Merge tag 'for-linus-4.8-rc0-tag' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/xen/tip

Pull xen updates from David Vrabel:
 "Features and fixes for 4.8-rc0:

   - ACPI support for guests on ARM platforms.
   - Generic steal time support for arm and x86.
   - Support cases where kernel cpu is not Xen VCPU number (e.g., if
     in-guest kexec is used).
   - Use the system workqueue instead of a custom workqueue in various
     places"

* tag 'for-linus-4.8-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (47 commits)
  xen: add static initialization of steal_clock op to xen_time_ops
  xen/pvhvm: run xen_vcpu_setup() for the boot CPU
  xen/evtchn: use xen_vcpu_id mapping
  xen/events: fifo: use xen_vcpu_id mapping
  xen/events: use xen_vcpu_id mapping in events_base
  x86/xen: use xen_vcpu_id mapping when pointing vcpu_info to shared_info
  x86/xen: use xen_vcpu_id mapping for HYPERVISOR_vcpu_op
  xen: introduce xen_vcpu_id mapping
  x86/acpi: store ACPI ids from MADT for future usage
  x86/xen: update cpuid.h from Xen-4.7
  xen/evtchn: add IOCTL_EVTCHN_RESTRICT
  xen-blkback: really don't leak mode property
  xen-blkback: constify instance of "struct attribute_group"
  xen-blkfront: prefer xenbus_scanf() over xenbus_gather()
  xen-blkback: prefer xenbus_scanf() over xenbus_gather()
  xen: support runqueue steal time on xen
  arm/xen: add support for vm_assist hypercall
  xen: update xen headers
  xen-pciback: drop superfluous variables
  xen-pciback: short-circuit read path used for merging write values
  ...

Documentation/devicetree/bindings/arm/xen.txt

@@ -11,15 +11,50 @@ the following properties:
   memory where the grant table should be mapped to, using an
   HYPERVISOR_memory_op hypercall. The memory region is large enough to map
   the whole grant table (it is larger or equal to gnttab_max_grant_frames()).
+  This property is unnecessary when booting Dom0 using ACPI.
 
 - interrupts: the interrupt used by Xen to inject event notifications.
   A GIC node is also required.
+  This property is unnecessary when booting Dom0 using ACPI.
 
+To support UEFI on Xen ARM virtual platforms, Xen populates the FDT "uefi" node
+under /hypervisor with following parameters:
+
+________________________________________________________________________________
+Name                      | Size   | Description
+================================================================================
+xen,uefi-system-table     | 64-bit | Guest physical address of the UEFI System
+			  |	   | Table.
+--------------------------------------------------------------------------------
+xen,uefi-mmap-start       | 64-bit | Guest physical address of the UEFI memory
+			  |	   | map.
+--------------------------------------------------------------------------------
+xen,uefi-mmap-size        | 32-bit | Size in bytes of the UEFI memory map
+                          |        | pointed to in previous entry.
+--------------------------------------------------------------------------------
+xen,uefi-mmap-desc-size   | 32-bit | Size in bytes of each entry in the UEFI
+                          |        | memory map.
+--------------------------------------------------------------------------------
+xen,uefi-mmap-desc-ver    | 32-bit | Version of the mmap descriptor format.
+--------------------------------------------------------------------------------
 
 Example (assuming #address-cells = <2> and #size-cells = <2>):
 
 hypervisor {
 	compatible = "xen,xen-4.3", "xen,xen";
 	reg = <0 0xb0000000 0 0x20000>;
 	interrupts = <1 15 0xf08>;
+	uefi {
+		xen,uefi-system-table = <0xXXXXXXXX>;
+		xen,uefi-mmap-start = <0xXXXXXXXX>;
+		xen,uefi-mmap-size = <0xXXXXXXXX>;
+		xen,uefi-mmap-desc-size = <0xXXXXXXXX>;
+		xen,uefi-mmap-desc-ver = <0xXXXXXXXX>;
+        };
 };
+
+The format and meaning of the "xen,uefi-*" parameters are similar to those in
+Documentation/arm/uefi.txt, which are provided by the regular UEFI stub. However
+they differ because they are provided by the Xen hypervisor, together with a set
+of UEFI runtime services implemented via hypercalls, see
+http://xenbits.xen.org/docs/unstable/hypercall/x86_64/include,public,platform.h.html.

