OpenCloudOS-Kernel/drivers/irqchip/irq-gic-v3.c

2465 lines
61 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2013-2017 ARM Limited, All Rights Reserved.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#define pr_fmt(fmt) "GICv3: " fmt
#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/percpu.h>
#include <linux/refcount.h>
#include <linux/slab.h>
#include <linux/irqchip.h>
#include <linux/irqchip/arm-gic-common.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/irqchip/irq-partition-percpu.h>
#include <asm/cputype.h>
#include <asm/exception.h>
#include <asm/smp_plat.h>
#include <asm/virt.h>
#include "irq-gic-common.h"
#define GICD_INT_NMI_PRI (GICD_INT_DEF_PRI & ~0x80)
#define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0)
irqchip/gic-v3: Workaround Cavium erratum 38539 when reading GICD_TYPER2 Despite the architecture spec requiring that reserved registers in the GIC distributor memory map are RES0 (and thus are not allowed to generate an exception), the Cavium ThunderX (aka TX1) SoC explodes as such: [ 0.000000] GICv3: GIC: Using split EOI/Deactivate mode [ 0.000000] GICv3: 128 SPIs implemented [ 0.000000] GICv3: 0 Extended SPIs implemented [ 0.000000] Internal error: synchronous external abort: 96000210 [#1] SMP [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc4-00035-g3cf6a3d5725f #7956 [ 0.000000] Hardware name: cavium,thunder-88xx (DT) [ 0.000000] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 0.000000] pc : __raw_readl+0x0/0x8 [ 0.000000] lr : gic_init_bases+0x110/0x560 [ 0.000000] sp : ffff800011243d90 [ 0.000000] x29: ffff800011243d90 x28: 0000000000000000 [ 0.000000] x27: 0000000000000018 x26: 0000000000000002 [ 0.000000] x25: ffff8000116f0000 x24: ffff000fbe6a2c80 [ 0.000000] x23: 0000000000000000 x22: ffff010fdc322b68 [ 0.000000] x21: ffff800010a7a208 x20: 00000000009b0404 [ 0.000000] x19: ffff80001124dad0 x18: 0000000000000010 [ 0.000000] x17: 000000004d8d492b x16: 00000000f67eb9af [ 0.000000] x15: ffffffffffffffff x14: ffff800011249908 [ 0.000000] x13: ffff800091243ae7 x12: ffff800011243af4 [ 0.000000] x11: ffff80001126e000 x10: ffff800011243a70 [ 0.000000] x9 : 00000000ffffffd0 x8 : ffff80001069c828 [ 0.000000] x7 : 0000000000000059 x6 : ffff8000113fb4d1 [ 0.000000] x5 : 0000000000000001 x4 : 0000000000000000 [ 0.000000] x3 : 0000000000000000 x2 : 0000000000000000 [ 0.000000] x1 : 0000000000000000 x0 : ffff8000116f000c [ 0.000000] Call trace: [ 0.000000] __raw_readl+0x0/0x8 [ 0.000000] gic_of_init+0x188/0x224 [ 0.000000] of_irq_init+0x200/0x3cc [ 0.000000] irqchip_init+0x1c/0x40 [ 0.000000] init_IRQ+0x160/0x1d0 [ 0.000000] start_kernel+0x2ec/0x4b8 [ 0.000000] Code: a8c47bfd d65f03c0 d538d080 d65f03c0 (b9400000) when reading the GICv4.1 GICD_TYPER2 register, which is unexpected... Work around it by adding a new quirk for the following variants: ThunderX: CN88xx OCTEON TX: CN83xx, CN81xx OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* and use this flag to avoid accessing GICD_TYPER2. Note that all reserved registers (including redistributors and ITS) are impacted by this erratum, but that only GICD_TYPER2 has to be worked around so far. Signed-off-by: Marc Zyngier <maz@kernel.org> Tested-by: Robert Richter <rrichter@marvell.com> Tested-by: Mark Salter <msalter@redhat.com> Tested-by: Tim Harvey <tharvey@gateworks.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Robert Richter <rrichter@marvell.com> Link: https://lore.kernel.org/r/20191027144234.8395-11-maz@kernel.org Link: https://lore.kernel.org/r/20200311115649.26060-1-maz@kernel.org
2020-03-11 19:56:49 +08:00
#define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1)
#define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1)
struct redist_region {
void __iomem *redist_base;
phys_addr_t phys_base;
bool single_redist;
};
struct gic_chip_data {
struct fwnode_handle *fwnode;
void __iomem *dist_base;
struct redist_region *redist_regions;
struct rdists rdists;
struct irq_domain *domain;
u64 redist_stride;
u32 nr_redist_regions;
u64 flags;
bool has_rss;
unsigned int ppi_nr;
struct partition_desc **ppi_descs;
};
static struct gic_chip_data gic_data __read_mostly;
static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
#define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
#define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
/*
* The behaviours of RPR and PMR registers differ depending on the value of
* SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the
* distributor and redistributors depends on whether security is enabled in the
* GIC.
*
* When security is enabled, non-secure priority values from the (re)distributor
* are presented to the GIC CPUIF as follow:
* (GIC_(R)DIST_PRI[irq] >> 1) | 0x80;
*
* If SCR_EL3.FIQ == 1, the values written to/read from PMR and RPR at non-secure
* EL1 are subject to a similar operation thus matching the priorities presented
* from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0,
* these values are unchanged by the GIC.
*
* see GICv3/GICv4 Architecture Specification (IHI0069D):
* - section 4.8.1 Non-secure accesses to register fields for Secure interrupt
* priorities.
* - Figure 4-7 Secure read of the priority field for a Non-secure Group 1
* interrupt.
*/
static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
/*
* Global static key controlling whether an update to PMR allowing more
* interrupts requires to be propagated to the redistributor (DSB SY).
* And this needs to be exported for modules to be able to enable
* interrupts...
*/
DEFINE_STATIC_KEY_FALSE(gic_pmr_sync);
EXPORT_SYMBOL(gic_pmr_sync);
DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities);
EXPORT_SYMBOL(gic_nonsecure_priorities);
/*
* When the Non-secure world has access to group 0 interrupts (as a
* consequence of SCR_EL3.FIQ == 0), reading the ICC_RPR_EL1 register will
* return the Distributor's view of the interrupt priority.
*
* When GIC security is enabled (GICD_CTLR.DS == 0), the interrupt priority
* written by software is moved to the Non-secure range by the Distributor.
*
* If both are true (which is when gic_nonsecure_priorities gets enabled),
* we need to shift down the priority programmed by software to match it
* against the value returned by ICC_RPR_EL1.
*/
#define GICD_INT_RPR_PRI(priority) \
({ \
u32 __priority = (priority); \
if (static_branch_unlikely(&gic_nonsecure_priorities)) \
__priority = 0x80 | (__priority >> 1); \
\
__priority; \
})
/* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
static refcount_t *ppi_nmi_refs;
static struct gic_kvm_info gic_v3_kvm_info __initdata;
static DEFINE_PER_CPU(bool, has_rss);
#define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4)
#define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist))
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
#define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K)
/* Our default, arbitrary priority value. Linux only uses one anyway. */
#define DEFAULT_PMR_VALUE 0xf0
enum gic_intid_range {
SGI_RANGE,
PPI_RANGE,
SPI_RANGE,
EPPI_RANGE,
ESPI_RANGE,
LPI_RANGE,
__INVALID_RANGE__
};
static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq)
{
switch (hwirq) {
case 0 ... 15:
return SGI_RANGE;
case 16 ... 31:
return PPI_RANGE;
case 32 ... 1019:
return SPI_RANGE;
case EPPI_BASE_INTID ... (EPPI_BASE_INTID + 63):
return EPPI_RANGE;
case ESPI_BASE_INTID ... (ESPI_BASE_INTID + 1023):
return ESPI_RANGE;
case 8192 ... GENMASK(23, 0):
return LPI_RANGE;
default:
return __INVALID_RANGE__;
}
}
static enum gic_intid_range get_intid_range(struct irq_data *d)
{
return __get_intid_range(d->hwirq);
}
static inline unsigned int gic_irq(struct irq_data *d)
{
return d->hwirq;
}
static inline bool gic_irq_in_rdist(struct irq_data *d)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
return true;
default:
return false;
}
}
static inline void __iomem *gic_dist_base(struct irq_data *d)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
/* SGI+PPI -> SGI_base for this CPU */
return gic_data_rdist_sgi_base();
case SPI_RANGE:
case ESPI_RANGE:
/* SPI -> dist_base */
return gic_data.dist_base;
default:
return NULL;
}
}
static void gic_do_wait_for_rwp(void __iomem *base, u32 bit)
{
u32 count = 1000000; /* 1s! */
while (readl_relaxed(base + GICD_CTLR) & bit) {
count--;
if (!count) {
pr_err_ratelimited("RWP timeout, gone fishing\n");
return;
}
cpu_relax();
udelay(1);
}
}
/* Wait for completion of a distributor change */
static void gic_dist_wait_for_rwp(void)
{
gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP);
}
/* Wait for completion of a redistributor change */
static void gic_redist_wait_for_rwp(void)
{
gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP);
}
#ifdef CONFIG_ARM64
static u64 __maybe_unused gic_read_iar(void)
{
if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154))
return gic_read_iar_cavium_thunderx();
else
return gic_read_iar_common();
}
#endif
static void gic_enable_redist(bool enable)
{
void __iomem *rbase;
u32 count = 1000000; /* 1s! */
u32 val;
if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996)
return;
rbase = gic_data_rdist_rd_base();
val = readl_relaxed(rbase + GICR_WAKER);
if (enable)
/* Wake up this CPU redistributor */
val &= ~GICR_WAKER_ProcessorSleep;
else
val |= GICR_WAKER_ProcessorSleep;
writel_relaxed(val, rbase + GICR_WAKER);
if (!enable) { /* Check that GICR_WAKER is writeable */
val = readl_relaxed(rbase + GICR_WAKER);
if (!(val & GICR_WAKER_ProcessorSleep))
return; /* No PM support in this redistributor */
}
while (--count) {
val = readl_relaxed(rbase + GICR_WAKER);
if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
break;
cpu_relax();
udelay(1);
}
if (!count)
pr_err_ratelimited("redistributor failed to %s...\n",
enable ? "wakeup" : "sleep");
}
/*
* Routines to disable, enable, EOI and route interrupts
*/
static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case SPI_RANGE:
*index = d->hwirq;
return offset;
case EPPI_RANGE:
/*
* Contrary to the ESPI range, the EPPI range is contiguous
* to the PPI range in the registers, so let's adjust the
* displacement accordingly. Consistency is overrated.
*/
*index = d->hwirq - EPPI_BASE_INTID + 32;
return offset;
case ESPI_RANGE:
*index = d->hwirq - ESPI_BASE_INTID;
switch (offset) {
case GICD_ISENABLER:
return GICD_ISENABLERnE;
case GICD_ICENABLER:
return GICD_ICENABLERnE;
case GICD_ISPENDR:
return GICD_ISPENDRnE;
case GICD_ICPENDR:
return GICD_ICPENDRnE;
case GICD_ISACTIVER:
return GICD_ISACTIVERnE;
case GICD_ICACTIVER:
return GICD_ICACTIVERnE;
case GICD_IPRIORITYR:
return GICD_IPRIORITYRnE;
case GICD_ICFGR:
return GICD_ICFGRnE;
case GICD_IROUTER:
return GICD_IROUTERnE;
default:
break;
}
break;
default:
break;
}
WARN_ON(1);
*index = d->hwirq;
return offset;
}
static int gic_peek_irq(struct irq_data *d, u32 offset)
{
void __iomem *base;
u32 index, mask;
offset = convert_offset_index(d, offset, &index);
mask = 1 << (index % 32);
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_data.dist_base;
return !!(readl_relaxed(base + offset + (index / 32) * 4) & mask);
}
static void gic_poke_irq(struct irq_data *d, u32 offset)
{
void __iomem *base;
u32 index, mask;
offset = convert_offset_index(d, offset, &index);
mask = 1 << (index % 32);
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_data.dist_base;
writel_relaxed(mask, base + offset + (index / 32) * 4);
}
static void gic_mask_irq(struct irq_data *d)
{
gic_poke_irq(d, GICD_ICENABLER);
if (gic_irq_in_rdist(d))
gic_redist_wait_for_rwp();
else
gic_dist_wait_for_rwp();
}
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, GICD_ICACTIVER);
}
static void gic_unmask_irq(struct irq_data *d)
{
gic_poke_irq(d, GICD_ISENABLER);
}
static inline bool gic_supports_nmi(void)
{
return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
static_branch_likely(&supports_pseudo_nmis);
}
static int gic_irq_set_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool val)
{
u32 reg;
if (d->hwirq >= 8192) /* SGI/PPI/SPI only */
return -EINVAL;
switch (which) {
case IRQCHIP_STATE_PENDING:
reg = val ? GICD_ISPENDR : GICD_ICPENDR;
break;
case IRQCHIP_STATE_ACTIVE:
reg = val ? GICD_ISACTIVER : GICD_ICACTIVER;
break;
case IRQCHIP_STATE_MASKED:
if (val) {
gic_mask_irq(d);
return 0;
}
reg = GICD_ISENABLER;
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)
{
if (d->hwirq >= 8192) /* PPI/SPI only */
return -EINVAL;
switch (which) {
case IRQCHIP_STATE_PENDING:
*val = gic_peek_irq(d, GICD_ISPENDR);
break;
case IRQCHIP_STATE_ACTIVE:
*val = gic_peek_irq(d, GICD_ISACTIVER);
break;
case IRQCHIP_STATE_MASKED:
*val = !gic_peek_irq(d, GICD_ISENABLER);
break;
default:
return -EINVAL;
}
return 0;
}
static void gic_irq_set_prio(struct irq_data *d, u8 prio)
{
void __iomem *base = gic_dist_base(d);
u32 offset, index;
offset = convert_offset_index(d, GICD_IPRIORITYR, &index);
writeb_relaxed(prio, base + offset + index);
}
static u32 __gic_get_ppi_index(irq_hw_number_t hwirq)
{
switch (__get_intid_range(hwirq)) {
case PPI_RANGE:
return hwirq - 16;
case EPPI_RANGE:
return hwirq - EPPI_BASE_INTID + 16;
default:
unreachable();
}
}
static u32 gic_get_ppi_index(struct irq_data *d)
{
return __gic_get_ppi_index(d->hwirq);
}
static int gic_irq_nmi_setup(struct irq_data *d)
{
struct irq_desc *desc = irq_to_desc(d->irq);
if (!gic_supports_nmi())
return -EINVAL;
if (gic_peek_irq(d, GICD_ISENABLER)) {
pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq);
return -EINVAL;
}
/*
* A secondary irq_chip should be in charge of LPI request,
* it should not be possible to get there
*/
if (WARN_ON(gic_irq(d) >= 8192))
return -EINVAL;
/* desc lock should already be held */
if (gic_irq_in_rdist(d)) {
u32 idx = gic_get_ppi_index(d);
/* Setting up PPI as NMI, only switch handler for first NMI */
if (!refcount_inc_not_zero(&ppi_nmi_refs[idx])) {
refcount_set(&ppi_nmi_refs[idx], 1);
desc->handle_irq = handle_percpu_devid_fasteoi_nmi;
}
} else {
desc->handle_irq = handle_fasteoi_nmi;
}
gic_irq_set_prio(d, GICD_INT_NMI_PRI);
return 0;
}
static void gic_irq_nmi_teardown(struct irq_data *d)
{
struct irq_desc *desc = irq_to_desc(d->irq);
if (WARN_ON(!gic_supports_nmi()))
return;
if (gic_peek_irq(d, GICD_ISENABLER)) {
pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq);
return;
}
/*
* A secondary irq_chip should be in charge of LPI request,
* it should not be possible to get there
*/
if (WARN_ON(gic_irq(d) >= 8192))
return;
/* desc lock should already be held */
if (gic_irq_in_rdist(d)) {
u32 idx = gic_get_ppi_index(d);
/* Tearing down NMI, only switch handler for last NMI */
if (refcount_dec_and_test(&ppi_nmi_refs[idx]))
desc->handle_irq = handle_percpu_devid_irq;
} else {
desc->handle_irq = handle_fasteoi_irq;
}
gic_irq_set_prio(d, GICD_INT_DEF_PRI);
}
static void gic_eoi_irq(struct irq_data *d)
{
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
write_gicreg(gic_irq(d), ICC_EOIR1_EL1);
isb();
}
static void gic_eoimode1_eoi_irq(struct irq_data *d)
{
/*
* No need to deactivate an LPI, or an interrupt that
* is is getting forwarded to a vcpu.
