diff options
Diffstat (limited to 'include/xen')
66 files changed, 7531 insertions, 1232 deletions
diff --git a/include/xen/acpi.h b/include/xen/acpi.h index 46aa3d1c1654..c66a8461612e 100644 --- a/include/xen/acpi.h +++ b/include/xen/acpi.h @@ -35,48 +35,17 @@ #include <linux/types.h> +typedef int (*get_gsi_from_sbdf_t)(u32 sbdf); + #ifdef CONFIG_XEN_DOM0 #include <asm/xen/hypervisor.h> #include <xen/xen.h> #include <linux/acpi.h> -#define ACPI_MEMORY_DEVICE_CLASS "memory" -#define ACPI_MEMORY_DEVICE_HID "PNP0C80" -#define ACPI_MEMORY_DEVICE_NAME "Hotplug Mem Device" - -int xen_stub_memory_device_init(void); -void xen_stub_memory_device_exit(void); - -#define ACPI_PROCESSOR_CLASS "processor" -#define ACPI_PROCESSOR_DEVICE_HID "ACPI0007" -#define ACPI_PROCESSOR_DEVICE_NAME "Processor" - -int xen_stub_processor_init(void); -void xen_stub_processor_exit(void); - -void xen_pcpu_hotplug_sync(void); -int xen_pcpu_id(uint32_t acpi_id); - -static inline int xen_acpi_get_pxm(acpi_handle h) -{ - unsigned long long pxm; - acpi_status status; - acpi_handle handle; - acpi_handle phandle = h; - - do { - handle = phandle; - status = acpi_evaluate_integer(handle, "_PXM", NULL, &pxm); - if (ACPI_SUCCESS(status)) - return pxm; - status = acpi_get_parent(handle, &phandle); - } while (ACPI_SUCCESS(status)); - - return -ENXIO; -} - -int xen_acpi_notify_hypervisor_state(u8 sleep_state, +int xen_acpi_notify_hypervisor_sleep(u8 sleep_state, u32 pm1a_cnt, u32 pm1b_cnd); +int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state, + u32 val_a, u32 val_b); static inline int xen_acpi_suspend_lowlevel(void) { @@ -93,15 +62,46 @@ static inline void xen_acpi_sleep_register(void) { if (xen_initial_domain()) { acpi_os_set_prepare_sleep( - &xen_acpi_notify_hypervisor_state); + &xen_acpi_notify_hypervisor_sleep); + acpi_os_set_prepare_extended_sleep( + &xen_acpi_notify_hypervisor_extended_sleep); acpi_suspend_lowlevel = xen_acpi_suspend_lowlevel; } } +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity); +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out); +void xen_acpi_register_get_gsi_func(get_gsi_from_sbdf_t func); +int xen_acpi_get_gsi_from_sbdf(u32 sbdf); #else static inline void xen_acpi_sleep_register(void) { } + +static inline int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + return -1; +} + +static inline int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + return -1; +} + +static inline void xen_acpi_register_get_gsi_func(get_gsi_from_sbdf_t func) +{ +} + +static inline int xen_acpi_get_gsi_from_sbdf(u32 sbdf) +{ + return -1; +} #endif #endif /* _XEN_ACPI_H */ diff --git a/include/xen/arm/hypercall.h b/include/xen/arm/hypercall.h new file mode 100644 index 000000000000..9d7dd1c65a21 --- /dev/null +++ b/include/xen/arm/hypercall.h @@ -0,0 +1,76 @@ +/****************************************************************************** + * 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 <linux/bug.h> + +#include <xen/interface/xen.h> +#include <xen/interface/sched.h> +#include <xen/interface/platform.h> + +struct xen_dm_op_buf; + +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); +int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); +int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type); +int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs, + struct xen_dm_op_buf *bufs); +int HYPERVISOR_platform_op_raw(void *arg); +static inline int HYPERVISOR_platform_op(struct xen_platform_op *op) +{ + op->interface_version = XENPF_INTERFACE_VERSION; + return HYPERVISOR_platform_op_raw(op); +} +int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr); + +static inline int +HYPERVISOR_suspend(unsigned long start_info_mfn) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* start_info_mfn is unused on ARM */ + return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); +} + +#endif /* _ASM_ARM_XEN_HYPERCALL_H */ diff --git a/include/xen/arm/hypervisor.h b/include/xen/arm/hypervisor.h new file mode 100644 index 000000000000..9995695204f5 --- /dev/null +++ b/include/xen/arm/hypervisor.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_XEN_HYPERVISOR_H +#define _ASM_ARM_XEN_HYPERVISOR_H + +#include <linux/init.h> + +extern struct shared_info *HYPERVISOR_shared_info; +extern struct start_info *xen_start_info; + +#ifdef CONFIG_XEN +void __init xen_early_init(void); +#else +static inline void xen_early_init(void) { return; } +#endif + +#ifdef CONFIG_HOTPLUG_CPU +static inline void xen_arch_register_cpu(int num) +{ +} + +static inline void xen_arch_unregister_cpu(int num) +{ +} +#endif + +#endif /* _ASM_ARM_XEN_HYPERVISOR_H */ diff --git a/include/xen/arm/interface.h b/include/xen/arm/interface.h new file mode 100644 index 000000000000..c3eada2642aa --- /dev/null +++ b/include/xen/arm/interface.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/****************************************************************************** + * 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) + +#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op + +#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. + * Note that this means that the xen_pfn_t type may be capable of + * representing pfn's which the guest cannot represent in its own pfn + * type. However since pfn space is controlled by the guest this is + * fine since it simply wouldn't be able to create any sure pfns in + * the first place. + */ +typedef uint64_t xen_pfn_t; +#define PRI_xen_pfn "llx" +typedef uint64_t xen_ulong_t; +#define PRI_xen_ulong "llx" +typedef int64_t xen_long_t; +#define PRI_xen_long "llx" +/* Guest handles for primitive C types. */ +__DEFINE_GUEST_HANDLE(uchar, unsigned char); +__DEFINE_GUEST_HANDLE(uint, unsigned int); +DEFINE_GUEST_HANDLE(char); +DEFINE_GUEST_HANDLE(int); +DEFINE_GUEST_HANDLE(void); +DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); +DEFINE_GUEST_HANDLE(xen_pfn_t); +DEFINE_GUEST_HANDLE(xen_ulong_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; + u32 sec_hi; +} __attribute__((__packed__)); +#endif + +#endif /* _ASM_ARM_XEN_INTERFACE_H */ diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h new file mode 100644 index 000000000000..e5c84ff28c8b --- /dev/null +++ b/include/xen/arm/page.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_XEN_PAGE_H +#define _ASM_ARM_XEN_PAGE_H + +#include <asm/page.h> + +#include <linux/pfn.h> +#include <linux/types.h> +#include <linux/dma-mapping.h> +#include <linux/pgtable.h> + +#include <xen/xen.h> +#include <xen/interface/grant_table.h> + +#define phys_to_machine_mapping_valid(pfn) (1) + +/* 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) }) + +#define INVALID_P2M_ENTRY (~0UL) + +/* + * The pseudo-physical frame (pfn) used in all the helpers is always based + * on Xen page granularity (i.e 4KB). + * + * A Linux page may be split across multiple non-contiguous Xen page so we + * have to keep track with frame based on 4KB page granularity. + * + * PV drivers should never make a direct usage of those helpers (particularly + * pfn_to_gfn and gfn_to_pfn). + */ + +unsigned long __pfn_to_mfn(unsigned long pfn); +extern struct rb_root phys_to_mach; + +/* Pseudo-physical <-> Guest conversion */ +static inline unsigned long pfn_to_gfn(unsigned long pfn) +{ + return pfn; +} + +static inline unsigned long gfn_to_pfn(unsigned long gfn) +{ + return gfn; +} + +/* Pseudo-physical <-> BUS conversion */ +static inline unsigned long pfn_to_bfn(unsigned long pfn) +{ + unsigned long mfn; + + if (phys_to_mach.rb_node != NULL) { + mfn = __pfn_to_mfn(pfn); + if (mfn != INVALID_P2M_ENTRY) + return mfn; + } + + return pfn; +} + +static inline unsigned long bfn_to_pfn(unsigned long bfn) +{ + return bfn; +} + +#define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) + +/* VIRT <-> GUEST conversion */ +#define virt_to_gfn(v) \ + ({ \ + WARN_ON_ONCE(!virt_addr_valid(v)); \ + pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT); \ + }) +#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) + +#define percpu_to_gfn(v) \ + (pfn_to_gfn(per_cpu_ptr_to_phys(v) >> XEN_PAGE_SHIFT)) + +/* Only used in PV code. But ARM guests are always HVM. */ +static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) +{ + BUG(); +} + +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); + +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, + struct page **pages, unsigned int count); + +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, + unsigned long nr_pages); + +static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + return __set_phys_to_machine(pfn, mfn); +} + +bool xen_arch_need_swiotlb(struct device *dev, + phys_addr_t phys, + dma_addr_t dev_addr); + +#endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/include/xen/arm/swiotlb-xen.h b/include/xen/arm/swiotlb-xen.h new file mode 100644 index 000000000000..33336ab58afc --- /dev/null +++ b/include/xen/arm/swiotlb-xen.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_SWIOTLB_XEN_H +#define _ASM_ARM_SWIOTLB_XEN_H + +#include <xen/features.h> +#include <xen/xen.h> + +static inline int xen_swiotlb_detect(void) +{ + if (!xen_domain()) + return 0; + if (xen_feature(XENFEAT_direct_mapped)) + return 1; + /* legacy case */ + if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain()) + return 1; + return 0; +} + +#endif /* _ASM_ARM_SWIOTLB_XEN_H */ diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h new file mode 100644 index 000000000000..70073f5a2b54 --- /dev/null +++ b/include/xen/arm/xen-ops.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_XEN_OPS_H +#define _ASM_ARM_XEN_OPS_H + +#include <xen/swiotlb-xen.h> +#include <xen/xen-ops.h> + +static inline void xen_setup_dma_ops(struct device *dev) +{ +#ifdef CONFIG_XEN + if (xen_swiotlb_detect()) + dev->dma_ops = &xen_swiotlb_dma_ops; +#endif +} + +#endif /* _ASM_ARM_XEN_OPS_H */ diff --git a/include/xen/balloon.h b/include/xen/balloon.h index cc2e1a7e44ec..f78a6cc94f1a 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -1,6 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /****************************************************************************** * Xen balloon functionality */ +#ifndef _XEN_BALLOON_H +#define _XEN_BALLOON_H #define RETRY_UNLIMITED 0 @@ -8,33 +11,30 @@ struct balloon_stats { /* We aim for 'current allocation' == 'target allocation'. */ unsigned long current_pages; unsigned long target_pages; + unsigned long target_unpopulated; /* Number of pages in high- and low-memory balloons. */ unsigned long balloon_low; unsigned long balloon_high; + unsigned long total_pages; unsigned long schedule_delay; unsigned long max_schedule_delay; unsigned long retry_count; unsigned long max_retry_count; -#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG - unsigned long hotplug_pages; - unsigned long balloon_hotplug; -#endif }; extern struct balloon_stats balloon_stats; void balloon_set_new_target(unsigned long target); -int alloc_xenballooned_pages(int nr_pages, struct page **pages, - bool highmem); -void free_xenballooned_pages(int nr_pages, struct page **pages); +int xen_alloc_ballooned_pages(unsigned int nr_pages, struct page **pages); +void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages); -struct device; -#ifdef CONFIG_XEN_SELFBALLOONING -extern int register_xen_selfballooning(struct device *dev); +#ifdef CONFIG_XEN_BALLOON +void xen_balloon_init(void); #else -static inline int register_xen_selfballooning(struct device *dev) +static inline void xen_balloon_init(void) { - return -ENOSYS; } #endif + +#endif /* _XEN_BALLOON_H */ diff --git a/include/xen/events.h b/include/xen/events.h index c9ea10ee2273..de5da58a0205 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -1,18 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_EVENTS_H #define _XEN_EVENTS_H #include <linux/interrupt.h> +#include <linux/irq.h> +#ifdef CONFIG_PCI_MSI +#include <linux/msi.h> +#endif #include <xen/interface/event_channel.h> #include <asm/xen/hypercall.h> #include <asm/xen/events.h> -int bind_evtchn_to_irq(unsigned int evtchn); -int bind_evtchn_to_irqhandler(unsigned int evtchn, +struct xenbus_device; + +unsigned xen_evtchn_nr_channels(void); + +int bind_evtchn_to_irq(evtchn_port_t evtchn); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn); +int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); +int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); -int bind_virq_to_irq(unsigned int virq, unsigned int cpu); +int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu); int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, @@ -23,12 +37,14 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, unsigned long irqflags, const char *devname, void *dev_id); -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - unsigned int remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id); +int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev, + evtchn_port_t remote_port); +int bind_interdomain_evtchn_to_irqhandler_lateeoi(struct xenbus_device *dev, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); /* * Common unbind function for all event sources. Takes IRQ to unbind from. @@ -38,17 +54,29 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, void unbind_from_irqhandler(unsigned int irq, void *dev_id); /* + * Send late EOI for an IRQ bound to an event channel via one of the *_lateeoi + * functions above. + */ +void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags); +/* Signal an event was spurious, i.e. there was no action resulting from it. */ +#define XEN_EOI_FLAG_SPURIOUS 0x00000001 + +#define XEN_IRQ_PRIORITY_MAX EVTCHN_FIFO_PRIORITY_MAX +#define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT +#define XEN_IRQ_PRIORITY_MIN EVTCHN_FIFO_PRIORITY_MIN +int xen_set_irq_priority(unsigned irq, unsigned priority); + +/* * Allow extra references to event channels exposed to userspace by evtchn */ -int evtchn_make_refcounted(unsigned int evtchn); -int evtchn_get(unsigned int evtchn); -void evtchn_put(unsigned int evtchn); +int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static); +int evtchn_get(evtchn_port_t evtchn); +void evtchn_put(evtchn_port_t evtchn); void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector); -int resend_irq_on_evtchn(unsigned int irq); -void rebind_evtchn_irq(int evtchn, int irq); +void rebind_evtchn_irq(evtchn_port_t evtchn, int irq); -static inline void notify_remote_via_evtchn(int port) +static inline void notify_remote_via_evtchn(evtchn_port_t port) { struct evtchn_send send = { .port = port }; (void)HYPERVISOR_event_channel_op(EVTCHNOP_send, &send); @@ -60,7 +88,6 @@ void xen_irq_resume(void); /* Clear an irq's pending state, in preparation for polling on it */ void xen_clear_irq_pending(int irq); -void xen_set_irq_pending(int irq); bool xen_test_irq_pending(int irq); /* Poll waiting for an irq to become pending. In the usual case, the @@ -72,17 +99,12 @@ void xen_poll_irq(int irq); void xen_poll_irq_timeout(int irq, u64 timeout); /* Determine the IRQ which is bound to an event channel */ -unsigned irq_from_evtchn(unsigned int evtchn); +unsigned int irq_from_evtchn(evtchn_port_t evtchn); +int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq, + evtchn_port_t *evtchn); -/* Xen HVM evtchn vector callback */ -void xen_hvm_callback_vector(void); -#ifdef CONFIG_TRACING -#define trace_xen_hvm_callback_vector xen_hvm_callback_vector -#endif -extern int xen_have_vector_callback; int xen_set_callback_via(uint64_t via); -void xen_evtchn_do_upcall(struct pt_regs *regs); -void xen_hvm_evtchn_do_upcall(void); +int xen_evtchn_do_upcall(void); /* Bind a pirq for a physical interrupt to an irq. */ int xen_bind_pirq_gsi_to_irq(unsigned gsi, @@ -93,15 +115,12 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi, int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc); /* Bind an PSI pirq to an irq. */ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, const char *name, domid_t domid); + int pirq, int nvec, const char *name, domid_t domid); #endif /* De-allocates the above mentioned physical interrupt. */ int xen_destroy_irq(int irq); -/* Return irq from pirq */ -int xen_irq_from_pirq(unsigned pirq); - /* Return the pirq allocated to the irq. */ int xen_pirq_from_irq(unsigned irq); @@ -113,4 +132,18 @@ int xen_test_irq_shared(int irq); /* initialize Xen IRQ subsystem */ void xen_init_IRQ(void); + +irqreturn_t xen_debug_interrupt(int irq, void *dev_id); + +static inline void xen_evtchn_close(evtchn_port_t port) +{ + struct evtchn_close close; + + close.port = port; + if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) + BUG(); +} + +extern bool xen_fifo_events; + #endif /* _XEN_EVENTS_H */ diff --git a/include/xen/features.h b/include/xen/features.h index 27292d4d2a6a..e4cb464386a9 100644 --- a/include/xen/features.h +++ b/include/xen/features.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /****************************************************************************** * features.h * diff --git a/include/xen/gntalloc.h b/include/xen/gntalloc.h deleted file mode 100644 index 76bd58065f4f..000000000000 --- a/include/xen/gntalloc.h +++ /dev/null @@ -1,82 +0,0 @@ -/****************************************************************************** - * gntalloc.h - * - * Interface to /dev/xen/gntalloc. - * - * Author: Daniel De Graaf <dgdegra@tycho.nsa.gov> - * - * This file is in the public domain. - */ - -#ifndef __LINUX_PUBLIC_GNTALLOC_H__ -#define __LINUX_PUBLIC_GNTALLOC_H__ - -/* - * Allocates a new page and creates a new grant reference. - */ -#define IOCTL_GNTALLOC_ALLOC_GREF \ -_IOC(_IOC_NONE, 'G', 5, sizeof(struct ioctl_gntalloc_alloc_gref)) -struct ioctl_gntalloc_alloc_gref { - /* IN parameters */ - /* The ID of the domain to be given access to the grants. */ - uint16_t domid; - /* Flags for this mapping */ - uint16_t flags; - /* Number of pages to map */ - uint32_t count; - /* OUT parameters */ - /* The offset to be used on a subsequent call to mmap(). */ - uint64_t index; - /* The grant references of the newly created grant, one per page */ - /* Variable size, depending on count */ - uint32_t gref_ids[1]; -}; - -#define GNTALLOC_FLAG_WRITABLE 1 - -/* - * Deallocates the grant reference, allowing the associated page to be freed if - * no other domains are using it. - */ -#define IOCTL_GNTALLOC_DEALLOC_GREF \ -_IOC(_IOC_NONE, 'G', 6, sizeof(struct ioctl_gntalloc_dealloc_gref)) -struct ioctl_gntalloc_dealloc_gref { - /* IN parameters */ - /* The offset returned in the map operation */ - uint64_t index; - /* Number of references to unmap */ - uint32_t count; -}; - -/* - * Sets up an unmap notification within the page, so that the other side can do - * cleanup if this side crashes. Required to implement cross-domain robust - * mutexes or close notification on communication channels. - * - * Each mapped page only supports one notification; multiple calls referring to - * the same page overwrite the previous notification. You must clear the - * notification prior to the IOCTL_GNTALLOC_DEALLOC_GREF if you do not want it - * to occur. - */ -#define IOCTL_GNTALLOC_SET_UNMAP_NOTIFY \ -_IOC(_IOC_NONE, 'G', 7, sizeof(struct ioctl_gntalloc_unmap_notify)) -struct ioctl_gntalloc_unmap_notify { - /* IN parameters */ - /* Offset in the file descriptor for a byte within the page (same as - * used in mmap). If using UNMAP_NOTIFY_CLEAR_BYTE, this is the byte to - * be cleared. Otherwise, it can be any byte in the page whose - * notification we are adjusting. - */ - uint64_t index; - /* Action(s) to take on unmap */ - uint32_t action; - /* Event channel to notify */ - uint32_t event_channel_port; -}; - -/* Clear (set to zero) the byte specified by index */ -#define UNMAP_NOTIFY_CLEAR_BYTE 0x1 -/* Send an interrupt on the indicated event channel */ -#define UNMAP_NOTIFY_SEND_EVENT 0x2 - -#endif /* __LINUX_PUBLIC_GNTALLOC_H__ */ diff --git a/include/xen/gntdev.h b/include/xen/gntdev.h deleted file mode 100644 index 5304bd3c84c5..000000000000 --- a/include/xen/gntdev.h +++ /dev/null @@ -1,150 +0,0 @@ -/****************************************************************************** - * gntdev.h - * - * Interface to /dev/xen/gntdev. - * - * Copyright (c) 2007, D G Murray - * - * 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 __LINUX_PUBLIC_GNTDEV_H__ -#define __LINUX_PUBLIC_GNTDEV_H__ - -struct ioctl_gntdev_grant_ref { - /* The domain ID of the grant to be mapped. */ - uint32_t domid; - /* The grant reference of the grant to be mapped. */ - uint32_t ref; -}; - -/* - * Inserts the grant references into the mapping table of an instance - * of gntdev. N.B. This does not perform the mapping, which is deferred - * until mmap() is called with @index as the offset. - */ -#define IOCTL_GNTDEV_MAP_GRANT_REF \ -_IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref)) -struct ioctl_gntdev_map_grant_ref { - /* IN parameters */ - /* The number of grants to be mapped. */ - uint32_t count; - uint32_t pad; - /* OUT parameters */ - /* The offset to be used on a subsequent call to mmap(). */ - uint64_t index; - /* Variable IN parameter. */ - /* Array of grant references, of size @count. */ - struct ioctl_gntdev_grant_ref refs[1]; -}; - -/* - * Removes the grant references from the mapping table of an instance of - * of gntdev. N.B. munmap() must be called on the relevant virtual address(es) - * before this ioctl is called, or an error will result. - */ -#define IOCTL_GNTDEV_UNMAP_GRANT_REF \ -_IOC(_IOC_NONE, 'G', 1, sizeof(struct ioctl_gntdev_unmap_grant_ref)) -struct ioctl_gntdev_unmap_grant_ref { - /* IN parameters */ - /* The offset was returned by the corresponding map operation. */ - uint64_t index; - /* The number of pages to be unmapped. */ - uint32_t count; - uint32_t pad; -}; - -/* - * Returns the offset in the driver's address space that corresponds - * to @vaddr. This can be used to perform a munmap(), followed by an - * UNMAP_GRANT_REF ioctl, where no state about the offset is retained by - * the caller. The number of pages that were allocated at the same time as - * @vaddr is returned in @count. - * - * N.B. Where more than one page has been mapped into a contiguous range, the - * supplied @vaddr must correspond to the start of the range; otherwise - * an error will result. It is only possible to munmap() the entire - * contiguously-allocated range at once, and not any subrange thereof. - */ -#define IOCTL_GNTDEV_GET_OFFSET_FOR_VADDR \ -_IOC(_IOC_NONE, 'G', 2, sizeof(struct ioctl_gntdev_get_offset_for_vaddr)) -struct ioctl_gntdev_get_offset_for_vaddr { - /* IN parameters */ - /* The virtual address of the first mapped page in a range. */ - uint64_t vaddr; - /* OUT parameters */ - /* The offset that was used in the initial mmap() operation. */ - uint64_t offset; - /* The number of pages mapped in the VM area that begins at @vaddr. */ - uint32_t count; - uint32_t pad; -}; - -/* - * Sets the maximum number of grants that may mapped at once by this gntdev - * instance. - * - * N.B. This must be called before any other ioctl is performed on the device. - */ -#define IOCTL_GNTDEV_SET_MAX_GRANTS \ -_IOC(_IOC_NONE, 'G', 3, sizeof(struct ioctl_gntdev_set_max_grants)) -struct ioctl_gntdev_set_max_grants { - /* IN parameter */ - /* The maximum number of grants that may be mapped at once. */ - uint32_t count; -}; - -/* - * Sets up an unmap notification within the page, so that the other side can do - * cleanup if this side crashes. Required to implement cross-domain robust - * mutexes or close notification on communication channels. - * - * Each mapped page only supports one notification; multiple calls referring to - * the same page overwrite the previous notification. You must clear the - * notification prior to the IOCTL_GNTALLOC_DEALLOC_GREF if you do not want it - * to occur. - */ -#define IOCTL_GNTDEV_SET_UNMAP_NOTIFY \ -_IOC(_IOC_NONE, 'G', 7, sizeof(struct ioctl_gntdev_unmap_notify)) -struct ioctl_gntdev_unmap_notify { - /* IN parameters */ - /* Offset in the file descriptor for a byte within the page (same as - * used in mmap). If using UNMAP_NOTIFY_CLEAR_BYTE, this is the byte to - * be cleared. Otherwise, it can be any byte in the page whose - * notification we are adjusting. - */ - uint64_t index; - /* Action(s) to take on unmap */ - uint32_t action; - /* Event channel to notify */ - uint32_t event_channel_port; -}; - -/* Clear (set to zero) the byte specified by index */ -#define UNMAP_NOTIFY_CLEAR_BYTE 0x1 -/* Send an interrupt on the indicated event channel */ -#define UNMAP_NOTIFY_SEND_EVENT 0x2 - -#endif /* __LINUX_PUBLIC_GNTDEV_H__ */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 694dcaf266e6..69ac6d80a006 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -45,8 +45,17 @@ #include <asm/xen/hypervisor.h> #include <xen/features.h> +#include <xen/page.h> +#include <linux/mm_types.h> +#include <linux/page-flags.h> +#include <linux/kernel.h> -#define GNTTAB_RESERVED_XENSTORE 1 +/* + * Technically there's no reliably invalid grant reference or grant handle, + * so pick the value that is the most unlikely one to be observed valid. + */ +#define INVALID_GRANT_REF ((grant_ref_t)-1) +#define INVALID_GRANT_HANDLE ((grant_handle_t)-1) /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 @@ -58,63 +67,74 @@ struct gnttab_free_callback { u16 count; }; +struct gntab_unmap_queue_data; + +typedef void (*gnttab_unmap_refs_done)(int result, struct gntab_unmap_queue_data *data); + +struct gntab_unmap_queue_data +{ + struct delayed_work gnttab_work; + void *data; + gnttab_unmap_refs_done done; + struct gnttab_unmap_grant_ref *unmap_ops; + struct gnttab_unmap_grant_ref *kunmap_ops; + struct page **pages; + unsigned int count; + unsigned int age; +}; + int gnttab_init(void); int gnttab_suspend(void); int gnttab_resume(void); int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame, - int flags, unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans(domid_t domid, int flags, - domid_t trans_domid, - grant_ref_t trans_gref); - -/* - * Are sub-page grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_subpage_grants_available(void); - -/* - * Are transitive grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_trans_grants_available(void); /* * End access through the given grant reference, iff the grant entry is no * longer in use. Return 1 if the grant entry was freed, 0 if it is still in * use. */ -int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); +int gnttab_end_foreign_access_ref(grant_ref_t ref); /* * Eventually end access through the given grant reference, and once that * access has been ended, free the given page too. Access will be ended * immediately iff the grant entry is not in use, otherwise it will happen - * some time later. page may be 0, in which case no freeing will occur. + * some time later. page may be NULL, in which case no freeing will occur. + * Note that the granted page might still be accessed (read or write) by the + * other side after gnttab_end_foreign_access() returns, so even if page was + * specified as NULL it is not allowed to just reuse the page for other + * purposes immediately. gnttab_end_foreign_access() will take an additional + * reference to the granted page in this case, which is dropped only after + * the grant is no longer in use. + * This requires that multi page allocations for areas subject to + * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing + * via free_pages_exact()) in order to avoid high order pages. */ -void gnttab_end_foreign_access(grant_ref_t ref, int readonly, - unsigned long page); - -int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); - -unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); -unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); +void gnttab_end_foreign_access(grant_ref_t ref, struct page *page); -int gnttab_query_foreign_access(grant_ref_t ref); +/* + * End access through the given grant reference, iff the grant entry is + * no longer in use. In case of success ending foreign access, the + * grant reference is deallocated. + * Return 1 if the grant entry was freed, 0 if it is still in use. + */ +int gnttab_try_end_foreign_access(grant_ref_t ref); /* * operations on reserved batches of grant references */ int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); +int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first); + void gnttab_free_grant_reference(grant_ref_t ref); void gnttab_free_grant_references(grant_ref_t head); +void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count); + int gnttab_empty_grant_references(const grant_ref_t *pprivate_head); int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); @@ -128,16 +148,15 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback); void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref); -void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, - unsigned long pfn); +/* Give access to the first 4K of the page */ +static inline void gnttab_page_grant_foreign_access_ref_one( + grant_ref_t ref, domid_t domid, + struct page *page, int readonly) +{ + gnttab_grant_foreign_access_ref(ref, domid, xen_page_to_gfn(page), + readonly); +} static inline void gnttab_set_map_op(struct gnttab_map_grant_ref *map, phys_addr_t addr, @@ -145,7 +164,7 @@ gnttab_set_map_op(struct gnttab_map_grant_ref *map, phys_addr_t addr, { if (flags & GNTMAP_contains_pte) map->host_addr = addr; - else if (xen_feature(XENFEAT_auto_translated_physmap)) + else if (!xen_pv_domain()) map->host_addr = __pa(addr); else map->host_addr = addr; @@ -153,6 +172,7 @@ gnttab_set_map_op(struct gnttab_map_grant_ref *map, phys_addr_t addr, map->flags = flags; map->ref = ref; map->dom = domid; + map->status = 1; /* arbitrary positive value */ } static inline void @@ -161,7 +181,7 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, { if (flags & GNTMAP_contains_pte) unmap->host_addr = addr; - else if (xen_feature(XENFEAT_auto_translated_physmap)) + else if (!xen_pv_domain()) unmap->host_addr = __pa(addr); else unmap->host_addr = addr; @@ -170,6 +190,7 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, unmap->dev_bus_addr = 0; } +int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status); int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, void **__shared); @@ -178,17 +199,68 @@ int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, grant_status_t **__shared); void arch_gnttab_unmap(void *shared, unsigned long nr_gframes); -extern unsigned long xen_hvm_resume_frames; +struct grant_frames { + xen_pfn_t *pfn; + unsigned int count; + void *vaddr; +}; +extern struct grant_frames xen_auto_xlat_grant_frames; unsigned int gnttab_max_grant_frames(void); +int gnttab_setup_auto_xlat_frames(phys_addr_t addr); +void gnttab_free_auto_xlat_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) +int gnttab_alloc_pages(int nr_pages, struct page **pages); +void gnttab_free_pages(int nr_pages, struct page **pages); + +struct gnttab_page_cache { + spinlock_t lock; +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC + struct page *pages; +#else + struct list_head pages; +#endif + unsigned int num_pages; +}; + +void gnttab_page_cache_init(struct gnttab_page_cache *cache); +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page); +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num); +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, + unsigned int num); + +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC +struct gnttab_dma_alloc_args { + /* Device for which DMA memory will be/was allocated. */ + struct device *dev; + /* If set then DMA buffer is coherent and write-combine otherwise. */ + bool coherent; + + int nr_pages; + struct page **pages; + xen_pfn_t *frames; + void *vaddr; + dma_addr_t dev_bus_addr; +}; + +int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args); +int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args); +#endif + +int gnttab_pages_set_private(int nr_pages, struct page **pages); +void gnttab_pages_clear_private(int nr_pages, struct page **pages); + int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kunmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count); +void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item); +int gnttab_unmap_refs_sync(struct gntab_unmap_queue_data *item); + /* Perform a batch of grant map/copy operations. Retry every batch slot * for which the hypervisor returns GNTST_eagain. This is typically due @@ -202,4 +274,68 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, void gnttab_batch_map(struct gnttab_map_grant_ref *batch, unsigned count); void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count); + +struct xen_page_foreign { + domid_t domid; + grant_ref_t gref; +}; + +static inline struct xen_page_foreign *xen_page_foreign(struct page *page) +{ + if (!PageForeign(page)) + return NULL; +#if BITS_PER_LONG < 64 + return (struct xen_page_foreign *)page->private; +#else + BUILD_BUG_ON(sizeof(struct xen_page_foreign) > BITS_PER_LONG); + return (struct xen_page_foreign *)&page->private; +#endif +} + +/* Split Linux page in chunk of the size of the grant and call fn + * + * Parameters of fn: + * gfn: guest frame number + * offset: offset in the grant + * len: length of the data in the grant. + * data: internal information + */ +typedef void (*xen_grant_fn_t)(unsigned long gfn, unsigned int offset, + unsigned int len, void *data); + +void gnttab_foreach_grant_in_range(struct page *page, + unsigned int offset, + unsigned int len, + xen_grant_fn_t fn, + void *data); + +/* Helper to get to call fn only on the first "grant chunk" */ +static inline void gnttab_for_one_grant(struct page *page, unsigned int offset, + unsigned len, xen_grant_fn_t fn, + void *data) +{ + /* The first request is limited to the size of one grant */ + len = min_t(unsigned int, XEN_PAGE_SIZE - (offset & ~XEN_PAGE_MASK), + len); + + gnttab_foreach_grant_in_range(page, offset, len, fn, data); +} + +/* Get @nr_grefs grants from an array of page and call fn for each grant */ +void gnttab_foreach_grant(struct page **pages, + unsigned int nr_grefs, + xen_grant_fn_t fn, + void *data); + +/* Get the number of grant in a specified region + * + * start: Offset from the beginning of the first page + * len: total length of data (can cross multiple page) + */ +static inline unsigned int gnttab_count_grant(unsigned int start, + unsigned int len) +{ + return XEN_PFN_UP(xen_offset_in_page(start) + len); +} + #endif /* __ASM_GNTTAB_H__ */ diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h index b62dfef15f61..d8949d5e227d 100644 --- a/include/xen/hvc-console.h +++ b/include/xen/hvc-console.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef XEN_HVC_CONSOLE_H #define XEN_HVC_CONSOLE_H diff --git a/include/xen/hvm.h b/include/xen/hvm.h index 63917a8de3b0..8da7a6747058 100644 --- a/include/xen/hvm.h +++ b/include/xen/hvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Simple wrappers around HVM functions */ #ifndef XEN_HVM_H__ #define XEN_HVM_H__ @@ -57,4 +58,8 @@ static inline int hvm_get_parameter(int idx, uint64_t *value) #define HVM_CALLBACK_VECTOR(x) (((uint64_t)HVM_CALLBACK_VIA_TYPE_VECTOR)<<\ HVM_CALLBACK_VIA_TYPE_SHIFT | (x)) +void xen_setup_callback_vector(void); + +int xen_set_upcall_vector(unsigned int cpu); + #endif /* XEN_HVM_H__ */ diff --git a/include/xen/interface/callback.h b/include/xen/interface/callback.h index 8c5fa0e20155..c67822a25ea6 100644 --- a/include/xen/interface/callback.h +++ b/include/xen/interface/callback.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * callback.h * * Register guest OS callbacks with Xen. * - * 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) 2006, Ian Campbell */ @@ -36,7 +19,7 @@ * @extra_args == Operation-specific extra arguments (NULL if none). */ -/* ia64, x86: Callback for event delivery. */ +/* x86: Callback for event delivery. */ #define CALLBACKTYPE_event 0 /* x86: Failsafe callback when guest state cannot be restored by Xen. */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h index 0360b15f4883..918f47d87d7a 100644 --- a/include/xen/interface/elfnote.h +++ b/include/xen/interface/elfnote.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * elfnote.h * @@ -10,7 +11,9 @@ #define __XEN_PUBLIC_ELFNOTE_H__ /* - * The notes should live in a SHT_NOTE segment and have "Xen" in the + * `incontents 200 elfnotes ELF notes + * + * The notes should live in a PT_NOTE segment and have "Xen" in the * name field. * * Numeric types are either 4 or 8 bytes depending on the content of @@ -18,12 +21,15 @@ * * LEGACY indicated the fields in the legacy __xen_guest string which * this a note type replaces. + * + * String values (for non-legacy) are NULL terminated ASCII, also known + * as ASCIZ type. + * + * Xen only uses ELF Notes contained in x86 binaries. */ /* * NAME=VALUE pair (string). - * - * LEGACY: FEATURES and PAE */ #define XEN_ELFNOTE_INFO 0 @@ -50,7 +56,7 @@ #define XEN_ELFNOTE_VIRT_BASE 3 /* - * The offset of the ELF paddr field from the acutal required + * The offset of the ELF paddr field from the actual required * pseudo-physical address (numeric). * * This is used to maintain backwards compatibility with older kernels @@ -90,7 +96,12 @@ #define XEN_ELFNOTE_LOADER 8 /* - * The kernel supports PAE (x86/32 only, string = "yes" or "no"). + * The kernel supports PAE (x86/32 only, string = "yes", "no" or + * "bimodal"). + * + * For compatibility with Xen 3.0.3 and earlier the "bimodal" setting + * may be given as "yes,bimodal" which will cause older Xen to treat + * this kernel as PAE. * * LEGACY: PAE (n.b. The legacy interface included a provision to * indicate 'extended-cr3' support allowing L3 page tables to be @@ -137,17 +148,129 @@ /* * Whether or not the guest supports cooperative suspend cancellation. + * This is a numeric value. + * + * Default is 0 */ #define XEN_ELFNOTE_SUSPEND_CANCEL 14 -#endif /* __XEN_PUBLIC_ELFNOTE_H__ */ +/* + * The (non-default) location the initial phys-to-machine map should be + * placed at by the hypervisor (Dom0) or the tools (DomU). + * The kernel must be prepared for this mapping to be established using + * large pages, despite such otherwise not being available to guests. Note + * that these large pages may be misaligned in PFN space (they'll obviously + * be aligned in MFN and virtual address spaces). + * The kernel must also be able to handle the page table pages used for + * this mapping not being accessible through the initial mapping. + * (Only x86-64 supports this at present.) + */ +#define XEN_ELFNOTE_INIT_P2M 15 + +/* + * Whether or not the guest can deal with being passed an initrd not + * mapped through its initial page tables. + */ +#define XEN_ELFNOTE_MOD_START_PFN 16 + +/* + * The features supported by this kernel (numeric). + * + * Other than XEN_ELFNOTE_FEATURES on pre-4.2 Xen, this note allows a + * kernel to specify support for features that older hypervisors don't + * know about. The set of features 4.2 and newer hypervisors will + * consider supported by the kernel is the combination of the sets + * specified through this and the string note. + * + * LEGACY: FEATURES + */ +#define XEN_ELFNOTE_SUPPORTED_FEATURES 17 /* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: + * 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 + +/* + * Physical loading constraints for PVH kernels + * + * The presence of this note indicates the kernel supports relocating itself. + * + * The note may include up to three 32bit values to place constraints on the + * guest physical loading addresses and alignment for a PVH kernel. Values + * are read in the following order: + * - a required start alignment (default 0x200000) + * - a minimum address for the start of the image (default 0; see below) + * - a maximum address for the last byte of the image (default 0xffffffff) + * + * When this note specifies an alignment value, it is used. Otherwise the + * maximum p_align value from loadable ELF Program Headers is used, if it is + * greater than or equal to 4k (0x1000). Otherwise, the default is used. + */ +#define XEN_ELFNOTE_PHYS32_RELOC 19 + +/* + * The number of the highest elfnote defined. + */ +#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_RELOC + +/* + * System information exported through crash notes. + * + * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_INFO + * note in case of a system crash. This note will contain various + * information about the system, see xen/include/xen/elfcore.h. + */ +#define XEN_ELFNOTE_CRASH_INFO 0x1000001 + +/* + * System registers exported through crash notes. + * + * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_REGS + * note per cpu in case of a system crash. This note is architecture + * specific and will contain registers not saved in the "CORE" note. + * See xen/include/xen/elfcore.h for more information. + */ +#define XEN_ELFNOTE_CRASH_REGS 0x1000002 + + +/* + * xen dump-core none note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_NONE + * in its dump file to indicate that the file is xen dump-core + * file. This note doesn't have any other information. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_NONE 0x2000000 + +/* + * xen dump-core header note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_HEADER + * in its dump file. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_HEADER 0x2000001 + +/* + * xen dump-core xen version note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_XEN_VERSION + * in its dump file. It contains the xen version obtained via the + * XENVER hypercall. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_XEN_VERSION 0x2000002 + +/* + * xen dump-core format version note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION + * in its dump file. It contains a format version identifier. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION 0x2000003 + +#endif /* __XEN_PUBLIC_ELFNOTE_H__ */ diff --git a/include/xen/interface/event_channel.h b/include/xen/interface/event_channel.h index f4942921e202..5f8da466e8a9 100644 --- a/include/xen/interface/event_channel.h +++ b/include/xen/interface/event_channel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * event_channel.h * @@ -190,6 +191,39 @@ struct evtchn_reset { }; typedef struct evtchn_reset evtchn_reset_t; +/* + * EVTCHNOP_init_control: initialize the control block for the FIFO ABI. + */ +#define EVTCHNOP_init_control 11 +struct evtchn_init_control { + /* IN parameters. */ + uint64_t control_gfn; + uint32_t offset; + uint32_t vcpu; + /* OUT parameters. */ + uint8_t link_bits; + uint8_t _pad[7]; +}; + +/* + * EVTCHNOP_expand_array: add an additional page to the event array. + */ +#define EVTCHNOP_expand_array 12 +struct evtchn_expand_array { + /* IN parameters. */ + uint64_t array_gfn; +}; + +/* + * EVTCHNOP_set_priority: set the priority for an event channel. + */ +#define EVTCHNOP_set_priority 13 +struct evtchn_set_priority { + /* IN parameters. */ + evtchn_port_t port; + uint32_t priority; +}; + struct evtchn_op { uint32_t cmd; /* EVTCHNOP_* */ union { @@ -207,4 +241,39 @@ struct evtchn_op { }; DEFINE_GUEST_HANDLE_STRUCT(evtchn_op); +/* + * 2-level ABI + */ + +#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) + +/* + * FIFO ABI + */ + +/* Events may have priorities from 0 (highest) to 15 (lowest). */ +#define EVTCHN_FIFO_PRIORITY_MAX 0 +#define EVTCHN_FIFO_PRIORITY_DEFAULT 7 +#define EVTCHN_FIFO_PRIORITY_MIN 15 + +#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1) + +typedef uint32_t event_word_t; + +#define EVTCHN_FIFO_PENDING 31 +#define EVTCHN_FIFO_MASKED 30 +#define EVTCHN_FIFO_LINKED 29 +#define EVTCHN_FIFO_BUSY 28 + +#define EVTCHN_FIFO_LINK_BITS 17 +#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1) + +#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS) + +struct evtchn_fifo_control_block { + uint32_t ready; + uint32_t _rsvd; + event_word_t head[EVTCHN_FIFO_MAX_QUEUES]; +}; + #endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h index 131a6ccdba25..53f760378e39 100644 --- a/include/xen/interface/features.h +++ b/include/xen/interface/features.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * features.h * @@ -41,6 +42,15 @@ /* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */ #define XENFEAT_mmu_pt_update_preserve_ad 5 +/* x86: Does this Xen host support the MMU_{CLEAR,COPY}_PAGE hypercall? */ +#define XENFEAT_highmem_assist 6 + +/* + * If set, GNTTABOP_map_grant_ref honors flags to be placed into guest kernel + * available pte bits. + */ +#define XENFEAT_gnttab_map_avail_bits 7 + /* x86: Does this Xen host support the HVM callback vector type? */ #define XENFEAT_hvm_callback_vector 8 @@ -53,6 +63,40 @@ /* operation as Dom0 is supported */ #define XENFEAT_dom0 11 +/* Xen also maps grant references at pfn = mfn. + * This feature flag is deprecated and should not be used. +#define XENFEAT_grant_map_identity 12 + */ + +/* Guest can use XENMEMF_vnode to specify virtual node for memory op. */ +#define XENFEAT_memory_op_vnode_supported 13 + +/* arm: Hypervisor supports ARM SMC calling convention. */ +#define XENFEAT_ARM_SMCCC_supported 14 + +/* + * x86/PVH: If set, ACPI RSDP can be placed at any address. Otherwise RSDP + * must be located in lower 1MB, as required by ACPI Specification for IA-PC + * systems. + * This feature flag is only consulted if XEN_ELFNOTE_GUEST_OS contains + * the "linux" string. + */ +#define XENFEAT_linux_rsdp_unrestricted 15 + +/* + * A direct-mapped (or 1:1 mapped) domain is a domain for which its + * local pages have gfn == mfn. If a domain is direct-mapped, + * XENFEAT_direct_mapped is set; otherwise XENFEAT_not_direct_mapped + * is set. + * + * If neither flag is set (e.g. older Xen releases) the assumptions are: + * - not auto_translated domains (x86 only) are always direct-mapped + * - on x86, auto_translated domains are not direct-mapped + * - on ARM, Dom0 is direct-mapped, DomUs are not + */ +#define XENFEAT_not_direct_mapped 16 +#define XENFEAT_direct_mapped 17 + #define XENFEAT_NR_SUBMAPS 1 #endif /* __XEN_PUBLIC_FEATURES_H__ */ diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index e40fae9bf11a..cebbd99f1f84 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -1,27 +1,10 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * grant_table.h * * Interface for granting foreign access to page frames, and receiving * page-ownership transfers. * - * 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) 2004, K A Fraser */ @@ -36,7 +19,8 @@ /* Some rough guidelines on accessing and updating grant-table entries * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD * * NB. WMB is a no-op on current-generation x86 processors. However, a * compiler barrier will still be required. @@ -97,8 +81,9 @@ typedef uint32_t grant_ref_t; */ /* - * Version 1 of the grant table entry structure is maintained purely - * for backwards compatibility. New guests should use version 2. + * Version 1 of the grant table entry structure is maintained largely for + * backwards compatibility. New guests are recommended to support using + * version 2 to overcome version 1 limitations, but to default to version 1. */ struct grant_entry_v1 { /* GTF_xxx: various type and flag information. [XEN,GST] */ @@ -106,12 +91,21 @@ struct grant_entry_v1 { /* The domain being granted foreign privileges. [GST] */ domid_t domid; /* - * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] - * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + /* * Type of grant entry. * GTF_invalid: This grant entry grants no privileges. @@ -128,10 +122,13 @@ struct grant_entry_v1 { #define GTF_type_mask (3U<<0) /* - * Subflags for GTF_permit_access. + * Subflags for GTF_permit_access and GTF_transitive. * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * Further subflags for GTF_permit_access only. + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for + * mappings of the grant [GST] * GTF_sub_page: Grant access to only a subrange of the page. @domid * will only be allowed to copy from the grant, and not * map it. [GST] @@ -142,6 +139,12 @@ struct grant_entry_v1 { #define GTF_reading (1U<<_GTF_reading) #define _GTF_writing (4) #define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) #define _GTF_sub_page (8) #define GTF_sub_page (1U<<_GTF_sub_page) @@ -181,8 +184,7 @@ struct grant_entry_header { }; /* - * Version 2 of the grant entry structure, here is an union because three - * different types are suppotted: full_page, sub_page and transitive. + * Version 2 of the grant entry structure. */ union grant_entry_v2 { struct grant_entry_header hdr; @@ -197,9 +199,9 @@ union grant_entry_v2 { * field of the same name in the V1 entry structure. */ struct { - struct grant_entry_header hdr; - uint32_t pad0; - uint64_t frame; + struct grant_entry_header hdr; + uint32_t pad0; + uint64_t frame; } full_page; /* @@ -208,10 +210,10 @@ union grant_entry_v2 { * in frame @frame. */ struct { - struct grant_entry_header hdr; - uint16_t page_off; - uint16_t length; - uint64_t frame; + struct grant_entry_header hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; } sub_page; /* @@ -219,12 +221,15 @@ union grant_entry_v2 { * grant @gref in domain @trans_domid, as if it was the local * domain. Obviously, the transitive access must be compatible * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. */ struct { - struct grant_entry_header hdr; - domid_t trans_domid; - uint16_t pad0; - grant_ref_t gref; + struct grant_entry_header hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; } transitive; uint32_t __spacer[4]; /* Pad to a power of two */ @@ -236,6 +241,21 @@ typedef uint16_t grant_status_t; * GRANT TABLE QUERIES AND USES */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 +/* ` } */ + /* * Handle to track a mapping created via a grant reference. */ @@ -244,7 +264,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access * by devices and/or host CPUs. If successful, <handle> is a tracking number - * that must be presented later to destroy the mapping(s). On error, <handle> + * that must be presented later to destroy the mapping(s). On error, <status> * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address @@ -258,7 +278,6 @@ typedef uint32_t grant_handle_t; * host mapping is destroyed by other means then it is *NOT* guaranteed * to be accounted to the correct grant reference! */ -#define GNTTABOP_map_grant_ref 0 struct gnttab_map_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -283,7 +302,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref); * 3. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_grant_ref 1 struct gnttab_unmap_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -303,7 +321,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref); * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. * 3. Xen may not support more than a single grant-table page per domain. */ -#define GNTTABOP_setup_table 2 struct gnttab_setup_table { /* IN parameters. */ domid_t dom; @@ -318,7 +335,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table); * GNTTABOP_dump_table: Dump the contents of the grant table to the * xen console. Debugging use only. */ -#define GNTTABOP_dump_table 3 struct gnttab_dump_table { /* IN parameters. */ domid_t dom; @@ -328,17 +344,17 @@ struct gnttab_dump_table { DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table); /* - * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * <domid, ref>. + * GNTTABOP_transfer: Transfer <frame> to a foreign domain. The foreign domain + * has previously registered its interest in the transfer via <domid, ref>. * * Note that, even if the transfer fails, the specified page no longer belongs * to the calling domain *unless* the error is GNTST_bad_page. + * + * Note further that only PV guests can use this operation. */ -#define GNTTABOP_transfer 4 struct gnttab_transfer { /* IN parameters. */ - xen_pfn_t mfn; + xen_pfn_t mfn; domid_t domid; grant_ref_t ref; /* OUT parameters. */ @@ -369,21 +385,20 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer); #define _GNTCOPY_dest_gref (1) #define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) -#define GNTTABOP_copy 5 struct gnttab_copy { - /* IN parameters. */ - struct { - union { - grant_ref_t ref; - xen_pfn_t gmfn; - } u; - domid_t domid; - uint16_t offset; - } source, dest; - uint16_t len; - uint16_t flags; /* GNTCOPY_* */ - /* OUT parameters. */ - int16_t status; + /* IN parameters. */ + struct gnttab_copy_ptr { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); @@ -394,7 +409,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_query_size 6 struct gnttab_query_size { /* IN parameters. */ domid_t dom; @@ -416,7 +430,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size); * 2. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_and_replace 7 struct gnttab_unmap_and_replace { /* IN parameters. */ uint64_t host_addr; @@ -429,14 +442,12 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace); /* * GNTTABOP_set_version: Request a particular version of the grant - * table shared table structure. This operation can only be performed - * once in any given domain. It must be performed before any grants - * are activated; otherwise, the domain will be stuck with version 1. - * The only defined versions are 1 and 2. + * table shared table structure. This operation may be used to toggle + * between different versions, but must be performed while no grants + * are active. The only defined versions are 1 and 2. */ -#define GNTTABOP_set_version 8 struct gnttab_set_version { - /* IN parameters */ + /* IN/OUT parameters */ uint32_t version; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); @@ -453,7 +464,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_get_status_frames 9 struct gnttab_get_status_frames { /* IN parameters. */ uint32_t nr_frames; @@ -468,7 +478,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames); * GNTTABOP_get_version: Get the grant table version which is in * effect for domain <dom>. */ -#define GNTTABOP_get_version 10 struct gnttab_get_version { /* IN parameters */ domid_t dom; @@ -479,7 +488,37 @@ struct gnttab_get_version { DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); /* - * Bitfield values for update_pin_status.flags. + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* GNTST_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_swap_grant_ref); + +/* + * Issue one or more cache maintenance operations on a portion of a + * page granted to the calling domain by a foreign domain. + */ +struct gnttab_cache_flush { + union { + uint64_t dev_bus_addr; + grant_ref_t ref; + } a; + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1u<<0) +#define GNTTAB_CACHE_INVAL (1u<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1u<<31) + uint32_t op; +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); + +/* + * Bitfield values for gnttab_map_grant_ref.flags. */ /* Map the grant entry for access by I/O devices. */ #define _GNTMAP_device_map (0) @@ -507,6 +546,13 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); #define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte) /* + * Bits to be placed in guest kernel available PTE bits (architecture + * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set). + */ +#define _GNTMAP_guest_avail0 (16) +#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0) + +/* * Values for error status returns. All errors are -ve. */ #define GNTST_okay (0) /* Normal return. */ @@ -522,6 +568,7 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); #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 GNTST_no_space (-13) /* Out of space (handles etc). */ #define GNTTABOP_error_msgs { \ "okay", \ @@ -536,7 +583,8 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); "bad page", \ "copy arguments cross page boundary", \ "page address size too large", \ - "operation not done; try again" \ + "operation not done; try again", \ + "out of space", \ } #endif /* __XEN_PUBLIC_GRANT_TABLE_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..08d972f87c7b --- /dev/null +++ b/include/xen/interface/hvm/dm_op.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (c) 2016, Citrix Systems Inc + */ + +#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_op.h b/include/xen/interface/hvm/hvm_op.h index 956a04682865..03134bf3cec1 100644 --- a/include/xen/interface/hvm/hvm_op.h +++ b/include/xen/interface/hvm/hvm_op.h @@ -1,26 +1,10 @@ -/* - * 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. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_HVM_HVM_OP_H__ #define __XEN_PUBLIC_HVM_HVM_OP_H__ +#include <xen/interface/xen.h> + /* Get/set subcommands: the second argument of the hypercall is a * pointer to a xen_hvm_param struct. */ #define HVMOP_set_param 0 @@ -62,4 +46,23 @@ struct xen_hvm_get_mem_type { }; DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_get_mem_type); +#if defined(__i386__) || defined(__x86_64__) + +/* + * HVMOP_set_evtchn_upcall_vector: Set a <vector> that should be used for event + * channel upcalls on the specified <vcpu>. If set, + * this vector will be used in preference to the + * domain global callback via (see + * HVM_PARAM_CALLBACK_IRQ). + */ +#define HVMOP_set_evtchn_upcall_vector 23 +struct xen_hvm_evtchn_upcall_vector { + uint32_t vcpu; + uint8_t vector; +}; +typedef struct xen_hvm_evtchn_upcall_vector xen_hvm_evtchn_upcall_vector_t; +DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_evtchn_upcall_vector_t); + +#endif /* defined(__i386__) || defined(__x86_64__) */ + #endif /* __XEN_PUBLIC_HVM_HVM_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..cbf93493275c --- /dev/null +++ b/include/xen/interface/hvm/hvm_vcpu.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: MIT */ +/* + * 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__ */ diff --git a/include/xen/interface/hvm/ioreq.h b/include/xen/interface/hvm/ioreq.h new file mode 100644 index 000000000000..b02cfeae7eb5 --- /dev/null +++ b/include/xen/interface/hvm/ioreq.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: MIT */ +/* + * ioreq.h: I/O request definitions for device models + * Copyright (c) 2004, Intel Corporation. + */ + +#ifndef __XEN_PUBLIC_HVM_IOREQ_H__ +#define __XEN_PUBLIC_HVM_IOREQ_H__ + +#define IOREQ_READ 1 +#define IOREQ_WRITE 0 + +#define STATE_IOREQ_NONE 0 +#define STATE_IOREQ_READY 1 +#define STATE_IOREQ_INPROCESS 2 +#define STATE_IORESP_READY 3 + +#define IOREQ_TYPE_PIO 0 /* pio */ +#define IOREQ_TYPE_COPY 1 /* mmio ops */ +#define IOREQ_TYPE_PCI_CONFIG 2 +#define IOREQ_TYPE_TIMEOFFSET 7 +#define IOREQ_TYPE_INVALIDATE 8 /* mapcache */ + +/* + * VMExit dispatcher should cooperate with instruction decoder to + * prepare this structure and notify service OS and DM by sending + * virq. + * + * For I/O type IOREQ_TYPE_PCI_CONFIG, the physical address is formatted + * as follows: + * + * 63....48|47..40|39..35|34..32|31........0 + * SEGMENT |BUS |DEV |FN |OFFSET + */ +struct ioreq { + uint64_t addr; /* physical address */ + uint64_t data; /* data (or paddr of data) */ + uint32_t count; /* for rep prefixes */ + uint32_t size; /* size in bytes */ + uint32_t vp_eport; /* evtchn for notifications to/from device model */ + uint16_t _pad0; + uint8_t state:4; + uint8_t data_is_ptr:1; /* if 1, data above is the guest paddr + * of the real data to use. */ + uint8_t dir:1; /* 1=read, 0=write */ + uint8_t df:1; + uint8_t _pad1:1; + uint8_t type; /* I/O type */ +}; + +#endif /* __XEN_PUBLIC_HVM_IOREQ_H__ */ diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h index a6c79911e729..4e2c94b3c466 100644 --- a/include/xen/interface/hvm/params.h +++ b/include/xen/interface/hvm/params.h @@ -1,22 +1,4 @@ -/* - * 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. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_HVM_PARAMS_H__ #define __XEN_PUBLIC_HVM_PARAMS_H__ @@ -27,16 +9,44 @@ * Parameter space for HVMOP_{set,get}_param. */ +#define HVM_PARAM_CALLBACK_IRQ 0 /* * How should CPU0 event-channel notifications be delivered? - * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt). - * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows: - * Domain = val[47:32], Bus = val[31:16], - * DevFn = val[15: 8], IntX = val[ 1: 0] - * val[63:56] == 2: val[7:0] is a vector number. + * * If val == 0 then CPU0 event-channel notifications are not delivered. + * If val != 0, val[63:56] encodes the type, as follows: */ -#define HVM_PARAM_CALLBACK_IRQ 0 + +#define HVM_PARAM_CALLBACK_TYPE_GSI 0 +/* + * val[55:0] is a delivery GSI. GSI 0 cannot be used, as it aliases val == 0, + * and disables all notifications. + */ + +#define HVM_PARAM_CALLBACK_TYPE_PCI_INTX 1 +/* + * val[55:0] is a delivery PCI INTx line: + * Domain = val[47:32], Bus = val[31:16] DevFn = val[15:8], IntX = val[1:0] + */ + +#if defined(__i386__) || defined(__x86_64__) +#define HVM_PARAM_CALLBACK_TYPE_VECTOR 2 +/* + * val[7:0] is a vector number. Check for XENFEAT_hvm_callback_vector to know + * if this delivery method is available. + */ +#elif defined(__arm__) || defined(__aarch64__) +#define HVM_PARAM_CALLBACK_TYPE_PPI 2 +/* + * val[55:16] needs to be zero. + * val[15:8] is interrupt flag of the PPI used by event-channel: + * bit 8: the PPI is edge(1) or level(0) triggered + * bit 9: the PPI is active low(1) or high(0) + * val[7:0] is a PPI number used by event-channel. + * This is only used by ARM/ARM64 and masking/eoi the interrupt associated to + * the notification is handled by the interrupt controller. + */ +#endif #define HVM_PARAM_STORE_PFN 1 #define HVM_PARAM_STORE_EVTCHN 2 diff --git a/include/xen/interface/hvm/start_info.h b/include/xen/interface/hvm/start_info.h new file mode 100644 index 000000000000..e33557c0b4e9 --- /dev/null +++ b/include/xen/interface/hvm/start_info.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: MIT */ +/* + * 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 1. 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 +----------------+ + * | memmap_paddr | Physical address of the (optional) memory map. Only + * | | present in version 1 and newer of the structure. + * 48 +----------------+ + * | memmap_entries | Number of entries in the memory map table. Zero + * | | if there is no memory map being provided. Only + * | | present in version 1 and newer of the structure. + * 52 +----------------+ + * | reserved | Version 1 and newer only. + * 56 +----------------+ + * + * 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 layout of each entry in the memory map table is as follows: + * + * 0 +----------------+ + * | addr | Base address + * 8 +----------------+ + * | size | Size of mapping in bytes + * 16 +----------------+ + * | type | Type of mapping as defined between the hypervisor + * | | and guest. See XEN_HVM_MEMMAP_TYPE_* values below. + * 20 +----------------| + * | reserved | + * 24 +----------------+ + * + * 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. + * + * Version numbers of the hvm_start_info structure have evolved like this: + * + * Version 0: Initial implementation. + * + * Version 1: Added the memmap_paddr/memmap_entries fields (plus 4 bytes of + * padding) to the end of the hvm_start_info struct. These new + * fields can be used to pass a memory map to the guest. The + * memory map is optional and so guests that understand version 1 + * of the structure must check that memmap_entries is non-zero + * before trying to read the memory map. + */ +#define XEN_HVM_START_MAGIC_VALUE 0x336ec578 + +/* + * The values used in the type field of the memory map table entries are + * defined below and match the Address Range Types as defined in the "System + * Address Map Interfaces" section of the ACPI Specification. Please refer to + * section 15 in version 6.2 of the ACPI spec: http://uefi.org/specifications + */ +#define XEN_HVM_MEMMAP_TYPE_RAM 1 +#define XEN_HVM_MEMMAP_TYPE_RESERVED 2 +#define XEN_HVM_MEMMAP_TYPE_ACPI 3 +#define XEN_HVM_MEMMAP_TYPE_NVS 4 +#define XEN_HVM_MEMMAP_TYPE_UNUSABLE 5 +#define XEN_HVM_MEMMAP_TYPE_DISABLED 6 +#define XEN_HVM_MEMMAP_TYPE_PMEM 7 + +/* + * 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. */ + /* All following fields only present in version 1 and newer */ + uint64_t memmap_paddr; /* Physical address of an array of */ + /* hvm_memmap_table_entry. */ + uint32_t memmap_entries; /* Number of entries in the memmap table. */ + /* Value will be zero if there is no memory */ + /* map being provided. */ + uint32_t reserved; /* Must be zero. */ +}; + +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; +}; + +struct hvm_memmap_table_entry { + uint64_t addr; /* Base address of the memory region */ + uint64_t size; /* Size of the memory region in bytes */ + uint32_t type; /* Mapping type */ + uint32_t reserved; /* Must be zero for Version 1. */ +}; + +#endif /* __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__ */ diff --git a/include/xen/interface/io/9pfs.h b/include/xen/interface/io/9pfs.h new file mode 100644 index 000000000000..f1a4c5ad2fd1 --- /dev/null +++ b/include/xen/interface/io/9pfs.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: MIT */ +/* + * 9pfs.h -- Xen 9PFS transport + * + * Copyright (C) 2017 Stefano Stabellini <stefano@aporeto.com> + */ + +#ifndef __XEN_PUBLIC_IO_9PFS_H__ +#define __XEN_PUBLIC_IO_9PFS_H__ + +#include "xen/interface/io/ring.h" + +/* + * See docs/misc/9pfs.markdown in xen.git for the full specification: + * https://xenbits.xen.org/docs/unstable/misc/9pfs.html + */ +DEFINE_XEN_FLEX_RING_AND_INTF(xen_9pfs); + +#endif diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index ffd4652de91c..ba1e9f5b630e 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * blkif.h * @@ -28,6 +29,54 @@ typedef uint16_t blkif_vdev_t; typedef uint64_t blkif_sector_t; /* + * Multiple hardware queues/rings: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vbd, and set its value to the maximum supported + * number of queues. + * Frontends that are aware of this feature and wish to use it can write the + * key "multi-queue-num-queues" with the number they wish to use, which must be + * greater than zero, and no more than the value reported by the backend in + * "multi-queue-max-queues". + * + * For frontends requesting just one queue, the usual event-channel and + * ring-ref keys are written as before, simplifying the backend processing + * to avoid distinguishing between a frontend that doesn't understand the + * multi-queue feature, and one that does, but requested only one queue. + * + * Frontends requesting two or more queues must not write the toplevel + * event-channel and ring-ref keys, instead writing those keys under sub-keys + * having the name "queue-N" where N is the integer ID of the queue/ring for + * which those keys belong. Queues are indexed from zero. + * For example, a frontend with two queues must write the following set of + * queue-related keys: + * + * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vbd/0/queue-0 = "" + * /local/domain/1/device/vbd/0/queue-0/ring-ref = "<ring-ref#0>" + * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>" + * /local/domain/1/device/vbd/0/queue-1 = "" + * /local/domain/1/device/vbd/0/queue-1/ring-ref = "<ring-ref#1>" + * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>" + * + * It is also possible to use multiple queues/rings together with + * feature multi-page ring buffer. + * For example, a frontend requests two queues/rings and the size of each ring + * buffer is two pages must write the following set of related keys: + * + * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vbd/0/ring-page-order = "1" + * /local/domain/1/device/vbd/0/queue-0 = "" + * /local/domain/1/device/vbd/0/queue-0/ring-ref0 = "<ring-ref#0>" + * /local/domain/1/device/vbd/0/queue-0/ring-ref1 = "<ring-ref#1>" + * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>" + * /local/domain/1/device/vbd/0/queue-1 = "" + * /local/domain/1/device/vbd/0/queue-1/ring-ref0 = "<ring-ref#2>" + * /local/domain/1/device/vbd/0/queue-1/ring-ref1 = "<ring-ref#3>" + * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>" + * + */ + +/* * REQUEST CODES. */ #define BLKIF_OP_READ 0 @@ -86,7 +135,7 @@ typedef uint64_t blkif_sector_t; * Interface%20manuals/100293068c.pdf * The backend can optionally provide three extra XenBus attributes to * further optimize the discard functionality: - * 'discard-aligment' - Devices that support discard functionality may + * 'discard-alignment' - Devices that support discard functionality may * internally allocate space in units that are bigger than the exported * logical block size. The discard-alignment parameter indicates how many bytes * the beginning of the partition is offset from the internal allocation unit's @@ -103,33 +152,61 @@ typedef uint64_t blkif_sector_t; #define BLKIF_OP_DISCARD 5 /* + * Recognized if "feature-max-indirect-segments" in present in the backend + * xenbus info. The "feature-max-indirect-segments" node contains the maximum + * number of segments allowed by the backend per request. If the node is + * present, the frontend might use blkif_request_indirect structs in order to + * issue requests with more than BLKIF_MAX_SEGMENTS_PER_REQUEST (11). The + * maximum number of indirect segments is fixed by the backend, but the + * frontend can issue requests with any number of indirect segments as long as + * it's less than the number provided by the backend. The indirect_grefs field + * in blkif_request_indirect should be filled by the frontend with the + * grant references of the pages that are holding the indirect segments. + * These pages are filled with an array of blkif_request_segment that hold the + * information about the segments. The number of indirect pages to use is + * determined by the number of segments an indirect request contains. Every + * indirect page can contain a maximum of + * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to + * calculate the number of indirect pages to use we have to do + * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))). + * + * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not* + * create the "feature-max-indirect-segments" node! + */ +#define BLKIF_OP_INDIRECT 6 + +/* * Maximum scatter/gather segments per request. * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE. * NB. This could be 12 if the ring indexes weren't stored in the same page. */ #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 +#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8 + +struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; +}; + struct blkif_request_rw { uint8_t nr_segments; /* number of segments */ blkif_vdev_t handle; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad1; /* offsetof(blkif_request,u.rw.id) == 8 */ #endif uint64_t id; /* private guest value, echoed in resp */ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ - struct blkif_request_segment { - grant_ref_t gref; /* reference to I/O buffer frame */ - /* @first_sect: first sector in frame to transfer (inclusive). */ - /* @last_sect: last sector in frame to transfer (inclusive). */ - uint8_t first_sect, last_sect; - } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; } __attribute__((__packed__)); struct blkif_request_discard { uint8_t flag; /* BLKIF_DISCARD_SECURE or zero. */ #define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */ blkif_vdev_t _pad1; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad2; /* offsetof(blkif_req..,u.discard.id)==8*/ #endif uint64_t id; /* private guest value, echoed in resp */ @@ -141,18 +218,37 @@ struct blkif_request_discard { struct blkif_request_other { uint8_t _pad1; blkif_vdev_t _pad2; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad3; /* offsetof(blkif_req..,u.other.id)==8*/ #endif uint64_t id; /* private guest value, echoed in resp */ } __attribute__((__packed__)); +struct blkif_request_indirect { + uint8_t indirect_op; + uint16_t nr_segments; +#ifndef CONFIG_X86_32 + uint32_t _pad1; /* offsetof(blkif_...,u.indirect.id) == 8 */ +#endif + uint64_t id; + blkif_sector_t sector_number; + blkif_vdev_t handle; + uint16_t _pad2; + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; +#ifndef CONFIG_X86_32 + uint32_t _pad3; /* make it 64 byte aligned */ +#else + uint64_t _pad3; /* make it 64 byte aligned */ +#endif +} __attribute__((__packed__)); + struct blkif_request { uint8_t operation; /* BLKIF_OP_??? */ union { struct blkif_request_rw rw; struct blkif_request_discard discard; struct blkif_request_other other; + struct blkif_request_indirect indirect; } u; } __attribute__((__packed__)); diff --git a/include/xen/interface/io/console.h b/include/xen/interface/io/console.h index e563de70f784..cf17e89ed861 100644 --- a/include/xen/interface/io/console.h +++ b/include/xen/interface/io/console.