From 2f7c68cb55ecb7331f2381deb497c27155f32faf Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 03 Jan 2024 09:43:39 +0000
Subject: [PATCH] update kernel to 5.10.198
---
kernel/drivers/irqchip/irq-gic-v3-its.c | 2247 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 1,921 insertions(+), 326 deletions(-)
diff --git a/kernel/drivers/irqchip/irq-gic-v3-its.c b/kernel/drivers/irqchip/irq-gic-v3-its.c
index 2cd131d..8f0b4a3 100644
--- a/kernel/drivers/irqchip/irq-gic-v3-its.c
+++ b/kernel/drivers/irqchip/irq-gic-v3-its.c
@@ -1,31 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2013-2017 ARM Limited, All Rights Reserved.
* Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * 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/acpi.h>
#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
#include <linux/bitmap.h>
#include <linux/cpu.h>
+#include <linux/crash_dump.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
+#include <linux/efi.h>
#include <linux/interrupt.h>
+#include <linux/iopoll.h>
#include <linux/irqdomain.h>
#include <linux/list.h>
-#include <linux/list_sort.h>
#include <linux/log2.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/msi.h>
#include <linux/of.h>
@@ -51,6 +44,7 @@
#define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2)
#define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0)
+#define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1)
static u32 lpi_id_bits;
@@ -63,7 +57,7 @@
#define LPI_PROPBASE_SZ ALIGN(BIT(LPI_NRBITS), SZ_64K)
#define LPI_PENDBASE_SZ ALIGN(BIT(LPI_NRBITS) / 8, SZ_64K)
-#define LPI_PROP_DEFAULT_PRIO 0xa0
+#define LPI_PROP_DEFAULT_PRIO GICD_INT_DEF_PRI
/*
* Collection structure - just an ID, and a redistributor address to
@@ -102,6 +96,7 @@
struct mutex dev_alloc_lock;
struct list_head entry;
void __iomem *base;
+ void __iomem *sgir_base;
phys_addr_t phys_base;
struct its_cmd_block *cmd_base;
struct its_cmd_block *cmd_write;
@@ -109,24 +104,36 @@
struct its_collection *collections;
struct fwnode_handle *fwnode_handle;
u64 (*get_msi_base)(struct its_device *its_dev);
+ u64 typer;
u64 cbaser_save;
u32 ctlr_save;
+ u32 mpidr;
struct list_head its_device_list;
u64 flags;
unsigned long list_nr;
- u32 ite_size;
- u32 device_ids;
int numa_node;
unsigned int msi_domain_flags;
u32 pre_its_base; /* for Socionext Synquacer */
- bool is_v4;
int vlpi_redist_offset;
};
+
+#define is_v4(its) (!!((its)->typer & GITS_TYPER_VLPIS))
+#define is_v4_1(its) (!!((its)->typer & GITS_TYPER_VMAPP))
+#define device_ids(its) (FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
#define ITS_ITT_ALIGN SZ_256
/* The maximum number of VPEID bits supported by VLPI commands */
-#define ITS_MAX_VPEID_BITS (16)
+#define ITS_MAX_VPEID_BITS \
+ ({ \
+ int nvpeid = 16; \
+ if (gic_rdists->has_rvpeid && \
+ gic_rdists->gicd_typer2 & GICD_TYPER2_VIL) \
+ nvpeid = 1 + (gic_rdists->gicd_typer2 & \
+ GICD_TYPER2_VID); \
+ \
+ nvpeid; \
+ })
#define ITS_MAX_VPEID (1 << (ITS_MAX_VPEID_BITS))
/* Convert page order to size in bytes */
@@ -137,7 +144,7 @@
u16 *col_map;
irq_hw_number_t lpi_base;
int nr_lpis;
- struct mutex vlpi_lock;
+ raw_spinlock_t vlpi_lock;
struct its_vm *vm;
struct its_vlpi_map *vlpi_maps;
int nr_vlpis;
@@ -167,6 +174,13 @@
int next_victim;
} vpe_proxy;
+struct cpu_lpi_count {
+ atomic_t managed;
+ atomic_t unmanaged;
+};
+
+static DEFINE_PER_CPU(struct cpu_lpi_count, cpu_lpi_count);
+
static LIST_HEAD(its_nodes);
static DEFINE_RAW_SPINLOCK(its_lock);
static struct rdists *gic_rdists;
@@ -183,20 +197,35 @@
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
#define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K)
+/*
+ * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
+ * always have vSGIs mapped.
+ */
+static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
+{
+ return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
+}
+
static u16 get_its_list(struct its_vm *vm)
{
struct its_node *its;
unsigned long its_list = 0;
list_for_each_entry(its, &its_nodes, entry) {
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
- if (vm->vlpi_count[its->list_nr])
+ if (require_its_list_vmovp(vm, its))
__set_bit(its->list_nr, &its_list);
}
return (u16)its_list;
+}
+
+static inline u32 its_get_event_id(struct irq_data *d)
+{
+ struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+ return d->hwirq - its_dev->event_map.lpi_base;
}
static struct its_collection *dev_event_to_col(struct its_device *its_dev,
@@ -205,6 +234,82 @@
struct its_node *its = its_dev->its;
return its->collections + its_dev->event_map.col_map[event];
+}
+
+static struct its_vlpi_map *dev_event_to_vlpi_map(struct its_device *its_dev,
+ u32 event)
+{
+ if (WARN_ON_ONCE(event >= its_dev->event_map.nr_lpis))
+ return NULL;
+
+ return &its_dev->event_map.vlpi_maps[event];
+}
+
+static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
+{
+ if (irqd_is_forwarded_to_vcpu(d)) {
+ struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+ u32 event = its_get_event_id(d);
+
+ return dev_event_to_vlpi_map(its_dev, event);
+ }
+
+ return NULL;
+}
+
+static int vpe_to_cpuid_lock(struct its_vpe *vpe, unsigned long *flags)
+{
+ raw_spin_lock_irqsave(&vpe->vpe_lock, *flags);
+ return vpe->col_idx;
+}
+
+static void vpe_to_cpuid_unlock(struct its_vpe *vpe, unsigned long flags)
+{
+ raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
+}
+
+static struct irq_chip its_vpe_irq_chip;
+
+static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags)
+{
+ struct its_vpe *vpe = NULL;
+ int cpu;
+
+ if (d->chip == &its_vpe_irq_chip) {
+ vpe = irq_data_get_irq_chip_data(d);
+ } else {
+ struct its_vlpi_map *map = get_vlpi_map(d);
+ if (map)
+ vpe = map->vpe;
+ }
+
+ if (vpe) {
+ cpu = vpe_to_cpuid_lock(vpe, flags);
+ } else {
+ /* Physical LPIs are already locked via the irq_desc lock */
+ struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+ cpu = its_dev->event_map.col_map[its_get_event_id(d)];
+ /* Keep GCC quiet... */
+ *flags = 0;
+ }
+
+ return cpu;
+}
+
+static void irq_to_cpuid_unlock(struct irq_data *d, unsigned long flags)
+{
+ struct its_vpe *vpe = NULL;
+
+ if (d->chip == &its_vpe_irq_chip) {
+ vpe = irq_data_get_irq_chip_data(d);
+ } else {
+ struct its_vlpi_map *map = get_vlpi_map(d);
+ if (map)
+ vpe = map->vpe;
+ }
+
+ if (vpe)
+ vpe_to_cpuid_unlock(vpe, flags);
}
static struct its_collection *valid_col(struct its_collection *col)
@@ -306,6 +411,19 @@
u16 seq_num;
u16 its_list;
} its_vmovp_cmd;
+
+ struct {
+ struct its_vpe *vpe;
+ } its_invdb_cmd;
+
+ struct {
+ struct its_vpe *vpe;
+ u8 sgi;
+ u8 priority;
+ bool enable;
+ bool group;
+ bool clear;
+ } its_vsgi_cmd;
};
};
@@ -313,7 +431,10 @@
* The ITS command block, which is what the ITS actually parses.
*/
struct its_cmd_block {
- u64 raw_cmd[4];
+ union {
+ u64 raw_cmd[4];
+ __le64 raw_cmd_le[4];
+ };
};
#define ITS_CMD_QUEUE_SZ SZ_64K
@@ -419,13 +540,70 @@
its_mask_encode(&cmd->raw_cmd[3], vpt_size, 4, 0);
}
+static void its_encode_vconf_addr(struct its_cmd_block *cmd, u64 vconf_pa)
+{
+ its_mask_encode(&cmd->raw_cmd[0], vconf_pa >> 16, 51, 16);
+}
+
+static void its_encode_alloc(struct its_cmd_block *cmd, bool alloc)
+{
+ its_mask_encode(&cmd->raw_cmd[0], alloc, 8, 8);
+}
+
+static void its_encode_ptz(struct its_cmd_block *cmd, bool ptz)
+{
+ its_mask_encode(&cmd->raw_cmd[0], ptz, 9, 9);
+}
+
+static void its_encode_vmapp_default_db(struct its_cmd_block *cmd,
+ u32 vpe_db_lpi)
+{
+ its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_vmovp_default_db(struct its_cmd_block *cmd,
+ u32 vpe_db_lpi)
+{
+ its_mask_encode(&cmd->raw_cmd[3], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_db(struct its_cmd_block *cmd, bool db)
+{
+ its_mask_encode(&cmd->raw_cmd[2], db, 63, 63);
+}
+
+static void its_encode_sgi_intid(struct its_cmd_block *cmd, u8 sgi)
+{
+ its_mask_encode(&cmd->raw_cmd[0], sgi, 35, 32);
+}
+
+static void its_encode_sgi_priority(struct its_cmd_block *cmd, u8 prio)
+{
+ its_mask_encode(&cmd->raw_cmd[0], prio >> 4, 23, 20);
+}
+
+static void its_encode_sgi_group(struct its_cmd_block *cmd, bool grp)
+{
+ its_mask_encode(&cmd->raw_cmd[0], grp, 10, 10);
+}
+
+static void its_encode_sgi_clear(struct its_cmd_block *cmd, bool clr)
+{
+ its_mask_encode(&cmd->raw_cmd[0], clr, 9, 9);
+}
+
+static void its_encode_sgi_enable(struct its_cmd_block *cmd, bool en)
+{
+ its_mask_encode(&cmd->raw_cmd[0], en, 8, 8);
+}
+
static inline void its_fixup_cmd(struct its_cmd_block *cmd)
{
/* Let's fixup BE commands */
- cmd->raw_cmd[0] = cpu_to_le64(cmd->raw_cmd[0]);
- cmd->raw_cmd[1] = cpu_to_le64(cmd->raw_cmd[1]);
- cmd->raw_cmd[2] = cpu_to_le64(cmd->raw_cmd[2]);
- cmd->raw_cmd[3] = cpu_to_le64(cmd->raw_cmd[3]);
+ cmd->raw_cmd_le[0] = cpu_to_le64(cmd->raw_cmd[0]);
+ cmd->raw_cmd_le[1] = cpu_to_le64(cmd->raw_cmd[1]);
+ cmd->raw_cmd_le[2] = cpu_to_le64(cmd->raw_cmd[2]);
+ cmd->raw_cmd_le[3] = cpu_to_le64(cmd->raw_cmd[3]);
}
static struct its_collection *its_build_mapd_cmd(struct its_node *its,
@@ -602,19 +780,45 @@
struct its_cmd_block *cmd,
struct its_cmd_desc *desc)
{
- unsigned long vpt_addr;
+ unsigned long vpt_addr, vconf_addr;
u64 target;
-
- vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
- target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+ bool alloc;
its_encode_cmd(cmd, GITS_CMD_VMAPP);
its_encode_vpeid(cmd, desc->its_vmapp_cmd.vpe->vpe_id);
its_encode_valid(cmd, desc->its_vmapp_cmd.valid);
+
+ if (!desc->its_vmapp_cmd.valid) {
+ if (is_v4_1(its)) {
+ alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
+ its_encode_alloc(cmd, alloc);
+ }
+
+ goto out;
+ }
+
+ vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
+ target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
+
its_encode_target(cmd, target);
its_encode_vpt_addr(cmd, vpt_addr);
its_encode_vpt_size(cmd, LPI_NRBITS - 1);
+ if (!is_v4_1(its))
+ goto out;
+
+ vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page));
+
+ alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count);
+
+ its_encode_alloc(cmd, alloc);
+
+ /* We can only signal PTZ when alloc==1. Why do we have two bits? */
+ its_encode_ptz(cmd, alloc);
+ its_encode_vconf_addr(cmd, vconf_addr);
+ its_encode_vmapp_default_db(cmd, desc->its_vmapp_cmd.vpe->vpe_db_lpi);
+
+out:
its_fixup_cmd(cmd);
return valid_vpe(its, desc->its_vmapp_cmd.vpe);
@@ -626,7 +830,7 @@
{
u32 db;
- if (desc->its_vmapti_cmd.db_enabled)
+ if (!is_v4_1(its) && desc->its_vmapti_cmd.db_enabled)
