Merge tag 'for-linus-4.11-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "Xen features and fixes:

   - a series from Boris Ostrovsky adding support for booting Linux as
     Xen PVH guest

   - a series from Juergen Gross streamlining the xenbus driver

   - a series from Paul Durrant adding support for the new device model
     hypercall

   - several small corrections"

* tag 'for-linus-4.11-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/privcmd: add IOCTL_PRIVCMD_RESTRICT
  xen/privcmd: Add IOCTL_PRIVCMD_DM_OP
  xen/privcmd: return -ENOTTY for unimplemented IOCTLs
  xen: optimize xenbus driver for multiple concurrent xenstore accesses
  xen: modify xenstore watch event interface
  xen: clean up xenbus internal headers
  xenbus: Neaten xenbus_va_dev_error
  xen/pvh: Use Xen's emergency_restart op for PVH guests
  xen/pvh: Enable CPU hotplug
  xen/pvh: PVH guests always have PV devices
  xen/pvh: Initialize grant table for PVH guests
  xen/pvh: Make sure we don't use ACPI_IRQ_MODEL_PIC for SCI
  xen/pvh: Bootstrap PVH guest
  xen/pvh: Import PVH-related Xen public interfaces
  xen/x86: Remove PVH support
  x86/boot/32: Convert the 32-bit pgtable setup code from assembly to C
  xen/manage: correct return value check on xenbus_scanf()
  x86/xen: Fix APIC id mismatch warning on Intel
  xen/netback: set default upper limit of tx/rx queues to 8
  xen/netfront: set default upper limit of tx/rx queues to 8

9 files changed, 312 insertions, 20 deletions

diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h
index 7ddeeda93809..63ee95c9dabb 100644
--- a/include/uapi/xen/privcmd.h
+++ b/include/uapi/xen/privcmd.h
@@ -77,6 +77,17 @@ struct privcmd_mmapbatch_v2 {
 	int __user *err;  /* array of error codes */
 };
 
+struct privcmd_dm_op_buf {
+	void __user *uptr;
+	size_t size;
+};
+
+struct privcmd_dm_op {
+	domid_t dom;
+	__u16 num;
+	const struct privcmd_dm_op_buf __user *ubufs;
+};
+
 /*
  * @cmd: IOCTL_PRIVCMD_HYPERCALL
  * @arg: &privcmd_hypercall_t
@@ -98,5 +109,9 @@ struct privcmd_mmapbatch_v2 {
 	_IOC(_IOC_NONE, 'P', 3, sizeof(struct privcmd_mmapbatch))
 #define IOCTL_PRIVCMD_MMAPBATCH_V2				\
 	_IOC(_IOC_NONE, 'P', 4, sizeof(struct privcmd_mmapbatch_v2))
+#define IOCTL_PRIVCMD_DM_OP					\
+	_IOC(_IOC_NONE, 'P', 5, sizeof(struct privcmd_dm_op))
+#define IOCTL_PRIVCMD_RESTRICT					\
+	_IOC(_IOC_NONE, 'P', 6, sizeof(domid_t))
 
 #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */
diff --git a/include/xen/arm/hypercall.h b/include/xen/arm/hypercall.h
index 9d874db13c0e..73db4b2eeb89 100644
--- a/include/xen/arm/hypercall.h
+++ b/include/xen/arm/hypercall.h
@@ -53,6 +53,7 @@ int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
 int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
+int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs, void *bufs);
 int HYPERVISOR_platform_op_raw(void *arg);
 static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
 {
diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h
index f90b03454659..9e9f9bf7c66d 100644
--- a/include/xen/interface/elfnote.h
+++ b/include/xen/interface/elfnote.h
@@ -193,9 +193,19 @@
 #define XEN_ELFNOTE_SUPPORTED_FEATURES 17
 
 /*
+ * Physical entry point into the kernel.
+ *
+ * 32bit entry point into the kernel. When requested to launch the
+ * guest kernel in a HVM container, Xen will use this entry point to
+ * launch the guest in 32bit protected mode with paging disabled.
+ * Ignored otherwise.
+ */
+#define XEN_ELFNOTE_PHYS32_ENTRY 18
+
+/*
  * The number of the highest elfnote defined.
  */
-#define XEN_ELFNOTE_MAX XEN_ELFNOTE_SUPPORTED_FEATURES
+#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_ENTRY
 
