--- /dev/null
+* Xen hypervisor device tree bindings
+
+Xen ARM virtual platforms shall have a top-level "hypervisor" node with
+the following properties:
+
+- compatible:
+ compatible = "xen,xen-<version>", "xen,xen";
+ where <version> is the version of the Xen ABI of the platform.
+
+- reg: specifies the base physical address and size of a region in
+ memory where the grant table should be mapped to, using an
+ HYPERVISOR_memory_op hypercall. The memory region is large enough to map
+ the whole grant table (it is larger or equal to gnttab_max_grant_frames()).
+
+- interrupts: the interrupt used by Xen to inject event notifications.
+ A GIC node is also required.
+
+
+Example (assuming #address-cells = <2> and #size-cells = <2>):
+
+hypervisor {
+ compatible = "xen,xen-4.3", "xen,xen";
+ reg = <0 0xb0000000 0 0x20000>;
+ interrupts = <1 15 0xf08>;
+};
F: arch/x86/include/asm/xen/
F: include/xen/
+XEN HYPERVISOR ARM
+M: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+L: xen-devel@lists.xensource.com (moderated for non-subscribers)
+S: Supported
+F: arch/arm/xen/
+F: arch/arm/include/asm/xen/
+
XEN NETWORK BACKEND DRIVER
M: Ian Campbell <ian.campbell@citrix.com>
L: xen-devel@lists.xensource.com (moderated for non-subscribers)
neutralized via a kernel panic.
This feature requires gcc version 4.2 or above.
+config XEN_DOM0
+ def_bool y
+ depends on XEN
+
+config XEN
+ bool "Xen guest support on ARM (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && ARM && OF
+ help
+ Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
+
endmenu
menu "Boot options"
core-$(CONFIG_FPE_NWFPE) += arch/arm/nwfpe/
core-$(CONFIG_FPE_FASTFPE) += $(FASTFPE_OBJ)
core-$(CONFIG_VFP) += arch/arm/vfp/
+core-$(CONFIG_XEN) += arch/arm/xen/
# If we have a machine-specific directory, then include it in the build.
core-y += arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
vexpress-v2p-ca9.dtb \
vexpress-v2p-ca15-tc1.dtb \
- vexpress-v2p-ca15_a7.dtb
+ vexpress-v2p-ca15_a7.dtb \
+ xenvm-4.2.dtb
endif
--- /dev/null
+/*
+ * Xen Virtual Machine for unprivileged guests
+ *
+ * Based on ARM Ltd. Versatile Express CoreTile Express (single CPU)
+ * Cortex-A15 MPCore (V2P-CA15)
+ *
+ */
+
+/dts-v1/;
+
+/ {
+ model = "XENVM-4.2";
+ compatible = "xen,xenvm-4.2", "xen,xenvm";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen {
+ /* this field is going to be adjusted by the hypervisor */
+ bootargs = "console=hvc0 root=/dev/xvda";
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ /* this field is going to be adjusted by the hypervisor */
+ reg = <0 0x80000000 0 0x08000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x100>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ hypervisor {
+ compatible = "xen,xen-4.2", "xen,xen";
+ /* this field is going to be adjusted by the hypervisor */
+ reg = <0 0xb0000000 0 0x20000>;
+ /* this field is going to be adjusted by the hypervisor */
+ interrupts = <1 15 0xf08>;
+ };
+
+ motherboard {
+ arm,v2m-memory-map = "rs1";
+ };
+};
--- /dev/null
+#ifndef _ASM_ARM_HYPERVISOR_H
+#define _ASM_ARM_HYPERVISOR_H
+
+#include <asm/xen/hypervisor.h>
+
+#endif
--- /dev/null
+#ifndef __ASM_SYNC_BITOPS_H__
+#define __ASM_SYNC_BITOPS_H__
+
+#include <asm/bitops.h>
+#include <asm/system.h>
+
+/* sync_bitops functions are equivalent to the SMP implementation of the
+ * original functions, independently from CONFIG_SMP being defined.
+ *
+ * We need them because _set_bit etc are not SMP safe if !CONFIG_SMP. But
+ * under Xen you might be communicating with a completely external entity
+ * who might be on another CPU (e.g. two uniprocessor guests communicating
+ * via event channels and grant tables). So we need a variant of the bit
+ * ops which are SMP safe even on a UP kernel.
+ */
+
+#define sync_set_bit(nr, p) _set_bit(nr, p)
+#define sync_clear_bit(nr, p) _clear_bit(nr, p)
+#define sync_change_bit(nr, p) _change_bit(nr, p)
+#define sync_test_and_set_bit(nr, p) _test_and_set_bit(nr, p)
+#define sync_test_and_clear_bit(nr, p) _test_and_clear_bit(nr, p)
+#define sync_test_and_change_bit(nr, p) _test_and_change_bit(nr, p)
+#define sync_test_bit(nr, addr) test_bit(nr, addr)
+#define sync_cmpxchg cmpxchg
+
+
+#endif
--- /dev/null
+#ifndef _ASM_ARM_XEN_EVENTS_H
+#define _ASM_ARM_XEN_EVENTS_H
+
+#include <asm/ptrace.h>
+
+enum ipi_vector {
+ XEN_PLACEHOLDER_VECTOR,
+
+ /* Xen IPIs go here */
+ XEN_NR_IPIS,
+};
+
+static inline int xen_irqs_disabled(struct pt_regs *regs)
+{
+ return raw_irqs_disabled_flags(regs->ARM_cpsr);
+}
+
+#endif /* _ASM_ARM_XEN_EVENTS_H */
--- /dev/null
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (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 _ASM_ARM_XEN_HYPERCALL_H
+#define _ASM_ARM_XEN_HYPERCALL_H
+
+#include <xen/interface/xen.h>
+
+long privcmd_call(unsigned call, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ unsigned long a4, unsigned long a5);
+int HYPERVISOR_xen_version(int cmd, void *arg);
+int HYPERVISOR_console_io(int cmd, int count, char *str);
+int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count);
+int HYPERVISOR_sched_op(int cmd, void *arg);
+int HYPERVISOR_event_channel_op(int cmd, void *arg);
+unsigned long HYPERVISOR_hvm_op(int op, void *arg);
+int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
+int HYPERVISOR_physdev_op(int cmd, void *arg);
+
+static inline void
+MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
+ unsigned int new_val, unsigned long flags)
+{
+ BUG();
+}
+
+static inline void
+MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
+ int count, int *success_count, domid_t domid)
+{
+ BUG();
+}
+
+static inline int
+HYPERVISOR_multicall(void *call_list, int nr_calls)
+{
+ BUG();
+}
+#endif /* _ASM_ARM_XEN_HYPERCALL_H */
--- /dev/null
+#ifndef _ASM_ARM_XEN_HYPERVISOR_H
+#define _ASM_ARM_XEN_HYPERVISOR_H
+
+extern struct shared_info *HYPERVISOR_shared_info;
+extern struct start_info *xen_start_info;
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+ PARAVIRT_LAZY_NONE,
+ PARAVIRT_LAZY_MMU,
+ PARAVIRT_LAZY_CPU,
+};
+
+static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
+{
+ return PARAVIRT_LAZY_NONE;
+}
+
+#endif /* _ASM_ARM_XEN_HYPERVISOR_H */
--- /dev/null
+/******************************************************************************
+ * Guest OS interface to ARM Xen.
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ */
+
+#ifndef _ASM_ARM_XEN_INTERFACE_H
+#define _ASM_ARM_XEN_INTERFACE_H
+
+#include <linux/types.h>
+
+#define uint64_aligned_t uint64_t __attribute__((aligned(8)))
+
+#define __DEFINE_GUEST_HANDLE(name, type) \
+ typedef struct { union { type *p; uint64_aligned_t q; }; } \
+ __guest_handle_ ## name
+
+#define DEFINE_GUEST_HANDLE_STRUCT(name) \
+ __DEFINE_GUEST_HANDLE(name, struct name)
+#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
+#define GUEST_HANDLE(name) __guest_handle_ ## name
+
+#define set_xen_guest_handle(hnd, val) \
+ do { \
+ if (sizeof(hnd) == 8) \
+ *(uint64_t *)&(hnd) = 0; \
+ (hnd).p = val; \
+ } while (0)
+
+#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the interface with
+ * Xen so that we can have one ABI that works for 32 and 64 bit guests. */
+typedef uint64_t xen_pfn_t;
+typedef uint64_t xen_ulong_t;
+/* Guest handles for primitive C types. */
+__DEFINE_GUEST_HANDLE(uchar, unsigned char);
+__DEFINE_GUEST_HANDLE(uint, unsigned int);
+__DEFINE_GUEST_HANDLE(ulong, unsigned long);
+DEFINE_GUEST_HANDLE(char);
+DEFINE_GUEST_HANDLE(int);
+DEFINE_GUEST_HANDLE(long);
+DEFINE_GUEST_HANDLE(void);
+DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(xen_pfn_t);
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 1
+
+struct arch_vcpu_info { };
+struct arch_shared_info { };
+
+/* TODO: Move pvclock definitions some place arch independent */
+struct pvclock_vcpu_time_info {
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+/* It is OK to have a 12 bytes struct with no padding because it is packed */
+struct pvclock_wall_clock {
+ u32 version;
+ u32 sec;
+ u32 nsec;
+} __attribute__((__packed__));
+#endif
+
+#endif /* _ASM_ARM_XEN_INTERFACE_H */
--- /dev/null
+#ifndef _ASM_ARM_XEN_PAGE_H
+#define _ASM_ARM_XEN_PAGE_H
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#include <linux/pfn.h>
+#include <linux/types.h>
+
+#include <xen/interface/grant_table.h>
+
+#define pfn_to_mfn(pfn) (pfn)
+#define phys_to_machine_mapping_valid (1)
+#define mfn_to_pfn(mfn) (mfn)
+#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+#define pte_mfn pte_pfn
+#define mfn_pte pfn_pte
+
+/* Xen machine address */
+typedef struct xmaddr {
+ phys_addr_t maddr;
+} xmaddr_t;
+
+/* Xen pseudo-physical address */
+typedef struct xpaddr {
+ phys_addr_t paddr;
+} xpaddr_t;
+
+#define XMADDR(x) ((xmaddr_t) { .maddr = (x) })
+#define XPADDR(x) ((xpaddr_t) { .paddr = (x) })
+
+static inline xmaddr_t phys_to_machine(xpaddr_t phys)
+{
+ unsigned offset = phys.paddr & ~PAGE_MASK;
+ return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
+}
+
+static inline xpaddr_t machine_to_phys(xmaddr_t machine)
+{
+ unsigned offset = machine.maddr & ~PAGE_MASK;
+ return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
+}
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v))))
+#define virt_to_pfn(v) (PFN_DOWN(__pa(v)))
+#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v)))
+#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
+{
+ /* TODO: assuming it is mapped in the kernel 1:1 */
+ return virt_to_machine(vaddr);
+}
+
+/* TODO: this shouldn't be here but it is because the frontend drivers
+ * are using it (its rolled in headers) even though we won't hit the code path.