*/
if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
return;
gic_write_dir(gic_irq(d));
}
static int gic_set_type(struct irq_data *d, unsigned int type)
{
enum gic_intid_range range;
unsigned int irq = gic_irq(d);
void __iomem *base;
u32 offset, index;
int ret;
range = get_intid_range(d);
/* Interrupt configuration for SGIs can't be changed */
if (range == SGI_RANGE)
return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0;
/* SPIs have restrictions on the supported types */
if ((range == SPI_RANGE || range == ESPI_RANGE) &&
type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
return -EINVAL;
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_data.dist_base;
offset = convert_offset_index(d, GICD_ICFGR, &index);
ret = gic_configure_irq(index, type, base + offset, NULL);
if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) {
/* Misconfigured PPIs are usually not fatal */
pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq);
ret = 0;
}
return ret;
}
static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
{
if (get_intid_range(d) == SGI_RANGE)
return -EINVAL;
if (vcpu)
irqd_set_forwarded_to_vcpu(d);
else
irqd_clr_forwarded_to_vcpu(d);
return 0;
}
static u64 gic_mpidr_to_affinity(unsigned long mpidr)
{
u64 aff;
aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
MPIDR_AFFINITY_LEVEL(mpidr, 0));
return aff;
}
static void gic_deactivate_unhandled(u32 irqnr)
{
if (static_branch_likely(&supports_deactivate_key)) {
if (irqnr < 8192)
gic_write_dir(irqnr);
} else {
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
write_gicreg(irqnr, ICC_EOIR1_EL1);
isb();
}
}
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
/*
* Follow a read of the IAR with any HW maintenance that needs to happen prior
* to invoking the relevant IRQ handler. We must do two things:
*
* (1) Ensure instruction ordering between a read of IAR and subsequent
* instructions in the IRQ handler using an ISB.
*
* It is possible for the IAR to report an IRQ which was signalled *after*
* the CPU took an IRQ exception as multiple interrupts can race to be
* recognized by the GIC, earlier interrupts could be withdrawn, and/or
* later interrupts could be prioritized by the GIC.
*
* For devices which are tightly coupled to the CPU, such as PMUs, a
* context synchronization event is necessary to ensure that system
* register state is not stale, as these may have been indirectly written
* *after* exception entry.
*
* (2) Deactivate the interrupt when EOI mode 1 is in use.
*/
static inline void gic_complete_ack(u32 irqnr)
{
if (static_branch_likely(&supports_deactivate_key))
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
write_gicreg(irqnr, ICC_EOIR1_EL1);
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
isb();
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
static bool gic_rpr_is_nmi_prio(void)
{
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (!gic_supports_nmi())
return false;
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
return unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI));
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
static bool gic_irqnr_is_special(u32 irqnr)
{
return irqnr >= 1020 && irqnr <= 1023;
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs)
{
if (gic_irqnr_is_special(irqnr))
return;
irqchip/gic-v3: Refactor ISB + EOIR at ack time There are cases where a context synchronization event is necessary between an IRQ being raised and being handled, and there are races such that we cannot rely upon the exception entry being subsequent to the interrupt being raised. To fix this, we place an ISB between a read of IAR and the subsequent invocation of an IRQ handler. When EOI mode 1 is in use, we need to EOI an interrupt prior to invoking its handler, and we have a write to EOIR for this. As this write to EOIR requires an ISB, and this is provided by the gic_write_eoir() helper, we omit the usual ISB in this case, with the logic being: | if (static_branch_likely(&supports_deactivate_key)) | gic_write_eoir(irqnr); | else | isb(); This is somewhat opaque, and it would be a little clearer if there were an unconditional ISB, with only the write to EOIR being conditional, e.g. | if (static_branch_likely(&supports_deactivate_key)) | write_gicreg(irqnr, ICC_EOIR1_EL1); | | isb(); This patch rewrites the code that way, with this logic factored into a new helper function with comments explaining what the ISB is for, as were originally laid out in commit: 39a06b67c2c1256b ("irqchip/gic: Ensure we have an ISB between ack and ->handle_irq") Note that since then, we removed the IAR polling in commit: 342677d70ab92142 ("irqchip/gic-v3: Remove acknowledge loop") ... which removed one of the two race conditions. For consistency, other portions of the driver are made to manipulate EOIR using write_gicreg() and explcit ISBs, and the gic_write_eoir() helper function is removed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-3-mark.rutland@arm.com
2022-05-13 21:30:37 +08:00
gic_complete_ack(irqnr);
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (generic_handle_domain_irq(gic_data.domain, irqnr)) {
WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr);
gic_deactivate_unhandled(irqnr);
}
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs)
{
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (gic_irqnr_is_special(irqnr))
return;
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
gic_complete_ack(irqnr);
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (generic_handle_domain_nmi(gic_data.domain, irqnr)) {
WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr);
gic_deactivate_unhandled(irqnr);
}
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
/*
* An exception has been taken from a context with IRQs enabled, and this could
* be an IRQ or an NMI.
*
* The entry code called us with DAIF.IF set to keep NMIs masked. We must clear
* DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning,
* after handling any NMI but before handling any IRQ.
*
* The entry code has performed IRQ entry, and if an NMI is detected we must
* perform NMI entry/exit around invoking the handler.
*/
static void __gic_handle_irq_from_irqson(struct pt_regs *regs)
{
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
bool is_nmi;
u32 irqnr;
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
irqnr = gic_read_iar();
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
is_nmi = gic_rpr_is_nmi_prio();
irqchip/gic-v3: Do not enable irqs when handling spurious interrups We triggered the following error while running our 4.19 kernel with the pseudo-NMI patches backported to it: [ 14.816231] ------------[ cut here ]------------ [ 14.816231] kernel BUG at irq.c:99! [ 14.816232] Internal error: Oops - BUG: 0 [#1] SMP [ 14.816232] Process swapper/0 (pid: 0, stack limit = 0x(____ptrval____)) [ 14.816233] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 4.19.95.aarch64 #14 [ 14.816233] Hardware name: evb (DT) [ 14.816234] pstate: 80400085 (Nzcv daIf +PAN -UAO) [ 14.816234] pc : asm_nmi_enter+0x94/0x98 [ 14.816235] lr : asm_nmi_enter+0x18/0x98 [ 14.816235] sp : ffff000008003c50 [ 14.816235] pmr_save: 00000070 [ 14.816237] x29: ffff000008003c50 x28: ffff0000095f56c0 [ 14.816238] x27: 0000000000000000 x26: ffff000008004000 [ 14.816239] x25: 00000000015e0000 x24: ffff8008fb916000 [ 14.816240] x23: 0000000020400005 x22: ffff0000080817cc [ 14.816241] x21: ffff000008003da0 x20: 0000000000000060 [ 14.816242] x19: 00000000000003ff x18: ffffffffffffffff [ 14.816243] x17: 0000000000000008 x16: 003d090000000000 [ 14.816244] x15: ffff0000095ea6c8 x14: ffff8008fff5ab40 [ 14.816244] x13: ffff8008fff58b9d x12: 0000000000000000 [ 14.816245] x11: ffff000008c8a200 x10: 000000008e31fca5 [ 14.816246] x9 : ffff000008c8a208 x8 : 000000000000000f [ 14.816247] x7 : 0000000000000004 x6 : ffff8008fff58b9e [ 14.816248] x5 : 0000000000000000 x4 : 0000000080000000 [ 14.816249] x3 : 0000000000000000 x2 : 0000000080000000 [ 14.816250] x1 : 0000000000120000 x0 : ffff0000095f56c0 [ 14.816251] Call trace: [ 14.816251] asm_nmi_enter+0x94/0x98 [ 14.816251] el1_irq+0x8c/0x180 (IRQ C) [ 14.816252] gic_handle_irq+0xbc/0x2e4 [ 14.816252] el1_irq+0xcc/0x180 (IRQ B) [ 14.816253] arch_timer_handler_virt+0x38/0x58 [ 14.816253] handle_percpu_devid_irq+0x90/0x240 [ 14.816253] generic_handle_irq+0x34/0x50 [ 14.816254] __handle_domain_irq+0x68/0xc0 [ 14.816254] gic_handle_irq+0xf8/0x2e4 [ 14.816255] el1_irq+0xcc/0x180 (IRQ A) [ 14.816255] arch_cpu_idle+0x34/0x1c8 [ 14.816255] default_idle_call+0x24/0x44 [ 14.816256] do_idle+0x1d0/0x2c8 [ 14.816256] cpu_startup_entry+0x28/0x30 [ 14.816256] rest_init+0xb8/0xc8 [ 14.816257] start_kernel+0x4c8/0x4f4 [ 14.816257] Code: 940587f1 d5384100 b9401001 36a7fd01 (d4210000) [ 14.816258] Modules linked in: start_dp(O) smeth(O) [ 15.103092] ---[ end trace 701753956cb14aa8 ]--- [ 15.103093] Kernel panic - not syncing: Fatal exception in interrupt [ 15.103099] SMP: stopping secondary CPUs [ 15.103100] Kernel Offset: disabled [ 15.103100] CPU features: 0x36,a2400218 [ 15.103100] Memory Limit: none which is cause by a 'BUG_ON(in_nmi())' in nmi_enter(). From the call trace, we can find three interrupts (noted A, B, C above): interrupt (A) is preempted by (B), which is further interrupted by (C). Subsequent investigations show that (B) results in nmi_enter() being called, but that it actually is a spurious interrupt. Furthermore, interrupts are reenabled in the context of (B), and (C) fires with NMI priority. We end-up with a nested NMI situation, something we definitely do not want to (and cannot) handle. The bug here is that spurious interrupts should never result in any state change, and we should just return to the interrupted context. Moving the handling of spurious interrupts as early as possible in the GICv3 handler fixes this issue. Fixes: 3f1f3234bc2d ("irqchip/gic-v3: Switch to PMR masking before calling IRQ handler") Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: He Ying <heying24@huawei.com> [maz: rewrote commit message, corrected Fixes: tag] Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20210423083516.170111-1-heying24@huawei.com Cc: stable@vger.kernel.org
2021-04-23 16:35:16 +08:00
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (is_nmi) {
nmi_enter();
__gic_handle_nmi(irqnr, regs);
nmi_exit();
}
if (gic_prio_masking_enabled()) {
gic_pmr_mask_irqs();
gic_arch_enable_irqs();
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
if (!is_nmi)
__gic_handle_irq(irqnr, regs);
}
irqchip/gic-v3: Fix priority mask handling When a kernel is built with CONFIG_ARM64_PSEUDO_NMI=y and pseudo-NMIs are enabled at runtime, GICv3's gic_handle_irq() can leave DAIF and ICC_PMR_EL1 in an unexpected state in some cases, breaking subsequent usage of local_irq_enable() and resulting in softirqs being run with IRQs erroneously masked (possibly resulting in deadlocks). This can happen when an IRQ exception is taken from a context where regular IRQs were unmasked, and either: (1) ICC_IAR1_EL1 indicates a special INTID (e.g. as a result of an IRQ being withdrawn since the IRQ exception was taken). (2) ICC_IAR1_EL1 and ICC_RPR_EL1 indicate an NMI was acknowledged. When an NMI is taken from a context where regular IRQs were masked, there is no problem. When CONFIG_ARM64_DEBUG_PRIORITY_MASKING=y, this can be detected with perf, e.g. | # ./perf record -a -g -e cycles:k ls -alR / > /dev/null 2>&1 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 14 at arch/arm64/include/asm/irqflags.h:32 arch_local_irq_enable+0x4c/0x6c | Modules linked in: | CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 5.18.0-rc5-00004-g876c38e3d20b #12 | Hardware name: linux,dummy-virt (DT) | pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : arch_local_irq_enable+0x4c/0x6c | lr : __do_softirq+0x110/0x5d8 | sp : ffff8000080bbbc0 | pmr_save: 000000f0 | x29: ffff8000080bbbc0 x28: ffff316ac3a6ca40 x27: 0000000000000000 | x26: 0000000000000000 x25: ffffa04611c06008 x24: ffffa04611c06008 | x23: 0000000040400005 x22: 0000000000000200 x21: ffff8000080bbe20 | x20: ffffa0460fe10320 x19: 0000000000000009 x18: 0000000000000000 | x17: ffff91252dfa9000 x16: ffff800008004000 x15: 0000000000004000 | x14: 0000000000000028 x13: ffffa0460fe17578 x12: ffffa0460fed4294 | x11: ffffa0460fedc168 x10: ffffffffffffff80 x9 : ffffa0460fe10a70 | x8 : ffffa0460fedc168 x7 : 000000000000b762 x6 : 00000000057c3bdf | x5 : ffff8000080bbb18 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ffff91252dfa9000 x1 : 0000000000000060 x0 : 00000000000000f0 | Call trace: | arch_local_irq_enable+0x4c/0x6c | __irq_exit_rcu+0x180/0x1ac | irq_exit_rcu+0x1c/0x44 | el1_interrupt+0x4c/0xe4 | el1h_64_irq_handler+0x18/0x24 | el1h_64_irq+0x74/0x78 | smpboot_thread_fn+0x68/0x2c0 | kthread+0x124/0x130 | ret_from_fork+0x10/0x20 | irq event stamp: 193241 | hardirqs last enabled at (193240): [<ffffa0460fe10a9c>] __do_softirq+0x10c/0x5d8 | hardirqs last disabled at (193241): [<ffffa0461102ffe4>] el1_dbg+0x24/0x90 | softirqs last enabled at (193234): [<ffffa0460fe10e00>] __do_softirq+0x470/0x5d8 | softirqs last disabled at (193239): [<ffffa0460fea9944>] __irq_exit_rcu+0x180/0x1ac | ---[ end trace 0000000000000000 ]--- The necessary manipulation of DAIF and ICC_PMR_EL1 depends on the interrupted context, but the structure of gic_handle_irq() makes this also depend on whether the GIC reports an IRQ, NMI, or special INTID: * When the interrupted context had regular IRQs masked (and hence the interrupt must be an NMI), the entry code performs the NMI entry/exit and gic_handle_irq() should return with DAIF and ICC_PMR_EL1 unchanged. This is handled correctly today. * When the interrupted context had regular IRQs unmasked, the entry code performs IRQ entry/exit, but expects gic_handle_irq() to always update ICC_PMR_EL1 and DAIF.IF to unmask NMIs (but not regular IRQs) prior to returning (which it must do prior to invoking any regular IRQ handler). This unbalanced calling convention is necessary because we don't know whether an NMI has been taken until acknowledged by a read from ICC_IAR1_EL1, and so we need to perform the read with NMI masked in case an NMI has been taken (and needs to be handled with NMIs masked). Unfortunately, this is not handled consistently: - When ICC_IAR1_EL1 reports a special INTID, gic_handle_irq() returns immediately without manipulating ICC_PMR_EL1 and DAIF. - When RPR_EL1 indicates an NMI, gic_handle_irq() calls gic_handle_nmi() to invoke the NMI handler, then returns without manipulating ICC_PMR_EL1 and DAIF. - For regular IRQs, gic_handle_irq() manipulates ICC_PMR_EL1 and DAIF prior to invoking the IRQ handler. There were related problems with special INTID handling in the past, where if an exception was taken from a context with regular IRQs masked and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously unmask NMIs in NMI context permitted an unexpected nested NMI. That case specifically was fixed by commit: a97709f563a078e2 ("irqchip/gic-v3: Do not enable irqs when handling spurious interrups") ... but unfortunately that commit added an inverse problem, where if an exception was taken from a context with regular IRQs *unmasked* and ICC_IAR_EL1 reported a special INTID, gic_handle_irq() would erroneously fail to unmask NMIs (and consequently regular IRQs could not be unmasked during softirq processing). Before and after that commit, if an NMI was taken from a context with regular IRQs unmasked gic_handle_irq() would not unmask NMIs prior to returning, leading to the same problem with softirq handling. This patch fixes this by restructuring gic_handle_irq(), splitting it into separate irqson/irqsoff helper functions which consistently perform the DAIF + ICC_PMR1_EL1 manipulation based upon the interrupted context, regardless of the event indicated by ICC_IAR1_EL1. The special INTID handling is moved into the low-level IRQ/NMI handler invocation helper functions, so that early returns don't prevent the required manipulation of DAIF + ICC_PMR_EL1. Fixes: f32c926651dcd168 ("irqchip/gic-v3: Handle pseudo-NMIs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220513133038.226182-4-mark.rutland@arm.com
2022-05-13 21:30:38 +08:00
/*
* An exception has been taken from a context with IRQs disabled, which can only
* be an NMI.
*
* The entry code called us with DAIF.IF set to keep NMIs masked. We must leave
* DAIF.IF (and ICC_PMR_EL1) unchanged.
*
* The entry code has performed NMI entry.
*/
static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs)
{
u64 pmr;
u32 irqnr;
/*
* We were in a context with IRQs disabled. However, the
* entry code has set PMR to a value that allows any
* interrupt to be acknowledged, and not just NMIs. This can
* lead to surprising effects if the NMI has been retired in
* the meantime, and that there is an IRQ pending. The IRQ
* would then be taken in NMI context, something that nobody
* wants to debug twice.
*
* Until we sort this, drop PMR again to a level that will
* actually only allow NMIs before reading IAR, and then
* restore it to what it was.
*/
pmr = gic_read_pmr();
gic_pmr_mask_irqs();
isb();
irqnr = gic_read_iar();
gic_write_pmr(pmr);
__gic_handle_nmi(irqnr, regs);
}
static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs)))
__gic_handle_irq_from_irqsoff(regs);
else
__gic_handle_irq_from_irqson(regs);
}
static u32 gic_get_pribits(void)
{
u32 pribits;
pribits = gic_read_ctlr();
pribits &= ICC_CTLR_EL1_PRI_BITS_MASK;
pribits >>= ICC_CTLR_EL1_PRI_BITS_SHIFT;
pribits++;
return pribits;
}
static bool gic_has_group0(void)
{
u32 val;
u32 old_pmr;
old_pmr = gic_read_pmr();
/*
* Let's find out if Group0 is under control of EL3 or not by
* setting the highest possible, non-zero priority in PMR.
*
* If SCR_EL3.FIQ is set, the priority gets shifted down in
* order for the CPU interface to set bit 7, and keep the
* actual priority in the non-secure range. In the process, it
* looses the least significant bit and the actual priority
* becomes 0x80. Reading it back returns 0, indicating that
* we're don't have access to Group0.
*/
gic_write_pmr(BIT(8 - gic_get_pribits()));
val = gic_read_pmr();
gic_write_pmr(old_pmr);
return val != 0;
}
static void __init gic_dist_init(void)
{
unsigned int i;
u64 affinity;
void __iomem *base = gic_data.dist_base;
u32 val;
/* Disable the distributor */
writel_relaxed(0, base + GICD_CTLR);
gic_dist_wait_for_rwp();
/*
* Configure SPIs as non-secure Group-1. This will only matter
* if the GIC only has a single security state. This will not
* do the right thing if the kernel is running in secure mode,
* but that's not the intended use case anyway.
*/
for (i = 32; i < GIC_LINE_NR; i += 32)
writel_relaxed(~0, base + GICD_IGROUPR + i / 8);
/* Extended SPI range, not handled by the GICv2/GICv3 common code */
for (i = 0; i < GIC_ESPI_NR; i += 32) {
writel_relaxed(~0U, base + GICD_ICENABLERnE + i / 8);
writel_relaxed(~0U, base + GICD_ICACTIVERnE + i / 8);
}
for (i = 0; i < GIC_ESPI_NR; i += 32)
writel_relaxed(~0U, base + GICD_IGROUPRnE + i / 8);
for (i = 0; i < GIC_ESPI_NR; i += 16)
writel_relaxed(0, base + GICD_ICFGRnE + i / 4);
for (i = 0; i < GIC_ESPI_NR; i += 4)
writel_relaxed(GICD_INT_DEF_PRI_X4, base + GICD_IPRIORITYRnE + i);
/* Now do the common stuff */
gic_dist_config(base, GIC_LINE_NR, NULL);
val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1;
if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) {
pr_info("Enabling SGIs without active state\n");
val |= GICD_CTLR_nASSGIreq;
}
/* Enable distributor with ARE, Group1, and wait for it to drain */
writel_relaxed(val, base + GICD_CTLR);
gic_dist_wait_for_rwp();
/*
* Set all global interrupts to the boot CPU only. ARE must be
* enabled.
*/
affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
for (i = 32; i < GIC_LINE_NR; i++)
gic_write_irouter(affinity, base + GICD_IROUTER + i * 8);
for (i = 0; i < GIC_ESPI_NR; i++)
gic_write_irouter(affinity, base + GICD_IROUTERnE + i * 8);
}
static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *))
{
int ret = -ENODEV;
int i;
for (i = 0; i < gic_data.nr_redist_regions; i++) {
void __iomem *ptr = gic_data.redist_regions[i].redist_base;
u64 typer;
u32 reg;
reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
if (reg != GIC_PIDR2_ARCH_GICv3 &&
reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
pr_warn("No redistributor present @%p\n", ptr);
break;
}
do {
typer = gic_read_typer(ptr + GICR_TYPER);
ret = fn(gic_data.redist_regions + i, ptr);
if (!ret)
return 0;
if (gic_data.redist_regions[i].single_redist)
break;
if (gic_data.redist_stride) {
ptr += gic_data.redist_stride;
} else {
ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
if (typer & GICR_TYPER_VLPIS)
ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
}
} while (!(typer & GICR_TYPER_LAST));
}
return ret ? -ENODEV : 0;
}
static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr)
{
unsigned long mpidr = cpu_logical_map(smp_processor_id());
u64 typer;
u32 aff;
/*
* Convert affinity to a 32bit value that can be matched to
* GICR_TYPER bits [63:32].
*/
aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
MPIDR_AFFINITY_LEVEL(mpidr, 0));
typer = gic_read_typer(ptr + GICR_TYPER);
if ((typer >> 32) == aff) {
u64 offset = ptr - region->redist_base;
raw_spin_lock_init(&gic_data_rdist()->rd_lock);
gic_data_rdist_rd_base() = ptr;
gic_data_rdist()->phys_base = region->phys_base + offset;
pr_info("CPU%d: found redistributor %lx region %d:%pa\n",
smp_processor_id(), mpidr,
(int)(region - gic_data.redist_regions),
&gic_data_rdist()->phys_base);
return 0;
}
/* Try next one */
return 1;
}
static int gic_populate_rdist(void)
{
if (gic_iterate_rdists(__gic_populate_rdist) == 0)
return 0;
/* We couldn't even deal with ourselves... */
WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n",
smp_processor_id(),
(unsigned long)cpu_logical_map(smp_processor_id()));
return -ENODEV;
}
static int __gic_update_rdist_properties(struct redist_region *region,
void __iomem *ptr)
{
u64 typer = gic_read_typer(ptr + GICR_TYPER);
u32 ctlr = readl_relaxed(ptr + GICR_CTLR);
/* Boot-time cleanip */
if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) {
u64 val;
/* Deactivate any present vPE */
val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER);
if (val & GICR_VPENDBASER_Valid)
gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast,
ptr + SZ_128K + GICR_VPENDBASER);
/* Mark the VPE table as invalid */
val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER);
val &= ~GICR_VPROPBASER_4_1_VALID;
gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER);
}
gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS);
/*
* TYPER.RVPEID implies some form of DirectLPI, no matter what the
* doc says... :-/ And CTLR.IR implies another subset of DirectLPI
* that the ITS driver can make use of for LPIs (and not VLPIs).
*
* These are 3 different ways to express the same thing, depending
* on the revision of the architecture and its relaxations over
* time. Just group them under the 'direct_lpi' banner.
*/
gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
!!(ctlr & GICR_CTLR_IR) |
gic_data.rdists.has_rvpeid);
gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY);
/* Detect non-sensical configurations */
if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
gic_data.rdists.has_direct_lpi = false;
gic_data.rdists.has_vlpis = false;
gic_data.rdists.has_rvpeid = false;
}
gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr);
return 1;
}
static void gic_update_rdist_properties(void)
{
gic_data.ppi_nr = UINT_MAX;
gic_iterate_rdists(__gic_update_rdist_properties);
if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
gic_data.ppi_nr = 0;
pr_info("GICv3 features: %d PPIs%s%s\n",
gic_data.ppi_nr,
gic_data.has_rss ? ", RSS" : "",
gic_data.rdists.has_direct_lpi ? ", DirectLPI" : "");
if (gic_data.rdists.has_vlpis)
pr_info("GICv4 features: %s%s%s\n",
gic_data.rdists.has_direct_lpi ? "DirectLPI " : "",
gic_data.rdists.has_rvpeid ? "RVPEID " : "",
gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
}
/* Check whether it's single security state view */
static inline bool gic_dist_security_disabled(void)
{
return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS;
}
static void gic_cpu_sys_reg_init(void)
{
int i, cpu = smp_processor_id();
u64 mpidr = cpu_logical_map(cpu);
u64 need_rss = MPIDR_RS(mpidr);
bool group0;
u32 pribits;
/*
* Need to check that the SRE bit has actually been set. If
* not, it means that SRE is disabled at EL2. We're going to
* die painfully, and there is nothing we can do about it.
*
* Kindly inform the luser.
*/
if (!gic_enable_sre())
pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
pribits = gic_get_pribits();
group0 = gic_has_group0();
/* Set priority mask register */
if (!gic_prio_masking_enabled()) {
write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1);
} else if (gic_supports_nmi()) {
/*
* Mismatch configuration with boot CPU, the system is likely
* to die as interrupt masking will not work properly on all
* CPUs
*
* The boot CPU calls this function before enabling NMI support,
* and as a result we'll never see this warning in the boot path
* for that CPU.
