint32_t grant_handle_t;
/*
* GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access
* by devices and/or host CPUs. If successful, <handle> is a tracking number
- * that must be presented later to destroy the mapping(s). On error, <handle>
+ * that must be presented later to destroy the mapping(s). On error, <status>
* is a negative status code.
* NOTES:
* 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address
diff --git a/include/xen/public/io/netif.h b/include/xen/public/io/netif.h
index 887a8a7..e47efb8 100644
--- a/include/xen/public/io/netif.h
+++ b/include/xen/public/io/netif.h
@@ -136,20 +136,512 @@
*/
/*
- * This is the 'wire' format for packets:
- * Request 1: netif_tx_request_t -- NETTXF_* (any flags)
- * [Request 2: netif_extra_info_t] (only if request 1 has NETTXF_extra_info)
- * [Request 3: netif_extra_info_t] (only if request 2 has XEN_NETIF_EXTRA_MORE)
- * Request 4: netif_tx_request_t -- NETTXF_more_data
- * Request 5: netif_tx_request_t -- NETTXF_more_data
- * ...
- * Request N: netif_tx_request_t -- 0
+ * "feature-multicast-control" and "feature-dynamic-multicast-control"
+ * advertise the capability to filter ethernet multicast packets in the
+ * backend. If the frontend wishes to take advantage of this feature then
+ * it may set "request-multicast-control". If the backend only advertises
+ * "feature-multicast-control" then "request-multicast-control" must be set
+ * before the frontend moves into the connected state. The backend will
+ * sample the value on this state transition and any subsequent change in
+ * value will have no effect. However, if the backend also advertises
+ * "feature-dynamic-multicast-control" then "request-multicast-control"
+ * may be set by the frontend at any time. In this case, the backend will
+ * watch the value and re-sample on watch events.
+ *
+ * If the sampled value of "request-multicast-control" is set then the
+ * backend transmit side should no LONG_PTRer flood multicast packets to the
+ * frontend, it should instead drop any multicast packet that does not
+ * match in a filter list.
+ * The list is amended by the frontend by sending dummy transmit requests
+ * containing XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} extra-info fragments as
+ * specified below.
+ * Note that the filter list may be amended even if the sampled value of
+ * "request-multicast-control" is not set, however the filter should only
+ * be applied if it is set.
+ */
+
+/*
+ * Control ring
+ * ============
+ *
+ * Some features, such as hashing (detailed below), require a
+ * significant amount of out-of-band data to be passed from frontend to
+ * backend. Use of xenstore is not suitable for large quantities of data
+ * because of quota limitations and so a dedicated 'control ring' is used.
+ * The ability of the backend to use a control ring is advertised by
+ * setting:
+ *
+ * /local/domain/X/backend/<domid>/<vif>/feature-ctrl-ring = "1"
+ *
+ * The frontend provides a control ring to the backend by setting:
+ *
+ * /local/domain/<domid>/device/vif/<vif>/ctrl-ring-ref = <gref>
+ * /local/domain/<domid>/device/vif/<vif>/event-channel-ctrl = <port>
+ *
+ * where <gref> is the grant reference of the shared page used to
+ * implement the control ring and <port> is an event channel to be used
+ * as a mailbox interrupt. These keys must be set before the frontend
+ * moves into the connected state.
+ *
+ * The control ring uses a fixed request/response message size and is
+ * balanced (i.e. one request to one response), so operationally it is much
+ * the same as a transmit or receive ring.
+ * Note that there is no requirement that responses are issued in the same
+ * order as requests.
+ */
+
+/*
+ * Hash types
+ * ==========
+ *
+ * For the purposes of the definitions below, 'Packet[]' is an array of
+ * octets containing an IP packet without options, 'Array[X..Y]' means a
+ * sub-array of 'Array' containing bytes X thru Y inclusive, and '+' is
+ * used to indicate concatenation of arrays.
+ */
+
+/*
+ * A hash calculated over an IP version 4 header as follows:
+ *
+ * Buffer[0..8] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address)
+ *
+ * Result = Hash(Buffer, 8)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4 0
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4 \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4)
+
+/*
+ * A hash calculated over an IP version 4 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..12] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address) +
+ * Packet[20..21] (source port) +
+ * Packet[22..23] (destination port)
+ *
+ * Result = Hash(Buffer, 12)
*/
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP 1
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)
+
+/*
+ * A hash calculated over an IP version 6 header as follows:
+ *
+ * Buffer[0..32] = Packet[8..23] (source address ) +
+ * Packet[24..39] (destination address)
+ *
+ * Result = Hash(Buffer, 32)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6 2
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6 \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6)
+
+/*
+ * A hash calculated over an IP version 6 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..36] = Packet[8..23] (source address) +
+ * Packet[24..39] (destination address) +
+ * Packet[40..41] (source port) +
+ * Packet[42..43] (destination port)
+ *
+ * Result = Hash(Buffer, 36)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP 3
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)
+
+/*
+ * Hash algorithms
+ * ===============
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_NONE 0
+
+/*
+ * Toeplitz hash:
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ 1
+
+/*
+ * This algorithm uses a 'key' as well as the data buffer itself.
