diff options
Diffstat (limited to 'drivers/irqchip/irq-gic-v3.c')
-rw-r--r-- | drivers/irqchip/irq-gic-v3.c | 615 |
1 files changed, 450 insertions, 165 deletions
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 1eec9d4649d5..34d58567b78d 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -36,6 +36,8 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #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; @@ -73,18 +75,16 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); * are presented to the GIC CPUIF as follow: * (GIC_(R)DIST_PRI[irq] >> 1) | 0x80; * - * If SCR_EL3.FIQ == 1, the values writen to/read from PMR and RPR at non-secure + * 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. + * 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. - * - * For now, we only support pseudo-NMIs if we have non-secure view of - * priorities. */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); @@ -97,10 +97,34 @@ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); 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; +static struct gic_kvm_info gic_v3_kvm_info __initdata; static DEFINE_PER_CPU(bool, has_rss); #define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4) @@ -112,6 +136,7 @@ static DEFINE_PER_CPU(bool, has_rss); #define DEFAULT_PMR_VALUE 0xf0 enum gic_intid_range { + SGI_RANGE, PPI_RANGE, SPI_RANGE, EPPI_RANGE, @@ -123,6 +148,8 @@ enum gic_intid_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: @@ -148,15 +175,22 @@ static inline unsigned int gic_irq(struct irq_data *d) return d->hwirq; } -static inline int gic_irq_in_rdist(struct irq_data *d) +static inline bool gic_irq_in_rdist(struct irq_data *d) { - enum gic_intid_range range = get_intid_range(d); - return range == PPI_RANGE || range == EPPI_RANGE; + 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 */ @@ -172,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) } } -static void gic_do_wait_for_rwp(void __iomem *base) +static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 count = 1000000; /* 1s! */ - while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) { + while (readl_relaxed(base + GICD_CTLR) & bit) { count--; if (!count) { pr_err_ratelimited("RWP timeout, gone fishing\n"); @@ -190,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base) /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data.dist_base); + 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()); + gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } #ifdef CONFIG_ARM64 @@ -253,6 +287,7 @@ static void gic_enable_redist(bool enable) 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; @@ -317,28 +352,27 @@ static int gic_peek_irq(struct irq_data *d, u32 offset) static void gic_poke_irq(struct irq_data *d, u32 offset) { - void (*rwp_wait)(void); void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } writel_relaxed(mask, base + offset + (index / 32) * 4); - rwp_wait(); } 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) @@ -372,7 +406,7 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, { u32 reg; - if (d->hwirq >= 8192) /* PPI/SPI only */ + if (d->hwirq >= 8192) /* SGI/PPI/SPI only */ return -EINVAL; switch (which) { @@ -385,7 +419,11 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, break; case IRQCHIP_STATE_MASKED: - reg = val ? GICD_ICENABLER : GICD_ISENABLER; + if (val) { + gic_mask_irq(d); + return 0; + } + reg = GICD_ISENABLER; break; default: @@ -432,18 +470,23 @@ static void gic_irq_set_prio(struct irq_data *d, u8 prio) writeb_relaxed(prio, base + offset + index); } -static u32 gic_get_ppi_index(struct irq_data *d) +static u32 __gic_get_ppi_index(irq_hw_number_t hwirq) { - switch (get_intid_range(d)) { + switch (__get_intid_range(hwirq)) { case PPI_RANGE: - return d->hwirq - 16; + return hwirq - 16; case EPPI_RANGE: - return d->hwirq - EPPI_BASE_INTID + 16; + 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); @@ -516,7 +559,8 @@ static void gic_irq_nmi_teardown(struct irq_data *d) static void gic_eoi_irq(struct irq_data *d) { - gic_write_eoir(gic_irq(d)); + write_gicreg(gic_irq(d), ICC_EOIR1_EL1); + isb(); } static void gic_eoimode1_eoi_irq(struct irq_data *d) @@ -534,33 +578,29 @@ static int gic_set_type(struct irq_data *d, unsigned int type) { enum gic_intid_range range; unsigned int irq = gic_irq(d); - void (*rwp_wait)(void); void __iomem *base; u32 offset, index; int ret; - /* Interrupt configuration for SGIs can't be changed */ - if (irq < 16) - return -EINVAL; - 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)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } offset = convert_offset_index(d, GICD_ICFGR, &index); - ret = gic_configure_irq(index, type, base + offset, rwp_wait); + 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); @@ -572,6 +612,9 @@ static int gic_set_type(struct irq_data *d, unsigned int type) 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 @@ -597,44 +640,101 @@ static void gic_deactivate_unhandled(u32 irqnr) if (irqnr < 8192) gic_write_dir(irqnr); } else { - gic_write_eoir(irqnr); + write_gicreg(irqnr, ICC_EOIR1_EL1); + isb(); } } -static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +/* + * 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) { - bool irqs_enabled = interrupts_enabled(regs); - int err; + if (static_branch_likely(&supports_deactivate_key)) + write_gicreg(irqnr, ICC_EOIR1_EL1); - if (irqs_enabled) - nmi_enter(); + isb(); +} - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - /* - * Leave the PSR.I bit set to prevent other NMIs to be - * received while handling this one. - * PSR.I will be restored when we ERET to the - * interrupted context. - */ - err = handle_domain_nmi(gic_data.domain, irqnr, regs); - if (err) +static bool gic_rpr_is_nmi_prio(void) +{ + if (!gic_supports_nmi()) + return false; + + return unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI)); +} + +static bool gic_irqnr_is_special(u32 irqnr) +{ + return irqnr >= 1020 && irqnr <= 1023; +} + +static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; + + gic_complete_ack(irqnr); + + if (generic_handle_domain_irq(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); + } +} - if (irqs_enabled) - nmi_exit(); +static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; + + gic_complete_ack(irqnr); + + if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); + gic_deactivate_unhandled(irqnr); + } } -static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +/* + * 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) { + bool is_nmi; u32 irqnr; irqnr = gic_read_iar(); - if (gic_supports_nmi() && - unlikely(gic_read_rpr() == GICD_INT_NMI_PRI)) { - gic_handle_nmi(irqnr, regs); - return; + is_nmi = gic_rpr_is_nmi_prio(); + + if (is_nmi) { + nmi_enter(); + __gic_handle_nmi(irqnr, regs); + nmi_exit(); } if (gic_prio_masking_enabled()) { @@ -642,43 +742,52 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs gic_arch_enable_irqs(); } - /* Check for special IDs first */ - if ((irqnr >= 1020 && irqnr <= 1023)) - return; + if (!is_nmi) + __gic_handle_irq(irqnr, regs); +} - /* Treat anything but SGIs in a uniform way */ - if (likely(irqnr > 15)) { - int err; +/* + * 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; - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - else - isb(); + /* + * 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); - err = handle_domain_irq(gic_data.domain, irqnr, regs); - if (err) { - WARN_ONCE(true, "Unexpected interrupt received!\n"); - gic_deactivate_unhandled(irqnr); - } - return; - } - if (irqnr < 16) { - gic_write_eoir(irqnr); - if (static_branch_likely(&supports_deactivate_key)) - gic_write_dir(irqnr); -#ifdef CONFIG_SMP - /* - * Unlike GICv2, we don't need an smp_rmb() here. - * The control dependency from gic_read_iar to - * the ISB in gic_write_eoir is enough to ensure - * that any shared data read by handle_IPI will - * be read after the ACK. - */ - handle_IPI(irqnr, regs); -#else - WARN_ONCE(true, "Unexpected SGI received!\n"); -#endif - } + __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) @@ -724,6 +833,7 @@ 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); @@ -753,12 +863,18 @@ static void __init gic_dist_init(void) 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, and wait for the distributor to drain */ - gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp); + /* Now do the common stuff */ + gic_dist_config(base, GIC_LINE_NR, NULL); - /* Enable distributor with ARE, Group1 */ - writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1, - base + GICD_CTLR); + 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 @@ -829,6 +945,7 @@ static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) 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; @@ -859,13 +976,40 @@ 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 cleanup */ + 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); - /* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */ + /* + * 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)) { @@ -885,11 +1029,16 @@ static void