db = desc->its_vmapti_cmd.vpe->vpe_db_lpi;
else
db = 1023;
@@ -649,7 +853,7 @@
{
u32 db;
- if (desc->its_vmovi_cmd.db_enabled)
+ if (!is_v4_1(its) && desc->its_vmovi_cmd.db_enabled)
db = desc->its_vmovi_cmd.vpe->vpe_db_lpi;
else
db = 1023;
@@ -679,9 +883,103 @@
its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id);
its_encode_target(cmd, target);
+ if (is_v4_1(its)) {
+ its_encode_db(cmd, true);
+ its_encode_vmovp_default_db(cmd, desc->its_vmovp_cmd.vpe->vpe_db_lpi);
+ }
+
its_fixup_cmd(cmd);
return valid_vpe(its, desc->its_vmovp_cmd.vpe);
+}
+
+static struct its_vpe *its_build_vinv_cmd(struct its_node *its,
+ struct its_cmd_block *cmd,
+ struct its_cmd_desc *desc)
+{
+ struct its_vlpi_map *map;
+
+ map = dev_event_to_vlpi_map(desc->its_inv_cmd.dev,
+ desc->its_inv_cmd.event_id);
+
+ its_encode_cmd(cmd, GITS_CMD_INV);
+ its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
+ its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
+
+ its_fixup_cmd(cmd);
+
+ return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_vint_cmd(struct its_node *its,
+ struct its_cmd_block *cmd,
+ struct its_cmd_desc *desc)
+{
+ struct its_vlpi_map *map;
+
+ map = dev_event_to_vlpi_map(desc->its_int_cmd.dev,
+ desc->its_int_cmd.event_id);
+
+ its_encode_cmd(cmd, GITS_CMD_INT);
+ its_encode_devid(cmd, desc->its_int_cmd.dev->device_id);
+ its_encode_event_id(cmd, desc->its_int_cmd.event_id);
+
+ its_fixup_cmd(cmd);
+
+ return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_vclear_cmd(struct its_node *its,
+ struct its_cmd_block *cmd,
+ struct its_cmd_desc *desc)
+{
+ struct its_vlpi_map *map;
+
+ map = dev_event_to_vlpi_map(desc->its_clear_cmd.dev,
+ desc->its_clear_cmd.event_id);
+
+ its_encode_cmd(cmd, GITS_CMD_CLEAR);
+ its_encode_devid(cmd, desc->its_clear_cmd.dev->device_id);
+ its_encode_event_id(cmd, desc->its_clear_cmd.event_id);
+
+ its_fixup_cmd(cmd);
+
+ return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_invdb_cmd(struct its_node *its,
+ struct its_cmd_block *cmd,
+ struct its_cmd_desc *desc)
+{
+ if (WARN_ON(!is_v4_1(its)))
+ return NULL;
+
+ its_encode_cmd(cmd, GITS_CMD_INVDB);
+ its_encode_vpeid(cmd, desc->its_invdb_cmd.vpe->vpe_id);
+
+ its_fixup_cmd(cmd);
+
+ return valid_vpe(its, desc->its_invdb_cmd.vpe);
+}
+
+static struct its_vpe *its_build_vsgi_cmd(struct its_node *its,
+ struct its_cmd_block *cmd,
+ struct its_cmd_desc *desc)
+{
+ if (WARN_ON(!is_v4_1(its)))
+ return NULL;
+
+ its_encode_cmd(cmd, GITS_CMD_VSGI);
+ its_encode_vpeid(cmd, desc->its_vsgi_cmd.vpe->vpe_id);
+ its_encode_sgi_intid(cmd, desc->its_vsgi_cmd.sgi);
+ its_encode_sgi_priority(cmd, desc->its_vsgi_cmd.priority);
+ its_encode_sgi_group(cmd, desc->its_vsgi_cmd.group);
+ its_encode_sgi_clear(cmd, desc->its_vsgi_cmd.clear);
+ its_encode_sgi_enable(cmd, desc->its_vsgi_cmd.enable);
+
+ its_fixup_cmd(cmd);
+
+ return valid_vpe(its, desc->its_vsgi_cmd.vpe);
}
static u64 its_cmd_ptr_to_offset(struct its_node *its,
@@ -961,7 +1259,7 @@
static void its_send_vmapti(struct its_device *dev, u32 id)
{
- struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id];
+ struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id);
struct its_cmd_desc desc;
desc.its_vmapti_cmd.vpe = map->vpe;
@@ -975,7 +1273,7 @@
static void its_send_vmovi(struct its_device *dev, u32 id)
{
- struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id];
+ struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id);
struct its_cmd_desc desc;
desc.its_vmovi_cmd.vpe = map->vpe;
@@ -1029,10 +1327,10 @@
/* Emit VMOVPs */
list_for_each_entry(its, &its_nodes, entry) {
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
- if (!vpe->its_vm->vlpi_count[its->list_nr])
+ if (!require_its_list_vmovp(vpe->its_vm, its))
continue;
desc.its_vmovp_cmd.col = &its->collections[col_id];
@@ -1050,40 +1348,79 @@
its_send_single_vcommand(its, its_build_vinvall_cmd, &desc);
}
+static void its_send_vinv(struct its_device *dev, u32 event_id)
+{
+ struct its_cmd_desc desc;
+
+ /*
+ * There is no real VINV command. This is just a normal INV,
+ * with a VSYNC instead of a SYNC.
+ */
+ desc.its_inv_cmd.dev = dev;
+ desc.its_inv_cmd.event_id = event_id;
+
+ its_send_single_vcommand(dev->its, its_build_vinv_cmd, &desc);
+}
+
+static void its_send_vint(struct its_device *dev, u32 event_id)
+{
+ struct its_cmd_desc desc;
+
+ /*
+ * There is no real VINT command. This is just a normal INT,
+ * with a VSYNC instead of a SYNC.
+ */
+ desc.its_int_cmd.dev = dev;
+ desc.its_int_cmd.event_id = event_id;
+
+ its_send_single_vcommand(dev->its, its_build_vint_cmd, &desc);
+}
+
+static void its_send_vclear(struct its_device *dev, u32 event_id)
+{
+ struct its_cmd_desc desc;
+
+ /*
+ * There is no real VCLEAR command. This is just a normal CLEAR,
+ * with a VSYNC instead of a SYNC.
+ */
+ desc.its_clear_cmd.dev = dev;
+ desc.its_clear_cmd.event_id = event_id;
+
+ its_send_single_vcommand(dev->its, its_build_vclear_cmd, &desc);
+}
+
+static void its_send_invdb(struct its_node *its, struct its_vpe *vpe)
+{
+ struct its_cmd_desc desc;
+
+ desc.its_invdb_cmd.vpe = vpe;
+ its_send_single_vcommand(its, its_build_invdb_cmd, &desc);
+}
+
/*
* irqchip functions - assumes MSI, mostly.
*/
-
-static inline u32 its_get_event_id(struct irq_data *d)
-{
- struct its_device *its_dev = irq_data_get_irq_chip_data(d);
- return d->hwirq - its_dev->event_map.lpi_base;
-}
-
static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
{
+ struct its_vlpi_map *map = get_vlpi_map(d);
irq_hw_number_t hwirq;
- struct page *prop_page;
+ void *va;
u8 *cfg;
- if (irqd_is_forwarded_to_vcpu(d)) {
- struct its_device *its_dev = irq_data_get_irq_chip_data(d);
- u32 event = its_get_event_id(d);
- struct its_vlpi_map *map;
-
- prop_page = its_dev->event_map.vm->vprop_page;
- map = &its_dev->event_map.vlpi_maps[event];
+ if (map) {
+ va = page_address(map->vm->vprop_page);
hwirq = map->vintid;
/* Remember the updated property */
map->properties &= ~clr;
map->properties |= set | LPI_PROP_GROUP1;
} else {
- prop_page = gic_rdists->prop_page;
+ va = gic_rdists->prop_table_va;
hwirq = d->hwirq;
}
- cfg = page_address(prop_page) + hwirq - 8192;
+ cfg = va + hwirq - 8192;
*cfg &= ~clr;
*cfg |= set | LPI_PROP_GROUP1;
@@ -1098,30 +1435,90 @@
dsb(ishst);
}
+static void wait_for_syncr(void __iomem *rdbase)
+{
+ while (readl_relaxed(rdbase + GICR_SYNCR) & 1)
+ cpu_relax();
+}
+
+static void __direct_lpi_inv(struct irq_data *d, u64 val)
+{
+ void __iomem *rdbase;
+ unsigned long flags;
+ int cpu;
+
+ /* Target the redistributor this LPI is currently routed to */
+ cpu = irq_to_cpuid_lock(d, &flags);
+ raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+
+ rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+ gic_write_lpir(val, rdbase + GICR_INVLPIR);
+ wait_for_syncr(rdbase);
+
+ raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+ irq_to_cpuid_unlock(d, flags);
+}
+
+static void direct_lpi_inv(struct irq_data *d)
+{
+ struct its_vlpi_map *map = get_vlpi_map(d);
+ u64 val;
+
+ if (map) {
+ struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+
+ WARN_ON(!is_v4_1(its_dev->its));
+
+ val = GICR_INVLPIR_V;
+ val |= FIELD_PREP(GICR_INVLPIR_VPEID, map->vpe->vpe_id);
+ val |= FIELD_PREP(GICR_INVLPIR_INTID, map->vintid);
+ } else {
+ val = d->hwirq;
+ }
+
+ __direct_lpi_inv(d, val);
+}
+
static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
{
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
lpi_write_config(d, clr, set);
- its_send_inv(its_dev, its_get_event_id(d));
+ if (gic_rdists->has_direct_lpi &&
+ (is_v4_1(its_dev->its) || !irqd_is_forwarded_to_vcpu(d)))
+ direct_lpi_inv(d);
+ else if (!irqd_is_forwarded_to_vcpu(d))
+ its_send_inv(its_dev, its_get_event_id(d));
+ else
+ its_send_vinv(its_dev, its_get_event_id(d));
}
static void its_vlpi_set_doorbell(struct irq_data *d, bool enable)
{
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
u32 event = its_get_event_id(d);
+ struct its_vlpi_map *map;
- if (its_dev->event_map.vlpi_maps[event].db_enabled == enable)
+ /*
+ * GICv4.1 does away with the per-LPI nonsense, nothing to do
+ * here.
+ */
+ if (is_v4_1(its_dev->its))
return;
- its_dev->event_map.vlpi_maps[event].db_enabled = enable;
+ map = dev_event_to_vlpi_map(its_dev, event);
+
+ if (map->db_enabled == enable)
+ return;
+
+ map->db_enabled = enable;
/*
* More fun with the architecture:
*
* Ideally, we'd issue a VMAPTI to set the doorbell to its LPI
* value or to 1023, depending on the enable bit. But that
- * would be issueing a mapping for an /existing/ DevID+EventID
+ * would be issuing a mapping for an /existing/ DevID+EventID
* pair, which is UNPREDICTABLE. Instead, let's issue a VMOVI
* to the /same/ vPE, using this opportunity to adjust the
* doorbell. Mouahahahaha. We loves it, Precious.
@@ -1145,42 +1542,159 @@
lpi_update_config(d, 0, LPI_PROP_ENABLED);
}
+static __maybe_unused u32 its_read_lpi_count(struct irq_data *d, int cpu)
+{
+ if (irqd_affinity_is_managed(d))
+ return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+
+ return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_inc_lpi_count(struct irq_data *d, int cpu)
+{
+ if (irqd_affinity_is_managed(d))
+ atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+ else
+ atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_dec_lpi_count(struct irq_data *d, int cpu)
+{
+ if (irqd_affinity_is_managed(d))
+ atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+ else
+ atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static unsigned int cpumask_pick_least_loaded(struct irq_data *d,
+ const struct cpumask *cpu_mask)
+{
+ unsigned int cpu = nr_cpu_ids, tmp;
+ int count = S32_MAX;
+
+ for_each_cpu(tmp, cpu_mask) {
+ int this_count = its_read_lpi_count(d, tmp);
+ if (this_count < count) {
+ cpu = tmp;
+ count = this_count;
+ }
+ }
+
+ return cpu;
+}
+
+/*
+ * As suggested by Thomas Gleixner in:
+ * https://lore.kernel.org/r/87h80q2aoc.fsf@nanos.tec.linutronix.de
+ */
+static int its_select_cpu(struct irq_data *d,
+ const struct cpumask *aff_mask)
+{
+ struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+ cpumask_var_t tmpmask;
+ int cpu, node;
+
+ if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+ return -ENOMEM;
+
+ node = its_dev->its->numa_node;
+
+ if (!irqd_affinity_is_managed(d)) {
+ /* First try the NUMA node */
+ if (node != NUMA_NO_NODE) {
+ /*
+ * Try the intersection of the affinity mask and the
+ * node mask (and the online mask, just to be safe).