+ * So for right now just punt with this.
+ */
+static inline pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+ BUG();
+ return NULL;
+}
+
+static inline int m2p_add_override(unsigned long mfn, struct page *page,
+ struct gnttab_map_grant_ref *kmap_op)
+{
+ return 0;
+}
+
+static inline int m2p_remove_override(struct page *page, bool clear_pte)
+{
+ return 0;
+}
+
+static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+ BUG();
+ return false;
+}
+#endif /* _ASM_ARM_XEN_PAGE_H */
const static char *v2m_dt_match[] __initconst = {
"arm,vexpress",
+ "xen,xenvm",
NULL,
};
--- /dev/null
+obj-y := enlighten.o hypercall.o grant-table.o
--- /dev/null
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/hvm.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/interface/hvm/params.h>
+#include <xen/features.h>
+#include <xen/platform_pci.h>
+#include <xen/xenbus.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+struct start_info _xen_start_info;
+struct start_info *xen_start_info = &_xen_start_info;
+EXPORT_SYMBOL_GPL(xen_start_info);
+
+enum xen_domain_type xen_domain_type = XEN_NATIVE;
+EXPORT_SYMBOL_GPL(xen_domain_type);
+
+struct shared_info xen_dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
+
+DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
+
+/* TODO: to be removed */
+__read_mostly int xen_have_vector_callback;
+EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+
+int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
+EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
+
+static __read_mostly int xen_events_irq = -1;
+
+int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
+ unsigned long addr,
+ unsigned long mfn, int nr,
+ pgprot_t prot, unsigned domid)
+{
+ return -ENOSYS;
+}
+EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
+
+/*
+ * see Documentation/devicetree/bindings/arm/xen.txt for the
+ * documentation of the Xen Device Tree format.
+ */
+#define GRANT_TABLE_PHYSADDR 0
+static int __init xen_guest_init(void)
+{
+ struct xen_add_to_physmap xatp;
+ static struct shared_info *shared_info_page = 0;
+ struct device_node *node;
+ int len;
+ const char *s = NULL;
+ const char *version = NULL;
+ const char *xen_prefix = "xen,xen-";
+ struct resource res;
+
+ node = of_find_compatible_node(NULL, NULL, "xen,xen");
+ if (!node) {
+ pr_debug("No Xen support\n");
+ return 0;
+ }
+ s = of_get_property(node, "compatible", &len);
+ if (strlen(xen_prefix) + 3 < len &&
+ !strncmp(xen_prefix, s, strlen(xen_prefix)))
+ version = s + strlen(xen_prefix);
+ if (version == NULL) {
+ pr_debug("Xen version not found\n");
+ return 0;
+ }
+ if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
+ return 0;
+ xen_hvm_resume_frames = res.start >> PAGE_SHIFT;
+ xen_events_irq = irq_of_parse_and_map(node, 0);
+ pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n",
+ version, xen_events_irq, xen_hvm_resume_frames);
+ xen_domain_type = XEN_HVM_DOMAIN;
+
+ xen_setup_features();
+ if (xen_feature(XENFEAT_dom0))
+ xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
+ else
+ xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
+
+ if (!shared_info_page)
+ shared_info_page = (struct shared_info *)
+ get_zeroed_page(GFP_KERNEL);
+ if (!shared_info_page) {
+ pr_err("not enough memory\n");
+ return -ENOMEM;
+ }
+ xatp.domid = DOMID_SELF;
+ xatp.idx = 0;
+ xatp.space = XENMAPSPACE_shared_info;
+ xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
+ if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
+ BUG();
+
+ HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
+
+ /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
+ * page, we use it in the event channel upcall and in some pvclock
+ * related functions. We don't need the vcpu_info placement
+ * optimizations because we don't use any pv_mmu or pv_irq op on
+ * HVM.
+ * The shared info contains exactly 1 CPU (the boot CPU). The guest
+ * is required to use VCPUOP_register_vcpu_info to place vcpu info
+ * for secondary CPUs as they are brought up. */
+ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
+
+ gnttab_init();
+ if (!xen_initial_domain())
+ xenbus_probe(NULL);
+
+ return 0;
+}
+core_initcall(xen_guest_init);
+
+static irqreturn_t xen_arm_callback(int irq, void *arg)
+{
+ xen_hvm_evtchn_do_upcall();
+ return IRQ_HANDLED;
+}
+
+static int __init xen_init_events(void)
+{
+ if (!xen_domain() || xen_events_irq < 0)
+ return -ENODEV;
+
+ xen_init_IRQ();
+
+ if (request_percpu_irq(xen_events_irq, xen_arm_callback,
+ "events", xen_vcpu)) {
+ pr_err("Error requesting IRQ %d\n", xen_events_irq);
+ return -EINVAL;
+ }
+
+ enable_percpu_irq(xen_events_irq, 0);
+
+ return 0;
+}
+postcore_initcall(xen_init_events);
+
+/* XXX: only until balloon is properly working */
+int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
+{
+ *pages = alloc_pages(highmem ? GFP_HIGHUSER : GFP_KERNEL,
+ get_order(nr_pages));
+ if (*pages == NULL)
+ return -ENOMEM;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(alloc_xenballooned_pages);
+
+void free_xenballooned_pages(int nr_pages, struct page **pages)
+{
+ kfree(*pages);
+ *pages = NULL;
+}
+EXPORT_SYMBOL_GPL(free_xenballooned_pages);
--- /dev/null
+/******************************************************************************
+ * grant_table.c
+ * ARM specific part
+ *
+ * Granting foreign access to our memory reservation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (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.
+ */
+
+#include <xen/interface/xen.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+
+int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
+ unsigned long max_nr_gframes,
+ void **__shared)
+{
+ return -ENOSYS;
+}
+
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
+{
+ return;
+}
+
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+ unsigned long max_nr_gframes,
+ grant_status_t **__shared)
+{
+ return -ENOSYS;
+}
--- /dev/null
+/******************************************************************************
+ * hypercall.S
+ *
+ * Xen hypercall wrappers
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (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.
+ */
+
+/*
+ * The Xen hypercall calling convention is very similar to the ARM
+ * procedure calling convention: the first paramter is passed in r0, the
+ * second in r1, the third in r2 and the fourth in r3. Considering that
+ * Xen hypercalls have 5 arguments at most, the fifth paramter is passed
+ * in r4, differently from the procedure calling convention of using the
+ * stack for that case.
+ *
+ * The hypercall number is passed in r12.
+ *
+ * The return value is in r0.
+ *
+ * The hvc ISS is required to be 0xEA1, that is the Xen specific ARM
+ * hypercall tag.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <xen/interface/xen.h>
+
+
+/* HVC 0xEA1 */
+#ifdef CONFIG_THUMB2_KERNEL
+#define xen_hvc .word 0xf7e08ea1
+#else
+#define xen_hvc .word 0xe140ea71
+#endif
+
+#define HYPERCALL_SIMPLE(hypercall) \
+ENTRY(HYPERVISOR_##hypercall) \
+ mov r12, #__HYPERVISOR_##hypercall; \
+ xen_hvc; \
+ mov pc, lr; \
+ENDPROC(HYPERVISOR_##hypercall)
+
+#define HYPERCALL0 HYPERCALL_SIMPLE
+#define HYPERCALL1 HYPERCALL_SIMPLE
+#define HYPERCALL2 HYPERCALL_SIMPLE
+#define HYPERCALL3 HYPERCALL_SIMPLE
+#define HYPERCALL4 HYPERCALL_SIMPLE
+
+#define HYPERCALL5(hypercall) \
+ENTRY(HYPERVISOR_##hypercall) \
+ stmdb sp!, {r4} \
+ ldr r4, [sp, #4] \
+ mov r12, #__HYPERVISOR_##hypercall; \
+ xen_hvc \
+ ldm sp!, {r4} \
+ mov pc, lr \
+ENDPROC(HYPERVISOR_##hypercall)
+
+ .text
+
+HYPERCALL2(xen_version);
+HYPERCALL3(console_io);
+HYPERCALL3(grant_table_op);
+HYPERCALL2(sched_op);
+HYPERCALL2(event_channel_op);
+HYPERCALL2(hvm_op);
+HYPERCALL2(memory_op);
+HYPERCALL2(physdev_op);
+
+ENTRY(privcmd_call)
+ stmdb sp!, {r4}
+ mov r12, r0
+ mov r0, r1
+ mov r1, r2
+ mov r2, r3
+ ldr r3, [sp, #8]
+ ldr r4, [sp, #4]
+ xen_hvc
+ ldm sp!, {r4}
+ mov pc, lr
+ENDPROC(privcmd_call);
#define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0)
#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the public interface
+ * with Xen so that we could have one ABI that works for 32 and 64 bit
+ * guests. */
+typedef unsigned long xen_pfn_t;
+typedef unsigned long xen_ulong_t;
/* Guest handles for primitive C types. */
__DEFINE_GUEST_HANDLE(uchar, unsigned char);
__DEFINE_GUEST_HANDLE(uint, unsigned int);
DEFINE_GUEST_HANDLE(uint64_t);
DEFINE_GUEST_HANDLE(uint32_t);
-typedef unsigned long xen_pfn_t;
DEFINE_GUEST_HANDLE(xen_pfn_t);
#define PRI_xen_pfn "lx"
#endif
#endif /* !__ASSEMBLY__ */
+#include <asm/pvclock-abi.h>
+
/* Size of the shared_info area (this is not related to page size). */
#define XSI_SHIFT 14
#define XSI_SIZE (1 << XSI_SHIFT)
#endif
#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the public interface
+ * with Xen so that on ARM we can have one ABI that works for 32 and 64
+ * bit guests. */
+typedef unsigned long xen_pfn_t;
+typedef unsigned long xen_ulong_t;
/* Guest handles for primitive C types. */
__DEFINE_GUEST_HANDLE(uchar, unsigned char);
__DEFINE_GUEST_HANDLE(uint, unsigned int);
DEFINE_GUEST_HANDLE(void);
DEFINE_GUEST_HANDLE(uint64_t);
DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(xen_pfn_t);
#endif
#ifndef HYPERVISOR_VIRT_START
#include "interface_64.h"
#endif
+#include <asm/pvclock-abi.h>
+
#ifndef __ASSEMBLY__
/*
* The following is all CPU context. Note that the fpu_ctxt block is filled
extern int xen_swiotlb;
extern int __init pci_xen_swiotlb_detect(void);
extern void __init pci_xen_swiotlb_init(void);
+extern int pci_xen_swiotlb_init_late(void);
#else
#define xen_swiotlb (0)
static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
static inline void __init pci_xen_swiotlb_init(void) { }
+static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
#endif
#endif /* _ASM_X86_SWIOTLB_XEN_H */
#include <xen/xen.h>
#include <xen/interface/physdev.h>
+#include "xen-ops.h"
-unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
+static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
{
struct physdev_apic apic_op;
int ret;
#include <linux/memblock.h>
#include <xen/xen.h>
+#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/version.h>
#include <xen/interface/physdev.h>
#include "smp.h"
#include "multicalls.h"
+#include <xen/events.h>
+
EXPORT_SYMBOL_GPL(hypercall_page);
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
{
struct physdev_set_iopl set_iopl;
int rc;
- pgd_t *pgd;
if (!xen_start_info)
return;
acpi_numa = -1;
#endif
- pgd = (pgd_t *)xen_start_info->pt_base;
-
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
early_boot_irqs_disabled = true;
xen_raw_console_write("mapping kernel into physical memory\n");
- pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+ xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
/* Allocate and initialize top and mid mfn levels for p2m structure */
xen_build_mfn_list_list();
const struct dom0_vga_console_info *info =
(void *)((char *)xen_start_info +
xen_start_info->console.dom0.info_off);
+ struct xen_platform_op op = {
+ .cmd = XENPF_firmware_info,
+ .interface_version = XENPF_INTERFACE_VERSION,
+ .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
+ };
xen_init_vga(info, xen_start_info->console.dom0.info_size);
xen_start_info->console.domU.mfn = 0;
xen_start_info->console.domU.evtchn = 0;
+ if (HYPERVISOR_dom0_op(&op) == 0)
+ boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
+
xen_init_apic();
/* Make sure ACS will be enabled */
#include <xen/interface/xen.h>
#include <xen/interface/sched.h>
#include <xen/interface/vcpu.h>
+#include <xen/events.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
*/
DEFINE_SPINLOCK(xen_reservation_lock);
+#ifdef CONFIG_X86_32
/*
* Identity map, in addition to plain kernel map. This needs to be
* large enough to allocate page table pages to allocate the rest.
