diff --git a/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml new file mode 100644 index 000000000000..a8d40c766dcd --- /dev/null +++ b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/bus/microsoft,vmbus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microsoft Hyper-V VMBus + +maintainers: + - Saurabh Sengar + +description: + VMBus is a software bus that implement the protocols for communication + between the root or host OS and guest OSs (virtual machines). + +properties: + compatible: + const: microsoft,vmbus + + ranges: true + + '#address-cells': + const: 2 + + '#size-cells': + const: 1 + +required: + - compatible + - ranges + - '#address-cells' + - '#size-cells' + +additionalProperties: false + +examples: + - | + soc { + #address-cells = <2>; + #size-cells = <1>; + bus { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges; + + vmbus@ff0000000 { + compatible = "microsoft,vmbus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0x0f 0xf0000000 0x0f 0xf0000000 0x10000000>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mips/loongson/devices.yaml b/Documentation/devicetree/bindings/mips/loongson/devices.yaml index f13ce386f42c..099e40e1482d 100644 --- a/Documentation/devicetree/bindings/mips/loongson/devices.yaml +++ b/Documentation/devicetree/bindings/mips/loongson/devices.yaml @@ -37,6 +37,18 @@ properties: items: - const: loongson,loongson64v-4core-virtio + - description: LS1B based boards + items: + - enum: + - loongson,lsgz-1b-dev + - const: loongson,ls1b + + - description: LS1C based boards + items: + - enum: + - loongmasses,smartloong-1c + - const: loongson,ls1c + additionalProperties: true ... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 72c0f5dcef43..82d39ab0231b 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -777,6 +777,8 @@ patternProperties: description: Lontium Semiconductor Corporation "^loongson,.*": description: Loongson Technology Corporation Limited + "^loongmasses,.*": + description: Nanjing Loongmasses Ltd. "^lsi,.*": description: LSI Corp. (LSI Logic) "^lwn,.*": diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index 5202186728b4..e22621f4af0b 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -160,7 +160,6 @@ directory name found in the arch/ directory. But some architectures such as x86 and sparc have aliases. - x86: i386 for 32 bit, x86_64 for 64 bit -- sh: sh for 32 bit, sh64 for 64 bit - sparc: sparc32 for 32 bit, sparc64 for 64 bit CROSS_COMPILE diff --git a/Documentation/scheduler/sched-arch.rst b/Documentation/scheduler/sched-arch.rst index 0eaec669790a..505cd27f9a92 100644 --- a/Documentation/scheduler/sched-arch.rst +++ b/Documentation/scheduler/sched-arch.rst @@ -70,7 +70,5 @@ Possible arch problems I found (and either tried to fix or didn't): ia64 - is safe_halt call racy vs interrupts? (does it sleep?) (See #4a) -sh64 - Is sleeping racy vs interrupts? (See #4a) - sparc - IRQs on at this point(?), change local_irq_save to _disable. - TODO: needs secondary CPUs to disable preempt (See #1) diff --git a/Documentation/translations/zh_CN/scheduler/sched-arch.rst b/Documentation/translations/zh_CN/scheduler/sched-arch.rst index 754a15c6b60f..ce3f39d9b3cb 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-arch.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-arch.rst @@ -70,7 +70,5 @@ arch/x86/kernel/process.c有轮询和睡眠空闲函数的例子。 ia64 - safe_halt的调用与中断相比，是否很荒谬？ (它睡眠了吗) (参考 #4a) -sh64 - 睡眠与中断相比，是否很荒谬？ (参考 #4a) - sparc - 在这一点上，IRQ是开着的（？），把local_irq_save改为_disable。 - 待办事项: 需要第二个CPU来禁用抢占 (参考 #1) diff --git a/MAINTAINERS b/MAINTAINERS index e310d8576255..2bbece504f51 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9588,6 +9588,7 @@ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git F: Documentation/ABI/stable/sysfs-bus-vmbus F: Documentation/ABI/testing/debugfs-hyperv +F: Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml F: Documentation/virt/hyperv F: Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst F: arch/arm64/hyperv @@ -22219,6 +22220,7 @@ F: include/uapi/linux/virtio_console.h VIRTIO CORE AND NET DRIVERS M: "Michael S. Tsirkin" M: Jason Wang +R: Xuan Zhuo L: virtualization@lists.linux-foundation.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-vdpa @@ -22232,6 +22234,7 @@ F: drivers/vdpa/ F: drivers/virtio/ F: include/linux/vdpa.h F: include/linux/virtio*.h +F: include/linux/vringh.h F: include/uapi/linux/virtio_*.h F: tools/virtio/ diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index d8a509c5d5bd..20218876bef2 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -40,27 +40,11 @@ static struct ctl_table ctl_isa_vars[4] = { static struct ctl_table_header *isa_sysctl_header; -static struct ctl_table ctl_isa[2] = { - { - .procname = "isa", - .mode = 0555, - .child = ctl_isa_vars, - }, {} -}; - -static struct ctl_table ctl_bus[2] = { - { - .procname = "bus", - .mode = 0555, - .child = ctl_isa, - }, {} -}; - void __init register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int portshift) { isa_membase = membase; isa_portbase = portbase; isa_portshift = portshift; - isa_sysctl_header = register_sysctl_table(ctl_bus); + isa_sysctl_header = register_sysctl("bus/isa", ctl_isa_vars); } diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index 2df115d0e210..b60259daed1b 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -332,22 +332,9 @@ static struct ctl_table alignment_tbl[5] = { {} }; -static struct ctl_table sysctl_table[2] = { - { - .procname = "csky_alignment", - .mode = 0555, - .child = alignment_tbl}, - {} -}; - -static struct ctl_path sysctl_path[2] = { - {.procname = "csky"}, - {} -}; - static int __init csky_alignment_init(void) { - register_sysctl_paths(sysctl_path, sysctl_table); + register_sysctl_init("csky/csky_alignment", alignment_tbl); return 0; } diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 76730f34685c..88b3ce3e66cd 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -234,15 +234,6 @@ static struct ctl_table kdump_ctl_table[] = { }, { } }; - -static struct ctl_table sys_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kdump_ctl_table, - }, - { } -}; #endif static int @@ -257,7 +248,7 @@ machine_crash_setup(void) if((ret = register_die_notifier(&kdump_init_notifier_nb)) != 0) return ret; #ifdef CONFIG_SYSCTL - register_sysctl_table(sys_table); + register_sysctl("kernel", kdump_ctl_table); #endif return 0; } diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 5d04438ee12e..caad195ba5c1 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -29,7 +29,6 @@ platform-$(CONFIG_SGI_IP30) += sgi-ip30/ platform-$(CONFIG_SGI_IP32) += sgi-ip32/ platform-$(CONFIG_SIBYTE_BCM112X) += sibyte/ platform-$(CONFIG_SIBYTE_SB1250) += sibyte/ -platform-$(CONFIG_SIBYTE_BCM1x55) += sibyte/ platform-$(CONFIG_SIBYTE_BCM1x80) += sibyte/ platform-$(CONFIG_SNI_RM) += sni/ platform-$(CONFIG_MACH_TX49XX) += txx9/ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 916af9cbac65..cd692acc386b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,7 +16,6 @@ config MIPS select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_KEEP_MEMBLOCK - select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT select ARCH_USE_MEMTEST @@ -113,7 +112,6 @@ config MACH_INGENIC select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_ZBOOT select DMA_NONCOHERENT - select ARCH_HAS_SYNC_DMA_FOR_CPU select IRQ_MIPS_CPU select PINCTRL select GPIOLIB @@ -132,7 +130,6 @@ choice config MIPS_GENERIC_KERNEL bool "Generic board-agnostic MIPS kernel" - select ARCH_HAS_SETUP_DMA_OPS select MIPS_GENERIC select BOOT_RAW select BUILTIN_DTB @@ -488,7 +485,6 @@ config MACH_LOONGSON64 select BOARD_SCACHE select CSRC_R4K select CEVT_R4K - select CPU_HAS_WB select FORCE_PCI select ISA select I8259 @@ -565,7 +561,6 @@ config MIPS_MALTA select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_MICROMIPS select SYS_SUPPORTS_MIPS16 - select SYS_SUPPORTS_MIPS_CMP select SYS_SUPPORTS_MIPS_CPS select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_RELOCATABLE @@ -793,24 +788,6 @@ config SGI_IP32 help If you want this kernel to run on SGI O2 workstation, say Y here. -config SIBYTE_CRHINE - bool "Sibyte BCM91120C-CRhine" - select BOOT_ELF32 - select SIBYTE_BCM1120 - select SWAP_IO_SPACE - select