+ */
+ cpumask_and(tmpmask, cpumask_of_node(node), aff_mask);
+ cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+ /*
+ * Ideally, we would check if the mask is empty, and
+ * try again on the full node here.
+ *
+ * But it turns out that the way ACPI describes the
+ * affinity for ITSs only deals about memory, and
+ * not target CPUs, so it cannot describe a single
+ * ITS placed next to two NUMA nodes.
+ *
+ * Instead, just fallback on the online mask. This
+ * diverges from Thomas' suggestion above.
+ */
+ cpu = cpumask_pick_least_loaded(d, tmpmask);
+ if (cpu < nr_cpu_ids)
+ goto out;
+
+ /* If we can't cross sockets, give up */
+ if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144))
+ goto out;
+
+ /* If the above failed, expand the search */
+ }
+
+ /* Try the intersection of the affinity and online masks */
+ cpumask_and(tmpmask, aff_mask, cpu_online_mask);
+
+ /* If that doesn't fly, the online mask is the last resort */
+ if (cpumask_empty(tmpmask))
+ cpumask_copy(tmpmask, cpu_online_mask);
+
+ cpu = cpumask_pick_least_loaded(d, tmpmask);
+ } else {
+ cpumask_copy(tmpmask, aff_mask);
+
+ /* If we cannot cross sockets, limit the search to that node */
+ if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) &&
+ node != NUMA_NO_NODE)
+ cpumask_and(tmpmask, tmpmask, cpumask_of_node(node));
+
+ cpu = cpumask_pick_least_loaded(d, tmpmask);
+ }
+out:
+ free_cpumask_var(tmpmask);
+
+ pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu);
+ return cpu;
+}
+
static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
bool force)
{
- unsigned int cpu;
- const struct cpumask *cpu_mask = cpu_online_mask;
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
struct its_collection *target_col;
u32 id = its_get_event_id(d);
+ int cpu, prev_cpu;
/* A forwarded interrupt should use irq_set_vcpu_affinity */
if (irqd_is_forwarded_to_vcpu(d))
return -EINVAL;
- /* lpi cannot be routed to a redistributor that is on a foreign node */
- if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
- if (its_dev->its->numa_node >= 0) {
- cpu_mask = cpumask_of_node(its_dev->its->numa_node);
- if (!cpumask_intersects(mask_val, cpu_mask))
- return -EINVAL;
- }
- }
+ prev_cpu = its_dev->event_map.col_map[id];
+ its_dec_lpi_count(d, prev_cpu);
- cpu = cpumask_any_and(mask_val, cpu_mask);
+ if (!force)
+ cpu = its_select_cpu(d, mask_val);
+ else
+ cpu = cpumask_pick_least_loaded(d, mask_val);
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
+ if (cpu < 0 || cpu >= nr_cpu_ids)
+ goto err;
/* don't set the affinity when the target cpu is same as current one */
- if (cpu != its_dev->event_map.col_map[id]) {
+ if (cpu != prev_cpu) {
target_col = &its_dev->its->collections[cpu];
its_send_movi(its_dev, target_col, id);
its_dev->event_map.col_map[id] = cpu;
irq_data_update_effective_affinity(d, cpumask_of(cpu));
}
+ its_inc_lpi_count(d, cpu);
+
return IRQ_SET_MASK_OK_DONE;
+
+err:
+ its_inc_lpi_count(d, prev_cpu);
+ return -EINVAL;
}
static u64 its_irq_get_msi_base(struct its_device *its_dev)
@@ -1203,7 +1717,7 @@
msg->address_hi = upper_32_bits(addr);
msg->data = its_get_event_id(d);
- iommu_dma_map_msi_msg(d->irq, msg);
+ iommu_dma_compose_msi_msg(irq_data_get_msi_desc(d), msg);
}
static int its_irq_set_irqchip_state(struct irq_data *d,
@@ -1216,20 +1730,51 @@
if (which != IRQCHIP_STATE_PENDING)
return -EINVAL;
- if (state)
- its_send_int(its_dev, event);
- else
- its_send_clear(its_dev, event);
+ if (irqd_is_forwarded_to_vcpu(d)) {
+ if (state)
+ its_send_vint(its_dev, event);
+ else
+ its_send_vclear(its_dev, event);
+ } else {
+ if (state)
+ its_send_int(its_dev, event);
+ else
+ its_send_clear(its_dev, event);
+ }
return 0;
+}
+
+static int its_irq_retrigger(struct irq_data *d)
+{
+ return !its_irq_set_irqchip_state(d, IRQCHIP_STATE_PENDING, true);
+}
+
+/*
+ * Two favourable cases:
+ *
+ * (a) Either we have a GICv4.1, and all vPEs have to be mapped at all times
+ * for vSGI delivery
+ *
+ * (b) Or the ITSs do not use a list map, meaning that VMOVP is cheap enough
+ * and we're better off mapping all VPEs always
+ *
+ * If neither (a) nor (b) is true, then we map vPEs on demand.
+ *
+ */
+static bool gic_requires_eager_mapping(void)
+{
+ if (!its_list_map || gic_rdists->has_rvpeid)
+ return true;
+
+ return false;
}
static void its_map_vm(struct its_node *its, struct its_vm *vm)
{
unsigned long flags;
- /* Not using the ITS list? Everything is always mapped. */
- if (!its_list_map)
+ if (gic_requires_eager_mapping())
return;
raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -1263,7 +1808,7 @@
unsigned long flags;
/* Not using the ITS list? Everything is always mapped. */
- if (!its_list_map)
+ if (gic_requires_eager_mapping())
return;
raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -1287,13 +1832,13 @@
if (!info->map)
return -EINVAL;
- mutex_lock(&its_dev->event_map.vlpi_lock);
+ raw_spin_lock(&its_dev->event_map.vlpi_lock);
if (!its_dev->event_map.vm) {
struct its_vlpi_map *maps;
maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps),
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!maps) {
ret = -ENOMEM;
goto out;
@@ -1336,29 +1881,30 @@
}
out:
- mutex_unlock(&its_dev->event_map.vlpi_lock);
+ raw_spin_unlock(&its_dev->event_map.vlpi_lock);
return ret;
}
static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info)
{
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
- u32 event = its_get_event_id(d);
+ struct its_vlpi_map *map;
int ret = 0;
- mutex_lock(&its_dev->event_map.vlpi_lock);
+ raw_spin_lock(&its_dev->event_map.vlpi_lock);
- if (!its_dev->event_map.vm ||
- !its_dev->event_map.vlpi_maps[event].vm) {
+ map = get_vlpi_map(d);
+
+ if (!its_dev->event_map.vm || !map) {
ret = -EINVAL;
goto out;
}
/* Copy our mapping information to the incoming request */
- *info->map = its_dev->event_map.vlpi_maps[event];
+ *info->map = *map;
out:
- mutex_unlock(&its_dev->event_map.vlpi_lock);
+ raw_spin_unlock(&its_dev->event_map.vlpi_lock);
return ret;
}
@@ -1368,7 +1914,7 @@
u32 event = its_get_event_id(d);
int ret = 0;
- mutex_lock(&its_dev->event_map.vlpi_lock);
+ raw_spin_lock(&its_dev->event_map.vlpi_lock);
if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) {
ret = -EINVAL;
@@ -1398,7 +1944,7 @@
}
out:
- mutex_unlock(&its_dev->event_map.vlpi_lock);
+ raw_spin_unlock(&its_dev->event_map.vlpi_lock);
return ret;
}
@@ -1424,7 +1970,7 @@
struct its_cmd_info *info = vcpu_info;
/* Need a v4 ITS */
- if (!its_dev->its->is_v4)
+ if (!is_v4(its_dev->its))
return -EINVAL;
/* Unmap request? */
@@ -1455,6 +2001,7 @@
.irq_set_affinity = its_set_affinity,
.irq_compose_msi_msg = its_irq_compose_msi_msg,
.irq_set_irqchip_state = its_irq_set_irqchip_state,
+ .irq_retrigger = its_irq_retrigger,
.irq_set_vcpu_affinity = its_irq_set_vcpu_affinity,
};
@@ -1489,39 +2036,13 @@
{
struct lpi_range *range;
- range = kzalloc(sizeof(*range), GFP_KERNEL);
+ range = kmalloc(sizeof(*range), GFP_KERNEL);
if (range) {
- INIT_LIST_HEAD(&range->entry);
range->base_id = base;
range->span = span;
}
return range;
-}
-
-static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
-{
- struct lpi_range *ra, *rb;
-
- ra = container_of(a, struct lpi_range, entry);
- rb = container_of(b, struct lpi_range, entry);
-
- return ra->base_id - rb->base_id;
-}
-
-static void merge_lpi_ranges(void)
-{
- struct lpi_range *range, *tmp;
-
- list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
- if (!list_is_last(&range->entry, &lpi_range_list) &&
- (tmp->base_id == (range->base_id + range->span))) {
- tmp->base_id = range->base_id;
- tmp->span += range->span;
- list_del(&range->entry);
- kfree(range);
- }
- }
}
static int alloc_lpi_range(u32 nr_lpis, u32 *base)
@@ -1553,25 +2074,49 @@
return err;
}
+static void merge_lpi_ranges(struct lpi_range *a, struct lpi_range *b)
+{
+ if (&a->entry == &lpi_range_list || &b->entry == &lpi_range_list)
+ return;
+ if (a->base_id + a->span != b->base_id)
+ return;
+ b->base_id = a->base_id;
+ b->span += a->span;
+ list_del(&a->entry);
+ kfree(a);
+}
+
static int free_lpi_range(u32 base, u32 nr_lpis)
{
- struct lpi_range *new;
- int err = 0;
+ struct lpi_range *new, *old;
+
+ new = mk_lpi_range(base, nr_lpis);
+ if (!new)
+ return -ENOMEM;
mutex_lock(&lpi_range_lock);
- new = mk_lpi_range(base, nr_lpis);
- if (!new) {
- err = -ENOMEM;
- goto out;
+ list_for_each_entry_reverse(old, &lpi_range_list, entry) {
+ if (old->base_id < base)
+ break;
}
+ /*
+ * old is the last element with ->base_id smaller than base,
+ * so new goes right after it. If there are no elements with
+ * ->base_id smaller than base, &old->entry ends up pointing
+ * at the head of the list, and inserting new it the start of
+ * the list is the right thing to do in that case as well.
+ */
+ list_add(&new->entry, &old->entry);
+ /*
+ * Now check if we can merge with the preceding and/or
+ * following ranges.
+ */
+ merge_lpi_ranges(old, new);
+ merge_lpi_ranges(new, list_next_entry(new, entry));
- list_add(&new->entry, &lpi_range_list);
- list_sort(NULL, &lpi_range_list, lpi_range_cmp);
- merge_lpi_ranges();
-out:
mutex_unlock(&lpi_range_lock);
- return err;
+ return 0;
}
static int __init its_lpi_init(u32 id_bits)
@@ -1635,23 +2180,28 @@
kfree(bitmap);
}
+static void gic_reset_prop_table(void *va)
+{
+ /* Priority 0xa0, Group-1, disabled */
+ memset(va, LPI_PROP_DEFAULT_PRIO | LPI_PROP_GROUP1, LPI_PROPBASE_SZ);
+
+ /* Make sure the GIC will observe the written configuration */
+ gic_flush_dcache_to_poc(va, LPI_PROPBASE_SZ);
+}
+
static struct page *its_allocate_prop_table(gfp_t gfp_flags)
{
struct page *prop_page;
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
gfp_flags |= GFP_DMA32;
prop_page = alloc_pages(gfp_flags, get_order(LPI_PROPBASE_SZ));
if (!prop_page)
return NULL;
- /* Priority 0xa0, Group-1, disabled */
- memset(page_address(prop_page),
- LPI_PROP_DEFAULT_PRIO | LPI_PROP_GROUP1,
- LPI_PROPBASE_SZ);
-
- /* Make sure the GIC will observe the written configuration */
- gic_flush_dcache_to_poc(page_address(prop_page), LPI_PROPBASE_SZ);
+ gic_reset_prop_table(page_address(prop_page));
return prop_page;
}
@@ -1662,20 +2212,74 @@
get_order(LPI_PROPBASE_SZ));
}
-static int __init its_alloc_lpi_prop_table(void)
+static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
{
- phys_addr_t paddr;
+ phys_addr_t start, end, addr_end;
+ u64 i;
- lpi_id_bits = min_t(u32, GICD_TYPER_ID_BITS(gic_rdists->gicd_typer),
- ITS_MAX_LPI_NRBITS);
- gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
- if (!gic_rdists->prop_page) {
- pr_err("Failed to allocate PROPBASE\n");
- return -ENOMEM;
+ /*
+ * We don't bother checking for a kdump kernel as by
+ * construction, the LPI tables are out of this kernel's
+ * memory map.