+ * (Buffer[] and Key[] are treated as shift-registers where the MSB of
+ * Buffer/Key[0] is considered 'left-most' and the LSB of Buffer/Key[N-1]
+ * is the 'right-most').
+ *
+ * Value = 0
+ * For number of bits in Buffer[]
+ * If (left-most bit of Buffer[] is 1)
+ * Value ^= left-most 32 bits of Key[]
+ * Key[] << 1
+ * Buffer[] << 1
+ *
+ * The code below is provided for convenience where an operating system
+ * does not already provide an implementation.
+ */
+#ifdef XEN_NETIF_DEFINE_TOEPLITZ
+static uint32_t xen_netif_toeplitz_hash(const uint8_t *key,
+ unsigned int keylen,
+ const uint8_t *buf,
+ unsigned int buflen)
+{
+ unsigned int keyi, bufi;
+ uint64_t prefix = 0;
+ uint64_t hash = 0;
+
+ /* Pre-load prefix with the first 8 bytes of the key */
+ for (keyi = 0; keyi < 8; keyi++) {
+ prefix <<= 8;
+ prefix |= (keyi < keylen) ? key[keyi] : 0;
+ }
+
+ for (bufi = 0; bufi < buflen; bufi++) {
+ uint8_t byte = buf[bufi];
+ unsigned int bit;
+
+ for (bit = 0; bit < 8; bit++) {
+ if (byte & 0x80)
+ hash ^= prefix;
+ prefix <<= 1;
+ byte <<=1;
+ }
+
+ /*
+ * 'prefix' has now been left-shifted by 8, so
+ * OR in the next byte.
+ */
+ prefix |= (keyi < keylen) ? key[keyi] : 0;
+ keyi++;
+ }
+
+ /* The valid part of the hash is in the upper 32 bits. */
+ return hash >> 32;
+}
+#endif /* XEN_NETIF_DEFINE_TOEPLITZ */
+
+/*
+ * Control requests (struct xen_netif_ctrl_request)
+ * ================================================
+ *
+ * All requests have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | data[0] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data[1] | data[2] |
+ * +-----+-----+-----+-----+-----------------------+
+ *
+ * id: the request identifier, echoed in response.
+ * type: the type of request (see below)
+ * data[]: any data associated with the request (determined by type)
+ */
+
+struct xen_netif_ctrl_request {
+ uint16_t id;
+ uint16_t type;
+
+#define XEN_NETIF_CTRL_TYPE_INVALID 0
+#define XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS 1
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS 2
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_KEY 3
+#define XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE 4
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE 5
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING 6
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM 7
+
+ uint32_t data[3];
+};
+
+/*
+ * Control responses (struct xen_netif_ctrl_response)
+ * ==================================================
+ *
+ * All responses have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | status |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data |
+ * +-----+-----+-----+-----+
+ *
+ * id: the corresponding request identifier
+ * type: the type of the corresponding request
+ * status: the status of request processing
+ * data: any data associated with the response (determined by type and
+ * status)
+ */
+
+struct xen_netif_ctrl_response {
+ uint16_t id;
+ uint16_t type;
+ uint32_t status;
+
+#define XEN_NETIF_CTRL_STATUS_SUCCESS 0
+#define XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED 1
+#define XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER 2
+#define XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW 3
+
+ uint32_t data;
+};
+
+/*
+ * Control messages
+ * ================
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ * --------------------------------------
+ *
+ * This is sent by the frontend to set the desired hash algorithm.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ * data[0] = a XEN_NETIF_CTRL_HASH_ALGORITHM_* value
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - The algorithm is not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ *
+ * NOTE: Setting data[0] to XEN_NETIF_CTRL_HASH_ALGORITHM_NONE disables
+ * hashing and the backend is free to choose how it steers packets
+ * to queues (which is the default behaviour).
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to query the types of hash supported by
+ * the backend.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = supported hash types (if operation was successful)
+ *
+ * NOTE: A valid hash algorithm must be selected before this operation can
+ * succeed.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to set the types of hash that the backend
+ * should calculate. (See above for hash type definitions).
+ * Note that the 'maximal' type of hash should always be chosen. For
+ * example, if the frontend sets both IPV4 and IPV4_TCP hash types then
+ * the latter hash type should be calculated for any TCP packet and the
+ * former only calculated for non-TCP packets.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS
+ * data[0] = bitwise OR of XEN_NETIF_CTRL_HASH_TYPE_* values
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - One or more flag
+ * value is invalid or
+ * unsupported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: A valid hash algorithm must be selected before this operation can
+ * succeed.