gic_update_rdist_properties(void) gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; - pr_info("%d PPIs implemented\n", gic_data.ppi_nr); - pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n", - !gic_data.rdists.has_vlpis ? "no " : "", - !gic_data.rdists.has_direct_lpi ? "no " : "", - !gic_data.rdists.has_rvpeid ? "no " : ""); + 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 */ @@ -923,14 +1072,20 @@ static void gic_cpu_sys_reg_init(void) /* Set priority mask register */ if (!gic_prio_masking_enabled()) { write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1); - } else { + } 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. */ - WARN_ON(gic_supports_nmi() && group0 && - !gic_dist_security_disabled()); + if (static_branch_unlikely(&gic_nonsecure_priorities)) + WARN_ON(!group0 || gic_dist_security_disabled()); + else + WARN_ON(group0 && !gic_dist_security_disabled()); } /* @@ -956,10 +1111,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); - /* Fall through */ + fallthrough; case 6: write_gicreg(0, ICC_AP0R1_EL1); - /* Fall through */ + fallthrough; case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); @@ -973,10 +1128,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); - /* Fall through */ + fallthrough; case 6: write_gicreg(0, ICC_AP1R1_EL1); - /* Fall through */ + fallthrough; case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); @@ -1116,37 +1271,51 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) gic_write_sgi1r(val); } -static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) +static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) { int cpu; - if (WARN_ON(irq >= 16)) + if (WARN_ON(d->hwirq >= 16)) return; /* * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ - wmb(); + 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, irq); + gic_send_sgi(cluster_id, tlist, d->hwirq); } /* Force the above writes to ICC_SGI1R_EL1 to be executed */ isb(); } -static void gic_smp_init(void) +static void __init gic_smp_init(void) { - set_smp_cross_call(gic_raise_softirq); + 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, @@ -1186,8 +1355,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, */ if (enabled) gic_unmask_irq(d); - else - gic_dist_wait_for_rwp(); irq_data_update_effective_affinity(d, cpumask_of(cpu)); @@ -1195,9 +1362,15 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, } #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) @@ -1233,10 +1406,12 @@ static struct irq_chip gic_chip = { .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, @@ -1249,11 +1424,13 @@ static struct irq_chip gic_eoimode1_chip = { .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, @@ -1263,17 +1440,18 @@ 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); - irq_set_status_flags(irq, IRQ_NOAUTOEN); break; case SPI_RANGE: @@ -1281,7 +1459,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); irq_set_probe(irq); - irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq))); + irqd_set_single_target(irqd); break; case LPI_RANGE: @@ -1295,16 +1473,22 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, return -EPERM; } + /* Prevents SW retriggers which mess up the ACK/EOI ordering */ + irqd_set_handle_enforce_irqctx(irqd); return 0; } -#define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) - 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; @@ -1340,7 +1524,7 @@ static int gic_irq_domain_translate(struct irq_domain *d, /* * Make it clear that broken DTs are... broken. - * Partitionned PPIs are an unfortunate exception. + * Partitioned PPIs are an unfortunate exception. */ WARN_ON(*type == IRQ_TYPE_NONE && fwspec->param[0] != GIC_IRQ_TYPE_PARTITION); @@ -1351,6 +1535,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, 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]; @@ -1394,10 +1584,34 @@ static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq, } } +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; @@ -1406,16 +1620,19 @@ static int gic_irq_domain_select(struct irq_domain *d, 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. */ - if (fwspec->param_count >= 4 && - fwspec->param[0] == 1 && fwspec->param[3] != 0 && - gic_data.ppi_descs) - return d == partition_get_domain(gic_data.ppi_descs[fwspec->param[1]]); - - return d == gic_data.