+ */
+ if (is_kdump_kernel())
+ return true;
+
+ addr_end = addr + size - 1;
+
+ for_each_reserved_mem_range(i, &start, &end) {
+ if (addr >= start && addr_end <= end)
+ return true;
}
- paddr = page_to_phys(gic_rdists->prop_page);
- pr_info("GIC: using LPI property table @%pa\n", &paddr);
+ /* Not found, not a good sign... */
+ pr_warn("GICv3: Expected reserved range [%pa:%pa], not found\n",
+ &addr, &addr_end);
+ add_taint(TAINT_CRAP, LOCKDEP_STILL_OK);
+ return false;
+}
+
+static int gic_reserve_range(phys_addr_t addr, unsigned long size)
+{
+ if (efi_enabled(EFI_CONFIG_TABLES))
+ return efi_mem_reserve_persistent(addr, size);
+
+ return 0;
+}
+
+static int __init its_setup_lpi_prop_table(void)
+{
+ if (gic_rdists->flags & RDIST_FLAGS_RD_TABLES_PREALLOCATED) {
+ u64 val;
+
+ val = gicr_read_propbaser(gic_data_rdist_rd_base() + GICR_PROPBASER);
+ lpi_id_bits = (val & GICR_PROPBASER_IDBITS_MASK) + 1;
+
+ gic_rdists->prop_table_pa = val & GENMASK_ULL(51, 12);
+ gic_rdists->prop_table_va = memremap(gic_rdists->prop_table_pa,
+ LPI_PROPBASE_SZ,
+ MEMREMAP_WB);
+ gic_reset_prop_table(gic_rdists->prop_table_va);
+ } else {
+ struct page *page;
+
+ lpi_id_bits = min_t(u32,
+ GICD_TYPER_ID_BITS(gic_rdists->gicd_typer),
+ ITS_MAX_LPI_NRBITS);
+ page = its_allocate_prop_table(GFP_NOWAIT);
+ if (!page) {
+ pr_err("Failed to allocate PROPBASE\n");
+ return -ENOMEM;
+ }
+
+ gic_rdists->prop_table_pa = page_to_phys(page);
+ gic_rdists->prop_table_va = page_address(page);
+ WARN_ON(gic_reserve_range(gic_rdists->prop_table_pa,
+ LPI_PROPBASE_SZ));
+ }
+
+ pr_info("GICv3: using LPI property table @%pa\n",
+ &gic_rdists->prop_table_pa);
return its_lpi_init(lpi_id_bits);
}
@@ -1707,18 +2311,18 @@
}
static int its_setup_baser(struct its_node *its, struct its_baser *baser,
- u64 cache, u64 shr, u32 psz, u32 order,
- bool indirect)
+ u64 cache, u64 shr, u32 order, bool indirect)
{
u64 val = its_read_baser(its, baser);
u64 esz = GITS_BASER_ENTRY_SIZE(val);
u64 type = GITS_BASER_TYPE(val);
u64 baser_phys, tmp;
- u32 alloc_pages;
+ u32 alloc_pages, psz;
+ struct page *page;
void *base;
gfp_t gfp_flags;
-retry_alloc_baser:
+ psz = baser->psz;
alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
if (alloc_pages > GITS_BASER_PAGES_MAX) {
pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n",
@@ -1729,12 +2333,15 @@
}
gfp_flags = GFP_KERNEL | __GFP_ZERO;
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
gfp_flags |= GFP_DMA32;
- base = (void *)__get_free_pages(gfp_flags, order);
- if (!base)
+ page = alloc_pages_node(its->numa_node, gfp_flags, order);
+ if (!page)
return -ENOMEM;
+ base = (void *)page_address(page);
baser_phys = virt_to_phys(base);
/* Check if the physical address of the memory is above 48bits */
@@ -1777,8 +2384,11 @@
its_write_baser(its, baser, val);
tmp = baser->val;
- if (of_machine_is_compatible("rockchip,rk3568") ||
- of_machine_is_compatible("rockchip,rk3566")) {
+ if (IS_ENABLED(CONFIG_NO_GKI) &&
+ (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566") ||
+ of_machine_is_compatible("rockchip,rk3588"))) {
if (tmp & GITS_BASER_SHAREABILITY_MASK)
tmp &= ~GITS_BASER_SHAREABILITY_MASK;
else
@@ -1799,25 +2409,6 @@
gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order));
}
goto retry_baser;
- }
-
- if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) {
- /*
- * Page size didn't stick. Let's try a smaller
- * size and retry. If we reach 4K, then
- * something is horribly wrong...
- */
- free_pages((unsigned long)base, order);
- baser->base = NULL;
-
- switch (psz) {
- case SZ_16K:
- psz = SZ_4K;
- goto retry_alloc_baser;
- case SZ_64K:
- psz = SZ_16K;
- goto retry_alloc_baser;
- }
}
if (val != tmp) {
@@ -1845,13 +2436,14 @@
static bool its_parse_indirect_baser(struct its_node *its,
struct its_baser *baser,
- u32 psz, u32 *order, u32 ids)
+ u32 *order, u32 ids)
{
u64 tmp = its_read_baser(its, baser);
u64 type = GITS_BASER_TYPE(tmp);
u64 esz = GITS_BASER_ENTRY_SIZE(tmp);
u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb;
u32 new_order = *order;
+ u32 psz = baser->psz;
bool indirect = false;
/* No need to enable Indirection if memory requirement < (psz*2)bytes */
@@ -1887,14 +2479,73 @@
if (new_order >= MAX_ORDER) {
new_order = MAX_ORDER - 1;
ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
- pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n",
+ pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
&its->phys_base, its_base_type_string[type],
- its->device_ids, ids);
+ device_ids(its), ids);
}
*order = new_order;
return indirect;
+}
+
+static u32 compute_common_aff(u64 val)
+{
+ u32 aff, clpiaff;
+
+ aff = FIELD_GET(GICR_TYPER_AFFINITY, val);
+ clpiaff = FIELD_GET(GICR_TYPER_COMMON_LPI_AFF, val);
+
+ return aff & ~(GENMASK(31, 0) >> (clpiaff * 8));
+}
+
+static u32 compute_its_aff(struct its_node *its)
+{
+ u64 val;
+ u32 svpet;
+
+ /*
+ * Reencode the ITS SVPET and MPIDR as a GICR_TYPER, and compute
+ * the resulting affinity. We then use that to see if this match
+ * our own affinity.
+ */
+ svpet = FIELD_GET(GITS_TYPER_SVPET, its->typer);
+ val = FIELD_PREP(GICR_TYPER_COMMON_LPI_AFF, svpet);
+ val |= FIELD_PREP(GICR_TYPER_AFFINITY, its->mpidr);
+ return compute_common_aff(val);
+}
+
+static struct its_node *find_sibling_its(struct its_node *cur_its)
+{
+ struct its_node *its;
+ u32 aff;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, cur_its->typer))
+ return NULL;
+
+ aff = compute_its_aff(cur_its);
+
+ list_for_each_entry(its, &its_nodes, entry) {
+ u64 baser;
+
+ if (!is_v4_1(its) || its == cur_its)
+ continue;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+ continue;
+
+ if (aff != compute_its_aff(its))
+ continue;
+
+ /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+ baser = its->tables[2].val;
+ if (!(baser & GITS_BASER_VALID))
+ continue;
+
+ return its;
+ }
+
+ return NULL;
}
static void its_free_tables(struct its_node *its)
@@ -1910,11 +2561,58 @@
}
}
+static int its_probe_baser_psz(struct its_node *its, struct its_baser *baser)
+{
+ u64 psz = SZ_64K;
+
+ while (psz) {
+ u64 val, gpsz;
+
+ val = its_read_baser(its, baser);
+ val &= ~GITS_BASER_PAGE_SIZE_MASK;
+
+ switch (psz) {
+ case SZ_64K:
+ gpsz = GITS_BASER_PAGE_SIZE_64K;
+ break;
+ case SZ_16K:
+ gpsz = GITS_BASER_PAGE_SIZE_16K;
+ break;
+ case SZ_4K:
+ default:
+ gpsz = GITS_BASER_PAGE_SIZE_4K;
+ break;
+ }
+
+ gpsz >>= GITS_BASER_PAGE_SIZE_SHIFT;
+
+ val |= FIELD_PREP(GITS_BASER_PAGE_SIZE_MASK, gpsz);
+ its_write_baser(its, baser, val);
+
+ if (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser->val) == gpsz)
+ break;
+
+ switch (psz) {
+ case SZ_64K:
+ psz = SZ_16K;
+ break;
+ case SZ_16K:
+ psz = SZ_4K;
+ break;
+ case SZ_4K:
+ default:
+ return -1;
+ }
+ }
+
+ baser->psz = psz;
+ return 0;
+}
+
static int its_alloc_tables(struct its_node *its)
{
u64 shr = GITS_BASER_InnerShareable;
u64 cache = GITS_BASER_RaWaWb;
- u32 psz = SZ_64K;
int err, i;
if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375)
@@ -1925,37 +2623,337 @@
struct its_baser *baser = its->tables + i;
u64 val = its_read_baser(its, baser);
u64 type = GITS_BASER_TYPE(val);
- u32 order = get_order(psz);
bool indirect = false;
+ u32 order;
- switch (type) {
- case GITS_BASER_TYPE_NONE:
+ if (type == GITS_BASER_TYPE_NONE)
continue;
+ if (its_probe_baser_psz(its, baser)) {
+ its_free_tables(its);
+ return -ENXIO;
+ }
+
+ order = get_order(baser->psz);
+
+ switch (type) {
case GITS_BASER_TYPE_DEVICE:
- indirect = its_parse_indirect_baser(its, baser,
- psz, &order,
- its->device_ids);
+ indirect = its_parse_indirect_baser(its, baser, &order,
+ device_ids(its));
break;
case GITS_BASER_TYPE_VCPU:
- indirect = its_parse_indirect_baser(its, baser,
- psz, &order,
+ if (is_v4_1(its)) {
+ struct its_node *sibling;
+
+ WARN_ON(i != 2);
+ if ((sibling = find_sibling_its(its))) {
+ *baser = sibling->tables[2];
+ its_write_baser(its, baser, baser->val);
+ continue;
+ }
+ }
+
+ indirect = its_parse_indirect_baser(its, baser, &order,
ITS_MAX_VPEID_BITS);
break;
}
- err = its_setup_baser(its, baser, cache, shr, psz, order, indirect);
+ err = its_setup_baser(its, baser, cache, shr, order, indirect);
if (err < 0) {
its_free_tables(its);
return err;
}
/* Update settings which will be used for next BASERn */
- psz = baser->psz;
cache = baser->val & GITS_BASER_CACHEABILITY_MASK;
shr = baser->val & GITS_BASER_SHAREABILITY_MASK;
}
+
+ return 0;
+}
+
+static u64 inherit_vpe_l1_table_from_its(void)
+{
+ struct its_node *its;
+ u64 val;
+ u32 aff;
+
+ val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+ aff = compute_common_aff(val);
+
+ list_for_each_entry(its, &its_nodes, entry) {
+ u64 baser, addr;
+
+ if (!is_v4_1(its))
+ continue;
+
+ if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+ continue;
+
+ if (aff != compute_its_aff(its))
+ continue;
+
+ /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+ baser = its->tables[2].val;
+ if (!(baser & GITS_BASER_VALID))
+ continue;
+
+ /* We have a winner! */
+ gic_data_rdist()->vpe_l1_base = its->tables[2].base;
+
+ val = GICR_VPROPBASER_4_1_VALID;
+ if (baser & GITS_BASER_INDIRECT)
+ val |= GICR_VPROPBASER_4_1_INDIRECT;
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE,
+ FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser));
+ switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) {
+ case GIC_PAGE_SIZE_64K:
+ addr = GITS_BASER_ADDR_48_to_52(baser);
+ break;
+ default:
+ addr = baser & GENMASK_ULL(47, 12);
+ break;
+ }
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
+ val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+ FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+ val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+ FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
+
+ return val;
+ }
+
+ return 0;
+}
+
+static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
+{
+ u32 aff;
+ u64 val;
+ int cpu;
+
+ val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+ aff = compute_common_aff(val);
+
+ for_each_possible_cpu(cpu) {
+ void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+
+ if (!base || cpu == smp_processor_id())
+ continue;
+
+ val = gic_read_typer(base + GICR_TYPER);
+ if (aff != compute_common_aff(val))
+ continue;
+
+ /*
+ * At this point, we have a victim. This particular CPU
+ * has already booted, and has an affinity that matches
+ * ours wrt CommonLPIAff. Let's use its own VPROPBASER.