+ * Also, setting data[0] to zero disables hashing and the backend
+ * is free to choose how it steers packets to queues.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_KEY
+ * --------------------------------
+ *
+ * This is sent by the frontend to set the key of the hash if the algorithm
+ * requires it. (See hash algorithms above).
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_KEY
+ * data[0] = grant reference of page containing the key (assumed to
+ * start at beginning of grant)
+ * data[1] = size of key in octets
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Key size is invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Key size is larger
+ * than the backend
+ * supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Any key octets not specified are assumed to be zero (the key
+ * is assumed to be empty by default) and specifying a new key
+ * invalidates any previous key, hence specifying a key size of
+ * zero will clear the key (which ensures that the calculated hash
+ * will always be zero).
+ * The maximum size of key is algorithm and backend specific, but
+ * is also limited by the single grant reference.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE
+ * -----------------------------------------
+ *
+ * This is sent by the frontend to query the maximum size of mapping
+ * table supported by the backend. The size is specified in terms of
+ * table entries.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = maximum number of entries allowed in the mapping table
+ * (if operation was successful) or zero if a mapping table is
+ * not supported (i.e. hash mapping is done only by modular
+ * arithmetic).
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * -------------------------------------
+ *
+ * This is sent by the frontend to set the actual size of the mapping
+ * table to be used by the backend. The size is specified in terms of
+ * table entries.
+ * Any previous table is invalidated by this message and any new table
+ * is assumed to be zero filled.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * data[0] = number of entries in mapping table
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size is invalid
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Setting data[0] to 0 means that hash mapping should be done
+ * using modular arithmetic.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend to set the content of the table mapping
+ * hash value to queue number. The backend should calculate the hash from
+ * the packet header, use it as an index into the table (modulo the size
+ * of the table) and then steer the packet to the queue number found at
+ * that index.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING
+ * data[0] = grant reference of page containing the mapping (sub-)table
+ * (assumed to start at beginning of grant)
+ * data[1] = size of (sub-)table in entries
+ * data[2] = offset, in entries, of sub-table within overall table
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size or content
+ * is invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Table size is larger
+ * than the backend
+ * supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: The overall table has the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[0] | mapping[1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | . |
+ * | . |
+ * | . |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[N-2] | mapping[N-1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * where N is specified by a XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * message and each mapping must specifies a queue between 0 and
+ * "multi-queue-num-queues" (see above).
+ * The backend may support a mapping table larger than can be
+ * mapped by a single grant reference. Thus sub-tables within a
+ * larger table can be individually set by sending multiple messages
+ * with differing offset values. Specifying a new sub-table does not
+ * invalidate any table data outside that range.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ */
+
+DEFINE_RING_TYPES(xen_netif_ctrl,
+ struct xen_netif_ctrl_request,
+ struct xen_netif_ctrl_response);
/*
* Guest transmit
* ==============
*
+ * This is the 'wire' format for transmit (frontend -> backend) packets:
+ *
+ * Fragment 1: netif_tx_request_t - flags = NETTXF_*
+ * size = total packet size
+ * [Extra 1: netif_extra_info_t] - (only if fragment 1 flags include
+ * NETTXF_extra_info)
+ * ...
+ * [Extra N: netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
+ * ...
+ * Fragment N: netif_tx_request_t - (only if fragment N-1 flags include
+ * NETTXF_more_data - flags on preceding
+ * extras are not relevant here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for receive
+ * (backend -> frontend) packets. Specifically, in a multi-fragment
+ * packet the actual size of fragment 1 can only be determined by
+ * subtracting the sizes of fragments 2..N from the total packet size.
+ *
* Ring slot size is 12 octets, however not all request/response
* structs use the full size.
*
@@ -185,6 +677,29 @@
* Guest receive
* =============
*
+ * This is the 'wire' format for receive (backend -> frontend) packets:
+ *
+ * Fragment 1: netif_rx_request_t - flags = NETRXF_*
+ * size = fragment size
+ * [Extra 1: netif_extra_info_t] - (only if fragment 1 flags include
+ * NETRXF_extra_info)
+ * ...
+ * [Extra N: netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
+ * ...
+ * Fragment N: netif_rx_request_t - (only if fragment N-1 flags include
+ * NETRXF_more_data - flags on preceding
+ * extras are not relevant here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for transmit
+ * (frontend -> backend) packets. Specifically, in a multi-fragment
+ * packet the size of the packet can only be determined by summing the
+ * sizes of fragments 1..N.
+ *
* Ring slot size is 8 octets.
*
* rx request (netif_rx_request_t)
@@ -211,15 +726,29 @@
* flags: NETRXF_*
* status: -ve: NETIF_RSP_*; +ve: Rx'ed pkt size.
*
+ * NOTE: Historically, to support GSO on the frontend receive side, Linux
+ * netfront does not make use of the rx response id (because, as
+ * described below, extra info structures overlay the id field).
+ * Instead it assumes that responses always appear in the same ring
+ * slot as their corresponding request. Thus, to maintain
+ * compatibility, backends must make sure this is the case.
