Merge tag 'for-linus-5.18-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - A bunch of minor cleanups

 - A fix for kexec in Xen dom0 when executed on a high cpu number

 - A fix for resuming after suspend of a Xen guest with assigned PCI
   devices

 - A fix for a crash due to not disabled preemption when resuming as Xen
   dom0

* tag 'for-linus-5.18-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: fix is_xen_pmu()
  xen: don't hang when resuming PCI device
  arch:x86:xen: Remove unnecessary assignment in xen_apic_read()
  xen/grant-table: remove readonly parameter from functions
  xen/grant-table: remove gnttab_*transfer*() functions
  drivers/xen: use helper macro __ATTR_RW
  x86/xen: Fix kerneldoc warning
  xen: delay xen_hvm_init_time_ops() if kdump is boot on vcpu>=32
  xen: use time_is_before_eq_jiffies() instead of open coding it

Author: torvalds

arch/x86/xen/apic.c

@@ -51,7 +51,7 @@ static u32 xen_apic_read(u32 reg)
 		.interface_version = XENPF_INTERFACE_VERSION,
 		.u.pcpu_info.xen_cpuid = 0,
 	};
-	int ret = 0;
+	int ret;
 
 	/* Shouldn't need this as APIC is turned off for PV, and we only
 	 * get called on the bootup processor. But just in case. */

arch/x86/xen/pmu.c

@@ -506,10 +506,7 @@ irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
 	return ret;
 }
 
-bool is_xen_pmu(int cpu)
-{
-	return (get_xenpmu_data() != NULL);
-}
+bool is_xen_pmu;
 
 void xen_pmu_init(int cpu)
 {
@@ -520,7 +517,7 @@ void xen_pmu_init(int cpu)
 
 	BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE);
 
-	if (xen_hvm_domain())
+	if (xen_hvm_domain() || (cpu != 0 && !is_xen_pmu))
 		return;
 
 	xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL);
@@ -541,7 +538,8 @@ void xen_pmu_init(int cpu)
 	per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data;
 	per_cpu(xenpmu_shared, cpu).flags = 0;
 
-	if (cpu == 0) {
+	if (!is_xen_pmu) {
+		is_xen_pmu = true;
 		perf_register_guest_info_callbacks(&xen_guest_cbs);
 		xen_pmu_arch_init();
 	}

arch/x86/xen/pmu.h

@@ -4,6 +4,8 @@
 
 #include <xen/interface/xenpmu.h>
 
+extern bool is_xen_pmu;
+
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
 #ifdef CONFIG_XEN_HAVE_VPMU
 void xen_pmu_init(int cpu);
@@ -12,7 +14,6 @@ void xen_pmu_finish(int cpu);
 static inline void xen_pmu_init(int cpu) {}
 static inline void xen_pmu_finish(int cpu) {}
 #endif
-bool is_xen_pmu(int cpu);
 bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
 bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
 int pmu_apic_update(uint32_t reg);

arch/x86/xen/setup.c

@@ -719,7 +719,7 @@ static void __init xen_reserve_xen_mfnlist(void)
 }
 
 /**
- * machine_specific_memory_setup - Hook for machine specific memory setup.
+ * xen_memory_setup - Hook for machine specific memory setup.
  **/
 char * __init xen_memory_setup(void)
 {

arch/x86/xen/smp_hvm.c

@@ -19,6 +19,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void)
 	 */
 	xen_vcpu_setup(0);
 
+	/*
+	 * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS.
+	 * Refer to comments in xen_hvm_init_time_ops().
+	 */
+	xen_hvm_init_time_ops();
+
 	/*
 	 * The alternative logic (which patches the unlock/lock) runs before
 	 * the smp bootup up code is activated. Hence we need to set this up

arch/x86/xen/smp_pv.c

@@ -129,7 +129,7 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	per_cpu(xen_irq_work, cpu).irq = rc;
 	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
-	if (is_xen_pmu(cpu)) {
+	if (is_xen_pmu) {
 		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
 		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
 					     xen_pmu_irq_handler,

arch/x86/xen/time.c

@@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 
 void __init xen_hvm_init_time_ops(void)
 {
+	static bool hvm_time_initialized;
+
+	if (hvm_time_initialized)
+		return;
+
 	/*
 	 * vector callback is needed otherwise we cannot receive interrupts
 	 * on cpu > 0 and at this point we don't know how many cpus are
@@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
+		pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer");
+		return;
+	}
+
+	/*
+	 * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'.
+	 * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest
+	 * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access
+	 * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic.
+	 *
+	 * The xen_hvm_init_time_ops() should be called again later after
+	 * __this_cpu_read(xen_vcpu) is available.
+	 */
+	if (!__this_cpu_read(xen_vcpu)) {
+		pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n",
+			xen_vcpu_nr(0));
 		return;
 	}
 
@@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void)
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
 	x86_platform.set_wallclock = xen_set_wallclock;
+
+	hvm_time_initialized = true;
 }
 #endif
 

drivers/block/xen-blkfront.c

@@ -1223,7 +1223,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 			list_del(&persistent_gnt->node);
 			if (persistent_gnt->gref != GRANT_INVALID_REF) {
 				gnttab_end_foreign_access(persistent_gnt->gref,
-							  0, 0UL);
+							  0UL);
 				rinfo->persistent_gnts_c--;
 			}
 			if (info->feature_persistent)
@@ -1246,7 +1246,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 		       rinfo->shadow[i].req.u.rw.nr_segments;
 		for (j = 0; j < segs; j++) {
 			persistent_gnt = rinfo->shadow[i].grants_used[j];
-			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+			gnttab_end_foreign_access(persistent_gnt->gref, 0UL);
 			if (info->feature_persistent)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
@@ -1261,7 +1261,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 
 		for (j = 0; j < INDIRECT_GREFS(segs); j++) {
 			persistent_gnt = rinfo->shadow[i].indirect_grants[j];
-			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+			gnttab_end_foreign_access(persistent_gnt->gref, 0UL);
 			__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1284,7 +1284,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 	/* Free resources associated with old device channel. */
 	for (i = 0; i < info->nr_ring_pages; i++) {
 		if (rinfo->ring_ref[i] != GRANT_INVALID_REF) {
-			gnttab_end_foreign_access(rinfo->ring_ref[i], 0, 0);
+			gnttab_end_foreign_access(rinfo->ring_ref[i], 0);
 			rinfo->ring_ref[i] = GRANT_INVALID_REF;
 		}
 	}

drivers/char/tpm/xen-tpmfront.c

@@ -332,7 +332,7 @@ static void ring_free(struct tpm_private *priv)
 		return;
 
 	if (priv->ring_ref)
-		gnttab_end_foreign_access(priv->ring_ref, 0,
+		gnttab_end_foreign_access(priv->ring_ref,
 				(unsigned long)priv->shr);
 	else
 		free_page((unsigned long)priv->shr);

drivers/gpu/drm/xen/xen_drm_front_evtchnl.c

@@ -148,7 +148,7 @@ static void evtchnl_free(struct xen_drm_front_info *front_info,
 
 	/* end access and free the page */
 	if (evtchnl->gref != GRANT_INVALID_REF)
-		gnttab_end_foreign_access(evtchnl->gref, 0, page);
+		gnttab_end_foreign_access(evtchnl->gref, page);
 
 	memset(evtchnl, 0, sizeof(*evtchnl));
 }