Resguardo inicial

linux-7.2.3/arch/powerpc/sysdev/xive/Kconfig

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+config PPC_XIVE
+	bool
+	select PPC_SMP_MUXED_IPI
+	select HARDIRQS_SW_RESEND
+
+config PPC_XIVE_NATIVE
+	bool
+	select PPC_XIVE
+	depends on PPC_POWERNV
+
+config PPC_XIVE_SPAPR
+	bool
+	select PPC_XIVE

linux-7.2.3/arch/powerpc/sysdev/xive/Makefile

@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-y				+= common.o
+obj-$(CONFIG_PPC_XIVE_NATIVE)	+= native.o
+obj-$(CONFIG_PPC_XIVE_SPAPR)	+= spapr.o

linux-7.2.3/arch/powerpc/sysdev/xive/native.c

@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "xive: " fmt
+
+#include <linux/types.h>
+#include <linux/irq.h>
+#include <linux/debugfs.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/cpumask.h>
+#include <linux/mm.h>
+#include <linux/kmemleak.h>
+
+#include <asm/machdep.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/opal.h>
+#include <asm/kvm_ppc.h>
+
+#include "xive-internal.h"
+
+
+static u32 xive_provision_size;
+static u32 *xive_provision_chips;
+static u32 xive_provision_chip_count;
+static u32 xive_queue_shift;
+static u32 xive_pool_vps = XIVE_INVALID_VP;
+static struct kmem_cache *xive_provision_cache;
+static bool xive_has_single_esc;
+bool xive_has_save_restore;
+
+int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
+{
+	__be64 flags, eoi_page, trig_page;
+	__be32 esb_shift, src_chip;
+	u64 opal_flags;
+	s64 rc;
+
+	memset(data, 0, sizeof(*data));
+
+	rc = opal_xive_get_irq_info(hw_irq, &flags, &eoi_page, &trig_page,
+				    &esb_shift, &src_chip);
+	if (rc) {
+		pr_err("opal_xive_get_irq_info(0x%x) returned %lld\n",
+		       hw_irq, rc);
+		return -EINVAL;
+	}
+
+	opal_flags = be64_to_cpu(flags);
+	if (opal_flags & OPAL_XIVE_IRQ_STORE_EOI)
+		data->flags |= XIVE_IRQ_FLAG_STORE_EOI;
+	if (opal_flags & OPAL_XIVE_IRQ_STORE_EOI2)
+		data->flags |= XIVE_IRQ_FLAG_STORE_EOI;
+	if (opal_flags & OPAL_XIVE_IRQ_LSI)
+		data->flags |= XIVE_IRQ_FLAG_LSI;
+	data->eoi_page = be64_to_cpu(eoi_page);
+	data->trig_page = be64_to_cpu(trig_page);
+	data->esb_shift = be32_to_cpu(esb_shift);
+	data->src_chip = be32_to_cpu(src_chip);
+
+	data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift);
+	if (!data->eoi_mmio) {
+		pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq);
+		return -ENOMEM;
+	}
+
+	data->hw_irq = hw_irq;
+
+	if (!data->trig_page)
+		return 0;
+	if (data->trig_page == data->eoi_page) {
+		data->trig_mmio = data->eoi_mmio;
+		return 0;
+	}
+
+	data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift);
+	if (!data->trig_mmio) {
+		pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq);
+		return -ENOMEM;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_populate_irq_data);
+
+int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
+{
+	s64 rc;
+
+	for (;;) {
+		rc = opal_xive_set_irq_config(hw_irq, target, prio, sw_irq);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	return rc == 0 ? 0 : -ENXIO;
+}
+EXPORT_SYMBOL_GPL(xive_native_configure_irq);
+
+static int xive_native_get_irq_config(u32 hw_irq, u32 *target, u8 *prio,
+				      u32 *sw_irq)
+{
+	s64 rc;
+	__be64 vp;
+	__be32 lirq;
+
+	rc = opal_xive_get_irq_config(hw_irq, &vp, prio, &lirq);
+
+	*target = be64_to_cpu(vp);
+	*sw_irq = be32_to_cpu(lirq);
+
+	return rc == 0 ? 0 : -ENXIO;
+}
+
+#define vp_err(vp, fmt, ...) pr_err("VP[0x%x]: " fmt, vp, ##__VA_ARGS__)
+
+/* This can be called multiple time to change a queue configuration */
+int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
+				__be32 *qpage, u32 order, bool can_escalate)
+{
+	s64 rc = 0;
+	__be64 qeoi_page_be;
+	__be32 esc_irq_be;
+	u64 flags, qpage_phys;
+
+	/* If there's an actual queue page, clean it */
+	if (order) {
+		if (WARN_ON(!qpage))
+			return -EINVAL;
+		qpage_phys = __pa(qpage);
+	} else
+		qpage_phys = 0;
+
+	/* Initialize the rest of the fields */
+	q->msk = order ? ((1u << (order - 2)) - 1) : 0;
+	q->idx = 0;
+	q->toggle = 0;
+
+	rc = opal_xive_get_queue_info(vp_id, prio, NULL, NULL,
+				      &qeoi_page_be,
+				      &esc_irq_be,
+				      NULL);
+	if (rc) {
+		vp_err(vp_id, "Failed to get queue %d info : %lld\n", prio, rc);
+		rc = -EIO;
+		goto fail;
+	}
+	q->eoi_phys = be64_to_cpu(qeoi_page_be);
+
+	/* Default flags */
+	flags = OPAL_XIVE_EQ_ALWAYS_NOTIFY | OPAL_XIVE_EQ_ENABLED;
+
+	/* Escalation needed ? */
+	if (can_escalate) {
+		q->esc_irq = be32_to_cpu(esc_irq_be);
+		flags |= OPAL_XIVE_EQ_ESCALATE;
+	}
+
+	/* Configure and enable the queue in HW */
+	for (;;) {
+		rc = opal_xive_set_queue_info(vp_id, prio, qpage_phys, order, flags);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc) {
+		vp_err(vp_id, "Failed to set queue %d info: %lld\n", prio, rc);
+		rc = -EIO;
+	} else {
+		/*
+		 * KVM code requires all of the above to be visible before
+		 * q->qpage is set due to how it manages IPI EOIs
+		 */
+		wmb();
+		q->qpage = qpage;
+	}
+fail:
+	return rc;
+}
+EXPORT_SYMBOL_GPL(xive_native_configure_queue);
+
+static void __xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
+{
+	s64 rc;
+
+	/* Disable the queue in HW */
+	for (;;) {
+		rc = opal_xive_set_queue_info(vp_id, prio, 0, 0, 0);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc)
+		vp_err(vp_id, "Failed to disable queue %d : %lld\n", prio, rc);
+}
+
+void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
+{
+	__xive_native_disable_queue(vp_id, q, prio);
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_queue);
+
+static int xive_native_setup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
+{
+	struct xive_q *q = &xc->queue[prio];
+	__be32 *qpage;
+
+	qpage = xive_queue_page_alloc(cpu, xive_queue_shift);
+	if (IS_ERR(qpage))
+		return PTR_ERR(qpage);
+
+	return xive_native_configure_queue(get_hard_smp_processor_id(cpu),
+					   q, prio, qpage, xive_queue_shift, false);
+}
+
+static void xive_native_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
+{
+	struct xive_q *q = &xc->queue[prio];
+	unsigned int alloc_order;
+
+	/*
+	 * We use the variant with no iounmap as this is called on exec
+	 * from an IPI and iounmap isn't safe
+	 */
+	__xive_native_disable_queue(get_hard_smp_processor_id(cpu), q, prio);
+	alloc_order = xive_alloc_order(xive_queue_shift);
+	free_pages((unsigned long)q->qpage, alloc_order);
+	q->qpage = NULL;
+}
+
+static bool xive_native_match(struct device_node *node)
+{
+	return of_device_is_compatible(node, "ibm,opal-xive-vc");
+}
+
+static s64 opal_xive_allocate_irq(u32 chip_id)
+{
+	s64 irq = opal_xive_allocate_irq_raw(chip_id);
+
+	/*
+	 * Old versions of skiboot can incorrectly return 0xffffffff to
+	 * indicate no space, fix it up here.