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * console.h * diff --git a/include/xen/interface/io/displif.h b/include/xen/interface/io/displif.h new file mode 100644 index 000000000000..60e42d3b760e --- /dev/null +++ b/include/xen/interface/io/displif.h @@ -0,0 +1,930 @@ +/* SPDX-License-Identifier: MIT */ +/****************************************************************************** + * displif.h + * + * Unified display device I/O interface for Xen guest OSes. + * + * Copyright (C) 2016-2017 EPAM Systems Inc. + * + * Authors: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + * Oleksandr Grytsov <oleksandr_grytsov@epam.com> + */ + +#ifndef __XEN_PUBLIC_IO_DISPLIF_H__ +#define __XEN_PUBLIC_IO_DISPLIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + ****************************************************************************** + * Protocol version + ****************************************************************************** + */ +#define XENDISPL_PROTOCOL_VERSION "2" +#define XENDISPL_PROTOCOL_VERSION_INT 2 + +/* + ****************************************************************************** + * Main features provided by the protocol + ****************************************************************************** + * This protocol aims to provide a unified protocol which fits more + * sophisticated use-cases than a framebuffer device can handle. At the + * moment basic functionality is supported with the intention to be extended: + * o multiple dynamically allocated/destroyed framebuffers + * o buffers of arbitrary sizes + * o buffer allocation at either back or front end + * o better configuration options including multiple display support + * + * Note: existing fbif can be used together with displif running at the + * same time, e.g. on Linux one provides framebuffer and another DRM/KMS + * + * Note: display resolution (XenStore's "resolution" property) defines + * visible area of the virtual display. At the same time resolution of + * the display and frame buffers may differ: buffers can be smaller, equal + * or bigger than the visible area. This is to enable use-cases, where backend + * may do some post-processing of the display and frame buffers supplied, + * e.g. those buffers can be just a part of the final composition. + * + ****************************************************************************** + * Direction of improvements + ****************************************************************************** + * Future extensions to the existing protocol may include: + * o display/connector cloning + * o allocation of objects other than display buffers + * o plane/overlay support + * o scaling support + * o rotation support + * + ****************************************************************************** + * Feature and Parameter Negotiation + ****************************************************************************** + * + * Front->back notifications: when enqueuing a new request, sending a + * notification can be made conditional on xendispl_req (i.e., the generic + * hold-off mechanism provided by the ring macros). Backends must set + * xendispl_req appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()). + * + * Back->front notifications: when enqueuing a new response, sending a + * notification can be made conditional on xendispl_resp (i.e., the generic + * hold-off mechanism provided by the ring macros). Frontends must set + * xendispl_resp appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()). + * + * The two halves of a para-virtual display driver utilize nodes within + * XenStore to communicate capabilities and to negotiate operating parameters. + * This section enumerates these nodes which reside in the respective front and + * backend portions of XenStore, following the XenBus convention. + * + * All data in XenStore is stored as strings. Nodes specifying numeric + * values are encoded in decimal. Integer value ranges listed below are + * expressed as fixed sized integer types capable of storing the conversion + * of a properly formated node string, without loss of information. + * + ****************************************************************************** + * Example configuration + ****************************************************************************** + * + * Note: depending on the use-case backend can expose more display connectors + * than the underlying HW physically has by employing SW graphics compositors + * + * This is an example of backend and frontend configuration: + * + *--------------------------------- Backend ----------------------------------- + * + * /local/domain/0/backend/vdispl/1/0/frontend-id = "1" + * /local/domain/0/backend/vdispl/1/0/frontend = "/local/domain/1/device/vdispl/0" + * /local/domain/0/backend/vdispl/1/0/state = "4" + * /local/domain/0/backend/vdispl/1/0/versions = "1,2" + * + *--------------------------------- Frontend ---------------------------------- + * + * /local/domain/1/device/vdispl/0/backend-id = "0" + * /local/domain/1/device/vdispl/0/backend = "/local/domain/0/backend/vdispl/1/0" + * /local/domain/1/device/vdispl/0/state = "4" + * /local/domain/1/device/vdispl/0/version = "1" + * /local/domain/1/device/vdispl/0/be-alloc = "1" + * + *-------------------------- Connector 0 configuration ------------------------ + * + * /local/domain/1/device/vdispl/0/0/resolution = "1920x1080" + * /local/domain/1/device/vdispl/0/0/req-ring-ref = "2832" + * /local/domain/1/device/vdispl/0/0/req-event-channel = "15" + * /local/domain/1/device/vdispl/0/0/evt-ring-ref = "387" + * /local/domain/1/device/vdispl/0/0/evt-event-channel = "16" + * + *-------------------------- Connector 1 configuration ------------------------ + * + * /local/domain/1/device/vdispl/0/1/resolution = "800x600" + * /local/domain/1/device/vdispl/0/1/req-ring-ref = "2833" + * /local/domain/1/device/vdispl/0/1/req-event-channel = "17" + * /local/domain/1/device/vdispl/0/1/evt-ring-ref = "388" + * /local/domain/1/device/vdispl/0/1/evt-event-channel = "18" + * + ****************************************************************************** + * Backend XenBus Nodes + ****************************************************************************** + * + *----------------------------- Protocol version ------------------------------ + * + * versions + * Values: <string> + * + * List of XENDISPL_LIST_SEPARATOR separated protocol versions supported + * by the backend. For example "1,2,3". + * + ****************************************************************************** + * Frontend XenBus Nodes + ****************************************************************************** + * + *-------------------------------- Addressing --------------------------------- + * + * dom-id + * Values: <uint16_t> + * + * Domain identifier. + * + * dev-id + * Values: <uint16_t> + * + * Device identifier. + * + * conn-idx + * Values: <uint8_t> + * + * Zero based contigous index of the connector. + * /local/domain/<dom-id>/device/vdispl/<dev-id>/<conn-idx>/... + * + *----------------------------- Protocol version ------------------------------ + * + * version + * Values: <string> + * + * Protocol version, chosen among the ones supported by the backend. + * + *------------------------- Backend buffer allocation ------------------------- + * + * be-alloc + * Values: "0", "1" + * + * If value is set to "1", then backend can be a buffer provider/allocator + * for this domain during XENDISPL_OP_DBUF_CREATE operation (see below + * for negotiation). + * If value is not "1" or omitted frontend must allocate buffers itself. + * + *----------------------------- Connector settings ---------------------------- + * + * unique-id + * Values: <string> + * + * After device instance initialization each connector is assigned a + * unique ID, so it can be identified by the backend by this ID. + * This can be UUID or such. + * + * resolution + * Values: <width, uint32_t>x<height, uint32_t> + * + * Width and height of the connector in pixels separated by + * XENDISPL_RESOLUTION_SEPARATOR. This defines visible area of the + * display. + * If backend provides extended display identification data (EDID) with + * XENDISPL_OP_GET_EDID request then EDID values must take precedence + * over the resolutions defined here. + * + *------------------ Connector Request Transport Parameters ------------------- + * + * This communication path is used to deliver requests from frontend to backend + * and get the corresponding responses from backend to frontend, + * set up per connector. + * + * req-event-channel + * Values: <uint32_t> + * + * The identifier of the Xen connector's control event channel + * used to signal activity in the ring buffer. + * + * req-ring-ref + * Values: <uint32_t> + * + * The Xen grant reference granting permission for the backend to map + * a sole page of connector's control ring buffer. + * + *------------------- Connector Event Transport Parameters -------------------- + * + * This communication path is used to deliver asynchronous events from backend + * to frontend, set up per connector. + * + * evt-event-channel + * Values: <uint32_t> + * + * The identifier of the Xen connector's event channel + * used to signal activity in the ring buffer. + * + * evt-ring-ref + * Values: <uint32_t> + * + * The Xen grant reference granting permission for the backend to map + * a sole page of connector's event ring buffer. + */ + +/* + ****************************************************************************** + * STATE DIAGRAMS + ****************************************************************************** + * + * Tool stack creates front and back state nodes with initial state + * XenbusStateInitialising. + * Tool stack creates and sets up frontend display configuration + * nodes per domain. + * + *-------------------------------- Normal flow -------------------------------- + * + * Front Back + * ================================= ===================================== + * XenbusStateInitialising XenbusStateInitialising + * o Query backend device identification + * data. + * o Open and validate backend device. + * | + * | + * V + * XenbusStateInitWait + * + * o Query frontend configuration + * o Allocate and initialize + * event channels per configured + * connector. + * o Publish transport parameters + * that will be in effect during + * this connection. + * | + * | + * V + * XenbusStateInitialised + * + * o Query frontend transport parameters. + * o Connect to the event channels. + * | + * | + * V + * XenbusStateConnected + * + * o Create and initialize OS + * virtual display connectors + * as per configuration. + * | + * | + * V + * XenbusStateConnected + * + * XenbusStateUnknown + * XenbusStateClosed + * XenbusStateClosing + * o Remove virtual display device + * o Remove event channels + * | + * | + * V + * XenbusStateClosed + * + *------------------------------- Recovery flow ------------------------------- + * + * In case of frontend unrecoverable errors backend handles that as + * if frontend goes into the XenbusStateClosed state. + * + * In case of backend unrecoverable errors frontend tries removing + * the virtualized device. If this is possible at the moment of error, + * then frontend goes into the XenbusStateInitialising state and is ready for + * new connection with backend. If the virtualized device is still in use and + * cannot be removed, then frontend goes into the XenbusStateReconfiguring state + * until either the virtualized device is removed or backend initiates a new + * connection. On the virtualized device removal frontend goes into the + * XenbusStateInitialising state. + * + * Note on XenbusStateReconfiguring state of the frontend: if backend has + * unrecoverable errors then frontend cannot send requests to the backend + * and thus cannot provide functionality of the virtualized device anymore. + * After backend is back to normal the virtualized device may still hold some + * state: configuration in use, allocated buffers, client application state etc. + * In most cases, this will require frontend to implement complex recovery + * reconnect logic. Instead, by going into XenbusStateReconfiguring state, + * frontend will make sure no new clients of the virtualized device are + * accepted, allow existing client(s) to exit gracefully by signaling error + * state etc. + * Once all the clients are gone frontend can reinitialize the virtualized + * device and get into XenbusStateInitialising state again signaling the + * backend that a new connection can be made. + * + * There are multiple conditions possible under which frontend will go from + * XenbusStateReconfiguring into XenbusStateInitialising, some of them are OS + * specific. For example: + * 1. The underlying OS framework may provide callbacks to signal that the last + * client of the virtualized device has gone and the device can be removed + * 2. Frontend can schedule a deferred work (timer/tasklet/workqueue) + * to periodically check if this is the right time to re-try removal of + * the virtualized device. + * 3. By any other means. + * + ****************************************************************************** + * REQUEST CODES + ****************************************************************************** + * Request codes [0; 15] are reserved and must not be used + */ + +#define XENDISPL_OP_DBUF_CREATE 0x10 +#define XENDISPL_OP_DBUF_DESTROY 0x11 +#define XENDISPL_OP_FB_ATTACH 0x12 +#define XENDISPL_OP_FB_DETACH 0x13 +#define XENDISPL_OP_SET_CONFIG 0x14 +#define XENDISPL_OP_PG_FLIP 0x15 +/* The below command is available in protocol version 2 and above. */ +#define XENDISPL_OP_GET_EDID 0x16 + +/* + ****************************************************************************** + * EVENT CODES + ****************************************************************************** + */ +#define XENDISPL_EVT_PG_FLIP 0x00 + +/* + ****************************************************************************** + * XENSTORE FIELD AND PATH NAME STRINGS, HELPERS + ****************************************************************************** + */ +#define XENDISPL_DRIVER_NAME "vdispl" + +#define XENDISPL_LIST_SEPARATOR "," +#define XENDISPL_RESOLUTION_SEPARATOR "x" + +#define XENDISPL_FIELD_BE_VERSIONS "versions" +#define XENDISPL_FIELD_FE_VERSION "version" +#define XENDISPL_FIELD_REQ_RING_REF "req-ring-ref" +#define XENDISPL_FIELD_REQ_CHANNEL "req-event-channel" +#define XENDISPL_FIELD_EVT_RING_REF "evt-ring-ref" +#define XENDISPL_FIELD_EVT_CHANNEL "evt-event-channel" +#define XENDISPL_FIELD_RESOLUTION "resolution" +#define XENDISPL_FIELD_BE_ALLOC "be-alloc" +#define XENDISPL_FIELD_UNIQUE_ID "unique-id" + +#define XENDISPL_EDID_BLOCK_SIZE 128 +#define XENDISPL_EDID_BLOCK_COUNT 256 +#define XENDISPL_EDID_MAX_SIZE (XENDISPL_EDID_BLOCK_SIZE * XENDISPL_EDID_BLOCK_COUNT) + +/* + ****************************************************************************** + * STATUS RETURN CODES + ****************************************************************************** + * + * Status return code is zero on success and -XEN_EXX on failure. + * + ****************************************************************************** + * Assumptions + ****************************************************************************** + * o usage of grant reference 0 as invalid grant reference: + * grant reference 0 is valid, but never exposed to a PV driver, + * because of the fact it is already in use/reserved by the PV console. + * o all references in this document to page sizes must be treated + * as pages of size XEN_PAGE_SIZE unless otherwise noted. + * + ****************************************************************************** + * Description of the protocol between frontend and backend driver + ****************************************************************************** + * + * The two halves of a Para-virtual display driver communicate with + * each other using shared pages and event channels. + * Shared page contains a ring with request/response packets. + * + * All reserved fields in the structures below must be 0. + * Display buffers's cookie of value 0 is treated as invalid. + * Framebuffer's cookie of value 0 is treated as invalid. + * + * For all request/response/event packets that use cookies: + * dbuf_cookie - uint64_t, unique to guest domain value used by the backend + * to map remote display buffer to its local one + * fb_cookie - uint64_t, unique to guest domain value used by the backend + * to map remote framebuffer to its local one + * + *---------------------------------- Requests --------------------------------- + * + * All requests/responses, which are not connector specific, must be sent over + * control ring of the connector which has the index value of 0: + * /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref + * + * All request packets have the same length (64 octets) + * All request packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * id - uint16_t, private guest value, echoed in response + * operation - uint8_t, operation code, XENDISPL_OP_??? + * + * Request dbuf creation - request creation of a display buffer. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id |_OP_DBUF_CREATE | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | width | 20 + * +----------------+----------------+----------------+----------------+ + * | height | 24 + * +----------------+----------------+----------------+----------------+ + * | bpp | 28 + * +----------------+----------------+----------------+----------------+ + * | buffer_sz | 32 + * +----------------+----------------+----------------+----------------+ + * | flags | 36 + * +----------------+----------------+----------------+----------------+ + * | gref_directory | 40 + * +----------------+----------------+----------------+----------------+ + * | data_ofs | 44 + * +----------------+----------------+----------------+----------------+ + * | reserved | 48 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Must be sent over control ring of the connector which has the index + * value of 0: + * /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref + * All unused bits in flags field must be set to 0. + * + * An attempt to create multiple display buffers with the same dbuf_cookie is + * an error. dbuf_cookie can be re-used after destroying the corresponding + * display buffer. + * + * Width and height of the display buffers can be smaller, equal or bigger + * than the connector's resolution. Depth/pixel format of the individual + * buffers can differ as well. + * + * width - uint32_t, width in pixels + * height - uint32_t, height in pixels + * bpp - uint32_t, bits per pixel + * buffer_sz - uint32_t, buffer size to be allocated, octets + * flags - uint32_t, flags of the operation + * o XENDISPL_DBUF_FLG_REQ_ALLOC - if set, then backend is requested + * to allocate the buffer with the parameters provided in this request. + * Page directory is handled as follows: + * Frontend on request: + * o allocates pages for the directory (gref_directory, + * gref_dir_next_page(s) + * o grants permissions for the pages of the directory to the backend + * o sets gref_dir_next_page fields + * Backend on response: + * o grants permissions for the pages of the buffer allocated to + * the frontend + * o fills in page directory with grant references + * (gref[] in struct xendispl_page_directory) + * gref_directory - grant_ref_t, a reference to the first shared page + * describing shared buffer references. At least one page exists. If shared + * buffer size (buffer_sz) exceeds what can be addressed by this single page, + * then reference to the next page must be supplied (see gref_dir_next_page + * below) + * data_ofs - uint32_t, offset of the data in the buffer, octets + */ + +#define XENDISPL_DBUF_FLG_REQ_ALLOC (1 << 0) + +struct xendispl_dbuf_create_req { + uint64_t dbuf_cookie; + uint32_t width; + uint32_t height; + uint32_t bpp; + uint32_t buffer_sz; + uint32_t flags; + grant_ref_t gref_directory; + uint32_t data_ofs; +}; + +/* + * Shared page for XENDISPL_OP_DBUF_CREATE buffer descriptor (gref_directory in + * the request) employs a list of pages, describing all pages of the shared + * data buffer: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | gref_dir_next_page | 4 + * +----------------+----------------+----------------+----------------+ + * | gref[0] | 8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | gref[i] | i*4+8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | gref[N - 1] | N*4+8 + * +----------------+----------------+----------------+----------------+ + * + * gref_dir_next_page - grant_ref_t, reference to the next page describing + * page directory. Must be 0 if there are no more pages in the list. + * gref[i] - grant_ref_t, reference to a shared page of the buffer + * allocated at XENDISPL_OP_DBUF_CREATE + * + * Number of grant_ref_t entries in the whole page directory is not + * passed, but instead can be calculated as: + * num_grefs_total = (XENDISPL_OP_DBUF_CREATE.buffer_sz + XEN_PAGE_SIZE - 1) / + * XEN_PAGE_SIZE + */ + +struct xendispl_page_directory { + grant_ref_t gref_dir_next_page; + grant_ref_t gref[]; +}; + +/* + * Request dbuf destruction - destroy a previously allocated display buffer: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id |_OP_DBUF_DESTROY| reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Must be sent over control ring of the connector which has the index + * value of 0: + * /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref + */ + +struct xendispl_dbuf_destroy_req { + uint64_t dbuf_cookie; +}; + +/* + * Request framebuffer attachment - request attachment of a framebuffer to + * previously created display buffer. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_FB_ATTACH | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | dbuf_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie low 32-bit | 20 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie high 32-bit | 24 + * +----------------+----------------+----------------+----------------+ + * | width | 28 + * +----------------+----------------+----------------+----------------+ + * | height | 32 + * +----------------+----------------+----------------+----------------+ + * | pixel_format | 36 + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Must be sent over control ring of the connector which has the index + * value of 0: + * /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref + * Width and height can be smaller, equal or bigger than the connector's + * resolution. + * + * An attempt to create multiple frame buffers with the same fb_cookie is + * an error. fb_cookie can be re-used after destroying the corresponding + * frame buffer. + * + * width - uint32_t, width in pixels + * height - uint32_t, height in pixels + * pixel_format - uint32_t, pixel format of the framebuffer, FOURCC code + */ + +struct xendispl_fb_attach_req { + uint64_t dbuf_cookie; + uint64_t fb_cookie; + uint32_t width; + uint32_t height; + uint32_t pixel_format; +}; + +/* + * Request framebuffer detach - detach a previously + * attached framebuffer from the display buffer in request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_FB_DETACH | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Must be sent over control ring of the connector which has the index + * value of 0: + * /local/domain/<dom-id>/device/vdispl/<dev-id>/0/req-ring-ref + */ + +struct xendispl_fb_detach_req { + uint64_t fb_cookie; +}; + +/* + * Request configuration set/reset - request to set or reset + * the configuration/mode of the display: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_SET_CONFIG | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | x | 20 + * +----------------+----------------+----------------+----------------+ + * | y | 24 + * +----------------+----------------+----------------+----------------+ + * | width | 28 + * +----------------+----------------+----------------+----------------+ + * | height | 32 + * +----------------+----------------+----------------+----------------+ + * | bpp | 40 + * +----------------+----------------+----------------+----------------+ + * | reserved | 44 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Pass all zeros to reset, otherwise command is treated as + * configuration set. + * Framebuffer's cookie defines which framebuffer/dbuf must be + * displayed while enabling display (applying configuration). + * x, y, width and height are bound by the connector's resolution and must not + * exceed it. + * + * x - uint32_t, starting position in pixels by X axis + * y - uint32_t, starting position in pixels by Y axis + * width - uint32_t, width in pixels + * height - uint32_t, height in pixels + * bpp - uint32_t, bits per pixel + */ + +struct xendispl_set_config_req { + uint64_t fb_cookie; + uint32_t x; + uint32_t y; + uint32_t width; + uint32_t height; + uint32_t bpp; +}; + +/* + * Request page flip - request to flip a page identified by the framebuffer + * cookie: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_PG_FLIP | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + */ + +struct xendispl_page_flip_req { + uint64_t fb_cookie; +}; + +/* + * Request EDID - request EDID describing current connector: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_GET_EDID | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | buffer_sz | 8 + * +----------------+----------------+----------------+----------------+ + * | gref_directory | 12 + * +----------------+----------------+----------------+----------------+ + * | reserved | 16 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Notes: + * - This command is not available in protocol version 1 and should be + * ignored. + * - This request is optional and if not supported then visible area + * is defined by the relevant XenStore's "resolution" property. + * - Shared buffer, allocated for EDID storage, must not be less then + * XENDISPL_EDID_MAX_SIZE octets. + * + * buffer_sz - uint32_t, buffer size to be allocated, octets + * gref_directory - grant_ref_t, a reference to the first shared page + * describing EDID buffer references. See XENDISPL_OP_DBUF_CREATE for + * grant page directory structure (struct xendispl_page_directory). + * + * See response format for this request. + */ + +struct xendispl_get_edid_req { + uint32_t buffer_sz; + grant_ref_t gref_directory; +}; + +/* + *---------------------------------- Responses -------------------------------- + * + * All response packets have the same length (64 octets) + * + * All response packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | status | 8 + * +----------------+----------------+----------------+----------------+ + * | reserved | 12 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * id - uint16_t, private guest value, echoed from request + * status - int32_t, response status, zero on success and -XEN_EXX on failure + * + * + * Get EDID response - response for XENDISPL_OP_GET_EDID: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | status | 8 + * +----------------+----------------+----------------+----------------+ + * | edid_sz | 12 + * +----------------+----------------+----------------+----------------+ + * | reserved | 16 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Notes: + * - This response is not available in protocol version 1 and should be + * ignored. + * + * edid_sz - uint32_t, size of the EDID, octets + */ + +struct xendispl_get_edid_resp { + uint32_t edid_sz; +}; + +/* + *----------------------------------- Events ---------------------------------- + * + * Events are sent via a shared page allocated by the front and propagated by + * evt-event-channel/evt-ring-ref XenStore entries + * All event packets have the same length (64 octets) + * All event packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | type | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * + * id - uint16_t, event id, may be used by front + * type - uint8_t, type of the event + * + * + * Page flip complete event - event from back to front on page flip completed: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _EVT_PG_FLIP | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | fb_cookie high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + */ + +struct xendispl_pg_flip_evt { + uint64_t fb_cookie; +}; + +struct xendispl_req { + uint16_t id; + uint8_t operation; + uint8_t reserved[5]; + union { + struct xendispl_dbuf_create_req dbuf_create; + struct xendispl_dbuf_destroy_req dbuf_destroy; + struct xendispl_fb_attach_req fb_attach; + struct xendispl_fb_detach_req fb_detach; + struct xendispl_set_config_req set_config; + struct xendispl_page_flip_req pg_flip; + struct xendispl_get_edid_req get_edid; + uint8_t reserved[56]; + } op; +}; + +struct xendispl_resp { + uint16_t id; + uint8_t operation; + uint8_t reserved; + int32_t status; + union { + struct xendispl_get_edid_resp get_edid; + uint8_t reserved1[56]; + } op; +}; + +struct xendispl_evt { + uint16_t id; + uint8_t type; + uint8_t reserved[5]; + union { + struct xendispl_pg_flip_evt pg_flip; + uint8_t reserved[56]; + } op; +}; + +DEFINE_RING_TYPES(xen_displif, struct xendispl_req, struct xendispl_resp); + +/* + ****************************************************************************** + * Back to front events delivery + ****************************************************************************** + * In order to deliver asynchronous events from back to front a shared page is + * allocated by front and its granted reference propagated to back via + * XenStore entries (evt-ring-ref/evt-event-channel). + * This page has a common header used by both front and back to synchronize + * access and control event's ring buffer, while back being a producer of the + * events and front being a consumer. The rest of the page after the header + * is used for event packets. + * + * Upon reception of an event(s) front may confirm its reception + * for either each event, group of events or none. + */ + +struct xendispl_event_page { + uint32_t in_cons; + uint32_t in_prod; + uint8_t reserved[56]; +}; + +#define XENDISPL_EVENT_PAGE_SIZE XEN_PAGE_SIZE +#define XENDISPL_IN_RING_OFFS (sizeof(struct xendispl_event_page)) +#define XENDISPL_IN_RING_SIZE (XENDISPL_EVENT_PAGE_SIZE - XENDISPL_IN_RING_OFFS) +#define XENDISPL_IN_RING_LEN (XENDISPL_IN_RING_SIZE / sizeof(struct xendispl_evt)) +#define XENDISPL_IN_RING(page) \ + ((struct xendispl_evt *)((char *)(page) + XENDISPL_IN_RING_OFFS)) +#define XENDISPL_IN_RING_REF(page, idx) \ + (XENDISPL_IN_RING((page))[(idx) % XENDISPL_IN_RING_LEN]) + +#endif /* __XEN_PUBLIC_IO_DISPLIF_H__ */ diff --git a/include/xen/interface/io/fbif.h b/include/xen/interface/io/fbif.h index 974a51ed9165..60ca808cef97 100644 --- a/include/xen/interface/io/fbif.h +++ b/include/xen/interface/io/fbif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * fbif.h -- Xen virtual frame buffer device * - * 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) 2005 Anthony Liguori <aliguori@us.ibm.com> * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com> */ diff --git a/include/xen/interface/io/kbdif.h b/include/xen/interface/io/kbdif.h index 8066c7849fbe..b8b08aa53325 100644 --- a/include/xen/interface/io/kbdif.h +++ b/include/xen/interface/io/kbdif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * kbdif.h -- Xen virtual keyboard/mouse * - * 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) 2005 Anthony Liguori <aliguori@us.ibm.com> * Copyright (C) 2006 Red Hat, Inc., Markus Armbruster <armbru@redhat.com> */ @@ -26,43 +9,472 @@ #ifndef __XEN_PUBLIC_IO_KBDIF_H__ #define __XEN_PUBLIC_IO_KBDIF_H__ -/* In events (backend -> frontend) */ +/* + ***************************************************************************** + * Feature and Parameter Negotiation + ***************************************************************************** + * + * The two halves of a para-virtual driver utilize nodes within + * XenStore to communicate capabilities and to negotiate operating parameters. + * This section enumerates these nodes which reside in the respective front and + * backend portions of XenStore, following XenBus convention. + * + * All data in XenStore is stored as strings. Nodes specifying numeric + * values are encoded in decimal. Integer value ranges listed below are + * expressed as fixed sized integer types capable of storing the conversion + * of a properly formated node string, without loss of information. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *---------------------------- Features supported ---------------------------- + * + * Capable backend advertises supported features by publishing + * corresponding entries in XenStore and puts 1 as the value of the entry. + * If a feature is not supported then 0 must be set or feature entry omitted. + * + * feature-disable-keyboard + * Values: <uint> + * + * If there is no need to expose a virtual keyboard device by the + * frontend then this must be set to 1. + * + * feature-disable-pointer + * Values: <uint> + * + * If there is no need to expose a virtual pointer device by the + * frontend then this must be set to 1. + * + * feature-abs-pointer + * Values: <uint> + * + * Backends, which support reporting of absolute coordinates for pointer + * device should set this to 1. + * + * feature-multi-touch + * Values: <uint> + * + * Backends, which support reporting of multi-touch events + * should set this to 1. + * + * feature-raw-pointer + * Values: <uint> + * + * Backends, which support reporting raw (unscaled) absolute coordinates + * for pointer devices should set this to 1. Raw (unscaled) values have + * a range of [0, 0x7fff]. + * + *----------------------- Device Instance Parameters ------------------------ + * + * unique-id + * Values: <string> + * + * After device instance initialization it is assigned a unique ID, + * so every instance of the frontend can be identified by the backend + * by this ID. This can be UUID or such. + * + *------------------------- Pointer Device Parameters ------------------------ + * + * width + * Values: <uint> + * + * Maximum X coordinate (width) to be used by the frontend + * while reporting input events, pixels, [0; UINT32_MAX]. + * + * height + * Values: <uint> + * + * Maximum Y coordinate (height) to be used by the frontend + * while reporting input events, pixels, [0; UINT32_MAX]. + * + *----------------------- Multi-touch Device Parameters ---------------------- + * + * multi-touch-num-contacts + * Values: <uint> + * + * Number of simultaneous touches reported. + * + * multi-touch-width + * Values: <uint> + * + * Width of the touch area to be used by the frontend + * while reporting input events, pixels, [0; UINT32_MAX]. + * + * multi-touch-height + * Values: <uint> + * + * Height of the touch area to be used by the frontend + * while reporting input events, pixels, [0; UINT32_MAX]. + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *------------------------------ Feature request ----------------------------- + * + * Capable frontend requests features from backend via setting corresponding + * entries to 1 in XenStore. Requests for features not advertised as supported + * by the backend have no effect. + * + * request-abs-pointer + * Values: <uint> + * + * Request backend to report absolute pointer coordinates + * (XENKBD_TYPE_POS) instead of relative ones (XENKBD_TYPE_MOTION). + * + * request-multi-touch + * Values: <uint> + * + * Request backend to report multi-touch events. + * + * request-raw-pointer + * Values: <uint> + * + * Request backend to report raw unscaled absolute pointer coordinates. + * This option is only valid if request-abs-pointer is also set. + * Raw unscaled coordinates have the range [0, 0x7fff] + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: <uint> + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * page-gref + * Values: <uint> + * + * The Xen grant reference granting permission for the backend to map + * a sole page in a single page sized event ring buffer. + * + * page-ref + * Values: <uint> + * + * OBSOLETE, not recommended for use. + * PFN of the shared page. + */ /* - * Frontends should ignore unknown in events. + * EVENT CODES. + */ + +#define XENKBD_TYPE_MOTION 1 +#define XENKBD_TYPE_RESERVED 2 +#define XENKBD_TYPE_KEY 3 +#define XENKBD_TYPE_POS 4 +#define XENKBD_TYPE_MTOUCH 5 + +/* Multi-touch event sub-codes */ + +#define XENKBD_MT_EV_DOWN 0 +#define XENKBD_MT_EV_UP 1 +#define XENKBD_MT_EV_MOTION 2 +#define XENKBD_MT_EV_SYN 3 +#define XENKBD_MT_EV_SHAPE 4 +#define XENKBD_MT_EV_ORIENT 5 + +/* + * CONSTANTS, XENSTORE FIELD AND PATH NAME STRINGS, HELPERS. */ -/* Pointer movement event */ -#define XENKBD_TYPE_MOTION 1 -/* Event type 2 currently not used */ -/* Key event (includes pointer buttons) */ -#define XENKBD_TYPE_KEY 3 +#define XENKBD_DRIVER_NAME "vkbd" + +#define XENKBD_FIELD_FEAT_DSBL_KEYBRD "feature-disable-keyboard" +#define XENKBD_FIELD_FEAT_DSBL_POINTER "feature-disable-pointer" +#define XENKBD_FIELD_FEAT_ABS_POINTER "feature-abs-pointer" +#define XENKBD_FIELD_FEAT_RAW_POINTER "feature-raw-pointer" +#define XENKBD_FIELD_FEAT_MTOUCH "feature-multi-touch" +#define XENKBD_FIELD_REQ_ABS_POINTER "request-abs-pointer" +#define XENKBD_FIELD_REQ_RAW_POINTER "request-raw-pointer" +#define XENKBD_FIELD_REQ_MTOUCH "request-multi-touch" +#define XENKBD_FIELD_RING_GREF "page-gref" +#define XENKBD_FIELD_EVT_CHANNEL "event-channel" +#define XENKBD_FIELD_WIDTH "width" +#define XENKBD_FIELD_HEIGHT "height" +#define XENKBD_FIELD_MT_WIDTH "multi-touch-width" +#define XENKBD_FIELD_MT_HEIGHT "multi-touch-height" +#define XENKBD_FIELD_MT_NUM_CONTACTS "multi-touch-num-contacts" +#define XENKBD_FIELD_UNIQUE_ID "unique-id" + +/* OBSOLETE, not recommended for use */ +#define XENKBD_FIELD_RING_REF "page-ref" + /* - * Pointer position event - * Capable backend sets feature-abs-pointer in xenstore. - * Frontend requests ot instead of XENKBD_TYPE_MOTION by setting - * request-abs-update in xenstore. + ***************************************************************************** + * Description of the protocol between frontend and backend driver. + ***************************************************************************** + * + * The two halves of a Para-virtual driver communicate with + * each other using a shared page and an event channel. + * Shared page contains a ring with event structures. + * + * All reserved fields in the structures below must be 0. + * + ***************************************************************************** + * Backend to frontend events + ***************************************************************************** + * + * Frontends should ignore unknown in events. + * All event packets have the same length (40 octets) + * All event packets have common header: + * + * 0 octet + * +-----------------+ + * | type | + * +-----------------+ + * type - uint8_t, event code, XENKBD_TYPE_??? + * + * + * Pointer relative movement event + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MOTION | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | rel_x | 8 + * +----------------+----------------+----------------+----------------+ + * | rel_y | 12 + * +----------------+----------------+----------------+----------------+ + * | rel_z | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * rel_x - int32_t, relative X motion + * rel_y - int32_t, relative Y motion + * rel_z - int32_t, relative Z motion (wheel) */ -#define XENKBD_TYPE_POS 4 struct xenkbd_motion { - uint8_t type; /* XENKBD_TYPE_MOTION */ - int32_t rel_x; /* relative X motion */ - int32_t rel_y; /* relative Y motion */ - int32_t rel_z; /* relative Z motion (wheel) */ + uint8_t type; + int32_t rel_x; + int32_t rel_y; + int32_t rel_z; }; +/* + * Key event (includes pointer buttons) + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_KEY | pressed | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | keycode | 8 + * +----------------+----------------+----------------+----------------+ + * | reserved | 12 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * pressed - uint8_t, 1 if pressed; 0 otherwise + * keycode - uint32_t, KEY_* from linux/input.h + */ + struct xenkbd_key { - uint8_t type; /* XENKBD_TYPE_KEY */ - uint8_t pressed; /* 1 if pressed; 0 otherwise */ - uint32_t keycode; /* KEY_* from linux/input.h */ + uint8_t type; + uint8_t pressed; + uint32_t keycode; }; +/* + * Pointer absolute position event + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_POS | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | abs_x | 8 + * +----------------+----------------+----------------+----------------+ + * | abs_y | 12 + * +----------------+----------------+----------------+----------------+ + * | rel_z | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * abs_x - int32_t, absolute X position (in FB pixels) + * abs_y - int32_t, absolute Y position (in FB pixels) + * rel_z - int32_t, relative Z motion (wheel) + */ + struct xenkbd_position { - uint8_t type; /* XENKBD_TYPE_POS */ - int32_t abs_x; /* absolute X position (in FB pixels) */ - int32_t abs_y; /* absolute Y position (in FB pixels) */ - int32_t rel_z; /* relative Z motion (wheel) */ + uint8_t type; + int32_t abs_x; + int32_t abs_y; + int32_t rel_z; +}; + +/* + * Multi-touch event and its sub-types + * + * All multi-touch event packets have common header: + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | event_type | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * + * event_type - unt8_t, multi-touch event sub-type, XENKBD_MT_EV_??? + * contact_id - unt8_t, ID of the contact + * + * Touch interactions can consist of one or more contacts. + * For each contact, a series of events is generated, starting + * with a down event, followed by zero or more motion events, + * and ending with an up event. Events relating to the same + * contact point can be identified by the ID of the sequence: contact ID. + * Contact ID may be reused after XENKBD_MT_EV_UP event and + * is in the [0; XENKBD_FIELD_NUM_CONTACTS - 1] range. + * + * For further information please refer to documentation on Wayland [1], + * Linux [2] and Windows [3] multi-touch support. + * + * [1] https://cgit.freedesktop.org/wayland/wayland/tree/protocol/wayland.xml + * [2] https://www.kernel.org/doc/Documentation/input/multi-touch-protocol.rst + * [3] https://msdn.microsoft.com/en-us/library/jj151564(v=vs.85).aspx + * + * + * Multi-touch down event - sent when a new touch is made: touch is assigned + * a unique contact ID, sent with this and consequent events related + * to this touch. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_DOWN | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | abs_x | 12 + * +----------------+----------------+----------------+----------------+ + * | abs_y | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * abs_x - int32_t, absolute X position, in pixels + * abs_y - int32_t, absolute Y position, in pixels + * + * Multi-touch contact release event + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_UP | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * Multi-touch motion event + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_MOTION | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | abs_x | 12 + * +----------------+----------------+----------------+----------------+ + * | abs_y | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * abs_x - int32_t, absolute X position, in pixels, + * abs_y - int32_t, absolute Y position, in pixels, + * + * Multi-touch input synchronization event - shows end of a set of events + * which logically belong together. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_SYN | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * Multi-touch shape event - touch point's shape has changed its shape. + * Shape is approximated by an ellipse through the major and minor axis + * lengths: major is the longer diameter of the ellipse and minor is the + * shorter one. Center of the ellipse is reported via + * XENKBD_MT_EV_DOWN/XENKBD_MT_EV_MOTION events. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_SHAPE | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | major | 12 + * +----------------+----------------+----------------+----------------+ + * | minor | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * major - unt32_t, length of the major axis, pixels + * minor - unt32_t, length of the minor axis, pixels + * + * Multi-touch orientation event - touch point's shape has changed + * its orientation: calculated as a clockwise angle between the major axis + * of the ellipse and positive Y axis in degrees, [-180; +180]. + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | _TYPE_MTOUCH | _MT_EV_ORIENT | contact_id | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | orientation | reserved | 12 + * +----------------+----------------+----------------+----------------+ + * | reserved | 16 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 40 + * +----------------+----------------+----------------+----------------+ + * + * orientation - int16_t, clockwise angle of the major axis + */ + +struct xenkbd_mtouch { + uint8_t type; /* XENKBD_TYPE_MTOUCH */ + uint8_t event_type; /* XENKBD_MT_EV_??? */ + uint8_t contact_id; + uint8_t reserved[5]; /* reserved for the future use */ + union { + struct { + int32_t abs_x; /* absolute X position, pixels */ + int32_t abs_y; /* absolute Y position, pixels */ + } pos; + struct { + uint32_t major; /* length of the major axis, pixels */ + uint32_t minor; /* length of the minor axis, pixels */ + } shape; + int16_t orientation; /* clockwise angle of the major axis */ + } u; }; #define XENKBD_IN_EVENT_SIZE 40 @@ -72,15 +484,26 @@ union xenkbd_in_event { struct xenkbd_motion motion; struct xenkbd_key key; struct xenkbd_position pos; + struct xenkbd_mtouch mtouch; char pad[XENKBD_IN_EVENT_SIZE]; }; -/* Out events (frontend -> backend) */ - /* + ***************************************************************************** + * Frontend to backend events + ***************************************************************************** + * * Out events may be sent only when requested by backend, and receipt * of an unknown out event is an error. * No out events currently defined. + + * All event packets have the same length (40 octets) + * All event packets have common header: + * 0 octet + * +-----------------+ + * | type | + * +-----------------+ + * type - uint8_t, event code */ #define XENKBD_OUT_EVENT_SIZE 40 @@ -90,7 +513,11 @@ union xenkbd_out_event { char pad[XENKBD_OUT_EVENT_SIZE]; }; -/* shared page */ +/* + ***************************************************************************** + * Shared page + ***************************************************************************** + */ #define XENKBD_IN_RING_SIZE 2048 #define XENKBD_IN_RING_LEN (XENKBD_IN_RING_SIZE / XENKBD_IN_EVENT_SIZE) @@ -113,4 +540,4 @@ struct xenkbd_page { uint32_t out_cons, out_prod; }; -#endif +#endif /* __XEN_PUBLIC_IO_KBDIF_H__ */ diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index eb262e3324d2..cb0c1a25d5d4 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -1,16 +1,17 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** - * netif.h + * xen_netif.h * * Unified network-device I/O interface for Xen guest OSes. * * Copyright (c) 2003-2004, Keir Fraser */ -#ifndef __XEN_PUBLIC_IO_NETIF_H__ -#define __XEN_PUBLIC_IO_NETIF_H__ +#ifndef __XEN_PUBLIC_IO_XEN_NETIF_H__ +#define __XEN_PUBLIC_IO_XEN_NETIF_H__ -#include <xen/interface/io/ring.h> -#include <xen/interface/grant_table.h> +#include "ring.h" +#include "../grant_table.h" /* * Older implementation of Xen network frontend / backend has an @@ -38,10 +39,10 @@ * that it cannot safely queue packets (as it may not be kicked to send them). */ - /* +/* * "feature-split-event-channels" is introduced to separate guest TX - * and RX notificaion. Backend either doesn't support this feature or - * advertise it via xenstore as 0 (disabled) or 1 (enabled). + * and RX notification. Backend either doesn't support this feature or + * advertises it via xenstore as 0 (disabled) or 1 (enabled). * * To make use of this feature, frontend should allocate two event * channels for TX and RX, advertise them to backend as @@ -51,143 +52,889 @@ */ /* - * This is the 'wire' format for packets: - * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags) - * [Request 2: xen_netif_extra_info] (only if request 1 has XEN_NETTXF_extra_info) - * [Request 3: xen_netif_extra_info] (only if request 2 has XEN_NETIF_EXTRA_MORE) - * Request 4: xen_netif_tx_request -- XEN_NETTXF_more_data - * Request 5: xen_netif_tx_request -- XEN_NETTXF_more_data + * Multiple transmit and receive queues: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vif, and set its value to the maximum supported + * number of queues. + * Frontends that are aware of this feature and wish to use it can write the + * key "multi-queue-num-queues", set to the number they wish to use, which + * must be greater than zero, and no more than the value reported by the backend + * in "multi-queue-max-queues". + * + * Queues replicate the shared rings and event channels. + * "feature-split-event-channels" may optionally be used when using + * multiple queues, but is not mandatory. + * + * Each queue consists of one shared ring pair, i.e. there must be the same + * number of tx and rx rings. + * + * For frontends requesting just one queue, the usual event-channel and + * ring-ref keys are written as before, simplifying the backend processing + * to avoid distinguishing between a frontend that doesn't understand the + * multi-queue feature, and one that does, but requested only one queue. + * + * Frontends requesting two or more queues must not write the toplevel + * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys, + * instead writing those keys under sub-keys having the name "queue-N" where + * N is the integer ID of the queue for which those keys belong. Queues + * are indexed from zero. For example, a frontend with two queues and split + * event channels must write the following set of queue-related keys: + * + * /local/domain/1/device/vif/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vif/0/queue-0 = "" + * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>" + * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>" + * /local/domain/1/device/vif/0/queue-1 = "" + * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>" + * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1" + * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>" + * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>" + * + * If there is any inconsistency in the XenStore data, the backend may + * choose not to connect any queues, instead treating the request as an + * error. This includes scenarios where more (or fewer) queues were + * requested than the frontend provided details for. + * + * Mapping of packets to queues is considered to be a function of the + * transmitting system (backend or frontend) and is not negotiated + * between the two. Guests are free to transmit packets on any queue + * they choose, provided it has been set up correctly. Guests must be + * prepared to receive packets on any queue they have requested be set up. + */ + +/* + * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum + * offload off or on. If it is missing then the feature is assumed to be on. + * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum + * offload on or off. If it is missing then the feature is assumed to be off. + */ + +/* + * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to + * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither + * frontends nor backends are assumed to be capable unless the flags are + * present. + */ + +/* + * "feature-multicast-control" and "feature-dynamic-multicast-control" + * advertise the capability to filter ethernet multicast packets in the + * backend. If the frontend wishes to take advantage of this feature then + * it may set "request-multicast-control". If the backend only advertises + * "feature-multicast-control" then "request-multicast-control" must be set + * before the frontend moves into the connected state. The backend will + * sample the value on this state transition and any subsequent change in + * value will have no effect. However, if the backend also advertises + * "feature-dynamic-multicast-control" then "request-multicast-control" + * may be set by the frontend at any time. In this case, the backend will + * watch the value and re-sample on watch events. + * + * If the sampled value of "request-multicast-control" is set then the + * backend transmit side should no longer flood multicast packets to the + * frontend, it should instead drop any multicast packet that does not + * match in a filter list. + * The list is amended by the frontend by sending dummy transmit requests + * containing XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} extra-info fragments as + * specified below. + * Note that the filter list may be amended even if the sampled value of + * "request-multicast-control" is not set, however the filter should only + * be applied if it is set. + */ + +/* + * "xdp-headroom" is used to request that extra space is added + * for XDP processing. The value is measured in bytes and passed by + * the frontend to be consistent between both ends. + * If the value is greater than zero that means that + * an RX response is going to be passed to an XDP program for processing. + * XEN_NETIF_MAX_XDP_HEADROOM defines the maximum headroom offset in bytes + * + * "feature-xdp-headroom" is set to "1" by the netback side like other features + * so a guest can check if an XDP program can be processed. + */ +#define XEN_NETIF_MAX_XDP_HEADROOM 0x7FFF + +/* + * Control ring + * ============ + * + * Some features, such as hashing (detailed below), require a + * significant amount of out-of-band data to be passed from frontend to + * backend. Use of xenstore is not suitable for large quantities of data + * because of quota limitations and so a dedicated 'control ring' is used. + * The ability of the backend to use a control ring is advertised by + * setting: + * + * /local/domain/X/backend/<domid>/<vif>/feature-ctrl-ring = "1" + * + * The frontend provides a control ring to the backend by setting: + * + * /local/domain/<domid>/device/vif/<vif>/ctrl-ring-ref = <gref> + * /local/domain/<domid>/device/vif/<vif>/event-channel-ctrl = <port> + * + * where <gref> is the grant reference of the shared page used to + * implement the control ring and <port> is an event channel to be used + * as a mailbox interrupt. These keys must be set before the frontend + * moves into the connected state. + * + * The control ring uses a fixed request/response message size and is + * balanced (i.e. one request to one response), so operationally it is much + * the same as a transmit or receive ring. + * Note that there is no requirement that responses are issued in the same + * order as requests. + */ + +/* + * Hash types + * ========== + * + * For the purposes of the definitions below, 'Packet[]' is an array of + * octets containing an IP packet without options, 'Array[X..Y]' means a + * sub-array of 'Array' containing bytes X thru Y inclusive, and '+' is + * used to indicate concatenation of arrays. + */ + +/* + * A hash calculated over an IP version 4 header as follows: + * + * Buffer[0..8] = Packet[12..15] (source address) + + * Packet[16..19] (destination address) + * + * Result = Hash(Buffer, 8) + */ +#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4 0 +#define XEN_NETIF_CTRL_HASH_TYPE_IPV4 \ + (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4) + +/* + * A hash calculated over an IP version 4 header and TCP header as + * follows: + * + * Buffer[0..12] = Packet[12..15] (source address) + + * Packet[16..19] (destination address) + + * Packet[20..21] (source port) + + * Packet[22..23] (destination port) + * + * Result = Hash(Buffer, 12) + */ +#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP 1 +#define XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP \ + (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP) + +/* + * A hash calculated over an IP version 6 header as follows: + * + * Buffer[0..32] = Packet[8..23] (source address ) + + * Packet[24..39] (destination address) + * + * Result = Hash(Buffer, 32) + */ +#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6 2 +#define XEN_NETIF_CTRL_HASH_TYPE_IPV6 \ + (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6) + +/* + * A hash calculated over an IP version 6 header and TCP header as + * follows: + * + * Buffer[0..36] = Packet[8..23] (source address) + + * Packet[24..39] (destination address) + + * Packet[40..41] (source port) + + * Packet[42..43] (destination port) + * + * Result = Hash(Buffer, 36) + */ +#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP 3 +#define XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP \ + (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP) + +/* + * Hash algorithms + * =============== + */ + +#define XEN_NETIF_CTRL_HASH_ALGORITHM_NONE 0 + +/* + * Toeplitz hash: + */ + +#define XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ 1 + +/* + * This algorithm uses a 'key' as well as the data buffer itself. + * (Buffer[] and Key[] are treated as shift-registers where the MSB of + * Buffer/Key[0] is considered 'left-most' and the LSB of Buffer/Key[N-1] + * is the 'right-most'). + * + * Value = 0 + * For number of bits in Buffer[] + * If (left-most bit of Buffer[] is 1) + * Value ^= left-most 32 bits of Key[] + * Key[] << 1 + * Buffer[] << 1 + * + * The code below is provided for convenience where an operating system + * does not already provide an implementation. + */ +#ifdef XEN_NETIF_DEFINE_TOEPLITZ +static uint32_t xen_netif_toeplitz_hash(const uint8_t *key, + unsigned int keylen, + const uint8_t *buf, unsigned int buflen) +{ + unsigned int keyi, bufi; + uint64_t prefix = 0; + uint64_t hash = 0; + + /* Pre-load prefix with the first 8 bytes of the key */ + for (keyi = 0; keyi < 8; keyi++) { + prefix <<= 8; + prefix |= (keyi < keylen) ? key[keyi] : 0; + } + + for (bufi = 0; bufi < buflen; bufi++) { + uint8_t byte = buf[bufi]; + unsigned int bit; + + for (bit = 0; bit < 8; bit++) { + if (byte & 0x80) + hash ^= prefix; + prefix <<= 1; + byte <<= 1; + } + + /* + * 'prefix' has now been left-shifted by 8, so + * OR in the next byte. + */ + prefix |= (keyi < keylen) ? key[keyi] : 0; + keyi++; + } + + /* The valid part of the hash is in the upper 32 bits. */ + return hash >> 32; +} +#endif /* XEN_NETIF_DEFINE_TOEPLITZ */ + +/* + * Control requests (struct xen_netif_ctrl_request) + * ================================================ + * + * All requests have the following format: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | type | data[0] | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | data[1] | data[2] | + * +-----+-----+-----+-----+-----------------------+ + * + * id: the request identifier, echoed in response. + * type: the type of request (see below) + * data[]: any data associated with the request (determined by type) + */ + +struct xen_netif_ctrl_request { + uint16_t id; + uint16_t type; + +#define XEN_NETIF_CTRL_TYPE_INVALID 0 +#define XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS 1 +#define XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS 2 +#define XEN_NETIF_CTRL_TYPE_SET_HASH_KEY 3 +#define XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE 4 +#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE 5 +#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING 6 +#define XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM 7 + + uint32_t data[3]; +}; + +/* + * Control responses (struct xen_netif_ctrl_response) + * ================================================== + * + * All responses have the following format: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | type | status | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | data | + * +-----+-----+-----+-----+ + * + * id: the corresponding request identifier + * type: the type of the corresponding request + * status: the status of request processing + * data: any data associated with the response (determined by type and + * status) + */ + +struct xen_netif_ctrl_response { + uint16_t id; + uint16_t type; + uint32_t status; + +#define XEN_NETIF_CTRL_STATUS_SUCCESS 0 +#define XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED 1 +#define XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER 2 +#define XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW 3 + + uint32_t data; +}; + +/* + * Control messages + * ================ + * + * XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM + * -------------------------------------- + * + * This is sent by the frontend to set the desired hash algorithm. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM + * data[0] = a XEN_NETIF_CTRL_HASH_ALGORITHM_* value + * data[1] = 0 + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not + * supported + * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - The algorithm is not + * supported + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * + * NOTE: Setting data[0] to XEN_NETIF_CTRL_HASH_ALGORITHM_NONE disables + * hashing and the backend is free to choose how it steers packets + * to queues (which is the default behaviour). + * + * XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS + * ---------------------------------- + * + * This is sent by the frontend to query the types of hash supported by + * the backend. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS + * data[0] = 0 + * data[1] = 0 + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = supported hash types (if operation was successful) + * + * NOTE: A valid hash algorithm must be selected before this operation can + * succeed. + * + * XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS + * ---------------------------------- + * + * This is sent by the frontend to set the types of hash that the backend + * should calculate. (See above for hash type definitions). + * Note that the 'maximal' type of hash should always be chosen. For + * example, if the frontend sets both IPV4 and IPV4_TCP hash types then + * the latter hash type should be calculated for any TCP packet and the + * former only calculated for non-TCP packets. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS + * data[0] = bitwise OR of XEN_NETIF_CTRL_HASH_TYPE_* values + * data[1] = 0 + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not + * supported + * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - One or more flag + * value is invalid or + * unsupported + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = 0 + * + * NOTE: A valid hash algorithm must be selected before this operation can + * succeed. + * Also, setting data[0] to zero disables hashing and the backend + * is free to choose how it steers packets to queues. + * + * XEN_NETIF_CTRL_TYPE_SET_HASH_KEY + * -------------------------------- + * + * This is sent by the frontend to set the key of the hash if the algorithm + * requires it. (See hash algorithms above). + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_SET_HASH_KEY + * data[0] = grant reference of page containing the key (assumed to + * start at beginning of grant) + * data[1] = size of key in octets + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not + * supported + * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Key size is invalid + * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Key size is larger + * than the backend + * supports + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = 0 + * + * NOTE: Any key octets not specified are assumed to be zero (the key + * is assumed to be empty by default) and specifying a new key + * invalidates any previous key, hence specifying a key size of + * zero will clear the key (which ensures that the calculated hash + * will always be zero). + * The maximum size of key is algorithm and backend specific, but + * is also limited by the single grant reference. + * The grant reference may be read-only and must remain valid until + * the response has been processed. + * + * XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE + * ----------------------------------------- + * + * This is sent by the frontend to query the maximum size of mapping + * table supported by the backend. The size is specified in terms of + * table entries. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE + * data[0] = 0 + * data[1] = 0 + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = maximum number of entries allowed in the mapping table + * (if operation was successful) or zero if a mapping table is + * not supported (i.e. hash mapping is done only by modular + * arithmetic). + * + * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE + * ------------------------------------- + * + * This is sent by the frontend to set the actual size of the mapping + * table to be used by the backend. The size is specified in terms of + * table entries. + * Any previous table is invalidated by this message and any new table + * is assumed to be zero filled. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE + * data[0] = number of entries in mapping table + * data[1] = 0 + * data[2] = 0 + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not + * supported + * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size is invalid + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = 0 + * + * NOTE: Setting data[0] to 0 means that hash mapping should be done + * using modular arithmetic. + * + * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING + * ------------------------------------ + * + * This is sent by the frontend to set the content of the table mapping + * hash value to queue number. The backend should calculate the hash from + * the packet header, use it as an index into the table (modulo the size + * of the table) and then steer the packet to the queue number found at + * that index. + * + * Request: + * + * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING + * data[0] = grant reference of page containing the mapping (sub-)table + * (assumed to start at beginning of grant) + * data[1] = size of (sub-)table in entries + * data[2] = offset, in entries, of sub-table within overall table + * + * Response: + * + * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not + * supported + * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size or content + * is invalid + * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Table size is larger + * than the backend + * supports + * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful + * data = 0 + * + * NOTE: The overall table has the following format: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | mapping[0] | mapping[1] | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | . | + * | . | + * | . | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | mapping[N-2] | mapping[N-1] | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * where N is specified by a XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE + * message and each mapping must specifies a queue between 0 and + * "multi-queue-num-queues" (see above). + * The backend may support a mapping table larger than can be + * mapped by a single grant reference. Thus sub-tables within a + * larger table can be individually set by sending multiple messages + * with differing offset values. Specifying a new sub-table does not + * invalidate any table data outside that range. + * The grant reference may be read-only and must remain valid until + * the response has been processed. + */ + +DEFINE_RING_TYPES(xen_netif_ctrl, + struct xen_netif_ctrl_request, + struct xen_netif_ctrl_response); + +/* + * Guest transmit + * ============== + * + * This is the 'wire' format for transmit (frontend -> backend) packets: + * + * Fragment 1: xen_netif_tx_request_t - flags = XEN_NETTXF_* + * size = total packet size + * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include + * XEN_NETTXF_extra_info) + * ... + * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include + * XEN_NETIF_EXTRA_MORE) * ... - * Request N: xen_netif_tx_request -- 0 + * Fragment N: xen_netif_tx_request_t - (only if fragment N-1 flags include + * XEN_NETTXF_more_data - flags on preceding + * extras are not relevant here) + * flags = 0 + * size = fragment size + * + * NOTE: + * + * This format slightly is different from that used for receive + * (backend -> frontend) packets. Specifically, in a multi-fragment + * packet the actual size of fragment 1 can only be determined by + * subtracting the sizes of fragments 2..N from the total packet size. + * + * Ring slot size is 12 octets, however not all request/response + * structs use the full size. + * + * tx request data (xen_netif_tx_request_t) + * ------------------------------------ + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | grant ref | offset | flags | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | size | + * +-----+-----+-----+-----+ + * + * grant ref: Reference to buffer page. + * offset: Offset within buffer page. + * flags: XEN_NETTXF_*. + * id: request identifier, echoed in response. + * size: packet size in bytes. + * + * tx response (xen_netif_tx_response_t) + * --------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | status | unused | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | unused | + * +-----+-----+-----+-----+ + * + * id: reflects id in transmit request + * status: XEN_NETIF_RSP_* + * + * Guest receive + * ============= + * + * This is the 'wire' format for receive (backend -> frontend) packets: + * + * Fragment 1: xen_netif_rx_request_t - flags = XEN_NETRXF_* + * size = fragment size + * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include + * XEN_NETRXF_extra_info) + * ... + * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include + * XEN_NETIF_EXTRA_MORE) + * ... + * Fragment N: xen_netif_rx_request_t - (only if fragment N-1 flags include + * XEN_NETRXF_more_data - flags on preceding + * extras are not relevant here) + * flags = 0 + * size = fragment size + * + * NOTE: + * + * This format slightly is different from that used for transmit + * (frontend -> backend) packets. Specifically, in a multi-fragment + * packet the size of the packet can only be determined by summing the + * sizes of fragments 1..N. + * + * Ring slot size is 8 octets. + * + * rx request (xen_netif_rx_request_t) + * ------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | pad | gref | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * id: request identifier, echoed in response. + * gref: reference to incoming granted frame. + * + * rx response (xen_netif_rx_response_t) + * --------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | offset | flags | status | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * id: reflects id in receive request + * offset: offset in page of start of received packet + * flags: XEN_NETRXF_* + * status: -ve: XEN_NETIF_RSP_*; +ve: Rx'ed pkt size. + * + * NOTE: Historically, to support GSO on the frontend receive side, Linux + * netfront does not make use of the rx response id (because, as + * described below, extra info structures overlay the id field). + * Instead it assumes that responses always appear in the same ring + * slot as their corresponding request. Thus, to maintain + * compatibility, backends must make sure this is the case. + * + * Extra Info + * ========== + * + * Can be present if initial request or response has NET{T,R}XF_extra_info, + * or previous extra request has XEN_NETIF_EXTRA_MORE. + * + * The struct therefore needs to fit into either a tx or rx slot and + * is therefore limited to 8 octets. + * + * NOTE: Because extra info data overlays the usual request/response + * structures, there is no id information in the opposite direction. + * So, if an extra info overlays an rx response the frontend can + * assume that it is in the same ring slot as the request that was + * consumed to make the slot available, and the backend must ensure + * this assumption is true. + * + * extra info (xen_netif_extra_info_t) + * ------------------------------- + * + * General format: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| type specific data | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | padding for tx | + * +-----+-----+-----+-----+ + * + * type: XEN_NETIF_EXTRA_TYPE_* + * flags: XEN_NETIF_EXTRA_FLAG_* + * padding for tx: present only in the tx case due to 8 octet limit + * from rx case. Not shown in type specific entries + * below. + * + * XEN_NETIF_EXTRA_TYPE_GSO: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| size |type | pad | features | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * type: Must be XEN_NETIF_EXTRA_TYPE_GSO + * flags: XEN_NETIF_EXTRA_FLAG_* + * size: Maximum payload size of each segment. For example, + * for TCP this is just the path MSS. + * type: XEN_NETIF_GSO_TYPE_*: This determines the protocol of + * the packet and any extra features required to segment the + * packet properly. + * features: EN_XEN_NETIF_GSO_FEAT_*: This specifies any extra GSO + * features required to process this packet, such as ECN + * support for TCPv4. + * + * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| addr | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * type: Must be XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} + * flags: XEN_NETIF_EXTRA_FLAG_* + * addr: address to add/remove + * + * XEN_NETIF_EXTRA_TYPE_HASH: + * + * A backend that supports teoplitz hashing is assumed to accept + * this type of extra info in transmit packets. + * A frontend that enables hashing is assumed to accept + * this type of extra info in receive packets. + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags|htype| alg |LSB ---- value ---- MSB| + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * type: Must be XEN_NETIF_EXTRA_TYPE_HASH + * flags: XEN_NETIF_EXTRA_FLAG_* + * htype: Hash type (one of _XEN_NETIF_CTRL_HASH_TYPE_* - see above) + * alg: The algorithm used to calculate the hash (one of + * XEN_NETIF_CTRL_HASH_TYPE_ALGORITHM_* - see above) + * value: Hash value */ /* Protocol checksum field is blank in the packet (hardware offload)? */ -#define _XEN_NETTXF_csum_blank (0) -#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank) +#define _XEN_NETTXF_csum_blank (0) +#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank) /* Packet data has been validated against protocol checksum. */ -#define _XEN_NETTXF_data_validated (1) -#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated) +#define _XEN_NETTXF_data_validated (1) +#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated) /* Packet continues in the next request descriptor. */ -#define _XEN_NETTXF_more_data (2) -#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data) +#define _XEN_NETTXF_more_data (2) +#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data) /* Packet to be followed by extra descriptor(s). */ -#define _XEN_NETTXF_extra_info (3) -#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info) +#define _XEN_NETTXF_extra_info (3) +#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info) #define XEN_NETIF_MAX_TX_SIZE 0xFFFF struct xen_netif_tx_request { - grant_ref_t gref; /* Reference to buffer page */ - uint16_t offset; /* Offset within buffer page */ - uint16_t flags; /* XEN_NETTXF_* */ - uint16_t id; /* Echoed in response message. */ - uint16_t size; /* Packet size in bytes. */ + grant_ref_t gref; + uint16_t offset; + uint16_t flags; + uint16_t id; + uint16_t size; }; /* Types of xen_netif_extra_info descriptors. */ -#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ -#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ -#define XEN_NETIF_EXTRA_TYPE_MAX (2) - -/* xen_netif_extra_info flags. */ -#define _XEN_NETIF_EXTRA_FLAG_MORE (0) -#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) - -/* GSO types - only TCPv4 currently supported. */ -#define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ +#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ +#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */ +#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */ +#define XEN_NETIF_EXTRA_TYPE_HASH (4) /* u.hash */ +#define XEN_NETIF_EXTRA_TYPE_XDP (5) /* u.xdp */ +#define XEN_NETIF_EXTRA_TYPE_MAX (6) + +/* xen_netif_extra_info_t flags. */ +#define _XEN_NETIF_EXTRA_FLAG_MORE (0) +#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) + +/* GSO types */ +#define XEN_NETIF_GSO_TYPE_NONE (0) +#define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_GSO_TYPE_TCPV6 (2) /* - * This structure needs to fit within both netif_tx_request and - * netif_rx_response for compatibility. + * This structure needs to fit within both xen_netif_tx_request_t and + * xen_netif_rx_response_t for compatibility. */ struct xen_netif_extra_info { - uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */ - uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */ - + uint8_t type; + uint8_t flags; union { struct { - /* - * Maximum payload size of each segment. For - * example, for TCP this is just the path MSS. - */ uint16_t size; - - /* - * GSO type. This determines the protocol of - * the packet and any extra features required - * to segment the packet properly. - */ - uint8_t type; /* XEN_NETIF_GSO_TYPE_* */ - - /* Future expansion. */ + uint8_t type; uint8_t pad; - - /* - * GSO features. This specifies any extra GSO - * features required to process this packet, - * such as ECN support for TCPv4. - */ - uint16_t features; /* XEN_NETIF_GSO_FEAT_* */ + uint16_t features; } gso; - + struct { + uint8_t addr[6]; + } mcast; + struct { + uint8_t type; + uint8_t algorithm; + uint8_t value[4]; + } hash; + struct { + uint16_t headroom; + uint16_t pad[2]; + } xdp; uint16_t pad[3]; } u; }; struct xen_netif_tx_response { uint16_t id; - int16_t status; /* XEN_NETIF_RSP_* */ + int16_t status; }; struct xen_netif_rx_request { - uint16_t id; /* Echoed in response message. */ - grant_ref_t gref; /* Reference to incoming granted frame */ + uint16_t id; /* Echoed in response message. */ + uint16_t pad; + grant_ref_t gref; }; /* Packet data has been validated against protocol checksum. */ -#define _XEN_NETRXF_data_validated (0) -#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated) +#define _XEN_NETRXF_data_validated (0) +#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated) /* Protocol checksum field is blank in the packet (hardware offload)? */ -#define _XEN_NETRXF_csum_blank (1) -#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank) +#define _XEN_NETRXF_csum_blank (1) +#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank) /* Packet continues in the next request descriptor. */ -#define _XEN_NETRXF_more_data (2) -#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data) +#define _XEN_NETRXF_more_data (2) +#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data) /* Packet to be followed by extra descriptor(s). */ -#define _XEN_NETRXF_extra_info (3) -#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info) +#define _XEN_NETRXF_extra_info (3) +#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info) -/* GSO Prefix descriptor. */ -#define _XEN_NETRXF_gso_prefix (4) -#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix) +/* Packet has GSO prefix. Deprecated but included for compatibility */ +#define _XEN_NETRXF_gso_prefix (4) +#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix) struct xen_netif_rx_response { - uint16_t id; - uint16_t offset; /* Offset in page of start of received packet */ - uint16_t flags; /* XEN_NETRXF_* */ - int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */ + uint16_t id; + uint16_t offset; + uint16_t flags; + int16_t status; }; /* - * Generate netif ring structures and types. + * Generate xen_netif ring structures and types. */ -DEFINE_RING_TYPES(xen_netif_tx, - struct xen_netif_tx_request, +DEFINE_RING_TYPES(xen_netif_tx, struct xen_netif_tx_request, struct xen_netif_tx_response); -DEFINE_RING_TYPES(xen_netif_rx, - struct xen_netif_rx_request, +DEFINE_RING_TYPES(xen_netif_rx, struct xen_netif_rx_request, struct xen_netif_rx_response); -#define XEN_NETIF_RSP_DROPPED -2 -#define XEN_NETIF_RSP_ERROR -1 -#define XEN_NETIF_RSP_OKAY 0 -/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */ -#define XEN_NETIF_RSP_NULL 1 +#define XEN_NETIF_RSP_DROPPED -2 +#define XEN_NETIF_RSP_ERROR -1 +#define XEN_NETIF_RSP_OKAY 0 +/* No response: used for auxiliary requests (e.g., xen_netif_extra_info_t). */ +#define XEN_NETIF_RSP_NULL 1 #endif diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h index d9922ae36eb5..d1a87b62daae 100644 --- a/include/xen/interface/io/pciif.h +++ b/include/xen/interface/io/pciif.h @@ -1,24 +1,7 @@ +/* SPDX-License-Identifier: MIT */ /* * PCI Backend/Frontend Common Data Structures & Macros * - * 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. - * * Author: Ryan Wilson <hap9@epoch.ncsc.mil> */ #ifndef __XEN_PCI_COMMON_H__ diff --git a/include/xen/interface/io/protocols.h b/include/xen/interface/io/protocols.h index 056744b4b05e..22099bb4079f 100644 --- a/include/xen/interface/io/protocols.h +++ b/include/xen/interface/io/protocols.h @@ -1,9 +1,9 @@ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PROTOCOLS_H__ #define __XEN_PROTOCOLS_H__ #define XEN_IO_PROTO_ABI_X86_32 "x86_32-abi" #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" @@ -11,8 +11,6 @@ # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32 #elif defined(__x86_64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64 -#elif defined(__ia64__) -# 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__) || defined(__aarch64__) diff --git a/include/xen/interface/io/pvcalls.h b/include/xen/interface/io/pvcalls.h new file mode 100644 index 000000000000..b6680fdbe2a8 --- /dev/null +++ b/include/xen/interface/io/pvcalls.