From 457ff81ecad222d946b8892d8e2e91eed2f9d208 Mon Sep 17 00:00:00 2001 From: Jianmin Lv Date: Wed, 20 Jul 2022 18:51:25 +0800 Subject: [PATCH 01/23] LoongArch: Prepare to support multiple pch-pic and pch-msi irqdomain ANBZ: #5200 commit 2dfded47da329a0dd619144a6bb43aefc13a77ba upstream. For systems with two chipsets, there are two related pch-pic and pch-msi irqdomains, each of which has the same node id as its parent irqdomain. So we use a structure to mantain the relation of node and it's parent irqdomain as pch irqdomin, the 'pci_segment' field is only used to match the pci segment of a pci device when setting msi irqdomain for the device. struct acpi_vector_group { int node; int pci_segment; struct irq_domain *parent; }; The field 'pci_segment' and 'node' are initialized from MCFG, and the parent irqdomain driver will set field 'parent' by matching same 'node'. Signed-off-by: Jianmin Lv Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-7-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 8 +++++++ arch/loongarch/kernel/irq.c | 38 ++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 99654d729329..80414d63f5fa 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -48,6 +48,14 @@ bool arch_trigger_cpumask_backtrace(const struct cpumask *mask, bool exclude_sel #define MAX_IO_PICS 2 #define NR_IRQS (64 + (256 * MAX_IO_PICS)) +struct acpi_vector_group { + int node; + int pci_segment; + struct irq_domain *parent; +}; +extern struct acpi_vector_group pch_group[MAX_IO_PICS]; +extern struct acpi_vector_group msi_group[MAX_IO_PICS]; + #define CORES_PER_EIO_NODE 4 #define LOONGSON_CPU_UART0_VEC 10 /* CPU UART0 */ diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index b34b8d792aa4..37dd2dca8221 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -31,6 +31,8 @@ struct irq_domain *pch_lpc_domain; struct irq_domain *pch_msi_domain[MAX_IO_PICS]; struct irq_domain *pch_pic_domain[MAX_IO_PICS]; +struct acpi_vector_group pch_group[MAX_IO_PICS]; +struct acpi_vector_group msi_group[MAX_IO_PICS]; /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -56,6 +58,41 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } +static int __init early_pci_mcfg_parse(struct acpi_table_header *header) +{ + struct acpi_table_mcfg *mcfg; + struct acpi_mcfg_allocation *mptr; + int i, n; + + if (header->length < sizeof(struct acpi_table_mcfg)) + return -EINVAL; + + n = (header->length - sizeof(struct acpi_table_mcfg)) / + sizeof(struct acpi_mcfg_allocation); + mcfg = (struct acpi_table_mcfg *)header; + mptr = (struct acpi_mcfg_allocation *) &mcfg[1]; + + for (i = 0; i < n; i++, mptr++) { + msi_group[i].pci_segment = mptr->pci_segment; + pch_group[i].node = msi_group[i].node = (mptr->address >> 44) & 0xf; + } + + return 0; +} + +static void __init init_vec_parent_group(void) +{ + int i; + + for (i = 0; i < MAX_IO_PICS; i++) { + msi_group[i].pci_segment = -1; + msi_group[i].node = -1; + pch_group[i].node = -1; + } + + acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse); +} + void __init init_IRQ(void) { int i; @@ -69,6 +106,7 @@ void __init init_IRQ(void) clear_csr_ecfg(ECFG0_IM); clear_csr_estat(ESTATF_IP); + init_vec_parent_group(); irqchip_init(); #ifdef CONFIG_SMP ipi_irq = EXCCODE_IPI - EXCCODE_INT_START; -- Gitee From 3f874fa2f96af900ca46ba413b0ef7d6a8fcec9a Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:26 +0800 Subject: [PATCH 02/23] irqchip: Add Loongson PCH LPC controller support ANBZ: #5200 commit ee73f14ee9eb7e1a04051b303b56130c4dd6e048 upstream. PCH-LPC stands for "LPC Interrupts" that described in Section 24.3 of "Loongson 7A1000 Bridge User Manual". For more information please refer Documentation/loongarch/irq-chip-model.rst. Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-8-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 4 +- arch/loongarch/kernel/irq.c | 1 - drivers/irqchip/Kconfig | 8 + drivers/irqchip/Makefile | 1 + drivers/irqchip/irq-loongson-pch-lpc.c | 206 +++++++++++++++++++++++++ 5 files changed, 217 insertions(+), 3 deletions(-) create mode 100644 drivers/irqchip/irq-loongson-pch-lpc.c diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 80414d63f5fa..3e10595fead1 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -112,7 +112,7 @@ struct irq_domain *eiointc_acpi_init(struct irq_domain *parent, struct irq_domain *htvec_acpi_init(struct irq_domain *parent, struct acpi_madt_ht_pic *acpi_htvec); -struct irq_domain *pch_lpc_acpi_init(struct irq_domain *parent, +int pch_lpc_acpi_init(struct irq_domain *parent, struct acpi_madt_lpc_pic *acpi_pchlpc); struct irq_domain *pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic *acpi_pchmsi); @@ -129,7 +129,7 @@ extern struct acpi_madt_bio_pic *acpi_pchpic[MAX_IO_PICS]; extern struct irq_domain *cpu_domain; extern struct irq_domain *liointc_domain; -extern struct irq_domain *pch_lpc_domain; +extern struct fwnode_handle *pch_lpc_handle; extern struct irq_domain *pch_msi_domain[MAX_IO_PICS]; extern struct irq_domain *pch_pic_domain[MAX_IO_PICS]; diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 37dd2dca8221..181504ba7e90 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -27,7 +27,6 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); struct irq_domain *cpu_domain; struct irq_domain *liointc_domain; -struct irq_domain *pch_lpc_domain; struct irq_domain *pch_msi_domain[MAX_IO_PICS]; struct irq_domain *pch_pic_domain[MAX_IO_PICS]; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index d82835756d1e..5463aa19c9af 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -616,6 +616,14 @@ config LOONGSON_PCH_MSI help Support for the Loongson PCH MSI Controller. +config LOONGSON_PCH_LPC + bool "Loongson PCH LPC Controller" + depends on MACH_LOONGSON64 + default (MACH_LOONGSON64 && LOONGARCH) + select IRQ_DOMAIN_HIERARCHY + help + Support for the Loongson PCH LPC Controller. + config MST_IRQ bool "MStar Interrupt Controller" depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index f98111ccf423..8c77e623eda9 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_LOONGSON_HTPIC) += irq-loongson-htpic.o obj-$(CONFIG_LOONGSON_HTVEC) += irq-loongson-htvec.o obj-$(CONFIG_LOONGSON_PCH_PIC) += irq-loongson-pch-pic.o obj-$(CONFIG_LOONGSON_PCH_MSI) += irq-loongson-pch-msi.o +obj-$(CONFIG_LOONGSON_PCH_LPC) += irq-loongson-pch-lpc.o obj-$(CONFIG_MST_IRQ) += irq-mst-intc.o obj-$(CONFIG_SL28CPLD_INTC) += irq-sl28cpld.o obj-$(CONFIG_IMS_MSI) += irq-ims-msi.o diff --git a/drivers/irqchip/irq-loongson-pch-lpc.c b/drivers/irqchip/irq-loongson-pch-lpc.c new file mode 100644 index 000000000000..68498af9af6f --- /dev/null +++ b/drivers/irqchip/irq-loongson-pch-lpc.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Loongson LPC Interrupt Controller support + * + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#define pr_fmt(fmt) "lpc: " fmt + +#include +#include +#include +#include +#include +#include + +/* Registers */ +#define LPC_INT_CTL 0x00 +#define LPC_INT_ENA 0x04 +#define LPC_INT_STS 0x08 +#define LPC_INT_CLR 0x0c +#define LPC_INT_POL 0x10 +#define LPC_COUNT 16 + +/* LPC_INT_CTL */ +#define LPC_INT_CTL_EN BIT(31) + +struct pch_lpc { + void __iomem *base; + struct irq_domain *lpc_domain; + raw_spinlock_t lpc_lock; + u32 saved_reg_ctl; + u32 saved_reg_ena; + u32 saved_reg_pol; +}; + +struct fwnode_handle *pch_lpc_handle; + +static void lpc_irq_ack(struct irq_data *d) +{ + unsigned long flags; + struct pch_lpc *priv = d->domain->host_data; + + raw_spin_lock_irqsave(&priv->lpc_lock, flags); + writel(0x1 << d->hwirq, priv->base + LPC_INT_CLR); + raw_spin_unlock_irqrestore(&priv->lpc_lock, flags); +} + +static void lpc_irq_mask(struct irq_data *d) +{ + unsigned long flags; + struct pch_lpc *priv = d->domain->host_data; + + raw_spin_lock_irqsave(&priv->lpc_lock, flags); + writel(readl(priv->base + LPC_INT_ENA) & (~(0x1 << (d->hwirq))), + priv->base + LPC_INT_ENA); + raw_spin_unlock_irqrestore(&priv->lpc_lock, flags); +} + +static void lpc_irq_unmask(struct irq_data *d) +{ + unsigned long flags; + struct pch_lpc *priv = d->domain->host_data; + + raw_spin_lock_irqsave(&priv->lpc_lock, flags); + writel(readl(priv->base + LPC_INT_ENA) | (0x1 << (d->hwirq)), + priv->base + LPC_INT_ENA); + raw_spin_unlock_irqrestore(&priv->lpc_lock, flags); +} + +static int lpc_irq_set_type(struct irq_data *d, unsigned int type) +{ + u32 val; + u32 mask = 0x1 << (d->hwirq); + struct pch_lpc *priv = d->domain->host_data; + + if (!(type & IRQ_TYPE_LEVEL_MASK)) + return 0; + + val = readl(priv->base + LPC_INT_POL); + + if (type == IRQ_TYPE_LEVEL_HIGH) + val |= mask; + else + val &= ~mask; + + writel(val, priv->base + LPC_INT_POL); + + return 0; +} + +static struct irq_chip pch_lpc_irq_chip = { + .name = "PCH LPC", + .irq_mask = lpc_irq_mask, + .irq_unmask = lpc_irq_unmask, + .irq_ack = lpc_irq_ack, + .irq_set_type = lpc_irq_set_type, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static void lpc_irq_dispatch(struct irq_desc *desc) +{ + u32 pending, bit, virq; + struct irq_chip *chip = irq_desc_get_chip(desc); + struct pch_lpc *priv = irq_desc_get_handler_data(desc); + + chained_irq_enter(chip, desc); + + pending = readl(priv->base + LPC_INT_ENA); + pending &= readl(priv->base + LPC_INT_STS); + if (!pending) + spurious_interrupt(); + + while (pending) { + bit = __ffs(pending); + + virq = irq_find_mapping(priv->lpc_domain, bit); + generic_handle_irq(virq); + pending &= ~BIT(bit); + } + chained_irq_exit(chip, desc); +} + +static int pch_lpc_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hw) +{ + irq_set_chip_and_handler(irq, &pch_lpc_irq_chip, handle_level_irq); + return 0; +} + +static const struct irq_domain_ops pch_lpc_domain_ops = { + .map = pch_lpc_map, + .translate = irq_domain_translate_twocell, +}; + +static void pch_lpc_reset(struct pch_lpc *priv) +{ + /* Enable the LPC interrupt, bit31: en bit30: edge */ + writel(LPC_INT_CTL_EN, priv->base + LPC_INT_CTL); + writel(0, priv->base + LPC_INT_ENA); + /* Clear all 18-bit interrpt bit */ + writel(GENMASK(17, 0), priv->base + LPC_INT_CLR); +} + +static int pch_lpc_disabled(struct pch_lpc *priv) +{ + return (readl(priv->base + LPC_INT_ENA) == 0xffffffff) && + (readl(priv->base + LPC_INT_STS) == 0xffffffff); +} + +int __init pch_lpc_acpi_init(struct irq_domain *parent, + struct acpi_madt_lpc_pic *acpi_pchlpc) +{ + int parent_irq; + struct pch_lpc *priv; + struct irq_fwspec fwspec; + struct fwnode_handle *irq_handle; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + raw_spin_lock_init(&priv->lpc_lock); + + priv->base = ioremap(acpi_pchlpc->address, acpi_pchlpc->size); + if (!priv->base) + goto free_priv; + + if (pch_lpc_disabled(priv)) { + pr_err("Failed to get LPC status\n"); + goto iounmap_base; + } + + irq_handle = irq_domain_alloc_named_fwnode("lpcintc"); + if (!irq_handle) { + pr_err("Unable to allocate domain handle\n"); + goto iounmap_base; + } + + priv->lpc_domain = irq_domain_create_linear(irq_handle, LPC_COUNT, + &pch_lpc_domain_ops, priv); + if (!priv->lpc_domain) { + pr_err("Failed to create IRQ domain\n"); + goto free_irq_handle; + } + pch_lpc_reset(priv); + + fwspec.fwnode = parent->fwnode; + fwspec.param[0] = acpi_pchlpc->cascade + GSI_MIN_PCH_IRQ; + fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH; + fwspec.param_count = 2; + parent_irq = irq_create_fwspec_mapping(&fwspec); + irq_set_chained_handler_and_data(parent_irq, lpc_irq_dispatch, priv); + + pch_lpc_handle = irq_handle; + return 0; + +free_irq_handle: + irq_domain_free_fwnode(irq_handle); +iounmap_base: + iounmap(priv->base); +free_priv: + kfree(priv); + + return -ENOMEM; +} -- Gitee From c0cb9abfde03c83c8903391d46624b75b7c4343e Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:27 +0800 Subject: [PATCH 03/23] irqchip/loongson-pch-pic: Add ACPI init support ANBZ: #5200 commit bcdd75c596c89d7925a3438fde2578ca23a62b06 upstream. PCH-PIC/PCH-MSI stands for "Interrupt Controller" that described in Section 5 of "Loongson 7A1000 Bridge User Manual". For more information please refer Documentation/loongarch/irq-chip-model.rst. Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-9-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 5 +- arch/loongarch/kernel/irq.c | 1 - arch/mips/include/asm/mach-loongson64/irq.h | 2 +- drivers/irqchip/Kconfig | 2 +- drivers/irqchip/irq-loongson-pch-pic.c | 175 ++++++++++++++++---- 5 files changed, 150 insertions(+), 35 deletions(-) diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 3e10595fead1..83739504c7fe 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -116,8 +116,9 @@ int pch_lpc_acpi_init(struct irq_domain *parent, struct acpi_madt_lpc_pic *acpi_pchlpc); struct irq_domain *pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic *acpi_pchmsi); -struct irq_domain *pch_pic_acpi_init(struct irq_domain *parent, +int pch_pic_acpi_init(struct irq_domain *parent, struct acpi_madt_bio_pic *acpi_pchpic); +int find_pch_pic(u32 gsi); extern struct acpi_madt_lio_pic *acpi_liointc; extern struct acpi_madt_eio_pic *acpi_eiointc[MAX_IO_PICS]; @@ -131,7 +132,7 @@ extern struct irq_domain *cpu_domain; extern struct irq_domain *liointc_domain; extern struct fwnode_handle *pch_lpc_handle; extern struct irq_domain *pch_msi_domain[MAX_IO_PICS]; -extern struct irq_domain *pch_pic_domain[MAX_IO_PICS]; +extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev); diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 181504ba7e90..575b8de08289 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -28,7 +28,6 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); struct irq_domain *cpu_domain; struct irq_domain *liointc_domain; struct irq_domain *pch_msi_domain[MAX_IO_PICS]; -struct irq_domain *pch_pic_domain[MAX_IO_PICS]; struct acpi_vector_group pch_group[MAX_IO_PICS]; struct acpi_vector_group msi_group[MAX_IO_PICS]; diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index 98ea977cf0b8..55e0dee12cb0 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -7,7 +7,7 @@ #define NR_MIPS_CPU_IRQS 8 #define NR_MAX_CHAINED_IRQS 40 /* Chained IRQs means those not directly used by devices */ #define NR_IRQS (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + NR_MAX_CHAINED_IRQS + 256) - +#define MAX_IO_PICS 1 #define MIPS_CPU_IRQ_BASE NR_IRQS_LEGACY #include diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 5463aa19c9af..a51aa5e61eec 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -599,7 +599,7 @@ config LOONGSON_HTVEC config LOONGSON_PCH_PIC bool "Loongson PCH PIC Controller" - depends on MACH_LOONGSON64 || COMPILE_TEST + depends on MACH_LOONGSON64 default MACH_LOONGSON64 select IRQ_DOMAIN_HIERARCHY select IRQ_FASTEOI_HIERARCHY_HANDLERS diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index 90e1ad6e3612..1b7ff05b18bd 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -33,13 +33,40 @@ #define PIC_REG_IDX(irq_id) ((irq_id) / PIC_COUNT_PER_REG) #define PIC_REG_BIT(irq_id) ((irq_id) % PIC_COUNT_PER_REG) +static int nr_pics; + struct pch_pic { void __iomem *base; struct irq_domain *pic_domain; u32 ht_vec_base; raw_spinlock_t pic_lock; + u32 vec_count; + u32 gsi_base; }; +static struct pch_pic *pch_pic_priv[MAX_IO_PICS]; + +struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; + +int