+	 */
+	return irq == 0xffffffff ? OPAL_RESOURCE : irq;
+}
+
+#ifdef CONFIG_SMP
+static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+	s64 irq;
+
+	/* Allocate an IPI and populate info about it */
+	for (;;) {
+		irq = opal_xive_allocate_irq(xc->chip_id);
+		if (irq == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+			continue;
+		}
+		if (irq < 0) {
+			pr_err("Failed to allocate IPI on CPU %d\n", cpu);
+			return -ENXIO;
+		}
+		xc->hw_ipi = irq;
+		break;
+	}
+	return 0;
+}
+#endif /* CONFIG_SMP */
+
+u32 xive_native_alloc_irq_on_chip(u32 chip_id)
+{
+	s64 rc;
+
+	for (;;) {
+		rc = opal_xive_allocate_irq(chip_id);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc < 0)
+		return 0;
+	return rc;
+}
+EXPORT_SYMBOL_GPL(xive_native_alloc_irq_on_chip);
+
+void xive_native_free_irq(u32 irq)
+{
+	for (;;) {
+		s64 rc = opal_xive_free_irq(irq);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+}
+EXPORT_SYMBOL_GPL(xive_native_free_irq);
+
+#ifdef CONFIG_SMP
+static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+	s64 rc;
+
+	/* Free the IPI */
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
+		return;
+	for (;;) {
+		rc = opal_xive_free_irq(xc->hw_ipi);
+		if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+			continue;
+		}
+		xc->hw_ipi = XIVE_BAD_IRQ;
+		break;
+	}
+}
+#endif /* CONFIG_SMP */
+
+static void xive_native_shutdown(void)
+{
+	/* Switch the XIVE to emulation mode */
+	opal_xive_reset(OPAL_XIVE_MODE_EMU);
+}
+
+/*
+ * Perform an "ack" cycle on the current thread, thus
+ * grabbing the pending active priorities and updating
+ * the CPPR to the most favored one.
+ */
+static void xive_native_update_pending(struct xive_cpu *xc)
+{
+	u8 he, cppr;
+	u16 ack;
+
+	/* Perform the acknowledge hypervisor to register cycle */
+	ack = be16_to_cpu(__raw_readw(xive_tima + TM_SPC_ACK_HV_REG));
+
+	/* Synchronize subsequent queue accesses */
+	mb();
+
+	/*
+	 * Grab the CPPR and the "HE" field which indicates the source
+	 * of the hypervisor interrupt (if any)
+	 */
+	cppr = ack & 0xff;
+	he = (ack >> 8) >> 6;
+	switch(he) {
+	case TM_QW3_NSR_HE_NONE: /* Nothing to see here */
+		break;
+	case TM_QW3_NSR_HE_PHYS: /* Physical thread interrupt */
+		if (cppr == 0xff)
+			return;
+		/* Mark the priority pending */
+		xc->pending_prio |= 1 << cppr;
+
+		/*
+		 * A new interrupt should never have a CPPR less favored
+		 * than our current one.
+		 */
+		if (cppr >= xc->cppr)
+			pr_err("CPU %d odd ack CPPR, got %d at %d\n",
+			       smp_processor_id(), cppr, xc->cppr);
+
+		/* Update our idea of what the CPPR is */
+		xc->cppr = cppr;
+		break;
+	case TM_QW3_NSR_HE_POOL: /* HV Pool interrupt (unused) */
+	case TM_QW3_NSR_HE_LSI:  /* Legacy FW LSI (unused) */
+		pr_err("CPU %d got unexpected interrupt type HE=%d\n",
+		       smp_processor_id(), he);
+		return;
+	}
+}
+
+static void xive_native_prepare_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	xc->chip_id = cpu_to_chip_id(cpu);
+}
+
+static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	s64 rc;
+	u32 vp;
+	__be64 vp_cam_be;
+	u64 vp_cam;
+
+	if (xive_pool_vps == XIVE_INVALID_VP)
+		return;
+
+	/* Check if pool VP already active, if it is, pull it */
+	if (in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2) & TM_QW2W2_VP)
+		in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
+	/* Enable the pool VP */
+	vp = xive_pool_vps + cpu;
+	for (;;) {
+		rc = opal_xive_set_vp_info(vp, OPAL_XIVE_VP_ENABLED, 0);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc) {
+		pr_err("Failed to enable pool VP on CPU %d\n", cpu);
+		return;
+	}
+
+	/* Grab its CAM value */
+	rc = opal_xive_get_vp_info(vp, NULL, &vp_cam_be, NULL, NULL);
+	if (rc) {
+		pr_err("Failed to get pool VP info CPU %d\n", cpu);
+		return;
+	}
+	vp_cam = be64_to_cpu(vp_cam_be);
+
+	/* Push it on the CPU (set LSMFB to 0xff to skip backlog scan) */
+	out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD0, 0xff);
+	out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2, TM_QW2W2_VP | vp_cam);
+}
+
+static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	s64 rc;
+	u32 vp;
+
+	if (xive_pool_vps == XIVE_INVALID_VP)
+		return;
+
+	/* Pull the pool VP from the CPU */
+	in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
+	/* Disable it */
+	vp = xive_pool_vps + cpu;
+	for (;;) {
+		rc = opal_xive_set_vp_info(vp, 0, 0);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+}
+
+void xive_native_sync_source(u32 hw_irq)
+{
+	opal_xive_sync(XIVE_SYNC_EAS, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_source);
+
+void xive_native_sync_queue(u32 hw_irq)
+{
+	opal_xive_sync(XIVE_SYNC_QUEUE, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_queue);
+
+#ifdef CONFIG_DEBUG_FS
+static int xive_native_debug_create(struct dentry *xive_dir)
+{
+	debugfs_create_bool("save-restore", 0600, xive_dir, &xive_has_save_restore);
+	return 0;
+}
+#endif
+