 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */
 
diff --git a/include/xen/interface/hvm/dm_op.h b/include/xen/interface/hvm/dm_op.h
new file mode 100644
index 000000000000..ee9e480bc559
--- /dev/null
+++ b/include/xen/interface/hvm/dm_op.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (c) 2016, Citrix Systems Inc
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_PUBLIC_HVM_DM_OP_H__
+#define __XEN_PUBLIC_HVM_DM_OP_H__
+
+struct xen_dm_op_buf {
+	GUEST_HANDLE(void) h;
+	xen_ulong_t size;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_dm_op_buf);
+
+#endif /* __XEN_PUBLIC_HVM_DM_OP_H__ */
diff --git a/include/xen/interface/hvm/hvm_vcpu.h b/include/xen/interface/hvm/hvm_vcpu.h
new file mode 100644
index 000000000000..32ca83edd44d
--- /dev/null
+++ b/include/xen/interface/hvm/hvm_vcpu.h
@@ -0,0 +1,143 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2015, Roger Pau Monne <roger.pau@citrix.com>
+ */
+
+#ifndef __XEN_PUBLIC_HVM_HVM_VCPU_H__
+#define __XEN_PUBLIC_HVM_HVM_VCPU_H__
+
+#include "../xen.h"
+
+struct vcpu_hvm_x86_32 {
+    uint32_t eax;
+    uint32_t ecx;
+    uint32_t edx;
+    uint32_t ebx;
+    uint32_t esp;
+    uint32_t ebp;
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t eip;
+    uint32_t eflags;
+
+    uint32_t cr0;
+    uint32_t cr3;
+    uint32_t cr4;
+
+    uint32_t pad1;
+
+    /*
+     * EFER should only be used to set the NXE bit (if required)
+     * when starting a vCPU in 32bit mode with paging enabled or
+     * to set the LME/LMA bits in order to start the vCPU in
+     * compatibility mode.
+     */
+    uint64_t efer;
+
+    uint32_t cs_base;
+    uint32_t ds_base;
+    uint32_t ss_base;
+    uint32_t es_base;
+    uint32_t tr_base;
+    uint32_t cs_limit;
+    uint32_t ds_limit;
+    uint32_t ss_limit;
+    uint32_t es_limit;
+    uint32_t tr_limit;
+    uint16_t cs_ar;
+    uint16_t ds_ar;
+    uint16_t ss_ar;
+    uint16_t es_ar;
+    uint16_t tr_ar;
+
+    uint16_t pad2[3];
+};
+
+/*
+ * The layout of the _ar fields of the segment registers is the
+ * following:
+ *
+ * Bits   [0,3]: type (bits 40-43).
+ * Bit        4: s    (descriptor type, bit 44).
+ * Bit    [5,6]: dpl  (descriptor privilege level, bits 45-46).
+ * Bit        7: p    (segment-present, bit 47).
+ * Bit        8: avl  (available for system software, bit 52).
+ * Bit        9: l    (64-bit code segment, bit 53).
+ * Bit       10: db   (meaning depends on the segment, bit 54).
+ * Bit       11: g    (granularity, bit 55)
+ * Bits [12,15]: unused, must be blank.
+ *
+ * A more complete description of the meaning of this fields can be
+ * obtained from the Intel SDM, Volume 3, section 3.4.5.
+ */
+
+struct vcpu_hvm_x86_64 {
+    uint64_t rax;
+    uint64_t rcx;
+    uint64_t rdx;
+    uint64_t rbx;
+    uint64_t rsp;
+    uint64_t rbp;
+    uint64_t rsi;
+    uint64_t rdi;
+    uint64_t rip;
+    uint64_t rflags;
+
+    uint64_t cr0;
+    uint64_t cr3;
+    uint64_t cr4;
+    uint64_t efer;
+
+    /*
+     * Using VCPU_HVM_MODE_64B implies that the vCPU is launched
+     * directly in long mode, so the cached parts of the segment
+     * registers get set to match that environment.
+     *
+     * If the user wants to launch the vCPU in compatibility mode
+     * the 32-bit structure should be used instead.
+     */
+};
+
+struct vcpu_hvm_context {
+#define VCPU_HVM_MODE_32B 0  /* 32bit fields of the structure will be used. */
+#define VCPU_HVM_MODE_64B 1  /* 64bit fields of the structure will be used. */
+    uint32_t mode;
+
+    uint32_t pad;
+
+    /* CPU registers. */
+    union {
+        struct vcpu_hvm_x86_32 x86_32;
+        struct vcpu_hvm_x86_64 x86_64;
+    } cpu_regs;
+};
+typedef struct vcpu_hvm_context vcpu_hvm_context_t;
+
+#endif /* __XEN_PUBLIC_HVM_HVM_VCPU_H__ */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/include/xen/interface/hvm/start_info.h b/include/xen/interface/hvm/start_info.h
new file mode 100644
index 000000000000..648415976ead
--- /dev/null
+++ b/include/xen/interface/hvm/start_info.h
@@ -0,0 +1,98 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2016, Citrix Systems, Inc.
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__
+#define __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__
+
+/*
+ * Start of day structure passed to PVH guests and to HVM 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
+
+/*
+ * C representation of the x86/HVM start info layout.
+ *
+ * The canonical definition of this layout is above, this is just a way to
+ * represent the layout described there using C types.
+ */
+struct hvm_start_info {
+    uint32_t magic;             /* Contains the magic value 0x336ec578       */
+                                /* ("xEn3" with the 0x80 bit of the "E" set).*/
+    uint32_t version;           /* Version of this structure.                */
+    uint32_t flags;             /* SIF_xxx flags.                            */
+    uint32_t nr_modules;        /* Number of modules passed to the kernel.   */
+    uint64_t modlist_paddr;     /* Physical address of an array of           */
+                                /* hvm_modlist_entry.                        */
+    uint64_t cmdline_paddr;     /* Physical address of the command line.     */
+    uint64_t rsdp_paddr;        /* Physical address of the RSDP ACPI data    */
+                                /* structure.                                */
+};
+
+struct hvm_modlist_entry {
+    uint64_t paddr;             /* Physical address of the module.           */
+    uint64_t size;              /* Size of the module in bytes.              */
+    uint64_t cmdline_paddr;     /* Physical address of the command line.     */
+    uint64_t reserved;
+};
+
+#endif /* __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 1b0d189cd3d3..4f4830ef8f93 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -81,6 +81,7 @@
 #define __HYPERVISOR_tmem_op              38
 #define __HYPERVISOR_xc_reserved_op       39 /* reserved for XenClient */
 #define __HYPERVISOR_xenpmu_op            40
+#define __HYPERVISOR_dm_op                41
 
