diff options
Diffstat (limited to 'arch/loongarch')
34 files changed, 1001 insertions, 825 deletions
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 4b19f93379a1..f0abc38c40ac 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -15,7 +15,6 @@ config LOONGARCH select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT - select ARCH_HAS_CRC32 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_FAST_MULTIPLIER @@ -25,7 +24,6 @@ config LOONGARCH select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PREEMPT_LAZY - select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_MEMORY select ARCH_HAS_SET_DIRECT_MAP @@ -120,11 +118,11 @@ config LOONGARCH select HAVE_ARCH_KASAN select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB if PERF_EVENTS + select HAVE_ARCH_KSTACK_ERASE select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER - select HAVE_ARCH_STACKLEAK select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD @@ -144,7 +142,6 @@ config LOONGARCH select HAVE_EXIT_THREAD select HAVE_GUP_FAST select HAVE_FTRACE_GRAPH_FUNC - select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_FREGS diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts index a34734a6c3ce..018ed904352a 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts @@ -41,6 +41,15 @@ }; }; +&apbdma3 { + status = "okay"; +}; + +&mmc0 { + status = "okay"; + bus-width = <4>; +}; + &gmac0 { status = "okay"; diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 760c60eebb89..588ebc3bded4 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -104,7 +104,7 @@ status = "disabled"; }; - dma-controller@1fe10c20 { + apbdma2: dma-controller@1fe10c20 { compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; reg = <0 0x1fe10c20 0 0x8>; interrupt-parent = <&eiointc>; @@ -114,7 +114,7 @@ status = "disabled"; }; - dma-controller@1fe10c30 { + apbdma3: dma-controller@1fe10c30 { compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; reg = <0 0x1fe10c30 0 0x8>; interrupt-parent = <&eiointc>; @@ -437,6 +437,30 @@ status = "disabled"; }; + mmc0: mmc@1ff64000 { + compatible = "loongson,ls2k0500-mmc"; + reg = <0 0x1ff64000 0 0x2000>, + <0 0x1fe10100 0 0x4>; + interrupt-parent = <&eiointc>; + interrupts = <57>; + dmas = <&apbdma3 0>; + dma-names = "rx-tx"; + clocks = <&clk LOONGSON2_APB_CLK>; + status = "disabled"; + }; + + mmc@1ff66000 { + compatible = "loongson,ls2k0500-mmc"; + reg = <0 0x1ff66000 0 0x2000>, + <0 0x1fe10100 0 0x4>; + interrupt-parent = <&eiointc>; + interrupts = <58>; + dmas = <&apbdma2 0>; + dma-names = "rx-tx"; + clocks = <&clk LOONGSON2_APB_CLK>; + status = "disabled"; + }; + pmc: power-management@1ff6c000 { compatible = "loongson,ls2k0500-pmc", "syscon"; reg = <0x0 0x1ff6c000 0x0 0x58>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts index 78ea995abf1c..d9a452ada5d7 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts @@ -48,6 +48,19 @@ }; }; +&apbdma1 { + status = "okay"; +}; + +&mmc { + status = "okay"; + + pinctrl-0 = <&sdio_pins_default>; + pinctrl-names = "default"; + bus-width = <4>; + cd-gpios = <&gpio0 22 GPIO_ACTIVE_LOW>; +}; + &gmac0 { status = "okay"; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index 1da3beb00f0e..d8e01e2534dd 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -187,14 +187,14 @@ <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, - <>, - <26 IRQ_TYPE_LEVEL_HIGH>, + <0 IRQ_TYPE_NONE>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, + <26 IRQ_TYPE_NONE>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, <26 IRQ_TYPE_LEVEL_HIGH>, @@ -209,13 +209,13 @@ <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, - <>, + <0 IRQ_TYPE_NONE>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, - <>, - <>, + <0 IRQ_TYPE_NONE>, + <0 IRQ_TYPE_NONE>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, <27 IRQ_TYPE_LEVEL_HIGH>, @@ -256,7 +256,7 @@ status = "disabled"; }; - dma-controller@1fe00c10 { + apbdma1: dma-controller@1fe00c10 { compatible = "loongson,ls2k1000-apbdma"; reg = <0x0 0x1fe00c10 0x0 0x8>; interrupt-parent = <&liointc1>; @@ -405,6 +405,18 @@ status = "disabled"; }; + mmc: mmc@1fe2c000 { + compatible = "loongson,ls2k1000-mmc"; + reg = <0 0x1fe2c000 0 0x68>, + <0 0x1fe00438 0 0x8>; + interrupt-parent = <&liointc0>; + interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + dmas = <&apbdma1 0>; + dma-names = "rx-tx"; + status = "disabled"; + }; + spi0: spi@1fff0220 { compatible = "loongson,ls2k1000-spi"; reg = <0x0 0x1fff0220 0x0 0x10>; diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts index ea9e6985d0e9..3c6b12220386 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts @@ -39,6 +39,16 @@ }; }; +&emmc { + status = "okay"; + + bus-width = <8>; + cap-mmc-highspeed; + mmc-hs200-1_8v; + no-sd; + no-sdio; +}; + &sata { status = "okay"; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index 9e0411f2754c..00cc485b753b 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -259,6 +259,24 @@ status = "disabled"; }; + emmc: mmc@79990000 { + compatible = "loongson,ls2k2000-mmc"; + reg = <0x0 0x79990000 0x0 0x1000>; + interrupt-parent = <&pic>; + interrupts = <51 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_EMMC_CLK>; + status = "disabled"; + }; + + mmc@79991000 { + compatible = "loongson,ls2k2000-mmc"; + reg = <0x0 0x79991000 0x0 0x1000>; + interrupt-parent = <&pic>; + interrupts = <50 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_EMMC_CLK>; + status = "disabled"; + }; + pcie@1a000000 { compatible = "loongson,ls2k-pci"; reg = <0x0 0x1a000000 0x0 0x02000000>, diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 0d59af6007b7..34eaee0384c9 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -225,7 +225,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m CONFIG_NETFILTER_XT_MATCH_CONNMARK=m CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m CONFIG_NETFILTER_XT_MATCH_CPU=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m @@ -784,8 +783,23 @@ CONFIG_SND_HDA_HWDEP=y CONFIG_SND_HDA_INPUT_BEEP=y CONFIG_SND_HDA_PATCH_LOADER=y CONFIG_SND_HDA_CODEC_REALTEK=y +CONFIG_SND_HDA_CODEC_REALTEK_LIB=y +CONFIG_SND_HDA_CODEC_ALC260=y +CONFIG_SND_HDA_CODEC_ALC262=y +CONFIG_SND_HDA_CODEC_ALC268=y +CONFIG_SND_HDA_CODEC_ALC269=y +CONFIG_SND_HDA_CODEC_ALC662=y +CONFIG_SND_HDA_CODEC_ALC680=y +CONFIG_SND_HDA_CODEC_ALC861=y +CONFIG_SND_HDA_CODEC_ALC861VD=y +CONFIG_SND_HDA_CODEC_ALC880=y +CONFIG_SND_HDA_CODEC_ALC882=y CONFIG_SND_HDA_CODEC_SIGMATEL=y CONFIG_SND_HDA_CODEC_HDMI=y +CONFIG_SND_HDA_CODEC_HDMI_GENERIC=y +CONFIG_SND_HDA_CODEC_HDMI_INTEL=y +CONFIG_SND_HDA_CODEC_HDMI_ATI=y +CONFIG_SND_HDA_CODEC_HDMI_NVIDIA=y CONFIG_SND_HDA_CODEC_CONEXANT=y CONFIG_SND_USB_AUDIO=m CONFIG_SND_SOC=m diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 80ddb5edb845..b04d2cef935f 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -10,5 +10,4 @@ generic-y += user.h generic-y += ioctl.h generic-y += mmzone.h generic-y += statfs.h -generic-y += param.h generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h index 4dc4b3e04225..ab68b594f889 100644 --- a/arch/loongarch/include/asm/hugetlb.h +++ b/arch/loongarch/include/asm/hugetlb.h @@ -10,20 +10,6 @@ uint64_t pmd_to_entrylo(unsigned long pmd_val); -#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, - unsigned long len) -{ - unsigned long task_size = STACK_TOP; - - if (len > task_size) - return -ENOMEM; - if (task_size - len < addr) - return -EINVAL; - return 0; -} - #define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index 3089785ca97e..277d2140676b 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -497,6 +497,7 @@ void arch_simulate_insn(union loongarch_instruction insn, struct pt_regs *regs); int larch_insn_read(void *addr, u32 *insnp); int larch_insn_write(void *addr, u32 insn); int larch_insn_patch_text(void *addr, u32 insn); +int larch_insn_text_copy(void *dst, void *src, size_t len); u32 larch_insn_gen_nop(void); u32 larch_insn_gen_b(unsigned long pc, unsigned long dest); @@ -510,6 +511,8 @@ u32 larch_insn_gen_move(enum loongarch_gpr rd, enum loongarch_gpr rj); u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm); u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm); u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); +u32 larch_insn_gen_beq(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); +u32 larch_insn_gen_bne(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm); static inline bool signed_imm_check(long val, unsigned int bit) diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index a3c4cc46c892..0cecbd038bb3 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -50,12 +50,6 @@ struct kvm_vm_stat { struct kvm_vm_stat_generic generic; u64 pages; u64 hugepages; - u64 ipi_read_exits; - u64 ipi_write_exits; - u64 eiointc_read_exits; - u64 eiointc_write_exits; - u64 pch_pic_read_exits; - u64 pch_pic_write_exits; }; struct kvm_vcpu_stat { @@ -65,6 +59,12 @@ struct kvm_vcpu_stat { u64 cpucfg_exits; u64 signal_exits; u64 hypercall_exits; + u64 ipi_read_exits; + u64 ipi_write_exits; + u64 eiointc_read_exits; + u64 eiointc_write_exits; + u64 pch_pic_read_exits; + u64 pch_pic_write_exits; }; #define KVM_MEM_HUGEPAGE_CAPABLE (1UL << 0) diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index a0994d226eff..09dfd7eb406e 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -451,6 +451,13 @@ #define LOONGARCH_CSR_KS6 0x36 #define LOONGARCH_CSR_KS7 0x37 #define LOONGARCH_CSR_KS8 0x38 +#define LOONGARCH_CSR_KS9 0x39 +#define LOONGARCH_CSR_KS10 0x3a +#define LOONGARCH_CSR_KS11 0x3b +#define LOONGARCH_CSR_KS12 0x3c +#define