SYS_HAS_CPU_SB1 - select SYS_SUPPORTS_BIG_ENDIAN - select SYS_SUPPORTS_LITTLE_ENDIAN - -config SIBYTE_CARMEL - bool "Sibyte BCM91120x-Carmel" - select BOOT_ELF32 - select SIBYTE_BCM1120 - select SWAP_IO_SPACE - select SYS_HAS_CPU_SB1 - select SYS_SUPPORTS_BIG_ENDIAN - select SYS_SUPPORTS_LITTLE_ENDIAN - config SIBYTE_CRHONE bool "Sibyte BCM91125C-CRhone" select BOOT_ELF32 @@ -824,7 +801,7 @@ config SIBYTE_CRHONE config SIBYTE_RHONE bool "Sibyte BCM91125E-Rhone" select BOOT_ELF32 - select SIBYTE_BCM1125H + select SIBYTE_SB1250 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 select SYS_SUPPORTS_BIG_ENDIAN @@ -1075,7 +1052,7 @@ config FW_CFE bool config ARCH_SUPPORTS_UPROBES - bool + def_bool y config DMA_NONCOHERENT bool @@ -1086,8 +1063,10 @@ config DMA_NONCOHERENT # by pgprot_writcombine can be mixed, and the latter sometimes provides # significant advantages. # + select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_DMA_WRITE_COMBINE select ARCH_HAS_DMA_PREP_COHERENT + select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_DMA_SET_UNCACHED select DMA_NONCOHERENT_MMAP @@ -1181,12 +1160,6 @@ config SYS_SUPPORTS_LITTLE_ENDIAN config MIPS_HUGE_TLB_SUPPORT def_bool HUGETLB_PAGE || TRANSPARENT_HUGEPAGE -config IRQ_MSP_SLP - bool - -config IRQ_MSP_CIC - bool - config IRQ_TXX9 bool @@ -1364,7 +1337,6 @@ config CPU_LOONGSON2F bool "Loongson 2F" depends on SYS_HAS_CPU_LOONGSON2F select CPU_LOONGSON2EF - select GPIOLIB help The Loongson 2F processor implements the MIPS III instruction set with many extensions. @@ -1786,7 +1758,6 @@ config CPU_LOONGSON2EF select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES - select ARCH_HAS_PHYS_TO_DMA config CPU_LOONGSON32 bool @@ -1851,11 +1822,9 @@ config SYS_HAS_CPU_MIPS32_R3_5 config SYS_HAS_CPU_MIPS32_R5 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS32_R6 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS64_R1 bool @@ -1865,15 +1834,12 @@ config SYS_HAS_CPU_MIPS64_R2 config SYS_HAS_CPU_MIPS64_R5 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS64_R6 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_P5600 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_R3000 bool @@ -1898,7 +1864,6 @@ config SYS_HAS_CPU_NEVADA config SYS_HAS_CPU_R10000 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_RM7000 bool @@ -1927,7 +1892,6 @@ config SYS_HAS_CPU_BMIPS4380 config SYS_HAS_CPU_BMIPS5000 bool select SYS_HAS_CPU_BMIPS - select ARCH_HAS_SYNC_DMA_FOR_CPU # # CPU may reorder R->R, R->W, W->R, W->W @@ -2298,15 +2262,10 @@ config MIPS_VPE_LOADER Includes a loader for loading an elf relocatable object onto another VPE and running it. -config MIPS_VPE_LOADER_CMP - bool - default "y" - depends on MIPS_VPE_LOADER && MIPS_CMP - config MIPS_VPE_LOADER_MT bool default "y" - depends on MIPS_VPE_LOADER && !MIPS_CMP + depends on MIPS_VPE_LOADER config MIPS_VPE_LOADER_TOM bool "Load VPE program into memory hidden from linux" @@ -2322,31 +2281,10 @@ config MIPS_VPE_APSP_API bool "Enable support for AP/SP API (RTLX)" depends on MIPS_VPE_LOADER -config MIPS_VPE_APSP_API_CMP - bool - default "y" - depends on MIPS_VPE_APSP_API && MIPS_CMP - config MIPS_VPE_APSP_API_MT bool default "y" - depends on MIPS_VPE_APSP_API && !MIPS_CMP - -config MIPS_CMP - bool "MIPS CMP framework support (DEPRECATED)" - depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select SMP - select SYNC_R4K - select SYS_SUPPORTS_SMP - select WEAK_ORDERING - default n - help - Select this if you are using a bootloader which implements the "CMP - framework" protocol (ie. YAMON) and want your kernel to make use of - its ability to start secondary CPUs. - - Unless you have a specific need, you should use CONFIG_MIPS_CPS - instead of this. + depends on MIPS_VPE_APSP_API config MIPS_CPS bool "MIPS Coherent Processing System support" @@ -2802,9 +2740,6 @@ config HOTPLUG_CPU config SMP_UP bool -config SYS_SUPPORTS_MIPS_CMP - bool - config SYS_SUPPORTS_MIPS_CPS bool diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 04e46ec24319..a7a4ee66a9d3 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -181,9 +181,47 @@ endif cflags-$(CONFIG_CAVIUM_CN63XXP1) += -Wa,-mfix-cn63xxp1 cflags-$(CONFIG_CPU_BMIPS) += -march=mips32 -Wa,-mips32 -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -Wa,--trap +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-mno-loongson-mmi) +ifdef CONFIG_CPU_LOONGSON64 +cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap +cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a +cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2 +endif +cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-mno-loongson-mmi) + cflags-$(CONFIG_CPU_R4000_WORKAROUNDS) += $(call cc-option,-mfix-r4000,) cflags-$(CONFIG_CPU_R4400_WORKAROUNDS) += $(call cc-option,-mfix-r4400,) cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS) += $(call cc-option,-mno-daddi,) +ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS +cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa,-mfix-loongson2f-nop +cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa,-mfix-loongson2f-jump +endif + +# +# Some versions of binutils, not currently mainline as of 2019/02/04, support +# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction +# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a +# description). +# +# We disable this in order to prevent the assembler meddling with the +# instruction that labels refer to, ie. if we label an ll instruction: +# +# 1: ll v0, 0(a0) +# +# ...then with the assembler fix applied the label may actually point at a sync +# instruction inserted by the assembler, and if we were using the label in an +# exception table the table would no longer contain the address of the ll +# instruction. +# +# Avoid this by explicitly disabling that assembler behaviour. If upstream +# binutils does not merge support for the flag then we can revisit & remove +# this later - for now it ensures vendor toolchains don't cause problems. +# +cflags-$(CONFIG_CPU_LOONGSON64) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) # For smartmips configurations, there are hundreds of warnings due to ISA overrides # in assembly and header files. smartmips is only supported for MIPS32r1 onwards diff --git a/arch/mips/ath79/Kconfig b/arch/mips/ath79/Kconfig index 7367416642cb..04154128c4de 100644 --- a/arch/mips/ath79/Kconfig +++ b/arch/mips/ath79/Kconfig @@ -29,20 +29,4 @@ config SOC_QCA955X config PCI_AR724X def_bool n -config ATH79_DEV_GPIO_BUTTONS - def_bool n - -config ATH79_DEV_LEDS_GPIO - def_bool n - -config ATH79_DEV_SPI - def_bool n - -config ATH79_DEV_USB - def_bool n - -config ATH79_DEV_WMAC - depends on (SOC_AR913X || SOC_AR933X || SOC_AR934X || SOC_QCA955X) - def_bool n - endif diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c index 90fb48b046c0..b487f687f62d 100644 --- a/arch/mips/bcm47xx/board.c +++ b/arch/mips/bcm47xx/board.c @@ -193,6 +193,7 @@ struct bcm47xx_board_type_list1 bcm47xx_board_list_board_id[] __initconst = { /* boardtype, boardnum, boardrev */ static const struct bcm47xx_board_type_list3 bcm47xx_board_list_board[] __initconst = { + {{BCM47XX_BOARD_HUAWEI_B593U_12, "Huawei B593u-12"}, "0x053d", "1234", "0x1301"}, {{BCM47XX_BOARD_HUAWEI_E970, "Huawei E970"}, "0x048e", "0x5347", "0x11"}, {{BCM47XX_BOARD_PHICOMM_M1, "Phicomm M1"}, "0x0590", "80", "0x1104"}, {{BCM47XX_BOARD_ZTE_H218N, "ZTE H218N"}, "0x053d", "1234", "0x1305"}, diff --git a/arch/mips/bcm47xx/leds.c b/arch/mips/bcm47xx/leds.c index 8e257d0896d2..64e37505b9b4 100644 --- a/arch/mips/bcm47xx/leds.c +++ b/arch/mips/bcm47xx/leds.c @@ -222,6 +222,11 @@ bcm47xx_leds_dlink_dir330[] __initconst = { /* Huawei */ +static const struct gpio_led +bcm47xx_leds_huawei_b593u_12[] __initconst = { + BCM47XX_GPIO_LED(5, "blue", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF), +}; + static const struct gpio_led bcm47xx_leds_huawei_e970[] __initconst = { BCM47XX_GPIO_LED(0, "unk", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF), @@ -672,6 +677,9 @@ void __init bcm47xx_leds_register(void) bcm47xx_set_pdata(bcm47xx_leds_dlink_dir330); break; + case BCM47XX_BOARD_HUAWEI_B593U_12: + bcm47xx_set_pdata(bcm47xx_leds_huawei_b593u_12); + break; case BCM47XX_BOARD_HUAWEI_E970: bcm47xx_set_pdata(bcm47xx_leds_huawei_e970); break; diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index c1899f109e19..450e979ef5d9 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -14,7 +14,8 @@ config CAVIUM_CN63XXP1 config CAVIUM_OCTEON_CVMSEG_SIZE int "Number of L1 cache lines reserved for CVMSEG memory" range 0 54 - default 1 + default 0 if !CAVIUM_OCTEON_SOC + default 1 if CAVIUM_OCTEON_SOC help CVMSEG LM is a segment that accesses portions of the dcache as a local memory; the larger CVMSEG is, the smaller the cache is. diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index fd8043f6ff8a..8425a6b38aa2 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2290,7 +2290,7 @@ static irqreturn_t octeon_irq_cib_handler(int my_irq, void *data) static int __init octeon_irq_init_cib(struct device_node *ciu_node, struct device_node *parent) { - const __be32 *addr; + struct resource res; u32 val; struct octeon_irq_cib_host_data *host_data; int parent_irq; @@ -2309,21 +2309,19 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node, return -ENOMEM; raw_spin_lock_init(&host_data->lock); - addr = of_get_address(ciu_node, 0, NULL, NULL); - if (!addr) { + r = of_address_to_resource(ciu_node, 0, &res); + if (r) { pr_err("ERROR: Couldn't acquire reg(0) %pOFn\n", ciu_node); - return -EINVAL; + return r; } - host_data->raw_reg = (u64)phys_to_virt( - of_translate_address(ciu_node, addr)); + host_data->raw_reg = (u64)phys_to_virt(res.start); - addr = of_get_address(ciu_node, 1, NULL, NULL); - if (!addr) { + r = of_address_to_resource(ciu_node, 1, &res); + if (r) { pr_err("ERROR: Couldn't acquire reg(1) %pOFn\n", ciu_node); - return -EINVAL; + return r; } - host_data->en_reg = (u64)phys_to_virt( - of_translate_address(ciu_node, addr)); + host_data->en_reg = (u64)phys_to_virt(res.start); r = of_property_read_u32(ciu_node, "cavium,max-bits", &val); if (r) { @@ -2874,11 +2872,11 @@ static struct irq_chip octeon_irq_chip_ciu3_mbox = { static int __init octeon_irq_init_ciu3(struct device_node *ciu_node, struct device_node *parent) { - int i; + int i, ret; int node; struct irq_domain *domain; struct octeon_ciu3_info *ciu3_info; - const __be32 *zero_addr; + struct resource res; u64 base_addr; union cvmx_ciu3_const consts; @@ -2888,14 +2886,11 @@ static int __init octeon_irq_init_ciu3(struct device_node *ciu_node, if (!ciu3_info) return -ENOMEM; - zero_addr = of_get_address(ciu_node, 0, NULL, NULL); - if (WARN_ON(!zero_addr)) - return -EINVAL; + ret = of_address_to_resource(ciu_node, 0, &res); + if (WARN_ON(ret)) + return ret; - base_addr = of_translate_address(ciu_node, zero_addr); - base_addr = (u64)phys_to_virt(base_addr); - - ciu3_info->ciu3_addr = base_addr; + ciu3_info->ciu3_addr = base_addr = (u64)phys_to_virt(res.start); ciu3_info->node = node; consts.u64 = cvmx_read_csr(base_addr + CIU3_CONST); diff --git a/arch/mips/configs/generic/board-virt.config b/arch/mips/configs/generic/board-virt.config new file mode 100644 index 000000000000..5594f9e5c3a8 --- /dev/null +++ b/arch/mips/configs/generic/board-virt.config @@ -0,0 +1,38 @@ +CONFIG_COMMON_CLK=y + +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIC=y + +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCI_HOST_GENERIC=y + +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +CONFIG_SYSCON_REBOOT_MODE=y + +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y + +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y + +CONFIG_MTD=y +CONFIG_MTD_CFI=y + +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_XHCI_HCD=y + +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_NET=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y diff --git a/arch/mips/fw/lib/cmdline.c b/arch/mips/fw/lib/cmdline.c index f24cbb4a39b5..892765b742bb 100644 --- a/arch/mips/fw/lib/cmdline.c +++ b/arch/mips/fw/lib/cmdline.c @@ -53,7 +53,7 @@ char *fw_getenv(char *envname) { char *result = NULL; - if (_fw_envp != NULL) { + if (_fw_envp != NULL && fw_envp(0) != NULL) { /* * Return a pointer to the given environment variable. * YAMON uses "name", "value" pairs, while U-Boot uses diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 1c4438f3f2ab..067a635d3bc8 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -45,12 +45,12 @@ #endif #ifdef CONFIG_CPU_HAS_DIEI - .macro local_irq_enable reg=t0 + .macro local_irq_enable ei irq_enable_hazard .endm - .macro local_irq_disable reg=t0 + .macro local_irq_disable di irq_disable_hazard .endm diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d72dc6e1cf3c..653f78f3a685 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -24,13 +24,7 @@ extern void check_bugs64_early(void); extern void check_bugs32(void); extern void check_bugs64(void); -static inline void check_bugs_early(void) -{ - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64_early(); -} - -static inline void check_bugs(void) +static inline void __init check_bugs(void) { unsigned int cpu = smp_processor_id(); diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h index 29187e12b861..3424a7908c0f 100644 --- a/arch/mips/include/asm/cache.h +++ b/arch/mips/include/asm/cache.h @@ -16,4 +16,6 @@ #define __read_mostly __section(".data..read_mostly") +extern void cache_noop(void); + #endif /* _ASM_CACHE_H */ diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index b3dc9c589442..d8d3f80f9fc0 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -110,7 +110,6 @@ extern void copy_from_user_page(struct vm_area_struct *vma, unsigned long len); extern void (*flush_icache_all)(void); -extern void (*local_flush_data_cache_page)(void * addr); extern void (*flush_data_cache_page)(unsigned long addr); /* Run kernel code uncached, useful for cache probing functions. */ diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c0983130a44c..51a1737b03d0 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -118,10 +118,27 @@ #define cpu_has_3k_cache __isa_lt_and_opt(1, MIPS_CPU_3K_CACHE) #endif #ifndef cpu_has_4k_cache -#define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) +#define cpu_has_4k_cache __opt(MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache -#define cpu_has_octeon_cache 0 +#define cpu_has_octeon_cache \ +({ \ + int __res; \ + \ + switch (current_cpu_type()) { \ + case CPU_CAVIUM_OCTEON: \ + case CPU_CAVIUM_OCTEON_PLUS: \ + case CPU_CAVIUM_OCTEON2: \ + case CPU_CAVIUM_OCTEON3: \ + __res = 1; \ + break; \ + \ + default: \ + __res = 0; \ + } \ + \ + __res; \ +}) #endif /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work. */ #ifndef cpu_has_fpu diff --git a/arch/mips/include/asm/ide.h b/arch/mips/include/asm/ide.h deleted file mode 100644 index bb674c3b0303..000000000000 --- a/arch/mips/include/asm/ide.h +++ /dev/null @@ -1,13 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * This file contains the MIPS architecture specific IDE code. - */ -#ifndef __ASM_IDE_H -#define __ASM_IDE_H - -#include - -#endif /* __ASM_IDE_H */ diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index e6d5ccaa309e..cc28d207a061 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -210,7 +210,7 @@ void iounmap(const volatile void __iomem *addr); #define ioremap_wc(offset, size) \ ioremap_prot((offset), (size), boot_cpu_data.writecombine) -#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON64) +#if defined(CONFIG_CPU_CAVIUM_OCTEON) #define war_io_reorder_wmb() wmb() #else #define war_io_reorder_wmb() barrier() diff --git a/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h b/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h index 3c401f11655e..4bd8c86ec6c3 100644 --- a/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h +++ b/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h @@ -53,6 +53,7 @@ enum bcm47xx_board { BCM47XX_BOARD_DLINK_DIR130, BCM47XX_BOARD_DLINK_DIR330, + BCM47XX_BOARD_HUAWEI_B593U_12, BCM47XX_BOARD_HUAWEI_E970, BCM47XX_BOARD_LINKSYS_E900V1, diff --git a/arch/mips/include/asm/mach-generic/ide.h b/arch/mips/include/asm/mach-generic/ide.h deleted file mode 100644 index 4ae5fbcb15a5..000000000000 --- a/arch/mips/include/asm/mach-generic/ide.h +++ /dev/null @@ -1,138 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - * - * Copied from i386; many of the especially older MIPS or ISA-based platforms - * are basically identical. Using this file probably implies i8259 PIC - * support in a system but the very least interrupt numbers 0 - 15 need to - * be put aside for legacy devices. - */ -#ifndef __ASM_MACH_GENERIC_IDE_H -#define __ASM_MACH_GENERIC_IDE_H - -#ifdef __KERNEL__ - -#include -#include -#include - -/* MIPS port and memory-mapped I/O string operations. */ -static inline void __ide_flush_prologue(void) -{ -#ifdef CONFIG_SMP - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) - preempt_disable(); -#endif -} - -static inline void __ide_flush_epilogue(void) -{ -#ifdef CONFIG_SMP - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) - preempt_enable(); -#endif -} - -static inline void __ide_flush_dcache_range(unsigned long addr, unsigned long size) -{ - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) { - unsigned long end = addr + size; - - while (addr < end) { - local_flush_data_cache_page((void *)addr); - addr += PAGE_SIZE; - } - } -} - -/* - * insw() and gang might be called with interrupts disabled, so we can't - * send IPIs for flushing due to the potencial of deadlocks, see the comment - * above smp_call_function() in arch/mips/kernel/smp.c. We work around the - * problem by disabling preemption so we know we actually perform the flush - * on the processor that actually has the lines to be flushed which hopefully - * is even better for performance anyway. - */ -static inline void __ide_insw(unsigned long port, void *addr, - unsigned int count) -{ - __ide_flush_prologue(); - insw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_insl(unsigned long port, void *addr, unsigned int count) -{ - __ide_flush_prologue(); - insl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_outsw(unsigned long port, const void *addr, - unsigned long count) -{ - __ide_flush_prologue(); - outsw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_outsl(unsigned long port, const void *addr, - unsigned long count) -{ - __ide_flush_prologue(); - outsl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_insw(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - readsw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_insl(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - readsl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_outsw(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - writesw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_outsl(void __iomem * port, void *addr, u32 count) -{ - __ide_flush_prologue(); - writesl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -/* ide_insw calls insw, not __ide_insw. Why? */ -#undef insw -#undef insl -#undef outsw -#undef outsl -#define insw(port, addr, count) __ide_insw(port, addr, count) -#define insl(port, addr, count) __ide_insl(port, addr, count) -#define outsw(port, addr, count) __ide_outsw(port, addr, count) -#define outsl(port, addr, count) __ide_outsl(port, addr, count) - -#endif /* __KERNEL__ */ - -#endif /* __ASM_MACH_GENERIC_IDE_H */ diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h index 4790cfa190d6..c2e0acb755cd 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h +++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h @@ -94,9 +94,6 @@ extern __iomem void *ltq_cgu_membase; #define LTQ_MPS_BASE_ADDR (KSEG1 + 0x1F107000) #define LTQ_MPS_CHIPID ((u32 *)(LTQ_MPS_BASE_ADDR + 0x0344)) -/* allow booting xrx200 phys */ -int xrx200_gphy_boot(struct device *dev, unsigned int id, dma_addr_t dev_addr); - /* request a non-gpio and set the PIO config */ #define PMU_PPE BIT(13) extern void ltq_pmu_enable(unsigned int module); diff --git a/arch/mips/include/asm/mach-ralink/mt7620.h b/arch/mips/include/asm/mach-ralink/mt7620.h index d51dfad8f543..3e37705ea9cf 100644 --- a/arch/mips/include/asm/mach-ralink/mt7620.h +++ b/arch/mips/include/asm/mach-ralink/mt7620.h @@ -11,7 +11,8 @@ #ifndef _MT7620_REGS_H_ #define _MT7620_REGS_H_ -#define MT7620_SYSC_BASE 0x10000000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define MT7620_SYSC_BASE IOMEM(0x10000000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/include/asm/mach-ralink/rt288x.h b/arch/mips/include/asm/mach-ralink/rt288x.h index 5f213534f0f5..66a999cd1d80 100644 --- a/arch/mips/include/asm/mach-ralink/rt288x.h +++ b/arch/mips/include/asm/mach-ralink/rt288x.h @@ -11,7 +11,8 @@ #ifndef _RT288X_REGS_H_ #define _RT288X_REGS_H_ -#define RT2880_SYSC_BASE 0x00300000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define RT2880_SYSC_BASE IOMEM(0x00300000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/include/asm/mach-ralink/rt305x.h b/arch/mips/include/asm/mach-ralink/rt305x.h index 4d8e8c8d83ce..ef58f7bff957 100644 --- a/arch/mips/include/asm/mach-ralink/rt305x.h +++ b/arch/mips/include/asm/mach-ralink/rt305x.h @@ -43,7 +43,8 @@ static inline int soc_is_rt5350(void) return ralink_soc == RT305X_SOC_RT5350; } -#define RT305X_SYSC_BASE 0x10000000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define RT305X_SYSC_BASE IOMEM(0x10000000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/include/asm/mach-ralink/rt3883.h b/arch/mips/include/asm/mach-ralink/rt3883.h index f250de9c055b..ad25d5e8d2dc 100644 --- a/arch/mips/include/asm/mach-ralink/rt3883.h +++ b/arch/mips/include/asm/mach-ralink/rt3883.h @@ -10,8 +10,10 @@ #include +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) + #define RT3883_SDRAM_BASE 0x00000000 -#define RT3883_SYSC_BASE 0x10000000 +#define RT3883_SYSC_BASE IOMEM(0x10000000) #define RT3883_TIMER_BASE 0x10000100 #define RT3883_INTC_BASE 0x10000200 #define RT3883_MEMC_BASE 0x10000300 diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index 2362842ee2b5..1c576679aa87 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -280,6 +280,7 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val) #define __WRITEABLE (_PAGE_SILENT_WRITE | _PAGE_WRITE | _PAGE_MODIFIED) #define _PAGE_CHG_MASK (_PAGE_ACCESSED | _PAGE_MODIFIED | \ - _PAGE_SOFT_DIRTY | _PFN_MASK | _CACHE_MASK) + _PAGE_SOFT_DIRTY | _PFN_MASK | \ + _CACHE_MASK | _PAGE_SPECIAL) #endif /* _ASM_PGTABLE_BITS_H */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 3fde1ff72bd1..ae2cd37a38f0 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -202,11 +202,13 @@ struct octeon_cop2_state { #define COP2_INIT \ .cp2 = {0,}, +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 struct octeon_cvmseg_state { unsigned long cvmseg[CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE] [cpu_dcache_line_size() / sizeof(unsigned long)]; }; - +#endif #else #define COP2_INIT #endif @@ -263,7 +265,10 @@ struct thread_struct { unsigned long trap_nr; #ifdef CONFIG_CPU_CAVIUM_OCTEON struct octeon_cop2_state cp2 __attribute__ ((__aligned__(128))); +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 struct octeon_cvmseg_state cvmseg __attribute__ ((__aligned__(128))); +#endif #endif struct mips_abi *abi; }; diff --git a/arch/mips/include/asm/rtlx.h b/arch/mips/include/asm/rtlx.h index c1020654876e..a72785b4bbf4 100644 --- a/arch/mips/include/asm/rtlx.h +++ b/arch/mips/include/asm/rtlx.h @@ -81,7 +81,6 @@ struct rtlx_channel { extern struct rtlx_info { unsigned long id; enum rtlx_state state; - int ap_int_pending; /* Status of 0 or 1 for CONFIG_MIPS_CMP only */ struct rtlx_channel channel[RTLX_CHANNELS]; } *rtlx; diff --git a/arch/mips/include/asm/sibyte/board.h b/arch/mips/include/asm/sibyte/board.h index 20fe2f16c97e..03463faa4244 100644 --- a/arch/mips/include/asm/sibyte/board.h +++ b/arch/mips/include/asm/sibyte/board.h @@ -7,7 +7,7 @@ #define _SIBYTE_BOARD_H #if defined(CONFIG_SIBYTE_SWARM) || defined(CONFIG_SIBYTE_CRHONE) || \ - defined(CONFIG_SIBYTE_CRHINE) || defined(CONFIG_SIBYTE_LITTLESUR) + defined(CONFIG_SIBYTE_LITTLESUR) #include #endif @@ -15,10 +15,6 @@ #include #endif -#ifdef CONFIG_SIBYTE_CARMEL -#include -#endif - #ifdef CONFIG_SIBYTE_BIGSUR #include #endif diff --git a/arch/mips/include/asm/sibyte/carmel.h b/arch/mips/include/asm/sibyte/carmel.h deleted file mode 100644 index c6730d7a6392..000000000000 --- a/arch/mips/include/asm/sibyte/carmel.