arch/arm/include/asm/xen/hypercall.h

@@ -52,6 +52,7 @@ 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_tmem_op(void *arg);
+int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
 int HYPERVISOR_platform_op_raw(void *arg);
 static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
 {

arch/arm/include/asm/xen/xen-ops.h

@@ -0,0 +1,6 @@
+#ifndef _ASM_XEN_OPS_H
+#define _ASM_XEN_OPS_H
+
+void xen_efi_runtime_setup(void);
+
+#endif /* _ASM_XEN_OPS_H */

arch/arm/kernel/setup.c

@@ -1064,6 +1064,7 @@ void __init setup_arch(char **cmdline_p)
 	early_paging_init(mdesc);
 #endif
 	setup_dma_zone(mdesc);
+	xen_early_init();
 	efi_init();
 	sanity_check_meminfo();
 	arm_memblock_init(mdesc);
@@ -1080,7 +1081,6 @@ void __init setup_arch(char **cmdline_p)
 
 	arm_dt_init_cpu_maps();
 	psci_dt_init();
-	xen_early_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
 		if (!mdesc->smp_init || !mdesc->smp_init()) {

arch/arm/xen/Makefile

@@ -1 +1,2 @@
 obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o
+obj-$(CONFIG_XEN_EFI) += efi.o

arch/arm/xen/efi.c

@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2015, Linaro Limited, Shannon Zhao
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/efi.h>
+#include <xen/xen-ops.h>
+#include <asm/xen/xen-ops.h>
+
+/* Set XEN EFI runtime services function pointers. Other fields of struct efi,
+ * e.g. efi.systab, will be set like normal EFI.
+ */
+void __init xen_efi_runtime_setup(void)
+{
+	efi.get_time                 = xen_efi_get_time;
+	efi.set_time                 = xen_efi_set_time;
+	efi.get_wakeup_time          = xen_efi_get_wakeup_time;
+	efi.set_wakeup_time          = xen_efi_set_wakeup_time;
+	efi.get_variable             = xen_efi_get_variable;
+	efi.get_next_variable        = xen_efi_get_next_variable;
+	efi.set_variable             = xen_efi_set_variable;
+	efi.query_variable_info      = xen_efi_query_variable_info;
+	efi.update_capsule           = xen_efi_update_capsule;
+	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
+	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
+	efi.reset_system             = NULL; /* Functionality provided by Xen. */
+}
+EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);

arch/arm/xen/enlighten.c

@@ -12,14 +12,16 @@
 #include <xen/page.h>
 #include <xen/interface/sched.h>
 #include <xen/xen-ops.h>
-#include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
+#include <asm/xen/xen-ops.h>
 #include <asm/system_misc.h>
+#include <asm/efi.h>
 #include <linux/interrupt.h>
 #include <linux/irqreturn.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_fdt.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/cpuidle.h>
@@ -30,6 +32,7 @@
 #include <linux/time64.h>
 #include <linux/timekeeping.h>
 #include <linux/timekeeper_internal.h>
+#include <linux/acpi.h>
 
 #include <linux/mm.h>
 
@@ -46,14 +49,16 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 static struct vcpu_info __percpu *xen_vcpu_info;
 
+/* Linux <-> Xen vCPU id mapping */
+DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
 /* These are unused until we support booting "pre-ballooned" */
 unsigned long xen_released_pages;
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
 static __read_mostly unsigned int xen_events_irq;
 
-static __initdata struct device_node *xen_node;
-
 int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       xen_pfn_t *gfn, int nr,
@@ -84,19 +89,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
 
-static unsigned long long xen_stolen_accounting(int cpu)
-{
-	struct vcpu_runstate_info state;
-
-	BUG_ON(cpu != smp_processor_id());
-
-	xen_get_runstate_snapshot(&state);
-
-	WARN_ON(state.state != RUNSTATE_running);
-
-	return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
-}
-
 static void xen_read_wallclock(struct timespec64 *ts)
 {
 	u32 version;
@@ -179,10 +171,14 @@ static void xen_percpu_init(void)
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
 
+	/* Direct vCPU id mapping for ARM guests. */
+	per_cpu(xen_vcpu_id, cpu) = cpu;
+
 	info.mfn = virt_to_gfn(vcpup);
 	info.offset = xen_offset_in_page(vcpup);
 
