linux_dsm_epyc7002/drivers/irqchip/irq-gic.c

1536 lines
38 KiB
C
Raw Normal View History

/*
* Copyright (C) 2002 ARM Limited, All Rights Reserved.
*
* 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.
*
* Interrupt architecture for the GIC:
*
* o There is one Interrupt Distributor, which receives interrupts
* from system devices and sends them to the Interrupt Controllers.
*
* o There is one CPU Interface per CPU, which sends interrupts sent
* by the Distributor, and interrupts generated locally, to the
* associated CPU. The base address of the CPU interface is usually
* aliased so that the same address points to different chips depending
* on the CPU it is accessed from.
*
* Note that IRQs 0-31 are special - they are local to each CPU.
* As such, the enable set/clear, pending set/clear and active bit
* registers are banked per-cpu for these sources.
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/cpumask.h>
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/acpi.h>
#include <linux/irqdomain.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/irqchip.h>
#include <linux/irqchip/chained_irq.h>
#include <linux/irqchip/arm-gic.h>
#include <asm/cputype.h>
#include <asm/irq.h>
#include <asm/exception.h>
#include <asm/smp_plat.h>
#include <asm/virt.h>
#include "irq-gic-common.h"
#ifdef CONFIG_ARM64
#include <asm/cpufeature.h>
static void gic_check_cpu_features(void)
{
WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
TAINT_CPU_OUT_OF_SPEC,
"GICv3 system registers enabled, broken firmware!\n");
}
#else
#define gic_check_cpu_features() do { } while(0)
#endif
union gic_base {
void __iomem *common_base;
void __percpu * __iomem *percpu_base;
};
struct gic_chip_data {
struct irq_chip chip;
union gic_base dist_base;
union gic_base cpu_base;
void __iomem *raw_dist_base;
void __iomem *raw_cpu_base;
u32 percpu_offset;
#ifdef CONFIG_CPU_PM
u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
u32 saved_spi_active[DIV_ROUND_UP(1020, 32)];
u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
u32 __percpu *saved_ppi_enable;
u32 __percpu *saved_ppi_active;
u32 __percpu *saved_ppi_conf;
#endif
struct irq_domain *domain;
unsigned int gic_irqs;
#ifdef CONFIG_GIC_NON_BANKED
void __iomem *(*get_base)(union gic_base *);
#endif
};
static DEFINE_RAW_SPINLOCK(irq_controller_lock);
/*
* The GIC mapping of CPU interfaces does not necessarily match
* the logical CPU numbering. Let's use a mapping as returned
* by the GIC itself.
*/
#define NR_GIC_CPU_IF 8
static u8 gic_cpu_map[NR_GIC_CPU_IF] __read_mostly;
static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE;
static struct gic_chip_data gic_data[CONFIG_ARM_GIC_MAX_NR] __read_mostly;
static struct gic_kvm_info gic_v2_kvm_info;
#ifdef CONFIG_GIC_NON_BANKED
static void __iomem *gic_get_percpu_base(union gic_base *base)
{
return raw_cpu_read(*base->percpu_base);
}
static void __iomem *gic_get_common_base(union gic_base *base)
{
return base->common_base;
}
static inline void __iomem *gic_data_dist_base(struct gic_chip_data *data)
{
return data->get_base(&data->dist_base);
}
static inline void __iomem *gic_data_cpu_base(struct gic_chip_data *data)
{
return data->get_base(&data->cpu_base);
}
static inline void gic_set_base_accessor(struct gic_chip_data *data,
void __iomem *(*f)(union gic_base *))
{
data->get_base = f;
}
#else
#define gic_data_dist_base(d) ((d)->dist_base.common_base)
#define gic_data_cpu_base(d) ((d)->cpu_base.common_base)
#define gic_set_base_accessor(d, f)
#endif
static inline void __iomem *gic_dist_base(struct irq_data *d)
{
struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
return gic_data_dist_base(gic_data);
}
static inline void __iomem *gic_cpu_base(struct irq_data *d)
{
struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
return gic_data_cpu_base(gic_data);
}
static inline unsigned int gic_irq(struct irq_data *d)
{
return d->hwirq;
}
static inline bool cascading_gic_irq(struct irq_data *d)
{
void *data = irq_data_get_irq_handler_data(d);
/*
* If handler_data is set, this is a cascading interrupt, and
* it cannot possibly be forwarded.
*/
return data != NULL;
}
/*
* Routines to acknowledge, disable and enable interrupts
*/
static void gic_poke_irq(struct irq_data *d, u32 offset)
{
u32 mask = 1 << (gic_irq(d) % 32);
writel_relaxed(mask, gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4);
}
static int gic_peek_irq(struct irq_data *d, u32 offset)
{
u32 mask = 1 << (gic_irq(d) % 32);
return !!(readl_relaxed(gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4) & mask);
}
static void gic_mask_irq(struct irq_data *d)
{
gic_poke_irq(d, GIC_DIST_ENABLE_CLEAR);
}
static void gic_eoimode1_mask_irq(struct irq_data *d)
{
gic_mask_irq(d);
/*
* When masking a forwarded interrupt, make sure it is
* deactivated as well.
*
* This ensures that an interrupt that is getting
* disabled/masked will not get "stuck", because there is
* noone to deactivate it (guest is being terminated).