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2002 Broadcom Corporation - */ -#ifndef __ASM_SIBYTE_CARMEL_H -#define __ASM_SIBYTE_CARMEL_H - -#include -#include - -#define SIBYTE_BOARD_NAME "Carmel" - -#define GPIO_PHY_INTERRUPT 2 -#define GPIO_NONMASKABLE_INT 3 -#define GPIO_CF_INSERTED 6 -#define GPIO_MONTEREY_RESET 7 -#define GPIO_QUADUART_INT 8 -#define GPIO_CF_INT 9 -#define GPIO_FPGA_CCLK 10 -#define GPIO_FPGA_DOUT 11 -#define GPIO_FPGA_DIN 12 -#define GPIO_FPGA_PGM 13 -#define GPIO_FPGA_DONE 14 -#define GPIO_FPGA_INIT 15 - -#define LEDS_CS 2 -#define LEDS_PHYS 0x100C0000 -#define MLEDS_CS 3 -#define MLEDS_PHYS 0x100A0000 -#define UART_CS 4 -#define UART_PHYS 0x100D0000 -#define ARAVALI_CS 5 -#define ARAVALI_PHYS 0x11000000 -#define IDE_CS 6 -#define IDE_PHYS 0x100B0000 -#define ARAVALI2_CS 7 -#define ARAVALI2_PHYS 0x100E0000 - -#if defined(CONFIG_SIBYTE_CARMEL) -#define K_GPIO_GB_IDE 9 -#define K_INT_GB_IDE (K_INT_GPIO_0 + K_GPIO_GB_IDE) -#endif - - -#endif /* __ASM_SIBYTE_CARMEL_H */ diff --git a/arch/mips/include/asm/sibyte/swarm.h b/arch/mips/include/asm/sibyte/swarm.h index 947122f487ed..49ea7a645c15 100644 --- a/arch/mips/include/asm/sibyte/swarm.h +++ b/arch/mips/include/asm/sibyte/swarm.h @@ -24,11 +24,6 @@ #define SIBYTE_HAVE_PCMCIA 0 #define SIBYTE_HAVE_IDE 0 #endif -#ifdef CONFIG_SIBYTE_CRHINE -#define SIBYTE_BOARD_NAME "BCM91120C (CRhine)" -#define SIBYTE_HAVE_PCMCIA 0 -#define SIBYTE_HAVE_IDE 0 -#endif /* Generic bus chip selects */ #define LEDS_CS 3 diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 864aea803984..0145bbfb5efb 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -80,22 +80,6 @@ static inline int register_up_smp_ops(void) #endif } -static inline int register_cmp_smp_ops(void) -{ -#ifdef CONFIG_MIPS_CMP - extern const struct plat_smp_ops cmp_smp_ops; - - if (!mips_cm_present()) - return -ENODEV; - - register_smp_ops(&cmp_smp_ops); - - return 0; -#else - return -ENODEV; -#endif -} - static inline int register_vsmp_smp_ops(void) { #ifdef CONFIG_MIPS_MT_SMP diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h index ef7e07829607..61fd4d0aeda4 100644 --- a/arch/mips/include/asm/vpe.h +++ b/arch/mips/include/asm/vpe.h @@ -29,12 +29,8 @@ static inline int aprp_cpu_index(void) { -#ifdef CONFIG_MIPS_CMP - return setup_max_cpus; -#else extern int tclimit; return tclimit; -#endif } enum vpe_state { diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 5d1addac5e28..853a43ee4b44 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -58,16 +58,13 @@ obj-$(CONFIG_CPU_BMIPS) += smp-bmips.o bmips_vec.o bmips_5xxx_init.o obj-$(CONFIG_MIPS_MT) += mips-mt.o obj-$(CONFIG_MIPS_MT_FPAFF) += mips-mt-fpaff.o obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o -obj-$(CONFIG_MIPS_CMP) += smp-cmp.o obj-$(CONFIG_MIPS_CPS) += smp-cps.o cps-vec.o obj-$(CONFIG_MIPS_CPS_NS16550) += cps-vec-ns16550.o obj-$(CONFIG_MIPS_SPRAM) += spram.o obj-$(CONFIG_MIPS_VPE_LOADER) += vpe.o -obj-$(CONFIG_MIPS_VPE_LOADER_CMP) += vpe-cmp.o obj-$(CONFIG_MIPS_VPE_LOADER_MT) += vpe-mt.o obj-$(CONFIG_MIPS_VPE_APSP_API) += rtlx.o -obj-$(CONFIG_MIPS_VPE_APSP_API_CMP) += rtlx-cmp.o obj-$(CONFIG_MIPS_VPE_APSP_API_MT) += rtlx-mt.o obj-$(CONFIG_MIPS_MSC) += irq-msc01.o diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index c4501897b870..40fd4051bb3d 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -306,7 +306,10 @@ void output_octeon_cop2_state_defines(void) OFFSET(OCTEON_CP2_HSH_IVW, octeon_cop2_state, cop2_hsh_ivw); OFFSET(OCTEON_CP2_SHA3, octeon_cop2_state, cop2_sha3); OFFSET(THREAD_CP2, task_struct, thread.cp2); +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 OFFSET(THREAD_CVMSEG, task_struct, thread.cvmseg.cvmseg); +#endif BLANK(); } #endif diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 8ef492da827f..64ecfdac6580 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -116,6 +116,8 @@ not_nmi: li t0, ST0_CU1 | ST0_CU0 | ST0_BEV | STATUS_BITDEPS mtc0 t0, CP0_STATUS + /* We don't know how to do coherence setup on earlier ISA */ +#if MIPS_ISA_REV > 0 /* Skip cache & coherence setup if we're already coherent */ lw s7, GCR_CL_COHERENCE_OFS(s1) bnez s7, 1f @@ -129,6 +131,7 @@ not_nmi: li t0, 0xff sw t0, GCR_CL_COHERENCE_OFS(s1) ehb +#endif /* MIPS_ISA_REV > 0 */ /* Set Kseg0 CCA to that in s0 */ 1: mfc0 t0, CP0_CONFIG @@ -515,6 +518,7 @@ LEAF(mips_cps_boot_vpes) nop END(mips_cps_boot_vpes) +#if MIPS_ISA_REV > 0 LEAF(mips_cps_cache_init) /* * Clear the bits used to index the caches. Note that the architecture @@ -588,6 +592,7 @@ dcache_done: jr ra nop END(mips_cps_cache_init) +#endif /* MIPS_ISA_REV > 0 */ #if defined(CONFIG_MIPS_CPS_PM) && defined(CONFIG_CPU_PM) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 7ddf07f255f3..6d15a398d389 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1602,6 +1602,8 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu) static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu) { decode_configs(c); + /* Octeon has different cache interface */ + c->options &= ~MIPS_CPU_4K_CACHE; switch (c->processor_id & PRID_IMP_MASK) { case PRID_IMP_CAVIUM_CN38XX: case PRID_IMP_CAVIUM_CN31XX: diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index b4f7d950c846..3f00788b0871 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -181,11 +181,16 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cm_core_lock_flags); phys_addr_t __mips_cm_phys_base(void) { - u32 config3 = read_c0_config3(); unsigned long cmgcr; /* Check the CMGCRBase register is implemented */ - if (!(config3 & MIPS_CONF3_CMGCR)) + if (!(read_c0_config() & MIPS_CONF_M)) + return 0; + + if (!(read_c0_config2() & MIPS_CONF_M)) + return 0; + + if (!(read_c0_config3() & MIPS_CONF3_CMGCR)) return 0; /* Read the address from CMGCRBase */ diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index 896080b445c2..9b7c8ab6f08c 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -428,7 +428,6 @@ done_restore: jr ra nop .space 30 * 4, 0 -octeon_mult_save_end: EXPORT(octeon_mult_save_end) END(octeon_mult_save) @@ -448,7 +447,6 @@ octeon_mult_save_end: sd k0, PT_MPL+8(sp) /* PT_MPL+8 has MPL1 */ jr ra sd k1, PT_MPL+16(sp) /* PT_MPL+16 has MPL2 */ -octeon_mult_save2_end: EXPORT(octeon_mult_save2_end) END(octeon_mult_save2) @@ -480,7 +478,6 @@ octeon_mult_save2_end: sd $10, PT_MPL+(4*8)(sp) /* store MPL4 */ jr ra sd $11, PT_MPL+(5*8)(sp) /* store MPL5 */ -octeon_mult_save3_end: EXPORT(octeon_mult_save3_end) END(octeon_mult_save3) .set pop @@ -498,7 +495,6 @@ octeon_mult_save3_end: jr ra nop .space 30 * 4, 0 -octeon_mult_restore_end: EXPORT(octeon_mult_restore_end) END(octeon_mult_restore) @@ -517,7 +513,6 @@ octeon_mult_restore_end: mtp1 v0 /* P1 */ jr ra mtp0 v1 /* P0 */ -octeon_mult_restore2_end: EXPORT(octeon_mult_restore2_end) END(octeon_mult_restore2) @@ -548,7 +543,6 @@ octeon_mult_restore2_end: .word 0x714b000b /* mtp2 $10, $11 restore P2 and P5 */ -octeon_mult_restore3_end: EXPORT(octeon_mult_restore3_end) END(octeon_mult_restore3) .set pop diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c deleted file mode 100644 index d26dcc4b46e7..000000000000 --- a/arch/mips/kernel/rtlx-cmp.c +++ /dev/null @@ -1,122 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2005 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - */ -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -static int major; - -static void rtlx_interrupt(void) -{ - int i; - struct rtlx_info *info; - struct rtlx_info **p = vpe_get_shared(aprp_cpu_index()); - - if (p == NULL || *p == NULL) - return; - - info = *p; - - if (info->ap_int_pending == 1 && smp_processor_id() == 0) { - for (i = 0; i < RTLX_CHANNELS; i++) { - wake_up(&channel_wqs[i].lx_queue); - wake_up(&channel_wqs[i].rt_queue); - } - info->ap_int_pending = 0; - } -} - -void _interrupt_sp(void) -{ - smp_send_reschedule(aprp_cpu_index()); -} - -int __init rtlx_module_init(void) -{ - struct device *dev; - int i, err; - - if (!cpu_has_mipsmt) { - pr_warn("VPE loader: not a MIPS MT capable processor\n"); - return -ENODEV; - } - - if (num_possible_cpus() - aprp_cpu_index() < 1) { - pr_warn("No TCs reserved for AP/SP, not initializing RTLX.