*/
#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4)
static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-
+#endif
#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
static void xen_post_allocator_init(void);
-static void __init xen_pagetable_init(void)
-{
- paging_init();
- xen_setup_shared_info();
- xen_post_allocator_init();
-}
-
static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
{
/* reserve the range used */
}
}
+#ifdef CONFIG_X86_64
+static void __init xen_cleanhighmap(unsigned long vaddr,
+ unsigned long vaddr_end)
+{
+ unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+ pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
+
+ /* NOTE: The loop is more greedy than the cleanup_highmap variant.
+ * We include the PMD passed in on _both_ boundaries. */
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ pmd++, vaddr += PMD_SIZE) {
+ if (pmd_none(*pmd))
+ continue;
+ if (vaddr < (unsigned long) _text || vaddr > kernel_end)
+ set_pmd(pmd, __pmd(0));
+ }
+ /* In case we did something silly, we should crash in this function
+ * instead of somewhere later and be confusing. */
+ xen_mc_flush();
+}
+#endif
+static void __init xen_pagetable_init(void)
+{
+#ifdef CONFIG_X86_64
+ unsigned long size;
+ unsigned long addr;
+#endif
+ paging_init();
+ xen_setup_shared_info();
+#ifdef CONFIG_X86_64
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ unsigned long new_mfn_list;
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+ /* On 32-bit, we get zero so this never gets executed. */
+ new_mfn_list = xen_revector_p2m_tree();
+ if (new_mfn_list && new_mfn_list != xen_start_info->mfn_list) {
+ /* using __ka address and sticking INVALID_P2M_ENTRY! */
+ memset((void *)xen_start_info->mfn_list, 0xff, size);
+
+ /* We should be in __ka space. */
+ BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
+ addr = xen_start_info->mfn_list;
+ /* We roundup to the PMD, which means that if anybody at this stage is
+ * using the __ka address of xen_start_info or xen_start_info->shared_info
+ * they are in going to crash. Fortunatly we have already revectored
+ * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+ size = roundup(size, PMD_SIZE);
+ xen_cleanhighmap(addr, addr + size);
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ memblock_free(__pa(xen_start_info->mfn_list), size);
+ /* And revector! Bye bye old array */
+ xen_start_info->mfn_list = new_mfn_list;
+ } else
+ goto skip;
+ }
+ /* At this stage, cleanup_highmap has already cleaned __ka space
+ * from _brk_limit way up to the max_pfn_mapped (which is the end of
+ * the ramdisk). We continue on, erasing PMD entries that point to page
+ * tables - do note that they are accessible at this stage via __va.
+ * For good measure we also round up to the PMD - which means that if
+ * anybody is using __ka address to the initial boot-stack - and try
+ * to use it - they are going to crash. The xen_start_info has been
+ * taken care of already in xen_setup_kernel_pagetable. */
+ addr = xen_start_info->pt_base;
+ size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+
+ xen_cleanhighmap(addr, addr + size);
+ xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
+#ifdef DEBUG
+ /* This is superflous and is not neccessary, but you know what
+ * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
+ * anything at this stage. */
+ xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
+#endif
+skip:
+#endif
+ xen_post_allocator_init();
+}
static void xen_write_cr2(unsigned long cr2)
{
this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
BUG();
}
-
+#ifdef CONFIG_X86_32
static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
set_page_prot(pmd, PAGE_KERNEL_RO);
}
-
+#endif
void __init xen_setup_machphys_mapping(void)
{
struct xen_machphys_mapping mapping;
for (i = 0; i < PTRS_PER_PTE; i++)
pte[i] = xen_make_pte(pte[i].pte);
}
-
+static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
+ unsigned long addr)
+{
+ if (*pt_base == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_base)++;
+ }
+ if (*pt_end == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_end)--;
+ }
+}
/*
* Set up the initial kernel pagetable.
*
* of the physical mapping once some sort of allocator has been set
* up.
*/
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pud_t *l3;
pmd_t *l2;
+ unsigned long addr[3];
+ unsigned long pt_base, pt_end;
+ unsigned i;
/* max_pfn_mapped is the last pfn mapped in the initial memory
* mappings. Considering that on Xen after the kernel mappings we
* set max_pfn_mapped to the last real pfn mapped. */
max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+ pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
+ pt_end = pt_base + xen_start_info->nr_pt_frames;
+
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
/* Pre-constructed entries are in pfn, so convert to mfn */
+ /* L4[272] -> level3_ident_pgt
+ * L4[511] -> level3_kernel_pgt */
convert_pfn_mfn(init_level4_pgt);
+
+ /* L3_i[0] -> level2_ident_pgt */
convert_pfn_mfn(level3_ident_pgt);
+ /* L3_k[510] -> level2_kernel_pgt
+ * L3_i[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
+ /* We get [511][511] and have Xen's version of level2_kernel_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
- memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
- memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
+ addr[0] = (unsigned long)pgd;
+ addr[1] = (unsigned long)l3;
+ addr[2] = (unsigned long)l2;
+ /* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
+ * Both L4[272][0] and L4[511][511] have entries that point to the same
+ * L2 (PMD) tables. Meaning that if you modify it in __va space
+ * it will be also modified in the __ka space! (But if you just
+ * modify the PMD table to point to other PTE's or none, then you
+ * are OK - which is what cleanup_highmap does) */
+ copy_page(level2_ident_pgt, l2);
+ /* Graft it onto L4[511][511] */
+ copy_page(level2_kernel_pgt, l2);
+
+ /* Get [511][510] and graft that in level2_fixmap_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
- memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
- /* Set up identity map */
- xen_map_identity_early(level2_ident_pgt, max_pfn);
+ copy_page(level2_fixmap_pgt, l2);
+ /* Note that we don't do anything with level1_fixmap_pgt which
+ * we don't need. */
/* Make pagetable pieces RO */
set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
/* Unpin Xen-provided one */
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /* Switch over */
- pgd = init_level4_pgt;
-
/*
* At this stage there can be no user pgd, and no page
* structure to attach it to, so make sure we just set kernel
* pgd.
*/
xen_mc_batch();
- __xen_write_cr3(true, __pa(pgd));
+ __xen_write_cr3(true, __pa(init_level4_pgt));
xen_mc_issue(PARAVIRT_LAZY_CPU);
- memblock_reserve(__pa(xen_start_info->pt_base),
- xen_start_info->nr_pt_frames * PAGE_SIZE);
+ /* We can't that easily rip out L3 and L2, as the Xen pagetables are
+ * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
+ * the initial domain. For guests using the toolstack, they are in:
+ * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
+ * rip out the [L4] (pgd), but for guests we shave off three pages.
+ */
+ for (i = 0; i < ARRAY_SIZE(addr); i++)
+ check_pt_base(&pt_base, &pt_end, addr[i]);
- return pgd;
+ /* Our (by three pages) smaller Xen pagetable that we are using */
+ memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+ /* Revector the xen_start_info */
+ xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
}
#else /* !CONFIG_X86_64 */
static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
*/
swapper_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- memcpy(swapper_kernel_pmd, initial_kernel_pmd,
- sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(swapper_kernel_pmd, initial_kernel_pmd);
swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
pv_mmu_ops.write_cr3 = &xen_write_cr3;
}
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pmd_t *kernel_pmd;
512*1024);
kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
- memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(initial_kernel_pmd, kernel_pmd);
xen_map_identity_early(initial_kernel_pmd, max_pfn);
- memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ copy_page(initial_page_table, pgd);
initial_page_table[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
memblock_reserve(__pa(xen_start_info->pt_base),
xen_start_info->nr_pt_frames * PAGE_SIZE);
-
- return initial_page_table;
}
#endif /* CONFIG_X86_64 */
unsigned long range;
int err = 0;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return -EINVAL;
+
prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
if (err)
goto out;
- err = -EFAULT;
- if (HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid) < 0)
+ err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid);
+ if (err < 0)
goto out;
nr -= batch;
*
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
- * 512 and 1024 entries respectively.