*/
if (static_branch_unlikely(&gic_nonsecure_priorities))
WARN_ON(!group0 || gic_dist_security_disabled());
else
WARN_ON(group0 && !gic_dist_security_disabled());
}
/*
* Some firmwares hand over to the kernel with the BPR changed from
* its reset value (and with a value large enough to prevent
* any pre-emptive interrupts from working at all). Writing a zero
* to BPR restores is reset value.
*/
gic_write_bpr1(0);
if (static_branch_likely(&supports_deactivate_key)) {
/* EOI drops priority only (mode 1) */
gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop);
} else {
/* EOI deactivates interrupt too (mode 0) */
gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
}
/* Always whack Group0 before Group1 */
if (group0) {
switch(pribits) {
case 8:
case 7:
write_gicreg(0, ICC_AP0R3_EL1);
write_gicreg(0, ICC_AP0R2_EL1);
fallthrough;
case 6:
write_gicreg(0, ICC_AP0R1_EL1);
fallthrough;
case 5:
case 4:
write_gicreg(0, ICC_AP0R0_EL1);
}
isb();
}
switch(pribits) {
case 8:
case 7:
write_gicreg(0, ICC_AP1R3_EL1);
write_gicreg(0, ICC_AP1R2_EL1);
fallthrough;
case 6:
write_gicreg(0, ICC_AP1R1_EL1);
fallthrough;
case 5:
case 4:
write_gicreg(0, ICC_AP1R0_EL1);
}
isb();
/* ... and let's hit the road... */
gic_write_grpen1(1);
/* Keep the RSS capability status in per_cpu variable */
per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS);
/* Check all the CPUs have capable of sending SGIs to other CPUs */
for_each_online_cpu(i) {
bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu);
need_rss |= MPIDR_RS(cpu_logical_map(i));
if (need_rss && (!have_rss))
pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n",
cpu, (unsigned long)mpidr,
i, (unsigned long)cpu_logical_map(i));
}
/**
* GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0,
* writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED
* UNPREDICTABLE choice of :
* - The write is ignored.
* - The RS field is treated as 0.
*/
if (need_rss && (!gic_data.has_rss))
pr_crit_once("RSS is required but GICD doesn't support it\n");
}
static bool gicv3_nolpi;
static int __init gicv3_nolpi_cfg(char *buf)
{
return strtobool(buf, &gicv3_nolpi);
}
early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg);
static int gic_dist_supports_lpis(void)
{
return (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) &&
!!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS) &&
!gicv3_nolpi);
}
static void gic_cpu_init(void)
{
void __iomem *rbase;
int i;
/* Register ourselves with the rest of the world */
if (gic_populate_rdist())
return;
gic_enable_redist(true);
WARN((gic_data.ppi_nr > 16 || GIC_ESPI_NR != 0) &&
!(gic_read_ctlr() & ICC_CTLR_EL1_ExtRange),
"Distributor has extended ranges, but CPU%d doesn't\n",
smp_processor_id());
rbase = gic_data_rdist_sgi_base();
/* Configure SGIs/PPIs as non-secure Group-1 */
for (i = 0; i < gic_data.ppi_nr + 16; i += 32)
writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8);
gic_cpu_config(rbase, gic_data.ppi_nr + 16, gic_redist_wait_for_rwp);
/* initialise system registers */
gic_cpu_sys_reg_init();
}
#ifdef CONFIG_SMP
#define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT)
#define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL)
static int gic_starting_cpu(unsigned int cpu)
{
gic_cpu_init();
if (gic_dist_supports_lpis())
its_cpu_init();
return 0;
}
static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
unsigned long cluster_id)
{
irqchip/gicv3: Silence noisy DEBUG_PER_CPU_MAPS warning gic_raise_softirq() walks the list of cpus using for_each_cpu(), it calls gic_compute_target_list() which advances the iterator by the number of CPUs in the cluster. If gic_compute_target_list() reaches the last CPU it leaves the iterator pointing at the last CPU. This means the next time round the for_each_cpu() loop cpumask_next() will be called with an invalid CPU. This triggers a warning when built with CONFIG_DEBUG_PER_CPU_MAPS: [ 3.077738] GICv3: CPU1: found redistributor 1 region 0:0x000000002f120000 [ 3.077943] CPU1: Booted secondary processor [410fd0f0] [ 3.078542] ------------[ cut here ]------------ [ 3.078746] WARNING: CPU: 1 PID: 0 at ../include/linux/cpumask.h:121 gic_raise_softirq+0x12c/0x170 [ 3.078812] Modules linked in: [ 3.078869] [ 3.078930] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc5+ #5188 [ 3.078994] Hardware name: Foundation-v8A (DT) [ 3.079059] task: ffff80087a1a0080 task.stack: ffff80087a19c000 [ 3.079145] PC is at gic_raise_softirq+0x12c/0x170 [ 3.079226] LR is at gic_raise_softirq+0xa4/0x170 [ 3.079296] pc : [<ffff0000083ead24>] lr : [<ffff0000083eac9c>] pstate: 200001c9 [ 3.081139] Call trace: [ 3.081202] Exception stack(0xffff80087a19fbe0 to 0xffff80087a19fd10) [ 3.082269] [<ffff0000083ead24>] gic_raise_softirq+0x12c/0x170 [ 3.082354] [<ffff00000808e614>] smp_send_reschedule+0x34/0x40 [ 3.082433] [<ffff0000080e80a0>] resched_curr+0x50/0x88 [ 3.082512] [<ffff0000080e89d0>] check_preempt_curr+0x60/0xd0 [ 3.082593] [<ffff0000080e8a60>] ttwu_do_wakeup+0x20/0xe8 [ 3.082672] [<ffff0000080e8bb8>] ttwu_do_activate+0x90/0xc0 [ 3.082753] [<ffff0000080ea9a4>] try_to_wake_up+0x224/0x370 [ 3.082836] [<ffff0000080eabc8>] default_wake_function+0x10/0x18 [ 3.082920] [<ffff000008103134>] __wake_up_common+0x5c/0xa0 [ 3.083003] [<ffff0000081031f4>] __wake_up_locked+0x14/0x20 [ 3.083086] [<ffff000008103f80>] complete+0x40/0x60 [ 3.083168] [<ffff00000808df7c>] secondary_start_kernel+0x15c/0x1d0 [ 3.083240] [<00000000808911a4>] 0x808911a4 [ 3.113401] Detected PIPT I-cache on CPU2 Avoid updating the iterator if the next call to cpumask_next() would cause the for_each_cpu() loop to exit. There is no change to gic_raise_softirq()'s behaviour, (cpumask_next()s eventual call to _find_next_bit() will return early as start >= nbits), this patch just silences the warning. Fixes: 021f653791ad ("irqchip: gic-v3: Initial support for GICv3") Signed-off-by: James Morse <james.morse@arm.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Jason Cooper <jason@lakedaemon.net> Link: http://lkml.kernel.org/r/1474306155-3303-1-git-send-email-james.morse@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-09-20 01:29:15 +08:00
int next_cpu, cpu = *base_cpu;
unsigned long mpidr = cpu_logical_map(cpu);
u16 tlist = 0;
while (cpu < nr_cpu_ids) {
tlist |= 1 << (mpidr & 0xf);
irqchip/gicv3: Silence noisy DEBUG_PER_CPU_MAPS warning gic_raise_softirq() walks the list of cpus using for_each_cpu(), it calls gic_compute_target_list() which advances the iterator by the number of CPUs in the cluster. If gic_compute_target_list() reaches the last CPU it leaves the iterator pointing at the last CPU. This means the next time round the for_each_cpu() loop cpumask_next() will be called with an invalid CPU. This triggers a warning when built with CONFIG_DEBUG_PER_CPU_MAPS: [ 3.077738] GICv3: CPU1: found redistributor 1 region 0:0x000000002f120000 [ 3.077943] CPU1: Booted secondary processor [410fd0f0] [ 3.078542] ------------[ cut here ]------------ [ 3.078746] WARNING: CPU: 1 PID: 0 at ../include/linux/cpumask.h:121 gic_raise_softirq+0x12c/0x170 [ 3.078812] Modules linked in: [ 3.078869] [ 3.078930] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc5+ #5188 [ 3.078994] Hardware name: Foundation-v8A (DT) [ 3.079059] task: ffff80087a1a0080 task.stack: ffff80087a19c000 [ 3.079145] PC is at gic_raise_softirq+0x12c/0x170 [ 3.079226] LR is at gic_raise_softirq+0xa4/0x170 [ 3.079296] pc : [<ffff0000083ead24>] lr : [<ffff0000083eac9c>] pstate: 200001c9 [ 3.081139] Call trace: [ 3.081202] Exception stack(0xffff80087a19fbe0 to 0xffff80087a19fd10) [ 3.082269] [<ffff0000083ead24>] gic_raise_softirq+0x12c/0x170 [ 3.082354] [<ffff00000808e614>] smp_send_reschedule+0x34/0x40 [ 3.082433] [<ffff0000080e80a0>] resched_curr+0x50/0x88 [ 3.082512] [<ffff0000080e89d0>] check_preempt_curr+0x60/0xd0 [ 3.082593] [<ffff0000080e8a60>] ttwu_do_wakeup+0x20/0xe8 [ 3.082672] [<ffff0000080e8bb8>] ttwu_do_activate+0x90/0xc0 [ 3.082753] [<ffff0000080ea9a4>] try_to_wake_up+0x224/0x370 [ 3.082836] [<ffff0000080eabc8>] default_wake_function+0x10/0x18 [ 3.082920] [<ffff000008103134>] __wake_up_common+0x5c/0xa0 [ 3.083003] [<ffff0000081031f4>] __wake_up_locked+0x14/0x20 [ 3.083086] [<ffff000008103f80>] complete+0x40/0x60 [ 3.083168] [<ffff00000808df7c>] secondary_start_kernel+0x15c/0x1d0 [ 3.083240] [<00000000808911a4>] 0x808911a4 [ 3.113401] Detected PIPT I-cache on CPU2 Avoid updating the iterator if the next call to cpumask_next() would cause the for_each_cpu() loop to exit. There is no change to gic_raise_softirq()'s behaviour, (cpumask_next()s eventual call to _find_next_bit() will return early as start >= nbits), this patch just silences the warning. Fixes: 021f653791ad ("irqchip: gic-v3: Initial support for GICv3") Signed-off-by: James Morse <james.morse@arm.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Jason Cooper <jason@lakedaemon.net> Link: http://lkml.kernel.org/r/1474306155-3303-1-git-send-email-james.morse@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-09-20 01:29:15 +08:00
next_cpu = cpumask_next(cpu, mask);
if (next_cpu >= nr_cpu_ids)
goto out;
irqchip/gicv3: Silence noisy DEBUG_PER_CPU_MAPS warning gic_raise_softirq() walks the list of cpus using for_each_cpu(), it calls gic_compute_target_list() which advances the iterator by the number of CPUs in the cluster. If gic_compute_target_list() reaches the last CPU it leaves the iterator pointing at the last CPU. This means the next time round the for_each_cpu() loop cpumask_next() will be called with an invalid CPU. This triggers a warning when built with CONFIG_DEBUG_PER_CPU_MAPS: [ 3.077738] GICv3: CPU1: found redistributor 1 region 0:0x000000002f120000 [ 3.077943] CPU1: Booted secondary processor [410fd0f0] [ 3.078542] ------------[ cut here ]------------ [ 3.078746] WARNING: CPU: 1 PID: 0 at ../include/linux/cpumask.h:121 gic_raise_softirq+0x12c/0x170 [ 3.078812] Modules linked in: [ 3.078869] [ 3.078930] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc5+ #5188 [ 3.078994] Hardware name: Foundation-v8A (DT) [ 3.079059] task: ffff80087a1a0080 task.stack: ffff80087a19c000 [ 3.079145] PC is at gic_raise_softirq+0x12c/0x170 [ 3.079226] LR is at gic_raise_softirq+0xa4/0x170 [ 3.079296] pc : [<ffff0000083ead24>] lr : [<ffff0000083eac9c>] pstate: 200001c9 [ 3.081139] Call trace: [ 3.081202] Exception stack(0xffff80087a19fbe0 to 0xffff80087a19fd10) [ 3.082269] [<ffff0000083ead24>] gic_raise_softirq+0x12c/0x170 [ 3.082354] [<ffff00000808e614>] smp_send_reschedule+0x34/0x40 [ 3.082433] [<ffff0000080e80a0>] resched_curr+0x50/0x88 [ 3.082512] [<ffff0000080e89d0>] check_preempt_curr+0x60/0xd0 [ 3.082593] [<ffff0000080e8a60>] ttwu_do_wakeup+0x20/0xe8 [ 3.082672] [<ffff0000080e8bb8>] ttwu_do_activate+0x90/0xc0 [ 3.082753] [<ffff0000080ea9a4>] try_to_wake_up+0x224/0x370 [ 3.082836] [<ffff0000080eabc8>] default_wake_function+0x10/0x18 [ 3.082920] [<ffff000008103134>] __wake_up_common+0x5c/0xa0 [ 3.083003] [<ffff0000081031f4>] __wake_up_locked+0x14/0x20 [ 3.083086] [<ffff000008103f80>] complete+0x40/0x60 [ 3.083168] [<ffff00000808df7c>] secondary_start_kernel+0x15c/0x1d0 [ 3.083240] [<00000000808911a4>] 0x808911a4 [ 3.113401] Detected PIPT I-cache on CPU2 Avoid updating the iterator if the next call to cpumask_next() would cause the for_each_cpu() loop to exit. There is no change to gic_raise_softirq()'s behaviour, (cpumask_next()s eventual call to _find_next_bit() will return early as start >= nbits), this patch just silences the warning. Fixes: 021f653791ad ("irqchip: gic-v3: Initial support for GICv3") Signed-off-by: James Morse <james.morse@arm.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Jason Cooper <jason@lakedaemon.net> Link: http://lkml.kernel.org/r/1474306155-3303-1-git-send-email-james.morse@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-09-20 01:29:15 +08:00
cpu = next_cpu;
mpidr = cpu_logical_map(cpu);