+static const struct xive_ops xive_native_ops = {
+	.populate_irq_data	= xive_native_populate_irq_data,
+	.configure_irq		= xive_native_configure_irq,
+	.get_irq_config		= xive_native_get_irq_config,
+	.setup_queue		= xive_native_setup_queue,
+	.cleanup_queue		= xive_native_cleanup_queue,
+	.match			= xive_native_match,
+	.shutdown		= xive_native_shutdown,
+	.update_pending		= xive_native_update_pending,
+	.prepare_cpu		= xive_native_prepare_cpu,
+	.setup_cpu		= xive_native_setup_cpu,
+	.teardown_cpu		= xive_native_teardown_cpu,
+	.sync_source		= xive_native_sync_source,
+#ifdef CONFIG_SMP
+	.get_ipi		= xive_native_get_ipi,
+	.put_ipi		= xive_native_put_ipi,
+#endif /* CONFIG_SMP */
+#ifdef CONFIG_DEBUG_FS
+	.debug_create		= xive_native_debug_create,
+#endif /* CONFIG_DEBUG_FS */
+	.name			= "native",
+};
+
+static bool __init xive_parse_provisioning(struct device_node *np)
+{
+	int rc;
+
+	if (of_property_read_u32(np, "ibm,xive-provision-page-size",
+				 &xive_provision_size) < 0)
+		return true;
+	rc = of_property_count_elems_of_size(np, "ibm,xive-provision-chips", 4);
+	if (rc < 0) {
+		pr_err("Error %d getting provision chips array\n", rc);
+		return false;
+	}
+	xive_provision_chip_count = rc;
+	if (rc == 0)
+		return true;
+
+	xive_provision_chips = kcalloc(4, xive_provision_chip_count,
+				       GFP_KERNEL);
+	if (WARN_ON(!xive_provision_chips))
+		return false;
+
+	rc = of_property_read_u32_array(np, "ibm,xive-provision-chips",
+					xive_provision_chips,
+					xive_provision_chip_count);
+	if (rc < 0) {
+		pr_err("Error %d reading provision chips array\n", rc);
+		return false;
+	}
+
+	xive_provision_cache = kmem_cache_create("xive-provision",
+						 xive_provision_size,
+						 xive_provision_size,
+						 0, NULL);
+	if (!xive_provision_cache) {
+		pr_err("Failed to allocate provision cache\n");
+		return false;
+	}
+	return true;
+}
+
+static void __init xive_native_setup_pools(void)
+{
+	/* Allocate a pool big enough */
+	pr_debug("Allocating VP block for pool size %u\n", nr_cpu_ids);
+
+	xive_pool_vps = xive_native_alloc_vp_block(nr_cpu_ids);
+	if (WARN_ON(xive_pool_vps == XIVE_INVALID_VP))
+		pr_err("Failed to allocate pool VP, KVM might not function\n");
+
+	pr_debug("Pool VPs allocated at 0x%x for %u max CPUs\n",
+		 xive_pool_vps, nr_cpu_ids);
+}
+
+u32 xive_native_default_eq_shift(void)
+{
+	return xive_queue_shift;
+}
+EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
+
+unsigned long xive_tima_os;
+EXPORT_SYMBOL_GPL(xive_tima_os);
+
+bool __init xive_native_init(void)
+{
+	struct device_node *np;
+	struct resource r;
+	void __iomem *tima;
+	u8 max_prio = 7;
+	u32 val, cpu;
+	s64 rc;
+
+	if (xive_cmdline_disabled)
+		return false;
+
+	pr_devel("xive_native_init()\n");
+	np = of_find_compatible_node(NULL, NULL, "ibm,opal-xive-pe");
+	if (!np) {
+		pr_devel("not found !\n");
+		return false;
+	}
+	pr_devel("Found %pOF\n", np);
+
+	/* Resource 1 is HV window */
+	if (of_address_to_resource(np, 1, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		goto err_put;
+	}
+	tima = ioremap(r.start, resource_size(&r));
+	if (!tima) {
+		pr_err("Failed to map thread mgmnt area\n");
+		goto err_put;
+	}
+
+	/* Read number of priorities */
+	if (of_property_read_u32(np, "ibm,xive-#priorities", &val) == 0)
+		max_prio = val - 1;
+
+	/* Iterate the EQ sizes and pick one */
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
+		xive_queue_shift = val;
+		if (val == PAGE_SHIFT)
+			break;
+	}
+
+	/* Do we support single escalation */
+	xive_has_single_esc = of_property_read_bool(np, "single-escalation-support");
+
+	xive_has_save_restore = of_property_read_bool(np, "vp-save-restore");
+
+	/* Configure Thread Management areas for KVM */
+	for_each_possible_cpu(cpu)
+		kvmppc_set_xive_tima(cpu, r.start, tima);
+
+	/* Resource 2 is OS window */
+	if (of_address_to_resource(np, 2, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		goto err_put;
+	}
+
+	xive_tima_os = r.start;
+
+	/* Grab size of provisioning pages */
+	xive_parse_provisioning(np);
+
+	/* Switch the XIVE to exploitation mode */
+	rc = opal_xive_reset(OPAL_XIVE_MODE_EXPL);
+	if (rc) {
+		pr_err("Switch to exploitation mode failed with error %lld\n", rc);
+		goto err_put;
+	}
+
+	/* Setup some dummy HV pool VPs */
+	xive_native_setup_pools();
+
+	/* Initialize XIVE core with our backend */
+	if (!xive_core_init(np, &xive_native_ops, tima, TM_QW3_HV_PHYS,
+			    max_prio)) {
+		opal_xive_reset(OPAL_XIVE_MODE_EMU);
+		goto err_put;
+	}
+	of_node_put(np);
+	pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10));
+	return true;
+
+err_put:
+	of_node_put(np);
+	return false;
+}
+
+static bool xive_native_provision_pages(void)
+{
+	u32 i;
+	void *p;
+
+	for (i = 0; i < xive_provision_chip_count; i++) {
+		u32 chip = xive_provision_chips[i];
+
+		/*
+		 * XXX TODO: Try to make the allocation local to the node where
+		 * the chip resides.