+ *
* Extra Info
* ==========
*
- * Can be present if initial request has NET{T,R}XF_extra_info, or
- * previous extra request has XEN_NETIF_EXTRA_MORE.
+ * Can be present if initial request or response has NET{T,R}XF_extra_info,
+ * or previous extra request has XEN_NETIF_EXTRA_MORE.
*
* The struct therefore needs to fit into either a tx or rx slot and
* is therefore limited to 8 octets.
*
+ * NOTE: Because extra info data overlays the usual request/response
+ * structures, there is no id information in the opposite direction.
+ * So, if an extra info overlays an rx response the frontend can
+ * assume that it is in the same ring slot as the request that was
+ * consumed to make the slot available, and the backend must ensure
+ * this assumption is true.
+ *
* extra info (netif_extra_info_t)
* -------------------------------
*
@@ -227,7 +756,7 @@
*
* 0 1 2 3 4 5 6 7 octet
* +-----+-----+-----+-----+-----+-----+-----+-----+
- * |type |flags| type specfic data |
+ * |type |flags| type specific data |
* +-----+-----+-----+-----+-----+-----+-----+-----+
* | padding for tx |
* +-----+-----+-----+-----+
@@ -235,7 +764,8 @@
* type: XEN_NETIF_EXTRA_TYPE_*
* flags: XEN_NETIF_EXTRA_FLAG_*
* padding for tx: present only in the tx case due to 8 octet limit
- * from rx case. Not shown in type specific entries below.
+ * from rx case. Not shown in type specific entries
+ * below.
*
* XEN_NETIF_EXTRA_TYPE_GSO:
*
@@ -246,9 +776,14 @@
*
* type: Must be XEN_NETIF_EXTRA_TYPE_GSO
* flags: XEN_NETIF_EXTRA_FLAG_*
- * size: Maximum payload size of each segment.
- * type: XEN_NETIF_GSO_TYPE_*
- * features: EN_NETIF_GSO_FEAT_*
+ * size: Maximum payload size of each segment. For example,
+ * for TCP this is just the path MSS.
+ * type: XEN_NETIF_GSO_TYPE_*: This determines the protocol of
+ * the packet and any extra features required to segment the
+ * packet properly.
+ * features: EN_NETIF_GSO_FEAT_*: This specifies any extra GSO
+ * features required to process this packet, such as ECN
+ * support for TCPv4.
*
* XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
*
@@ -260,6 +795,25 @@
* type: Must be XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}
* flags: XEN_NETIF_EXTRA_FLAG_*
* addr: address to add/remove
+ *
+ * XEN_NETIF_EXTRA_TYPE_HASH:
+ *
+ * A backend that supports teoplitz hashing is assumed to accept
+ * this type of extra info in transmit packets.
+ * A frontend that enables hashing is assumed to accept
+ * this type of extra info in receive packets.
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags|htype| alg |LSB ---- value ---- MSB|
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_HASH
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * htype: Hash type (one of _XEN_NETIF_CTRL_HASH_TYPE_* - see above)
+ * alg: The algorithm used to calculate the hash (one of
+ * XEN_NETIF_CTRL_HASH_TYPE_ALGORITHM_* - see above)
+ * value: Hash value
*/
/* Protocol checksum field is blank in the packet (hardware offload)? */
@@ -280,11 +834,11 @@
#define XEN_NETIF_MAX_TX_SIZE 0xFFFF
struct netif_tx_request {
- grant_ref_t gref; /* Reference to buffer page */
- uint16_t offset; /* Offset within buffer page */
- uint16_t flags; /* NETTXF_* */
- uint16_t id; /* Echoed in response message. */
- uint16_t size; /* Packet size in bytes. */
+ grant_ref_t gref;
+ uint16_t offset;
+ uint16_t flags;
+ uint16_t id;
+ uint16_t size;
};
typedef struct netif_tx_request netif_tx_request_t;
@@ -293,7 +847,8 @@ typedef struct netif_tx_request netif_tx_request_t;
#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
-#define XEN_NETIF_EXTRA_TYPE_MAX (4)
+#define XEN_NETIF_EXTRA_TYPE_HASH (4) /* u.hash */
+#define XEN_NETIF_EXTRA_TYPE_MAX (5)
/* netif_extra_info_t flags. */
#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
@@ -309,51 +864,23 @@ typedef struct netif_tx_request netif_tx_request_t;
* netif_rx_response_t for compatibility.
*/
struct netif_extra_info {
- uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */
- uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */
-
+ uint8_t type;
+ uint8_t flags;
union {
- /*
- * XEN_NETIF_EXTRA_TYPE_GSO:
- */
struct {
- /*
- * Maximum payload size of each segment. For example, for TCP this
- * is just the path MSS.
- */
uint16_t size;
-
- /*
- * GSO type. This determines the protocol of the packet and any
- * extra features required to segment the packet properly.