*/
if (irqd_is_forwarded_to_vcpu(d))
gic_poke_irq(d, GIC_DIST_ACTIVE_CLEAR);
}
static void gic_unmask_irq(struct irq_data *d)
{
gic_poke_irq(d, GIC_DIST_ENABLE_SET);
}
static void gic_eoi_irq(struct irq_data *d)
{
writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
}
static void gic_eoimode1_eoi_irq(struct irq_data *d)
{
/* Do not deactivate an IRQ forwarded to a vcpu. */
if (irqd_is_forwarded_to_vcpu(d))
return;
writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_DEACTIVATE);
}
static int gic_irq_set_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool val)
{
u32 reg;
switch (which) {
case IRQCHIP_STATE_PENDING:
reg = val ? GIC_DIST_PENDING_SET : GIC_DIST_PENDING_CLEAR;
break;
case IRQCHIP_STATE_ACTIVE:
reg = val ? GIC_DIST_ACTIVE_SET : GIC_DIST_ACTIVE_CLEAR;
break;
case IRQCHIP_STATE_MASKED:
reg = val ? GIC_DIST_ENABLE_CLEAR : GIC_DIST_ENABLE_SET;
break;
default:
return -EINVAL;
}
gic_poke_irq(d, reg);
return 0;
}
static int gic_irq_get_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool *val)
{
switch (which) {
case IRQCHIP_STATE_PENDING:
*val = gic_peek_irq(d, GIC_DIST_PENDING_SET);
break;
case IRQCHIP_STATE_ACTIVE:
*val = gic_peek_irq(d, GIC_DIST_ACTIVE_SET);
break;
case IRQCHIP_STATE_MASKED:
*val = !gic_peek_irq(d, GIC_DIST_ENABLE_SET);
break;
default:
return -EINVAL;
}
return 0;
}
static int gic_set_type(struct irq_data *d, unsigned int type)
{
void __iomem *base = gic_dist_base(d);
unsigned int gicirq = gic_irq(d);
/* Interrupt configuration for SGIs can't be changed */
if (gicirq < 16)
return -EINVAL;
/* SPIs have restrictions on the supported types */
if (gicirq >= 32 && type != IRQ_TYPE_LEVEL_HIGH &&
type != IRQ_TYPE_EDGE_RISING)
return -EINVAL;
return gic_configure_irq(gicirq, type, base, NULL);
}
static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
{
/* Only interrupts on the primary GIC can be forwarded to a vcpu. */
if (cascading_gic_irq(d))
return -EINVAL;
if (vcpu)
irqd_set_forwarded_to_vcpu(d);
else
irqd_clr_forwarded_to_vcpu(d);
return 0;
}
#ifdef CONFIG_SMP
static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
bool force)
{
void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
u32 val, mask, bit;
unsigned long flags;
if (!force)
cpu = cpumask_any_and(mask_val, cpu_online_mask);
else
cpu = cpumask_first(mask_val);
if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
return -EINVAL;
raw_spin_lock_irqsave(&irq_controller_lock, flags);
mask = 0xff << shift;
bit = gic_cpu_map[cpu] << shift;
val = readl_relaxed(reg) & ~mask;
writel_relaxed(val | bit, reg);
raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
return IRQ_SET_MASK_OK_DONE;
}
#endif
static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
u32 irqstat, irqnr;
struct gic_chip_data *gic = &gic_data[0];
void __iomem *cpu_base = gic_data_cpu_base(gic);
do {
irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
irqnr = irqstat & GICC_IAR_INT_ID_MASK;
if (likely(irqnr > 15 && irqnr < 1020)) {
if (static_key_true(&supports_deactivate))
writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
handle_domain_irq(gic->domain, irqnr, regs);
continue;
}
if (irqnr < 16) {
writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
if (static_key_true(&supports_deactivate))
writel_relaxed(irqstat, cpu_base + GIC_CPU_DEACTIVATE);
#ifdef CONFIG_SMP
irqchip/gic: Ensure ordering between read of INTACK and shared data When an IPI is generated by a CPU, the pattern looks roughly like: <write shared data> smp_wmb(); <write to GIC to signal SGI> On the receiving CPU we rely on the fact that, once we've taken the interrupt, then the freshly written shared data must be visible to us. Put another way, the CPU isn't going to speculate taking an interrupt. Unfortunately, this assumption turns out to be broken. Consider that CPUx wants to send an IPI to CPUy, which will cause CPUy to read some shared_data. Before CPUx has done anything, a random peripheral raises an IRQ to the GIC and the IRQ line on CPUy is raised. CPUy then takes the IRQ and starts executing the entry code, heading towards gic_handle_irq. Furthermore, let's assume that a bunch of the previous interrupts handled by CPUy were SGIs, so the branch predictor kicks in and speculates that irqnr will be <16 and we're likely to head into handle_IPI. The prefetcher then grabs a speculative copy of shared_data which contains a stale value. Meanwhile, CPUx gets round to updating shared_data and asking the GIC to send an SGI to CPUy. Internally, the GIC decides that the SGI is more important than the peripheral interrupt (which hasn't yet been ACKed) but doesn't need to do anything to CPUy, because the IRQ line is already raised. CPUy then reads the ACK register on the GIC, sees the SGI value which confirms the branch prediction and we end up with a stale shared_data value. This patch fixes the problem by adding an smp_rmb() to the IPI entry code in gic_handle_irq. As it turns out, the combination of a control dependency and an ISB instruction from the EOI in the GICv3 driver is enough to provide the ordering we need, so we add a comment there justifying the absence of an explicit smp_rmb(). Cc: stable@vger.kernel.org Signed-off-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2016-04-26 18:00:00 +07:00
/*
* Ensure any shared data written by the CPU sending
* the IPI is read after we've read the ACK register
* on the GIC.
*
* Pairs with the write barrier in gic_raise_softirq
*/
smp_rmb();
handle_IPI(irqnr, regs);
#endif
continue;
}
break;
} while (1);
}
static void gic_handle_cascade_irq(struct irq_desc *desc)
{
struct gic_chip_data *chip_data = irq_desc_get_handler_data(desc);
struct irq_chip *chip = irq_desc_get_chip(desc);
unsigned int cascade_irq, gic_irq;
unsigned long status;
chained_irq_enter(chip, desc);
raw_spin_lock(&irq_controller_lock);
status = readl_relaxed(gic_data_cpu_base(chip_data) + GIC_CPU_INTACK);
raw_spin_unlock(&irq_controller_lock);
gic_irq = (status & GICC_IAR_INT_ID_MASK);
if (gic_irq == GICC_INT_SPURIOUS)
goto out;
cascade_irq = irq_find_mapping(chip_data->domain, gic_irq);
if (unlikely(gic_irq < 32 || gic_irq > 1020))
handle_bad_irq(desc);
else
generic_handle_irq(cascade_irq);
out:
chained_irq_exit(chip, desc);
}
static struct irq_chip gic_chip = {
.irq_mask = gic_mask_irq,
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoi_irq,
.irq_set_type = gic_set_type,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
irqchip/gic: Enable SKIP_SET_WAKE and MASK_ON_SUSPEND The GIC controller doesn't provides any facility to configure the wakeup sources. For the same reason, GIC chip implementation can't provide irq_set_wake functionality, but that results in the irqchip core preventing the systems from entering sleep states like "suspend to RAM". The GICv1/v2 controllers support wakeup events. They signal these wakeup events even when CPU interface is disabled which means the wakeup outputs are always enabled with the required logic in always-on domain. An implementation can powerdown the GIC completely, but then the wake-up must be relayed to some control logic within the power controller that acts as wake-up interrupt controller. Setting the IRQCHIP_SKIP_SET_WAKE flags will ensure that the interrupts from GIC can work as wakeup interrupts and resume from suspend-to-{idle, ram}. The wakeup interrupt sources need to use enable_irq_wake() and the irqchip core will then set the IRQD_WAKEUP_STATE flag. Also it's always safer to mask all the non wakeup interrupts are masked at the chip level when suspending. The irqchip infrastructure can handle masking of those interrupts at the chip level. The chip implementation just have to indicate that with IRQCHIP_MASK_ON_SUSPEND. This patch enables IRQCHIP_SKIP_SET_WAKE and IRQCHIP_MASK_ON_SUSPEND so that the irqchip core allows and handles the power managemant wake up modes. Signed-off-by: Sudeep Holla <sudeep.holla@arm.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: Simon Horman <horms@verge.net.au> Cc: Jason Cooper <jason@lakedaemon.net> Cc: Michal Simek <michal.simek@xilinx.com> Cc: Linus Walleij <linus.walleij@linaro.org> Cc: Magnus Damm <magnus.damm@gmail.com> Cc: Gregory CLEMENT <gregory.clement@free-electrons.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1436971109-20189-1-git-send-email-sudeep.holla@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-07-15 21:38:28 +07:00
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
{
BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
irq_set_chained_handler_and_data(irq, gic_handle_cascade_irq,
&gic_data[gic_nr]);
}
static u8 gic_get_cpumask(struct gic_chip_data *gic)
{
void __iomem *base = gic_data_dist_base(gic);
u32 mask, i;
for (i = mask = 0; i < 32; i += 4) {
mask = readl_relaxed(base + GIC_DIST_TARGET + i);
mask |= mask >> 16;
mask |= mask >> 8;
if (mask)
break;
}
if (!mask && num_possible_cpus() > 1)
pr_crit("GIC CPU mask not found - kernel will fail to boot.\n");
return mask;
}
static void gic_cpu_if_up(struct gic_chip_data *gic)
{
void __iomem *cpu_base = gic_data_cpu_base(gic);
u32 bypass = 0;
u32 mode = 0;
if (gic == &gic_data[0] && static_key_true(&supports_deactivate))
mode = GIC_CPU_CTRL_EOImodeNS;
/*
* Preserve bypass disable bits to be written back later
*/
bypass = readl(cpu_base + GIC_CPU_CTRL);
bypass &= GICC_DIS_BYPASS_MASK;
writel_relaxed(bypass | mode | GICC_ENABLE, cpu_base + GIC_CPU_CTRL);
}
static void __init gic_dist_init(struct gic_chip_data *gic)
{
unsigned int i;
u32 cpumask;
unsigned int gic_irqs = gic->gic_irqs;
void __iomem *base = gic_data_dist_base(gic);
writel_relaxed(GICD_DISABLE, base + GIC_DIST_CTRL);
/*
* Set all global interrupts to this CPU only.