+ * 512 and 1024 entries respectively.
*
* In short, these structures contain the Machine Frame Number (MFN) of the PFN.
*
* / | ~0, ~0, .... |
* | \---------------/
* |
- * p2m_missing p2m_missing
- * /------------------\ /------------\
- * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
- * | [p2m_mid_missing]+---->| ..., ~0 |
- * \------------------/ \------------/
+ * p2m_mid_missing p2m_missing
+ * /-----------------\ /------------\
+ * | [p2m_missing] +---->| ~0, ~0, ~0 |
+ * | [p2m_missing] +---->| ..., ~0 |
+ * \-----------------/ \------------/
*
* where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
m2p_override_init();
}
+#ifdef CONFIG_X86_64
+#include <linux/bootmem.h>
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ unsigned long va_start;
+ unsigned long va_end;
+ unsigned long pfn;
+ unsigned long pfn_free = 0;
+ unsigned long *mfn_list = NULL;
+ unsigned long size;
+
+ va_start = xen_start_info->mfn_list;
+ /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
+ * so make sure it is rounded up to that */
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ va_end = va_start + size;
+
+ /* If we were revectored already, don't do it again. */
+ if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
+ return 0;
+
+ mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
+ if (!mfn_list) {
+ pr_warn("Could not allocate space for a new P2M tree!\n");
+ return xen_start_info->mfn_list;
+ }
+ /* Fill it out with INVALID_P2M_ENTRY value */
+ memset(mfn_list, 0xFF, size);
+
+ for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx;
+ unsigned long *mid_p;
+
+ if (!p2m_top[topidx])
+ continue;
+
+ if (p2m_top[topidx] == p2m_mid_missing)
+ continue;
+
+ mididx = p2m_mid_index(pfn);
+ mid_p = p2m_top[topidx][mididx];
+ if (!mid_p)
+ continue;
+ if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
+ continue;
+
+ if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
+ continue;
+
+ /* The old va. Rebase it on mfn_list */
+ if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
+ unsigned long *new;
+
+ if (pfn_free > (size / sizeof(unsigned long))) {
+ WARN(1, "Only allocated for %ld pages, but we want %ld!\n",
+ size / sizeof(unsigned long), pfn_free);
+ return 0;
+ }
+ new = &mfn_list[pfn_free];
+
+ copy_page(new, mid_p);
+ p2m_top[topidx][mididx] = &mfn_list[pfn_free];
+ p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]);
+
+ pfn_free += P2M_PER_PAGE;
+ }
+ /* This should be the leafs allocated for identity from _brk. */
+ }
+ return (unsigned long)mfn_list;
+
+}
+#else
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ return 0;
+}
+#endif
unsigned long get_phys_to_machine(unsigned long pfn)
{
unsigned topidx, mididx, idx;
free_page((unsigned long)p);
}
-/*
+/*
* Fully allocate the p2m structure for a given pfn. We need to check
* that both the top and mid levels are allocated, and make sure the
* parallel mfn tree is kept in sync. We may race with other cpus, so
#include <xen/xen.h>
#include <asm/iommu_table.h>
+
+#include <asm/xen/swiotlb-xen.h>
+#ifdef CONFIG_X86_64
+#include <asm/iommu.h>
+#include <asm/dma.h>
+#endif
+#include <linux/export.h>
+
int xen_swiotlb __read_mostly;
static struct dma_map_ops xen_swiotlb_dma_ops = {
int __init pci_xen_swiotlb_detect(void)
{
+ if (!xen_pv_domain())
+ return 0;
+
/* If running as PV guest, either iommu=soft, or swiotlb=force will
* activate this IOMMU. If running as PV privileged, activate it
* irregardless.
*/
- if ((xen_initial_domain() || swiotlb || swiotlb_force) &&
- (xen_pv_domain()))
+ if ((xen_initial_domain() || swiotlb || swiotlb_force))
xen_swiotlb = 1;
/* If we are running under Xen, we MUST disable the native SWIOTLB.
* Don't worry about swiotlb_force flag activating the native, as
* the 'swiotlb' flag is the only one turning it on. */
- if (xen_pv_domain())
- swiotlb = 0;
+ swiotlb = 0;
+#ifdef CONFIG_X86_64
+ /* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
+ * (so no iommu=X command line over-writes).
+ * Considering that PV guests do not want the *native SWIOTLB* but
+ * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
+ */
+ if (max_pfn > MAX_DMA32_PFN)
+ no_iommu = 1;
+#endif
return xen_swiotlb;
}
void __init pci_xen_swiotlb_init(void)
{
if (xen_swiotlb) {
- xen_swiotlb_init(1);
+ xen_swiotlb_init(1, true /* early */);
dma_ops = &xen_swiotlb_dma_ops;
/* Make sure ACS will be enabled */
pci_request_acs();
}
}
+
+int pci_xen_swiotlb_init_late(void)
+{
+ int rc;
+
+ if (xen_swiotlb)
+ return 0;
+
+ rc = xen_swiotlb_init(1, false /* late */);
+ if (rc)
+ return rc;
+
+ dma_ops = &xen_swiotlb_dma_ops;
+ /* Make sure ACS will be enabled */
+ pci_request_acs();
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+
IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
- 0,
+ NULL,
pci_xen_swiotlb_init,
- 0);
+ NULL);
#include <linux/module.h>
#include <xen/platform_pci.h>
+#include "xen-ops.h"
#define XEN_PLATFORM_ERR_MAGIC -1
#define XEN_PLATFORM_ERR_PROTOCOL -2
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
+ * We tried to make the the memblock_reserve more selective so
+ * that it would be clear what region is reserved. Sadly we ran
+ * in the problem wherein on a 64-bit hypervisor with a 32-bit
+ * initial domain, the pt_base has the cr3 value which is not
+ * neccessarily where the pagetable starts! As Jan put it: "
+ * Actually, the adjustment turns out to be correct: The page
+ * tables for a 32-on-64 dom0 get allocated in the order "first L1",
+ * "first L2", "first L3", so the offset to the page table base is
+ * indeed 2. When reading xen/include/public/xen.h's comment
+ * very strictly, this is not a violation (since there nothing is said
+ * that the first thing in the page table space is pointed to by
+ * pt_base; I admit that this seems to be implied though, namely
+ * do I think that it is implied that the page table space is the
+ * range [pt_base, pt_base + nt_pt_frames), whereas that
+ * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
+ * which - without a priori knowledge - the kernel would have
+ * difficulty to figure out)." - so lets just fall back to the
+ * easy way and reserve the whole region.
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
info->u.text_mode_3.font_height;
break;
+ case XEN_VGATYPE_EFI_LFB:
case XEN_VGATYPE_VESA_LFB:
if (size < offsetof(struct dom0_vga_console_info,
u.vesa_lfb.gbl_caps))
screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+
+ if (info->video_type == XEN_VGATYPE_EFI_LFB) {
+ screen_info->orig_video_isVGA = VIDEO_TYPE_EFI;
+ break;
+ }
+
if (size >= offsetof(struct dom0_vga_console_info,
u.vesa_lfb.gbl_caps)
+ sizeof(info->u.vesa_lfb.gbl_caps))
__FINIT
.pushsection .text
- .align PAGE_SIZE
+ .balign PAGE_SIZE
ENTRY(hypercall_page)
- .skip PAGE_SIZE
+#define NEXT_HYPERCALL(x) \
+ ENTRY(xen_hypercall_##x) \
+ .skip 32
+
+NEXT_HYPERCALL(set_trap_table)
+NEXT_HYPERCALL(mmu_update)
+NEXT_HYPERCALL(set_gdt)
+NEXT_HYPERCALL(stack_switch)
+NEXT_HYPERCALL(set_callbacks)
+NEXT_HYPERCALL(fpu_taskswitch)
+NEXT_HYPERCALL(sched_op_compat)
+NEXT_HYPERCALL(platform_op)
+NEXT_HYPERCALL(set_debugreg)
+NEXT_HYPERCALL(get_debugreg)
+NEXT_HYPERCALL(update_descriptor)
+NEXT_HYPERCALL(ni)
+NEXT_HYPERCALL(memory_op)
+NEXT_HYPERCALL(multicall)
+NEXT_HYPERCALL(update_va_mapping)
+NEXT_HYPERCALL(set_timer_op)
+NEXT_HYPERCALL(event_channel_op_compat)
+NEXT_HYPERCALL(xen_version)
+NEXT_HYPERCALL(console_io)
+NEXT_HYPERCALL(physdev_op_compat)
+NEXT_HYPERCALL(grant_table_op)
+NEXT_HYPERCALL(vm_assist)
+NEXT_HYPERCALL(update_va_mapping_otherdomain)
+NEXT_HYPERCALL(iret)
+NEXT_HYPERCALL(vcpu_op)
+NEXT_HYPERCALL(set_segment_base)
+NEXT_HYPERCALL(mmuext_op)
+NEXT_HYPERCALL(xsm_op)
+NEXT_HYPERCALL(nmi_op)
+NEXT_HYPERCALL(sched_op)
+NEXT_HYPERCALL(callback_op)
+NEXT_HYPERCALL(xenoprof_op)
+NEXT_HYPERCALL(event_channel_op)
+NEXT_HYPERCALL(physdev_op)
+NEXT_HYPERCALL(hvm_op)
+NEXT_HYPERCALL(sysctl)
+NEXT_HYPERCALL(domctl)
+NEXT_HYPERCALL(kexec_op)
+NEXT_HYPERCALL(tmem_op) /* 38 */
+ENTRY(xen_hypercall_rsvr)
+ .skip 320
+NEXT_HYPERCALL(mca) /* 48 */
+NEXT_HYPERCALL(arch_1)
+NEXT_HYPERCALL(arch_2)
+NEXT_HYPERCALL(arch_3)
+NEXT_HYPERCALL(arch_4)
+NEXT_HYPERCALL(arch_5)
+NEXT_HYPERCALL(arch_6)
+ .balign PAGE_SIZE
.popsection
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
void xen_setup_shared_info(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
-pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
+void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_reserve_top(void);
extern unsigned long xen_max_p2m_pfn;