LOONGARCH_CSR_KS13 0x3d +#define LOONGARCH_CSR_KS14 0x3e +#define LOONGARCH_CSR_KS15 0x3f /* Exception allocated KS0, KS1 and KS2 statically */ #define EXCEPTION_KS0 LOONGARCH_CSR_KS0 diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 7bbfb04a54cc..2fc3789220ac 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -22,7 +22,6 @@ #define _PAGE_PFN_SHIFT 12 #define _PAGE_SWP_EXCLUSIVE_SHIFT 23 #define _PAGE_PFN_END_SHIFT 48 -#define _PAGE_DEVMAP_SHIFT 59 #define _PAGE_PRESENT_INVALID_SHIFT 60 #define _PAGE_NO_READ_SHIFT 61 #define _PAGE_NO_EXEC_SHIFT 62 @@ -36,7 +35,6 @@ #define _PAGE_MODIFIED (_ULCAST_(1) << _PAGE_MODIFIED_SHIFT) #define _PAGE_PROTNONE (_ULCAST_(1) << _PAGE_PROTNONE_SHIFT) #define _PAGE_SPECIAL (_ULCAST_(1) << _PAGE_SPECIAL_SHIFT) -#define _PAGE_DEVMAP (_ULCAST_(1) << _PAGE_DEVMAP_SHIFT) /* We borrow bit 23 to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE (_ULCAST_(1) << _PAGE_SWP_EXCLUSIVE_SHIFT) @@ -76,8 +74,8 @@ #define __READABLE (_PAGE_VALID) #define __WRITEABLE (_PAGE_DIRTY | _PAGE_WRITE) -#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) -#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) +#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) +#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_NO_READ | \ _PAGE_USER | _CACHE_CC) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index f2aeff544cee..bd128696e96d 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -409,9 +409,6 @@ static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; static inline pte_t pte_mkspecial(pte_t pte) { pte_val(pte) |= _PAGE_SPECIAL; return pte; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ -static inline int pte_devmap(pte_t pte) { return !!(pte_val(pte) & _PAGE_DEVMAP); } -static inline pte_t pte_mkdevmap(pte_t pte) { pte_val(pte) |= _PAGE_DEVMAP; return pte; } - #define pte_accessible pte_accessible static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) { @@ -540,17 +537,6 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pmd; } -static inline int pmd_devmap(pmd_t pmd) -{ - return !!(pmd_val(pmd) & _PAGE_DEVMAP); -} - -static inline pmd_t pmd_mkdevmap(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_DEVMAP; - return pmd; -} - static inline struct page *pmd_page(pmd_t pmd) { if (pmd_trans_huge(pmd)) @@ -606,11 +592,6 @@ static inline long pmd_protnone(pmd_t pmd) #define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0) #define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0) -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define pud_devmap(pud) (0) -#define pgd_devmap(pgd) (0) -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - /* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 27144de5c5fe..c0a5dc9aeae2 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -39,16 +39,19 @@ void __init init_environ(void) static int __init init_cpu_fullname(void) { - struct device_node *root; int cpu, ret; - char *model; + char *cpuname; + const char *model; + struct device_node *root; /* Parsing cpuname from DTS model property */ root = of_find_node_by_path("/"); - ret = of_property_read_string(root, "model", (const char **)&model); + ret = of_property_read_string(root, "model", &model); + if (ret == 0) { + cpuname = kstrdup(model, GFP_KERNEL); + loongson_sysconf.cpuname = strsep(&cpuname, " "); + } of_node_put(root); - if (ret == 0) - loongson_sysconf.cpuname = strsep(&model, " "); if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) { for (cpu = 0; cpu < NR_CPUS; cpu++) diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 14d7d700bcb9..72ecfed29d55 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -4,6 +4,8 @@ */ #include <linux/sizes.h> #include <linux/uaccess.h> +#include <linux/set_memory.h> +#include <linux/stop_machine.h> #include <asm/cacheflush.h> #include <asm/inst.h> @@ -218,6 +220,50 @@ int larch_insn_patch_text(void *addr, u32 insn) return ret; } +struct insn_copy { + void *dst; + void *src; + size_t len; + unsigned int cpu; +}; + +static int text_copy_cb(void *data) +{ + int ret = 0; + struct insn_copy *copy = data; + + if (smp_processor_id() == copy->cpu) { + ret = copy_to_kernel_nofault(copy->dst, copy->src, copy->len); + if (ret) + pr_err("%s: operation failed\n", __func__); + } + + flush_icache_range((unsigned long)copy->dst, (unsigned long)copy->dst + copy->len); + + return ret; +} + +int larch_insn_text_copy(void *dst, void *src, size_t len) +{ + int ret = 0; + size_t start, end; + struct insn_copy copy = { + .dst = dst, + .src = src, + .len = len, + .cpu = smp_processor_id(), + }; + + start = round_down((size_t)dst, PAGE_SIZE); + end = round_up((size_t)dst + len, PAGE_SIZE); + + set_memory_rw(start, (end - start) / PAGE_SIZE); + ret = stop_machine(text_copy_cb, ©, cpu_online_mask); + set_memory_rox(start, (end - start) / PAGE_SIZE); + + return ret; +} + u32 larch_insn_gen_nop(void) { return INSN_NOP; @@ -323,6 +369,34 @@ u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) return insn.word; } +u32 larch_insn_gen_beq(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) +{ + union loongarch_instruction insn; + + if ((imm & 3) || imm < -SZ_128K || imm >= SZ_128K) { + pr_warn("The generated beq instruction is out of range.\n"); + return INSN_BREAK; + } + + emit_beq(&insn, rj, rd, imm >> 2); + + return insn.word; +} + +u32 larch_insn_gen_bne(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) +{ + union loongarch_instruction insn; + + if ((imm & 3) || imm < -SZ_128K || imm >= SZ_128K) { + pr_warn("The generated bne instruction is out of range.\n"); + return INSN_BREAK; + } + + emit_bne(&insn, rj, rd, imm >> 2); + + return insn.word; +} + u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) { union loongarch_instruction insn; diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index 5e2402cfcab0..8edd0954e55a 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -864,7 +864,7 @@ enum loongarch_regset { static const struct user_regset loongarch64_regsets[] = { [REGSET_GPR] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(elf_greg_t), .align = sizeof(elf_greg_t), @@ -872,7 +872,7 @@ static const struct user_regset loongarch64_regsets[] = { .set = gpr_set, }, [REGSET_FPR] = { - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(elf_fpreg_t), .align = sizeof(elf_fpreg_t), @@ -880,7 +880,7 @@ static const struct user_regset loongarch64_regsets[] = { .set = fpr_set, }, [REGSET_CPUCFG] = { - .core_note_type = NT_LOONGARCH_CPUCFG, + USER_REGSET_NOTE_TYPE(LOONGARCH_CPUCFG), .n = 64, .size = sizeof(u32), .align = sizeof(u32), @@ -889,7 +889,7 @@ static const struct user_regset loongarch64_regsets[] = { }, #ifdef CONFIG_CPU_HAS_LSX [REGSET_LSX] = { - .core_note_type = NT_LOONGARCH_LSX, + USER_REGSET_NOTE_TYPE(LOONGARCH_LSX), .n = NUM_FPU_REGS, .size = 16, .align = 16, @@ -899,7 +899,7 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_CPU_HAS_LASX [REGSET_LASX] = { - .core_note_type = NT_LOONGARCH_LASX, + USER_REGSET_NOTE_TYPE(LOONGARCH_LASX), .n = NUM_FPU_REGS, .size = 32, .align = 32, @@ -909,7 +909,7 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_CPU_HAS_LBT [REGSET_LBT] = { - .core_note_type = NT_LOONGARCH_LBT, + USER_REGSET_NOTE_TYPE(LOONGARCH_LBT), .n = 5, .size = sizeof(u64), .align = sizeof(u64), @@ -919,7 +919,7 @@ static const struct user_regset loongarch64_regsets[] = { #endif #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { - .core_note_type = NT_LOONGARCH_HW_BREAK, + USER_REGSET_NOTE_TYPE(LOONGARCH_HW_BREAK), .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), @@ -927,7 +927,7 @@ static const struct user_regset loongarch64_regsets[] = { .set = hw_break_set, }, [REGSET_HW_WATCH] = { - .core_note_type = NT_LOONGARCH_HW_WATCH, + USER_REGSET_NOTE_TYPE(LOONGARCH_HW_WATCH), .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index 84e6de2fd973..8b5140ac9ea1 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -109,4 +109,4 @@ SYM_CODE_END(kexec_smp_wait) relocate_new_kernel_end: .section ".data" -SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel) +SYM_DATA(relocate_new_kernel_size, .quad relocate_new_kernel_end - relocate_new_kernel) diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index b99fbb388fe0..075b79b2c1d3 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -191,6 +191,16 @@ static int __init early_parse_mem(char *p) return -EINVAL; } + start = 0; + size = memparse(p, &p); + if (*p == '@') /* Every mem=... should contain '@' */ + start = memparse(p + 1, &p); + else { /* Only one mem=... is allowed if no '@' */ + usermem = 1; + memblock_enforce_memory_limit(size); + return 0; + } + /* * If a user specifies memory size, we * blow away any automatically generated @@ -201,14 +211,6 @@ static int __init early_parse_mem(char *p) memblock_remove(memblock_start_of_DRAM(), memblock_end_of_DRAM() - memblock_start_of_DRAM()); } - start = 0; - size = memparse(p, &p); - if (*p == '@') - start = memparse(p + 1, &p); - else { - pr_err("Invalid format!\n"); - return -EINVAL; - } if (!IS_ENABLED(CONFIG_NUMA)) memblock_add(start, size); @@ -265,7 +267,7 @@ static void __init arch_reserve_crashkernel(void) return; ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &crash_size, &crash_base, &low_size, &high); + &crash_size, &crash_base, &low_size, NULL, &high); if (ret) return; diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c index 0005be49b056..0d5fa64a2225 100644 --- a/arch/loongarch/kernel/unwind_orc.c +++ b/arch/loongarch/kernel/unwind_orc.c @@ -508,7 +508,7 @@ bool unwind_next_frame(struct unwind_state *state) state->pc = bt_address(pc); if (!state->pc) { - pr_err("cannot find unwind pc at %pK\n", (void *)pc); + pr_err("cannot find unwind pc at %p\n", (void *)pc); goto err; } diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index fa52251b3bf1..2ce41f93b2a4 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -289,9 +289,11 @@ static int kvm_trap_handle_gspr(struct kvm_vcpu *vcpu) er = EMULATE_FAIL; switch (((inst.word >> 24) & 0xff)) { case 0x0: /* CPUCFG GSPR */ + trace_kvm_exit_cpucfg(vcpu, KVM_TRACE_EXIT_CPUCFG); er = kvm_emu_cpucfg(vcpu, inst); break; case 0x4: /* CSR{RD,WR,XCHG} GSPR */ + trace_kvm_exit_csr(vcpu, KVM_TRACE_EXIT_CSR); er = kvm_handle_csr(vcpu, inst); break; case 0x6: /* Cache, Idle and IOCSR GSPR */ @@ -821,32 +823,25 @@ static int kvm_handle_lbt_disabled(struct kvm_vcpu *vcpu, int ecode) return RESUME_GUEST; } -static int kvm_send_pv_ipi(struct kvm_vcpu *vcpu) +static void kvm_send_pv_ipi(struct kvm_vcpu *vcpu) { - unsigned int min, cpu, i; - unsigned long ipi_bitmap; + unsigned int min, cpu; struct kvm_vcpu *dest; + DECLARE_BITMAP(ipi_bitmap, BITS_PER_LONG * 2) = { + kvm_read_reg(vcpu, LOONGARCH_GPR_A1), + kvm_read_reg(vcpu, LOONGARCH_GPR_A2) + }; min = kvm_read_reg(vcpu, LOONGARCH_GPR_A3); - for (i = 0; i < 2; i++, min += BITS_PER_LONG) { - ipi_bitmap = kvm_read_reg(vcpu, LOONGARCH_GPR_A1 + i); - if (!ipi_bitmap) + for_each_set_bit(cpu, ipi_bitmap, BITS_PER_LONG * 2) { + dest = kvm_get_vcpu_by_cpuid(vcpu->kvm, cpu + min); + if (!dest) continue; - cpu = find_first_bit((void *)&ipi_bitmap, BITS_PER_LONG); - while (cpu < BITS_PER_LONG) { - dest = kvm_get_vcpu_by_cpuid(vcpu->kvm, cpu + min); - cpu = find_next_bit((void *)&ipi_bitmap, BITS_PER_LONG, cpu + 1); - if (!dest) - continue; - - /* Send SWI0 to dest vcpu to emulate IPI interrupt */ - kvm_queue_irq(dest, INT_SWI0); - kvm_vcpu_kick(dest); - } + /* Send SWI0 to dest vcpu to emulate IPI interrupt */ + kvm_queue_irq(dest, INT_SWI0); + kvm_vcpu_kick(dest); } - - return 0; } /* diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index a75f865d6fb9..a3a12af9ecbf 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -9,7 +9,7 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) { - int ipnum, cpu, cpuid, irq_index, irq_mask, irq; + int ipnum, cpu, cpuid, irq; struct kvm_vcpu *vcpu; for (irq = 0; irq < EIOINTC_IRQS; irq++) { @@ -18,8 +18,6 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) ipnum = count_trailing_zeros(ipnum); ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0; } - irq_index = irq / 32; - irq_mask = BIT(irq & 0x1f); cpuid = s->coremap.reg_u8[irq]; vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); @@ -27,16 +25,16 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) continue; cpu = vcpu->vcpu_id; - if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask)) - set_bit(irq, s->sw_coreisr[cpu][ipnum]); + if (test_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu])) + __set_bit(irq, s->sw_coreisr[cpu][ipnum]); else - clear_bit(irq, s->sw_coreisr[cpu][ipnum]); + __clear_bit(irq, s->sw_coreisr[cpu][ipnum]); } } static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) { - int ipnum, cpu, found, irq_index, irq_mask; + int ipnum, cpu, found; struct kvm_vcpu *vcpu; struct kvm_interrupt vcpu_irq; @@ -48,19 +46,16 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) cpu = s->sw_coremap[irq]; vcpu = kvm_get_vcpu(s->kvm, cpu); - irq_index = irq / 32; - irq_mask = BIT(irq & 0x1f); - if (level) { /* if not enable return false */ - if (((s->enable.reg_u32[irq_index]) & irq_mask) == 0) + if (!test_bit(irq, (unsigned long *)s->enable.reg_u32)) return; - s->coreisr.reg_u32[cpu][irq_index] |= irq_mask; + __set_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu]); found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS); - set_bit(irq, s->sw_coreisr[cpu][ipnum]); + __set_bit(irq, s->sw_coreisr[cpu][ipnum]); } else { - s->coreisr.reg_u32[cpu][irq_index] &= ~irq_mask; - clear_bit(irq, s->sw_coreisr[cpu][ipnum]); + __clear_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu]); + __clear_bit(irq, s->sw_coreisr[cpu][ipnum]); found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS); } @@ -110,159 +105,14 @@ void eiointc_set_irq(struct loongarch_eiointc *s, int irq, int level) unsigned long flags; unsigned long *isr = (unsigned long *)s->isr.reg_u8; - level ? set_bit(irq, isr) : clear_bit(irq, isr); spin_lock_irqsave(&s->lock, flags); + level ? __set_bit(irq, isr) : __clear_bit(irq, isr); eiointc_update_irq(s, irq, level); spin_unlock_irqrestore(&s->lock, flags); } -static inline void eiointc_enable_irq(struct kvm_vcpu *vcpu, - struct loongarch_eiointc *s, int index, u8 mask, int level) -{ - u8 val; - int irq; - - val = mask & s->isr.reg_u8[index]; - irq = ffs(val); - while (irq != 0) { - /* - * enable bit change from 0 to 1, - * need to update irq by pending bits - */ - eiointc_update_irq(s, irq - 1 + index * 8, level); - val &= ~BIT(irq - 1); - irq = ffs(val); - } -} - -static int loongarch_eiointc_readb(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, - gpa_t addr, int len, void *val) -{ - int index, ret = 0; - u8 data = 0; - gpa_t offset; - - offset = addr - EIOINTC_BASE; - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = offset - EIOINTC_NODETYPE_START; - data = s->nodetype.reg_u8[index]; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - index = offset - EIOINTC_IPMAP_START; - data = s->ipmap.reg_u8[index]; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = offset - EIOINTC_ENABLE_START; - data = s->enable.reg_u8[index]; - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - index = offset - EIOINTC_BOUNCE_START; - data = s->bounce.reg_u8[index]; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = offset - EIOINTC_COREISR_START; - data = s->coreisr.reg_u8[vcpu->vcpu_id][index]; - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - index = offset - EIOINTC_COREMAP_START; - data = s->coremap.reg_u8[index]; - break; - default: - ret = -EINVAL; - break; - } - *(u8 *)val = data; - - return ret; -} - -static int loongarch_eiointc_readw(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, - gpa_t addr, int len, void *val) -{ - int index, ret = 0; - u16 data = 0; - gpa_t offset; - - offset = addr - EIOINTC_BASE; - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = (offset - EIOINTC_NODETYPE_START) >> 1; - data = s->nodetype.reg_u16[index]; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - index = (offset - EIOINTC_IPMAP_START) >> 1; - data = s->ipmap.reg_u16[index]; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = (offset - EIOINTC_ENABLE_START) >> 1; - data = s->enable.reg_u16[index]; - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - index = (offset - EIOINTC_BOUNCE_START) >> 1; - data = s->bounce.reg_u16[index]; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = (offset - EIOINTC_COREISR_START) >> 1; - data = s->coreisr.reg_u16[vcpu->vcpu_id][index]; - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - index = (offset - EIOINTC_COREMAP_START) >> 1; - data = s->coremap.reg_u16[index]; - break; - default: - ret = -EINVAL; - break; - } - *(u16 *)val = data; - - return ret; -} - -static int loongarch_eiointc_readl(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, - gpa_t addr, int len, void *val) -{ - int index, ret = 0; - u32 data = 0; - gpa_t offset; - - offset = addr - EIOINTC_BASE; - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = (offset - EIOINTC_NODETYPE_START) >> 2; - data = s->nodetype.reg_u32[index]; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - index = (offset - EIOINTC_IPMAP_START) >> 2; - data = s->ipmap.reg_u32[index]; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = (offset - EIOINTC_ENABLE_START) >> 2; - data = s->enable.reg_u32[index]; - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - index = (offset - EIOINTC_BOUNCE_START) >> 2; - data = s->bounce.reg_u32[index]; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = (offset - EIOINTC_COREISR_START) >> 2; - data = s->coreisr.reg_u32[vcpu->vcpu_id][index]; - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - index = (offset - EIOINTC_COREMAP_START) >> 2; - data = s->coremap.reg_u32[index]; - break; - default: - ret = -EINVAL; - break; - } - *(u32 *)val = data; - - return ret; -} - -static int loongarch_eiointc_readq(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, - gpa_t addr, int len, void *val) +static int loongarch_eiointc_read(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, + gpa_t addr, unsigned long *val) { int index, ret = 0; u64 data = 0; @@ -298,7 +148,7 @@ static int loongarch_eiointc_readq(struct kvm_vcpu *vcpu, struct loongarch_eioin ret = -EINVAL; break; } - *(u64 *)val = data; + *val = data; return ret; } @@ -308,7 +158,7 @@ static int kvm_eiointc_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *val) { int ret = -EINVAL; - unsigned long flags; + unsigned long flags, data, offset; struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; if (!eiointc) { @@ -321,355 +171,115 @@ static int kvm_eiointc_read(struct kvm_vcpu *vcpu, return -EINVAL; } - vcpu->kvm->stat.eiointc_read_exits++; + offset = addr & 0x7; + addr -= offset; + vcpu->stat.eiointc_read_exits++; spin_lock_irqsave(&eiointc->lock, flags); + ret = loongarch_eiointc_read(vcpu, eiointc, addr, &data); + spin_unlock_irqrestore(&eiointc->lock, flags); + if (ret) + return ret; + + data = data >> (offset * 8); switch (len) { case 1: - ret = loongarch_eiointc_readb(vcpu, eiointc, addr, len, val); + *(long *)val = (s8)data; break; case 2: - ret = loongarch_eiointc_readw(vcpu, eiointc, addr, len, val); + *(long *)val = (s16)data; break; case 4: - ret = loongarch_eiointc_readl(vcpu, eiointc, addr, len, val); - break; - case 8: - ret = loongarch_eiointc_readq(vcpu, eiointc, addr, len, val); + *(long *)val = (s32)data; break; default: - WARN_ONCE(1, "%s: Abnormal address access: addr 0x%llx, size %d\n", - __func__, addr, len); - } - spin_unlock_irqrestore(&eiointc->lock, flags); - - return ret; -} - -static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu, - struct loongarch_eiointc *s, - gpa_t addr, int len, const void *val) -{ - int index, irq, bits, ret = 0; - u8 cpu; - u8 data, old_data; - u8 coreisr, old_coreisr; - gpa_t offset; - - data = *(u8 *)val; - offset = addr - EIOINTC_BASE; - - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = (offset - EIOINTC_NODETYPE_START); - s->nodetype.reg_u8[index] = data; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - /* - * ipmap cannot be set at runtime, can be set only at the beginning - * of irqchip driver, need not update upper irq level - */ - index = (offset - EIOINTC_IPMAP_START); - s->ipmap.reg_u8[index] = data; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = (offset - EIOINTC_ENABLE_START); - old_data = s->enable.reg_u8[index]; - s->enable.reg_u8[index] = data; - /* - * 1: enable irq. - * update irq when isr is set. - */ - data = s->enable.reg_u8[index] & ~old_data & s->isr.reg_u8[index]; - eiointc_enable_irq(vcpu, s, index, data, 1); - /* - * 0: disable irq. - * update irq when isr is set. - */ - data = ~s->enable.reg_u8[index] & old_data & s->isr.reg_u8[index]; - eiointc_enable_irq(vcpu, s, index, data, 0); - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - /* do not emulate hw bounced irq routing */ - index = offset - EIOINTC_BOUNCE_START; - s->bounce.reg_u8[index] = data; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = (offset - EIOINTC_COREISR_START); - /* use attrs to get current cpu index */ - cpu = vcpu->vcpu_id; - coreisr = data; - old_coreisr = s->coreisr.reg_u8[cpu][index]; - /* write 1 to clear interrupt */ - s->coreisr.reg_u8[cpu][index] = old_coreisr & ~coreisr; - coreisr &= old_coreisr; - bits = sizeof(data) * 8; - irq = find_first_bit((void *)&coreisr, bits); - while (irq < bits) { - eiointc_update_irq(s, irq + index * bits, 0); - bitmap_clear((void *)&coreisr, irq, 1); - irq = find_first_bit((void *)&coreisr, bits); - } - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - irq = offset - EIOINTC_COREMAP_START; - index = irq; - s->coremap.reg_u8[index] = data; - eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - -static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, - struct loongarch_eiointc *s, - gpa_t addr, int len, const void *val) -{ - int i, index, irq, bits, ret = 0; - u8 cpu; - u16 data, old_data; - u16 coreisr, old_coreisr; - gpa_t offset; - - data = *(u16 *)val; - offset = addr - EIOINTC_BASE; - - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = (offset - EIOINTC_NODETYPE_START) >> 1; - s->nodetype.reg_u16[index] = data; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - /* - * ipmap cannot be set at runtime, can be set only at the beginning - * of irqchip driver, need not update upper irq level - */ - index = (offset - EIOINTC_IPMAP_START) >> 1; - s->ipmap.reg_u16[index] = data; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = (offset - EIOINTC_ENABLE_START) >> 1; - old_data = s->enable.reg_u16[index]; - s->enable.reg_u16[index] = data; - /* - * 1: enable irq. - * update irq when isr is set. - */ - data = s->enable.reg_u16[index] & ~old_data & s->isr.reg_u16[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 1); - } - /* - * 0: disable irq. - * update irq when isr is set. - */ - data = ~s->enable.reg_u16[index] & old_data & s->isr.reg_u16[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 0); - } - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - /* do not emulate hw bounced irq routing */ - index = (offset - EIOINTC_BOUNCE_START) >> 1; - s->bounce.reg_u16[index] = data; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = (offset - EIOINTC_COREISR_START) >> 1; - /* use attrs to get current cpu index */ - cpu = vcpu->vcpu_id; - coreisr = data; - old_coreisr = s->coreisr.reg_u16[cpu][index]; - /* write 1 to clear interrupt */ - s->coreisr.reg_u16[cpu][index] = old_coreisr & ~coreisr; - coreisr &= old_coreisr; - bits = sizeof(data) * 8; - irq = find_first_bit((void *)&coreisr, bits); - while (irq < bits) { - eiointc_update_irq(s, irq + index * bits, 0); - bitmap_clear((void *)&coreisr, irq, 1); - irq = find_first_bit((void *)&coreisr, bits); - } - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - irq = offset - EIOINTC_COREMAP_START; - index = irq >> 1; - s->coremap.reg_u16[index] = data; - eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); - break; - default: - ret = -EINVAL; + *(long *)val = (long)data; break; } - return ret; + return 0; } -static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, +static int loongarch_eiointc_write(struct kvm_vcpu *vcpu, struct loongarch_eiointc *s, - gpa_t addr, int len, const void *val) + gpa_t addr, u64 value, u64 field_mask) { - int i, index, irq, bits, ret = 0; + int index, irq, ret = 0; u8 cpu; - u32 data, old_data; - u32 coreisr, old_coreisr; + u64 data, old, mask; gpa_t offset; - data = *(u32 *)val; - offset = addr - EIOINTC_BASE; + offset = addr & 7; + mask = field_mask << (offset * 8); + data = (value & field_mask) << (offset * 8); - switch (offset) { - case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: - index = (offset - EIOINTC_NODETYPE_START) >> 2; - s->nodetype.reg_u32[index] = data; - break; - case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: - /* - * ipmap cannot be set at runtime, can be set only at the beginning - * of irqchip driver, need not update upper irq level - */ - index = (offset - EIOINTC_IPMAP_START) >> 2; - s->ipmap.reg_u32[index] = data; - break; - case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: - index = (offset - EIOINTC_ENABLE_START) >> 2; - old_data = s->enable.reg_u32[index]; - s->enable.reg_u32[index] = data; - /* - * 1: enable irq. - * update irq when isr is set. - */ - data = s->enable.reg_u32[index] & ~old_data & s->isr.reg_u32[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 1); - } - /* - * 0: disable irq. - * update irq when isr is set. - */ - data = ~s->enable.reg_u32[index] & old_data & s->isr.reg_u32[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 0); - } - break; - case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: - /* do not emulate hw bounced irq routing */ - index = (offset - EIOINTC_BOUNCE_START) >> 2; - s->bounce.reg_u32[index] = data; - break; - case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: - index = (offset - EIOINTC_COREISR_START) >> 2; - /* use attrs to get current cpu index */ - cpu = vcpu->vcpu_id; - coreisr = data; - old_coreisr = s->coreisr.reg_u32[cpu][index]; - /* write 1 to clear interrupt */ - s->coreisr.reg_u32[cpu][index] = old_coreisr & ~coreisr; - coreisr &= old_coreisr; - bits = sizeof(data) * 8; - irq = find_first_bit((void *)&coreisr, bits); - while (irq < bits) { - eiointc_update_irq(s, irq + index * bits, 0); - bitmap_clear((void *)&coreisr, irq, 1); - irq = find_first_bit((void *)&coreisr, bits); - } - break; - case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - irq = offset - EIOINTC_COREMAP_START; - index = irq >> 2; - s->coremap.reg_u32[index] = data; - eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); - break; - default: - ret = -EINVAL; - break; - } - - return ret; -} - -static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, - struct loongarch_eiointc *s, - gpa_t addr, int len, const void *val) -{ - int i, index, irq, bits, ret = 0; - u8 cpu; - u64 data, old_data; - u64 coreisr, old_coreisr; - gpa_t offset; - - data = *(u64 *)val; + addr -= offset; offset = addr - EIOINTC_BASE; switch (offset) { case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: index = (offset - EIOINTC_NODETYPE_START) >> 3; - s->nodetype.reg_u64[index] = data; + old = s->nodetype.reg_u64[index]; + s->nodetype.reg_u64[index] = (old & ~mask) | data; break; case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: /* * ipmap cannot be set at runtime, can be set only at the beginning * of irqchip driver, need not update upper irq level */ - index = (offset - EIOINTC_IPMAP_START) >> 3; - s->ipmap.reg_u64 = data; + old = s->ipmap.reg_u64; + s->ipmap.reg_u64 = (old & ~mask) | data; break; case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: index = (offset - EIOINTC_ENABLE_START) >> 3; - old_data = s->enable.reg_u64[index]; - s->enable.reg_u64[index] = data; + old = s->enable.reg_u64[index]; + s->enable.reg_u64[index] = (old & ~mask) | data; /* * 1: enable irq. * update irq when isr is set. */ - data = s->enable.reg_u64[index] & ~old_data & s->isr.reg_u64[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 1); + data = s->enable.reg_u64[index] & ~old & s->isr.reg_u64[index]; + while (data) { + irq = __ffs(data); + eiointc_update_irq(s, irq + index * 64, 1); + data &= ~BIT_ULL(irq); } /* * 0: disable irq. * update irq when isr is set. */ - data = ~s->enable.reg_u64[index] & old_data & s->isr.reg_u64[index]; - for (i = 0; i < sizeof(data); i++) { - u8 mask = (data >> (i * 8)) & 0xff; - eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 0); + data = ~s->enable.reg_u64[index] & old & s->isr.reg_u64[index]; + while (data) { + irq = __ffs(data); + eiointc_update_irq(s, irq + index * 64, 0); + data &= ~BIT_ULL(irq); } break; case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: /* do not emulate hw bounced irq routing */ index = (offset - EIOINTC_BOUNCE_START) >> 3; - s->bounce.reg_u64[index] = data; + old = s->bounce.reg_u64[index]; + s->bounce.reg_u64[index] = (old & ~mask) | data; break; case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: index = (offset - EIOINTC_COREISR_START) >> 3; /* use attrs to get current cpu index */ cpu = vcpu->vcpu_id; - coreisr = data; - old_coreisr = s->coreisr.reg_u64[cpu][index]; + old = s->coreisr.reg_u64[cpu][index]; /* write 1 to clear interrupt */ - s->coreisr.reg_u64[cpu][index] = old_coreisr & ~coreisr; - coreisr &= old_coreisr; - bits = sizeof(data) * 8; - irq = find_first_bit((void *)&coreisr, bits); - while (irq < bits) { - eiointc_update_irq(s, irq + index * bits, 0); - bitmap_clear((void *)&coreisr, irq, 1); - irq = find_first_bit((void *)&coreisr, bits); + s->coreisr.reg_u64[cpu][index] = old & ~data; + data &= old; + while (data) { + irq = __ffs(data); + eiointc_update_irq(s, irq + index * 64, 0); + data &= ~BIT_ULL(irq); } break; case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: - irq = offset - EIOINTC_COREMAP_START; - index = irq >> 3; - s->coremap.reg_u64[index] = data; - eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); + index = (offset - EIOINTC_COREMAP_START) >> 3; + old = s->coremap.reg_u64[index]; + s->coremap.reg_u64[index] = (old & ~mask) | data; + data = s->coremap.reg_u64[index]; + eiointc_update_sw_coremap(s, index * 8, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -684,7 +294,7 @@ static int kvm_eiointc_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, const void *val) { int ret = -EINVAL; - unsigned long flags; + unsigned long flags, value; struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; if (!eiointc) { @@ -697,24 +307,25 @@ static int kvm_eiointc_write(struct kvm_vcpu *vcpu, return -EINVAL; } - vcpu->kvm->stat.eiointc_write_exits++; + vcpu->stat.eiointc_write_exits++; spin_lock_irqsave(&eiointc->lock, flags); switch (len) { case 1: - ret = loongarch_eiointc_writeb(vcpu, eiointc, addr, len, val); + value = *(unsigned char *)val; + ret = loongarch_eiointc_write(vcpu, eiointc, addr, value, 0xFF); break; case 2: - ret = loongarch_eiointc_writew(vcpu, eiointc, addr, len, val); + value = *(unsigned short *)val; + ret = loongarch_eiointc_write(vcpu, eiointc, addr, value, USHRT_MAX); break; case 4: - ret = loongarch_eiointc_writel(vcpu, eiointc, addr, len, val); - break; - case 8: - ret = loongarch_eiointc_writeq(vcpu, eiointc, addr, len, val); + value = *(unsigned int *)val; + ret = loongarch_eiointc_write(vcpu, eiointc, addr, value, UINT_MAX); break; default: - WARN_ONCE(1, "%s: Abnormal address access: addr 0x%llx, size %d\n", - __func__, addr, len); + value = *(unsigned long *)val; + ret = loongarch_eiointc_write(vcpu, eiointc, addr, value, ULONG_MAX); + break; } spin_unlock_irqrestore(&eiointc->lock, flags); @@ -989,7 +600,7 @@ static int kvm_eiointc_create(struct kvm_device *dev, u32 type) { int ret; struct loongarch_eiointc *s; - struct kvm_io_device *device, *device1; + struct kvm_io_device *device; struct kvm *kvm = dev->kvm; /* eiointc has been created */ @@ -1017,10 +628,10 @@ static int kvm_eiointc_create(struct kvm_device *dev, u32 type) return ret; } - device1 = &s->device_vext; - kvm_iodevice_init(device1, &kvm_eiointc_virt_ops); + device = &s->device_vext; + kvm_iodevice_init(device, &kvm_eiointc_virt_ops); ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS, - EIOINTC_VIRT_BASE, EIOINTC_VIRT_SIZE, device1); + EIOINTC_VIRT_BASE, EIOINTC_VIRT_SIZE, device); if (ret < 0) { kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &s->device); kfree(s); diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index fe734dc062ed..e658d5b37c04 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -268,36 +268,16 @@ static int kvm_ipi_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { - int ret; - struct loongarch_ipi *ipi; - - ipi = vcpu->kvm->arch.ipi; - if (!ipi) { - kvm_err("%s: ipi irqchip not valid!\n", __func__); - return -EINVAL; - } - ipi->kvm->stat.ipi_read_exits++; - ret = loongarch_ipi_readl(vcpu, addr, len, val); - - return ret; + vcpu->stat.ipi_read_exits++; + return loongarch_ipi_readl(vcpu, addr, len, val); } static int kvm_ipi_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { - int ret; - struct loongarch_ipi *ipi; - - ipi = vcpu->kvm->arch.ipi; - if (!ipi) { - kvm_err("%s: ipi irqchip not valid!\n", __func__); - return -EINVAL; - } - ipi->kvm->stat.ipi_write_exits++; - ret = loongarch_ipi_writel(vcpu, addr, len, val); - - return ret; + vcpu->stat.ipi_write_exits++; + return loongarch_ipi_writel(vcpu, addr, len, val); } static const struct kvm_io_device_ops kvm_ipi_ops = { diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index 08fce845f668..6f00ffe05c54 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -196,7 +196,7 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu, } /* statistics of pch pic reading */ - vcpu->kvm->stat.pch_pic_read_exits++; + vcpu->stat.pch_pic_read_exits++; ret = loongarch_pch_pic_read(s, addr, len, val); return ret; @@ -303,7 +303,7 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu, } /* statistics of pch pic writing */ - vcpu->kvm->stat.pch_pic_write_exits++; + vcpu->stat.pch_pic_write_exits++; ret = loongarch_pch_pic_write(s, addr, len, val); return ret; diff --git a/arch/loongarch/kvm/interrupt.c b/arch/loongarch/kvm/interrupt.c index 4c3f22de4b40..8462083f0301 100644 --- a/arch/loongarch/kvm/interrupt.c +++ b/arch/loongarch/kvm/interrupt.c @@ -83,28 +83,11 @@ void kvm_deliver_intr(struct kvm_vcpu *vcpu) unsigned long *pending = &vcpu->arch.irq_pending; unsigned long *pending_clr = &vcpu->arch.irq_clear; - if (!(*pending) && !(*pending_clr)) - return; - - if (*pending_clr) { - priority = __ffs(*pending_clr); - while (priority <= INT_IPI) { - kvm_irq_clear(vcpu, priority); - priority = find_next_bit(pending_clr, - BITS_PER_BYTE * sizeof(*pending_clr), - priority + 1); - } - } + for_each_set_bit(priority, pending_clr, INT_IPI + 1) + kvm_irq_clear(vcpu, priority); - if (*pending) { - priority = __ffs(*pending); - while (priority <= INT_IPI) { - kvm_irq_deliver(vcpu, priority); - priority = find_next_bit(pending, - BITS_PER_BYTE * sizeof(*pending), - priority + 1); - } - } + for_each_set_bit(priority, pending, INT_IPI + 1) + kvm_irq_deliver(vcpu, priority); } int kvm_pending_timer(struct kvm_vcpu *vcpu) diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h index 1783397b1bc8..145514dab6d5 100644 --- a/arch/loongarch/kvm/trace.h +++ b/arch/loongarch/kvm/trace.h @@ -46,11 +46,15 @@ DEFINE_EVENT(kvm_transition, kvm_out, /* Further exit reasons */ #define KVM_TRACE_EXIT_IDLE 64 #define KVM_TRACE_EXIT_CACHE 65 +#define KVM_TRACE_EXIT_CPUCFG 66 +#define KVM_TRACE_EXIT_CSR 67 /* Tracepoints for VM exits */ #define kvm_trace_symbol_exit_types \ { KVM_TRACE_EXIT_IDLE, "IDLE" }, \ - { KVM_TRACE_EXIT_CACHE, "CACHE" } + { KVM_TRACE_EXIT_CACHE, "CACHE" }, \ + { KVM_TRACE_EXIT_CPUCFG, "CPUCFG" }, \ + { KVM_TRACE_EXIT_CSR, "CSR" } DECLARE_EVENT_CLASS(kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), @@ -82,6 +86,14 @@ DEFINE_EVENT(kvm_exit, kvm_exit_cache, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason)); +DEFINE_EVENT(kvm_exit, kvm_exit_cpucfg, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), + TP_ARGS(vcpu, reason)); + +DEFINE_EVENT(kvm_exit, kvm_exit_csr, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), + TP_ARGS(vcpu, reason)); + DEFINE_EVENT(kvm_exit, kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason)); diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 5af32ec62cb1..d1b8c50941ca 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -20,7 +20,13 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, idle_exits), STATS_DESC_COUNTER(VCPU, cpucfg_exits), STATS_DESC_COUNTER(VCPU, signal_exits), - STATS_DESC_COUNTER(VCPU, hypercall_exits) + STATS_DESC_COUNTER(VCPU, hypercall_exits), + STATS_DESC_COUNTER(VCPU, ipi_read_exits), + STATS_DESC_COUNTER(VCPU, ipi_write_exits), + STATS_DESC_COUNTER(VCPU, eiointc_read_exits), + STATS_DESC_COUNTER(VCPU, eiointc_write_exits), + STATS_DESC_COUNTER(VCPU, pch_pic_read_exits), + STATS_DESC_COUNTER(VCPU, pch_pic_write_exits) }; const struct kvm_stats_header kvm_vcpu_stats_header = { diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index fae77809048b..ccea3bbd4353 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -11,5 +11,3 @@ obj-$(CONFIG_ARCH_SUPPORTS_INT128) += tishift.o obj-$(CONFIG_CPU_HAS_LSX) += xor_simd.o xor_simd_glue.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o - -obj-$(CONFIG_CRC32_ARCH) += crc32-loongarch.o diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c deleted file mode 100644 index db22c2ec55e2..000000000000 --- a/arch/loongarch/lib/crc32-loongarch.c +++ /dev/null @@ -1,136 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * CRC32 and CRC32C using LoongArch crc* instructions - * - * Module based on mips/crypto/crc32-mips.c - * - * Copyright (C) 2014 Linaro Ltd <yazen.ghannam@linaro.org> - * Copyright (C) 2018 MIPS Tech, LLC - * Copyright (C) 2020-2023 Loongson Technology Corporation Limited - */ - -#include <asm/cpu-features.h> -#include <linux/crc32.h> -#include <linux/export.h> -#include <linux/module.h> -#include <linux/unaligned.h> - -#define _CRC32(crc, value, size, type) \ -do { \ - __asm__ __volatile__( \ - #type ".w." #size ".w" " %0, %1, %0\n\t"\ - : "+r" (crc) \ - : "r" (value) \ - : "memory"); \ -} while (0) - -#define CRC32(crc, value, size) _CRC32(crc, value, size, crc) -#define CRC32C(crc, value, size) _CRC32(crc, value, size, crcc) - -static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32); - -u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) -{ - if (!static_branch_likely(&have_crc32)) - return crc32_le_base(crc, p, len); - - while (len >= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32(crc, value, d); - p += sizeof(u64); - len -= sizeof(u64); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32(crc, value, w); - p += sizeof(u32); - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32(crc, value, b); - } - - return crc; -} -EXPORT_SYMBOL(crc32_le_arch); - -u32 crc32c_arch(u32 crc, const u8 *p, size_t len) -{ - if (!static_branch_likely(&have_crc32)) - return crc32c_base(crc, p, len); - - while (len >= sizeof(u64)) { - u64 value = get_unaligned_le64(p); - - CRC32C(crc, value, d); - p += sizeof(u64); - len -= sizeof(u64); - } - - if (len & sizeof(u32)) { - u32 value = get_unaligned_le32(p); - - CRC32C(crc, value, w); - p += sizeof(u32); - } - - if (len & sizeof(u16)) { - u16 value = get_unaligned_le16(p); - - CRC32C(crc, value, h); - p += sizeof(u16); - } - - if (len & sizeof(u8)) { - u8 value = *p++; - - CRC32C(crc, value, b); - } - - return crc; -} -EXPORT_SYMBOL(crc32c_arch); - -u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) -{ - return crc32_be_base(crc, p, len); -} -EXPORT_SYMBOL(crc32_be_arch); - -static int __init crc32_loongarch_init(void) -{ - if (cpu_has_crc32) - static_branch_enable(&have_crc32); - return 0; -} -subsys_initcall(crc32_loongarch_init); - -static void __exit crc32_loongarch_exit(void) -{ -} -module_exit(crc32_loongarch_exit); - -u32 crc32_optimizations(void) -{ - if (static_key_enabled(&have_crc32)) - return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION; - return 0; -} -EXPORT_SYMBOL(crc32_optimizations); - -MODULE_AUTHOR("Min Zhou <zhoumin@loongson.cn>"); -MODULE_AUTHOR("Huacai Chen <chenhuacai@loongson.cn>"); -MODULE_DESCRIPTION("CRC32 and CRC32C using LoongArch crc* instructions"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c index 99165903908a..f5e910b68229 100644 --- a/arch/loongarch/mm/pageattr.c +++ b/arch/loongarch/mm/pageattr.c @@ -118,7 +118,7 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgp return 0; mmap_write_lock(&init_mm); - ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks); + ret = walk_kernel_page_table_range(start, end, &pageattr_ops, NULL, &masks); mmap_write_unlock(&init_mm); flush_tlb_kernel_range(start, end); diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index fa1500d4aa3e..abfdb6bb5c38 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -4,13 +4,20 @@ * * Copyright (C) 2022 Loongson Technology Corporation Limited */ +#include <linux/memory.h> #include "bpf_jit.h" -#define REG_TCC LOONGARCH_GPR_A6 -#define TCC_SAVED LOONGARCH_GPR_S5 +#define LOONGARCH_MAX_REG_ARGS 8 + +#define LOONGARCH_LONG_JUMP_NINSNS 5 +#define LOONGARCH_LONG_JUMP_NBYTES (LOONGARCH_LONG_JUMP_NINSNS * 4) -#define SAVE_RA BIT(0) -#define SAVE_TCC BIT(1) +#define LOONGARCH_FENTRY_NINSNS 2 +#define LOONGARCH_FENTRY_NBYTES (LOONGARCH_FENTRY_NINSNS * 4) +#define LOONGARCH_BPF_FENTRY_NBYTES (LOONGARCH_LONG_JUMP_NINSNS * 4) + +#define REG_TCC LOONGARCH_GPR_A6 +#define BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack) (round_up(stack, 16) - 80) static const int regmap[] = { /* return value from in-kernel function, and exit value for eBPF program */ @@ -32,32 +39,57 @@ static const int regmap[] = { [BPF_REG_AX] = LOONGARCH_GPR_T0, }; -static void mark_call(struct jit_ctx *ctx) +static void prepare_bpf_tail_call_cnt(struct jit_ctx *ctx, int *store_offset) { - ctx->flags |= SAVE_RA; -} + const struct bpf_prog *prog = ctx->prog; + const bool is_main_prog = !bpf_is_subprog(prog); -static void mark_tail_call(struct jit_ctx *ctx) -{ - ctx->flags |= SAVE_TCC; -} + if (is_main_prog) { + /* + * LOONGARCH_GPR_T3 = MAX_TAIL_CALL_CNT + * if (REG_TCC > T3 ) + * std REG_TCC -> LOONGARCH_GPR_SP + store_offset + * else + * std REG_TCC -> LOONGARCH_GPR_SP + store_offset + * REG_TCC = LOONGARCH_GPR_SP + store_offset + * + * std REG_TCC -> LOONGARCH_GPR_SP + store_offset + * + * The purpose of this code is to first push the TCC into stack, + * and then push the address of TCC into stack. + * In cases where bpf2bpf and tailcall are used in combination, + * the value in REG_TCC may be a count or an address, + * these two cases need to be judged and handled separately. + */ + emit_insn(ctx, addid, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT); + *store_offset -= sizeof(long); -static bool seen_call(struct jit_ctx *ctx) -{ - return (ctx->flags & SAVE_RA); -} + emit_cond_jmp(ctx, BPF_JGT, REG_TCC, LOONGARCH_GPR_T3, 4); -static bool seen_tail_call(struct jit_ctx *ctx) -{ - return (ctx->flags & SAVE_TCC); -} + /* + * If REG_TCC < MAX_TAIL_CALL_CNT, the value in REG_TCC is a count, + * push tcc into stack + */ + emit_insn(ctx, std, REG_TCC, LOONGARCH_GPR_SP, *store_offset); -static u8 tail_call_reg(struct jit_ctx *ctx) -{ - if (seen_call(ctx)) - return TCC_SAVED; + /* Push the address of TCC into the REG_TCC */ + emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_SP, *store_offset); + + emit_uncond_jmp(ctx, 2); + + /* + * If REG_TCC > MAX_TAIL_CALL_CNT, the value in REG_TCC is an address, + * push tcc_ptr into stack + */ + emit_insn(ctx, std, REG_TCC, LOONGARCH_GPR_SP, *store_offset); + } else { + *store_offset -= sizeof(long); + emit_insn(ctx, std, REG_TCC, LOONGARCH_GPR_SP, *store_offset); + } - return REG_TCC; + /* Push tcc_ptr into stack */ + *store_offset -= sizeof(long); + emit_insn(ctx, std, REG_TCC, LOONGARCH_GPR_SP, *store_offset); } /* @@ -80,6 +112,10 @@ static u8 tail_call_reg(struct jit_ctx *ctx) * | $s4 | * +-------------------------+ * | $s5 | + * +-------------------------+ + * | tcc | + * +-------------------------+ + * | tcc_ptr | * +-------------------------+ <--BPF_REG_FP * | prog->aux->stack_depth | * | (optional) | @@ -88,22 +124,32 @@ static u8 tail_call_reg(struct jit_ctx *ctx) */ static void build_prologue(struct jit_ctx *ctx) { - int stack_adjust = 0, store_offset, bpf_stack_adjust; + int i, stack_adjust = 0, store_offset, bpf_stack_adjust; + const struct bpf_prog *prog = ctx->prog; + const bool is_main_prog = !bpf_is_subprog(prog); bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); - /* To store ra, fp, s0, s1, s2, s3, s4 and s5. */ + /* To store ra, fp, s0, s1, s2, s3, s4, s5 */ stack_adjust += sizeof(long) * 8; + /* To store tcc and tcc_ptr */ + stack_adjust += sizeof(long) * 2; + stack_adjust = round_up(stack_adjust, 16); stack_adjust += bpf_stack_adjust; + /* Reserve space for the move_imm + jirl instruction */ + for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) + emit_insn(ctx, nop); + /* - * First instruction initializes the tail call count (TCC). - * On tail call we skip this instruction, and the TCC is - * passed in REG_TCC from the caller. + * First instruction initializes the tail call count (TCC) + * register to zero. On tail call we skip this instruction, + * and the TCC is passed in REG_TCC from the caller. */ - emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT); + if (is_main_prog) + emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_ZERO, 0); emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_adjust); @@ -131,20 +177,13 @@ static void build_prologue(struct jit_ctx *ctx) store_offset -= sizeof(long); emit_insn(ctx, std, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, store_offset); + prepare_bpf_tail_call_cnt(ctx, &store_offset); + emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_adjust); if (bpf_stack_adjust) emit_insn(ctx, addid, regmap[BPF_REG_FP], LOONGARCH_GPR_SP, bpf_stack_adjust); - /* - * Program contains calls and tail calls, so REG_TCC need - * to be saved across calls. - */ - if (seen_tail_call(ctx) && seen_call(ctx)) - move_reg(ctx, TCC_SAVED, REG_TCC); - else - emit_insn(ctx, nop); - ctx->stack_size = stack_adjust; } @@ -177,6 +216,16 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) load_offset -= sizeof(long); emit_insn(ctx, ldd, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, load_offset); + /* + * When push into the stack, follow the order of tcc then tcc_ptr. + * When pop from the stack, first pop tcc_ptr then followed by tcc. + */ + load_offset -= 2 * sizeof(long); + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, load_offset); + + load_offset += sizeof(long); + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, load_offset); + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, stack_adjust); if (!is_tail_call) { @@ -189,7 +238,7 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) * Call the next bpf prog and skip the first instruction * of TCC initialization. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 1); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 6); } } @@ -208,12 +257,10 @@ bool bpf_jit_supports_far_kfunc_call(void) return true; } -/* initialized on the first pass of build_body() */ -static int out_offset = -1; -static int emit_bpf_tail_call(struct jit_ctx *ctx) +static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) { - int off; - u8 tcc = tail_call_reg(ctx); + int off, tc_ninsn = 0; + int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(ctx->stack_size); u8 a1 = LOONGARCH_GPR_A1; u8 a2 = LOONGARCH_GPR_A2; u8 t1 = LOONGARCH_GPR_T1; @@ -222,7 +269,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) const int idx0 = ctx->idx; #define cur_offset (ctx->idx - idx0) -#define jmp_offset (out_offset - (cur_offset)) +#define jmp_offset (tc_ninsn - (cur_offset)) /* * a0: &ctx @@ -232,6 +279,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) * if (index >= array->map.max_entries) * goto out; */ + tc_ninsn = insn ? ctx->offset[insn+1] - ctx->offset[insn] : ctx->offset[0]; off = offsetof(struct bpf_array, map.max_entries); emit_insn(ctx, ldwu, t1, a1, off); /* bgeu $a2, $t1, jmp_offset */ @@ -239,11 +287,15 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) goto toofar; /* - * if (--TCC < 0) - * goto out; + * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) + * goto out; */ - emit_insn(ctx, addid, REG_TCC, tcc, -1); - if (emit_tailcall_jmp(ctx, BPF_JSLT, REG_TCC, LOONGARCH_GPR_ZERO, jmp_offset) < 0) + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off); + emit_insn(ctx, ldd, t3, REG_TCC, 0); + emit_insn(ctx, addid, t3, t3, 1); + emit_insn(ctx, std, t3, REG_TCC, 0); + emit_insn(ctx, addid, t2, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT); + if (emit_tailcall_jmp(ctx, BPF_JSGT, t3, t2, jmp_offset) < 0) goto toofar; /* @@ -263,15 +315,6 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit_insn(ctx, ldd, t3, t2, off); __build_epilogue(ctx, true); - /* out: */ - if (out_offset == -1) - out_offset = cur_offset; - if (cur_offset != out_offset) { - pr_err_once("tail_call out_offset = %d, expected %d!\n", - cur_offset, out_offset); - return -1; - } - return 0; toofar: @@ -463,7 +506,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext u64 func_addr; bool func_addr_fixed, sign_extend; int i = insn - ctx->prog->insnsi; - int ret, jmp_offset; + int ret, jmp_offset, tcc_ptr_off; const u8 code = insn->code; const u8 cond = BPF_OP(code); const u8 t1 = LOONGARCH_GPR_T1; @@ -899,12 +942,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* function call */ case BPF_JMP | BPF_CALL: - mark_call(ctx); ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &func_addr, &func_addr_fixed); if (ret < 0) return ret; + if (insn->src_reg == BPF_PSEUDO_CALL) { + tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(ctx->stack_size); + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off); + } + move_addr(ctx, t1, func_addr); emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); @@ -915,8 +962,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* tail call */ case BPF_JMP | BPF_TAIL_CALL: - mark_tail_call(ctx); - if (emit_bpf_tail_call(ctx) < 0) + if (emit_bpf_tail_call(ctx, i) < 0) return -EINVAL; break; @@ -1180,12 +1226,528 @@ static int validate_code(struct jit_ctx *ctx) return -1; } + return 0; +} + +static int validate_ctx(struct jit_ctx *ctx) +{ + if (validate_code(ctx)) + return -1; + if (WARN_ON_ONCE(ctx->num_exentries != ctx->prog->aux->num_exentries)) return -1; return 0; } +static int emit_jump_and_link(struct jit_ctx *ctx, u8 rd, u64 target) +{ + if (!target) { + pr_err("bpf_jit: jump target address is error\n"); + return -EFAULT; + } + + move_imm(ctx, LOONGARCH_GPR_T1, target, false); + emit_insn(ctx, jirl, rd, LOONGARCH_GPR_T1, 0); + + return 0; +} + +static int emit_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) +{ + int i; + struct jit_ctx ctx; + + ctx.idx = 0; + ctx.image = (union loongarch_instruction *)insns; + + if (!target) { + for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) + emit_insn((&ctx), nop); + return 0; + } + + return emit_jump_and_link(&ctx, is_call ? LOONGARCH_GPR_T0 : LOONGARCH_GPR_ZERO, (u64)target); +} + +static int emit_call(struct jit_ctx *ctx, u64 addr) +{ + return emit_jump_and_link(ctx, LOONGARCH_GPR_RA, addr); +} + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = larch_insn_text_copy(dst, src, len); + mutex_unlock(&text_mutex); + + return ret ? ERR_PTR(-EINVAL) : dst; +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, + void *old_addr, void *new_addr) +{ + int ret; + bool is_call = (poke_type == BPF_MOD_CALL); + u32 old_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; + u32 new_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; + + if (!is_kernel_text((unsigned long)ip) && + !is_bpf_text_address((unsigned long)ip)) + return -ENOTSUPP; + + ret = emit_jump_or_nops(old_addr, ip, old_insns, is_call); + if (ret) + return ret; + + if (memcmp(ip, old_insns, LOONGARCH_LONG_JUMP_NBYTES)) + return -EFAULT; + + ret = emit_jump_or_nops(new_addr, ip, new_insns, is_call); + if (ret) + return ret; + + mutex_lock(&text_mutex); + if (memcmp(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES)) + ret = larch_insn_text_copy(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES); + mutex_unlock(&text_mutex); + + return ret; +} + +int bpf_arch_text_invalidate(void *dst, size_t len) +{ + int i; + int ret = 0; + u32 *inst; + + inst = kvmalloc(len, GFP_KERNEL); + if (!inst) + return -ENOMEM; + + for (i = 0; i < (len / sizeof(u32)); i++) + inst[i] = INSN_BREAK; + + mutex_lock(&text_mutex); + if (larch_insn_text_copy(dst, inst, len)) + ret = -EINVAL; + mutex_unlock(&text_mutex); + + kvfree(inst); + + return ret; +} + +static void store_args(struct jit_ctx *ctx, int nargs, int args_off) +{ + int i; + + for (i = 0; i < nargs; i++) { + emit_insn(ctx, std, LOONGARCH_GPR_A0 + i, LOONGARCH_GPR_FP, -args_off); + args_off -= 8; + } +} + +static void restore_args(struct jit_ctx *ctx, int nargs, int args_off) +{ + int i; + + for (i = 0; i < nargs; i++) { + emit_insn(ctx, ldd, LOONGARCH_GPR_A0 + i, LOONGARCH_GPR_FP, -args_off); + args_off -= 8; + } +} + +static int invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, + int args_off, int retval_off, int run_ctx_off, bool save_ret) +{ + int ret; + u32 *branch; + struct bpf_prog *p = l->link.prog; + int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); + + if (l->cookie) { + move_imm(ctx, LOONGARCH_GPR_T1, l->cookie, false); + emit_insn(ctx, std, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -run_ctx_off + cookie_off); + } else { + emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -run_ctx_off + cookie_off); + } + + /* arg1: prog */ + move_imm(ctx, LOONGARCH_GPR_A0, (const s64)p, false); + /* arg2: &run_ctx */ + emit_insn(ctx, addid, LOONGARCH_GPR_A1, LOONGARCH_GPR_FP, -run_ctx_off); + ret = emit_call(ctx, (const u64)bpf_trampoline_enter(p)); + if (ret) + return ret; + + /* store prog start time */ + move_reg(ctx, LOONGARCH_GPR_S1, LOONGARCH_GPR_A0); + + /* + * if (__bpf_prog_enter(prog) == 0) + * goto skip_exec_of_prog; + */ + branch = (u32 *)ctx->image + ctx->idx; + /* nop reserved for conditional jump */ + emit_insn(ctx, nop); + + /* arg1: &args_off */ + emit_insn(ctx, addid, LOONGARCH_GPR_A0, LOONGARCH_GPR_FP, -args_off); + if (!p->jited) + move_imm(ctx, LOONGARCH_GPR_A1, (const s64)p->insnsi, false); + ret = emit_call(ctx, (const u64)p->bpf_func); + if (ret) + return ret; + + if (save_ret) { + emit_insn(ctx, std, LOONGARCH_GPR_A0, LOONGARCH_GPR_FP, -retval_off); + emit_insn(ctx, std, regmap[BPF_REG_0], LOONGARCH_GPR_FP, -(retval_off - 8)); + } + + /* update branch with beqz */ + if (ctx->image) { + int offset = (void *)(&ctx->image[ctx->idx]) - (void *)branch; + *branch = larch_insn_gen_beq(LOONGARCH_GPR_A0, LOONGARCH_GPR_ZERO, offset); + } + + /* arg1: prog */ + move_imm(ctx, LOONGARCH_GPR_A0, (const s64)p, false); + /* arg2: prog start time */ + move_reg(ctx, LOONGARCH_GPR_A1, LOONGARCH_GPR_S1); + /* arg3: &run_ctx */ + emit_insn(ctx, addid, LOONGARCH_GPR_A2, LOONGARCH_GPR_FP, -run_ctx_off); + ret = emit_call(ctx, (const u64)bpf_trampoline_exit(p)); + + return ret; +} + +static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl, + int args_off, int retval_off, int run_ctx_off, u32 **branches) +{ + int i; + + emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -retval_off); + for (i = 0; i < tl->nr_links; i++) { + invoke_bpf_prog(ctx, tl->links[i], args_off, retval_off, run_ctx_off, true); + emit_insn(ctx, ldd, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -retval_off); + branches[i] = (u32 *)ctx->image + ctx->idx; + emit_insn(ctx, nop); + } +} + +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, jit_fill_hole); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, + const struct btf_func_model *m, struct bpf_tramp_links *tlinks, + void *func_addr, u32 flags) +{ + int i, ret, save_ret; + int stack_size = 0, nargs = 0; + int retval_off, args_off, nargs_off, ip_off, run_ctx_off, sreg_off, tcc_ptr_off; + bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT; + void *orig_call = func_addr; + struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; + struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; + struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; + u32 **branches = NULL; + + if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY)) + return -ENOTSUPP; + + /* + * FP + 8 [ RA to parent func ] return address to parent + * function + * FP + 0 [ FP of parent func ] frame pointer of parent + * function + * FP - 8 [ T0 to traced func ] return address of traced + * function + * FP - 16 [ FP of traced func ] frame pointer of traced + * function + * + * FP - retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or + * BPF_TRAMP_F_RET_FENTRY_RET + * [ argN ] + * [ ... ] + * FP - args_off [ arg1 ] + * + * FP - nargs_off [ regs count ] + * + * FP - ip_off [ traced func ] BPF_TRAMP_F_IP_ARG + * + * FP - run_ctx_off [ bpf_tramp_run_ctx ] + * + * FP - sreg_off [ callee saved reg ] + * + * FP - tcc_ptr_off [ tail_call_cnt_ptr ] + */ + + if (m->nr_args > LOONGARCH_MAX_REG_ARGS) + return -ENOTSUPP; + + if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY)) + return -ENOTSUPP; + + stack_size = 0; + + /* Room of trampoline frame to store return address and frame pointer */ + stack_size += 16; + + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) { + /* Save BPF R0 and A0 */ + stack_size += 16; + retval_off = stack_size; + } + + /* Room of trampoline frame to store args */ + nargs = m->nr_args; + stack_size += nargs * 8; + args_off = stack_size; + + /* Room of trampoline frame to store args number */ + stack_size += 8; + nargs_off = stack_size; + + /* Room of trampoline frame to store ip address */ + if (flags & BPF_TRAMP_F_IP_ARG) { + stack_size += 8; + ip_off = stack_size; + } + + /* Room of trampoline frame to store struct bpf_tramp_run_ctx */ + stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8); + run_ctx_off = stack_size; + + stack_size += 8; + sreg_off = stack_size; + + /* Room of trampoline frame to store tail_call_cnt_ptr */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { + stack_size += 8; + tcc_ptr_off = stack_size; + } + + stack_size = round_up(stack_size, 16); + + if (is_struct_ops) { + /* + * For the trampoline called directly, just handle + * the frame of trampoline. + */ + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_size); + emit_insn(ctx, std, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, stack_size - 8); + emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size - 16); + emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size); + } else { + /* + * For the trampoline called from function entry, + * the frame of traced function and the frame of + * trampoline need to be considered. + */ + /* RA and FP for parent function */ + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -16); + emit_insn(ctx, std, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, 8); + emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, 0); + emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, 16); + + /* RA and FP for traced function */ + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_size); + emit_insn(ctx, std, LOONGARCH_GPR_T0, LOONGARCH_GPR_SP, stack_size - 8); + emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size - 16); + emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size); + } + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_insn(ctx, std, REG_TCC, LOONGARCH_GPR_FP, -tcc_ptr_off); + + /* callee saved register S1 to pass start time */ + emit_insn(ctx, std, LOONGARCH_GPR_S1, LOONGARCH_GPR_FP, -sreg_off); + + /* store ip address of the traced function */ + if (flags & BPF_TRAMP_F_IP_ARG) { + move_imm(ctx, LOONGARCH_GPR_T1, (const s64)func_addr, false); + emit_insn(ctx, std, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -ip_off); + } + + /* store nargs number */ + move_imm(ctx, LOONGARCH_GPR_T1, nargs, false); + emit_insn(ctx, std, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -nargs_off); + + store_args(ctx, nargs, args_off); + + /* To traced function */ + /* Ftrace jump skips 2 NOP instructions */ + if (is_kernel_text((unsigned long)orig_call)) + orig_call += LOONGARCH_FENTRY_NBYTES; + /* Direct jump skips 5 NOP instructions */ + else if (is_bpf_text_address((unsigned long)orig_call)) + orig_call += LOONGARCH_BPF_FENTRY_NBYTES; + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + move_imm(ctx, LOONGARCH_GPR_A0, (const s64)im, false); + ret = emit_call(ctx, (const u64)__bpf_tramp_enter); + if (ret) + return ret; + } + + for (i = 0; i < fentry->nr_links; i++) { + ret = invoke_bpf_prog(ctx, fentry->links[i], args_off, retval_off, + run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET); + if (ret) + return ret; + } + if (fmod_ret->nr_links) { + branches = kcalloc(fmod_ret->nr_links, sizeof(u32 *), GFP_KERNEL); + if (!branches) + return -ENOMEM; + + invoke_bpf_mod_ret(ctx, fmod_ret, args_off, retval_off, run_ctx_off, branches); + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + restore_args(ctx, m->nr_args, args_off); + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_FP, -tcc_ptr_off); + + ret = emit_call(ctx, (const u64)orig_call); + if (ret) + goto out; + emit_insn(ctx, std, LOONGARCH_GPR_A0, LOONGARCH_GPR_FP, -retval_off); + emit_insn(ctx, std, regmap[BPF_REG_0], LOONGARCH_GPR_FP, -(retval_off - 8)); + im->ip_after_call = ctx->ro_image + ctx->idx; + /* Reserve space for the move_imm + jirl instruction */ + for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) + emit_insn(ctx, nop); + } + + for (i = 0; ctx->image && i < fmod_ret->nr_links; i++) { + int offset = (void *)(&ctx->image[ctx->idx]) - (void *)branches[i]; + *branches[i] = larch_insn_gen_bne(LOONGARCH_GPR_T1, LOONGARCH_GPR_ZERO, offset); + } + + for (i = 0; i < fexit->nr_links; i++) { + ret = invoke_bpf_prog(ctx, fexit->links[i], args_off, retval_off, run_ctx_off, false); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = ctx->ro_image + ctx->idx; + move_imm(ctx, LOONGARCH_GPR_A0, (const s64)im, false); + ret = emit_call(ctx, (const u64)__bpf_tramp_exit); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_args(ctx, m->nr_args, args_off); + + if (save_ret) { + emit_insn(ctx, ldd, LOONGARCH_GPR_A0, LOONGARCH_GPR_FP, -retval_off); + emit_insn(ctx, ldd, regmap[BPF_REG_0], LOONGARCH_GPR_FP, -(retval_off - 8)); + } + + emit_insn(ctx, ldd, LOONGARCH_GPR_S1, LOONGARCH_GPR_FP, -sreg_off); + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_FP, -tcc_ptr_off); + + if (is_struct_ops) { + /* trampoline called directly */ + emit_insn(ctx, ldd, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, stack_size - 8); + emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size - 16); + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, stack_size); + + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); + } else { + /* trampoline called from function entry */ + emit_insn(ctx, ldd, LOONGARCH_GPR_T0, LOONGARCH_GPR_SP, stack_size - 8); + emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_size - 16); + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, stack_size); + + emit_insn(ctx, ldd, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, 8); + emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, 0); + emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, 16); + + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* return to parent function */ + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); + else + /* return to traced function */ + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T0, 0); + } + + ret = ctx->idx; +out: + kfree(branches); + + return ret; +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, + void *ro_image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) +{ + int ret, size; + void *image, *tmp; + struct jit_ctx ctx; + + size = ro_image_end - ro_image; + image = kvmalloc(size, GFP_KERNEL); + if (!image) + return -ENOMEM; + + ctx.image = (union loongarch_instruction *)image; + ctx.ro_image = (union loongarch_instruction *)ro_image; + ctx.idx = 0; + + jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image)); + ret = __arch_prepare_bpf_trampoline(&ctx, im, m, tlinks, func_addr, flags); + if (ret > 0 && validate_code(&ctx) < 0) { + ret = -EINVAL; + goto out; + } + + tmp = bpf_arch_text_copy(ro_image, image, size); + if (IS_ERR(tmp)) { + ret = PTR_ERR(tmp); + goto out; + } + + bpf_flush_icache(ro_image, ro_image_end); +out: + kvfree(image); + return ret < 0 ? ret : size; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + int ret; + struct jit_ctx ctx; + struct bpf_tramp_image im; + + ctx.image = NULL; + ctx.idx = 0; + + ret = __arch_prepare_bpf_trampoline(&ctx, &im, m, tlinks, func_addr, flags); + + /* Page align */ + return ret < 0 ? ret : round_up(ret * LOONGARCH_INSN_SIZE, PAGE_SIZE); +} + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { bool tmp_blinded = false, extra_pass = false; @@ -1288,7 +1850,7 @@ skip_init_ctx: build_epilogue(&ctx); /* 3. Extra pass to validate JITed code */ - if (validate_code(&ctx)) { + if (validate_ctx(&ctx)) { bpf_jit_binary_free(header); prog = orig_prog; goto out_offset; @@ -1342,7 +1904,6 @@ out: if (tmp_blinded) bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); - out_offset = -1; return prog; @@ -1354,6 +1915,16 @@ out_free: goto out_offset; } +bool bpf_jit_bypass_spec_v1(void) +{ + return true; +} + +bool bpf_jit_bypass_spec_v4(void) +{ + return true; +} + /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */ bool bpf_jit_supports_subprog_tailcalls(void) { diff --git a/arch/loongarch/net/bpf_jit.h b/arch/loongarch/net/bpf_jit.h index f9c569f53949..5697158fd164 100644 --- a/arch/loongarch/net/bpf_jit.h +++ b/arch/loongarch/net/bpf_jit.h @@ -18,6 +18,7 @@ struct jit_ctx { u32 *offset; int num_exentries; union loongarch_instruction *image; + union loongarch_instruction *ro_image; u32 stack_size; }; @@ -308,3 +309,8 @@ static inline int emit_tailcall_jmp(struct jit_ctx *ctx, u8 cond, enum loongarch return -EINVAL; } + +static inline void bpf_flush_icache(void *start, void *end) +{ + flush_icache_range((unsigned long)start, (unsigned long)end); +} diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index ccd2c5e135c6..d8316f993482 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -36,7 +36,7 @@ endif # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ - $(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared --build-id -T + $(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id -T # # Shared build commands. |