*/
cpumask = gic_get_cpumask(gic);
cpumask |= cpumask << 8;
cpumask |= cpumask << 16;
for (i = 32; i < gic_irqs; i += 4)
writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
gic_dist_config(base, gic_irqs, NULL);
writel_relaxed(GICD_ENABLE, base + GIC_DIST_CTRL);
}
static int gic_cpu_init(struct gic_chip_data *gic)
{
void __iomem *dist_base = gic_data_dist_base(gic);
void __iomem *base = gic_data_cpu_base(gic);
unsigned int cpu_mask, cpu = smp_processor_id();
int i;
/*
* Setting up the CPU map is only relevant for the primary GIC
* because any nested/secondary GICs do not directly interface
* with the CPU(s).
*/
if (gic == &gic_data[0]) {
/*
* Get what the GIC says our CPU mask is.
*/
if (WARN_ON(cpu >= NR_GIC_CPU_IF))
return -EINVAL;
gic_check_cpu_features();
cpu_mask = gic_get_cpumask(gic);
gic_cpu_map[cpu] = cpu_mask;
/*
* Clear our mask from the other map entries in case they're
* still undefined.
*/
for (i = 0; i < NR_GIC_CPU_IF; i++)
if (i != cpu)
gic_cpu_map[i] &= ~cpu_mask;
}
gic_cpu_config(dist_base, NULL);
writel_relaxed(GICC_INT_PRI_THRESHOLD, base + GIC_CPU_PRIMASK);
gic_cpu_if_up(gic);
return 0;
}
int gic_cpu_if_down(unsigned int gic_nr)
{
void __iomem *cpu_base;
u32 val = 0;
if (gic_nr >= CONFIG_ARM_GIC_MAX_NR)
return -EINVAL;
cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
val = readl(cpu_base + GIC_CPU_CTRL);
val &= ~GICC_ENABLE;
writel_relaxed(val, cpu_base + GIC_CPU_CTRL);
return 0;
}
#ifdef CONFIG_CPU_PM
/*
* Saves the GIC distributor registers during suspend or idle. Must be called
* with interrupts disabled but before powering down the GIC. After calling
* this function, no interrupts will be delivered by the GIC, and another
* platform-specific wakeup source must be enabled.
*/
static void gic_dist_save(struct gic_chip_data *gic)
{
unsigned int gic_irqs;
void __iomem *dist_base;
int i;
if (WARN_ON(!gic))
return;
gic_irqs = gic->gic_irqs;
dist_base = gic_data_dist_base(gic);
if (!dist_base)
return;
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
gic->saved_spi_conf[i] =
readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
gic->saved_spi_target[i] =
readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
gic->saved_spi_enable[i] =
readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
gic->saved_spi_active[i] =
readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
}
/*
* Restores the GIC distributor registers during resume or when coming out of
* idle. Must be called before enabling interrupts. If a level interrupt
* that occured while the GIC was suspended is still present, it will be
* handled normally, but any edge interrupts that occured will not be seen by
* the GIC and need to be handled by the platform-specific wakeup source.
*/
static void gic_dist_restore(struct gic_chip_data *gic)
{
unsigned int gic_irqs;
unsigned int i;
void __iomem *dist_base;
if (WARN_ON(!gic))
return;
gic_irqs = gic->gic_irqs;
dist_base = gic_data_dist_base(gic);
if (!dist_base)
return;
writel_relaxed(GICD_DISABLE, dist_base + GIC_DIST_CTRL);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
writel_relaxed(gic->saved_spi_conf[i],
dist_base + GIC_DIST_CONFIG + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
writel_relaxed(GICD_INT_DEF_PRI_X4,
dist_base + GIC_DIST_PRI + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
writel_relaxed(gic->saved_spi_target[i],
dist_base + GIC_DIST_TARGET + i * 4);
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
writel_relaxed(GICD_INT_EN_CLR_X32,
dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
writel_relaxed(gic->saved_spi_enable[i],
dist_base + GIC_DIST_ENABLE_SET + i * 4);
}
for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
writel_relaxed(GICD_INT_EN_CLR_X32,
dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
writel_relaxed(gic->saved_spi_active[i],
dist_base + GIC_DIST_ACTIVE_SET + i * 4);
}
writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
}
static void gic_cpu_save(struct gic_chip_data *gic)
{
int i;
u32 *ptr;
void __iomem *dist_base;
void __iomem *cpu_base;
if (WARN_ON(!gic))
return;
dist_base = gic_data_dist_base(gic);
cpu_base = gic_data_cpu_base(gic);
if (!dist_base || !cpu_base)
return;
ptr = raw_cpu_ptr(gic->saved_ppi_enable);
for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
ptr = raw_cpu_ptr(gic->saved_ppi_active);
for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
ptr[i] = readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
ptr = raw_cpu_ptr(gic->saved_ppi_conf);
for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
}
static void gic_cpu_restore(struct gic_chip_data *gic)
{
int i;
u32 *ptr;
void __iomem *dist_base;
void __iomem *cpu_base;
if (WARN_ON(!gic))
return;
dist_base = gic_data_dist_base(gic);
cpu_base = gic_data_cpu_base(gic);
if (!dist_base || !cpu_base)
return;
ptr = raw_cpu_ptr(gic->saved_ppi_enable);
for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
writel_relaxed(GICD_INT_EN_CLR_X32,
dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
}
ptr = raw_cpu_ptr(gic->saved_ppi_active);
for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
writel_relaxed(GICD_INT_EN_CLR_X32,
dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
writel_relaxed(ptr[i], dist_base + GIC_DIST_ACTIVE_SET + i * 4);
}
ptr = raw_cpu_ptr(gic->saved_ppi_conf);
for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