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
-void __init xen_init_IRQ(void);
void xen_enable_sysenter(void);
void xen_enable_syscall(void);
void xen_vcpu_restore(void);
void xen_unplug_emulated_devices(void);
void __init xen_build_dynamic_phys_to_machine(void);
+unsigned long __init xen_revector_p2m_tree(void);
void xen_init_irq_ops(void);
void xen_setup_timer(int cpu);
#include <xen/events.h>
#include <xen/page.h>
+#include <xen/xen.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include "common.h"
#include <net/tcp.h>
+#include <xen/xen.h>
#include <xen/events.h>
#include <xen/interface/memory.h>
#include <linux/slab.h>
#include <net/ip.h>
+#include <asm/xen/page.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/events.h>
#include <linux/bitops.h>
#include <linux/time.h>
+#include <asm/xen/swiotlb-xen.h>
#define INVALID_GRANT_REF (0)
#define INVALID_EVTCHN (-1)
return errno_to_pcibios_err(do_pci_op(pdev, &op));
}
-struct pci_ops pcifront_bus_ops = {
+static struct pci_ops pcifront_bus_ops = {
.read = pcifront_bus_read,
.write = pcifront_bus_write,
};
schedule_pcifront_aer_op(pdev);
return IRQ_HANDLED;
}
-static int pcifront_connect(struct pcifront_device *pdev)
+static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)
{
int err = 0;
dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
err = -EEXIST;
}
-
spin_unlock(&pcifront_dev_lock);
+ if (!err && !swiotlb_nr_tbl()) {
+ err = pci_xen_swiotlb_init_late();
+ if (err)
+ dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n");
+ }
return err;
}
XenbusStateInitialised)
goto out;
- err = pcifront_connect(pdev);
+ err = pcifront_connect_and_init_dma(pdev);
if (err) {
xenbus_dev_fatal(pdev->xdev, err,
- "Error connecting PCI Frontend");
+ "Error setting up PCI Frontend");
goto out;
}
#include <linux/console.h>
#include <linux/delay.h>
#include <linux/err.h>
+#include <linux/irq.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/list.h>
#include <xen/page.h>
#include <xen/events.h>
#include <xen/interface/io/console.h>
+#include <xen/interface/sched.h>
#include <xen/hvc-console.h>
#include <xen/xenbus.h>
-obj-y += grant-table.o features.o events.o manage.o balloon.o
+ifneq ($(CONFIG_ARM),y)
+obj-y += manage.o balloon.o
+obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o
+endif
+obj-y += grant-table.o features.o events.o
obj-y += xenbus/
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_features.o := $(nostackp)
+dom0-$(CONFIG_PCI) += pci.o
+dom0-$(CONFIG_ACPI) += acpi.o
+dom0-$(CONFIG_X86) += pcpu.o
+dom0-$(CONFIG_USB_SUPPORT) += dbgp.o
+obj-$(CONFIG_XEN_DOM0) += $(dom0-y)
obj-$(CONFIG_BLOCK) += biomerge.o
-obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o
obj-$(CONFIG_XEN_XENCOMM) += xencomm.o
obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o
obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o
obj-$(CONFIG_XEN_PVHVM) += platform-pci.o
obj-$(CONFIG_XEN_TMEM) += tmem.o
obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o
-obj-$(CONFIG_XEN_DOM0) += pcpu.o
-obj-$(CONFIG_XEN_DOM0) += pci.o dbgp.o acpi.o
obj-$(CONFIG_XEN_MCE_LOG) += mcelog.o
obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/
obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o
#include <linux/irqnr.h>
#include <linux/pci.h>
+#ifdef CONFIG_X86
#include <asm/desc.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/io_apic.h>
-#include <asm/sync_bitops.h>
#include <asm/xen/page.h>
#include <asm/xen/pci.h>
+#endif
+#include <asm/sync_bitops.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/hvm/params.h>
+#include <xen/interface/physdev.h>
+#include <xen/interface/sched.h>
+#include <asm/hw_irq.h>
/*
* This lock protects updates to the following mapping and reference-count
{
struct shared_info *s = HYPERVISOR_shared_info;
unsigned int cpu = get_cpu();
+ int do_hypercall = 0, evtchn_pending = 0;
BUG_ON(!irqs_disabled());
- /* Slow path (hypercall) if this is a non-local port. */
- if (unlikely(cpu != cpu_from_evtchn(port))) {
+ if (unlikely((cpu != cpu_from_evtchn(port))))
+ do_hypercall = 1;
+ else
+ evtchn_pending = sync_test_bit(port, &s->evtchn_pending[0]);
+
+ if (unlikely(evtchn_pending && xen_hvm_domain()))
+ do_hypercall = 1;
+
+ /* Slow path (hypercall) if this is a non-local port or if this is
+ * an hvm domain and an event is pending (hvm domains don't have
+ * their own implementation of irq_enable). */
+ if (do_hypercall) {
struct evtchn_unmask unmask = { .port = port };
(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
} else {
* 'hw_resend_irq'. Just like a real IO-APIC we 'lose
* the interrupt edge' if the channel is masked.
*/
- if (sync_test_bit(port, &s->evtchn_pending[0]) &&
+ if (evtchn_pending &&
!sync_test_and_set_bit(port / BITS_PER_LONG,
&vcpu_info->evtchn_pending_sel))
vcpu_info->evtchn_upcall_pending = 1;
struct irq_info *info = info_for_irq(irq);
WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
}
+ irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
out:
mutex_unlock(&irq_mapping_update_lock);
{
struct pt_regs *old_regs = set_irq_regs(regs);
+#ifdef CONFIG_X86
exit_idle();
+#endif
irq_enter();
__xen_evtchn_do_upcall();
void __init xen_init_IRQ(void)
{
- int i, rc;
+ int i;
evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
GFP_KERNEL);
pirq_needs_eoi = pirq_needs_eoi_flag;
+#ifdef CONFIG_X86
if (xen_hvm_domain()) {
xen_callback_vector();
native_init_IRQ();
* __acpi_register_gsi can point at the right function */
pci_xen_hvm_init();
} else {
+ int rc;
struct physdev_pirq_eoi_gmfn eoi_gmfn;
irq_ctx_init(smp_processor_id());
} else
pirq_needs_eoi = pirq_check_eoi_map;
}
+#endif
}
spin_unlock(&priv->lock);
}
-struct mmu_notifier_ops gntdev_mmu_ops = {
+static struct mmu_notifier_ops gntdev_mmu_ops = {
.release = mn_release,
.invalidate_page = mn_invl_page,
.invalidate_range_start = mn_invl_range_start,
#include <xen/interface/memory.h>
#include <xen/hvc-console.h>
#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
#include <asm/pgtable.h>
#include <asm/sync_bitops.h>
}
EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
-void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
- unsigned long frame, int flags,
- unsigned page_off,
- unsigned length)
+static void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
+ unsigned long frame, int flags,
+ unsigned page_off, unsigned length)
{
gnttab_shared.v2[ref].sub_page.frame = frame;
gnttab_shared.v2[ref].sub_page.page_off = page_off;
}
EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available);
-void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
- int flags, domid_t trans_domid,
- grant_ref_t trans_gref)
+static void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
+ int flags, domid_t trans_domid,
+ grant_ref_t trans_gref)
{
gnttab_shared.v2[ref].transitive.trans_domid = trans_domid;
gnttab_shared.v2[ref].transitive.gref = trans_gref;
*/
static int gather_array(struct list_head *pagelist,
unsigned nelem, size_t size,
- void __user *data)
+ const void __user *data)
{
unsigned pageidx;
void *pagedata;
domid_t domain;
unsigned long va;
struct vm_area_struct *vma;
- int err;
-
- xen_pfn_t __user *user;
+ /* A tristate:
+ * 0 for no errors
+ * 1 if at least one error has happened (and no
+ * -ENOENT errors have happened)
+ * -ENOENT if at least 1 -ENOENT has happened.
+ */
+ int global_error;
+ /* An array for individual errors */
+ int *err;
+
+ /* User-space mfn array to store errors in the second pass for V1. */
+ xen_pfn_t __user *user_mfn;
};
static int mmap_batch_fn(void *data, void *state)
{
xen_pfn_t *mfnp = data;
struct mmap_batch_state *st = state;
+ int ret;
+
+ ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
+ st->vma->vm_page_prot, st->domain);
- if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
- st->vma->vm_page_prot, st->domain) < 0) {
- *mfnp |= 0xf0000000U;
- st->err++;
+ /* Store error code for second pass. */
+ *(st->err++) = ret;
+
+ /* And see if it affects the global_error. */
+ if (ret < 0) {
+ if (ret == -ENOENT)
+ st->global_error = -ENOENT;
+ else {
+ /* Record that at least one error has happened. */
+ if (st->global_error == 0)
+ st->global_error = 1;
+ }
}
st->va += PAGE_SIZE;
return 0;
}
-static int mmap_return_errors(void *data, void *state)
+static int mmap_return_errors_v1(void *data, void *state)
{
xen_pfn_t *mfnp = data;
struct mmap_batch_state *st = state;
-
- return put_user(*mfnp, st->user++);
+ int err = *(st->err++);
+
+ /*
+ * V1 encodes the error codes in the 32bit top nibble of the
+ * mfn (with its known limitations vis-a-vis 64 bit callers).
+ */
+ *mfnp |= (err == -ENOENT) ?