+		 */
+		p = kmem_cache_alloc(xive_provision_cache, GFP_KERNEL);
+		if (!p) {
+			pr_err("Failed to allocate provisioning page\n");
+			return false;
+		}
+		kmemleak_ignore(p);
+		opal_xive_donate_page(chip, __pa(p));
+	}
+	return true;
+}
+
+u32 xive_native_alloc_vp_block(u32 max_vcpus)
+{
+	s64 rc;
+	u32 order;
+
+	order = fls(max_vcpus) - 1;
+	if (max_vcpus > (1 << order))
+		order++;
+
+	pr_debug("VP block alloc, for max VCPUs %d use order %d\n",
+		 max_vcpus, order);
+
+	for (;;) {
+		rc = opal_xive_alloc_vp_block(order);
+		switch (rc) {
+		case OPAL_BUSY:
+			msleep(OPAL_BUSY_DELAY_MS);
+			break;
+		case OPAL_XIVE_PROVISIONING:
+			if (!xive_native_provision_pages())
+				return XIVE_INVALID_VP;
+			break;
+		default:
+			if (rc < 0) {
+				pr_err("OPAL failed to allocate VCPUs order %d, err %lld\n",
+				       order, rc);
+				return XIVE_INVALID_VP;
+			}
+			return rc;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(xive_native_alloc_vp_block);
+
+void xive_native_free_vp_block(u32 vp_base)
+{
+	s64 rc;
+
+	if (vp_base == XIVE_INVALID_VP)
+		return;
+
+	rc = opal_xive_free_vp_block(vp_base);
+	if (rc < 0)
+		pr_warn("OPAL error %lld freeing VP block\n", rc);
+}
+EXPORT_SYMBOL_GPL(xive_native_free_vp_block);
+
+int xive_native_enable_vp(u32 vp_id, bool single_escalation)
+{
+	s64 rc;
+	u64 flags = OPAL_XIVE_VP_ENABLED;
+
+	if (single_escalation)
+		flags |= OPAL_XIVE_VP_SINGLE_ESCALATION;
+	for (;;) {
+		rc = opal_xive_set_vp_info(vp_id, flags, 0);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc)
+		vp_err(vp_id, "Failed to enable VP : %lld\n", rc);
+	return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_enable_vp);
+
+int xive_native_disable_vp(u32 vp_id)
+{
+	s64 rc;
+
+	for (;;) {
+		rc = opal_xive_set_vp_info(vp_id, 0, 0);
+		if (rc != OPAL_BUSY)
+			break;
+		msleep(OPAL_BUSY_DELAY_MS);
+	}
+	if (rc)
+		vp_err(vp_id, "Failed to disable VP : %lld\n", rc);
+	return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_vp);
+
+int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id)
+{
+	__be64 vp_cam_be;
+	__be32 vp_chip_id_be;
+	s64 rc;
+
+	rc = opal_xive_get_vp_info(vp_id, NULL, &vp_cam_be, NULL, &vp_chip_id_be);
+	if (rc) {
+		vp_err(vp_id, "Failed to get VP info : %lld\n", rc);
+		return -EIO;
+	}
+	*out_cam_id = be64_to_cpu(vp_cam_be) & 0xffffffffu;
+	*out_chip_id = be32_to_cpu(vp_chip_id_be);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_info);
+
+bool xive_native_has_single_escalation(void)
+{
+	return xive_has_single_esc;
+}
+EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
+
+bool xive_native_has_save_restore(void)
+{
+	return xive_has_save_restore;
+}
+EXPORT_SYMBOL_GPL(xive_native_has_save_restore);
+
+int xive_native_get_queue_info(u32 vp_id, u32 prio,
+			       u64 *out_qpage,
+			       u64 *out_qsize,
+			       u64 *out_qeoi_page,
+			       u32 *out_escalate_irq,
+			       u64 *out_qflags)
+{
+	__be64 qpage;
+	__be64 qsize;
+	__be64 qeoi_page;
+	__be32 escalate_irq;
+	__be64 qflags;
+	s64 rc;
+
+	rc = opal_xive_get_queue_info(vp_id, prio, &qpage, &qsize,
+				      &qeoi_page, &escalate_irq, &qflags);
+	if (rc) {
+		vp_err(vp_id, "failed to get queue %d info : %lld\n", prio, rc);
+		return -EIO;
+	}
+
+	if (out_qpage)
+		*out_qpage = be64_to_cpu(qpage);
+	if (out_qsize)
+		*out_qsize = be64_to_cpu(qsize);
+	if (out_qeoi_page)
+		*out_qeoi_page = be64_to_cpu(qeoi_page);
+	if (out_escalate_irq)
+		*out_escalate_irq = be32_to_cpu(escalate_irq);
+	if (out_qflags)
+		*out_qflags = be64_to_cpu(qflags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_info);
+
+int xive_native_get_queue_state(u32 vp_id, u32 prio, u32 *qtoggle, u32 *qindex)
+{
+	__be32 opal_qtoggle;
+	__be32 opal_qindex;
+	s64 rc;
+
+	rc = opal_xive_get_queue_state(vp_id, prio, &opal_qtoggle,
+				       &opal_qindex);
+	if (rc) {
+		vp_err(vp_id, "failed to get queue %d state : %lld\n", prio, rc);
+		return -EIO;
+	}
+
+	if (qtoggle)
+		*qtoggle = be32_to_cpu(opal_qtoggle);
+	if (qindex)
+		*qindex = be32_to_cpu(opal_qindex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_state);
+
+int xive_native_set_queue_state(u32 vp_id, u32 prio, u32 qtoggle, u32 qindex)
+{
+	s64 rc;
+
+	rc = opal_xive_set_queue_state(vp_id, prio, qtoggle, qindex);
+	if (rc) {
+		vp_err(vp_id, "failed to set queue %d state : %lld\n", prio, rc);
+		return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_set_queue_state);
+
+bool xive_native_has_queue_state_support(void)
+{
+	return opal_check_token(OPAL_XIVE_GET_QUEUE_STATE) &&
+		opal_check_token(OPAL_XIVE_SET_QUEUE_STATE);
+}
+EXPORT_SYMBOL_GPL(xive_native_has_queue_state_support);
+
+int xive_native_get_vp_state(u32 vp_id, u64 *out_state)
+{
+	__be64 state;
+	s64 rc;
+
+	rc = opal_xive_get_vp_state(vp_id, &state);
+	if (rc) {
+		vp_err(vp_id, "failed to get vp state : %lld\n", rc);
+		return -EIO;
+	}
+
+	if (out_state)
+		*out_state = be64_to_cpu(state);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_state);
+
+machine_arch_initcall(powernv, xive_core_debug_init);

linux-7.2.3/arch/powerpc/sysdev/xive/spapr.c

@@ -0,0 +1,884 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "xive: " fmt
+
+#include <linux/types.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/bitmap.h>
+#include <linux/cpumask.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/libfdt.h>
+
+#include <asm/machdep.h>
+#include <asm/prom.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/hvcall.h>
+#include <asm/svm.h>
+#include <asm/ultravisor.h>
+
+#include "xive-internal.h"
+
+static u32 xive_queue_shift;
+
+struct xive_irq_bitmap {
+	unsigned long		*bitmap;
+	unsigned int		base;
+	unsigned int		count;
+	spinlock_t		lock;
+	struct list_head	list;
+};
+
+static LIST_HEAD(xive_irq_bitmaps);
+
+static int __init xive_irq_bitmap_add(int base, int count)
+{
+	struct xive_irq_bitmap *xibm;
+
+	xibm = kzalloc_obj(*xibm);
+	if (!xibm)
+		return -ENOMEM;
+
+	spin_lock_init(&xibm->lock);
+	xibm->base = base;
+	xibm->count = count;
+	xibm->bitmap = bitmap_zalloc(xibm->count, GFP_KERNEL);
+	if (!xibm->bitmap) {
+		kfree(xibm);
+		return -ENOMEM;
+	}
+	list_add(&xibm->list, &xive_irq_bitmaps);
+
+	pr_info("Using IRQ range [%x-%x]", xibm->base,