writel_relaxed(GICD_INT_DEF_PRI_X4,
dist_base + GIC_DIST_PRI + i * 4);
writel_relaxed(GICC_INT_PRI_THRESHOLD, cpu_base + GIC_CPU_PRIMASK);
gic_cpu_if_up(gic);
}
static int gic_notifier(struct notifier_block *self, unsigned long cmd, void *v)
{
int i;
for (i = 0; i < CONFIG_ARM_GIC_MAX_NR; i++) {
#ifdef CONFIG_GIC_NON_BANKED
/* Skip over unused GICs */
if (!gic_data[i].get_base)
continue;
#endif
switch (cmd) {
case CPU_PM_ENTER:
gic_cpu_save(&gic_data[i]);
break;
case CPU_PM_ENTER_FAILED:
case CPU_PM_EXIT:
gic_cpu_restore(&gic_data[i]);
break;
case CPU_CLUSTER_PM_ENTER:
gic_dist_save(&gic_data[i]);
break;
case CPU_CLUSTER_PM_ENTER_FAILED:
case CPU_CLUSTER_PM_EXIT:
gic_dist_restore(&gic_data[i]);
break;
}
}
return NOTIFY_OK;
}
static struct notifier_block gic_notifier_block = {
.notifier_call = gic_notifier,
};
static int __init gic_pm_init(struct gic_chip_data *gic)
{
gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
sizeof(u32));
if (WARN_ON(!gic->saved_ppi_enable))
return -ENOMEM;
gic->saved_ppi_active = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
sizeof(u32));
if (WARN_ON(!gic->saved_ppi_active))
goto free_ppi_enable;
gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
sizeof(u32));
if (WARN_ON(!gic->saved_ppi_conf))
goto free_ppi_active;
if (gic == &gic_data[0])
cpu_pm_register_notifier(&gic_notifier_block);
return 0;
free_ppi_active:
free_percpu(gic->saved_ppi_active);
free_ppi_enable:
free_percpu(gic->saved_ppi_enable);
return -ENOMEM;
}
#else
static int __init gic_pm_init(struct gic_chip_data *gic)
{
return 0;
}
#endif
#ifdef CONFIG_SMP
static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
{
int cpu;
unsigned long flags, map = 0;
raw_spin_lock_irqsave(&irq_controller_lock, flags);
/* Convert our logical CPU mask into a physical one. */
for_each_cpu(cpu, mask)
map |= gic_cpu_map[cpu];
/*
* Ensure that stores to Normal memory are visible to the
* other CPUs before they observe us issuing the IPI.
*/
dmb(ishst);
/* this always happens on GIC0 */
writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
}
#endif
#ifdef CONFIG_BL_SWITCHER
/*
* gic_send_sgi - send a SGI directly to given CPU interface number
*
* cpu_id: the ID for the destination CPU interface
* irq: the IPI number to send a SGI for
*/
void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
{
BUG_ON(cpu_id >= NR_GIC_CPU_IF);
cpu_id = 1 << cpu_id;
/* this always happens on GIC0 */
writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
}
/*
* gic_get_cpu_id - get the CPU interface ID for the specified CPU
*
* @cpu: the logical CPU number to get the GIC ID for.
*
* Return the CPU interface ID for the given logical CPU number,
* or -1 if the CPU number is too large or the interface ID is
* unknown (more than one bit set).
*/
int gic_get_cpu_id(unsigned int cpu)
{
unsigned int cpu_bit;
if (cpu >= NR_GIC_CPU_IF)
return -1;
cpu_bit = gic_cpu_map[cpu];
if (cpu_bit & (cpu_bit - 1))
return -1;
return __ffs(cpu_bit);
}
/*
* gic_migrate_target - migrate IRQs to another CPU interface
*
* @new_cpu_id: the CPU target ID to migrate IRQs to
*
* Migrate all peripheral interrupts with a target matching the current CPU
* to the interface corresponding to @new_cpu_id. The CPU interface mapping
* is also updated. Targets to other CPU interfaces are unchanged.
* This must be called with IRQs locally disabled.
*/
void gic_migrate_target(unsigned int new_cpu_id)
{
unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
void __iomem *dist_base;
int i, ror_val, cpu = smp_processor_id();
u32 val, cur_target_mask, active_mask;
BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
dist_base = gic_data_dist_base(&gic_data[gic_nr]);
if (!dist_base)
return;
gic_irqs = gic_data[gic_nr].gic_irqs;
cur_cpu_id = __ffs(gic_cpu_map[cpu]);
cur_target_mask = 0x01010101 << cur_cpu_id;
ror_val = (cur_cpu_id - new_cpu_id) & 31;
raw_spin_lock(&irq_controller_lock);
/* Update the target interface for this logical CPU */
gic_cpu_map[cpu] = 1 << new_cpu_id;
/*
* Find all the peripheral interrupts targetting the current
* CPU interface and migrate them to the new CPU interface.
* We skip DIST_TARGET 0 to 7 as they are read-only.
*/
for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
active_mask = val & cur_target_mask;
if (active_mask) {
val &= ~active_mask;
val |= ror32(active_mask, ror_val);
writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
}
}
raw_spin_unlock(&irq_controller_lock);
/*
* Now let's migrate and clear any potential SGIs that might be
* pending for us (cur_cpu_id). Since GIC_DIST_SGI_PENDING_SET
* is a banked register, we can only forward the SGI using
* GIC_DIST_SOFTINT. The original SGI source is lost but Linux
* doesn't use that information anyway.
*
* For the same reason we do not adjust SGI source information
* for previously sent SGIs by us to other CPUs either.
*/
for (i = 0; i < 16; i += 4) {
int j;
val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
if (!val)
continue;
writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
for (j = i; j < i + 4; j++) {
if (val & 0xff)
writel_relaxed((1 << (new_cpu_id + 16)) | j,
dist_base + GIC_DIST_SOFTINT);
val >>= 8;
}
}
}
/*
* gic_get_sgir_physaddr - get the physical address for the SGI register
*
* REturn the physical address of the SGI register to be used
* by some early assembly code when the kernel is not yet available.