\n" - "Pass maxcpus= argument as kernel argument\n"); - - return -ENODEV; - } - - major = register_chrdev(0, RTLX_MODULE_NAME, &rtlx_fops); - if (major < 0) { - pr_err("rtlx_module_init: unable to register device\n"); - return major; - } - - /* initialise the wait queues */ - for (i = 0; i < RTLX_CHANNELS; i++) { - init_waitqueue_head(&channel_wqs[i].rt_queue); - init_waitqueue_head(&channel_wqs[i].lx_queue); - atomic_set(&channel_wqs[i].in_open, 0); - mutex_init(&channel_wqs[i].mutex); - - dev = device_create(mt_class, NULL, MKDEV(major, i), NULL, - "%s%d", RTLX_MODULE_NAME, i); - if (IS_ERR(dev)) { - while (i--) - device_destroy(mt_class, MKDEV(major, i)); - - err = PTR_ERR(dev); - goto out_chrdev; - } - } - - /* set up notifiers */ - rtlx_notify.start = rtlx_starting; - rtlx_notify.stop = rtlx_stopping; - vpe_notify(aprp_cpu_index(), &rtlx_notify); - - if (cpu_has_vint) { - aprp_hook = rtlx_interrupt; - } else { - pr_err("APRP RTLX init on non-vectored-interrupt processor\n"); - err = -ENODEV; - goto out_class; - } - - return 0; - -out_class: - for (i = 0; i < RTLX_CHANNELS; i++) - device_destroy(mt_class, MKDEV(major, i)); -out_chrdev: - unregister_chrdev(major, RTLX_MODULE_NAME); - - return err; -} - -void __exit rtlx_module_exit(void) -{ - int i; - - for (i = 0; i < RTLX_CHANNELS; i++) - device_destroy(mt_class, MKDEV(major, i)); - - unregister_chrdev(major, RTLX_MODULE_NAME); - - aprp_hook = NULL; -} diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index f1c88f8a1dc5..febdc5564638 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -786,7 +786,8 @@ void __init setup_arch(char **cmdline_p) setup_early_printk(); #endif cpu_report(); - check_bugs_early(); + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64_early(); #if defined(CONFIG_VT) #if defined(CONFIG_VGA_CONSOLE) diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c deleted file mode 100644 index 76f5824cdb00..000000000000 --- a/arch/mips/kernel/smp-cmp.c +++ /dev/null @@ -1,148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Copyright (C) 2007 MIPS Technologies, Inc. - * Chris Dearman (chris@mips.com) - */ - -#undef DEBUG - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static void cmp_init_secondary(void) -{ - struct cpuinfo_mips *c __maybe_unused = ¤t_cpu_data; - - /* Assume GIC is present */ - change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 | - STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7); - - /* Enable per-cpu interrupts: platform specific */ - -#ifdef CONFIG_MIPS_MT_SMP - if (cpu_has_mipsmt) - cpu_set_vpe_id(c, (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & - TCBIND_CURVPE); -#endif -} - -static void cmp_smp_finish(void) -{ - pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__); - - /* CDFIXME: remove this? */ - write_c0_compare(read_c0_count() + (8 * mips_hpt_frequency / HZ)); - -#ifdef CONFIG_MIPS_MT_FPAFF - /* If we have an FPU, enroll ourselves in the FPU-full mask */ - if (cpu_has_fpu) - cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask); -#endif /* CONFIG_MIPS_MT_FPAFF */ - - local_irq_enable(); -} - -/* - * Setup the PC, SP, and GP of a secondary processor and start it running - * smp_bootstrap is the place to resume from - * __KSTK_TOS(idle) is apparently the stack pointer - * (unsigned long)idle->thread_info the gp - */ -static int cmp_boot_secondary(int cpu, struct task_struct *idle) -{ - struct thread_info *gp = task_thread_info(idle); - unsigned long sp = __KSTK_TOS(idle); - unsigned long pc = (unsigned long)&smp_bootstrap; - unsigned long a0 = 0; - - pr_debug("SMPCMP: CPU%d: %s cpu %d\n", smp_processor_id(), - __func__, cpu); - -#if 0 - /* Needed? */ - flush_icache_range((unsigned long)gp, - (unsigned long)(gp + sizeof(struct thread_info))); -#endif - - amon_cpu_start(cpu, pc, sp, (unsigned long)gp, a0); - return 0; -} - -/* - * Common setup before any secondaries are started - */ -void __init cmp_smp_setup(void) -{ - int i; - int ncpu = 0; - - pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__); - -#ifdef CONFIG_MIPS_MT_FPAFF - /* If we have an FPU, enroll ourselves in the FPU-full mask */ - if (cpu_has_fpu) - cpumask_set_cpu(0, &mt_fpu_cpumask); -#endif /* CONFIG_MIPS_MT_FPAFF */ - - for (i = 1; i < NR_CPUS; i++) { - if (amon_cpu_avail(i)) { - set_cpu_possible(i, true); - __cpu_number_map[i] = ++ncpu; - __cpu_logical_map[ncpu] = i; - } - } - - if (cpu_has_mipsmt) { - unsigned int nvpe = 1; -#ifdef CONFIG_MIPS_MT_SMP - unsigned int mvpconf0 = read_c0_mvpconf0(); - - nvpe = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1; -#endif - smp_num_siblings = nvpe; - } - pr_info("Detected %i available secondary CPU(s)\n", ncpu); -} - -void __init cmp_prepare_cpus(unsigned int max_cpus) -{ - pr_debug("SMPCMP: CPU%d: %s max_cpus=%d\n", - smp_processor_id(), __func__, max_cpus); - -#ifdef CONFIG_MIPS_MT - /* - * FIXME: some of these options are per-system, some per-core and - * some per-cpu - */ - mips_mt_set_cpuoptions(); -#endif - -} - -const struct plat_smp_ops cmp_smp_ops = { - .send_ipi_single = mips_smp_send_ipi_single, - .send_ipi_mask = mips_smp_send_ipi_mask, - .init_secondary = cmp_init_secondary, - .smp_finish = cmp_smp_finish, - .boot_secondary = cmp_boot_secondary, - .smp_setup = cmp_smp_setup, - .prepare_cpus = cmp_prepare_cpus, -}; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 4fc288bb85b9..f968a319d87f 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -361,6 +361,8 @@ out: static void cps_init_secondary(void) { + int core = cpu_core(¤t_cpu_data); + /* Disable MT - we only want to run 1 TC per VPE */ if (cpu_has_mipsmt) dmt(); @@ -376,6 +378,9 @@ static void cps_init_secondary(void) BUG_ON(ident != mips_cm_vp_id(smp_processor_id())); } + if (core > 0 && !read_gcr_cl_coherence()) + pr_warn("Core %u is not in coherent domain\n", core); + if (cpu_has_veic) clear_c0_status(ST0_IM); else diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c index 6c063aa188e6..401b148f8917 100644 --- a/arch/mips/kernel/uprobes.c +++ b/arch/mips/kernel/uprobes.c @@ -191,6 +191,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *aup, { struct uprobe_task *utask = current->utask; + current->thread.trap_nr = utask->autask.saved_trap_nr; instruction_pointer_set(regs, utask->vaddr); } @@ -207,24 +208,6 @@ unsigned long arch_uretprobe_hijack_return_addr( return ra; } -/** - * set_swbp - store breakpoint at a given address. - * @auprobe: arch specific probepoint information. - * @mm: the probed process address space. - * @vaddr: the virtual address to insert the opcode. - * - * For mm @mm, store the breakpoint instruction at @vaddr. - * Return 0 (success) or a negative errno. - * - * This version overrides the weak version in kernel/events/uprobes.c. - * It is required to handle MIPS16 and microMIPS. - */ -int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, - unsigned long vaddr) -{ - return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); -} - void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { diff --git a/arch/mips/kernel/vpe-cmp.c b/arch/mips/kernel/vpe-cmp.c deleted file mode 100644 index 4ef7f49a4c6d..000000000000 --- a/arch/mips/kernel/vpe-cmp.c +++ /dev/null @@ -1,179 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2004, 2005 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - */ -#include -#include -#include -#include -#include - -#include - -static int major; - -void cleanup_tc(struct tc *tc) -{ - -} - -static ssize_t store_kill(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - struct vpe_notifications *notifier; - - list_for_each_entry(notifier, &vpe->notify, list) - notifier->stop(aprp_cpu_index()); - - release_progmem(vpe->load_addr); - vpe->state = VPE_STATE_UNUSED; - - return len; -} -static DEVICE_ATTR(kill, S_IWUSR, NULL, store_kill); - -static ssize_t ntcs_show(struct device *cd, struct device_attribute *attr, - char *buf) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - - return sprintf(buf, "%d\n", vpe->ntcs); -} - -static ssize_t ntcs_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - unsigned long new; - int ret; - - ret = kstrtoul(buf, 0, &new); - if (ret < 0) - return ret; - - /* APRP can only reserve one TC in a VPE and no more. */ - if (new != 1) - return -EINVAL; - - vpe->ntcs = new; - - return len; -} -static DEVICE_ATTR_RW(ntcs); - -static struct attribute *vpe_attrs[] = { - &dev_attr_kill.attr, - &dev_attr_ntcs.attr, - NULL, -}; -ATTRIBUTE_GROUPS(vpe); - -static void vpe_device_release(struct device *cd) -{ -} - -static struct class vpe_class = { - .name = "vpe", - .dev_release = vpe_device_release, - .dev_groups = vpe_groups, -}; - -static struct device vpe_device; - -int __init vpe_module_init(void) -{ - struct vpe *v = NULL; - struct tc *t; - int err; - - if (!cpu_has_mipsmt) { - pr_warn("VPE loader: not a MIPS MT capable processor\n"); - return -ENODEV; - } - - if (num_possible_cpus() - aprp_cpu_index() < 1) { - pr_warn("No VPEs reserved for AP/SP, not initialize VPE loader\n" - "Pass maxcpus= argument as kernel argument\n"); - return -ENODEV; - } - - major = register_chrdev(0, VPE_MODULE_NAME, &vpe_fops); - if (major < 0) { - pr_warn("VPE loader: unable to register character device\n"); - return major; - } - - err = class_register(&vpe_class); - if (err) { - pr_err("vpe_class registration failed\n"); - goto out_chrdev; - } - - device_initialize(&vpe_device); - vpe_device.class = &vpe_class; - vpe_device.parent = NULL; - dev_set_name(&vpe_device, "vpe_sp"); - vpe_device.devt = MKDEV(major, VPE_MODULE_MINOR); - err = device_add(&vpe_device); - if (err) { - pr_err("Adding vpe_device failed\n"); - goto out_class; - } - - t = alloc_tc(aprp_cpu_index()); - if (!t) { - pr_warn("VPE: unable to allocate TC\n"); - err = -ENOMEM; - goto out_dev; - } - - /* VPE */ - v = alloc_vpe(aprp_cpu_index()); - if (v == NULL) { - pr_warn("VPE: unable to allocate VPE\n"); - kfree(t); - err = -ENOMEM; - goto out_dev; - } - - v->ntcs = 1; - - /* add the tc to the list of this vpe's tc's. */ - list_add(&t->tc, &v->tc); - - /* TC */ - t->pvpe = v; /* set the parent vpe */ - - return 0; - -out_dev: - device_del(&vpe_device); - -out_class: - put_device(&vpe_device); - class_unregister(&vpe_class); - -out_chrdev: - unregister_chrdev(major, VPE_MODULE_NAME); - - return err; -} - -void __exit vpe_module_exit(void) -{ - struct vpe *v, *n; - - device_unregister(&vpe_device); - class_unregister(&vpe_class); - unregister_chrdev(major, VPE_MODULE_NAME); - - /* No locking needed here */ - list_for_each_entry_safe(v, n, &vpecontrol.vpe_list, list) - if (v->state != VPE_STATE_UNUSED) - release_vpe(v); -} diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 5c4adc6ff0c1..e9a0cfd02ae2 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -794,7 +794,7 @@ static int vpe_open(struct inode *inode, struct file *filp) static int vpe_release(struct inode *inode, struct file *filp) { -#if defined(CONFIG_MIPS_VPE_LOADER_MT) || defined(CONFIG_MIPS_VPE_LOADER_CMP) +#ifdef CONFIG_MIPS_VPE_LOADER_MT struct vpe *v; Elf_Ehdr *hdr; int ret = 0; diff --git a/arch/mips/loongson2ef/Kconfig b/arch/mips/loongson2ef/Kconfig index 96dc6eba4310..f93eb6f42238 100644 --- a/arch/mips/loongson2ef/Kconfig +++ b/arch/mips/loongson2ef/Kconfig @@ -7,6 +7,7 @@ choice config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE + select ARCH_HAS_PHYS_TO_DMA select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select CEVT_R4K @@ -36,6 +37,7 @@ config LEMOTE_FULOONG2E config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_HAS_PHYS_TO_DMA select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select BOARD_SCACHE @@ -46,6 +48,7 @@ config LEMOTE_MACH2F select CSRC_R4K if ! MIPS_EXTERNAL_TIMER select DMA_NONCOHERENT select GENERIC_ISA_DMA_SUPPORT_BROKEN + select GPIOLIB select FORCE_PCI select I8259 select IRQ_MIPS_CPU diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform index c6f7a4b95997..d446b705fba4 100644 --- a/arch/mips/loongson2ef/Platform +++ b/arch/mips/loongson2ef/Platform @@ -2,41 +2,6 @@ # Loongson Processors' Support # -cflags-$(CONFIG_CPU_LOONGSON2EF) += -Wa,--trap -cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -# -# Some versions of binutils, not currently mainline as of 2019/02/04, support -# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction -# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a -# description). -# -# We disable this in order to prevent the assembler meddling with the -# instruction that labels refer to, ie. if we label an ll instruction: -# -# 1: ll v0, 0(a0) -# -# ...then with the assembler fix applied the label may actually point at a sync -# instruction inserted by the assembler, and if we were using the label in an -# exception table the table would no longer contain the address of the ll -# instruction. -# -# Avoid this by explicitly disabling that assembler behaviour. If upstream -# binutils does not merge support for the flag then we can revisit & remove -# this later - for now it ensures vendor toolchains don't cause problems. -# -cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-Wa$(comma)-mno-fix-loongson3-llsc,) - -# Enable the workarounds for Loongson2f -ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS -cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa,-mfix-loongson2f-nop -cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa,-mfix-loongson2f-jump -endif - -# Some -march= flags enable MMI instructions, and GCC complains about that -# support being enabled alongside -msoft-float. Thus explicitly disable MMI. -cflags-y += $(call cc-option,-mno-loongson-mmi) - # # Loongson Machines' Support # diff --git a/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c index 5ad38f86ee62..d60dd9992377 100644 --- a/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c @@ -213,7 +213,7 @@ void pci_isa_write_reg(int reg, u32 value) lo |= 0x00000063; _wrmsr(SB_MSR_REG(SB_ERROR), hi, lo); } - + break; default: /* ALL OTHER PCI CONFIG SPACE HEADER IS NOT IMPLEMENTED. */ break; diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 473404cae1c4..49c9889e3d56 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -1,19 +1,3 @@ -# -# Loongson Processors' Support -# - - -cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap - -ifdef CONFIG_CPU_LOONGSON64 -cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a -cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2 -endif - -# Some -march= flags enable MMI instructions, and GCC complains about that -# support being enabled alongside -msoft-float. Thus explicitly disable MMI. -cflags-y += $(call cc-option,-mno-loongson-mmi) - # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/setup.c b/arch/mips/loongson64/setup.c index 3cd11c2b308b..257038e18779 100644 --- a/arch/mips/loongson64/setup.c +++ b/arch/mips/loongson64/setup.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include @@ -17,20 +16,6 @@ void *loongson_fdt_blob; -static void wbflush_loongson(void) -{ - asm(".set\tpush\n\t" - ".set\tnoreorder\n\t" - ".set mips3\n\t" - "sync\n\t" - "nop\n\t" - ".set\tpop\n\t" - ".set mips0\n\t"); -} - -void (*__wbflush)(void) = wbflush_loongson; -EXPORT_SYMBOL(__wbflush); - void __init plat_mem_setup(void) { if (loongson_fdt_blob) diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index 660e1de4412a..90c783981197 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -27,30 +27,13 @@ DEFINE_PER_CPU(int, cpu_state); #define LS_IPI_IRQ (MIPS_CPU_IRQ_BASE + 6) -static void *ipi_set0_regs[16]; -static void *ipi_clear0_regs[16]; -static void *ipi_status0_regs[16]; -static void *ipi_en0_regs[16]; -static void *ipi_mailbox_buf[16]; +static void __iomem *ipi_set0_regs[16]; +static void __iomem *ipi_clear0_regs[16]; +static void __iomem *ipi_status0_regs[16]; +static void __iomem *ipi_en0_regs[16]; +static void __iomem *ipi_mailbox_buf[16]; static uint32_t core0_c0count[NR_CPUS]; -/* read a 32bit value from ipi register */ -#define loongson3_ipi_read32(addr) readl(addr) -/* read a 64bit value from ipi register */ -#define loongson3_ipi_read64(addr) readq(addr) -/* write a 32bit value to ipi register */ -#define loongson3_ipi_write32(action, addr) \ - do { \ - writel(action, addr); \ - __wbflush(); \ - } while (0) -/* write a 64bit value to ipi register */ -#define loongson3_ipi_write64(action, addr) \ - do { \ - writeq(action, addr); \ - __wbflush(); \ - } while (0) - static u32 (*ipi_read_clear)(int cpu); static void (*ipi_write_action)(int cpu, u32 action); static void (*ipi_write_enable)(int cpu); @@ -136,26 +119,28 @@ static u32 legacy_ipi_read_clear(int cpu) u32 action; /* Load the ipi register to figure out what we're supposed to do */ - action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + action = readl_relaxed(ipi_status0_regs[cpu_logical_map(cpu)]); /* Clear the ipi