+		xibm->base + xibm->count - 1);
+	return 0;
+}
+
+static void xive_irq_bitmap_remove_all(void)
+{
+	struct xive_irq_bitmap *xibm, *tmp;
+
+	list_for_each_entry_safe(xibm, tmp, &xive_irq_bitmaps, list) {
+		list_del(&xibm->list);
+		bitmap_free(xibm->bitmap);
+		kfree(xibm);
+	}
+}
+
+static int __xive_irq_bitmap_alloc(struct xive_irq_bitmap *xibm)
+{
+	int irq;
+
+	irq = find_first_zero_bit(xibm->bitmap, xibm->count);
+	if (irq != xibm->count) {
+		set_bit(irq, xibm->bitmap);
+		irq += xibm->base;
+	} else {
+		irq = -ENOMEM;
+	}
+
+	return irq;
+}
+
+static int xive_irq_bitmap_alloc(void)
+{
+	struct xive_irq_bitmap *xibm;
+	unsigned long flags;
+	int irq = -ENOENT;
+
+	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
+		spin_lock_irqsave(&xibm->lock, flags);
+		irq = __xive_irq_bitmap_alloc(xibm);
+		spin_unlock_irqrestore(&xibm->lock, flags);
+		if (irq >= 0)
+			break;
+	}
+	return irq;
+}
+
+static void xive_irq_bitmap_free(int irq)
+{
+	unsigned long flags;
+	struct xive_irq_bitmap *xibm;
+
+	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
+		if ((irq >= xibm->base) && (irq < xibm->base + xibm->count)) {
+			spin_lock_irqsave(&xibm->lock, flags);
+			clear_bit(irq - xibm->base, xibm->bitmap);
+			spin_unlock_irqrestore(&xibm->lock, flags);
+			break;
+		}
+	}
+}
+
+
+/* Based on the similar routines in RTAS */
+static unsigned int plpar_busy_delay_time(long rc)
+{
+	unsigned int ms = 0;
+
+	if (H_IS_LONG_BUSY(rc)) {
+		ms = get_longbusy_msecs(rc);
+	} else if (rc == H_BUSY) {
+		ms = 10; /* seems appropriate for XIVE hcalls */
+	}
+
+	return ms;
+}
+
+static unsigned int plpar_busy_delay(int rc)
+{
+	unsigned int ms;
+
+	ms = plpar_busy_delay_time(rc);
+	if (ms)
+		mdelay(ms);
+
+	return ms;
+}
+
+/*
+ * Note: this call has a partition wide scope and can take a while to
+ * complete. If it returns H_LONG_BUSY_* it should be retried
+ * periodically.
+ */
+static long plpar_int_reset(unsigned long flags)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_INT_RESET, flags);
+	} while (plpar_busy_delay(rc));
+
+	if (rc)
+		pr_err("H_INT_RESET failed %ld\n", rc);
+
+	return rc;
+}
+
+static long plpar_int_get_source_info(unsigned long flags,
+				      unsigned long lisn,
+				      unsigned long *src_flags,
+				      unsigned long *eoi_page,
+				      unsigned long *trig_page,
+				      unsigned long *esb_shift)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_INT_GET_SOURCE_INFO, retbuf, flags, lisn);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_GET_SOURCE_INFO lisn=0x%lx failed %ld\n", lisn, rc);
+		return rc;
+	}
+
+	*src_flags = retbuf[0];
+	*eoi_page  = retbuf[1];
+	*trig_page = retbuf[2];
+	*esb_shift = retbuf[3];
+
+	pr_debug("H_INT_GET_SOURCE_INFO lisn=0x%lx flags=0x%lx eoi=0x%lx trig=0x%lx shift=0x%lx\n",
+		 lisn, retbuf[0], retbuf[1], retbuf[2], retbuf[3]);
+
+	return 0;
+}
+
+#define XIVE_SRC_SET_EISN (1ull << (63 - 62))
+#define XIVE_SRC_MASK     (1ull << (63 - 63)) /* unused */
+
+static long plpar_int_set_source_config(unsigned long flags,
+					unsigned long lisn,
+					unsigned long target,
+					unsigned long prio,
+					unsigned long sw_irq)
+{
+	long rc;
+
+
+	pr_debug("H_INT_SET_SOURCE_CONFIG flags=0x%lx lisn=0x%lx target=%ld prio=%ld sw_irq=%ld\n",
+		 flags, lisn, target, prio, sw_irq);
+
+
+	do {
+		rc = plpar_hcall_norets(H_INT_SET_SOURCE_CONFIG, flags, lisn,
+					target, prio, sw_irq);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_SET_SOURCE_CONFIG lisn=0x%lx target=%ld prio=%ld failed %ld\n",
+		       lisn, target, prio, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static long plpar_int_get_source_config(unsigned long flags,
+					unsigned long lisn,
+					unsigned long *target,
+					unsigned long *prio,
+					unsigned long *sw_irq)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	pr_debug("H_INT_GET_SOURCE_CONFIG flags=0x%lx lisn=0x%lx\n", flags, lisn);
+
+	do {
+		rc = plpar_hcall(H_INT_GET_SOURCE_CONFIG, retbuf, flags, lisn,
+				 target, prio, sw_irq);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_GET_SOURCE_CONFIG lisn=0x%lx failed %ld\n",
+		       lisn, rc);
+		return rc;
+	}
+
+	*target = retbuf[0];
+	*prio   = retbuf[1];
+	*sw_irq = retbuf[2];
+
+	pr_debug("H_INT_GET_SOURCE_CONFIG target=%ld prio=%ld sw_irq=%ld\n",
+		 retbuf[0], retbuf[1], retbuf[2]);
+
+	return 0;
+}
+
+static long plpar_int_get_queue_info(unsigned long flags,
+				     unsigned long target,
+				     unsigned long priority,
+				     unsigned long *esn_page,
+				     unsigned long *esn_size)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_INT_GET_QUEUE_INFO, retbuf, flags, target,
+				 priority);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld failed %ld\n",
+		       target, priority, rc);
+		return rc;
+	}
+
+	*esn_page = retbuf[0];
+	*esn_size = retbuf[1];
+
+	pr_debug("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld page=0x%lx size=0x%lx\n",
+		 target, priority, retbuf[0], retbuf[1]);
+
+	return 0;
+}
+
+#define XIVE_EQ_ALWAYS_NOTIFY (1ull << (63 - 63))
+
+static long plpar_int_set_queue_config(unsigned long flags,
+				       unsigned long target,
+				       unsigned long priority,
+				       unsigned long qpage,
+				       unsigned long qsize)
+{
+	long rc;
+
+	pr_debug("H_INT_SET_QUEUE_CONFIG flags=0x%lx target=%ld priority=0x%lx qpage=0x%lx qsize=0x%lx\n",
+		 flags,  target, priority, qpage, qsize);
+
+	do {
+		rc = plpar_hcall_norets(H_INT_SET_QUEUE_CONFIG, flags, target,
+					priority, qpage, qsize);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_SET_QUEUE_CONFIG cpu=%ld prio=%ld qpage=0x%lx returned %ld\n",
+		       target, priority, qpage, rc);
+		return  rc;
+	}
+
+	return 0;
+}
+
+static long plpar_int_sync(unsigned long flags, unsigned long lisn)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_INT_SYNC, flags, lisn);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_SYNC lisn=0x%lx returned %ld\n", lisn, rc);
+		return  rc;
+	}
+
+	return 0;
+}
+
+#define XIVE_ESB_FLAG_STORE (1ull << (63 - 63))
+
+static long plpar_int_esb(unsigned long flags,
+			  unsigned long lisn,
+			  unsigned long offset,
+			  unsigned long in_data,