*/
static unsigned long gic_dist_physaddr;
unsigned long gic_get_sgir_physaddr(void)
{
if (!gic_dist_physaddr)
return 0;
return gic_dist_physaddr + GIC_DIST_SOFTINT;
}
void __init gic_init_physaddr(struct device_node *node)
{
struct resource res;
if (of_address_to_resource(node, 0, &res) == 0) {
gic_dist_physaddr = res.start;
pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
}
}
#else
#define gic_init_physaddr(node) do { } while (0)
#endif
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
struct gic_chip_data *gic = d->host_data;
if (hw < 32) {
irq_set_percpu_devid(irq);
irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
handle_percpu_devid_irq, NULL, NULL);
irq_set_status_flags(irq, IRQ_NOAUTOEN);
} else {
irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
handle_fasteoi_irq, NULL, NULL);
irq_set_probe(irq);
}
return 0;
}
static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
{
}
static int gic_irq_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
unsigned int *type)
{
if (is_of_node(fwspec->fwnode)) {
if (fwspec->param_count < 3)
return -EINVAL;
/* Get the interrupt number and add 16 to skip over SGIs */
*hwirq = fwspec->param[1] + 16;
/*
* For SPIs, we need to add 16 more to get the GIC irq
* ID number
*/
if (!fwspec->param[0])
*hwirq += 16;
*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
return 0;
}
if (is_fwnode_irqchip(fwspec->fwnode)) {
if(fwspec->param_count != 2)
return -EINVAL;
*hwirq = fwspec->param[0];
*type = fwspec->param[1];
return 0;
}
return -EINVAL;
}
#ifdef CONFIG_SMP
static int gic_secondary_init(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
irqchip: gic: call gic_cpu_init() as well in CPU_STARTING_FROZEN case Commit c011470 (irqchip: gic: Perform the gic_secondary_init() call via CPU notifier) moves gic_secondary_init() that used to be called in .smp_secondary_init hook into a notifier call. But it changes the system behavior a little bit. Before the commit, gic_cpu_init() is called not only when kernel brings up the secondary cores but also when system resuming procedure hot-plugs the cores back to kernel. While after the commit, the function will not be called in the latter case, where the 'action' will not be CPU_STARTING but CPU_STARTING_FROZEN. This behavior difference at least causes the following suspend/resume regression on imx6q. $ echo mem > /sys/power/state PM: Syncing filesystems ... done. PM: Preparing system for mem sleep mmc1: card e624 removed Freezing user space processes ... (elapsed 0.01 seconds) done. Freezing remaining freezable tasks ... (elapsed 0.01 seconds) done. PM: Entering mem sleep PM: suspend of devices complete after 5.930 msecs PM: suspend devices took 0.010 seconds PM: late suspend of devices complete after 0.343 msecs PM: noirq suspend of devices complete after 0.828 msecs Disabling non-boot CPUs ... CPU1: shutdown CPU2: shutdown CPU3: shutdown Enabling non-boot CPUs ... CPU1: Booted secondary processor INFO: rcu_sched detected stalls on CPUs/tasks: { 1 2 3} (detected by 0, t=2102 jiffies, g=4294967169, c=4294967168, q=17) Task dump for CPU 1: swapper/1 R running 0 0 1 0x00000000 Backtrace: [<bf895ff4>] (0xbf895ff4) from [<00000000>] ( (null)) Backtrace aborted due to bad frame pointer <8007ccdc> Task dump for CPU 2: swapper/2 R running 0 0 1 0x00000000 Backtrace: [<8075dbdc>] (0x8075dbdc) from [<00000000>] ( (null)) Backtrace aborted due to bad frame pointer <00000002> Task dump for CPU 3: swapper/3 R running 0 0 1 0x00000000 Backtrace: [<8075dbdc>] (0x8075dbdc) from [<00000000>] ( (null)) Fix the regression by checking 'action' being CPU_STARTING_FROZEN to have gic_cpu_init() called for secondary cores when system resumes. Signed-off-by: Shawn Guo <shawn.guo@linaro.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Tested-by: Joseph Lo <josephl@nvidia.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
2013-06-12 18:30:27 +07:00
if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
gic_cpu_init(&gic_data[0]);
return NOTIFY_OK;
}
/*
* Notifier for enabling the GIC CPU interface. Set an arbitrarily high
* priority because the GIC needs to be up before the ARM generic timers.
*/
static struct notifier_block gic_cpu_notifier = {
.notifier_call = gic_secondary_init,
.priority = 100,
};
#endif
static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
int i, ret;
irq_hw_number_t hwirq;
unsigned int type = IRQ_TYPE_NONE;
struct irq_fwspec *fwspec = arg;
ret = gic_irq_domain_translate(domain, fwspec, &hwirq, &type);
if (ret)
return ret;
for (i = 0; i < nr_irqs; i++)
gic_irq_domain_map(domain, virq + i, hwirq + i);
return 0;
}
static const struct irq_domain_ops gic_irq_domain_hierarchy_ops = {
.translate = gic_irq_domain_translate,
.alloc = gic_irq_domain_alloc,
.free = irq_domain_free_irqs_top,
};
static const struct irq_domain_ops gic_irq_domain_ops = {
.map = gic_irq_domain_map,
.unmap = gic_irq_domain_unmap,
};
static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
struct fwnode_handle *handle)
{
irq_hw_number_t hwirq_base;
int gic_irqs, irq_base, i, ret;
if (WARN_ON(!gic || gic->domain))
return -EINVAL;
/* Initialize irq_chip */
gic->chip = gic_chip;
if (static_key_true(&supports_deactivate) && gic == &gic_data[0]) {
gic->chip.irq_mask = gic_eoimode1_mask_irq;
gic->chip.irq_eoi = gic_eoimode1_eoi_irq;
gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
gic->chip.name = kasprintf(GFP_KERNEL, "GICv2");
} else {
gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d",
(int)(gic - &gic_data[0]));
}
#ifdef CONFIG_SMP
if (gic == &gic_data[0])
gic->chip.irq_set_affinity = gic_set_affinity;
#endif
if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
/* Frankein-GIC without banked registers... */
unsigned int cpu;
gic->dist_base.percpu_base = alloc_percpu(void __iomem *);
gic->cpu_base.percpu_base = alloc_percpu(void __iomem *);
if (WARN_ON(!gic->dist_base.percpu_base ||
!gic->cpu_base.percpu_base)) {
ret = -ENOMEM;
goto error;
}
for_each_possible_cpu(cpu) {
u32 mpidr = cpu_logical_map(cpu);
u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
unsigned long offset = gic->percpu_offset * core_id;
*per_cpu_ptr(gic->dist_base.percpu_base, cpu) =
gic->raw_dist_base + offset;
*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) =
gic->raw_cpu_base + offset;
}
gic_set_base_accessor(gic, gic_get_percpu_base);
} else {
/* Normal, sane GIC... */
WARN(gic->percpu_offset,
"GIC_NON_BANKED not enabled, ignoring %08x offset!",
gic->percpu_offset);
gic->dist_base.common_base = gic->raw_dist_base;
gic->cpu_base.common_base = gic->raw_cpu_base;
gic_set_base_accessor(gic, gic_get_common_base);
}
/*
* Find out how many interrupts are supported.
* The GIC only supports up to 1020 interrupt sources.
*/
gic_irqs = readl_relaxed(gic_data_dist_base(gic) + GIC_DIST_CTR) & 0x1f;
gic_irqs = (gic_irqs + 1) * 32;
if (gic_irqs > 1020)
gic_irqs = 1020;
gic->gic_irqs = gic_irqs;
if (handle) { /* DT/ACPI */
gic->domain = irq_domain_create_linear(handle, gic_irqs,
&gic_irq_domain_hierarchy_ops,
gic);
} else { /* Legacy support */
/*
* For primary GICs, skip over SGIs.
* For secondary GICs, skip over PPIs, too.