find_pch_pic(u32 gsi) +{ + int i; + + /* Find the PCH_PIC that manages this GSI. */ + for (i = 0; i < MAX_IO_PICS; i++) { + struct pch_pic *priv = pch_pic_priv[i]; + + if (!priv) + return -1; + + if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count)) + return i; + } + + pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi); + return -1; +} + static void pch_pic_bitset(struct pch_pic *priv, int offset, int bit) { u32 reg; @@ -139,6 +166,28 @@ static struct irq_chip pch_pic_irq_chip = { .irq_set_type = pch_pic_set_type, }; +static int pch_pic_domain_translate(struct irq_domain *d, + struct irq_fwspec *fwspec, + unsigned long *hwirq, + unsigned int *type) +{ + struct pch_pic *priv = d->host_data; + struct device_node *of_node = to_of_node(fwspec->fwnode); + + if (fwspec->param_count < 1) + return -EINVAL; + + if (of_node) { + *hwirq = fwspec->param[0] + priv->ht_vec_base; + *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; + } else { + *hwirq = fwspec->param[0] - priv->gsi_base; + *type = IRQ_TYPE_NONE; + } + + return 0; +} + static int pch_pic_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { @@ -149,13 +198,13 @@ static int pch_pic_alloc(struct irq_domain *domain, unsigned int virq, struct irq_fwspec parent_fwspec; struct pch_pic *priv = domain->host_data; - err = irq_domain_translate_twocell(domain, fwspec, &hwirq, &type); + err = pch_pic_domain_translate(domain, fwspec, &hwirq, &type); if (err) return err; parent_fwspec.fwnode = domain->parent->fwnode; parent_fwspec.param_count = 1; - parent_fwspec.param[0] = hwirq + priv->ht_vec_base; + parent_fwspec.param[0] = hwirq; err = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec); if (err) @@ -170,7 +219,7 @@ static int pch_pic_alloc(struct irq_domain *domain, unsigned int virq, } static const struct irq_domain_ops pch_pic_domain_ops = { - .translate = irq_domain_translate_twocell, + .translate = pch_pic_domain_translate, .alloc = pch_pic_alloc, .free = irq_domain_free_irqs_parent, }; @@ -198,50 +247,37 @@ static void pch_pic_reset(struct pch_pic *priv) } } -static int pch_pic_of_init(struct device_node *node, - struct device_node *parent) +static int pch_pic_init(phys_addr_t addr, unsigned long size, int vec_base, + struct irq_domain *parent_domain, struct fwnode_handle *domain_handle, + u32 gsi_base) { struct pch_pic *priv; - struct irq_domain *parent_domain; - int err; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; raw_spin_lock_init(&priv->pic_lock); - priv->base = of_iomap(node, 0); - if (!priv->base) { - err = -ENOMEM; + priv->base = ioremap(addr, size); + if (!priv->base) goto free_priv; - } - parent_domain = irq_find_host(parent); - if (!parent_domain) { - pr_err("Failed to find the parent domain\n"); - err = -ENXIO; - goto iounmap_base; - } - - if (of_property_read_u32(node, "loongson,pic-base-vec", - &priv->ht_vec_base)) { - pr_err("Failed to determine pic-base-vec\n"); - err = -EINVAL; - goto iounmap_base; - } + priv->ht_vec_base = vec_base; + priv->vec_count = ((readq(priv->base) >> 48) & 0xff) + 1; + priv->gsi_base = gsi_base; priv->pic_domain = irq_domain_create_hierarchy(parent_domain, 0, - PIC_COUNT, - of_node_to_fwnode(node), - &pch_pic_domain_ops, - priv); + priv->vec_count, domain_handle, + &pch_pic_domain_ops, priv); + if (!priv->pic_domain) { pr_err("Failed to create IRQ domain\n"); - err = -ENOMEM; goto iounmap_base; } pch_pic_reset(priv); + pch_pic_handle[nr_pics] = domain_handle; + pch_pic_priv[nr_pics++] = priv; return 0; @@ -250,7 +286,86 @@ static int pch_pic_of_init(struct device_node *node, free_priv: kfree(priv); - return err; + return -EINVAL; +} + +#ifdef CONFIG_OF + +static int pch_pic_of_init(struct device_node *node, + struct device_node *parent) +{ + int err, vec_base; + struct resource res; + struct irq_domain *parent_domain; + + if (of_address_to_resource(node, 0, &res)) + return -EINVAL; + + parent_domain = irq_find_host(parent); + if (!parent_domain) { + pr_err("Failed to find the parent domain\n"); + return -ENXIO; + } + + if (of_property_read_u32(node, "loongson,pic-base-vec", &vec_base)) { + pr_err("Failed to determine pic-base-vec\n"); + return -EINVAL; + } + + err = pch_pic_init(res.start, resource_size(&res), vec_base, + parent_domain, of_node_to_fwnode(node), 0); + if (err < 0) + return err; + + return 0; } IRQCHIP_DECLARE(pch_pic, "loongson,pch-pic-1.0", pch_pic_of_init); + +#endif + +#ifdef CONFIG_ACPI +static int __init +pch_lpc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_lpc_pic *pchlpc_entry = (struct acpi_madt_lpc_pic *)header; + + return pch_lpc_acpi_init(pch_pic_priv[0]->pic_domain, pchlpc_entry); +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_LPC_PIC, + pch_lpc_parse_madt, 0); + return 0; +} + +int __init pch_pic_acpi_init(struct irq_domain *parent, + struct acpi_madt_bio_pic *acpi_pchpic) +{ + int ret, vec_base; + struct fwnode_handle *domain_handle; + + vec_base = acpi_pchpic->gsi_base - GSI_MIN_PCH_IRQ; + + domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchpic); + if (!domain_handle) { + pr_err("Unable to allocate domain handle\n"); + return -ENOMEM; + } + + ret = pch_pic_init(acpi_pchpic->address, acpi_pchpic->size, + vec_base, parent, domain_handle, acpi_pchpic->gsi_base); + + if (ret < 0) { + irq_domain_free_fwnode(domain_handle); + return ret; + } + + if (acpi_pchpic->id == 0) + acpi_cascade_irqdomain_init(); + + return ret; +} +#endif -- Gitee From 42fedf16d373a23c80ea86b2dda6d344d2aa83b3 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:28 +0800 Subject: [PATCH 04/23] irqchip/loongson-pch-msi: Add ACPI init support ANBZ: #5200 commit 023087324000ae704cf3cfd0abf1fc30c6e0e8d5 upstream. PCH-PIC/PCH-MSI stands for "Interrupt Controller" that described in Section 5 of "Loongson 7A1000 Bridge User Manual". For more information please refer Documentation/loongarch/irq-chip-model.rst. Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-10-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 12 ++- arch/loongarch/kernel/irq.c | 1 - drivers/irqchip/Kconfig | 2 +- drivers/irqchip/irq-loongson-pch-msi.c | 129 ++++++++++++++++--------- 4 files changed, 97 insertions(+), 47 deletions(-) diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 83739504c7fe..7e0cce6bd7f1 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -114,11 +114,20 @@ struct irq_domain *htvec_acpi_init(struct irq_domain *parent, struct acpi_madt_ht_pic *acpi_htvec); int pch_lpc_acpi_init(struct irq_domain *parent, struct acpi_madt_lpc_pic *acpi_pchlpc); -struct irq_domain *pch_msi_acpi_init(struct irq_domain *parent, +#if IS_ENABLED(CONFIG_LOONGSON_PCH_MSI) +int pch_msi_acpi_init(struct irq_domain *parent, struct acpi_madt_msi_pic *acpi_pchmsi); +#else +static inline int pch_msi_acpi_init(struct irq_domain *parent, + struct acpi_madt_msi_pic *acpi_pchmsi) +{ + return 0; +} +#endif int pch_pic_acpi_init(struct irq_domain *parent, struct acpi_madt_bio_pic *acpi_pchpic); int find_pch_pic(u32 gsi); +struct fwnode_handle *get_pch_msi_handle(int pci_segment); extern struct acpi_madt_lio_pic *acpi_liointc; extern struct acpi_madt_eio_pic *acpi_eiointc[MAX_IO_PICS]; @@ -131,7 +140,6 @@ extern struct acpi_madt_bio_pic *acpi_pchpic[MAX_IO_PICS]; extern struct irq_domain *cpu_domain; extern struct irq_domain *liointc_domain; extern struct fwnode_handle *pch_lpc_handle; -extern struct irq_domain *pch_msi_domain[MAX_IO_PICS]; extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev); diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 575b8de08289..066f892943fe 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -27,7 +27,6 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); struct irq_domain *cpu_domain; struct irq_domain *liointc_domain; -struct irq_domain *pch_msi_domain[MAX_IO_PICS]; struct acpi_vector_group pch_group[MAX_IO_PICS]; struct acpi_vector_group msi_group[MAX_IO_PICS]; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index a51aa5e61eec..492fc8328334 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -608,7 +608,7 @@ config LOONGSON_PCH_PIC config LOONGSON_PCH_MSI bool "Loongson PCH MSI Controller" - depends on MACH_LOONGSON64 || COMPILE_TEST + depends on MACH_LOONGSON64 depends on PCI default MACH_LOONGSON64 select IRQ_DOMAIN_HIERARCHY diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c index 32562b7e681b..d0e8551bebfa 100644 --- a/drivers/irqchip/irq-loongson-pch-msi.c +++ b/drivers/irqchip/irq-loongson-pch-msi.c @@ -15,6 +15,8 @@ #include #include +static int nr_pics; + struct pch_msi_data { struct mutex msi_map_lock; phys_addr_t doorbell; @@ -23,6 +25,8 @@ struct pch_msi_data { unsigned long *msi_map; }; +static struct fwnode_handle *pch_msi_handle[MAX_IO_PICS]; + static void pch_msi_mask_msi_irq(struct irq_data *d) { pci_msi_mask_irq(d); @@ -154,12 +158,12 @@ static const struct irq_domain_ops pch_msi_middle_domain_ops = { }; static int pch_msi_init_domains(struct pch_msi_data *priv, - struct device_node *node, - struct irq_domain *parent) + struct irq_domain *parent, + struct fwnode_handle *domain_handle) { struct irq_domain *middle_domain, *msi_domain; - middle_domain = irq_domain_create_linear(of_node_to_fwnode(node), + middle_domain = irq_domain_create_linear(domain_handle, priv->num_irqs, &pch_msi_middle_domain_ops, priv); @@ -171,7 +175,7 @@ static int pch_msi_init_domains(struct pch_msi_data *priv, middle_domain->parent = parent; irq_domain_update_bus_token(middle_domain, DOMAIN_BUS_NEXUS); - msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node), + msi_domain = pci_msi_create_irq_domain(domain_handle, &pch_msi_domain_info, middle_domain); if (!msi_domain) { @@ -183,19 +187,11 @@ static int pch_msi_init_domains(struct pch_msi_data *priv, return 0; } -static int pch_msi_init(struct device_node *node, - struct device_node *parent) +static int pch_msi_init(phys_addr_t msg_address, int irq_base, int irq_count, + struct irq_domain *parent_domain, struct fwnode_handle *domain_handle) { - struct pch_msi_data *priv; - struct irq_domain *parent_domain; - struct resource res; int ret; - - parent_domain = irq_find_host(parent); - if (!parent_domain) { - pr_err("Failed to find the parent domain\n"); - return -ENXIO; - } + struct pch_msi_data *priv; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) @@ -203,48 +199,95 @@ static int pch_msi_init(struct device_node *node, mutex_init(&priv->msi_map_lock); - ret = of_address_to_resource(node, 0, &res); - if (ret) { - pr_err("Failed to allocate resource\n"); - goto err_priv; - } - - priv->doorbell = res.start; - - if (of_property_read_u32(node, "loongson,msi-base-vec", - &priv->irq_first)) { - pr_err("Unable to parse MSI vec base\n"); - ret = -EINVAL; - goto err_priv; - } - - if (of_property_read_u32(node, "loongson,msi-num-vecs", - &priv->num_irqs)) { - pr_err("Unable to parse MSI vec number\n"); - ret = -EINVAL; - goto err_priv; - } + priv->doorbell = msg_address; + priv->irq_first = irq_base; + priv->num_irqs = irq_count; priv->msi_map = bitmap_zalloc(priv->num_irqs, GFP_KERNEL); - if (!priv->msi_map) { - ret = -ENOMEM; + if (!priv->msi_map) goto err_priv; - } pr_debug("Registering %d MSIs, starting at %d\n", priv->num_irqs, priv->irq_first); - ret = pch_msi_init_domains(priv, node, parent_domain); + ret = pch_msi_init_domains(priv, parent_domain, domain_handle); if (ret) goto err_map; + pch_msi_handle[nr_pics++] = domain_handle; return 0; err_map: - kfree(priv->msi_map); + bitmap_free(priv->msi_map); err_priv: kfree(priv); - return ret; + + return -EINVAL; +} + +#ifdef CONFIG_OF +static int pch_msi_of_init(struct device_node *node, struct device_node *parent) +{ + int err; + int irq_base, irq_count; + struct resource res; + struct irq_domain *parent_domain; + + parent_domain = irq_find_host(parent); + if (!parent_domain) { + pr_err("Failed to find the parent domain\n"); + return -ENXIO; + } + + if (of_address_to_resource(node, 0, &res)) { + pr_err("Failed to allocate resource\n"); + return -EINVAL; + } + + if (of_property_read_u32(node, "loongson,msi-base-vec", &irq_base)) { + pr_err("Unable to parse MSI vec base\n"); + return -EINVAL; + } + + if (of_property_read_u32(node, "loongson,msi-num-vecs", &irq_count)) { + pr_err("Unable to parse MSI vec number\n"); + return -EINVAL; + } + + err = pch_msi_init(res.start, irq_base, irq_count, parent_domain, of_node_to_fwnode(node)); + if (err < 0) + return err; + + return 0; } -IRQCHIP_DECLARE(pch_msi, "loongson,pch-msi-1.0", pch_msi_init); +IRQCHIP_DECLARE(pch_msi, "loongson,pch-msi-1.0", pch_msi_of_init); +#endif + +#ifdef CONFIG_ACPI +struct fwnode_handle *get_pch_msi_handle(int pci_segment) +{ + int i; + + for (i = 0; i < MAX_IO_PICS; i++) { + if (msi_group[i].pci_segment == pci_segment) + return pch_msi_handle[i]; + } + return NULL; +} + +int __init pch_msi_acpi_init(struct irq_domain *parent, + struct acpi_madt_msi_pic *acpi_pchmsi) +{ + int ret; + struct fwnode_handle *domain_handle; + + domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchmsi); + ret = pch_msi_init(acpi_pchmsi->msg_address, acpi_pchmsi->start, + acpi_pchmsi->count, parent, domain_handle); + if (ret < 0) + irq_domain_free_fwnode(domain_handle); + + return ret; +} +#endif -- Gitee From 242f97378e02d1ba5439879ff1df3e7ecf14af99 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:29 +0800 Subject: [PATCH 05/23] irqchip/loongson-liointc: Add ACPI init support ANBZ: #5200 commit 0858ed035a85c3ae79553200d2d818797cf849f5 upstream. LIOINTC stands for "Legacy I/O Interrupts" that described in Section 11.1 of "Loongson 3A5000 Processor Reference Manual". For more information please refer Documentation/loongarch/irq-chip-model.rst. Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-11-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 4 +- arch/loongarch/kernel/irq.c | 1 - arch/mips/include/asm/mach-loongson64/irq.h | 1 + drivers/irqchip/irq-loongson-liointc.c | 189 +++++++++++++++----- 4 files changed, 149 insertions(+), 46 deletions(-) diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 7e0cce6bd7f1..c6feec204b03 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -105,7 +105,7 @@ struct acpi_madt_lpc_pic; struct irq_domain *loongarch_cpu_irq_init(void); -struct irq_domain *liointc_acpi_init(struct irq_domain *parent, +int liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc); struct irq_domain *eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc); @@ -138,7 +138,7 @@ extern struct acpi_madt_msi_pic *acpi_pchmsi[MAX_IO_PICS]; extern struct acpi_madt_bio_pic *acpi_pchpic[MAX_IO_PICS]; extern struct irq_domain *cpu_domain; -extern struct irq_domain *liointc_domain; +extern struct fwnode_handle *liointc_handle; extern struct fwnode_handle *pch_lpc_handle; extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 066f892943fe..da131f51225a 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -26,7 +26,6 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); struct irq_domain *cpu_domain; -struct irq_domain *liointc_domain; struct acpi_vector_group pch_group[MAX_IO_PICS]; struct acpi_vector_group msi_group[MAX_IO_PICS]; diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index 55e0dee12cb0..67c15f320f93 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -9,6 +9,7 @@ #define NR_IRQS (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + NR_MAX_CHAINED_IRQS + 256) #define MAX_IO_PICS 1 #define MIPS_CPU_IRQ_BASE NR_IRQS_LEGACY +#define GSI_MIN_CPU_IRQ 0 #include diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 9ed1bc473663..3c9feab780b3 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -16,10 +16,15 @@ #include #include -#include +#ifdef CONFIG_MIPS +#include +#else +#include +#endif #define LIOINTC_CHIP_IRQ 32 -#define LIOINTC_NUM_PARENT 4 +#define LIOINTC_NUM_PARENT 4 +#define LIOINTC_NUM_CORES 4 #define LIOINTC_INTC_CHIP_START 0x20 @@ -34,6 +39,12 @@ #define LIOINTC_ERRATA_IRQ 10 +#if defined(CONFIG_MIPS) +#define liointc_core_id get_ebase_cpunum() +#else +#define liointc_core_id get_csr_cpuid() +#endif + struct liointc_handler_data { struct liointc_priv *priv; u32 parent_int_map; @@ -42,20 +53,24 @@ struct liointc_handler_data { struct liointc_priv { struct irq_chip_generic *gc; struct liointc_handler_data handler[LIOINTC_NUM_PARENT]; + void __iomem *core_isr[LIOINTC_NUM_CORES]; u8 map_cache[LIOINTC_CHIP_IRQ]; bool has_lpc_irq_errata; }; +struct fwnode_handle *liointc_handle; + static void liointc_chained_handle_irq(struct irq_desc *desc) { struct liointc_handler_data *handler = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); struct irq_chip_generic *gc = handler->priv->gc; + int core = liointc_core_id % LIOINTC_NUM_CORES; u32 pending; chained_irq_enter(chip, desc); - pending = readl(gc->reg_base + LIOINTC_REG_INTC_STATUS); + pending = readl(handler->priv->core_isr[core]); if (!pending) { /* Always blame LPC IRQ if we have that bug */ @@ -140,67 +155,79 @@ static void liointc_resume(struct irq_chip_generic *gc) irq_gc_unlock_irqrestore(gc, flags); } -static const char * const parent_names[] = {"int0", "int1", "int2", "int3"}; +static int parent_irq[LIOINTC_NUM_PARENT]; +static u32 parent_int_map[LIOINTC_NUM_PARENT]; +static const char *const parent_names[] = {"int0", "int1", "int2", "int3"}; +static const char *const core_reg_names[] = {"isr0", "isr1", "isr2", "isr3"}; + +static int liointc_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0] - GSI_MIN_CPU_IRQ; + *out_type = IRQ_TYPE_NONE; + return 0; +} + +static const struct irq_domain_ops acpi_irq_gc_ops = { + .map = irq_map_generic_chip, + .unmap = irq_unmap_generic_chip, + .xlate = liointc_domain_xlate, +}; -int __init liointc_of_init(struct device_node *node, - struct device_node *parent) +static int liointc_init(phys_addr_t addr, unsigned long size, int revision, + struct fwnode_handle *domain_handle, struct device_node *node) { + int i, err; + void __iomem *base; + struct irq_chip_type *ct; struct irq_chip_generic *gc; struct irq_domain *domain; - struct irq_chip_type *ct; struct liointc_priv *priv; - void __iomem *base; - u32 of_parent_int_map[LIOINTC_NUM_PARENT]; - int parent_irq[LIOINTC_NUM_PARENT]; - bool have_parent = FALSE; - int sz, i, err = 0; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - base = of_iomap(node, 0); - if (!base) { - err = -ENODEV; + base = ioremap(addr, size); + if (!base) goto out_free_priv; - } - - for (i = 0; i < LIOINTC_NUM_PARENT; i++) { - parent_irq[i] = of_irq_get_byname(node, parent_names[i]); - if (parent_irq[i] > 0) - have_parent = TRUE; - } - if (!have_parent) { - err = -ENODEV; - goto out_iounmap; - } - sz = of_property_read_variable_u32_array(node, - "loongson,parent_int_map", - &of_parent_int_map[0], - LIOINTC_NUM_PARENT, - LIOINTC_NUM_PARENT); - if (sz < 4) { - pr_err("loongson-liointc: No parent_int_map\n"); - err = -ENODEV; - goto out_iounmap; - } + for (i = 0; i < LIOINTC_NUM_CORES; i++) + priv->core_isr[i] = base + LIOINTC_REG_INTC_STATUS; for (i = 0; i < LIOINTC_NUM_PARENT; i++) - priv->handler[i].parent_int_map = of_parent_int_map[i]; + priv->handler[i].parent_int_map = parent_int_map[i]; + + if (revision > 1) { + for (i = 0; i < LIOINTC_NUM_CORES; i++) { + int index = of_property_match_string(node, + "reg-names", core_reg_names[i]); + + if (index < 0) + return -EINVAL; + + priv->core_isr[i] = of_iomap(node, index); + } + } /* Setup IRQ domain */ - domain = irq_domain_add_linear(node, 32, + if (!acpi_disabled) + domain = irq_domain_create_linear(domain_handle, LIOINTC_CHIP_IRQ, + &acpi_irq_gc_ops, priv); + else + domain = irq_domain_create_linear(domain_handle, LIOINTC_CHIP_IRQ, &irq_generic_chip_ops, priv); if (!domain) { pr_err("loongson-liointc: cannot add IRQ domain\n"); - err = -EINVAL; goto out_iounmap; } - err = irq_alloc_domain_generic_chips(domain, 32, 1, - node->full_name, handle_level_irq, - IRQ_NOPROBE, 0, 0); + err = irq_alloc_domain_generic_chips(domain, LIOINTC_CHIP_IRQ, 1, + (node ? node->full_name : "LIOINTC"), + handle_level_irq, 0, IRQ_NOPROBE, 0); if (err) { pr_err("loongson-liointc: unable to register IRQ domain\n"); goto out_free_domain; @@ -256,6 +283,7 @@ int __init liointc_of_init(struct device_node *node, liointc_chained_handle_irq, &priv->handler[i]); } + liointc_handle = domain_handle; return 0; out_free_domain: @@ -265,8 +293,83 @@ int __init liointc_of_init(struct device_node *node, out_free_priv: kfree(priv); - return err; + return -EINVAL; +} + +#ifdef CONFIG_OF + +static int __init liointc_of_init(struct device_node *node, + struct device_node *parent) +{ + bool have_parent = FALSE; + int sz, i, index, revision, err = 0; + struct resource res; + + if (!of_device_is_compatible(node, "loongson,liointc-2.0")) { + index = 0; + revision = 1; + } else { + index = of_property_match_string(node, "reg-names", "main"); + revision = 2; + } + + if (of_address_to_resource(node, index, &res)) + return -EINVAL; + + for (i = 0; i < LIOINTC_NUM_PARENT; i++) { + parent_irq[i] = of_irq_get_byname(node, parent_names[i]); + if (parent_irq[i] > 0) + have_parent = TRUE; + } + if (!have_parent) + return -ENODEV; + + sz = of_property_read_variable_u32_array(node, + "loongson,parent_int_map", + &parent_int_map[0], + LIOINTC_NUM_PARENT, + LIOINTC_NUM_PARENT); + if (sz < 4) { + pr_err("loongson-liointc: No parent_int_map\n"); + return -ENODEV; + } + + err = liointc_init(res.start, resource_size(&res), + revision, of_node_to_fwnode(node), node); + if (err < 0) + return err; + + return 0; } IRQCHIP_DECLARE(loongson_liointc_1_0, "loongson,liointc-1.0", liointc_of_init); IRQCHIP_DECLARE(loongson_liointc_1_0a, "loongson,liointc-1.0a", liointc_of_init); +IRQCHIP_DECLARE(loongson_liointc_2_0, "loongson,liointc-2.0", liointc_of_init); + +#endif + +#ifdef CONFIG_ACPI +int __init liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc) +{ + int ret; + struct fwnode_handle *domain_handle; + + parent_int_map[0] = acpi_liointc->cascade_map[0]; + parent_int_map[1] = acpi_liointc->cascade_map[1]; + + parent_irq[0] = irq_create_mapping(parent, acpi_liointc->cascade[0]); + parent_irq[1] = irq_create_mapping(parent, acpi_liointc->cascade[1]); + + domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_liointc); + if (!domain_handle) { + pr_err("Unable to allocate domain handle\n"); + return -ENOMEM; + } + ret = liointc_init(acpi_liointc->address, acpi_liointc->size, + 1, domain_handle, NULL); + if (ret) + irq_domain_free_fwnode(domain_handle); + + return ret; +} +#endif -- Gitee From 87245d03c3b213cbb10880731c4afdcf1039b2d6 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:30 +0800 Subject: [PATCH 06/23] irqchip: Add Loongson Extended I/O interrupt controller support ANBZ: #5200 commit dd281e1a1a937ee2f13bd0db5be78e5f5b811ca7 upstream. EIOINTC stands for "Extended I/O Interrupts" that described in Section 11.2 of "Loongson 3A5000 Processor Reference Manual". For more information please refer Documentation/loongarch/irq-chip-model.rst. Loongson-3A5000 has 4 cores per NUMA node, and each NUMA node has an EIOINTC; while Loongson-3C5000 has 16 cores per NUMA node, and each NUMA node has 4 EIOINTCs. In other words, 16 cores of one NUMA node in Loongson-3C5000 are organized in 4 groups, each group connects to an EIOINTC. We call the "group" here as an EIOINTC node, so each EIOINTC node always includes 4 cores (both in Loongson-3A5000 and Loongson- 3C5000). Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-12-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 11 +- drivers/irqchip/Kconfig | 10 + drivers/irqchip/Makefile | 1 + drivers/irqchip/irq-loongson-eiointc.c | 395 +++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 5 files changed, 408 insertions(+), 10 deletions(-) create mode 100644 drivers/irqchip/irq-loongson-eiointc.c diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index c6feec204b03..2308c51973bd 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -87,15 +87,6 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS]; extern int find_pch_pic(u32 gsi); extern int eiointc_get_node(int id); -static inline void eiointc_enable(void) -{ - uint64_t misc; - - misc = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); - misc |= IOCSR_MISC_FUNC_EXT_IOI_EN; - iocsr_write64(misc, LOONGARCH_IOCSR_MISC_FUNC); -} - struct acpi_madt_lio_pic; struct acpi_madt_eio_pic; struct acpi_madt_ht_pic; @@ -107,7 +98,7 @@ struct irq_domain *loongarch_cpu_irq_init(void); int liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc); -struct irq_domain *eiointc_acpi_init(struct irq_domain *parent, +int eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc); struct irq_domain *htvec_acpi_init(struct irq_domain *parent, diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 492fc8328334..271996254dc6 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -580,6 +580,16 @@ config LOONGSON_LIOINTC help Support for the Loongson Local I/O Interrupt Controller. +config LOONGSON_EIOINTC + bool "Loongson Extend I/O Interrupt Controller" + depends on LOONGARCH + depends on MACH_LOONGSON64 + default MACH_LOONGSON64 + select IRQ_DOMAIN_HIERARCHY + select GENERIC_IRQ_CHIP + help + Support for the Loongson3 Extend I/O Interrupt Vector Controller. + config LOONGSON_HTPIC bool "Loongson3 HyperTransport PIC Controller" depends on MACH_LOONGSON64 diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 8c77e623eda9..973ea2f98daf 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -114,6 +114,7 @@ obj-$(CONFIG_TI_SCI_INTR_IRQCHIP) += irq-ti-sci-intr.o obj-$(CONFIG_TI_SCI_INTA_IRQCHIP) += irq-ti-sci-inta.o obj-$(CONFIG_TI_PRUSS_INTC) += irq-pruss-intc.o obj-$(CONFIG_LOONGSON_LIOINTC) += irq-loongson-liointc.o +obj-$(CONFIG_LOONGSON_EIOINTC) += irq-loongson-eiointc.o obj-$(CONFIG_LOONGSON_HTPIC) += irq-loongson-htpic.o obj-$(CONFIG_LOONGSON_HTVEC) += irq-loongson-htvec.o obj-$(CONFIG_LOONGSON_PCH_PIC) += irq-loongson-pch-pic.o diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c new file mode 100644 index 000000000000..3017d75d0d75 --- /dev/null +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Loongson Extend I/O Interrupt Controller support + * + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#define pr_fmt(fmt) "eiointc: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define EIOINTC_REG_NODEMAP 0x14a0 +#define EIOINTC_REG_IPMAP 0x14c0 +#define EIOINTC_REG_ENABLE 0x1600 +#define EIOINTC_REG_BOUNCE 0x1680 +#define EIOINTC_REG_ISR 0x1800 +#define EIOINTC_REG_ROUTE 0x1c00 + +#define VEC_REG_COUNT 4 +#define VEC_COUNT_PER_REG 64 +#define VEC_COUNT (VEC_REG_COUNT * VEC_COUNT_PER_REG) +#define VEC_REG_IDX(irq_id) ((irq_id) / VEC_COUNT_PER_REG) +#define VEC_REG_BIT(irq_id) ((irq_id) % VEC_COUNT_PER_REG) +#define EIOINTC_ALL_ENABLE 0xffffffff + +#define MAX_EIO_NODES (NR_CPUS / CORES_PER_EIO_NODE) + +static int nr_pics; + +struct eiointc_priv { + u32 node; + nodemask_t node_map; + cpumask_t cpuspan_map; + struct fwnode_handle *domain_handle; + struct irq_domain *eiointc_domain; +}; + +static struct eiointc_priv *eiointc_priv[MAX_IO_PICS]; + +static void eiointc_enable(void) +{ + uint64_t misc; + + misc = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC); + misc |= IOCSR_MISC_FUNC_EXT_IOI_EN; + iocsr_write64(misc, LOONGARCH_IOCSR_MISC_FUNC); +} + +static int cpu_to_eio_node(int cpu) +{ + return cpu_logical_map(cpu) / CORES_PER_EIO_NODE; +} + +static void eiointc_set_irq_route(int pos, unsigned int cpu, unsigned int mnode, nodemask_t *node_map) +{ + int i, node, cpu_node, route_node; + unsigned char coremap; + uint32_t pos_off, data, data_byte, data_mask; + + pos_off = pos & ~3; + data_byte = pos & 3; + data_mask = ~BIT_MASK(data_byte) & 0xf; + + /* Calculate node and coremap of target irq */ + cpu_node = cpu_logical_map(cpu) / CORES_PER_EIO_NODE; + coremap = BIT(cpu_logical_map(cpu) % CORES_PER_EIO_NODE); + + for_each_online_cpu(i) { + node = cpu_to_eio_node(i); + if (!node_isset(node, *node_map)) + continue; + + /* EIO node 0 is in charge of inter-node interrupt dispatch */ + route_node = (node == mnode) ? cpu_node : node; + data = ((coremap | (route_node << 4)) << (data_byte * 8)); + csr_any_send(EIOINTC_REG_ROUTE + pos_off, data, data_mask, node * CORES_PER_EIO_NODE); + } +} + +static DEFINE_RAW_SPINLOCK(affinity_lock); + +static int eiointc_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, bool force) +{ + unsigned int cpu; + unsigned long flags; + uint32_t vector, regaddr; + struct cpumask intersect_affinity; + struct eiointc_priv *priv = d->domain->host_data; + + raw_spin_lock_irqsave(&affinity_lock, flags); + + cpumask_and(&intersect_affinity, affinity, cpu_online_mask); + cpumask_and(&intersect_affinity, &intersect_affinity, &priv->cpuspan_map); + + if (cpumask_empty(&intersect_affinity)) { + raw_spin_unlock_irqrestore(&affinity_lock, flags); + return -EINVAL; + } + cpu = cpumask_first(&intersect_affinity); + + vector = d->hwirq; + regaddr = EIOINTC_REG_ENABLE + ((vector >> 5) << 2); + + /* Mask target vector */ + csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)), 0x0, 0); + /* Set route for target vector */ + eiointc_set_irq_route(vector, cpu, priv->node, &priv->node_map); + /* Unmask target vector */ + csr_any_send(regaddr, EIOINTC_ALL_ENABLE, 0x0, 0); + + irq_data_update_effective_affinity(d, cpumask_of(cpu)); + + raw_spin_unlock_irqrestore(&affinity_lock, flags); + + return IRQ_SET_MASK_OK; +} + +static int eiointc_index(int node) +{ + int i; + + for (i = 0; i < nr_pics; i++) { + if (node_isset(node, eiointc_priv[i]->node_map)) + return i; + } + + return -1; +} + +static int eiointc_router_init(unsigned int cpu) +{ + int i, bit; + uint32_t data; + uint32_t node = cpu_to_eio_node(cpu); + uint32_t index = eiointc_index(node); + + if (index < 0) { + pr_err("Error: invalid nodemap!