 /* Architecture-specific hypercall definitions. */
 #define __HYPERVISOR_arch_0               48
diff --git a/include/xen/xen.h b/include/xen/xen.h
index f0f0252cff9a..6e8b7fc79801 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -30,16 +30,10 @@ extern enum xen_domain_type xen_domain_type;
 #endif	/* CONFIG_XEN_DOM0 */
 
 #ifdef CONFIG_XEN_PVH
-/* This functionality exists only for x86. The XEN_PVHVM support exists
- * only in x86 world - hence on ARM it will be always disabled.
- * N.B. ARM guests are neither PV nor HVM nor PVHVM.
- * It's a bit like PVH but is different also (it's further towards the H
- * end of the spectrum than even PVH).
- */
-#include <xen/features.h>
-#define xen_pvh_domain() (xen_pv_domain() && \
-			  xen_feature(XENFEAT_auto_translated_physmap))
+extern bool xen_pvh;
+#define xen_pvh_domain()	(xen_hvm_domain() && xen_pvh)
 #else
 #define xen_pvh_domain()	(0)
 #endif
+
 #endif	/* _XEN_XEN_H */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 271ba62503c7..869c816d5f8c 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -38,6 +38,7 @@
 #include <linux/notifier.h>
 #include <linux/mutex.h>
 #include <linux/export.h>
+#include <linux/fs.h>
 #include <linux/completion.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -60,7 +61,7 @@ struct xenbus_watch
 
 	/* Callback (executed in a process context with no locks held). */
 	void (*callback)(struct xenbus_watch *,
-			 const char **vec, unsigned int len);
+			 const char *path, const char *token);
 };
 
 
@@ -175,16 +176,9 @@ void xs_suspend(void);
 void xs_resume(void);
 void xs_suspend_cancel(void);
 
-/* Used by xenbus_dev to borrow kernel's store connection. */
-void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg);
-
 struct work_struct;
 
-/* Prepare for domain suspend: then resume or cancel the suspend. */
-void xenbus_suspend(void);
-void xenbus_resume(void);
 void xenbus_probe(struct work_struct *);
-void xenbus_suspend_cancel(void);
 
 #define XENBUS_IS_ERR_READ(str) ({			\
 	if (!IS_ERR(str) && strlen(str) == 0) {		\
@@ -199,11 +193,11 @@ void xenbus_suspend_cancel(void);
 int xenbus_watch_path(struct xenbus_device *dev, const char *path,
 		      struct xenbus_watch *watch,
 		      void (*callback)(struct xenbus_watch *,
-				       const char **, unsigned int));
+				       const char *, const char *));
 __printf(4, 5)
 int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch,
 			 void (*callback)(struct xenbus_watch *,
-					  const char **, unsigned int),
+					  const char *, const char *),
 			 const char *pathfmt, ...);
 
 int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state);
@@ -235,4 +229,8 @@ const char *xenbus_strstate(enum xenbus_state state);
 int xenbus_dev_is_online(struct xenbus_device *dev);
 int xenbus_frontend_closed(struct xenbus_device *dev);
 
+extern const struct file_operations xen_xenbus_fops;
+extern struct xenstore_domain_interface *xen_store_interface;
+extern int xen_store_evtchn;
+
 #endif /* _XEN_XENBUS_H */