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 = { @@ -1430,7 +1647,9 @@ static int partition_domain_translate(struct irq_domain *d, 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) @@ -1440,7 +1659,12 @@ static int partition_domain_translate(struct irq_domain *d, if (WARN_ON(!np)) return -EINVAL; - ret = partition_translate_id(gic_data.ppi_descs[fwspec->param[1]], + 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; @@ -1536,11 +1760,6 @@ static void gic_enable_nmi_support(void) if (!gic_prio_masking_enabled()) return; - if (gic_has_group0() && !gic_dist_security_disabled()) { - pr_warn("SCR_EL3.FIQ is cleared, cannot enable use of pseudo-NMIs\n"); - return; - } - ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); if (!ppi_nmi_refs) return; @@ -1556,8 +1775,38 @@ static void gic_enable_nmi_support(void) if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) static_branch_enable(&gic_pmr_sync); - pr_info("%s ICC_PMR_EL1 synchronisation\n", - static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing"); + 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); @@ -1609,20 +1858,20 @@ static int __init gic_init_bases(void __iomem *dist_base, gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); - irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); 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); - pr_info("Distributor has %sRange Selector support\n", - gic_data.has_rss ? "" : "no "); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); @@ -1634,14 +1883,15 @@ static int __init gic_init_bases(void __iomem *dist_base, gic_update_rdist_properties(); - gic_smp_init(); 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(); + its_lpi_memreserve_init(); } else { if (IS_ENABLED(CONFIG_ARM_GIC_V2M)) gicv2m_init(handle, gic_data.domain); @@ -1682,7 +1932,7 @@ static void __init gic_populate_ppi_partitions(struct device_node *gic_node) gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL); if (!gic_data.ppi_descs) - return; + goto out_put_node; nr_parts = of_get_child_count(parts_node); @@ -1723,12 +1973,15 @@ static void __init gic_populate_ppi_partitions(struct device_node *gic_node) continue; cpu = of_cpu_node_to_id(cpu_node); - if (WARN_ON(cpu < 0)) + 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"); @@ -1785,21 +2038,47 @@ static void __init gic_of_setup_kvm_info(struct device_node *node) gic_v3_kvm_info.vcpu = r; gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; - gic_set_kvm_info(&gic_v3_kvm_info); + 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 = of_iomap(node, 0); - if (!dist_base) { + 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 -ENXIO; + return PTR_ERR(dist_base); } err = gic_validate_dist_version(dist_base); @@ -1819,12 +2098,8 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare } for (i = 0; i < nr_redist_regions; i++) { - struct resource res; - int ret; - - ret = of_address_to_resource(node, 1 + i, &res); - rdist_regs[i].redist_base = of_iomap(node, 1 + i); - if (ret || !rdist_regs[i].redist_base) { + 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; @@ -1850,7 +2125,7 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) - if (rdist_regs[i].redist_base) + 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: @@ -1897,6 +2172,7 @@ gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, 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; @@ -1919,6 +2195,7 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, 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; @@ -2100,14 +2377,21 @@ static void __init gic_acpi_setup_kvm_info(void) } gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; - gic_set_kvm_info(&gic_v3_kvm_info); + 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(struct acpi_subtable_header *header, const unsigned long end) +gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_distributor *dist; - struct fwnode_handle *domain_handle; size_t size; int i, err; @@ -2119,6 +2403,7 @@ gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end) 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) { @@ -2138,18 +2423,18 @@ gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end) if (err) goto out_redist_unmap; - domain_handle = irq_domain_alloc_fwnode(&dist->base_address); - if (!domain_handle) { + 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, domain_handle); + acpi_data.nr_redist_regions, 0, gsi_domain_handle); if (err) goto out_fwhandle_free; - acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle); + 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(); @@ -2157,7 +2442,7 @@ gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end) return 0; out_fwhandle_free: - irq_domain_free_fwnode(domain_handle); + 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) |