\n"); + return -1; + } + + if ((cpu_logical_map(cpu) % CORES_PER_EIO_NODE) == 0) { + eiointc_enable(); + + for (i = 0; i < VEC_COUNT / 32; i++) { + data = (((1 << (i * 2 + 1)) << 16) | (1 << (i * 2))); + iocsr_write32(data, EIOINTC_REG_NODEMAP + i * 4); + } + + for (i = 0; i < VEC_COUNT / 32 / 4; i++) { + bit = BIT(1 + index); /* Route to IP[1 + index] */ + data = bit | (bit << 8) | (bit << 16) | (bit << 24); + iocsr_write32(data, EIOINTC_REG_IPMAP + i * 4); + } + + for (i = 0; i < VEC_COUNT / 4; i++) { + /* Route to Node-0 Core-0 */ + if (index == 0) + bit = BIT(cpu_logical_map(0)); + else + bit = (eiointc_priv[index]->node << 4) | 1; + + data = bit | (bit << 8) | (bit << 16) | (bit << 24); + iocsr_write32(data, EIOINTC_REG_ROUTE + i * 4); + } + + for (i = 0; i < VEC_COUNT / 32; i++) { + data = 0xffffffff; + iocsr_write32(data, EIOINTC_REG_ENABLE + i * 4); + iocsr_write32(data, EIOINTC_REG_BOUNCE + i * 4); + } + } + + return 0; +} + +static void eiointc_irq_dispatch(struct irq_desc *desc) +{ + int i; + u64 pending; + bool handled = false; + struct irq_chip *chip = irq_desc_get_chip(desc); + struct eiointc_priv *priv = irq_desc_get_handler_data(desc); + + chained_irq_enter(chip, desc); + + for (i = 0; i < VEC_REG_COUNT; i++) { + pending = iocsr_read64(EIOINTC_REG_ISR + (i << 3)); + iocsr_write64(pending, EIOINTC_REG_ISR + (i << 3)); + while (pending) { + int bit = __ffs(pending); + int virq = irq_linear_revmap(priv->eiointc_domain, bit + VEC_COUNT_PER_REG * i); + + generic_handle_irq(virq); + pending &= ~BIT(bit); + handled = true; + } + } + + if (!handled) + spurious_interrupt(); + + chained_irq_exit(chip, desc); +} + +static void eiointc_ack_irq(struct irq_data *d) +{ +} + +static void eiointc_mask_irq(struct irq_data *d) +{ +} + +static void eiointc_unmask_irq(struct irq_data *d) +{ +} + +static struct irq_chip eiointc_irq_chip = { + .name = "EIOINTC", + .irq_ack = eiointc_ack_irq, + .irq_mask = eiointc_mask_irq, + .irq_unmask = eiointc_unmask_irq, + .irq_set_affinity = eiointc_set_irq_affinity, +}; + +static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + int ret; + unsigned int i, type; + unsigned long hwirq = 0; + struct eiointc *priv = domain->host_data; + + ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, &eiointc_irq_chip, + priv, handle_edge_irq, NULL, NULL); + } + + return 0; +} + +static void eiointc_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 const struct irq_domain_ops eiointc_domain_ops = { + .translate = irq_domain_translate_onecell, + .alloc = eiointc_domain_alloc, + .free = eiointc_domain_free, +}; + +static void acpi_set_vec_parent(int node, struct irq_domain *parent, struct acpi_vector_group *vec_group) +{ + int i; + + if (cpu_has_flatmode) + node = cpu_to_node(node * CORES_PER_EIO_NODE); + + for (i = 0; i < MAX_IO_PICS; i++) { + if (node == vec_group[i].node) { + vec_group[i].parent = parent; + return; + } + } +} + +struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group) +{ + int i; + + for (i = 0; i < MAX_IO_PICS; i++) { + if (node == vec_group[i].node) + return vec_group[i].parent; + } + return NULL; +} + +static int __init +pch_pic_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_bio_pic *pchpic_entry = (struct acpi_madt_bio_pic *)header; + unsigned int node = (pchpic_entry->address >> 44) & 0xf; + struct irq_domain *parent = acpi_get_vec_parent(node, pch_group); + + if (parent) + return pch_pic_acpi_init(parent, pchpic_entry); + + return -EINVAL; +} + +static int __init +pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; + struct irq_domain *parent = acpi_get_vec_parent(eiointc_priv[nr_pics - 1]->node, msi_group); + + if (parent) + return pch_msi_acpi_init(parent, pchmsi_entry); + + return -EINVAL; +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_BIO_PIC, + pch_pic_parse_madt, 0); + acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, + pch_msi_parse_madt, 1); + return 0; +} + +int __init eiointc_acpi_init(struct irq_domain *parent, + struct acpi_madt_eio_pic *acpi_eiointc) +{ + int i, parent_irq; + unsigned long node_map; + struct eiointc_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_eiointc); + if (!priv->domain_handle) { + pr_err("Unable to allocate domain handle\n"); + goto out_free_priv; + } + + priv->node = acpi_eiointc->node; + node_map = acpi_eiointc->node_map ? : -1ULL; + + for_each_possible_cpu(i) { + if (node_map & (1ULL << cpu_to_eio_node(i))) { + node_set(cpu_to_eio_node(i), priv->node_map); + cpumask_or(&priv->cpuspan_map, &priv->cpuspan_map, cpumask_of(i)); + } + } + + /* Setup IRQ domain */ + priv->eiointc_domain = irq_domain_create_linear(priv->domain_handle, VEC_COUNT, + &eiointc_domain_ops, priv); + if (!priv->eiointc_domain) { + pr_err("loongson-eiointc: cannot add IRQ domain\n"); + goto out_free_handle; + } + + eiointc_priv[nr_pics++] = priv; + + eiointc_router_init(0); + + parent_irq = irq_create_mapping(parent, acpi_eiointc->cascade); + irq_set_chained_handler_and_data(parent_irq, eiointc_irq_dispatch, priv); + + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, + "irqchip/loongarch/intc:starting", + eiointc_router_init, NULL); + + acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, pch_group); + acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, msi_group); + acpi_cascade_irqdomain_init(); + + return 0; + +out_free_handle: + irq_domain_free_fwnode(priv->domain_handle); + priv->domain_handle = NULL; +out_free_priv: + kfree(priv); + + return -ENOMEM; +} diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e6a0fc45e79e..7fa85e9d135d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -105,6 +105,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_RISCV_STARTING, + CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_MICROCODE_LOADER, -- Gitee From e46b08747bd8a0b073e01450910a41549333d512 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Jul 2022 18:51:31 +0800 Subject: [PATCH 07/23] irqchip: Add LoongArch CPU interrupt controller support ANBZ: #5200 commit b2d3e3354e2a0d0e912308618ea33d0337f405c3 upstream. LoongArch CPUINTC stands for CSR.ECFG/CSR.ESTAT and related interrupt controller that described in Section 7.4 of "LoongArch Reference Manual, Vol 1". For more information please refer Documentation/loongarch/irq- chip-model.rst. LoongArch CPUINTC has 13 interrupt sources: SWI0~1, HWI0~7, IPI, TI (Timer) and PCOV (PMC). IRQ mappings of HWI0~7 are configurable (can be created from DT/ACPI), but IPI, TI (Timer) and PCOV (PMC) are hardcoded bits, so we expose the fwnode_handle to map them, and get mapped irq by irq_create_mapping when using them. Co-developed-by: Jianmin Lv Signed-off-by: Jianmin Lv Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1658314292-35346-13-git-send-email-lvjianmin@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 7 +- arch/loongarch/kernel/irq.c | 16 +++- arch/loongarch/kernel/time.c | 14 +++- drivers/irqchip/Kconfig | 10 +++ drivers/irqchip/Makefile | 1 + drivers/irqchip/irq-loongarch-cpu.c | 111 ++++++++++++++++++++++++++++ 6 files changed, 149 insertions(+), 10 deletions(-) create mode 100644 drivers/irqchip/irq-loongarch-cpu.c diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 2308c51973bd..389a4c7aa92a 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -35,9 +35,6 @@ static inline bool on_irq_stack(int cpu, unsigned long sp) return (low <= sp && sp <= high); } -int get_ipi_irq(void); -int get_pmc_irq(void); -int get_timer_irq(void); void spurious_interrupt(void); #define NR_IRQS_LEGACY 16 @@ -94,8 +91,6 @@ struct acpi_madt_bio_pic; struct acpi_madt_msi_pic; struct acpi_madt_lpc_pic; -struct irq_domain *loongarch_cpu_irq_init(void); - int liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc); int eiointc_acpi_init(struct irq_domain *parent, @@ -128,7 +123,7 @@ extern struct acpi_madt_lpc_pic *acpi_pchlpc; extern struct acpi_madt_msi_pic *acpi_pchmsi[MAX_IO_PICS]; extern struct acpi_madt_bio_pic *acpi_pchpic[MAX_IO_PICS]; -extern struct irq_domain *cpu_domain; +extern struct fwnode_handle *cpuintc_handle; extern struct fwnode_handle *liointc_handle; extern struct fwnode_handle *pch_lpc_handle; extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index da131f51225a..1ba19c76563e 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -25,8 +25,6 @@ DEFINE_PER_CPU(unsigned long, irq_stack); DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); -struct irq_domain *cpu_domain; - struct acpi_vector_group pch_group[MAX_IO_PICS]; struct acpi_vector_group msi_group[MAX_IO_PICS]; /* @@ -89,6 +87,16 @@ static void __init init_vec_parent_group(void) acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse); } +static int __init get_ipi_irq(void) +{ + struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); + + if (d) + return irq_create_mapping(d, EXCCODE_IPI - EXCCODE_INT_START); + + return -EINVAL; +} + void __init init_IRQ(void) { int i; @@ -105,7 +113,9 @@ void __init init_IRQ(void) init_vec_parent_group(); irqchip_init(); #ifdef CONFIG_SMP - ipi_irq = EXCCODE_IPI - EXCCODE_INT_START; + ipi_irq = get_ipi_irq(); + if (ipi_irq < 0) + panic("IPI IRQ mapping failed\n"); irq_set_percpu_devid(ipi_irq); r = request_percpu_irq(ipi_irq, loongson3_ipi_interrupt, "IPI", &ipi_dummy_dev); if (r < 0) diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index fe6823875895..79dc5eddf504 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -123,6 +123,16 @@ void sync_counter(void) csr_write64(-init_timeval, LOONGARCH_CSR_CNTC); } +static int get_timer_irq(void) +{ + struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); + + if (d) + return irq_create_mapping(d, EXCCODE_TIMER - EXCCODE_INT_START); + + return -EINVAL; +} + int constant_clockevent_init(void) { unsigned int irq; @@ -132,7 +142,9 @@ int constant_clockevent_init(void) struct clock_event_device *cd; static int timer_irq_installed = 0; - irq = EXCCODE_TIMER - EXCCODE_INT_START; + irq = get_timer_irq(); + if (irq < 0) + pr_err("Failed to map irq %d (timer)\n", irq); cd = &per_cpu(constant_clockevent_device, cpu); diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 271996254dc6..02002d436ba7 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -571,6 +571,16 @@ config EXYNOS_IRQ_COMBINER Say yes here to add support for the IRQ combiner devices embedded in Samsung Exynos chips. +config IRQ_LOONGARCH_CPU + bool + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN + select GENERIC_IRQ_EFFECTIVE_AFF_MASK + help + Support for the LoongArch CPU Interrupt Controller. For details of + irq chip hierarchy on LoongArch platforms please read the document + Documentation/loongarch/irq-chip-model.rst. + config LOONGSON_LIOINTC bool "Loongson Local I/O Interrupt Controller" depends on MACH_LOONGSON64 diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 973ea2f98daf..769a2f84d93e 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -113,6 +113,7 @@ obj-$(CONFIG_LS1X_IRQ) += irq-ls1x.o obj-$(CONFIG_TI_SCI_INTR_IRQCHIP) += irq-ti-sci-intr.o obj-$(CONFIG_TI_SCI_INTA_IRQCHIP) += irq-ti-sci-inta.o obj-$(CONFIG_TI_PRUSS_INTC) += irq-pruss-intc.o +obj-$(CONFIG_IRQ_LOONGARCH_CPU) += irq-loongarch-cpu.o obj-$(CONFIG_LOONGSON_LIOINTC) += irq-loongson-liointc.o obj-$(CONFIG_LOONGSON_EIOINTC) += irq-loongson-eiointc.o obj-$(CONFIG_LOONGSON_HTPIC) += irq-loongson-htpic.o diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c new file mode 100644 index 000000000000..aed345410d09 --- /dev/null +++ b/drivers/irqchip/irq-loongarch-cpu.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +static struct irq_domain *irq_domain; +struct fwnode_handle *cpuintc_handle; + +static void mask_loongarch_irq(struct irq_data *d) +{ + clear_csr_ecfg(ECFGF(d->hwirq)); +} + +static void unmask_loongarch_irq(struct irq_data *d) +{ + set_csr_ecfg(ECFGF(d->hwirq)); +} + +static struct irq_chip cpu_irq_controller = { + .name = "CPUINTC", + .irq_mask = mask_loongarch_irq, + .irq_unmask = unmask_loongarch_irq, +}; + +static void handle_cpu_irq(struct pt_regs *regs) +{ + int hwirq; + unsigned int estat = read_csr_estat() & CSR_ESTAT_IS; + + while ((hwirq = ffs(estat))) { + estat &= ~BIT(hwirq - 1); + handle_domain_irq(irq_domain, hwirq - 1, regs); + } +} + +static int loongarch_cpu_intc_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_noprobe(irq); + irq_set_chip_and_handler(irq, &cpu_irq_controller, handle_percpu_irq); + + return 0; +} + +static const struct irq_domain_ops loongarch_cpu_intc_irq_domain_ops = { + .map = loongarch_cpu_intc_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int __init +liointc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_lio_pic *liointc_entry = (struct acpi_madt_lio_pic *)header; + + return liointc_acpi_init(irq_domain, liointc_entry); +} + +static int __init +eiointc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_eio_pic *eiointc_entry = (struct acpi_madt_eio_pic *)header; + + return eiointc_acpi_init(irq_domain, eiointc_entry); +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_LIO_PIC, + liointc_parse_madt, 0); + acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, + eiointc_parse_madt, 0); + return 0; +} + +static int __init cpuintc_acpi_init(union acpi_subtable_headers *header, + const unsigned long end) +{ + if (irq_domain) + return 0; + + /* Mask interrupts. */ + clear_csr_ecfg(ECFG0_IM); + clear_csr_estat(ESTATF_IP); + + cpuintc_handle = irq_domain_alloc_fwnode(NULL); + irq_domain = irq_domain_create_linear(cpuintc_handle, EXCCODE_INT_NUM, + &loongarch_cpu_intc_irq_domain_ops, NULL); + + if (!irq_domain) + panic("Failed to add irqdomain for LoongArch CPU"); + + set_handle_irq(&handle_cpu_irq); + acpi_cascade_irqdomain_init(); + + return 0; +} + +IRQCHIP_ACPI_DECLARE(cpuintc_v1, ACPI_MADT_TYPE_CORE_PIC, + NULL, ACPI_MADT_CORE_PIC_VERSION_V1, cpuintc_acpi_init); -- Gitee From 4050ae738f4c7fc6c73520009db2d020d8a67d07 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:16 +0800 Subject: [PATCH 08/23] LoongArch: Use ABI names of registers where appropriate ANBZ: #5200 commit d8e7f201a4cf148c3801cdc9603963061d28d64f upstream. Some of the assembly in the LoongArch port seem to come from a prehistoric time, when the assembler didn't even have support for the ABI names we all come to know and love, thus used raw register numbers which hampered readability. The usages are found with a regex match inside arch/loongarch, then manually adjusted for those non-definitions. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/barrier.h | 4 +- arch/loongarch/include/asm/loongson.h | 4 +- arch/loongarch/include/asm/stacktrace.h | 12 ++-- arch/loongarch/include/asm/thread_info.h | 4 +- arch/loongarch/include/asm/uaccess.h | 2 +- arch/loongarch/mm/page.S | 4 +- arch/loongarch/mm/tlbex.S | 80 ++++++++++++------------ 7 files changed, 55 insertions(+), 55 deletions(-) diff --git a/arch/loongarch/include/asm/barrier.h b/arch/loongarch/include/asm/barrier.h index b6517eeeb141..cda977675854 100644 --- a/arch/loongarch/include/asm/barrier.h +++ b/arch/loongarch/include/asm/barrier.h @@ -48,9 +48,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, __asm__ __volatile__( "sltu %0, %1, %2\n\t" #if (__SIZEOF_LONG__ == 4) - "sub.w %0, $r0, %0\n\t" + "sub.w %0, $zero, %0\n\t" #elif (__SIZEOF_LONG__ == 8) - "sub.d %0, $r0, %0\n\t" + "sub.d %0, $zero, %0\n\t" #endif : "=r" (mask) : "r" (index), "r" (size) diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h index 6a8038725ba7..8522afafc24e 100644 --- a/arch/loongarch/include/asm/loongson.h +++ b/arch/loongarch/include/asm/loongson.h @@ -58,7 +58,7 @@ static inline void xconf_writel(u32 val, volatile void __iomem *addr) { asm volatile ( " st.w %[v], %[hw], 0 \n" - " ld.b $r0, %[hw], 0 \n" + " ld.b $zero, %[hw], 0 \n" : : [hw] "r" (addr), [v] "r" (val) ); @@ -68,7 +68,7 @@ static inline void xconf_writeq(u64 val64, volatile void __iomem *addr) { asm volatile ( " st.d %[v], %[hw], 0 \n" - " ld.b $r0, %[hw], 0 \n" + " ld.b $zero, %[hw], 0 \n" : : [hw] "r" (addr), [v] "r" (val64) ); diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h index 26483e396ad1..6b5c2a7aa706 100644 --- a/arch/loongarch/include/asm/stacktrace.h +++ b/arch/loongarch/include/asm/stacktrace.h @@ -23,13 +23,13 @@ static __always_inline void prepare_frametrace(struct pt_regs *regs) { __asm__ __volatile__( - /* Save $r1 */ + /* Save $ra */ STORE_ONE_REG(1) - /* Use $r1 to save PC */ - "pcaddi $r1, 0\n\t" - STR_LONG_S " $r1, %0\n\t" - /* Restore $r1 */ - STR_LONG_L " $r1, %1, "STR_LONGSIZE"\n\t" + /* Use $ra to save PC */ + "pcaddi $ra, 0\n\t" + STR_LONG_S " $ra, %0\n\t" + /* Restore $ra */ + STR_LONG_L " $ra, %1, "STR_LONGSIZE"\n\t" STORE_ONE_REG(2) STORE_ONE_REG(3) STORE_ONE_REG(4) diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index a548b456ab4e..1be904ab3792 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -44,14 +44,14 @@ struct thread_info { } /* How to get the thread information struct from C. */ -register struct thread_info *__current_thread_info __asm__("$r2"); +register struct thread_info *__current_thread_info __asm__("$tp"); static inline struct thread_info *current_thread_info(void) { return __current_thread_info; } -register unsigned long current_stack_pointer __asm__("$r3"); +register unsigned long current_stack_pointer __asm__("$sp"); #endif /* !