*/
if (gic == &gic_data[0] && (irq_start & 31) > 0) {
hwirq_base = 16;
if (irq_start != -1)
irq_start = (irq_start & ~31) + 16;
} else {
hwirq_base = 32;
}
gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
numa_node_id());
remove lots of IS_ERR_VALUE abuses Most users of IS_ERR_VALUE() in the kernel are wrong, as they pass an 'int' into a function that takes an 'unsigned long' argument. This happens to work because the type is sign-extended on 64-bit architectures before it gets converted into an unsigned type. However, anything that passes an 'unsigned short' or 'unsigned int' argument into IS_ERR_VALUE() is guaranteed to be broken, as are 8-bit integers and types that are wider than 'unsigned long'. Andrzej Hajda has already fixed a lot of the worst abusers that were causing actual bugs, but it would be nice to prevent any users that are not passing 'unsigned long' arguments. This patch changes all users of IS_ERR_VALUE() that I could find on 32-bit ARM randconfig builds and x86 allmodconfig. For the moment, this doesn't change the definition of IS_ERR_VALUE() because there are probably still architecture specific users elsewhere. Almost all the warnings I got are for files that are better off using 'if (err)' or 'if (err < 0)'. The only legitimate user I could find that we get a warning for is the (32-bit only) freescale fman driver, so I did not remove the IS_ERR_VALUE() there but changed the type to 'unsigned long'. For 9pfs, I just worked around one user whose calling conventions are so obscure that I did not dare change the behavior. I was using this definition for testing: #define IS_ERR_VALUE(x) ((unsigned long*)NULL == (typeof (x)*)NULL && \ unlikely((unsigned long long)(x) >= (unsigned long long)(typeof(x))-MAX_ERRNO)) which ends up making all 16-bit or wider types work correctly with the most plausible interpretation of what IS_ERR_VALUE() was supposed to return according to its users, but also causes a compile-time warning for any users that do not pass an 'unsigned long' argument. I suggested this approach earlier this year, but back then we ended up deciding to just fix the users that are obviously broken. After the initial warning that caused me to get involved in the discussion (fs/gfs2/dir.c) showed up again in the mainline kernel, Linus asked me to send the whole thing again. [ Updated the 9p parts as per Al Viro - Linus ] Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Andrzej Hajda <a.hajda@samsung.com> Cc: Andrew Morton <akpm@linux-foundation.org> Link: https://lkml.org/lkml/2016/1/7/363 Link: https://lkml.org/lkml/2016/5/27/486 Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> # For nvmem part Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-28 04:23:25 +07:00
if (irq_base < 0) {
WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
irq_start);
irq_base = irq_start;
}
gic->domain = irq_domain_add_legacy(NULL, gic_irqs, irq_base,
hwirq_base, &gic_irq_domain_ops, gic);
}
if (WARN_ON(!gic->domain)) {
ret = -ENODEV;
goto error;
}
if (gic == &gic_data[0]) {
/*
* Initialize the CPU interface map to all CPUs.
* It will be refined as each CPU probes its ID.
* This is only necessary for the primary GIC.
*/
for (i = 0; i < NR_GIC_CPU_IF; i++)
gic_cpu_map[i] = 0xff;
#ifdef CONFIG_SMP
set_smp_cross_call(gic_raise_softirq);
register_cpu_notifier(&gic_cpu_notifier);
#endif
set_handle_irq(gic_handle_irq);
if (static_key_true(&supports_deactivate))
pr_info("GIC: Using split EOI/Deactivate mode\n");
}
gic_dist_init(gic);
ret = gic_cpu_init(gic);
if (ret)
goto error;
ret = gic_pm_init(gic);
if (ret)
goto error;
return 0;
error:
if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
free_percpu(gic->dist_base.percpu_base);
free_percpu(gic->cpu_base.percpu_base);
}
kfree(gic->chip.name);
return ret;
}
void __init gic_init(unsigned int gic_nr, int irq_start,
void __iomem *dist_base, void __iomem *cpu_base)
{
struct gic_chip_data *gic;
if (WARN_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR))
return;
/*
* Non-DT/ACPI systems won't run a hypervisor, so let's not
* bother with these...
*/
static_key_slow_dec(&supports_deactivate);
gic = &gic_data[gic_nr];
gic->raw_dist_base = dist_base;
gic->raw_cpu_base = cpu_base;
__gic_init_bases(gic, irq_start, NULL);
}
static void gic_teardown(struct gic_chip_data *gic)
{
if (WARN_ON(!gic))
return;
if (gic->raw_dist_base)
iounmap(gic->raw_dist_base);
if (gic->raw_cpu_base)
iounmap(gic->raw_cpu_base);
}
#ifdef CONFIG_OF
static int gic_cnt __initdata;
irqchip/GIC: Add workaround for aliased GIC400 The GICv2 architecture mandates that the two 4kB GIC regions are contiguous, and on two separate physical pages (so that access to the second page can be trapped by a hypervisor). This doesn't work very well when PAGE_SIZE is 64kB. A relatively common hack^Wway to work around this is to alias each 4kB region over its own 64kB page. Of course in this case, the base address you want to use is not really the begining of the region, but base + 60kB (so that you get a contiguous 8kB region over two distinct pages). Normally, this would be described in DT with a new property, but some HW is already out there, and the firmware makes sure that it will override whatever you put in the GIC node. Duh. And of course, said firmware source code is not available, despite being based on u-boot. The workaround is to detect the case where the CPU interface size is set to 128kB, and verify the aliasing by checking that the ID register for GIC400 (which is the only GIC wired this way so far) is the same at base and base + 0xF000. In this case, we update the GIC base address and let it roll. And if you feel slightly sick by looking at this, rest assured that I do too... Reported-by: Julien Grall <julien.grall@citrix.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Stuart Yoder <stuart.yoder@freescale.com> Cc: Pavel Fedin <p.fedin@samsung.com> Cc: Jason Cooper <jason@lakedaemon.net> Link: http://lkml.kernel.org/r/1442142873-20213-2-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-09-13 18:14:31 +07:00
static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
{
struct resource cpuif_res;
of_address_to_resource(node, 1, &cpuif_res);
if (!is_hyp_mode_available())
return false;
if (resource_size(&cpuif_res) < SZ_8K)
return false;
if (resource_size(&cpuif_res) == SZ_128K) {
u32 val_low, val_high;
/*
* Verify that we have the first 4kB of a GIC400
* aliased over the first 64kB by checking the
* GICC_IIDR register on both ends.
*/
val_low = readl_relaxed(*base + GIC_CPU_IDENT);
val_high = readl_relaxed(*base + GIC_CPU_IDENT + 0xf000);
if ((val_low & 0xffff0fff) != 0x0202043B ||
val_low != val_high)
return false;
/*
* Move the base up by 60kB, so that we have a 8kB
* contiguous region, which allows us to use GICC_DIR
* at its normal offset. Please pass me that bucket.