+ PRIVCMD_MMAPBATCH_PAGED_ERROR :
+ PRIVCMD_MMAPBATCH_MFN_ERROR;
+ return __put_user(*mfnp, st->user_mfn++);
}
static struct vm_operations_struct privcmd_vm_ops;
-static long privcmd_ioctl_mmap_batch(void __user *udata)
+static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
{
int ret;
- struct privcmd_mmapbatch m;
+ struct privcmd_mmapbatch_v2 m;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long nr_pages;
LIST_HEAD(pagelist);
+ int *err_array = NULL;
struct mmap_batch_state state;
if (!xen_initial_domain())
return -EPERM;
- if (copy_from_user(&m, udata, sizeof(m)))
- return -EFAULT;
+ switch (version) {
+ case 1:
+ if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch)))
+ return -EFAULT;
+ /* Returns per-frame error in m.arr. */
+ m.err = NULL;
+ if (!access_ok(VERIFY_WRITE, m.arr, m.num * sizeof(*m.arr)))
+ return -EFAULT;
+ break;
+ case 2:
+ if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch_v2)))
+ return -EFAULT;
+ /* Returns per-frame error code in m.err. */
+ if (!access_ok(VERIFY_WRITE, m.err, m.num * (sizeof(*m.err))))
+ return -EFAULT;
+ break;
+ default:
+ return -EINVAL;
+ }
nr_pages = m.num;
if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
return -EINVAL;
- ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t),
- m.arr);
+ ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), m.arr);
- if (ret || list_empty(&pagelist))
+ if (ret)
goto out;
+ if (list_empty(&pagelist)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ err_array = kcalloc(m.num, sizeof(int), GFP_KERNEL);
+ if (err_array == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
down_write(&mm->mmap_sem);
goto out;
}
- state.domain = m.dom;
- state.vma = vma;
- state.va = m.addr;
- state.err = 0;
+ state.domain = m.dom;
+ state.vma = vma;
+ state.va = m.addr;
+ state.global_error = 0;
+ state.err = err_array;
- ret = traverse_pages(m.num, sizeof(xen_pfn_t),
- &pagelist, mmap_batch_fn, &state);
+ /* mmap_batch_fn guarantees ret == 0 */
+ BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t),
+ &pagelist, mmap_batch_fn, &state));
up_write(&mm->mmap_sem);
- if (state.err > 0) {
- state.user = m.arr;
+ if (state.global_error && (version == 1)) {
+ /* Write back errors in second pass. */
+ state.user_mfn = (xen_pfn_t *)m.arr;
+ state.err = err_array;
ret = traverse_pages(m.num, sizeof(xen_pfn_t),
- &pagelist,
- mmap_return_errors, &state);
+ &pagelist, mmap_return_errors_v1, &state);
+ } else if (version == 2) {
+ ret = __copy_to_user(m.err, err_array, m.num * sizeof(int));
+ if (ret)
+ ret = -EFAULT;
}
+ /* If we have not had any EFAULT-like global errors then set the global
+ * error to -ENOENT if necessary. */
+ if ((ret == 0) && (state.global_error == -ENOENT))
+ ret = -ENOENT;
+
out:
+ kfree(err_array);
free_page_list(&pagelist);
return ret;
break;
case IOCTL_PRIVCMD_MMAPBATCH:
- ret = privcmd_ioctl_mmap_batch(udata);
+ ret = privcmd_ioctl_mmap_batch(udata, 1);
+ break;
+
+ case IOCTL_PRIVCMD_MMAPBATCH_V2:
+ ret = privcmd_ioctl_mmap_batch(udata, 2);
break;
default:
static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
{
- /* Unsupported for auto-translate guests. */
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return -ENOSYS;
-
/* DONTCOPY is essential for Xen because copy_page_range doesn't know
* how to recreate these mappings */
vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY | VM_PFNMAP;
* Quick lookup value of the bus address of the IOTLB.
*/
-u64 start_dma_addr;
+static u64 start_dma_addr;
static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
} while (i < nslabs);
return 0;
}
+static unsigned long xen_set_nslabs(unsigned long nr_tbl)
+{
+ if (!nr_tbl) {
+ xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+ xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+ } else
+ xen_io_tlb_nslabs = nr_tbl;
-void __init xen_swiotlb_init(int verbose)
+ return xen_io_tlb_nslabs << IO_TLB_SHIFT;
+}
+
+enum xen_swiotlb_err {
+ XEN_SWIOTLB_UNKNOWN = 0,
+ XEN_SWIOTLB_ENOMEM,
+ XEN_SWIOTLB_EFIXUP
+};
+
+static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
+{
+ switch (err) {
+ case XEN_SWIOTLB_ENOMEM:
+ return "Cannot allocate Xen-SWIOTLB buffer\n";
+ case XEN_SWIOTLB_EFIXUP:
+ return "Failed to get contiguous memory for DMA from Xen!\n"\
+ "You either: don't have the permissions, do not have"\
+ " enough free memory under 4GB, or the hypervisor memory"\
+ " is too fragmented!";
+ default:
+ break;
+ }
+ return "";
+}
+int __ref xen_swiotlb_init(int verbose, bool early)
{
- unsigned long bytes;
+ unsigned long bytes, order;
int rc = -ENOMEM;
- unsigned long nr_tbl;
- char *m = NULL;
+ enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
unsigned int repeat = 3;
- nr_tbl = swiotlb_nr_tbl();
- if (nr_tbl)
- xen_io_tlb_nslabs = nr_tbl;
- else {
- xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
- xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
+ xen_io_tlb_nslabs = swiotlb_nr_tbl();
retry:
- bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
-
+ bytes = xen_set_nslabs(xen_io_tlb_nslabs);
+ order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
/*
* Get IO TLB memory from any location.
*/
- xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+ if (early)
+ xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+ else {
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+ while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+ xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
+ if (xen_io_tlb_start)
+ break;
+ order--;
+ }
+ if (order != get_order(bytes)) {
+ pr_warn("Warning: only able to allocate %ld MB "
+ "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+ xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
+ bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+ }
+ }
if (!xen_io_tlb_start) {
- m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+ m_ret = XEN_SWIOTLB_ENOMEM;
goto error;
}
xen_io_tlb_end = xen_io_tlb_start + bytes;
bytes,
xen_io_tlb_nslabs);
if (rc) {
- free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
- m = "Failed to get contiguous memory for DMA from Xen!\n"\
- "You either: don't have the permissions, do not have"\
- " enough free memory under 4GB, or the hypervisor memory"\
- "is too fragmented!";
+ if (early)
+ free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+ else {
+ free_pages((unsigned long)xen_io_tlb_start, order);
+ xen_io_tlb_start = NULL;
+ }
+ m_ret = XEN_SWIOTLB_EFIXUP;
goto error;
}
start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
- swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
-
- return;
+ if (early) {
+ swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+ rc = 0;
+ } else
+ rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+ return rc;
error:
if (repeat--) {
xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
(xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
goto retry;
}
- xen_raw_printk("%s (rc:%d)", m, rc);
- panic("%s (rc:%d)", m, rc);
+ pr_err("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+ if (early)
+ panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+ else
+ free_pages((unsigned long)xen_io_tlb_start, order);
+ return rc;
}
-
void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
-int
-xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
-{
- return xen_swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
-}
-EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg);
-
/*
* Unmap a set of streaming mode DMA translations. Again, cpu read rules
* concerning calls here are the same as for swiotlb_unmap_page() above.
}
EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
-void
-xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
-{
- return xen_swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
-}
-EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg);
-
/*
* Make physical memory consistent for a set of streaming mode DMA translations
* after a transfer.
/* UUID */
-static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+static ssize_t uuid_show_fallback(struct hyp_sysfs_attr *attr, char *buffer)
{
char *vm, *val;
int ret;
return ret;
}
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ xen_domain_handle_t uuid;
+ int ret;
+ ret = HYPERVISOR_xen_version(XENVER_guest_handle, uuid);
+ if (ret)
+ return uuid_show_fallback(attr, buffer);
+ ret = sprintf(buffer, "%pU\n", uuid);
+ return ret;
+}
+
HYPERVISOR_ATTR_RO(uuid);
static int __init xen_sysfs_uuid_init(void)
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
#include <asm/xen/hypervisor.h>
+#include <xen/tmem.h>
#define TMEM_CONTROL 0
#define TMEM_NEW_POOL 1
else {
dev_dbg(&dev->dev, "reseting (FLR, D3, etc) the device\n");
__pci_reset_function_locked(dev);
+ pci_restore_state(dev);
}
/* Now disable the device (this also ensures some private device
* data is setup before we export)
dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
" by HVM, kill it\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
if (!test_bit(_XEN_PCIB_AERHANDLER,
(unsigned long *)&psdev->pdev->sh_info->flags)) {
dev_err(&dev->dev,
"guest with no AER driver should have been killed\n");
- goto release;
+ goto end;
}
result = common_process(psdev, 1, XEN_PCI_OP_aer_slotreset, result);
"No AER slot_reset service or disconnected!\n");
kill_domain_by_device(psdev);
}
-release:
- pcistub_device_put(psdev);
end:
+ if (psdev)
+ pcistub_device_put(psdev);
up_write(&pcistub_sem);
return result;
dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
" by HVM, kill it\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
if (!test_bit(_XEN_PCIB_AERHANDLER,
(unsigned long *)&psdev->pdev->sh_info->flags)) {
dev_err(&dev->dev,
"guest with no AER driver should have been killed\n");
- goto release;
+ goto end;
}
result = common_process(psdev, 1, XEN_PCI_OP_aer_mmio, result);
"No AER mmio_enabled service or disconnected!\n");
kill_domain_by_device(psdev);
}
-release:
- pcistub_device_put(psdev);
end:
+ if (psdev)
+ pcistub_device_put(psdev);
up_write(&pcistub_sem);
return result;
}
dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
" by HVM, kill it\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