- */
- uint8_t type; /* XEN_NETIF_GSO_TYPE_* */
-
- /* Future expansion. */
+ uint8_t type;
uint8_t pad;
-
- /*
- * GSO features. This specifies any extra GSO features required
- * to process this packet, such as ECN support for TCPv4.
- */
- uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
+ uint16_t features;
} gso;
-
- /*
- * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
- * Backend advertises availability via 'feature-multicast-control'
- * xenbus node containing value '1'.
- * Frontend requests this feature by advertising
- * 'request-multicast-control' xenbus node containing value '1'.
- * If multicast control is requested then multicast flooding is
- * disabled and the frontend must explicitly register its interest
- * in multicast groups using dummy transmit requests containing
- * MCAST_{ADD,DEL} extra-info fragments.
- */
struct {
- uint8_t addr[6]; /* Address to add/remove. */
+ uint8_t addr[6];
} mcast;
-
+ struct {
+ uint8_t type;
+ uint8_t algorithm;
+ uint8_t value[4];
+ } hash;
uint16_t pad[3];
} u;
};
@@ -361,14 +888,14 @@ typedef struct netif_extra_info netif_extra_info_t;
struct netif_tx_response {
uint16_t id;
- int16_t status; /* NETIF_RSP_* */
+ int16_t status;
};
typedef struct netif_tx_response netif_tx_response_t;
struct netif_rx_request {
uint16_t id; /* Echoed in response message. */
uint16_t pad;
- grant_ref_t gref; /* Reference to incoming granted frame */
+ grant_ref_t gref;
};
typedef struct netif_rx_request netif_rx_request_t;
@@ -388,11 +915,15 @@ typedef struct netif_rx_request netif_rx_request_t;
#define _NETRXF_extra_info (3)
#define NETRXF_extra_info (1U<<_NETRXF_extra_info)
+/* Packet has GSO prefix. Deprecated but included for compatibility */
+#define _NETRXF_gso_prefix (4)
+#define NETRXF_gso_prefix (1U<<_NETRXF_gso_prefix)
+
struct netif_rx_response {
uint16_t id;
- uint16_t offset; /* Offset in page of start of received packet */
- uint16_t flags; /* NETRXF_* */
- int16_t status; /* -ve: NETIF_RSP_* ; +ve: Rx'ed pkt size. */
+ uint16_t offset;
+ uint16_t flags;
+ int16_t status;
};
typedef struct netif_rx_response netif_rx_response_t;
diff --git a/include/xen/public/io/ring.h b/include/xen/public/io/ring.h
index b1666d8..1d29cc0 100644
--- a/include/xen/public/io/ring.h
+++ b/include/xen/public/io/ring.h
@@ -111,7 +111,7 @@ struct __name##_sring {
\
uint8_t msg; \
} tapif_user; \
uint8_t pvt_pad[4]; \
- } private; \
+ } pvt; \
uint8_t __pad[44]; \
union __name##_sring_entry ring[1]; /* variable-length */ \
}; \
@@ -156,7 +156,7 @@ typedef struct __name##_back_ring __name##_back_ring_t
#define SHARED_RING_INIT(_s) do { \
(_s)->req_prod = (_s)->rsp_prod = 0; \
(_s)->req_event = (_s)->rsp_event = 1; \
- (void)memset((_s)->private.pvt_pad, 0, sizeof((_s)->private.pvt_pad)); \
+ (void)memset((_s)->pvt.pvt_pad, 0, sizeof((_s)->pvt.pvt_pad)); \
(void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \
} while(0)
@@ -212,6 +212,20 @@ typedef struct __name##_back_ring __name##_back_ring_t
#define RING_GET_REQUEST(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
+/*
+ * Get a local copy of a request.
+ *
+ * Use this in preference to RING_GET_REQUEST() so all processing is
+ * done on a local copy that cannot be modified by the other end.
+ *
+ * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
+ * to be ineffective where _req is a struct which consists of only bitfields.