+ * Make sure we don't write the Z bit in that case.
+ */
+ val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+ val &= ~GICR_VPROPBASER_4_1_Z;
+
+ gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base;
+ *mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
+
+ return val;
+ }
+
+ return 0;
+}
+
+static bool allocate_vpe_l2_table(int cpu, u32 id)
+{
+ void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+ unsigned int psz, esz, idx, npg, gpsz;
+ u64 val;
+ struct page *page;
+ __le64 *table;
+
+ if (!gic_rdists->has_rvpeid)
+ return true;
+
+ /* Skip non-present CPUs */
+ if (!base)
+ return true;
+
+ val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+
+ esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val) + 1;
+ gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+ npg = FIELD_GET(GICR_VPROPBASER_4_1_SIZE, val) + 1;
+
+ switch (gpsz) {
+ default:
+ WARN_ON(1);
+ fallthrough;
+ case GIC_PAGE_SIZE_4K:
+ psz = SZ_4K;
+ break;
+ case GIC_PAGE_SIZE_16K:
+ psz = SZ_16K;
+ break;
+ case GIC_PAGE_SIZE_64K:
+ psz = SZ_64K;
+ break;
+ }
+
+ /* Don't allow vpe_id that exceeds single, flat table limit */
+ if (!(val & GICR_VPROPBASER_4_1_INDIRECT))
+ return (id < (npg * psz / (esz * SZ_8)));
+
+ /* Compute 1st level table index & check if that exceeds table limit */
+ idx = id >> ilog2(psz / (esz * SZ_8));
+ if (idx >= (npg * psz / GITS_LVL1_ENTRY_SIZE))
+ return false;
+
+ table = gic_data_rdist_cpu(cpu)->vpe_l1_base;
+
+ /* Allocate memory for 2nd level table */
+ if (!table[idx]) {
+ page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
+ if (!page)
+ return false;
+
+ /* Flush Lvl2 table to PoC if hw doesn't support coherency */
+ if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK))
+ gic_flush_dcache_to_poc(page_address(page), psz);
+
+ table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID);
+
+ /* Flush Lvl1 entry to PoC if hw doesn't support coherency */
+ if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK))
+ gic_flush_dcache_to_poc(table + idx, GITS_LVL1_ENTRY_SIZE);
+
+ /* Ensure updated table contents are visible to RD hardware */
+ dsb(sy);
+ }
+
+ return true;
+}
+
+static int allocate_vpe_l1_table(void)
+{
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+ u64 val, gpsz, npg, pa;
+ unsigned int psz = SZ_64K;
+ unsigned int np, epp, esz;
+ struct page *page;
+
+ if (!gic_rdists->has_rvpeid)
+ return 0;
+
+ /*
+ * if VPENDBASER.Valid is set, disable any previously programmed
+ * VPE by setting PendingLast while clearing Valid. This has the
+ * effect of making sure no doorbell will be generated and we can
+ * then safely clear VPROPBASER.Valid.
+ */
+ if (gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid)
+ gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast,
+ vlpi_base + GICR_VPENDBASER);
+
+ /*
+ * If we can inherit the configuration from another RD, let's do
+ * so. Otherwise, we have to go through the allocation process. We
+ * assume that all RDs have the exact same requirements, as
+ * nothing will work otherwise.
+ */
+ val = inherit_vpe_l1_table_from_rd(&gic_data_rdist()->vpe_table_mask);
+ if (val & GICR_VPROPBASER_4_1_VALID)
+ goto out;
+
+ gic_data_rdist()->vpe_table_mask = kzalloc(sizeof(cpumask_t), GFP_ATOMIC);
+ if (!gic_data_rdist()->vpe_table_mask)
+ return -ENOMEM;
+
+ val = inherit_vpe_l1_table_from_its();
+ if (val & GICR_VPROPBASER_4_1_VALID)
+ goto out;
+
+ /* First probe the page size */
+ val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K);
+ gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ val = gicr_read_vpropbaser(vlpi_base + GICR_VPROPBASER);
+ gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+ esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val);
+
+ switch (gpsz) {
+ default:
+ gpsz = GIC_PAGE_SIZE_4K;
+ fallthrough;
+ case GIC_PAGE_SIZE_4K:
+ psz = SZ_4K;
+ break;
+ case GIC_PAGE_SIZE_16K:
+ psz = SZ_16K;
+ break;
+ case GIC_PAGE_SIZE_64K:
+ psz = SZ_64K;
+ break;
+ }
+
+ /*
+ * Start populating the register from scratch, including RO fields
+ * (which we want to print in debug cases...)
+ */
+ val = 0;
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, gpsz);
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ENTRY_SIZE, esz);
+
+ /* How many entries per GIC page? */
+ esz++;
+ epp = psz / (esz * SZ_8);
+
+ /*
+ * If we need more than just a single L1 page, flag the table
+ * as indirect and compute the number of required L1 pages.
+ */
+ if (epp < ITS_MAX_VPEID) {
+ int nl2;
+
+ val |= GICR_VPROPBASER_4_1_INDIRECT;
+
+ /* Number of L2 pages required to cover the VPEID space */
+ nl2 = DIV_ROUND_UP(ITS_MAX_VPEID, epp);
+
+ /* Number of L1 pages to point to the L2 pages */
+ npg = DIV_ROUND_UP(nl2 * SZ_8, psz);
+ } else {
+ npg = 1;
+ }
+
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg - 1);
+
+ /* Right, that's the number of CPU pages we need for L1 */
+ np = DIV_ROUND_UP(npg * psz, PAGE_SIZE);
+
+ pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
+ np, npg, psz, epp, esz);
+ page = alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
+ if (!page)
+ return -ENOMEM;
+
+ gic_data_rdist()->vpe_l1_base = page_address(page);
+ pa = virt_to_phys(page_address(page));
+ WARN_ON(!IS_ALIGNED(pa, psz));
+
+ val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
+ val |= GICR_VPROPBASER_RaWb;
+ val |= GICR_VPROPBASER_InnerShareable;
+ val |= GICR_VPROPBASER_4_1_Z;
+ val |= GICR_VPROPBASER_4_1_VALID;
+
+out:
+ gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask);
+
+ pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n",
+ smp_processor_id(), val,
+ cpumask_pr_args(gic_data_rdist()->vpe_table_mask));
return 0;
}
@@ -1978,14 +2976,13 @@
static struct page *its_allocate_pending_table(gfp_t gfp_flags)
{
struct page *pend_page;
- /*
- * The pending pages have to be at least 64kB aligned,
- * hence the 'max(LPI_PENDBASE_SZ, SZ_64K)' below.
- */
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
gfp_flags |= GFP_DMA32;
pend_page = alloc_pages(gfp_flags | __GFP_ZERO,
- get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)));
+ get_order(LPI_PENDBASE_SZ));
if (!pend_page)
return NULL;
@@ -1997,38 +2994,42 @@
static void its_free_pending_table(struct page *pt)
{
- free_pages((unsigned long)page_address(pt),
- get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)));
+ free_pages((unsigned long)page_address(pt), get_order(LPI_PENDBASE_SZ));
}
-static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
+/*
+ * Booting with kdump and LPIs enabled is generally fine. Any other
+ * case is wrong in the absence of firmware/EFI support.
+ */
+static bool enabled_lpis_allowed(void)
{
- u32 count = 1000000; /* 1s! */
- bool clean;
+ phys_addr_t addr;
u64 val;
- val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
- val &= ~GICR_VPENDBASER_Valid;
- gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+ /* Check whether the property table is in a reserved region */
+ val = gicr_read_propbaser(gic_data_rdist_rd_base() + GICR_PROPBASER);
+ addr = val & GENMASK_ULL(51, 12);
- do {
- val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
- clean = !(val & GICR_VPENDBASER_Dirty);
- if (!clean) {
- count--;
- cpu_relax();
- udelay(1);
- }
- } while (!clean && count);
-
- return val;
+ return gic_check_reserved_range(addr, LPI_PROPBASE_SZ);
}
static int __init allocate_lpi_tables(void)
{
+ u64 val;
int err, cpu;
- err = its_alloc_lpi_prop_table();
+ /*
+ * If LPIs are enabled while we run this from the boot CPU,
+ * flag the RD tables as pre-allocated if the stars do align.
+ */
+ val = readl_relaxed(gic_data_rdist_rd_base() + GICR_CTLR);
+ if ((val & GICR_CTLR_ENABLE_LPIS) && enabled_lpis_allowed()) {
+ gic_rdists->flags |= (RDIST_FLAGS_RD_TABLES_PREALLOCATED |
+ RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING);
+ pr_info("GICv3: Using preallocated redistributor tables\n");
+ }
+
+ err = its_setup_lpi_prop_table();
if (err)
return err;
@@ -2052,6 +3053,46 @@
return 0;
}
+static u64 read_vpend_dirty_clear(void __iomem *vlpi_base)
+{
+ u32 count = 1000000; /* 1s! */
+ bool clean;
+ u64 val;
+
+ do {
+ val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+ clean = !(val & GICR_VPENDBASER_Dirty);
+ if (!clean) {
+ count--;
+ cpu_relax();
+ udelay(1);
+ }
+ } while (!clean && count);
+
+ if (unlikely(!clean))
+ pr_err_ratelimited("ITS virtual pending table not cleaning\n");
+
+ return val;
+}
+
+static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
+{
+ u64 val;
+
+ /* Make sure we wait until the RD is done with the initial scan */
+ val = read_vpend_dirty_clear(vlpi_base);
+ val &= ~GICR_VPENDBASER_Valid;
+ val &= ~clr;
+ val |= set;
+ gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+ val = read_vpend_dirty_clear(vlpi_base);
+ if (unlikely(val & GICR_VPENDBASER_Dirty))
+ val |= GICR_VPENDBASER_PendingLast;
+
+ return val;
+}
+
static void its_cpu_init_lpis(void)
{
void __iomem *rbase = gic_data_rdist_rd_base();
@@ -2062,11 +3103,34 @@
if (gic_data_rdist()->lpi_enabled)
return;
+ val = readl_relaxed(rbase + GICR_CTLR);
+ if ((gic_rdists->flags & RDIST_FLAGS_RD_TABLES_PREALLOCATED) &&
+ (val & GICR_CTLR_ENABLE_LPIS)) {
+ /*
+ * Check that we get the same property table on all
+ * RDs. If we don't, this is hopeless.
+ */
+ paddr = gicr_read_propbaser(rbase + GICR_PROPBASER);
+ paddr &= GENMASK_ULL(51, 12);
+ if (WARN_ON(gic_rdists->prop_table_pa != paddr))
+ add_taint(TAINT_CRAP, LOCKDEP_STILL_OK);
+
+ paddr = gicr_read_pendbaser(rbase + GICR_PENDBASER);
+ paddr &= GENMASK_ULL(51, 16);
+
+ WARN_ON(!gic_check_reserved_range(paddr, LPI_PENDBASE_SZ));
+ its_free_pending_table(gic_data_rdist()->pend_page);
+ gic_data_rdist()->pend_page = NULL;
+
+ goto out;
+ }
+
pend_page = gic_data_rdist()->pend_page;
paddr = page_to_phys(pend_page);
+ WARN_ON(gic_reserve_range(paddr, LPI_PENDBASE_SZ));
/* set PROPBASE */
- val = (page_to_phys(gic_rdists->prop_page) |
+ val = (gic_rdists->prop_table_pa |
GICR_PROPBASER_InnerShareable |
GICR_PROPBASER_RaWaWb |
((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK));
@@ -2074,7 +3138,11 @@
gicr_write_propbaser(val, rbase + GICR_PROPBASER);
tmp = gicr_read_propbaser(rbase + GICR_PROPBASER);
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (IS_ENABLED(CONFIG_NO_GKI) &&
+ (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566") ||
+ of_machine_is_compatible("rockchip,rk3588")))
tmp &= ~GICR_PROPBASER_SHAREABILITY_MASK;
if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) {
@@ -2101,7 +3169,11 @@
gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (IS_ENABLED(CONFIG_NO_GKI) &&
+ (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566") ||
+ of_machine_is_compatible("rockchip,rk3588")))
tmp &= ~GICR_PENDBASER_SHAREABILITY_MASK;
if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) {
@@ -2120,12 +3192,12 @@
val |= GICR_CTLR_ENABLE_LPIS;
writel_relaxed(val, rbase + GICR_CTLR);
- if (gic_rdists->has_vlpis) {
+ if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
/*
* It's possible for CPU to receive VLPIs before it is
- * sheduled as a vPE, especially for the first CPU, and the
+ * scheduled as a vPE, especially for the first CPU, and the
* VLPI with INTID larger than 2^(IDbits+1) will be considered
* as out of range and dropped by GIC.