__ASSEMBLY__ */ diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 9e58c8aa0be5..f4ba308338f1 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -204,7 +204,7 @@ do { \ "2: \n" \ " .section .fixup,\"ax\" \n" \ "3: li.w %0, %3 \n" \ - " or %1, $r0, $r0 \n" \ + " or %1, $zero, $zero \n" \ " b 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S index ddc78ab33c7b..270d509adbaa 100644 --- a/arch/loongarch/mm/page.S +++ b/arch/loongarch/mm/page.S @@ -32,7 +32,7 @@ SYM_FUNC_START(clear_page) st.d zero, a0, -8 bne t0, a0, 1b - jirl $r0, ra, 0 + jirl zero, ra, 0 SYM_FUNC_END(clear_page) EXPORT_SYMBOL(clear_page) @@ -79,6 +79,6 @@ SYM_FUNC_START(copy_page) st.d t7, a0, -8 bne t8, a0, 1b - jirl $r0, ra, 0 + jirl zero, ra, 0 SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index e36c2c07dee3..a6cfad6f3c75 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -47,7 +47,7 @@ SYM_FUNC_START(handle_tlb_load) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_load + blt t0, zero, vmalloc_load csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_load: @@ -80,7 +80,7 @@ vmalloc_done_load: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_load + bne t0, zero, tlb_huge_update_load csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -100,12 +100,12 @@ smp_pgtable_change_load: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_load + beq ra, zero, nopage_tlb_load ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_load + beq t0, zero, smp_pgtable_change_load #else st.d t0, t1, 0 #endif @@ -139,23 +139,23 @@ tlb_huge_update_load: #endif srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_load + beq ra, zero, nopage_tlb_load tlbsrch ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_load + beq t0, zero, tlb_huge_update_load ld.d t0, t1, 0 #else st.d t0, t1, 0 #endif - addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16) + addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) addi.d ra, t1, 0 csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr - csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX + csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the @@ -178,27 +178,27 @@ tlb_huge_update_load: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbfill - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_load: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_0 - jirl $r0, t0, 0 + jirl zero, t0, 0 SYM_FUNC_END(handle_tlb_load) SYM_FUNC_START(handle_tlb_store) @@ -210,7 +210,7 @@ SYM_FUNC_START(handle_tlb_store) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_store + blt t0, zero, vmalloc_store csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_store: @@ -244,7 +244,7 @@ vmalloc_done_store: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_store + bne t0, zero, tlb_huge_update_store csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -265,12 +265,12 @@ smp_pgtable_change_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, $r0, nopage_tlb_store + bne ra, zero, nopage_tlb_store ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_store + beq t0, zero, smp_pgtable_change_store #else st.d t0, t1, 0 #endif @@ -306,24 +306,24 @@ tlb_huge_update_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, $r0, nopage_tlb_store + bne ra, zero, nopage_tlb_store tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_store + beq t0, zero, tlb_huge_update_store ld.d t0, t1, 0 #else st.d t0, t1, 0 #endif - addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16) + addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) addi.d ra, t1, 0 csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr - csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX + csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -345,28 +345,28 @@ tlb_huge_update_store: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbfill /* Reset default page size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_store: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl $r0, t0, 0 + jirl zero, t0, 0 SYM_FUNC_END(handle_tlb_store) SYM_FUNC_START(handle_tlb_modify) @@ -378,7 +378,7 @@ SYM_FUNC_START(handle_tlb_modify) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, $r0, vmalloc_modify + blt t0, zero, vmalloc_modify csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_modify: @@ -411,7 +411,7 @@ vmalloc_done_modify: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, $r0, tlb_huge_update_modify + bne t0, zero, tlb_huge_update_modify csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -431,12 +431,12 @@ smp_pgtable_change_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_modify + beq ra, zero, nopage_tlb_modify ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, smp_pgtable_change_modify + beq t0, zero, smp_pgtable_change_modify #else st.d t0, t1, 0 #endif @@ -471,14 +471,14 @@ tlb_huge_update_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, $r0, nopage_tlb_modify + beq ra, zero, nopage_tlb_modify tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, $r0, tlb_huge_update_modify + beq t0, zero, tlb_huge_update_modify ld.d t0, t1, 0 #else st.d t0, t1, 0 @@ -504,28 +504,28 @@ tlb_huge_update_modify: addi.d t0, ra, 0 /* Convert to entrylo1 */ - addi.d t1, $r0, 1 + addi.d t1, zero, 1 slli.d t1, t1, (HPAGE_SHIFT - 1) add.d t0, t0, t1 csrwr t0, LOONGARCH_CSR_TLBELO1 /* Set huge page tlb entry size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbwr /* Reset default page size */ - addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16) - addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) + addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) + addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_modify: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl $r0, t0, 0 + jirl zero, t0, 0 SYM_FUNC_END(handle_tlb_modify) SYM_FUNC_START(handle_tlb_refill) -- Gitee From 06d5d42ede3361498ac0159702d480f8d2465e7b Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:17 +0800 Subject: [PATCH 09/23] LoongArch: Use the "jr" pseudo-instruction where applicable ANBZ: #5200 commit 07b480695d24d1c9f27bb60fd4b980ae87e8bc1e upstream. Some of the assembly code in the LoongArch port likely originated from a time when the assembler did not support pseudo-instructions like "move" or "jr", so the desugared form was used and readability suffers (to a minor degree) as a result. As the upstream toolchain supports these pseudo-instructions from the beginning, migrate the existing few usages to them for better readability. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/fpu.S | 12 ++++++------ arch/loongarch/kernel/genex.S | 4 ++-- arch/loongarch/kernel/head.S | 4 ++-- arch/loongarch/mm/page.S | 4 ++-- arch/loongarch/mm/tlbex.S | 6 +++--- 5 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index a631a7137667..e14f096d40bd 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -153,7 +153,7 @@ SYM_FUNC_START(_save_fp) fpu_save_csr a0 t1 fpu_save_double a0 t1 # clobbers t1 fpu_save_cc a0 t1 t2 # clobbers t1, t2 - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_save_fp) EXPORT_SYMBOL(_save_fp) @@ -164,7 +164,7 @@ SYM_FUNC_START(_restore_fp) fpu_restore_double a0 t1 # clobbers t1 fpu_restore_csr a0 t1 fpu_restore_cc a0 t1 t2 # clobbers t1, t2 - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_restore_fp) /* @@ -216,7 +216,7 @@ SYM_FUNC_START(_init_fpu) movgr2fr.d $f30, t1 movgr2fr.d $f31, t1 - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_init_fpu) /* @@ -229,7 +229,7 @@ SYM_FUNC_START(_save_fp_context) sc_save_fcsr a2 t1 sc_save_fp a0 li.w a0, 0 # success - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_save_fp_context) /* @@ -242,10 +242,10 @@ SYM_FUNC_START(_restore_fp_context) sc_restore_fcc a1 t1 t2 sc_restore_fcsr a2 t1 li.w a0, 0 # success - jirl zero, ra, 0 + jr ra SYM_FUNC_END(_restore_fp_context) SYM_FUNC_START(fault) li.w a0, -EFAULT # failure - jirl zero, ra, 0 + jr ra SYM_FUNC_END(fault) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 93496852b3cc..0df6d17dde23 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -28,7 +28,7 @@ SYM_FUNC_START(__arch_cpu_idle) nop idle 0 /* end of rollback region */ -1: jirl zero, ra, 0 +1: jr ra SYM_FUNC_END(__arch_cpu_idle) SYM_FUNC_START(handle_vint) @@ -91,5 +91,5 @@ SYM_FUNC_END(except_vec_cex) SYM_FUNC_START(handle_sys) la.abs t0, handle_syscall - jirl zero, t0, 0 + jr t0 SYM_FUNC_END(handle_sys) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index d01e62dd414f..e553c5fc17da 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -32,7 +32,7 @@ SYM_CODE_START(kernel_entry) # kernel entry point /* We might not get launched at the address the kernel is linked to, so we jump there. */ la.abs t0, 0f - jirl zero, t0, 0 + jr t0 0: la t0, __bss_start # clear .bss st.d zero, t0, 0 @@ -86,7 +86,7 @@ SYM_CODE_START(smpboot_entry) ld.d tp, t0, CPU_BOOT_TINFO la.abs t0, 0f - jirl zero, t0, 0 + jr t0 0: bl start_secondary SYM_CODE_END(smpboot_entry) diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S index 270d509adbaa..1e20dd5e3a4b 100644 --- a/arch/loongarch/mm/page.S +++ b/arch/loongarch/mm/page.S @@ -32,7 +32,7 @@ SYM_FUNC_START(clear_page) st.d zero, a0, -8 bne t0, a0, 1b - jirl zero, ra, 0 + jr ra SYM_FUNC_END(clear_page) EXPORT_SYMBOL(clear_page) @@ -79,6 +79,6 @@ SYM_FUNC_START(copy_page) st.d t7, a0, -8 bne t8, a0, 1b - jirl zero, ra, 0 + jr ra SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index a6cfad6f3c75..72692ebbca07 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -198,7 +198,7 @@ nopage_tlb_load: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_0 - jirl zero, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_load) SYM_FUNC_START(handle_tlb_store) @@ -366,7 +366,7 @@ nopage_tlb_store: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl zero, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_store) SYM_FUNC_START(handle_tlb_modify) @@ -525,7 +525,7 @@ nopage_tlb_modify: dbar 0 csrrd ra, EXCEPTION_KS2 la.abs t0, tlb_do_page_fault_1 - jirl zero, t0, 0 + jr t0 SYM_FUNC_END(handle_tlb_modify) SYM_FUNC_START(handle_tlb_refill) -- Gitee From 6152394eabdd28bf78c52232c000a0f0673d9e5b Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:18 +0800 Subject: [PATCH 10/23] LoongArch: Use the "move" pseudo-instruction where applicable ANBZ: #5200 commit 57ce5d3eefacfaadfe2ed0a3a85713d1ae6287b9 upstream. Some of the assembly code in the LoongArch port likely originated from a time when the assembler did not support pseudo-instructions like "move" or "jr", so the desugared form was used and readability suffers (to a minor degree) as a result. As the upstream toolchain supports these pseudo-instructions from the beginning, migrate the existing few usages to them for better readability. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/atomic.h | 8 ++++---- arch/loongarch/include/asm/cmpxchg.h | 2 +- arch/loongarch/include/asm/futex.h | 2 +- arch/loongarch/include/asm/uaccess.h | 2 +- arch/loongarch/kernel/head.S | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 1b68bf237776..1e205bafca16 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -159,7 +159,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) __asm__ __volatile__( "1: ll.w %1, %2 # atomic_sub_if_positive\n" " addi.w %0, %1, %3 \n" - " or %1, %0, $zero \n" + " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.w %1, %2 \n" " beq $zero, %1, 1b \n" @@ -172,7 +172,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) __asm__ __volatile__( "1: ll.w %1, %2 # atomic_sub_if_positive\n" " sub.w %0, %1, %3 \n" - " or %1, %0, $zero \n" + " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.w %1, %2 \n" " beq $zero, %1, 1b \n" @@ -322,7 +322,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) __asm__ __volatile__( "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " addi.d %0, %1, %3 \n" - " or %1, %0, $zero \n" + " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.d %1, %2 \n" " beq %1, $zero, 1b \n" @@ -335,7 +335,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) __asm__ __volatile__( "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " sub.d %0, %1, %3 \n" - " or %1, %0, $zero \n" + " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.d %1, %2 \n" " beq %1, $zero, 1b \n" diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 75b3a4478652..9e9939196471 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -55,7 +55,7 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, __asm__ __volatile__( \ "1: " ld " %0, %2 # __cmpxchg_asm \n" \ " bne %0, %z3, 2f \n" \ - " or $t0, %z4, $zero \n" \ + " move $t0, %z4 \n" \ " " st " $t0, %1 \n" \ " beq $zero, $t0, 1b \n" \ "2: \n" \ diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h index 9de8231694ec..170ec9f97e58 100644 --- a/arch/loongarch/include/asm/futex.h +++ b/arch/loongarch/include/asm/futex.h @@ -82,7 +82,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv "# futex_atomic_cmpxchg_inatomic \n" "1: ll.w %1, %3 \n" " bne %1, %z4, 3f \n" - " or $t0, %z5, $zero \n" + " move $t0, %z5 \n" "2: sc.w $t0, %2 \n" " beq $zero, $t0, 1b \n" "3: \n" diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index f4ba308338f1..2c6bfecb17d4 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -204,7 +204,7 @@ do { \ "2: \n" \ " .section .fixup,\"ax\" \n" \ "3: li.w %0, %3 \n" \ - " or %1, $zero, $zero \n" \ + " move %1, $zero \n" \ " b 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index e553c5fc17da..fd6a62f17161 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -50,7 +50,7 @@ SYM_CODE_START(kernel_entry) # kernel entry point /* KSave3 used for percpu base, initialized as 0 */ csrwr zero, PERCPU_BASE_KS /* GPR21 used for percpu base (runtime), initialized as 0 */ - or u0, zero, zero + move u0, zero la tp, init_thread_union /* Set the SP after an empty pt_regs. */ -- Gitee From 16b13f97a47e39bcf420d5ce0070d7555e144bce Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:19 +0800 Subject: [PATCH 11/23] LoongArch: Simplify "BEQ/BNE foo, zero" with BEQZ/BNEZ ANBZ: #5200 commit d47b2dc87c58154052daf8ac0f9229db5c7890cc upstream. While B{EQ,NE}Z and B{EQ,NE} are different instructions, and the vastly expanded range for branch destination does not really matter in the few cases touched, use the B{EQ,NE}Z where possible for shorter lines and better consistency (e.g. some places used "BEQ foo, zero", while some used "BEQ zero, foo"). Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/atomic.h | 8 ++++---- arch/loongarch/include/asm/cmpxchg.h | 2 +- arch/loongarch/include/asm/futex.h | 4 ++-- arch/loongarch/mm/tlbex.S | 30 ++++++++++++++-------------- 4 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 1e205bafca16..a408e8890bbe 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -162,7 +162,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.w %1, %2 \n" - " beq $zero, %1, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB : "=&r" (result), "=&r" (temp), @@ -175,7 +175,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.w %1, %2 \n" - " beq $zero, %1, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB : "=&r" (result), "=&r" (temp), @@ -325,7 +325,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.d %1, %2 \n" - " beq %1, $zero, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB : "=&r" (result), "=&r" (temp), @@ -338,7 +338,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) " move %1, %0 \n" " blt %0, $zero, 2f \n" " sc.d %1, %2 \n" - " beq %1, $zero, 1b \n" + " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB : "=&r" (result), "=&r" (temp), diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 9e9939196471..0a9b0fac1eee 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -57,7 +57,7 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, " bne %0, %z3, 2f \n" \ " move $t0, %z4 \n" \ " " st " $t0, %1 \n" \ - " beq $zero, $t0, 1b \n" \ + " beqz $t0, 1b \n" \ "2: \n" \ __WEAK_LLSC_MB \ : "=&r" (__ret), "=ZB"(*m) \ diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h index 170ec9f97e58..837659335fb1 100644 --- a/arch/loongarch/include/asm/futex.h +++ b/arch/loongarch/include/asm/futex.h @@ -17,7 +17,7 @@ "1: ll.w %1, %4 # __futex_atomic_op\n" \ " " insn " \n" \ "2: sc.w $t0, %2 \n" \ - " beq $t0, $zero, 1b \n" \ + " beqz $t0, 1b \n" \ "3: \n" \ " .section .fixup,\"ax\" \n" \ "4: li.w %0, %6 \n" \ @@ -84,7 +84,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv " bne %1, %z4, 3f \n" " move $t0, %z5 \n" "2: sc.w $t0, %2 \n" - " beq $zero, $t0, 1b \n" + " beqz $t0, 1b \n" "3: \n" __WEAK_LLSC_MB " .section .fixup,\"ax\" \n" diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 72692ebbca07..f200ed1a9698 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -80,7 +80,7 @@ vmalloc_done_load: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, zero, tlb_huge_update_load + bnez t0, tlb_huge_update_load csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -100,12 +100,12 @@ smp_pgtable_change_load: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, zero, nopage_tlb_load + beqz ra, nopage_tlb_load ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, smp_pgtable_change_load + beqz t0, smp_pgtable_change_load #else st.d t0, t1, 0 #endif @@ -139,13 +139,13 @@ tlb_huge_update_load: #endif srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, 1 - beq ra, zero, nopage_tlb_load + beqz ra, nopage_tlb_load tlbsrch ori t0, t0, _PAGE_VALID #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, tlb_huge_update_load + beqz t0, tlb_huge_update_load ld.d t0, t1, 0 #else st.d t0, t1, 0 @@ -244,7 +244,7 @@ vmalloc_done_store: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, zero, tlb_huge_update_store + bnez t0, tlb_huge_update_store csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -265,12 +265,12 @@ smp_pgtable_change_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, zero, nopage_tlb_store + bnez ra, nopage_tlb_store ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, smp_pgtable_change_store + beqz t0, smp_pgtable_change_store #else st.d t0, t1, 0 #endif @@ -306,14 +306,14 @@ tlb_huge_update_store: srli.d ra, t0, _PAGE_PRESENT_SHIFT andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT) - bne ra, zero, nopage_tlb_store + bnez ra, nopage_tlb_store tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, tlb_huge_update_store + beqz t0, tlb_huge_update_store ld.d t0, t1, 0 #else st.d t0, t1, 0 @@ -411,7 +411,7 @@ vmalloc_done_modify: * see if we need to jump to huge tlb processing. */ andi t0, ra, _PAGE_HUGE - bne t0, zero, tlb_huge_update_modify + bnez t0, tlb_huge_update_modify csrrd t0, LOONGARCH_CSR_BADV srli.d t0, t0, PAGE_SHIFT @@ -431,12 +431,12 @@ smp_pgtable_change_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, zero, nopage_tlb_modify + beqz ra, nopage_tlb_modify ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, smp_pgtable_change_modify + beqz t0, smp_pgtable_change_modify #else st.d t0, t1, 0 #endif @@ -471,14 +471,14 @@ tlb_huge_update_modify: srli.d ra, t0, _PAGE_WRITE_SHIFT andi ra, ra, 1 - beq ra, zero, nopage_tlb_modify + beqz ra, nopage_tlb_modify tlbsrch ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #ifdef CONFIG_SMP sc.d t0, t1, 0 - beq t0, zero, tlb_huge_update_modify + beqz t0, tlb_huge_update_modify ld.d t0, t1, 0 #else st.d t0, t1, 0 -- Gitee From a6c5f413367864b52b36a3f1cc1ab0e5238eda8b Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:20 +0800 Subject: [PATCH 12/23] LoongArch: Simplify "BLT foo, zero" with BLTZ ANBZ: #5200 commit d1bc75d7595b237f78b594509ea7cc159f98cae9 upstream. Support for the syntactic sugar is present in upstream binutils port from the beginning. Use it for shorter lines and better consistency. Generated code should be identical. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/atomic.h | 8 ++++---- arch/loongarch/mm/tlbex.S | 6 +++--- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index a408e8890bbe..12d6a9944467 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -160,7 +160,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) "1: ll.w %1, %2 # atomic_sub_if_positive\n" " addi.w %0, %1, %3 \n" " move %1, %0 \n" - " blt %0, $zero, 2f \n" + " bltz %0, 2f \n" " sc.w %1, %2 \n" " beqz %1, 1b \n" "2: \n" @@ -173,7 +173,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) "1: ll.w %1, %2 # atomic_sub_if_positive\n" " sub.w %0, %1, %3 \n" " move %1, %0 \n" - " blt %0, $zero, 2f \n" + " bltz %0, 2f \n" " sc.w %1, %2 \n" " beqz %1, 1b \n" "2: \n" @@ -323,7 +323,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " addi.d %0, %1, %3 \n" " move %1, %0 \n" - " blt %0, $zero, 2f \n" + " bltz %0, 2f \n" " sc.d %1, %2 \n" " beqz %1, 1b \n" "2: \n" @@ -336,7 +336,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) "1: ll.d %1, %2 # atomic64_sub_if_positive \n" " sub.d %0, %1, %3 \n" " move %1, %0 \n" - " blt %0, $zero, 2f \n" + " bltz %0, 2f \n" " sc.d %1, %2 \n" " beqz %1, 1b \n" "2: \n" diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index f200ed1a9698..0d369d485332 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -47,7 +47,7 @@ SYM_FUNC_START(handle_tlb_load) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, zero, vmalloc_load + bltz t0, vmalloc_load csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_load: @@ -210,7 +210,7 @@ SYM_FUNC_START(handle_tlb_store) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, zero, vmalloc_store + bltz t0, vmalloc_store csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_store: @@ -378,7 +378,7 @@ SYM_FUNC_START(handle_tlb_modify) * The vmalloc handling is not in the hotpath. */ csrrd t0, LOONGARCH_CSR_BADV - blt t0, zero, vmalloc_modify + bltz t0, vmalloc_modify csrrd t1, LOONGARCH_CSR_PGDL vmalloc_done_modify: -- Gitee From 51a61ce330e64bddd34f634038d06c92f9eb508d Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:21 +0800 Subject: [PATCH 13/23] LoongArch: Simplify "BGT foo, zero" with BGTZ ANBZ: #5200 commit 1fdb9a92495a6b6996530d27781892796e22f08b upstream. Support for the syntactic sugar is present in upstream binutils port from the beginning. Use it for shorter lines and better consistency. Generated code should be identical. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/lib/clear_user.S | 2 +- arch/loongarch/lib/copy_user.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 25d9be5fbb19..16ba2b8dd68a 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -32,7 +32,7 @@ SYM_FUNC_START(__clear_user) 1: st.b zero, a0, 0 addi.d a0, a0, 1 addi.d a1, a1, -1 - bgt a1, zero, 1b + bgtz a1, 1b 2: move a0, a1 jr ra diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 9ae507f851b5..97d20327a69e 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -35,7 +35,7 @@ SYM_FUNC_START(__copy_user) addi.d a0, a0, 1 addi.d a1, a1, 1 addi.d a2, a2, -1 - bgt a2, zero, 1b + bgtz a2, 1b 3: move a0, a2 jr ra -- Gitee From 25c0e20fc64ea3247c841e6ce663b2c777f57791 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:22 +0800 Subject: [PATCH 14/23] LoongArch: Re-tab the assembly files ANBZ: #5200 commit f5c3c22f21b6a002e371afdcc9180a2fa47dc267 upstream. Reflow the *.S files for better stylistic consistency, namely hard tabs after mnemonic position, and vertical alignment of the first operand with hard tabs. Tab width is obviously 8. Some pre-existing intra-block vertical alignments are preserved. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/kernel/entry.S | 4 +- arch/loongarch/kernel/fpu.S | 170 ++++++++++++++++----------------- arch/loongarch/kernel/genex.S | 8 +- arch/loongarch/kernel/head.S | 4 +- arch/loongarch/kernel/switch.S | 4 +- arch/loongarch/mm/page.S | 118 +++++++++++------------ arch/loongarch/mm/tlbex.S | 18 ++-- 7 files changed, 163 insertions(+), 163 deletions(-) diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index d5b3dbcf5425..d53b631c9022 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -27,7 +27,7 @@ SYM_FUNC_START(handle_syscall) addi.d sp, sp, -PT_SIZE cfi_st t2, PT_R3 - cfi_rel_offset sp, PT_R3 + cfi_rel_offset sp, PT_R3 st.d zero, sp, PT_R0 csrrd t2, LOONGARCH_CSR_PRMD st.d t2, sp, PT_PRMD @@ -50,7 +50,7 @@ SYM_FUNC_START(handle_syscall) cfi_st a7, PT_R11 csrrd ra, LOONGARCH_CSR_ERA st.d ra, sp, PT_ERA - cfi_rel_offset ra, PT_ERA + cfi_rel_offset ra, PT_ERA cfi_st tp, PT_R2 cfi_st u0, PT_R21 diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index e14f096d40bd..576b3370a296 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -27,78 +27,78 @@ .endm .macro sc_save_fp base - EX fst.d $f0, \base, (0 * FPU_REG_WIDTH) - EX fst.d $f1, \base, (1 * FPU_REG_WIDTH) - EX fst.d $f2, \base, (2 * FPU_REG_WIDTH) - EX fst.d $f3, \base, (3 * FPU_REG_WIDTH) - EX fst.d $f4, \base, (4 * FPU_REG_WIDTH) - EX fst.d $f5, \base, (5 * FPU_REG_WIDTH) - EX fst.d $f6, \base, (6 * FPU_REG_WIDTH) - EX fst.d $f7, \base, (7 * FPU_REG_WIDTH) - EX fst.d $f8, \base, (8 * FPU_REG_WIDTH) - EX fst.d $f9, \base, (9 * FPU_REG_WIDTH) - EX fst.d $f10, \base, (10 * FPU_REG_WIDTH) - EX fst.d $f11, \base, (11 * FPU_REG_WIDTH) - EX fst.d $f12, \base, (12 * FPU_REG_WIDTH) - EX fst.d $f13, \base, (13 * FPU_REG_WIDTH) - EX fst.d $f14, \base, (14 * FPU_REG_WIDTH) - EX fst.d $f15, \base, (15 * FPU_REG_WIDTH) - EX fst.d $f16, \base, (16 * FPU_REG_WIDTH) - EX fst.d $f17, \base, (17 * FPU_REG_WIDTH) - EX fst.d $f18, \base, (18 * FPU_REG_WIDTH) - EX fst.d $f19, \base, (19 * FPU_REG_WIDTH) - EX fst.d $f20, \base, (20 * FPU_REG_WIDTH) - EX fst.d $f21, \base, (21 * FPU_REG_WIDTH) - EX fst.d $f22, \base, (22 * FPU_REG_WIDTH) - EX fst.d $f23, \base, (23 * FPU_REG_WIDTH) - EX fst.d $f24, \base, (24 * FPU_REG_WIDTH) - EX fst.d $f25, \base, (25 * FPU_REG_WIDTH) - EX fst.d $f26, \base, (26 * FPU_REG_WIDTH) - EX fst.d $f27, \base, (27 * FPU_REG_WIDTH) - EX fst.d $f28, \base, (28 * FPU_REG_WIDTH) - EX fst.d $f29, \base, (29 * FPU_REG_WIDTH) - EX fst.d $f30, \base, (30 * FPU_REG_WIDTH) - EX fst.d $f31, \base, (31 * FPU_REG_WIDTH) + EX fst.d $f0, \base, (0 * FPU_REG_WIDTH) + EX fst.d $f1, \base, (1 * FPU_REG_WIDTH) + EX fst.d $f2, \base, (2 * FPU_REG_WIDTH) + EX fst.d $f3, \base, (3 * FPU_REG_WIDTH) + EX fst.d $f4, \base, (4 * FPU_REG_WIDTH) + EX fst.d $f5, \base, (5 * FPU_REG_WIDTH) + EX fst.d $f6, \base, (6 * FPU_REG_WIDTH) + EX fst.d $f7, \base, (7 * FPU_REG_WIDTH) + EX fst.d $f8, \base, (8 * FPU_REG_WIDTH) + EX fst.d $f9, \base, (9 * FPU_REG_WIDTH) + EX fst.d $f10, \base, (10 * FPU_REG_WIDTH) + EX fst.d $f11, \base, (11 * FPU_REG_WIDTH) + EX fst.d $f12, \base, (12 * FPU_REG_WIDTH) + EX fst.d $f13, \base, (13 * FPU_REG_WIDTH) + EX fst.d $f14, \base, (14 * FPU_REG_WIDTH) + EX fst.d $f15, \base, (15 * FPU_REG_WIDTH) + EX fst.d $f16, \base, (16 * FPU_REG_WIDTH) + EX fst.d $f17, \base, (17 * FPU_REG_WIDTH) + EX fst.d $f18, \base, (18 * FPU_REG_WIDTH) + EX fst.d $f19, \base, (19 * FPU_REG_WIDTH) + EX fst.d $f20, \base, (20 * FPU_REG_WIDTH) + EX fst.d $f21, \base, (21 * FPU_REG_WIDTH) + EX fst.d $f22, \base, (22 * FPU_REG_WIDTH) + EX fst.d $f23, \base, (23 * FPU_REG_WIDTH) + EX fst.d $f24, \base, (24 * FPU_REG_WIDTH) + EX fst.d $f25, \base, (25 * FPU_REG_WIDTH) + EX fst.d $f26, \base, (26 * FPU_REG_WIDTH) + EX fst.d $f27, \base, (27 * FPU_REG_WIDTH) + EX fst.d $f28, \base, (28 * FPU_REG_WIDTH) + EX fst.d $f29, \base, (29 * FPU_REG_WIDTH) + EX fst.d $f30, \base, (30 * FPU_REG_WIDTH) + EX fst.d $f31, \base, (31 * FPU_REG_WIDTH) .endm .macro sc_restore_fp base - EX fld.d $f0, \base, (0 * FPU_REG_WIDTH) - EX fld.d $f1, \base, (1 * FPU_REG_WIDTH) - EX fld.d $f2, \base, (2 * FPU_REG_WIDTH) - EX fld.d $f3, \base, (3 * FPU_REG_WIDTH) - EX fld.d $f4, \base, (4 * FPU_REG_WIDTH) - EX fld.d $f5, \base, (5 * FPU_REG_WIDTH) - EX fld.d $f6, \base, (6 * FPU_REG_WIDTH) - EX fld.d $f7, \base, (7 * FPU_REG_WIDTH) - EX fld.d $f8, \base, (8 * FPU_REG_WIDTH) - EX fld.d $f9, \base, (9 * FPU_REG_WIDTH) - EX fld.d $f10, \base, (10 * FPU_REG_WIDTH) - EX fld.d $f11, \base, (11 * FPU_REG_WIDTH) - EX fld.d $f12, \base, (12 * FPU_REG_WIDTH) - EX fld.d $f13, \base, (13 * FPU_REG_WIDTH) - EX fld.d $f14, \base, (14 * FPU_REG_WIDTH) - EX fld.d $f15, \base, (15 * FPU_REG_WIDTH) - EX fld.d $f16, \base, (16 * FPU_REG_WIDTH) - EX fld.d $f17, \base, (17 * FPU_REG_WIDTH) - EX fld.d $f18, \base, (18 * FPU_REG_WIDTH) - EX fld.d $f19, \base, (19 * FPU_REG_WIDTH) - EX fld.d $f20, \base, (20 * FPU_REG_WIDTH) - EX fld.d $f21, \base, (21 * FPU_REG_WIDTH) - EX fld.d $f22, \base, (22 * FPU_REG_WIDTH) - EX fld.d $f23, \base, (23 * FPU_REG_WIDTH) - EX fld.d $f24, \base, (24 * FPU_REG_WIDTH) - EX fld.d $f25, \base, (25 * FPU_REG_WIDTH) - EX fld.d $f26, \base, (26 * FPU_REG_WIDTH) - EX fld.d $f27, \base, (27 * FPU_REG_WIDTH) - EX fld.d $f28, \base, (28 * FPU_REG_WIDTH) - EX fld.d $f29, \base, (29 * FPU_REG_WIDTH) - EX fld.d $f30, \base, (30 * FPU_REG_WIDTH) - EX fld.d $f31, \base, (31 * FPU_REG_WIDTH) + EX fld.d $f0, \base, (0 * FPU_REG_WIDTH) + EX fld.d $f1, \base, (1 * FPU_REG_WIDTH) + EX fld.d $f2, \base, (2 * FPU_REG_WIDTH) + EX fld.d $f3, \base, (3 * FPU_REG_WIDTH) + EX fld.d $f4, \base, (4 * FPU_REG_WIDTH) + EX fld.d $f5, \base, (5 * FPU_REG_WIDTH) + EX fld.d $f6, \base, (6 * FPU_REG_WIDTH) + EX fld.d $f7, \base, (7 * FPU_REG_WIDTH) + EX fld.d $f8, \base, (8 * FPU_REG_WIDTH) + EX fld.d $f9, \base, (9 * FPU_REG_WIDTH) + EX fld.d $f10, \base, (10 * FPU_REG_WIDTH) + EX fld.d $f11, \base, (11 * FPU_REG_WIDTH) + EX fld.d $f12, \base, (12 * FPU_REG_WIDTH) + EX fld.d $f13, \base, (13 * FPU_REG_WIDTH) + EX fld.d $f14, \base, (14 * FPU_REG_WIDTH) + EX fld.d $f15, \base, (15 * FPU_REG_WIDTH) + EX fld.d $f16, \base, (16 * FPU_REG_WIDTH) + EX fld.d $f17, \base, (17 * FPU_REG_WIDTH) + EX fld.d $f18, \base, (18 * FPU_REG_WIDTH) + EX fld.d $f19, \base, (19 * FPU_REG_WIDTH) + EX fld.d $f20, \base, (20 * FPU_REG_WIDTH) + EX fld.d $f21, \base, (21 * FPU_REG_WIDTH) + EX fld.d $f22, \base, (22 * FPU_REG_WIDTH) + EX fld.d $f23, \base, (23 * FPU_REG_WIDTH) + EX fld.d $f24, \base, (24 * FPU_REG_WIDTH) + EX fld.d $f25, \base, (25 * FPU_REG_WIDTH) + EX fld.d $f26, \base, (26 * FPU_REG_WIDTH) + EX fld.d $f27, \base, (27 * FPU_REG_WIDTH) + EX fld.d $f28, \base, (28 * FPU_REG_WIDTH) + EX fld.d $f29, \base, (29 * FPU_REG_WIDTH) + EX fld.d $f30, \base, (30 * FPU_REG_WIDTH) + EX fld.d $f31, \base, (31 * FPU_REG_WIDTH) .endm .macro sc_save_fcc base, tmp0, tmp1 movcf2gr \tmp0, $fcc0 - move \tmp1, \tmp0 + move \tmp1, \tmp0 movcf2gr \tmp0, $fcc1 bstrins.d \tmp1, \tmp0, 15, 8 movcf2gr \tmp0, $fcc2 @@ -113,11 +113,11 @@ bstrins.d \tmp1, \tmp0, 55, 48 movcf2gr \tmp0, $fcc7 bstrins.d \tmp1, \tmp0, 63, 56 - EX st.d \tmp1, \base, 0 + EX st.d \tmp1, \base, 0 .endm .macro sc_restore_fcc base, tmp0, tmp1 - EX ld.d \tmp0, \base, 0 + EX ld.d \tmp0, \base, 0 bstrpick.d \tmp1, \tmp0, 7, 0 movgr2cf $fcc0, \tmp1 bstrpick.d \tmp1, \tmp0, 15, 8 @@ -138,11 +138,11 @@ .macro sc_save_fcsr base, tmp0 movfcsr2gr \tmp0, fcsr0 - EX st.w \tmp0, \base, 0 + EX st.w \tmp0, \base, 0 .endm .macro sc_restore_fcsr base, tmp0 - EX ld.w \tmp0, \base, 0 + EX ld.w \tmp0, \base, 0 movgr2fcsr fcsr0, \tmp0 .endm @@ -151,9 +151,9 @@ */ SYM_FUNC_START(_save_fp) fpu_save_csr a0 t1 - fpu_save_double a0 t1 # clobbers t1 + fpu_save_double a0 t1 # clobbers t1 fpu_save_cc a0 t1 t2 # clobbers t1, t2 - jr ra + jr ra SYM_FUNC_END(_save_fp) EXPORT_SYMBOL(_save_fp) @@ -161,10 +161,10 @@ EXPORT_SYMBOL(_save_fp) * Restore a thread's fp context. */ SYM_FUNC_START(_restore_fp) - fpu_restore_double a0 t1 # clobbers t1 - fpu_restore_csr a0 t1 - fpu_restore_cc a0 t1 t2 # clobbers t1, t2 - jr ra + fpu_restore_double a0 t1 # clobbers t1 + fpu_restore_csr a0 t1 + fpu_restore_cc a0 t1 t2 # clobbers t1, t2 + jr ra SYM_FUNC_END(_restore_fp) /* @@ -225,11 +225,11 @@ SYM_FUNC_END(_init_fpu) * a2: fcsr */ SYM_FUNC_START(_save_fp_context) - sc_save_fcc a1 t1 t2 - sc_save_fcsr a2 t1 - sc_save_fp a0 - li.w a0, 0 # success - jr ra + sc_save_fcc a1 t1 t2 + sc_save_fcsr a2 t1 + sc_save_fp a0 + li.w a0, 0 # success + jr ra SYM_FUNC_END(_save_fp_context) /* @@ -238,11 +238,11 @@ SYM_FUNC_END(_save_fp_context) * a2: fcsr */ SYM_FUNC_START(_restore_fp_context) - sc_restore_fp a0 - sc_restore_fcc a1 t1 t2 - sc_restore_fcsr a2 t1 - li.w a0, 0 # success - jr ra + sc_restore_fp a0 + sc_restore_fcc a1 t1 t2 + sc_restore_fcsr a2 t1 + li.w a0, 0 # success + jr ra SYM_FUNC_END(_restore_fp_context) SYM_FUNC_START(fault) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 0df6d17dde23..75e5be807a0d 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -35,16 +35,16 @@ SYM_FUNC_START(handle_vint) BACKUP_T0T1 SAVE_ALL la.abs t1, __arch_cpu_idle - LONG_L t0, sp, PT_ERA + LONG_L t0, sp, PT_ERA /* 32 byte rollback region */ ori t0, t0, 0x1f xori t0, t0, 0x1f bne t0, t1, 1f - LONG_S t0, sp, PT_ERA + LONG_S t0, sp, PT_ERA 1: move a0, sp move a1, sp la.abs t0, do_vint - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_vint) @@ -72,7 +72,7 @@ SYM_FUNC_END(except_vec_cex) build_prep_\prep move a0, sp la.abs t0, do_\handler - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_\exception) .endm diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index fd6a62f17161..7062cdf0e33e 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -85,8 +85,8 @@ SYM_CODE_START(smpboot_entry) ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO - la.abs t0, 0f - jr t0 + la.abs t0, 0f + jr t0 0: bl start_secondary SYM_CODE_END(smpboot_entry) diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 53e2fa8e580e..37e84ac8ffc2 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to) move tp, a2 cpu_restore_nonscratch a1 - li.w t0, _THREAD_SIZE - 32 - PTR_ADD t0, t0, tp + li.w t0, _THREAD_SIZE - 32 + PTR_ADD t0, t0, tp set_saved_sp t0, t1, t2 ldptr.d t1, a1, THREAD_CSRPRMD diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S index 1e20dd5e3a4b..4c874a7af0ad 100644 --- a/arch/loongarch/mm/page.S +++ b/arch/loongarch/mm/page.S @@ -10,75 +10,75 @@ .align 5 SYM_FUNC_START(clear_page) - lu12i.w t0, 1 << (PAGE_SHIFT - 12) - add.d t0, t0, a0 + lu12i.w t0, 1 << (PAGE_SHIFT - 12) + add.d t0, t0, a0 1: - st.d zero, a0, 0 - st.d zero, a0, 8 - st.d zero, a0, 16 - st.d zero, a0, 24 - st.d zero, a0, 32 - st.d zero, a0, 40 - st.d zero, a0, 48 - st.d zero, a0, 56 - addi.d a0, a0, 128 - st.d zero, a0, -64 - st.d zero, a0, -56 - st.d zero, a0, -48 - st.d zero, a0, -40 - st.d zero, a0, -32 - st.d zero, a0, -24 - st.d zero, a0, -16 - st.d zero, a0, -8 - bne t0, a0, 1b + st.d zero, a0, 0 + st.d zero, a0, 8 + st.d zero, a0, 16 + st.d zero, a0, 24 + st.d zero, a0, 32 + st.d zero, a0, 40 + st.d zero, a0, 48 + st.d zero, a0, 56 + addi.d a0, a0, 128 + st.d zero, a0, -64 + st.d zero, a0, -56 + st.d zero, a0, -48 + st.d zero, a0, -40 + st.d zero, a0, -32 + st.d zero, a0, -24 + st.d zero, a0, -16 + st.d zero, a0, -8 + bne t0, a0, 1b - jr ra + jr ra SYM_FUNC_END(clear_page) EXPORT_SYMBOL(clear_page) .align 5 SYM_FUNC_START(copy_page) - lu12i.w t8, 1 << (PAGE_SHIFT - 12) - add.d t8, t8, a0 + lu12i.w t8, 1 << (PAGE_SHIFT - 12) + add.d t8, t8, a0 1: - ld.d t0, a1, 0 - ld.d t1, a1, 8 - ld.d t2, a1, 16 - ld.d t3, a1, 24 - ld.d t4, a1, 32 - ld.d t5, a1, 40 - ld.d t6, a1, 48 - ld.d t7, a1, 56 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + ld.d t4, a1, 32 + ld.d t5, a1, 40 + ld.d t6, a1, 48 + ld.d t7, a1, 56 - st.d t0, a0, 0 - st.d t1, a0, 8 - ld.d t0, a1, 64 - ld.d t1, a1, 72 - st.d t2, a0, 16 - st.d t3, a0, 24 - ld.d t2, a1, 80 - ld.d t3, a1, 88 - st.d t4, a0, 32 - st.d t5, a0, 40 - ld.d t4, a1, 96 - ld.d t5, a1, 104 - st.d t6, a0, 48 - st.d t7, a0, 56 - ld.d t6, a1, 112 - ld.d t7, a1, 120 - addi.d a0, a0, 128 - addi.d a1, a1, 128 + st.d t0, a0, 0 + st.d t1, a0, 8 + ld.d t0, a1, 64 + ld.d t1, a1, 72 + st.d t2, a0, 16 + st.d t3, a0, 24 + ld.d t2, a1, 80 + ld.d t3, a1, 88 + st.d t4, a0, 32 + st.d t5, a0, 40 + ld.d t4, a1, 96 + ld.d t5, a1, 104 + st.d t6, a0, 48 + st.d t7, a0, 56 + ld.d t6, a1, 112 + ld.d t7, a1, 120 + addi.d a0, a0, 128 + addi.d a1, a1, 128 - st.d t0, a0, -64 - st.d t1, a0, -56 - st.d t2, a0, -48 - st.d t3, a0, -40 - st.d t4, a0, -32 - st.d t5, a0, -24 - st.d t6, a0, -16 - st.d t7, a0, -8 + st.d t0, a0, -64 + st.d t1, a0, -56 + st.d t2, a0, -48 + st.d t3, a0, -40 + st.d t4, a0, -32 + st.d t5, a0, -24 + st.d t6, a0, -16 + st.d t7, a0, -8 - bne t8, a0, 1b - jr ra + bne t8, a0, 1b + jr ra SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 0d369d485332..39743337999e 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -18,7 +18,7 @@ REG_S a2, sp, PT_BVADDR li.w a1, \write la.abs t0, do_page_fault - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(tlb_do_page_fault_\write) .endm @@ -34,7 +34,7 @@ SYM_FUNC_START(handle_tlb_protect) csrrd a2, LOONGARCH_CSR_BADV REG_S a2, sp, PT_BVADDR la.abs t0, do_page_fault - jirl ra, t0, 0 + jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_tlb_protect) @@ -151,8 +151,8 @@ tlb_huge_update_load: st.d t0, t1, 0 #endif addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX + addi.d ra, t1, 0 + csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr csrxchg zero, t1, LOONGARCH_CSR_TLBIDX @@ -319,8 +319,8 @@ tlb_huge_update_store: st.d t0, t1, 0 #endif addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX + addi.d ra, t1, 0 + csrxchg ra, t1, LOONGARCH_CSR_TLBIDX tlbwr csrxchg zero, t1, LOONGARCH_CSR_TLBIDX @@ -454,7 +454,7 @@ leave_modify: ertn #ifdef CONFIG_64BIT vmalloc_modify: - la.abs t1, swapper_pg_dir + la.abs t1, swapper_pg_dir b vmalloc_done_modify #endif @@ -512,14 +512,14 @@ tlb_huge_update_modify: /* Set huge page tlb entry size */ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) - csrxchg t1, t0, LOONGARCH_CSR_TLBIDX + csrxchg t1, t0, LOONGARCH_CSR_TLBIDX tlbwr /* Reset default page size */ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) - csrxchg t1, t0, LOONGARCH_CSR_TLBIDX + csrxchg t1, t0, LOONGARCH_CSR_TLBIDX nopage_tlb_modify: dbar 0 -- Gitee From 5e2a0ede41cb27a766af5e68ade90b2cb33d4efe Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Tue, 26 Jul 2022 23:57:15 +0800 Subject: [PATCH 15/23] LoongArch: Remove several syntactic sugar macros for branches ANBZ: #5200 commit ab6e57a69df515cc9231b578de5b820f9ba3d0be upstream. These syntactic sugars have been supported by upstream binutils from the beginning, so no need to patch them locally. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/asmmacro.h | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index a1a04083bd67..be037a40580d 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -274,16 +274,4 @@ nor \dst, \src, zero .endm -.macro bgt r0 r1 label - blt \r1, \r0, \label -.endm - -.macro bltz r0 label - blt \r0, zero, \label -.endm - -.macro bgez r0 label - bge \r0, zero, \label -.endm - #endif /* _ASM_ASMMACRO_H */ -- Gitee From 38bad08a1092cddc95d0914bf460ebaf4fd8eec7 Mon Sep 17 00:00:00 2001 From: Jun Yi Date: Thu, 21 Jul 2022 19:10:49 +0800 Subject: [PATCH 16/23] LoongArch: Remove useless header compiler.h ANBZ: #5200 commit f62b7626cb79dfbfe292145b7ebeee4dc63c9499 upstream. The content of LoongArch's compiler.h is trivial, with some unused anywhere, so inline the definitions and remove the header. Signed-off-by: Jun Yi Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/Kconfig | 1 - arch/loongarch/include/asm/atomic.h | 13 ++++--------- arch/loongarch/include/asm/compiler.h | 15 --------------- arch/loongarch/include/asm/futex.h | 5 ++--- arch/loongarch/include/asm/irqflags.h | 1 - arch/loongarch/include/asm/local.h | 1 - arch/loongarch/kernel/reset.c | 1 - arch/loongarch/lib/delay.c | 1 - 8 files changed, 6 insertions(+), 32 deletions(-) delete mode 100644 arch/loongarch/include/asm/compiler.h diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 212456b27468..21092405a704 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -70,7 +70,6 @@ config LOONGARCH select GENERIC_TIME_VSYSCALL select GPIOLIB select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_COMPILER_H select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 12d6a9944467..98a24f221746 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -12,7 +12,6 @@ #include #include #include -#include #if __SIZEOF_LONG__ == 4 #define __LL "ll.w " @@ -165,8 +164,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "I" (-i)); } else { __asm__ __volatile__( @@ -178,8 +176,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v) " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "r" (i)); } @@ -328,8 +325,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "I" (-i)); } else { __asm__ __volatile__( @@ -341,8 +337,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v) " beqz %1, 1b \n" "2: \n" __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) + : "=&r" (result), "=&r" (temp), "+ZC" (v->counter) : "r" (i)); } diff --git a/arch/loongarch/include/asm/compiler.h b/arch/loongarch/include/asm/compiler.h deleted file mode 100644 index 657cebe70ace..000000000000 --- a/arch/loongarch/include/asm/compiler.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_COMPILER_H -#define _ASM_COMPILER_H - -#define GCC_OFF_SMALL_ASM() "ZC" - -#define LOONGARCH_ISA_LEVEL "loongarch" -#define LOONGARCH_ISA_ARCH_LEVEL "arch=loongarch" -#define LOONGARCH_ISA_LEVEL_RAW loongarch -#define LOONGARCH_ISA_ARCH_LEVEL_RAW LOONGARCH_ISA_LEVEL_RAW - -#endif /* _ASM_COMPILER_H */ diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h index 837659335fb1..feb6658c84ff 100644 --- a/arch/loongarch/include/asm/futex.h +++ b/arch/loongarch/include/asm/futex.h @@ -8,7 +8,6 @@ #include #include #include -#include #include #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ @@ -95,8 +94,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv " "__UA_ADDR "\t1b, 4b \n" " "__UA_ADDR "\t2b, 4b \n" " .previous \n" - : "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr) - : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), + : "+r" (ret), "=&r" (val), "=ZC" (*uaddr) + : "ZC" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory", "t0"); diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h index 52121cd791fe..319a8c616f1f 100644 --- a/arch/loongarch/include/asm/irqflags.h +++ b/arch/loongarch/include/asm/irqflags.h @@ -9,7 +9,6 @@ #include #include -#include #include static inline void arch_local_irq_enable(void) diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h index 2052a2267337..65fbbae9fc4d 100644 --- a/arch/loongarch/include/asm/local.h +++ b/arch/loongarch/include/asm/local.h @@ -9,7 +9,6 @@ #include #include #include -#include typedef struct { atomic_long_t a; diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 2b86469e4718..800c965a17ea 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -13,7 +13,6 @@ #include #include -#include #include #include #include diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c index 5d856694fcfe..831d4761f385 100644 --- a/arch/loongarch/lib/delay.c +++ b/arch/loongarch/lib/delay.c @@ -7,7 +7,6 @@ #include #include -#include #include void __delay(unsigned long cycles) -- Gitee From 38d917c6a5a7e91bdfbba272f9cdb036cd3f832b Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Wed, 20 Jul 2022 15:21:51 +0800 Subject: [PATCH 17/23] LoongArch: Remove clock setting during cpu hotplug stage ANBZ: #5200 commit 71610ab1d017e131a9888ef8acd035284fb0e1dd upstream. On physical machine we can save power by disabling clock of hot removed cpu. However as different platforms require different methods to configure clocks, the code is platform-specific, and probably belongs to firmware/pmu or cpu regulator, rather than generic arch/loongarch code. Also, there is no such register on QEMU virt machine since the clock/frequency regulation is not emulated. This patch removes the hard-coded clock register accesses in generic LoongArch cpu hotplug flow. Reviewed-by: WANG Xuerui Signed-off-by: Bibo Mao Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Juxin Gao --- arch/loongarch/kernel/smp.c | 113 +++++------------------------------- include/linux/cpuhotplug.h | 1 - 2 files changed, 13 insertions(+), 101 deletions(-) diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 73cec62504fb..09743103d9b3 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -278,116 +278,29 @@ void loongson3_cpu_die(unsigned int cpu) mb(); } -/* - * The target CPU should go to XKPRANGE (uncached area) and flush - * ICache/DCache/VCache before the control CPU can safely disable its clock. - */ -static void loongson3_play_dead(int *state_addr) +void play_dead(void) { - register int val; - register void *addr; + register uint64_t addr; register void (*init_fn)(void); - __asm__ __volatile__( - " li.d %[addr], 0x8000000000000000\n" - "1: cacop 0x8, %[addr], 0 \n" /* flush ICache */ - " cacop 0x8, %[addr], 1 \n" - " cacop 0x8, %[addr], 2 \n" - " cacop 0x8, %[addr], 3 \n" - " cacop 0x9, %[addr], 0 \n" /* flush DCache */ - " cacop 0x9, %[addr], 1 \n" - " cacop 0x9, %[addr], 2 \n" - " cacop 0x9, %[addr], 3 \n" - " addi.w %[sets], %[sets], -1 \n" - " addi.d %[addr], %[addr], 0x40 \n" - " bnez %[sets], 1b \n" - " li.d %[addr], 0x8000000000000000\n" - "2: cacop 0xa, %[addr], 0 \n" /* flush VCache */ - " cacop 0xa, %[addr], 1 \n" - " cacop 0xa, %[addr], 2 \n" - " cacop 0xa, %[addr], 3 \n" - " cacop 0xa, %[addr], 4 \n" - " cacop 0xa, %[addr], 5 \n" - " cacop 0xa, %[addr], 6 \n" - " cacop 0xa, %[addr], 7 \n" - " cacop 0xa, %[addr], 8 \n" - " cacop 0xa, %[addr], 9 \n" - " cacop 0xa, %[addr], 10 \n" - " cacop 0xa, %[addr], 11 \n" - " cacop 0xa, %[addr], 12 \n" - " cacop 0xa, %[addr], 13 \n" - " cacop 0xa, %[addr], 14 \n" - " cacop 0xa, %[addr], 15 \n" - " addi.w %[vsets], %[vsets], -1 \n" - " addi.d %[addr], %[addr], 0x40 \n" - " bnez %[vsets], 2b \n" - " li.w %[val], 0x7 \n" /* *state_addr = CPU_DEAD; */ - " st.w %[val], %[state_addr], 0 \n" - " dbar 0 \n" - " cacop 0x11, %[state_addr], 0 \n" /* flush entry of *state_addr */ - : [addr] "=&r" (addr), [val] "=&r" (val) - : [state_addr] "r" (state_addr), - [sets] "r" (cpu_data[smp_processor_id()].dcache.sets), - [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets)); - + idle_task_exit(); local_irq_enable(); - change_csr_ecfg(ECFG0_IM, ECFGF_IPI); + set_csr_ecfg(ECFGF_IPI); + __this_cpu_write(cpu_state, CPU_DEAD); + + __smp_mb(); + do { + __asm__ __volatile__("idle 0\n\t"); + addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); + } while (addr == 0); - __asm__ __volatile__( - " idle 0 \n" - " li.w $t0, 0x1020 \n" - " iocsrrd.d %[init_fn], $t0 \n" /* Get init PC */ - : [init_fn] "=&r" (addr) - : /* No Input */ - : "a0"); - init_fn = __va(addr); + init_fn = (void *)TO_CACHE(addr); + iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); init_fn(); unreachable(); } -void play_dead(void) -{ - int *state_addr; - unsigned int cpu = smp_processor_id(); - void (*play_dead_uncached)(int *s); - - idle_task_exit(); - play_dead_uncached = (void *)TO_UNCACHE(__pa((unsigned long)loongson3_play_dead)); - state_addr = &per_cpu(cpu_state, cpu); - mb(); - play_dead_uncached(state_addr); -} - -static int loongson3_enable_clock(unsigned int cpu) -{ - uint64_t core_id = cpu_data[cpu].core; - uint64_t package_id = cpu_data[cpu].package; - - LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3); - - return 0; -} - -static int loongson3_disable_clock(unsigned int cpu) -{ - uint64_t core_id = cpu_data[cpu].core; - uint64_t package_id = cpu_data[cpu].package; - - LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3)); - - return 0; -} - -static int register_loongson3_notifier(void) -{ - return cpuhp_setup_state_nocalls(CPUHP_LOONGARCH_SOC_PREPARE, - "loongarch/loongson:prepare", - loongson3_enable_clock, - loongson3_disable_clock); -} -early_initcall(register_loongson3_notifier); - #endif /* diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7fa85e9d135d..3217e3e84728 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, CPUHP_MIPS_SOC_PREPARE, - CPUHP_LOONGARCH_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, -- Gitee From e2dd82ddf754ef076276d69515714fdeaa676606 Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Wed, 20 Jul 2022 15:21:52 +0800 Subject: [PATCH 18/23] LoongArch: Remove unused variables ANBZ: #5200 commit 3a3a4f7a65e3ff7ad395afc8c41ac317c8667546 upstream. There are some variables never used or referenced, this patch removes these varaibles and make the code cleaner. Reviewed-by: WANG Xuerui Signed-off-by: Bibo Mao Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/loongson.h | 12 ------------ arch/loongarch/kernel/env.c | 20 -------------------- 2 files changed, 32 deletions(-) diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h index 8522afafc24e..6e8f6972ceb6 100644 --- a/arch/loongarch/include/asm/loongson.h +++ b/arch/loongarch/include/asm/loongson.h @@ -39,18 +39,6 @@ extern const struct plat_smp_ops loongson3_smp_ops; #define MAX_PACKAGES 16 -/* Chip Config register of each physical cpu package */ -extern u64 loongson_chipcfg[MAX_PACKAGES]; -#define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id])) - -/* Chip Temperature register of each physical cpu package */ -extern u64 loongson_chiptemp[MAX_PACKAGES]; -#define LOONGSON_CHIPTEMP(id) (*(volatile u32 *)(loongson_chiptemp[id])) - -/* Freq Control register of each physical cpu package */ -extern u64 loongson_freqctrl[MAX_PACKAGES]; -#define LOONGSON_FREQCTRL(id) (*(volatile u32 *)(loongson_freqctrl[id])) - #define xconf_readl(addr) readl(addr) #define xconf_readq(addr) readq(addr) diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 467946ecf451..82b478a5c665 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -17,21 +17,6 @@ u64 efi_system_table; struct loongson_system_configuration loongson_sysconf; EXPORT_SYMBOL(loongson_sysconf); -u64 loongson_chipcfg[MAX_PACKAGES]; -u64 loongson_chiptemp[MAX_PACKAGES]; -u64 loongson_freqctrl[MAX_PACKAGES]; -unsigned long long smp_group[MAX_PACKAGES]; - -static void __init register_addrs_set(u64 *registers, const u64 addr, int num) -{ - u64 i; - - for (i = 0; i < num; i++) { - *registers = (i << 44) | addr; - registers++; - } -} - void __init init_environ(void) { int efi_boot = fw_arg0; @@ -50,11 +35,6 @@ void __init init_environ(void) efi_memmap_init_early(&data); memblock_reserve(data.phys_map & PAGE_MASK, PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK))); - - register_addrs_set(smp_group, TO_UNCACHE(0x1fe01000), 16); - register_addrs_set(loongson_chipcfg, TO_UNCACHE(0x1fe00180), 16); - register_addrs_set(loongson_chiptemp, TO_UNCACHE(0x1fe0019c), 16); - register_addrs_set(loongson_freqctrl, TO_UNCACHE(0x1fe001d0), 16); } static int __init init_cpu_fullname(void) -- Gitee From db68a8faae31ac8ff0f6be344cd72ae1d5f1cda6 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 26 Jul 2022 20:43:11 +0800 Subject: [PATCH 19/23] LoongArch: Disable executable stack by default ANBZ: #5200 commit 317980e6b4d03884429f2cdaf51efd28f01b71b0 upstream. Disable executable stack for LoongArch by default, as all modern architectures do. Reported-by: Andreas Schwab Suggested-by: WANG Xuerui Link: https://sourceware.org/pipermail/binutils/2022-July/121992.html Tested-by: WANG Xuerui Tested-by: Xi Ruoyao Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/elf.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index f3960b18a90e..5f3ff4781fda 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -288,8 +288,6 @@ struct arch_elf_state { .interp_fp_abi = LOONGARCH_ABI_FP_ANY, \ } -#define elf_read_implies_exec(ex, exec_stk) (exec_stk == EXSTACK_DEFAULT) - extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, bool is_interp, struct arch_elf_state *state); -- Gitee From cca3437d39920a54c8dffe95fc5a9e273512e05c Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 13 Jul 2022 18:00:41 +0800 Subject: [PATCH 20/23] LoongArch: Fix shared cache size calculation ANBZ: #5200 commit 1aea29d7c3569e5b6c40e73c51e9f4b2142c96ef upstream. Current calculation of shared cache size is from the node (die) scope, but we hope 'lscpu' to show the shared cache size of the whole package for multi-die chips (e.g., Loongson-3C5000L, which contains 4 dies in one package). So fix it by multiplying nodes_per_package. Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/kernel/cacheinfo.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index b38f5489d094..4662b06269f4 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -4,8 +4,9 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ -#include #include +#include +#include /* Populates leaf and increments to next leaf */ #define populate_cache(cache, leaf, c_level, c_type) \ @@ -17,6 +18,8 @@ do { \ leaf->ways_of_associativity = c->cache.ways; \ leaf->size = c->cache.linesz * c->cache.sets * \ c->cache.ways; \ + if (leaf->level > 2) \ + leaf->size *= nodes_per_package; \ leaf++; \ } while (0) @@ -95,11 +98,15 @@ static void cache_cpumap_setup(unsigned int cpu) int populate_cache_leaves(unsigned int cpu) { - int level = 1; + int level = 1, nodes_per_package = 1; struct cpuinfo_loongarch *c = ¤t_cpu_data; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf = this_cpu_ci->info_list; + if (loongson_sysconf.nr_nodes > 1) + nodes_per_package = loongson_sysconf.cores_per_package + / loongson_sysconf.cores_per_node; + if (c->icache.waysize) { populate_cache(dcache, this_leaf, level, CACHE_TYPE_DATA); populate_cache(icache, this_leaf, level++, CACHE_TYPE_INST); -- Gitee From 3fc3de3fcef66473567f0e76eecb558f7c8b4a61 Mon Sep 17 00:00:00 2001 From: Qi Hu Date: Thu, 14 Jul 2022 14:25:50 +0800 Subject: [PATCH 21/23] LoongArch: Fix missing fcsr in ptrace's fpr_set ANBZ: #5200 commit b0f3bdc00240fc9d7bf0f2a076943122d168c95e upstream. In file ptrace.c, function fpr_set does not copy fcsr data from ubuf to kbuf. That's the reason why fcsr cannot be modified by ptrace. This patch fixs this problem and allows users using ptrace to modify the fcsr. Co-developed-by: Xu Li Signed-off-by: Qi Hu Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/kernel/ptrace.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index e6ab87948e1d..dc2b82ea894c 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -193,7 +193,7 @@ static int fpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { const int fcc_start = NUM_FPU_REGS * sizeof(elf_fpreg_t); - const int fcc_end = fcc_start + sizeof(u64); + const int fcsr_start = fcc_start + sizeof(u64); int err; BUG_ON(count % sizeof(elf_fpreg_t)); @@ -209,10 +209,12 @@ static int fpr_set(struct task_struct *target, if (err) return err; - if (count > 0) - err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.fcc, - fcc_start, fcc_end); + err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcc, fcc_start, + fcc_start + sizeof(u64)); + err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcsr, fcsr_start, + fcsr_start + sizeof(u32)); return err; } -- Gitee From d71f1a0ca0aefbcb42e730fad9e754af364a386c Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 21 Jul 2022 17:53:01 +0800 Subject: [PATCH 22/23] LoongArch: Fix wrong "ROM Size" of boardinfo ANBZ: #5200 commit 45b53c9051770c0d9145083a328548745ee2e75b upstream. We can see the "ROM Size" is different in the following outputs: [root@linux loongson]# cat /sys/firmware/loongson/boardinfo BIOS Information Vendor : Loongson Version : vUDK2018-LoongArch-V2.0.pre-beta8 ROM Size : 63 KB Release Date : 06/15/2022 Board Information Manufacturer : Loongson Board Name : Loongson-LS3A5000-7A1000-1w-A2101 Family : LOONGSON64 [root@linux loongson]# dmidecode | head -11 ... Handle 0x0000, DMI type 0, 26 bytes BIOS Information Vendor: Loongson Version: vUDK2018-LoongArch-V2.0.pre-beta8 Release Date: 06/15/2022 ROM Size: 4 MB According to "BIOS Information (Type 0) structure" in the SMBIOS Reference Specification [1], it shows 64K * (n+1) is the size of the physical device containing the BIOS if the size is less than 16M. Additionally, we can see the related code in dmidecode [2]: u64 s = { .l = (code1 + 1) << 6 }; So the output of dmidecode is correct, the output of boardinfo is wrong, fix it. By the way, at present no need to consider the size is 16M or greater on LoongArch, because it is usually 4M or 8M which is enough to use. [1] https://www.dmtf.org/sites/default/files/standards/documents/DSP0134_3.6.0.pdf [2] https://git.savannah.nongnu.org/cgit/dmidecode.git/tree/dmidecode.c#n347 Fixes: 628c3bb40e9a ("LoongArch: Add boot and setup routines") Reviewed-by: WANG Xuerui Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 8e3f7bc9125e..7bdf4935e856 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -126,7 +126,7 @@ static void __init parse_bios_table(const struct dmi_header *dm) char *dmi_data = (char *)dm; bios_extern = *(dmi_data + SMBIOS_BIOSEXTERN_OFFSET); - b_info.bios_size = *(dmi_data + SMBIOS_BIOSSIZE_OFFSET); + b_info.bios_size = (*(dmi_data + SMBIOS_BIOSSIZE_OFFSET) + 1) << 6; if (bios_extern & LOONGSON_EFI_ENABLE) set_bit(EFI_BOOT, &efi.flags); -- Gitee From 34be050f119e4126f4386227b066f18dc7d1b9bb Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 8 Aug 2022 17:32:05 +0800 Subject: [PATCH 23/23] irqchip/loongson-pch-pic: Move find_pch_pic() into CONFIG_ACPI ANBZ: #5200 commit fda7409a8fcfa457814f8186f2861a9f00008e75 upstream. MIPS doesn't declare find_pch_pic(), which makes a build warning: >> drivers/irqchip/irq-loongson-pch-pic.c:51:5: warning: no previous prototype for function 'find_pch_pic' [-Wmissing-prototypes] int find_pch_pic(u32 gsi) ^ drivers/irqchip/irq-loongson-pch-pic.c:51:1: note: declare 'static' if the function is not intended to be used outside of this translation unit int find_pch_pic(u32 gsi) ^ static 1 warning generated. Move find_pch_pic() into CONFIG_ACPI which only used by LoongArch to fix the warning. BTW, remove the duplicated declaration of find_pch_pic() in irq.h. Reported-by: kernel test robot Signed-off-by: Huacai Chen Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220808093205.3658485-1-chenhuacai@loongson.cn Signed-off-by: Xuefeng Li Signed-off-by: Bibo Mao Signed-off-by: Juxin Gao --- arch/loongarch/include/asm/irq.h | 1 - drivers/irqchip/irq-loongson-pch-pic.c | 38 +++++++++++++------------- 2 files changed, 19 insertions(+), 20 deletions(-) diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 389a4c7aa92a..43883e98ad9d 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -81,7 +81,6 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS]; #define GSI_MIN_PCH_IRQ LOONGSON_PCH_IRQ_BASE #define GSI_MAX_PCH_IRQ (LOONGSON_PCH_IRQ_BASE + 256 - 1) -extern int find_pch_pic(u32 gsi); extern int eiointc_get_node(int id); struct acpi_madt_lio_pic; diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index 1b7ff05b18bd..829bb8a27d5f 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -48,25 +48,6 @@ static struct pch_pic *pch_pic_priv[MAX_IO_PICS]; struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; -int find_pch_pic(u32 gsi) -{ - int i; - - /* Find the PCH_PIC that manages this GSI. */ - for (i = 0; i < MAX_IO_PICS; i++) { - struct pch_pic *priv = pch_pic_priv[i]; - - if (!priv) - return -1; - - if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count)) - return i; - } - - pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi); - return -1; -} - static void pch_pic_bitset(struct pch_pic *priv, int offset, int bit) { u32 reg; @@ -325,6 +306,25 @@ IRQCHIP_DECLARE(pch_pic, "loongson,pch-pic-1.0", pch_pic_of_init); #endif #ifdef CONFIG_ACPI +int find_pch_pic(u32 gsi) +{ + int i; + + /* Find the PCH_PIC that manages this GSI. */ + for (i = 0; i < MAX_IO_PICS; i++) { + struct pch_pic *priv = pch_pic_priv[i]; + + if (!priv) + return -1; + + if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count)) + return i; + } + + pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi); + return -1; +} + static int __init pch_lpc_parse_madt(union acpi_subtable_headers *header, const unsigned long end) -- Gitee