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef __XEN_PUBLIC_IO_XEN_PVCALLS_H__ +#define __XEN_PUBLIC_IO_XEN_PVCALLS_H__ + +#include <linux/net.h> +#include <xen/interface/io/ring.h> +#include <xen/interface/grant_table.h> + +/* "1" means socket, connect, release, bind, listen, accept and poll */ +#define XENBUS_FUNCTIONS_CALLS "1" + +/* + * See docs/misc/pvcalls.markdown in xen.git for the full specification: + * https://xenbits.xen.org/docs/unstable/misc/pvcalls.html + */ +struct pvcalls_data_intf { + RING_IDX in_cons, in_prod, in_error; + + uint8_t pad1[52]; + + RING_IDX out_cons, out_prod, out_error; + + uint8_t pad2[52]; + + RING_IDX ring_order; + grant_ref_t ref[]; +}; +DEFINE_XEN_FLEX_RING(pvcalls); + +#define PVCALLS_SOCKET 0 +#define PVCALLS_CONNECT 1 +#define PVCALLS_RELEASE 2 +#define PVCALLS_BIND 3 +#define PVCALLS_LISTEN 4 +#define PVCALLS_ACCEPT 5 +#define PVCALLS_POLL 6 + +struct xen_pvcalls_request { + uint32_t req_id; /* private to guest, echoed in response */ + uint32_t cmd; /* command to execute */ + union { + struct xen_pvcalls_socket { + uint64_t id; + uint32_t domain; + uint32_t type; + uint32_t protocol; + } socket; + struct xen_pvcalls_connect { + uint64_t id; + uint8_t addr[28]; + uint32_t len; + uint32_t flags; + grant_ref_t ref; + uint32_t evtchn; + } connect; + struct xen_pvcalls_release { + uint64_t id; + uint8_t reuse; + } release; + struct xen_pvcalls_bind { + uint64_t id; + uint8_t addr[28]; + uint32_t len; + } bind; + struct xen_pvcalls_listen { + uint64_t id; + uint32_t backlog; + } listen; + struct xen_pvcalls_accept { + uint64_t id; + uint64_t id_new; + grant_ref_t ref; + uint32_t evtchn; + } accept; + struct xen_pvcalls_poll { + uint64_t id; + } poll; + /* dummy member to force sizeof(struct xen_pvcalls_request) + * to match across archs */ + struct xen_pvcalls_dummy { + uint8_t dummy[56]; + } dummy; + } u; +}; + +struct xen_pvcalls_response { + uint32_t req_id; + uint32_t cmd; + int32_t ret; + uint32_t pad; + union { + struct _xen_pvcalls_socket { + uint64_t id; + } socket; + struct _xen_pvcalls_connect { + uint64_t id; + } connect; + struct _xen_pvcalls_release { + uint64_t id; + } release; + struct _xen_pvcalls_bind { + uint64_t id; + } bind; + struct _xen_pvcalls_listen { + uint64_t id; + } listen; + struct _xen_pvcalls_accept { + uint64_t id; + } accept; + struct _xen_pvcalls_poll { + uint64_t id; + } poll; + struct _xen_pvcalls_dummy { + uint8_t dummy[8]; + } dummy; + } u; +}; + +DEFINE_RING_TYPES(xen_pvcalls, struct xen_pvcalls_request, + struct xen_pvcalls_response); + +#endif diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 75271b9a8f61..4fef1efcdcab 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * ring.h * @@ -9,10 +10,27 @@ #ifndef __XEN_PUBLIC_IO_RING_H__ #define __XEN_PUBLIC_IO_RING_H__ +/* + * When #include'ing this header, you need to provide the following + * declaration upfront: + * - standard integers types (uint8_t, uint16_t, etc) + * They are provided by stdint.h of the standard headers. + * + * In addition, if you intend to use the FLEX macros, you also need to + * provide the following, before invoking the FLEX macros: + * - size_t + * - memcpy + * - grant_ref_t + * These declarations are provided by string.h of the standard headers, + * and grant_table.h from the Xen public headers. + */ + +#include <xen/interface/grant_table.h> + typedef unsigned int RING_IDX; /* Round a 32-bit unsigned constant down to the nearest power of two. */ -#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) +#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) #define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x)) #define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x)) #define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x)) @@ -24,82 +42,78 @@ typedef unsigned int RING_IDX; * A ring contains as many entries as will fit, rounded down to the nearest * power of two (so we can mask with (size-1) to loop around). */ -#define __CONST_RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ - sizeof(((struct _s##_sring *)0)->ring[0]))) - +#define __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) /* * The same for passing in an actual pointer instead of a name tag. */ -#define __RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) /* * Macros to make the correct C datatypes for a new kind of ring. * * To make a new ring datatype, you need to have two message structures, - * let's say struct request, and struct response already defined. + * let's say request_t, and response_t already defined. * * In a header where you want the ring datatype declared, you then do: * - * DEFINE_RING_TYPES(mytag, struct request, struct response); + * DEFINE_RING_TYPES(mytag, request_t, response_t); * * These expand out to give you a set of types, as you can see below. * The most important of these are: * - * struct mytag_sring - The shared ring. - * struct mytag_front_ring - The 'front' half of the ring. - * struct mytag_back_ring - The 'back' half of the ring. + * mytag_sring_t - The shared ring. + * mytag_front_ring_t - The 'front' half of the ring. + * mytag_back_ring_t - The 'back' half of the ring. * * To initialize a ring in your code you need to know the location and size * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * struct mytag_front_ring front_ring; - * SHARED_RING_INIT((struct mytag_sring *)shared_page); - * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_front_ring_t ring; + * XEN_FRONT_RING_INIT(&ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): * - * struct mytag_back_ring back_ring; - * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_back_ring_t back_ring; + * BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); */ -#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ - \ -/* Shared ring entry */ \ -union __name##_sring_entry { \ - __req_t req; \ - __rsp_t rsp; \ -}; \ - \ -/* Shared ring page */ \ -struct __name##_sring { \ - RING_IDX req_prod, req_event; \ - RING_IDX rsp_prod, rsp_event; \ - uint8_t pad[48]; \ - union __name##_sring_entry ring[1]; /* variable-length */ \ -}; \ - \ -/* "Front" end's private variables */ \ -struct __name##_front_ring { \ - RING_IDX req_prod_pvt; \ - RING_IDX rsp_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; \ - \ -/* "Back" end's private variables */ \ -struct __name##_back_ring { \ - RING_IDX rsp_prod_pvt; \ - RING_IDX req_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; - +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + uint8_t __pad[48]; \ + union __name##_sring_entry ring[]; \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ /* * Macros for manipulating rings. * @@ -116,86 +130,109 @@ struct __name##_back_ring { \ */ /* Initialising empty rings */ -#define SHARED_RING_INIT(_s) do { \ - (_s)->req_prod = (_s)->rsp_prod = 0; \ - (_s)->req_event = (_s)->rsp_event = 1; \ - memset((_s)->pad, 0, sizeof((_s)->pad)); \ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \ } while(0) -#define FRONT_RING_INIT(_r, _s, __size) do { \ - (_r)->req_prod_pvt = 0; \ - (_r)->rsp_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ +#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->req_prod_pvt = (_i); \ + (_r)->rsp_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) -#define BACK_RING_INIT(_r, _s, __size) do { \ - (_r)->rsp_prod_pvt = 0; \ - (_r)->req_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ -} while (0) +#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) -/* Initialize to existing shared indexes -- for recovery */ -#define FRONT_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->req_prod_pvt = (_s)->req_prod; \ - (_r)->rsp_cons = (_s)->rsp_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ +#define XEN_FRONT_RING_INIT(r, s, size) do { \ + SHARED_RING_INIT(s); \ + FRONT_RING_INIT(r, s, size); \ } while (0) -#define BACK_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ - (_r)->req_cons = (_s)->req_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ +#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->rsp_prod_pvt = (_i); \ + (_r)->req_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) +#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size) + /* How big is this ring? */ -#define RING_SIZE(_r) \ +#define RING_SIZE(_r) \ ((_r)->nr_ents) /* Number of free requests (for use on front side only). */ -#define RING_FREE_REQUESTS(_r) \ +#define RING_FREE_REQUESTS(_r) \ (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) /* Test if there is an empty slot available on the front ring. * (This is only meaningful from the front. ) */ -#define RING_FULL(_r) \ +#define RING_FULL(_r) \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define XEN_RING_NR_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ - ({ \ - unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ - unsigned int rsp = RING_SIZE(_r) - \ - ((_r)->req_cons - (_r)->rsp_prod_pvt); \ - req < rsp ? req : rsp; \ - }) +#define XEN_RING_NR_UNCONSUMED_REQUESTS(_r) ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ +}) + +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + (!!XEN_RING_NR_UNCONSUMED_RESPONSES(_r)) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + (!!XEN_RING_NR_UNCONSUMED_REQUESTS(_r)) /* Direct access to individual ring elements, by index. */ -#define RING_GET_REQUEST(_r, _idx) \ +#define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) -#define RING_GET_RESPONSE(_r, _idx) \ +#define RING_GET_RESPONSE(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) +/* + * Get a local copy of a request/response. + * + * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is + * done on a local copy that cannot be modified by the other end. + * + * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this + * to be ineffective where dest is a struct which consists of only bitfields. + */ +#define RING_COPY_(type, r, idx, dest) do { \ + /* Use volatile to force the copy into dest. */ \ + *(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx); \ +} while (0) + +#define RING_COPY_REQUEST(r, idx, req) RING_COPY_(REQUEST, r, idx, req) +#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp) + /* Loop termination condition: Would the specified index overflow the ring? */ -#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) -#define RING_PUSH_REQUESTS(_r) do { \ - wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +/* Ill-behaved frontend determination: Can there be this many requests? */ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) + +/* Ill-behaved backend determination: Can there be this many responses? */ +#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r)) + +#define RING_PUSH_REQUESTS(_r) do { \ + virt_wmb(); /* back sees requests /before/ updated producer index */\ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ } while (0) -#define RING_PUSH_RESPONSES(_r) do { \ - wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +#define RING_PUSH_RESPONSES(_r) do { \ + virt_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ } while (0) /* @@ -228,40 +265,183 @@ struct __name##_back_ring { \ * field appropriately. */ -#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->req_prod; \ - RING_IDX __new = (_r)->req_prod_pvt; \ - wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = __new; \ - mb(); /* back sees new requests /before/ we check req_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + virt_wmb(); /* back sees requests /before/ updated producer index */\ + (_r)->sring->req_prod = __new; \ + virt_mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->rsp_prod; \ - RING_IDX __new = (_r)->rsp_prod_pvt; \ - wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = __new; \ - mb(); /* front sees new responses /before/ we check rsp_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + virt_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + virt_mb(); /* front sees new resps /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ - if (_work_to_do) break; \ - (_r)->sring->req_event = (_r)->req_cons + 1; \ - mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + virt_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ } while (0) -#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ - if (_work_to_do) break; \ - (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ - mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + virt_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ } while (0) + +/* + * DEFINE_XEN_FLEX_RING_AND_INTF defines two monodirectional rings and + * functions to check if there is data on the ring, and to read and + * write to them. + * + * DEFINE_XEN_FLEX_RING is similar to DEFINE_XEN_FLEX_RING_AND_INTF, but + * does not define the indexes page. As different protocols can have + * extensions to the basic format, this macro allow them to define their + * own struct. + * + * XEN_FLEX_RING_SIZE + * Convenience macro to calculate the size of one of the two rings + * from the overall order. + * + * $NAME_mask + * Function to apply the size mask to an index, to reduce the index + * within the range [0-size]. + * + * $NAME_read_packet + * Function to read data from the ring. The amount of data to read is + * specified by the "size" argument. + * + * $NAME_write_packet + * Function to write data to the ring. The amount of data to write is + * specified by the "size" argument. + * + * $NAME_get_ring_ptr + * Convenience function that returns a pointer to read/write to the + * ring at the right location. + * + * $NAME_data_intf + * Indexes page, shared between frontend and backend. It also + * contains the array of grant refs. + * + * $NAME_queued + * Function to calculate how many bytes are currently on the ring, + * ready to be read. It can also be used to calculate how much free + * space is currently on the ring (XEN_FLEX_RING_SIZE() - + * $NAME_queued()). + */ + +#ifndef XEN_PAGE_SHIFT +/* The PAGE_SIZE for ring protocols and hypercall interfaces is always + * 4K, regardless of the architecture, and page granularity chosen by + * operating systems. + */ +#define XEN_PAGE_SHIFT 12 +#endif +#define XEN_FLEX_RING_SIZE(order) \ + (1UL << ((order) + XEN_PAGE_SHIFT - 1)) + +#define DEFINE_XEN_FLEX_RING(name) \ +static inline RING_IDX name##_mask(RING_IDX idx, RING_IDX ring_size) \ +{ \ + return idx & (ring_size - 1); \ +} \ + \ +static inline unsigned char *name##_get_ring_ptr(unsigned char *buf, \ + RING_IDX idx, \ + RING_IDX ring_size) \ +{ \ + return buf + name##_mask(idx, ring_size); \ +} \ + \ +static inline void name##_read_packet(void *opaque, \ + const unsigned char *buf, \ + size_t size, \ + RING_IDX masked_prod, \ + RING_IDX *masked_cons, \ + RING_IDX ring_size) \ +{ \ + if (*masked_cons < masked_prod || \ + size <= ring_size - *masked_cons) { \ + memcpy(opaque, buf + *masked_cons, size); \ + } else { \ + memcpy(opaque, buf + *masked_cons, ring_size - *masked_cons); \ + memcpy((unsigned char *)opaque + ring_size - *masked_cons, buf, \ + size - (ring_size - *masked_cons)); \ + } \ + *masked_cons = name##_mask(*masked_cons + size, ring_size); \ +} \ + \ +static inline void name##_write_packet(unsigned char *buf, \ + const void *opaque, \ + size_t size, \ + RING_IDX *masked_prod, \ + RING_IDX masked_cons, \ + RING_IDX ring_size) \ +{ \ + if (*masked_prod < masked_cons || \ + size <= ring_size - *masked_prod) { \ + memcpy(buf + *masked_prod, opaque, size); \ + } else { \ + memcpy(buf + *masked_prod, opaque, ring_size - *masked_prod); \ + memcpy(buf, (unsigned char *)opaque + (ring_size - *masked_prod), \ + size - (ring_size - *masked_prod)); \ + } \ + *masked_prod = name##_mask(*masked_prod + size, ring_size); \ +} \ + \ +static inline RING_IDX name##_queued(RING_IDX prod, \ + RING_IDX cons, \ + RING_IDX ring_size) \ +{ \ + RING_IDX size; \ + \ + if (prod == cons) \ + return 0; \ + \ + prod = name##_mask(prod, ring_size); \ + cons = name##_mask(cons, ring_size); \ + \ + if (prod == cons) \ + return ring_size; \ + \ + if (prod > cons) \ + size = prod - cons; \ + else \ + size = ring_size - (cons - prod); \ + return size; \ +} \ + \ +struct name##_data { \ + unsigned char *in; /* half of the allocation */ \ + unsigned char *out; /* half of the allocation */ \ +} + +#define DEFINE_XEN_FLEX_RING_AND_INTF(name) \ +struct name##_data_intf { \ + RING_IDX in_cons, in_prod; \ + \ + uint8_t pad1[56]; \ + \ + RING_IDX out_cons, out_prod; \ + \ + uint8_t pad2[56]; \ + \ + RING_IDX ring_order; \ + grant_ref_t ref[]; \ +}; \ +DEFINE_XEN_FLEX_RING(name) + #endif /* __XEN_PUBLIC_IO_RING_H__ */ diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h new file mode 100644 index 000000000000..b818517588b5 --- /dev/null +++ b/include/xen/interface/io/sndif.h @@ -0,0 +1,1064 @@ +/* SPDX-License-Identifier: MIT */ +/****************************************************************************** + * sndif.h + * + * Unified sound-device I/O interface for Xen guest OSes. + * + * Copyright (C) 2013-2015 GlobalLogic Inc. + * Copyright (C) 2016-2017 EPAM Systems Inc. + * + * Authors: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + * Oleksandr Grytsov <oleksandr_grytsov@epam.com> + * Oleksandr Dmytryshyn <oleksandr.dmytryshyn@globallogic.com> + * Iurii Konovalenko <iurii.konovalenko@globallogic.com> + */ + +#ifndef __XEN_PUBLIC_IO_SNDIF_H__ +#define __XEN_PUBLIC_IO_SNDIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + ****************************************************************************** + * Protocol version + ****************************************************************************** + */ +#define XENSND_PROTOCOL_VERSION 2 + +/* + ****************************************************************************** + * Feature and Parameter Negotiation + ****************************************************************************** + * + * Front->back notifications: when enqueuing a new request, sending a + * notification can be made conditional on xensnd_req (i.e., the generic + * hold-off mechanism provided by the ring macros). Backends must set + * xensnd_req appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()). + * + * Back->front notifications: when enqueuing a new response, sending a + * notification can be made conditional on xensnd_resp (i.e., the generic + * hold-off mechanism provided by the ring macros). Frontends must set + * xensnd_resp appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()). + * + * The two halves of a para-virtual sound card driver utilize nodes within + * XenStore to communicate capabilities and to negotiate operating parameters. + * This section enumerates these nodes which reside in the respective front and + * backend portions of XenStore, following the XenBus convention. + * + * All data in XenStore is stored as strings. Nodes specifying numeric + * values are encoded in decimal. Integer value ranges listed below are + * expressed as fixed sized integer types capable of storing the conversion + * of a properly formated node string, without loss of information. + * + ****************************************************************************** + * Example configuration + ****************************************************************************** + * + * Note: depending on the use-case backend can expose more sound cards and + * PCM devices/streams than the underlying HW physically has by employing + * SW mixers, configuring virtual sound streams, channels etc. + * + * This is an example of backend and frontend configuration: + * + *--------------------------------- Backend ----------------------------------- + * + * /local/domain/0/backend/vsnd/1/0/frontend-id = "1" + * /local/domain/0/backend/vsnd/1/0/frontend = "/local/domain/1/device/vsnd/0" + * /local/domain/0/backend/vsnd/1/0/state = "4" + * /local/domain/0/backend/vsnd/1/0/versions = "1,2" + * + *--------------------------------- Frontend ---------------------------------- + * + * /local/domain/1/device/vsnd/0/backend-id = "0" + * /local/domain/1/device/vsnd/0/backend = "/local/domain/0/backend/vsnd/1/0" + * /local/domain/1/device/vsnd/0/state = "4" + * /local/domain/1/device/vsnd/0/version = "1" + * + *----------------------------- Card configuration ---------------------------- + * + * /local/domain/1/device/vsnd/0/short-name = "Card short name" + * /local/domain/1/device/vsnd/0/long-name = "Card long name" + * /local/domain/1/device/vsnd/0/sample-rates = "8000,32000,44100,48000,96000" + * /local/domain/1/device/vsnd/0/sample-formats = "s8,u8,s16_le,s16_be" + * /local/domain/1/device/vsnd/0/buffer-size = "262144" + * + *------------------------------- PCM device 0 -------------------------------- + * + * /local/domain/1/device/vsnd/0/0/name = "General analog" + * /local/domain/1/device/vsnd/0/0/channels-max = "5" + * + *----------------------------- Stream 0, playback ---------------------------- + * + * /local/domain/1/device/vsnd/0/0/0/type = "p" + * /local/domain/1/device/vsnd/0/0/0/sample-formats = "s8,u8" + * /local/domain/1/device/vsnd/0/0/0/unique-id = "0" + * + * /local/domain/1/device/vsnd/0/0/0/ring-ref = "386" + * /local/domain/1/device/vsnd/0/0/0/event-channel = "15" + * /local/domain/1/device/vsnd/0/0/0/evt-ring-ref = "1386" + * /local/domain/1/device/vsnd/0/0/0/evt-event-channel = "215" + * + *------------------------------ Stream 1, capture ---------------------------- + * + * /local/domain/1/device/vsnd/0/0/1/type = "c" + * /local/domain/1/device/vsnd/0/0/1/channels-max = "2" + * /local/domain/1/device/vsnd/0/0/1/unique-id = "1" + * + * /local/domain/1/device/vsnd/0/0/1/ring-ref = "384" + * /local/domain/1/device/vsnd/0/0/1/event-channel = "13" + * /local/domain/1/device/vsnd/0/0/1/evt-ring-ref = "1384" + * /local/domain/1/device/vsnd/0/0/1/evt-event-channel = "213" + * + *------------------------------- PCM device 1 -------------------------------- + * + * /local/domain/1/device/vsnd/0/1/name = "HDMI-0" + * /local/domain/1/device/vsnd/0/1/sample-rates = "8000,32000,44100" + * + *------------------------------ Stream 0, capture ---------------------------- + * + * /local/domain/1/device/vsnd/0/1/0/type = "c" + * /local/domain/1/device/vsnd/0/1/0/unique-id = "2" + * + * /local/domain/1/device/vsnd/0/1/0/ring-ref = "387" + * /local/domain/1/device/vsnd/0/1/0/event-channel = "151" + * /local/domain/1/device/vsnd/0/1/0/evt-ring-ref = "1387" + * /local/domain/1/device/vsnd/0/1/0/evt-event-channel = "351" + * + *------------------------------- PCM device 2 -------------------------------- + * + * /local/domain/1/device/vsnd/0/2/name = "SPDIF" + * + *----------------------------- Stream 0, playback ---------------------------- + * + * /local/domain/1/device/vsnd/0/2/0/type = "p" + * /local/domain/1/device/vsnd/0/2/0/unique-id = "3" + * + * /local/domain/1/device/vsnd/0/2/0/ring-ref = "389" + * /local/domain/1/device/vsnd/0/2/0/event-channel = "152" + * /local/domain/1/device/vsnd/0/2/0/evt-ring-ref = "1389" + * /local/domain/1/device/vsnd/0/2/0/evt-event-channel = "452" + * + ****************************************************************************** + * Backend XenBus Nodes + ****************************************************************************** + * + *----------------------------- Protocol version ------------------------------ + * + * versions + * Values: <string> + * + * List of XENSND_LIST_SEPARATOR separated protocol versions supported + * by the backend. For example "1,2,3". + * + ****************************************************************************** + * Frontend XenBus Nodes + ****************************************************************************** + * + *-------------------------------- Addressing --------------------------------- + * + * dom-id + * Values: <uint16_t> + * + * Domain identifier. + * + * dev-id + * Values: <uint16_t> + * + * Device identifier. + * + * pcm-dev-idx + * Values: <uint8_t> + * + * Zero based contigous index of the PCM device. + * + * stream-idx + * Values: <uint8_t> + * + * Zero based contigous index of the stream of the PCM device. + * + * The following pattern is used for addressing: + * /local/domain/<dom-id>/device/vsnd/<dev-id>/<pcm-dev-idx>/<stream-idx>/... + * + *----------------------------- Protocol version ------------------------------ + * + * version + * Values: <string> + * + * Protocol version, chosen among the ones supported by the backend. + * + *------------------------------- PCM settings -------------------------------- + * + * Every virtualized sound frontend has a set of PCM devices and streams, each + * could be individually configured. Part of the PCM configuration can be + * defined at higher level of the hierarchy and be fully or partially re-used + * by the underlying layers. These configuration values are: + * o number of channels (min/max) + * o supported sample rates + * o supported sample formats. + * E.g. one can define these values for the whole card, device or stream. + * Every underlying layer in turn can re-define some or all of them to better + * fit its needs. For example, card may define number of channels to be + * in [1; 8] range, and some particular stream may be limited to [1; 2] only. + * The rule is that the underlying layer must be a subset of the upper layer + * range. + * + * channels-min + * Values: <uint8_t> + * + * The minimum amount of channels that is supported, [1; channels-max]. + * Optional, if not set or omitted a value of 1 is used. + * + * channels-max + * Values: <uint8_t> + * + * The maximum amount of channels that is supported. + * Must be at least <channels-min>. + * + * sample-rates + * Values: <list of uint32_t> + * + * List of supported sample rates separated by XENSND_LIST_SEPARATOR. + * Sample rates are expressed as a list of decimal values w/o any + * ordering requirement. + * + * sample-formats + * Values: <list of XENSND_PCM_FORMAT_XXX_STR> + * + * List of supported sample formats separated by XENSND_LIST_SEPARATOR. + * Items must not exceed XENSND_SAMPLE_FORMAT_MAX_LEN length. + * + * buffer-size + * Values: <uint32_t> + * + * The maximum size in octets of the buffer to allocate per stream. + * + *----------------------- Virtual sound card settings ------------------------- + * short-name + * Values: <char[32]> + * + * Short name of the virtual sound card. Optional. + * + * long-name + * Values: <char[80]> + * + * Long name of the virtual sound card. Optional. + * + *----------------------------- Device settings ------------------------------- + * name + * Values: <char[80]> + * + * Name of the sound device within the virtual sound card. Optional. + * + *----------------------------- Stream settings ------------------------------- + * + * type + * Values: "p", "c" + * + * Stream type: "p" - playback stream, "c" - capture stream + * + * If both capture and playback are needed then two streams need to be + * defined under the same device. + * + * unique-id + * Values: <string> + * + * After stream initialization it is assigned a unique ID, so every + * stream of the frontend can be identified by the backend by this ID. + * This can be UUID or such. + * + *-------------------- Stream Request Transport Parameters -------------------- + * + * event-channel + * Values: <uint32_t> + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * ring-ref + * Values: <uint32_t> + * + * The Xen grant reference granting permission for the backend to map + * a sole page in a single page sized ring buffer. + * + *--------------------- Stream Event Transport Parameters --------------------- + * + * This communication path is used to deliver asynchronous events from backend + * to frontend, set up per stream. + * + * evt-event-channel + * Values: <uint32_t> + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * evt-ring-ref + * Values: <uint32_t> + * + * The Xen grant reference granting permission for the backend to map + * a sole page in a single page sized ring buffer. + * + ****************************************************************************** + * STATE DIAGRAMS + ****************************************************************************** + * + * Tool stack creates front and back state nodes with initial state + * XenbusStateInitialising. + * Tool stack creates and sets up frontend sound configuration nodes per domain. + * + * Front Back + * ================================= ===================================== + * XenbusStateInitialising XenbusStateInitialising + * o Query backend device identification + * data. + * o Open and validate backend device. + * | + * | + * V + * XenbusStateInitWait + * + * o Query frontend configuration + * o Allocate and initialize + * event channels per configured + * playback/capture stream. + * o Publish transport parameters + * that will be in effect during + * this connection. + * | + * | + * V + * XenbusStateInitialised + * + * o Query frontend transport parameters. + * o Connect to the event channels. + * | + * | + * V + * XenbusStateConnected + * + * o Create and initialize OS + * virtual sound device instances + * as per configuration. + * | + * | + * V + * XenbusStateConnected + * + * XenbusStateUnknown + * XenbusStateClosed + * XenbusStateClosing + * o Remove virtual sound device + * o Remove event channels + * | + * | + * V + * XenbusStateClosed + * + *------------------------------- Recovery flow ------------------------------- + * + * In case of frontend unrecoverable errors backend handles that as + * if frontend goes into the XenbusStateClosed state. + * + * In case of backend unrecoverable errors frontend tries removing + * the virtualized device. If this is possible at the moment of error, + * then frontend goes into the XenbusStateInitialising state and is ready for + * new connection with backend. If the virtualized device is still in use and + * cannot be removed, then frontend goes into the XenbusStateReconfiguring state + * until either the virtualized device removed or backend initiates a new + * connection. On the virtualized device removal frontend goes into the + * XenbusStateInitialising state. + * + * Note on XenbusStateReconfiguring state of the frontend: if backend has + * unrecoverable errors then frontend cannot send requests to the backend + * and thus cannot provide functionality of the virtualized device anymore. + * After backend is back to normal the virtualized device may still hold some + * state: configuration in use, allocated buffers, client application state etc. + * So, in most cases, this will require frontend to implement complex recovery + * reconnect logic. Instead, by going into XenbusStateReconfiguring state, + * frontend will make sure no new clients of the virtualized device are + * accepted, allow existing client(s) to exit gracefully by signaling error + * state etc. + * Once all the clients are gone frontend can reinitialize the virtualized + * device and get into XenbusStateInitialising state again signaling the + * backend that a new connection can be made. + * + * There are multiple conditions possible under which frontend will go from + * XenbusStateReconfiguring into XenbusStateInitialising, some of them are OS + * specific. For example: + * 1. The underlying OS framework may provide callbacks to signal that the last + * client of the virtualized device has gone and the device can be removed + * 2. Frontend can schedule a deferred work (timer/tasklet/workqueue) + * to periodically check if this is the right time to re-try removal of + * the virtualized device. + * 3. By any other means. + * + ****************************************************************************** + * PCM FORMATS + ****************************************************************************** + * + * XENSND_PCM_FORMAT_<format>[_<endian>] + * + * format: <S/U/F><bits> or <name> + * S - signed, U - unsigned, F - float + * bits - 8, 16, 24, 32 + * name - MU_LAW, GSM, etc. + * + * endian: <LE/BE>, may be absent + * LE - Little endian, BE - Big endian + */ +#define XENSND_PCM_FORMAT_S8 0 +#define XENSND_PCM_FORMAT_U8 1 +#define XENSND_PCM_FORMAT_S16_LE 2 +#define XENSND_PCM_FORMAT_S16_BE 3 +#define XENSND_PCM_FORMAT_U16_LE 4 +#define XENSND_PCM_FORMAT_U16_BE 5 +#define XENSND_PCM_FORMAT_S24_LE 6 +#define XENSND_PCM_FORMAT_S24_BE 7 +#define XENSND_PCM_FORMAT_U24_LE 8 +#define XENSND_PCM_FORMAT_U24_BE 9 +#define XENSND_PCM_FORMAT_S32_LE 10 +#define XENSND_PCM_FORMAT_S32_BE 11 +#define XENSND_PCM_FORMAT_U32_LE 12 +#define XENSND_PCM_FORMAT_U32_BE 13 +#define XENSND_PCM_FORMAT_F32_LE 14 /* 4-byte float, IEEE-754 32-bit, */ +#define XENSND_PCM_FORMAT_F32_BE 15 /* range -1.0 to 1.0 */ +#define XENSND_PCM_FORMAT_F64_LE 16 /* 8-byte float, IEEE-754 64-bit, */ +#define XENSND_PCM_FORMAT_F64_BE 17 /* range -1.0 to 1.0 */ +#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE 18 +#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE 19 +#define XENSND_PCM_FORMAT_MU_LAW 20 +#define XENSND_PCM_FORMAT_A_LAW 21 +#define XENSND_PCM_FORMAT_IMA_ADPCM 22 +#define XENSND_PCM_FORMAT_MPEG 23 +#define XENSND_PCM_FORMAT_GSM 24 + +/* + ****************************************************************************** + * REQUEST CODES + ****************************************************************************** + */ +#define XENSND_OP_OPEN 0 +#define XENSND_OP_CLOSE 1 +#define XENSND_OP_READ 2 +#define XENSND_OP_WRITE 3 +#define XENSND_OP_SET_VOLUME 4 +#define XENSND_OP_GET_VOLUME 5 +#define XENSND_OP_MUTE 6 +#define XENSND_OP_UNMUTE 7 +#define XENSND_OP_TRIGGER 8 +#define XENSND_OP_HW_PARAM_QUERY 9 + +#define XENSND_OP_TRIGGER_START 0 +#define XENSND_OP_TRIGGER_PAUSE 1 +#define XENSND_OP_TRIGGER_STOP 2 +#define XENSND_OP_TRIGGER_RESUME 3 + +/* + ****************************************************************************** + * EVENT CODES + ****************************************************************************** + */ +#define XENSND_EVT_CUR_POS 0 + +/* + ****************************************************************************** + * XENSTORE FIELD AND PATH NAME STRINGS, HELPERS + ****************************************************************************** + */ +#define XENSND_DRIVER_NAME "vsnd" + +#define XENSND_LIST_SEPARATOR "," +/* Field names */ +#define XENSND_FIELD_BE_VERSIONS "versions" +#define XENSND_FIELD_FE_VERSION "version" +#define XENSND_FIELD_VCARD_SHORT_NAME "short-name" +#define XENSND_FIELD_VCARD_LONG_NAME "long-name" +#define XENSND_FIELD_RING_REF "ring-ref" +#define XENSND_FIELD_EVT_CHNL "event-channel" +#define XENSND_FIELD_EVT_RING_REF "evt-ring-ref" +#define XENSND_FIELD_EVT_EVT_CHNL "evt-event-channel" +#define XENSND_FIELD_DEVICE_NAME "name" +#define XENSND_FIELD_TYPE "type" +#define XENSND_FIELD_STREAM_UNIQUE_ID "unique-id" +#define XENSND_FIELD_CHANNELS_MIN "channels-min" +#define XENSND_FIELD_CHANNELS_MAX "channels-max" +#define XENSND_FIELD_SAMPLE_RATES "sample-rates" +#define XENSND_FIELD_SAMPLE_FORMATS "sample-formats" +#define XENSND_FIELD_BUFFER_SIZE "buffer-size" + +/* Stream type field values. */ +#define XENSND_STREAM_TYPE_PLAYBACK "p" +#define XENSND_STREAM_TYPE_CAPTURE "c" +/* Sample rate max string length */ +#define XENSND_SAMPLE_RATE_MAX_LEN 11 +/* Sample format field values */ +#define XENSND_SAMPLE_FORMAT_MAX_LEN 24 + +#define XENSND_PCM_FORMAT_S8_STR "s8" +#define XENSND_PCM_FORMAT_U8_STR "u8" +#define XENSND_PCM_FORMAT_S16_LE_STR "s16_le" +#define XENSND_PCM_FORMAT_S16_BE_STR "s16_be" +#define XENSND_PCM_FORMAT_U16_LE_STR "u16_le" +#define XENSND_PCM_FORMAT_U16_BE_STR "u16_be" +#define XENSND_PCM_FORMAT_S24_LE_STR "s24_le" +#define XENSND_PCM_FORMAT_S24_BE_STR "s24_be" +#define XENSND_PCM_FORMAT_U24_LE_STR "u24_le" +#define XENSND_PCM_FORMAT_U24_BE_STR "u24_be" +#define XENSND_PCM_FORMAT_S32_LE_STR "s32_le" +#define XENSND_PCM_FORMAT_S32_BE_STR "s32_be" +#define XENSND_PCM_FORMAT_U32_LE_STR "u32_le" +#define XENSND_PCM_FORMAT_U32_BE_STR "u32_be" +#define XENSND_PCM_FORMAT_F32_LE_STR "float_le" +#define XENSND_PCM_FORMAT_F32_BE_STR "float_be" +#define XENSND_PCM_FORMAT_F64_LE_STR "float64_le" +#define XENSND_PCM_FORMAT_F64_BE_STR "float64_be" +#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_LE_STR "iec958_subframe_le" +#define XENSND_PCM_FORMAT_IEC958_SUBFRAME_BE_STR "iec958_subframe_be" +#define XENSND_PCM_FORMAT_MU_LAW_STR "mu_law" +#define XENSND_PCM_FORMAT_A_LAW_STR "a_law" +#define XENSND_PCM_FORMAT_IMA_ADPCM_STR "ima_adpcm" +#define XENSND_PCM_FORMAT_MPEG_STR "mpeg" +#define XENSND_PCM_FORMAT_GSM_STR "gsm" + + +/* + ****************************************************************************** + * STATUS RETURN CODES + ****************************************************************************** + * + * Status return code is zero on success and -XEN_EXX on failure. + * + ****************************************************************************** + * Assumptions + ****************************************************************************** + * o usage of grant reference 0 as invalid grant reference: + * grant reference 0 is valid, but never exposed to a PV driver, + * because of the fact it is already in use/reserved by the PV console. + * o all references in this document to page sizes must be treated + * as pages of size XEN_PAGE_SIZE unless otherwise noted. + * + ****************************************************************************** + * Description of the protocol between frontend and backend driver + ****************************************************************************** + * + * The two halves of a Para-virtual sound driver communicate with + * each other using shared pages and event channels. + * Shared page contains a ring with request/response packets. + * + * Packets, used for input/output operations, e.g. read/write, set/get volume, + * etc., provide offset/length fields in order to allow asynchronous protocol + * operation with buffer space sharing: part of the buffer allocated at + * XENSND_OP_OPEN can be used for audio samples and part, for example, + * for volume control. + * + * All reserved fields in the structures below must be 0. + * + *---------------------------------- Requests --------------------------------- + * + * All request packets have the same length (64 octets) + * All request packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * id - uint16_t, private guest value, echoed in response + * operation - uint8_t, operation code, XENSND_OP_??? + * + * For all packets which use offset and length: + * offset - uint32_t, read or write data offset within the shared buffer, + * passed with XENSND_OP_OPEN request, octets, + * [0; XENSND_OP_OPEN.buffer_sz - 1]. + * length - uint32_t, read or write data length, octets + * + * Request open - open a PCM stream for playback or capture: + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | XENSND_OP_OPEN | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | pcm_rate | 12 + * +----------------+----------------+----------------+----------------+ + * | pcm_format | pcm_channels | reserved | 16 + * +----------------+----------------+----------------+----------------+ + * | buffer_sz | 20 + * +----------------+----------------+----------------+----------------+ + * | gref_directory | 24 + * +----------------+----------------+----------------+----------------+ + * | period_sz | 28 + * +----------------+----------------+----------------+----------------+ + * | reserved | 32 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * pcm_rate - uint32_t, stream data rate, Hz + * pcm_format - uint8_t, XENSND_PCM_FORMAT_XXX