* So we initialize IDbits to known value to avoid VLPI drop.
@@ -2133,22 +3205,33 @@
val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n",
smp_processor_id(), val);
- gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
/*
* Also clear Valid bit of GICR_VPENDBASER, in case some
* ancient programming gets left in and has possibility of
* corrupting memory.
*/
- val = its_clear_vpend_valid(vlpi_base);
- WARN_ON(val & GICR_VPENDBASER_Dirty);
+ val = its_clear_vpend_valid(vlpi_base, 0, 0);
+ }
+
+ if (allocate_vpe_l1_table()) {
+ /*
+ * If the allocation has failed, we're in massive trouble.
+ * Disable direct injection, and pray that no VM was
+ * already running...
+ */
+ gic_rdists->has_rvpeid = false;
+ gic_rdists->has_vlpis = false;
}
/* Make sure the GIC has seen the above */
dsb(sy);
+out:
gic_data_rdist()->lpi_enabled = true;
- pr_info("GICv3: CPU%d: using LPI pending table @%pa\n",
+ pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n",
smp_processor_id(),
+ gic_data_rdist()->pend_page ? "allocated" : "reserved",
&paddr);
}
@@ -2234,7 +3317,8 @@
return NULL;
}
-static bool its_alloc_table_entry(struct its_baser *baser, u32 id)
+static bool its_alloc_table_entry(struct its_node *its,
+ struct its_baser *baser, u32 id)
{
struct page *page;
u32 esz, idx;
@@ -2256,9 +3340,12 @@
if (!table[idx]) {
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO;
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
gfp_flags |= GFP_DMA32;
- page = alloc_pages(gfp_flags, get_order(baser->psz));
+ page = alloc_pages_node(its->numa_node, gfp_flags,
+ get_order(baser->psz));
if (!page)
return false;
@@ -2287,14 +3374,15 @@
/* Don't allow device id that exceeds ITS hardware limit */
if (!baser)
- return (ilog2(dev_id) < its->device_ids);
+ return (ilog2(dev_id) < device_ids(its));
- return its_alloc_table_entry(baser, dev_id);
+ return its_alloc_table_entry(its, baser, dev_id);
}
static bool its_alloc_vpe_table(u32 vpe_id)
{
struct its_node *its;
+ int cpu;
/*
* Make sure the L2 tables are allocated on *all* v4 ITSs. We
@@ -2306,14 +3394,27 @@
list_for_each_entry(its, &its_nodes, entry) {
struct its_baser *baser;
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
baser = its_get_baser(its, GITS_BASER_TYPE_VCPU);
if (!baser)
return false;
- if (!its_alloc_table_entry(baser, vpe_id))
+ if (!its_alloc_table_entry(its, baser, vpe_id))
+ return false;
+ }
+
+ /* Non v4.1? No need to iterate RDs and go back early. */
+ if (!gic_rdists->has_rvpeid)
+ return true;
+
+ /*
+ * Make sure the L2 tables are allocated for all copies of
+ * the L1 table on *all* v4.1 RDs.
+ */
+ for_each_possible_cpu(cpu) {
+ if (!allocate_vpe_l2_table(cpu, vpe_id))
return false;
}
@@ -2346,12 +3447,18 @@
* sized as a power of two (and you need at least one bit...).
*/
nr_ites = max(2, nvecs);
- sz = nr_ites * its->ite_size;
+ sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
gfp_flags = GFP_KERNEL;
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566")) {
gfp_flags |= GFP_DMA32;
- itt = (void *)__get_free_pages(gfp_flags, get_order(sz));
+ itt = (void *)__get_free_pages(gfp_flags, get_order(sz));
+ } else {
+ itt = kzalloc_node(sz, gfp_flags, its->numa_node);
+ }
+
if (alloc_lpis) {
lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
if (lpi_map)
@@ -2365,7 +3472,14 @@
if (!dev || !itt || !col_map || (!lpi_map && alloc_lpis)) {
kfree(dev);
- free_pages((unsigned long)itt, get_order(sz));
+
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
+ free_pages((unsigned long)itt, get_order(sz));
+ else
+ kfree(itt);
+
kfree(lpi_map);
kfree(col_map);
return NULL;
@@ -2381,7 +3495,7 @@
dev->event_map.col_map = col_map;
dev->event_map.lpi_base = lpi_base;
dev->event_map.nr_lpis = nr_lpis;
- mutex_init(&dev->event_map.vlpi_lock);
+ raw_spin_lock_init(&dev->event_map.vlpi_lock);
dev->device_id = dev_id;
INIT_LIST_HEAD(&dev->entry);
@@ -2402,7 +3516,15 @@
raw_spin_lock_irqsave(&its_dev->its->lock, flags);
list_del(&its_dev->entry);
raw_spin_unlock_irqrestore(&its_dev->its->lock, flags);
- free_pages((unsigned long)its_dev->itt, get_order(its_dev->itt_sz));
+ kfree(its_dev->event_map.col_map);
+
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
+ free_pages((unsigned long)its_dev->itt, get_order(its_dev->itt_sz));
+ else
+ kfree(its_dev->itt);
+
kfree(its_dev);
}
@@ -2410,6 +3532,7 @@
{
int idx;
+ /* Find a free LPI region in lpi_map and allocate them. */
idx = bitmap_find_free_region(dev->event_map.lpi_map,
dev->event_map.nr_lpis,
get_count_order(nvecs));
@@ -2417,7 +3540,6 @@
return -ENOSPC;
*hwirq = dev->event_map.lpi_base + idx;
- set_bit(idx, dev->event_map.lpi_map);
return 0;
}
@@ -2432,7 +3554,7 @@
int err = 0;
/*
- * We ignore "dev" entierely, and rely on the dev_id that has
+ * We ignore "dev" entirely, and rely on the dev_id that has
* been passed via the scratchpad. This limits this domain's
* usefulness to upper layers that definitely know that they
* are built on top of the ITS.
@@ -2511,12 +3633,17 @@
{
msi_alloc_info_t *info = args;
struct its_device *its_dev = info->scratchpad[0].ptr;
+ struct its_node *its = its_dev->its;
struct irq_data *irqd;
irq_hw_number_t hwirq;
int err;
int i;
err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq);
+ if (err)
+ return err;
+
+ err = iommu_dma_prepare_msi(info->desc, its->get_msi_base(its_dev));
if (err)
return err;
@@ -2543,22 +3670,13 @@
{
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
u32 event = its_get_event_id(d);
- const struct cpumask *cpu_mask = cpu_online_mask;
int cpu;
- /* get the cpu_mask of local node */
- if (its_dev->its->numa_node >= 0)
- cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+ cpu = its_select_cpu(d, cpu_online_mask);
+ if (cpu < 0 || cpu >= nr_cpu_ids)
+ return -EINVAL;
- /* Bind the LPI to the first possible CPU */
- cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
- if (cpu >= nr_cpu_ids) {
- if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
- return -EINVAL;
-
- cpu = cpumask_first(cpu_online_mask);
- }
-
+ its_inc_lpi_count(d, cpu);
its_dev->event_map.col_map[event] = cpu;
irq_data_update_effective_affinity(d, cpumask_of(cpu));
@@ -2573,6 +3691,7 @@
struct its_device *its_dev = irq_data_get_irq_chip_data(d);
u32 event = its_get_event_id(d);
+ its_dec_lpi_count(d, its_dev->event_map.col_map[event]);
/* Stop the delivery of interrupts */
its_send_discard(its_dev, event);
}
@@ -2600,7 +3719,7 @@
/*
* If all interrupts have been freed, start mopping the
- * floor. This is conditionned on the device not being shared.
+ * floor. This is conditioned on the device not being shared.
*/
if (!its_dev->shared &&
bitmap_empty(its_dev->event_map.lpi_map,
@@ -2608,7 +3727,6 @@
its_lpi_free(its_dev->event_map.lpi_map,
its_dev->event_map.lpi_base,
its_dev->event_map.nr_lpis);
- kfree(its_dev->event_map.col_map);
/* Unmap device/itt */
its_send_mapd(its_dev, 0);
@@ -2630,7 +3748,7 @@
/*
* This is insane.
*
- * If a GICv4 doesn't implement Direct LPIs (which is extremely
+ * If a GICv4.0 doesn't implement Direct LPIs (which is extremely
* likely), the only way to perform an invalidate is to use a fake
* device to issue an INV command, implying that the LPI has first
* been mapped to some event on that device. Since this is not exactly
@@ -2638,9 +3756,20 @@
* only issue an UNMAP if we're short on available slots.
*
* Broken by design(tm).
+ *
+ * GICv4.1, on the other hand, mandates that we're able to invalidate
+ * by writing to a MMIO register. It doesn't implement the whole of
+ * DirectLPI, but that's good enough. And most of the time, we don't
+ * even have to invalidate anything, as the redistributor can be told
+ * whether to generate a doorbell or not (we thus leave it enabled,
+ * always).
*/
static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
{
+ /* GICv4.1 doesn't use a proxy, so nothing to do here */
+ if (gic_rdists->has_rvpeid)
+ return;
+
/* Already unmapped? */
if (vpe->vpe_proxy_event == -1)
return;
@@ -2663,6 +3792,10 @@
static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
{
+ /* GICv4.1 doesn't use a proxy, so nothing to do here */
+ if (gic_rdists->has_rvpeid)
+ return;
+
if (!gic_rdists->has_direct_lpi) {
unsigned long flags;
@@ -2674,6 +3807,10 @@
static void its_vpe_db_proxy_map_locked(struct its_vpe *vpe)
{
+ /* GICv4.1 doesn't use a proxy, so nothing to do here */
+ if (gic_rdists->has_rvpeid)
+ return;
+
/* Already mapped? */
if (vpe->vpe_proxy_event != -1)
return;
@@ -2696,13 +3833,16 @@
unsigned long flags;
struct its_collection *target_col;
+ /* GICv4.1 doesn't use a proxy, so nothing to do here */
+ if (gic_rdists->has_rvpeid)
+ return;
+
if (gic_rdists->has_direct_lpi) {
void __iomem *rdbase;
rdbase = per_cpu_ptr(gic_rdists->rdist, from)->rd_base;
gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
- while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
- cpu_relax();
+ wait_for_syncr(rdbase);
return;
}
@@ -2723,25 +3863,58 @@
bool force)
{
struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
- int cpu = cpumask_first(mask_val);
+ int from, cpu = cpumask_first(mask_val);
+ unsigned long flags;
/*
* Changing affinity is mega expensive, so let's be as lazy as
* we can and only do it if we really have to. Also, if mapped
* into the proxy device, we need to move the doorbell
* interrupt to its new location.
+ *
+ * Another thing is that changing the affinity of a vPE affects
+ * *other interrupts* such as all the vLPIs that are routed to
+ * this vPE. This means that the irq_desc lock is not enough to
+ * protect us, and that we must ensure nobody samples vpe->col_idx
+ * during the update, hence the lock below which must also be
+ * taken on any vLPI handling path that evaluates vpe->col_idx.
*/
- if (vpe->col_idx != cpu) {
- int from = vpe->col_idx;
+ from = vpe_to_cpuid_lock(vpe, &flags);
+ if (from == cpu)
+ goto out;
- vpe->col_idx = cpu;
- its_send_vmovp(vpe);
- its_vpe_db_proxy_move(vpe, from, cpu);
- }
+ vpe->col_idx = cpu;
+ /*
+ * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
+ * is sharing its VPE table with the current one.