+ */
+#define RING_COPY_REQUEST(_r, _idx, _req) do { \
+ /* Use volatile to force the copy into _req. */ \
+ *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \
+} while (0)
+
#define RING_GET_RESPONSE(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
diff --git a/include/xen/public/trace.h b/include/xen/public/trace.h
index 1a2859c..95b00e8 100644
--- a/include/xen/public/trace.h
+++ b/include/xen/public/trace.h
@@ -75,7 +75,7 @@
/* Per-scheduler IDs, to identify scheduler specific events */
#define TRC_SCHED_CSCHED 0
#define TRC_SCHED_CSCHED2 1
-#define TRC_SCHED_SEDF 2
+/* #define XEN_SCHEDULER_SEDF 2 (Removed) */
#define TRC_SCHED_ARINC653 3
#define TRC_SCHED_RTDS 4
@@ -85,6 +85,9 @@
((TRC_SCHED_##_c << TRC_SCHED_ID_SHIFT) & TRC_SCHED_ID_MASK) ) + \
(_e & TRC_SCHED_EVT_MASK) )
+/* Trace classes for DOM0 operations */
+#define TRC_DOM0_DOMOPS 0x00041000 /* Domains manipulations */
+
/* Trace classes for Hardware */
#define TRC_HW_PM 0x00801000 /* Power management traces */
#define TRC_HW_IRQ 0x00802000 /* Traces relating to the handling of
IRQs */
@@ -113,6 +116,9 @@
#define TRC_SCHED_SWITCH_INFNEXT (TRC_SCHED_VERBOSE + 15)
#define TRC_SCHED_SHUTDOWN_CODE (TRC_SCHED_VERBOSE + 16)
+#define TRC_DOM0_DOM_ADD (TRC_DOM0_DOMOPS + 1)
+#define TRC_DOM0_DOM_REM (TRC_DOM0_DOMOPS + 2)
+
#define TRC_MEM_PAGE_GRANT_MAP (TRC_MEM + 1)
#define TRC_MEM_PAGE_GRANT_UNMAP (TRC_MEM + 2)
#define TRC_MEM_PAGE_GRANT_TRANSFER (TRC_MEM + 3)
diff --git a/include/xen/public/xen-compat.h b/include/xen/public/xen-compat.h
index e23c371..2eea0e2 100644
--- a/include/xen/public/xen-compat.h
+++ b/include/xen/public/xen-compat.h
@@ -27,7 +27,7 @@
#ifndef __XEN_PUBLIC_XEN_COMPAT_H__
#define __XEN_PUBLIC_XEN_COMPAT_H__
-#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040600
+#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040700
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/* Xen is built with matching headers and implements the latest interface. */
diff --git a/include/xen/public/xen.h b/include/xen/public/xen.h
index 006631b..2057b52 100644
--- a/include/xen/public/xen.h
+++ b/include/xen/public/xen.h
@@ -52,6 +52,19 @@ DEFINE_XEN_GUEST_HANDLE(void);
DEFINE_XEN_GUEST_HANDLE(uint64_t);
DEFINE_XEN_GUEST_HANDLE(xen_pfn_t);
DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
+
+/* Turn a plain number into a C unsigned (LONG_PTR) constant. */
+#define __xen_mk_uint(x) x ## U
+#define __xen_mk_ulong(x) x ## UL
+#define xen_mk_uint(x) __xen_mk_uint(x)
+#define xen_mk_ulong(x) __xen_mk_ulong(x)
+
+#else
+
+/* In assembly code we cannot use C numeric constant suffixes. */
+#define xen_mk_uint(x) x
+#define xen_mk_ulong(x) x
+
#endif
/*
@@ -101,6 +114,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
#define __HYPERVISOR_kexec_op 37
#define __HYPERVISOR_tmem_op 38
#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */
+#define __HYPERVISOR_xenpmu_op 40
/* Architecture-specific hypercall definitions. */
#define __HYPERVISOR_arch_0 48
@@ -160,6 +174,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t);
#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */
#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */
#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */
+#define VIRQ_XENPMU 13 /* V. PMC interrupt */
/* Architecture-specific VIRQ definitions. */
#define VIRQ_ARCH_0 16
@@ -449,13 +464,13 @@ DEFINE_XEN_GUEST_HANDLE(mmuext_op_t);
/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */
/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */
/* ` enum uvm_flags { */
-#define UVMF_NONE (0UL<<0) /* No flushing at all. */
-#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */
-#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */
-#define UVMF_FLUSHTYPE_MASK (3UL<<0)
-#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */
-#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */
-#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */
+#define UVMF_NONE (xen_mk_ulong(0)<<0) /* No flushing at all. */
+#define UVMF_TLB_FLUSH (xen_mk_ulong(1)<<0) /* Flush entire TLB(s). */
+#define UVMF_INVLPG (xen_mk_ulong(2)<<0) /* Flush only one entry. */
+#define UVMF_FLUSHTYPE_MASK (xen_mk_ulong(3)<<0)
+#define UVMF_MULTI (xen_mk_ulong(0)<<2) /* Flush subset of TLBs. */
+#define UVMF_LOCAL (xen_mk_ulong(0)<<2) /* Flush local TLB. */
+#define UVMF_ALL (xen_mk_ulong(1)<<2) /* Flush all TLBs. */
/* ` } */
/*
@@ -486,17 +501,35 @@ DEFINE_XEN_GUEST_HANDLE(mmuext_op_t);
/* x86/PAE guests: support PDPTs above 4GB. */
#define VMASST_TYPE_pae_extended_cr3 3
-#define MAX_VMASST_TYPE 3
+/*
+ * x86 guests: Sane behaviour for virtual iopl
+ * - virtual iopl updated from do_iret() hypercalls.
+ * - virtual iopl reported in bounce frames.