value + * pcm_channels - uint8_t, number of channels of this stream, + * [channels-min; channels-max] + * buffer_sz - uint32_t, buffer size to be allocated, octets + * period_sz - uint32_t, event period size, octets + * This is the requested value of the period at which frontend would + * like to receive XENSND_EVT_CUR_POS notifications from the backend when + * stream position advances during playback/capture. + * It shows how many octets are expected to be played/captured before + * sending such an event. + * If set to 0 no XENSND_EVT_CUR_POS events are sent by the backend. + * + * gref_directory - grant_ref_t, a reference to the first shared page + * describing shared buffer references. At least one page exists. If shared + * buffer size (buffer_sz) exceeds what can be addressed by this single page, + * then reference to the next page must be supplied (see gref_dir_next_page + * below) + */ + +struct xensnd_open_req { + uint32_t pcm_rate; + uint8_t pcm_format; + uint8_t pcm_channels; + uint16_t reserved; + uint32_t buffer_sz; + grant_ref_t gref_directory; + uint32_t period_sz; +}; + +/* + * Shared page for XENSND_OP_OPEN buffer descriptor (gref_directory in the + * request) employs a list of pages, describing all pages of the shared data + * buffer: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | gref_dir_next_page | 4 + * +----------------+----------------+----------------+----------------+ + * | gref[0] | 8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | gref[i] | i*4+8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | gref[N - 1] | N*4+8 + * +----------------+----------------+----------------+----------------+ + * + * gref_dir_next_page - grant_ref_t, reference to the next page describing + * page directory. Must be 0 if there are no more pages in the list. + * gref[i] - grant_ref_t, reference to a shared page of the buffer + * allocated at XENSND_OP_OPEN + * + * Number of grant_ref_t entries in the whole page directory is not + * passed, but instead can be calculated as: + * num_grefs_total = (XENSND_OP_OPEN.buffer_sz + XEN_PAGE_SIZE - 1) / + * XEN_PAGE_SIZE + */ + +struct xensnd_page_directory { + grant_ref_t gref_dir_next_page; + grant_ref_t gref[]; +}; + +/* + * Request close - close an opened pcm stream: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | XENSND_OP_CLOSE| reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Request read/write - used for read (for capture) or write (for playback): + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | offset | 12 + * +----------------+----------------+----------------+----------------+ + * | length | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * operation - XENSND_OP_READ for read or XENSND_OP_WRITE for write + */ + +struct xensnd_rw_req { + uint32_t offset; + uint32_t length; +}; + +/* + * Request set/get volume - set/get channels' volume of the stream given: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | offset | 12 + * +----------------+----------------+----------------+----------------+ + * | length | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * operation - XENSND_OP_SET_VOLUME for volume set + * or XENSND_OP_GET_VOLUME for volume get + * Buffer passed with XENSND_OP_OPEN is used to exchange volume + * values: + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | channel[0] | 4 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | channel[i] | i*4 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | channel[N - 1] | (N-1)*4 + * +----------------+----------------+----------------+----------------+ + * + * N = XENSND_OP_OPEN.pcm_channels + * i - uint8_t, index of a channel + * channel[i] - sint32_t, volume of i-th channel + * Volume is expressed as a signed value in steps of 0.001 dB, + * while 0 being 0 dB. + * + * Request mute/unmute - mute/unmute stream: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | offset | 12 + * +----------------+----------------+----------------+----------------+ + * | length | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * operation - XENSND_OP_MUTE for mute or XENSND_OP_UNMUTE for unmute + * Buffer passed with XENSND_OP_OPEN is used to exchange mute/unmute + * values: + * + * 0 octet + * +----------------+----------------+----------------+----------------+ + * | channel[0] | 4 + * +----------------+----------------+----------------+----------------+ + * +/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | channel[i] | i*4 + * +----------------+----------------+----------------+----------------+ + * +/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | channel[N - 1] | (N-1)*4 + * +----------------+----------------+----------------+----------------+ + * + * N = XENSND_OP_OPEN.pcm_channels + * i - uint8_t, index of a channel + * channel[i] - uint8_t, non-zero if i-th channel needs to be muted/unmuted + * + *------------------------------------ N.B. ----------------------------------- + * + * The 'struct xensnd_rw_req' is also used for XENSND_OP_SET_VOLUME, + * XENSND_OP_GET_VOLUME, XENSND_OP_MUTE, XENSND_OP_UNMUTE. + * + * Request stream running state change - trigger PCM stream running state + * to start, stop, pause or resume: + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _OP_TRIGGER | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | type | reserved | 12 + * +----------------+----------------+----------------+----------------+ + * | reserved | 16 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * type - uint8_t, XENSND_OP_TRIGGER_XXX value + */ + +struct xensnd_trigger_req { + uint8_t type; +}; + +/* + * Request stream parameter ranges: request intervals and + * masks of supported ranges for stream configuration values. + * + * Sound device configuration for a particular stream is a limited subset + * of the multidimensional configuration available on XenStore, e.g. + * once the frame rate has been selected there is a limited supported range + * for sample rates becomes available (which might be the same set configured + * on XenStore or less). For example, selecting 96kHz sample rate may limit + * number of channels available for such configuration from 4 to 2, etc. + * Thus, each call to XENSND_OP_HW_PARAM_QUERY may reduce configuration + * space making it possible to iteratively get the final stream configuration, + * used in XENSND_OP_OPEN request. + * + * See response format for this request. + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _HW_PARAM_QUERY| reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | formats mask low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | formats mask high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | min rate | 20 + * +----------------+----------------+----------------+----------------+ + * | max rate | 24 + * +----------------+----------------+----------------+----------------+ + * | min channels | 28 + * +----------------+----------------+----------------+----------------+ + * | max channels | 32 + * +----------------+----------------+----------------+----------------+ + * | min buffer frames | 36 + * +----------------+----------------+----------------+----------------+ + * | max buffer frames | 40 + * +----------------+----------------+----------------+----------------+ + * | min period frames | 44 + * +----------------+----------------+----------------+----------------+ + * | max period frames | 48 + * +----------------+----------------+----------------+----------------+ + * | reserved | 52 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * formats - uint64_t, bit mask representing values of the parameter + * made as bitwise OR of (1 << XENSND_PCM_FORMAT_XXX) values + * + * For interval parameters: + * min - uint32_t, minimum value of the parameter + * max - uint32_t, maximum value of the parameter + * + * Frame is defined as a product of the number of channels by the + * number of octets per one sample. + */ + +struct xensnd_query_hw_param { + uint64_t formats; + struct { + uint32_t min; + uint32_t max; + } rates; + struct { + uint32_t min; + uint32_t max; + } channels; + struct { + uint32_t min; + uint32_t max; + } buffer; + struct { + uint32_t min; + uint32_t max; + } period; +}; + +/* + *---------------------------------- Responses -------------------------------- + * + * All response packets have the same length (64 octets) + * + * All response packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | status | 8 + * +----------------+----------------+----------------+----------------+ + * + * id - uint16_t, copied from the request + * operation - uint8_t, XENSND_OP_* - copied from request + * status - int32_t, response status, zero on success and -XEN_EXX on failure + * + * + * HW parameter query response - response for XENSND_OP_HW_PARAM_QUERY: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | operation | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | status | 8 + * +----------------+----------------+----------------+----------------+ + * | formats mask low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | formats mask high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | min rate | 20 + * +----------------+----------------+----------------+----------------+ + * | max rate | 24 + * +----------------+----------------+----------------+----------------+ + * | min channels | 28 + * +----------------+----------------+----------------+----------------+ + * | max channels | 32 + * +----------------+----------------+----------------+----------------+ + * | min buffer frames | 36 + * +----------------+----------------+----------------+----------------+ + * | max buffer frames | 40 + * +----------------+----------------+----------------+----------------+ + * | min period frames | 44 + * +----------------+----------------+----------------+----------------+ + * | max period frames | 48 + * +----------------+----------------+----------------+----------------+ + * | reserved | 52 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * Meaning of the values in this response is the same as for + * XENSND_OP_HW_PARAM_QUERY request. + */ + +/* + *----------------------------------- Events ---------------------------------- + * + * Events are sent via shared page allocated by the front and propagated by + * evt-event-channel/evt-ring-ref XenStore entries + * All event packets have the same length (64 octets) + * All event packets have common header: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | type | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * + * id - uint16_t, event id, may be used by front + * type - uint8_t, type of the event + * + * + * Current stream position - event from back to front when stream's + * playback/capture position has advanced: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | _EVT_CUR_POS | reserved | 4 + * +----------------+----------------+----------------+----------------+ + * | reserved | 8 + * +----------------+----------------+----------------+----------------+ + * | position low 32-bit | 12 + * +----------------+----------------+----------------+----------------+ + * | position high 32-bit | 16 + * +----------------+----------------+----------------+----------------+ + * | reserved | 20 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | reserved | 64 + * +----------------+----------------+----------------+----------------+ + * + * position - current value of stream's playback/capture position, octets + * + */ + +struct xensnd_cur_pos_evt { + uint64_t position; +}; + +struct xensnd_req { + uint16_t id; + uint8_t operation; + uint8_t reserved[5]; + union { + struct xensnd_open_req open; + struct xensnd_rw_req rw; + struct xensnd_trigger_req trigger; + struct xensnd_query_hw_param hw_param; + uint8_t reserved[56]; + } op; +}; + +struct xensnd_resp { + uint16_t id; + uint8_t operation; + uint8_t reserved; + int32_t status; + union { + struct xensnd_query_hw_param hw_param; + uint8_t reserved1[56]; + } resp; +}; + +struct xensnd_evt { + uint16_t id; + uint8_t type; + uint8_t reserved[5]; + union { + struct xensnd_cur_pos_evt cur_pos; + uint8_t reserved[56]; + } op; +}; + +DEFINE_RING_TYPES(xen_sndif, struct xensnd_req, struct xensnd_resp); + +/* + ****************************************************************************** + * Back to front events delivery + ****************************************************************************** + * In order to deliver asynchronous events from back to front a shared page is + * allocated by front and its granted reference propagated to back via + * XenStore entries (evt-ring-ref/evt-event-channel). + * This page has a common header used by both front and back to synchronize + * access and control event's ring buffer, while back being a producer of the + * events and front being a consumer. The rest of the page after the header + * is used for event packets. + * + * Upon reception of an event(s) front may confirm its reception + * for either each event, group of events or none. + */ + +struct xensnd_event_page { + uint32_t in_cons; + uint32_t in_prod; + uint8_t reserved[56]; +}; + +#define XENSND_EVENT_PAGE_SIZE XEN_PAGE_SIZE +#define XENSND_IN_RING_OFFS (sizeof(struct xensnd_event_page)) +#define XENSND_IN_RING_SIZE (XENSND_EVENT_PAGE_SIZE - XENSND_IN_RING_OFFS) +#define XENSND_IN_RING_LEN (XENSND_IN_RING_SIZE / sizeof(struct xensnd_evt)) +#define XENSND_IN_RING(page) \ + ((struct xensnd_evt *)((char *)(page) + XENSND_IN_RING_OFFS)) +#define XENSND_IN_RING_REF(page, idx) \ + (XENSND_IN_RING((page))[(idx) % XENSND_IN_RING_LEN]) + +#endif /* __XEN_PUBLIC_IO_SNDIF_H__ */ diff --git a/include/xen/interface/io/tpmif.h b/include/xen/interface/io/tpmif.h new file mode 100644 index 000000000000..f8aa8bac5196 --- /dev/null +++ b/include/xen/interface/io/tpmif.h @@ -0,0 +1,52 @@ +/****************************************************************************** + * tpmif.h + * + * TPM I/O interface for Xen guest OSes, v2 + * + * This file is in the public domain. + * + */ + +#ifndef __XEN_PUBLIC_IO_TPMIF_H__ +#define __XEN_PUBLIC_IO_TPMIF_H__ + +/* + * Xenbus state machine + * + * Device open: + * 1. Both ends start in XenbusStateInitialising + * 2. Backend transitions to InitWait (frontend does not wait on this step) + * 3. Frontend populates ring-ref, event-channel, feature-protocol-v2 + * 4. Frontend transitions to Initialised + * 5. Backend maps grant and event channel, verifies feature-protocol-v2 + * 6. Backend transitions to Connected + * 7. Frontend verifies feature-protocol-v2, transitions to Connected + * + * Device close: + * 1. State is changed to XenbusStateClosing + * 2. Frontend transitions to Closed + * 3. Backend unmaps grant and event, changes state to InitWait + */ + +enum vtpm_shared_page_state { + VTPM_STATE_IDLE, /* no contents / vTPM idle / cancel complete */ + VTPM_STATE_SUBMIT, /* request ready / vTPM working */ + VTPM_STATE_FINISH, /* response ready / vTPM idle */ + VTPM_STATE_CANCEL, /* cancel requested / vTPM working */ +}; +/* The backend should only change state to IDLE or FINISH, while the + * frontend should only change to SUBMIT or CANCEL. */ + + +struct vtpm_shared_page { + uint32_t length; /* request/response length in bytes */ + + uint8_t state; /* enum vtpm_shared_page_state */ + uint8_t locality; /* for the current request */ + uint8_t pad; + + uint8_t nr_extra_pages; /* extra pages for long packets; may be zero */ + uint32_t extra_pages[]; /* grant IDs; length in nr_extra_pages */ +}; + +#endif diff --git a/include/xen/interface/io/usbif.h b/include/xen/interface/io/usbif.h new file mode 100644 index 000000000000..a70e0b93178b --- /dev/null +++ b/include/xen/interface/io/usbif.h @@ -0,0 +1,405 @@ +/* SPDX-License-Identifier: MIT */ + +/* + * usbif.h + * + * USB I/O interface for Xen guest OSes. + * + * Copyright (C) 2009, FUJITSU LABORATORIES LTD. + * Author: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com> + */ + +#ifndef __XEN_PUBLIC_IO_USBIF_H__ +#define __XEN_PUBLIC_IO_USBIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Detailed Interface Description + * ============================== + * The pvUSB interface is using a split driver design: a frontend driver in + * the guest and a backend driver in a driver domain (normally dom0) having + * access to the physical USB device(s) being passed to the guest. + * + * The frontend and backend drivers use XenStore to initiate the connection + * between them, the I/O activity is handled via two shared ring pages and an + * event channel. As the interface between frontend and backend is at the USB + * host connector level, multiple (up to 31) physical USB devices can be + * handled by a single connection. + * + * The Xen pvUSB device name is "qusb", so the frontend's XenStore entries are + * to be found under "device/qusb", while the backend's XenStore entries are + * under "backend/<guest-dom-id>/qusb". + * + * When a new pvUSB connection is established, the frontend needs to setup the + * two shared ring pages for communication and the event channel. The ring + * pages need to be made available to the backend via the grant table + * interface. + * + * One of the shared ring pages is used by the backend to inform the frontend + * about USB device plug events (device to be added or removed). This is the + * "conn-ring". + * + * The other ring page is used for USB I/O communication (requests and + * responses). This is the "urb-ring". + * + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen pvUSB driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * num-ports + * Values: unsigned [1...31] + * + * Number of ports for this (virtual) USB host connector. + * + * usb-ver + * Values: unsigned [1...2] + * + * USB version of this host connector: 1 = USB 1.1, 2 = USB 2.0. + * + * port/[1...31] + * Values: string + * + * Physical USB device connected to the given port, e.g. "3-1.5". + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: unsigned + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * urb-ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. This is the ring + * buffer for urb requests. + * + * conn-ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. This is the ring + * buffer for connection/disconnection requests. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + * + * Protocol Description + * ==================== + * + *-------------------------- USB device plug events -------------------------- + * + * USB device plug events are send via the "conn-ring" shared page. As only + * events are being sent, the respective requests from the frontend to the + * backend are just dummy ones. + * The events sent to the frontend have the following layout: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | portnum | speed | 4 + * +----------------+----------------+----------------+----------------+ + * id - uint16_t, event id (taken from the actual frontend dummy request) + * portnum - uint8_t, port number (1 ... 31) + * speed - uint8_t, device XENUSB_SPEED_*, XENUSB_SPEED_NONE == unplug + * + * The dummy request: + * 0 1 octet + * +----------------+----------------+ + * | id | 2 + * +----------------+----------------+ + * id - uint16_t, guest supplied value (no need for being unique) + * + *-------------------------- USB I/O request --------------------------------- + * + * A single USB I/O request on the "urb-ring" has the following layout: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | nr_buffer_segs | 4 + * +----------------+----------------+----------------+----------------+ + * | pipe | 8 + * +----------------+----------------+----------------+----------------+ + * | transfer_flags | buffer_length | 12 + * +----------------+----------------+----------------+----------------+ + * | request type specific | 16 + * | data | 20 + * +----------------+----------------+----------------+----------------+ + * | seg[0] | 24 + * | data | 28 + * +----------------+----------------+----------------+----------------+ + * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/| + * +----------------+----------------+----------------+----------------+ + * | seg[XENUSB_MAX_SEGMENTS_PER_REQUEST - 1] | 144 + * | data | 148 + * +----------------+----------------+----------------+----------------+ + * Bit field bit number 0 is always least significant bit, undefined bits must + * be zero. + * id - uint16_t, guest supplied value + * nr_buffer_segs - uint16_t, number of segment entries in seg[] array + * pipe - uint32_t, bit field with multiple information: + * bits 0-4: port request to send to + * bit 5: unlink request with specified id (cancel I/O) if set (see below) + * bit 7: direction (1 = read from device) + * bits 8-14: device number on port + * bits 15-18: endpoint of device + * bits 30-31: request type: 00 = isochronous, 01 = interrupt, + * 10 = control, 11 = bulk + * transfer_flags - uint16_t, bit field with processing flags: + * bit 0: less data than specified allowed + * buffer_length - uint16_t, total length of data + * request type specific data - 8 bytes, see below + * seg[] - array with 8 byte elements, see below + * + * Request type specific data for isochronous request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | interval | start_frame | 4 + * +----------------+----------------+----------------+----------------+ + * | number_of_packets | nr_frame_desc_segs | 8 + * +----------------+----------------+----------------+----------------+ + * interval - uint16_t, time interval in msecs between frames + * start_frame - uint16_t, start frame number + * number_of_packets - uint16_t, number of packets to transfer + * nr_frame_desc_segs - uint16_t number of seg[] frame descriptors elements + * + * Request type specific data for interrupt request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | interval | 0 | 4 + * +----------------+----------------+----------------+----------------+ + * | 0 | 8 + * +----------------+----------------+----------------+----------------+ + * interval - uint16_t, time in msecs until interruption + * + * Request type specific data for control request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | data of setup packet | 4 + * | | 8 + * +----------------+----------------+----------------+----------------+ + * + * Request type specific data for bulk request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | 0 | 4 + * | 0 | 8 + * +----------------+----------------+----------------+----------------+ + * + * Request type specific data for unlink request: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | unlink_id | 0 | 4 + * +----------------+----------------+----------------+----------------+ + * | 0 | 8 + * +----------------+----------------+----------------+----------------+ + * unlink_id - uint16_t, request id of request to terminate + * + * seg[] array element layout: + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | gref | 4 + * +----------------+----------------+----------------+----------------+ + * | offset | length | 8 + * +----------------+----------------+----------------+----------------+ + * gref - uint32_t, grant reference of buffer page + * offset - uint16_t, offset of buffer start in page + * length - uint16_t, length of buffer in page + * + *-------------------------- USB I/O response -------------------------------- + * + * 0 1 2 3 octet + * +----------------+----------------+----------------+----------------+ + * | id | start_frame | 4 + * +----------------+----------------+----------------+----------------+ + * | status | 8 + * +----------------+----------------+----------------+----------------+ + * | actual_length | 12 + * +----------------+----------------+----------------+----------------+ + * | error_count | 16 + * +----------------+----------------+----------------+----------------+ + * id - uint16_t, id of the request this response belongs to + * start_frame - uint16_t, start_frame this response (iso requests only) + * status - int32_t, XENUSB_STATUS_* (non-iso requests) + * actual_length - uint32_t, actual size of data transferred + * error_count - uint32_t, number of errors (iso requests) + */ + +enum xenusb_spec_version { + XENUSB_VER_UNKNOWN = 0, + XENUSB_VER_USB11, + XENUSB_VER_USB20, + XENUSB_VER_USB30, /* not supported yet */ +}; + +/* + * USB pipe in xenusb_request + * + * - port number: bits 0-4 + * (USB_MAXCHILDREN is 31) + * + * - operation flag: bit 5 + * (0 = submit urb, + * 1 = unlink urb) + * + * - direction: bit 7 + * (0 = Host-to-Device [Out] + * 1 = Device-to-Host [In]) + * + * - device address: bits 8-14 + * + * - endpoint: bits 15-18 + * + * - pipe type: bits 30-31 + * (00 = isochronous, 01 = interrupt, + * 10 = control, 11 = bulk) + */ + +#define XENUSB_PIPE_PORT_MASK 0x0000001f +#define XENUSB_PIPE_UNLINK 0x00000020 +#define XENUSB_PIPE_DIR 0x00000080 +#define XENUSB_PIPE_DEV_MASK 0x0000007f +#define XENUSB_PIPE_DEV_SHIFT 8 +#define XENUSB_PIPE_EP_MASK 0x0000000f +#define XENUSB_PIPE_EP_SHIFT 15 +#define XENUSB_PIPE_TYPE_MASK 0x00000003 +#define XENUSB_PIPE_TYPE_SHIFT 30 +#define XENUSB_PIPE_TYPE_ISOC 0 +#define XENUSB_PIPE_TYPE_INT 1 +#define XENUSB_PIPE_TYPE_CTRL 2 +#define XENUSB_PIPE_TYPE_BULK 3 + +#define xenusb_pipeportnum(pipe) ((pipe) & XENUSB_PIPE_PORT_MASK) +#define xenusb_setportnum_pipe(pipe, portnum) ((pipe) | (portnum)) + +#define xenusb_pipeunlink(pipe) ((pipe) & XENUSB_PIPE_UNLINK) +#define xenusb_pipesubmit(pipe) (!xenusb_pipeunlink(pipe)) +#define xenusb_setunlink_pipe(pipe) ((pipe) | XENUSB_PIPE_UNLINK) + +#define xenusb_pipein(pipe) ((pipe) & XENUSB_PIPE_DIR) +#define xenusb_pipeout(pipe) (!xenusb_pipein(pipe)) + +#define xenusb_pipedevice(pipe) \ + (((pipe) >> XENUSB_PIPE_DEV_SHIFT) & XENUSB_PIPE_DEV_MASK) + +#define xenusb_pipeendpoint(pipe) \ + (((pipe) >> XENUSB_PIPE_EP_SHIFT) & XENUSB_PIPE_EP_MASK) + +#define xenusb_pipetype(pipe) \ + (((pipe) >> XENUSB_PIPE_TYPE_SHIFT) & XENUSB_PIPE_TYPE_MASK) +#define xenusb_pipeisoc(pipe) (xenusb_pipetype(pipe) == XENUSB_PIPE_TYPE_ISOC) +#define xenusb_pipeint(pipe) (xenusb_pipetype(pipe) == XENUSB_PIPE_TYPE_INT) +#define xenusb_pipectrl(pipe) (xenusb_pipetype(pipe) == XENUSB_PIPE_TYPE_CTRL) +#define xenusb_pipebulk(pipe) (xenusb_pipetype(pipe) == XENUSB_PIPE_TYPE_BULK) + +#define XENUSB_MAX_SEGMENTS_PER_REQUEST (16) +#define XENUSB_MAX_PORTNR 31 +#define XENUSB_RING_SIZE 4096 + +/* + * RING for transferring urbs. + */ +struct xenusb_request_segment { + grant_ref_t gref; + uint16_t offset; + uint16_t length; +}; + +struct xenusb_urb_request { + uint16_t id; /* request id */ + uint16_t nr_buffer_segs; /* number of urb->transfer_buffer segments */ + + /* basic urb parameter */ + uint32_t pipe; + uint16_t transfer_flags; +#define XENUSB_SHORT_NOT_OK 0x0001 + uint16_t buffer_length; + union { + uint8_t ctrl[8]; /* setup_packet (Ctrl) */ + + struct { + uint16_t interval; /* maximum (1024*8) in usb core */ + uint16_t start_frame; /* start frame */ + uint16_t number_of_packets; /* number of ISO packet */ + uint16_t nr_frame_desc_segs; /* number of iso_frame_desc segments */ + } isoc; + + struct { + uint16_t interval; /* maximum (1024*8) in usb core */ + uint16_t pad[3]; + } intr; + + struct { + uint16_t unlink_id; /* unlink request id */ + uint16_t pad[3]; + } unlink; + + } u; + + /* urb data segments */ + struct xenusb_request_segment seg[XENUSB_MAX_SEGMENTS_PER_REQUEST]; +}; + +struct xenusb_urb_response { + uint16_t id; /* request id */ + uint16_t start_frame; /* start frame (ISO) */ + int32_t status; /* status (non-ISO) */ +#define XENUSB_STATUS_OK 0 +#define XENUSB_STATUS_NODEV (-19) +#define XENUSB_STATUS_INVAL (-22) +#define XENUSB_STATUS_STALL (-32) +#define XENUSB_STATUS_IOERROR (-71) +#define XENUSB_STATUS_BABBLE (-75) +#define XENUSB_STATUS_SHUTDOWN (-108) + int32_t actual_length; /* actual transfer length */ + int32_t error_count; /* number of ISO errors */ +}; + +DEFINE_RING_TYPES(xenusb_urb, struct xenusb_urb_request, struct xenusb_urb_response); +#define XENUSB_URB_RING_SIZE __CONST_RING_SIZE(xenusb_urb, XENUSB_RING_SIZE) + +/* + * RING for notifying connect/disconnect events to frontend + */ +struct xenusb_conn_request { + uint16_t id; +}; + +struct xenusb_conn_response { + uint16_t id; /* request id */ + uint8_t portnum; /* port number */ + uint8_t speed; /* usb_device_speed */ +#define XENUSB_SPEED_NONE 0 +#define XENUSB_SPEED_LOW 1 +#define XENUSB_SPEED_FULL 2 +#define XENUSB_SPEED_HIGH 3 +}; + +DEFINE_RING_TYPES(xenusb_conn, struct xenusb_conn_request, struct xenusb_conn_response); +#define XENUSB_CONN_RING_SIZE __CONST_RING_SIZE(xenusb_conn, XENUSB_RING_SIZE) + +#endif /* __XEN_PUBLIC_IO_USBIF_H__ */ diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h new file mode 100644 index 000000000000..7ea4dc9611c4 --- /dev/null +++ b/include/xen/interface/io/vscsiif.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: MIT */ +/****************************************************************************** + * vscsiif.h + * + * Based on the blkif.h code. + * + * Copyright(c) FUJITSU Limited 2008. + */ + +#ifndef __XEN__PUBLIC_IO_SCSI_H__ +#define __XEN__PUBLIC_IO_SCSI_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen pvSCSI driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * p-devname + * Values: string + * + * A free string used to identify the physical device (e.g. a disk name). + * + * p-dev + * Values: string + * + * A string specifying the backend device: either a 4-tuple "h:c:t:l" + * (host, controller, target, lun, all integers), or a WWN (e.g. + * "naa.60014054ac780582:0"). + * + * v-dev + * Values: string + * + * A string specifying the frontend device in form of a 4-tuple "h:c:t:l" + * (host, controller, target, lun, all integers). + * + *--------------------------------- Features --------------------------------- + * + * feature-sg-grant + * Values: unsigned [VSCSIIF_SG_TABLESIZE...65535] + * Default Value: 0 + * + * Specifies the maximum number of scatter/gather elements in grant pages + * supported. If not set, the backend supports up to VSCSIIF_SG_TABLESIZE + * SG elements specified directly in the request. + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: unsigned + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + */ + +/* + * Xenstore format in practice + * =========================== + * + * The backend driver uses a single_host:many_devices notation to manage domU + * devices. Everything is stored in /local/domain/<backend_domid>/backend/vscsi/. + * The xenstore layout looks like this (dom0 is assumed to be the backend_domid): + * + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" or "naa.wwn:lun" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * + * The frontend driver maintains its state in + * /local/domain/<domid>/device/vscsi/. + * + * <vhost>/backend = "/local/domain/0/backend/vscsi/<domid>/<vhost>" + * <vhost>/backend-id = "0" + * <vhost>/event-channel = "20" + * <vhost>/ring-ref = "43" + * <vhost>/state = "4" + * <vhost>/vscsi-devs/dev-0/state = "4" + * <vhost>/vscsi-devs/dev-1/state = "4" + * + * In addition to the entries for backend and frontend these flags are stored + * for the toolstack: + * + * <domid>/<vhost>/vscsi-devs/dev-1/p-devname = "/dev/$device" + * <domid>/<vhost>/libxl_ctrl_index = "0" + * + * + * Backend/frontend protocol + * ========================= + * + * To create a vhost along with a device: + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-0/state become 4 + * + * To add another device to a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-1/state become 4 + * + * To remove a device from a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "5" + * Wait for <domid>/<vhost>/state to become 4 + * Wait for <domid>/<vhost>/vscsi-devs/dev-1/state become 6 + * Remove <domid>/<vhost>/vscsi-devs/dev-1/{state,p-dev,v-dev,p-devname} + * Remove <domid>/<vhost>/vscsi-devs/dev-1/ + * + */ + +/* Requests from the frontend to the backend */ + +/* + * Request a SCSI operation specified via a CDB in vscsiif_request.cmnd. + * The target is specified via channel, id and lun. + * + * The operation to be performed is specified via a CDB in cmnd[], the length + * of the CDB is in cmd_len. sc_data_direction specifies the direction of data + * (to the device, from the device, or none at all). + * + * If data is to be transferred to or from the device the buffer(s) in the + * guest memory is/are specified via one or multiple scsiif_request_segment + * descriptors each specifying a memory page via a grant_ref_t, a offset into + * the page and the length of the area in that page. All scsiif_request_segment + * areas concatenated form the resulting data buffer used by the operation. + * If the number of scsiif_request_segment areas is not too large (less than + * or equal VSCSIIF_SG_TABLESIZE) the areas can be specified directly in the + * seg[] array and the number of valid scsiif_request_segment elements is to be + * set in nr_segments. + * + * If "feature-sg-grant" in the Xenstore is set it is possible to specify more + * than VSCSIIF_SG_TABLESIZE scsiif_request_segment elements via indirection. + * The maximum number of allowed scsiif_request_segment elements is the value + * of the "feature-sg-grant" entry from Xenstore. When using indirection the + * seg[] array doesn't contain specifications of the data buffers, but + * references to scsiif_request_segment arrays, which in turn reference the + * data buffers. While nr_segments holds the number of populated seg[] entries + * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment + * elements referencing the target data buffers is calculated from the lengths + * of the seg[] elements (the sum of all valid seg[].length divided by the + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. + */ +#define VSCSIIF_ACT_SCSI_CDB 1 + +/* + * Request abort of a running operation for the specified target given by + * channel, id, lun and the operation's rqid in ref_rqid. + */ +#define VSCSIIF_ACT_SCSI_ABORT 2 + +/* + * Request a device reset of the specified target (channel and id). + */ +#define VSCSIIF_ACT_SCSI_RESET 3 + +/* + * Preset scatter/gather elements for a following request. Deprecated. + * Keeping the define only to avoid usage of the value "4" for other actions. + */ +#define VSCSIIF_ACT_SCSI_SG_PRESET 4 + +/* + * Maximum scatter/gather segments per request. + * + * Considering balance between allocating at least 16 "vscsiif_request" + * structures on one page (4096 bytes) and the number of scatter/gather + * elements needed, we decided to use 26 as a magic number. + * + * If "feature-sg-grant" is set, more scatter/gather elements can be specified + * by placing them in one or more (up to VSCSIIF_SG_TABLESIZE) granted pages. + * In this case the vscsiif_request seg elements don't contain references to + * the user data, but to the SG elements referencing the user data. + */ +#define VSCSIIF_SG_TABLESIZE 26 + +/* + * based on Linux kernel 2.6.18, still valid + * + * Changing these values requires support of multiple protocols via the rings + * as "old clients" will blindly use these values and the resulting structure + * sizes. + */ +#define VSCSIIF_MAX_COMMAND_SIZE 16 +#define VSCSIIF_SENSE_BUFFERSIZE 96 +#define VSCSIIF_PAGE_SIZE 4096 + +struct scsiif_request_segment { + grant_ref_t gref; + uint16_t offset; + uint16_t length; +}; + +#define VSCSIIF_SG_PER_PAGE (VSCSIIF_PAGE_SIZE / \ + sizeof(struct scsiif_request_segment)) + +/* Size of one request is 252 bytes */ +struct vscsiif_request { + uint16_t rqid; /* private guest value, echoed in resp */ + uint8_t act; /* command between backend and frontend */ + uint8_t cmd_len; /* valid CDB bytes */ + + uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE]; /* the CDB */ + uint16_t timeout_per_command; /* deprecated */ + uint16_t channel, id, lun; /* (virtual) device specification */ + uint16_t ref_rqid; /* command abort reference */ + uint8_t sc_data_direction; /* for DMA_TO_DEVICE(1) + DMA_FROM_DEVICE(2) + DMA_NONE(3) requests */ + uint8_t nr_segments; /* Number of pieces of scatter-gather */ +/* + * flag in nr_segments: SG elements via grant page + * + * If VSCSIIF_SG_GRANT is set, the low 7 bits of nr_segments specify the number + * of grant pages containing SG elements. Usable if "feature-sg-grant" set. + */ +#define VSCSIIF_SG_GRANT 0x80 + + struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE]; + uint32_t reserved[3]; +}; + +/* Size of one response is 252 bytes */ +struct vscsiif_response { + uint16_t rqid; /* identifies request */ + uint8_t padding; + uint8_t sense_len; + uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE]; + int32_t rslt; + uint32_t residual_len; /* request bufflen - + return the value from physical device */ + uint32_t reserved[36]; +}; + +/* SCSI I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_STATUS(x) ((x) & 0x00ff) + +/* Host I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_HOST(x) (((x) & 0x00ff0000) >> 16) +#define XEN_VSCSIIF_RSLT_HOST_OK 0 +/* Couldn't connect before timeout */ +#define XEN_VSCSIIF_RSLT_HOST_NO_CONNECT 1 +/* Bus busy through timeout */ +#define XEN_VSCSIIF_RSLT_HOST_BUS_BUSY 2 +/* Timed out for other reason */ +#define XEN_VSCSIIF_RSLT_HOST_TIME_OUT 3 +/* Bad target */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_TARGET 4 +/* Abort for some other reason */ +#define XEN_VSCSIIF_RSLT_HOST_ABORT 5 +/* Parity error */ +#define XEN_VSCSIIF_RSLT_HOST_PARITY 6 +/* Internal error */ +#define XEN_VSCSIIF_RSLT_HOST_ERROR 7 +/* Reset by somebody */ +#define XEN_VSCSIIF_RSLT_HOST_RESET 8 +/* Unexpected interrupt */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_INTR 9 +/* Force command past mid-layer */ +#define XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH 10 +/* Retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR 11 +/* Hidden retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_IMM_RETRY 12 +/* Requeue command requested */ +#define XEN_VSCSIIF_RSLT_HOST_REQUEUE 13 +/* Transport error disrupted I/O */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED 14 +/* Transport class fastfailed */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST 15 +/* Permanent target failure */ +#define XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE 16 +/* Permanent nexus failure on path */ +#define XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE 17 +/* Space allocation on device failed */ +#define XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE 18 +/* Medium error */ +#define XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR 19 +/* Transport marginal errors */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL 20 + +/* Result values of reset operations */ +#define XEN_VSCSIIF_RSLT_RESET_SUCCESS 0x2002 +#define XEN_VSCSIIF_RSLT_RESET_FAILED 0x2003 + +DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); + + +#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ diff --git a/include/xen/interface/io/xenbus.h b/include/xen/interface/io/xenbus.h index 9fda532973a5..44456e2853fc 100644 --- a/include/xen/interface/io/xenbus.h +++ b/include/xen/interface/io/xenbus.