+ */
+ if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
+ cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+ goto out;
+
+ its_send_vmovp(vpe);
+ its_vpe_db_proxy_move(vpe, from, cpu);
+
+out:
irq_data_update_effective_affinity(d, cpumask_of(cpu));
+ vpe_to_cpuid_unlock(vpe, flags);
return IRQ_SET_MASK_OK_DONE;
+}
+
+static void its_wait_vpt_parse_complete(void)
+{
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+ u64 val;
+
+ if (!gic_rdists->has_vpend_valid_dirty)
+ return;
+
+ WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER,
+ val,
+ !(val & GICR_VPENDBASER_Dirty),
+ 10, 500));
}
static void its_vpe_schedule(struct its_vpe *vpe)
@@ -2755,12 +3928,12 @@
val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
val |= GICR_VPROPBASER_RaWb;
val |= GICR_VPROPBASER_InnerShareable;
- gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+ gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
val = virt_to_phys(page_address(vpe->vpt_page)) &
GENMASK_ULL(51, 16);
val |= GICR_VPENDBASER_RaWaWb;
- val |= GICR_VPENDBASER_NonShareable;
+ val |= GICR_VPENDBASER_InnerShareable;
/*
* There is no good way of finding out if the pending table is
* empty as we can race against the doorbell interrupt very
@@ -2773,7 +3946,7 @@
val |= GICR_VPENDBASER_PendingLast;
val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
val |= GICR_VPENDBASER_Valid;
- gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+ gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
}
static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -2781,16 +3954,10 @@
void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
u64 val;
- val = its_clear_vpend_valid(vlpi_base);
+ val = its_clear_vpend_valid(vlpi_base, 0, 0);
- if (unlikely(val & GICR_VPENDBASER_Dirty)) {
- pr_err_ratelimited("ITS virtual pending table not cleaning\n");
- vpe->idai = false;
- vpe->pending_last = true;
- } else {
- vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
- vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
- }
+ vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
+ vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
}
static void its_vpe_invall(struct its_vpe *vpe)
@@ -2798,7 +3965,7 @@
struct its_node *its;
list_for_each_entry(its, &its_nodes, entry) {
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr])
@@ -2827,6 +3994,10 @@
its_vpe_deschedule(vpe);
return 0;
+ case COMMIT_VPE:
+ its_wait_vpt_parse_complete();
+ return 0;
+
case INVALL_VPE:
its_vpe_invall(vpe);
return 0;
@@ -2853,16 +4024,10 @@
{
struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
- if (gic_rdists->has_direct_lpi) {
- void __iomem *rdbase;
-
- rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
- gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_INVLPIR);
- while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
- cpu_relax();
- } else {
+ if (gic_rdists->has_direct_lpi)
+ __direct_lpi_inv(d, d->parent_data->hwirq);
+ else
its_vpe_send_cmd(vpe, its_send_inv);
- }
}
static void its_vpe_mask_irq(struct irq_data *d)
@@ -2901,8 +4066,7 @@
gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_SETLPIR);
} else {
gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
- while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
- cpu_relax();
+ wait_for_syncr(rdbase);
}
} else {
if (state)
@@ -2928,6 +4092,375 @@
.irq_retrigger = its_vpe_retrigger,
.irq_set_irqchip_state = its_vpe_set_irqchip_state,
.irq_set_vcpu_affinity = its_vpe_set_vcpu_affinity,
+};
+
+static struct its_node *find_4_1_its(void)
+{
+ static struct its_node *its = NULL;
+
+ if (!its) {
+ list_for_each_entry(its, &its_nodes, entry) {
+ if (is_v4_1(its))
+ return its;
+ }
+
+ /* Oops? */
+ its = NULL;
+ }
+
+ return its;
+}
+
+static void its_vpe_4_1_send_inv(struct irq_data *d)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ struct its_node *its;
+
+ /*
+ * GICv4.1 wants doorbells to be invalidated using the
+ * INVDB command in order to be broadcast to all RDs. Send
+ * it to the first valid ITS, and let the HW do its magic.
+ */
+ its = find_4_1_its();
+ if (its)
+ its_send_invdb(its, vpe);
+}
+
+static void its_vpe_4_1_mask_irq(struct irq_data *d)
+{
+ lpi_write_config(d->parent_data, LPI_PROP_ENABLED, 0);
+ its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_unmask_irq(struct irq_data *d)
+{
+ lpi_write_config(d->parent_data, 0, LPI_PROP_ENABLED);
+ its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_schedule(struct its_vpe *vpe,
+ struct its_cmd_info *info)
+{
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+ u64 val = 0;
+
+ /* Schedule the VPE */
+ val |= GICR_VPENDBASER_Valid;
+ val |= info->g0en ? GICR_VPENDBASER_4_1_VGRP0EN : 0;
+ val |= info->g1en ? GICR_VPENDBASER_4_1_VGRP1EN : 0;
+ val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
+
+ gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+}
+
+static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
+ struct its_cmd_info *info)
+{
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+ u64 val;
+
+ if (info->req_db) {
+ unsigned long flags;
+
+ /*
+ * vPE is going to block: make the vPE non-resident with
+ * PendingLast clear and DB set. The GIC guarantees that if
+ * we read-back PendingLast clear, then a doorbell will be
+ * delivered when an interrupt comes.
+ *
+ * Note the locking to deal with the concurrent update of
+ * pending_last from the doorbell interrupt handler that can
+ * run concurrently.
+ */
+ raw_spin_lock_irqsave(&vpe->vpe_lock, flags);
+ val = its_clear_vpend_valid(vlpi_base,
+ GICR_VPENDBASER_PendingLast,
+ GICR_VPENDBASER_4_1_DB);
+ vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+ raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
+ } else {
+ /*
+ * We're not blocking, so just make the vPE non-resident
+ * with PendingLast set, indicating that we'll be back.
+ */
+ val = its_clear_vpend_valid(vlpi_base,
+ 0,
+ GICR_VPENDBASER_PendingLast);
+ vpe->pending_last = true;
+ }
+}
+
+static void its_vpe_4_1_invall(struct its_vpe *vpe)
+{
+ void __iomem *rdbase;
+ unsigned long flags;
+ u64 val;
+ int cpu;
+
+ val = GICR_INVALLR_V;
+ val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
+
+ /* Target the redistributor this vPE is currently known on */
+ cpu = vpe_to_cpuid_lock(vpe, &flags);
+ raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+ rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+ gic_write_lpir(val, rdbase + GICR_INVALLR);
+
+ wait_for_syncr(rdbase);
+ raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+ vpe_to_cpuid_unlock(vpe, flags);
+}
+
+static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ struct its_cmd_info *info = vcpu_info;
+
+ switch (info->cmd_type) {
+ case SCHEDULE_VPE:
+ its_vpe_4_1_schedule(vpe, info);
+ return 0;
+
+ case DESCHEDULE_VPE:
+ its_vpe_4_1_deschedule(vpe, info);
+ return 0;
+
+ case COMMIT_VPE:
+ its_wait_vpt_parse_complete();
+ return 0;
+
+ case INVALL_VPE:
+ its_vpe_4_1_invall(vpe);
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static struct irq_chip its_vpe_4_1_irq_chip = {
+ .name = "GICv4.1-vpe",
+ .irq_mask = its_vpe_4_1_mask_irq,
+ .irq_unmask = its_vpe_4_1_unmask_irq,
+ .irq_eoi = irq_chip_eoi_parent,
+ .irq_set_affinity = its_vpe_set_affinity,
+ .irq_set_vcpu_affinity = its_vpe_4_1_set_vcpu_affinity,
+};
+
+static void its_configure_sgi(struct irq_data *d, bool clear)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ struct its_cmd_desc desc;
+
+ desc.its_vsgi_cmd.vpe = vpe;
+ desc.its_vsgi_cmd.sgi = d->hwirq;
+ desc.its_vsgi_cmd.priority = vpe->sgi_config[d->hwirq].priority;
+ desc.its_vsgi_cmd.enable = vpe->sgi_config[d->hwirq].enabled;
+ desc.its_vsgi_cmd.group = vpe->sgi_config[d->hwirq].group;
+ desc.its_vsgi_cmd.clear = clear;
+
+ /*
+ * GICv4.1 allows us to send VSGI commands to any ITS as long as the
+ * destination VPE is mapped there. Since we map them eagerly at
+ * activation time, we're pretty sure the first GICv4.1 ITS will do.
+ */
+ its_send_single_vcommand(find_4_1_its(), its_build_vsgi_cmd, &desc);
+}
+
+static void its_sgi_mask_irq(struct irq_data *d)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+ vpe->sgi_config[d->hwirq].enabled = false;
+ its_configure_sgi(d, false);
+}
+
+static void its_sgi_unmask_irq(struct irq_data *d)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+ vpe->sgi_config[d->hwirq].enabled = true;
+ its_configure_sgi(d, false);
+}
+
+static int its_sgi_set_affinity(struct irq_data *d,
+ const struct cpumask *mask_val,
+ bool force)
+{
+ /*
+ * There is no notion of affinity for virtual SGIs, at least
+ * not on the host (since they can only be targeting a vPE).
+ * Tell the kernel we've done whatever it asked for.
+ */
+ irq_data_update_effective_affinity(d, mask_val);
+ return IRQ_SET_MASK_OK;
+}
+
+static int its_sgi_set_irqchip_state(struct irq_data *d,
+ enum irqchip_irq_state which,
+ bool state)
+{
+ if (which != IRQCHIP_STATE_PENDING)
+ return -EINVAL;
+
+ if (state) {
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ struct its_node *its = find_4_1_its();
+ u64 val;
+
+ val = FIELD_PREP(GITS_SGIR_VPEID, vpe->vpe_id);
+ val |= FIELD_PREP(GITS_SGIR_VINTID, d->hwirq);
+ writeq_relaxed(val, its->sgir_base + GITS_SGIR - SZ_128K);
+ } else {
+ its_configure_sgi(d, true);
+ }
+
+ return 0;
+}
+
+static int its_sgi_get_irqchip_state(struct irq_data *d,
+ enum irqchip_irq_state which, bool *val)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ void __iomem *base;
+ unsigned long flags;
+ u32 count = 1000000; /* 1s! */
+ u32 status;
+ int cpu;
+
+ if (which != IRQCHIP_STATE_PENDING)
+ return -EINVAL;
+
+ /*
+ * Locking galore! We can race against two different events:
+ *
+ * - Concurrent vPE affinity change: we must make sure it cannot
+ * happen, or we'll talk to the wrong redistributor. This is
+ * identical to what happens with vLPIs.
+ *
+ * - Concurrent VSGIPENDR access: As it involves accessing two
+ * MMIO registers, this must be made atomic one way or another.
+ */
+ cpu = vpe_to_cpuid_lock(vpe, &flags);
+ raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+ base = gic_data_rdist_cpu(cpu)->rd_base + SZ_128K;
+ writel_relaxed(vpe->vpe_id, base + GICR_VSGIR);
+ do {
+ status = readl_relaxed(base + GICR_VSGIPENDR);
+ if (!(status & GICR_VSGIPENDR_BUSY))
+ goto out;
+
+ count--;
+ if (!count) {
+ pr_err_ratelimited("Unable to get SGI status\n");
+ goto out;
+ }
+ cpu_relax();
+ udelay(1);
+ } while (count);
+
+out:
+ raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+ vpe_to_cpuid_unlock(vpe, flags);
+
+ if (!count)
+ return -ENXIO;
+
+ *val = !!(status & (1 << d->hwirq));
+
+ return 0;
+}
+
+static int its_sgi_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+ struct its_cmd_info *info = vcpu_info;
+
+ switch (info->cmd_type) {
+ case PROP_UPDATE_VSGI:
+ vpe->sgi_config[d->hwirq].priority = info->priority;
+ vpe->sgi_config[d->hwirq].group = info->group;
+ its_configure_sgi(d, false);
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static struct irq_chip its_sgi_irq_chip = {
+ .name = "GICv4.1-sgi",
+ .irq_mask = its_sgi_mask_irq,
+ .irq_unmask = its_sgi_unmask_irq,
+ .irq_set_affinity = its_sgi_set_affinity,
+ .irq_set_irqchip_state = its_sgi_set_irqchip_state,
+ .irq_get_irqchip_state = its_sgi_get_irqchip_state,
+ .irq_set_vcpu_affinity = its_sgi_set_vcpu_affinity,
+};
+
+static int its_sgi_irq_domain_alloc(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs,
+ void *args)
+{
+ struct its_vpe *vpe = args;
+ int i;
+
+ /* Yes, we do want 16 SGIs */
+ WARN_ON(nr_irqs != 16);
+
+ for (i = 0; i < 16; i++) {
+ vpe->sgi_config[i].priority = 0;
+ vpe->sgi_config[i].enabled = false;
+ vpe->sgi_config[i].group = false;
+
+ irq_domain_set_hwirq_and_chip(domain, virq + i, i,
+ &its_sgi_irq_chip, vpe);
+ irq_set_status_flags(virq + i, IRQ_DISABLE_UNLAZY);
+ }
+
+ return 0;
+}
+
+static void its_sgi_irq_domain_free(struct irq_domain *domain,
+ unsigned int virq,
+ unsigned int nr_irqs)
+{
+ /* Nothing to do */
+}
+
+static int its_sgi_irq_domain_activate(struct irq_domain *domain,
+ struct irq_data *d, bool reserve)
+{
+ /* Write out the initial SGI configuration */
+ its_configure_sgi(d, false);
+ return 0;
+}
+
+static void its_sgi_irq_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *d)
+{
+ struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+ /*
+ * The VSGI command is awkward:
+ *
+ * - To change the configuration, CLEAR must be set to false,
+ * leaving the pending bit unchanged.