+			  unsigned long *out_data)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	pr_debug("H_INT_ESB flags=0x%lx lisn=0x%lx offset=0x%lx in=0x%lx\n",
+		 flags,  lisn, offset, in_data);
+
+	do {
+		rc = plpar_hcall(H_INT_ESB, retbuf, flags, lisn, offset,
+				 in_data);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_ESB lisn=0x%lx offset=0x%lx returned %ld\n",
+		       lisn, offset, rc);
+		return  rc;
+	}
+
+	*out_data = retbuf[0];
+
+	return 0;
+}
+
+static u64 xive_spapr_esb_rw(u32 lisn, u32 offset, u64 data, bool write)
+{
+	unsigned long read_data;
+	long rc;
+
+	rc = plpar_int_esb(write ? XIVE_ESB_FLAG_STORE : 0,
+			   lisn, offset, data, &read_data);
+	if (rc)
+		return -1;
+
+	return write ? 0 : read_data;
+}
+
+#define XIVE_SRC_H_INT_ESB     (1ull << (63 - 60))
+#define XIVE_SRC_LSI           (1ull << (63 - 61))
+#define XIVE_SRC_TRIGGER       (1ull << (63 - 62))
+#define XIVE_SRC_STORE_EOI     (1ull << (63 - 63))
+
+static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
+{
+	long rc;
+	unsigned long flags;
+	unsigned long eoi_page;
+	unsigned long trig_page;
+	unsigned long esb_shift;
+
+	memset(data, 0, sizeof(*data));
+
+	rc = plpar_int_get_source_info(0, hw_irq, &flags, &eoi_page, &trig_page,
+				       &esb_shift);
+	if (rc)
+		return  -EINVAL;
+
+	if (flags & XIVE_SRC_H_INT_ESB)
+		data->flags  |= XIVE_IRQ_FLAG_H_INT_ESB;
+	if (flags & XIVE_SRC_STORE_EOI)
+		data->flags  |= XIVE_IRQ_FLAG_STORE_EOI;
+	if (flags & XIVE_SRC_LSI)
+		data->flags  |= XIVE_IRQ_FLAG_LSI;
+	data->eoi_page  = eoi_page;
+	data->esb_shift = esb_shift;
+	data->trig_page = trig_page;
+
+	data->hw_irq = hw_irq;
+
+	/*
+	 * No chip-id for the sPAPR backend. This has an impact how we
+	 * pick a target. See xive_pick_irq_target().
+	 */
+	data->src_chip = XIVE_INVALID_CHIP_ID;
+
+	/*
+	 * When the H_INT_ESB flag is set, the H_INT_ESB hcall should
+	 * be used for interrupt management. Skip the remapping of the
+	 * ESB pages which are not available.
+	 */
+	if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB)
+		return 0;
+
+	data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift);
+	if (!data->eoi_mmio) {
+		pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq);
+		return -ENOMEM;
+	}
+
+	/* Full function page supports trigger */
+	if (flags & XIVE_SRC_TRIGGER) {
+		data->trig_mmio = data->eoi_mmio;
+		return 0;
+	}
+
+	data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift);
+	if (!data->trig_mmio) {
+		iounmap(data->eoi_mmio);
+		pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static int xive_spapr_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
+{
+	long rc;
+
+	rc = plpar_int_set_source_config(XIVE_SRC_SET_EISN, hw_irq, target,
+					 prio, sw_irq);
+
+	return rc == 0 ? 0 : -ENXIO;
+}
+
+static int xive_spapr_get_irq_config(u32 hw_irq, u32 *target, u8 *prio,
+				     u32 *sw_irq)
+{
+	long rc;
+	unsigned long h_target;
+	unsigned long h_prio;
+	unsigned long h_sw_irq;
+
+	rc = plpar_int_get_source_config(0, hw_irq, &h_target, &h_prio,
+					 &h_sw_irq);
+
+	*target = h_target;
+	*prio = h_prio;
+	*sw_irq = h_sw_irq;
+
+	return rc == 0 ? 0 : -ENXIO;
+}
+
+/* This can be called multiple time to change a queue configuration */
+static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio,
+				   __be32 *qpage, u32 order)
+{
+	s64 rc = 0;
+	unsigned long esn_page;
+	unsigned long esn_size;
+	u64 flags, qpage_phys;
+
+	/* If there's an actual queue page, clean it */
+	if (order) {
+		if (WARN_ON(!qpage))
+			return -EINVAL;
+		qpage_phys = __pa(qpage);
+	} else {
+		qpage_phys = 0;
+	}
+
+	/* Initialize the rest of the fields */
+	q->msk = order ? ((1u << (order - 2)) - 1) : 0;
+	q->idx = 0;
+	q->toggle = 0;
+
+	rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size);
+	if (rc) {
+		pr_err("Error %lld getting queue info CPU %d prio %d\n", rc,
+		       target, prio);
+		rc = -EIO;
+		goto fail;
+	}
+
+	/* TODO: add support for the notification page */
+	q->eoi_phys = esn_page;
+
+	/* Default is to always notify */
+	flags = XIVE_EQ_ALWAYS_NOTIFY;
+
+	/* Configure and enable the queue in HW */
+	rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order);
+	if (rc) {
+		pr_err("Error %lld setting queue for CPU %d prio %d\n", rc,
+		       target, prio);
+		rc = -EIO;
+	} else {
+		q->qpage = qpage;
+		if (is_secure_guest())
+			uv_share_page(PHYS_PFN(qpage_phys),
+					1 << xive_alloc_order(order));
+	}
+fail:
+	return rc;
+}
+
+static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc,
+				  u8 prio)
+{
+	struct xive_q *q = &xc->queue[prio];
+	__be32 *qpage;
+
+	qpage = xive_queue_page_alloc(cpu, xive_queue_shift);
+	if (IS_ERR(qpage))
+		return PTR_ERR(qpage);
+
+	return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu),
+					  q, prio, qpage, xive_queue_shift);
+}
+
+static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
+				  u8 prio)
+{
+	struct xive_q *q = &xc->queue[prio];
+	unsigned int alloc_order;
+	long rc;
+	int hw_cpu = get_hard_smp_processor_id(cpu);
+
+	rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0);
+	if (rc)
+		pr_err("Error %ld setting queue for CPU %d prio %d\n", rc,
+		       hw_cpu, prio);
+
+	alloc_order = xive_alloc_order(xive_queue_shift);
+	if (is_secure_guest())
+		uv_unshare_page(PHYS_PFN(__pa(q->qpage)), 1 << alloc_order);
+	free_pages((unsigned long)q->qpage, alloc_order);
+	q->qpage = NULL;
+}
+
+static bool xive_spapr_match(struct device_node *node)
+{
+	/* Ignore cascaded controllers for the moment */
+	return true;
+}
+
+#ifdef CONFIG_SMP
+static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+	int irq = xive_irq_bitmap_alloc();
+
+	if (irq < 0) {
+		pr_err("Failed to allocate IPI on CPU %d\n", cpu);
+		return -ENXIO;
+	}
+
+	xc->hw_ipi = irq;
+	return 0;
+}
+
+static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
+{
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
+		return;
+
+	xive_irq_bitmap_free(xc->hw_ipi);
+	xc->hw_ipi = XIVE_BAD_IRQ;
+}
+#endif /* CONFIG_SMP */
+
+static void xive_spapr_shutdown(void)
+{
+	plpar_int_reset(0);
+}
+
+/*
+ * Perform an "ack" cycle on the current thread. Grab the pending
+ * active priorities and update the CPPR to the most favored one.