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /***************************************************************************** * xenbus.h * @@ -38,13 +39,3 @@ enum xenbus_state }; #endif /* _XEN_PUBLIC_IO_XENBUS_H */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index 794deb07eb53..b62365478ac0 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /* * Details of the "wire" protocol between Xen Store Daemon and client * library or guest kernel. @@ -9,7 +10,8 @@ enum xsd_sockmsg_type { - XS_DEBUG, + XS_CONTROL, +#define XS_DEBUG XS_CONTROL XS_DIRECTORY, XS_READ, XS_GET_PERMS, @@ -29,8 +31,13 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES, + /* XS_RESTRICT has been removed */ + XS_RESET_WATCHES = XS_SET_TARGET + 2, + XS_DIRECTORY_PART, + + XS_TYPE_COUNT, /* Number of valid types. */ + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -58,7 +65,8 @@ static struct xsd_errors xsd_errors[] __attribute__((unused)) = { XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; struct xsd_sockmsg @@ -86,9 +94,31 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; + uint32_t error; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ #define XENSTORE_PAYLOAD_MAX 4096 +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 +/* The presence of the "error" field in the ring page */ +#define XENSTORE_SERVER_FEATURE_ERROR 2 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + +/* Valid values for the error field */ +#define XENSTORE_ERROR_NONE 0 /* No error */ +#define XENSTORE_ERROR_COMM 1 /* Communication problem */ +#define XENSTORE_ERROR_RINGIDX 2 /* Invalid ring index */ +#define XENSTORE_ERROR_PROTO 3 /* Protocol violation (payload too long) */ + #endif /* _XS_WIRE_H */ diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h index 2ecfe4f700d9..1a371a825c55 100644 --- a/include/xen/interface/memory.h +++ b/include/xen/interface/memory.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * memory.h * @@ -160,6 +161,7 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t); #define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom, * XENMEM_add_to_physmap_range only. */ +#define XENMAPSPACE_dev_mmio 5 /* device mmio region */ /* * Sets the GPFN at which a particular page appears in the specified guest's @@ -243,12 +245,6 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_memory_map); /* - * Prevent the balloon driver from changing the memory reservation - * during a driver critical region. - */ -extern spinlock_t xen_reservation_lock; - -/* * Unmaps the page appearing at a particular GPFN from the specified guest's * pseudophysical address space. * arg == addr of xen_remove_from_physmap_t. @@ -263,4 +259,70 @@ struct xen_remove_from_physmap { }; DEFINE_GUEST_HANDLE_STRUCT(xen_remove_from_physmap); +/* + * Get the pages for a particular guest resource, so that they can be + * mapped directly by a tools domain. + */ +#define XENMEM_acquire_resource 28 +struct xen_mem_acquire_resource { + /* IN - The domain whose resource is to be mapped */ + domid_t domid; + /* IN - the type of resource */ + uint16_t type; + +#define XENMEM_resource_ioreq_server 0 +#define XENMEM_resource_grant_table 1 + + /* + * IN - a type-specific resource identifier, which must be zero + * unless stated otherwise. + * + * type == XENMEM_resource_ioreq_server -> id == ioreq server id + * type == XENMEM_resource_grant_table -> id defined below + */ + uint32_t id; + +#define XENMEM_resource_grant_table_id_shared 0 +#define XENMEM_resource_grant_table_id_status 1 + + /* IN/OUT - As an IN parameter number of frames of the resource + * to be mapped. However, if the specified value is 0 and + * frame_list is NULL then this field will be set to the + * maximum value supported by the implementation on return. + */ + uint32_t nr_frames; + /* + * OUT - Must be zero on entry. On return this may contain a bitwise + * OR of the following values. + */ + uint32_t flags; + + /* The resource pages have been assigned to the calling domain */ +#define _XENMEM_rsrc_acq_caller_owned 0 +#define XENMEM_rsrc_acq_caller_owned (1u << _XENMEM_rsrc_acq_caller_owned) + + /* + * IN - the index of the initial frame to be mapped. This parameter + * is ignored if nr_frames is 0. + */ + uint64_t frame; + +#define XENMEM_resource_ioreq_server_frame_bufioreq 0 +#define XENMEM_resource_ioreq_server_frame_ioreq(n) (1 + (n)) + + /* + * IN/OUT - If the tools domain is PV then, upon return, frame_list + * will be populated with the MFNs of the resource. + * If the tools domain is HVM then it is expected that, on + * entry, frame_list will be populated with a list of GFNs + * that will be mapped to the MFNs of the resource. + * If -EIO is returned then the frame_list has only been + * partially mapped and it is up to the caller to unmap all + * the GFNs. + * This parameter may be NULL if nr_frames is 0. + */ + GUEST_HANDLE(xen_pfn_t) frame_list; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_mem_acquire_resource); + #endif /* __XEN_PUBLIC_MEMORY_H__ */ diff --git a/include/xen/interface/nmi.h b/include/xen/interface/nmi.h new file mode 100644 index 000000000000..b665fdbef1fd --- /dev/null +++ b/include/xen/interface/nmi.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: MIT */ +/****************************************************************************** + * nmi.h + * + * NMI callback registration and reason codes. + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_NMI_H__ +#define __XEN_PUBLIC_NMI_H__ + +#include <xen/interface/xen.h> + +/* + * NMI reason codes: + * Currently these are x86-specific, stored in arch_shared_info.nmi_reason. + */ + /* I/O-check error reported via ISA port 0x61, bit 6. */ +#define _XEN_NMIREASON_io_error 0 +#define XEN_NMIREASON_io_error (1UL << _XEN_NMIREASON_io_error) + /* PCI SERR reported via ISA port 0x61, bit 7. */ +#define _XEN_NMIREASON_pci_serr 1 +#define XEN_NMIREASON_pci_serr (1UL << _XEN_NMIREASON_pci_serr) + /* Unknown hardware-generated NMI. */ +#define _XEN_NMIREASON_unknown 2 +#define XEN_NMIREASON_unknown (1UL << _XEN_NMIREASON_unknown) + +/* + * long nmi_op(unsigned int cmd, void *arg) + * NB. All ops return zero on success, else a negative error code. + */ + +/* + * Register NMI callback for this (calling) VCPU. Currently this only makes + * sense for domain 0, vcpu 0. All other callers will be returned EINVAL. + * arg == pointer to xennmi_callback structure. + */ +#define XENNMI_register_callback 0 +struct xennmi_callback { + unsigned long handler_address; + unsigned long pad; +}; +DEFINE_GUEST_HANDLE_STRUCT(xennmi_callback); + +/* + * Deregister NMI callback for this (calling) VCPU. + * arg == NULL. + */ +#define XENNMI_unregister_callback 1 + +#endif /* __XEN_PUBLIC_NMI_H__ */ diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index 7000bb1f6e96..df74e65a884b 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -1,22 +1,4 @@ -/* - * 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. - */ +/* SPDX-License-Identifier: MIT */ #ifndef __XEN_PUBLIC_PHYSDEV_H__ #define __XEN_PUBLIC_PHYSDEV_H__ @@ -131,6 +113,7 @@ struct physdev_irq { #define MAP_PIRQ_TYPE_GSI 0x1 #define MAP_PIRQ_TYPE_UNKNOWN 0x2 #define MAP_PIRQ_TYPE_MSI_SEG 0x3 +#define MAP_PIRQ_TYPE_MULTI_MSI 0x4 #define PHYSDEVOP_map_pirq 13 struct physdev_map_pirq { @@ -141,11 +124,16 @@ struct physdev_map_pirq { int index; /* IN or OUT */ int pirq; - /* IN - high 16 bits hold segment for MAP_PIRQ_TYPE_MSI_SEG */ + /* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */ int bus; /* IN */ int devfn; - /* IN */ + /* IN + * - For MSI-X contains entry number. + * - For MSI with ..._MULTI_MSI contains number of vectors. + * OUT (..._MULTI_MSI only) + * - Number of vectors allocated. + */ int entry_nr; /* IN */ uint64_t table_base; @@ -231,6 +219,17 @@ struct physdev_get_free_pirq { #define XEN_PCI_DEV_VIRTFN 0x2 #define XEN_PCI_DEV_PXM 0x4 +#define XEN_PCI_MMCFG_RESERVED 0x1 + +#define PHYSDEVOP_pci_mmcfg_reserved 24 +struct physdev_pci_mmcfg_reserved { + uint64_t address; + uint16_t segment; + uint8_t start_bus; + uint8_t end_bus; + uint32_t flags; +}; + #define PHYSDEVOP_pci_device_add 25 struct physdev_pci_device_add { /* IN */ @@ -257,6 +256,13 @@ struct physdev_pci_device_add { */ #define PHYSDEVOP_prepare_msix 30 #define PHYSDEVOP_release_msix 31 +/* + * Notify the hypervisor that a PCI device has been reset, so that any + * internally cached state is regenerated. Should be called after any + * device reset performed by the hardware domain. + */ +#define PHYSDEVOP_pci_device_reset 32 + struct physdev_pci_device { /* IN */ uint16_t seg; @@ -264,6 +270,16 @@ struct physdev_pci_device { uint8_t devfn; }; +struct pci_device_reset { + struct physdev_pci_device dev; +#define PCI_DEVICE_RESET_COLD 0x0 +#define PCI_DEVICE_RESET_WARM 0x1 +#define PCI_DEVICE_RESET_HOT 0x2 +#define PCI_DEVICE_RESET_FLR 0x3 +#define PCI_DEVICE_RESET_MASK 0x3 + uint32_t flags; +}; + #define PHYSDEVOP_DBGP_RESET_PREPARE 1 #define PHYSDEVOP_DBGP_RESET_DONE 2 diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index c57d5f67f702..79a443c65ea9 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * platform.h * * Hardware platform operations. Intended for use by domain-0 kernel. * - * 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) 2002-2006, K Fraser */ @@ -35,14 +18,23 @@ * Set clock such that it would read <secs,nsecs> after 00:00:00 UTC, * 1 January, 1970 if the current system time was <system_time>. */ -#define XENPF_settime 17 -struct xenpf_settime { +#define XENPF_settime32 17 +struct xenpf_settime32 { /* IN variables. */ uint32_t secs; uint32_t nsecs; uint64_t system_time; }; -DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime_t); +DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime32_t); +#define XENPF_settime64 62 +struct xenpf_settime64 { + /* IN variables. */ + uint64_t secs; + uint32_t nsecs; + uint32_t mbz; + uint64_t system_time; +}; +DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime64_t); /* * Request memory range (@mfn, @mfn+@nr_mfns-1) to have type @type. @@ -108,11 +100,113 @@ struct xenpf_platform_quirk { }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_platform_quirk_t); +#define XENPF_efi_runtime_call 49 +#define XEN_EFI_get_time 1 +#define XEN_EFI_set_time 2 +#define XEN_EFI_get_wakeup_time 3 +#define XEN_EFI_set_wakeup_time 4 +#define XEN_EFI_get_next_high_monotonic_count 5 +#define XEN_EFI_get_variable 6 +#define XEN_EFI_set_variable 7 +#define XEN_EFI_get_next_variable_name 8 +#define XEN_EFI_query_variable_info 9 +#define XEN_EFI_query_capsule_capabilities 10 +#define XEN_EFI_update_capsule 11 + +struct xenpf_efi_runtime_call { + uint32_t function; + /* + * This field is generally used for per sub-function flags (defined + * below), except for the XEN_EFI_get_next_high_monotonic_count case, + * where it holds the single returned value. + */ + uint32_t misc; + xen_ulong_t status; + union { +#define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001 + struct { + struct xenpf_efi_time { + uint16_t year; + uint8_t month; + uint8_t day; + uint8_t hour; + uint8_t min; + uint8_t sec; + uint32_t ns; + int16_t tz; + uint8_t daylight; + } time; + uint32_t resolution; + uint32_t accuracy; + } get_time; + + struct xenpf_efi_time set_time; + +#define XEN_EFI_GET_WAKEUP_TIME_ENABLED 0x00000001 +#define XEN_EFI_GET_WAKEUP_TIME_PENDING 0x00000002 + struct xenpf_efi_time get_wakeup_time; + +#define XEN_EFI_SET_WAKEUP_TIME_ENABLE 0x00000001 +#define XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY 0x00000002 + struct xenpf_efi_time set_wakeup_time; + +#define XEN_EFI_VARIABLE_NON_VOLATILE 0x00000001 +#define XEN_EFI_VARIABLE_BOOTSERVICE_ACCESS 0x00000002 +#define XEN_EFI_VARIABLE_RUNTIME_ACCESS 0x00000004 + struct { + GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ + xen_ulong_t size; + GUEST_HANDLE(void) data; + struct xenpf_efi_guid { + uint32_t data1; + uint16_t data2; + uint16_t data3; + uint8_t data4[8]; + } vendor_guid; + } get_variable, set_variable; + + struct { + xen_ulong_t size; + GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ + struct xenpf_efi_guid vendor_guid; + } get_next_variable_name; + + struct { + uint32_t attr; + uint64_t max_store_size; + uint64_t remain_store_size; + uint64_t max_size; + } query_variable_info; + + struct { + GUEST_HANDLE(void) capsule_header_array; + xen_ulong_t capsule_count; + uint64_t max_capsule_size; + uint32_t reset_type; + } query_capsule_capabilities; + + struct { + GUEST_HANDLE(void) capsule_header_array; + xen_ulong_t capsule_count; + uint64_t sg_list; /* machine address */ + } update_capsule; + } u; +}; +DEFINE_GUEST_HANDLE_STRUCT(xenpf_efi_runtime_call); + +#define XEN_FW_EFI_VERSION 0 +#define XEN_FW_EFI_CONFIG_TABLE 1 +#define XEN_FW_EFI_VENDOR 2 +#define XEN_FW_EFI_MEM_INFO 3 +#define XEN_FW_EFI_RT_VERSION 4 + #define XENPF_firmware_info 50 #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_EFI_INFO 4 /* from EFI */ #define XEN_FW_KBD_SHIFT_FLAGS 5 /* Int16, Fn02: Get keyboard shift flags. */ + struct xenpf_firmware_info { /* IN variables. */ uint32_t type; @@ -144,6 +238,26 @@ struct xenpf_firmware_info { GUEST_HANDLE(uchar) edid; } vbeddc_info; /* XEN_FW_VBEDDC_INFO */ + union xenpf_efi_info { + uint32_t version; + struct { + uint64_t addr; /* EFI_CONFIGURATION_TABLE */ + uint32_t nent; + } cfg; + struct { + uint32_t revision; + uint32_t bufsz; /* input, in bytes */ + GUEST_HANDLE(void) name; + /* UCS-2/UTF-16 string */ + } vendor; + struct { + uint64_t addr; + uint64_t size; + uint64_t attr; + uint32_t type; + } mem; + } efi_info; /* XEN_FW_EFI_INFO */ + uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */ } u; }; @@ -152,10 +266,11 @@ DEFINE_GUEST_HANDLE_STRUCT(xenpf_firmware_info_t); #define XENPF_enter_acpi_sleep 51 struct xenpf_enter_acpi_sleep { /* IN variables */ - uint16_t pm1a_cnt_val; /* PM1a control value. */ - uint16_t pm1b_cnt_val; /* PM1b control value. */ + uint16_t val_a; /* PM1a control / sleep type A. */ + uint16_t val_b; /* PM1b control / sleep type B. */ uint32_t sleep_state; /* Which state to enter (Sn). */ - uint32_t flags; /* Must be zero. */ +#define XENPF_ACPI_SLEEP_EXTENDED 0x00000001 + uint32_t flags; /* XENPF_ACPI_SLEEP_*. */ }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_enter_acpi_sleep_t); @@ -351,16 +466,37 @@ struct xenpf_core_parking { }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_core_parking); +#define XENPF_get_symbol 63 +struct xenpf_symdata { + /* IN/OUT variables */ + uint32_t namelen; /* size of 'name' buffer */ + + /* IN/OUT variables */ + uint32_t symnum; /* IN: Symbol to read */ + /* OUT: Next available symbol. If same as IN */ + /* then we reached the end */ + + /* OUT variables */ + GUEST_HANDLE(char) name; + uint64_t address; + char type; +}; +DEFINE_GUEST_HANDLE_STRUCT(xenpf_symdata); + +#define XENPF_get_dom0_console 64 + struct xen_platform_op { uint32_t cmd; uint32_t interface_version; /* XENPF_INTERFACE_VERSION */ union { - struct xenpf_settime settime; + struct xenpf_settime32 settime32; + struct xenpf_settime64 settime64; struct xenpf_add_memtype add_memtype; struct xenpf_del_memtype del_memtype; struct xenpf_read_memtype read_memtype; struct xenpf_microcode_update microcode; struct xenpf_platform_quirk platform_quirk; + struct xenpf_efi_runtime_call efi_runtime_call; struct xenpf_firmware_info firmware_info; struct xenpf_enter_acpi_sleep enter_acpi_sleep; struct xenpf_change_freq change_freq; @@ -371,6 +507,8 @@ struct xen_platform_op { struct xenpf_cpu_hotadd cpu_add; struct xenpf_mem_hotadd mem_add; struct xenpf_core_parking core_parking; + struct xenpf_symdata symdata; + struct dom0_vga_console_info dom0_console; uint8_t pad[128]; } u; }; diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h index 9ce083960a25..4dac0634ffff 100644 --- a/include/xen/interface/sched.h +++ b/include/xen/interface/sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * sched.h * @@ -12,18 +13,30 @@ #include <xen/interface/event_channel.h> /* + * Guest Scheduler Operations + * + * The SCHEDOP interface provides mechanisms for a guest to interact + * with the scheduler, including yield, blocking and shutting itself + * down. + */ + +/* * The prototype for this hypercall is: - * long sched_op_new(int cmd, void *arg) + * long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...) + * * @cmd == SCHEDOP_??? (scheduler operation). * @arg == Operation-specific extra argument(s), as described below. + * ... == Additional Operation-specific extra arguments, described below. * - * **NOTE**: - * Versions of Xen prior to 3.0.2 provide only the following legacy version + * Versions of Xen prior to 3.0.2 provided only the following legacy version * of this hypercall, supporting only the commands yield, block and shutdown: * long sched_op(int cmd, unsigned long arg) * @cmd == SCHEDOP_??? (scheduler operation). * @arg == 0 (SCHEDOP_yield and SCHEDOP_block) * == SHUTDOWN_* code (SCHEDOP_shutdown) + * + * This legacy version is available to new guests as: + * long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg) */ /* @@ -44,12 +57,17 @@ /* * Halt execution of this domain (all VCPUs) and notify the system controller. * @arg == pointer to sched_shutdown structure. + * + * If the sched_shutdown_t reason is SHUTDOWN_suspend then + * x86 PV guests must also set RDX (EDX for 32-bit guests) to the MFN + * of the guest's start info page. RDX/EDX is the third hypercall + * argument. + * + * In addition, which reason is SHUTDOWN_suspend this hypercall + * returns 1 if suspend was cancelled or the domain was merely + * checkpointed, and 0 if it is resuming in a new domain. */ #define SCHEDOP_shutdown 2 -struct sched_shutdown { - unsigned int reason; /* SHUTDOWN_* */ -}; -DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown); /* * Poll a set of event-channel ports. Return when one or more are pending. An @@ -57,12 +75,6 @@ DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown); * @arg == pointer to sched_poll structure. */ #define SCHEDOP_poll 3 -struct sched_poll { - GUEST_HANDLE(evtchn_port_t) ports; - unsigned int nr_ports; - uint64_t timeout; -}; -DEFINE_GUEST_HANDLE_STRUCT(sched_poll); /* * Declare a shutdown for another domain. The main use of this function is @@ -71,15 +83,11 @@ DEFINE_GUEST_HANDLE_STRUCT(sched_poll); * @arg == pointer to sched_remote_shutdown structure. */ #define SCHEDOP_remote_shutdown 4 -struct sched_remote_shutdown { - domid_t domain_id; /* Remote domain ID */ - unsigned int reason; /* SHUTDOWN_xxx reason */ -}; /* * Latch a shutdown code, so that when the domain later shuts down it * reports this code to the control tools. - * @arg == as for SCHEDOP_shutdown. + * @arg == sched_shutdown, as for SCHEDOP_shutdown. */ #define SCHEDOP_shutdown_code 5 @@ -92,10 +100,47 @@ struct sched_remote_shutdown { * With id != 0 and timeout != 0, poke watchdog timer and set new timeout. */ #define SCHEDOP_watchdog 6 + +/* + * Override the current vcpu affinity by pinning it to one physical cpu or + * undo this override restoring the previous affinity. + * @arg == pointer to sched_pin_override structure. + * + * A negative pcpu value will undo a previous pin override and restore the + * previous cpu affinity. + * This call is allowed for the hardware domain only and requires the cpu + * to be part of the domain's cpupool. + */ +#define SCHEDOP_pin_override 7 + +struct sched_shutdown { + unsigned int reason; /* SHUTDOWN_* => shutdown reason */ +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown); + +struct sched_poll { + GUEST_HANDLE(evtchn_port_t) ports; + unsigned int nr_ports; + uint64_t timeout; +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_poll); + +struct sched_remote_shutdown { + domid_t domain_id; /* Remote domain ID */ + unsigned int reason; /* SHUTDOWN_* => shutdown reason */ +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_remote_shutdown); + struct sched_watchdog { uint32_t id; /* watchdog ID */ uint32_t timeout; /* timeout */ }; +DEFINE_GUEST_HANDLE_STRUCT(sched_watchdog); + +struct sched_pin_override { + int32_t pcpu; +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_pin_override); /* * Reason codes for SCHEDOP_shutdown. These may be interpreted by control @@ -108,4 +153,14 @@ struct sched_watchdog { #define SHUTDOWN_crash 3 /* Tell controller we've crashed. */ #define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */ +/* + * Domain asked to perform 'soft reset' for it. The expected behavior is to + * reset internal Xen state for the domain returning it to the point where it + * was created but leaving the domain's memory contents and vCPU contexts + * intact. This will allow the domain to start over and set up all Xen specific + * interfaces again. + */ +#define SHUTDOWN_soft_reset 5 +#define SHUTDOWN_MAX 5 /* Maximum valid shutdown reason. */ + #endif /* __XEN_PUBLIC_SCHED_H__ */ diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h index 87e6f8a48661..c7cc28ad8d63 100644 --- a/include/xen/interface/vcpu.h +++ b/include/xen/interface/vcpu.h @@ -1,26 +1,9 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * vcpu.h * * VCPU initialisation, query, and hotplug. * - * 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) 2005, Keir Fraser <keir@xensource.com> */ @@ -75,15 +58,21 @@ */ #define VCPUOP_get_runstate_info 4 struct vcpu_runstate_info { - /* VCPU's current state (RUNSTATE_*). */ - int state; - /* When was current state entered (system time, ns)? */ - uint64_t state_entry_time; - /* - * Time spent in each RUNSTATE_* (ns). The sum of these times is - * guaranteed not to drift from system time. - */ - uint64_t time[4]; + /* VCPU's current state (RUNSTATE_*). */ + int state; + /* When was current state entered (system time, ns)? */ + uint64_t state_entry_time; + /* + * Update indicator set in state_entry_time: + * When activated via VMASST_TYPE_runstate_update_flag, set during + * updates in guest memory mapped copy of vcpu_runstate_info. + */ +#define XEN_RUNSTATE_UPDATE (1ULL << 63) + /* + * Time spent in each RUNSTATE_* (ns). The sum of these times is + * guaranteed not to drift from system time. + */ + uint64_t time[4]; }; DEFINE_GUEST_HANDLE_STRUCT(vcpu_runstate_info); @@ -170,4 +159,48 @@ struct vcpu_register_vcpu_info { }; DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_vcpu_info); +/* Send an NMI to the specified VCPU. @extra_arg == NULL. */ +#define VCPUOP_send_nmi 11 + +/* + * Get the physical ID information for a pinned vcpu's underlying physical + * processor. The physical ID informmation is architecture-specific. + * On x86: id[31:0]=apic_id, id[63:32]=acpi_id. + * This command returns -EINVAL if it is not a valid operation for this VCPU. + */ +#define VCPUOP_get_physid 12 /* arg == vcpu_get_physid_t */ +struct vcpu_get_physid { + uint64_t phys_id; +}; +DEFINE_GUEST_HANDLE_STRUCT(vcpu_get_physid); +#define xen_vcpu_physid_to_x86_apicid(physid) ((uint32_t)(physid)) +#define xen_vcpu_physid_to_x86_acpiid(physid) ((uint32_t)((physid) >> 32)) + +/* + * Register a memory location to get a secondary copy of the vcpu time + * parameters. The master copy still exists as part of the vcpu shared + * memory area, and this secondary copy is updated whenever the master copy + * is updated (and using the same versioning scheme for synchronisation). + * + * The intent is that this copy may be mapped (RO) into userspace so + * that usermode can compute system time using the time info and the + * tsc. Usermode will see an array of vcpu_time_info structures, one + * for each vcpu, and choose the right one by an existing mechanism + * which allows it to get the current vcpu number (such as via a + * segment limit). It can then apply the normal algorithm to compute + * system time from the tsc. + * + * @extra_arg == pointer to vcpu_register_time_info_memory_area structure. + */ +#define VCPUOP_register_vcpu_time_memory_area 13 +DEFINE_GUEST_HANDLE_STRUCT(vcpu_time_info); +struct vcpu_register_time_memory_area { + union { + GUEST_HANDLE(vcpu_time_info) h; + struct pvclock_vcpu_time_info *v; + uint64_t p; + } addr; +}; +DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_time_memory_area); + #endif /* __XEN_PUBLIC_VCPU_H__ */ diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h index 7ff6498679a3..37d6588873d6 100644 --- a/include/xen/interface/version.h +++ b/include/xen/interface/version.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * version.h * @@ -63,4 +64,19 @@ struct xen_feature_info { /* arg == xen_domain_handle_t. */ #define XENVER_guest_handle 8 +#define XENVER_commandline 9 +struct xen_commandline { + char buf[1024]; +}; + +/* + * Return value is the number of bytes written, or XEN_Exx on error. + * Calling with empty parameter returns the size of build_id. + */ +#define XENVER_build_id 10 +struct xen_build_id { + uint32_t len; /* IN: size of buf[]. */ + unsigned char buf[]; +}; + #endif /* __XEN_PUBLIC_VERSION_H__ */ diff --git a/include/xen/interface/xen-mca.h b/include/xen/interface/xen-mca.h index 73a4ea714d93..1c9afbe8cc26 100644 --- a/include/xen/interface/xen-mca.h +++ b/include/xen/interface/xen-mca.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * arch-x86/mca.h * Guest OS machine check interface to x86 Xen. @@ -183,7 +184,6 @@ struct mc_info { DEFINE_GUEST_HANDLE_STRUCT(mc_info); #define __MC_MSR_ARRAYSIZE 8 -#define __MC_MSR_MCGCAP 0 #define __MC_NMSRS 1 #define MC_NCAPS 7 struct mcinfo_logical_cpu { @@ -332,7 +332,11 @@ struct xen_mc { }; DEFINE_GUEST_HANDLE_STRUCT(xen_mc); -/* Fields are zero when not available */ +/* + * Fields are zero when not available. Also, this struct is shared with + * userspace mcelog and thus must keep existing fields at current offsets. + * Only add new fields to the end of the structure + */ struct xen_mce { __u64 status; __u64 misc; @@ -353,6 +357,9 @@ struct xen_mce { __u32 socketid; /* CPU socket ID */ __u32 apicid; /* CPU initial apic ID */ __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */ + __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ + __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ + __u64 ppin; /* Protected Processor Inventory Number */ }; /* @@ -365,7 +372,7 @@ struct xen_mce { #define XEN_MCE_LOG_LEN 32 struct xen_mce_log { - char signature[12]; /* "MACHINECHECK" */ + char signature[12] __nonstring; /* "MACHINECHECK" */ unsigned len; /* = XEN_MCE_LOG_LEN */ unsigned next; unsigned flags; diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h index 53ec4167bd0b..0ca23eca2a9c 100644 --- a/include/xen/interface/xen.h +++ b/include/xen/interface/xen.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * xen.h * @@ -30,7 +31,7 @@ #define __HYPERVISOR_set_callbacks 4 #define __HYPERVISOR_fpu_taskswitch 5 #define __HYPERVISOR_sched_op_compat 6 -#define __HYPERVISOR_dom0_op 7 +#define __HYPERVISOR_platform_op 7 #define __HYPERVISOR_set_debugreg 8 #define __HYPERVISOR_get_debugreg 9 #define __HYPERVISOR_update_descriptor 10 @@ -49,7 +50,7 @@ #define __HYPERVISOR_vcpu_op 24 #define __HYPERVISOR_set_segment_base 25 /* x86/64 only */ #define __HYPERVISOR_mmuext_op 26 -#define __HYPERVISOR_acm_op 27 +#define __HYPERVISOR_xsm_op 27 #define __HYPERVISOR_nmi_op 28 #define __HYPERVISOR_sched_op 29 #define __HYPERVISOR_callback_op 30 @@ -57,7 +58,13 @@ #define __HYPERVISOR_event_channel_op 32 #define __HYPERVISOR_physdev_op 33 #define __HYPERVISOR_hvm_op 34 +#define __HYPERVISOR_sysctl 35 +#define __HYPERVISOR_domctl 36 +#define __HYPERVISOR_kexec_op 37 #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 @@ -73,13 +80,24 @@ * VIRTUAL INTERRUPTS * * Virtual interrupts that a guest OS may receive from Xen. + * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a + * global VIRQ. The former can be bound once per VCPU and cannot be re-bound. + * The latter can be allocated only once per guest: they must initially be + * allocated to VCPU0 but can subsequently be re-bound. */ -#define VIRQ_TIMER 0 /* Timebase update, and/or requested timeout. */ -#define VIRQ_DEBUG 1 /* Request guest to dump debug info. */ -#define VIRQ_CONSOLE 2 /* (DOM0) Bytes received on emergency console. */ -#define VIRQ_DOM_EXC 3 /* (DOM0) Exceptional event for some domain. */ -#define VIRQ_DEBUGGER 6 /* (DOM0) A domain has paused for debugging. */ -#define VIRQ_PCPU_STATE 9 /* (DOM0) PCPU state changed */ +#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */ +#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */ +#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */ +#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */ +#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */ +#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */ +#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */ +#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */ +#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */ +#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */ +#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */ +#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */ +#define VIRQ_XENPMU 13 /* PMC interrupt */ /* Architecture-specific VIRQ definitions. */ #define VIRQ_ARCH_0 16 @@ -92,24 +110,68 @@ #define VIRQ_ARCH_7 23 #define NR_VIRQS 24 + /* - * MMU-UPDATE REQUESTS - * - * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs. - * A foreigndom (FD) can be specified (or DOMID_SELF for none). - * Where the FD has some effect, it is described below. - * ptr[1:0] specifies the appropriate MMU_* command. + * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[], + * unsigned count, unsigned *done_out, + * unsigned foreigndom) + * @reqs is an array of mmu_update_t structures ((ptr, val) pairs). + * @count is the length of the above array. + * @pdone is an output parameter indicating number of completed operations + * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this + * hypercall invocation. Can be DOMID_SELF. + * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced + * in this hypercall invocation. The value of this field + * (x) encodes the PFD as follows: + * x == 0 => PFD == DOMID_SELF + * x != 0 => PFD == x - 1 * + * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command. + * ------------- * ptr[1:0] == MMU_NORMAL_PT_UPDATE: - * Updates an entry in a page table. If updating an L1 table, and the new - * table entry is valid/present, the mapped frame must belong to the FD, if - * an FD has been specified. If attempting to map an I/O page then the - * caller assumes the privilege of the FD. + * Updates an entry in a page table belonging to PFD. If updating an L1 table, + * and the new table entry is valid/present, the mapped frame must belong to + * FD. If attempting to map an I/O page then the caller assumes the privilege + * of the FD. * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller. * FD == DOMID_XEN: Map restricted areas of Xen's heap space. * ptr[:2] -- Machine address of the page-table entry to modify. * val -- Value to write. * + * There also certain implicit requirements when using this hypercall. The + * pages that make up a pagetable must be mapped read-only in the guest. + * This prevents uncontrolled guest updates to the pagetable. Xen strictly + * enforces this, and will disallow any pagetable update which will end up + * mapping pagetable page RW, and will disallow using any writable page as a + * pagetable. In practice it means that when constructing a page table for a + * process, thread, etc, we MUST be very dilligient in following these rules: + * 1). Start with top-level page (PGD or in Xen language: L4). Fill out + * the entries. + * 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD + * or L2). + * 3). Start filling out the PTE table (L1) with the PTE entries. Once + * done, make sure to set each of those entries to RO (so writeable bit + * is unset). Once that has been completed, set the PMD (L2) for this + * PTE table as RO. + * 4). When completed with all of the PMD (L2) entries, and all of them have + * been set to RO, make sure to set RO the PUD (L3). Do the same + * operation on PGD (L4) pagetable entries that have a PUD (L3) entry. + * 5). Now before you can use those pages (so setting the cr3), you MUST also + * pin them so that the hypervisor can verify the entries. This is done + * via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame + * number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op( + * MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be + * issued. + * For 32-bit guests, the L4 is not used (as there is less pagetables), so + * instead use L3. + * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE + * hypercall. Also if so desired the OS can also try to write to the PTE + * and be trapped by the hypervisor (as the PTE entry is RO). + * + * To deallocate the pages, the operations are the reverse of the steps + * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the + * pagetable MUST not be in use (meaning that the cr3 is not set to it). + * * ptr[1:0] == MMU_MACHPHYS_UPDATE: * Updates an entry in the machine->pseudo-physical mapping table. * ptr[:2] -- Machine address within the frame whose mapping to modify. @@ -119,15 +181,87 @@ * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD: * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed * with those in @val. + * + * @val is usually the machine frame number along with some attributes. + * The attributes by default follow the architecture defined bits. Meaning that + * if this is a X86_64 machine and four page table layout is used, the layout + * of val is: + * - 63 if set means No execute (NX) + * - 46-13 the machine frame number + * - 12 available for guest + * - 11 available for guest + * - 10 available for guest + * - 9 available for guest + * - 8 global + * - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages) + * - 6 dirty + * - 5 accessed + * - 4 page cached disabled + * - 3 page write through + * - 2 userspace accessible + * - 1 writeable + * - 0 present + * + * The one bits that does not fit with the default layout is the PAGE_PSE + * also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the + * HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB + * (or 2MB) instead of using the PAGE_PSE bit. + * + * The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen + * using it as the Page Attribute Table (PAT) bit - for details on it please + * refer to Intel SDM 10.12. The PAT allows to set the caching attributes of + * pages instead of using MTRRs. + * + * The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits): + * PAT4 PAT0 + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots) + * +-----+-----+----+----+----+-----+----+----+ + * | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen + * +-----+-----+----+----+----+-----+----+----+ + * + * The lookup of this index table translates to looking up + * Bit 7, Bit 4, and Bit 3 of val entry: + * + * PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3). + * + * If all bits are off, then we are using PAT0. If bit 3 turned on, + * then we are using PAT1, if bit 3 and bit 4, then PAT2.. + * + * As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means + * that if a guest that follows Linux's PAT setup and would like to set Write + * Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is + * set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the + * caching as: + * + * WB = none (so PAT0) + * WC = PWT (bit 3 on) + * UC = PWT | PCD (bit 3 and 4 are on). + * + * To make it work with Xen, it needs to translate the WC bit as so: + * + * PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3 + * + * And to translate back it would: + * + * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7. */ -#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */ -#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */ -#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */ +#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */ +#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */ +#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */ +#define MMU_PT_UPDATE_NO_TRANSLATE 3 /* checked '*ptr = val'. ptr is MA. */ /* * MMU EXTENDED OPERATIONS * - * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. + * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[], + * unsigned int count, + * unsigned int *pdone, + * unsigned int foreigndom) + */ +/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. * A foreigndom (FD) can be specified (or DOMID_SELF for none). * Where the FD has some effect, it is described below. * @@ -164,9 +298,23 @@ * cmd: MMUEXT_FLUSH_CACHE * No additional arguments. Writes back and flushes cache contents. * + * cmd: MMUEXT_FLUSH_CACHE_GLOBAL + * No additional arguments. Writes back and flushes cache contents + * on all CPUs in the system. + * * cmd: MMUEXT_SET_LDT * linear_addr: Linear address of LDT base (NB. must be page-aligned). * nr_ents: Number of entries in LDT. + * + * cmd: MMUEXT_CLEAR_PAGE + * mfn: Machine frame number to be cleared. + * + * cmd: MMUEXT_COPY_PAGE + * mfn: Machine frame number of the destination page. + * src_mfn: Machine frame number of the source page. + * + * cmd: MMUEXT_[UN]MARK_SUPER + * mfn: Machine frame number of head of superpage to be [un]marked. */ #define MMUEXT_PIN_L1_TABLE 0 #define MMUEXT_PIN_L2_TABLE 1 @@ -183,12 +331,18 @@ #define MMUEXT_FLUSH_CACHE 12 #define MMUEXT_SET_LDT 13 #define MMUEXT_NEW_USER_BASEPTR 15 +#define MMUEXT_CLEAR_PAGE 16 +#define MMUEXT_COPY_PAGE 17 +#define MMUEXT_FLUSH_CACHE_GLOBAL 18 +#define MMUEXT_MARK_SUPER 19 +#define MMUEXT_UNMARK_SUPER 20 #ifndef __ASSEMBLY__ struct mmuext_op { unsigned int cmd; union { - /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */ + /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR + * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */ xen_pfn_t mfn; /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */ unsigned long linear_addr; @@ -198,6 +352,8 @@ struct mmuext_op { unsigned int nr_ents; /* TLB_FLUSH_MULTI, INVLPG_MULTI */ void *vcpumask; + /* COPY_PAGE */ + xen_pfn_t src_mfn; } arg2; }; DEFINE_GUEST_HANDLE_STRUCT(mmuext_op); @@ -225,11 +381,39 @@ DEFINE_GUEST_HANDLE_STRUCT(mmuext_op); */ #define VMASST_CMD_enable 0 #define VMASST_CMD_disable 1 + +/* x86/32 guests: simulate full 4GB segment limits. */ #define VMASST_TYPE_4gb_segments 0 + +/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */ #define VMASST_TYPE_4gb_segments_notify 1 + +/* + * x86 guests: support writes to bottom-level PTEs. + * NB1. Page-directory entries cannot be written. + * NB2. Guest must continue to remove all writable mappings of PTEs. + */ #define VMASST_TYPE_writable_pagetables 