875 lines · 20.2 KB · C
RawDownload
// 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_SMPstatic 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_SMPstatic 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_FSstatic 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)

Lines 1–500 of 875.