/*Guest owns the device yet no aer handler regiested, kill guest*/
(unsigned long *)&psdev->pdev->sh_info->flags)) {
dev_dbg(&dev->dev, "guest may have no aer driver, kill it\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
result = common_process(psdev, error, XEN_PCI_OP_aer_detected, result);
"No AER error_detected service or disconnected!\n");
kill_domain_by_device(psdev);
}
-release:
- pcistub_device_put(psdev);
end:
+ if (psdev)
+ pcistub_device_put(psdev);
up_write(&pcistub_sem);
return result;
}
dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
" by HVM, kill it\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
if (!test_bit(_XEN_PCIB_AERHANDLER,
dev_err(&dev->dev,
"guest with no AER driver should have been killed\n");
kill_domain_by_device(psdev);
- goto release;
+ goto end;
}
common_process(psdev, 1, XEN_PCI_OP_aer_resume,
PCI_ERS_RESULT_RECOVERED);
-release:
- pcistub_device_put(psdev);
end:
+ if (psdev)
+ pcistub_device_put(psdev);
up_write(&pcistub_sem);
return;
}
int *slot, int *func)
{
int err;
+ char wc = '*';
err = sscanf(buf, " %x:%x:%x.%x", domain, bus, slot, func);
- if (err == 4)
+ switch (err) {
+ case 3:
+ *func = -1;
+ err = sscanf(buf, " %x:%x:%x.%c", domain, bus, slot, &wc);
+ break;
+ case 2:
+ *slot = *func = -1;
+ err = sscanf(buf, " %x:%x:*.%c", domain, bus, &wc);
+ if (err >= 2)
+ ++err;
+ break;
+ }
+ if (err == 4 && wc == '*')
return 0;
else if (err < 0)
return -EINVAL;
/* try again without domain */
*domain = 0;
+ wc = '*';
err = sscanf(buf, " %x:%x.%x", bus, slot, func);
- if (err == 3)
+ switch (err) {
+ case 2:
+ *func = -1;
+ err = sscanf(buf, " %x:%x.%c", bus, slot, &wc);
+ break;
+ case 1:
+ *slot = *func = -1;
+ err = sscanf(buf, " %x:*.%c", bus, &wc) + 1;
+ break;
+ }
+ if (err == 3 && wc == '*')
return 0;
return -EINVAL;
{
struct pcistub_device_id *pci_dev_id;
unsigned long flags;
+ int rc = 0;
+
+ if (slot < 0) {
+ for (slot = 0; !rc && slot < 32; ++slot)
+ rc = pcistub_device_id_add(domain, bus, slot, func);
+ return rc;
+ }
+
+ if (func < 0) {
+ for (func = 0; !rc && func < 8; ++func)
+ rc = pcistub_device_id_add(domain, bus, slot, func);
+ return rc;
+ }
pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL);
if (!pci_dev_id)
static int pcistub_device_id_remove(int domain, int bus, int slot, int func)
{
struct pcistub_device_id *pci_dev_id, *t;
- int devfn = PCI_DEVFN(slot, func);
int err = -ENOENT;
unsigned long flags;
spin_lock_irqsave(&device_ids_lock, flags);
list_for_each_entry_safe(pci_dev_id, t, &pcistub_device_ids,
slot_list) {
- if (pci_dev_id->domain == domain
- && pci_dev_id->bus == bus && pci_dev_id->devfn == devfn) {
+ if (pci_dev_id->domain == domain && pci_dev_id->bus == bus
+ && (slot < 0 || PCI_SLOT(pci_dev_id->devfn) == slot)
+ && (func < 0 || PCI_FUNC(pci_dev_id->devfn) == func)) {
/* Don't break; here because it's possible the same
* slot could be in the list more than once
*/
struct config_field *field;
psdev = pcistub_device_find(domain, bus, slot, func);
- if (!psdev || !psdev->dev) {
+ if (!psdev) {
err = -ENODEV;
goto out;
}
if (err)
kfree(field);
out:
+ if (psdev)
+ pcistub_device_put(psdev);
return err;
}
err = str_to_slot(buf, &domain, &bus, &slot, &func);
if (err)
- goto out;
+ return err;
psdev = pcistub_device_find(domain, bus, slot, func);
-
if (!psdev)
goto out;
if (dev_data->isr_on)
dev_data->ack_intr = 1;
out:
+ if (psdev)
+ pcistub_device_put(psdev);
if (!err)
err = count;
return err;
err = str_to_slot(buf, &domain, &bus, &slot, &func);
if (err)
goto out;
+ if (slot < 0 || func < 0) {
+ err = -EINVAL;
+ goto out;
+ }
psdev = pcistub_device_find(domain, bus, slot, func);
if (!psdev) {
err = -ENODEV;
goto out;
}
- if (!psdev->dev) {
- err = -ENODEV;
- goto release;
- }
+
dev_data = pci_get_drvdata(psdev->dev);
/* the driver data for a device should never be null at this point */
if (!dev_data) {
if (pci_devs_to_hide && *pci_devs_to_hide) {
do {
+ char wc = '*';
+
parsed = 0;
err = sscanf(pci_devs_to_hide + pos,
" (%x:%x:%x.%x) %n",
&domain, &bus, &slot, &func, &parsed);
- if (err != 4) {
+ switch (err) {
+ case 3:
+ func = -1;
+ err = sscanf(pci_devs_to_hide + pos,
+ " (%x:%x:%x.%c) %n",
+ &domain, &bus, &slot, &wc,
+ &parsed);
+ break;
+ case 2:
+ slot = func = -1;
+ err = sscanf(pci_devs_to_hide + pos,
+ " (%x:%x:*.%c) %n",
+ &domain, &bus, &wc, &parsed) + 1;
+ break;
+ }
+
+ if (err != 4 || wc != '*') {
domain = 0;
+ wc = '*';
err = sscanf(pci_devs_to_hide + pos,
" (%x:%x.%x) %n",
&bus, &slot, &func, &parsed);
- if (err != 3)
+ switch (err) {
+ case 2:
+ func = -1;
+ err = sscanf(pci_devs_to_hide + pos,
+ " (%x:%x.%c) %n",
+ &bus, &slot, &wc,
+ &parsed);
+ break;
+ case 1:
+ slot = func = -1;
+ err = sscanf(pci_devs_to_hide + pos,
+ " (%x:*.%c) %n",
+ &bus, &wc, &parsed) + 1;
+ break;
+ }
+ if (err != 3 || wc != '*')
goto parse_error;
}
int err;
err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting,
0, "xenbus", &xb_waitq);
- if (err <= 0) {
+ if (err < 0) {
printk(KERN_ERR "XENBUS request irq failed %i\n", err);
return err;
}
return 0;
}
-const struct file_operations xenbus_backend_fops = {
+static const struct file_operations xenbus_backend_fops = {
.open = xenbus_backend_open,
.mmap = xenbus_backend_mmap,
.unlocked_ioctl = xenbus_backend_ioctl,
return 0;
}
-struct xenbus_device *xenbus_device_find(const char *nodename,
- struct bus_type *bus)
+static struct xenbus_device *xenbus_device_find(const char *nodename,
+ struct bus_type *bus)
{
struct xb_find_info info = { .dev = NULL, .nodename = nodename };
return err;
}
+enum xenstore_init {
+ UNKNOWN,
+ PV,
+ HVM,
+ LOCAL,
+};
static int __init xenbus_init(void)
{
int err = 0;
+ enum xenstore_init usage = UNKNOWN;
+ uint64_t v = 0;
if (!xen_domain())
return -ENODEV;
xenbus_ring_ops_init();
- if (xen_hvm_domain()) {
- uint64_t v = 0;
+ if (xen_pv_domain())
+ usage = PV;
+ if (xen_hvm_domain())
+ usage = HVM;
+ if (xen_hvm_domain() && xen_initial_domain())
+ usage = LOCAL;
+ if (xen_pv_domain() && !xen_start_info->store_evtchn)
+ usage = LOCAL;
+ if (xen_pv_domain() && xen_start_info->store_evtchn)
+ xenstored_ready = 1;
+
+ switch (usage) {
+ case LOCAL:
+ err = xenstored_local_init();
+ if (err)
+ goto out_error;
+ xen_store_interface = mfn_to_virt(xen_store_mfn);
+ break;
+ case PV:
+ xen_store_evtchn = xen_start_info->store_evtchn;
+ xen_store_mfn = xen_start_info->store_mfn;
+ xen_store_interface = mfn_to_virt(xen_store_mfn);
+ break;
+ case HVM:
err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
if (err)
goto out_error;
if (err)
goto out_error;
xen_store_mfn = (unsigned long)v;
- xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
- } else {
- xen_store_evtchn = xen_start_info->store_evtchn;
- xen_store_mfn = xen_start_info->store_mfn;
- if (xen_store_evtchn)
- xenstored_ready = 1;
- else {
- err = xenstored_local_init();
- if (err)
- goto out_error;
- }
- xen_store_interface = mfn_to_virt(xen_store_mfn);
+ xen_store_interface =
+ ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
+ break;
+ default:
+ pr_warn("Xenstore state unknown\n");
+ break;
}
/* Initialize the interface to xenstore. */
#include <xen/xenbus.h>
#include <xen/events.h>
#include <xen/page.h>
+#include <xen/xen.h>
#include <xen/platform_pci.h>
#include <linux/rwsem.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <asm/xen/hypervisor.h>
#include <xen/xenbus.h>
#include <xen/xen.h>
#include "xenbus_comms.h"
{
int err, supported = 0;
- if (!xen_hvm_domain())
+ if (!xen_hvm_domain() || xen_initial_domain())
return;
err = xenbus_scanf(XBT_NIL, "control",
extern void swiotlb_init(int verbose);
extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
extern unsigned long swiotlb_nr_tbl(void);
+extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
/*
* Enumeration for sync targets
/* Determine whether to ignore this IRQ if it is passed to a guest. */
int xen_test_irq_shared(int irq);
+/* initialize Xen IRQ subsystem */
+void xen_init_IRQ(void);
#endif /* _XEN_EVENTS_H */
/* x86: pirq can be used by HVM guests */
#define XENFEAT_hvm_pirqs 10
+/* operation as Dom0 is supported */
+#define XENFEAT_dom0 11
+
#define XENFEAT_NR_SUBMAPS 1
#endif /* __XEN_PUBLIC_FEATURES_H__ */
#define GNTTABOP_transfer 4
struct gnttab_transfer {
/* IN parameters. */
- unsigned long mfn;
+ xen_pfn_t mfn;
domid_t domid;
grant_ref_t ref;
/* OUT parameters. */
struct {
union {
grant_ref_t ref;
- unsigned long gmfn;
+ xen_pfn_t gmfn;
} u;
domid_t domid;
uint16_t offset;
#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */
#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */
#define GNTST_bad_page (-9) /* Specified page was invalid for op. */
-#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary */
+#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */
+#define GNTST_address_too_big (-11) /* transfer page address too large. */
+#define GNTST_eagain (-12) /* Operation not done; try again. */
#define GNTTABOP_error_msgs { \
"okay", \
"no spare translation slot in the I/O MMU", \
"permission denied", \
"bad page", \
- "copy arguments cross page boundary" \
+ "copy arguments cross page boundary", \
+ "page address size too large", \
+ "operation not done; try again" \
}
#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */
#define XEN_IO_PROTO_ABI_X86_64 "x86_64-abi"
#define XEN_IO_PROTO_ABI_IA64 "ia64-abi"
#define XEN_IO_PROTO_ABI_POWERPC64 "powerpc64-abi"
+#define XEN_IO_PROTO_ABI_ARM "arm-abi"
#if defined(__i386__)
# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32
# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_IA64
#elif defined(__powerpc64__)
# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_POWERPC64
+#elif defined(__arm__)
+# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM
#else
# error arch fixup needed here
#endif
* OUT: GMFN bases of extents that were allocated
* (NB. This command also updates the mach_to_phys translation table)
*/
- GUEST_HANDLE(ulong) extent_start;
+ GUEST_HANDLE(xen_pfn_t) extent_start;
/* Number of extents, and size/alignment of each (2^extent_order pages). */
- unsigned long nr_extents;
+ xen_ulong_t nr_extents;
unsigned int extent_order;
/*
* command will be non-zero.