+ * - guest kernels assumed to be level 0 for the purpose of iopl checks.
+ */
+#define VMASST_TYPE_architectural_iopl 4
-#ifndef __ASSEMBLY__
+/*
+ * x86/64 guests: strictly hide M2P from user mode.
+ * This allows the guest to control respective hypervisor behavior:
+ * - when not set, L4 tables get created with the respective slot blank,
+ * and whenever the L4 table gets used as a kernel one the missing
+ * mapping gets inserted,
+ * - when set, L4 tables get created with the respective slot initialized
+ * as before, and whenever the L4 table gets used as a user one the
+ * mapping gets zapped.
+ */
+#define VMASST_TYPE_m2p_strict 32
-typedef uint16_t domid_t;
+#if __XEN_INTERFACE_VERSION__ < 0x00040600
+#define MAX_VMASST_TYPE 3
+#endif
/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
-#define DOMID_FIRST_RESERVED (0x7FF0U)
+#define DOMID_FIRST_RESERVED xen_mk_uint(0x7FF0)
/* DOMID_SELF is used in certain contexts to refer to oneself. */
-#define DOMID_SELF (0x7FF0U)
+#define DOMID_SELF xen_mk_uint(0x7FF0)
/*
* DOMID_IO is used to restrict page-table updates to mapping I/O memory.
@@ -507,7 +540,7 @@ typedef uint16_t domid_t;
* This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
* be specified by any calling domain.
*/
-#define DOMID_IO (0x7FF1U)
+#define DOMID_IO xen_mk_uint(0x7FF1)
/*
* DOMID_XEN is used to allow privileged domains to map restricted parts of
@@ -515,17 +548,21 @@ typedef uint16_t domid_t;
* This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
* the caller is privileged.
*/
-#define DOMID_XEN (0x7FF2U)
+#define DOMID_XEN xen_mk_uint(0x7FF2)
/*
* DOMID_COW is used as the owner of sharable pages */
-#define DOMID_COW (0x7FF3U)
+#define DOMID_COW xen_mk_uint(0x7FF3)
/* DOMID_INVALID is used to identify pages with unknown owner. */
-#define DOMID_INVALID (0x7FF4U)
+#define DOMID_INVALID xen_mk_uint(0x7FF4)
/* Idle domain. */
-#define DOMID_IDLE (0x7FFFU)
+#define DOMID_IDLE xen_mk_uint(0x7FFF)
+
+#ifndef __ASSEMBLY__
+
+typedef uint16_t domid_t;
/*
* Send an array of these to HYPERVISOR_mmu_update().
@@ -585,10 +622,18 @@ struct vcpu_time_info {
*/
uint32_t tsc_to_system_mul;
int8_t tsc_shift;
+#if __XEN_INTERFACE_VERSION__ > 0x040600
+ uint8_t flags;
+ uint8_t pad1[2];
+#else
int8_t pad1[3];
+#endif
}; /* 32 bytes */
typedef struct vcpu_time_info vcpu_time_info_t;
+#define XEN_PVCLOCK_TSC_STABLE_BIT (1 << 0)
+#define XEN_PVCLOCK_GUEST_STOPPED (1 << 1)
+
struct vcpu_info {
/*
* 'evtchn_upcall_pending' is written non-zero by Xen to indicate
@@ -704,24 +749,27 @@ typedef struct shared_info shared_info_t;
* 3. This the order of bootstrap elements in the initial virtual region:
* a. relocated kernel image
* b. initial ram disk [mod_start, mod_len]
+ * (may be omitted)
* c. list of allocated page frames [mfn_list, nr_pages]
* (unless relocated due to XEN_ELFNOTE_INIT_P2M)
* d. start_info_t structure [register ESI (x86)]
- * e. bootstrap page tables [pt_base and CR3 (x86)]
- * f. bootstrap stack [register ESP (x86)]
+ * in case of dom0 this page contains the console info, too
+ * e. unless dom0: xenstore ring page
+ * f. unless dom0: console ring page
+ * g. bootstrap page tables [pt_base and CR3 (x86)]
+ * h. bootstrap stack [register ESP (x86)]
* 4. Bootstrap elements are packed together, but each is 4kB-aligned.
- * 5. The initial ram disk may be omitted.
- * 6. The list of page frames forms a contiguous 'pseudo-physical' memory
+ * 5. The list of page frames forms a contiguous 'pseudo-physical' memory
* layout for the domain. In particular, the bootstrap virtual-memory
* region is a 1:1 mapping to the first section of the pseudo-physical map.
- * 7. All bootstrap elements are mapped read-writable for the guest OS. The
+ * 6. All bootstrap elements are mapped read-writable for the guest OS. The
* only exception is the bootstrap page table, which is mapped read-only.
- * 8. There is guaranteed to be at least 512kB padding after the final
+ * 7. There is guaranteed to be at least 512kB padding after the final
* bootstrap element. If necessary, the bootstrap virtual region is
* extended by an extra 4MB to ensure this.