+ */
+static void xive_spapr_update_pending(struct xive_cpu *xc)
+{
+	u8 nsr, cppr;
+	u16 ack;
+
+	/*
+	 * Perform the "Acknowledge O/S to Register" cycle.
+	 *
+	 * Let's speedup the access to the TIMA using the raw I/O
+	 * accessor as we don't need the synchronisation routine of
+	 * the higher level ones
+	 */
+	ack = be16_to_cpu(__raw_readw(xive_tima + TM_SPC_ACK_OS_REG));
+
+	/* Synchronize subsequent queue accesses */
+	mb();
+
+	/*
+	 * Grab the CPPR and the "NSR" field which indicates the source
+	 * of the interrupt (if any)
+	 */
+	cppr = ack & 0xff;
+	nsr = ack >> 8;
+
+	if (nsr & TM_QW1_NSR_EO) {
+		if (cppr == 0xff)
+			return;
+		/* Mark the priority pending */
+		xc->pending_prio |= 1 << cppr;
+
+		/*
+		 * A new interrupt should never have a CPPR less favored
+		 * than our current one.
+		 */
+		if (cppr >= xc->cppr)
+			pr_err("CPU %d odd ack CPPR, got %d at %d\n",
+			       smp_processor_id(), cppr, xc->cppr);
+
+		/* Update our idea of what the CPPR is */
+		xc->cppr = cppr;
+	}
+}
+
+static void xive_spapr_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	/* Only some debug on the TIMA settings */
+	pr_debug("(HW value: %08x %08x %08x)\n",
+		 in_be32(xive_tima + TM_QW1_OS + TM_WORD0),
+		 in_be32(xive_tima + TM_QW1_OS + TM_WORD1),
+		 in_be32(xive_tima + TM_QW1_OS + TM_WORD2));
+}
+
+static void xive_spapr_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
+{
+	/* Nothing to do */;
+}
+
+static void xive_spapr_sync_source(u32 hw_irq)
+{
+	/* Specs are unclear on what this is doing */
+	plpar_int_sync(0, hw_irq);
+}
+
+static int xive_spapr_debug_show(struct seq_file *m, void *private)
+{
+	struct xive_irq_bitmap *xibm;
+
+	list_for_each_entry(xibm, &xive_irq_bitmaps, list)
+		seq_printf(m, "bitmap #%d: %*pbl\n", xibm->count, xibm->count, xibm->bitmap);
+
+	return 0;
+}
+
+static const struct xive_ops xive_spapr_ops = {
+	.populate_irq_data	= xive_spapr_populate_irq_data,
+	.configure_irq		= xive_spapr_configure_irq,
+	.get_irq_config		= xive_spapr_get_irq_config,
+	.setup_queue		= xive_spapr_setup_queue,
+	.cleanup_queue		= xive_spapr_cleanup_queue,
+	.match			= xive_spapr_match,
+	.shutdown		= xive_spapr_shutdown,
+	.update_pending		= xive_spapr_update_pending,
+	.setup_cpu		= xive_spapr_setup_cpu,
+	.teardown_cpu		= xive_spapr_teardown_cpu,
+	.sync_source		= xive_spapr_sync_source,
+	.esb_rw			= xive_spapr_esb_rw,
+#ifdef CONFIG_SMP
+	.get_ipi		= xive_spapr_get_ipi,
+	.put_ipi		= xive_spapr_put_ipi,
+	.debug_show		= xive_spapr_debug_show,
+#endif /* CONFIG_SMP */
+	.name			= "spapr",
+};
+
+/*
+ * get max priority from "/ibm,plat-res-int-priorities"
+ */
+static bool __init xive_get_max_prio(u8 *max_prio)
+{
+	struct device_node *rootdn;
+	const __be32 *reg;
+	u32 len;
+	int prio, found;
+
+	rootdn = of_find_node_by_path("/");
+	if (!rootdn) {
+		pr_err("not root node found !\n");
+		return false;
+	}
+
+	reg = of_get_property(rootdn, "ibm,plat-res-int-priorities", &len);
+	of_node_put(rootdn);
+	if (!reg) {
+		pr_err("Failed to read 'ibm,plat-res-int-priorities' property\n");
+		return false;
+	}
+
+	if (len % (2 * sizeof(u32)) != 0) {
+		pr_err("invalid 'ibm,plat-res-int-priorities' property\n");
+		return false;
+	}
+
+	/* HW supports priorities in the range [0-7] and 0xFF is a
+	 * wildcard priority used to mask. We scan the ranges reserved
+	 * by the hypervisor to find the lowest priority we can use.