* 5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER!
*/
- unsigned long nr_exchanged;
+ xen_ulong_t nr_exchanged;
};
DEFINE_GUEST_HANDLE_STRUCT(xen_memory_exchange);
* any large discontiguities in the machine address space, 2MB gaps in
* the machphys table will be represented by an MFN base of zero.
*/
- GUEST_HANDLE(ulong) extent_start;
+ GUEST_HANDLE(xen_pfn_t) extent_start;
/*
* Number of extents written to the above array. This will be smaller
*/
#define XENMEM_machphys_mapping 12
struct xen_machphys_mapping {
- unsigned long v_start, v_end; /* Start and end virtual addresses. */
- unsigned long max_mfn; /* Maximum MFN that can be looked up. */
+ xen_ulong_t v_start, v_end; /* Start and end virtual addresses. */
+ xen_ulong_t max_mfn; /* Maximum MFN that can be looked up. */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t);
/* Which domain to change the mapping for. */
domid_t domid;
+ /* Number of pages to go through for gmfn_range */
+ uint16_t size;
+
/* Source mapping space. */
#define XENMAPSPACE_shared_info 0 /* shared info page */
#define XENMAPSPACE_grant_table 1 /* grant table page */
unsigned int space;
/* Index into source mapping space. */
- unsigned long idx;
+ xen_ulong_t idx;
/* GPFN where the source mapping page should appear. */
- unsigned long gpfn;
+ xen_pfn_t gpfn;
};
DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap);
domid_t domid;
/* Length of list. */
- unsigned long nr_gpfns;
+ xen_ulong_t nr_gpfns;
/* List of GPFNs to translate. */
GUEST_HANDLE(ulong) gpfn_list;
#define PHYSDEVOP_pirq_eoi_gmfn_v2 28
struct physdev_pirq_eoi_gmfn {
/* IN */
- unsigned long gmfn;
+ xen_ulong_t gmfn;
};
/*
#define XENPF_add_memtype 31
struct xenpf_add_memtype {
/* IN variables. */
- unsigned long mfn;
+ xen_pfn_t mfn;
uint64_t nr_mfns;
uint32_t type;
/* OUT variables. */
/* IN variables. */
uint32_t reg;
/* OUT variables. */
- unsigned long mfn;
+ xen_pfn_t mfn;
uint64_t nr_mfns;
uint32_t type;
};
#define XEN_FW_DISK_INFO 1 /* from int 13 AH=08/41/48 */
#define XEN_FW_DISK_MBR_SIGNATURE 2 /* from MBR offset 0x1b8 */
#define XEN_FW_VBEDDC_INFO 3 /* from int 10 AX=4f15 */
+#define XEN_FW_KBD_SHIFT_FLAGS 5 /* Int16, Fn02: Get keyboard shift flags. */
struct xenpf_firmware_info {
/* IN variables. */
uint32_t type;
/* must refer to 128-byte buffer */
GUEST_HANDLE(uchar) edid;
} vbeddc_info; /* XEN_FW_VBEDDC_INFO */
+
+ uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */
} u;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_firmware_info_t);
#define XENVER_platform_parameters 5
struct xen_platform_parameters {
- unsigned long virt_start;
+ xen_ulong_t virt_start;
};
#define XENVER_get_features 6
/* arg == NULL; returns host memory page size. */
#define XENVER_pagesize 7
+/* arg == xen_domain_handle_t. */
+#define XENVER_guest_handle 8
+
#endif /* __XEN_PUBLIC_VERSION_H__ */
#define __XEN_PUBLIC_XEN_H__
#include <asm/xen/interface.h>
-#include <asm/pvclock-abi.h>
/*
* XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
unsigned int cmd;
union {
/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */
- unsigned long mfn;
+ xen_pfn_t mfn;
/* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
unsigned long linear_addr;
} arg1;
unsigned long nr_pages; /* Total pages allocated to this domain. */
unsigned long shared_info; /* MACHINE address of shared info struct. */
uint32_t flags; /* SIF_xxx flags. */
- unsigned long store_mfn; /* MACHINE page number of shared page. */
+ xen_pfn_t store_mfn; /* MACHINE page number of shared page. */
uint32_t store_evtchn; /* Event channel for store communication. */
union {
struct {
- unsigned long mfn; /* MACHINE page number of console page. */
+ xen_pfn_t mfn; /* MACHINE page number of console page. */
uint32_t evtchn; /* Event channel for console page. */
} domU;
struct {
uint8_t video_type;
#define XEN_VGATYPE_TEXT_MODE_3 0x03
#define XEN_VGATYPE_VESA_LFB 0x23
+#define XEN_VGATYPE_EFI_LFB 0x70
union {
struct {
#include <linux/types.h>
#include <linux/compiler.h>
-
-typedef unsigned long xen_pfn_t;
+#include <xen/interface/xen.h>
struct privcmd_hypercall {
__u64 op;
int num; /* number of pages to populate */
domid_t dom; /* target domain */
__u64 addr; /* virtual address */
- xen_pfn_t __user *arr; /* array of mfns - top nibble set on err */
+ xen_pfn_t __user *arr; /* array of mfns - or'd with
+ PRIVCMD_MMAPBATCH_*_ERROR on err */
+};
+
+#define PRIVCMD_MMAPBATCH_MFN_ERROR 0xf0000000U
+#define PRIVCMD_MMAPBATCH_PAGED_ERROR 0x80000000U
+
+struct privcmd_mmapbatch_v2 {
+ unsigned int num; /* number of pages to populate */
+ domid_t dom; /* target domain */
+ __u64 addr; /* virtual address */
+ const xen_pfn_t __user *arr; /* array of mfns */
+ int __user *err; /* array of error codes */
};
/*
* @cmd: IOCTL_PRIVCMD_HYPERCALL
* @arg: &privcmd_hypercall_t
* Return: Value returned from execution of the specified hypercall.
+ *
+ * @cmd: IOCTL_PRIVCMD_MMAPBATCH_V2
+ * @arg: &struct privcmd_mmapbatch_v2
+ * Return: 0 on success (i.e., arg->err contains valid error codes for
+ * each frame). On an error other than a failed frame remap, -1 is
+ * returned and errno is set to EINVAL, EFAULT etc. As an exception,
+ * if the operation was otherwise successful but any frame failed with
+ * -ENOENT, then -1 is returned and errno is set to ENOENT.
*/
#define IOCTL_PRIVCMD_HYPERCALL \
_IOC(_IOC_NONE, 'P', 0, sizeof(struct privcmd_hypercall))
_IOC(_IOC_NONE, 'P', 2, sizeof(struct privcmd_mmap))
#define IOCTL_PRIVCMD_MMAPBATCH \
_IOC(_IOC_NONE, 'P', 3, sizeof(struct privcmd_mmapbatch))
+#define IOCTL_PRIVCMD_MMAPBATCH_V2 \
+ _IOC(_IOC_NONE, 'P', 4, sizeof(struct privcmd_mmapbatch_v2))
#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */
#include <linux/swiotlb.h>
-extern void xen_swiotlb_init(int verbose);
+extern int xen_swiotlb_init(int verbose, bool early);
extern void
*xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
extern void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs);
-/*
-extern int
-xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir);
-
-extern void
-xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir);
-*/
extern int
xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
int nelems, enum dma_data_direction dir,
#include <xen/interface/xen.h>
#include <asm/xen/hypervisor.h>
-#define xen_initial_domain() (xen_pv_domain() && \
+#define xen_initial_domain() (xen_domain() && \
xen_start_info->flags & SIF_INITDOMAIN)
#else /* !CONFIG_XEN_DOM0 */
#define xen_initial_domain() (0)
* Statically reserve bounce buffer space and initialize bounce buffer data
* structures for the software IO TLB used to implement the DMA API.
*/
-void __init
+static void __init
swiotlb_init_with_default_size(size_t default_size, int verbose)
{
unsigned long bytes;
int
swiotlb_late_init_with_default_size(size_t default_size)
{
- unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
+ unsigned long bytes, req_nslabs = io_tlb_nslabs;
unsigned int order;
+ int rc = 0;
if (!io_tlb_nslabs) {
io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
order--;
}
- if (!io_tlb_start)
- goto cleanup1;
-
+ if (!io_tlb_start) {
+ io_tlb_nslabs = req_nslabs;
+ return -ENOMEM;
+ }
if (order != get_order(bytes)) {
printk(KERN_WARNING "Warning: only able to allocate %ld MB "
"for software IO TLB\n", (PAGE_SIZE << order) >> 20);
io_tlb_nslabs = SLABS_PER_PAGE << order;
- bytes = io_tlb_nslabs << IO_TLB_SHIFT;
}
+ rc = swiotlb_late_init_with_tbl(io_tlb_start, io_tlb_nslabs);
+ if (rc)
+ free_pages((unsigned long)io_tlb_start, order);
+ return rc;
+}
+
+int
+swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
+{
+ unsigned long i, bytes;
+
+ bytes = nslabs << IO_TLB_SHIFT;
+
+ io_tlb_nslabs = nslabs;
+ io_tlb_start = tlb;
io_tlb_end = io_tlb_start + bytes;
+
memset(io_tlb_start, 0, bytes);
/*
io_tlb_list = NULL;
cleanup2:
io_tlb_end = NULL;
- free_pages((unsigned long)io_tlb_start, order);
io_tlb_start = NULL;
-cleanup1:
- io_tlb_nslabs = req_nslabs;
+ io_tlb_nslabs = 0;
return -ENOMEM;
}