-	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
+	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+				 &info);
 	BUG_ON(err);
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
@@ -237,33 +233,65 @@ static irqreturn_t xen_arm_callback(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+static __initdata struct {
+	const char *compat;
+	const char *prefix;
+	const char *version;
+	bool found;
+} hyper_node = {"xen,xen", "xen,xen-", NULL, false};
+
+static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
+				      int depth, void *data)
+{
+	const void *s = NULL;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "hypervisor") != 0)
+		return 0;
+
+	if (of_flat_dt_is_compatible(node, hyper_node.compat))
+		hyper_node.found = true;
+
+	s = of_get_flat_dt_prop(node, "compatible", &len);
+	if (strlen(hyper_node.prefix) + 3  < len &&
+	    !strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
+		hyper_node.version = s + strlen(hyper_node.prefix);
+
+	/*
+	 * Check if Xen supports EFI by checking whether there is the
+	 * "/hypervisor/uefi" node in DT. If so, runtime services are available
+	 * through proxy functions (e.g. in case of Xen dom0 EFI implementation
+	 * they call special hypercall which executes relevant EFI functions)
+	 * and that is why they are always enabled.
+	 */
+	if (IS_ENABLED(CONFIG_XEN_EFI)) {
+		if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
+		    !efi_runtime_disabled())
+			set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+	}
+
+	return 0;
+}
+
 /*
  * see Documentation/devicetree/bindings/arm/xen.txt for the
  * documentation of the Xen Device Tree format.
  */
 #define GRANT_TABLE_PHYSADDR 0
 void __init xen_early_init(void)
 {
-	int len;
-	const char *s = NULL;
-	const char *version = NULL;
-	const char *xen_prefix = "xen,xen-";
-
-	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
-	if (!xen_node) {
+	of_scan_flat_dt(fdt_find_hyper_node, NULL);
+	if (!hyper_node.found) {
 		pr_debug("No Xen support\n");
 		return;
 	}
-	s = of_get_property(xen_node, "compatible", &len);
-	if (strlen(xen_prefix) + 3  < len &&
-			!strncmp(xen_prefix, s, strlen(xen_prefix)))
-		version = s + strlen(xen_prefix);
-	if (version == NULL) {
+
+	if (hyper_node.version == NULL) {
 		pr_debug("Xen version not found\n");
 		return;
 	}
 
-	pr_info("Xen %s support found\n", version);
+	pr_info("Xen %s support found\n", hyper_node.version);
 
 	xen_domain_type = XEN_HVM_DOMAIN;
 
@@ -278,28 +306,68 @@ void __init xen_early_init(void)
 		add_preferred_console("hvc", 0, NULL);
 }
 
+static void __init xen_acpi_guest_init(void)
+{
+#ifdef CONFIG_ACPI
+	struct xen_hvm_param a;
+	int interrupt, trigger, polarity;
+
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+
+	if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
+	    || (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
+		xen_events_irq = 0;
+		return;
+	}
+
+	interrupt = a.value & 0xff;
+	trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
+					 : ACPI_LEVEL_SENSITIVE;
+	polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
+					  : ACPI_ACTIVE_HIGH;
+	xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
+#endif
+}
+
+static void __init xen_dt_guest_init(void)
+{
+	struct device_node *xen_node;
+
+	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (!xen_node) {
+		pr_err("Xen support was detected before, but it has disappeared\n");
+		return;
+	}
+
+	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+}
+
 static int __init xen_guest_init(void)
 {
 	struct xen_add_to_physmap xatp;
 	struct shared_info *shared_info_page = NULL;
-	struct resource res;
-	phys_addr_t grant_frames;
 
 	if (!xen_domain())
 		return 0;
 
-	if (of_address_to_resource(xen_node, GRANT_TABLE_PHYSADDR, &res)) {
-		pr_err("Xen grant table base address not found\n");
-		return -ENODEV;
-	}
-	grant_frames = res.start;
+	if (!acpi_disabled)
+		xen_acpi_guest_init();
+	else
+		xen_dt_guest_init();
 
-	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
 	if (!xen_events_irq) {
 		pr_err("Xen event channel interrupt not found\n");
 		return -ENODEV;
 	}
 
+	/*
+	 * The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
+	 * parameters are found. Force enable runtime services.
+	 */
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		xen_efi_runtime_setup();
+
 	shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
 
 	if (!shared_info_page) {
@@ -328,7 +396,13 @@ static int __init xen_guest_init(void)
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
 
-	if (gnttab_setup_auto_xlat_frames(grant_frames)) {
+	/* Direct vCPU id mapping for ARM guests. */
+	per_cpu(xen_vcpu_id, 0) = 0;
+
+	xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
+	if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
+					  &xen_auto_xlat_grant_frames.vaddr,
+					  xen_auto_xlat_grant_frames.count)) {
 		free_percpu(xen_vcpu_info);
 		return -ENOMEM;
 	}
@@ -355,8 +429,8 @@ static int __init xen_guest_init(void)
 
 	register_cpu_notifier(&xen_cpu_notifier);
 
-	pv_time_ops.steal_clock = xen_stolen_accounting;
-	static_key_slow_inc(&paravirt_steal_enabled);
+	xen_time_setup_guest();
+
 	if (xen_initial_domain())
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
@@ -403,4 +477,5 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
+EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
 EXPORT_SYMBOL_GPL(privcmd_call);