Merge tag 'for-linus-6.0-rc1b-tag' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/xen/tip

Pull more xen updates from Juergen Gross:

 - fix the handling of the "persistent grants" feature negotiation
   between Xen blkfront and Xen blkback drivers

 - a cleanup of xen.config and adding xen.config to Xen section in
   MAINTAINERS

 - support HVMOP_set_evtchn_upcall_vector, which is more compliant to
   "normal" interrupt handling than the global callback used up to now

 - further small cleanups

* tag 'for-linus-6.0-rc1b-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  MAINTAINERS: add xen config fragments to XEN HYPERVISOR sections
  xen: remove XEN_SCRUB_PAGES in xen.config
  xen/pciback: Fix comment typo
  xen/xenbus: fix return type in xenbus_file_read()
  xen-blkfront: Apply 'feature_persistent' parameter when connect
  xen-blkback: Apply 'feature_persistent' parameter when connect
  xen-blkback: fix persistent grants negotiation
  x86/xen: Add support for HVMOP_set_evtchn_upcall_vector

Documentation/ABI/testing/sysfs-driver-xen-blkback

@@ -42,5 +42,5 @@ KernelVersion:  5.10
 Contact:        Maximilian Heyne <mheyne@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
-                that this option only takes effect on newly created backends.
+                that this option only takes effect on newly connected backends.
                 The default is Y (enable).

Documentation/ABI/testing/sysfs-driver-xen-blkfront

@@ -15,5 +15,5 @@ KernelVersion:  5.10
 Contact:        Maximilian Heyne <mheyne@amazon.de>
 Description:
                 Whether to enable the persistent grants feature or not.  Note
-                that this option only takes effect on newly created frontends.
+                that this option only takes effect on newly connected frontends.
                 The default is Y (enable).

MAINTAINERS

@@ -22200,12 +22200,14 @@ F:	drivers/*/xen-*front.c
 F:	drivers/xen/
 F:	include/uapi/xen/
 F:	include/xen/
+F:	kernel/configs/xen.config
 
 XEN HYPERVISOR X86
 M:	Juergen Gross <jgross@suse.com>
 R:	Boris Ostrovsky <boris.ostrovsky@oracle.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
+F:	arch/x86/configs/xen.config
 F:	arch/x86/include/asm/pvclock-abi.h
 F:	arch/x86/include/asm/xen/
 F:	arch/x86/platform/pvh/

arch/x86/include/asm/xen/cpuid.h

@@ -107,6 +107,8 @@
  * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768.
  */
 #define XEN_HVM_CPUID_EXT_DEST_ID      (1u << 5)
+/* Per-vCPU event channel upcalls */
+#define XEN_HVM_CPUID_UPCALL_VECTOR    (1u << 6)
 
 /*
  * Leaf 6 (0x40000x05)

arch/x86/include/asm/xen/events.h

@@ -23,7 +23,7 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 /* No need for a barrier -- XCHG is a barrier on x86. */
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
-extern int xen_have_vector_callback;
+extern bool xen_have_vector_callback;
 
 /*
  * Events delivered via platform PCI interrupts are always
@@ -34,4 +34,5 @@ static inline bool xen_support_evtchn_rebind(void)
 	return (!xen_hvm_domain() || xen_have_vector_callback);
 }
 
+extern bool xen_percpu_upcall;
 #endif /* _ASM_X86_XEN_EVENTS_H */

arch/x86/xen/enlighten.c

@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(xen_start_info);
 
 struct shared_info xen_dummy_shared_info;
 
-__read_mostly int xen_have_vector_callback;
+__read_mostly bool xen_have_vector_callback = true;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
 /*

arch/x86/xen/enlighten_hvm.c

@@ -8,6 +8,8 @@
 
 #include <xen/features.h>
 #include <xen/events.h>
+#include <xen/hvm.h>
+#include <xen/interface/hvm/hvm_op.h>
 #include <xen/interface/memory.h>
 
 #include <asm/apic.h>
@@ -31,6 +33,9 @@
 
 static unsigned long shared_info_pfn;
 
+__ro_after_init bool xen_percpu_upcall;
+EXPORT_SYMBOL_GPL(xen_percpu_upcall);
+
 void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
@@ -126,6 +131,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
+	if (xen_percpu_upcall)
+		ack_APIC_irq();
+
 	inc_irq_stat(irq_hv_callback_count);
 
 	xen_hvm_evtchn_do_upcall();
@@ -169,6 +177,15 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	if (!xen_have_vector_callback)
 		return 0;
 
+	if (xen_percpu_upcall) {
+		rc = xen_set_upcall_vector(cpu);
+		if (rc) {
+			WARN(1, "HVMOP_set_evtchn_upcall_vector"
+			     " for CPU %d failed: %d\n", cpu, rc);
+			return rc;
+		}
+	}
+
 	if (xen_feature(XENFEAT_hvm_safe_pvclock))
 		xen_setup_timer(cpu);
 