if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) {
cpu--;
goto out;
}
}
out:
*base_cpu = cpu;
return tlist;
}
#define MPIDR_TO_SGI_AFFINITY(cluster_id, level) \
(MPIDR_AFFINITY_LEVEL(cluster_id, level) \
<< ICC_SGI1R_AFFINITY_## level ##_SHIFT)
static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
{
u64 val;
val = (MPIDR_TO_SGI_AFFINITY(cluster_id, 3) |
MPIDR_TO_SGI_AFFINITY(cluster_id, 2) |
irq << ICC_SGI1R_SGI_ID_SHIFT |
MPIDR_TO_SGI_AFFINITY(cluster_id, 1) |
MPIDR_TO_SGI_RS(cluster_id) |
tlist << ICC_SGI1R_TARGET_LIST_SHIFT);
irqchip/gic-v3: Change pr_debug message to pr_devel The pr_debug() in gic-v3 gic_send_sgi() can trigger a circular locking warning: GICv3: CPU10: ICC_SGI1R_EL1 5000400 ====================================================== WARNING: possible circular locking dependency detected 4.15.0+ #1 Tainted: G W ------------------------------------------------------ dynamic_debug01/1873 is trying to acquire lock: ((console_sem).lock){-...}, at: [<0000000099c891ec>] down_trylock+0x20/0x4c but task is already holding lock: (&rq->lock){-.-.}, at: [<00000000842e1587>] __task_rq_lock+0x54/0xdc which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&rq->lock){-.-.}: __lock_acquire+0x3b4/0x6e0 lock_acquire+0xf4/0x2a8 _raw_spin_lock+0x4c/0x60 task_fork_fair+0x3c/0x148 sched_fork+0x10c/0x214 copy_process.isra.32.part.33+0x4e8/0x14f0 _do_fork+0xe8/0x78c kernel_thread+0x48/0x54 rest_init+0x34/0x2a4 start_kernel+0x45c/0x488 -> #1 (&p->pi_lock){-.-.}: __lock_acquire+0x3b4/0x6e0 lock_acquire+0xf4/0x2a8 _raw_spin_lock_irqsave+0x58/0x70 try_to_wake_up+0x48/0x600 wake_up_process+0x28/0x34 __up.isra.0+0x60/0x6c up+0x60/0x68 __up_console_sem+0x4c/0x7c console_unlock+0x328/0x634 vprintk_emit+0x25c/0x390 dev_vprintk_emit+0xc4/0x1fc dev_printk_emit+0x88/0xa8 __dev_printk+0x58/0x9c _dev_info+0x84/0xa8 usb_new_device+0x100/0x474 hub_port_connect+0x280/0x92c hub_event+0x740/0xa84 process_one_work+0x240/0x70c worker_thread+0x60/0x400 kthread+0x110/0x13c ret_from_fork+0x10/0x18 -> #0 ((console_sem).lock){-...}: validate_chain.isra.34+0x6e4/0xa20 __lock_acquire+0x3b4/0x6e0 lock_acquire+0xf4/0x2a8 _raw_spin_lock_irqsave+0x58/0x70 down_trylock+0x20/0x4c __down_trylock_console_sem+0x3c/0x9c console_trylock+0x20/0xb0 vprintk_emit+0x254/0x390 vprintk_default+0x58/0x90 vprintk_func+0xbc/0x164 printk+0x80/0xa0 __dynamic_pr_debug+0x84/0xac gic_raise_softirq+0x184/0x18c smp_cross_call+0xac/0x218 smp_send_reschedule+0x3c/0x48 resched_curr+0x60/0x9c check_preempt_curr+0x70/0xdc wake_up_new_task+0x310/0x470 _do_fork+0x188/0x78c SyS_clone+0x44/0x50 __sys_trace_return+0x0/0x4 other info that might help us debug this: Chain exists of: (console_sem).lock --> &p->pi_lock --> &rq->lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&rq->lock); lock(&p->pi_lock); lock(&rq->lock); lock((console_sem).lock); *** DEADLOCK *** 2 locks held by dynamic_debug01/1873: #0: (&p->pi_lock){-.-.}, at: [<000000001366df53>] wake_up_new_task+0x40/0x470 #1: (&rq->lock){-.-.}, at: [<00000000842e1587>] __task_rq_lock+0x54/0xdc stack backtrace: CPU: 10 PID: 1873 Comm: dynamic_debug01 Tainted: G W 4.15.0+ #1 Hardware name: GIGABYTE R120-T34-00/MT30-GS2-00, BIOS T48 10/02/2017 Call trace: dump_backtrace+0x0/0x188 show_stack+0x24/0x2c dump_stack+0xa4/0xe0 print_circular_bug.isra.31+0x29c/0x2b8 check_prev_add.constprop.39+0x6c8/0x6dc validate_chain.isra.34+0x6e4/0xa20 __lock_acquire+0x3b4/0x6e0 lock_acquire+0xf4/0x2a8 _raw_spin_lock_irqsave+0x58/0x70 down_trylock+0x20/0x4c __down_trylock_console_sem+0x3c/0x9c console_trylock+0x20/0xb0 vprintk_emit+0x254/0x390 vprintk_default+0x58/0x90 vprintk_func+0xbc/0x164 printk+0x80/0xa0 __dynamic_pr_debug+0x84/0xac gic_raise_softirq+0x184/0x18c smp_cross_call+0xac/0x218 smp_send_reschedule+0x3c/0x48 resched_curr+0x60/0x9c check_preempt_curr+0x70/0xdc wake_up_new_task+0x310/0x470 _do_fork+0x188/0x78c SyS_clone+0x44/0x50 __sys_trace_return+0x0/0x4 GICv3: CPU0: ICC_SGI1R_EL1 12000 This could be fixed with printk_deferred() but that might lessen its usefulness for debugging. So change it to pr_devel to keep it out of production kernels. Developers working on gic-v3 can enable it as needed in their kernels. Signed-off-by: Mark Salter <msalter@redhat.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2018-02-02 22:20:29 +08:00
pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
gic_write_sgi1r(val);
}
static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
{
int cpu;
if (WARN_ON(d->hwirq >= 16))
return;
/*
* Ensure that stores to Normal memory are visible to the
* other CPUs before issuing the IPI.
*/
irqchip/gic-v3: Use dsb(ishst) to order writes with ICC_SGI1R_EL1 accesses A dsb(ishst) barrier should be enough to order previous writes with the system register generating the SGI, as we only need to guarantee the visibility of data to other CPUs in the inner shareable domain before we send the SGI. A micro-benchmark is written to verify the performance impact on kunpeng920 machine with 2 sockets, each socket has 2 dies, and each die has 24 CPUs, so totally the system has 2 * 2 * 24 = 96 CPUs. ~2% performance improvement can be seen by this benchmark. The code of benchmark module: #include <linux/module.h> #include <linux/timekeeping.h> volatile int data0 ____cacheline_aligned; volatile int data1 ____cacheline_aligned; volatile int data2 ____cacheline_aligned; volatile int data3 ____cacheline_aligned; volatile int data4 ____cacheline_aligned; volatile int data5 ____cacheline_aligned; volatile int data6 ____cacheline_aligned; static void ipi_latency_func(void *val) { } static int __init ipi_latency_init(void) { ktime_t stime, etime, delta; int cpu, i; int start = smp_processor_id(); stime = ktime_get(); for ( i = 0; i < 1000; i++) for (cpu = 0; cpu < 96; cpu++) { data0 = data1 = data2 = data3 = data4 = data5 = data6 = cpu; smp_call_function_single(cpu, ipi_latency_func, NULL, 1); } etime = ktime_get(); delta = ktime_sub(etime, stime); printk("%s ipi from cpu%d to cpu0-95 delta of 1000times:%lld\n", __func__, start, delta); return 0; } module_init(ipi_latency_init); static void ipi_latency_exit(void) { } module_exit(ipi_latency_exit); MODULE_DESCRIPTION("IPI benchmark"); MODULE_LICENSE("GPL"); run the below commands 10 times on both Vanilla and the kernel with this patch: # taskset -c 0 insmod test.ko # rmmod test The result on vanilla: ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126757449 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126784249 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126177703 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:127022281 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126184883 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:127374585 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:125778089 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126974441 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:127357625 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:126228184 The result on the kernel with this patch: ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:124467401 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123474209 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123558497 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:122993951 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:122984223 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123323609 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:124507583 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123386963 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123340664 ipi_latency_init ipi from cpu0 to cpu0-95 delta of 1000times:123285324 Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> [maz: tidied up commit message] Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20220220061910.6155-1-21cnbao@gmail.com
2022-02-20 14:19:10 +08:00
dsb(ishst);
for_each_cpu(cpu, mask) {
u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu));
u16 tlist;
tlist = gic_compute_target_list(&cpu, mask, cluster_id);
gic_send_sgi(cluster_id, tlist, d->hwirq);
}
/* Force the above writes to ICC_SGI1R_EL1 to be executed */
isb();
}
static void __init gic_smp_init(void)
{
struct irq_fwspec sgi_fwspec = {
.fwnode = gic_data.fwnode,
.param_count = 1,
};
int base_sgi;
cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
"irqchip/arm/gicv3:starting",
gic_starting_cpu, NULL);
/* Register all 8 non-secure SGIs */
base_sgi = __irq_domain_alloc_irqs(gic_data.domain, -1, 8,
NUMA_NO_NODE, &sgi_fwspec,
false, NULL);
if (WARN_ON(base_sgi <= 0))
return;
set_smp_ipi_range(base_sgi, 8);
}
static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
bool force)
{
unsigned int cpu;
u32 offset, index;
void __iomem *reg;
int enabled;
u64 val;
if (force)
cpu = cpumask_first(mask_val);
else
cpu = cpumask_any_and(mask_val, cpu_online_mask);
irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity The GICv3 driver doesn't check if the target CPU for gic_set_affinity is valid before going ahead and making the changes. This triggers the following splat with KASAN: [ 141.189434] BUG: KASAN: global-out-of-bounds in gic_set_affinity+0x8c/0x140 [ 141.189704] Read of size 8 at addr ffff200009741d20 by task swapper/1/0 [ 141.189958] [ 141.190158] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.12.0-rc7 [ 141.190458] Hardware name: Foundation-v8A (DT) [ 141.190658] Call trace: [ 141.190908] [<ffff200008089d70>] dump_backtrace+0x0/0x328 [ 141.191224] [<ffff20000808a1b4>] show_stack+0x14/0x20 [ 141.191507] [<ffff200008504c3c>] dump_stack+0xa4/0xc8 [ 141.191858] [<ffff20000826c19c>] print_address_description+0x13c/0x250 [ 141.192219] [<ffff20000826c5c8>] kasan_report+0x210/0x300 [ 141.192547] [<ffff20000826ad54>] __asan_load8+0x84/0x98 [ 141.192874] [<ffff20000854eeec>] gic_set_affinity+0x8c/0x140 [ 141.193158] [<ffff200008148b14>] irq_do_set_affinity+0x54/0xb8 [ 141.193473] [<ffff200008148d2c>] irq_set_affinity_locked+0x64/0xf0 [ 141.193828] [<ffff200008148e00>] __irq_set_affinity+0x48/0x78 [ 141.194158] [<ffff200008bc48a4>] arm_perf_starting_cpu+0x104/0x150 [ 141.194513] [<ffff2000080d73bc>] cpuhp_invoke_callback+0x17c/0x1f8 [ 141.194783] [<ffff2000080d94ec>] notify_cpu_starting+0x8c/0xb8 [ 141.195130] [<ffff2000080911ec>] secondary_start_kernel+0x15c/0x200 [ 141.195390] [<0000000080db81b4>] 0x80db81b4 [ 141.195603] [ 141.195685] The buggy address belongs to the variable: [ 141.196012] __cpu_logical_map+0x200/0x220 [ 141.196176] [ 141.196315] Memory state around the buggy address: [ 141.196586] ffff200009741c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 141.196913] ffff200009741c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 141.197158] >ffff200009741d00: 00 00 00 00 fa fa fa fa 00 00 00 00 00 00 00 00 [ 141.197487] ^ [ 141.197758] ffff200009741d80: 00 00 00 00 00 00 00 00 fa fa fa fa 00 00 00 00 [ 141.198060] ffff200009741e00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 141.198358] ================================================================== [ 141.198609] Disabling lock debugging due to kernel taint [ 141.198961] CPU1: Booted secondary processor [410fd051] This patch adds the check to make sure the cpu is valid. Fixes: commit 021f653791ad17e03f98 ("irqchip: gic-v3: Initial support for GICv3") Cc: stable@vger.kernel.org Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2017-06-30 17:58:28 +08:00
if (cpu >= nr_cpu_ids)
return -EINVAL;
if (gic_irq_in_rdist(d))
return -EINVAL;
/* If interrupt was enabled, disable it first */
enabled = gic_peek_irq(d, GICD_ISENABLER);
if (enabled)
gic_mask_irq(d);
offset = convert_offset_index(d, GICD_IROUTER, &index);
reg = gic_dist_base(d) + offset + (index * 8);
val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
gic_write_irouter(val, reg);
/*
* If the interrupt was enabled, enabled it again. Otherwise,
* just wait for the distributor to have digested our changes.