2 + +/* x86/PAE guests: support PDPTs above 4GB. */ #define VMASST_TYPE_pae_extended_cr3 3 -#define MAX_VMASST_TYPE 3 + +/* + * x86 guests: Sane behaviour for virtual iopl + * - virtual iopl updated from do_iret() hypercalls. + * - virtual iopl reported in bounce frames. + * - guest kernels assumed to be level 0 for the purpose of iopl checks. + */ +#define VMASST_TYPE_architectural_iopl 4 + +/* + * All guests: activate update indicator in vcpu_runstate_info + * Enable setting the XEN_RUNSTATE_UPDATE flag in guest memory mapped + * vcpu_runstate_info during updates of the runstate information. + */ +#define VMASST_TYPE_runstate_update_flag 5 + +#define MAX_VMASST_TYPE 5 #ifndef __ASSEMBLY__ @@ -260,6 +444,15 @@ typedef uint16_t domid_t; */ #define DOMID_XEN (0x7FF2U) +/* DOMID_COW is used as the owner of sharable pages */ +#define DOMID_COW (0x7FF3U) + +/* DOMID_INVALID is used to identify pages with unknown owner. */ +#define DOMID_INVALID (0x7FF4U) + +/* Idle domain. */ +#define DOMID_IDLE (0x7FFFU) + /* * Send an array of these to HYPERVISOR_mmu_update(). * NB. The fields are natural pointer/address size for this architecture. @@ -272,21 +465,17 @@ DEFINE_GUEST_HANDLE_STRUCT(mmu_update); /* * Send an array of these to HYPERVISOR_multicall(). - * NB. The fields are natural register size for this architecture. + * NB. The fields are logically the natural register size for this + * architecture. In cases where xen_ulong_t is larger than this then + * any unused bits in the upper portion must be zero. */ struct multicall_entry { - unsigned long op; - long result; - unsigned long args[6]; + xen_ulong_t op; + xen_long_t result; + xen_ulong_t args[6]; }; DEFINE_GUEST_HANDLE_STRUCT(multicall_entry); -/* - * Event channel endpoints per domain: - * 1024 if a long is 32 bits; 4096 if a long is 64 bits. - */ -#define NR_EVENT_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) - struct vcpu_time_info { /* * Updates to the following values are preceded and followed @@ -392,32 +581,37 @@ struct shared_info { * their gettimeofday() syscall on this wallclock-base value. */ struct pvclock_wall_clock wc; - +#ifndef CONFIG_X86_32 + uint32_t wc_sec_hi; +#endif struct arch_shared_info arch; }; /* - * Start-of-day memory layout for the initial domain (DOM0): + * Start-of-day memory layout + * * 1. The domain is started within contiguous virtual-memory region. * 2. The contiguous region begins and ends on an aligned 4MB boundary. - * 3. The region start corresponds to the load address of the OS image. - * If the load address is not 4MB aligned then the address is rounded down. - * 4. This the order of bootstrap elements in the initial virtual region: + * 3. This the order of bootstrap elements in the initial virtual region: * a. relocated kernel image * b. initial ram disk [mod_start, mod_len] + * (may be omitted) * c. list of allocated page frames [mfn_list, nr_pages] + * (unless relocated due to XEN_ELFNOTE_INIT_P2M) * d. start_info_t structure [register ESI (x86)] - * e. bootstrap page tables [pt_base, CR3 (x86)] - * f. bootstrap stack [register ESP (x86)] - * 5. Bootstrap elements are packed together, but each is 4kB-aligned. - * 6. The initial ram disk may be omitted. - * 7. The list of page frames forms a contiguous 'pseudo-physical' memory + * in case of dom0 this page contains the console info, too + * e. unless dom0: xenstore ring page + * f. unless dom0: console ring page + * g. bootstrap page tables [pt_base, CR3 (x86)] + * h. bootstrap stack [register ESP (x86)] + * 4. Bootstrap elements are packed together, but each is 4kB-aligned. + * 5. The list of page frames forms a contiguous 'pseudo-physical' memory * layout for the domain. In particular, the bootstrap virtual-memory * region is a 1:1 mapping to the first section of the pseudo-physical map. - * 8. All bootstrap elements are mapped read-writable for the guest OS. The + * 6. All bootstrap elements are mapped read-writable for the guest OS. The * only exception is the bootstrap page table, which is mapped read-only. - * 9. There is guaranteed to be at least 512kB padding after the final + * 7. There is guaranteed to be at least 512kB padding after the final * bootstrap element. If necessary, the bootstrap virtual region is * extended by an extra 4MB to ensure this. */ @@ -448,8 +642,50 @@ struct start_info { unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */ unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ int8_t cmd_line[MAX_GUEST_CMDLINE]; + /* The pfn range here covers both page table and p->m table frames. */ + unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */ + unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */ }; +/* These flags are passed in the 'flags' field of start_info_t. */ +#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */ +#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */ +#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */ +#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */ +#define SIF_VIRT_P2M_4TOOLS (1<<4) /* Do Xen tools understand a virt. mapped */ + /* P->M making the 3 level tree obsolete? */ +#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */ + +/* + * A multiboot module is a package containing modules very similar to a + * multiboot module array. The only differences are: + * - the array of module descriptors is by convention simply at the beginning + * of the multiboot module, + * - addresses in the module descriptors are based on the beginning of the + * multiboot module, + * - the number of modules is determined by a termination descriptor that has + * mod_start == 0. + * + * This permits to both build it statically and reference it in a configuration + * file, and let the PV guest easily rebase the addresses to virtual addresses + * and at the same time count the number of modules. + */ +struct xen_multiboot_mod_list { + /* Address of first byte of the module */ + uint32_t mod_start; + /* Address of last byte of the module (inclusive) */ + uint32_t mod_end; + /* Address of zero-terminated command line */ + uint32_t cmdline; + /* Unused, must be zero */ + uint32_t pad; +}; +/* + * The console structure in start_info.console.dom0 + * + * This structure includes a variety of information required to + * have a working VGA/VESA console. + */ struct dom0_vga_console_info { uint8_t video_type; #define XEN_VGATYPE_TEXT_MODE_3 0x03 @@ -486,15 +722,13 @@ struct dom0_vga_console_info { uint32_t gbl_caps; /* Mode attributes (offset 0x0, VESA command 0x4f01). */ uint16_t mode_attrs; + uint16_t pad; + /* high 32 bits of lfb_base */ + uint32_t ext_lfb_base; } vesa_lfb; } u; }; -/* These flags are passed in the 'flags' field of start_info_t. */ -#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */ -#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */ -#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */ - typedef uint64_t cpumap_t; typedef uint8_t xen_domain_handle_t[16]; diff --git a/include/xen/interface/xencomm.h b/include/xen/interface/xencomm.h deleted file mode 100644 index ac45e0712afa..000000000000 --- a/include/xen/interface/xencomm.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * 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) IBM Corp. 2006 - */ - -#ifndef _XEN_XENCOMM_H_ -#define _XEN_XENCOMM_H_ - -/* A xencomm descriptor is a scatter/gather list containing physical - * addresses corresponding to a virtually contiguous memory area. The - * hypervisor translates these physical addresses to machine addresses to copy - * to and from the virtually contiguous area. - */ - -#define XENCOMM_MAGIC 0x58434F4D /* 'XCOM' */ -#define XENCOMM_INVALID (~0UL) - -struct xencomm_desc { - uint32_t magic; - uint32_t nr_addrs; /* the number of entries in address[] */ - uint64_t address[0]; -}; - -#endif /* _XEN_XENCOMM_H_ */ diff --git a/include/xen/interface/xenpmu.h b/include/xen/interface/xenpmu.h new file mode 100644 index 000000000000..e2ee73d91bd6 --- /dev/null +++ b/include/xen/interface/xenpmu.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: MIT */ +#ifndef __XEN_PUBLIC_XENPMU_H__ +#define __XEN_PUBLIC_XENPMU_H__ + +#include "xen.h" + +#define XENPMU_VER_MAJ 0 +#define XENPMU_VER_MIN 1 + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_xenpmu_op(enum xenpmu_op cmd, struct xenpmu_params *args); + * + * @cmd == XENPMU_* (PMU operation) + * @args == struct xenpmu_params + */ +/* ` enum xenpmu_op { */ +#define XENPMU_mode_get 0 /* Also used for getting PMU version */ +#define XENPMU_mode_set 1 +#define XENPMU_feature_get 2 +#define XENPMU_feature_set 3 +#define XENPMU_init 4 +#define XENPMU_finish 5 +#define XENPMU_lvtpc_set 6 +#define XENPMU_flush 7 + +/* ` } */ + +/* Parameters structure for HYPERVISOR_xenpmu_op call */ +struct xen_pmu_params { + /* IN/OUT parameters */ + struct { + uint32_t maj; + uint32_t min; + } version; + uint64_t val; + + /* IN parameters */ + uint32_t vcpu; + uint32_t pad; +}; + +/* PMU modes: + * - XENPMU_MODE_OFF: No PMU virtualization + * - XENPMU_MODE_SELF: Guests can profile themselves + * - XENPMU_MODE_HV: Guests can profile themselves, dom0 profiles + * itself and Xen + * - XENPMU_MODE_ALL: Only dom0 has access to VPMU and it profiles + * everyone: itself, the hypervisor and the guests. + */ +#define XENPMU_MODE_OFF 0 +#define XENPMU_MODE_SELF (1<<0) +#define XENPMU_MODE_HV (1<<1) +#define XENPMU_MODE_ALL (1<<2) + +/* + * PMU features: + * - XENPMU_FEATURE_INTEL_BTS: Intel BTS support (ignored on AMD) + */ +#define XENPMU_FEATURE_INTEL_BTS 1 + +/* + * Shared PMU data between hypervisor and PV(H) domains. + * + * The hypervisor fills out this structure during PMU interrupt and sends an + * interrupt to appropriate VCPU. + * Architecture-independent fields of xen_pmu_data are WO for the hypervisor + * and RO for the guest but some fields in xen_pmu_arch can be writable + * by both the hypervisor and the guest (see arch-$arch/pmu.h). + */ +struct xen_pmu_data { + /* Interrupted VCPU */ + uint32_t vcpu_id; + + /* + * Physical processor on which the interrupt occurred. On non-privileged + * guests set to vcpu_id; + */ + uint32_t pcpu_id; + + /* + * Domain that was interrupted. On non-privileged guests set to + * DOMID_SELF. + * On privileged guests can be DOMID_SELF, DOMID_XEN, or, when in + * XENPMU_MODE_ALL mode, domain ID of another domain. + */ + domid_t domain_id; + + uint8_t pad[6]; + + /* Architecture-specific information */ + struct xen_pmu_arch pmu; +}; + +#endif /* __XEN_PUBLIC_XENPMU_H__ */ diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h new file mode 100644 index 000000000000..3cbe3df0dfd4 --- /dev/null +++ b/include/xen/mem-reservation.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Xen memory reservation utilities. + * + * Copyright (c) 2003, B Dragovic + * Copyright (c) 2003-2004, M Williamson, K Fraser + * Copyright (c) 2005 Dan M. Smith, IBM Corporation + * Copyright (c) 2010 Daniel Kiper + * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc. + */ + +#ifndef _XENMEM_RESERVATION_H +#define _XENMEM_RESERVATION_H + +#include <linux/highmem.h> + +#include <xen/page.h> + +extern bool xen_scrub_pages; + +static inline void xenmem_reservation_scrub_page(struct page *page) +{ + if (xen_scrub_pages) + clear_highpage(page); +} + +#ifdef CONFIG_XEN_HAVE_PVMMU +void __xenmem_reservation_va_mapping_update(unsigned long count, + struct page **pages, + xen_pfn_t *frames); + +void __xenmem_reservation_va_mapping_reset(unsigned long count, + struct page **pages); +#endif + +static inline void xenmem_reservation_va_mapping_update(unsigned long count, + struct page **pages, + xen_pfn_t *frames) +{ +#ifdef CONFIG_XEN_HAVE_PVMMU + if (xen_pv_domain()) + __xenmem_reservation_va_mapping_update(count, pages, frames); +#endif +} + +static inline void xenmem_reservation_va_mapping_reset(unsigned long count, + struct page **pages) +{ +#ifdef CONFIG_XEN_HAVE_PVMMU + if (xen_pv_domain()) + __xenmem_reservation_va_mapping_reset(count, pages); +#endif +} + +int xenmem_reservation_increase(int count, xen_pfn_t *frames); + +int xenmem_reservation_decrease(int count, xen_pfn_t *frames); + +#endif diff --git a/include/xen/page.h b/include/xen/page.h index 12765b6f9517..285677b42943 100644 --- a/include/xen/page.h +++ b/include/xen/page.h @@ -1,14 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_PAGE_H #define _XEN_PAGE_H +#include <asm/page.h> + +/* The hypercall interface supports only 4KB page */ +#define XEN_PAGE_SHIFT 12 +#define XEN_PAGE_SIZE (_AC(1, UL) << XEN_PAGE_SHIFT) +#define XEN_PAGE_MASK (~(XEN_PAGE_SIZE-1)) +#define xen_offset_in_page(p) ((unsigned long)(p) & ~XEN_PAGE_MASK) + +/* + * We assume that PAGE_SIZE is a multiple of XEN_PAGE_SIZE + * XXX: Add a BUILD_BUG_ON? + */ + +#define xen_pfn_to_page(xen_pfn) \ + (pfn_to_page((unsigned long)(xen_pfn) >> (PAGE_SHIFT - XEN_PAGE_SHIFT))) +#define page_to_xen_pfn(page) \ + ((page_to_pfn(page)) << (PAGE_SHIFT - XEN_PAGE_SHIFT)) + +#define XEN_PFN_PER_PAGE (PAGE_SIZE / XEN_PAGE_SIZE) + +#define XEN_PFN_DOWN(x) ((x) >> XEN_PAGE_SHIFT) +#define XEN_PFN_UP(x) (((x) + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT) + #include <asm/xen/page.h> +/* Return the GFN associated to the first 4KB of the page */ +static inline unsigned long xen_page_to_gfn(struct page *page) +{ + return pfn_to_gfn(page_to_xen_pfn(page)); +} + struct xen_memory_region { - phys_addr_t start; - phys_addr_t size; + unsigned long start_pfn; + unsigned long n_pfns; }; -#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820MAX */ +#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820_MAX_ENTRIES_ZEROPAGE */ extern __initdata struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS]; diff --git a/include/xen/pci.h b/include/xen/pci.h new file mode 100644 index 000000000000..424b8ea89ca8 --- /dev/null +++ b/include/xen/pci.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __XEN_PCI_H__ +#define __XEN_PCI_H__ + +#if defined(CONFIG_XEN_DOM0) +int xen_reset_device(const struct pci_dev *dev); +int xen_find_device_domain_owner(struct pci_dev *dev); +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); +int xen_unregister_device_domain_owner(struct pci_dev *dev); +#else +static inline int xen_reset_device(const struct pci_dev *dev) +{ + return -1; +} + +static inline int xen_find_device_domain_owner(struct pci_dev *dev) +{ + return -1; +} + +static inline int xen_register_device_domain_owner(struct pci_dev *dev, + uint16_t domain) +{ + return -1; +} + +static inline int xen_unregister_device_domain_owner(struct pci_dev *dev) +{ + return -1; +} +#endif + +#endif diff --git a/include/xen/platform_pci.h b/include/xen/platform_pci.h index 438c256c274b..e51e7cb71a85 100644 --- a/include/xen/platform_pci.h +++ b/include/xen/platform_pci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_PLATFORM_PCI_H #define _XEN_PLATFORM_PCI_H @@ -46,6 +47,27 @@ static inline int xen_must_unplug_disks(void) { #endif } -extern int xen_platform_pci_unplug; - +#if defined(CONFIG_XEN_PVHVM) +extern bool xen_has_pv_devices(void); +extern bool xen_has_pv_disk_devices(void); +extern bool xen_has_pv_nic_devices(void); +extern bool xen_has_pv_and_legacy_disk_devices(void); +#else +static inline bool xen_has_pv_devices(void) +{ + return IS_ENABLED(CONFIG_XEN); +} +static inline bool xen_has_pv_disk_devices(void) +{ + return IS_ENABLED(CONFIG_XEN); +} +static inline bool xen_has_pv_nic_devices(void) +{ + return IS_ENABLED(CONFIG_XEN); +} +static inline bool xen_has_pv_and_legacy_disk_devices(void) +{ + return false; +} +#endif #endif /* _XEN_PLATFORM_PCI_H */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index de8bcc641c49..808d17ad8d57 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -1,58 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SWIOTLB_XEN_H #define __LINUX_SWIOTLB_XEN_H #include <linux/swiotlb.h> +#include <asm/xen/swiotlb-xen.h> -extern int xen_swiotlb_init(int verbose, bool early); +void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir); +void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir); -extern void -*xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs); - -extern void -xen_swiotlb_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); - -extern dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - struct dma_attrs *attrs); - -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_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); - -extern void -xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); - -extern void -xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - -extern void -xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir); - -extern void -xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); - -extern int -xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); - -extern int -xen_swiotlb_dma_supported(struct device *hwdev, u64 mask); +extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ diff --git a/include/xen/tmem.h b/include/xen/tmem.h deleted file mode 100644 index 3930a90045ff..000000000000 --- a/include/xen/tmem.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _XEN_TMEM_H -#define _XEN_TMEM_H - -#include <linux/types.h> - -#ifdef CONFIG_XEN_TMEM_MODULE -#define tmem_enabled true -#else -/* defined in drivers/xen/tmem.c */ -extern bool tmem_enabled; -#endif - -#ifdef CONFIG_XEN_SELFBALLOONING -extern int xen_selfballoon_init(bool, bool); -#endif - -#endif /* _XEN_TMEM_H */ diff --git a/include/xen/xen-front-pgdir-shbuf.h b/include/xen/xen-front-pgdir-shbuf.h new file mode 100644 index 000000000000..150ef7ec51ec --- /dev/null +++ b/include/xen/xen-front-pgdir-shbuf.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen frontend/backend page directory based shared buffer + * helper module. + * + * Copyright (C) 2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_FRONT_PGDIR_SHBUF_H_ +#define __XEN_FRONT_PGDIR_SHBUF_H_ + +#include <linux/kernel.h> + +#include <xen/grant_table.h> + +struct xen_front_pgdir_shbuf_ops; + +struct xen_front_pgdir_shbuf { + /* + * Number of references granted for the backend use: + * + * - for frontend allocated/imported buffers this holds the number + * of grant references for the page directory and the pages + * of the buffer + * + * - for the buffer provided by the backend this only holds the number + * of grant references for the page directory itself as grant + * references for the buffer will be provided by the backend. + */ + int num_grefs; + grant_ref_t *grefs; + /* Page directory backing storage. */ + u8 *directory; + + /* + * Number of pages for the shared buffer itself (excluding the page + * directory). + */ + int num_pages; + /* + * Backing storage of the shared buffer: these are the pages being + * shared. + */ + struct page **pages; + + struct xenbus_device *xb_dev; + + /* These are the ops used internally depending on be_alloc mode. */ + const struct xen_front_pgdir_shbuf_ops *ops; + + /* Xen map handles for the buffer allocated by the backend. */ + grant_handle_t *backend_map_handles; +}; + +struct xen_front_pgdir_shbuf_cfg { + struct xenbus_device *xb_dev; + + /* Number of pages of the buffer backing storage. */ + int num_pages; + /* Pages of the buffer to be shared. */ + struct page **pages; + + /* + * This is allocated outside because there are use-cases when + * the buffer structure is allocated as a part of a bigger one. + */ + struct xen_front_pgdir_shbuf *pgdir; + /* + * Mode of grant reference sharing: if set then backend will share + * grant references to the buffer with the frontend. + */ + int be_alloc; +}; + +int xen_front_pgdir_shbuf_alloc(struct xen_front_pgdir_shbuf_cfg *cfg); + +grant_ref_t +xen_front_pgdir_shbuf_get_dir_start(struct xen_front_pgdir_shbuf *buf); + +int xen_front_pgdir_shbuf_map(struct xen_front_pgdir_shbuf *buf); + +int xen_front_pgdir_shbuf_unmap(struct xen_front_pgdir_shbuf *buf); + +void xen_front_pgdir_shbuf_free(struct xen_front_pgdir_shbuf *buf); + +#endif /* __XEN_FRONT_PGDIR_SHBUF_H_ */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index d6fe062cad6b..496e6013c689 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -1,37 +1,228 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef INCLUDE_XEN_OPS_H #define INCLUDE_XEN_OPS_H #include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/efi.h> +#include <linux/virtio_anchor.h> +#include <xen/xen.h> +#include <xen/features.h> #include <asm/xen/interface.h> +#include <xen/interface/vcpu.h> DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); +DECLARE_PER_CPU(uint32_t, xen_vcpu_id); +static inline uint32_t xen_vcpu_nr(int cpu) +{ + return per_cpu(xen_vcpu_id, cpu); +} + +#define XEN_VCPU_ID_INVALID U32_MAX + void xen_arch_pre_suspend(void); void xen_arch_post_suspend(int suspend_cancelled); -void xen_arch_hvm_post_suspend(int suspend_cancelled); - -void xen_mm_pin_all(void); -void xen_mm_unpin_all(void); void xen_timer_resume(void); void xen_arch_resume(void); +void xen_arch_suspend(void); + +void xen_reboot(int reason); + +void xen_resume_notifier_register(struct notifier_block *nb); + +bool xen_vcpu_stolen(int vcpu); +void xen_setup_runstate_info(int cpu); +void xen_time_setup_guest(void); +void xen_manage_runstate_time(int action); +u64 xen_steal_clock(int cpu); int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -int xen_create_contiguous_region(unsigned long vstart, unsigned int order, - unsigned int address_bits); -void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order); +#if defined(CONFIG_XEN_PV) +int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, + unsigned int domid, bool no_translate); +#else +static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, + pgprot_t prot, unsigned int domid, + bool no_translate) +{ + BUG(); + return 0; +} +#endif struct vm_area_struct; -int xen_remap_domain_mfn_range(struct vm_area_struct *vma, - unsigned long addr, - xen_pfn_t mfn, int nr, - pgprot_t prot, unsigned domid, - struct page **pages); -int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, + +#ifdef CONFIG_XEN_AUTO_XLATE +int xen_xlate_remap_gfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *gfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned int domid, + struct page **pages); +int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, + int nr, struct page **pages); +#else +/* + * These two functions are called from arch/x86/xen/mmu.c and so stubs + * are needed for a configuration not specifying CONFIG_XEN_AUTO_XLATE. + */ +static inline int xen_xlate_remap_gfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *gfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned int domid, + struct page **pages) +{ + return -EOPNOTSUPP; +} + +static inline int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, + int nr, struct page **pages) +{ + return -EOPNOTSUPP; +} +#endif + +int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long len); + +/* + * xen_remap_domain_gfn_array() - map an array of foreign frames by gfn + * @vma: VMA to map the pages into + * @addr: Address at which to map the pages + * @gfn: Array of GFNs to map + * @nr: Number entries in the GFN array + * @err_ptr: Returns per-GFN error status. + * @prot: page protection mask + * @domid: Domain owning the pages + * @pages: Array of pages if this domain has an auto-translated physmap + * + * @gfn and @err_ptr may point to the same buffer, the GFNs will be + * overwritten by the error codes after they are mapped. + * + * Returns the number of successfully mapped frames, or a -ve error + * code. + */ +static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *gfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned int domid, + struct page **pages) +{ + if (!xen_pv_domain()) + return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr, + prot, domid, pages); + + /* We BUG_ON because it's a programmer error to pass a NULL err_ptr, + * and the consequences later is quite hard to detect what the actual + * cause of "wrong memory was mapped in". + */ + BUG_ON(err_ptr == NULL); + return xen_remap_pfn(vma, addr, gfn, nr, err_ptr, prot, domid, + false); +} + +/* + * xen_remap_domain_mfn_array() - map an array of foreign frames by mfn + * @vma: VMA to map the pages into + * @addr: Address at which to map the pages + * @mfn: Array of MFNs to map + * @nr: Number entries in the MFN array + * @err_ptr: Returns per-MFN error status. + * @prot: page protection mask + * @domid: Domain owning the pages + * + * @mfn and @err_ptr may point to the same buffer, the MFNs will be + * overwritten by the error codes after they are mapped. + * + * Returns the number of successfully mapped frames, or a -ve error + * code. + */ +static inline int xen_remap_domain_mfn_array(struct vm_area_struct *vma, + unsigned long addr, xen_pfn_t *mfn, + int nr, int *err_ptr, + pgprot_t prot, unsigned int domid) +{ + if (!xen_pv_domain()) + return -EOPNOTSUPP; + + return xen_remap_pfn(vma, addr, mfn, nr, err_ptr, prot, domid, + true); +} + +/* xen_remap_domain_gfn_range() - map a range of foreign frames + * @vma: VMA to map the pages into + * @addr: Address at which to map the pages + * @gfn: First GFN to map. + * @nr: Number frames to map + * @prot: page protection mask + * @domid: Domain owning the pages + * @pages: Array of pages if this domain has an auto-translated physmap + * + * Returns the number of successfully mapped frames, or a -ve error + * code. + */ +static inline int xen_remap_domain_gfn_range(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t gfn, int nr, + pgprot_t prot, unsigned int domid, + struct page **pages) +{ + if (!xen_pv_domain()) + return -EOPNOTSUPP; + + return xen_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false); +} + +int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages); +int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr, + unsigned long nr_grant_frames); + bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); + +void xen_efi_runtime_setup(void); + + +#if defined(CONFIG_XEN_PV) && !defined(CONFIG_PREEMPTION) + +DECLARE_PER_CPU(bool, xen_in_preemptible_hcall); + +static inline void xen_preemptible_hcall_begin(void) +{ + __this_cpu_write(xen_in_preemptible_hcall, true); +} + +static inline void xen_preemptible_hcall_end(void) +{ + __this_cpu_write(xen_in_preemptible_hcall, false); +} + +#else + +static inline void xen_preemptible_hcall_begin(void) { } +static inline void xen_preemptible_hcall_end(void) { } + +#endif /* CONFIG_XEN_PV && !CONFIG_PREEMPTION */ + +#ifdef CONFIG_XEN_GRANT_DMA_OPS +bool xen_virtio_restricted_mem_acc(struct virtio_device *dev); +#else +struct virtio_device; + +static inline bool xen_virtio_restricted_mem_acc(struct virtio_device *dev) +{ + return false; +} +#endif /* CONFIG_XEN_GRANT_DMA_OPS */ + #endif /* INCLUDE_XEN_OPS_H */ diff --git a/include/xen/xen.h b/include/xen/xen.h index a74d4362c4f8..61854e3f2837 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -1,6 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_XEN_H #define _XEN_XEN_H +#include <linux/types.h> + enum xen_domain_type { XEN_NATIVE, /* running on bare hardware */ XEN_PV_DOMAIN, /* running in a PV domain */ @@ -13,20 +16,86 @@ extern enum xen_domain_type xen_domain_type; #define xen_domain_type XEN_NATIVE #endif +#ifdef CONFIG_XEN_PVH +extern bool xen_pvh; +#else +#define xen_pvh 0 +#endif + +#ifdef CONFIG_X86 +#include <asm/cpufeature.h> + +#define xen_pv_domain() (cpu_feature_enabled(X86_FEATURE_XENPV)) +#else +#define xen_pv_domain() 0 +#endif + #define xen_domain() (xen_domain_type != XEN_NATIVE) -#define xen_pv_domain() (xen_domain() && \ - xen_domain_type == XEN_PV_DOMAIN) -#define xen_hvm_domain() (xen_domain() && \ - xen_domain_type == XEN_HVM_DOMAIN) +#define xen_hvm_domain() (xen_domain_type == XEN_HVM_DOMAIN) +#define xen_pvh_domain() (xen_pvh) + +extern uint32_t xen_start_flags; + +#ifdef CONFIG_XEN_PV +extern bool xen_pv_pci_possible; +#else +#define xen_pv_pci_possible 0 +#endif + +#include <xen/interface/hvm/start_info.h> +extern struct hvm_start_info pvh_start_info; +void xen_prepare_pvh(void); +struct pt_regs; +void xen_pv_evtchn_do_upcall(struct pt_regs *regs); #ifdef CONFIG_XEN_DOM0 #include <xen/interface/xen.h> #include <asm/xen/hypervisor.h> #define xen_initial_domain() (xen_domain() && \ - xen_start_info && xen_start_info->flags & SIF_INITDOMAIN) + (xen_start_flags & SIF_INITDOMAIN)) #else /* !CONFIG_XEN_DOM0 */ #define xen_initial_domain() (0) #endif /* CONFIG_XEN_DOM0 */ +struct bio_vec; +struct page; + +bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, + const struct page *page); + +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON) +extern u64 xen_saved_max_mem_size; +#endif + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); +void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); +#include <linux/ioport.h> +int arch_xen_unpopulated_init(struct resource **res); +#else +#include <xen/balloon.h> +static inline int xen_alloc_unpopulated_pages(unsigned int nr_pages, + struct page **pages) +{ + return xen_alloc_ballooned_pages(nr_pages, pages); +} +static inline void xen_free_unpopulated_pages(unsigned int nr_pages, + struct page **pages) +{ + xen_free_ballooned_pages(nr_pages, pages); +} +#endif + +#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI) && defined(CONFIG_X86) +bool __init xen_processor_present(uint32_t acpi_id); +#else +#include <linux/bug.h> +static inline bool xen_processor_present(uint32_t acpi_id) +{ + BUG(); + return false; +} +#endif + #endif /* _XEN_XEN_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 569c07f2e344..c94caf852aea 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -38,13 +38,19 @@ #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> +#include <linux/semaphore.h> #include <xen/interface/xen.h> #include <xen/interface/grant_table.h> #include <xen/interface/io/xenbus.h> #include <xen/interface/io/xs_wire.h> +#include <xen/interface/event_channel.h> + +#define XENBUS_MAX_RING_GRANT_ORDER 4 +#define XENBUS_MAX_RING_GRANTS (1U << XENBUS_MAX_RING_GRANT_ORDER) /* Register callback to watch this node. */ struct xenbus_watch @@ -54,9 +60,18 @@ struct xenbus_watch /* Path being watched. */ const char *node; + unsigned int nr_pending; + + /* + * Called just before enqueing new event while a spinlock is held. + * The event will be discarded if this callback returns false. + */ + bool (*will_handle)(struct xenbus_watch *, + const char *path, const char *token); + /* 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); }; @@ -71,12 +86,17 @@ struct xenbus_device { enum xenbus_state state; struct completion down; struct work_struct work; + struct semaphore reclaim_sem; + + /* Event channel based statistics and settings. */ + atomic_t event_channels; + atomic_t events; + atomic_t spurious_events; + atomic_t jiffies_eoi_delayed; + unsigned int spurious_threshold; }; -static inline struct xenbus_device *to_xenbus_device(struct device *dev) -{ - return container_of(dev, struct xenbus_device, dev); -} +#define to_xenbus_device(__dev) container_of_const(__dev, struct xenbus_device, dev) struct xenbus_device_id { @@ -86,34 +106,37 @@ struct xenbus_device_id /* A xenbus driver. */ struct xenbus_driver { + const char *name; /* defaults to ids[0].devicetype */ const struct xenbus_device_id *ids; + bool allow_rebind; /* avoid setting xenstore closed during remove */ + bool not_essential; /* is not mandatory for boot progress */ int (*probe)(struct xenbus_device *dev, const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, enum xenbus_state backend_state); - int (*remove)(struct xenbus_device *dev); + void (*remove)(struct xenbus_device *dev); int (*suspend)(struct xenbus_device *dev); int (*resume)(struct xenbus_device *dev); - int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *); + int (*uevent)(const struct xenbus_device *, struct kobj_uevent_env *); struct device_driver driver; int (*read_otherend_details)(struct xenbus_device *dev); int (*is_ready)(struct xenbus_device *dev); + void (*reclaim_memory)(struct xenbus_device *dev); }; -#define DEFINE_XENBUS_DRIVER(var, drvname, methods...) \ -struct xenbus_driver var ## _driver = { \ - .driver.name = drvname + 0 ?: var ## _ids->devicetype, \ - .driver.owner = THIS_MODULE, \ - .ids = var ## _ids, ## methods \ -} +#define to_xenbus_driver(__drv) container_of_const(__drv, struct xenbus_driver, driver) -static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv) -{ - return container_of(drv, struct xenbus_driver, driver); -} +int __must_check __xenbus_register_frontend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); +int __must_check __xenbus_register_backend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); -int __must_check xenbus_register_frontend(struct xenbus_driver *); -int __must_check xenbus_register_backend(struct xenbus_driver *); +#define xenbus_register_frontend(drv) \ + __xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME) +#define xenbus_register_backend(drv) \ + __xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME) void xenbus_unregister_driver(struct xenbus_driver *drv); @@ -131,19 +154,21 @@ void *xenbus_read(struct xenbus_transaction t, const char *dir, const char *node, unsigned int *len); int xenbus_write(struct xenbus_transaction t, const char *dir, const char *node, const char *string); -int xenbus_mkdir(struct xenbus_transaction t, - const char *dir, const char *node); int xenbus_exists(struct xenbus_transaction t, const char *dir, const char *node); int xenbus_rm(struct xenbus_transaction t, const char *dir, const char *node); int xenbus_transaction_start(struct xenbus_transaction *t); -int xenbus_transaction_end(struct xenbus_transaction t, int abort); +int xenbus_transaction_end(struct xenbus_transaction t, bool abort); /* Single read and scanf: returns -errno or num scanned if > 0. */ __scanf(4, 5) int xenbus_scanf(struct xenbus_transaction t, const char *dir, const char *node, const char *fmt, ...); +/* Read an (optional) unsigned value. */ +unsigned int xenbus_read_unsigned(const char *dir, const char *node, + unsigned int default_val); + /* Single printf and write: returns -errno or 0. */ __printf(4, 5) int xenbus_printf(struct xenbus_transaction t, @@ -153,7 +178,7 @@ int xenbus_printf(struct xenbus_transaction t, * sprintf-style type string, and pointer. Returns 0 or errno.*/ int xenbus_gather(struct xenbus_transaction t, const char *dir, ...); -/* notifer routines for when the xenstore comes up */ +/* notifier routines for when the xenstore comes up */ extern int xenstored_ready; int register_xenstore_notifier(struct notifier_block *nb); void unregister_xenstore_notifier(struct notifier_block *nb); @@ -164,17 +189,8 @@ 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) { \ kfree(str); \ @@ -187,28 +203,30 @@ void xenbus_suspend_cancel(void); int xenbus_watch_path(struct xenbus_device *dev, const char *path, struct xenbus_watch *watch, + bool (*will_handle)(struct xenbus_watch *, + const char *, const char *), void (*callback)(struct xenbus_watch *, - const char **, unsigned int)); -__printf(4, 5) + const char *, const char *)); +__printf(5, 6) int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, + bool (*will_handle)(struct xenbus_watch *, + const char *, const char *), 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); -int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); -int xenbus_map_ring_valloc(struct xenbus_device *dev, - int gnt_ref, void **vaddr); -int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref, - grant_handle_t *handle, void *vaddr); +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, + unsigned int nr_pages, grant_ref_t *grefs); +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs); +int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, + unsigned int nr_grefs, void **vaddr); int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr); -int xenbus_unmap_ring(struct xenbus_device *dev, - grant_handle_t handle, void *vaddr); -int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); -int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port); -int xenbus_free_evtchn(struct xenbus_device *dev, int port); +int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port); +int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port); enum xenbus_state xenbus_read_driver_state(const char *path); @@ -221,4 +239,8 @@ 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 */ diff --git a/include/xen/xenbus_dev.h b/include/xen/xenbus_dev.h index bbee8c6a349d..4dc45a51c044 100644 --- a/include/xen/xenbus_dev.h +++ b/include/xen/xenbus_dev.h @@ -1,6 +1,4 @@ /****************************************************************************** - * evtchn.h - * * Interface to /dev/xen/xenbus_backend. * * Copyright (c) 2011 Bastian Blank <waldi@debian.org> diff --git a/include/xen/xencomm.h b/include/xen/xencomm.h deleted file mode 100644 index e43b039be112..000000000000 --- a/include/xen/xencomm.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) IBM Corp. 2006 - * - * Authors: Hollis Blanchard <hollisb@us.ibm.com> - * Jerone Young <jyoung5@us.ibm.com> - */ - -#ifndef _LINUX_XENCOMM_H_ -#define _LINUX_XENCOMM_H_ - -#include <xen/interface/xencomm.h> - -#define XENCOMM_MINI_ADDRS 3 -struct xencomm_mini { - struct xencomm_desc _desc; - uint64_t address[XENCOMM_MINI_ADDRS]; -}; - -/* To avoid additionnal virt to phys conversion, an opaque structure is - presented. */ -struct xencomm_handle; - -extern void xencomm_free(struct xencomm_handle *desc); -extern struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes); -extern struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, - unsigned long bytes, struct xencomm_mini *xc_area); - -#if 0 -#define XENCOMM_MINI_ALIGNED(xc_desc, n) \ - struct xencomm_mini xc_desc ## _base[(n)] \ - __attribute__((__aligned__(sizeof(struct xencomm_mini)))); \ - struct xencomm_mini *xc_desc = &xc_desc ## _base[0]; -#else -/* - * gcc bug workaround: - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=16660 - * gcc doesn't handle properly stack variable with - * __attribute__((__align__(sizeof(struct xencomm_mini)))) - */ -#define XENCOMM_MINI_ALIGNED(xc_desc, n) \ - unsigned char xc_desc ## _base[((n) + 1 ) * \ - sizeof(struct xencomm_mini)]; \ - struct xencomm_mini *xc_desc = (struct xencomm_mini *) \ - ((unsigned long)xc_desc ## _base + \ - (sizeof(struct xencomm_mini) - \ - ((unsigned long)xc_desc ## _base) % \ - sizeof(struct xencomm_mini))); -#endif -#define xencomm_map_no_alloc(ptr, bytes) \ - ({ XENCOMM_MINI_ALIGNED(xc_desc, 1); \ - __xencomm_map_no_alloc(ptr, bytes, xc_desc); }) - -/* provided by architecture code: */ -extern unsigned long xencomm_vtop(unsigned long vaddr); - -static inline void *xencomm_pa(void *ptr) -{ - return (void *)xencomm_vtop((unsigned long)ptr); -} - -#define xen_guest_handle(hnd) ((hnd).p) - -#endif /* _LINUX_XENCOMM_H_ */ |