*/
*base += 0xf000;
cpuif_res.start += 0xf000;
pr_warn("GIC: Adjusting CPU interface base to %pa",
&cpuif_res.start);
}
return true;
}
Small release overall. - x86: miscellaneous fixes, AVIC support (local APIC virtualization, AMD version) - s390: polling for interrupts after a VCPU goes to halted state is now enabled for s390; use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities; improve perf output; floating interrupt controller improvements. - MIPS: miscellaneous fixes - PPC: bugfixes only - ARM: 16K page size support, generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com "more formally and for documentation purposes". -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQEcBAABAgAGBQJXPJjyAAoJEL/70l94x66DhioH/j4fwQ0FmfPSM9PArzaFHQdx LNE3tU4+bobbsy1BJr4DiAaOUQn3DAgwUvGLWXdeLiOXtoWXBiFHKaxlqEsCA6iQ xcTH1TgfxsVoqGQ6bT9X/2GCx70heYpcWG3f+zqBy7ZfFmQykLAC/HwOr52VQL8f hUFi3YmTHcnorp0n5Xg+9r3+RBS4D/kTbtdn6+KCLnPJ0RcgNkI3/NcafTemoofw Tkv8+YYFNvKV13qlIfVqxMa0GwWI3pP6YaNKhaS5XO8Pu16HuuF1JthJsUBDzwBa RInp8R9MoXgsBYhLpz3jc9vWG7G9yDl5LehsD9KOUGOaFYJ7sQN+QZOusa6jFgA= =llO5 -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Paolo Bonzini: "Small release overall. x86: - miscellaneous fixes - AVIC support (local APIC virtualization, AMD version) s390: - polling for interrupts after a VCPU goes to halted state is now enabled for s390 - use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities - improve perf output - floating interrupt controller improvements. MIPS: - miscellaneous fixes PPC: - bugfixes only ARM: - 16K page size support - generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more formally and for documentation purposes')" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits) KVM: MTRR: remove MSR 0x2f8 KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same svm: Manage vcpu load/unload when enable AVIC svm: Do not intercept CR8 when enable AVIC svm: Do not expose x2APIC when enable AVIC KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore svm: Add VMEXIT handlers for AVIC svm: Add interrupt injection via AVIC KVM: x86: Detect and Initialize AVIC support svm: Introduce new AVIC VMCB registers KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg KVM: x86: Misc LAPIC changes to expose helper functions KVM: shrink halt polling even more for invalid wakeups KVM: s390: set halt polling to 80 microseconds KVM: halt_polling: provide a way to qualify wakeups during poll KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts kvm: Conditionally register IRQ bypass consumer ...
2016-05-20 01:27:09 +07:00
static int __init gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
{
if (!gic || !node)
return -EINVAL;
gic->raw_dist_base = of_iomap(node, 0);
if (WARN(!gic->raw_dist_base, "unable to map gic dist registers\n"))
goto error;
gic->raw_cpu_base = of_iomap(node, 1);
if (WARN(!gic->raw_cpu_base, "unable to map gic cpu registers\n"))
goto error;
if (of_property_read_u32(node, "cpu-offset", &gic->percpu_offset))
gic->percpu_offset = 0;
return 0;
error:
gic_teardown(gic);
return -ENOMEM;
}
static void __init gic_of_setup_kvm_info(struct device_node *node)
{
int ret;
struct resource *vctrl_res = &gic_v2_kvm_info.vctrl;
struct resource *vcpu_res = &gic_v2_kvm_info.vcpu;
gic_v2_kvm_info.type = GIC_V2;
gic_v2_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
if (!gic_v2_kvm_info.maint_irq)
return;
ret = of_address_to_resource(node, 2, vctrl_res);
if (ret)
return;
ret = of_address_to_resource(node, 3, vcpu_res);
if (ret)
return;
gic_set_kvm_info(&gic_v2_kvm_info);
}
int __init
gic_of_init(struct device_node *node, struct device_node *parent)
{
struct gic_chip_data *gic;
int irq, ret;
if (WARN_ON(!node))
return -ENODEV;
if (WARN_ON(gic_cnt >= CONFIG_ARM_GIC_MAX_NR))
return -EINVAL;
gic = &gic_data[gic_cnt];
ret = gic_of_setup(gic, node);
if (ret)
return ret;
/*
* Disable split EOI/Deactivate if either HYP is not available
* or the CPU interface is too small.
*/
if (gic_cnt == 0 && !gic_check_eoimode(node, &gic->raw_cpu_base))
static_key_slow_dec(&supports_deactivate);
ret = __gic_init_bases(gic, -1, &node->fwnode);
if (ret) {
gic_teardown(gic);
return ret;
}
if (!gic_cnt) {
gic_init_physaddr(node);
gic_of_setup_kvm_info(node);
}
if (parent) {
irq = irq_of_parse_and_map(node, 0);
gic_cascade_irq(gic_cnt, irq);
}
if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
gicv2m_init(&node->fwnode, gic_data[gic_cnt].domain);
gic_cnt++;
return 0;
}
IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
IRQCHIP_DECLARE(arm11mp_gic, "arm,arm11mp-gic", gic_of_init);
IRQCHIP_DECLARE(arm1176jzf_dc_gic, "arm,arm1176jzf-devchip-gic", gic_of_init);
IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
IRQCHIP_DECLARE(pl390, "arm,pl390", gic_of_init);
#endif
#ifdef CONFIG_ACPI
static struct
{
phys_addr_t cpu_phys_base;
u32 maint_irq;
int maint_irq_mode;
phys_addr_t vctrl_base;
phys_addr_t vcpu_base;
} acpi_data __initdata;
static int __init
gic_acpi_parse_madt_cpu(struct acpi_subtable_header *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *processor;
phys_addr_t gic_cpu_base;
static int cpu_base_assigned;
processor = (struct acpi_madt_generic_interrupt *)header;
if (BAD_MADT_GICC_ENTRY(processor, end))
return -EINVAL;
/*
* There is no support for non-banked GICv1/2 register in ACPI spec.
* All CPU interface addresses have to be the same.