*/
if (enabled)
gic_unmask_irq(d);
irq_data_update_effective_affinity(d, cpumask_of(cpu));
return IRQ_SET_MASK_OK_DONE;
}
#else
#define gic_set_affinity NULL
#define gic_ipi_send_mask NULL
#define gic_smp_init() do { } while(0)
#endif
static int gic_retrigger(struct irq_data *data)
{
return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true);
}
#ifdef CONFIG_CPU_PM
static int gic_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd, void *v)
{
if (cmd == CPU_PM_EXIT) {
2016-08-17 20:49:19 +08:00
if (gic_dist_security_disabled())
gic_enable_redist(true);
gic_cpu_sys_reg_init();
2016-08-17 20:49:19 +08:00
} else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) {
gic_write_grpen1(0);
gic_enable_redist(false);
}
return NOTIFY_OK;
}
static struct notifier_block gic_cpu_pm_notifier_block = {
.notifier_call = gic_cpu_pm_notifier,
};
static void gic_cpu_pm_init(void)
{
cpu_pm_register_notifier(&gic_cpu_pm_notifier_block);
}
#else
static inline void gic_cpu_pm_init(void) { }
#endif /* CONFIG_CPU_PM */
static struct irq_chip gic_chip = {
.name = "GICv3",
.irq_mask = gic_mask_irq,
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoi_irq,
.irq_set_type = gic_set_type,
.irq_set_affinity = gic_set_affinity,
.irq_retrigger = gic_retrigger,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
.irq_nmi_setup = gic_irq_nmi_setup,
.irq_nmi_teardown = gic_irq_nmi_teardown,
.ipi_send_mask = gic_ipi_send_mask,
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
static struct irq_chip gic_eoimode1_chip = {
.name = "GICv3",
.irq_mask = gic_eoimode1_mask_irq,
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoimode1_eoi_irq,
.irq_set_type = gic_set_type,
.irq_set_affinity = gic_set_affinity,
.irq_retrigger = gic_retrigger,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity,
.irq_nmi_setup = gic_irq_nmi_setup,
.irq_nmi_teardown = gic_irq_nmi_teardown,
.ipi_send_mask = gic_ipi_send_mask,
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
struct irq_chip *chip = &gic_chip;
struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq));
if (static_branch_likely(&supports_deactivate_key))
chip = &gic_eoimode1_chip;
switch (__get_intid_range(hw)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
irq_set_percpu_devid(irq);
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_percpu_devid_irq, NULL, NULL);
break;
case SPI_RANGE:
case ESPI_RANGE:
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_fasteoi_irq, NULL, NULL);
irq_set_probe(irq);
irqd_set_single_target(irqd);
break;
case LPI_RANGE:
if (!gic_dist_supports_lpis())
return -EPERM;
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_fasteoi_irq, NULL, NULL);
break;
default:
return -EPERM;
}
/* Prevents SW retriggers which mess up the ACK/EOI ordering */
irqd_set_handle_enforce_irqctx(irqd);
return 0;
}
static int gic_irq_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
unsigned int *type)
{
if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
*hwirq = fwspec->param[0];
*type = IRQ_TYPE_EDGE_RISING;
return 0;
}
if (is_of_node(fwspec->fwnode)) {
if (fwspec->param_count < 3)
return -EINVAL;
switch (fwspec->param[0]) {
case 0: /* SPI */
*hwirq = fwspec->param[1] + 32;
break;
case 1: /* PPI */
*hwirq = fwspec->param[1] + 16;
break;
case 2: /* ESPI */
*hwirq = fwspec->param[1] + ESPI_BASE_INTID;
break;
case 3: /* EPPI */
*hwirq = fwspec->param[1] + EPPI_BASE_INTID;
break;
case GIC_IRQ_TYPE_LPI: /* LPI */
*hwirq = fwspec->param[1];
break;
case GIC_IRQ_TYPE_PARTITION:
*hwirq = fwspec->param[1];
if (fwspec->param[1] >= 16)
*hwirq += EPPI_BASE_INTID - 16;
else
*hwirq += 16;
break;
default:
return -EINVAL;
}
*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
/*
* Make it clear that broken DTs are... broken.
* Partitioned PPIs are an unfortunate exception.
*/
WARN_ON(*type == IRQ_TYPE_NONE &&
fwspec->param[0] != GIC_IRQ_TYPE_PARTITION);
return 0;
}
if (is_fwnode_irqchip(fwspec->fwnode)) {
if(fwspec->param_count != 2)
return -EINVAL;
if (fwspec->param[0] < 16) {
pr_err(FW_BUG "Illegal GSI%d translation request\n",
fwspec->param[0]);
return -EINVAL;
}
*hwirq = fwspec->param[0];
*type = fwspec->param[1];
WARN_ON(*type == IRQ_TYPE_NONE);
return 0;
}
return -EINVAL;
}
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++) {
ret = gic_irq_domain_map(domain, virq + i, hwirq + i);
if (ret)
return ret;
}
return 0;
}
static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
int i;
for (i = 0; i < nr_irqs; i++) {
struct irq_data *d = irq_domain_get_irq_data(domain, virq + i);
irq_set_handler(virq + i, NULL);
irq_domain_reset_irq_data(d);
}
}
static bool fwspec_is_partitioned_ppi(struct irq_fwspec *fwspec,
irq_hw_number_t hwirq)
{
enum gic_intid_range range;
if (!gic_data.ppi_descs)
return false;
if (!is_of_node(fwspec->fwnode))
return false;
if (fwspec->param_count < 4 || !fwspec->param[3])
return false;
range = __get_intid_range(hwirq);
if (range != PPI_RANGE && range != EPPI_RANGE)
return false;
return true;
}
static int gic_irq_domain_select(struct irq_domain *d,
struct irq_fwspec *fwspec,
enum irq_domain_bus_token bus_token)
{
unsigned int type, ret, ppi_idx;
irq_hw_number_t hwirq;
/* Not for us */
if (fwspec->fwnode != d->fwnode)
return 0;
/* If this is not DT, then we have a single domain */
if (!is_of_node(fwspec->fwnode))
return 1;
ret = gic_irq_domain_translate(d, fwspec, &hwirq, &type);
if (WARN_ON_ONCE(ret))
return 0;
if (!fwspec_is_partitioned_ppi(fwspec, hwirq))
return d == gic_data.domain;
/*
* If this is a PPI and we have a 4th (non-null) parameter,
* then we need to match the partition domain.
*/
ppi_idx = __gic_get_ppi_index(hwirq);
return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]);
}
static const struct irq_domain_ops gic_irq_domain_ops = {
.translate = gic_irq_domain_translate,
.alloc = gic_irq_domain_alloc,
.free = gic_irq_domain_free,
.select = gic_irq_domain_select,
};
static int partition_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
unsigned int *type)
{
unsigned long ppi_intid;
struct device_node *np;
unsigned int ppi_idx;
int ret;
if (!gic_data.ppi_descs)
return -ENOMEM;
np = of_find_node_by_phandle(fwspec->param[3]);
if (WARN_ON(!np))
return -EINVAL;
ret = gic_irq_domain_translate(d, fwspec, &ppi_intid, type);
if (WARN_ON_ONCE(ret))
return 0;
ppi_idx = __gic_get_ppi_index(ppi_intid);
ret = partition_translate_id(gic_data.ppi_descs[ppi_idx],
of_node_to_fwnode(np));
if (ret < 0)
return ret;
*hwirq = ret;
*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
return 0;
}
static const struct irq_domain_ops partition_domain_ops = {
.translate = partition_domain_translate,
.select = gic_irq_domain_select,
};
static bool gic_enable_quirk_msm8996(void *data)
{
struct gic_chip_data *d = data;
d->flags |= FLAGS_WORKAROUND_GICR_WAKER_MSM8996;
return true;
}
irqchip/gic-v3: Workaround Cavium erratum 38539 when reading GICD_TYPER2 Despite the architecture spec requiring that reserved registers in the GIC distributor memory map are RES0 (and thus are not allowed to generate an exception), the Cavium ThunderX (aka TX1) SoC explodes as such: [ 0.000000] GICv3: GIC: Using split EOI/Deactivate mode [ 0.000000] GICv3: 128 SPIs implemented [ 0.000000] GICv3: 0 Extended SPIs implemented [ 0.000000] Internal error: synchronous external abort: 96000210 [#1] SMP [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc4-00035-g3cf6a3d5725f #7956 [ 0.000000] Hardware name: cavium,thunder-88xx (DT) [ 0.000000] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 0.000000] pc : __raw_readl+0x0/0x8 [ 0.000000] lr : gic_init_bases+0x110/0x560 [ 0.000000] sp : ffff800011243d90 [ 0.000000] x29: ffff800011243d90 x28: 0000000000000000 [ 0.000000] x27: 0000000000000018 x26: 0000000000000002 [ 0.000000] x25: ffff8000116f0000 x24: ffff000fbe6a2c80 [ 0.000000] x23: 0000000000000000 x22: ffff010fdc322b68 [ 0.000000] x21: ffff800010a7a208 x20: 00000000009b0404 [ 0.000000] x19: ffff80001124dad0 x18: 0000000000000010 [ 0.000000] x17: 000000004d8d492b x16: 00000000f67eb9af [ 0.000000] x15: ffffffffffffffff x14: ffff800011249908 [ 0.000000] x13: ffff800091243ae7 x12: ffff800011243af4 [ 0.000000] x11: ffff80001126e000 x10: ffff800011243a70 [ 0.000000] x9 : 00000000ffffffd0 x8 : ffff80001069c828 [ 0.000000] x7 : 0000000000000059 x6 : ffff8000113fb4d1 [ 0.000000] x5 : 0000000000000001 x4 : 0000000000000000 [ 0.000000] x3 : 0000000000000000 x2 : 0000000000000000 [ 0.000000] x1 : 0000000000000000 x0 : ffff8000116f000c [ 0.000000] Call trace: [ 0.000000] __raw_readl+0x0/0x8 [ 0.000000] gic_of_init+0x188/0x224 [ 0.000000] of_irq_init+0x200/0x3cc [ 0.000000] irqchip_init+0x1c/0x40 [ 0.000000] init_IRQ+0x160/0x1d0 [ 0.000000] start_kernel+0x2ec/0x4b8 [ 0.000000] Code: a8c47bfd d65f03c0 d538d080 d65f03c0 (b9400000) when reading the GICv4.1 GICD_TYPER2 register, which is unexpected... Work around it by adding a new quirk for the following variants: ThunderX: CN88xx OCTEON TX: CN83xx, CN81xx OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* and use this flag to avoid accessing GICD_TYPER2. Note that all reserved registers (including redistributors and ITS) are impacted by this erratum, but that only GICD_TYPER2 has to be worked around so far. Signed-off-by: Marc Zyngier <maz@kernel.org> Tested-by: Robert Richter <rrichter@marvell.com> Tested-by: Mark Salter <msalter@redhat.com> Tested-by: Tim Harvey <tharvey@gateworks.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Robert Richter <rrichter@marvell.com> Link: https://lore.kernel.org/r/20191027144234.8395-11-maz@kernel.org Link: https://lore.kernel.org/r/20200311115649.26060-1-maz@kernel.org
2020-03-11 19:56:49 +08:00
static bool gic_enable_quirk_cavium_38539(void *data)
{
struct gic_chip_data *d = data;
d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539;
return true;
}
static bool gic_enable_quirk_hip06_07(void *data)
{
struct gic_chip_data *d = data;
/*
* HIP06 GICD_IIDR clashes with GIC-600 product number (despite
* not being an actual ARM implementation). The saving grace is
* that GIC-600 doesn't have ESPI, so nothing to do in that case.
* HIP07 doesn't even have a proper IIDR, and still pretends to
* have ESPI. In both cases, put them right.
*/
if (d->rdists.gicd_typer & GICD_TYPER_ESPI) {
/* Zero both ESPI and the RES0 field next to it... */
d->rdists.gicd_typer &= ~GENMASK(9, 8);
return true;
}
return false;
}
static const struct gic_quirk gic_quirks[] = {
{
.desc = "GICv3: Qualcomm MSM8996 broken firmware",
.compatible = "qcom,msm8996-gic-v3",
.init = gic_enable_quirk_msm8996,
},
{
.desc = "GICv3: HIP06 erratum 161010803",
.iidr = 0x0204043b,
.mask = 0xffffffff,
.init = gic_enable_quirk_hip06_07,
},
{
.desc = "GICv3: HIP07 erratum 161010803",
.iidr = 0x00000000,
.mask = 0xffffffff,
.init = gic_enable_quirk_hip06_07,
},
irqchip/gic-v3: Workaround Cavium erratum 38539 when reading GICD_TYPER2 Despite the architecture spec requiring that reserved registers in the GIC distributor memory map are RES0 (and thus are not allowed to generate an exception), the Cavium ThunderX (aka TX1) SoC explodes as such: [ 0.000000] GICv3: GIC: Using split EOI/Deactivate mode [ 0.000000] GICv3: 128 SPIs implemented [ 0.000000] GICv3: 0 Extended SPIs implemented [ 0.000000] Internal error: synchronous external abort: 96000210 [#1] SMP [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc4-00035-g3cf6a3d5725f #7956 [ 0.000000] Hardware name: cavium,thunder-88xx (DT) [ 0.000000] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 0.000000] pc : __raw_readl+0x0/0x8 [ 0.000000] lr : gic_init_bases+0x110/0x560 [ 0.000000] sp : ffff800011243d90 [ 0.000000] x29: ffff800011243d90 x28: 0000000000000000 [ 0.000000] x27: 0000000000000018 x26: 0000000000000002 [ 0.000000] x25: ffff8000116f0000 x24: ffff000fbe6a2c80 [ 0.000000] x23: 0000000000000000 x22: ffff010fdc322b68 [ 0.000000] x21: ffff800010a7a208 x20: 00000000009b0404 [ 0.000000] x19: ffff80001124dad0 x18: 0000000000000010 [ 0.000000] x17: 000000004d8d492b x16: 00000000f67eb9af [ 0.000000] x15: ffffffffffffffff x14: ffff800011249908 [ 0.000000] x13: ffff800091243ae7 x12: ffff800011243af4 [ 0.000000] x11: ffff80001126e000 x10: ffff800011243a70 [ 0.000000] x9 : 00000000ffffffd0 x8 : ffff80001069c828 [ 0.000000] x7 : 0000000000000059 x6 : ffff8000113fb4d1 [ 0.000000] x5 : 0000000000000001 x4 : 0000000000000000 [ 0.000000] x3 : 0000000000000000 x2 : 0000000000000000 [ 0.000000] x1 : 0000000000000000 x0 : ffff8000116f000c [ 0.000000] Call trace: [ 0.000000] __raw_readl+0x0/0x8 [ 0.000000] gic_of_init+0x188/0x224 [ 0.000000] of_irq_init+0x200/0x3cc [ 0.000000] irqchip_init+0x1c/0x40 [ 0.000000] init_IRQ+0x160/0x1d0 [ 0.000000] start_kernel+0x2ec/0x4b8 [ 0.000000] Code: a8c47bfd d65f03c0 d538d080 d65f03c0 (b9400000) when reading the GICv4.1 GICD_TYPER2 register, which is unexpected... Work around it by adding a new quirk for the following variants: ThunderX: CN88xx OCTEON TX: CN83xx, CN81xx OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* and use this flag to avoid accessing GICD_TYPER2. Note that all reserved registers (including redistributors and ITS) are impacted by this erratum, but that only GICD_TYPER2 has to be worked around so far. Signed-off-by: Marc Zyngier <maz@kernel.org> Tested-by: Robert Richter <rrichter@marvell.com> Tested-by: Mark Salter <msalter@redhat.com> Tested-by: Tim Harvey <tharvey@gateworks.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Robert Richter <rrichter@marvell.com> Link: https://lore.kernel.org/r/20191027144234.8395-11-maz@kernel.org Link: https://lore.kernel.org/r/20200311115649.26060-1-maz@kernel.org
2020-03-11 19:56:49 +08:00
{
/*
* Reserved register accesses generate a Synchronous
* External Abort. This erratum applies to:
* - ThunderX: CN88xx
* - OCTEON TX: CN83xx, CN81xx
* - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx*
*/
.desc = "GICv3: Cavium erratum 38539",
.iidr = 0xa000034c,
.mask = 0xe8f00fff,
.init = gic_enable_quirk_cavium_38539,
},
{
}
};
static void gic_enable_nmi_support(void)
{
int i;
if (!gic_prio_masking_enabled())
return;
ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL);
if (!ppi_nmi_refs)
return;
for (i = 0; i < gic_data.ppi_nr; i++)
refcount_set(&ppi_nmi_refs[i], 0);
/*
* Linux itself doesn't use 1:N distribution, so has no need to
* set PMHE. The only reason to have it set is if EL3 requires it
* (and we can't change it).