@@ -189,8 +206,6 @@ static int xen_cpu_dead_hvm(unsigned int cpu)
 	return 0;
 }
 
-static bool no_vector_callback __initdata;
-
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -213,9 +228,6 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
-	if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
-		xen_have_vector_callback = 1;
-
 	xen_hvm_smp_init();
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_hvm, xen_cpu_dead_hvm));
 	xen_unplug_emulated_devices();
@@ -241,7 +253,7 @@ early_param("xen_nopv", xen_parse_nopv);
 
 static __init int xen_parse_no_vector_callback(char *arg)
 {
-	no_vector_callback = true;
+	xen_have_vector_callback = false;
 	return 0;
 }
 early_param("xen_no_vector_callback", xen_parse_no_vector_callback);

arch/x86/xen/suspend_hvm.c

@@ -5,6 +5,7 @@
 #include <xen/hvm.h>
 #include <xen/features.h>
 #include <xen/interface/features.h>
+#include <xen/events.h>
 
 #include "xen-ops.h"
 
@@ -14,6 +15,13 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 		xen_hvm_init_shared_info();
 		xen_vcpu_restore();
 	}
-	xen_setup_callback_vector();
+	if (xen_percpu_upcall) {
+		unsigned int cpu;
+
+		for_each_online_cpu(cpu)
+			BUG_ON(xen_set_upcall_vector(cpu));
+	} else {
+		xen_setup_callback_vector();
+	}
 	xen_unplug_emulated_devices();
 }

drivers/block/xen-blkback/xenbus.c

@@ -157,6 +157,11 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
 	return 0;
 }
 
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent, "Enables the persistent grants feature");
+
 static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 {
 	struct xen_blkif *blkif;
@@ -472,12 +477,6 @@ static void xen_vbd_free(struct xen_vbd *vbd)
 	vbd->bdev = NULL;
 }
 
-/* Enable the persistent grants feature. */
-static bool feature_persistent = true;
-module_param(feature_persistent, bool, 0644);
-MODULE_PARM_DESC(feature_persistent,
-		"Enables the persistent grants feature");
-
 static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 			  unsigned major, unsigned minor, int readonly,
 			  int cdrom)
@@ -520,8 +519,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (bdev_max_secure_erase_sectors(bdev))
 		vbd->discard_secure = true;
 
-	vbd->feature_gnt_persistent = feature_persistent;
-
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
 		handle, blkif->domid);
 	return 0;
@@ -1087,10 +1084,9 @@ static int connect_ring(struct backend_info *be)
 		xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
 		return -ENOSYS;
 	}
-	if (blkif->vbd.feature_gnt_persistent)
-		blkif->vbd.feature_gnt_persistent =
-			xenbus_read_unsigned(dev->otherend,
-					"feature-persistent", 0);
+
+	blkif->vbd.feature_gnt_persistent = feature_persistent &&
+		xenbus_read_unsigned(dev->otherend, "feature-persistent", 0);
 
 	blkif->vbd.overflow_max_grants = 0;
 

drivers/block/xen-blkfront.c

@@ -1988,8 +1988,6 @@ static int blkfront_probe(struct xenbus_device *dev,
 	info->vdevice = vdevice;
 	info->connected = BLKIF_STATE_DISCONNECTED;
 
-	info->feature_persistent = feature_persistent;
-
 	/* Front end dir is a number, which is used as the id. */
 	info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
 	dev_set_drvdata(&dev->dev, info);
@@ -2283,7 +2281,7 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0))
 		blkfront_setup_discard(info);
 
-	if (info->feature_persistent)
+	if (feature_persistent)
 		info->feature_persistent =
 			!!xenbus_read_unsigned(info->xbdev->otherend,
 					       "feature-persistent", 0);

drivers/xen/events/events_base.c

@@ -45,6 +45,7 @@
 #include <asm/irq.h>
 #include <asm/io_apic.h>
 #include <asm/i8259.h>
+#include <asm/xen/cpuid.h>
 #include <asm/xen/pci.h>
 #endif
 #include <asm/sync_bitops.h>
@@ -2184,6 +2185,7 @@ static struct irq_chip xen_percpu_chip __read_mostly = {
 	.irq_ack		= ack_dynirq,
 };
 
+#ifdef CONFIG_X86
 #ifdef CONFIG_XEN_PVHVM
 /* Vector callbacks are better than PCI interrupts to receive event
  * channel notifications because we can receive vector callbacks on any
@@ -2196,11 +2198,48 @@ void xen_setup_callback_vector(void)
 		callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR);
 		if (xen_set_callback_via(callback_via)) {
 			pr_err("Request for Xen HVM callback vector failed\n");
-			xen_have_vector_callback = 0;
+			xen_have_vector_callback = false;
 		}
 	}
 }
 