+ * - To clear the pending bit, CLEAR must be set to true, leaving
+ * the configuration unchanged.
+ *
+ * You just can't do both at once, hence the two commands below.
+ */
+ vpe->sgi_config[d->hwirq].enabled = false;
+ its_configure_sgi(d, false);
+ its_configure_sgi(d, true);
+}
+
+static const struct irq_domain_ops its_sgi_domain_ops = {
+ .alloc = its_sgi_irq_domain_alloc,
+ .free = its_sgi_irq_domain_free,
+ .activate = its_sgi_irq_domain_activate,
+ .deactivate = its_sgi_irq_domain_deactivate,
};
static int its_vpe_id_alloc(void)
@@ -2963,9 +4496,13 @@
return -ENOMEM;
}
+ raw_spin_lock_init(&vpe->vpe_lock);
vpe->vpe_id = vpe_id;
vpe->vpt_page = vpt_page;
- vpe->vpe_proxy_event = -1;
+ if (gic_rdists->has_rvpeid)
+ atomic_set(&vpe->vmapp_count, 0);
+ else
+ vpe->vpe_proxy_event = -1;
return 0;
}
@@ -3007,6 +4544,7 @@
static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *args)
{
+ struct irq_chip *irqchip = &its_vpe_irq_chip;
struct its_vm *vm = args;
unsigned long *bitmap;
struct page *vprop_page;
@@ -3034,6 +4572,9 @@
vm->nr_db_lpis = nr_ids;
vm->vprop_page = vprop_page;
+ if (gic_rdists->has_rvpeid)
+ irqchip = &its_vpe_4_1_irq_chip;
+
for (i = 0; i < nr_irqs; i++) {
vm->vpes[i]->vpe_db_lpi = base + i;
err = its_vpe_init(vm->vpes[i]);
@@ -3044,7 +4585,7 @@
if (err)
break;
irq_domain_set_hwirq_and_chip(domain, virq + i, i,
- &its_vpe_irq_chip, vm->vpes[i]);
+ irqchip, vm->vpes[i]);
set_bit(i, bitmap);
}
@@ -3065,15 +4606,19 @@
struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
struct its_node *its;
- /* If we use the list map, we issue VMAPP on demand... */
- if (its_list_map)
+ /*
+ * If we use the list map, we issue VMAPP on demand... Unless
+ * we're on a GICv4.1 and we eagerly map the VPE on all ITSs
+ * so that VSGIs can work.
+ */
+ if (!gic_requires_eager_mapping())
return 0;
/* Map the VPE to the first possible CPU */
vpe->col_idx = cpumask_first(cpu_online_mask);
list_for_each_entry(its, &its_nodes, entry) {
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
its_send_vmapp(its, vpe, true);
@@ -3092,14 +4637,14 @@
struct its_node *its;
/*
- * If we use the list map, we unmap the VPE once no VLPIs are
- * associated with the VM.
+ * If we use the list map on GICv4.0, we unmap the VPE once no
+ * VLPIs are associated with the VM.
*/
- if (its_list_map)
+ if (!gic_requires_eager_mapping())
return;
list_for_each_entry(its, &its_nodes, entry) {
- if (!its->is_v4)
+ if (!is_v4(its))
continue;
its_send_vmapp(its, vpe, false);
@@ -3150,8 +4695,9 @@
{
struct its_node *its = data;
- /* erratum 22375: only alloc 8MB table size */
- its->device_ids = 0x14; /* 20 bits, 8MB */
+ /* erratum 22375: only alloc 8MB table size (20 bits) */
+ its->typer &= ~GITS_TYPER_DEVBITS;
+ its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1);
its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
return true;
@@ -3171,7 +4717,8 @@
struct its_node *its = data;
/* On QDF2400, the size of the ITE is 16Bytes */
- its->ite_size = 16;
+ its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE;
+ its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1);
return true;
}
@@ -3205,8 +4752,10 @@
its->get_msi_base = its_irq_get_msi_base_pre_its;
ids = ilog2(pre_its_window[1]) - 2;
- if (its->device_ids > ids)
- its->device_ids = ids;
+ if (device_ids(its) > ids) {
+ its->typer &= ~GITS_TYPER_DEVBITS;
+ its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1);
+ }
/* the pre-ITS breaks isolation, so disable MSI remapping */
its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP;
@@ -3433,7 +4982,7 @@
}
/* Use the last possible DevID */
- devid = GENMASK(its->device_ids - 1, 0);
+ devid = GENMASK(device_ids(its) - 1, 0);
vpe_proxy.dev = its_create_device(its, devid, entries, false);
if (!vpe_proxy.dev) {
kfree(vpe_proxy.vpes);
@@ -3496,10 +5045,11 @@
void __iomem *its_base;
u32 val, ctlr;
u64 baser, tmp, typer;
+ struct page *page;
int err;
gfp_t gfp_flags;
- its_base = ioremap(res->start, resource_size(res));
+ its_base = ioremap(res->start, SZ_64K);
if (!its_base) {
pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start);
return -ENOMEM;
@@ -3531,12 +5081,10 @@
INIT_LIST_HEAD(&its->entry);
INIT_LIST_HEAD(&its->its_device_list);
typer = gic_read_typer(its_base + GITS_TYPER);
+ its->typer = typer;
its->base = its_base;
its->phys_base = res->start;
- its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer);
- its->device_ids = GITS_TYPER_DEVBITS(typer);
- its->is_v4 = !!(typer & GITS_TYPER_VLPIS);
- if (its->is_v4) {
+ if (is_v4(its)) {
if (!(typer & GITS_TYPER_VMOVP)) {
err = its_compute_its_list_map(res, its_base);
if (err < 0)
@@ -3549,19 +5097,37 @@
} else {
pr_info("ITS@%pa: Single VMOVP capable\n", &res->start);
}
+
+ if (is_v4_1(its)) {
+ u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer);
+
+ its->sgir_base = ioremap(res->start + SZ_128K, SZ_64K);
+ if (!its->sgir_base) {
+ err = -ENOMEM;
+ goto out_free_its;
+ }
+
+ its->mpidr = readl_relaxed(its_base + GITS_MPIDR);
+
+ pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n",
+ &res->start, its->mpidr, svpet);
+ }
}
its->numa_node = numa_node;
gfp_flags = GFP_KERNEL | __GFP_ZERO;
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566"))
gfp_flags |= GFP_DMA32;
- its->cmd_base = (void *)__get_free_pages(gfp_flags,
- get_order(ITS_CMD_QUEUE_SZ));
- if (!its->cmd_base) {
+ page = alloc_pages_node(its->numa_node, gfp_flags,
+ get_order(ITS_CMD_QUEUE_SZ));
+ if (!page) {
err = -ENOMEM;
- goto out_free_its;
+ goto out_unmap_sgir;
}
+ its->cmd_base = (void *)page_address(page);
its->cmd_write = its->cmd_base;
its->fwnode_handle = handle;
its->get_msi_base = its_irq_get_msi_base;
@@ -3586,7 +5152,11 @@
gits_write_cbaser(baser, its->base + GITS_CBASER);
tmp = gits_read_cbaser(its->base + GITS_CBASER);
- if (of_machine_is_compatible("rockchip,rk3568") || of_machine_is_compatible("rockchip,rk3566"))
+ if (IS_ENABLED(CONFIG_NO_GKI) &&
+ (of_machine_is_compatible("rockchip,rk3568") ||
+ of_machine_is_compatible("rockchip,rk3567") ||
+ of_machine_is_compatible("rockchip,rk3566") ||
+ of_machine_is_compatible("rockchip,rk3588")))
tmp &= ~GITS_CBASER_SHAREABILITY_MASK;
if ((tmp ^ baser) & GITS_CBASER_SHAREABILITY_MASK) {
@@ -3608,7 +5178,7 @@
gits_write_cwriter(0, its->base + GITS_CWRITER);
ctlr = readl_relaxed(its->base + GITS_CTLR);
ctlr |= GITS_CTLR_ENABLE;
- if (its->is_v4)
+ if (is_v4(its))
ctlr |= GITS_CTLR_ImDe;
writel_relaxed(ctlr, its->base + GITS_CTLR);
@@ -3626,6 +5196,9 @@
its_free_tables(its);
out_free_cmd:
free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+out_unmap_sgir:
+ if (its->sgir_base)
+ iounmap(its->sgir_base);
out_free_its:
kfree(its);
out_unmap:
@@ -3658,8 +5231,11 @@
* If coming via a CPU hotplug event, we don't need to disable
* LPIs before trying to re-enable them. They are already
* configured and all is well in the world.
+ *
+ * If running with preallocated tables, there is nothing to do.
*/
- if (gic_data_rdist()->lpi_enabled)
+ if (gic_data_rdist()->lpi_enabled ||
+ (gic_rdists->flags & RDIST_FLAGS_RD_TABLES_PREALLOCATED))
return 0;
/*
@@ -3776,13 +5352,13 @@
return NUMA_NO_NODE;
}
-static int __init gic_acpi_match_srat_its(struct acpi_subtable_header *header,
+static int __init gic_acpi_match_srat_its(union acpi_subtable_headers *header,
const unsigned long end)
{
return 0;
}
-static int __init gic_acpi_parse_srat_its(struct acpi_subtable_header *header,
+static int __init gic_acpi_parse_srat_its(union acpi_subtable_headers *header,
const unsigned long end)
{
int node;
@@ -3798,7 +5374,12 @@
return -EINVAL;
}
- node = acpi_map_pxm_to_node(its_affinity->proximity_domain);
+ /*
+ * Note that in theory a new proximity node could be created by this
+ * entry as it is an SRAT resource allocation structure.
+ * We do not currently support doing so.
+ */
+ node = pxm_to_node(its_affinity->proximity_domain);
if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
pr_err("SRAT: Invalid NUMA node %d in ITS affinity\n", node);
@@ -3849,7 +5430,7 @@
static void __init acpi_its_srat_maps_free(void) { }
#endif
-static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header,
+static int __init gic_acpi_parse_madt_its(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_translator *its_entry;
@@ -3863,7 +5444,7 @@
res.end = its_entry->base_address + ACPI_GICV3_ITS_MEM_SIZE - 1;
res.flags = IORESOURCE_MEM;
- dom_handle = irq_domain_alloc_fwnode((void *)its_entry->base_address);
+ dom_handle = irq_domain_alloc_fwnode(&res.start);
if (!dom_handle) {
pr_err("ITS@%pa: Unable to allocate GICv3 ITS domain token\n",
&res.start);
@@ -3906,7 +5487,10 @@
struct device_node *of_node;
struct its_node *its;
bool has_v4 = false;
+ bool has_v4_1 = false;
int err;
+
+ gic_rdists = rdists;
its_parent = parent_domain;
of_node = to_of_node(handle);
@@ -3920,18 +5504,29 @@
return -ENXIO;
}
- gic_rdists = rdists;
-
err = allocate_lpi_tables();
if (err)
return err;
- list_for_each_entry(its, &its_nodes, entry)
- has_v4 |= its->is_v4;
+ list_for_each_entry(its, &its_nodes, entry) {
+ has_v4 |= is_v4(its);
+ has_v4_1 |= is_v4_1(its);
+ }
+
+ /* Don't bother with inconsistent systems */
+ if (WARN_ON(!has_v4_1 && rdists->has_rvpeid))
+ rdists->has_rvpeid = false;
if (has_v4 & rdists->has_vlpis) {
+ const struct irq_domain_ops *sgi_ops;
+
+ if (has_v4_1)
+ sgi_ops = &its_sgi_domain_ops;
+ else
+ sgi_ops = NULL;
+
if (its_init_vpe_domain() ||
- its_init_v4(parent_domain, &its_vpe_domain_ops)) {
+ its_init_v4(parent_domain, &its_vpe_domain_ops, sgi_ops)) {
rdists->has_vlpis = false;
pr_err("ITS: Disabling GICv4 support\n");
}
--
Gitblit v1.6.2