*/
if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK)
static_branch_enable(&gic_pmr_sync);
pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
static_branch_unlikely(&gic_pmr_sync) ? "forced" : "relaxed");
/*
* How priority values are used by the GIC depends on two things:
* the security state of the GIC (controlled by the GICD_CTRL.DS bit)
* and if Group 0 interrupts can be delivered to Linux in the non-secure
* world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the
* ICC_PMR_EL1 register and the priority that software assigns to
* interrupts:
*
* GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Group 1 priority
* -----------------------------------------------------------
* 1 | - | unchanged | unchanged
* -----------------------------------------------------------
* 0 | 1 | non-secure | non-secure
* -----------------------------------------------------------
* 0 | 0 | unchanged | non-secure
*
* where non-secure means that the value is right-shifted by one and the
* MSB bit set, to make it fit in the non-secure priority range.
*
* In the first two cases, where ICC_PMR_EL1 and the interrupt priority
* are both either modified or unchanged, we can use the same set of
* priorities.
*
* In the last case, where only the interrupt priorities are modified to
* be in the non-secure range, we use a different PMR value to mask IRQs
* and the rest of the values that we use remain unchanged.
*/
if (gic_has_group0() && !gic_dist_security_disabled())
static_branch_enable(&gic_nonsecure_priorities);
static_branch_enable(&supports_pseudo_nmis);
if (static_branch_likely(&supports_deactivate_key))
gic_eoimode1_chip.flags |= IRQCHIP_SUPPORTS_NMI;
else
gic_chip.flags |= IRQCHIP_SUPPORTS_NMI;
}
static int __init gic_init_bases(void __iomem *dist_base,
struct redist_region *rdist_regs,
u32 nr_redist_regions,
u64 redist_stride,
struct fwnode_handle *handle)
{
u32 typer;
int err;
if (!is_hyp_mode_available())
static_branch_disable(&supports_deactivate_key);
if (static_branch_likely(&supports_deactivate_key))
pr_info("GIC: Using split EOI/Deactivate mode\n");
gic_data.fwnode = handle;
gic_data.dist_base = dist_base;
gic_data.redist_regions = rdist_regs;
gic_data.nr_redist_regions = nr_redist_regions;
gic_data.redist_stride = redist_stride;
/*
* Find out how many interrupts are supported.
*/
typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
gic_data.rdists.gicd_typer = typer;
gic_enable_quirks(readl_relaxed(gic_data.dist_base + GICD_IIDR),
gic_quirks, &gic_data);
pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
irqchip/gic-v3: Workaround Cavium erratum 38539 when reading GICD_TYPER2 Despite the architecture spec requiring that reserved registers in the GIC distributor memory map are RES0 (and thus are not allowed to generate an exception), the Cavium ThunderX (aka TX1) SoC explodes as such: [ 0.000000] GICv3: GIC: Using split EOI/Deactivate mode [ 0.000000] GICv3: 128 SPIs implemented [ 0.000000] GICv3: 0 Extended SPIs implemented [ 0.000000] Internal error: synchronous external abort: 96000210 [#1] SMP [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc4-00035-g3cf6a3d5725f #7956 [ 0.000000] Hardware name: cavium,thunder-88xx (DT) [ 0.000000] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 0.000000] pc : __raw_readl+0x0/0x8 [ 0.000000] lr : gic_init_bases+0x110/0x560 [ 0.000000] sp : ffff800011243d90 [ 0.000000] x29: ffff800011243d90 x28: 0000000000000000 [ 0.000000] x27: 0000000000000018 x26: 0000000000000002 [ 0.000000] x25: ffff8000116f0000 x24: ffff000fbe6a2c80 [ 0.000000] x23: 0000000000000000 x22: ffff010fdc322b68 [ 0.000000] x21: ffff800010a7a208 x20: 00000000009b0404 [ 0.000000] x19: ffff80001124dad0 x18: 0000000000000010 [ 0.000000] x17: 000000004d8d492b x16: 00000000f67eb9af [ 0.000000] x15: ffffffffffffffff x14: ffff800011249908 [ 0.000000] x13: ffff800091243ae7 x12: ffff800011243af4 [ 0.000000] x11: ffff80001126e000 x10: ffff800011243a70 [ 0.000000] x9 : 00000000ffffffd0 x8 : ffff80001069c828 [ 0.000000] x7 : 0000000000000059 x6 : ffff8000113fb4d1 [ 0.000000] x5 : 0000000000000001 x4 : 0000000000000000 [ 0.000000] x3 : 0000000000000000 x2 : 0000000000000000 [ 0.000000] x1 : 0000000000000000 x0 : ffff8000116f000c [ 0.000000] Call trace: [ 0.000000] __raw_readl+0x0/0x8 [ 0.000000] gic_of_init+0x188/0x224 [ 0.000000] of_irq_init+0x200/0x3cc [ 0.000000] irqchip_init+0x1c/0x40 [ 0.000000] init_IRQ+0x160/0x1d0 [ 0.000000] start_kernel+0x2ec/0x4b8 [ 0.000000] Code: a8c47bfd d65f03c0 d538d080 d65f03c0 (b9400000) when reading the GICv4.1 GICD_TYPER2 register, which is unexpected... Work around it by adding a new quirk for the following variants: ThunderX: CN88xx OCTEON TX: CN83xx, CN81xx OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* and use this flag to avoid accessing GICD_TYPER2. Note that all reserved registers (including redistributors and ITS) are impacted by this erratum, but that only GICD_TYPER2 has to be worked around so far. Signed-off-by: Marc Zyngier <maz@kernel.org> Tested-by: Robert Richter <rrichter@marvell.com> Tested-by: Mark Salter <msalter@redhat.com> Tested-by: Tim Harvey <tharvey@gateworks.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Robert Richter <rrichter@marvell.com> Link: https://lore.kernel.org/r/20191027144234.8395-11-maz@kernel.org Link: https://lore.kernel.org/r/20200311115649.26060-1-maz@kernel.org
2020-03-11 19:56:49 +08:00
/*
* ThunderX1 explodes on reading GICD_TYPER2, in violation of the
* architecture spec (which says that reserved registers are RES0).
*/
if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539))
gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
&gic_data);
gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
gic_data.rdists.has_rvpeid = true;
gic_data.rdists.has_vlpis = true;
gic_data.rdists.has_direct_lpi = true;
gic_data.rdists.has_vpend_valid_dirty = true;
if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
err = -ENOMEM;
goto out_free;
}
irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
gic_data.has_rss = !!(typer & GICD_TYPER_RSS);
if (typer & GICD_TYPER_MBIS) {
err = mbi_init(handle, gic_data.domain);
if (err)
pr_err("Failed to initialize MBIs\n");
}
set_handle_irq(gic_handle_irq);
gic_update_rdist_properties();
gic_dist_init();
gic_cpu_init();
gic_smp_init();
gic_cpu_pm_init();
if (gic_dist_supports_lpis()) {
its_init(handle, &gic_data.rdists, gic_data.domain);
its_cpu_init();
irqchip/gic-v3-its: Postpone LPI pending table freeing and memreserve Memory used by the LPI tables have to be made persistent for kexec to have a chance to work, as explained in [1]. If they have been made persistent and we are booting into a kexec'd kernel, we also need to free the pages that were preemptively allocated by the new kernel for those tables. Both of those operations currently happen during its_cpu_init(), which happens in a _STARTING (IOW atomic) cpuhp callback for secondary CPUs. efi_mem_reserve_iomem() issues a GFP_ATOMIC allocation, which unfortunately doesn't work under PREEMPT_RT (this ends up grabbing a non-raw spinlock, which can sleep under PREEMPT_RT). Similarly, freeing the pages ends up grabbing a sleepable spinlock. Since the memreserve is only required by kexec, it doesn't have to be done so early in the secondary boot process. Issue the reservation in a new CPUHP_AP_ONLINE_DYN cpuhp callback, and piggy-back the page freeing on top of it. A CPU gets to run the body of this new callback exactly once. As kexec issues a machine_shutdown() prior to machine_kexec(), it will be serialized vs a CPU being plugged to life by the hotplug machinery - either the CPU will have been brought up and have had its redistributor's pending table memreserved, or it never went online and will have its table allocated by the new kernel. [1]: https://lore.kernel.org/lkml/20180921195954.21574-1-marc.zyngier@arm.com/ Signed-off-by: Valentin Schneider <valentin.schneider@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20211027151506.2085066-3-valentin.schneider@arm.com
2021-10-27 23:15:05 +08:00
its_lpi_memreserve_init();
} else {
if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
gicv2m_init(handle, gic_data.domain);
}
gic_enable_nmi_support();
return 0;
out_free:
if (gic_data.domain)
irq_domain_remove(gic_data.domain);
free_percpu(gic_data.rdists.rdist);
return err;
}
static int __init gic_validate_dist_version(void __iomem *dist_base)
{
u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4)
return -ENODEV;
return 0;
}
/* Create all possible partitions at boot time */
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 02:27:09 +08:00
static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
{
struct device_node *parts_node, *child_part;
int part_idx = 0, i;
int nr_parts;
struct partition_affinity *parts;
parts_node = of_get_child_by_name(gic_node, "ppi-partitions");
if (!parts_node)
return;
gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL);
if (!gic_data.ppi_descs)
goto out_put_node;
nr_parts = of_get_child_count(parts_node);
if (!nr_parts)
goto out_put_node;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL);
if (WARN_ON(!parts))
goto out_put_node;
for_each_child_of_node(parts_node, child_part) {
struct partition_affinity *part;
int n;
part = &parts[part_idx];
part->partition_id = of_node_to_fwnode(child_part);
pr_info("GIC: PPI partition %pOFn[%d] { ",
child_part, part_idx);
n = of_property_count_elems_of_size(child_part, "affinity",
sizeof(u32));
WARN_ON(n <= 0);
for (i = 0; i < n; i++) {
int err, cpu;
u32 cpu_phandle;
struct device_node *cpu_node;
err = of_property_read_u32_index(child_part, "affinity",
i, &cpu_phandle);
if (WARN_ON(err))
continue;
cpu_node = of_find_node_by_phandle(cpu_phandle);
if (WARN_ON(!cpu_node))
continue;
cpu = of_cpu_node_to_id(cpu_node);
if (WARN_ON(cpu < 0)) {
of_node_put(cpu_node);
continue;
}
pr_cont("%pOF[%d] ", cpu_node, cpu);
cpumask_set_cpu(cpu, &part->mask);
of_node_put(cpu_node);
}
pr_cont("}\n");
part_idx++;
}
for (i = 0; i < gic_data.ppi_nr; i++) {
unsigned int irq;
struct partition_desc *desc;
struct irq_fwspec ppi_fwspec = {
.fwnode = gic_data.fwnode,
.param_count = 3,
.param = {
[0] = GIC_IRQ_TYPE_PARTITION,
[1] = i,
[2] = IRQ_TYPE_NONE,
},
};
irq = irq_create_fwspec_mapping(&ppi_fwspec);
if (WARN_ON(!irq))
continue;
desc = partition_create_desc(gic_data.fwnode, parts, nr_parts,
irq, &partition_domain_ops);
if (WARN_ON(!desc))
continue;
gic_data.ppi_descs[i] = desc;
}
out_put_node:
of_node_put(parts_node);
}
static void __init gic_of_setup_kvm_info(struct device_node *node)
{
int ret;
struct resource r;
u32 gicv_idx;
gic_v3_kvm_info.type = GIC_V3;
gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
if (!gic_v3_kvm_info.maint_irq)
return;
if (of_property_read_u32(node, "#redistributor-regions",
&gicv_idx))
gicv_idx = 1;
gicv_idx += 3; /* Also skip GICD, GICC, GICH */
ret = of_address_to_resource(node, gicv_idx, &r);
if (!ret)
gic_v3_kvm_info.vcpu = r;
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
vgic_set_kvm_info(&gic_v3_kvm_info);
}
static void gic_request_region(resource_size_t base, resource_size_t size,
const char *name)
{
if (!request_mem_region(base, size, name))
pr_warn_once(FW_BUG "%s region %pa has overlapping address\n",
name, &base);
}
static void __iomem *gic_of_iomap(struct device_node *node, int idx,
const char *name, struct resource *res)
{
void __iomem *base;
int ret;
ret = of_address_to_resource(node, idx, res);
if (ret)
return IOMEM_ERR_PTR(ret);
gic_request_region(res->start, resource_size(res), name);
base = of_iomap(node, idx);
return base ?: IOMEM_ERR_PTR(-ENOMEM);
}
static int __init gic_of_init(struct device_node *node, struct device_node *parent)
{
void __iomem *dist_base;
struct redist_region *rdist_regs;
struct resource res;
u64 redist_stride;
u32 nr_redist_regions;
int err, i;
dist_base = gic_of_iomap(node, 0, "GICD", &res);
if (IS_ERR(dist_base)) {
pr_err("%pOF: unable to map gic dist registers\n", node);
return PTR_ERR(dist_base);
}
err = gic_validate_dist_version(dist_base);
if (err) {
pr_err("%pOF: no distributor detected, giving up\n", node);
goto out_unmap_dist;
}
if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions))
nr_redist_regions = 1;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
rdist_regs = kcalloc(nr_redist_regions, sizeof(*rdist_regs),
GFP_KERNEL);
if (!rdist_regs) {