+/*
+ * Setup per-vCPU vector-type callbacks. If this setup is unavailable,
+ * fallback to the global vector-type callback.
+ */
+static __init void xen_init_setup_upcall_vector(void)
+{
+	if (!xen_have_vector_callback)
+		return;
+
+	if ((cpuid_eax(xen_cpuid_base() + 4) & XEN_HVM_CPUID_UPCALL_VECTOR) &&
+	    !xen_set_upcall_vector(0))
+		xen_percpu_upcall = true;
+	else if (xen_feature(XENFEAT_hvm_callback_vector))
+		xen_setup_callback_vector();
+	else
+		xen_have_vector_callback = false;
+}
+
+int xen_set_upcall_vector(unsigned int cpu)
+{
+	int rc;
+	xen_hvm_evtchn_upcall_vector_t op = {
+		.vector = HYPERVISOR_CALLBACK_VECTOR,
+		.vcpu = per_cpu(xen_vcpu_id, cpu),
+	};
+
+	rc = HYPERVISOR_hvm_op(HVMOP_set_evtchn_upcall_vector, &op);
+	if (rc)
+		return rc;
+
+	/* Trick toolstack to think we are enlightened. */
+	if (!cpu)
+		rc = xen_set_callback_via(1);
+
+	return rc;
+}
+
 static __init void xen_alloc_callback_vector(void)
 {
 	if (!xen_have_vector_callback)
@@ -2211,8 +2250,11 @@ static __init void xen_alloc_callback_vector(void)
 }
 #else
 void xen_setup_callback_vector(void) {}
+static inline void xen_init_setup_upcall_vector(void) {}
+int xen_set_upcall_vector(unsigned int cpu) {}
 static inline void xen_alloc_callback_vector(void) {}
-#endif
+#endif /* CONFIG_XEN_PVHVM */
+#endif /* CONFIG_X86 */
 
 bool xen_fifo_events = true;
 module_param_named(fifo_events, xen_fifo_events, bool, 0);
@@ -2272,10 +2314,9 @@ void __init xen_init_IRQ(void)
 		if (xen_initial_domain())
 			pci_xen_initial_domain();
 	}
-	if (xen_feature(XENFEAT_hvm_callback_vector)) {
-		xen_setup_callback_vector();
-		xen_alloc_callback_vector();
-	}
+	xen_init_setup_upcall_vector();
+	xen_alloc_callback_vector();
+
 
 	if (xen_hvm_domain()) {
 		native_init_IRQ();

drivers/xen/xen-pciback/pciback_ops.c

@@ -159,7 +159,7 @@ int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev,
 		return XEN_PCI_ERR_op_failed;
 	}
 
-	/* The value the guest needs is actually the IDT vector, not the
+	/* The value the guest needs is actually the IDT vector, not
 	 * the local domain's IRQ number. */
 
 	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;

drivers/xen/xenbus/xenbus_dev_frontend.c

@@ -128,7 +128,7 @@ static ssize_t xenbus_file_read(struct file *filp,
 {
 	struct xenbus_file_priv *u = filp->private_data;
 	struct read_buffer *rb;
-	unsigned i;
+	ssize_t i;
 	int ret;
 
 	mutex_lock(&u->reply_mutex);
@@ -148,7 +148,7 @@ static ssize_t xenbus_file_read(struct file *filp,
 	rb = list_entry(u->read_buffers.next, struct read_buffer, list);
 	i = 0;
 	while (i < len) {
-		unsigned sz = min((unsigned)len - i, rb->len - rb->cons);
+		size_t sz = min_t(size_t, len - i, rb->len - rb->cons);
 
 		ret = copy_to_user(ubuf + i, &rb->msg[rb->cons], sz);
 

include/xen/hvm.h

@@ -60,4 +60,6 @@ static inline int hvm_get_parameter(int idx, uint64_t *value)
 
 void xen_setup_callback_vector(void);
 
+int xen_set_upcall_vector(unsigned int cpu);
+
 #endif /* XEN_HVM_H__ */

include/xen/interface/hvm/hvm_op.h

@@ -46,4 +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__ */

kernel/configs/xen.config

@@ -34,7 +34,6 @@ CONFIG_INPUT_XEN_KBDDEV_FRONTEND=m
 CONFIG_XEN_SCSI_FRONTEND=m
 # others
 CONFIG_XEN_BALLOON=y
-CONFIG_XEN_SCRUB_PAGES=y
 CONFIG_XEN_DEV_EVTCHN=m
 CONFIG_XEN_BLKDEV_FRONTEND=m
 CONFIG_XEN_NETDEV_FRONTEND=m