+	 */
+	found = 0xFF;
+	for (prio = 0; prio < 8; prio++) {
+		int reserved = 0;
+		int i;
+
+		for (i = 0; i < len / (2 * sizeof(u32)); i++) {
+			int base  = be32_to_cpu(reg[2 * i]);
+			int range = be32_to_cpu(reg[2 * i + 1]);
+
+			if (prio >= base && prio < base + range)
+				reserved++;
+		}
+
+		if (!reserved)
+			found = prio;
+	}
+
+	if (found == 0xFF) {
+		pr_err("no valid priority found in 'ibm,plat-res-int-priorities'\n");
+		return false;
+	}
+
+	*max_prio = found;
+	return true;
+}
+
+static const u8 *__init get_vec5_feature(unsigned int index)
+{
+	unsigned long root, chosen;
+	int size;
+	const u8 *vec5;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return NULL;
+
+	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
+	if (!vec5)
+		return NULL;
+
+	if (size <= index)
+		return NULL;
+
+	return vec5 + index;
+}
+
+static bool __init xive_spapr_disabled(void)
+{
+	const u8 *vec5_xive;
+
+	vec5_xive = get_vec5_feature(OV5_INDX(OV5_XIVE_SUPPORT));
+	if (vec5_xive) {
+		u8 val;
+
+		val = *vec5_xive & OV5_FEAT(OV5_XIVE_SUPPORT);
+		switch (val) {
+		case OV5_FEAT(OV5_XIVE_EITHER):
+		case OV5_FEAT(OV5_XIVE_LEGACY):
+			break;
+		case OV5_FEAT(OV5_XIVE_EXPLOIT):
+			/* Hypervisor only supports XIVE */
+			if (xive_cmdline_disabled)
+				pr_warn("WARNING: Ignoring cmdline option xive=off\n");
+			return false;
+		default:
+			pr_warn("%s: Unknown xive support option: 0x%x\n",
+				__func__, val);
+			break;
+		}
+	}
+
+	return xive_cmdline_disabled;
+}
+
+bool __init xive_spapr_init(void)
+{
+	struct device_node *np;
+	struct resource r;
+	void __iomem *tima;
+	u8 max_prio;
+	u32 val;
+	u32 len;
+	const __be32 *reg;
+	int i, err;
+
+	if (xive_spapr_disabled())
+		return false;
+
+	pr_devel("%s()\n", __func__);
+	np = of_find_compatible_node(NULL, NULL, "ibm,power-ivpe");
+	if (!np) {
+		pr_devel("not found !\n");
+		return false;
+	}
+	pr_devel("Found %s\n", np->full_name);
+
+	/* Resource 1 is the OS ring TIMA */
+	if (of_address_to_resource(np, 1, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		goto err_put;
+	}
+	tima = ioremap(r.start, resource_size(&r));
+	if (!tima) {
+		pr_err("Failed to map thread mgmnt area\n");
+		goto err_put;
+	}
+
+	if (!xive_get_max_prio(&max_prio))
+		goto err_unmap;
+
+	/* Feed the IRQ number allocator with the ranges given in the DT */
+	reg = of_get_property(np, "ibm,xive-lisn-ranges", &len);
+	if (!reg) {
+		pr_err("Failed to read 'ibm,xive-lisn-ranges' property\n");
+		goto err_unmap;
+	}
+
+	if (len % (2 * sizeof(u32)) != 0) {
+		pr_err("invalid 'ibm,xive-lisn-ranges' property\n");
+		goto err_unmap;
+	}
+
+	for (i = 0; i < len / (2 * sizeof(u32)); i++, reg += 2) {
+		err = xive_irq_bitmap_add(be32_to_cpu(reg[0]),
+					  be32_to_cpu(reg[1]));
+		if (err < 0)
+			goto err_mem_free;
+	}
+
+	/* Iterate the EQ sizes and pick one */
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
+		xive_queue_shift = val;
+		if (val == PAGE_SHIFT)
+			break;
+	}
+
+	/* Initialize XIVE core with our backend */
+	if (!xive_core_init(np, &xive_spapr_ops, tima, TM_QW1_OS, max_prio))
+		goto err_mem_free;
+
+	of_node_put(np);
+	pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10));
+	return true;
+
+err_mem_free:
+	xive_irq_bitmap_remove_all();
+err_unmap:
+	iounmap(tima);
+err_put:
+	of_node_put(np);
+	return false;
+}
+
+machine_arch_initcall(pseries, xive_core_debug_init);

linux-7.2.3/arch/powerpc/sysdev/xive/xive-internal.h

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2016,2017 IBM Corporation.
+ */
+#ifndef __XIVE_INTERNAL_H
+#define __XIVE_INTERNAL_H
+
+/*
+ * A "disabled" interrupt should never fire, to catch problems
+ * we set its logical number to this
+ */
+#define XIVE_BAD_IRQ		0x7fffffff
+#define XIVE_MAX_IRQ		(XIVE_BAD_IRQ - 1)
+
+/* Each CPU carry one of these with various per-CPU state */
+struct xive_cpu {
+#ifdef CONFIG_SMP
+	/* HW irq number and data of IPI */
+	u32 hw_ipi;
+	struct xive_irq_data ipi_data;
+#endif /* CONFIG_SMP */
+
+	int chip_id;
+
+	/* Queue datas. Only one is populated */
+#define XIVE_MAX_QUEUES	8
+	struct xive_q queue[XIVE_MAX_QUEUES];
+
+	/*
+	 * Pending mask. Each bit corresponds to a priority that
+	 * potentially has pending interrupts.
+	 */
+	u8 pending_prio;
+
+	/* Cache of HW CPPR */
+	u8 cppr;
+};
+
+/* Backend ops */
+struct xive_ops {
+	int	(*populate_irq_data)(u32 hw_irq, struct xive_irq_data *data);
+	int 	(*configure_irq)(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
+	int	(*get_irq_config)(u32 hw_irq, u32 *target, u8 *prio,
+				  u32 *sw_irq);
+	int	(*setup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
+	void	(*cleanup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
+	void	(*prepare_cpu)(unsigned int cpu, struct xive_cpu *xc);
+	void	(*setup_cpu)(unsigned int cpu, struct xive_cpu *xc);
+	void	(*teardown_cpu)(unsigned int cpu, struct xive_cpu *xc);
+	bool	(*match)(struct device_node *np);
+	void	(*shutdown)(void);
+
+	void	(*update_pending)(struct xive_cpu *xc);
+	void	(*sync_source)(u32 hw_irq);
+	u64	(*esb_rw)(u32 hw_irq, u32 offset, u64 data, bool write);
+#ifdef CONFIG_SMP
+	int	(*get_ipi)(unsigned int cpu, struct xive_cpu *xc);
+	void	(*put_ipi)(unsigned int cpu, struct xive_cpu *xc);
+#endif
+	int	(*debug_show)(struct seq_file *m, void *private);
+	int	(*debug_create)(struct dentry *xive_dir);
+	const char *name;
+};
+
+bool xive_core_init(struct device_node *np, const struct xive_ops *ops,
+		    void __iomem *area, u32 offset, u8 max_prio);
+__be32 *xive_queue_page_alloc(unsigned int cpu, u32 queue_shift);
+int xive_core_debug_init(void);
+
+static inline u32 xive_alloc_order(u32 queue_shift)
+{
+	return (queue_shift > PAGE_SHIFT) ? (queue_shift - PAGE_SHIFT) : 0;
+}
+
+extern bool xive_cmdline_disabled;
+extern bool xive_has_save_restore;
+
+#endif /*  __XIVE_INTERNAL_H */