*/
gic_cpu_base = processor->base_address;
if (cpu_base_assigned && gic_cpu_base != acpi_data.cpu_phys_base)
return -EINVAL;
acpi_data.cpu_phys_base = gic_cpu_base;
acpi_data.maint_irq = processor->vgic_interrupt;
acpi_data.maint_irq_mode = (processor->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE;
acpi_data.vctrl_base = processor->gich_base_address;
acpi_data.vcpu_base = processor->gicv_base_address;
cpu_base_assigned = 1;
return 0;
}
/* The things you have to do to just *count* something... */
static int __init acpi_dummy_func(struct acpi_subtable_header *header,
const unsigned long end)
{
return 0;
}
static bool __init acpi_gic_redist_is_present(void)
{
return acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR,
acpi_dummy_func, 0) > 0;
}
static bool __init gic_validate_dist(struct acpi_subtable_header *header,
struct acpi_probe_entry *ape)
{
struct acpi_madt_generic_distributor *dist;
dist = (struct acpi_madt_generic_distributor *)header;
return (dist->version == ape->driver_data &&
(dist->version != ACPI_MADT_GIC_VERSION_NONE ||
!acpi_gic_redist_is_present()));
}
#define ACPI_GICV2_DIST_MEM_SIZE (SZ_4K)
#define ACPI_GIC_CPU_IF_MEM_SIZE (SZ_8K)
#define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K)
#define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K)
static void __init gic_acpi_setup_kvm_info(void)
{
int irq;
struct resource *vctrl_res = &gic_v2_kvm_info.vctrl;
struct resource *vcpu_res = &gic_v2_kvm_info.vcpu;
gic_v2_kvm_info.type = GIC_V2;
if (!acpi_data.vctrl_base)
return;
vctrl_res->flags = IORESOURCE_MEM;
vctrl_res->start = acpi_data.vctrl_base;
vctrl_res->end = vctrl_res->start + ACPI_GICV2_VCTRL_MEM_SIZE - 1;
if (!acpi_data.vcpu_base)
return;
vcpu_res->flags = IORESOURCE_MEM;
vcpu_res->start = acpi_data.vcpu_base;
vcpu_res->end = vcpu_res->start + ACPI_GICV2_VCPU_MEM_SIZE - 1;
irq = acpi_register_gsi(NULL, acpi_data.maint_irq,
acpi_data.maint_irq_mode,
ACPI_ACTIVE_HIGH);
if (irq <= 0)
return;
gic_v2_kvm_info.maint_irq = irq;
gic_set_kvm_info(&gic_v2_kvm_info);
}
static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
const unsigned long end)
{
struct acpi_madt_generic_distributor *dist;
struct fwnode_handle *domain_handle;
struct gic_chip_data *gic = &gic_data[0];
int count, ret;
/* Collect CPU base addresses */
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_parse_madt_cpu, 0);
if (count <= 0) {
pr_err("No valid GICC entries exist\n");
return -EINVAL;
}
Small release overall. - x86: miscellaneous fixes, AVIC support (local APIC virtualization, AMD version) - s390: polling for interrupts after a VCPU goes to halted state is now enabled for s390; use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities; improve perf output; floating interrupt controller improvements. - MIPS: miscellaneous fixes - PPC: bugfixes only - ARM: 16K page size support, generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com "more formally and for documentation purposes". -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQEcBAABAgAGBQJXPJjyAAoJEL/70l94x66DhioH/j4fwQ0FmfPSM9PArzaFHQdx LNE3tU4+bobbsy1BJr4DiAaOUQn3DAgwUvGLWXdeLiOXtoWXBiFHKaxlqEsCA6iQ xcTH1TgfxsVoqGQ6bT9X/2GCx70heYpcWG3f+zqBy7ZfFmQykLAC/HwOr52VQL8f hUFi3YmTHcnorp0n5Xg+9r3+RBS4D/kTbtdn6+KCLnPJ0RcgNkI3/NcafTemoofw Tkv8+YYFNvKV13qlIfVqxMa0GwWI3pP6YaNKhaS5XO8Pu16HuuF1JthJsUBDzwBa RInp8R9MoXgsBYhLpz3jc9vWG7G9yDl5LehsD9KOUGOaFYJ7sQN+QZOusa6jFgA= =llO5 -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Paolo Bonzini: "Small release overall. x86: - miscellaneous fixes - AVIC support (local APIC virtualization, AMD version) s390: - polling for interrupts after a VCPU goes to halted state is now enabled for s390 - use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities - improve perf output - floating interrupt controller improvements. MIPS: - miscellaneous fixes PPC: - bugfixes only ARM: - 16K page size support - generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more formally and for documentation purposes')" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits) KVM: MTRR: remove MSR 0x2f8 KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same svm: Manage vcpu load/unload when enable AVIC svm: Do not intercept CR8 when enable AVIC svm: Do not expose x2APIC when enable AVIC KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore svm: Add VMEXIT handlers for AVIC svm: Add interrupt injection via AVIC KVM: x86: Detect and Initialize AVIC support svm: Introduce new AVIC VMCB registers KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg KVM: x86: Misc LAPIC changes to expose helper functions KVM: shrink halt polling even more for invalid wakeups KVM: s390: set halt polling to 80 microseconds KVM: halt_polling: provide a way to qualify wakeups during poll KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts kvm: Conditionally register IRQ bypass consumer ...
2016-05-20 01:27:09 +07:00
gic->raw_cpu_base = ioremap(acpi_data.cpu_phys_base, ACPI_GIC_CPU_IF_MEM_SIZE);
if (!gic->raw_cpu_base) {
pr_err("Unable to map GICC registers\n");
return -ENOMEM;
}
dist = (struct acpi_madt_generic_distributor *)header;
gic->raw_dist_base = ioremap(dist->base_address,
ACPI_GICV2_DIST_MEM_SIZE);
if (!gic->raw_dist_base) {
pr_err("Unable to map GICD registers\n");
gic_teardown(gic);
return -ENOMEM;
}
/*
* Disable split EOI/Deactivate if HYP is not available. ACPI
* guarantees that we'll always have a GICv2, so the CPU
* interface will always be the right size.
*/
if (!is_hyp_mode_available())
static_key_slow_dec(&supports_deactivate);
/*
* Initialize GIC instance zero (no multi-GIC support).
*/
domain_handle = irq_domain_alloc_fwnode(gic->raw_dist_base);
if (!domain_handle) {
pr_err("Unable to allocate domain handle\n");
gic_teardown(gic);
return -ENOMEM;
}
ret = __gic_init_bases(gic, -1, domain_handle);
if (ret) {
pr_err("Failed to initialise GIC\n");
irq_domain_free_fwnode(domain_handle);
gic_teardown(gic);
return ret;
}
ACPI: move arm64 GSI IRQ model to generic GSI IRQ layer The code deployed to implement GSI linux IRQ numbers mapping on arm64 turns out to be generic enough so that it can be moved to ACPI core code along with its respective config option ACPI_GENERIC_GSI selectable on architectures that can reuse the same code. Current ACPI IRQ mapping code is not integrated in the kernel IRQ domain infrastructure, in particular there is no way to look-up the IRQ domain associated with a particular interrupt controller, so this first version of GSI generic code carries out the GSI<->IRQ mapping relying on the IRQ default domain which is supposed to be always set on a specific architecture in case the domain structure passed to irq_create/find_mapping() functions is missing. This patch moves the arm64 acpi functions that implement the gsi mappings: acpi_gsi_to_irq() acpi_register_gsi() acpi_unregister_gsi() to ACPI core code. Since the generic GSI<->domain mapping is based on IRQ domains, it can be extended as soon as a way to map an interrupt controller to an IRQ domain is implemented for ACPI in the IRQ domain layer. x86 and ia64 code for GSI mappings cannot rely on the generic GSI layer at present for legacy reasons, so they do not select the ACPI_GENERIC_GSI config options and keep relying on their arch specific GSI mapping layer. Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Acked-by: Will Deacon <will.deacon@arm.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-25 00:58:51 +07:00
acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle);
if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
gicv2m_init(NULL, gic_data[0].domain);
gic_acpi_setup_kvm_info();
return 0;
}
IRQCHIP_ACPI_DECLARE(gic_v2, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
gic_validate_dist, ACPI_MADT_GIC_VERSION_V2,
gic_v2_acpi_init);
IRQCHIP_ACPI_DECLARE(gic_v2_maybe, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
gic_validate_dist, ACPI_MADT_GIC_VERSION_NONE,
gic_v2_acpi_init);
#endif