err = -ENOMEM;
goto out_unmap_dist;
}
for (i = 0; i < nr_redist_regions; i++) {
rdist_regs[i].redist_base = gic_of_iomap(node, 1 + i, "GICR", &res);
if (IS_ERR(rdist_regs[i].redist_base)) {
pr_err("%pOF: couldn't map region %d\n", node, i);
err = -ENODEV;
goto out_unmap_rdist;
}
rdist_regs[i].phys_base = res.start;
}
if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
redist_stride = 0;
gic_enable_of_quirks(node, gic_quirks, &gic_data);
err = gic_init_bases(dist_base, rdist_regs, nr_redist_regions,
redist_stride, &node->fwnode);
if (err)
goto out_unmap_rdist;
gic_populate_ppi_partitions(node);
if (static_branch_likely(&supports_deactivate_key))
gic_of_setup_kvm_info(node);
return 0;
out_unmap_rdist:
for (i = 0; i < nr_redist_regions; i++)
if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base))
iounmap(rdist_regs[i].redist_base);
kfree(rdist_regs);
out_unmap_dist:
iounmap(dist_base);
return err;
}
IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
#ifdef CONFIG_ACPI
static struct
{
void __iomem *dist_base;
struct redist_region *redist_regs;
u32 nr_redist_regions;
bool single_redist;
int enabled_rdists;
u32 maint_irq;
int maint_irq_mode;
phys_addr_t vcpu_base;
} acpi_data __initdata;
static void __init
gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base)
{
static int count = 0;
acpi_data.redist_regs[count].phys_base = phys_base;
acpi_data.redist_regs[count].redist_base = redist_base;
acpi_data.redist_regs[count].single_redist = acpi_data.single_redist;
count++;
}
static int __init
gic_acpi_parse_madt_redist(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_redistributor *redist =
(struct acpi_madt_generic_redistributor *)header;
void __iomem *redist_base;
redist_base = ioremap(redist->base_address, redist->length);
if (!redist_base) {
pr_err("Couldn't map GICR region @%llx\n", redist->base_address);
return -ENOMEM;
}
gic_request_region(redist->base_address, redist->length, "GICR");
gic_acpi_register_redist(redist->base_address, redist_base);
return 0;
}
static int __init
gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
void __iomem *redist_base;
irqchip/gic-v3: Fix the driver probe() fail due to disabled GICC entry The ACPI specification says OS shouldn't attempt to use GICC configuration parameters if the flag ACPI_MADT_ENABLED is cleared. The ARM64-SMP code skips the disabled GICC entries but not causing any issue. However the current GICv3 driver probe bails out causing kernel panic() instead of skipping the disabled GICC interfaces. This issue happens on systems where redistributor regions are not in the always-on power domain and one of GICC interface marked with ACPI_MADT_ENABLED=0. This patch does the two things to fix the panic. - Don't return an error in gic_acpi_match_gicc() for disabled GICC entry. - No need to keep GICR region information for disabled GICC entry. Observed kernel crash on QDF2400 platform GICC entry is disabled. Kernel crash traces: Kernel panic - not syncing: No interrupt controller found. CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.5 #26 [<ffff000008087770>] dump_backtrace+0x0/0x218 [<ffff0000080879dc>] show_stack+0x14/0x20 [<ffff00000883b078>] dump_stack+0x98/0xb8 [<ffff0000080c5c14>] panic+0x118/0x26c [<ffff000008b62348>] init_IRQ+0x24/0x2c [<ffff000008b609fc>] start_kernel+0x230/0x394 [<ffff000008b601e4>] __primary_switched+0x64/0x6c ---[ end Kernel panic - not syncing: No interrupt controller found. Disabled GICC subtable example: Subtable Type : 0B [Generic Interrupt Controller] Length : 50 Reserved : 0000 CPU Interface Number : 0000003D Processor UID : 0000003D Flags (decoded below) : 00000000 Processor Enabled : 0 Performance Interrupt Trig Mode : 0 Virtual GIC Interrupt Trig Mode : 0 Parking Protocol Version : 00000000 Performance Interrupt : 00000017 Parked Address : 0000000000000000 Base Address : 0000000000000000 Virtual GIC Base Address : 0000000000000000 Hypervisor GIC Base Address : 0000000000000000 Virtual GIC Interrupt : 00000019 Redistributor Base Address : 0000FFFF88F40000 ARM MPIDR : 000000000000000D Efficiency Class : 00 Reserved : 000000 Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2017-12-06 03:16:21 +08:00
/* GICC entry which has !ACPI_MADT_ENABLED is not unusable so skip */
if (!(gicc->flags & ACPI_MADT_ENABLED))
return 0;
redist_base = ioremap(gicc->gicr_base_address, size);
if (!redist_base)
return -ENOMEM;
gic_request_region(gicc->gicr_base_address, size, "GICR");
gic_acpi_register_redist(gicc->gicr_base_address, redist_base);
return 0;
}
static int __init gic_acpi_collect_gicr_base(void)
{
acpi_tbl_entry_handler redist_parser;
enum acpi_madt_type type;
if (acpi_data.single_redist) {
type = ACPI_MADT_TYPE_GENERIC_INTERRUPT;
redist_parser = gic_acpi_parse_madt_gicc;
} else {
type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR;
redist_parser = gic_acpi_parse_madt_redist;
}
/* Collect redistributor base addresses in GICR entries */
if (acpi_table_parse_madt(type, redist_parser, 0) > 0)
return 0;
pr_info("No valid GICR entries exist\n");
return -ENODEV;
}
static int __init gic_acpi_match_gicr(union acpi_subtable_headers *header,
const unsigned long end)
{
/* Subtable presence means that redist exists, that's it */
return 0;
}
static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
/*
* If GICC is enabled and has valid gicr base address, then it means
* GICR base is presented via GICC
*/
if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) {
acpi_data.enabled_rdists++;
return 0;
}
irqchip/gic-v3: Fix the driver probe() fail due to disabled GICC entry The ACPI specification says OS shouldn't attempt to use GICC configuration parameters if the flag ACPI_MADT_ENABLED is cleared. The ARM64-SMP code skips the disabled GICC entries but not causing any issue. However the current GICv3 driver probe bails out causing kernel panic() instead of skipping the disabled GICC interfaces. This issue happens on systems where redistributor regions are not in the always-on power domain and one of GICC interface marked with ACPI_MADT_ENABLED=0. This patch does the two things to fix the panic. - Don't return an error in gic_acpi_match_gicc() for disabled GICC entry. - No need to keep GICR region information for disabled GICC entry. Observed kernel crash on QDF2400 platform GICC entry is disabled. Kernel crash traces: Kernel panic - not syncing: No interrupt controller found. CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.5 #26 [<ffff000008087770>] dump_backtrace+0x0/0x218 [<ffff0000080879dc>] show_stack+0x14/0x20 [<ffff00000883b078>] dump_stack+0x98/0xb8 [<ffff0000080c5c14>] panic+0x118/0x26c [<ffff000008b62348>] init_IRQ+0x24/0x2c [<ffff000008b609fc>] start_kernel+0x230/0x394 [<ffff000008b601e4>] __primary_switched+0x64/0x6c ---[ end Kernel panic - not syncing: No interrupt controller found. Disabled GICC subtable example: Subtable Type : 0B [Generic Interrupt Controller] Length : 50 Reserved : 0000 CPU Interface Number : 0000003D Processor UID : 0000003D Flags (decoded below) : 00000000 Processor Enabled : 0 Performance Interrupt Trig Mode : 0 Virtual GIC Interrupt Trig Mode : 0 Parking Protocol Version : 00000000 Performance Interrupt : 00000017 Parked Address : 0000000000000000 Base Address : 0000000000000000 Virtual GIC Base Address : 0000000000000000 Hypervisor GIC Base Address : 0000000000000000 Virtual GIC Interrupt : 00000019 Redistributor Base Address : 0000FFFF88F40000 ARM MPIDR : 000000000000000D Efficiency Class : 00 Reserved : 000000 Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2017-12-06 03:16:21 +08:00
/*
* It's perfectly valid firmware can pass disabled GICC entry, driver
* should not treat as errors, skip the entry instead of probe fail.
*/
if (!(gicc->flags & ACPI_MADT_ENABLED))
return 0;
return -ENODEV;
}
static int __init gic_acpi_count_gicr_regions(void)
{
int count;
/*
* Count how many redistributor regions we have. It is not allowed
* to mix redistributor description, GICR and GICC subtables have to be
* mutually exclusive.
*/
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR,
gic_acpi_match_gicr, 0);
if (count > 0) {
acpi_data.single_redist = false;
return count;
}
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_match_gicc, 0);
if (count > 0) {
acpi_data.single_redist = true;
count = acpi_data.enabled_rdists;
}
return count;
}
static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header,
struct acpi_probe_entry *ape)
{
struct acpi_madt_generic_distributor *dist;
int count;
dist = (struct acpi_madt_generic_distributor *)header;
if (dist->version != ape->driver_data)
return false;
/* We need to do that exercise anyway, the sooner the better */
count = gic_acpi_count_gicr_regions();
if (count <= 0)
return false;
acpi_data.nr_redist_regions = count;
return true;
}
static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
int maint_irq_mode;
static int first_madt = true;
/* Skip unusable CPUs */
if (!(gicc->flags & ACPI_MADT_ENABLED))
return 0;
maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE;
if (first_madt) {
first_madt = false;
acpi_data.maint_irq = gicc->vgic_interrupt;
acpi_data.maint_irq_mode = maint_irq_mode;
acpi_data.vcpu_base = gicc->gicv_base_address;
return 0;
}
/*
* The maintenance interrupt and GICV should be the same for every CPU
*/
if ((acpi_data.maint_irq != gicc->vgic_interrupt) ||
(acpi_data.maint_irq_mode != maint_irq_mode) ||
(acpi_data.vcpu_base != gicc->gicv_base_address))
return -EINVAL;
return 0;
}
static bool __init gic_acpi_collect_virt_info(void)
{
int count;
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_parse_virt_madt_gicc, 0);
return (count > 0);
}
#define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K)
#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;
if (!gic_acpi_collect_virt_info()) {
pr_warn("Unable to get hardware information used for virtualization\n");
return;
}
gic_v3_kvm_info.type = GIC_V3;
irq = acpi_register_gsi(NULL, acpi_data.maint_irq,
acpi_data.maint_irq_mode,
ACPI_ACTIVE_HIGH);
if (irq <= 0)
return;
gic_v3_kvm_info.maint_irq = irq;
if (acpi_data.vcpu_base) {
struct resource *vcpu = &gic_v3_kvm_info.vcpu;
vcpu->flags = IORESOURCE_MEM;
vcpu->start = acpi_data.vcpu_base;
vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1;
}
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
vgic_set_kvm_info(&gic_v3_kvm_info);
}
static struct fwnode_handle *gsi_domain_handle;
static struct fwnode_handle *gic_v3_get_gsi_domain_id(u32 gsi)
{
return gsi_domain_handle;
}
static int __init
gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end)
{
struct acpi_madt_generic_distributor *dist;
size_t size;
int i, err;
/* Get distributor base address */
dist = (struct acpi_madt_generic_distributor *)header;
acpi_data.dist_base = ioremap(dist->base_address,
ACPI_GICV3_DIST_MEM_SIZE);
if (!acpi_data.dist_base) {
pr_err("Unable to map GICD registers\n");
return -ENOMEM;
}
gic_request_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD");
err = gic_validate_dist_version(acpi_data.dist_base);
if (err) {
pr_err("No distributor detected at @%p, giving up\n",
acpi_data.dist_base);
goto out_dist_unmap;
}
size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions;
acpi_data.redist_regs = kzalloc(size, GFP_KERNEL);
if (!acpi_data.redist_regs) {
err = -ENOMEM;
goto out_dist_unmap;
}
err = gic_acpi_collect_gicr_base();
if (err)
goto out_redist_unmap;
gsi_domain_handle = irq_domain_alloc_fwnode(&dist->base_address);
if (!gsi_domain_handle) {
err = -ENOMEM;
goto out_redist_unmap;
}
err = gic_init_bases(acpi_data.dist_base, acpi_data.redist_regs,
acpi_data.nr_redist_regions, 0, gsi_domain_handle);
if (err)
goto out_fwhandle_free;
acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, gic_v3_get_gsi_domain_id);
if (static_branch_likely(&supports_deactivate_key))
gic_acpi_setup_kvm_info();
return 0;
out_fwhandle_free:
irq_domain_free_fwnode(gsi_domain_handle);
out_redist_unmap:
for (i = 0; i < acpi_data.nr_redist_regions; i++)
if (acpi_data.redist_regs[i].redist_base)
iounmap(acpi_data.redist_regs[i].redist_base);
kfree(acpi_data.redist_regs);
out_dist_unmap:
iounmap(acpi_data.dist_base);
return err;
}
IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3,
gic_acpi_init);
IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4,
gic_acpi_init);
IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE,
gic_acpi_init);
#endif