*
* Note: Prior to 25833:bb85bbccb1c9. ("x86/32-on-64 adjust Dom0 initial page
- * table layout") a bug caused the pt_base (3.e above) and cr3 to not point
+ * table layout") a bug caused the pt_base (3.g above) and cr3 to not point
* to the start of the guest page tables (it was offset by two pages).
* This only manifested itself on 32-on-64 dom0 kernels and not 32-on-64 domU
* or 64-bit kernels of any colour. The page tables for a 32-on-64 dom0 got
@@ -765,6 +813,52 @@ struct start_info {
};
typedef struct start_info start_info_t;
+/*
+ * Start of day structure passed to PVH guests in %ebx.
+ *
+ * NOTE: nothing will be loaded at physical address 0, so a 0 value in any
+ * of the address fields should be treated as not present.
+ *
+ * 0 +----------------+
+ * | magic | Contains the magic value XEN_HVM_START_MAGIC_VALUE
+ * | | ("xEn3" with the 0x80 bit of the "E" set).
+ * 4 +----------------+
+ * | version | Version of this structure. Current version is 0. New
+ * | | versions are guaranteed to be backwards-compatible.
+ * 8 +----------------+
+ * | flags | SIF_xxx flags.
+ * 12 +----------------+
+ * | nr_modules | Number of modules passed to the kernel.
+ * 16 +----------------+
+ * | modlist_paddr | Physical address of an array of modules
+ * | | (layout of the structure below).
+ * 24 +----------------+
+ * | cmdline_paddr | Physical address of the command line,
+ * | | a zero-terminated ASCII string.
+ * 32 +----------------+
+ * | rsdp_paddr | Physical address of the RSDP ACPI data structure.
+ * 40 +----------------+
+ *
+ * The layout of each entry in the module structure is the following:
+ *
+ * 0 +----------------+
+ * | paddr | Physical address of the module.
+ * 8 +----------------+
+ * | size | Size of the module in bytes.
+ * 16 +----------------+
+ * | cmdline_paddr | Physical address of the command line,
+ * | | a zero-terminated ASCII string.
+ * 24 +----------------+
+ * | reserved |
+ * 32 +----------------+
+ *
+ * The address and sizes are always a 64bit little endian unsigned integer.
+ *
+ * NB: Xen on x86 will always try to place all the data below the 4GiB
+ * boundary.
+ */
+#define XEN_HVM_START_MAGIC_VALUE 0x336ec578
+
/* New console union for dom0 introduced in 0x00030203. */
#if __XEN_INTERFACE_VERSION__ < 0x00030203
#define console_mfn console.domU.mfn
@@ -777,6 +871,8 @@ typedef struct start_info start_info_t;
#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */
#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */
#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */
+#define SIF_VIRT_P2M_4TOOLS (1<<4) /* Do Xen tools understand a virt. mapped */
+ /* P->M making the 3 level tree obsolete? */
#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */
/*
@@ -857,20 +953,11 @@ typedef struct dom0_vga_console_info {
typedef uint8_t xen_domain_handle_t[16];
-/* Turn a plain number into a C ULONG_PTR constant. */
-#define __mk_unsigned_long(x) x ## UL
-#define mk_unsigned_long(x) __mk_unsigned_long(x)
-
__DEFINE_XEN_GUEST_HANDLE(uint8, uint8_t);
__DEFINE_XEN_GUEST_HANDLE(uint16, uint16_t);
__DEFINE_XEN_GUEST_HANDLE(uint32, uint32_t);
__DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t);
-#else /* __ASSEMBLY__ */
-
-/* In assembly code we cannot use C numeric constant suffixes. */
-#define mk_unsigned_long(x) x
-
#endif /* !__ASSEMBLY__ */
/* Default definitions for macros used by domctl/sysctl. */
diff --git a/include/xen/xen/errno.h b/include/xen/xen/errno.h
index 3178466..69b28dd 100644
--- a/include/xen/xen/errno.h
+++ b/include/xen/xen/errno.h
@@ -1,18 +1,16 @@
#ifndef __XEN_ERRNO_H__
#define __XEN_ERRNO_H__
-#include <public/errno.h>
-
#ifndef __ASSEMBLY__
-#define XEN_ERRNO(name, value) name = XEN_##name,
+#define XEN_ERRNO(name, value) name = value,
enum {
#include <public/errno.h>
};
#else /* !__ASSEMBLY__ */
-#define XEN_ERRNO(name, value) .equ name, XEN_##name
+#define XEN_ERRNO(name, value) .equ name, value
#include <public/errno.h>
#endif /* __ASSEMBLY__ */
--
2.1.1
_______________________________________________
win-pv-devel mailing list
win-pv-devel@xxxxxxxxxxxxxxxxxxxx
http://lists.xenproject.org/cgi-bin/mailman/listinfo/win-pv-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |