diff options
Diffstat (limited to 'arch/loongarch')
180 files changed, 7999 insertions, 1651 deletions
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index bfa21465d83a..beb8499dd8ed 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -4,7 +4,6 @@ obj-y += net/ obj-y += vdso/ obj-$(CONFIG_KVM) += kvm/ -obj-$(CONFIG_BUILTIN_DTB) += boot/dts/ # for cleaning subdir- += boot diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 929f68926b34..2b8bd27a852f 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -15,11 +15,20 @@ 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 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if CPU_HAS_FPU 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 select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION @@ -55,28 +64,35 @@ config LOONGARCH select ARCH_SUPPORTS_ACPI select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_HUGETLBFS + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_RT select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_NO_INSTR + select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BUILDTIME_TABLE_SORT select COMMON_CLK select CPU_PM + select EDAC_SUPPORT select EFI select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_DEVICES + select GENERIC_CPU_VULNERABILITIES select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY select GENERIC_IOREMAP if !ARCH_IOREMAP + select GENERIC_IRQ_MATRIX_ALLOCATOR select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW @@ -100,10 +116,12 @@ config LOONGARCH select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB if PERF_EVENTS 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_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD select HAVE_ASM_MODVERSIONS select HAVE_CONTEXT_TRACKING_USER select HAVE_C_RECORDMCOUNT @@ -112,16 +130,18 @@ config LOONGARCH select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + 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_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -133,21 +153,25 @@ config LOONGARCH select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES - select HAVE_KVM + select HAVE_LIVEPATCH select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI + select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_PREEMPT_DYNAMIC_KEY select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC select HAVE_RETHOOK select HAVE_RSEQ select HAVE_RUST select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_SETUP_PER_CPU_AREA if NUMA + select HAVE_STACK_VALIDATION if HAVE_OBJTOOL select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_TIF_NOHZ @@ -169,7 +193,6 @@ config LOONGARCH select PCI_QUIRKS select PERF_USE_VMALLOC select RTC_LIB - select SMP select SPARSE_IRQ select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_ARCH_UNALIGN_NO_WARN @@ -178,6 +201,7 @@ config LOONGARCH select TRACE_IRQFLAGS_SUPPORT select USE_PERCPU_NUMA_NODE_ID select USER_STACKTRACE_SUPPORT + select VDSO_GETRANDOM select ZONE_DMA32 config 32BIT @@ -225,16 +249,7 @@ config MACH_LOONGSON64 def_bool 64BIT config FIX_EARLYCON_MEM - def_bool y - -config PAGE_SIZE_4KB - bool - -config PAGE_SIZE_16KB - bool - -config PAGE_SIZE_64KB - bool + def_bool !ARCH_IOREMAP config PGTABLE_2LEVEL bool @@ -261,6 +276,9 @@ config AS_HAS_EXPLICIT_RELOCS config AS_HAS_FCSR_CLASS def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0) +config AS_HAS_THIN_ADD_SUB + def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) || AS_IS_LLVM + config AS_HAS_LSX_EXTENSION def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0) @@ -288,7 +306,7 @@ choice config 4KB_3LEVEL bool "4KB with 3 levels" - select PAGE_SIZE_4KB + select HAVE_PAGE_SIZE_4KB select PGTABLE_3LEVEL help This option selects 4KB page size with 3 level page tables, which @@ -296,7 +314,7 @@ config 4KB_3LEVEL config 4KB_4LEVEL bool "4KB with 4 levels" - select PAGE_SIZE_4KB + select HAVE_PAGE_SIZE_4KB select PGTABLE_4LEVEL help This option selects 4KB page size with 4 level page tables, which @@ -304,7 +322,7 @@ config 4KB_4LEVEL config 16KB_2LEVEL bool "16KB with 2 levels" - select PAGE_SIZE_16KB + select HAVE_PAGE_SIZE_16KB select PGTABLE_2LEVEL help This option selects 16KB page size with 2 level page tables, which @@ -312,7 +330,7 @@ config 16KB_2LEVEL config 16KB_3LEVEL bool "16KB with 3 levels" - select PAGE_SIZE_16KB + select HAVE_PAGE_SIZE_16KB select PGTABLE_3LEVEL help This option selects 16KB page size with 3 level page tables, which @@ -320,7 +338,7 @@ config 16KB_3LEVEL config 64KB_2LEVEL bool "64KB with 2 levels" - select PAGE_SIZE_64KB + select HAVE_PAGE_SIZE_64KB select PGTABLE_2LEVEL help This option selects 64KB page size with 2 level page tables, which @@ -328,7 +346,7 @@ config 64KB_2LEVEL config 64KB_3LEVEL bool "64KB with 3 levels" - select PAGE_SIZE_64KB + select HAVE_PAGE_SIZE_64KB select PGTABLE_3LEVEL help This option selects 64KB page size with 3 level page tables, which @@ -382,6 +400,7 @@ endchoice config BUILTIN_DTB bool "Enable built-in dtb in kernel" depends on OF + select GENERIC_BUILTIN_DTB help Some existing systems do not provide a canonical device tree to the kernel at boot time. Let's provide a device tree table in the @@ -424,6 +443,7 @@ config EFI_STUB config SCHED_SMT bool "SMT scheduler support" + depends on SMP default y help Improves scheduler's performance when there are multiple @@ -469,7 +489,6 @@ config NR_CPUS config NUMA bool "NUMA Support" select SMP - select ACPI_NUMA if ACPI help Say Y to compile the kernel with NUMA (Non-Uniform Memory Access) support. This option improves performance on systems with more @@ -593,16 +612,20 @@ config ARCH_SUPPORTS_KEXEC config ARCH_SUPPORTS_CRASH_DUMP def_bool y +config ARCH_DEFAULT_CRASH_DUMP + def_bool y + config ARCH_SELECTS_CRASH_DUMP def_bool y depends on CRASH_DUMP select RELOCATABLE config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config RELOCATABLE bool "Relocatable kernel" + select ARCH_HAS_RELR help This builds the kernel as a Position Independent Executable (PIE), which retains all relocation metadata required, so as to relocate @@ -634,6 +657,28 @@ config RANDOMIZE_BASE_MAX_OFFSET This is limited by the size of the lower address memory, 256MB. +source "kernel/livepatch/Kconfig" + +config PARAVIRT + bool "Enable paravirtualization code" + depends on AS_HAS_LVZ_EXTENSION + help + This changes the kernel so it can modify itself when it is run + under a hypervisor, potentially improving performance significantly + over full virtualization. However, when run without a hypervisor + the kernel is theoretically slower and slightly larger. + +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + depends on PARAVIRT + help + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + endmenu config ARCH_SELECT_MEMORY_MODEL @@ -684,6 +729,7 @@ config ARCH_HIBERNATION_POSSIBLE source "kernel/power/Kconfig" source "drivers/acpi/Kconfig" +source "drivers/cpufreq/Kconfig" endmenu diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug index 8d36aab53008..8b2ce5b5d43e 100644 --- a/arch/loongarch/Kconfig.debug +++ b/arch/loongarch/Kconfig.debug @@ -26,4 +26,16 @@ config UNWINDER_PROLOGUE Some of the addresses it reports may be incorrect (but better than the Guess unwinder). +config UNWINDER_ORC + bool "ORC unwinder" + depends on HAVE_OBJTOOL + select OBJTOOL + help + This option enables the ORC (Oops Rewind Capability) unwinder for + unwinding kernel stack traces. It uses a custom data format which is + a simplified version of the DWARF Call Frame Information standard. + + Enabling this option will increase the kernel's runtime memory usage + by roughly 2-4MB, depending on your kernel config. + endchoice diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 983aa2b1629a..567bd122a9ee 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -26,6 +26,21 @@ endif 32bit-emul = elf32loongarch 64bit-emul = elf64loongarch +CC_FLAGS_FPU := -mfpu=64 +CC_FLAGS_NO_FPU := -msoft-float + +ifdef CONFIG_UNWINDER_ORC +orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h +orc_hash_sh := $(srctree)/scripts/orc_hash.sh +targets += $(orc_hash_h) +quiet_cmd_orc_hash = GEN $@ + cmd_orc_hash = mkdir -p $(dir $@); \ + $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@ +$(orc_hash_h): $(srctree)/arch/loongarch/include/asm/orc_types.h $(orc_hash_sh) FORCE + $(call if_changed,orc_hash) +archprepare: $(orc_hash_h) +endif + ifdef CONFIG_DYNAMIC_FTRACE KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY CC_FLAGS_FTRACE := -fpatchable-function-entry=2 @@ -44,10 +59,10 @@ endif ifdef CONFIG_64BIT ld-emul = $(64bit-emul) -cflags-y += -mabi=lp64s +cflags-y += -mabi=lp64s -mcmodel=normal endif -cflags-y += -pipe -msoft-float +cflags-y += -pipe $(CC_FLAGS_NO_FPU) LDFLAGS_vmlinux += -static -n -nostdlib # When the assembler supports explicit relocation hint, we must use it. @@ -72,8 +87,6 @@ KBUILD_CFLAGS_KERNEL += $(call cc-option,-mdirect-extern-access) KBUILD_CFLAGS_KERNEL += $(call cc-option,-fdirect-access-external-data) KBUILD_AFLAGS_MODULE += $(call cc-option,-fno-direct-access-external-data) KBUILD_CFLAGS_MODULE += $(call cc-option,-fno-direct-access-external-data) -KBUILD_AFLAGS_MODULE += $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax) -KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax) else cflags-y += $(call cc-option,-mno-explicit-relocs) KBUILD_AFLAGS_KERNEL += -Wa,-mla-global-with-pcrel @@ -82,7 +95,18 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif -KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic +KBUILD_AFLAGS += $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax) +KBUILD_CFLAGS += $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax) +KBUILD_AFLAGS += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub) +KBUILD_CFLAGS += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub) + +ifdef CONFIG_OBJTOOL +KBUILD_CFLAGS += -fno-jump-tables +endif + +KBUILD_RUSTFLAGS += --target=loongarch64-unknown-none-softfloat -Ccode-model=small +KBUILD_RUSTFLAGS_KERNEL += -Zdirect-access-external-data=yes +KBUILD_RUSTFLAGS_MODULE += -Zdirect-access-external-data=no ifeq ($(CONFIG_RELOCATABLE),y) KBUILD_CFLAGS_KERNEL += -fPIE diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile index 747d0c3f6389..15d5e14fe418 100644 --- a/arch/loongarch/boot/dts/Makefile +++ b/arch/loongarch/boot/dts/Makefile @@ -1,5 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb - -obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME)) diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts index 8aefb0c12672..a34734a6c3ce 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts @@ -44,14 +44,14 @@ &gmac0 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; bus_id = <0x0>; }; &gmac1 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; bus_id = <0x1>; }; diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 444779c21034..3b38ff8853a7 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -6,6 +6,7 @@ /dts-v1/; #include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/clock/loongson,ls2k-clk.h> / { #address-cells = <2>; @@ -19,14 +20,15 @@ compatible = "loongson,la264"; device_type = "cpu"; reg = <0x0>; - clocks = <&cpu_clk>; + clocks = <&clk LOONGSON2_NODE_CLK>; }; }; - cpu_clk: cpu-clk { + ref_100m: clock-ref-100m { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <500000000>; + clock-frequency = <100000000>; + clock-output-names = "ref_100m"; }; cpuintc: interrupt-controller { @@ -35,6 +37,28 @@ interrupt-controller; }; + thermal-zones { + cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + thermal-sensors = <&tsensor 0>; + + trips { + cpu-alert { + temperature = <33000>; + hysteresis = <2000>; + type = "active"; + }; + + cpu-crit { + temperature = <85000>; + hysteresis = <5000>; + type = "critical"; + }; + }; + }; + }; + bus@10000000 { compatible = "simple-bus"; ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>, @@ -52,6 +76,54 @@ ranges = <1 0x0 0x0 0x16400000 0x4000>; }; + clk: clock-controller@1fe10400 { + compatible = "loongson,ls2k0500-clk"; + reg = <0x0 0x1fe10400 0x0 0x2c>; + #clock-cells = <1>; + clocks = <&ref_100m>; + clock-names = "ref_100m"; + }; + + dma-controller@1fe10c00 { + compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; + reg = <0 0x1fe10c00 0 0x8>; + interrupt-parent = <&eiointc>; + interrupts = <67>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe10c10 { + compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; + reg = <0 0x1fe10c10 0 0x8>; + interrupt-parent = <&eiointc>; + interrupts = <68>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe10c20 { + compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; + reg = <0 0x1fe10c20 0 0x8>; + interrupt-parent = <&eiointc>; + interrupts = <69>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + + dma-controller@1fe10c30 { + compatible = "loongson,ls2k0500-apbdma", "loongson,ls2k1000-apbdma"; + reg = <0 0x1fe10c30 0 0x8>; + interrupt-parent = <&eiointc>; + interrupts = <70>; + clocks = <&clk LOONGSON2_APB_CLK>; + #dma-cells = <1>; + status = "disabled"; + }; + liointc0: interrupt-controller@1fe11400 { compatible = "loongson,liointc-2.0"; reg = <0x0 0x1fe11400 0x0 0x40>, @@ -139,6 +211,14 @@ status = "disabled"; }; + tsensor: thermal-sensor@1fe11500 { + compatible = "loongson,ls2k0500-thermal", "loongson,ls2k1000-thermal"; + reg = <0x0 0x1fe11500 0x0 0x30>; + interrupt-parent = <&liointc0>; + interrupts = <7 IRQ_TYPE_LEVEL_HIGH>; + #thermal-sensor-cells = <1>; + }; + uart0: serial@1ff40800 { compatible = "ns16550a"; reg = <0x0 0x1ff40800 0x0 0x10>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts index ed4d32434041..23cf26cc3e5f 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts @@ -43,7 +43,7 @@ &gmac0 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy0>; mdio { compatible = "snps,dwmac-mdio"; @@ -58,7 +58,7 @@ &gmac1 { status = "okay"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy1>; mdio { compatible = "snps,dwmac-mdio"; @@ -113,10 +113,6 @@ status = "okay"; }; -&clk { - status = "okay"; -}; - &rtc0 { status = "okay"; }; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index 49a70f8c3cab..8dff2aa52417 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -100,6 +100,13 @@ #size-cells = <2>; dma-coherent; + isa@18000000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18000000 0x4000>; + }; + liointc0: interrupt-controller@1fe01400 { compatible = "loongson,liointc-2.0"; reg = <0x0 0x1fe01400 0x0 0x40>, @@ -152,7 +159,6 @@ #clock-cells = <1>; clocks = <&ref_100m>; clock-names = "ref_100m"; - status = "disabled"; }; gpio0: gpio@1fe00500 { @@ -260,7 +266,7 @@ status = "disabled"; }; - dma-controller@1fe00c20 { + apbdma2: dma-controller@1fe00c20 { compatible = "loongson,ls2k1000-apbdma"; reg = <0x0 0x1fe00c20 0x0 0x8>; interrupt-parent = <&liointc1>; @@ -270,7 +276,7 @@ status = "disabled"; }; - dma-controller@1fe00c30 { + apbdma3: dma-controller@1fe00c30 { compatible = "loongson,ls2k1000-apbdma"; reg = <0x0 0x1fe00c30 0x0 0x8>; interrupt-parent = <&liointc1>; @@ -346,6 +352,19 @@ status = "disabled"; }; + i2s: i2s@1fe2d000 { + compatible = "loongson,ls2k1000-i2s"; + reg = <0 0x1fe2d000 0 0x14>, + <0 0x1fe00438 0 0x8>; + interrupt-parent = <&liointc0>; + interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk LOONGSON2_APB_CLK>; + dmas = <&apbdma2 0>, <&apbdma3 0>; + dma-names = "tx", "rx"; + #sound-dai-cells = <0>; + 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 dca91caf895e..ea9e6985d0e9 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts @@ -61,12 +61,45 @@ &gmac0 { status = "okay"; + + phy-mode = "gmii"; + phy-handle = <&phy0>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <2>; + }; + }; }; &gmac1 { status = "okay"; + + phy-mode = "gmii"; + phy-handle = <&phy1>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy1: ethernet-phy@1 { + reg = <2>; + }; + }; }; &gmac2 { status = "okay"; + + phy-mode = "rgmii-id"; + phy-handle = <&phy2>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy2: ethernet-phy@2 { + reg = <0>; + }; + }; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index a231949b5f55..b4ff55a33e90 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -6,6 +6,7 @@ /dts-v1/; #include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/clock/loongson,ls2k-clk.h> / { #address-cells = <2>; @@ -19,21 +20,22 @@ compatible = "loongson,la364"; device_type = "cpu"; reg = <0x0>; - clocks = <&cpu_clk>; + clocks = <&clk LOONGSON2_NODE_CLK>; }; cpu1: cpu@2 { compatible = "loongson,la364"; device_type = "cpu"; reg = <0x1>; - clocks = <&cpu_clk>; + clocks = <&clk LOONGSON2_NODE_CLK>; }; }; - cpu_clk: cpu-clk { + ref_100m: clock-ref-100m { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <1400000000>; + clock-frequency = <100000000>; + clock-output-names = "ref_100m"; }; cpuintc: interrupt-controller { @@ -42,6 +44,28 @@ interrupt-controller; }; + thermal-zones { + cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + thermal-sensors = <&tsensor 0>; + + trips { + cpu-alert { + temperature = <40000>; + hysteresis = <2000>; + type = "active"; + }; + + cpu-crit { + temperature = <85000>; + hysteresis = <5000>; + type = "critical"; + }; + }; + }; + }; + bus@10000000 { compatible = "simple-bus"; ranges = <0x0 0x10000000 0x0 0x10000000 0x0 0x10000000>, @@ -51,6 +75,21 @@ #address-cells = <2>; #size-cells = <2>; + isa@18400000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18400000 0x4000>; + }; + + clk: clock-controller@10010480 { + compatible = "loongson,ls2k2000-clk"; + reg = <0x0 0x10010480 0x0 0x100>; + #clock-cells = <1>; + clocks = <&ref_100m>; + clock-names = "ref_100m"; + }; + pmc: power-management@100d0000 { compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon"; reg = <0x0 0x100d0000 0x0 0x58>; @@ -73,6 +112,15 @@ }; }; + tsensor: thermal-sensor@1fe01460 { + compatible = "loongson,ls2k2000-thermal"; + reg = <0x0 0x1fe01460 0x0 0x30>, + <0x0 0x1fe0019c 0x0 0x4>; + interrupt-parent = <&liointc>; + interrupts = <7 IRQ_TYPE_LEVEL_HIGH>; + #thermal-sensor-cells = <1>; + }; + liointc: interrupt-controller@1fe01400 { compatible = "loongson,liointc-1.0"; reg = <0x0 0x1fe01400 0x0 0x64>; @@ -109,6 +157,8 @@ msi: msi-controller@1fe01140 { compatible = "loongson,pch-msi-1.0"; reg = <0x0 0x1fe01140 0x0 0x8>; + interrupt-controller; + #interrupt-cells = <1>; msi-controller; loongson,msi-base-vec = <64>; loongson,msi-num-vecs = <192>; @@ -123,6 +173,22 @@ status = "disabled"; }; + i2c@1fe00120 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1fe00120 0x0 0x8>; + interrupt-parent = <&liointc>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + i2c@1fe00130 { + compatible = "loongson,ls2k-i2c"; + reg = <0x0 0x1fe00130 0x0 0x8>; + interrupt-parent = <&liointc>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + uart0: serial@1fe001e0 { compatible = "ns16550a"; reg = <0x0 0x1fe001e0 0x0 0x10>; @@ -140,27 +206,34 @@ #address-cells = <3>; #size-cells = <2>; device_type = "pci"; + msi-parent = <&msi>; bus-range = <0x0 0xff>; - ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>, + ranges = <0x01000000 0x0 0x00008000 0x0 0x18408000 0x0 0x00008000>, <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>; gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; gmac2: ethernet@3,2 { reg = <0x1a00 0x0 0x0 0x0 0x0>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>, + <18 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; @@ -186,9 +259,11 @@ status = "disabled"; }; - hda@7,0 { + i2s@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupts = <58 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <78 IRQ_TYPE_LEVEL_HIGH>, + <79 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "tx", "rx"; interrupt-parent = <&pic>; status = "disabled"; }; diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index f18c2ba871ef..73c77500ac46 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -1,4 +1,5 @@ # CONFIG_LOCALVERSION_AUTO is not set +CONFIG_KERNEL_ZSTD=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_NO_HZ=y @@ -14,6 +15,10 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_IKHEADERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y @@ -66,6 +71,14 @@ CONFIG_ACPI_IPMI=m CONFIG_ACPI_HOTPLUG_CPU=y CONFIG_ACPI_PCI_SLOT=y CONFIG_ACPI_HOTPLUG_MEMORY=y +CONFIG_ACPI_BGRT=y +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y +CONFIG_LOONGSON3_CPUFREQ=m CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_JUMP_LABEL=y @@ -74,14 +87,18 @@ CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y +CONFIG_MODULE_COMPRESS=y +CONFIG_MODULE_COMPRESS_ZSTD=y +CONFIG_MODULE_DECOMPRESS=y CONFIG_BLK_DEV_ZONED=y CONFIG_BLK_DEV_THROTTLING=y -CONFIG_BLK_DEV_THROTTLING_LOW=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_FC_APPID=y CONFIG_BLK_CGROUP_IOCOST=y CONFIG_BLK_CGROUP_IOPRIO=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y CONFIG_BSD_DISKLABEL=y CONFIG_UNIXWARE_DISKLABEL=y @@ -93,11 +110,13 @@ CONFIG_ZPOOL=y CONFIG_ZSWAP=y CONFIG_ZSWAP_COMPRESSOR_DEFAULT_ZSTD=y CONFIG_ZBUD=y -CONFIG_Z3FOLD=y CONFIG_ZSMALLOC=m # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set +CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL is not set +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE is not set CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y @@ -130,13 +149,22 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y +CONFIG_INET_AH=m CONFIG_INET_ESP=m +CONFIG_INET_ESP_OFFLOAD=m +CONFIG_INET_ESPINTCP=y +CONFIG_INET_IPCOMP=m CONFIG_INET_UDP_DIAG=y CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_BBR=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y +CONFIG_INET6_AH=m CONFIG_INET6_ESP=m +CONFIG_INET6_ESP_OFFLOAD=m +CONFIG_INET6_ESPINTCP=y +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_MROUTE=y CONFIG_MPTCP=y CONFIG_NETWORK_PHY_TIMESTAMPING=y @@ -152,6 +180,8 @@ CONFIG_NF_CONNTRACK_PPTP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_INET=y +CONFIG_NFT_CT=m CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -164,6 +194,7 @@ CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m +CONFIG_NFT_FIB_INET=m CONFIG_NFT_SOCKET=m CONFIG_NFT_OSF=m CONFIG_NFT_TPROXY=m @@ -260,6 +291,7 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_TABLES_IPV6=y +CONFIG_NFT_FIB_IPV6=m CONFIG_IP6_NF_IPTABLES=y CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -280,6 +312,7 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NF_CONNTRACK_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -397,7 +430,16 @@ CONFIG_PARPORT_PC=y CONFIG_PARPORT_SERIAL=y CONFIG_PARPORT_PC_FIFO=y CONFIG_ZRAM=m +CONFIG_ZRAM_BACKEND_LZ4=y +CONFIG_ZRAM_BACKEND_LZ4HC=y +CONFIG_ZRAM_BACKEND_ZSTD=y +CONFIG_ZRAM_BACKEND_DEFLATE=y +CONFIG_ZRAM_BACKEND_842=y +CONFIG_ZRAM_BACKEND_LZO=y CONFIG_ZRAM_DEF_COMP_ZSTD=y +CONFIG_ZRAM_WRITEBACK=y +CONFIG_ZRAM_MEMORY_TRACKING=y +CONFIG_ZRAM_MULTI_COMP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m @@ -417,6 +459,9 @@ CONFIG_NVME_TARGET_RDMA=m CONFIG_NVME_TARGET_FC=m CONFIG_NVME_TARGET_TCP=m CONFIG_EEPROM_AT24=m +CONFIG_PVPANIC=y +CONFIG_PVPANIC_MMIO=m +CONFIG_PVPANIC_PCI=m CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y @@ -454,12 +499,10 @@ CONFIG_PATA_ATIIXP=y CONFIG_PATA_PCMCIA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=m -CONFIG_MD_LINEAR=m CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MD_MULTIPATH=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y CONFIG_DM_CRYPT=m @@ -473,6 +516,16 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m +CONFIG_DM_MULTIPATH_IOA=m +CONFIG_DM_INIT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y +CONFIG_DM_VERITY_FEC=y +CONFIG_DM_INTEGRITY=m +CONFIG_DM_ZONED=m +CONFIG_DM_VDO=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -484,6 +537,13 @@ CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=y CONFIG_WIREGUARD=m +CONFIG_IFB=m +CONFIG_NET_TEAM=m +CONFIG_NET_TEAM_MODE_BROADCAST=m +CONFIG_NET_TEAM_MODE_ROUNDROBIN=m +CONFIG_NET_TEAM_MODE_RANDOM=m +CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m +CONFIG_NET_TEAM_MODE_LOADBALANCE=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_IPVLAN=m @@ -550,6 +610,7 @@ CONFIG_NGBE=y CONFIG_TXGBE=y # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set +CONFIG_MOTORCOMM_PHY=y CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -563,12 +624,14 @@ CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m CONFIG_USB_RTL8150=m CONFIG_USB_RTL8152=m +CONFIG_USB_USBNET=m # CONFIG_USB_NET_AX8817X is not set # CONFIG_USB_NET_AX88179_178A is not set CONFIG_USB_NET_CDC_EEM=m CONFIG_USB_NET_HUAWEI_CDC_NCM=m CONFIG_USB_NET_CDC_MBIM=m # CONFIG_USB_NET_NET1080 is not set +CONFIG_USB_NET_RNDIS_HOST=m # CONFIG_USB_BELKIN is not set # CONFIG_USB_ARMLINUX is not set # CONFIG_USB_NET_ZAURUS is not set @@ -577,10 +640,11 @@ CONFIG_ATH9K_HTC=m CONFIG_IWLWIFI=m CONFIG_IWLDVM=m CONFIG_IWLMVM=m -CONFIG_HOSTAP=m CONFIG_MT7601U=m CONFIG_RT2X00=m CONFIG_RT2800USB=m +CONFIG_RTL8180=m +CONFIG_RTL8187=m CONFIG_RTL8192CE=m CONFIG_RTL8192SE=m CONFIG_RTL8192DE=m @@ -590,18 +654,26 @@ CONFIG_RTL8188EE=m CONFIG_RTL8192EE=m CONFIG_RTL8821AE=m CONFIG_RTL8192CU=m +CONFIG_RTL8192DU=m # CONFIG_RTLWIFI_DEBUG is not set CONFIG_RTL8XXXU=m CONFIG_RTW88=m CONFIG_RTW88_8822BE=m +CONFIG_RTW88_8822BU=m CONFIG_RTW88_8822CE=m +CONFIG_RTW88_8822CU=m CONFIG_RTW88_8723DE=m +CONFIG_RTW88_8723DU=m CONFIG_RTW88_8821CE=m +CONFIG_RTW88_8821CU=m CONFIG_RTW89=m +CONFIG_RTW89_8851BE=m CONFIG_RTW89_8852AE=m +CONFIG_RTW89_8852BE=m +CONFIG_RTW89_8852BTE=m CONFIG_RTW89_8852CE=m +CONFIG_RTW89_8922AE=m CONFIG_ZD1211RW=m -CONFIG_USB_NET_RNDIS_WLAN=m CONFIG_USB4_NET=m CONFIG_INPUT_MOUSEDEV=y CONFIG_INPUT_MOUSEDEV_PSAUX=y @@ -634,6 +706,9 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=m CONFIG_I2C_CHARDEV=y CONFIG_I2C_PIIX4=y +CONFIG_I2C_DESIGNWARE_CORE=y +CONFIG_I2C_DESIGNWARE_SLAVE=y +CONFIG_I2C_DESIGNWARE_PCI=y CONFIG_I2C_GPIO=y CONFIG_I2C_LS2X=y CONFIG_SPI=y @@ -710,11 +785,22 @@ CONFIG_SND_HDA_CODEC_CONEXANT=y CONFIG_SND_USB_AUDIO=m CONFIG_SND_SOC=m CONFIG_SND_SOC_LOONGSON_CARD=m +CONFIG_SND_SOC_ES7134=m +CONFIG_SND_SOC_ES7241=m +CONFIG_SND_SOC_ES8311=m +CONFIG_SND_SOC_ES8316=m +CONFIG_SND_SOC_ES8323=m +CONFIG_SND_SOC_ES8326=m +CONFIG_SND_SOC_ES8328_I2C=m +CONFIG_SND_SOC_ES8328_SPI=m +CONFIG_SND_SOC_UDA1334=m +CONFIG_SND_SOC_UDA1342=m CONFIG_SND_VIRTIO=m CONFIG_HIDRAW=y CONFIG_UHID=m CONFIG_HID_A4TECH=m CONFIG_HID_CHERRY=m +CONFIG_HID_ELAN=m CONFIG_HID_LOGITECH=m CONFIG_HID_LOGITECH_DJ=m CONFIG_LOGITECH_FF=y @@ -723,7 +809,11 @@ CONFIG_LOGIG940_FF=y CONFIG_HID_MICROSOFT=m CONFIG_HID_MULTITOUCH=m CONFIG_HID_SUNPLUS=m +CONFIG_HID_WACOM=m CONFIG_USB_HIDDEV=y +CONFIG_I2C_HID_ACPI=m +CONFIG_I2C_HID_OF=m +CONFIG_I2C_HID_OF_ELAN=m CONFIG_USB=y CONFIG_USB_OTG=y CONFIG_USB_MON=y @@ -758,7 +848,7 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y CONFIG_RTC_DRV_LOONGSON=y CONFIG_DMADEVICES=y -CONFIG_LS2X_APB_DMA=y +CONFIG_LOONGSON2_APB_DMA=y CONFIG_UDMABUF=y CONFIG_DMABUF_HEAPS=y CONFIG_DMABUF_HEAPS_SYSTEM=y @@ -811,6 +901,7 @@ CONFIG_NTB_SWITCHTEC=m CONFIG_NTB_PERF=m CONFIG_NTB_TRANSPORT=m CONFIG_PWM=y +CONFIG_GENERIC_PHY=y CONFIG_USB4=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y @@ -834,6 +925,9 @@ CONFIG_F2FS_FS=m CONFIG_F2FS_FS_SECURITY=y CONFIG_F2FS_CHECK_FS=y CONFIG_F2FS_FS_COMPRESSION=y +CONFIG_FS_ENCRYPTION=y +CONFIG_FS_ENCRYPTION_INLINE_CRYPT=y +CONFIG_FS_VERITY=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y @@ -876,23 +970,24 @@ CONFIG_UBIFS_FS=m CONFIG_UBIFS_FS_ADVANCED_COMPR=y CONFIG_CRAMFS=m CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_FILE_DIRECT=y +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y CONFIG_MINIX_FS=m CONFIG_ROMFS_FS=m CONFIG_PSTORE=m -CONFIG_PSTORE_LZO_COMPRESS=m -CONFIG_PSTORE_LZ4_COMPRESS=m -CONFIG_PSTORE_LZ4HC_COMPRESS=m -CONFIG_PSTORE_842_COMPRESS=y -CONFIG_PSTORE_ZSTD_COMPRESS=y -CONFIG_PSTORE_ZSTD_COMPRESS_DEFAULT=y +CONFIG_PSTORE_COMPRESS=y CONFIG_SYSV_FS=m CONFIG_UFS_FS=m CONFIG_EROFS_FS=m CONFIG_EROFS_FS_ZIP_LZMA=y +CONFIG_EROFS_FS_ZIP_DEFLATE=y +CONFIG_EROFS_FS_ZIP_ZSTD=y +CONFIG_EROFS_FS_ONDEMAND=y CONFIG_EROFS_FS_PCPU_KTHREAD=y CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y @@ -937,7 +1032,6 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_LZO=m @@ -948,7 +1042,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_CRYPTO_CRC32_LOONGARCH=m CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_DMA_CMA=y CONFIG_DMA_NUMA_CMA=y @@ -961,3 +1054,4 @@ CONFIG_DEBUG_FS=y CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_PREEMPT is not set # CONFIG_FTRACE is not set +CONFIG_UNWINDER_ORC=y diff --git a/arch/loongarch/crypto/Kconfig b/arch/loongarch/crypto/Kconfig index 200a6e8b43b1..a0270b3e5b30 100644 --- a/arch/loongarch/crypto/Kconfig +++ b/arch/loongarch/crypto/Kconfig @@ -2,13 +2,4 @@ menu "Accelerated Cryptographic Algorithms for CPU (loongarch)" -config CRYPTO_CRC32_LOONGARCH - tristate "CRC32c and CRC32" - select CRC32 - select CRYPTO_HASH - help - CRC32c and CRC32 CRC algorithms - - Architecture: LoongArch with CRC32 instructions - endmenu diff --git a/arch/loongarch/crypto/Makefile b/arch/loongarch/crypto/Makefile index d22613d27ce9..ba83755dde2b 100644 --- a/arch/loongarch/crypto/Makefile +++ b/arch/loongarch/crypto/Makefile @@ -2,5 +2,3 @@ # # Makefile for LoongArch crypto files.. # - -obj-$(CONFIG_CRYPTO_CRC32_LOONGARCH) += crc32-loongarch.o diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c deleted file mode 100644 index a49e507af38c..000000000000 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ /dev/null @@ -1,302 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * crc32.c - 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 <linux/module.h> -#include <crypto/internal/hash.h> - -#include <asm/cpu-features.h> -#include <asm/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 u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - 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); - len -= 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; -} - -static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) -{ - u32 crc = crc_; - - 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); - len -= 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; -} - -#define CHKSUM_BLOCK_SIZE 1 -#define CHKSUM_DIGEST_SIZE 4 - -struct chksum_ctx { - u32 key; -}; - -struct chksum_desc_ctx { - u32 crc; -}; - -static int chksum_init(struct shash_desc *desc) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = mctx->key; - - return 0; -} - -/* - * Setting the seed allows arbitrary accumulators and flexible XOR policy - * If your algorithm starts with ~0, then XOR with ~0 before you set the seed. - */ -static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(tfm); - - if (keylen != sizeof(mctx->key)) - return -EINVAL; - - mctx->key = get_unaligned_le32(key); - - return 0; -} - -static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32_loongarch_hw(ctx->crc, data, length); - return 0; -} - -static int chksumc_update(struct shash_desc *desc, const u8 *data, unsigned int length) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - ctx->crc = crc32c_loongarch_hw(ctx->crc, data, length); - return 0; -} - -static int chksum_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(ctx->crc, out); - return 0; -} - -static int chksumc_final(struct shash_desc *desc, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - put_unaligned_le32(~ctx->crc, out); - return 0; -} - -static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(crc32_loongarch_hw(crc, data, len), out); - return 0; -} - -static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) -{ - put_unaligned_le32(~crc32c_loongarch_hw(crc, data, len), out); - return 0; -} - -static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksum_finup(ctx->crc, data, len, out); -} - -static int chksumc_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) -{ - struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); - - return __chksumc_finup(ctx->crc, data, len, out); -} - -static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksum_finup(mctx->key, data, length, out); -} - -static int chksumc_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) -{ - struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); - - return __chksumc_finup(mctx->key, data, length, out); -} - -static int chksum_cra_init(struct crypto_tfm *tfm) -{ - struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = 0; - return 0; -} - -static int chksumc_cra_init(struct crypto_tfm *tfm) -{ - struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); - - mctx->key = ~0; - return 0; -} - -static struct shash_alg crc32_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksum_update, - .final = chksum_final, - .finup = chksum_finup, - .digest = chksum_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32", - .cra_driver_name = "crc32-loongarch", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksum_cra_init, - } -}; - -static struct shash_alg crc32c_alg = { - .digestsize = CHKSUM_DIGEST_SIZE, - .setkey = chksum_setkey, - .init = chksum_init, - .update = chksumc_update, - .final = chksumc_final, - .finup = chksumc_finup, - .digest = chksumc_digest, - .descsize = sizeof(struct chksum_desc_ctx), - .base = { - .cra_name = "crc32c", - .cra_driver_name = "crc32c-loongarch", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .cra_blocksize = CHKSUM_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct chksum_ctx), - .cra_module = THIS_MODULE, - .cra_init = chksumc_cra_init, - } -}; - -static int __init crc32_mod_init(void) -{ - int err; - - if (!cpu_has(CPU_FEATURE_CRC32)) - return 0; - - err = crypto_register_shash(&crc32_alg); - if (err) - return err; - - err = crypto_register_shash(&crc32c_alg); - if (err) - return err; - - return 0; -} - -static void __exit crc32_mod_exit(void) -{ - if (!cpu_has(CPU_FEATURE_CRC32)) - return; - - crypto_unregister_shash(&crc32_alg); - crypto_unregister_shash(&crc32c_alg); -} - -module_init(crc32_mod_init); -module_exit(crc32_mod_exit); - -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/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 93783fa24f6e..80ddb5edb845 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -1,26 +1,14 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += dma-contiguous.h +syscall-y += syscall_table_64.h +generated-y += orc_hash.h + generic-y += mcs_spinlock.h generic-y += parport.h generic-y += early_ioremap.h generic-y += qrwlock.h -generic-y += rwsem.h -generic-y += segment.h generic-y += user.h -generic-y += stat.h -generic-y += fcntl.h generic-y += ioctl.h -generic-y += ioctls.h -generic-y += mman.h -generic-y += msgbuf.h -generic-y += sembuf.h -generic-y += shmbuf.h +generic-y += mmzone.h generic-y += statfs.h -generic-y += socket.h -generic-y += sockios.h -generic-y += termbits.h -generic-y += poll.h generic-y += param.h -generic-y += posix_types.h -generic-y += resource.h -generic-y += kvm_para.h +generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h index 49e29b29996f..313f66f7913a 100644 --- a/arch/loongarch/include/asm/acpi.h +++ b/arch/loongarch/include/asm/acpi.h @@ -8,6 +8,7 @@ #ifndef _ASM_LOONGARCH_ACPI_H #define _ASM_LOONGARCH_ACPI_H +#include <asm/smp.h> #include <asm/suspend.h> #ifdef CONFIG_ACPI diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index b24437e28c6e..fe198b473f84 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -11,6 +11,7 @@ #define _ASM_ADDRSPACE_H #include <linux/const.h> +#include <linux/sizes.h> #include <asm/loongarch.h> @@ -36,6 +37,10 @@ extern unsigned long vm_map_base; #define UNCACHE_BASE CSR_DMW0_BASE #endif +#ifndef WRITECOMBINE_BASE +#define WRITECOMBINE_BASE CSR_DMW2_BASE +#endif + #define DMW_PABITS 48 #define TO_PHYS_MASK ((1ULL << DMW_PABITS) - 1) diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h index cf8e1a4e7c19..51f224bcfc65 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -6,3 +6,9 @@ #include <asm/page.h> #include <asm/ftrace.h> #include <asm-generic/asm-prototypes.h> + +#ifdef CONFIG_ARCH_SUPPORTS_INT128 +__int128_t __ashlti3(__int128_t a, int b); +__int128_t __ashrti3(__int128_t a, int b); +__int128_t __lshrti3(__int128_t a, int b); +#endif diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index 655db7d7a427..8d7f501b0a12 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -609,6 +609,7 @@ lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 .pushsection ".la_abs", "aw", %progbits + .p2align 3 .dword 766b .dword \sym .popsection diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 99af8b3160a8..c86f0ab922ec 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -15,6 +15,7 @@ #define __LL "ll.w " #define __SC "sc.w " #define __AMADD "amadd.w " +#define __AMOR "amor.w " #define __AMAND_DB "amand_db.w " #define __AMOR_DB "amor_db.w " #define __AMXOR_DB "amxor_db.w " @@ -22,6 +23,7 @@ #define __LL "ll.d " #define __SC "sc.d " #define __AMADD "amadd.d " +#define __AMOR "amor.d " #define __AMAND_DB "amand_db.d " #define __AMOR_DB "amor_db.d " #define __AMXOR_DB "amxor_db.d " diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h index 6d5846dd075c..7657e016233f 100644 --- a/arch/loongarch/include/asm/bootinfo.h +++ b/arch/loongarch/include/asm/bootinfo.h @@ -26,6 +26,10 @@ struct loongson_board_info { #define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG) +/* + * The "core" of cores_per_node and cores_per_package stands for a + * logical core, which means in a SMT system it stands for a thread. + */ struct loongson_system_configuration { int nr_cpus; int nr_nodes; diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h index d4ca3ba25418..f6f254f2c5db 100644 --- a/arch/loongarch/include/asm/bug.h +++ b/arch/loongarch/include/asm/bug.h @@ -4,6 +4,7 @@ #include <asm/break.h> #include <linux/stringify.h> +#include <linux/objtool.h> #ifndef CONFIG_DEBUG_BUGVERBOSE #define _BUGVERBOSE_LOCATION(file, line) @@ -33,24 +34,25 @@ #define ASM_BUG_FLAGS(flags) \ __BUG_ENTRY(flags) \ - break BRK_BUG + break BRK_BUG; #define ASM_BUG() ASM_BUG_FLAGS(0) -#define __BUG_FLAGS(flags) \ - asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags))); +#define __BUG_FLAGS(flags, extra) \ + asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags)) \ + extra); #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(BUGFLAG_WARNING|(flags)); \ + __BUG_FLAGS(BUGFLAG_WARNING|(flags), ANNOTATE_REACHABLE(10001b));\ instrumentation_end(); \ } while (0) #define BUG() \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(0); \ + __BUG_FLAGS(0, ""); \ unreachable(); \ } while (0) diff --git a/arch/loongarch/include/asm/cacheflush.h b/arch/loongarch/include/asm/cacheflush.h index 80bd74106985..f8754d08a31a 100644 --- a/arch/loongarch/include/asm/cacheflush.h +++ b/arch/loongarch/include/asm/cacheflush.h @@ -37,8 +37,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_range local_flush_icache_range #define flush_icache_user_range local_flush_icache_range -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 - #define flush_cache_all() do { } while (0) #define flush_cache_mm(mm) do { } while (0) #define flush_cache_dup_mm(mm) do { } while (0) @@ -47,7 +45,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end); #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) #define flush_icache_user_page(vma, page, addr, len) do { } while (0) -#define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index 2eafe6a6aca8..fc83bb32f9f0 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -51,6 +51,7 @@ #define cpu_has_lbt_mips cpu_opt(LOONGARCH_CPU_LBT_MIPS) #define cpu_has_lbt (cpu_has_lbt_x86|cpu_has_lbt_arm|cpu_has_lbt_mips) #define cpu_has_csr cpu_opt(LOONGARCH_CPU_CSR) +#define cpu_has_iocsr cpu_opt(LOONGARCH_CPU_IOCSR) #define cpu_has_tlb cpu_opt(LOONGARCH_CPU_TLB) #define cpu_has_watch cpu_opt(LOONGARCH_CPU_WATCH) #define cpu_has_vint cpu_opt(LOONGARCH_CPU_VINT) @@ -65,5 +66,7 @@ #define cpu_has_guestid cpu_opt(LOONGARCH_CPU_GUESTID) #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) +#define cpu_has_lspw cpu_opt(LOONGARCH_CPU_LSPW) +#define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h index 900589cb159d..7f5bc0ad9d50 100644 --- a/arch/loongarch/include/asm/cpu-info.h +++ b/arch/loongarch/include/asm/cpu-info.h @@ -57,6 +57,7 @@ struct cpuinfo_loongarch { int global_id; /* physical global thread number */ int vabits; /* Virtual Address size in bits */ int pabits; /* Physical Address size in bits */ + int timerbits; /* Width of arch timer in bits */ unsigned int ksave_mask; /* Usable KSave mask. */ unsigned int watch_dreg_count; /* Number data breakpoints */ unsigned int watch_ireg_count; /* Number instruction breakpoints */ @@ -75,27 +76,6 @@ extern const char *__cpu_full_name[]; #define cpu_family_string() __cpu_family[raw_smp_processor_id()] #define cpu_full_name_string() __cpu_full_name[raw_smp_processor_id()] -struct seq_file; -struct notifier_block; - -extern int register_proc_cpuinfo_notifier(struct notifier_block *nb); -extern int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v); - -#define proc_cpuinfo_notifier(fn, pri) \ -({ \ - static struct notifier_block fn##_nb = { \ - .notifier_call = fn, \ - .priority = pri \ - }; \ - \ - register_proc_cpuinfo_notifier(&fn##_nb); \ -}) - -struct proc_cpuinfo_notifier_args { - struct seq_file *m; - unsigned long n; -}; - static inline bool cpus_are_siblings(int cpua, int cpub) { struct cpuinfo_loongarch *infoa = &cpu_data[cpua]; diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 48b9f7168bcc..98cf4d7b4b0a 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -87,18 +87,21 @@ enum cpu_type_enum { #define CPU_FEATURE_LBT_MIPS 12 /* CPU has MIPS Binary Translation */ #define CPU_FEATURE_TLB 13 /* CPU has TLB */ #define CPU_FEATURE_CSR 14 /* CPU has CSR */ -#define CPU_FEATURE_WATCH 15 /* CPU has watchpoint registers */ -#define CPU_FEATURE_VINT 16 /* CPU has vectored interrupts */ -#define CPU_FEATURE_CSRIPI 17 /* CPU has CSR-IPI */ -#define CPU_FEATURE_EXTIOI 18 /* CPU has EXT-IOI */ -#define CPU_FEATURE_PREFETCH 19 /* CPU has prefetch instructions */ -#define CPU_FEATURE_PMP 20 /* CPU has perfermance counter */ -#define CPU_FEATURE_SCALEFREQ 21 /* CPU supports cpufreq scaling */ -#define CPU_FEATURE_FLATMODE 22 /* CPU has flat mode */ -#define CPU_FEATURE_EIODECODE 23 /* CPU has EXTIOI interrupt pin decode mode */ -#define CPU_FEATURE_GUESTID 24 /* CPU has GuestID feature */ -#define CPU_FEATURE_HYPERVISOR 25 /* CPU has hypervisor (running in VM) */ -#define CPU_FEATURE_PTW 26 /* CPU has hardware page table walker */ +#define CPU_FEATURE_IOCSR 15 /* CPU has IOCSR */ +#define CPU_FEATURE_WATCH 16 /* CPU has watchpoint registers */ +#define CPU_FEATURE_VINT 17 /* CPU has vectored interrupts */ +#define CPU_FEATURE_CSRIPI 18 /* CPU has CSR-IPI */ +#define CPU_FEATURE_EXTIOI 19 /* CPU has EXT-IOI */ +#define CPU_FEATURE_PREFETCH 20 /* CPU has prefetch instructions */ +#define CPU_FEATURE_PMP 21 /* CPU has perfermance counter */ +#define CPU_FEATURE_SCALEFREQ 22 /* CPU supports cpufreq scaling */ +#define CPU_FEATURE_FLATMODE 23 /* CPU has flat mode */ +#define CPU_FEATURE_EIODECODE 24 /* CPU has EXTIOI interrupt pin decode mode */ +#define CPU_FEATURE_GUESTID 25 /* CPU has GuestID feature */ +#define CPU_FEATURE_HYPERVISOR 26 /* CPU has hypervisor (running in VM) */ +#define CPU_FEATURE_PTW 27 /* CPU has hardware page table walker */ +#define CPU_FEATURE_LSPW 28 /* CPU has LSPW (lddir/ldpte instructions) */ +#define CPU_FEATURE_AVECINT 29 /* CPU has AVEC interrupt */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -114,6 +117,7 @@ enum cpu_type_enum { #define LOONGARCH_CPU_LBT_ARM BIT_ULL(CPU_FEATURE_LBT_ARM) #define LOONGARCH_CPU_LBT_MIPS BIT_ULL(CPU_FEATURE_LBT_MIPS) #define LOONGARCH_CPU_TLB BIT_ULL(CPU_FEATURE_TLB) +#define LOONGARCH_CPU_IOCSR BIT_ULL(CPU_FEATURE_IOCSR) #define LOONGARCH_CPU_CSR BIT_ULL(CPU_FEATURE_CSR) #define LOONGARCH_CPU_WATCH BIT_ULL(CPU_FEATURE_WATCH) #define LOONGARCH_CPU_VINT BIT_ULL(CPU_FEATURE_VINT) @@ -127,5 +131,7 @@ enum cpu_type_enum { #define LOONGARCH_CPU_GUESTID BIT_ULL(CPU_FEATURE_GUESTID) #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) +#define LOONGARCH_CPU_LSPW BIT_ULL(CPU_FEATURE_LSPW) +#define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_reserve.h index 218bdbfa527b..a1d9b84b1c7d 100644 --- a/arch/loongarch/include/asm/crash_core.h +++ b/arch/loongarch/include/asm/crash_reserve.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _LOONGARCH_CRASH_CORE_H -#define _LOONGARCH_CRASH_CORE_H +#ifndef _LOONGARCH_CRASH_RESERVE_H +#define _LOONGARCH_CRASH_RESERVE_H #define CRASH_ALIGN SZ_2M diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h deleted file mode 100644 index 75ccd808a2af..000000000000 --- a/arch/loongarch/include/asm/dma-direct.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _LOONGARCH_DMA_DIRECT_H -#define _LOONGARCH_DMA_DIRECT_H - -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr); - -#endif /* _LOONGARCH_DMA_DIRECT_H */ diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h index af74a3fdcad1..c6d20736fd92 100644 --- a/arch/loongarch/include/asm/exception.h +++ b/arch/loongarch/include/asm/exception.h @@ -6,6 +6,8 @@ #include <asm/ptrace.h> #include <linux/kprobes.h> +extern void *exception_table[]; + void show_registers(struct pt_regs *regs); asmlinkage void cache_parity_error(void); diff --git a/arch/loongarch/include/asm/fprobe.h b/arch/loongarch/include/asm/fprobe.h new file mode 100644 index 000000000000..7af3b3126caf --- /dev/null +++ b/arch/loongarch/include/asm/fprobe.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_FPROBE_H +#define _ASM_LOONGARCH_FPROBE_H + +/* + * Explicitly undef ARCH_DEFINE_ENCODE_FPROBE_HEADER, because loongarch does not + * have enough number of fixed MSBs of the address of kernel objects for + * encoding the size of data in fprobe_header. Use 2-entries encoding instead. + */ +#undef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#endif /* _ASM_LOONGARCH_FPROBE_H */ diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h index c2d8962fda00..3177674228f8 100644 --- a/arch/loongarch/include/asm/fpu.h +++ b/arch/loongarch/include/asm/fpu.h @@ -21,6 +21,7 @@ struct sigcontext; +#define kernel_fpu_available() cpu_has_fpu extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index de891c2c83d4..6e0a99763a9a 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -28,7 +28,6 @@ struct dyn_ftrace; struct dyn_arch_ftrace { }; #define ARCH_SUPPORTS_FTRACE_OPS 1 -#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR #define ftrace_init_nop ftrace_init_nop int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); @@ -45,39 +44,28 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent); #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS struct ftrace_ops; -struct ftrace_regs { - struct pt_regs regs; -}; +#include <linux/ftrace_regs.h> static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) { - return &fregs->regs; -} - -static __always_inline unsigned long -ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs) -{ - return instruction_pointer(&fregs->regs); + return &arch_ftrace_regs(fregs)->regs; } static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) { - instruction_pointer_set(&fregs->regs, ip); + instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip); } -#define ftrace_regs_get_argument(fregs, n) \ - regs_get_kernel_argument(&(fregs)->regs, n) -#define ftrace_regs_get_stack_pointer(fregs) \ - kernel_stack_pointer(&(fregs)->regs) -#define ftrace_regs_return_value(fregs) \ - regs_return_value(&(fregs)->regs) -#define ftrace_regs_set_return_value(fregs, ret) \ - regs_set_return_value(&(fregs)->regs, ret) -#define ftrace_override_function_with_return(fregs) \ - override_function_with_return(&(fregs)->regs) -#define ftrace_regs_query_register_offset(name) \ - regs_query_register_offset(name) +#undef ftrace_regs_get_frame_pointer +#define ftrace_regs_get_frame_pointer(fregs) \ + (arch_ftrace_regs(fregs)->regs.regs[22]) + +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]); +} #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -91,7 +79,7 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) } #define arch_ftrace_set_direct_caller(fregs, addr) \ - __arch_ftrace_set_direct_caller(&(fregs)->regs, addr) + __arch_ftrace_set_direct_caller(&arch_ftrace_regs(fregs)->regs, addr) #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #endif @@ -100,26 +88,4 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif /* CONFIG_FUNCTION_TRACER */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* a0 - a1 */ - unsigned long regs[2]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_LOONGARCH_FTRACE_H */ diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h index 0ef3b18f8980..10da8d6961cb 100644 --- a/arch/loongarch/include/asm/hardirq.h +++ b/arch/loongarch/include/asm/hardirq.h @@ -12,11 +12,19 @@ extern void ack_bad_irq(unsigned int irq); #define ack_bad_irq ack_bad_irq -#define NR_IPI 2 +#define NR_IPI 4 + +enum ipi_msg_type { + IPI_RESCHEDULE, + IPI_CALL_FUNCTION, + IPI_IRQ_WORK, + IPI_CLEAR_VECTOR, +}; typedef struct { unsigned int ipi_irqs[NR_IPI]; unsigned int __softirq_pending; + atomic_t message ____cacheline_aligned_in_smp; } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h index aa44b3fe43dd..4dc4b3e04225 100644 --- a/arch/loongarch/include/asm/hugetlb.h +++ b/arch/loongarch/include/asm/hugetlb.h @@ -16,12 +16,7 @@ static inline int prepare_hugepage_range(struct file *file, unsigned long len) { unsigned long task_size = STACK_TOP; - struct hstate *h = hstate_file(file); - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; if (len > task_size) return -ENOMEM; if (task_size - len < addr) @@ -29,12 +24,23 @@ static inline int prepare_hugepage_range(struct file *file, 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) +{ + pte_t clear; + + pte_val(clear) = (unsigned long)invalid_pte_table; + set_pte_at(mm, addr, ptep, clear); +} + #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) + unsigned long addr, pte_t *ptep, + unsigned long sz) { pte_t clear; - pte_t pte = *ptep; + pte_t pte = ptep_get(ptep); pte_val(clear) = (unsigned long)invalid_pte_table; set_pte_at(mm, addr, ptep, clear); @@ -46,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; + unsigned long sz = huge_page_size(hstate_vma(vma)); - pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz); flush_tlb_page(vma, addr); return pte; } @@ -65,7 +72,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t pte, int dirty) { - int changed = !pte_same(*ptep, pte); + int changed = !pte_same(ptep_get(ptep), pte); if (changed) { set_pte_at(vma->vm_mm, addr, ptep, pte); diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 21447fb1efc7..13b2462f3d8c 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -38,8 +38,8 @@ struct arch_hw_breakpoint { * Limits. * Changing these will require modifications to the register accessors. */ -#define LOONGARCH_MAX_BRP 8 -#define LOONGARCH_MAX_WRP 8 +#define LOONGARCH_MAX_BRP 14 +#define LOONGARCH_MAX_WRP 14 /* Virtual debug register bases. */ #define CSR_CFG_ADDR 0 @@ -75,6 +75,8 @@ do { \ #define CSR_MWPC_NUM 0x3f #define CTRL_PLV_ENABLE 0x1e +#define CTRL_PLV0_ENABLE 0x02 +#define CTRL_PLV3_ENABLE 0x10 #define MWPnCFG3_LoadEn 8 #define MWPnCFG3_StoreEn 9 @@ -101,7 +103,7 @@ struct perf_event; struct perf_event_attr; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset); + int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); extern int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, diff --git a/arch/loongarch/include/asm/hw_irq.h b/arch/loongarch/include/asm/hw_irq.h index af4f4e8fbd85..8156ffb67415 100644 --- a/arch/loongarch/include/asm/hw_irq.h +++ b/arch/loongarch/include/asm/hw_irq.h @@ -9,6 +9,8 @@ extern atomic_t irq_err_count; +#define ARCH_IRQ_INIT_FLAGS IRQ_NOPROBE + /* * interrupt-retrigger: NOP for now. This may not be appropriate for all * machines, we'll see ... diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index d8f637f9e400..3089785ca97e 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -12,6 +12,7 @@ #define INSN_NOP 0x03400000 #define INSN_BREAK 0x002a0000 +#define INSN_HVCL 0x002b8000 #define ADDR_IMMMASK_LU52ID 0xFFF0000000000000 #define ADDR_IMMMASK_LU32ID 0x000FFFFF00000000 @@ -67,6 +68,7 @@ enum reg2_op { revhd_op = 0x11, extwh_op = 0x16, extwb_op = 0x17, + cpucfg_op = 0x1b, iocsrrdb_op = 0x19200, iocsrrdh_op = 0x19201, iocsrrdw_op = 0x19202, @@ -530,6 +532,9 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \ DEF_EMIT_REG0I15_FORMAT(break, break_op) +/* like emit_break(imm) but returns a constant expression */ +#define __emit_break(imm) ((u32)((imm) | (break_op << 15))) + #define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ int offset) \ @@ -678,7 +683,17 @@ DEF_EMIT_REG2I16_FORMAT(blt, blt_op) DEF_EMIT_REG2I16_FORMAT(bge, bge_op) DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op) DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op) -DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op) + +static inline void emit_jirl(union loongarch_instruction *insn, + enum loongarch_gpr rd, + enum loongarch_gpr rj, + int offset) +{ + insn->reg2i16_format.opcode = jirl_op; + insn->reg2i16_format.immediate = offset; + insn->reg2i16_format.rd = rd; + insn->reg2i16_format.rj = rj; +} #define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index c486c2341b66..e77a56eaf906 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -14,11 +14,6 @@ #include <asm/pgtable-bits.h> #include <asm/string.h> -/* - * Change "struct page" to physical address. - */ -#define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT) - extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size); extern void __init early_iounmap(void __iomem *addr, unsigned long size); @@ -30,10 +25,16 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long prot_val) { - if (prot_val & _CACHE_CC) + switch (prot_val & _CACHE_MASK) { + case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); - else + case _CACHE_SUC: return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset); + case _CACHE_WUC: + return (void __iomem *)(unsigned long)(WRITECOMBINE_BASE + offset); + default: + return NULL; + } } #define ioremap(offset, size) \ @@ -61,15 +62,22 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, #define mmiowb() wmb() -/* - * String version of I/O memory access operations. - */ -extern void __memset_io(volatile void __iomem *dst, int c, size_t count); -extern void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count); -extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count); -#define memset_io(c, v, l) __memset_io((c), (v), (l)) -#define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l)) -#define memcpy_toio(c, a, l) __memcpy_toio((c), (a), (l)) +#define __io_aw() mmiowb() + +#ifdef CONFIG_KFENCE +#define virt_to_phys(kaddr) \ +({ \ + (likely((unsigned long)kaddr < vm_map_base)) ? __pa((unsigned long)kaddr) : \ + page_to_phys(tlb_virt_to_page((unsigned long)kaddr)) + offset_in_page((unsigned long)kaddr);\ +}) + +#define phys_to_virt(paddr) \ +({ \ + extern char *__kfence_pool; \ + (unlikely(__kfence_pool == NULL)) ? __va((unsigned long)paddr) : \ + page_address(phys_to_page((unsigned long)paddr)) + offset_in_page((unsigned long)paddr);\ +}) +#endif #include <asm-generic/io.h> diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 218b4da0ea90..a0ca84da8541 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -39,11 +39,22 @@ void spurious_interrupt(void); #define NR_IRQS_LEGACY 16 +/* + * 256 Vectors Mapping for AVECINTC: + * + * 0 - 15: Mapping classic IPs, e.g. IP0-12. + * 16 - 255: Mapping vectors for external IRQ. + * + */ +#define NR_VECTORS 256 +#define NR_LEGACY_VECTORS 16 +#define IRQ_MATRIX_BITS NR_VECTORS + #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace void arch_trigger_cpumask_backtrace(const struct cpumask *mask, int exclude_cpu); #define MAX_IO_PICS 2 -#define NR_IRQS (64 + (256 * MAX_IO_PICS)) +#define NR_IRQS (64 + NR_VECTORS * (NR_CPUS + MAX_IO_PICS)) struct acpi_vector_group { int node; @@ -54,6 +65,7 @@ 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 CORES_PER_VEIO_NODE 256 #define LOONGSON_CPU_UART0_VEC 10 /* CPU UART0 */ #define LOONGSON_CPU_THSENS_VEC 14 /* CPU Thsens */ @@ -65,7 +77,7 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS]; #define LOONGSON_LPC_LAST_IRQ (LOONGSON_LPC_IRQ_BASE + 15) #define LOONGSON_CPU_IRQ_BASE 16 -#define LOONGSON_CPU_LAST_IRQ (LOONGSON_CPU_IRQ_BASE + 14) +#define LOONGSON_CPU_LAST_IRQ (LOONGSON_CPU_IRQ_BASE + 15) #define LOONGSON_PCH_IRQ_BASE 64 #define LOONGSON_PCH_ACPI_IRQ (LOONGSON_PCH_IRQ_BASE + 47) @@ -88,20 +100,8 @@ struct acpi_madt_bio_pic; struct acpi_madt_msi_pic; struct acpi_madt_lpc_pic; -int liointc_acpi_init(struct irq_domain *parent, - struct acpi_madt_lio_pic *acpi_liointc); -int eiointc_acpi_init(struct irq_domain *parent, - struct acpi_madt_eio_pic *acpi_eiointc); - -int 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); -int pch_msi_acpi_init(struct irq_domain *parent, - struct acpi_madt_msi_pic *acpi_pchmsi); -int pch_pic_acpi_init(struct irq_domain *parent, - struct acpi_madt_bio_pic *acpi_pchpic); -int find_pch_pic(u32 gsi); +void complete_irq_moving(void); + struct fwnode_handle *get_pch_msi_handle(int pci_segment); extern struct acpi_madt_lio_pic *acpi_liointc; @@ -117,7 +117,16 @@ extern struct fwnode_handle *liointc_handle; extern struct fwnode_handle *pch_lpc_handle; extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS]; -extern irqreturn_t loongson_ipi_interrupt(int irq, void *dev); +static inline int get_percpu_irq(int vector) +{ + struct irq_domain *d; + + d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); + if (d) + return irq_create_mapping(d, vector); + + return -EINVAL; +} #include <asm-generic/irq.h> diff --git a/arch/loongarch/include/asm/irq_work.h b/arch/loongarch/include/asm/irq_work.h new file mode 100644 index 000000000000..d63076e9160d --- /dev/null +++ b/arch/loongarch/include/asm/irq_work.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_IRQ_WORK_H +#define _ASM_LOONGARCH_IRQ_WORK_H + +static inline bool arch_irq_work_has_interrupt(void) +{ + return IS_ENABLED(CONFIG_SMP); +} + +#endif /* _ASM_LOONGARCH_IRQ_WORK_H */ diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 29acfe3de3fa..8a924bd69d19 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -13,18 +13,22 @@ #define JUMP_LABEL_NOP_SIZE 4 -#define JUMP_TABLE_ENTRY \ +/* This macro is also expanded on the Rust side. */ +#define JUMP_TABLE_ENTRY(key, label) \ ".pushsection __jump_table, \"aw\" \n\t" \ ".align 3 \n\t" \ - ".long 1b - ., %l[l_yes] - . \n\t" \ - ".quad %0 - . \n\t" \ + ".long 1b - ., " label " - . \n\t" \ + ".quad " key " - . \n\t" \ ".popsection \n\t" +#define ARCH_STATIC_BRANCH_ASM(key, label) \ + "1: nop \n\t" \ + JUMP_TABLE_ENTRY(key, label) + static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm goto( - "1: nop \n\t" - JUMP_TABLE_ENTRY + ARCH_STATIC_BRANCH_ASM("%0", "%l[l_yes]") : : "i"(&((char *)key)[branch]) : : l_yes); return false; @@ -37,7 +41,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke { asm goto( "1: b %l[l_yes] \n\t" - JUMP_TABLE_ENTRY + JUMP_TABLE_ENTRY("%0", "%l[l_yes]") : : "i"(&((char *)key)[branch]) : : l_yes); return false; diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index cd6084f4e153..7f52bd31b9d4 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -16,7 +16,7 @@ #define XRANGE_SHIFT (48) /* Valid address length */ -#define XRANGE_SHADOW_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) +#define XRANGE_SHADOW_SHIFT min(cpu_vabits, VA_BITS) /* Used for taking out the valid address */ #define XRANGE_SHADOW_MASK GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0) /* One segment whole address space size */ @@ -25,6 +25,7 @@ /* 64-bit segment value. */ #define XKPRANGE_UC_SEG (0x8000) #define XKPRANGE_CC_SEG (0x9000) +#define XKPRANGE_WC_SEG (0xa000) #define XKVRANGE_VC_SEG (0xffff) /* Cached */ @@ -41,20 +42,28 @@ #define XKPRANGE_UC_SHADOW_SIZE (XKPRANGE_UC_SIZE >> KASAN_SHADOW_SCALE_SHIFT) #define XKPRANGE_UC_SHADOW_END (XKPRANGE_UC_KASAN_OFFSET + XKPRANGE_UC_SHADOW_SIZE) +/* WriteCombine */ +#define XKPRANGE_WC_START WRITECOMBINE_BASE +#define XKPRANGE_WC_SIZE XRANGE_SIZE +#define XKPRANGE_WC_KASAN_OFFSET XKPRANGE_UC_SHADOW_END +#define XKPRANGE_WC_SHADOW_SIZE (XKPRANGE_WC_SIZE >> KASAN_SHADOW_SCALE_SHIFT) +#define XKPRANGE_WC_SHADOW_END (XKPRANGE_WC_KASAN_OFFSET + XKPRANGE_WC_SHADOW_SIZE) + /* VMALLOC (Cached or UnCached) */ #define XKVRANGE_VC_START MODULES_VADDR #define XKVRANGE_VC_SIZE round_up(KFENCE_AREA_END - MODULES_VADDR + 1, PGDIR_SIZE) -#define XKVRANGE_VC_KASAN_OFFSET XKPRANGE_UC_SHADOW_END +#define XKVRANGE_VC_KASAN_OFFSET XKPRANGE_WC_SHADOW_END #define XKVRANGE_VC_SHADOW_SIZE (XKVRANGE_VC_SIZE >> KASAN_SHADOW_SCALE_SHIFT) #define XKVRANGE_VC_SHADOW_END (XKVRANGE_VC_KASAN_OFFSET + XKVRANGE_VC_SHADOW_SIZE) /* KAsan shadow memory start right after vmalloc. */ #define KASAN_SHADOW_START round_up(KFENCE_AREA_END, PGDIR_SIZE) #define KASAN_SHADOW_SIZE (XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET) -#define KASAN_SHADOW_END round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) +#define KASAN_SHADOW_END (round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) - 1) #define XKPRANGE_CC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET) #define XKPRANGE_UC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET) +#define XKPRANGE_WC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_WC_KASAN_OFFSET) #define XKVRANGE_VC_SHADOW_OFFSET (KASAN_SHADOW_START + XKVRANGE_VC_KASAN_OFFSET) extern bool kasan_early_stage; diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h index 6c82aea1c993..da9e93024626 100644 --- a/arch/loongarch/include/asm/kfence.h +++ b/arch/loongarch/include/asm/kfence.h @@ -10,12 +10,14 @@ #define _ASM_LOONGARCH_KFENCE_H #include <linux/kfence.h> +#include <linux/vmalloc.h> #include <asm/pgtable.h> #include <asm/tlb.h> static inline bool arch_kfence_init_pool(void) { int err; + char *kaddr, *vaddr; char *kfence_pool = __kfence_pool; struct vm_struct *area; @@ -35,6 +37,14 @@ static inline bool arch_kfence_init_pool(void) return false; } + kaddr = kfence_pool; + vaddr = __kfence_pool; + while (kaddr < kfence_pool + KFENCE_POOL_SIZE) { + set_page_address(virt_to_page(kaddr), vaddr); + kaddr += PAGE_SIZE; + vaddr += PAGE_SIZE; + } + return true; } @@ -43,13 +53,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { pte_t *pte = virt_to_kpte(addr); - if (WARN_ON(!pte) || pte_none(*pte)) + if (WARN_ON(!pte) || pte_none(ptep_get(pte))) return false; if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT))); + set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT))); else - set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT))); + set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT))); preempt_disable(); local_flush_tlb_one(addr); diff --git a/arch/loongarch/include/asm/kvm_csr.h b/arch/loongarch/include/asm/kvm_csr.h index 724ca8b7b401..4a76ce796f1f 100644 --- a/arch/loongarch/include/asm/kvm_csr.h +++ b/arch/loongarch/include/asm/kvm_csr.h @@ -30,6 +30,7 @@ : [val] "+r" (__v) \ : [reg] "i" (csr) \ : "memory"); \ + __v; \ }) #define gcsr_xchg(v, m, csr) \ @@ -181,6 +182,8 @@ __BUILD_GCSR_OP(tlbidx) #define kvm_save_hw_gcsr(csr, gid) (csr->csrs[gid] = gcsr_read(gid)) #define kvm_restore_hw_gcsr(csr, gid) (gcsr_write(csr->csrs[gid], gid)) +#define kvm_read_clear_hw_gcsr(csr, gid) (csr->csrs[gid] = gcsr_write(0, gid)) + int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu); static __always_inline unsigned long kvm_read_sw_gcsr(struct loongarch_csrs *csr, int gid) @@ -208,4 +211,7 @@ static __always_inline void kvm_change_sw_gcsr(struct loongarch_csrs *csr, csr->csrs[gid] |= val & _mask; } +#define KVM_PMU_EVENT_ENABLED (CSR_PERFCTRL_PLV0 | CSR_PERFCTRL_PLV1 | \ + CSR_PERFCTRL_PLV2 | CSR_PERFCTRL_PLV3) + #endif /* __ASM_LOONGARCH_KVM_CSR_H__ */ diff --git a/arch/loongarch/include/asm/kvm_eiointc.h b/arch/loongarch/include/asm/kvm_eiointc.h new file mode 100644 index 000000000000..a3a40aba8acf --- /dev/null +++ b/arch/loongarch/include/asm/kvm_eiointc.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef __ASM_KVM_EIOINTC_H +#define __ASM_KVM_EIOINTC_H + +#include <kvm/iodev.h> + +#define EIOINTC_IRQS 256 +#define EIOINTC_ROUTE_MAX_VCPUS 256 +#define EIOINTC_IRQS_U8_NUMS (EIOINTC_IRQS / 8) +#define EIOINTC_IRQS_U16_NUMS (EIOINTC_IRQS_U8_NUMS / 2) +#define EIOINTC_IRQS_U32_NUMS (EIOINTC_IRQS_U8_NUMS / 4) +#define EIOINTC_IRQS_U64_NUMS (EIOINTC_IRQS_U8_NUMS / 8) +/* map to ipnum per 32 irqs */ +#define EIOINTC_IRQS_NODETYPE_COUNT 16 + +#define EIOINTC_BASE 0x1400 +#define EIOINTC_SIZE 0x900 + +#define EIOINTC_NODETYPE_START 0xa0 +#define EIOINTC_NODETYPE_END 0xbf +#define EIOINTC_IPMAP_START 0xc0 +#define EIOINTC_IPMAP_END 0xc7 +#define EIOINTC_ENABLE_START 0x200 +#define EIOINTC_ENABLE_END 0x21f +#define EIOINTC_BOUNCE_START 0x280 +#define EIOINTC_BOUNCE_END 0x29f +#define EIOINTC_ISR_START 0x300 +#define EIOINTC_ISR_END 0x31f +#define EIOINTC_COREISR_START 0x400 +#define EIOINTC_COREISR_END 0x41f +#define EIOINTC_COREMAP_START 0x800 +#define EIOINTC_COREMAP_END 0x8ff + +#define EIOINTC_VIRT_BASE (0x40000000) +#define EIOINTC_VIRT_SIZE (0x1000) + +#define EIOINTC_VIRT_FEATURES (0x0) +#define EIOINTC_HAS_VIRT_EXTENSION (0) +#define EIOINTC_HAS_ENABLE_OPTION (1) +#define EIOINTC_HAS_INT_ENCODE (2) +#define EIOINTC_HAS_CPU_ENCODE (3) +#define EIOINTC_VIRT_HAS_FEATURES ((1U << EIOINTC_HAS_VIRT_EXTENSION) \ + | (1U << EIOINTC_HAS_ENABLE_OPTION) \ + | (1U << EIOINTC_HAS_INT_ENCODE) \ + | (1U << EIOINTC_HAS_CPU_ENCODE)) +#define EIOINTC_VIRT_CONFIG (0x4) +#define EIOINTC_ENABLE (1) +#define EIOINTC_ENABLE_INT_ENCODE (2) +#define EIOINTC_ENABLE_CPU_ENCODE (3) + +#define LOONGSON_IP_NUM 8 + +struct loongarch_eiointc { + spinlock_t lock; + struct kvm *kvm; + struct kvm_io_device device; + struct kvm_io_device device_vext; + uint32_t num_cpu; + uint32_t features; + uint32_t status; + + /* hardware state */ + union nodetype { + u64 reg_u64[EIOINTC_IRQS_NODETYPE_COUNT / 4]; + u32 reg_u32[EIOINTC_IRQS_NODETYPE_COUNT / 2]; + u16 reg_u16[EIOINTC_IRQS_NODETYPE_COUNT]; + u8 reg_u8[EIOINTC_IRQS_NODETYPE_COUNT * 2]; + } nodetype; + + /* one bit shows the state of one irq */ + union bounce { + u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; + u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; + u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; + u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; + } bounce; + + union isr { + u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; + u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; + u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; + u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; + } isr; + union coreisr { + u64 reg_u64[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U64_NUMS]; + u32 reg_u32[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U32_NUMS]; + u16 reg_u16[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U16_NUMS]; + u8 reg_u8[EIOINTC_ROUTE_MAX_VCPUS][EIOINTC_IRQS_U8_NUMS]; + } coreisr; + union enable { + u64 reg_u64[EIOINTC_IRQS_U64_NUMS]; + u32 reg_u32[EIOINTC_IRQS_U32_NUMS]; + u16 reg_u16[EIOINTC_IRQS_U16_NUMS]; + u8 reg_u8[EIOINTC_IRQS_U8_NUMS]; + } enable; + + /* use one byte to config ipmap for 32 irqs at once */ + union ipmap { + u64 reg_u64; + u32 reg_u32[EIOINTC_IRQS_U32_NUMS / 4]; + u16 reg_u16[EIOINTC_IRQS_U16_NUMS / 4]; + u8 reg_u8[EIOINTC_IRQS_U8_NUMS / 4]; + } ipmap; + /* use one byte to config coremap for one irq */ + union coremap { + u64 reg_u64[EIOINTC_IRQS / 8]; + u32 reg_u32[EIOINTC_IRQS / 4]; + u16 reg_u16[EIOINTC_IRQS / 2]; + u8 reg_u8[EIOINTC_IRQS]; + } coremap; + + DECLARE_BITMAP(sw_coreisr[EIOINTC_ROUTE_MAX_VCPUS][LOONGSON_IP_NUM], EIOINTC_IRQS); + uint8_t sw_coremap[EIOINTC_IRQS]; +}; + +int kvm_loongarch_register_eiointc_device(void); +void eiointc_set_irq(struct loongarch_eiointc *s, int irq, int level); + +#endif /* __ASM_KVM_EIOINTC_H */ diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 2d62f7b0d377..590982cd986e 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -18,23 +18,43 @@ #include <asm/inst.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_ipi.h> +#include <asm/kvm_eiointc.h> +#include <asm/kvm_pch_pic.h> #include <asm/loongarch.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + /* Loongarch KVM register ids */ #define KVM_GET_IOC_CSR_IDX(id) ((id & KVM_CSR_IDX_MASK) >> LOONGARCH_REG_SHIFT) #define KVM_GET_IOC_CPUCFG_IDX(id) ((id & KVM_CPUCFG_IDX_MASK) >> LOONGARCH_REG_SHIFT) #define KVM_MAX_VCPUS 256 #define KVM_MAX_CPUCFG_REGS 21 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 0 #define KVM_HALT_POLL_NS_DEFAULT 500000 +#define KVM_REQ_TLB_FLUSH_GPA KVM_ARCH_REQ(0) +#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(1) +#define KVM_REQ_PMU KVM_ARCH_REQ(2) + +#define KVM_GUESTDBG_SW_BP_MASK \ + (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP) +#define KVM_GUESTDBG_VALID_MASK \ + (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP | KVM_GUESTDBG_SINGLESTEP) + +#define KVM_DIRTY_LOG_MANUAL_CAPS \ + (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | KVM_DIRTY_LOG_INITIALLY_SET) 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 { @@ -43,6 +63,7 @@ struct kvm_vcpu_stat { u64 idle_exits; u64 cpucfg_exits; u64 signal_exits; + u64 hypercall_exits; }; #define KVM_MEM_HUGEPAGE_CAPABLE (1UL << 0) @@ -51,9 +72,13 @@ struct kvm_arch_memory_slot { unsigned long flags; }; +#define HOST_MAX_PMNUM 16 struct kvm_context { unsigned long vpid_cache; struct kvm_vcpu *last_vcpu; + /* Host PMU CSR */ + u64 perf_ctrl[HOST_MAX_PMNUM]; + u64 perf_cntr[HOST_MAX_PMNUM]; }; struct kvm_world_switch { @@ -64,6 +89,31 @@ struct kvm_world_switch { #define MAX_PGTABLE_LEVELS 4 +/* + * Physical CPUID is used for interrupt routing, there are different + * definitions about physical cpuid on different hardwares. + * + * For LOONGARCH_CSR_CPUID register, max CPUID size if 512 + * For IPI hardware, max destination CPUID size 1024 + * For eiointc interrupt controller, max destination CPUID size is 256 + * For msgint interrupt controller, max supported CPUID size is 65536 + * + * Currently max CPUID is defined as 256 for KVM hypervisor, in future + * it will be expanded to 4096, including 16 packages at most. And every + * package supports at most 256 vcpus + */ +#define KVM_MAX_PHYID 256 + +struct kvm_phyid_info { + struct kvm_vcpu *vcpu; + bool enabled; +}; + +struct kvm_phyid_map { + int max_phyid; + struct kvm_phyid_info phys_map[KVM_MAX_PHYID]; +}; + struct kvm_arch { /* Guest physical mm */ kvm_pte_t *pgd; @@ -71,9 +121,16 @@ struct kvm_arch { unsigned long invalid_ptes[MAX_PGTABLE_LEVELS]; unsigned int pte_shifts[MAX_PGTABLE_LEVELS]; unsigned int root_level; + spinlock_t phyid_map_lock; + struct kvm_phyid_map *phyid_map; + /* Enabled PV features */ + unsigned long pv_features; s64 time_offset; struct kvm_context __percpu *vmcs; + struct loongarch_ipi *ipi; + struct loongarch_eiointc *eiointc; + struct loongarch_pch_pic *pch_pic; }; #define CSR_MAX_NUMS 0x800 @@ -97,8 +154,16 @@ enum emulation_result { #define KVM_LARCH_FPU (0x1 << 0) #define KVM_LARCH_LSX (0x1 << 1) #define KVM_LARCH_LASX (0x1 << 2) -#define KVM_LARCH_SWCSR_LATEST (0x1 << 3) -#define KVM_LARCH_HWCSR_USABLE (0x1 << 4) +#define KVM_LARCH_LBT (0x1 << 3) +#define KVM_LARCH_PMU (0x1 << 4) +#define KVM_LARCH_SWCSR_LATEST (0x1 << 5) +#define KVM_LARCH_HWCSR_USABLE (0x1 << 6) + +#define LOONGARCH_PV_FEAT_UPDATED BIT_ULL(63) +#define LOONGARCH_PV_FEAT_MASK (BIT(KVM_FEATURE_IPI) | \ + BIT(KVM_FEATURE_STEAL_TIME) | \ + BIT(KVM_FEATURE_USER_HCALL) | \ + BIT(KVM_FEATURE_VIRT_EXTIOI)) struct kvm_vcpu_arch { /* @@ -132,10 +197,14 @@ struct kvm_vcpu_arch { /* FPU state */ struct loongarch_fpu fpu FPU_ALIGN; + struct loongarch_lbt lbt; /* CSR state */ struct loongarch_csrs *csr; + /* Guest max PMU CSR id */ + int max_pmu_csrid; + /* GPR used as IO source/target */ u32 io_gpr; @@ -157,6 +226,7 @@ struct kvm_vcpu_arch { /* vcpu's vpid */ u64 vpid; + gpa_t flush_gpa; /* Frequency of stable timer in Hz */ u64 timer_mhz; @@ -166,8 +236,17 @@ struct kvm_vcpu_arch { int last_sched_cpu; /* mp state */ struct kvm_mp_state mp_state; + /* ipi state */ + struct ipi_state ipi_state; /* cpucfg */ u32 cpucfg[KVM_MAX_CPUCFG_REGS]; + + /* paravirt steal time */ + struct { + u64 guest_addr; + u64 last_steal; + struct gfn_to_hva_cache cache; + } st; }; static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg) @@ -195,6 +274,21 @@ static inline bool kvm_guest_has_lasx(struct kvm_vcpu_arch *arch) return arch->cpucfg[2] & CPUCFG2_LASX; } +static inline bool kvm_guest_has_lbt(struct kvm_vcpu_arch *arch) +{ + return arch->cpucfg[2] & (CPUCFG2_X86BT | CPUCFG2_ARMBT | CPUCFG2_MIPSBT); +} + +static inline bool kvm_guest_has_pmu(struct kvm_vcpu_arch *arch) +{ + return arch->cpucfg[6] & CPUCFG6_PMP; +} + +static inline int kvm_get_pmu_num(struct kvm_vcpu_arch *arch) +{ + return (arch->cpucfg[6] & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT; +} + /* Debug: dump vcpu state */ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); @@ -203,7 +297,6 @@ void kvm_flush_tlb_all(void); void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa); int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write); -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -229,7 +322,6 @@ static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch) static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} -static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} diff --git a/arch/loongarch/include/asm/kvm_ipi.h b/arch/loongarch/include/asm/kvm_ipi.h new file mode 100644 index 000000000000..060163dfb4a3 --- /dev/null +++ b/arch/loongarch/include/asm/kvm_ipi.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef __ASM_KVM_IPI_H +#define __ASM_KVM_IPI_H + +#include <kvm/iodev.h> + +#define LARCH_INT_IPI 12 + +struct loongarch_ipi { + spinlock_t lock; + struct kvm *kvm; + struct kvm_io_device device; +}; + +struct ipi_state { + spinlock_t lock; + uint32_t status; + uint32_t en; + uint32_t set; + uint32_t clear; + uint64_t buf[4]; +}; + +#define IOCSR_IPI_BASE 0x1000 +#define IOCSR_IPI_SIZE 0x160 + +#define IOCSR_IPI_STATUS 0x000 +#define IOCSR_IPI_EN 0x004 +#define IOCSR_IPI_SET 0x008 +#define IOCSR_IPI_CLEAR 0x00c +#define IOCSR_IPI_BUF_20 0x020 +#define IOCSR_IPI_BUF_28 0x028 +#define IOCSR_IPI_BUF_30 0x030 +#define IOCSR_IPI_BUF_38 0x038 +#define IOCSR_IPI_SEND 0x040 +#define IOCSR_MAIL_SEND 0x048 +#define IOCSR_ANY_SEND 0x158 + +int kvm_loongarch_register_ipi_device(void); + +#endif diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h new file mode 100644 index 000000000000..3e4b397f423f --- /dev/null +++ b/arch/loongarch/include/asm/kvm_para.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_KVM_PARA_H +#define _ASM_LOONGARCH_KVM_PARA_H + +#include <uapi/asm/kvm_para.h> + +/* + * Hypercall code field + */ +#define HYPERVISOR_KVM 1 +#define HYPERVISOR_VENDOR_SHIFT 8 +#define HYPERCALL_ENCODE(vendor, code) ((vendor << HYPERVISOR_VENDOR_SHIFT) + code) + +#define KVM_HCALL_CODE_SERVICE 0 +#define KVM_HCALL_CODE_SWDBG 1 +#define KVM_HCALL_CODE_USER_SERVICE 2 + +#define KVM_HCALL_SERVICE HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SERVICE) +#define KVM_HCALL_FUNC_IPI 1 +#define KVM_HCALL_FUNC_NOTIFY 2 + +#define KVM_HCALL_SWDBG HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SWDBG) + +#define KVM_HCALL_USER_SERVICE HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_USER_SERVICE) + +/* + * LoongArch hypercall return code + */ +#define KVM_HCALL_SUCCESS 0 +#define KVM_HCALL_INVALID_CODE -1UL +#define KVM_HCALL_INVALID_PARAMETER -2UL + +#define KVM_STEAL_PHYS_VALID BIT_ULL(0) +#define KVM_STEAL_PHYS_MASK GENMASK_ULL(63, 6) + +struct kvm_steal_time { + __u64 steal; + __u32 version; + __u32 flags; + __u32 pad[12]; +}; + +/* + * Hypercall interface for KVM hypervisor + * + * a0: function identifier + * a1-a5: args + * Return value will be placed in a0. + * Up to 5 arguments are passed in a1, a2, a3, a4, a5. + */ +static __always_inline long kvm_hypercall0(u64 fid) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r" (fun) + : "memory" + ); + + return ret; +} + +static __always_inline long kvm_hypercall1(u64 fid, unsigned long arg0) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + register unsigned long a1 asm("a1") = arg0; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r" (fun), "r" (a1) + : "memory" + ); + + return ret; +} + +static __always_inline long kvm_hypercall2(u64 fid, + unsigned long arg0, unsigned long arg1) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + register unsigned long a1 asm("a1") = arg0; + register unsigned long a2 asm("a2") = arg1; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r" (fun), "r" (a1), "r" (a2) + : "memory" + ); + + return ret; +} + +static __always_inline long kvm_hypercall3(u64 fid, + unsigned long arg0, unsigned long arg1, unsigned long arg2) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + register unsigned long a1 asm("a1") = arg0; + register unsigned long a2 asm("a2") = arg1; + register unsigned long a3 asm("a3") = arg2; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r" (fun), "r" (a1), "r" (a2), "r" (a3) + : "memory" + ); + + return ret; +} + +static __always_inline long kvm_hypercall4(u64 fid, + unsigned long arg0, unsigned long arg1, + unsigned long arg2, unsigned long arg3) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + register unsigned long a1 asm("a1") = arg0; + register unsigned long a2 asm("a2") = arg1; + register unsigned long a3 asm("a3") = arg2; + register unsigned long a4 asm("a4") = arg3; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4) + : "memory" + ); + + return ret; +} + +static __always_inline long kvm_hypercall5(u64 fid, + unsigned long arg0, unsigned long arg1, + unsigned long arg2, unsigned long arg3, unsigned long arg4) +{ + register long ret asm("a0"); + register unsigned long fun asm("a0") = fid; + register unsigned long a1 asm("a1") = arg0; + register unsigned long a2 asm("a2") = arg1; + register unsigned long a3 asm("a3") = arg2; + register unsigned long a4 asm("a4") = arg3; + register unsigned long a5 asm("a5") = arg4; + + __asm__ __volatile__( + "hvcl "__stringify(KVM_HCALL_SERVICE) + : "=r" (ret) + : "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4), "r" (a5) + : "memory" + ); + + return ret; +} + +#ifdef CONFIG_PARAVIRT +bool kvm_para_available(void); +unsigned int kvm_arch_para_features(void); +#else +static inline bool kvm_para_available(void) +{ + return false; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} +#endif + +static inline unsigned int kvm_arch_para_hints(void) +{ + return 0; +} + +static inline bool kvm_check_and_clear_guest_paused(void) +{ + return false; +} + +#endif /* _ASM_LOONGARCH_KVM_PARA_H */ diff --git a/arch/loongarch/include/asm/kvm_pch_pic.h b/arch/loongarch/include/asm/kvm_pch_pic.h new file mode 100644 index 000000000000..e6df6a4c1c70 --- /dev/null +++ b/arch/loongarch/include/asm/kvm_pch_pic.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef __ASM_KVM_PCH_PIC_H +#define __ASM_KVM_PCH_PIC_H + +#include <kvm/iodev.h> + +#define PCH_PIC_SIZE 0x3e8 + +#define PCH_PIC_INT_ID_START 0x0 +#define PCH_PIC_INT_ID_END 0x7 +#define PCH_PIC_MASK_START 0x20 +#define PCH_PIC_MASK_END 0x27 +#define PCH_PIC_HTMSI_EN_START 0x40 +#define PCH_PIC_HTMSI_EN_END 0x47 +#define PCH_PIC_EDGE_START 0x60 +#define PCH_PIC_EDGE_END 0x67 +#define PCH_PIC_CLEAR_START 0x80 +#define PCH_PIC_CLEAR_END 0x87 +#define PCH_PIC_AUTO_CTRL0_START 0xc0 +#define PCH_PIC_AUTO_CTRL0_END 0xc7 +#define PCH_PIC_AUTO_CTRL1_START 0xe0 +#define PCH_PIC_AUTO_CTRL1_END 0xe7 +#define PCH_PIC_ROUTE_ENTRY_START 0x100 +#define PCH_PIC_ROUTE_ENTRY_END 0x13f +#define PCH_PIC_HTMSI_VEC_START 0x200 +#define PCH_PIC_HTMSI_VEC_END 0x23f +#define PCH_PIC_INT_IRR_START 0x380 +#define PCH_PIC_INT_IRR_END 0x38f +#define PCH_PIC_INT_ISR_START 0x3a0 +#define PCH_PIC_INT_ISR_END 0x3af +#define PCH_PIC_POLARITY_START 0x3e0 +#define PCH_PIC_POLARITY_END 0x3e7 +#define PCH_PIC_INT_ID_VAL 0x7000000UL +#define PCH_PIC_INT_ID_VER 0x1UL + +struct loongarch_pch_pic { + spinlock_t lock; + struct kvm *kvm; + struct kvm_io_device device; + uint64_t mask; /* 1:disable irq, 0:enable irq */ + uint64_t htmsi_en; /* 1:msi */ + uint64_t edge; /* 1:edge triggered, 0:level triggered */ + uint64_t auto_ctrl0; /* only use default value 00b */ + uint64_t auto_ctrl1; /* only use default value 00b */ + uint64_t last_intirr; /* edge detection */ + uint64_t irr; /* interrupt request register */ + uint64_t isr; /* interrupt service register */ + uint64_t polarity; /* 0: high level trigger, 1: low level trigger */ + uint8_t route_entry[64]; /* default value 0, route to int0: eiointc */ + uint8_t htmsi_vector[64]; /* irq route table for routing to eiointc */ + uint64_t pch_pic_base; +}; + +int kvm_loongarch_register_pch_pic_device(void); +void pch_pic_set_irq(struct loongarch_pch_pic *s, int irq, int level); +void pch_msi_set_irq(struct kvm *kvm, int irq, int level); + +#endif /* __ASM_KVM_PCH_PIC_H */ diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h index 0cb4fdb8a9b5..2c349f961bfb 100644 --- a/arch/loongarch/include/asm/kvm_vcpu.h +++ b/arch/loongarch/include/asm/kvm_vcpu.h @@ -43,6 +43,7 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst); int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst); int kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_complete_iocsr_read(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_complete_user_service(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_emu_idle(struct kvm_vcpu *vcpu); int kvm_pending_timer(struct kvm_vcpu *vcpu); int kvm_handle_fault(struct kvm_vcpu *vcpu, int fault); @@ -75,12 +76,18 @@ static inline void kvm_save_lasx(struct loongarch_fpu *fpu) { } static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { } #endif +#ifdef CONFIG_CPU_HAS_LBT +int kvm_own_lbt(struct kvm_vcpu *vcpu); +#else +static inline int kvm_own_lbt(struct kvm_vcpu *vcpu) { return -EINVAL; } +#endif + void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz); -void kvm_reset_timer(struct kvm_vcpu *vcpu); void kvm_save_timer(struct kvm_vcpu *vcpu); void kvm_restore_timer(struct kvm_vcpu *vcpu); int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); +struct kvm_vcpu *kvm_get_vcpu_by_cpuid(struct kvm *kvm, int cpuid); /* * Loongarch KVM guest interrupt handling @@ -109,4 +116,24 @@ static inline int kvm_queue_exception(struct kvm_vcpu *vcpu, return -1; } +static inline unsigned long kvm_read_reg(struct kvm_vcpu *vcpu, int num) +{ + return vcpu->arch.gprs[num]; +} + +static inline void kvm_write_reg(struct kvm_vcpu *vcpu, int num, unsigned long val) +{ + vcpu->arch.gprs[num] = val; +} + +static inline bool kvm_pvtime_supported(void) +{ + return !!sched_info_on(); +} + +static inline bool kvm_guest_has_pv_feature(struct kvm_vcpu *vcpu, unsigned int feature) +{ + return vcpu->kvm->arch.pv_features & BIT(feature); +} + #endif /* __ASM_LOONGARCH_KVM_VCPU_H__ */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 46366e783c84..52651aa0e583 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -62,6 +62,7 @@ #define LOONGARCH_CPUCFG1 0x1 #define CPUCFG1_ISGR32 BIT(0) #define CPUCFG1_ISGR64 BIT(1) +#define CPUCFG1_ISA GENMASK(1, 0) #define CPUCFG1_PAGING BIT(2) #define CPUCFG1_IOCSR BIT(3) #define CPUCFG1_PABITS GENMASK(11, 4) @@ -107,6 +108,12 @@ #define CPUCFG3_SPW_HG_HF BIT(11) #define CPUCFG3_RVA BIT(12) #define CPUCFG3_RVAMAX GENMASK(16, 13) +#define CPUCFG3_ALDORDER_CAP BIT(18) /* All address load ordered, capability */ +#define CPUCFG3_ASTORDER_CAP BIT(19) /* All address store ordered, capability */ +#define CPUCFG3_ALDORDER_STA BIT(20) /* All address load ordered, status */ +#define CPUCFG3_ASTORDER_STA BIT(21) /* All address store ordered, status */ +#define CPUCFG3_SLDORDER_CAP BIT(22) /* Same address load ordered, capability */ +#define CPUCFG3_SLDORDER_STA BIT(23) /* Same address load ordered, status */ #define LOONGARCH_CPUCFG4 0x4 #define CPUCFG4_CCFREQ GENMASK(31, 0) @@ -119,6 +126,7 @@ #define CPUCFG6_PMP BIT(0) #define CPUCFG6_PAMVER GENMASK(3, 1) #define CPUCFG6_PMNUM GENMASK(7, 4) +#define CPUCFG6_PMNUM_SHIFT 4 #define CPUCFG6_PMBITS GENMASK(13, 8) #define CPUCFG6_UPM BIT(14) @@ -158,6 +166,11 @@ #define CPUCFG48_VFPU_CG BIT(2) #define CPUCFG48_RAM_CG BIT(3) +/* + * CPUCFG index area: 0x40000000 -- 0x400000ff + * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h + */ + #ifndef __ASSEMBLY__ /* CSR */ @@ -240,10 +253,10 @@ #define CSR_ESTAT_EXC_WIDTH 6 #define CSR_ESTAT_EXC (_ULCAST_(0x3f) << CSR_ESTAT_EXC_SHIFT) #define CSR_ESTAT_IS_SHIFT 0 -#define CSR_ESTAT_IS_WIDTH 14 -#define CSR_ESTAT_IS (_ULCAST_(0x3fff) << CSR_ESTAT_IS_SHIFT) +#define CSR_ESTAT_IS_WIDTH 15 +#define CSR_ESTAT_IS (_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT) -#define LOONGARCH_CSR_ERA 0x6 /* ERA */ +#define LOONGARCH_CSR_ERA 0x6 /* Exception return address */ #define LOONGARCH_CSR_BADV 0x7 /* Bad virtual address */ @@ -459,7 +472,6 @@ #define LOONGARCH_CSR_TCFG 0x41 /* Timer config */ #define CSR_TCFG_VAL_SHIFT 2 -#define CSR_TCFG_VAL_WIDTH 48 #define CSR_TCFG_VAL (_ULCAST_(0x3fffffffffff) << CSR_TCFG_VAL_SHIFT) #define CSR_TCFG_PERIOD_SHIFT 1 #define CSR_TCFG_PERIOD (_ULCAST_(0x1) << CSR_TCFG_PERIOD_SHIFT) @@ -559,6 +571,15 @@ /* Implement dependent */ #define LOONGARCH_CSR_IMPCTL1 0x80 /* Loongson config1 */ +#define CSR_LDSTORDER_SHIFT 28 +#define CSR_LDSTORDER_WIDTH 3 +#define CSR_LDSTORDER_MASK (_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT) +#define CSR_LDSTORDER_NLD_NST (_ULCAST_(0x0) << CSR_LDSTORDER_SHIFT) /* 000 = No Load No Store */ +#define CSR_LDSTORDER_ALD_NST (_ULCAST_(0x1) << CSR_LDSTORDER_SHIFT) /* 001 = All Load No Store */ +#define CSR_LDSTORDER_SLD_NST (_ULCAST_(0x3) << CSR_LDSTORDER_SHIFT) /* 011 = Same Load No Store */ +#define CSR_LDSTORDER_NLD_AST (_ULCAST_(0x4) << CSR_LDSTORDER_SHIFT) /* 100 = No Load All Store */ +#define CSR_LDSTORDER_ALD_AST (_ULCAST_(0x5) << CSR_LDSTORDER_SHIFT) /* 101 = All Load All Store */ +#define CSR_LDSTORDER_SLD_AST (_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT) /* 111 = Same Load All Store */ #define CSR_MISPEC_SHIFT 20 #define CSR_MISPEC_WIDTH 8 #define CSR_MISPEC (_ULCAST_(0xff) << CSR_MISPEC_SHIFT) @@ -636,6 +657,13 @@ #define LOONGARCH_CSR_CTAG 0x98 /* TagLo + TagHi */ +#define LOONGARCH_CSR_ISR0 0xa0 +#define LOONGARCH_CSR_ISR1 0xa1 +#define LOONGARCH_CSR_ISR2 0xa2 +#define LOONGARCH_CSR_ISR3 0xa3 + +#define LOONGARCH_CSR_IRR 0xa4 + #define LOONGARCH_CSR_PRID 0xc0 /* Shadow MCSR : 0xc0 ~ 0xff */ @@ -865,7 +893,7 @@ #define LOONGARCH_CSR_DMWIN2 0x182 /* 64 direct map win2: MEM */ #define LOONGARCH_CSR_DMWIN3 0x183 /* 64 direct map win3: MEM */ -/* Direct Map window 0/1 */ +/* Direct Map window 0/1/2/3 */ #define CSR_DMW0_PLV0 _CONST64_(1 << 0) #define CSR_DMW0_VSEG _CONST64_(0x8000) #define CSR_DMW0_BASE (CSR_DMW0_VSEG << DMW_PABITS) @@ -877,6 +905,14 @@ #define CSR_DMW1_BASE (CSR_DMW1_VSEG << DMW_PABITS) #define CSR_DMW1_INIT (CSR_DMW1_BASE | CSR_DMW1_MAT | CSR_DMW1_PLV0) +#define CSR_DMW2_PLV0 _CONST64_(1 << 0) +#define CSR_DMW2_MAT _CONST64_(2 << 4) +#define CSR_DMW2_VSEG _CONST64_(0xa000) +#define CSR_DMW2_BASE (CSR_DMW2_VSEG << DMW_PABITS) +#define CSR_DMW2_INIT (CSR_DMW2_BASE | CSR_DMW2_MAT | CSR_DMW2_PLV0) + +#define CSR_DMW3_INIT 0x0 + /* Performance Counter registers */ #define LOONGARCH_CSR_PERFCTRL0 0x200 /* 32 perf event 0 config */ #define LOONGARCH_CSR_PERFCNTR0 0x201 /* 64 perf event 0 count value */ @@ -937,6 +973,36 @@ #define LOONGARCH_CSR_DB7CTRL 0x34a /* data breakpoint 7 control */ #define LOONGARCH_CSR_DB7ASID 0x34b /* data breakpoint 7 asid */ +#define LOONGARCH_CSR_DB8ADDR 0x350 /* data breakpoint 8 address */ +#define LOONGARCH_CSR_DB8MASK 0x351 /* data breakpoint 8 mask */ +#define LOONGARCH_CSR_DB8CTRL 0x352 /* data breakpoint 8 control */ +#define LOONGARCH_CSR_DB8ASID 0x353 /* data breakpoint 8 asid */ + +#define LOONGARCH_CSR_DB9ADDR 0x358 /* data breakpoint 9 address */ +#define LOONGARCH_CSR_DB9MASK 0x359 /* data breakpoint 9 mask */ +#define LOONGARCH_CSR_DB9CTRL 0x35a /* data breakpoint 9 control */ +#define LOONGARCH_CSR_DB9ASID 0x35b /* data breakpoint 9 asid */ + +#define LOONGARCH_CSR_DB10ADDR 0x360 /* data breakpoint 10 address */ +#define LOONGARCH_CSR_DB10MASK 0x361 /* data breakpoint 10 mask */ +#define LOONGARCH_CSR_DB10CTRL 0x362 /* data breakpoint 10 control */ +#define LOONGARCH_CSR_DB10ASID 0x363 /* data breakpoint 10 asid */ + +#define LOONGARCH_CSR_DB11ADDR 0x368 /* data breakpoint 11 address */ +#define LOONGARCH_CSR_DB11MASK 0x369 /* data breakpoint 11 mask */ +#define LOONGARCH_CSR_DB11CTRL 0x36a /* data breakpoint 11 control */ +#define LOONGARCH_CSR_DB11ASID 0x36b /* data breakpoint 11 asid */ + +#define LOONGARCH_CSR_DB12ADDR 0x370 /* data breakpoint 12 address */ +#define LOONGARCH_CSR_DB12MASK 0x371 /* data breakpoint 12 mask */ +#define LOONGARCH_CSR_DB12CTRL 0x372 /* data breakpoint 12 control */ +#define LOONGARCH_CSR_DB12ASID 0x373 /* data breakpoint 12 asid */ + +#define LOONGARCH_CSR_DB13ADDR 0x378 /* data breakpoint 13 address */ +#define LOONGARCH_CSR_DB13MASK 0x379 /* data breakpoint 13 mask */ +#define LOONGARCH_CSR_DB13CTRL 0x37a /* data breakpoint 13 control */ +#define LOONGARCH_CSR_DB13ASID 0x37b /* data breakpoint 13 asid */ + #define LOONGARCH_CSR_FWPC 0x380 /* instruction breakpoint config */ #define LOONGARCH_CSR_FWPS 0x381 /* instruction breakpoint status */ @@ -980,6 +1046,36 @@ #define LOONGARCH_CSR_IB7CTRL 0x3ca /* inst breakpoint 7 control */ #define LOONGARCH_CSR_IB7ASID 0x3cb /* inst breakpoint 7 asid */ +#define LOONGARCH_CSR_IB8ADDR 0x3d0 /* inst breakpoint 8 address */ +#define LOONGARCH_CSR_IB8MASK 0x3d1 /* inst breakpoint 8 mask */ +#define LOONGARCH_CSR_IB8CTRL 0x3d2 /* inst breakpoint 8 control */ +#define LOONGARCH_CSR_IB8ASID 0x3d3 /* inst breakpoint 8 asid */ + +#define LOONGARCH_CSR_IB9ADDR 0x3d8 /* inst breakpoint 9 address */ +#define LOONGARCH_CSR_IB9MASK 0x3d9 /* inst breakpoint 9 mask */ +#define LOONGARCH_CSR_IB9CTRL 0x3da /* inst breakpoint 9 control */ +#define LOONGARCH_CSR_IB9ASID 0x3db /* inst breakpoint 9 asid */ + +#define LOONGARCH_CSR_IB10ADDR 0x3e0 /* inst breakpoint 10 address */ +#define LOONGARCH_CSR_IB10MASK 0x3e1 /* inst breakpoint 10 mask */ +#define LOONGARCH_CSR_IB10CTRL 0x3e2 /* inst breakpoint 10 control */ +#define LOONGARCH_CSR_IB10ASID 0x3e3 /* inst breakpoint 10 asid */ + +#define LOONGARCH_CSR_IB11ADDR 0x3e8 /* inst breakpoint 11 address */ +#define LOONGARCH_CSR_IB11MASK 0x3e9 /* inst breakpoint 11 mask */ +#define LOONGARCH_CSR_IB11CTRL 0x3ea /* inst breakpoint 11 control */ +#define LOONGARCH_CSR_IB11ASID 0x3eb /* inst breakpoint 11 asid */ + +#define LOONGARCH_CSR_IB12ADDR 0x3f0 /* inst breakpoint 12 address */ +#define LOONGARCH_CSR_IB12MASK 0x3f1 /* inst breakpoint 12 mask */ +#define LOONGARCH_CSR_IB12CTRL 0x3f2 /* inst breakpoint 12 control */ +#define LOONGARCH_CSR_IB12ASID 0x3f3 /* inst breakpoint 12 asid */ + +#define LOONGARCH_CSR_IB13ADDR 0x3f8 /* inst breakpoint 13 address */ +#define LOONGARCH_CSR_IB13MASK 0x3f9 /* inst breakpoint 13 mask */ +#define LOONGARCH_CSR_IB13CTRL 0x3fa /* inst breakpoint 13 control */ +#define LOONGARCH_CSR_IB13ASID 0x3fb /* inst breakpoint 13 asid */ + #define LOONGARCH_CSR_DEBUG 0x500 /* debug config */ #define LOONGARCH_CSR_DERA 0x501 /* debug era */ #define LOONGARCH_CSR_DESAVE 0x502 /* debug save */ @@ -990,7 +1086,7 @@ /* * CSR_ECFG IM */ -#define ECFG0_IM 0x00001fff +#define ECFG0_IM 0x00005fff #define ECFGB_SIP0 0 #define ECFGF_SIP0 (_ULCAST_(1) << ECFGB_SIP0) #define ECFGB_SIP1 1 @@ -1033,6 +1129,7 @@ #define IOCSRF_EIODECODE BIT_ULL(9) #define IOCSRF_FLATMODE BIT_ULL(10) #define IOCSRF_VM BIT_ULL(11) +#define IOCSRF_AVEC BIT_ULL(15) #define LOONGARCH_IOCSR_VENDOR 0x10 @@ -1041,11 +1138,15 @@ #define LOONGARCH_IOCSR_NODECNT 0x408 #define LOONGARCH_IOCSR_MISC_FUNC 0x420 +#define IOCSR_MISC_FUNC_SOFT_INT BIT_ULL(10) #define IOCSR_MISC_FUNC_TIMER_RESET BIT_ULL(21) #define IOCSR_MISC_FUNC_EXT_IOI_EN BIT_ULL(48) +#define IOCSR_MISC_FUNC_AVEC_EN BIT_ULL(51) #define LOONGARCH_IOCSR_CPUTEMP 0x428 +#define LOONGARCH_IOCSR_SMCMBX 0x51c + /* PerCore CSR, only accessible by local cores */ #define LOONGARCH_IOCSR_IPI_STATUS 0x1000 #define LOONGARCH_IOCSR_IPI_EN 0x1004 @@ -1363,9 +1464,10 @@ __BUILD_CSR_OP(tlbidx) #define INT_TI 11 /* Timer */ #define INT_IPI 12 #define INT_NMI 13 +#define INT_AVEC 14 /* ExcCodes corresponding to interrupts */ -#define EXCCODE_INT_NUM (INT_NMI + 1) +#define EXCCODE_INT_NUM (INT_AVEC + 1) #define EXCCODE_INT_START 64 #define EXCCODE_INT_END (EXCCODE_INT_START + EXCCODE_INT_NUM - 1) diff --git a/arch/loongarch/include/asm/mmu_context.h b/arch/loongarch/include/asm/mmu_context.h index 9f97c3453b9c..304363bd3935 100644 --- a/arch/loongarch/include/asm/mmu_context.h +++ b/arch/loongarch/include/asm/mmu_context.h @@ -49,12 +49,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) /* Normal, classic get_new_mmu_context */ static inline void -get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) +get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, bool *need_flush) { u64 asid = asid_cache(cpu); if (!((++asid) & cpu_asid_mask(&cpu_data[cpu]))) - local_flush_tlb_user(); /* start new asid cycle */ + *need_flush = true; /* start new asid cycle */ cpu_context(cpu, mm) = asid_cache(cpu) = asid; } @@ -74,21 +74,34 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) return 0; } +static inline void atomic_update_pgd_asid(unsigned long asid, unsigned long pgdl) +{ + __asm__ __volatile__( + "csrwr %[pgdl_val], %[pgdl_reg] \n\t" + "csrwr %[asid_val], %[asid_reg] \n\t" + : [asid_val] "+r" (asid), [pgdl_val] "+r" (pgdl) + : [asid_reg] "i" (LOONGARCH_CSR_ASID), [pgdl_reg] "i" (LOONGARCH_CSR_PGDL) + : "memory" + ); +} + static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + bool need_flush = false; unsigned int cpu = smp_processor_id(); /* Check if our ASID is of an older version and thus invalid */ if (!asid_valid(next, cpu)) - get_new_mmu_context(next, cpu); - - write_csr_asid(cpu_asid(cpu, next)); + get_new_mmu_context(next, cpu, &need_flush); if (next != &init_mm) - csr_write64((unsigned long)next->pgd, LOONGARCH_CSR_PGDL); + atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)next->pgd); else - csr_write64((unsigned long)invalid_pg_dir, LOONGARCH_CSR_PGDL); + atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)invalid_pg_dir); + + if (need_flush) + local_flush_tlb_user(); /* Flush tlb after update ASID */ /* * Mark current->active_mm as not "active" anymore. @@ -135,9 +148,15 @@ drop_mmu_context(struct mm_struct *mm, unsigned int cpu) asid = read_csr_asid() & cpu_asid_mask(¤t_cpu_data); if (asid == cpu_asid(cpu, mm)) { + bool need_flush = false; + if (!current->mm || (current->mm == mm)) { - get_new_mmu_context(mm, cpu); + get_new_mmu_context(mm, cpu, &need_flush); + write_csr_asid(cpu_asid(cpu, mm)); + if (need_flush) + local_flush_tlb_user(); /* Flush tlb after update ASID */ + goto out; } } diff --git a/arch/loongarch/include/asm/mmzone.h b/arch/loongarch/include/asm/mmzone.h deleted file mode 100644 index 2b9a90727e19..000000000000 --- a/arch/loongarch/include/asm/mmzone.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Author: Huacai Chen (chenhuacai@loongson.cn) - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_MMZONE_H_ -#define _ASM_MMZONE_H_ - -#include <asm/page.h> -#include <asm/numa.h> - -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[(nid)]) - -#endif /* _ASM_MMZONE_H_ */ diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h index 2ecd82bb64e1..f33f3fd32ecc 100644 --- a/arch/loongarch/include/asm/module.h +++ b/arch/loongarch/include/asm/module.h @@ -6,6 +6,7 @@ #define _ASM_MODULE_H #include <asm/inst.h> +#include <asm/orc_types.h> #include <asm-generic/module.h> #define RELA_STACK_DEPTH 16 @@ -21,6 +22,12 @@ struct mod_arch_specific { struct mod_section plt; struct mod_section plt_idx; +#ifdef CONFIG_UNWINDER_ORC + unsigned int num_orcs; + int *orc_unwind_ip; + struct orc_entry *orc_unwind; +#endif + /* For CONFIG_DYNAMIC_FTRACE */ struct plt_entry *ftrace_trampolines; }; diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index 27f319b49862..b5f9de9f102e 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu); static inline void early_numa_add_cpu(int cpuid, s16 node) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void set_cpuid_to_node(int cpuid, s16 node) { } static inline int early_cpu_to_node(int cpu) { diff --git a/arch/loongarch/include/asm/orc_header.h b/arch/loongarch/include/asm/orc_header.h new file mode 100644 index 000000000000..f9d509c3fd70 --- /dev/null +++ b/arch/loongarch/include/asm/orc_header.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _ORC_HEADER_H +#define _ORC_HEADER_H + +#include <linux/types.h> +#include <linux/compiler.h> +#include <asm/orc_hash.h> + +/* + * The header is currently a 20-byte hash of the ORC entry definition; see + * scripts/orc_hash.sh. + */ +#define ORC_HEADER \ + __used __section(".orc_header") __aligned(4) \ + static const u8 orc_header[] = { ORC_HASH } + +#endif /* _ORC_HEADER_H */ diff --git a/arch/loongarch/include/asm/orc_lookup.h b/arch/loongarch/include/asm/orc_lookup.h new file mode 100644 index 000000000000..b02e6357def4 --- /dev/null +++ b/arch/loongarch/include/asm/orc_lookup.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ORC_LOOKUP_H +#define _ORC_LOOKUP_H + +/* + * This is a lookup table for speeding up access to the .orc_unwind table. + * Given an input address offset, the corresponding lookup table entry + * specifies a subset of the .orc_unwind table to search. + * + * Each block represents the end of the previous range and the start of the + * next range. An extra block is added to give the last range an end. + * + * The block size should be a power of 2 to avoid a costly 'div' instruction. + * + * A block size of 256 was chosen because it roughly doubles unwinder + * performance while only adding ~5% to the ORC data footprint. + */ +#define LOOKUP_BLOCK_ORDER 8 +#define LOOKUP_BLOCK_SIZE (1 << LOOKUP_BLOCK_ORDER) + +#ifndef LINKER_SCRIPT + +extern unsigned int orc_lookup[]; +extern unsigned int orc_lookup_end[]; + +#define LOOKUP_START_IP (unsigned long)_stext +#define LOOKUP_STOP_IP (unsigned long)_etext + +#endif /* LINKER_SCRIPT */ + +#endif /* _ORC_LOOKUP_H */ diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h new file mode 100644 index 000000000000..caf1f71a1057 --- /dev/null +++ b/arch/loongarch/include/asm/orc_types.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ORC_TYPES_H +#define _ORC_TYPES_H + +#include <linux/types.h> + +/* + * The ORC_REG_* registers are base registers which are used to find other + * registers on the stack. + * + * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the + * address of the previous frame: the caller's SP before it called the current + * function. + * + * ORC_REG_UNDEFINED means the corresponding register's value didn't change in + * the current frame. + * + * The most commonly used base registers are SP and FP -- which the previous SP + * is usually based on -- and PREV_SP and UNDEFINED -- which the previous FP is + * usually based on. + * + * The rest of the base registers are needed for special cases like entry code + * and GCC realigned stacks. + */ +#define ORC_REG_UNDEFINED 0 +#define ORC_REG_PREV_SP 1 +#define ORC_REG_SP 2 +#define ORC_REG_FP 3 +#define ORC_REG_MAX 4 + +#define ORC_TYPE_UNDEFINED 0 +#define ORC_TYPE_END_OF_STACK 1 +#define ORC_TYPE_CALL 2 +#define ORC_TYPE_REGS 3 +#define ORC_TYPE_REGS_PARTIAL 4 + +#ifndef __ASSEMBLY__ +/* + * This struct is more or less a vastly simplified version of the DWARF Call + * Frame Information standard. It contains only the necessary parts of DWARF + * CFI, simplified for ease of access by the in-kernel unwinder. It tells the + * unwinder how to find the previous SP and FP (and sometimes entry regs) on + * the stack for a given code address. Each instance of the struct corresponds + * to one or more code locations. + */ +struct orc_entry { + s16 sp_offset; + s16 fp_offset; + s16 ra_offset; + unsigned int sp_reg:4; + unsigned int fp_reg:4; + unsigned int ra_reg:4; + unsigned int type:3; + unsigned int signal:1; +}; +#endif /* __ASSEMBLY__ */ + +#endif /* _ORC_TYPES_H */ diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 63f137ce82a4..7368f12b7cb1 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -8,20 +8,7 @@ #include <linux/const.h> #include <asm/addrspace.h> -/* - * PAGE_SHIFT determines the page size - */ -#ifdef CONFIG_PAGE_SIZE_4KB -#define PAGE_SHIFT 12 -#endif -#ifdef CONFIG_PAGE_SIZE_16KB -#define PAGE_SHIFT 14 -#endif -#ifdef CONFIG_PAGE_SIZE_64KB -#define PAGE_SHIFT 16 -#endif -#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#include <vdso/page.h> #define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) @@ -83,7 +70,26 @@ typedef struct { unsigned long pgprot; } pgprot_t; #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) -#define virt_to_pfn(kaddr) PFN_DOWN(PHYSADDR(kaddr)) +struct page *dmw_virt_to_page(unsigned long kaddr); +struct page *tlb_virt_to_page(unsigned long kaddr); + +#define pfn_to_phys(pfn) __pfn_to_phys(pfn) +#define phys_to_pfn(paddr) __phys_to_pfn(paddr) + +#ifndef CONFIG_KFENCE + +#define page_to_virt(page) __va(page_to_phys(page)) +#define virt_to_page(kaddr) phys_to_page(__pa(kaddr)) + +#else + +#define WANT_PAGE_VIRTUAL + +#define page_to_virt(page) \ +({ \ + extern char *__kfence_pool; \ + (__kfence_pool == NULL) ? __va(page_to_phys(page)) : page_address(page); \ +}) #define virt_to_page(kaddr) \ ({ \ @@ -91,13 +97,15 @@ typedef struct { unsigned long pgprot; } pgprot_t; dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\ }) +#endif + +#define pfn_to_virt(pfn) page_to_virt(pfn_to_page(pfn)) +#define virt_to_pfn(kaddr) page_to_pfn(virt_to_page(kaddr)) + extern int __virt_addr_valid(volatile void *kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr)) -#define VM_DATA_DEFAULT_FLAGS \ - (VM_READ | VM_WRITE | \ - ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/loongarch/include/asm/paravirt.h b/arch/loongarch/include/asm/paravirt.h new file mode 100644 index 000000000000..3f4323603e6a --- /dev/null +++ b/arch/loongarch/include/asm/paravirt.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_PARAVIRT_H +#define _ASM_LOONGARCH_PARAVIRT_H + +#ifdef CONFIG_PARAVIRT + +#include <linux/static_call_types.h> +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +u64 dummy_steal_clock(int cpu); +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); + +static inline u64 paravirt_steal_clock(int cpu) +{ + return static_call(pv_steal_clock)(cpu); +} + +int __init pv_ipi_init(void); +int __init pv_time_init(void); +int __init pv_spinlock_init(void); + +#else + +static inline int pv_ipi_init(void) +{ + return 0; +} + +static inline int pv_time_init(void) +{ + return 0; +} + +static inline int pv_spinlock_init(void) +{ + return 0; +} + +#endif // CONFIG_PARAVIRT +#endif diff --git a/arch/loongarch/include/asm/paravirt_api_clock.h b/arch/loongarch/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/loongarch/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include <asm/paravirt.h> diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 9b36ac003f89..87be9b14e9da 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -29,7 +29,12 @@ static inline void set_my_cpu_offset(unsigned long off) __my_cpu_offset = off; csr_write64(off, PERCPU_BASE_KS); } -#define __my_cpu_offset __my_cpu_offset + +#define __my_cpu_offset \ +({ \ + __asm__ __volatile__("":"+r"(__my_cpu_offset)); \ + __my_cpu_offset; \ +}) #define PERCPU_OP(op, asm_op, c_op) \ static __always_inline unsigned long __percpu_##op(void *ptr, \ @@ -63,75 +68,6 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size) -{ - unsigned long ret; - - switch (size) { - case 1: - __asm__ __volatile__ ("ldx.b %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 2: - __asm__ __volatile__ ("ldx.h %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 4: - __asm__ __volatile__ ("ldx.w %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 8: - __asm__ __volatile__ ("ldx.d %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - default: - ret = 0; - BUILD_BUG(); - } - - return ret; -} - -static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size) -{ - switch (size) { - case 1: - __asm__ __volatile__("stx.b %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 2: - __asm__ __volatile__("stx.h %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 4: - __asm__ __volatile__("stx.w %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 8: - __asm__ __volatile__("stx.d %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - default: - BUILD_BUG(); - } -} - static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size) { switch (size) { @@ -152,6 +88,33 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, return 0; } +#define __pcpu_op_1(op) op ".b " +#define __pcpu_op_2(op) op ".h " +#define __pcpu_op_4(op) op ".w " +#define __pcpu_op_8(op) op ".d " + +#define _percpu_read(size, _pcp) \ +({ \ + typeof(_pcp) __pcp_ret; \ + \ + __asm__ __volatile__( \ + __pcpu_op_##size("ldx") "%[ret], $r21, %[ptr] \n" \ + : [ret] "=&r"(__pcp_ret) \ + : [ptr] "r"(&(_pcp)) \ + : "memory"); \ + \ + __pcp_ret; \ +}) + +#define _percpu_write(size, _pcp, _val) \ +do { \ + __asm__ __volatile__( \ + __pcpu_op_##size("stx") "%[val], $r21, %[ptr] \n" \ + : \ + : [val] "r"(_val), [ptr] "r"(&(_pcp)) \ + : "memory"); \ +} while (0) + /* this_cpu_cmpxchg */ #define _protect_cmpxchg_local(pcp, o, n) \ ({ \ @@ -162,18 +125,6 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, __ret; \ }) -#define _percpu_read(pcp) \ -({ \ - typeof(pcp) __retval; \ - __retval = (typeof(pcp))__percpu_read(&(pcp), sizeof(pcp)); \ - __retval; \ -}) - -#define _percpu_write(pcp, val) \ -do { \ - __percpu_write(&(pcp), (unsigned long)(val), sizeof(pcp)); \ -} while (0) \ - #define _pcp_protect(operation, pcp, val) \ ({ \ typeof(pcp) __retval; \ @@ -210,15 +161,15 @@ do { \ #define this_cpu_or_4(pcp, val) _percpu_or(pcp, val) #define this_cpu_or_8(pcp, val) _percpu_or(pcp, val) -#define this_cpu_read_1(pcp) _percpu_read(pcp) -#define this_cpu_read_2(pcp) _percpu_read(pcp) -#define this_cpu_read_4(pcp) _percpu_read(pcp) -#define this_cpu_read_8(pcp) _percpu_read(pcp) +#define this_cpu_read_1(pcp) _percpu_read(1, pcp) +#define this_cpu_read_2(pcp) _percpu_read(2, pcp) +#define this_cpu_read_4(pcp) _percpu_read(4, pcp) +#define this_cpu_read_8(pcp) _percpu_read(8, pcp) -#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val) +#define this_cpu_write_1(pcp, val) _percpu_write(1, pcp, val) +#define this_cpu_write_2(pcp, val) _percpu_write(2, pcp, val) +#define this_cpu_write_4(pcp, val) _percpu_write(4, pcp, val) +#define this_cpu_write_8(pcp, val) _percpu_write(8, pcp, val) #define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaa..f948a0676daf 100644 --- a/arch/loongarch/include/asm/perf_event.h +++ b/arch/loongarch/include/asm/perf_event.h @@ -7,6 +7,13 @@ #ifndef __LOONGARCH_PERF_EVENT_H__ #define __LOONGARCH_PERF_EVENT_H__ +#include <asm/ptrace.h> + #define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->csr_era = (__ip); \ + (regs)->regs[3] = (unsigned long) __builtin_frame_address(0); \ +} + #endif /* __LOONGARCH_PERF_EVENT_H__ */ diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 4e2d6b7ca2ee..7211dff8c969 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -10,6 +10,7 @@ #define __HAVE_ARCH_PMD_ALLOC_ONE #define __HAVE_ARCH_PUD_ALLOC_ONE +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL #include <asm-generic/pgalloc.h> static inline void pmd_populate_kernel(struct mm_struct *mm, @@ -44,9 +45,19 @@ extern void pagetable_init(void); extern pgd_t *pgd_alloc(struct mm_struct *mm); +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) +{ + pte_t *pte = __pte_alloc_one_kernel(mm); + + if (pte) + kernel_pte_init(pte); + + return pte; +} + #define __pte_free_tlb(tlb, pte, address) \ do { \ - pagetable_pte_dtor(page_ptdesc(pte)); \ + pagetable_dtor(page_ptdesc(pte)); \ tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 21319c1e045c..45bfc65a0c9f 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -22,6 +22,7 @@ #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 @@ -35,6 +36,7 @@ #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) @@ -74,8 +76,8 @@ #define __READABLE (_PAGE_VALID) #define __WRITEABLE (_PAGE_DIRTY | _PAGE_WRITE) -#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_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_NONE __pgprot(_PAGE_PROTNONE | _PAGE_NO_READ | \ _PAGE_USER | _CACHE_CC) @@ -94,6 +96,13 @@ #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_SUC) +#define pgprot_nx pgprot_nx + +static inline pgprot_t pgprot_nx(pgprot_t _prot) +{ + return __pgprot(pgprot_val(_prot) | _PAGE_NO_EXEC); +} + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t _prot) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 8b5df1bbf9e9..da346733a1da 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -106,6 +106,9 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define KFENCE_AREA_START (VMEMMAP_END + 1) #define KFENCE_AREA_END (KFENCE_AREA_START + KFENCE_AREA_SIZE - 1) +#define ptep_get(ptep) READ_ONCE(*(ptep)) +#define pmdp_get(pmdp) READ_ONCE(*(pmdp)) + #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e)) #ifndef __PAGETABLE_PMD_FOLDED @@ -147,11 +150,6 @@ static inline int p4d_present(p4d_t p4d) return p4d_val(p4d) != (unsigned long)invalid_pud_table; } -static inline void p4d_clear(p4d_t *p4dp) -{ - p4d_val(*p4dp) = (unsigned long)invalid_pud_table; -} - static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)p4d_val(p4d); @@ -159,7 +157,12 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) static inline void set_p4d(p4d_t *p4d, p4d_t p4dval) { - *p4d = p4dval; + WRITE_ONCE(*p4d, p4dval); +} + +static inline void p4d_clear(p4d_t *p4dp) +{ + set_p4d(p4dp, __p4d((unsigned long)invalid_pud_table)); } #define p4d_phys(p4d) PHYSADDR(p4d_val(p4d)) @@ -193,17 +196,20 @@ static inline int pud_present(pud_t pud) return pud_val(pud) != (unsigned long)invalid_pmd_table; } -static inline void pud_clear(pud_t *pudp) +static inline pmd_t *pud_pgtable(pud_t pud) { - pud_val(*pudp) = ((unsigned long)invalid_pmd_table); + return (pmd_t *)pud_val(pud); } -static inline pmd_t *pud_pgtable(pud_t pud) +static inline void set_pud(pud_t *pud, pud_t pudval) { - return (pmd_t *)pud_val(pud); + WRITE_ONCE(*pud, pudval); } -#define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while (0) +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, __pud((unsigned long)invalid_pmd_table)); +} #define pud_phys(pud) PHYSADDR(pud_val(pud)) #define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT)) @@ -231,12 +237,15 @@ static inline int pmd_present(pmd_t pmd) return pmd_val(pmd) != (unsigned long)invalid_pte_table; } -static inline void pmd_clear(pmd_t *pmdp) +static inline void set_pmd(pmd_t *pmd, pmd_t pmdval) { - pmd_val(*pmdp) = ((unsigned long)invalid_pte_table); + WRITE_ONCE(*pmd, pmdval); } -#define set_pmd(pmdptr, pmdval) do { *(pmdptr) = (pmdval); } while (0) +static inline void pmd_clear(pmd_t *pmdp) +{ + set_pmd(pmdp, __pmd((unsigned long)invalid_pte_table)); +} #define pmd_phys(pmd) PHYSADDR(pmd_val(pmd)) @@ -259,7 +268,11 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm */ extern void pgd_init(void *addr); extern void pud_init(void *addr); +#define pud_init pud_init extern void pmd_init(void *addr); +#define pmd_init pmd_init +extern void kernel_pte_init(void *addr); +#define kernel_pte_init kernel_pte_init /* * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that @@ -314,46 +327,19 @@ extern void paging_init(void); static inline void set_pte(pte_t *ptep, pte_t pteval) { - *ptep = pteval; - if (pte_val(pteval) & _PAGE_GLOBAL) { - pte_t *buddy = ptep_buddy(ptep); - /* - * Make sure the buddy is global too (if it's !none, - * it better already be global) - */ + WRITE_ONCE(*ptep, pteval); + #ifdef CONFIG_SMP - /* - * For SMP, multiple CPUs can race, so we need to do - * this atomically. - */ - unsigned long page_global = _PAGE_GLOBAL; - unsigned long tmp; - - __asm__ __volatile__ ( - "1:" __LL "%[tmp], %[buddy] \n" - " bnez %[tmp], 2f \n" - " or %[tmp], %[tmp], %[global] \n" - __SC "%[tmp], %[buddy] \n" - " beqz %[tmp], 1b \n" - " nop \n" - "2: \n" - __WEAK_LLSC_MB - : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) - : [global] "r" (page_global)); -#else /* !CONFIG_SMP */ - if (pte_none(*buddy)) - pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; -#endif /* CONFIG_SMP */ - } + if (pte_val(pteval) & _PAGE_GLOBAL) + DBAR(0b11000); /* o_wrw = 0b11000 */ +#endif } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - /* Preserve global status for the pair */ - if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL) - set_pte(ptep, __pte(_PAGE_GLOBAL)); - else - set_pte(ptep, __pte(0)); + pte_t pte = ptep_get(ptep); + pte_val(pte) &= _PAGE_GLOBAL; + set_pte(ptep, pte); } #define PGD_T_LOG2 (__builtin_ffs(sizeof(pgd_t)) - 1) @@ -363,9 +349,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt extern pgd_t swapper_pg_dir[]; extern pgd_t invalid_pg_dir[]; -struct page *dmw_virt_to_page(unsigned long kaddr); -struct page *tlb_virt_to_page(unsigned long kaddr); - /* * The following only work if pte_present() is true. * Undefined behaviour if not.. @@ -427,6 +410,9 @@ 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) { @@ -470,8 +456,8 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) -#define __HAVE_ARCH_UPDATE_MMU_TLB -#define update_mmu_tlb update_mmu_cache +#define update_mmu_tlb_range(vma, addr, ptep, nr) \ + update_mmu_cache_range(NULL, vma, addr, ptep, nr) static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -561,6 +547,17 @@ 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)) @@ -592,7 +589,7 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - pmd_t old = *pmdp; + pmd_t old = pmdp_get(pmdp); pmd_clear(pmdp); @@ -616,6 +613,11 @@ 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/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h index 34f43f8ad591..e76d3aa1e1eb 100644 --- a/arch/loongarch/include/asm/qspinlock.h +++ b/arch/loongarch/include/asm/qspinlock.h @@ -1,18 +1,41 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_QSPINLOCK_H -#define _ASM_QSPINLOCK_H +#ifndef _ASM_LOONGARCH_QSPINLOCK_H +#define _ASM_LOONGARCH_QSPINLOCK_H -#include <asm-generic/qspinlock_types.h> +#include <linux/jump_label.h> -#define queued_spin_unlock queued_spin_unlock +#ifdef CONFIG_PARAVIRT -static inline void queued_spin_unlock(struct qspinlock *lock) +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); + +#define virt_spin_lock virt_spin_lock + +static inline bool virt_spin_lock(struct qspinlock *lock) { - compiletime_assert_atomic_type(lock->locked); - c_sync(); - WRITE_ONCE(lock->locked, 0); + int val; + + if (!static_branch_unlikely(&virt_spin_lock_key)) + return false; + + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + +__retry: + val = atomic_read(&lock->val); + + if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) { + cpu_relax(); + goto __retry; + } + + return true; } +#endif /* CONFIG_PARAVIRT */ + #include <asm-generic/qspinlock.h> -#endif /* _ASM_QSPINLOCK_H */ +#endif // _ASM_LOONGARCH_QSPINLOCK_H diff --git a/arch/loongarch/include/asm/set_memory.h b/arch/loongarch/include/asm/set_memory.h new file mode 100644 index 000000000000..55dfaefd02c8 --- /dev/null +++ b/arch/loongarch/include/asm/set_memory.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef _ASM_LOONGARCH_SET_MEMORY_H +#define _ASM_LOONGARCH_SET_MEMORY_H + +/* + * Functions to change memory attributes. + */ +int set_memory_x(unsigned long addr, int numpages); +int set_memory_nx(unsigned long addr, int numpages); +int set_memory_ro(unsigned long addr, int numpages); +int set_memory_rw(unsigned long addr, int numpages); + +bool kernel_page_present(struct page *page); +int set_direct_map_default_noflush(struct page *page); +int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); + +#endif /* _ASM_LOONGARCH_SET_MEMORY_H */ diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index ee52fb1e9963..3c2fb16b11b6 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -34,6 +34,11 @@ extern long __la_abs_end; extern long __rela_dyn_begin; extern long __rela_dyn_end; +#ifdef CONFIG_RELR +extern long __relr_dyn_begin; +extern long __relr_dyn_end; +#endif + extern unsigned long __init relocate_kernel(void); #endif diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index f81e5f01d619..b87d1d5e5890 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -6,12 +6,21 @@ #ifndef __ASM_SMP_H #define __ASM_SMP_H +#ifdef CONFIG_SMP + #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/linkage.h> #include <linux/threads.h> #include <linux/cpumask.h> +struct smp_ops { + void (*init_ipi)(void); + void (*send_ipi_single)(int cpu, unsigned int action); + void (*send_ipi_mask)(const struct cpumask *mask, unsigned int action); +}; +extern struct smp_ops mp_ops; + extern int smp_num_siblings; extern int num_processors; extern int disabled_cpus; @@ -24,8 +33,6 @@ void loongson_prepare_cpus(unsigned int max_cpus); void loongson_boot_secondary(int cpu, struct task_struct *idle); void loongson_init_secondary(void); void loongson_smp_finish(void); -void loongson_send_ipi_single(int cpu, unsigned int action); -void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action); #ifdef CONFIG_HOTPLUG_CPU int loongson_cpu_disable(void); void loongson_cpu_die(unsigned int cpu); @@ -59,9 +66,18 @@ extern int __cpu_logical_map[NR_CPUS]; #define cpu_physical_id(cpu) cpu_logical_map(cpu) -#define SMP_BOOT_CPU 0x1 -#define SMP_RESCHEDULE 0x2 -#define SMP_CALL_FUNCTION 0x4 +#define ACTION_BOOT_CPU 0 +#define ACTION_RESCHEDULE 1 +#define ACTION_CALL_FUNCTION 2 +#define ACTION_IRQ_WORK 3 +#define ACTION_CLEAR_VECTOR 4 +#define SMP_BOOT_CPU BIT(ACTION_BOOT_CPU) +#define SMP_RESCHEDULE BIT(ACTION_RESCHEDULE) +#define SMP_CALL_FUNCTION BIT(ACTION_CALL_FUNCTION) +#define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK) +#define SMP_CLEAR_VECTOR BIT(ACTION_CLEAR_VECTOR) + +struct seq_file; struct secondary_data { unsigned long stack; @@ -81,12 +97,12 @@ extern void show_ipi_list(struct seq_file *p, int prec); static inline void arch_send_call_function_single_ipi(int cpu) { - loongson_send_ipi_single(cpu, SMP_CALL_FUNCTION); + mp_ops.send_ipi_single(cpu, ACTION_CALL_FUNCTION); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - loongson_send_ipi_mask(mask, SMP_CALL_FUNCTION); + mp_ops.send_ipi_mask(mask, ACTION_CALL_FUNCTION); } #ifdef CONFIG_HOTPLUG_CPU @@ -101,4 +117,8 @@ static inline void __cpu_die(unsigned int cpu) } #endif +#else /* !CONFIG_SMP */ +#define cpu_logical_map(cpu) 0 +#endif /* CONFIG_SMP */ + #endif /* __ASM_SMP_H */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 4fb1e6408b98..66736837085b 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -13,6 +13,7 @@ #include <asm/asm-offsets.h> #include <asm/loongarch.h> #include <asm/thread_info.h> +#include <asm/unwind_hints.h> /* Make the addition of cfi info a little easier. */ .macro cfi_rel_offset reg offset=0 docfi=0 @@ -37,11 +38,22 @@ cfi_restore \reg \offset \docfi .endm + .macro SETUP_DMWINS temp + li.d \temp, CSR_DMW0_INIT # WUC, PLV0, 0x8000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN0 + li.d \temp, CSR_DMW1_INIT # CAC, PLV0, 0x9000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN1 + li.d \temp, CSR_DMW2_INIT # WUC, PLV0, 0xa000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN2 + li.d \temp, CSR_DMW3_INIT # 0x0, unused + csrwr \temp, LOONGARCH_CSR_DMWIN3 + .endm + /* Jump to the runtime virtual address. */ .macro JUMP_VIRT_ADDR temp1 temp2 li.d \temp1, CACHE_BASE pcaddi \temp2, 0 - or \temp1, \temp1, \temp2 + bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0 jirl zero, \temp1, 0xc .endm @@ -162,6 +174,7 @@ li.w t0, CSR_CRMD_WE csrxchg t0, t0, LOONGARCH_CSR_CRMD #endif + UNWIND_HINT_REGS .endm .macro SAVE_ALL docfi=0 @@ -219,6 +232,7 @@ .macro RESTORE_SP_AND_RET docfi=0 cfi_ld sp, PT_R3, \docfi + UNWIND_HINT_FUNC ertn .endm diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index 8cb653d49a54..4f5a9441754e 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -66,8 +66,9 @@ register unsigned long current_stack_pointer __asm__("$sp"); * - pending work-to-be-done flags are in LSW * - other flags in MSW */ -#define TIF_SIGPENDING 1 /* signal pending */ -#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NEED_RESCHED 0 /* rescheduling necessary */ +#define TIF_NEED_RESCHED_LAZY 1 /* lazy rescheduling necessary */ +#define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NOTIFY_RESUME 3 /* callback before returning to user */ #define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */ @@ -86,9 +87,11 @@ register unsigned long current_stack_pointer __asm__("$sp"); #define TIF_LASX_CTX_LIVE 18 /* LASX context must be preserved */ #define TIF_USEDLBT 19 /* LBT was used by this task this quantum (SMP) */ #define TIF_LBT_CTX_LIVE 20 /* LBT context must be preserved */ +#define TIF_PATCH_PENDING 21 /* pending live patching update */ -#define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) +#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) +#define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_NOTIFY_SIGNAL (1<<TIF_NOTIFY_SIGNAL) #define _TIF_NOHZ (1<<TIF_NOHZ) @@ -105,6 +108,7 @@ register unsigned long current_stack_pointer __asm__("$sp"); #define _TIF_LASX_CTX_LIVE (1<<TIF_LASX_CTX_LIVE) #define _TIF_USEDLBT (1<<TIF_USEDLBT) #define _TIF_LBT_CTX_LIVE (1<<TIF_LBT_CTX_LIVE) +#define _TIF_PATCH_PENDING (1<<TIF_PATCH_PENDING) #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h index da7a3b5b9374..e071f5e9e858 100644 --- a/arch/loongarch/include/asm/tlb.h +++ b/arch/loongarch/include/asm/tlb.h @@ -132,8 +132,6 @@ static __always_inline void invtlb_all(u32 op, u32 info, u64 addr) ); } -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) - static void tlb_flush(struct mmu_gather *tlb); #define tlb_flush tlb_flush diff --git a/arch/loongarch/include/asm/topology.h b/arch/loongarch/include/asm/topology.h index 66128dec0bf6..50273c9187d0 100644 --- a/arch/loongarch/include/asm/topology.h +++ b/arch/loongarch/include/asm/topology.h @@ -8,6 +8,7 @@ #include <linux/smp.h> #ifdef CONFIG_NUMA +#include <asm/numa.h> extern cpumask_t cpus_on_node[]; diff --git a/arch/loongarch/include/asm/unistd.h b/arch/loongarch/include/asm/unistd.h index cfddb0116a8c..e2c0f3d86c7b 100644 --- a/arch/loongarch/include/asm/unistd.h +++ b/arch/loongarch/include/asm/unistd.h @@ -8,4 +8,7 @@ #include <uapi/asm/unistd.h> +#define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SYS_CLONE + #define NR_syscalls (__NR_syscalls) diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h index b9dce87afd2e..40a6763c5aec 100644 --- a/arch/loongarch/include/asm/unwind.h +++ b/arch/loongarch/include/asm/unwind.h @@ -16,6 +16,7 @@ enum unwinder_type { UNWINDER_GUESS, UNWINDER_PROLOGUE, + UNWINDER_ORC, }; struct unwind_state { @@ -24,7 +25,7 @@ struct unwind_state { struct task_struct *task; bool first, error, reset; int graph_idx; - unsigned long sp, pc, ra; + unsigned long sp, fp, pc, ra; }; bool default_next_frame(struct unwind_state *state); @@ -61,14 +62,17 @@ static __always_inline void __unwind_start(struct unwind_state *state, state->sp = regs->regs[3]; state->pc = regs->csr_era; state->ra = regs->regs[1]; + state->fp = regs->regs[22]; } else if (task && task != current) { state->sp = thread_saved_fp(task); state->pc = thread_saved_ra(task); state->ra = 0; + state->fp = 0; } else { state->sp = (unsigned long)__builtin_frame_address(0); state->pc = (unsigned long)__builtin_return_address(0); state->ra = 0; + state->fp = 0; } state->task = task; get_stack_info(state->sp, state->task, &state->stack_info); @@ -77,6 +81,18 @@ static __always_inline void __unwind_start(struct unwind_state *state, static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state) { - return unwind_done(state) ? 0 : state->pc; + if (unwind_done(state)) + return 0; + + return __kernel_text_address(state->pc) ? state->pc : 0; } + +#ifdef CONFIG_UNWINDER_ORC +void unwind_init(void); +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); +#else +static inline void unwind_init(void) {} +static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} +#endif + #endif /* _ASM_UNWIND_H */ diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h new file mode 100644 index 000000000000..a01086ad9dde --- /dev/null +++ b/arch/loongarch/include/asm/unwind_hints.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_UNWIND_HINTS_H +#define _ASM_LOONGARCH_UNWIND_HINTS_H + +#include <linux/objtool.h> +#include <asm/orc_types.h> + +#ifdef __ASSEMBLY__ + +.macro UNWIND_HINT_UNDEFINED + UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED +.endm + +.macro UNWIND_HINT_END_OF_STACK + UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK +.endm + +.macro UNWIND_HINT_REGS + UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_REGS +.endm + +.macro UNWIND_HINT_FUNC + UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL +.endm + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */ diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h index c8f59983f702..99a0d198927f 100644 --- a/arch/loongarch/include/asm/uprobes.h +++ b/arch/loongarch/include/asm/uprobes.h @@ -9,10 +9,10 @@ typedef u32 uprobe_opcode_t; #define MAX_UINSN_BYTES 8 #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES -#define UPROBE_SWBP_INSN larch_insn_gen_break(BRK_UPROBE_BP) +#define UPROBE_SWBP_INSN __emit_break(BRK_UPROBE_BP) #define UPROBE_SWBP_INSN_SIZE LOONGARCH_INSN_SIZE -#define UPROBE_XOLBP_INSN larch_insn_gen_break(BRK_UPROBE_XOLBP) +#define UPROBE_XOLBP_INSN __emit_break(BRK_UPROBE_XOLBP) struct arch_uprobe { unsigned long resume_era; diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h new file mode 100644 index 000000000000..e80f3c4ac748 --- /dev/null +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLY__ + +#include <asm/unistd.h> +#include <asm/vdso/vdso.h> + +static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, unsigned int _flags) +{ + register long ret asm("a0"); + register long nr asm("a7") = __NR_getrandom; + register void *buffer asm("a0") = _buffer; + register size_t len asm("a1") = _len; + register unsigned int flags asm("a2") = _flags; + + asm volatile( + " syscall 0\n" + : "+r" (ret) + : "r" (nr), "r" (buffer), "r" (len), "r" (flags) + : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", + "memory"); + + return ret; +} + +static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) +{ + return &_loongarch_data.rng_data; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 89e6b222c2f2..7eb3f041af76 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -91,14 +91,14 @@ static inline bool loongarch_vdso_hres_capable(void) static __always_inline const struct vdso_data *__arch_get_vdso_data(void) { - return (const struct vdso_data *)get_vdso_data(); + return _vdso_data; } #ifdef CONFIG_TIME_NS static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { - return (const struct vdso_data *)(get_vdso_data() + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE); + return _timens_data; } #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h index 5a12309d9fb5..1c183a9b2115 100644 --- a/arch/loongarch/include/asm/vdso/vdso.h +++ b/arch/loongarch/include/asm/vdso/vdso.h @@ -4,6 +4,9 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#ifndef _ASM_VDSO_VDSO_H +#define _ASM_VDSO_VDSO_H + #ifndef __ASSEMBLY__ #include <asm/asm.h> @@ -16,6 +19,7 @@ struct vdso_pcpu_data { struct loongarch_vdso_data { struct vdso_pcpu_data pdata[NR_CPUS]; + struct vdso_rng_data rng_data; }; /* @@ -44,22 +48,8 @@ enum vvar_pages { #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -static inline unsigned long get_vdso_base(void) -{ - unsigned long addr; - - __asm__( - " la.pcrel %0, _start\n" - : "=r" (addr) - : - :); - - return addr; -} - -static inline unsigned long get_vdso_data(void) -{ - return get_vdso_base() - VVAR_SIZE; -} +extern struct loongarch_vdso_data _loongarch_data __attribute__((visibility("hidden"))); #endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h index 5de615383a22..8987e951d0a9 100644 --- a/arch/loongarch/include/asm/vdso/vsyscall.h +++ b/arch/loongarch/include/asm/vdso/vsyscall.h @@ -4,14 +4,11 @@ #ifndef __ASSEMBLY__ -#include <linux/timekeeper_internal.h> #include <vdso/datapage.h> extern struct vdso_data *vdso_data; +extern struct vdso_rng_data *vdso_rng_data; -/* - * Update the vDSO data page to keep in sync with kernel timekeeping. - */ static __always_inline struct vdso_data *__loongarch_get_k_vdso_data(void) { @@ -19,6 +16,13 @@ struct vdso_data *__loongarch_get_k_vdso_data(void) } #define __arch_get_k_vdso_data __loongarch_get_k_vdso_data +static __always_inline +struct vdso_rng_data *__loongarch_get_k_vdso_rng_data(void) +{ + return vdso_rng_data; +} +#define __arch_get_k_vdso_rng_data __loongarch_get_k_vdso_rng_data + /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/loongarch/include/asm/fb.h b/arch/loongarch/include/asm/video.h index 0b218b10a9ec..9f76845f2d4f 100644 --- a/arch/loongarch/include/asm/fb.h +++ b/arch/loongarch/include/asm/video.h @@ -2,8 +2,8 @@ /* * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ -#ifndef _ASM_FB_H_ -#define _ASM_FB_H_ +#ifndef _ASM_VIDEO_H_ +#define _ASM_VIDEO_H_ #include <linux/compiler.h> #include <linux/string.h> @@ -26,6 +26,6 @@ static inline void fb_memset_io(volatile void __iomem *addr, int c, size_t n) } #define fb_memset fb_memset_io -#include <asm-generic/fb.h> +#include <asm-generic/video.h> -#endif /* _ASM_FB_H_ */ +#endif /* _ASM_VIDEO_H_ */ diff --git a/arch/loongarch/include/uapi/asm/Kbuild b/arch/loongarch/include/uapi/asm/Kbuild index 4aa680ca2e5f..517761419999 100644 --- a/arch/loongarch/include/uapi/asm/Kbuild +++ b/arch/loongarch/include/uapi/asm/Kbuild @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -generic-y += kvm_para.h +syscall-y += unistd_64.h diff --git a/arch/loongarch/include/uapi/asm/hwcap.h b/arch/loongarch/include/uapi/asm/hwcap.h index 6955a7cb2c65..2b34e56cfa9e 100644 --- a/arch/loongarch/include/uapi/asm/hwcap.h +++ b/arch/loongarch/include/uapi/asm/hwcap.h @@ -17,5 +17,6 @@ #define HWCAP_LOONGARCH_LBT_ARM (1 << 11) #define HWCAP_LOONGARCH_LBT_MIPS (1 << 12) #define HWCAP_LOONGARCH_PTW (1 << 13) +#define HWCAP_LOONGARCH_LSPW (1 << 14) #endif /* _UAPI_ASM_HWCAP_H */ diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h index 923d0bd38294..5f354f5c6847 100644 --- a/arch/loongarch/include/uapi/asm/kvm.h +++ b/arch/loongarch/include/uapi/asm/kvm.h @@ -8,17 +8,19 @@ #include <linux/types.h> +#define __KVM_HAVE_IRQ_LINE + /* * KVM LoongArch specific structures and definitions. * * Some parts derived from the x86 version of this file. */ -#define __KVM_HAVE_READONLY_MEM - #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_DIRTY_LOG_PAGE_OFFSET 64 +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 + /* * for KVM_GET_REGS and KVM_SET_REGS */ @@ -64,6 +66,7 @@ struct kvm_fpu { #define KVM_REG_LOONGARCH_KVM (KVM_REG_LOONGARCH | 0x20000ULL) #define KVM_REG_LOONGARCH_FPSIMD (KVM_REG_LOONGARCH | 0x30000ULL) #define KVM_REG_LOONGARCH_CPUCFG (KVM_REG_LOONGARCH | 0x40000ULL) +#define KVM_REG_LOONGARCH_LBT (KVM_REG_LOONGARCH | 0x50000ULL) #define KVM_REG_LOONGARCH_MASK (KVM_REG_LOONGARCH | 0x70000ULL) #define KVM_CSR_IDX_MASK 0x7fff #define KVM_CPUCFG_IDX_MASK 0x7fff @@ -74,12 +77,37 @@ struct kvm_fpu { #define KVM_REG_LOONGARCH_COUNTER (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 1) #define KVM_REG_LOONGARCH_VCPU_RESET (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 2) +/* Debugging: Special instruction for software breakpoint */ +#define KVM_REG_LOONGARCH_DEBUG_INST (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 3) + +/* LBT registers */ +#define KVM_REG_LOONGARCH_LBT_SCR0 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_LOONGARCH_LBT_SCR1 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 2) +#define KVM_REG_LOONGARCH_LBT_SCR2 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 3) +#define KVM_REG_LOONGARCH_LBT_SCR3 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 4) +#define KVM_REG_LOONGARCH_LBT_EFLAGS (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 5) +#define KVM_REG_LOONGARCH_LBT_FTOP (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 6) #define LOONGARCH_REG_SHIFT 3 #define LOONGARCH_REG_64(TYPE, REG) (TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT)) #define KVM_IOC_CSRID(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG) #define KVM_IOC_CPUCFG(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG) + +/* Device Control API on vm fd */ +#define KVM_LOONGARCH_VM_FEAT_CTRL 0 +#define KVM_LOONGARCH_VM_FEAT_LSX 0 +#define KVM_LOONGARCH_VM_FEAT_LASX 1 +#define KVM_LOONGARCH_VM_FEAT_X86BT 2 +#define KVM_LOONGARCH_VM_FEAT_ARMBT 3 +#define KVM_LOONGARCH_VM_FEAT_MIPSBT 4 +#define KVM_LOONGARCH_VM_FEAT_PMU 5 +#define KVM_LOONGARCH_VM_FEAT_PV_IPI 6 +#define KVM_LOONGARCH_VM_FEAT_PV_STEALTIME 7 + +/* Device Control API on vcpu fd */ #define KVM_LOONGARCH_VCPU_CPUCFG 0 +#define KVM_LOONGARCH_VCPU_PVTIME_CTRL 1 +#define KVM_LOONGARCH_VCPU_PVTIME_GPA 0 struct kvm_debug_exit_arch { }; @@ -106,4 +134,22 @@ struct kvm_iocsr_entry { #define KVM_IRQCHIP_NUM_PINS 64 #define KVM_MAX_CORES 256 +#define KVM_DEV_LOONGARCH_IPI_GRP_REGS 0x40000001 + +#define KVM_DEV_LOONGARCH_EXTIOI_GRP_REGS 0x40000002 + +#define KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS 0x40000003 +#define KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU 0x0 +#define KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE 0x1 +#define KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE 0x2 + +#define KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL 0x40000004 +#define KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU 0x0 +#define KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE 0x1 +#define KVM_DEV_LOONGARCH_EXTIOI_CTRL_LOAD_FINISHED 0x3 + +#define KVM_DEV_LOONGARCH_PCH_PIC_GRP_REGS 0x40000005 +#define KVM_DEV_LOONGARCH_PCH_PIC_GRP_CTRL 0x40000006 +#define KVM_DEV_LOONGARCH_PCH_PIC_CTRL_INIT 0 + #endif /* __UAPI_ASM_LOONGARCH_KVM_H */ diff --git a/arch/loongarch/include/uapi/asm/kvm_para.h b/arch/loongarch/include/uapi/asm/kvm_para.h new file mode 100644 index 000000000000..76d802ef01ce --- /dev/null +++ b/arch/loongarch/include/uapi/asm/kvm_para.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_KVM_PARA_H +#define _UAPI_ASM_KVM_PARA_H + +#include <linux/types.h> + +/* + * CPUCFG index area: 0x40000000 -- 0x400000ff + * SW emulation for KVM hypervirsor + */ +#define CPUCFG_KVM_BASE 0x40000000 +#define CPUCFG_KVM_SIZE 0x100 +#define CPUCFG_KVM_SIG (CPUCFG_KVM_BASE + 0) +#define KVM_SIGNATURE "KVM\0" +#define CPUCFG_KVM_FEATURE (CPUCFG_KVM_BASE + 4) +#define KVM_FEATURE_IPI 1 +#define KVM_FEATURE_STEAL_TIME 2 +/* BIT 24 - 31 are features configurable by user space vmm */ +#define KVM_FEATURE_VIRT_EXTIOI 24 +#define KVM_FEATURE_USER_HCALL 25 + +#endif /* _UAPI_ASM_KVM_PARA_H */ diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index ac915f841650..aafb3cd9e943 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -72,6 +72,16 @@ struct user_watch_state { } dbg_regs[8]; }; +struct user_watch_state_v2 { + uint64_t dbg_info; + struct { + uint64_t addr; + uint64_t mask; + uint32_t ctrl; + uint32_t pad; + } dbg_regs[14]; +}; + #define PTRACE_SYSEMU 0x1f #define PTRACE_SYSEMU_SINGLESTEP 0x20 diff --git a/arch/loongarch/include/uapi/asm/sigcontext.h b/arch/loongarch/include/uapi/asm/sigcontext.h index 6c22f616b8f1..5cd121275bac 100644 --- a/arch/loongarch/include/uapi/asm/sigcontext.h +++ b/arch/loongarch/include/uapi/asm/sigcontext.h @@ -9,7 +9,6 @@ #define _UAPI_ASM_SIGCONTEXT_H #include <linux/types.h> -#include <linux/posix_types.h> /* FP context was used */ #define SC_USED_FP (1 << 0) diff --git a/arch/loongarch/include/uapi/asm/unistd.h b/arch/loongarch/include/uapi/asm/unistd.h index fcb668984f03..1f01980f9c94 100644 --- a/arch/loongarch/include/uapi/asm/unistd.h +++ b/arch/loongarch/include/uapi/asm/unistd.h @@ -1,5 +1,3 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#define __ARCH_WANT_SYS_CLONE -#define __ARCH_WANT_SYS_CLONE3 -#include <asm-generic/unistd.h> +#include <asm/unistd_64.h> diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 3c808c680370..4853e8b04c6f 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -3,12 +3,14 @@ # Makefile for the Linux/LoongArch kernel. # +OBJECT_FILES_NON_STANDARD_head.o := y + extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ - traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ + traps.o irq.o idle.o process.o dma.o mem.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unwind.o + alternative.o kdebugfs.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o @@ -21,6 +23,7 @@ obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o CFLAGS_module.o += $(call cc-option,-Wno-override-init,) CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,) +CFLAGS_traps.o += $(call cc-option,-Wno-override-init,) CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_FUNCTION_TRACER @@ -48,6 +51,7 @@ obj-$(CONFIG_MODULES) += module.o module-sections.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_PROC_FS) += proc.o +obj-$(CONFIG_PARAVIRT) += paravirt.o obj-$(CONFIG_SMP) += smp.o @@ -62,6 +66,7 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_regs.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o diff --git a/arch/loongarch/kernel/Makefile.syscalls b/arch/loongarch/kernel/Makefile.syscalls new file mode 100644 index 000000000000..ab7d9baa2915 --- /dev/null +++ b/arch/loongarch/kernel/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +# No special ABIs on loongarch so far +syscall_abis_64 += diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 5cf59c617126..1120ac2824f6 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/acpi.h> +#include <linux/efi-bgrt.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/memblock.h> @@ -58,38 +59,47 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) } #ifdef CONFIG_SMP -static int set_processor_mask(u32 id, u32 flags) +static int set_processor_mask(u32 id, u32 pass) { + int cpu = -1, cpuid = id; - int cpu, cpuid = id; - - if (num_processors >= nr_cpu_ids) { - pr_warn(PREFIX "nr_cpus/possible_cpus limit of %i reached." - " processor 0x%x ignored.\n", nr_cpu_ids, cpuid); + if (num_processors >= NR_CPUS) { + pr_warn(PREFIX "nr_cpus limit of %i reached." + " processor 0x%x ignored.\n", NR_CPUS, cpuid); return -ENODEV; } + if (cpuid == loongson_sysconf.boot_cpu_id) cpu = 0; - else - cpu = cpumask_next_zero(-1, cpu_present_mask); - if (flags & ACPI_MADT_ENABLED) { + switch (pass) { + case 1: /* Pass 1 handle enabled processors */ + if (cpu < 0) + cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS); num_processors++; - set_cpu_possible(cpu, true); set_cpu_present(cpu, true); - __cpu_number_map[cpuid] = cpu; - __cpu_logical_map[cpu] = cpuid; - } else + break; + case 2: /* Pass 2 handle disabled processors */ + if (cpu < 0) + cpu = find_first_zero_bit(cpumask_bits(cpu_possible_mask), NR_CPUS); disabled_cpus++; + break; + default: + return cpu; + } + + set_cpu_possible(cpu, true); + __cpu_number_map[cpuid] = cpu; + __cpu_logical_map[cpu] = cpuid; return cpu; } #endif static int __init -acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long end) +acpi_parse_p1_processor(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_core_pic *processor = NULL; @@ -100,13 +110,30 @@ acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long en acpi_table_print_madt_entry(&header->common); #ifdef CONFIG_SMP acpi_core_pic[processor->core_id] = *processor; - set_processor_mask(processor->core_id, processor->flags); + if (processor->flags & ACPI_MADT_ENABLED) + set_processor_mask(processor->core_id, 1); #endif return 0; } static int __init +acpi_parse_p2_processor(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_core_pic *processor = NULL; + + processor = (struct acpi_madt_core_pic *)header; + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + +#ifdef CONFIG_SMP + if (!(processor->flags & ACPI_MADT_ENABLED)) + set_processor_mask(processor->core_id, 2); +#endif + + return 0; +} +static int __init acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long end) { static int core = 0; @@ -133,7 +160,10 @@ static void __init acpi_process_madt(void) } #endif acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC, - acpi_parse_processor, MAX_CORE_PIC); + acpi_parse_p1_processor, MAX_CORE_PIC); + + acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC, + acpi_parse_p2_processor, MAX_CORE_PIC); acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, acpi_parse_eio_master, MAX_IO_PICS); @@ -202,6 +232,9 @@ void __init acpi_boot_table_init(void) /* Do not enable ACPI SPCR console by default */ acpi_parse_spcr(earlycon_acpi_spcr_enable, false); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); + return; fdt_earlycon: @@ -216,18 +249,6 @@ static __init int setup_node(int pxm) return acpi_map_pxm_to_node(pxm); } -/* - * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for - * I/O localities since SRAT does not list them. I/O localities are - * not supported at this point. - */ -unsigned int numa_distance_cnt; - -static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit) -{ - return slit->locality_count; -} - void __init numa_set_distance(int from, int to, int distance) { if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) { @@ -296,6 +317,10 @@ static int __ref acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) int nid; nid = acpi_get_node(handle); + + if (nid != NUMA_NO_NODE) + nid = early_cpu_to_node(cpu); + if (nid != NUMA_NO_NODE) { set_cpuid_to_node(physid, nid); node_set(nid, numa_nodes_parsed); @@ -310,12 +335,14 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu { int cpu; - cpu = set_processor_mask(physid, ACPI_MADT_ENABLED); - if (cpu < 0) { + cpu = cpu_number_map(physid); + if (cpu < 0 || cpu >= nr_cpu_ids) { pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); - return cpu; + return -ERANGE; } + num_processors++; + set_cpu_present(cpu, true); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index bee9f7a3108f..8be1c38ad8eb 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -14,6 +14,7 @@ #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/ftrace.h> +#include <vdso/datapage.h> static void __used output_ptreg_defines(void) { @@ -279,18 +280,6 @@ static void __used output_pbe_defines(void) } #endif -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __used output_fgraph_ret_regs_defines(void) -{ - COMMENT("LoongArch fgraph_ret_regs offsets."); - OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]); - OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]); - OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); - BLANK(); -} -#endif - static void __used output_kvm_defines(void) { COMMENT("KVM/LoongArch Specific offsets."); @@ -321,3 +310,11 @@ static void __used output_kvm_defines(void) OFFSET(KVM_GPGD, kvm, arch.pgd); BLANK(); } + +static void __used output_vdso_defines(void) +{ + COMMENT("LoongArch vDSO offsets."); + + DEFINE(__VVAR_PAGES, VVAR_NR_PAGES); + BLANK(); +} diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index c7988f757281..8e231b0d2cd6 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -51,6 +51,12 @@ static void cache_cpumap_setup(unsigned int cpu) continue; sib_leaf = sib_cpu_ci->info_list + index; + /* SMT cores share all caches */ + if (cpus_are_siblings(i, cpu)) { + cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); + cpumask_set_cpu(i, &this_leaf->shared_cpu_map); + } + /* Node's cores share shared caches */ if (cache_leaves_are_shared(this_leaf, sib_leaf)) { cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); cpumask_set_cpu(i, &this_leaf->shared_cpu_map); diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 55320813ee08..fedaa67cde41 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -91,12 +91,30 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) unsigned int config; unsigned long asid_mask; - c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | - LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; + c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_VINT; elf_hwcap = HWCAP_LOONGARCH_CPUCFG; config = read_cpucfg(LOONGARCH_CPUCFG1); + + switch (config & CPUCFG1_ISA) { + case 0: + set_isa(c, LOONGARCH_CPU_ISA_LA32R); + break; + case 1: + set_isa(c, LOONGARCH_CPU_ISA_LA32S); + break; + case 2: + set_isa(c, LOONGARCH_CPU_ISA_LA64); + break; + default: + pr_warn("Warning: unknown ISA level\n"); + } + + if (config & CPUCFG1_PAGING) + c->options |= LOONGARCH_CPU_TLB; + if (config & CPUCFG1_IOCSR) + c->options |= LOONGARCH_CPU_IOCSR; if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; @@ -106,7 +124,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) elf_hwcap |= HWCAP_LOONGARCH_CRC32; } - config = read_cpucfg(LOONGARCH_CPUCFG2); if (config & CPUCFG2_LAM) { c->options |= LOONGARCH_CPU_LAM; @@ -140,6 +157,10 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_PTW; elf_hwcap |= HWCAP_LOONGARCH_PTW; } + if (config & CPUCFG2_LSPW) { + c->options |= LOONGARCH_CPU_LSPW; + elf_hwcap |= HWCAP_LOONGARCH_LSPW; + } if (config & CPUCFG2_LVZP) { c->options |= LOONGARCH_CPU_LVZ; elf_hwcap |= HWCAP_LOONGARCH_LVZ; @@ -163,26 +184,13 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) if (config & CPUCFG6_PMP) c->options |= LOONGARCH_CPU_PMP; - config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); - if (config & IOCSRF_CSRIPI) - c->options |= LOONGARCH_CPU_CSRIPI; - if (config & IOCSRF_EXTIOI) - c->options |= LOONGARCH_CPU_EXTIOI; - if (config & IOCSRF_FREQSCALE) - c->options |= LOONGARCH_CPU_SCALEFREQ; - if (config & IOCSRF_FLATMODE) - c->options |= LOONGARCH_CPU_FLATMODE; - if (config & IOCSRF_EIODECODE) - c->options |= LOONGARCH_CPU_EIODECODE; - if (config & IOCSRF_VM) - c->options |= LOONGARCH_CPU_HYPERVISOR; - config = csr_read32(LOONGARCH_CSR_ASID); config = (config & CSR_ASID_BIT) >> CSR_ASID_BIT_SHIFT; asid_mask = GENMASK(config - 1, 0); set_cpu_asid_mask(c, asid_mask); config = read_csr_prcfg1(); + c->timerbits = (config & CSR_CONF1_TMRBITS) >> CSR_CONF1_TMRBITS_SHIFT; c->ksave_mask = GENMASK((config & CSR_CONF1_KSNUM) - 1, 0); c->ksave_mask &= ~(EXC_KSAVE_MASK | PERCPU_KSAVE_MASK | KVM_KSAVE_MASK); @@ -209,6 +217,9 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) default: pr_warn("Warning: unknown TLB type\n"); } + + if (get_num_brps() + get_num_wrps()) + c->options |= LOONGARCH_CPU_WATCH; } #define MAX_NAME_LEN 32 @@ -219,52 +230,67 @@ static char cpu_full_name[MAX_NAME_LEN] = " - "; static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int cpu) { + uint32_t config; uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]); uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]); + const char *core_name = "Unknown"; - if (!__cpu_full_name[cpu]) - __cpu_full_name[cpu] = cpu_full_name; - - *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); - *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); - - switch (c->processor_id & PRID_SERIES_MASK) { - case PRID_SERIES_LA132: + switch (BIT(fls(c->isa_level) - 1)) { + case LOONGARCH_CPU_ISA_LA32R: + case LOONGARCH_CPU_ISA_LA32S: c->cputype = CPU_LOONGSON32; - set_isa(c, LOONGARCH_CPU_ISA_LA32S); __cpu_family[cpu] = "Loongson-32bit"; - pr_info("32-bit Loongson Processor probed (LA132 Core)\n"); break; - case PRID_SERIES_LA264: + case LOONGARCH_CPU_ISA_LA64: c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA264 Core)\n"); + break; + } + + switch (c->processor_id & PRID_SERIES_MASK) { + case PRID_SERIES_LA132: + core_name = "LA132"; + break; + case PRID_SERIES_LA264: + core_name = "LA264"; break; case PRID_SERIES_LA364: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA364 Core)\n"); + core_name = "LA364"; break; case PRID_SERIES_LA464: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA464 Core)\n"); + core_name = "LA464"; break; case PRID_SERIES_LA664: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA664 Core)\n"); + core_name = "LA664"; break; - default: /* Default to 64 bit */ - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (Unknown Core)\n"); } + + pr_info("%s Processor probed (%s Core)\n", __cpu_family[cpu], core_name); + + if (!cpu_has_iocsr) + return; + + if (!__cpu_full_name[cpu]) + __cpu_full_name[cpu] = cpu_full_name; + + *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); + *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); + + config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); + if (config & IOCSRF_CSRIPI) + c->options |= LOONGARCH_CPU_CSRIPI; + if (config & IOCSRF_EXTIOI) + c->options |= LOONGARCH_CPU_EXTIOI; + if (config & IOCSRF_FREQSCALE) + c->options |= LOONGARCH_CPU_SCALEFREQ; + if (config & IOCSRF_FLATMODE) + c->options |= LOONGARCH_CPU_FLATMODE; + if (config & IOCSRF_EIODECODE) + c->options |= LOONGARCH_CPU_EIODECODE; + if (config & IOCSRF_AVEC) + c->options |= LOONGARCH_CPU_AVECINT; + if (config & IOCSRF_VM) + c->options |= LOONGARCH_CPU_HYPERVISOR; } #ifdef CONFIG_64BIT diff --git a/arch/loongarch/kernel/dma.c b/arch/loongarch/kernel/dma.c index 7a9c6a9dd2d0..429555fb4e13 100644 --- a/arch/loongarch/kernel/dma.c +++ b/arch/loongarch/kernel/dma.c @@ -8,17 +8,12 @@ void acpi_arch_dma_setup(struct device *dev) { int ret; - u64 mask, end = 0; + u64 mask, end; const struct bus_dma_region *map = NULL; ret = acpi_dma_get_range(dev, &map); if (!ret && map) { - const struct bus_dma_region *r = map; - - for (end = 0; r->size; r++) { - if (r->dma_start + r->size - 1 > end) - end = r->dma_start + r->size - 1; - } + end = dma_range_map_max(map); mask = DMA_BIT_MASK(ilog2(end) + 1); dev->bus_dma_limit = end; diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 000825406c1f..de21e72759ee 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -66,6 +66,12 @@ void __init efi_runtime_init(void) set_bit(EFI_RUNTIME_SERVICES, &efi.flags); } +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES) && + (acpi_gbl_reduced_hardware || acpi_no_s5); +} + unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) @@ -89,7 +95,7 @@ static void __init init_screen_info(void) memset(si, 0, sizeof(*si)); early_memunmap(si, sizeof(*si)); - memblock_reserve(screen_info.lfb_base, screen_info.lfb_size); + memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size); } void __init efi_init(void) diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index 1ec8e4c4cc2b..48e7e34e355e 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -14,11 +14,13 @@ #include <asm/regdef.h> #include <asm/stackframe.h> #include <asm/thread_info.h> +#include <asm/unwind_hints.h> .text .cfi_sections .debug_frame .align 5 SYM_CODE_START(handle_syscall) + UNWIND_HINT_UNDEFINED csrrd t0, PERCPU_BASE_KS la.pcrel t1, kernelsp add.d t1, t1, t0 @@ -57,6 +59,7 @@ SYM_CODE_START(handle_syscall) cfi_st fp, PT_R22 SAVE_STATIC + UNWIND_HINT_REGS #ifdef CONFIG_KGDB li.w t1, CSR_CRMD_WE @@ -75,6 +78,7 @@ SYM_CODE_END(handle_syscall) _ASM_NOKPROBE(handle_syscall) SYM_CODE_START(ret_from_fork) + UNWIND_HINT_REGS bl schedule_tail # a0 = struct task_struct *prev move a0, sp bl syscall_exit_to_user_mode @@ -84,6 +88,7 @@ SYM_CODE_START(ret_from_fork) SYM_CODE_END(ret_from_fork) SYM_CODE_START(ret_from_kernel_thread) + UNWIND_HINT_REGS bl schedule_tail # a0 = struct task_struct *prev move a0, s1 jirl ra, s0, 0 diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index 4382e36ae3d4..6ab640101457 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -15,6 +15,7 @@ #include <asm/fpregdef.h> #include <asm/loongarch.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> #define FPU_REG_WIDTH 8 #define LSX_REG_WIDTH 16 @@ -526,3 +527,13 @@ SYM_FUNC_END(_restore_lasx_context) .L_fpu_fault: li.w a0, -EFAULT # failure jr ra + +#ifdef CONFIG_CPU_HAS_LBT +STACK_FRAME_NON_STANDARD _restore_fp +#ifdef CONFIG_CPU_HAS_LSX +STACK_FRAME_NON_STANDARD _restore_lsx +#endif +#ifdef CONFIG_CPU_HAS_LASX +STACK_FRAME_NON_STANDARD _restore_lasx +#endif +#endif diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 73858c9029cc..25c9a4cfd5fa 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -241,10 +241,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent) void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - struct pt_regs *regs = &fregs->regs; + struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *parent = (unsigned long *)®s->regs[1]; + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; - prepare_ftrace_return(ip, (unsigned long *)parent); + old = *parent; + + if (!function_graph_enter_regs(old, ip, 0, parent, fregs)) + *parent = return_hooker; } #else static int ftrace_modify_graph_caller(bool enable) @@ -287,6 +295,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; struct kprobe_ctlblk *kcb; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 2bb3aa2dcfcb..4f0912141781 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -18,27 +18,30 @@ .align 5 SYM_FUNC_START(__arch_cpu_idle) - /* start of rollback region */ - LONG_L t0, tp, TI_FLAGS - nop - andi t0, t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop + /* start of idle interrupt region */ + ori t0, zero, CSR_CRMD_IE + /* idle instruction needs irq enabled */ + csrxchg t0, t0, LOONGARCH_CSR_CRMD + /* + * If an interrupt lands here; between enabling interrupts above and + * going idle on the next instruction, we must *NOT* go idle since the + * interrupt could have set TIF_NEED_RESCHED or caused an timer to need + * reprogramming. Fall through -- see handle_vint() below -- and have + * the idle loop take care of things. + */ idle 0 - /* end of rollback region */ + /* end of idle interrupt region */ 1: jr ra SYM_FUNC_END(__arch_cpu_idle) SYM_CODE_START(handle_vint) + UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL - la_abs t1, __arch_cpu_idle + la_abs t1, 1b LONG_L t0, sp, PT_ERA - /* 32 byte rollback region */ - ori t0, t0, 0x1f - xori t0, t0, 0x1f + /* 3 instructions idle interrupt region */ + ori t0, t0, 0b1100 bne t0, t1, 1f LONG_S t0, sp, PT_ERA 1: move a0, sp @@ -49,6 +52,7 @@ SYM_CODE_START(handle_vint) SYM_CODE_END(handle_vint) SYM_CODE_START(except_vec_cex) + UNWIND_HINT_UNDEFINED b cache_parity_error SYM_CODE_END(except_vec_cex) @@ -67,6 +71,7 @@ SYM_CODE_END(except_vec_cex) .macro BUILD_HANDLER exception handler prep .align 5 SYM_CODE_START(handle_\exception) + UNWIND_HINT_UNDEFINED 666: BACKUP_T0T1 SAVE_ALL @@ -77,7 +82,9 @@ SYM_CODE_END(except_vec_cex) 668: RESTORE_ALL_AND_RET SYM_CODE_END(handle_\exception) + .pushsection ".data", "aw", %progbits SYM_DATA(unwind_hint_\exception, .word 668b - 666b) + .popsection .endm BUILD_HANDLER ade ade badv @@ -94,6 +101,7 @@ SYM_CODE_END(except_vec_cex) BUILD_HANDLER reserved reserved none /* others */ SYM_CODE_START(handle_sys) + UNWIND_HINT_UNDEFINED la_abs t0, handle_syscall jr t0 SYM_CODE_END(handle_sys) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index c4f7de2e2805..506a99a5bbc7 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -22,7 +22,7 @@ _head: .word MZ_MAGIC /* "MZ", MS-DOS header */ .org 0x8 - .dword kernel_entry /* Kernel entry point */ + .dword _kernel_entry /* Kernel entry point (physical address) */ .dword _kernel_asize /* Kernel image effective size */ .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ @@ -44,11 +44,7 @@ SYM_DATA(kernel_fsize, .long _kernel_fsize); SYM_CODE_START(kernel_entry) # kernel entry point /* Config direct window and set PG */ - li.d t0, CSR_DMW0_INIT # UC, PLV0, 0x8000 xxxx xxxx xxxx - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0, 0x9000 xxxx xxxx xxxx - csrwr t0, LOONGARCH_CSR_DMWIN1 - + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 /* Enable PG */ @@ -124,11 +120,8 @@ SYM_CODE_END(kernel_entry) * function after setting up the stack and tp registers. */ SYM_CODE_START(smpboot_entry) - li.d t0, CSR_DMW0_INIT # UC, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN1 + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 #ifdef CONFIG_PAGE_SIZE_4KB diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index fc55c4de2a11..c35f9bf38033 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -51,7 +51,13 @@ int hw_breakpoint_slots(int type) READ_WB_REG_CASE(OFF, 4, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 5, REG, T, VAL); \ READ_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - READ_WB_REG_CASE(OFF, 7, REG, T, VAL); + READ_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 13, REG, T, VAL); #define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL) \ WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL); \ @@ -61,7 +67,13 @@ int hw_breakpoint_slots(int type) WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL); \ WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL); \ - WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); + WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 8, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 9, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 10, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 11, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 12, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 13, REG, T, VAL); static u64 read_wb_reg(int reg, int n, int t) { @@ -174,11 +186,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) static int hw_breakpoint_control(struct perf_event *bp, enum hw_breakpoint_ops ops) { - u32 ctrl; + u32 ctrl, privilege; int i, max_slots, enable; + struct pt_regs *regs; struct perf_event **slots; struct arch_hw_breakpoint *info = counter_arch_bp(bp); + if (arch_check_bp_in_kernelspace(info)) + privilege = CTRL_PLV0_ENABLE; + else + privilege = CTRL_PLV3_ENABLE; + + /* Whether bp belongs to a task. */ + if (bp->hw.target) + regs = task_pt_regs(bp->hw.target); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { /* Breakpoint */ slots = this_cpu_ptr(bp_on_reg); @@ -197,31 +219,38 @@ static int hw_breakpoint_control(struct perf_event *bp, switch (ops) { case HW_BREAKPOINT_INSTALL: /* Set the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); - write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); - write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); - write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { - write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, privilege); } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH)) + regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, 0); - write_wb_reg(CSR_CFG_ADDR, i, 1, 0); - write_wb_reg(CSR_CFG_MASK, i, 0, 0); - write_wb_reg(CSR_CFG_MASK, i, 1, 0); - write_wb_reg(CSR_CFG_CTRL, i, 0, 0); - write_wb_reg(CSR_CFG_CTRL, i, 1, 0); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + } + if (bp->hw.target) + regs->csr_prmd &= ~CSR_PRMD_PWE; break; } @@ -283,7 +312,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset) + int *gen_len, int *gen_type) { /* Type */ switch (ctrl.type) { @@ -303,11 +332,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } - if (!ctrl.len) - return -EINVAL; - - *offset = __ffs(ctrl.len); - /* Len */ switch (ctrl.len) { case LOONGARCH_BREAKPOINT_LEN_1: @@ -386,21 +410,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, struct arch_hw_breakpoint *hw) { int ret; - u64 alignment_mask, offset; + u64 alignment_mask; /* Build the arch_hw_breakpoint. */ ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) - alignment_mask = 0x7; - else + if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { alignment_mask = 0x3; - offset = hw->address & alignment_mask; - - hw->address &= ~alignment_mask; - hw->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + } return 0; } @@ -471,12 +491,15 @@ void breakpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(bp_on_reg); for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { - bp = slots[i]; - if (bp == NULL) - continue; - perf_bp_event(bp, regs); + if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_FWPS); + update_bp_registers(regs, 0, 0); + } } - update_bp_registers(regs, 0, 0); } NOKPROBE_SYMBOL(breakpoint_handler); @@ -488,12 +511,15 @@ void watchpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { - wp = slots[i]; - if (wp == NULL) - continue; - perf_bp_event(wp, regs); + if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_MWPS); + update_bp_registers(regs, 0, 1); + } } - update_bp_registers(regs, 0, 1); } NOKPROBE_SYMBOL(watchpoint_handler); diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c index 0b5dd2faeb90..54b247d8cdb6 100644 --- a/arch/loongarch/kernel/idle.c +++ b/arch/loongarch/kernel/idle.c @@ -11,7 +11,6 @@ void __cpuidle arch_cpu_idle(void) { - raw_local_irq_enable(); - __arch_cpu_idle(); /* idle instruction needs irq enabled */ + __arch_cpu_idle(); raw_local_irq_disable(); } diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 3050329556d1..14d7d700bcb9 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -332,7 +332,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) return INSN_BREAK; } - emit_jirl(&insn, rj, rd, imm >> 2); + emit_jirl(&insn, rd, rj, imm >> 2); return insn.word; } diff --git a/arch/loongarch/kernel/io.c b/arch/loongarch/kernel/io.c deleted file mode 100644 index cb85bda5a6ad..000000000000 --- a/arch/loongarch/kernel/io.c +++ /dev/null @@ -1,94 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#include <linux/export.h> -#include <linux/types.h> -#include <linux/io.h> - -/* - * Copy data from IO memory space to "real" memory space. - */ -void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) -{ - while (count && !IS_ALIGNED((unsigned long)from, 8)) { - *(u8 *)to = __raw_readb(from); - from++; - to++; - count--; - } - - while (count >= 8) { - *(u64 *)to = __raw_readq(from); - from += 8; - to += 8; - count -= 8; - } - - while (count) { - *(u8 *)to = __raw_readb(from); - from++; - to++; - count--; - } -} -EXPORT_SYMBOL(__memcpy_fromio); - -/* - * Copy data from "real" memory space to IO memory space. - */ -void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count) -{ - while (count && !IS_ALIGNED((unsigned long)to, 8)) { - __raw_writeb(*(u8 *)from, to); - from++; - to++; - count--; - } - - while (count >= 8) { - __raw_writeq(*(u64 *)from, to); - from += 8; - to += 8; - count -= 8; - } - - while (count) { - __raw_writeb(*(u8 *)from, to); - from++; - to++; - count--; - } -} -EXPORT_SYMBOL(__memcpy_toio); - -/* - * "memset" on IO memory space. - */ -void __memset_io(volatile void __iomem *dst, int c, size_t count) -{ - u64 qc = (u8)c; - - qc |= qc << 8; - qc |= qc << 16; - qc |= qc << 32; - - while (count && !IS_ALIGNED((unsigned long)dst, 8)) { - __raw_writeb(c, dst); - dst++; - count--; - } - - while (count >= 8) { - __raw_writeq(qc, dst); - dst += 8; - count -= 8; - } - - while (count) { - __raw_writeb(c, dst); - dst++; - count--; - } -} -EXPORT_SYMBOL(__memset_io); diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 883e5066ae44..80946cafaec1 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -87,23 +87,21 @@ 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) +int __init arch_probe_nr_irqs(void) { - struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); + int nr_io_pics = bitmap_weight(loongson_sysconf.cores_io_master, NR_CPUS); - if (d) - return irq_create_mapping(d, INT_IPI); + if (!cpu_has_avecint) + irq_set_nr_irqs(64 + NR_VECTORS * nr_io_pics); + else + irq_set_nr_irqs(64 + NR_VECTORS * (nr_cpu_ids + nr_io_pics)); - return -EINVAL; + return NR_IRQS_LEGACY; } void __init init_IRQ(void) { int i; -#ifdef CONFIG_SMP - int r, ipi_irq; - static int ipi_dummy_dev; -#endif unsigned int order = get_order(IRQ_STACK_SIZE); struct page *page; @@ -113,18 +111,9 @@ void __init init_IRQ(void) init_vec_parent_group(); irqchip_init(); #ifdef CONFIG_SMP - 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, loongson_ipi_interrupt, "IPI", &ipi_dummy_dev); - if (r < 0) - panic("IPI IRQ request failed\n"); + mp_ops.init_ipi(); #endif - for (i = 0; i < NR_IRQS; i++) - irq_set_noprobe(i); - for_each_possible_cpu(i) { page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order); @@ -133,5 +122,5 @@ void __init init_IRQ(void) per_cpu(irq_stack, i), per_cpu(irq_stack, i) + IRQ_STACK_SIZE); } - set_csr_ecfg(ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC); + set_csr_ecfg(ECFGF_SIP0 | ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC); } diff --git a/arch/loongarch/kernel/kdebugfs.c b/arch/loongarch/kernel/kdebugfs.c new file mode 100644 index 000000000000..80cf64772399 --- /dev/null +++ b/arch/loongarch/kernel/kdebugfs.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/export.h> +#include <linux/debugfs.h> +#include <linux/kstrtox.h> +#include <asm/loongarch.h> + +struct dentry *arch_debugfs_dir; +EXPORT_SYMBOL(arch_debugfs_dir); + +static int sfb_state, tso_state; + +static void set_sfb_state(void *info) +{ + int val = *(int *)info << CSR_STFILL_SHIFT; + + csr_xchg32(val, CSR_STFILL, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t sfb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[32]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %x\nCurrent State: %x\n", sfb_state, state); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t sfb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: + on_each_cpu(set_sfb_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations sfb_fops = { + .read = sfb_read, + .write = sfb_write, + .open = simple_open, + .llseek = default_llseek +}; + +#define LDSTORDER_NLD_NST 0x0 /* 000 = No Load No Store */ +#define LDSTORDER_ALD_NST 0x1 /* 001 = All Load No Store */ +#define LDSTORDER_SLD_NST 0x3 /* 011 = Same Load No Store */ +#define LDSTORDER_NLD_AST 0x4 /* 100 = No Load All Store */ +#define LDSTORDER_ALD_AST 0x5 /* 101 = All Load All Store */ +#define LDSTORDER_SLD_AST 0x7 /* 111 = Same Load All Store */ + +static char *tso_hints[] = { + "No Load No Store", + "All Load No Store", + "Invalid Config", + "Same Load No Store", + "No Load All Store", + "All Load All Store", + "Invalid Config", + "Same Load All Store" +}; + +static void set_tso_state(void *info) +{ + int val = *(int *)info << CSR_LDSTORDER_SHIFT; + + csr_xchg32(val, CSR_LDSTORDER_MASK, LOONGARCH_CSR_IMPCTL1); +} + +static ssize_t tso_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + int s, state; + char str[240]; + + state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + + s = snprintf(str, sizeof(str), "Boot State: %d (%s)\n" + "Current State: %d (%s)\n\n" + "Available States:\n" + "0 (%s)\t" "1 (%s)\t" "3 (%s)\n" + "4 (%s)\t" "5 (%s)\t" "7 (%s)\n", + tso_state, tso_hints[tso_state], state, tso_hints[state], + tso_hints[0], tso_hints[1], tso_hints[3], tso_hints[4], tso_hints[5], tso_hints[7]); + + if (*ppos >= s) + return 0; + + s -= *ppos; + s = min_t(u32, s, count); + + if (copy_to_user(buf, &str[*ppos], s)) + return -EFAULT; + + *ppos += s; + + return s; +} + +static ssize_t tso_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + int state; + + if (kstrtoint_from_user(buf, count, 10, &state)) + return -EFAULT; + + switch (state) { + case 0: case 1: case 3: + case 4: case 5: case 7: + on_each_cpu(set_tso_state, &state, 1); + break; + default: + return -EINVAL; + } + + return count; +} + +static const struct file_operations tso_fops = { + .read = tso_read, + .write = tso_write, + .open = simple_open, + .llseek = default_llseek +}; + +static int __init arch_kdebugfs_init(void) +{ + unsigned int config = read_cpucfg(LOONGARCH_CPUCFG3); + + arch_debugfs_dir = debugfs_create_dir("loongarch", NULL); + + if (config & CPUCFG3_SFB) { + debugfs_create_file("sfb_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &sfb_state, &sfb_fops); + sfb_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT; + } + + if (config & (CPUCFG3_ALDORDER_CAP | CPUCFG3_ASTORDER_CAP)) { + debugfs_create_file("tso_state", S_IRUGO | S_IWUSR, + arch_debugfs_dir, &tso_state, &tso_fops); + tso_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT; + } + + return 0; +} +postcore_initcall(arch_kdebugfs_init); diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 17b040bd6067..8ba391cfabb0 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -4,8 +4,8 @@ #include <linux/preempt.h> #include <asm/break.h> -#define KPROBE_BP_INSN larch_insn_gen_break(BRK_KPROBE_BP) -#define KPROBE_SSTEPBP_INSN larch_insn_gen_break(BRK_KPROBE_SSTEPBP) +#define KPROBE_BP_INSN __emit_break(BRK_KPROBE_BP) +#define KPROBE_SSTEPBP_INSN __emit_break(BRK_KPROBE_SSTEPBP) DEFINE_PER_CPU(struct kprobe *, current_kprobe); DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S index 9c75120a26d8..001f061d226a 100644 --- a/arch/loongarch/kernel/lbt.S +++ b/arch/loongarch/kernel/lbt.S @@ -11,6 +11,7 @@ #include <asm/asm-offsets.h> #include <asm/errno.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> #define SCR_REG_WIDTH 8 @@ -153,3 +154,5 @@ SYM_FUNC_END(_restore_ftop_context) .L_lbt_fault: li.w a0, -EFAULT # failure jr ra + +STACK_FRAME_NON_STANDARD _restore_ftop_context diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c index 2dcb9e003657..f9381800e291 100644 --- a/arch/loongarch/kernel/machine_kexec.c +++ b/arch/loongarch/kernel/machine_kexec.c @@ -126,14 +126,14 @@ void kexec_reboot(void) /* All secondary cpus go to kexec_smp_wait */ if (smp_processor_id() > 0) { relocated_kexec_smp_wait(NULL); - unreachable(); + BUG(); } #endif do_kexec = (void *)reboot_code_buffer; do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry); - unreachable(); + BUG(); } @@ -225,6 +225,7 @@ void crash_smp_send_stop(void) void machine_shutdown(void) { +#ifdef CONFIG_SMP int cpu; /* All CPUs go to reboot_code_buffer */ @@ -232,7 +233,6 @@ void machine_shutdown(void) if (!cpu_online(cpu)) cpu_device_up(get_cpu_device(cpu)); -#ifdef CONFIG_SMP smp_call_function(kexec_shutdown_secondary, NULL, 0); #endif } diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index 3015896016a0..b6850503e061 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller) SYM_FUNC_END(ftrace_graph_caller) SYM_FUNC_START(return_to_handler) - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + /* Save return value regs */ + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler @@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler) /* Restore the real parent address: a0 -> ra */ move ra, a0 - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + /* Restore return value regs */ + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE + jr ra SYM_FUNC_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index 482aa553aa2d..d6b474ad1d5e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -73,6 +73,7 @@ SYM_FUNC_START(ftrace_stub) SYM_FUNC_END(ftrace_stub) SYM_CODE_START(ftrace_common) + UNWIND_HINT_UNDEFINED PTR_ADDI a0, ra, -8 /* arg0: ip */ move a1, t0 /* arg1: parent_ip */ la.pcrel t1, function_trace_op @@ -113,12 +114,14 @@ ftrace_common_return: SYM_CODE_END(ftrace_common) SYM_CODE_START(ftrace_caller) + UNWIND_HINT_UNDEFINED ftrace_regs_entry allregs=0 b ftrace_common SYM_CODE_END(ftrace_caller) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS SYM_CODE_START(ftrace_regs_caller) + UNWIND_HINT_UNDEFINED ftrace_regs_entry allregs=1 b ftrace_common SYM_CODE_END(ftrace_regs_caller) @@ -126,6 +129,7 @@ SYM_CODE_END(ftrace_regs_caller) #ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_CODE_START(ftrace_graph_caller) + UNWIND_HINT_UNDEFINED PTR_L a0, sp, PT_ERA PTR_ADDI a0, a0, -8 /* arg0: self_addr */ PTR_ADDI a1, sp, PT_R1 /* arg1: parent */ @@ -134,20 +138,21 @@ SYM_CODE_START(ftrace_graph_caller) SYM_CODE_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) + UNWIND_HINT_UNDEFINED /* Save return value regs */ - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler move ra, a0 /* Restore return value regs */ - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE jr ra SYM_CODE_END(return_to_handler) @@ -155,6 +160,7 @@ SYM_CODE_END(return_to_handler) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) + UNWIND_HINT_UNDEFINED jr t0 SYM_CODE_END(ftrace_stub_direct_tramp) #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c index b13b2858fe39..36d6d9eeb7c7 100644 --- a/arch/loongarch/kernel/module.c +++ b/arch/loongarch/kernel/module.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <asm/alternative.h> #include <asm/inst.h> +#include <asm/unwind.h> static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top) { @@ -489,12 +490,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, return 0; } -void *module_alloc(unsigned long size) -{ - return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); -} - static void module_init_ftrace_plt(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { @@ -515,15 +510,28 @@ static void module_init_ftrace_plt(const Elf_Ehdr *hdr, int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { - const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + const Elf_Shdr *s, *alt = NULL, *orc = NULL, *orc_ip = NULL, *ftrace = NULL; - for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { + for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { if (!strcmp(".altinstructions", secstrs + s->sh_name)) - apply_alternatives((void *)s->sh_addr, (void *)s->sh_addr + s->sh_size); + alt = s; + if (!strcmp(".orc_unwind", secstrs + s->sh_name)) + orc = s; + if (!strcmp(".orc_unwind_ip", secstrs + s->sh_name)) + orc_ip = s; if (!strcmp(".ftrace_trampoline", secstrs + s->sh_name)) - module_init_ftrace_plt(hdr, s, mod); + ftrace = s; } + if (alt) + apply_alternatives((void *)alt->sh_addr, (void *)alt->sh_addr + alt->sh_size); + + if (orc && orc_ip) + unwind_module_init(mod, (void *)orc_ip->sh_addr, orc_ip->sh_size, (void *)orc->sh_addr, orc->sh_size); + + if (ftrace) + module_init_ftrace_plt(hdr, ftrace, mod); + return 0; } diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 8fe21f868f72..84fe7f854820 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -27,10 +27,7 @@ #include <asm/time.h> int numa_off; -struct pglist_data *node_data[MAX_NUMNODES]; unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES]; - -EXPORT_SYMBOL(node_data); EXPORT_SYMBOL(node_distances); static struct numa_meminfo numa_meminfo; @@ -190,24 +187,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -static void __init alloc_node_data(int nid) -{ - void *nd; - unsigned long nd_pa; - size_t nd_sz = roundup(sizeof(pg_data_t), PAGE_SIZE); - - nd_pa = memblock_phys_alloc_try_nid(nd_sz, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu Byte for node_data (initial node: %d)\n", nd_sz, nid); - return; - } - - nd = __va(nd_pa); - - node_data[nid] = nd; - memset(nd, 0, sizeof(pg_data_t)); -} - static void __init node_mem_init(unsigned int node) { unsigned long start_pfn, end_pfn; diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c new file mode 100644 index 000000000000..e5a39bbad078 --- /dev/null +++ b/arch/loongarch/kernel/paravirt.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/irq_work.h> +#include <linux/jump_label.h> +#include <linux/kvm_para.h> +#include <linux/reboot.h> +#include <linux/static_call.h> +#include <asm/paravirt.h> + +static int has_steal_clock; +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; +static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); +DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key); + +static u64 native_steal_clock(int cpu) +{ + return 0; +} + +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); + +static bool steal_acc = true; + +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} +early_param("no-steal-acc", parse_no_stealacc); + +static u64 paravt_steal_clock(int cpu) +{ + int version; + u64 steal; + struct kvm_steal_time *src; + + src = &per_cpu(steal_time, cpu); + do { + + version = src->version; + virt_rmb(); /* Make sure that the version is read before the steal */ + steal = src->steal; + virt_rmb(); /* Make sure that the steal is read before the next version */ + + } while ((version & 1) || (version != src->version)); + + return steal; +} + +#ifdef CONFIG_SMP +static struct smp_ops native_ops; + +static void pv_send_ipi_single(int cpu, unsigned int action) +{ + int min, old; + irq_cpustat_t *info = &per_cpu(irq_stat, cpu); + + if (unlikely(action == ACTION_BOOT_CPU)) { + native_ops.send_ipi_single(cpu, action); + return; + } + + old = atomic_fetch_or(BIT(action), &info->message); + if (old) + return; + + min = cpu_logical_map(cpu); + kvm_hypercall3(KVM_HCALL_FUNC_IPI, 1, 0, min); +} + +#define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) + +static void pv_send_ipi_mask(const struct cpumask *mask, unsigned int action) +{ + int i, cpu, min = 0, max = 0, old; + __uint128_t bitmap = 0; + irq_cpustat_t *info; + + if (cpumask_empty(mask)) + return; + + if (unlikely(action == ACTION_BOOT_CPU)) { + native_ops.send_ipi_mask(mask, action); + return; + } + + action = BIT(action); + for_each_cpu(i, mask) { + info = &per_cpu(irq_stat, i); + old = atomic_fetch_or(action, &info->message); + if (old) + continue; + + cpu = cpu_logical_map(i); + if (!bitmap) { + min = max = cpu; + } else if (cpu < min && cpu > (max - KVM_IPI_CLUSTER_SIZE)) { + /* cpu < min, and bitmap still enough */ + bitmap <<= min - cpu; + min = cpu; + } else if (cpu > min && cpu < (min + KVM_IPI_CLUSTER_SIZE)) { + /* cpu > min, and bitmap still enough */ + max = cpu > max ? cpu : max; + } else { + /* + * With cpu, bitmap will exceed KVM_IPI_CLUSTER_SIZE, + * send IPI here directly and skip the remaining CPUs. + */ + kvm_hypercall3(KVM_HCALL_FUNC_IPI, (unsigned long)bitmap, + (unsigned long)(bitmap >> BITS_PER_LONG), min); + min = max = cpu; + bitmap = 0; + } + __set_bit(cpu - min, (unsigned long *)&bitmap); + } + + if (bitmap) + kvm_hypercall3(KVM_HCALL_FUNC_IPI, (unsigned long)bitmap, + (unsigned long)(bitmap >> BITS_PER_LONG), min); +} + +static irqreturn_t pv_ipi_interrupt(int irq, void *dev) +{ + u32 action; + irq_cpustat_t *info; + + /* Clear SWI interrupt */ + clear_csr_estat(1 << INT_SWI0); + info = this_cpu_ptr(&irq_stat); + action = atomic_xchg(&info->message, 0); + + if (action & SMP_RESCHEDULE) { + scheduler_ipi(); + info->ipi_irqs[IPI_RESCHEDULE]++; + } + + if (action & SMP_CALL_FUNCTION) { + generic_smp_call_function_interrupt(); + info->ipi_irqs[IPI_CALL_FUNCTION]++; + } + + if (action & SMP_IRQ_WORK) { + irq_work_run(); + info->ipi_irqs[IPI_IRQ_WORK]++; + } + + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + info->ipi_irqs[IPI_CLEAR_VECTOR]++; + } + + return IRQ_HANDLED; +} + +static void pv_init_ipi(void) +{ + int r, swi; + + /* Init native ipi irq for ACTION_BOOT_CPU */ + native_ops.init_ipi(); + swi = get_percpu_irq(INT_SWI0); + if (swi < 0) + panic("SWI0 IRQ mapping failed\n"); + irq_set_percpu_devid(swi); + r = request_percpu_irq(swi, pv_ipi_interrupt, "SWI0-IPI", &irq_stat); + if (r < 0) + panic("SWI0 IRQ request failed\n"); +} +#endif + +bool kvm_para_available(void) +{ + int config; + static int hypervisor_type; + + if (!cpu_has_hypervisor) + return false; + + if (!hypervisor_type) { + config = read_cpucfg(CPUCFG_KVM_SIG); + if (!memcmp(&config, KVM_SIGNATURE, 4)) + hypervisor_type = HYPERVISOR_KVM; + } + + return hypervisor_type == HYPERVISOR_KVM; +} + +unsigned int kvm_arch_para_features(void) +{ + static unsigned int feature; + + if (!kvm_para_available()) + return 0; + + if (!feature) + feature = read_cpucfg(CPUCFG_KVM_FEATURE); + + return feature; +} + +int __init pv_ipi_init(void) +{ + if (!kvm_para_has_feature(KVM_FEATURE_IPI)) + return 0; + +#ifdef CONFIG_SMP + native_ops = mp_ops; + mp_ops.init_ipi = pv_init_ipi; + mp_ops.send_ipi_single = pv_send_ipi_single; + mp_ops.send_ipi_mask = pv_send_ipi_mask; +#endif + + return 0; +} + +static int pv_enable_steal_time(void) +{ + int cpu = smp_processor_id(); + unsigned long addr; + struct kvm_steal_time *st; + + if (!has_steal_clock) + return -EPERM; + + st = &per_cpu(steal_time, cpu); + addr = per_cpu_ptr_to_phys(st); + + /* The whole structure kvm_steal_time should be in one page */ + if (PFN_DOWN(addr) != PFN_DOWN(addr + sizeof(*st))) { + pr_warn("Illegal PV steal time addr %lx\n", addr); + return -EFAULT; + } + + addr |= KVM_STEAL_PHYS_VALID; + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), addr); + + return 0; +} + +static void pv_disable_steal_time(void) +{ + if (has_steal_clock) + kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), 0); +} + +#ifdef CONFIG_SMP +static int pv_time_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_enable_steal_time(); + local_irq_restore(flags); + + return 0; +} + +static int pv_time_cpu_down_prepare(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + pv_disable_steal_time(); + local_irq_restore(flags); + + return 0; +} +#endif + +static void pv_cpu_reboot(void *unused) +{ + pv_disable_steal_time(); +} + +static int pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) +{ + on_each_cpu(pv_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block pv_reboot_nb = { + .notifier_call = pv_reboot_notify, +}; + +int __init pv_time_init(void) +{ + int r; + + if (!kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) + return 0; + + has_steal_clock = 1; + r = pv_enable_steal_time(); + if (r < 0) { + has_steal_clock = 0; + return 0; + } + register_reboot_notifier(&pv_reboot_nb); + +#ifdef CONFIG_SMP + r = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "loongarch/pv_time:online", + pv_time_cpu_online, pv_time_cpu_down_prepare); + if (r < 0) { + has_steal_clock = 0; + pr_err("Failed to install cpu hotplug callbacks\n"); + return r; + } +#endif + + static_call_update(pv_steal_clock, paravt_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); +#endif + + pr_info("Using paravirt steal-time\n"); + + return 0; +} + +int __init pv_spinlock_init(void) +{ + if (!cpu_has_hypervisor) + return 0; + + static_branch_enable(&virt_spin_lock_key); + + return 0; +} diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 0491bf453cd4..f86a4b838dd7 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -456,16 +456,6 @@ static void loongarch_pmu_disable(struct pmu *pmu) static DEFINE_MUTEX(pmu_reserve_mutex); static atomic_t active_events = ATOMIC_INIT(0); -static int get_pmc_irq(void) -{ - struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); - - if (d) - return irq_create_mapping(d, INT_PCOV); - - return -EINVAL; -} - static void reset_counters(void *arg); static int __hw_perf_event_init(struct perf_event *event); @@ -473,7 +463,7 @@ static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) { on_each_cpu(reset_counters, NULL, 1); - free_irq(get_pmc_irq(), &loongarch_pmu); + free_irq(get_percpu_irq(INT_PCOV), &loongarch_pmu); mutex_unlock(&pmu_reserve_mutex); } } @@ -562,7 +552,7 @@ static int loongarch_pmu_event_init(struct perf_event *event) if (event->cpu >= 0 && !cpu_online(event->cpu)) return -ENODEV; - irq = get_pmc_irq(); + irq = get_percpu_irq(INT_PCOV); flags = IRQF_PERCPU | IRQF_NOBALANCING | IRQF_NO_THREAD | IRQF_NO_SUSPEND | IRQF_SHARED; if (!atomic_inc_not_zero(&active_events)) { mutex_lock(&pmu_reserve_mutex); @@ -884,4 +874,4 @@ static int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 0d33cbc47e51..cea30768ae92 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -13,27 +13,12 @@ #include <asm/processor.h> #include <asm/time.h> -/* - * No lock; only written during early bootup by CPU 0. - */ -static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain); - -int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb) -{ - return raw_notifier_chain_register(&proc_cpuinfo_chain, nb); -} - -int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v) -{ - return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v); -} - static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; + unsigned int isa = cpu_data[n].isa_level; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; - struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args; #ifdef CONFIG_SMP if (!cpu_online(n)) @@ -64,9 +49,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) cpu_pabits + 1, cpu_vabits + 1); seq_printf(m, "ISA\t\t\t:"); - if (cpu_has_loongarch32) - seq_printf(m, " loongarch32"); - if (cpu_has_loongarch64) + if (isa & LOONGARCH_CPU_ISA_LA32R) + seq_printf(m, " loongarch32r"); + if (isa & LOONGARCH_CPU_ISA_LA32S) + seq_printf(m, " loongarch32s"); + if (isa & LOONGARCH_CPU_ISA_LA64) seq_printf(m, " loongarch64"); seq_printf(m, "\n"); @@ -81,26 +68,20 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_complex) seq_printf(m, " complex"); if (cpu_has_crypto) seq_printf(m, " crypto"); if (cpu_has_ptw) seq_printf(m, " ptw"); + if (cpu_has_lspw) seq_printf(m, " lspw"); if (cpu_has_lvz) seq_printf(m, " lvz"); if (cpu_has_lbt_x86) seq_printf(m, " lbt_x86"); if (cpu_has_lbt_arm) seq_printf(m, " lbt_arm"); if (cpu_has_lbt_mips) seq_printf(m, " lbt_mips"); seq_printf(m, "\n"); - seq_printf(m, "Hardware Watchpoint\t: %s", - cpu_has_watch ? "yes, " : "no\n"); + seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch)); if (cpu_has_watch) { - seq_printf(m, "iwatch count: %d, dwatch count: %d\n", + seq_printf(m, ", iwatch count: %d, dwatch count: %d", cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count); } - proc_cpuinfo_notifier_args.m = m; - proc_cpuinfo_notifier_args.n = n; - - raw_notifier_call_chain(&proc_cpuinfo_chain, 0, - &proc_cpuinfo_notifier_args); - - seq_printf(m, "\n"); + seq_printf(m, "\n\n"); return 0; } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index f2ff8b5d591e..6e58f65455c7 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -293,13 +293,15 @@ unsigned long stack_top(void) { unsigned long top = TASK_SIZE & PAGE_MASK; - /* Space for the VDSO & data page */ - top -= PAGE_ALIGN(current->thread.vdso->size); - top -= VVAR_SIZE; - - /* Space to randomize the VDSO base */ - if (current->flags & PF_RANDOMIZE) - top -= VDSO_RANDOMIZE_SIZE; + if (current->thread.vdso) { + /* Space for the VDSO & data page */ + top -= PAGE_ALIGN(current->thread.vdso->size); + top -= VVAR_SIZE; + + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + } return top; } diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index c114c5ef1332..5e2402cfcab0 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, offset; + int err, len, type; - err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + err = arch_bp_generic_fields(ctrl, &len, &type); if (err) return err; - switch (note_type) { - case NT_LOONGARCH_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_LOONGARCH_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: - return -EINVAL; - } - attr->bp_len = len; attr->bp_type = type; - attr->bp_addr += offset; return 0; } @@ -603,16 +589,36 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; + struct thread_info *ti = task_thread_info(tsk); bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); attr = bp->attr; - decode_ctrl_reg(uctrl, &ctrl); - err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); - if (err) - return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case NT_LOONGARCH_HW_WATCH: + decode_ctrl_reg(uctrl, &ctrl); + break; + default: + return -EINVAL; + } + + if (uctrl & CTRL_PLV_ENABLE) { + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + attr.disabled = 0; + set_ti_thread_flag(ti, TIF_LOAD_WATCH); + } else { + attr.disabled = 1; + clear_ti_thread_flag(ti, TIF_LOAD_WATCH); + } return modify_user_hw_breakpoint(bp, &attr); } @@ -643,6 +649,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; + /* Kernel-space address cannot be monitored by user-space */ + if ((unsigned long)addr >= XKPRANGE) + return -EINVAL; + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); @@ -710,7 +720,7 @@ static int hw_break_set(struct task_struct *target, unsigned int note_type = regset->core_note_type; /* Resource info */ - offset = offsetof(struct user_watch_state, dbg_regs); + offset = offsetof(struct user_watch_state_v2, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, mask, ctrl) registers */ @@ -910,7 +920,7 @@ static const struct user_regset loongarch64_regsets[] = { #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_LOONGARCH_HW_BREAK, - .n = sizeof(struct user_watch_state) / sizeof(u32), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, @@ -918,7 +928,7 @@ static const struct user_regset loongarch64_regsets[] = { }, [REGSET_HW_WATCH] = { .core_note_type = NT_LOONGARCH_HW_WATCH, - .n = sizeof(struct user_watch_state) / sizeof(u32), + .n = sizeof(struct user_watch_state_v2) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 1acfa704c8d0..50c469067f3a 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -13,6 +13,7 @@ #include <asm/bootinfo.h> #include <asm/early_ioremap.h> #include <asm/inst.h> +#include <asm/io.h> #include <asm/sections.h> #include <asm/setup.h> @@ -34,11 +35,27 @@ static inline void __init relocate_relative(void) if (rela->r_info != R_LARCH_RELATIVE) continue; - if (relocated_addr >= VMLINUX_LOAD_ADDRESS) - relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); - + relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); *(Elf64_Addr *)RELOCATED(addr) = relocated_addr; } + +#ifdef CONFIG_RELR + u64 *addr = NULL; + u64 *relr = (u64 *)&__relr_dyn_begin; + u64 *relr_end = (u64 *)&__relr_dyn_end; + + for ( ; relr < relr_end; relr++) { + if ((*relr & 1) == 0) { + addr = (u64 *)(*relr + reloc_offset); + *addr++ += reloc_offset; + } else { + for (u64 *p = addr, r = *relr >> 1; r; p++, r >>= 1) + if (r & 1) + *p += reloc_offset; + addr += 63; + } + } +#endif } static inline void __init relocate_absolute(long random_offset) @@ -123,6 +140,32 @@ static inline __init bool kaslr_disabled(void) if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) return true; +#ifdef CONFIG_HIBERNATION + str = strstr(builtin_cmdline, "nohibernate"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return false; + + str = strstr(boot_command_line, "nohibernate"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return false; + + str = strstr(builtin_cmdline, "noresume"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return false; + + str = strstr(boot_command_line, "noresume"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return false; + + str = strstr(builtin_cmdline, "resume="); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return true; + + str = strstr(boot_command_line, "resume="); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return true; +#endif + return false; } @@ -170,7 +213,7 @@ unsigned long __init relocate_kernel(void) unsigned long kernel_length; unsigned long random_offset = 0; void *location_new = _text; /* Default to original kernel start */ - char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ + char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); @@ -182,6 +225,7 @@ unsigned long __init relocate_kernel(void) random_offset = (unsigned long)location_new - (unsigned long)(_text); #endif reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS; + early_memunmap(cmdline, COMMAND_LINE_SIZE); if (random_offset) { kernel_length = (long)(_end) - (long)(_text); diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index f49f6b053763..84e6de2fd973 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -15,6 +15,7 @@ #include <asm/addrspace.h> SYM_CODE_START(relocate_new_kernel) + UNWIND_HINT_UNDEFINED /* * a0: EFI boot flag for the new kernel * a1: Command line pointer for the new kernel @@ -90,6 +91,7 @@ SYM_CODE_END(relocate_new_kernel) * then start at the entry point from LOONGARCH_IOCSR_MBUF0. */ SYM_CODE_START(kexec_smp_wait) + UNWIND_HINT_UNDEFINED 1: li.w t0, 0x100 /* wait for init loop */ 2: addi.w t0, t0, -1 /* limit mailbox access */ bnez t0, 2b @@ -106,6 +108,5 @@ SYM_CODE_END(kexec_smp_wait) relocate_new_kernel_end: -SYM_DATA_START(relocate_new_kernel_size) - PTR relocate_new_kernel_end - relocate_new_kernel -SYM_DATA_END(relocate_new_kernel_size) + .section ".data" +SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel) diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 1ef8c6383535..de8fa5a8a825 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -33,7 +33,7 @@ void machine_halt(void) console_flush_on_panic(CONSOLE_FLUSH_PENDING); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -53,7 +53,7 @@ void machine_power_off(void) #endif while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -74,6 +74,6 @@ void machine_restart(char *command) acpi_reboot(); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } diff --git a/arch/loongarch/kernel/rethook_trampoline.S b/arch/loongarch/kernel/rethook_trampoline.S index bd5772c96338..d4ceb2fa2a5c 100644 --- a/arch/loongarch/kernel/rethook_trampoline.S +++ b/arch/loongarch/kernel/rethook_trampoline.S @@ -76,6 +76,7 @@ .endm SYM_CODE_START(arch_rethook_trampoline) + UNWIND_HINT_UNDEFINED addi.d sp, sp, -PT_SIZE save_all_base_regs diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 634ef17fd38b..90cb3ca96f08 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -47,6 +47,7 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/time.h> +#include <asm/unwind.h> #define SMBIOS_BIOSSIZE_OFFSET 0x09 #define SMBIOS_BIOSEXTERN_OFFSET 0x13 @@ -54,6 +55,7 @@ #define SMBIOS_FREQHIGH_OFFSET 0x17 #define SMBIOS_FREQLOW_MASK 0xFF #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 +#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25 #define LOONGSON_EFI_ENABLE (1 << 3) unsigned long fw_arg0, fw_arg1, fw_arg2; @@ -124,7 +126,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm) cpu_clock_freq = freq_temp * 1000000; loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]); - loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET); + loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); pr_info("CpuClock = %llu\n", cpu_clock_freq); } @@ -260,7 +262,7 @@ static void __init arch_reserve_crashkernel(void) char *cmdline = boot_command_line; bool high = false; - if (!IS_ENABLED(CONFIG_KEXEC_CORE)) + if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), @@ -281,7 +283,7 @@ static void __init fdt_setup(void) return; /* Prefer to use built-in dtb, checking its legality first. */ - if (!fdt_check_header(__dtb_start)) + if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start)) fdt_pointer = __dtb_start; else fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */ @@ -289,7 +291,7 @@ static void __init fdt_setup(void) if (!fdt_pointer || fdt_check_header(fdt_pointer)) return; - early_init_dt_scan(fdt_pointer); + early_init_dt_scan(fdt_pointer, __pa(fdt_pointer)); early_init_fdt_reserve_self(); max_low_pfn = PFN_PHYS(memblock_end_of_DRAM()); @@ -350,10 +352,8 @@ void __init platform_init(void) arch_reserve_vmcore(); arch_reserve_crashkernel(); -#ifdef CONFIG_ACPI_TABLE_UPGRADE - acpi_table_upgrade(); -#endif #ifdef CONFIG_ACPI + acpi_table_upgrade(); acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif @@ -387,6 +387,9 @@ static void __init check_kernel_sections_mem(void) */ static void __init arch_mem_init(char **cmdline_p) { + /* Recalculate max_low_pfn for "mem=xxx" */ + max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + if (usermem) pr_info("User-defined physical RAM map overwrite\n"); @@ -431,7 +434,7 @@ static void __init resource_init(void) num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); - standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES); + standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES); for_each_mem_region(region) { res = &standard_resources[i++]; @@ -490,7 +493,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, } vaddr = (unsigned long)(PCI_IOBASE + range->io_start); - ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); + vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); return 0; } @@ -577,8 +580,10 @@ static void __init prefill_possible_map(void) for (i = 0; i < possible; i++) set_cpu_possible(i, true); - for (; i < NR_CPUS; i++) + for (; i < NR_CPUS; i++) { + set_cpu_present(i, false); set_cpu_possible(i, false); + } set_nr_cpu_ids(possible); } @@ -587,6 +592,7 @@ static void __init prefill_possible_map(void) void __init setup_arch(char **cmdline_p) { cpu_probe(); + unwind_init(); init_environ(); efi_init(); @@ -601,6 +607,8 @@ void __init setup_arch(char **cmdline_p) arch_mem_init(cmdline_p); resource_init(); + jump_label_init(); /* Initialise the static keys for paravirtualization */ + #ifdef CONFIG_SMP plat_smp_setup(); prefill_possible_map(); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index aabee0b280fe..4b24589c0b56 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -13,11 +13,13 @@ #include <linux/cpumask.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/irq_work.h> #include <linux/profile.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/threads.h> #include <linux/export.h> +#include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/time.h> #include <linux/tracepoint.h> @@ -29,6 +31,7 @@ #include <asm/loongson.h> #include <asm/mmu_context.h> #include <asm/numa.h> +#include <asm/paravirt.h> #include <asm/processor.h> #include <asm/setup.h> #include <asm/time.h> @@ -66,14 +69,11 @@ static cpumask_t cpu_core_setup_map; struct secondary_data cpuboot_data; static DEFINE_PER_CPU(int, cpu_state); -enum ipi_msg_type { - IPI_RESCHEDULE, - IPI_CALL_FUNCTION, -}; - static const char *ipi_types[NR_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNCTION] = "Function call interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_CLEAR_VECTOR] = "Clear vector interrupts", }; void show_ipi_list(struct seq_file *p, int prec) @@ -83,7 +83,7 @@ void show_ipi_list(struct seq_file *p, int prec) for (i = 0; i < NR_IPI; i++) { seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : ""); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).ipi_irqs[i]); + seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, cpu).ipi_irqs[i], 10); seq_printf(p, " LoongArch %d %s\n", i + 1, ipi_types[i]); } } @@ -190,24 +190,19 @@ static u32 ipi_read_clear(int cpu) static void ipi_write_action(int cpu, u32 action) { - unsigned int irq = 0; + uint32_t val; - while ((irq = ffs(action))) { - uint32_t val = IOCSR_IPI_SEND_BLOCKING; - - val |= (irq - 1); - val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT); - iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND); - action &= ~BIT(irq - 1); - } + val = IOCSR_IPI_SEND_BLOCKING | action; + val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT); + iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND); } -void loongson_send_ipi_single(int cpu, unsigned int action) +static void loongson_send_ipi_single(int cpu, unsigned int action) { ipi_write_action(cpu_logical_map(cpu), (u32)action); } -void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) +static void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) { unsigned int i; @@ -222,11 +217,18 @@ void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) */ void arch_smp_send_reschedule(int cpu) { - loongson_send_ipi_single(cpu, SMP_RESCHEDULE); + mp_ops.send_ipi_single(cpu, ACTION_RESCHEDULE); } EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); -irqreturn_t loongson_ipi_interrupt(int irq, void *dev) +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + mp_ops.send_ipi_single(smp_processor_id(), ACTION_IRQ_WORK); +} +#endif + +static irqreturn_t loongson_ipi_interrupt(int irq, void *dev) { unsigned int action; unsigned int cpu = smp_processor_id(); @@ -243,9 +245,39 @@ irqreturn_t loongson_ipi_interrupt(int irq, void *dev) per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++; } + if (action & SMP_IRQ_WORK) { + irq_work_run(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++; + } + + if (action & SMP_CLEAR_VECTOR) { + complete_irq_moving(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_CLEAR_VECTOR]++; + } + return IRQ_HANDLED; } +static void loongson_init_ipi(void) +{ + int r, ipi_irq; + + ipi_irq = get_percpu_irq(INT_IPI); + if (ipi_irq < 0) + panic("IPI IRQ mapping failed\n"); + + irq_set_percpu_devid(ipi_irq); + r = request_percpu_irq(ipi_irq, loongson_ipi_interrupt, "IPI", &irq_stat); + if (r < 0) + panic("IPI IRQ request failed\n"); +} + +struct smp_ops mp_ops = { + .init_ipi = loongson_init_ipi, + .send_ipi_single = loongson_send_ipi_single, + .send_ipi_mask = loongson_send_ipi_mask, +}; + static void __init fdt_smp_setup(void) { #ifdef CONFIG_OF @@ -260,18 +292,19 @@ static void __init fdt_smp_setup(void) if (cpuid >= nr_cpu_ids) continue; - if (cpuid == loongson_sysconf.boot_cpu_id) { + if (cpuid == loongson_sysconf.boot_cpu_id) cpu = 0; - numa_add_cpu(cpu); - } else { - cpu = cpumask_next_zero(-1, cpu_present_mask); - } + else + cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS); num_processors++; set_cpu_possible(cpu, true); set_cpu_present(cpu, true); __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; + + early_numa_add_cpu(cpuid, 0); + set_cpuid_to_node(cpuid, 0); } loongson_sysconf.nr_cpus = num_processors; @@ -289,6 +322,7 @@ void __init loongson_smp_setup(void) cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package; cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package; + pv_ipi_init(); iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN); pr_info("Detected %i available CPU(s)\n", loongson_sysconf.nr_cpus); } @@ -298,11 +332,11 @@ void __init loongson_prepare_cpus(unsigned int max_cpus) int i = 0; parse_acpi_topology(); + cpu_data[0].global_id = cpu_logical_map(0); for (i = 0; i < loongson_sysconf.nr_cpus; i++) { set_cpu_present(i, true); csr_mail_send(0, __cpu_logical_map[i], 0); - cpu_data[i].global_id = __cpu_logical_map[i]; } per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -323,7 +357,7 @@ void loongson_boot_secondary(int cpu, struct task_struct *idle) csr_mail_send(entry, cpu_logical_map(cpu), 0); - loongson_send_ipi_single(cpu, SMP_BOOT_CPU); + loongson_send_ipi_single(cpu, ACTION_BOOT_CPU); } /* @@ -333,7 +367,7 @@ void loongson_init_secondary(void) { unsigned int cpu = smp_processor_id(); unsigned int imask = ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | - ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER; + ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER | ECFGF_SIP0; change_csr_ecfg(ECFG0_IM, imask); @@ -347,6 +381,7 @@ void loongson_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; cpu_data[cpu].core = pptt_enabled ? cpu_data[cpu].core : cpu_logical_map(cpu) % loongson_sysconf.cores_per_package; + cpu_data[cpu].global_id = cpu_logical_map(cpu); } void loongson_smp_finish(void) @@ -389,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu) mb(); } -void __noreturn arch_cpu_idle_dead(void) +static void __noreturn idle_play_dead(void) { register uint64_t addr; register void (*init_fn)(void); @@ -413,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void) BUG(); } +#ifdef CONFIG_HIBERNATION +static void __noreturn poll_play_dead(void) +{ + register uint64_t addr; + register void (*init_fn)(void); + + idle_task_exit(); + __this_cpu_write(cpu_state, CPU_DEAD); + + __smp_mb(); + do { + __asm__ __volatile__("nop\n\t"); + addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); + } while (addr == 0); + + init_fn = (void *)TO_CACHE(addr); + iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); + + init_fn(); + BUG(); +} +#endif + +static void (*play_dead)(void) = idle_play_dead; + +void __noreturn arch_cpu_idle_dead(void) +{ + play_dead(); + BUG(); /* play_dead() doesn't return */ +} + +#ifdef CONFIG_HIBERNATION +int hibernate_resume_nonboot_cpu_disable(void) +{ + int ret; + + play_dead = poll_play_dead; + ret = suspend_disable_secondary_cpus(); + play_dead = idle_play_dead; + + return ret; +} +#endif + #endif /* @@ -449,13 +528,14 @@ core_initcall(ipi_pm_init); #endif /* Preload SMP state for boot cpu */ -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { unsigned int cpu, node, rr_node; set_cpu_possible(0, true); set_cpu_online(0, true); set_my_cpu_offset(per_cpu_offset(0)); + numa_add_cpu(0); rr_node = first_node(node_online_map); for_each_possible_cpu(cpu) { @@ -481,6 +561,8 @@ void smp_prepare_boot_cpu(void) rr_node = next_node_in(rr_node, node_online_map); } } + + pv_spinlock_init(); } /* called from main before smp_init() */ diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c index f623feb2129f..9a038d1070d7 100644 --- a/arch/loongarch/kernel/stacktrace.c +++ b/arch/loongarch/kernel/stacktrace.c @@ -29,6 +29,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, regs->csr_era = thread_saved_ra(task); } regs->regs[1] = 0; + regs->regs[22] = 0; } for (unwind_start(&state, task, regs); @@ -39,6 +40,46 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, } } +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task) +{ + unsigned long addr; + struct pt_regs dummyregs; + struct pt_regs *regs = &dummyregs; + struct unwind_state state; + + if (task == current) { + regs->regs[3] = (unsigned long)__builtin_frame_address(0); + regs->csr_era = (unsigned long)__builtin_return_address(0); + } else { + regs->regs[3] = thread_saved_fp(task); + regs->csr_era = thread_saved_ra(task); + } + regs->regs[1] = 0; + regs->regs[22] = 0; + + for (unwind_start(&state, task, regs); + !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + + /* + * A NULL or invalid return address probably means there's some + * generated code which __kernel_text_address() doesn't know about. + */ + if (!addr) + return -EINVAL; + + if (!consume_entry(cookie, addr)) + return -EINVAL; + } + + /* Check for stack corruption */ + if (unwind_error(&state)) + return -EINVAL; + + return 0; +} + static int copy_stack_frame(unsigned long fp, struct stack_frame *frame) { diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 31dd8199b245..9c23cb7e432f 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -12,7 +12,7 @@ /* * task_struct *__switch_to(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, void *sched_ra, void *sched_cfa) */ .align 5 SYM_FUNC_START(__switch_to) diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index b4c5acd7aa3b..168bd97540f8 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -9,20 +9,24 @@ #include <linux/entry-common.h> #include <linux/errno.h> #include <linux/linkage.h> +#include <linux/objtool.h> +#include <linux/randomize_kstack.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <asm/asm.h> #include <asm/exception.h> +#include <asm/loongarch.h> #include <asm/signal.h> #include <asm/switch_to.h> #include <asm-generic/syscalls.h> #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, - prot, unsigned long, flags, unsigned long, fd, off_t, offset) + prot, unsigned long, flags, unsigned long, fd, unsigned long, offset) { if (offset & ~PAGE_MASK) return -EINVAL; @@ -32,13 +36,13 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, void *sys_call_table[__NR_syscalls] = { [0 ... __NR_syscalls - 1] = sys_ni_syscall, -#include <asm/unistd.h> +#include <asm/syscall_table_64.h> }; typedef long (*sys_call_fn)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -void noinstr do_syscall(struct pt_regs *regs) +void noinstr __no_stack_protector do_syscall(struct pt_regs *regs) { unsigned long nr; sys_call_fn syscall_fn; @@ -54,11 +58,24 @@ void noinstr do_syscall(struct pt_regs *regs) nr = syscall_enter_from_user_mode(regs, nr); + add_random_kstack_offset(); + if (nr < NR_syscalls) { syscall_fn = sys_call_table[nr]; regs->regs[4] = syscall_fn(regs->orig_a0, regs->regs[5], regs->regs[6], regs->regs[7], regs->regs[8], regs->regs[9]); } + /* + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints: 16-bytes (i.e. 4-bits) + * aligned, which will remove the 4 low bits from any entropy chosen + * here. + * + * The resulting 6 bits of entropy is seen in SP[9:4]. + */ + choose_random_kstack_offset(drdtime()); + syscall_exit_to_user_mode(regs); } diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index e7015f7b70e3..e2d3bfeb6366 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -15,6 +15,7 @@ #include <asm/cpu-features.h> #include <asm/loongarch.h> +#include <asm/paravirt.h> #include <asm/time.h> u64 cpu_clock_freq; @@ -123,26 +124,20 @@ void sync_counter(void) csr_write64(init_offset, 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, INT_TI); - - return -EINVAL; -} - int constant_clockevent_init(void) { unsigned int cpu = smp_processor_id(); - unsigned long min_delta = 0x600; - unsigned long max_delta = (1UL << 48) - 1; +#ifdef CONFIG_PREEMPT_RT + unsigned long min_delta = 100; +#else + unsigned long min_delta = 1000; +#endif + unsigned long max_delta = GENMASK_ULL(boot_cpu_data.timerbits, 0); struct clock_event_device *cd; static int irq = 0, timer_irq_installed = 0; if (!timer_irq_installed) { - irq = get_timer_irq(); + irq = get_percpu_irq(INT_TI); if (irq < 0) pr_err("Failed to map irq %d (timer)\n", irq); } @@ -224,4 +219,5 @@ void __init time_init(void) constant_clockevent_init(); constant_clocksource_init(); + pv_time_init(); } diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index aebfc3733a76..2ec3106c0da3 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -53,6 +53,32 @@ #include "access-helper.h" +void *exception_table[EXCCODE_INT_START] = { + [0 ... EXCCODE_INT_START - 1] = handle_reserved, + + [EXCCODE_TLBI] = handle_tlb_load, + [EXCCODE_TLBL] = handle_tlb_load, + [EXCCODE_TLBS] = handle_tlb_store, + [EXCCODE_TLBM] = handle_tlb_modify, + [EXCCODE_TLBNR] = handle_tlb_protect, + [EXCCODE_TLBNX] = handle_tlb_protect, + [EXCCODE_TLBPE] = handle_tlb_protect, + [EXCCODE_ADE] = handle_ade, + [EXCCODE_ALE] = handle_ale, + [EXCCODE_BCE] = handle_bce, + [EXCCODE_SYS] = handle_sys, + [EXCCODE_BP] = handle_bp, + [EXCCODE_INE] = handle_ri, + [EXCCODE_IPE] = handle_ri, + [EXCCODE_FPDIS] = handle_fpu, + [EXCCODE_LSXDIS] = handle_lsx, + [EXCCODE_LASXDIS] = handle_lasx, + [EXCCODE_FPE] = handle_fpe, + [EXCCODE_WATCH] = handle_watch, + [EXCCODE_BTDIS] = handle_lbt, +}; +EXPORT_SYMBOL_GPL(exception_table); + static void show_backtrace(struct task_struct *task, const struct pt_regs *regs, const char *loglvl, bool user) { @@ -529,6 +555,9 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs) #else unsigned int *pc; + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_enable(); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); /* @@ -553,6 +582,8 @@ sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); out: + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_disable(); #endif irqentry_exit(regs, state); } @@ -566,17 +597,24 @@ int is_valid_bugaddr(unsigned long addr) static void bug_handler(struct pt_regs *regs) { + if (user_mode(regs)) { + force_sig(SIGTRAP); + return; + } + switch (report_bug(regs->csr_era, regs)) { case BUG_TRAP_TYPE_BUG: - case BUG_TRAP_TYPE_NONE: - die_if_kernel("Oops - BUG", regs); - force_sig(SIGTRAP); + die("Oops - BUG", regs); break; case BUG_TRAP_TYPE_WARN: /* Skip the BUG instruction and continue */ regs->csr_era += LOONGARCH_INSN_SIZE; break; + + default: + if (!fixup_exception(regs)) + die("Oops - BUG", regs); } } @@ -1150,19 +1188,9 @@ void __init trap_init(void) for (i = EXCCODE_INT_START; i <= EXCCODE_INT_END; i++) set_handler(i * VECSIZE, handle_vint, VECSIZE); - set_handler(EXCCODE_ADE * VECSIZE, handle_ade, VECSIZE); - set_handler(EXCCODE_ALE * VECSIZE, handle_ale, VECSIZE); - set_handler(EXCCODE_BCE * VECSIZE, handle_bce, VECSIZE); - set_handler(EXCCODE_SYS * VECSIZE, handle_sys, VECSIZE); - set_handler(EXCCODE_BP * VECSIZE, handle_bp, VECSIZE); - set_handler(EXCCODE_INE * VECSIZE, handle_ri, VECSIZE); - set_handler(EXCCODE_IPE * VECSIZE, handle_ri, VECSIZE); - set_handler(EXCCODE_FPDIS * VECSIZE, handle_fpu, VECSIZE); - set_handler(EXCCODE_LSXDIS * VECSIZE, handle_lsx, VECSIZE); - set_handler(EXCCODE_LASXDIS * VECSIZE, handle_lasx, VECSIZE); - set_handler(EXCCODE_FPE * VECSIZE, handle_fpe, VECSIZE); - set_handler(EXCCODE_BTDIS * VECSIZE, handle_lbt, VECSIZE); - set_handler(EXCCODE_WATCH * VECSIZE, handle_watch, VECSIZE); + /* Set exception vector handler */ + for (i = EXCCODE_ADE; i <= EXCCODE_BTDIS; i++) + set_handler(i * VECSIZE, exception_table[i], VECSIZE); cache_error_setup(); diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c index 3abf163dda05..487be604b96a 100644 --- a/arch/loongarch/kernel/unaligned.c +++ b/arch/loongarch/kernel/unaligned.c @@ -482,14 +482,10 @@ sigbus: #ifdef CONFIG_DEBUG_FS static int __init debugfs_unaligned(void) { - struct dentry *d; - - d = debugfs_create_dir("loongarch", NULL); - debugfs_create_u32("unaligned_instructions_user", - S_IRUGO, d, &unaligned_instructions_user); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_user); debugfs_create_u32("unaligned_instructions_kernel", - S_IRUGO, d, &unaligned_instructions_kernel); + S_IRUGO, arch_debugfs_dir, &unaligned_instructions_kernel); return 0; } diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c new file mode 100644 index 000000000000..b25722876331 --- /dev/null +++ b/arch/loongarch/kernel/unwind_orc.c @@ -0,0 +1,528 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/objtool.h> +#include <linux/module.h> +#include <linux/sort.h> +#include <asm/exception.h> +#include <asm/orc_header.h> +#include <asm/orc_lookup.h> +#include <asm/orc_types.h> +#include <asm/ptrace.h> +#include <asm/setup.h> +#include <asm/stacktrace.h> +#include <asm/tlb.h> +#include <asm/unwind.h> + +ORC_HEADER; + +#define orc_warn(fmt, ...) \ + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +extern int __start_orc_unwind_ip[]; +extern int __stop_orc_unwind_ip[]; +extern struct orc_entry __start_orc_unwind[]; +extern struct orc_entry __stop_orc_unwind[]; + +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; + +/* Fake frame pointer entry -- used as a fallback for generated code */ +static struct orc_entry orc_fp_entry = { + .sp_reg = ORC_REG_FP, + .sp_offset = 16, + .fp_reg = ORC_REG_PREV_SP, + .fp_offset = -16, + .ra_reg = ORC_REG_PREV_SP, + .ra_offset = -8, + .type = ORC_TYPE_CALL +}; + +/* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer, + * and we don't have unwind information for NULL. + * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function + * pointer into its parent and then continue normally from there. + */ +static struct orc_entry orc_null_entry = { + .sp_reg = ORC_REG_SP, + .sp_offset = sizeof(long), + .fp_reg = ORC_REG_UNDEFINED, + .type = ORC_TYPE_CALL +}; + +static inline unsigned long orc_ip(const int *ip) +{ + return (unsigned long)ip + *ip; +} + +static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table, + unsigned int num_entries, unsigned long ip) +{ + int *first = ip_table; + int *mid = first, *found = first; + int *last = ip_table + num_entries - 1; + + if (!num_entries) + return NULL; + + /* + * Do a binary range search to find the rightmost duplicate of a given + * starting address. Some entries are section terminators which are + * "weak" entries for ensuring there are no gaps. They should be + * ignored when they conflict with a real entry. + */ + while (first <= last) { + mid = first + ((last - first) / 2); + + if (orc_ip(mid) <= ip) { + found = mid; + first = mid + 1; + } else + last = mid - 1; + } + + return u_table + (found - ip_table); +} + +#ifdef CONFIG_MODULES +static struct orc_entry *orc_module_find(unsigned long ip) +{ + struct module *mod; + + mod = __module_address(ip); + if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip) + return NULL; + + return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind, mod->arch.num_orcs, ip); +} +#else +static struct orc_entry *orc_module_find(unsigned long ip) +{ + return NULL; +} +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +static struct orc_entry *orc_find(unsigned long ip); + +/* + * Ftrace dynamic trampolines do not have orc entries of their own. + * But they are copies of the ftrace entries that are static and + * defined in ftrace_*.S, which do have orc entries. + * + * If the unwinder comes across a ftrace trampoline, then find the + * ftrace function that was used to create it, and use that ftrace + * function's orc entry, as the placement of the return code in + * the stack will be identical. + */ +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + struct ftrace_ops *ops; + unsigned long tramp_addr, offset; + + ops = ftrace_ops_trampoline(ip); + if (!ops) + return NULL; + + /* Set tramp_addr to the start of the code copied by the trampoline */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + tramp_addr = (unsigned long)ftrace_regs_caller; + else + tramp_addr = (unsigned long)ftrace_caller; + + /* Now place tramp_addr to the location within the trampoline ip is at */ + offset = ip - ops->trampoline; + tramp_addr += offset; + + /* Prevent unlikely recursion */ + if (ip == tramp_addr) + return NULL; + + return orc_find(tramp_addr); +} +#else +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + return NULL; +} +#endif + +static struct orc_entry *orc_find(unsigned long ip) +{ + static struct orc_entry *orc; + + if (ip == 0) + return &orc_null_entry; + + /* For non-init vmlinux addresses, use the fast lookup table: */ + if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { + unsigned int idx, start, stop; + + idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; + + if (unlikely((idx >= lookup_num_blocks-1))) { + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n", + idx, lookup_num_blocks, (void *)ip); + return NULL; + } + + start = orc_lookup[idx]; + stop = orc_lookup[idx + 1] + 1; + + if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || + (__start_orc_unwind + stop > __stop_orc_unwind))) { + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n", + idx, lookup_num_blocks, start, stop, (void *)ip); + return NULL; + } + + return __orc_find(__start_orc_unwind_ip + start, + __start_orc_unwind + start, stop - start, ip); + } + + /* vmlinux .init slow lookup: */ + if (is_kernel_inittext(ip)) + return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); + + /* Module lookup: */ + orc = orc_module_find(ip); + if (orc) + return orc; + + return orc_ftrace_find(ip); +} + +#ifdef CONFIG_MODULES + +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + +static void orc_sort_swap(void *_a, void *_b, int size) +{ + int delta = _b - _a; + int *a = _a, *b = _b, tmp; + struct orc_entry *orc_a, *orc_b; + + /* Swap the .orc_unwind_ip entries: */ + tmp = *a; + *a = *b + delta; + *b = tmp - delta; + + /* Swap the corresponding .orc_unwind entries: */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + orc_b = cur_orc_table + (b - cur_orc_ip_table); + swap(*orc_a, *orc_b); +} + +static int orc_sort_cmp(const void *_a, const void *_b) +{ + const int *a = _a, *b = _b; + unsigned long a_val = orc_ip(a); + unsigned long b_val = orc_ip(b); + struct orc_entry *orc_a; + + if (a_val > b_val) + return 1; + if (a_val < b_val) + return -1; + + /* + * The "weak" section terminator entries need to always be first + * to ensure the lookup code skips them in favor of real entries. + * These terminator entries exist to handle any gaps created by + * whitelisted .o files which didn't get objtool generation. + */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; +} + +void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, + void *_orc, size_t orc_size) +{ + int *orc_ip = _orc_ip; + struct orc_entry *orc = _orc; + unsigned int num_entries = orc_ip_size / sizeof(int); + + WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(*orc) != 0 || + num_entries != orc_size / sizeof(*orc)); + + /* + * The 'cur_orc_*' globals allow the orc_sort_swap() callback to + * associate an .orc_unwind_ip table entry with its corresponding + * .orc_unwind entry so they can both be swapped. + */ + mutex_lock(&sort_mutex); + cur_orc_ip_table = orc_ip; + cur_orc_table = orc; + sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap); + mutex_unlock(&sort_mutex); + + mod->arch.orc_unwind_ip = orc_ip; + mod->arch.orc_unwind = orc; + mod->arch.num_orcs = num_entries; +} +#endif + +void __init unwind_init(void) +{ + int i; + size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind; + size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip; + size_t num_entries = orc_ip_size / sizeof(int); + struct orc_entry *orc; + + if (!num_entries || orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(struct orc_entry) != 0 || + num_entries != orc_size / sizeof(struct orc_entry)) { + orc_warn("WARNING: Bad or missing .orc_unwind table. Disabling unwinder.\n"); + return; + } + + /* + * Note, the orc_unwind and orc_unwind_ip tables were already + * sorted at build time via the 'sorttable' tool. + * It's ready for binary search straight away, no need to sort it. + */ + + /* Initialize the fast lookup table: */ + lookup_num_blocks = orc_lookup_end - orc_lookup; + for (i = 0; i < lookup_num_blocks-1; i++) { + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + num_entries, LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i)); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + + orc_lookup[i] = orc - __start_orc_unwind; + } + + /* Initialize the ending block: */ + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries, LOOKUP_STOP_IP); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind; + + orc_init = true; +} + +static inline bool on_stack(struct stack_info *info, unsigned long addr, size_t len) +{ + unsigned long begin = info->begin; + unsigned long end = info->end; + + return (info->type != STACK_TYPE_UNKNOWN && + addr >= begin && addr < end && addr + len > begin && addr + len <= end); +} + +static bool stack_access_ok(struct unwind_state *state, unsigned long addr, size_t len) +{ + struct stack_info *info = &state->stack_info; + + if (on_stack(info, addr, len)) + return true; + + return !get_stack_info(addr, state->task, info) && on_stack(info, addr, len); +} + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + return __unwind_get_return_address(state); +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs) +{ + __unwind_start(state, task, regs); + state->type = UNWINDER_ORC; + if (!unwind_done(state) && !__kernel_text_address(state->pc)) + unwind_next_frame(state); +} +EXPORT_SYMBOL_GPL(unwind_start); + +static bool is_entry_func(unsigned long addr) +{ + extern u32 kernel_entry; + extern u32 kernel_entry_end; + + return addr >= (unsigned long)&kernel_entry && addr < (unsigned long)&kernel_entry_end; +} + +static inline unsigned long bt_address(unsigned long ra) +{ + extern unsigned long eentry; + + if (__kernel_text_address(ra)) + return ra; + + if (__module_text_address(ra)) + return ra; + + if (ra >= eentry && ra < eentry + EXCCODE_INT_END * VECSIZE) { + unsigned long func; + unsigned long type = (ra - eentry) / VECSIZE; + unsigned long offset = (ra - eentry) % VECSIZE; + + switch (type) { + case 0 ... EXCCODE_INT_START - 1: + func = (unsigned long)exception_table[type]; + break; + case EXCCODE_INT_START ... EXCCODE_INT_END: + func = (unsigned long)handle_vint; + break; + default: + func = (unsigned long)handle_reserved; + break; + } + + return func + offset; + } + + return ra; +} + +bool unwind_next_frame(struct unwind_state *state) +{ + unsigned long *p, pc; + struct pt_regs *regs; + struct orc_entry *orc; + struct stack_info *info = &state->stack_info; + + if (unwind_done(state)) + return false; + + /* Don't let modules unload while we're reading their ORC data. */ + preempt_disable(); + + if (is_entry_func(state->pc)) + goto end; + + orc = orc_find(state->pc); + if (!orc) { + /* + * As a fallback, try to assume this code uses a frame pointer. + * This is useful for generated code, like BPF, which ORC + * doesn't know about. This is just a guess, so the rest of + * the unwind is no longer considered reliable. + */ + orc = &orc_fp_entry; + state->error = true; + } else { + if (orc->type == ORC_TYPE_UNDEFINED) + goto err; + + if (orc->type == ORC_TYPE_END_OF_STACK) + goto end; + } + + switch (orc->sp_reg) { + case ORC_REG_SP: + if (info->type == STACK_TYPE_IRQ && state->sp == info->end) + orc->type = ORC_TYPE_REGS; + else + state->sp = state->sp + orc->sp_offset; + break; + case ORC_REG_FP: + state->sp = state->fp; + break; + default: + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->pc); + goto err; + } + + switch (orc->fp_reg) { + case ORC_REG_PREV_SP: + p = (unsigned long *)(state->sp + orc->fp_offset); + if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long))) + goto err; + + state->fp = *p; + break; + case ORC_REG_UNDEFINED: + /* Nothing. */ + break; + default: + orc_warn("unknown FP base reg %d at %pB\n", orc->fp_reg, (void *)state->pc); + goto err; + } + + switch (orc->type) { + case ORC_TYPE_CALL: + if (orc->ra_reg == ORC_REG_PREV_SP) { + p = (unsigned long *)(state->sp + orc->ra_offset); + if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long))) + goto err; + + pc = unwind_graph_addr(state, *p, state->sp); + pc -= LOONGARCH_INSN_SIZE; + } else if (orc->ra_reg == ORC_REG_UNDEFINED) { + if (!state->ra || state->ra == state->pc) + goto err; + + pc = unwind_graph_addr(state, state->ra, state->sp); + pc -= LOONGARCH_INSN_SIZE; + state->ra = 0; + } else { + orc_warn("unknown ra base reg %d at %pB\n", orc->ra_reg, (void *)state->pc); + goto err; + } + break; + case ORC_TYPE_REGS: + if (info->type == STACK_TYPE_IRQ && state->sp == info->end) + regs = (struct pt_regs *)info->next_sp; + else + regs = (struct pt_regs *)state->sp; + + if (!stack_access_ok(state, (unsigned long)regs, sizeof(*regs))) + goto err; + + if ((info->end == (unsigned long)regs + sizeof(*regs)) && + !regs->regs[3] && !regs->regs[1]) + goto end; + + if (user_mode(regs)) + goto end; + + pc = regs->csr_era; + if (!__kernel_text_address(pc)) + goto err; + + state->sp = regs->regs[3]; + state->ra = regs->regs[1]; + state->fp = regs->regs[22]; + get_stack_info(state->sp, state->task, info); + + break; + default: + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)state->pc); + goto err; + } + + state->pc = bt_address(pc); + if (!state->pc) { + pr_err("cannot find unwind pc at %pK\n", (void *)pc); + goto err; + } + + if (!__kernel_text_address(state->pc)) + goto err; + + preempt_enable(); + return true; + +err: + state->error = true; + +end: + preempt_enable(); + state->stack_info.type = STACK_TYPE_UNKNOWN; + return false; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 14941e4be66d..05e5fbac102a 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -15,30 +15,27 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/time_namespace.h> -#include <linux/timekeeper_internal.h> #include <asm/page.h> #include <asm/vdso.h> #include <vdso/helpers.h> #include <vdso/vsyscall.h> +#include <vdso/datapage.h> #include <generated/vdso-offsets.h> extern char vdso_start[], vdso_end[]; /* Kernel-provided data used by the VDSO. */ -static union { - u8 page[PAGE_SIZE]; - struct vdso_data data[CS_BASES]; -} generic_vdso_data __page_aligned_data; +static union vdso_data_store generic_vdso_data __page_aligned_data; static union { u8 page[LOONGARCH_VDSO_DATA_SIZE]; struct loongarch_vdso_data vdata; } loongarch_vdso_data __page_aligned_data; -static struct page *vdso_pages[] = { NULL }; struct vdso_data *vdso_data = generic_vdso_data.data; struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata; +struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data; static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -86,10 +83,8 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, struct loongarch_vdso_info vdso_info = { .vdso = vdso_start, - .size = PAGE_SIZE, .code_mapping = { .name = "[vdso]", - .pages = vdso_pages, .mremap = vdso_mremap, }, .data_mapping = { @@ -104,11 +99,14 @@ static int __init init_vdso(void) unsigned long i, cpu, pfn; BUG_ON(!PAGE_ALIGNED(vdso_info.vdso)); - BUG_ON(!PAGE_ALIGNED(vdso_info.size)); for_each_possible_cpu(cpu) vdso_pdata[cpu].node = cpu_to_node(cpu); + vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start); + vdso_info.code_mapping.pages = + kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL); + pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso)); for (i = 0; i < vdso_info.size / PAGE_SIZE; i++) vdso_info.code_mapping.pages[i] = pfn_to_page(pfn + i); diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index a5d0cd2035da..08ea921cdec1 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -2,9 +2,11 @@ #include <linux/sizes.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#include <asm/orc_lookup.h> #define PAGE_SIZE _PAGE_SIZE #define RO_EXCEPTION_TABLE_ALIGN 4 +#define PHYSADDR_MASK 0xffffffffffff /* 48-bit */ /* * Put .bss..swapper_pg_dir as the first thing in .bss. This will @@ -111,6 +113,14 @@ SECTIONS __rela_dyn_end = .; } +#ifdef CONFIG_RELR + .relr.dyn : ALIGN(8) { + __relr_dyn_begin = .; + *(.relr.dyn) + __relr_dyn_end = .; + } +#endif + .data.rel : { *(.data.rel*) } #ifdef CONFIG_RELOCATABLE @@ -122,6 +132,8 @@ SECTIONS } #endif + ORC_UNWIND_TABLE + .sdata : { *(.sdata) } @@ -139,10 +151,11 @@ SECTIONS #ifdef CONFIG_EFI_STUB /* header symbols */ - _kernel_asize = _end - _text; - _kernel_fsize = _edata - _text; - _kernel_vsize = _end - __initdata_begin; - _kernel_rsize = _edata - __initdata_begin; + _kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK); + _kernel_asize = ABSOLUTE(_end - _text); + _kernel_fsize = ABSOLUTE(_edata - _text); + _kernel_vsize = ABSOLUTE(_end - __initdata_begin); + _kernel_rsize = ABSOLUTE(_edata - __initdata_begin); #endif .gptab.sdata : { diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig index 61f7e33b1f95..97a811077ac3 100644 --- a/arch/loongarch/kvm/Kconfig +++ b/arch/loongarch/kvm/Kconfig @@ -20,8 +20,11 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on AS_HAS_LVZ_EXTENSION - depends on HAVE_KVM select HAVE_KVM_DIRTY_RING_ACQ_REL + select HAVE_KVM_IRQ_ROUTING + select HAVE_KVM_IRQCHIP + select HAVE_KVM_MSI + select HAVE_KVM_READONLY_MEM select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT @@ -29,6 +32,7 @@ config KVM select KVM_GENERIC_MMU_NOTIFIER select KVM_MMIO select KVM_XFER_TO_GUEST_WORK + select SCHED_INFO help Support hosting virtualized guest machines using hardware virtualization extensions. You will need diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index 244467d7792a..3a01292f71cc 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -3,7 +3,7 @@ # Makefile for LoongArch KVM support # -ccflags-y += -I $(srctree)/$(src) +ccflags-y += -I $(src) include $(srctree)/virt/kvm/Makefile.kvm @@ -18,5 +18,9 @@ kvm-y += timer.o kvm-y += tlb.o kvm-y += vcpu.o kvm-y += vm.o +kvm-y += intc/ipi.o +kvm-y += intc/eiointc.o +kvm-y += intc/pch_pic.o +kvm-y += irqfd.o CFLAGS_exit.o += $(call cc-option,-Wno-override-init,) diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index ed1d89d53e2e..ea321403644a 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/preempt.h> #include <linux/vmalloc.h> +#include <trace/events/kvm.h> #include <asm/fpu.h> #include <asm/inst.h> #include <asm/loongarch.h> @@ -20,6 +21,47 @@ #include <asm/kvm_vcpu.h> #include "trace.h" +static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst) +{ + int rd, rj; + unsigned int index, ret; + + if (inst.reg2_format.opcode != cpucfg_op) + return EMULATE_FAIL; + + rd = inst.reg2_format.rd; + rj = inst.reg2_format.rj; + ++vcpu->stat.cpucfg_exits; + index = vcpu->arch.gprs[rj]; + + /* + * By LoongArch Reference Manual 2.2.10.5 + * Return value is 0 for undefined CPUCFG index + * + * Disable preemption since hw gcsr is accessed + */ + preempt_disable(); + switch (index) { + case 0 ... (KVM_MAX_CPUCFG_REGS - 1): + vcpu->arch.gprs[rd] = vcpu->arch.cpucfg[index]; + break; + case CPUCFG_KVM_SIG: + /* CPUCFG emulation between 0x40000000 -- 0x400000ff */ + vcpu->arch.gprs[rd] = *(unsigned int *)KVM_SIGNATURE; + break; + case CPUCFG_KVM_FEATURE: + ret = vcpu->kvm->arch.pv_features & LOONGARCH_PV_FEAT_MASK; + vcpu->arch.gprs[rd] = ret; + break; + default: + vcpu->arch.gprs[rd] = 0; + break; + } + preempt_enable(); + + return EMULATE_DONE; +} + static unsigned long kvm_emu_read_csr(struct kvm_vcpu *vcpu, int csrid) { unsigned long val = 0; @@ -83,6 +125,14 @@ static int kvm_handle_csr(struct kvm_vcpu *vcpu, larch_inst inst) rj = inst.reg2csr_format.rj; csrid = inst.reg2csr_format.csr; + if (csrid >= LOONGARCH_CSR_PERFCTRL0 && csrid <= vcpu->arch.max_pmu_csrid) { + if (kvm_guest_has_pmu(&vcpu->arch)) { + vcpu->arch.pc -= 4; + kvm_make_request(KVM_REQ_PMU, vcpu); + return EMULATE_DONE; + } + } + /* Process CSR ops */ switch (rj) { case 0: /* process csrrd */ @@ -106,8 +156,8 @@ static int kvm_handle_csr(struct kvm_vcpu *vcpu, larch_inst inst) int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu) { - int ret; - unsigned long val; + int idx, ret; + unsigned long *val; u32 addr, rd, rj, opcode; /* @@ -117,9 +167,9 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu) rj = inst.reg2_format.rj; opcode = inst.reg2_format.opcode; addr = vcpu->arch.gprs[rj]; - ret = EMULATE_DO_IOCSR; run->iocsr_io.phys_addr = addr; run->iocsr_io.is_write = 0; + val = &vcpu->arch.gprs[rd]; /* LoongArch is Little endian */ switch (opcode) { @@ -152,16 +202,33 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu) run->iocsr_io.is_write = 1; break; default: - ret = EMULATE_FAIL; - break; + return EMULATE_FAIL; } - if (ret == EMULATE_DO_IOCSR) { - if (run->iocsr_io.is_write) { - val = vcpu->arch.gprs[rd]; - memcpy(run->iocsr_io.data, &val, run->iocsr_io.len); + if (run->iocsr_io.is_write) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (ret == 0) + ret = EMULATE_DONE; + else { + ret = EMULATE_DO_IOCSR; + /* Save data and let user space to write it */ + memcpy(run->iocsr_io.data, val, run->iocsr_io.len); } - vcpu->arch.io_gpr = rd; + trace_kvm_iocsr(KVM_TRACE_IOCSR_WRITE, run->iocsr_io.len, addr, val); + } else { + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (ret == 0) + ret = EMULATE_DONE; + else { + ret = EMULATE_DO_IOCSR; + /* Save register id for iocsr read completion */ + vcpu->arch.io_gpr = rd; + } + trace_kvm_iocsr(KVM_TRACE_IOCSR_READ, run->iocsr_io.len, addr, NULL); } return ret; @@ -208,8 +275,6 @@ int kvm_emu_idle(struct kvm_vcpu *vcpu) static int kvm_trap_handle_gspr(struct kvm_vcpu *vcpu) { - int rd, rj; - unsigned int index; unsigned long curr_pc; larch_inst inst; enum emulation_result er = EMULATE_DONE; @@ -224,21 +289,7 @@ static int kvm_trap_handle_gspr(struct kvm_vcpu *vcpu) er = EMULATE_FAIL; switch (((inst.word >> 24) & 0xff)) { case 0x0: /* CPUCFG GSPR */ - if (inst.reg2_format.opcode == 0x1B) { - rd = inst.reg2_format.rd; - rj = inst.reg2_format.rj; - ++vcpu->stat.cpucfg_exits; - index = vcpu->arch.gprs[rj]; - er = EMULATE_DONE; - /* - * By LoongArch Reference Manual 2.2.10.5 - * return value is 0 for undefined cpucfg index - */ - if (index < KVM_MAX_CPUCFG_REGS) - vcpu->arch.gprs[rd] = vcpu->arch.cpucfg[index]; - else - vcpu->arch.gprs[rd] = 0; - } + er = kvm_emu_cpucfg(vcpu, inst); break; case 0x4: /* CSR{RD,WR,XCHG} GSPR */ er = kvm_handle_csr(vcpu, inst); @@ -315,7 +366,7 @@ static int kvm_handle_gspr(struct kvm_vcpu *vcpu) int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst) { - int ret; + int idx, ret; unsigned int op8, opcode, rd; struct kvm_run *run = vcpu->run; @@ -413,17 +464,35 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst) } if (ret == EMULATE_DO_MMIO) { + trace_kvm_mmio(KVM_TRACE_MMIO_READ, run->mmio.len, run->mmio.phys_addr, NULL); + + /* + * If mmio device such as PCH-PIC is emulated in KVM, + * it need not return to user space to handle the mmio + * exception. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, vcpu->arch.badv, + run->mmio.len, &vcpu->arch.gprs[rd]); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (!ret) { + update_pc(&vcpu->arch); + vcpu->mmio_needed = 0; + return EMULATE_DONE; + } + /* Set for kvm_complete_mmio_read() use */ vcpu->arch.io_gpr = rd; run->mmio.is_write = 0; vcpu->mmio_is_write = 0; - } else { - kvm_err("Read not supported Inst=0x%08x @%lx BadVaddr:%#lx\n", - inst.word, vcpu->arch.pc, vcpu->arch.badv); - kvm_arch_vcpu_dump_regs(vcpu); - vcpu->mmio_needed = 0; + return EMULATE_DO_MMIO; } + kvm_err("Read not supported Inst=0x%08x @%lx BadVaddr:%#lx\n", + inst.word, vcpu->arch.pc, vcpu->arch.badv); + kvm_arch_vcpu_dump_regs(vcpu); + vcpu->mmio_needed = 0; + return ret; } @@ -463,12 +532,15 @@ int kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run) break; } + trace_kvm_mmio(KVM_TRACE_MMIO_READ, run->mmio.len, + run->mmio.phys_addr, run->mmio.data); + return er; } int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst) { - int ret; + int idx, ret; unsigned int rd, op8, opcode; unsigned long curr_pc, rd_val = 0; struct kvm_run *run = vcpu->run; @@ -561,17 +633,31 @@ int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst) } if (ret == EMULATE_DO_MMIO) { + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, run->mmio.len, run->mmio.phys_addr, data); + + /* + * If mmio device such as PCH-PIC is emulated in KVM, + * it need not return to user space to handle the mmio + * exception. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, vcpu->arch.badv, run->mmio.len, data); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (!ret) + return EMULATE_DONE; + run->mmio.is_write = 1; vcpu->mmio_needed = 1; vcpu->mmio_is_write = 1; - } else { - vcpu->arch.pc = curr_pc; - kvm_err("Write not supported Inst=0x%08x @%lx BadVaddr:%#lx\n", - inst.word, vcpu->arch.pc, vcpu->arch.badv); - kvm_arch_vcpu_dump_regs(vcpu); - /* Rollback PC if emulation was unsuccessful */ + return EMULATE_DO_MMIO; } + vcpu->arch.pc = curr_pc; + kvm_err("Write not supported Inst=0x%08x @%lx BadVaddr:%#lx\n", + inst.word, vcpu->arch.pc, vcpu->arch.badv); + kvm_arch_vcpu_dump_regs(vcpu); + /* Rollback PC if emulation was unsuccessful */ + return ret; } @@ -583,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write) struct kvm_run *run = vcpu->run; unsigned long badv = vcpu->arch.badv; + /* Inject ADE exception if exceed max GPA size */ + if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) { + kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM); + return RESUME_GUEST; + } + ret = kvm_handle_mm_fault(vcpu, badv, write); if (ret) { /* Treat as MMIO */ @@ -623,6 +715,14 @@ static int kvm_handle_write_fault(struct kvm_vcpu *vcpu) return kvm_handle_rdwr_fault(vcpu, true); } +int kvm_complete_user_service(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + update_pc(&vcpu->arch); + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, run->hypercall.ret); + + return 0; +} + /** * kvm_handle_fpu_disabled() - Guest used fpu however it is disabled at host * @vcpu: Virtual CPU context. @@ -655,6 +755,31 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +static long kvm_save_notify(struct kvm_vcpu *vcpu) +{ + unsigned long id, data; + + id = kvm_read_reg(vcpu, LOONGARCH_GPR_A1); + data = kvm_read_reg(vcpu, LOONGARCH_GPR_A2); + switch (id) { + case BIT(KVM_FEATURE_STEAL_TIME): + if (data & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID)) + return KVM_HCALL_INVALID_PARAMETER; + + vcpu->arch.st.guest_addr = data; + if (!(data & KVM_STEAL_PHYS_VALID)) + return 0; + + vcpu->arch.st.last_steal = current->sched_info.run_delay; + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + return 0; + default: + return KVM_HCALL_INVALID_CODE; + }; + + return KVM_HCALL_INVALID_CODE; +}; + /* * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root. * @vcpu: Virtual CPU context. @@ -685,6 +810,125 @@ static int kvm_handle_lasx_disabled(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +static int kvm_handle_lbt_disabled(struct kvm_vcpu *vcpu) +{ + if (kvm_own_lbt(vcpu)) + kvm_queue_exception(vcpu, EXCCODE_INE, 0); + + return RESUME_GUEST; +} + +static int kvm_send_pv_ipi(struct kvm_vcpu *vcpu) +{ + unsigned int min, cpu, i; + unsigned long ipi_bitmap; + struct kvm_vcpu *dest; + + 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) + 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); + } + } + + return 0; +} + +/* + * Hypercall emulation always return to guest, Caller should check retval. + */ +static void kvm_handle_service(struct kvm_vcpu *vcpu) +{ + long ret = KVM_HCALL_INVALID_CODE; + unsigned long func = kvm_read_reg(vcpu, LOONGARCH_GPR_A0); + + switch (func) { + case KVM_HCALL_FUNC_IPI: + if (kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_IPI)) { + kvm_send_pv_ipi(vcpu); + ret = KVM_HCALL_SUCCESS; + } + break; + case KVM_HCALL_FUNC_NOTIFY: + if (kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME)) + ret = kvm_save_notify(vcpu); + break; + default: + break; + } + + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, ret); +} + +static int kvm_handle_hypercall(struct kvm_vcpu *vcpu) +{ + int ret; + larch_inst inst; + unsigned int code; + + inst.word = vcpu->arch.badi; + code = inst.reg0i15_format.immediate; + ret = RESUME_GUEST; + + switch (code) { + case KVM_HCALL_SERVICE: + vcpu->stat.hypercall_exits++; + kvm_handle_service(vcpu); + break; + case KVM_HCALL_USER_SERVICE: + if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_USER_HCALL)) { + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, KVM_HCALL_INVALID_CODE); + break; + } + + vcpu->stat.hypercall_exits++; + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HCALL_USER_SERVICE; + vcpu->run->hypercall.args[0] = kvm_read_reg(vcpu, LOONGARCH_GPR_A0); + vcpu->run->hypercall.args[1] = kvm_read_reg(vcpu, LOONGARCH_GPR_A1); + vcpu->run->hypercall.args[2] = kvm_read_reg(vcpu, LOONGARCH_GPR_A2); + vcpu->run->hypercall.args[3] = kvm_read_reg(vcpu, LOONGARCH_GPR_A3); + vcpu->run->hypercall.args[4] = kvm_read_reg(vcpu, LOONGARCH_GPR_A4); + vcpu->run->hypercall.args[5] = kvm_read_reg(vcpu, LOONGARCH_GPR_A5); + vcpu->run->hypercall.flags = 0; + /* + * Set invalid return value by default, let user-mode VMM modify it. + */ + vcpu->run->hypercall.ret = KVM_HCALL_INVALID_CODE; + ret = RESUME_HOST; + break; + case KVM_HCALL_SWDBG: + /* KVM_HCALL_SWDBG only in effective when SW_BP is enabled */ + if (vcpu->guest_debug & KVM_GUESTDBG_SW_BP_MASK) { + vcpu->run->exit_reason = KVM_EXIT_DEBUG; + ret = RESUME_HOST; + break; + } + fallthrough; + default: + /* Treat it as noop intruction, only set return value */ + kvm_write_reg(vcpu, LOONGARCH_GPR_A0, KVM_HCALL_INVALID_CODE); + break; + } + + if (ret == RESUME_GUEST) + update_pc(&vcpu->arch); + + return ret; +} + /* * LoongArch KVM callback handling for unimplemented guest exiting */ @@ -715,7 +959,9 @@ static exit_handle_fn kvm_fault_tables[EXCCODE_INT_START] = { [EXCCODE_FPDIS] = kvm_handle_fpu_disabled, [EXCCODE_LSXDIS] = kvm_handle_lsx_disabled, [EXCCODE_LASXDIS] = kvm_handle_lasx_disabled, + [EXCCODE_BTDIS] = kvm_handle_lbt_disabled, [EXCCODE_GSPR] = kvm_handle_gspr, + [EXCCODE_HVC] = kvm_handle_hypercall, }; int kvm_handle_fault(struct kvm_vcpu *vcpu, int fault) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c new file mode 100644 index 000000000000..f39929d7bf8a --- /dev/null +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -0,0 +1,1027 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <asm/kvm_eiointc.h> +#include <asm/kvm_vcpu.h> +#include <linux/count_zeros.h> + +static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) +{ + int ipnum, cpu, irq_index, irq_mask, irq; + + for (irq = 0; irq < EIOINTC_IRQS; irq++) { + ipnum = s->ipmap.reg_u8[irq / 32]; + if (!(s->status & BIT(EIOINTC_ENABLE_INT_ENCODE))) { + ipnum = count_trailing_zeros(ipnum); + ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0; + } + irq_index = irq / 32; + irq_mask = BIT(irq & 0x1f); + + cpu = s->coremap.reg_u8[irq]; + if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask)) + set_bit(irq, s->sw_coreisr[cpu][ipnum]); + else + 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; + struct kvm_vcpu *vcpu; + struct kvm_interrupt vcpu_irq; + + ipnum = s->ipmap.reg_u8[irq / 32]; + if (!(s->status & BIT(EIOINTC_ENABLE_INT_ENCODE))) { + ipnum = count_trailing_zeros(ipnum); + ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0; + } + + 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) + return; + s->coreisr.reg_u32[cpu][irq_index] |= irq_mask; + found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS); + 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]); + found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS); + } + + if (found < EIOINTC_IRQS) + return; /* other irq is handling, needn't update parent irq */ + + vcpu_irq.irq = level ? (INT_HWI0 + ipnum) : -(INT_HWI0 + ipnum); + kvm_vcpu_ioctl_interrupt(vcpu, &vcpu_irq); +} + +static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, + int irq, void *pvalue, u32 len, bool notify) +{ + int i, cpu; + u64 val = *(u64 *)pvalue; + + for (i = 0; i < len; i++) { + cpu = val & 0xff; + val = val >> 8; + + if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) { + cpu = ffs(cpu) - 1; + cpu = (cpu >= 4) ? 0 : cpu; + } + + if (s->sw_coremap[irq + i] == cpu) + continue; + + if (notify && test_bit(irq + i, (unsigned long *)s->isr.reg_u8)) { + /* lower irq at old cpu and raise irq at new cpu */ + eiointc_update_irq(s, irq + i, 0); + s->sw_coremap[irq + i] = cpu; + eiointc_update_irq(s, irq + i, 1); + } else { + s->sw_coremap[irq + i] = cpu; + } + } +} + +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); + 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) +{ + int index, ret = 0; + u64 data = 0; + gpa_t offset; + + offset = addr - EIOINTC_BASE; + switch (offset) { + case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: + index = (offset - EIOINTC_NODETYPE_START) >> 3; + data = s->nodetype.reg_u64[index]; + break; + case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: + index = (offset - EIOINTC_IPMAP_START) >> 3; + data = s->ipmap.reg_u64; + break; + case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: + index = (offset - EIOINTC_ENABLE_START) >> 3; + data = s->enable.reg_u64[index]; + break; + case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: + index = (offset - EIOINTC_BOUNCE_START) >> 3; + data = s->bounce.reg_u64[index]; + break; + case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: + index = (offset - EIOINTC_COREISR_START) >> 3; + data = s->coreisr.reg_u64[vcpu->vcpu_id][index]; + break; + case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: + index = (offset - EIOINTC_COREMAP_START) >> 3; + data = s->coremap.reg_u64[index]; + break; + default: + ret = -EINVAL; + break; + } + *(u64 *)val = data; + + return ret; +} + +static int kvm_eiointc_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + int ret = -EINVAL; + unsigned long flags; + struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; + + if (!eiointc) { + kvm_err("%s: eiointc irqchip not valid!\n", __func__); + return -EINVAL; + } + + vcpu->kvm->stat.eiointc_read_exits++; + spin_lock_irqsave(&eiointc->lock, flags); + switch (len) { + case 1: + ret = loongarch_eiointc_readb(vcpu, eiointc, addr, len, val); + break; + case 2: + ret = loongarch_eiointc_readw(vcpu, eiointc, addr, len, val); + break; + case 4: + ret = loongarch_eiointc_readl(vcpu, eiointc, addr, len, val); + break; + case 8: + ret = loongarch_eiointc_readq(vcpu, eiointc, addr, len, val); + 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, (void *)&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_u32[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]; + index = index << 1; + for (i = 0; i < sizeof(data); i++) { + u8 mask = (data >> (i * 8)) & 0xff; + eiointc_enable_irq(vcpu, s, index + 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, 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, (void *)&data, sizeof(data), true); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int loongarch_eiointc_writel(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; + u32 data, old_data; + u32 coreisr, old_coreisr; + gpa_t offset; + + data = *(u32 *)val; + offset = addr - EIOINTC_BASE; + + 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]; + index = index << 2; + for (i = 0; i < sizeof(data); i++) { + u8 mask = (data >> (i * 8)) & 0xff; + eiointc_enable_irq(vcpu, s, index + 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, 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, (void *)&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; + 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; + 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; + 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; + /* + * 1: enable irq. + * update irq when isr is set. + */ + data = s->enable.reg_u64[index] & ~old_data & s->isr.reg_u64[index]; + index = index << 3; + for (i = 0; i < sizeof(data); i++) { + u8 mask = (data >> (i * 8)) & 0xff; + eiointc_enable_irq(vcpu, s, index + i, mask, 1); + } + /* + * 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, mask, 0); + } + 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; + 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]; + /* 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); + } + 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, (void *)&data, sizeof(data), true); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int kvm_eiointc_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + int ret = -EINVAL; + unsigned long flags; + struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; + + if (!eiointc) { + kvm_err("%s: eiointc irqchip not valid!\n", __func__); + return -EINVAL; + } + + vcpu->kvm->stat.eiointc_write_exits++; + spin_lock_irqsave(&eiointc->lock, flags); + switch (len) { + case 1: + ret = loongarch_eiointc_writeb(vcpu, eiointc, addr, len, val); + break; + case 2: + ret = loongarch_eiointc_writew(vcpu, eiointc, addr, len, val); + break; + case 4: + ret = loongarch_eiointc_writel(vcpu, eiointc, addr, len, val); + break; + case 8: + ret = loongarch_eiointc_writeq(vcpu, eiointc, addr, len, val); + 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 const struct kvm_io_device_ops kvm_eiointc_ops = { + .read = kvm_eiointc_read, + .write = kvm_eiointc_write, +}; + +static int kvm_eiointc_virt_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + unsigned long flags; + u32 *data = val; + struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; + + if (!eiointc) { + kvm_err("%s: eiointc irqchip not valid!\n", __func__); + return -EINVAL; + } + + addr -= EIOINTC_VIRT_BASE; + spin_lock_irqsave(&eiointc->lock, flags); + switch (addr) { + case EIOINTC_VIRT_FEATURES: + *data = eiointc->features; + break; + case EIOINTC_VIRT_CONFIG: + *data = eiointc->status; + break; + default: + break; + } + spin_unlock_irqrestore(&eiointc->lock, flags); + + return 0; +} + +static int kvm_eiointc_virt_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + int ret = 0; + unsigned long flags; + u32 value = *(u32 *)val; + struct loongarch_eiointc *eiointc = vcpu->kvm->arch.eiointc; + + if (!eiointc) { + kvm_err("%s: eiointc irqchip not valid!\n", __func__); + return -EINVAL; + } + + addr -= EIOINTC_VIRT_BASE; + spin_lock_irqsave(&eiointc->lock, flags); + switch (addr) { + case EIOINTC_VIRT_FEATURES: + ret = -EPERM; + break; + case EIOINTC_VIRT_CONFIG: + /* + * eiointc features can only be set at disabled status + */ + if ((eiointc->status & BIT(EIOINTC_ENABLE)) && value) { + ret = -EPERM; + break; + } + eiointc->status = value & eiointc->features; + break; + default: + break; + } + spin_unlock_irqrestore(&eiointc->lock, flags); + + return ret; +} + +static const struct kvm_io_device_ops kvm_eiointc_virt_ops = { + .read = kvm_eiointc_virt_read, + .write = kvm_eiointc_virt_write, +}; + +static int kvm_eiointc_ctrl_access(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret = 0; + unsigned long flags; + unsigned long type = (unsigned long)attr->attr; + u32 i, start_irq; + void __user *data; + struct loongarch_eiointc *s = dev->kvm->arch.eiointc; + + data = (void __user *)attr->addr; + spin_lock_irqsave(&s->lock, flags); + switch (type) { + case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: + if (copy_from_user(&s->num_cpu, data, 4)) + ret = -EFAULT; + break; + case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE: + if (copy_from_user(&s->features, data, 4)) + ret = -EFAULT; + if (!(s->features & BIT(EIOINTC_HAS_VIRT_EXTENSION))) + s->status |= BIT(EIOINTC_ENABLE); + break; + case KVM_DEV_LOONGARCH_EXTIOI_CTRL_LOAD_FINISHED: + eiointc_set_sw_coreisr(s); + for (i = 0; i < (EIOINTC_IRQS / 4); i++) { + start_irq = i * 4; + eiointc_update_sw_coremap(s, start_irq, + (void *)&s->coremap.reg_u32[i], sizeof(u32), false); + } + break; + default: + break; + } + spin_unlock_irqrestore(&s->lock, flags); + + return ret; +} + +static int kvm_eiointc_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + bool is_write) +{ + int addr, cpuid, offset, ret = 0; + unsigned long flags; + void *p = NULL; + void __user *data; + struct loongarch_eiointc *s; + + s = dev->kvm->arch.eiointc; + addr = attr->attr; + cpuid = addr >> 16; + addr &= 0xffff; + data = (void __user *)attr->addr; + switch (addr) { + case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: + offset = (addr - EIOINTC_NODETYPE_START) / 4; + p = &s->nodetype.reg_u32[offset]; + break; + case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: + offset = (addr - EIOINTC_IPMAP_START) / 4; + p = &s->ipmap.reg_u32[offset]; + break; + case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: + offset = (addr - EIOINTC_ENABLE_START) / 4; + p = &s->enable.reg_u32[offset]; + break; + case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: + offset = (addr - EIOINTC_BOUNCE_START) / 4; + p = &s->bounce.reg_u32[offset]; + break; + case EIOINTC_ISR_START ... EIOINTC_ISR_END: + offset = (addr - EIOINTC_ISR_START) / 4; + p = &s->isr.reg_u32[offset]; + break; + case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: + offset = (addr - EIOINTC_COREISR_START) / 4; + p = &s->coreisr.reg_u32[cpuid][offset]; + break; + case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: + offset = (addr - EIOINTC_COREMAP_START) / 4; + p = &s->coremap.reg_u32[offset]; + break; + default: + kvm_err("%s: unknown eiointc register, addr = %d\n", __func__, addr); + return -EINVAL; + } + + spin_lock_irqsave(&s->lock, flags); + if (is_write) { + if (copy_from_user(p, data, 4)) + ret = -EFAULT; + } else { + if (copy_to_user(data, p, 4)) + ret = -EFAULT; + } + spin_unlock_irqrestore(&s->lock, flags); + + return ret; +} + +static int kvm_eiointc_sw_status_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + bool is_write) +{ + int addr, ret = 0; + unsigned long flags; + void *p = NULL; + void __user *data; + struct loongarch_eiointc *s; + + s = dev->kvm->arch.eiointc; + addr = attr->attr; + addr &= 0xffff; + + data = (void __user *)attr->addr; + switch (addr) { + case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU: + p = &s->num_cpu; + break; + case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE: + p = &s->features; + break; + case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE: + p = &s->status; + break; + default: + kvm_err("%s: unknown eiointc register, addr = %d\n", __func__, addr); + return -EINVAL; + } + spin_lock_irqsave(&s->lock, flags); + if (is_write) { + if (copy_from_user(p, data, 4)) + ret = -EFAULT; + } else { + if (copy_to_user(data, p, 4)) + ret = -EFAULT; + } + spin_unlock_irqrestore(&s->lock, flags); + + return ret; +} + +static int kvm_eiointc_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_LOONGARCH_EXTIOI_GRP_REGS: + return kvm_eiointc_regs_access(dev, attr, false); + case KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS: + return kvm_eiointc_sw_status_access(dev, attr, false); + default: + return -EINVAL; + } +} + +static int kvm_eiointc_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL: + return kvm_eiointc_ctrl_access(dev, attr); + case KVM_DEV_LOONGARCH_EXTIOI_GRP_REGS: + return kvm_eiointc_regs_access(dev, attr, true); + case KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS: + return kvm_eiointc_sw_status_access(dev, attr, true); + default: + return -EINVAL; + } +} + +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 *kvm = dev->kvm; + + /* eiointc has been created */ + if (kvm->arch.eiointc) + return -EINVAL; + + s = kzalloc(sizeof(struct loongarch_eiointc), GFP_KERNEL); + if (!s) + return -ENOMEM; + + spin_lock_init(&s->lock); + s->kvm = kvm; + + /* + * Initialize IOCSR device + */ + device = &s->device; + kvm_iodevice_init(device, &kvm_eiointc_ops); + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS, + EIOINTC_BASE, EIOINTC_SIZE, device); + mutex_unlock(&kvm->slots_lock); + if (ret < 0) { + kfree(s); + return ret; + } + + device1 = &s->device_vext; + kvm_iodevice_init(device1, &kvm_eiointc_virt_ops); + ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS, + EIOINTC_VIRT_BASE, EIOINTC_VIRT_SIZE, device1); + if (ret < 0) { + kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &s->device); + kfree(s); + return ret; + } + kvm->arch.eiointc = s; + + return 0; +} + +static void kvm_eiointc_destroy(struct kvm_device *dev) +{ + struct kvm *kvm; + struct loongarch_eiointc *eiointc; + + if (!dev || !dev->kvm || !dev->kvm->arch.eiointc) + return; + + kvm = dev->kvm; + eiointc = kvm->arch.eiointc; + kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device); + kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext); + kfree(eiointc); +} + +static struct kvm_device_ops kvm_eiointc_dev_ops = { + .name = "kvm-loongarch-eiointc", + .create = kvm_eiointc_create, + .destroy = kvm_eiointc_destroy, + .set_attr = kvm_eiointc_set_attr, + .get_attr = kvm_eiointc_get_attr, +}; + +int kvm_loongarch_register_eiointc_device(void) +{ + return kvm_register_device_ops(&kvm_eiointc_dev_ops, KVM_DEV_TYPE_LOONGARCH_EIOINTC); +} diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c new file mode 100644 index 000000000000..93f4acd44523 --- /dev/null +++ b/arch/loongarch/kvm/intc/ipi.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_ipi.h> +#include <asm/kvm_vcpu.h> + +static void ipi_send(struct kvm *kvm, uint64_t data) +{ + int cpu, action; + uint32_t status; + struct kvm_vcpu *vcpu; + struct kvm_interrupt irq; + + cpu = ((data & 0xffffffff) >> 16) & 0x3ff; + vcpu = kvm_get_vcpu_by_cpuid(kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return; + } + + action = BIT(data & 0x1f); + spin_lock(&vcpu->arch.ipi_state.lock); + status = vcpu->arch.ipi_state.status; + vcpu->arch.ipi_state.status |= action; + spin_unlock(&vcpu->arch.ipi_state.lock); + if (status == 0) { + irq.irq = LARCH_INT_IPI; + kvm_vcpu_ioctl_interrupt(vcpu, &irq); + } +} + +static void ipi_clear(struct kvm_vcpu *vcpu, uint64_t data) +{ + uint32_t status; + struct kvm_interrupt irq; + + spin_lock(&vcpu->arch.ipi_state.lock); + vcpu->arch.ipi_state.status &= ~data; + status = vcpu->arch.ipi_state.status; + spin_unlock(&vcpu->arch.ipi_state.lock); + if (status == 0) { + irq.irq = -LARCH_INT_IPI; + kvm_vcpu_ioctl_interrupt(vcpu, &irq); + } +} + +static uint64_t read_mailbox(struct kvm_vcpu *vcpu, int offset, int len) +{ + uint64_t data = 0; + + spin_lock(&vcpu->arch.ipi_state.lock); + data = *(ulong *)((void *)vcpu->arch.ipi_state.buf + (offset - 0x20)); + spin_unlock(&vcpu->arch.ipi_state.lock); + + switch (len) { + case 1: + return data & 0xff; + case 2: + return data & 0xffff; + case 4: + return data & 0xffffffff; + case 8: + return data; + default: + kvm_err("%s: unknown data len: %d\n", __func__, len); + return 0; + } +} + +static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int len) +{ + void *pbuf; + + spin_lock(&vcpu->arch.ipi_state.lock); + pbuf = (void *)vcpu->arch.ipi_state.buf + (offset - 0x20); + + switch (len) { + case 1: + *(unsigned char *)pbuf = (unsigned char)data; + break; + case 2: + *(unsigned short *)pbuf = (unsigned short)data; + break; + case 4: + *(unsigned int *)pbuf = (unsigned int)data; + break; + case 8: + *(unsigned long *)pbuf = (unsigned long)data; + break; + default: + kvm_err("%s: unknown data len: %d\n", __func__, len); + } + spin_unlock(&vcpu->arch.ipi_state.lock); +} + +static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) +{ + int i, idx, ret; + uint32_t val = 0, mask = 0; + + /* + * Bit 27-30 is mask for byte writing. + * If the mask is 0, we need not to do anything. + */ + if ((data >> 27) & 0xf) { + /* Read the old val */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (unlikely(ret)) { + kvm_err("%s: : read date from addr %llx failed\n", __func__, addr); + return ret; + } + /* Construct the mask by scanning the bit 27-30 */ + for (i = 0; i < 4; i++) { + if (data & (BIT(27 + i))) + mask |= (0xff << (i * 8)); + } + /* Save the old part of val */ + val &= mask; + } + val |= ((uint32_t)(data >> 32) & ~mask); + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (unlikely(ret)) + kvm_err("%s: : write date to addr %llx failed\n", __func__, addr); + + return ret; +} + +static int mail_send(struct kvm *kvm, uint64_t data) +{ + int cpu, mailbox, offset; + struct kvm_vcpu *vcpu; + + cpu = ((data & 0xffffffff) >> 16) & 0x3ff; + vcpu = kvm_get_vcpu_by_cpuid(kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return -EINVAL; + } + mailbox = ((data & 0xffffffff) >> 2) & 0x7; + offset = IOCSR_IPI_BASE + IOCSR_IPI_BUF_20 + mailbox * 4; + + return send_ipi_data(vcpu, offset, data); +} + +static int any_send(struct kvm *kvm, uint64_t data) +{ + int cpu, offset; + struct kvm_vcpu *vcpu; + + cpu = ((data & 0xffffffff) >> 16) & 0x3ff; + vcpu = kvm_get_vcpu_by_cpuid(kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return -EINVAL; + } + offset = data & 0xffff; + + return send_ipi_data(vcpu, offset, data); +} + +static int loongarch_ipi_readl(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *val) +{ + int ret = 0; + uint32_t offset; + uint64_t res = 0; + + offset = (uint32_t)(addr & 0x1ff); + WARN_ON_ONCE(offset & (len - 1)); + + switch (offset) { + case IOCSR_IPI_STATUS: + spin_lock(&vcpu->arch.ipi_state.lock); + res = vcpu->arch.ipi_state.status; + spin_unlock(&vcpu->arch.ipi_state.lock); + break; + case IOCSR_IPI_EN: + spin_lock(&vcpu->arch.ipi_state.lock); + res = vcpu->arch.ipi_state.en; + spin_unlock(&vcpu->arch.ipi_state.lock); + break; + case IOCSR_IPI_SET: + res = 0; + break; + case IOCSR_IPI_CLEAR: + res = 0; + break; + case IOCSR_IPI_BUF_20 ... IOCSR_IPI_BUF_38 + 7: + if (offset + len > IOCSR_IPI_BUF_38 + 8) { + kvm_err("%s: invalid offset or len: offset = %d, len = %d\n", + __func__, offset, len); + ret = -EINVAL; + break; + } + res = read_mailbox(vcpu, offset, len); + break; + default: + kvm_err("%s: unknown addr: %llx\n", __func__, addr); + ret = -EINVAL; + break; + } + *(uint64_t *)val = res; + + return ret; +} + +static int loongarch_ipi_writel(struct kvm_vcpu *vcpu, gpa_t addr, int len, const void *val) +{ + int ret = 0; + uint64_t data; + uint32_t offset; + + data = *(uint64_t *)val; + + offset = (uint32_t)(addr & 0x1ff); + WARN_ON_ONCE(offset & (len - 1)); + + switch (offset) { + case IOCSR_IPI_STATUS: + ret = -EINVAL; + break; + case IOCSR_IPI_EN: + spin_lock(&vcpu->arch.ipi_state.lock); + vcpu->arch.ipi_state.en = data; + spin_unlock(&vcpu->arch.ipi_state.lock); + break; + case IOCSR_IPI_SET: + ret = -EINVAL; + break; + case IOCSR_IPI_CLEAR: + /* Just clear the status of the current vcpu */ + ipi_clear(vcpu, data); + break; + case IOCSR_IPI_BUF_20 ... IOCSR_IPI_BUF_38 + 7: + if (offset + len > IOCSR_IPI_BUF_38 + 8) { + kvm_err("%s: invalid offset or len: offset = %d, len = %d\n", + __func__, offset, len); + ret = -EINVAL; + break; + } + write_mailbox(vcpu, offset, data, len); + break; + case IOCSR_IPI_SEND: + ipi_send(vcpu->kvm, data); + break; + case IOCSR_MAIL_SEND: + ret = mail_send(vcpu->kvm, *(uint64_t *)val); + break; + case IOCSR_ANY_SEND: + ret = any_send(vcpu->kvm, *(uint64_t *)val); + break; + default: + kvm_err("%s: unknown addr: %llx\n", __func__, addr); + ret = -EINVAL; + break; + } + + return ret; +} + +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; +} + +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; +} + +static const struct kvm_io_device_ops kvm_ipi_ops = { + .read = kvm_ipi_read, + .write = kvm_ipi_write, +}; + +static int kvm_ipi_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + bool is_write) +{ + int len = 4; + int cpu, addr; + uint64_t val; + void *p = NULL; + struct kvm_vcpu *vcpu; + + cpu = (attr->attr >> 16) & 0x3ff; + addr = attr->attr & 0xff; + + vcpu = kvm_get_vcpu(dev->kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return -EINVAL; + } + + switch (addr) { + case IOCSR_IPI_STATUS: + p = &vcpu->arch.ipi_state.status; + break; + case IOCSR_IPI_EN: + p = &vcpu->arch.ipi_state.en; + break; + case IOCSR_IPI_SET: + p = &vcpu->arch.ipi_state.set; + break; + case IOCSR_IPI_CLEAR: + p = &vcpu->arch.ipi_state.clear; + break; + case IOCSR_IPI_BUF_20: + p = &vcpu->arch.ipi_state.buf[0]; + len = 8; + break; + case IOCSR_IPI_BUF_28: + p = &vcpu->arch.ipi_state.buf[1]; + len = 8; + break; + case IOCSR_IPI_BUF_30: + p = &vcpu->arch.ipi_state.buf[2]; + len = 8; + break; + case IOCSR_IPI_BUF_38: + p = &vcpu->arch.ipi_state.buf[3]; + len = 8; + break; + default: + kvm_err("%s: unknown ipi register, addr = %d\n", __func__, addr); + return -EINVAL; + } + + if (is_write) { + if (len == 4) { + if (get_user(val, (uint32_t __user *)attr->addr)) + return -EFAULT; + *(uint32_t *)p = (uint32_t)val; + } else if (len == 8) { + if (get_user(val, (uint64_t __user *)attr->addr)) + return -EFAULT; + *(uint64_t *)p = val; + } + } else { + if (len == 4) { + val = *(uint32_t *)p; + return put_user(val, (uint32_t __user *)attr->addr); + } else if (len == 8) { + val = *(uint64_t *)p; + return put_user(val, (uint64_t __user *)attr->addr); + } + } + + return 0; +} + +static int kvm_ipi_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_LOONGARCH_IPI_GRP_REGS: + return kvm_ipi_regs_access(dev, attr, false); + default: + kvm_err("%s: unknown group (%d)\n", __func__, attr->group); + return -EINVAL; + } +} + +static int kvm_ipi_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_LOONGARCH_IPI_GRP_REGS: + return kvm_ipi_regs_access(dev, attr, true); + default: + kvm_err("%s: unknown group (%d)\n", __func__, attr->group); + return -EINVAL; + } +} + +static int kvm_ipi_create(struct kvm_device *dev, u32 type) +{ + int ret; + struct kvm *kvm; + struct kvm_io_device *device; + struct loongarch_ipi *s; + + if (!dev) { + kvm_err("%s: kvm_device ptr is invalid!\n", __func__); + return -EINVAL; + } + + kvm = dev->kvm; + if (kvm->arch.ipi) { + kvm_err("%s: LoongArch IPI has already been created!\n", __func__); + return -EINVAL; + } + + s = kzalloc(sizeof(struct loongarch_ipi), GFP_KERNEL); + if (!s) + return -ENOMEM; + + spin_lock_init(&s->lock); + s->kvm = kvm; + + /* + * Initialize IOCSR device + */ + device = &s->device; + kvm_iodevice_init(device, &kvm_ipi_ops); + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS, IOCSR_IPI_BASE, IOCSR_IPI_SIZE, device); + mutex_unlock(&kvm->slots_lock); + if (ret < 0) { + kvm_err("%s: Initialize IOCSR dev failed, ret = %d\n", __func__, ret); + goto err; + } + + kvm->arch.ipi = s; + return 0; + +err: + kfree(s); + return -EFAULT; +} + +static void kvm_ipi_destroy(struct kvm_device *dev) +{ + struct kvm *kvm; + struct loongarch_ipi *ipi; + + if (!dev || !dev->kvm || !dev->kvm->arch.ipi) + return; + + kvm = dev->kvm; + ipi = kvm->arch.ipi; + kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device); + kfree(ipi); +} + +static struct kvm_device_ops kvm_ipi_dev_ops = { + .name = "kvm-loongarch-ipi", + .create = kvm_ipi_create, + .destroy = kvm_ipi_destroy, + .set_attr = kvm_ipi_set_attr, + .get_attr = kvm_ipi_get_attr, +}; + +int kvm_loongarch_register_ipi_device(void) +{ + return kvm_register_device_ops(&kvm_ipi_dev_ops, KVM_DEV_TYPE_LOONGARCH_IPI); +} diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c new file mode 100644 index 000000000000..08fce845f668 --- /dev/null +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -0,0 +1,519 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <asm/kvm_eiointc.h> +#include <asm/kvm_pch_pic.h> +#include <asm/kvm_vcpu.h> +#include <linux/count_zeros.h> + +/* update the isr according to irq level and route irq to eiointc */ +static void pch_pic_update_irq(struct loongarch_pch_pic *s, int irq, int level) +{ + u64 mask = BIT(irq); + + /* + * set isr and route irq to eiointc and + * the route table is in htmsi_vector[] + */ + if (level) { + if (mask & s->irr & ~s->mask) { + s->isr |= mask; + irq = s->htmsi_vector[irq]; + eiointc_set_irq(s->kvm->arch.eiointc, irq, level); + } + } else { + if (mask & s->isr & ~s->irr) { + s->isr &= ~mask; + irq = s->htmsi_vector[irq]; + eiointc_set_irq(s->kvm->arch.eiointc, irq, level); + } + } +} + +/* update batch irqs, the irq_mask is a bitmap of irqs */ +static void pch_pic_update_batch_irqs(struct loongarch_pch_pic *s, u64 irq_mask, int level) +{ + int irq, bits; + + /* find each irq by irqs bitmap and update each irq */ + bits = sizeof(irq_mask) * 8; + irq = find_first_bit((void *)&irq_mask, bits); + while (irq < bits) { + pch_pic_update_irq(s, irq, level); + bitmap_clear((void *)&irq_mask, irq, 1); + irq = find_first_bit((void *)&irq_mask, bits); + } +} + +/* called when a irq is triggered in pch pic */ +void pch_pic_set_irq(struct loongarch_pch_pic *s, int irq, int level) +{ + u64 mask = BIT(irq); + + spin_lock(&s->lock); + if (level) + s->irr |= mask; /* set irr */ + else { + /* + * In edge triggered mode, 0 does not mean to clear irq + * The irr register variable is cleared when cpu writes to the + * PCH_PIC_CLEAR_START address area + */ + if (s->edge & mask) { + spin_unlock(&s->lock); + return; + } + s->irr &= ~mask; + } + pch_pic_update_irq(s, irq, level); + spin_unlock(&s->lock); +} + +/* msi irq handler */ +void pch_msi_set_irq(struct kvm *kvm, int irq, int level) +{ + eiointc_set_irq(kvm->arch.eiointc, irq, level); +} + +/* + * pch pic register is 64-bit, but it is accessed by 32-bit, + * so we use high to get whether low or high 32 bits we want + * to read. + */ +static u32 pch_pic_read_reg(u64 *s, int high) +{ + u64 val = *s; + + /* read the high 32 bits when high is 1 */ + return high ? (u32)(val >> 32) : (u32)val; +} + +/* + * pch pic register is 64-bit, but it is accessed by 32-bit, + * so we use high to get whether low or high 32 bits we want + * to write. + */ +static u32 pch_pic_write_reg(u64 *s, int high, u32 v) +{ + u64 val = *s, data = v; + + if (high) { + /* + * Clear val high 32 bits + * Write the high 32 bits when the high is 1 + */ + *s = (val << 32 >> 32) | (data << 32); + val >>= 32; + } else + /* + * Clear val low 32 bits + * Write the low 32 bits when the high is 0 + */ + *s = (val >> 32 << 32) | v; + + return (u32)val; +} + +static int loongarch_pch_pic_read(struct loongarch_pch_pic *s, gpa_t addr, int len, void *val) +{ + int offset, index, ret = 0; + u32 data = 0; + u64 int_id = 0; + + offset = addr - s->pch_pic_base; + + spin_lock(&s->lock); + switch (offset) { + case PCH_PIC_INT_ID_START ... PCH_PIC_INT_ID_END: + /* int id version */ + int_id |= (u64)PCH_PIC_INT_ID_VER << 32; + /* irq number */ + int_id |= (u64)31 << (32 + 16); + /* int id value */ + int_id |= PCH_PIC_INT_ID_VAL; + *(u64 *)val = int_id; + break; + case PCH_PIC_MASK_START ... PCH_PIC_MASK_END: + offset -= PCH_PIC_MASK_START; + index = offset >> 2; + /* read mask reg */ + data = pch_pic_read_reg(&s->mask, index); + *(u32 *)val = data; + break; + case PCH_PIC_HTMSI_EN_START ... PCH_PIC_HTMSI_EN_END: + offset -= PCH_PIC_HTMSI_EN_START; + index = offset >> 2; + /* read htmsi enable reg */ + data = pch_pic_read_reg(&s->htmsi_en, index); + *(u32 *)val = data; + break; + case PCH_PIC_EDGE_START ... PCH_PIC_EDGE_END: + offset -= PCH_PIC_EDGE_START; + index = offset >> 2; + /* read edge enable reg */ + data = pch_pic_read_reg(&s->edge, index); + *(u32 *)val = data; + break; + case PCH_PIC_AUTO_CTRL0_START ... PCH_PIC_AUTO_CTRL0_END: + case PCH_PIC_AUTO_CTRL1_START ... PCH_PIC_AUTO_CTRL1_END: + /* we only use default mode: fixed interrupt distribution mode */ + *(u32 *)val = 0; + break; + case PCH_PIC_ROUTE_ENTRY_START ... PCH_PIC_ROUTE_ENTRY_END: + /* only route to int0: eiointc */ + *(u8 *)val = 1; + break; + case PCH_PIC_HTMSI_VEC_START ... PCH_PIC_HTMSI_VEC_END: + offset -= PCH_PIC_HTMSI_VEC_START; + /* read htmsi vector */ + data = s->htmsi_vector[offset]; + *(u8 *)val = data; + break; + case PCH_PIC_POLARITY_START ... PCH_PIC_POLARITY_END: + /* we only use defalut value 0: high level triggered */ + *(u32 *)val = 0; + break; + default: + ret = -EINVAL; + } + spin_unlock(&s->lock); + + return ret; +} + +static int kvm_pch_pic_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + int ret; + struct loongarch_pch_pic *s = vcpu->kvm->arch.pch_pic; + + if (!s) { + kvm_err("%s: pch pic irqchip not valid!\n", __func__); + return -EINVAL; + } + + /* statistics of pch pic reading */ + vcpu->kvm->stat.pch_pic_read_exits++; + ret = loongarch_pch_pic_read(s, addr, len, val); + + return ret; +} + +static int loongarch_pch_pic_write(struct loongarch_pch_pic *s, gpa_t addr, + int len, const void *val) +{ + int ret; + u32 old, data, offset, index; + u64 irq; + + ret = 0; + data = *(u32 *)val; + offset = addr - s->pch_pic_base; + + spin_lock(&s->lock); + switch (offset) { + case PCH_PIC_MASK_START ... PCH_PIC_MASK_END: + offset -= PCH_PIC_MASK_START; + /* get whether high or low 32 bits we want to write */ + index = offset >> 2; + old = pch_pic_write_reg(&s->mask, index, data); + /* enable irq when mask value change to 0 */ + irq = (old & ~data) << (32 * index); + pch_pic_update_batch_irqs(s, irq, 1); + /* disable irq when mask value change to 1 */ + irq = (~old & data) << (32 * index); + pch_pic_update_batch_irqs(s, irq, 0); + break; + case PCH_PIC_HTMSI_EN_START ... PCH_PIC_HTMSI_EN_END: + offset -= PCH_PIC_HTMSI_EN_START; + index = offset >> 2; + pch_pic_write_reg(&s->htmsi_en, index, data); + break; + case PCH_PIC_EDGE_START ... PCH_PIC_EDGE_END: + offset -= PCH_PIC_EDGE_START; + index = offset >> 2; + /* 1: edge triggered, 0: level triggered */ + pch_pic_write_reg(&s->edge, index, data); + break; + case PCH_PIC_CLEAR_START ... PCH_PIC_CLEAR_END: + offset -= PCH_PIC_CLEAR_START; + index = offset >> 2; + /* write 1 to clear edge irq */ + old = pch_pic_read_reg(&s->irr, index); + /* + * get the irq bitmap which is edge triggered and + * already set and to be cleared + */ + irq = old & pch_pic_read_reg(&s->edge, index) & data; + /* write irr to the new state where irqs have been cleared */ + pch_pic_write_reg(&s->irr, index, old & ~irq); + /* update cleared irqs */ + pch_pic_update_batch_irqs(s, irq, 0); + break; + case PCH_PIC_AUTO_CTRL0_START ... PCH_PIC_AUTO_CTRL0_END: + offset -= PCH_PIC_AUTO_CTRL0_START; + index = offset >> 2; + /* we only use default mode: fixed interrupt distribution mode */ + pch_pic_write_reg(&s->auto_ctrl0, index, 0); + break; + case PCH_PIC_AUTO_CTRL1_START ... PCH_PIC_AUTO_CTRL1_END: + offset -= PCH_PIC_AUTO_CTRL1_START; + index = offset >> 2; + /* we only use default mode: fixed interrupt distribution mode */ + pch_pic_write_reg(&s->auto_ctrl1, index, 0); + break; + case PCH_PIC_ROUTE_ENTRY_START ... PCH_PIC_ROUTE_ENTRY_END: + offset -= PCH_PIC_ROUTE_ENTRY_START; + /* only route to int0: eiointc */ + s->route_entry[offset] = 1; + break; + case PCH_PIC_HTMSI_VEC_START ... PCH_PIC_HTMSI_VEC_END: + /* route table to eiointc */ + offset -= PCH_PIC_HTMSI_VEC_START; + s->htmsi_vector[offset] = (u8)data; + break; + case PCH_PIC_POLARITY_START ... PCH_PIC_POLARITY_END: + offset -= PCH_PIC_POLARITY_START; + index = offset >> 2; + /* we only use defalut value 0: high level triggered */ + pch_pic_write_reg(&s->polarity, index, 0); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock(&s->lock); + + return ret; +} + +static int kvm_pch_pic_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + int ret; + struct loongarch_pch_pic *s = vcpu->kvm->arch.pch_pic; + + if (!s) { + kvm_err("%s: pch pic irqchip not valid!\n", __func__); + return -EINVAL; + } + + /* statistics of pch pic writing */ + vcpu->kvm->stat.pch_pic_write_exits++; + ret = loongarch_pch_pic_write(s, addr, len, val); + + return ret; +} + +static const struct kvm_io_device_ops kvm_pch_pic_ops = { + .read = kvm_pch_pic_read, + .write = kvm_pch_pic_write, +}; + +static int kvm_pch_pic_init(struct kvm_device *dev, u64 addr) +{ + int ret; + struct kvm *kvm = dev->kvm; + struct kvm_io_device *device; + struct loongarch_pch_pic *s = dev->kvm->arch.pch_pic; + + s->pch_pic_base = addr; + device = &s->device; + /* init device by pch pic writing and reading ops */ + kvm_iodevice_init(device, &kvm_pch_pic_ops); + mutex_lock(&kvm->slots_lock); + /* register pch pic device */ + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, addr, PCH_PIC_SIZE, device); + mutex_unlock(&kvm->slots_lock); + + return (ret < 0) ? -EFAULT : 0; +} + +/* used by user space to get or set pch pic registers */ +static int kvm_pch_pic_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + bool is_write) +{ + int addr, offset, len = 8, ret = 0; + void __user *data; + void *p = NULL; + struct loongarch_pch_pic *s; + + s = dev->kvm->arch.pch_pic; + addr = attr->attr; + data = (void __user *)attr->addr; + + /* get pointer to pch pic register by addr */ + switch (addr) { + case PCH_PIC_MASK_START: + p = &s->mask; + break; + case PCH_PIC_HTMSI_EN_START: + p = &s->htmsi_en; + break; + case PCH_PIC_EDGE_START: + p = &s->edge; + break; + case PCH_PIC_AUTO_CTRL0_START: + p = &s->auto_ctrl0; + break; + case PCH_PIC_AUTO_CTRL1_START: + p = &s->auto_ctrl1; + break; + case PCH_PIC_ROUTE_ENTRY_START ... PCH_PIC_ROUTE_ENTRY_END: + offset = addr - PCH_PIC_ROUTE_ENTRY_START; + p = &s->route_entry[offset]; + len = 1; + break; + case PCH_PIC_HTMSI_VEC_START ... PCH_PIC_HTMSI_VEC_END: + offset = addr - PCH_PIC_HTMSI_VEC_START; + p = &s->htmsi_vector[offset]; + len = 1; + break; + case PCH_PIC_INT_IRR_START: + p = &s->irr; + break; + case PCH_PIC_INT_ISR_START: + p = &s->isr; + break; + case PCH_PIC_POLARITY_START: + p = &s->polarity; + break; + default: + return -EINVAL; + } + + spin_lock(&s->lock); + /* write or read value according to is_write */ + if (is_write) { + if (copy_from_user(p, data, len)) + ret = -EFAULT; + } else { + if (copy_to_user(data, p, len)) + ret = -EFAULT; + } + spin_unlock(&s->lock); + + return ret; +} + +static int kvm_pch_pic_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_LOONGARCH_PCH_PIC_GRP_REGS: + return kvm_pch_pic_regs_access(dev, attr, false); + default: + return -EINVAL; + } +} + +static int kvm_pch_pic_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + u64 addr; + void __user *uaddr = (void __user *)(long)attr->addr; + + switch (attr->group) { + case KVM_DEV_LOONGARCH_PCH_PIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_LOONGARCH_PCH_PIC_CTRL_INIT: + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + if (!dev->kvm->arch.pch_pic) { + kvm_err("%s: please create pch_pic irqchip first!\n", __func__); + return -ENODEV; + } + + return kvm_pch_pic_init(dev, addr); + default: + kvm_err("%s: unknown group (%d) attr (%lld)\n", __func__, attr->group, + attr->attr); + return -EINVAL; + } + case KVM_DEV_LOONGARCH_PCH_PIC_GRP_REGS: + return kvm_pch_pic_regs_access(dev, attr, true); + default: + return -EINVAL; + } +} + +static int kvm_setup_default_irq_routing(struct kvm *kvm) +{ + int i, ret; + u32 nr = KVM_IRQCHIP_NUM_PINS; + struct kvm_irq_routing_entry *entries; + + entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL); + if (!entries) + return -ENOMEM; + + for (i = 0; i < nr; i++) { + entries[i].gsi = i; + entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; + entries[i].u.irqchip.irqchip = 0; + entries[i].u.irqchip.pin = i; + } + ret = kvm_set_irq_routing(kvm, entries, nr, 0); + kfree(entries); + + return ret; +} + +static int kvm_pch_pic_create(struct kvm_device *dev, u32 type) +{ + int ret; + struct kvm *kvm = dev->kvm; + struct loongarch_pch_pic *s; + + /* pch pic should not has been created */ + if (kvm->arch.pch_pic) + return -EINVAL; + + ret = kvm_setup_default_irq_routing(kvm); + if (ret) + return -ENOMEM; + + s = kzalloc(sizeof(struct loongarch_pch_pic), GFP_KERNEL); + if (!s) + return -ENOMEM; + + spin_lock_init(&s->lock); + s->kvm = kvm; + kvm->arch.pch_pic = s; + + return 0; +} + +static void kvm_pch_pic_destroy(struct kvm_device *dev) +{ + struct kvm *kvm; + struct loongarch_pch_pic *s; + + if (!dev || !dev->kvm || !dev->kvm->arch.pch_pic) + return; + + kvm = dev->kvm; + s = kvm->arch.pch_pic; + /* unregister pch pic device and free it's memory */ + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device); + kfree(s); +} + +static struct kvm_device_ops kvm_pch_pic_dev_ops = { + .name = "kvm-loongarch-pch-pic", + .create = kvm_pch_pic_create, + .destroy = kvm_pch_pic_destroy, + .set_attr = kvm_pch_pic_set_attr, + .get_attr = kvm_pch_pic_get_attr, +}; + +int kvm_loongarch_register_pch_pic_device(void) +{ + return kvm_register_device_ops(&kvm_pch_pic_dev_ops, KVM_DEV_TYPE_LOONGARCH_PCHPIC); +} diff --git a/arch/loongarch/kvm/irqfd.c b/arch/loongarch/kvm/irqfd.c new file mode 100644 index 000000000000..9a39627aecf0 --- /dev/null +++ b/arch/loongarch/kvm/irqfd.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <linux/kvm_host.h> +#include <trace/events/kvm.h> +#include <asm/kvm_pch_pic.h> + +static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, bool line_status) +{ + /* PCH-PIC pin (0 ~ 64) <---> GSI (0 ~ 64) */ + pch_pic_set_irq(kvm->arch.pch_pic, e->irqchip.pin, level); + + return 0; +} + +/* + * kvm_set_msi: inject the MSI corresponding to the + * MSI routing entry + * + * This is the entry point for irqfd MSI injection + * and userspace MSI injection. + */ +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, bool line_status) +{ + if (!level) + return -1; + + pch_msi_set_irq(kvm, e->msi.data, level); + + return 0; +} + +/* + * kvm_set_routing_entry: populate a kvm routing entry + * from a user routing entry + * + * @kvm: the VM this entry is applied to + * @e: kvm kernel routing entry handle + * @ue: user api routing entry handle + * return 0 on success, -EINVAL on errors. + */ +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + switch (ue->type) { + case KVM_IRQ_ROUTING_IRQCHIP: + e->set = kvm_set_pic_irq; + e->irqchip.irqchip = ue->u.irqchip.irqchip; + e->irqchip.pin = ue->u.irqchip.pin; + + if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) + return -EINVAL; + + return 0; + case KVM_IRQ_ROUTING_MSI: + e->set = kvm_set_msi; + e->msi.address_lo = ue->u.msi.address_lo; + e->msi.address_hi = ue->u.msi.address_hi; + e->msi.data = ue->u.msi.data; + return 0; + default: + return -EINVAL; + } +} + +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, bool line_status) +{ + switch (e->type) { + case KVM_IRQ_ROUTING_IRQCHIP: + pch_pic_set_irq(kvm->arch.pch_pic, e->irqchip.pin, level); + return 0; + case KVM_IRQ_ROUTING_MSI: + pch_msi_set_irq(kvm, e->msi.data, level); + return 0; + default: + return -EWOULDBLOCK; + } +} + +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return kvm_arch_irqchip_in_kernel(kvm); +} diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 86a2f2d0cb27..b6864d6e5ec8 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -9,6 +9,8 @@ #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/kvm_csr.h> +#include <asm/kvm_eiointc.h> +#include <asm/kvm_pch_pic.h> #include "trace.h" unsigned long vpid_mask; @@ -242,6 +244,25 @@ void kvm_check_vpid(struct kvm_vcpu *vcpu) kvm_update_vpid(vcpu, cpu); trace_kvm_vpid_change(vcpu, vcpu->arch.vpid); vcpu->cpu = cpu; + kvm_clear_request(KVM_REQ_TLB_FLUSH_GPA, vcpu); + + /* + * LLBCTL is a separated guest CSR register from host, a general + * exception ERET instruction clears the host LLBCTL register in + * host mode, and clears the guest LLBCTL register in guest mode. + * ERET in tlb refill exception does not clear LLBCTL register. + * + * When secondary mmu mapping is changed, guest OS does not know + * even if the content is changed after mapping is changed. + * + * Here clear WCLLB of the guest LLBCTL register when mapping is + * changed. Otherwise, if mmu mapping is changed while guest is + * executing LL/SC pair, LL loads with the old address and set + * the LLBCTL flag, SC checks the LLBCTL flag and will store the + * new address successfully since LLBCTL_WCLLB is on, even if + * memory with new address is changed on other VCPUs. + */ + set_gcsr_llbctl(CSR_LLBCTL_WCLLB); } /* Restore GSTAT(0x50).vpid */ @@ -260,7 +281,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -ENOIOCTLCMD; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { unsigned long env, gcfg = 0; @@ -282,9 +303,9 @@ int kvm_arch_hardware_enable(void) * TOE=0: Trap on Exception. * TIT=0: Trap on Timer. */ - if (env & CSR_GCFG_GCIP_ALL) + if (env & CSR_GCFG_GCIP_SECURE) gcfg |= CSR_GCFG_GCI_SECURE; - if (env & CSR_GCFG_MATC_ROOT) + if (env & CSR_GCFG_MATP_ROOT) gcfg |= CSR_GCFG_MATC_ROOT; write_csr_gcfg(gcfg); @@ -296,10 +317,17 @@ int kvm_arch_hardware_enable(void) kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx", read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc()); + /* + * HW Guest CSR registers are lost after CPU suspend and resume. + * Clear last_vcpu so that Guest CSR registers forced to reload + * from vCPU SW state. + */ + this_cpu_ptr(vmcs)->last_vcpu = NULL; + return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { write_csr_gcfg(0); write_csr_gstat(0); @@ -312,7 +340,7 @@ void kvm_arch_hardware_disable(void) static int kvm_loongarch_env_init(void) { - int cpu, order; + int cpu, order, ret; void *addr; struct kvm_context *context; @@ -367,7 +395,20 @@ static int kvm_loongarch_env_init(void) kvm_init_gcsr_flag(); - return 0; + /* Register LoongArch IPI interrupt controller interface. */ + ret = kvm_loongarch_register_ipi_device(); + if (ret) + return ret; + + /* Register LoongArch EIOINTC interrupt controller interface. */ + ret = kvm_loongarch_register_eiointc_device(); + if (ret) + return ret; + + /* Register LoongArch PCH-PIC interrupt controller interface. */ + ret = kvm_loongarch_register_pch_pic_device(); + + return ret; } static void kvm_loongarch_env_exit(void) diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 50a6acd7ffe4..4d203294767c 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -163,6 +163,7 @@ static kvm_pte_t *kvm_populate_gpa(struct kvm *kvm, child = kvm_mmu_memory_cache_alloc(cache); _kvm_pte_init(child, ctx.invalid_ptes[ctx.level - 1]); + smp_wmb(); /* Make pte visible before pmd */ kvm_set_pte(entry, __pa(child)); } else if (kvm_pte_huge(*entry)) { return entry; @@ -444,6 +445,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, enum kvm_mr_change change) { int needs_flush; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; + + /* Only track memslot flags changed */ + if (change != KVM_MR_FLAGS_ONLY) + return; + + /* Discard dirty page tracking on readonly memslot */ + if ((old_flags & new_flags) & KVM_MEM_READONLY) + return; /* * If dirty page logging is enabled, write protect all pages in the slot @@ -454,9 +466,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot() */ - if (change == KVM_MR_FLAGS_ONLY && - (!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) && - new->flags & KVM_MEM_LOG_DIRTY_PAGES)) { + if (!(old_flags & KVM_MEM_LOG_DIRTY_PAGES) && log_dirty_pages) { + /* + * Initially-all-set does not require write protecting any page + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; + spin_lock(&kvm->mmu_lock); /* Write protect GPA page table entries */ needs_flush = kvm_mkclean_gpa_pt(kvm, new->base_gfn, @@ -494,38 +511,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) range->end << PAGE_SHIFT, &ctx); } -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) -{ - unsigned long prot_bits; - kvm_pte_t *ptep; - kvm_pfn_t pfn = pte_pfn(range->arg.pte); - gpa_t gpa = range->start << PAGE_SHIFT; - - ptep = kvm_populate_gpa(kvm, NULL, gpa, 0); - if (!ptep) - return false; - - /* Replacing an absent or old page doesn't need flushes */ - if (!kvm_pte_present(NULL, ptep) || !kvm_pte_young(*ptep)) { - kvm_set_pte(ptep, 0); - return false; - } - - /* Fill new pte if write protected or page migrated */ - prot_bits = _PAGE_PRESENT | __READABLE; - prot_bits |= _CACHE_MASK & pte_val(range->arg.pte); - - /* - * Set _PAGE_WRITE or _PAGE_DIRTY iff old and new pte both support - * _PAGE_WRITE for map_page_fast if next page write fault - * _PAGE_DIRTY since gpa has already recorded as dirty page - */ - prot_bits |= __WRITEABLE & *ptep & pte_val(range->arg.pte); - kvm_set_pte(ptep, kvm_pfn_pte(pfn, __pgprot(prot_bits))); - - return true; -} - bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_ptw_ctx ctx; @@ -567,7 +552,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) { int ret = 0; - kvm_pfn_t pfn = 0; kvm_pte_t *ptep, changed, new; gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; @@ -583,11 +567,7 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ } /* Track access to pages marked old */ - new = *ptep; - if (!kvm_pte_young(new)) - new = kvm_pte_mkyoung(new); - /* call kvm_set_pfn_accessed() after unlock */ - + new = kvm_pte_mkyoung(*ptep); if (write && !kvm_pte_dirty(new)) { if (!kvm_pte_write(new)) { ret = -EFAULT; @@ -611,23 +591,14 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ } changed = new ^ (*ptep); - if (changed) { + if (changed) kvm_set_pte(ptep, new); - pfn = kvm_pte_pfn(new); - } - spin_unlock(&kvm->mmu_lock); - /* - * Fixme: pfn may be freed after mmu_lock - * kvm_try_get_pfn(pfn)/kvm_release_pfn pair to prevent this? - */ - if (kvm_pte_young(changed)) - kvm_set_pfn_accessed(pfn); + spin_unlock(&kvm->mmu_lock); - if (kvm_pte_dirty(changed)) { + if (kvm_pte_dirty(changed)) mark_page_dirty(kvm, gfn); - kvm_set_pfn_dirty(pfn); - } + return ret; out: spin_unlock(&kvm->mmu_lock); @@ -723,23 +694,23 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, /* * Read each entry once. As above, a non-leaf entry can be promoted to * a huge page _during_ this walk. Re-reading the entry could send the - * walk into the weeks, e.g. p*d_large() returns false (sees the old + * walk into the weeks, e.g. p*d_leaf() returns false (sees the old * value) and then p*d_offset() walks into the target huge page instead * of the old page table (sees the new value). */ - pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); + pgd = pgdp_get(pgd_offset(kvm->mm, hva)); if (pgd_none(pgd)) goto out; - p4d = READ_ONCE(*p4d_offset(&pgd, hva)); + p4d = p4dp_get(p4d_offset(&pgd, hva)); if (p4d_none(p4d) || !p4d_present(p4d)) goto out; - pud = READ_ONCE(*pud_offset(&p4d, hva)); + pud = pudp_get(pud_offset(&p4d, hva)); if (pud_none(pud) || !pud_present(pud)) goto out; - pmd = READ_ONCE(*pmd_offset(&pud, hva)); + pmd = pmdp_get(pmd_offset(&pud, hva)); if (pmd_none(pmd) || !pmd_present(pmd)) goto out; @@ -769,6 +740,7 @@ static kvm_pte_t *kvm_split_huge(struct kvm_vcpu *vcpu, kvm_pte_t *ptep, gfn_t g val += PAGE_SIZE; } + smp_wmb(); /* Make pte visible before pmd */ /* The later kvm_flush_tlb_gpa() will flush hugepage tlb */ kvm_set_pte(ptep, __pa(child)); @@ -808,6 +780,7 @@ static int kvm_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) struct kvm *kvm = vcpu->kvm; struct kvm_memory_slot *memslot; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + struct page *page; /* Try the fast path to handle old / clean pages */ srcu_idx = srcu_read_lock(&kvm->srcu); @@ -835,7 +808,7 @@ retry: mmu_seq = kvm->mmu_invalidate_seq; /* * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads in - * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't + * kvm_faultin_pfn() (which calls get_user_pages()), so that we don't * risk the page we get a reference to getting unmapped before we have a * chance to grab the mmu_lock without mmu_invalidate_retry() noticing. * @@ -847,7 +820,7 @@ retry: smp_rmb(); /* Slow path - ask KVM core whether we can access this GPA */ - pfn = gfn_to_pfn_prot(kvm, gfn, write, &writeable); + pfn = kvm_faultin_pfn(vcpu, gfn, write, &writeable, &page); if (is_error_noslot_pfn(pfn)) { err = -EFAULT; goto out; @@ -859,10 +832,10 @@ retry: /* * This can happen when mappings are changed asynchronously, but * also synchronously if a COW is triggered by - * gfn_to_pfn_prot(). + * kvm_faultin_pfn(). */ spin_unlock(&kvm->mmu_lock); - kvm_release_pfn_clean(pfn); + kvm_release_page_unused(page); if (retry_no > 100) { retry_no = 0; schedule(); @@ -890,11 +863,21 @@ retry: /* Disable dirty logging on HugePages */ level = 0; - if (!fault_supports_huge_mapping(memslot, hva, write)) { - level = 0; - } else { + if (fault_supports_huge_mapping(memslot, hva, write)) { + /* Check page level about host mmu*/ level = host_pfn_mapping_level(kvm, gfn, memslot); if (level == 1) { + /* + * Check page level about secondary mmu + * Disable hugepage if it is normal page on + * secondary mmu already + */ + ptep = kvm_populate_gpa(kvm, NULL, gpa, 0); + if (ptep && !kvm_pte_huge(*ptep)) + level = 0; + } + + if (level == 1) { gfn = gfn & ~(PTRS_PER_PTE - 1); pfn = pfn & ~(PTRS_PER_PTE - 1); } @@ -917,15 +900,13 @@ retry: else ++kvm->stat.pages; kvm_set_pte(ptep, new_pte); + + kvm_release_faultin_page(kvm, page, false, writeable); spin_unlock(&kvm->mmu_lock); - if (prot_bits & _PAGE_DIRTY) { + if (prot_bits & _PAGE_DIRTY) mark_page_dirty_in_slot(kvm, memslot, gfn); - kvm_set_pfn_dirty(pfn); - } - kvm_set_pfn_accessed(pfn); - kvm_release_pfn_clean(pfn); out: srcu_read_unlock(&kvm->srcu, srcu_idx); return err; @@ -940,7 +921,8 @@ int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) return ret; /* Invalidate this entry in the TLB */ - kvm_flush_tlb_gpa(vcpu, gpa); + vcpu->arch.flush_gpa = gpa; + kvm_make_request(KVM_REQ_TLB_FLUSH_GPA, vcpu); return 0; } diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index ba976509bfe8..1be185e94807 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -8,7 +8,7 @@ #include <asm/asmmacro.h> #include <asm/loongarch.h> #include <asm/regdef.h> -#include <asm/stackframe.h> +#include <asm/unwind_hints.h> #define HGPR_OFFSET(x) (PT_R0 + 8*x) #define GGPR_OFFSET(x) (KVM_ARCH_GGPR + 8*x) @@ -85,7 +85,7 @@ * Guest CRMD comes from separate GCSR_CRMD register */ ori t0, zero, CSR_PRMD_PIE - csrxchg t0, t0, LOONGARCH_CSR_PRMD + csrwr t0, LOONGARCH_CSR_PRMD /* Set PVM bit to setup ertn to guest context */ ori t0, zero, CSR_GSTAT_PVM @@ -112,6 +112,7 @@ .text .cfi_sections .debug_frame SYM_CODE_START(kvm_exc_entry) + UNWIND_HINT_UNDEFINED csrwr a2, KVM_TEMP_KS csrrd a2, KVM_VCPU_KS addi.d a2, a2, KVM_VCPU_ARCH @@ -213,12 +214,6 @@ SYM_FUNC_START(kvm_enter_guest) /* Save host GPRs */ kvm_save_host_gpr a2 - /* Save host CRMD, PRMD to stack */ - csrrd a3, LOONGARCH_CSR_CRMD - st.d a3, a2, PT_CRMD - csrrd a3, LOONGARCH_CSR_PRMD - st.d a3, a2, PT_PRMD - addi.d a2, a1, KVM_VCPU_ARCH st.d sp, a2, KVM_ARCH_HSP st.d tp, a2, KVM_ARCH_HTP @@ -279,3 +274,13 @@ SYM_FUNC_END(kvm_restore_lasx) .section ".rodata" SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry) SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest) + +#ifdef CONFIG_CPU_HAS_LBT +STACK_FRAME_NON_STANDARD kvm_restore_fpu +#ifdef CONFIG_CPU_HAS_LSX +STACK_FRAME_NON_STANDARD kvm_restore_lsx +#endif +#ifdef CONFIG_CPU_HAS_LASX +STACK_FRAME_NON_STANDARD kvm_restore_lasx +#endif +#endif diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c index 111328f60872..32dc213374be 100644 --- a/arch/loongarch/kvm/timer.c +++ b/arch/loongarch/kvm/timer.c @@ -23,24 +23,6 @@ static inline u64 tick_to_ns(struct kvm_vcpu *vcpu, u64 tick) return div_u64(tick * MNSEC_PER_SEC, vcpu->arch.timer_mhz); } -/* - * Push timer forward on timeout. - * Handle an hrtimer event by push the hrtimer forward a period. - */ -static enum hrtimer_restart kvm_count_timeout(struct kvm_vcpu *vcpu) -{ - unsigned long cfg, period; - - /* Add periodic tick to current expire time */ - cfg = kvm_read_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG); - if (cfg & CSR_TCFG_PERIOD) { - period = tick_to_ns(vcpu, cfg & CSR_TCFG_VAL); - hrtimer_add_expires_ns(&vcpu->arch.swtimer, period); - return HRTIMER_RESTART; - } else - return HRTIMER_NORESTART; -} - /* Low level hrtimer wake routine */ enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer) { @@ -50,7 +32,7 @@ enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer) kvm_queue_irq(vcpu, INT_TI); rcuwait_wake_up(&vcpu->wait); - return kvm_count_timeout(vcpu); + return HRTIMER_NORESTART; } /* @@ -93,7 +75,8 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu) /* * Freeze the soft-timer and sync the guest stable timer with it. */ - hrtimer_cancel(&vcpu->arch.swtimer); + if (kvm_vcpu_is_blocking(vcpu)) + hrtimer_cancel(&vcpu->arch.swtimer); /* * From LoongArch Reference Manual Volume 1 Chapter 7.6.2 @@ -168,26 +151,21 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu) * Here judge one-shot timer fired by checking whether TVAL is larger * than TCFG */ - if (ticks < cfg) { + if (ticks < cfg) delta = tick_to_ns(vcpu, ticks); - expire = ktime_add_ns(ktime_get(), delta); - vcpu->arch.expire = expire; + else + delta = 0; + + expire = ktime_add_ns(ktime_get(), delta); + vcpu->arch.expire = expire; + if (kvm_vcpu_is_blocking(vcpu)) { /* - * HRTIMER_MODE_PINNED is suggested since vcpu may run in - * the same physical cpu in next time - */ - hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED); - } else if (vcpu->stat.generic.blocking) { - /* - * Inject timer interrupt so that halt polling can dectect and exit. - * VCPU is scheduled out already and sleeps in rcuwait queue and - * will not poll pending events again. kvm_queue_irq() is not enough, - * hrtimer swtimer should be used here. + * HRTIMER_MODE_PINNED_HARD is suggested since vcpu may run in + * the same physical cpu in next time, and the timer should run + * in hardirq context even in the PREEMPT_RT case. */ - expire = ktime_add_ns(ktime_get(), 10); - vcpu->arch.expire = expire; - hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED); + hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED_HARD); } } @@ -211,10 +189,3 @@ void kvm_save_timer(struct kvm_vcpu *vcpu) kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT); preempt_enable(); } - -void kvm_reset_timer(struct kvm_vcpu *vcpu) -{ - write_gcsr_timercfg(0); - kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG, 0); - hrtimer_cancel(&vcpu->arch.swtimer); -} diff --git a/arch/loongarch/kvm/tlb.c b/arch/loongarch/kvm/tlb.c index 02535df6b51f..ebdbe9264e9c 100644 --- a/arch/loongarch/kvm/tlb.c +++ b/arch/loongarch/kvm/tlb.c @@ -23,10 +23,7 @@ void kvm_flush_tlb_all(void) void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa) { - unsigned long flags; - - local_irq_save(flags); + lockdep_assert_irqs_disabled(); gpa &= (PAGE_MASK << 1); invtlb(INVTLB_GID_ADDR, read_csr_gstat() & CSR_GSTAT_GID, gpa); - local_irq_restore(flags); } diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h index c2484ad4cffa..1783397b1bc8 100644 --- a/arch/loongarch/kvm/trace.h +++ b/arch/loongarch/kvm/trace.h @@ -19,14 +19,16 @@ DECLARE_EVENT_CLASS(kvm_transition, TP_PROTO(struct kvm_vcpu *vcpu), TP_ARGS(vcpu), TP_STRUCT__entry( + __field(unsigned int, vcpu_id) __field(unsigned long, pc) ), TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; __entry->pc = vcpu->arch.pc; ), - TP_printk("PC: 0x%08lx", __entry->pc) + TP_printk("vcpu %u PC: 0x%08lx", __entry->vcpu_id, __entry->pc) ); DEFINE_EVENT(kvm_transition, kvm_enter, @@ -54,19 +56,22 @@ DECLARE_EVENT_CLASS(kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason), TP_STRUCT__entry( + __field(unsigned int, vcpu_id) __field(unsigned long, pc) __field(unsigned int, reason) ), TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; __entry->pc = vcpu->arch.pc; __entry->reason = reason; ), - TP_printk("[%s]PC: 0x%08lx", - __print_symbolic(__entry->reason, - kvm_trace_symbol_exit_types), - __entry->pc) + TP_printk("vcpu %u [%s] PC: 0x%08lx", + __entry->vcpu_id, + __print_symbolic(__entry->reason, + kvm_trace_symbol_exit_types), + __entry->pc) ); DEFINE_EVENT(kvm_exit, kvm_exit_idle, @@ -85,14 +90,17 @@ TRACE_EVENT(kvm_exit_gspr, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int inst_word), TP_ARGS(vcpu, inst_word), TP_STRUCT__entry( + __field(unsigned int, vcpu_id) __field(unsigned int, inst_word) ), TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; __entry->inst_word = inst_word; ), - TP_printk("Inst word: 0x%08x", __entry->inst_word) + TP_printk("vcpu %u Inst word: 0x%08x", __entry->vcpu_id, + __entry->inst_word) ); #define KVM_TRACE_AUX_SAVE 0 diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 36106922b5d7..9e1a9b4aa4c6 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -6,6 +6,7 @@ #include <linux/kvm_host.h> #include <linux/entry-kvm.h> #include <asm/fpu.h> +#include <asm/lbt.h> #include <asm/loongarch.h> #include <asm/setup.h> #include <asm/time.h> @@ -19,6 +20,7 @@ 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) }; const struct kvm_stats_header kvm_vcpu_stats_header = { @@ -30,6 +32,170 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; +static inline void kvm_save_host_pmu(struct kvm_vcpu *vcpu) +{ + struct kvm_context *context; + + context = this_cpu_ptr(vcpu->kvm->arch.vmcs); + context->perf_cntr[0] = read_csr_perfcntr0(); + context->perf_cntr[1] = read_csr_perfcntr1(); + context->perf_cntr[2] = read_csr_perfcntr2(); + context->perf_cntr[3] = read_csr_perfcntr3(); + context->perf_ctrl[0] = write_csr_perfctrl0(0); + context->perf_ctrl[1] = write_csr_perfctrl1(0); + context->perf_ctrl[2] = write_csr_perfctrl2(0); + context->perf_ctrl[3] = write_csr_perfctrl3(0); +} + +static inline void kvm_restore_host_pmu(struct kvm_vcpu *vcpu) +{ + struct kvm_context *context; + + context = this_cpu_ptr(vcpu->kvm->arch.vmcs); + write_csr_perfcntr0(context->perf_cntr[0]); + write_csr_perfcntr1(context->perf_cntr[1]); + write_csr_perfcntr2(context->perf_cntr[2]); + write_csr_perfcntr3(context->perf_cntr[3]); + write_csr_perfctrl0(context->perf_ctrl[0]); + write_csr_perfctrl1(context->perf_ctrl[1]); + write_csr_perfctrl2(context->perf_ctrl[2]); + write_csr_perfctrl3(context->perf_ctrl[3]); +} + + +static inline void kvm_save_guest_pmu(struct kvm_vcpu *vcpu) +{ + struct loongarch_csrs *csr = vcpu->arch.csr; + + kvm_save_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR0); + kvm_save_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR1); + kvm_save_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR2); + kvm_save_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR3); + kvm_read_clear_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); + kvm_read_clear_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); + kvm_read_clear_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL2); + kvm_read_clear_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); +} + +static inline void kvm_restore_guest_pmu(struct kvm_vcpu *vcpu) +{ + struct loongarch_csrs *csr = vcpu->arch.csr; + + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR0); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR1); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR2); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCNTR3); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL2); + kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); +} + +static int kvm_own_pmu(struct kvm_vcpu *vcpu) +{ + unsigned long val; + + if (!kvm_guest_has_pmu(&vcpu->arch)) + return -EINVAL; + + kvm_save_host_pmu(vcpu); + + /* Set PM0-PM(num) to guest */ + val = read_csr_gcfg() & ~CSR_GCFG_GPERF; + val |= (kvm_get_pmu_num(&vcpu->arch) + 1) << CSR_GCFG_GPERF_SHIFT; + write_csr_gcfg(val); + + kvm_restore_guest_pmu(vcpu); + + return 0; +} + +static void kvm_lose_pmu(struct kvm_vcpu *vcpu) +{ + unsigned long val; + struct loongarch_csrs *csr = vcpu->arch.csr; + + if (!(vcpu->arch.aux_inuse & KVM_LARCH_PMU)) + return; + + kvm_save_guest_pmu(vcpu); + + /* Disable pmu access from guest */ + write_csr_gcfg(read_csr_gcfg() & ~CSR_GCFG_GPERF); + + /* + * Clear KVM_LARCH_PMU if the guest is not using PMU CSRs when + * exiting the guest, so that the next time trap into the guest. + * We don't need to deal with PMU CSRs contexts. + */ + val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); + val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); + val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL2); + val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); + if (!(val & KVM_PMU_EVENT_ENABLED)) + vcpu->arch.aux_inuse &= ~KVM_LARCH_PMU; + + kvm_restore_host_pmu(vcpu); +} + +static void kvm_restore_pmu(struct kvm_vcpu *vcpu) +{ + if ((vcpu->arch.aux_inuse & KVM_LARCH_PMU)) + kvm_make_request(KVM_REQ_PMU, vcpu); +} + +static void kvm_check_pmu(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_PMU, vcpu)) { + kvm_own_pmu(vcpu); + vcpu->arch.aux_inuse |= KVM_LARCH_PMU; + } +} + +static void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ + u32 version; + u64 steal; + gpa_t gpa; + struct kvm_memslots *slots; + struct kvm_steal_time __user *st; + struct gfn_to_hva_cache *ghc; + + ghc = &vcpu->arch.st.cache; + gpa = vcpu->arch.st.guest_addr; + if (!(gpa & KVM_STEAL_PHYS_VALID)) + return; + + gpa &= KVM_STEAL_PHYS_MASK; + slots = kvm_memslots(vcpu->kvm); + if (slots->generation != ghc->generation || gpa != ghc->gpa) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st))) { + ghc->gpa = INVALID_GPA; + return; + } + } + + st = (struct kvm_steal_time __user *)ghc->hva; + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ + + version += 1; + unsafe_put_user(version, &st->version, out); + smp_wmb(); + + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); + + smp_wmb(); + version += 1; + unsafe_put_user(version, &st->version, out); +out: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); +} + /* * kvm_check_requests - check and handle pending vCPU requests * @@ -47,9 +213,22 @@ static int kvm_check_requests(struct kvm_vcpu *vcpu) if (kvm_dirty_ring_check_request(vcpu)) return RESUME_HOST; + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + kvm_update_stolen_time(vcpu); + return RESUME_GUEST; } +static void kvm_late_check_requests(struct kvm_vcpu *vcpu) +{ + lockdep_assert_irqs_disabled(); + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GPA, vcpu)) + if (vcpu->arch.flush_gpa != INVALID_GPA) { + kvm_flush_tlb_gpa(vcpu, vcpu->arch.flush_gpa); + vcpu->arch.flush_gpa = INVALID_GPA; + } +} + /* * Check and handle pending signal and vCPU requests etc * Run with irq enabled and preempt enabled @@ -61,7 +240,7 @@ static int kvm_check_requests(struct kvm_vcpu *vcpu) */ static int kvm_enter_guest_check(struct kvm_vcpu *vcpu) { - int ret; + int idx, ret; /* * Check conditions before entering the guest @@ -70,7 +249,9 @@ static int kvm_enter_guest_check(struct kvm_vcpu *vcpu) if (ret < 0) return ret; + idx = srcu_read_lock(&vcpu->kvm->srcu); ret = kvm_check_requests(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } @@ -100,6 +281,14 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu) /* Make sure the vcpu mode has been written */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); kvm_check_vpid(vcpu); + kvm_check_pmu(vcpu); + + /* + * Called after function kvm_check_vpid() + * Since it updates CSR.GSTAT used by kvm_flush_tlb_gpa(), + * and it may also clear KVM_REQ_TLB_FLUSH_GPA pending bit + */ + kvm_late_check_requests(vcpu); vcpu->arch.host_eentry = csr_read64(LOONGARCH_CSR_EENTRY); /* Clear KVM_LARCH_SWCSR_LATEST as CSR will change when enter guest */ vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; @@ -122,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) { int ret = RESUME_GUEST; unsigned long estat = vcpu->arch.host_estat; - u32 intr = estat & 0x1fff; /* Ignore NMI */ + u32 intr = estat & CSR_ESTAT_IS; u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT; vcpu->mode = OUTSIDE_GUEST_MODE; @@ -130,6 +319,8 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) /* Set a default exit reason */ run->exit_reason = KVM_EXIT_UNKNOWN; + kvm_lose_pmu(vcpu); + guest_timing_exit_irqoff(); guest_state_exit_irqoff(); local_irq_enable(); @@ -247,7 +438,101 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - return -EINVAL; + if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) + return -EINVAL; + + if (dbg->control & KVM_GUESTDBG_ENABLE) + vcpu->guest_debug = dbg->control; + else + vcpu->guest_debug = 0; + + return 0; +} + +static inline int kvm_set_cpuid(struct kvm_vcpu *vcpu, u64 val) +{ + int cpuid; + struct kvm_phyid_map *map; + struct loongarch_csrs *csr = vcpu->arch.csr; + + if (val >= KVM_MAX_PHYID) + return -EINVAL; + + map = vcpu->kvm->arch.phyid_map; + cpuid = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_CPUID); + + spin_lock(&vcpu->kvm->arch.phyid_map_lock); + if ((cpuid < KVM_MAX_PHYID) && map->phys_map[cpuid].enabled) { + /* Discard duplicated CPUID set operation */ + if (cpuid == val) { + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); + return 0; + } + + /* + * CPUID is already set before + * Forbid changing to a different CPUID at runtime + */ + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); + return -EINVAL; + } + + if (map->phys_map[val].enabled) { + /* Discard duplicated CPUID set operation */ + if (vcpu == map->phys_map[val].vcpu) { + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); + return 0; + } + + /* + * New CPUID is already set with other vcpu + * Forbid sharing the same CPUID between different vcpus + */ + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); + return -EINVAL; + } + + kvm_write_sw_gcsr(csr, LOONGARCH_CSR_CPUID, val); + map->phys_map[val].enabled = true; + map->phys_map[val].vcpu = vcpu; + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); + + return 0; +} + +static inline void kvm_drop_cpuid(struct kvm_vcpu *vcpu) +{ + int cpuid; + struct kvm_phyid_map *map; + struct loongarch_csrs *csr = vcpu->arch.csr; + + map = vcpu->kvm->arch.phyid_map; + cpuid = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_CPUID); + + if (cpuid >= KVM_MAX_PHYID) + return; + + spin_lock(&vcpu->kvm->arch.phyid_map_lock); + if (map->phys_map[cpuid].enabled) { + map->phys_map[cpuid].vcpu = NULL; + map->phys_map[cpuid].enabled = false; + kvm_write_sw_gcsr(csr, LOONGARCH_CSR_CPUID, KVM_MAX_PHYID); + } + spin_unlock(&vcpu->kvm->arch.phyid_map_lock); +} + +struct kvm_vcpu *kvm_get_vcpu_by_cpuid(struct kvm *kvm, int cpuid) +{ + struct kvm_phyid_map *map; + + if (cpuid >= KVM_MAX_PHYID) + return NULL; + + map = kvm->arch.phyid_map; + if (!map->phys_map[cpuid].enabled) + return NULL; + + return map->phys_map[cpuid].vcpu; } static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val) @@ -259,6 +544,17 @@ static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val) return -EINVAL; if (id == LOONGARCH_CSR_ESTAT) { + preempt_disable(); + vcpu_load(vcpu); + /* + * Sync pending interrupts into ESTAT so that interrupt + * remains during VM migration stage + */ + kvm_deliver_intr(vcpu); + vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; + vcpu_put(vcpu); + preempt_enable(); + /* ESTAT IP0~IP7 get from GINTC */ gintc = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_GINTC) & 0xff; *val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT) | (gintc << 2); @@ -282,6 +578,9 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val) if (get_gcsr_flag(id) & INVALID_GCSR) return -EINVAL; + if (id == LOONGARCH_CSR_CPUID) + return kvm_set_cpuid(vcpu, val); + if (id == LOONGARCH_CSR_ESTAT) { /* ESTAT IP0~IP7 inject through GINTC */ gintc = (val >> 2) & 0xff; @@ -295,6 +594,22 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val) kvm_write_sw_gcsr(csr, id, val); + /* + * After modifying the PMU CSR register value of the vcpu. + * If the PMU CSRs are used, we need to set KVM_REQ_PMU. + */ + if (id >= LOONGARCH_CSR_PERFCTRL0 && id <= LOONGARCH_CSR_PERFCNTR3) { + unsigned long val; + + val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0) | + kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1) | + kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL2) | + kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); + + if (val & KVM_PMU_EVENT_ENABLED) + kvm_make_request(KVM_REQ_PMU, vcpu); + } + return ret; } @@ -304,11 +619,18 @@ static int _kvm_get_cpucfg_mask(int id, u64 *v) return -EINVAL; switch (id) { - case 2: + case LOONGARCH_CPUCFG0: + *v = GENMASK(31, 0); + return 0; + case LOONGARCH_CPUCFG1: + /* CPUCFG1_MSGINT is not supported by KVM */ + *v = GENMASK(25, 0); + return 0; + case LOONGARCH_CPUCFG2: /* CPUCFG2 features unconditionally supported by KVM */ *v = CPUCFG2_FP | CPUCFG2_FPSP | CPUCFG2_FPDP | CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV | - CPUCFG2_LAM; + CPUCFG2_LSPW | CPUCFG2_LAM; /* * For the ISA extensions listed below, if one is supported * by the host, then it is also supported by KVM. @@ -317,15 +639,39 @@ static int _kvm_get_cpucfg_mask(int id, u64 *v) *v |= CPUCFG2_LSX; if (cpu_has_lasx) *v |= CPUCFG2_LASX; + if (cpu_has_lbt_x86) + *v |= CPUCFG2_X86BT; + if (cpu_has_lbt_arm) + *v |= CPUCFG2_ARMBT; + if (cpu_has_lbt_mips) + *v |= CPUCFG2_MIPSBT; return 0; + case LOONGARCH_CPUCFG3: + *v = GENMASK(16, 0); + return 0; + case LOONGARCH_CPUCFG4: + case LOONGARCH_CPUCFG5: + *v = GENMASK(31, 0); + return 0; + case LOONGARCH_CPUCFG6: + if (cpu_has_pmp) + *v = GENMASK(14, 0); + else + *v = 0; + return 0; + case LOONGARCH_CPUCFG16: + *v = GENMASK(16, 0); + return 0; + case LOONGARCH_CPUCFG17 ... LOONGARCH_CPUCFG20: + *v = GENMASK(30, 0); + return 0; default: /* - * No restrictions on other valid CPUCFG IDs' values, but - * CPUCFG data is limited to 32 bits as the LoongArch ISA - * manual says (Volume 1, Section 2.2.10.5 "CPUCFG"). + * CPUCFG bits should be zero if reserved by HW or not + * supported by KVM. */ - *v = U32_MAX; + *v = 0; return 0; } } @@ -344,7 +690,7 @@ static int kvm_check_cpucfg(int id, u64 val) return -EINVAL; switch (id) { - case 2: + case LOONGARCH_CPUCFG2: if (!(val & CPUCFG2_LLFTP)) /* Guests must have a constant timer */ return -EINVAL; @@ -358,6 +704,17 @@ static int kvm_check_cpucfg(int id, u64 val) /* LASX architecturally implies LSX and FP but val does not satisfy that */ return -EINVAL; return 0; + case LOONGARCH_CPUCFG6: + if (val & CPUCFG6_PMP) { + u32 host = read_cpucfg(LOONGARCH_CPUCFG6); + if ((val & CPUCFG6_PMBITS) != (host & CPUCFG6_PMBITS)) + return -EINVAL; + if ((val & CPUCFG6_PMNUM) > (host & CPUCFG6_PMNUM)) + return -EINVAL; + if ((val & CPUCFG6_UPM) && !(host & CPUCFG6_UPM)) + return -EINVAL; + } + return 0; default: /* * Values for the other CPUCFG IDs are not being further validated @@ -385,11 +742,42 @@ static int kvm_get_one_reg(struct kvm_vcpu *vcpu, else ret = -EINVAL; break; + case KVM_REG_LOONGARCH_LBT: + if (!kvm_guest_has_lbt(&vcpu->arch)) + return -ENXIO; + + switch (reg->id) { + case KVM_REG_LOONGARCH_LBT_SCR0: + *v = vcpu->arch.lbt.scr0; + break; + case KVM_REG_LOONGARCH_LBT_SCR1: + *v = vcpu->arch.lbt.scr1; + break; + case KVM_REG_LOONGARCH_LBT_SCR2: + *v = vcpu->arch.lbt.scr2; + break; + case KVM_REG_LOONGARCH_LBT_SCR3: + *v = vcpu->arch.lbt.scr3; + break; + case KVM_REG_LOONGARCH_LBT_EFLAGS: + *v = vcpu->arch.lbt.eflags; + break; + case KVM_REG_LOONGARCH_LBT_FTOP: + *v = vcpu->arch.fpu.ftop; + break; + default: + ret = -EINVAL; + break; + } + break; case KVM_REG_LOONGARCH_KVM: switch (reg->id) { case KVM_REG_LOONGARCH_COUNTER: *v = drdtime() + vcpu->kvm->arch.time_offset; break; + case KVM_REG_LOONGARCH_DEBUG_INST: + *v = INSN_HVCL | KVM_HCALL_SWDBG; + break; default: ret = -EINVAL; break; @@ -440,6 +828,37 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu, if (ret) break; vcpu->arch.cpucfg[id] = (u32)v; + if (id == LOONGARCH_CPUCFG6) + vcpu->arch.max_pmu_csrid = + LOONGARCH_CSR_PERFCTRL0 + 2 * kvm_get_pmu_num(&vcpu->arch) + 1; + break; + case KVM_REG_LOONGARCH_LBT: + if (!kvm_guest_has_lbt(&vcpu->arch)) + return -ENXIO; + + switch (reg->id) { + case KVM_REG_LOONGARCH_LBT_SCR0: + vcpu->arch.lbt.scr0 = v; + break; + case KVM_REG_LOONGARCH_LBT_SCR1: + vcpu->arch.lbt.scr1 = v; + break; + case KVM_REG_LOONGARCH_LBT_SCR2: + vcpu->arch.lbt.scr2 = v; + break; + case KVM_REG_LOONGARCH_LBT_SCR3: + vcpu->arch.lbt.scr3 = v; + break; + case KVM_REG_LOONGARCH_LBT_EFLAGS: + vcpu->arch.lbt.eflags = v; + break; + case KVM_REG_LOONGARCH_LBT_FTOP: + vcpu->arch.fpu.ftop = v; + break; + default: + ret = -EINVAL; + break; + } break; case KVM_REG_LOONGARCH_KVM: switch (reg->id) { @@ -452,7 +871,7 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu, vcpu->kvm->arch.time_offset = (signed long)(v - drdtime()); break; case KVM_REG_LOONGARCH_VCPU_RESET: - kvm_reset_timer(vcpu); + vcpu->arch.st.guest_addr = 0; memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending)); memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear)); break; @@ -533,7 +952,10 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { - case 2: + case LOONGARCH_CPUCFG2: + case LOONGARCH_CPUCFG6: + return 0; + case CPUCFG_KVM_FEATURE: return 0; default: return -ENXIO; @@ -542,6 +964,16 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu, return -ENXIO; } +static int kvm_loongarch_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME) + || attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + return 0; +} + static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -551,6 +983,9 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, case KVM_LOONGARCH_VCPU_CPUCFG: ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr); break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_has_attr(vcpu, attr); + break; default: break; } @@ -558,22 +993,48 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu, return ret; } -static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu, +static int kvm_loongarch_cpucfg_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = 0; uint64_t val; uint64_t __user *uaddr = (uint64_t __user *)attr->addr; - ret = _kvm_get_cpucfg_mask(attr->attr, &val); - if (ret) - return ret; + switch (attr->attr) { + case 0 ... (KVM_MAX_CPUCFG_REGS - 1): + ret = _kvm_get_cpucfg_mask(attr->attr, &val); + if (ret) + return ret; + break; + case CPUCFG_KVM_FEATURE: + val = vcpu->kvm->arch.pv_features & LOONGARCH_PV_FEAT_MASK; + break; + default: + return -ENXIO; + } put_user(val, uaddr); return ret; } +static int kvm_loongarch_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 gpa; + u64 __user *user = (u64 __user *)attr->addr; + + if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME) + || attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + gpa = vcpu->arch.st.guest_addr; + if (put_user(gpa, user)) + return -EFAULT; + + return 0; +} + static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -581,7 +1042,10 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu, switch (attr->group) { case KVM_LOONGARCH_VCPU_CPUCFG: - ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr); + ret = kvm_loongarch_cpucfg_get_attr(vcpu, attr); + break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_get_attr(vcpu, attr); break; default: break; @@ -593,7 +1057,65 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu, static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - return -ENXIO; + u64 val, valid; + u64 __user *user = (u64 __user *)attr->addr; + struct kvm *kvm = vcpu->kvm; + + switch (attr->attr) { + case CPUCFG_KVM_FEATURE: + if (get_user(val, user)) + return -EFAULT; + + valid = LOONGARCH_PV_FEAT_MASK; + if (val & ~valid) + return -EINVAL; + + /* All vCPUs need set the same PV features */ + if ((kvm->arch.pv_features & LOONGARCH_PV_FEAT_UPDATED) + && ((kvm->arch.pv_features & valid) != val)) + return -EINVAL; + kvm->arch.pv_features = val | LOONGARCH_PV_FEAT_UPDATED; + return 0; + default: + return -ENXIO; + } +} + +static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int idx, ret = 0; + u64 gpa, __user *user = (u64 __user *)attr->addr; + struct kvm *kvm = vcpu->kvm; + + if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME) + || attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA) + return -ENXIO; + + if (get_user(gpa, user)) + return -EFAULT; + + if (gpa & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID)) + return -EINVAL; + + if (!(gpa & KVM_STEAL_PHYS_VALID)) { + vcpu->arch.st.guest_addr = gpa; + return 0; + } + + /* Check the address is in a valid memslot */ + idx = srcu_read_lock(&kvm->srcu); + if (kvm_is_error_hva(gfn_to_hva(kvm, gpa >> PAGE_SHIFT))) + ret = -EINVAL; + srcu_read_unlock(&kvm->srcu, idx); + + if (!ret) { + vcpu->arch.st.guest_addr = gpa; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + } + + return ret; } static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu, @@ -605,6 +1127,9 @@ static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu, case KVM_LOONGARCH_VCPU_CPUCFG: ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr); break; + case KVM_LOONGARCH_VCPU_PVTIME_CTRL: + ret = kvm_loongarch_pvtime_set_attr(vcpu, attr); + break; default: break; } @@ -709,12 +1234,66 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } +#ifdef CONFIG_CPU_HAS_LBT +int kvm_own_lbt(struct kvm_vcpu *vcpu) +{ + if (!kvm_guest_has_lbt(&vcpu->arch)) + return -EINVAL; + + preempt_disable(); + set_csr_euen(CSR_EUEN_LBTEN); + _restore_lbt(&vcpu->arch.lbt); + vcpu->arch.aux_inuse |= KVM_LARCH_LBT; + preempt_enable(); + + return 0; +} + +static void kvm_lose_lbt(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (vcpu->arch.aux_inuse & KVM_LARCH_LBT) { + _save_lbt(&vcpu->arch.lbt); + clear_csr_euen(CSR_EUEN_LBTEN); + vcpu->arch.aux_inuse &= ~KVM_LARCH_LBT; + } + preempt_enable(); +} + +static void kvm_check_fcsr(struct kvm_vcpu *vcpu, unsigned long fcsr) +{ + /* + * If TM is enabled, top register save/restore will + * cause lbt exception, here enable lbt in advance + */ + if (fcsr & FPU_CSR_TM) + kvm_own_lbt(vcpu); +} + +static void kvm_check_fcsr_alive(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) { + if (vcpu->arch.aux_inuse & KVM_LARCH_LBT) + return; + kvm_check_fcsr(vcpu, read_fcsr(LOONGARCH_FCSR0)); + } +} +#else +static inline void kvm_lose_lbt(struct kvm_vcpu *vcpu) { } +static inline void kvm_check_fcsr(struct kvm_vcpu *vcpu, unsigned long fcsr) { } +static inline void kvm_check_fcsr_alive(struct kvm_vcpu *vcpu) { } +#endif + /* Enable FPU and restore context */ void kvm_own_fpu(struct kvm_vcpu *vcpu) { preempt_disable(); - /* Enable FPU */ + /* + * Enable FPU for guest + * Set FR and FRE according to guest context + */ + kvm_check_fcsr(vcpu, vcpu->arch.fpu.fcsr); set_csr_euen(CSR_EUEN_FPEN); kvm_restore_fpu(&vcpu->arch.fpu); @@ -734,6 +1313,7 @@ int kvm_own_lsx(struct kvm_vcpu *vcpu) preempt_disable(); /* Enable LSX for guest */ + kvm_check_fcsr(vcpu, vcpu->arch.fpu.fcsr); set_csr_euen(CSR_EUEN_LSXEN | CSR_EUEN_FPEN); switch (vcpu->arch.aux_inuse & KVM_LARCH_FPU) { case KVM_LARCH_FPU: @@ -768,6 +1348,7 @@ int kvm_own_lasx(struct kvm_vcpu *vcpu) preempt_disable(); + kvm_check_fcsr(vcpu, vcpu->arch.fpu.fcsr); set_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN); switch (vcpu->arch.aux_inuse & (KVM_LARCH_FPU | KVM_LARCH_LSX)) { case KVM_LARCH_LSX: @@ -799,6 +1380,7 @@ void kvm_lose_fpu(struct kvm_vcpu *vcpu) { preempt_disable(); + kvm_check_fcsr_alive(vcpu); if (vcpu->arch.aux_inuse & KVM_LARCH_LASX) { kvm_save_lasx(&vcpu->arch.fpu); vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU | KVM_LARCH_LASX); @@ -821,6 +1403,7 @@ void kvm_lose_fpu(struct kvm_vcpu *vcpu) /* Disable FPU */ clear_csr_euen(CSR_EUEN_FPEN); } + kvm_lose_lbt(vcpu); preempt_enable(); } @@ -874,8 +1457,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct loongarch_csrs *csr; vcpu->arch.vpid = 0; + vcpu->arch.flush_gpa = INVALID_GPA; - hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); vcpu->arch.swtimer.function = kvm_swtimer_wakeup; vcpu->arch.handle_exit = kvm_handle_exit; @@ -893,6 +1477,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Init */ vcpu->arch.last_sched_cpu = -1; + /* Init ipi_state lock */ + spin_lock_init(&vcpu->arch.ipi_state.lock); + /* * Initialize guest register state to valid architectural reset state. */ @@ -905,6 +1492,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Set cpuid */ kvm_write_sw_gcsr(csr, LOONGARCH_CSR_TMID, vcpu->vcpu_id); + kvm_write_sw_gcsr(csr, LOONGARCH_CSR_CPUID, KVM_MAX_PHYID); /* Start with no pending virtual guest interrupts */ csr->csrs[LOONGARCH_CSR_GINTC] = 0; @@ -923,6 +1511,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) hrtimer_cancel(&vcpu->arch.swtimer); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); + kvm_drop_cpuid(vcpu); kfree(vcpu->arch.csr); /* @@ -959,9 +1548,10 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Restore timer state regardless */ kvm_restore_timer(vcpu); + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); - /* Control guest page CCA attribute */ - change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT); + /* Restore hardware PMU CSRs */ + kvm_restore_pmu(vcpu); /* Don't bother restoring registers multiple times unless necessary */ if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE) @@ -1139,12 +1729,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mmio_needed = 0; } - if (run->exit_reason == KVM_EXIT_LOONGARCH_IOCSR) { + switch (run->exit_reason) { + case KVM_EXIT_HYPERCALL: + kvm_complete_user_service(vcpu, run); + break; + case KVM_EXIT_LOONGARCH_IOCSR: if (!run->iocsr_io.is_write) kvm_complete_iocsr_read(vcpu, run); + break; } - if (run->immediate_exit) + if (!vcpu->wants_to_run) return r; /* Clear exit_reason */ diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 0a37f6fa8f2d..edccfc8c9cd8 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -5,6 +5,9 @@ #include <linux/kvm_host.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_vcpu.h> +#include <asm/kvm_eiointc.h> +#include <asm/kvm_pch_pic.h> const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), @@ -30,8 +33,26 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (!kvm->arch.pgd) return -ENOMEM; + kvm->arch.phyid_map = kvzalloc(sizeof(struct kvm_phyid_map), GFP_KERNEL_ACCOUNT); + if (!kvm->arch.phyid_map) { + free_page((unsigned long)kvm->arch.pgd); + kvm->arch.pgd = NULL; + return -ENOMEM; + } + spin_lock_init(&kvm->arch.phyid_map_lock); + kvm_init_vmcs(kvm); - kvm->arch.gpa_size = BIT(cpu_vabits - 1); + + /* Enable all PV features by default */ + kvm->arch.pv_features = BIT(KVM_FEATURE_IPI); + if (kvm_pvtime_supported()) + kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME); + + /* + * cpu_vabits means user address space only (a half of total). + * GPA size of VM is the same with the size of user address space. + */ + kvm->arch.gpa_size = BIT(cpu_vabits); kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1; kvm->arch.invalid_ptes[0] = 0; kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table; @@ -52,6 +73,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_destroy_vcpus(kvm); free_page((unsigned long)kvm->arch.pgd); kvm->arch.pgd = NULL; + kvfree(kvm->arch.phyid_map); + kvm->arch.phyid_map = NULL; } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -59,6 +82,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { + case KVM_CAP_IRQCHIP: case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: @@ -66,6 +90,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_IOEVENTFD: case KVM_CAP_MP_STATE: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_NR_VCPUS: @@ -88,7 +113,85 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } +static int kvm_vm_feature_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_LOONGARCH_VM_FEAT_LSX: + if (cpu_has_lsx) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_LASX: + if (cpu_has_lasx) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_X86BT: + if (cpu_has_lbt_x86) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_ARMBT: + if (cpu_has_lbt_arm) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_MIPSBT: + if (cpu_has_lbt_mips) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_PMU: + if (cpu_has_pmp) + return 0; + return -ENXIO; + case KVM_LOONGARCH_VM_FEAT_PV_IPI: + return 0; + case KVM_LOONGARCH_VM_FEAT_PV_STEALTIME: + if (kvm_pvtime_supported()) + return 0; + return -ENXIO; + default: + return -ENXIO; + } +} + +static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_LOONGARCH_VM_FEAT_CTRL: + return kvm_vm_feature_has_attr(kvm, attr); + default: + return -ENXIO; + } +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { - return -ENOIOCTLCMD; + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + struct kvm_device_attr attr; + + switch (ioctl) { + case KVM_CREATE_IRQCHIP: + return 0; + case KVM_HAS_DEVICE_ATTR: + if (copy_from_user(&attr, argp, sizeof(attr))) + return -EFAULT; + + return kvm_vm_has_attr(kvm, &attr); + default: + return -ENOIOCTLCMD; + } +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, bool line_status) +{ + if (!kvm_arch_irqchip_in_kernel(kvm)) + return -ENXIO; + + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, line_status); + + return 0; +} + +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return (kvm->arch.ipi && kvm->arch.eiointc && kvm->arch.pch_pic); } diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index a77bf160bfc4..fae77809048b 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -6,6 +6,10 @@ lib-y += delay.o memset.o memcpy.o memmove.o \ clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o +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/clear_user.S b/arch/loongarch/lib/clear_user.S index be741544e62b..7a0db643b286 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -10,6 +10,7 @@ #include <asm/asm-extable.h> #include <asm/cpu.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> SYM_FUNC_START(__clear_user) /* @@ -204,3 +205,5 @@ SYM_FUNC_START(__clear_user_fast) _asm_extable 28b, .Lsmall_fixup _asm_extable 29b, .Lexit SYM_FUNC_END(__clear_user_fast) + +STACK_FRAME_NON_STANDARD __clear_user_fast diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index feec3d362803..095ce9181c6c 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -10,6 +10,7 @@ #include <asm/asm-extable.h> #include <asm/cpu.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> SYM_FUNC_START(__copy_user) /* @@ -278,3 +279,5 @@ SYM_FUNC_START(__copy_user_fast) _asm_extable 58b, .Lexit _asm_extable 59b, .Lexit SYM_FUNC_END(__copy_user_fast) + +STACK_FRAME_NON_STANDARD __copy_user_fast diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c new file mode 100644 index 000000000000..8af8113ecd9d --- /dev/null +++ b/arch/loongarch/lib/crc32-loongarch.c @@ -0,0 +1,135 @@ +// 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/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 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_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (!static_branch_likely(&have_crc32)) + return crc32c_le_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_le_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; +} +arch_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/lib/csum.c b/arch/loongarch/lib/csum.c index a5e84b403c3b..df309ae4045d 100644 --- a/arch/loongarch/lib/csum.c +++ b/arch/loongarch/lib/csum.c @@ -25,7 +25,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) const u64 *ptr; u64 data, sum64 = 0; - if (unlikely(len == 0)) + if (unlikely(len <= 0)) return 0; offset = (unsigned long)buff & 7; diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index fa1148878d2b..9517a2f961af 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -9,6 +9,7 @@ #include <asm/asmmacro.h> #include <asm/cpu.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> .section .noinstr.text, "ax" @@ -197,3 +198,5 @@ SYM_FUNC_START(__memcpy_fast) jr ra SYM_FUNC_END(__memcpy_fast) _ASM_NOKPROBE(__memcpy_fast) + +STACK_FRAME_NON_STANDARD __memcpy_small diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index 06d3ca54cbfe..df3846620553 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -9,6 +9,7 @@ #include <asm/asmmacro.h> #include <asm/cpu.h> #include <asm/regdef.h> +#include <asm/unwind_hints.h> .macro fill_to_64 r0 bstrins.d \r0, \r0, 15, 8 @@ -166,3 +167,5 @@ SYM_FUNC_START(__memset_fast) jr ra SYM_FUNC_END(__memset_fast) _ASM_NOKPROBE(__memset_fast) + +STACK_FRAME_NON_STANDARD __memset_fast diff --git a/arch/loongarch/lib/tishift.S b/arch/loongarch/lib/tishift.S new file mode 100644 index 000000000000..fa1d310012bc --- /dev/null +++ b/arch/loongarch/lib/tishift.S @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <asm/asmmacro.h> +#include <linux/export.h> +#include <linux/linkage.h> + +SYM_FUNC_START(__ashlti3) + srli.d t2, a0, 1 + nor t3, zero, a2 + sll.d t1, a1, a2 + srl.d t2, t2, t3 + andi t0, a2, 64 + sll.d a0, a0, a2 + or t1, t2, t1 + maskeqz a1, a0, t0 + masknez a0, a0, t0 + masknez t0, t1, t0 + or a1, t0, a1 + jr ra +SYM_FUNC_END(__ashlti3) +EXPORT_SYMBOL(__ashlti3) + +SYM_FUNC_START(__ashrti3) + nor t3, zero, a2 + slli.d t2, a1, 1 + srl.d t1, a0, a2 + sll.d t2, t2, t3 + andi t0, a2, 64 + or t1, t2, t1 + sra.d a2, a1, a2 + srai.d a1, a1, 63 + maskeqz a0, a2, t0 + maskeqz a1, a1, t0 + masknez a2, a2, t0 + masknez t0, t1, t0 + or a1, a1, a2 + or a0, t0, a0 + jr ra +SYM_FUNC_END(__ashrti3) +EXPORT_SYMBOL(__ashrti3) + +SYM_FUNC_START(__lshrti3) + slli.d t2, a1, 1 + nor t3, zero, a2 + srl.d t1, a0, a2 + sll.d t2, t2, t3 + andi t0, a2, 64 + srl.d a1, a1, a2 + or t1, t2, t1 + maskeqz a0, a1, t0 + masknez a1, a1, t0 + masknez t0, t1, t0 + or a0, t0, a0 + jr ra +SYM_FUNC_END(__lshrti3) +EXPORT_SYMBOL(__lshrti3) diff --git a/arch/loongarch/mm/Makefile b/arch/loongarch/mm/Makefile index e4d1e581dbae..278be2c8fc36 100644 --- a/arch/loongarch/mm/Makefile +++ b/arch/loongarch/mm/Makefile @@ -4,7 +4,8 @@ # obj-y += init.o cache.o tlb.o tlbex.o extable.o \ - fault.o ioremap.o maccess.o mmap.o pgtable.o page.o + fault.o ioremap.o maccess.o mmap.o pgtable.o \ + page.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_KASAN) += kasan_init.o diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1fc2f6813ea0..deefd9617d00 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -31,11 +31,52 @@ int show_unhandled_signals = 1; +static int __kprobes spurious_fault(unsigned long write, unsigned long address) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (!(address & __UA_LIMIT)) + return 0; + + pgd = pgd_offset_k(address); + if (!pgd_present(pgdp_get(pgd))) + return 0; + + p4d = p4d_offset(pgd, address); + if (!p4d_present(p4dp_get(p4d))) + return 0; + + pud = pud_offset(p4d, address); + if (!pud_present(pudp_get(pud))) + return 0; + + pmd = pmd_offset(pud, address); + if (!pmd_present(pmdp_get(pmd))) + return 0; + + if (pmd_leaf(*pmd)) { + return write ? pmd_write(pmdp_get(pmd)) : 1; + } else { + pte = pte_offset_kernel(pmd, address); + if (!pte_present(ptep_get(pte))) + return 0; + + return write ? pte_write(ptep_get(pte)) : 1; + } +} + static void __kprobes no_context(struct pt_regs *regs, unsigned long write, unsigned long address) { const int field = sizeof(unsigned long) * 2; + if (spurious_fault(write, address)) + return; + /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) return; @@ -202,10 +243,10 @@ good_area: if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } else { - if (!(vma->vm_flags & VM_READ) && address != exception_era(regs)) - goto bad_area; if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs)) goto bad_area; + if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs)) + goto bad_area; } /* diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index 1e76fcb83093..e4068906143b 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -39,32 +39,22 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, pmd_t *pmd = NULL; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { + if (pgd_present(pgdp_get(pgd))) { p4d = p4d_offset(pgd, addr); - if (p4d_present(*p4d)) { + if (p4d_present(p4dp_get(p4d))) { pud = pud_offset(p4d, addr); - if (pud_present(*pud)) + if (pud_present(pudp_get(pud))) pmd = pmd_offset(pud, addr); } } return (pte_t *) pmd; } -int pmd_huge(pmd_t pmd) -{ - return (pmd_val(pmd) & _PAGE_HUGE) != 0; -} - -int pud_huge(pud_t pud) -{ - return (pud_val(pud) & _PAGE_HUGE) != 0; -} - uint64_t pmd_to_entrylo(unsigned long pmd_val) { uint64_t val; /* PMD as PTE. Must be huge page */ - if (!pmd_huge(__pmd(pmd_val))) + if (!pmd_leaf(__pmd(pmd_val))) panic("%s", __func__); val = pmd_val ^ _PAGE_HUGE; diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 4dd53427f657..ca5aa5f46a9f 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -24,6 +24,7 @@ #include <linux/gfp.h> #include <linux/hugetlb.h> #include <linux/mmzone.h> +#include <linux/execmem.h> #include <asm/asm-offsets.h> #include <asm/bootinfo.h> @@ -140,7 +141,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next) { - int huge = pmd_val(*pmd) & _PAGE_HUGE; + int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE; if (huge) vmemmap_verify((pte_t *)pmd, node, addr, next); @@ -172,10 +173,8 @@ pte_t * __init populate_kernel_pte(unsigned long addr) pud_t *pud; pmd_t *pmd; - if (p4d_none(*p4d)) { - pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pud) - panic("%s: Failed to allocate memory\n", __func__); + if (p4d_none(p4dp_get(p4d))) { + pud = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); p4d_populate(&init_mm, p4d, pud); #ifndef __PAGETABLE_PUD_FOLDED pud_init(pud); @@ -183,10 +182,8 @@ pte_t * __init populate_kernel_pte(unsigned long addr) } pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pmd) - panic("%s: Failed to allocate memory\n", __func__); + if (pud_none(pudp_get(pud))) { + pmd = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, pmd); #ifndef __PAGETABLE_PMD_FOLDED pmd_init(pmd); @@ -194,13 +191,12 @@ pte_t * __init populate_kernel_pte(unsigned long addr) } pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { + if (!pmd_present(pmdp_get(pmd))) { pte_t *pte; - pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate memory\n", __func__); + pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, pte); + kernel_pte_init(pte); } return pte_offset_kernel(pmd, addr); @@ -215,7 +211,7 @@ void __init __set_fixmap(enum fixed_addresses idx, BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = populate_kernel_pte(addr); - if (!pte_none(*ptep)) { + if (!pte_none(ptep_get(ptep))) { pte_ERROR(*ptep); return; } @@ -248,3 +244,23 @@ EXPORT_SYMBOL(invalid_pmd_table); #endif pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; EXPORT_SYMBOL(invalid_pte_table); + +#ifdef CONFIG_EXECMEM +static struct execmem_info execmem_info __ro_after_init; + +struct execmem_info __init *execmem_arch_setup(void) +{ + execmem_info = (struct execmem_info){ + .ranges = { + [EXECMEM_DEFAULT] = { + .start = MODULES_VADDR, + .end = MODULES_END, + .pgprot = PAGE_KERNEL, + .alignment = 1, + }, + }, + }; + + return &execmem_info; +} +#endif /* CONFIG_EXECMEM */ diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index c608adc99845..d2681272d8f0 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -13,6 +13,13 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); +#ifdef __PAGETABLE_P4D_FOLDED +#define __pgd_none(early, pgd) (0) +#else +#define __pgd_none(early, pgd) (early ? (pgd_val(pgd) == 0) : \ +(__pa(pgd_val(pgd)) == (unsigned long)__pa(kasan_early_shadow_p4d))) +#endif + #ifdef __PAGETABLE_PUD_FOLDED #define __p4d_none(early, p4d) (0) #else @@ -55,6 +62,9 @@ void *kasan_mem_to_shadow(const void *addr) case XKPRANGE_UC_SEG: offset = XKPRANGE_UC_SHADOW_OFFSET; break; + case XKPRANGE_WC_SEG: + offset = XKPRANGE_WC_SHADOW_OFFSET; + break; case XKVRANGE_VC_SEG: offset = XKVRANGE_VC_SHADOW_OFFSET; break; @@ -79,6 +89,8 @@ const void *kasan_shadow_to_mem(const void *shadow_addr) if (addr >= XKVRANGE_VC_SHADOW_OFFSET) return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START); + else if (addr >= XKPRANGE_WC_SHADOW_OFFSET) + return (void *)(((addr - XKPRANGE_WC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_WC_START); else if (addr >= XKPRANGE_UC_SHADOW_OFFSET) return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START); else if (addr >= XKPRANGE_CC_SHADOW_OFFSET) @@ -105,7 +117,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (__pmd_none(early, READ_ONCE(*pmdp))) { + if (__pmd_none(early, pmdp_get(pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node); if (!early) @@ -118,7 +130,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (__pud_none(early, READ_ONCE(*pudp))) { + if (__pud_none(early, pudp_get(pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node); if (!early) @@ -131,7 +143,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early) { - if (__p4d_none(early, READ_ONCE(*p4dp))) { + if (__p4d_none(early, p4dp_get(p4dp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node); if (!early) @@ -142,6 +154,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, return pud_offset(p4dp, addr); } +static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) +{ + if (__pgd_none(early, pgdp_get(pgdp))) { + phys_addr_t p4d_phys = early ? + __pa_symbol(kasan_early_shadow_p4d) : kasan_alloc_zeroed_page(node); + if (!early) + memcpy(__va(p4d_phys), kasan_early_shadow_p4d, sizeof(kasan_early_shadow_p4d)); + pgd_populate(&init_mm, pgdp, (p4d_t *)__va(p4d_phys)); + } + + return p4d_offset(pgdp, addr); +} + static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { @@ -154,7 +179,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep))); + } while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep))); } static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, @@ -166,7 +191,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, do { next = pmd_addr_end(addr, end); kasan_pte_populate(pmdp, addr, next, node, early); - } while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp))); + } while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp))); } static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, @@ -178,19 +203,19 @@ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, do { next = pud_addr_end(addr, end); kasan_pmd_populate(pudp, addr, next, node, early); - } while (pudp++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end && __pud_none(early, READ_ONCE(*pudp))); } static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early); do { next = p4d_addr_end(addr, end); kasan_pud_populate(p4dp, addr, next, node, early); - } while (p4dp++, addr = next, addr != end); + } while (p4dp++, addr = next, addr != end && __p4d_none(early, READ_ONCE(*p4dp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, @@ -218,7 +243,7 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END + 1, PGDIR_SIZE)); } static inline void kasan_set_pgd(pgd_t *pgdp, pgd_t pgdval) @@ -233,7 +258,7 @@ static void __init clear_pgds(unsigned long start, unsigned long end) * swapper_pg_dir. pgd_clear() can't be used * here because it's nop on 2,3-level pagetable setups */ - for (; start < end; start += PGDIR_SIZE) + for (; start < end; start = pgd_addr_end(start, end)) kasan_set_pgd((pgd_t *)pgd_offset_k(start), __pgd(0)); } @@ -243,6 +268,17 @@ void __init kasan_init(void) phys_addr_t pa_start, pa_end; /* + * If PGDIR_SIZE is too large for cpu_vabits, KASAN_SHADOW_END will + * overflow UINTPTR_MAX and then looks like a user space address. + * For example, PGDIR_SIZE of CONFIG_4KB_4LEVEL is 2^39, which is too + * large for Loongson-2K series whose cpu_vabits = 39. + */ + if (KASAN_SHADOW_END < vm_map_base) { + pr_warn("PGDIR_SIZE too large for cpu_vabits, KernelAddressSanitizer disabled.\n"); + return; + } + + /* * PGD was populated as invalid_pmd_table or invalid_pud_table * in pagetable_init() which depends on how many levels of page * table you are using, but we had to clean the gpd of kasan diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index a9630a81b38a..1df9e99582cc 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -3,7 +3,9 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/export.h> +#include <linux/hugetlb.h> #include <linux/io.h> +#include <linux/kfence.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/mman.h> @@ -24,7 +26,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -62,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, } info.length = len; - info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0; info.align_offset = pgoff << PAGE_SHIFT; + if (filp && is_file_hugepages(filp)) + info.align_mask = huge_page_mask_align(filp); + else + info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0; if (dir == DOWN) { info.flags = VM_UNMAPPED_AREA_TOPDOWN; @@ -82,14 +87,14 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; return vm_unmapped_area(&info); } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, - unsigned long len, unsigned long pgoff, unsigned long flags) + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, UP); @@ -101,7 +106,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, */ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, - unsigned long flags) + unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, DOWN); @@ -111,6 +116,9 @@ int __virt_addr_valid(volatile void *kaddr) { unsigned long vaddr = (unsigned long)kaddr; + if (is_kfence_address((void *)kaddr)) + return 1; + if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base)) return 0; diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c new file mode 100644 index 000000000000..99165903908a --- /dev/null +++ b/arch/loongarch/mm/pageattr.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <linux/memblock.h> +#include <linux/pagewalk.h> +#include <linux/pgtable.h> +#include <asm/set_memory.h> +#include <asm/tlbflush.h> + +struct pageattr_masks { + pgprot_t set_mask; + pgprot_t clear_mask; +}; + +static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) +{ + unsigned long new_val = val; + struct pageattr_masks *masks = walk->private; + + new_val &= ~(pgprot_val(masks->clear_mask)); + new_val |= (pgprot_val(masks->set_mask)); + + return new_val; +} + +static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pgd_t val = pgdp_get(pgd); + + if (pgd_leaf(val)) { + val = __pgd(set_pageattr_masks(pgd_val(val), walk)); + set_pgd(pgd, val); + } + + return 0; +} + +static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + p4d_t val = p4dp_get(p4d); + + if (p4d_leaf(val)) { + val = __p4d(set_pageattr_masks(p4d_val(val), walk)); + set_p4d(p4d, val); + } + + return 0; +} + +static int pageattr_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pud_t val = pudp_get(pud); + + if (pud_leaf(val)) { + val = __pud(set_pageattr_masks(pud_val(val), walk)); + set_pud(pud, val); + } + + return 0; +} + +static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pmd_t val = pmdp_get(pmd); + + if (pmd_leaf(val)) { + val = __pmd(set_pageattr_masks(pmd_val(val), walk)); + set_pmd(pmd, val); + } + + return 0; +} + +static int pageattr_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t val = ptep_get(pte); + + val = __pte(set_pageattr_masks(pte_val(val), walk)); + set_pte(pte, val); + + return 0; +} + +static int pageattr_pte_hole(unsigned long addr, unsigned long next, + int depth, struct mm_walk *walk) +{ + return 0; +} + +static const struct mm_walk_ops pageattr_ops = { + .pgd_entry = pageattr_pgd_entry, + .p4d_entry = pageattr_p4d_entry, + .pud_entry = pageattr_pud_entry, + .pmd_entry = pageattr_pmd_entry, + .pte_entry = pageattr_pte_entry, + .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, +}; + +static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) +{ + int ret; + unsigned long start = addr; + unsigned long end = start + PAGE_SIZE * numpages; + struct pageattr_masks masks = { + .set_mask = set_mask, + .clear_mask = clear_mask + }; + + if (!numpages) + return 0; + + mmap_write_lock(&init_mm); + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks); + mmap_write_unlock(&init_mm); + + flush_tlb_kernel_range(start, end); + + return ret; +} + +int set_memory_x(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_NO_EXEC)); +} + +int set_memory_nx(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(_PAGE_NO_EXEC), __pgprot(0)); +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_WRITE | _PAGE_DIRTY)); +} + +int set_memory_rw(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(_PAGE_WRITE | _PAGE_DIRTY), __pgprot(0)); +} + +bool kernel_page_present(struct page *page) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return memblock_is_memory(__pa(addr)); + + pgd = pgd_offset_k(addr); + if (pgd_none(pgdp_get(pgd))) + return false; + if (pgd_leaf(pgdp_get(pgd))) + return true; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(p4dp_get(p4d))) + return false; + if (p4d_leaf(p4dp_get(p4d))) + return true; + + pud = pud_offset(p4d, addr); + if (pud_none(pudp_get(pud))) + return false; + if (pud_leaf(pudp_get(pud))) + return true; + + pmd = pmd_offset(pud, addr); + if (pmd_none(pmdp_get(pmd))) + return false; + if (pmd_leaf(pmdp_get(pmd))) + return true; + + pte = pte_offset_kernel(pmd, addr); + return pte_present(ptep_get(pte)); +} + +int set_direct_map_default_noflush(struct page *page) +{ + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, 1, PAGE_KERNEL, __pgprot(0)); +} + +int set_direct_map_invalid_noflush(struct page *page) +{ + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, 1, __pgprot(0), __pgprot(_PAGE_PRESENT | _PAGE_VALID)); +} + +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + unsigned long addr = (unsigned long)page_address(page); + pgprot_t set, clear; + + if (addr < vm_map_base) + return 0; + + if (valid) { + set = PAGE_KERNEL; + clear = __pgprot(0); + } else { + set = __pgprot(0); + clear = __pgprot(_PAGE_PRESENT | _PAGE_VALID); + } + + return __set_memory(addr, 1, set, clear); +} diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 2aae72e63871..22a94bb3e6e8 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -11,23 +11,22 @@ struct page *dmw_virt_to_page(unsigned long kaddr) { - return pfn_to_page(virt_to_pfn(kaddr)); + return phys_to_page(__pa(kaddr)); } EXPORT_SYMBOL(dmw_virt_to_page); struct page *tlb_virt_to_page(unsigned long kaddr) { - return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr))); + return phys_to_page(pfn_to_phys(pte_pfn(*virt_to_kpte(kaddr)))); } EXPORT_SYMBOL(tlb_virt_to_page); pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *init, *ret = NULL; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); + pgd_t *init, *ret; - if (ptdesc) { - ret = (pgd_t *)ptdesc_address(ptdesc); + ret = __pgd_alloc(mm, 0); + if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, @@ -116,6 +115,26 @@ void pud_init(void *addr) EXPORT_SYMBOL_GPL(pud_init); #endif +void kernel_pte_init(void *addr) +{ + unsigned long *p, *end; + + p = (unsigned long *)addr; + end = p + PTRS_PER_PTE; + + do { + p[0] = _PAGE_GLOBAL; + p[1] = _PAGE_GLOBAL; + p[2] = _PAGE_GLOBAL; + p[3] = _PAGE_GLOBAL; + p[4] = _PAGE_GLOBAL; + p += 8; + p[-3] = _PAGE_GLOBAL; + p[-2] = _PAGE_GLOBAL; + p[-1] = _PAGE_GLOBAL; + } while (p != end); +} + pmd_t mk_pmd(struct page *page, pgprot_t prot) { pmd_t pmd; @@ -128,7 +147,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot) void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); flush_tlb_all(); } diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index 0b95d32b30c9..3b427b319db2 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -9,8 +9,9 @@ #include <linux/hugetlb.h> #include <linux/export.h> -#include <asm/cpu.h> #include <asm/bootinfo.h> +#include <asm/cpu.h> +#include <asm/exception.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/tlb.h> @@ -266,24 +267,20 @@ static void setup_tlb_handler(int cpu) setup_ptwalker(); local_flush_tlb_all(); + if (cpu_has_ptw) { + exception_table[EXCCODE_TLBI] = handle_tlb_load_ptw; + exception_table[EXCCODE_TLBL] = handle_tlb_load_ptw; + exception_table[EXCCODE_TLBS] = handle_tlb_store_ptw; + exception_table[EXCCODE_TLBM] = handle_tlb_modify_ptw; + } + /* The tlb handlers are generated only once */ if (cpu == 0) { memcpy((void *)tlbrentry, handle_tlb_refill, 0x80); local_flush_icache_range(tlbrentry, tlbrentry + 0x80); - if (!cpu_has_ptw) { - set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load, VECSIZE); - set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load, VECSIZE); - set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store, VECSIZE); - set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify, VECSIZE); - } else { - set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load_ptw, VECSIZE); - set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load_ptw, VECSIZE); - set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store_ptw, VECSIZE); - set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify_ptw, VECSIZE); - } - set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE); - set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE); - set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE); + + for (int i = EXCCODE_TLBL; i <= EXCCODE_TLBPE; i++) + set_handler(i * VECSIZE, exception_table[i], VECSIZE); } else { int vec_sz __maybe_unused; void *addr __maybe_unused; @@ -292,7 +289,7 @@ static void setup_tlb_handler(int cpu) /* Avoid lockdep warning */ rcutree_report_cpu_starting(cpu); -#ifdef CONFIG_NUMA +#if defined(CONFIG_NUMA) && !defined(CONFIG_PREEMPT_RT) vec_sz = sizeof(exception_handlers); if (pcpu_handlers[cpu]) diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index d5d682f3d29f..c08682a89c58 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -18,6 +18,7 @@ .macro tlb_do_page_fault, write SYM_CODE_START(tlb_do_page_fault_\write) + UNWIND_HINT_UNDEFINED SAVE_ALL csrrd a2, LOONGARCH_CSR_BADV move a0, sp @@ -32,6 +33,7 @@ tlb_do_page_fault 1 SYM_CODE_START(handle_tlb_protect) + UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL move a0, sp @@ -44,6 +46,7 @@ SYM_CODE_START(handle_tlb_protect) SYM_CODE_END(handle_tlb_protect) SYM_CODE_START(handle_tlb_load) + UNWIND_HINT_UNDEFINED csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -122,6 +125,8 @@ vmalloc_load: tlb_huge_update_load: #ifdef CONFIG_SMP ll.d ra, t1, 0 +#else + rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) #endif andi t0, ra, _PAGE_PRESENT beqz t0, nopage_tlb_load @@ -132,7 +137,6 @@ tlb_huge_update_load: beqz t0, tlb_huge_update_load ori t0, ra, _PAGE_VALID #else - rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) ori t0, ra, _PAGE_VALID st.d t0, t1, 0 #endif @@ -190,6 +194,7 @@ nopage_tlb_load: SYM_CODE_END(handle_tlb_load) SYM_CODE_START(handle_tlb_load_ptw) + UNWIND_HINT_UNDEFINED csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_0 @@ -197,6 +202,7 @@ SYM_CODE_START(handle_tlb_load_ptw) SYM_CODE_END(handle_tlb_load_ptw) SYM_CODE_START(handle_tlb_store) + UNWIND_HINT_UNDEFINED csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -276,6 +282,8 @@ vmalloc_store: tlb_huge_update_store: #ifdef CONFIG_SMP ll.d ra, t1, 0 +#else + rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) #endif andi t0, ra, _PAGE_PRESENT | _PAGE_WRITE xori t0, t0, _PAGE_PRESENT | _PAGE_WRITE @@ -287,7 +295,6 @@ tlb_huge_update_store: beqz t0, tlb_huge_update_store ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #else - rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif @@ -346,6 +353,7 @@ nopage_tlb_store: SYM_CODE_END(handle_tlb_store) SYM_CODE_START(handle_tlb_store_ptw) + UNWIND_HINT_UNDEFINED csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 @@ -353,6 +361,7 @@ SYM_CODE_START(handle_tlb_store_ptw) SYM_CODE_END(handle_tlb_store_ptw) SYM_CODE_START(handle_tlb_modify) + UNWIND_HINT_UNDEFINED csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -431,6 +440,8 @@ vmalloc_modify: tlb_huge_update_modify: #ifdef CONFIG_SMP ll.d ra, t1, 0 +#else + rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) #endif andi t0, ra, _PAGE_WRITE beqz t0, nopage_tlb_modify @@ -441,7 +452,6 @@ tlb_huge_update_modify: beqz t0, tlb_huge_update_modify ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) #else - rotri.d ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1) ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif @@ -500,6 +510,7 @@ nopage_tlb_modify: SYM_CODE_END(handle_tlb_modify) SYM_CODE_START(handle_tlb_modify_ptw) + UNWIND_HINT_UNDEFINED csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 @@ -507,6 +518,7 @@ SYM_CODE_START(handle_tlb_modify_ptw) SYM_CODE_END(handle_tlb_modify_ptw) SYM_CODE_START(handle_tlb_refill) + UNWIND_HINT_UNDEFINED csrwr t0, LOONGARCH_CSR_TLBRSAVE csrrd t0, LOONGARCH_CSR_PGD lddir t0, t0, 3 diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index e73323d759d0..ea357a3edc09 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -179,15 +179,15 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) if (!is_tail_call) { /* Set return value */ - move_reg(ctx, LOONGARCH_GPR_A0, regmap[BPF_REG_0]); + emit_insn(ctx, addiw, LOONGARCH_GPR_A0, regmap[BPF_REG_0], 0); /* Return to the caller */ - emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); } else { /* * Call the next bpf prog and skip the first instruction * of TCC initialization. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 1); } } @@ -904,7 +904,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext return ret; move_addr(ctx, t1, func_addr); - emit_insn(ctx, jirl, t1, LOONGARCH_GPR_RA, 0); + emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0); break; @@ -1294,16 +1294,19 @@ skip_init_ctx: flush_icache_range((unsigned long)header, (unsigned long)(ctx.image + ctx.idx)); if (!prog->is_func || extra_pass) { + int err; + if (extra_pass && ctx.idx != jit_data->ctx.idx) { pr_err_once("multi-func JIT bug %d != %d\n", ctx.idx, jit_data->ctx.idx); - bpf_jit_binary_free(header); - prog->bpf_func = NULL; - prog->jited = 0; - prog->jited_len = 0; - goto out_offset; + goto out_free; + } + err = bpf_jit_binary_lock_ro(header); + if (err) { + pr_err_once("bpf_jit_binary_lock_ro() returned %d\n", + err); + goto out_free; } - bpf_jit_binary_lock_ro(header); } else { jit_data->ctx = ctx; jit_data->image = image_ptr; @@ -1334,6 +1337,13 @@ out: out_offset = -1; return prog; + +out_free: + bpf_jit_binary_free(header); + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; } /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */ diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index 365f7de771cb..1da4dc46df43 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -225,6 +225,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (bus) { memcpy(bus->sysdata, info->cfg, sizeof(struct pci_config_window)); kfree(info); + kfree(root_ops); } else { struct pci_bus *child; diff --git a/arch/loongarch/power/platform.c b/arch/loongarch/power/platform.c index 3ea8e07aa225..5bbdb9fd76e5 100644 --- a/arch/loongarch/power/platform.c +++ b/arch/loongarch/power/platform.c @@ -17,7 +17,7 @@ void enable_gpe_wakeup(void) if (acpi_gbl_reduced_hardware) return; - acpi_enable_all_wakeup_gpes(); + acpi_hw_enable_all_wakeup_gpes(); } void enable_pci_wakeup(void) @@ -34,22 +34,49 @@ void enable_pci_wakeup(void) acpi_write_bit_register(ACPI_BITREG_PCIEXP_WAKE_DISABLE, 0); } +static struct platform_device loongson3_cpufreq_device = { + .name = "loongson3_cpufreq", + .id = -1, +}; + +static int __init loongson_cpufreq_init(void) +{ + if (!cpu_has_scalefreq) + return -ENODEV; + + return platform_device_register(&loongson3_cpufreq_device); +} + +arch_initcall(loongson_cpufreq_init); + +static void default_suspend_addr(void) +{ + acpi_enter_sleep_state(ACPI_STATE_S3); +} + static int __init loongson3_acpi_suspend_init(void) { #ifdef CONFIG_ACPI acpi_status status; uint64_t suspend_addr = 0; - if (acpi_disabled || acpi_gbl_reduced_hardware) + if (acpi_disabled) + return 0; + + if (!acpi_gbl_reduced_hardware) + acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1); + + if (!acpi_sleep_state_supported(ACPI_STATE_S3)) return 0; - acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1); status = acpi_evaluate_integer(NULL, "\\SADR", NULL, &suspend_addr); if (ACPI_FAILURE(status) || !suspend_addr) { - pr_err("ACPI S3 is not support!\n"); - return -1; + pr_info("ACPI S3 supported with hardware register default\n"); + loongson_sysconf.suspend_addr = (u64)default_suspend_addr; + } else { + pr_info("ACPI S3 supported with Loongson ACPI SADR extension\n"); + loongson_sysconf.suspend_addr = (u64)phys_to_virt(PHYSADDR(suspend_addr)); } - loongson_sysconf.suspend_addr = (u64)phys_to_virt(PHYSADDR(suspend_addr)); #endif return 0; } diff --git a/arch/loongarch/power/suspend.c b/arch/loongarch/power/suspend.c index 166d9e06a64b..c9e594925c47 100644 --- a/arch/loongarch/power/suspend.c +++ b/arch/loongarch/power/suspend.c @@ -24,6 +24,7 @@ struct saved_registers { u64 kpgd; u32 pwctl0; u32 pwctl1; + u64 pcpu_base; }; static struct saved_registers saved_regs; @@ -36,6 +37,7 @@ void loongarch_common_suspend(void) saved_regs.pwctl1 = csr_read32(LOONGARCH_CSR_PWCTL1); saved_regs.ecfg = csr_read32(LOONGARCH_CSR_ECFG); saved_regs.euen = csr_read32(LOONGARCH_CSR_EUEN); + saved_regs.pcpu_base = csr_read64(PERCPU_BASE_KS); loongarch_suspend_addr = loongson_sysconf.suspend_addr; } @@ -44,7 +46,6 @@ void loongarch_common_resume(void) { sync_counter(); local_flush_tlb_all(); - csr_write64(per_cpu_offset(0), PERCPU_BASE_KS); csr_write64(eentry, LOONGARCH_CSR_EENTRY); csr_write64(eentry, LOONGARCH_CSR_MERRENTRY); csr_write64(tlbrentry, LOONGARCH_CSR_TLBRENTRY); @@ -55,6 +56,7 @@ void loongarch_common_resume(void) csr_write32(saved_regs.pwctl1, LOONGARCH_CSR_PWCTL1); csr_write32(saved_regs.ecfg, LOONGARCH_CSR_ECFG); csr_write32(saved_regs.euen, LOONGARCH_CSR_EUEN); + csr_write64(saved_regs.pcpu_base, PERCPU_BASE_KS); } int loongarch_acpi_suspend(void) diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index e2fc3b4e31f0..df0865df26fa 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -30,9 +30,6 @@ st.d $r29, sp, PT_R29 st.d $r30, sp, PT_R30 st.d $r31, sp, PT_R31 - - la.pcrel t0, acpi_saved_sp - st.d sp, t0, 0 .endm .macro SETUP_WAKEUP @@ -51,6 +48,7 @@ ld.d $r29, sp, PT_R29 ld.d $r30, sp, PT_R30 ld.d $r31, sp, PT_R31 + addi.d sp, sp, PT_SIZE .endm .text @@ -59,6 +57,10 @@ /* Sleep/wakeup code for Loongson-3 */ SYM_FUNC_START(loongarch_suspend_enter) SETUP_SLEEP + + la.pcrel t0, acpi_saved_sp + st.d sp, t0, 0 + bl __flush_cache_all /* Pass RA and SP to BIOS */ @@ -66,18 +68,14 @@ SYM_FUNC_START(loongarch_suspend_enter) la.pcrel a0, loongarch_wakeup_start la.pcrel t0, loongarch_suspend_addr ld.d t0, t0, 0 - jirl a0, t0, 0 /* Call BIOS's STR sleep routine */ + jirl ra, t0, 0 /* Call BIOS's STR sleep routine */ /* * This is where we return upon wakeup. * Reload all of the registers and return. */ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) - li.d t0, CSR_DMW0_INIT # UC, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN1 - + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 /* Enable PG */ @@ -86,7 +84,7 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) la.pcrel t0, acpi_saved_sp ld.d sp, t0, 0 + SETUP_WAKEUP - addi.d sp, sp, PT_SIZE jr ra SYM_FUNC_END(loongarch_suspend_enter) diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index f597cd08a96b..fdde1bcd4e26 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -1,14 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Objects to go into the VDSO. -KASAN_SANITIZE := n -UBSAN_SANITIZE := n -KCOV_INSTRUMENT := n - # Include the generic Makefile to check the built vdso. include $(srctree)/lib/vdso/Makefile -obj-vdso-y := elf.o vgetcpu.o vgettimeofday.o sigreturn.o +obj-vdso-y := elf.o vgetcpu.o vgettimeofday.o vgetrandom.o \ + vgetrandom-chacha.o sigreturn.o # Common compiler flags between ABIs. ccflags-vdso := \ @@ -22,7 +19,7 @@ ccflags-vdso := \ cflags-vdso := $(ccflags-vdso) \ -isystem $(shell $(CC) -print-file-name=include) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ - -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \ + -std=gnu11 -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) @@ -33,13 +30,15 @@ ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) endif +ifneq ($(c-getrandom-y),) + CFLAGS_vgetrandom.o += -include $(c-getrandom-y) +endif + # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ $(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \ --hash-style=sysv --build-id -T -GCOV_PROFILE := n - # # Shared build commands. # @@ -51,7 +50,7 @@ quiet_cmd_vdsoas_o_S = AS $@ cmd_vdsoas_o_S = $(CC) $(a_flags) -c -o $@ $< # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/loongarch/vdso/vdso.lds.S b/arch/loongarch/vdso/vdso.lds.S index 56ad855896de..160cfaef2de4 100644 --- a/arch/loongarch/vdso/vdso.lds.S +++ b/arch/loongarch/vdso/vdso.lds.S @@ -3,6 +3,8 @@ * Author: Huacai Chen <chenhuacai@loongson.cn> * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <asm/page.h> +#include <generated/asm-offsets.h> OUTPUT_FORMAT("elf64-loongarch", "elf64-loongarch", "elf64-loongarch") @@ -10,7 +12,11 @@ OUTPUT_ARCH(loongarch) SECTIONS { - PROVIDE(_start = .); + PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif + PROVIDE(_loongarch_data = _vdso_data + 2 * PAGE_SIZE); . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -62,6 +68,7 @@ VERSION __vdso_clock_getres; __vdso_clock_gettime; __vdso_gettimeofday; + __vdso_getrandom; __vdso_rt_sigreturn; local: *; }; diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c index 9e445be39763..0db51258b2a7 100644 --- a/arch/loongarch/vdso/vgetcpu.c +++ b/arch/loongarch/vdso/vgetcpu.c @@ -21,7 +21,7 @@ static __always_inline int read_cpu_id(void) static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void) { - return (struct vdso_pcpu_data *)(get_vdso_data() + VVAR_LOONGARCH_PAGES_START * PAGE_SIZE); + return _loongarch_data.pdata; } extern diff --git a/arch/loongarch/vdso/vgetrandom-chacha.S b/arch/loongarch/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..c2733e6c3a8d --- /dev/null +++ b/arch/loongarch/vdso/vgetrandom-chacha.S @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + */ + +#include <asm/asm.h> +#include <asm/regdef.h> +#include <linux/linkage.h> + +.text + +.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3 + \op \d0, \d0, \s0 + \op \d1, \d1, \s1 + \op \d2, \d2, \s2 + \op \d3, \d3, \s3 +.endm + +/* + * Very basic LoongArch implementation of ChaCha20. Produces a given positive + * number of blocks of output with a nonce of 0, taking an input key and + * 8-byte counter. Importantly does not spill to the stack. Its arguments + * are: + * + * a0: output bytes + * a1: 32-byte key input + * a2: 8-byte counter input/output + * a3: number of 64-byte blocks to write to output + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) + +/* We don't need a frame pointer */ +#define s9 fp + +#define output a0 +#define key a1 +#define counter a2 +#define nblocks a3 +#define i a4 +#define state0 s0 +#define state1 s1 +#define state2 s2 +#define state3 s3 +#define state4 s4 +#define state5 s5 +#define state6 s6 +#define state7 s7 +#define state8 s8 +#define state9 s9 +#define state10 a5 +#define state11 a6 +#define state12 a7 +#define state13 t0 +#define state14 t1 +#define state15 t2 +#define cnt_lo t3 +#define cnt_hi t4 +#define copy0 t5 +#define copy1 t6 +#define copy2 t7 + +/* Reuse i as copy3 */ +#define copy3 i + +/* Packs to be used with OP_4REG */ +#define line0 state0, state1, state2, state3 +#define line1 state4, state5, state6, state7 +#define line2 state8, state9, state10, state11 +#define line3 state12, state13, state14, state15 + +#define line1_perm state5, state6, state7, state4 +#define line2_perm state10, state11, state8, state9 +#define line3_perm state15, state12, state13, state14 + +#define copy copy0, copy1, copy2, copy3 + +#define _16 16, 16, 16, 16 +#define _20 20, 20, 20, 20 +#define _24 24, 24, 24, 24 +#define _25 25, 25, 25, 25 + + /* + * The ABI requires s0-s9 saved, and sp aligned to 16-byte. + * This does not violate the stack-less requirement: no sensitive data + * is spilled onto the stack. + */ + PTR_ADDI sp, sp, (-SZREG * 10) & STACK_ALIGN + REG_S s0, sp, 0 + REG_S s1, sp, SZREG + REG_S s2, sp, SZREG * 2 + REG_S s3, sp, SZREG * 3 + REG_S s4, sp, SZREG * 4 + REG_S s5, sp, SZREG * 5 + REG_S s6, sp, SZREG * 6 + REG_S s7, sp, SZREG * 7 + REG_S s8, sp, SZREG * 8 + REG_S s9, sp, SZREG * 9 + + li.w copy0, 0x61707865 + li.w copy1, 0x3320646e + li.w copy2, 0x79622d32 + + ld.w cnt_lo, counter, 0 + ld.w cnt_hi, counter, 4 + +.Lblock: + /* state[0,1,2,3] = "expand 32-byte k" */ + move state0, copy0 + move state1, copy1 + move state2, copy2 + li.w state3, 0x6b206574 + + /* state[4,5,..,11] = key */ + ld.w state4, key, 0 + ld.w state5, key, 4 + ld.w state6, key, 8 + ld.w state7, key, 12 + ld.w state8, key, 16 + ld.w state9, key, 20 + ld.w state10, key, 24 + ld.w state11, key, 28 + + /* state[12,13] = counter */ + move state12, cnt_lo + move state13, cnt_hi + + /* state[14,15] = 0 */ + move state14, zero + move state15, zero + + li.w i, 10 +.Lpermute: + /* odd round */ + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _16 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _20 + + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _24 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _25 + + /* even round */ + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _16 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _20 + + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _24 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _25 + + addi.w i, i, -1 + bnez i, .Lpermute + + /* + * copy[3] = "expa", materialize it here because copy[3] shares the + * same register with i which just became dead. + */ + li.w copy3, 0x6b206574 + + /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */ + OP_4REG add.w line0, copy + st.w state0, output, 0 + st.w state1, output, 4 + st.w state2, output, 8 + st.w state3, output, 12 + + /* from now on state[0,1,2,3] are scratch registers */ + + /* state[0,1,2,3] = lo32(key) */ + ld.w state0, key, 0 + ld.w state1, key, 4 + ld.w state2, key, 8 + ld.w state3, key, 12 + + /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */ + OP_4REG add.w line1, line0 + st.w state4, output, 16 + st.w state5, output, 20 + st.w state6, output, 24 + st.w state7, output, 28 + + /* state[0,1,2,3] = hi32(key) */ + ld.w state0, key, 16 + ld.w state1, key, 20 + ld.w state2, key, 24 + ld.w state3, key, 28 + + /* output[8,9,10,11] = state[0,1,2,3] + state[8,9,10,11] */ + OP_4REG add.w line2, line0 + st.w state8, output, 32 + st.w state9, output, 36 + st.w state10, output, 40 + st.w state11, output, 44 + + /* output[12,13,14,15] = state[12,13,14,15] + [cnt_lo, cnt_hi, 0, 0] */ + add.w state12, state12, cnt_lo + add.w state13, state13, cnt_hi + st.w state12, output, 48 + st.w state13, output, 52 + st.w state14, output, 56 + st.w state15, output, 60 + + /* ++counter */ + addi.w cnt_lo, cnt_lo, 1 + sltui state0, cnt_lo, 1 + add.w cnt_hi, cnt_hi, state0 + + /* output += 64 */ + PTR_ADDI output, output, 64 + /* --nblocks */ + PTR_ADDI nblocks, nblocks, -1 + bnez nblocks, .Lblock + + /* counter = [cnt_lo, cnt_hi] */ + st.w cnt_lo, counter, 0 + st.w cnt_hi, counter, 4 + + /* + * Zero out the potentially sensitive regs, in case nothing uses these + * again. As at now copy[0,1,2,3] just contains "expand 32-byte k" and + * state[0,...,9] are s0-s9 those we'll restore in the epilogue, so we + * only need to zero state[11,...,15]. + */ + move state10, zero + move state11, zero + move state12, zero + move state13, zero + move state14, zero + move state15, zero + + REG_L s0, sp, 0 + REG_L s1, sp, SZREG + REG_L s2, sp, SZREG * 2 + REG_L s3, sp, SZREG * 3 + REG_L s4, sp, SZREG * 4 + REG_L s5, sp, SZREG * 5 + REG_L s6, sp, SZREG * 6 + REG_L s7, sp, SZREG * 7 + REG_L s8, sp, SZREG * 8 + REG_L s9, sp, SZREG * 9 + PTR_ADDI sp, sp, -((-SZREG * 10) & STACK_ALIGN) + + jr ra +SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/loongarch/vdso/vgetrandom.c b/arch/loongarch/vdso/vgetrandom.c new file mode 100644 index 000000000000..d5f258ac4a36 --- /dev/null +++ b/arch/loongarch/vdso/vgetrandom.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + */ +#include <linux/types.h> + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); +} |