register to clear the interrupt */ - loongson3_ipi_write32(action, ipi_clear0_regs[cpu_logical_map(cpu)]); + writel_relaxed(action, ipi_clear0_regs[cpu_logical_map(cpu)]); + nudge_writes(); return action; } static void legacy_ipi_write_action(int cpu, u32 action) { - loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu]); + writel_relaxed((u32)action, ipi_set0_regs[cpu]); + nudge_writes(); } static void legacy_ipi_write_enable(int cpu) { - loongson3_ipi_write32(0xffffffff, ipi_en0_regs[cpu_logical_map(cpu)]); + writel_relaxed(0xffffffff, ipi_en0_regs[cpu_logical_map(cpu)]); } static void legacy_ipi_clear_buf(int cpu) { - loongson3_ipi_write64(0, ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); + writeq_relaxed(0, ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); } static void legacy_ipi_write_buf(int cpu, struct task_struct *idle) @@ -171,14 +156,15 @@ static void legacy_ipi_write_buf(int cpu, struct task_struct *idle) pr_debug("CPU#%d, func_pc=%lx, sp=%lx, gp=%lx\n", cpu, startargs[0], startargs[1], startargs[2]); - loongson3_ipi_write64(startargs[3], + writeq_relaxed(startargs[3], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x18); - loongson3_ipi_write64(startargs[2], + writeq_relaxed(startargs[2], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x10); - loongson3_ipi_write64(startargs[1], + writeq_relaxed(startargs[1], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x8); - loongson3_ipi_write64(startargs[0], + writeq_relaxed(startargs[0], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); + nudge_writes(); } static void csr_ipi_probe(void) @@ -418,7 +404,7 @@ static irqreturn_t loongson3_ipi_interrupt(int irq, void *dev_id) c0count = c0count ? c0count : 1; for (i = 1; i < nr_cpu_ids; i++) core0_c0count[i] = c0count; - __wbflush(); /* Let others see the result ASAP */ + nudge_writes(); /* Let others see the result ASAP */ } return IRQ_HANDLED; diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index c7ed589de882..b7393b61cfa7 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -83,8 +83,13 @@ static void octeon_flush_icache_all_cores(struct vm_area_struct *vma) else mask = *cpu_online_mask; cpumask_clear_cpu(cpu, &mask); +#ifdef CONFIG_CAVIUM_OCTEON_SOC for_each_cpu(cpu, &mask) octeon_send_ipi_single(cpu, SMP_ICACHE_FLUSH); +#else + smp_call_function_many(&mask, (smp_call_func_t)octeon_local_flush_icache, + NULL, 1); +#endif preempt_enable(); #endif diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index df6755ca1892..5869df848fab 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -261,10 +261,6 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma, r3k_flush_icache_range(kaddr, kaddr + PAGE_SIZE); } -static void local_r3k_flush_data_cache_page(void *addr) -{ -} - static void r3k_flush_data_cache_page(unsigned long addr) { } @@ -302,7 +298,6 @@ void r3k_cache_init(void) __flush_kernel_vmap_range = r3k_flush_kernel_vmap_range; - local_flush_data_cache_page = local_r3k_flush_data_cache_page; flush_data_cache_page = r3k_flush_data_cache_page; _dma_cache_wback_inv = r3k_dma_cache_wback_inv; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index a549fa98c2f4..4b6554b48923 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -110,20 +110,6 @@ static unsigned long dcache_size __read_mostly; static unsigned long vcache_size __read_mostly; static unsigned long scache_size __read_mostly; -/* - * Dummy cache handling routines for machines without boardcaches - */ -static void cache_noop(void) {} - -static struct bcache_ops no_sc_ops = { - .bc_enable = (void *)cache_noop, - .bc_disable = (void *)cache_noop, - .bc_wback_inv = (void *)cache_noop, - .bc_inv = (void *)cache_noop -}; - -struct bcache_ops *bcops = &no_sc_ops; - #define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010) #define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020) @@ -201,24 +187,6 @@ static void r4k_blast_dcache_user_page_setup(void) #endif -static void (* r4k_blast_dcache_page_indexed)(unsigned long addr); - -static void r4k_blast_dcache_page_indexed_setup(void) -{ - unsigned long dc_lsize = cpu_dcache_line_size(); - - if (dc_lsize == 0) - r4k_blast_dcache_page_indexed = (void *)cache_noop; - else if (dc_lsize == 16) - r4k_blast_dcache_page_indexed = blast_dcache16_page_indexed; - else if (dc_lsize == 32) - r4k_blast_dcache_page_indexed = blast_dcache32_page_indexed; - else if (dc_lsize == 64) - r4k_blast_dcache_page_indexed = blast_dcache64_page_indexed; - else if (dc_lsize == 128) - r4k_blast_dcache_page_indexed = blast_dcache128_page_indexed; -} - void (* r4k_blast_dcache)(void); EXPORT_SYMBOL(r4k_blast_dcache); @@ -280,39 +248,6 @@ static inline void tx49_blast_icache32(void) addr | ws, 32); } -static inline void blast_icache32_r4600_v1_page_indexed(unsigned long page) -{ - unsigned long flags; - - local_irq_save(flags); - blast_icache32_page_indexed(page); - local_irq_restore(flags); -} - -static inline void tx49_blast_icache32_page_indexed(unsigned long page) -{ - unsigned long indexmask = current_cpu_data.icache.waysize - 1; - unsigned long start = INDEX_BASE + (page & indexmask); - unsigned long end = start + PAGE_SIZE; - unsigned long ws_inc = 1UL << current_cpu_data.icache.waybit; - unsigned long ws_end = current_cpu_data.icache.ways << - current_cpu_data.icache.waybit; - unsigned long ws, addr; - - CACHE32_UNROLL32_ALIGN2; - /* I'm in even chunk. blast odd chunks */ - for (ws = 0; ws < ws_end; ws += ws_inc) - for (addr = start + 0x400; addr < end; addr += 0x400 * 2) - cache_unroll(32, kernel_cache, Index_Invalidate_I, - addr | ws, 32); - CACHE32_UNROLL32_ALIGN; - /* I'm in odd chunk. blast even chunks */ - for (ws = 0; ws < ws_end; ws += ws_inc) - for (addr = start; addr < end; addr += 0x400 * 2) - cache_unroll(32, kernel_cache, Index_Invalidate_I, - addr | ws, 32); -} - static void (* r4k_blast_icache_page)(unsigned long addr); static void r4k_blast_icache_page_setup(void) @@ -355,34 +290,6 @@ static void r4k_blast_icache_user_page_setup(void) #endif -static void (* r4k_blast_icache_page_indexed)(unsigned long addr); - -static void r4k_blast_icache_page_indexed_setup(void) -{ - unsigned long ic_lsize = cpu_icache_line_size(); - - if (ic_lsize == 0) - r4k_blast_icache_page_indexed = (void *)cache_noop; - else if (ic_lsize == 16) - r4k_blast_icache_page_indexed = blast_icache16_page_indexed; - else if (ic_lsize == 32) { - if (IS_ENABLED(CONFIG_WAR_R4600_V1_INDEX_ICACHEOP) && - cpu_is_r4600_v1_x()) - r4k_blast_icache_page_indexed = - blast_icache32_r4600_v1_page_indexed; - else if (IS_ENABLED(CONFIG_WAR_TX49XX_ICACHE_INDEX_INV)) - r4k_blast_icache_page_indexed = - tx49_blast_icache32_page_indexed; - else if (current_cpu_type() == CPU_LOONGSON2EF) - r4k_blast_icache_page_indexed = - loongson2_blast_icache32_page_indexed; - else - r4k_blast_icache_page_indexed = - blast_icache32_page_indexed; - } else if (ic_lsize == 64) - r4k_blast_icache_page_indexed = blast_icache64_page_indexed; -} - void (* r4k_blast_icache)(void); EXPORT_SYMBOL(r4k_blast_icache); @@ -428,24 +335,6 @@ static void r4k_blast_scache_page_setup(void) r4k_blast_scache_page = blast_scache128_page; } -static void (* r4k_blast_scache_page_indexed)(unsigned long addr); - -static void r4k_blast_scache_page_indexed_setup(void) -{ - unsigned long sc_lsize = cpu_scache_line_size(); - - if (scache_size == 0) - r4k_blast_scache_page_indexed = (void *)cache_noop; - else if (sc_lsize == 16) - r4k_blast_scache_page_indexed = blast_scache16_page_indexed; - else if (sc_lsize == 32) - r4k_blast_scache_page_indexed = blast_scache32_page_indexed; - else if (sc_lsize == 64) - r4k_blast_scache_page_indexed = blast_scache64_page_indexed; - else if (sc_lsize == 128) - r4k_blast_scache_page_indexed = blast_scache128_page_indexed; -} - static void (* r4k_blast_scache)(void); static void r4k_blast_scache_setup(void) @@ -1821,13 +1710,10 @@ void r4k_cache_init(void) setup_scache(); r4k_blast_dcache_page_setup(); - r4k_blast_dcache_page_indexed_setup(); r4k_blast_dcache_setup(); r4k_blast_icache_page_setup(); - r4k_blast_icache_page_indexed_setup(); r4k_blast_icache_setup(); r4k_blast_scache_page_setup(); - r4k_blast_scache_page_indexed_setup(); r4k_blast_scache_setup(); r4k_blast_scache_node_setup(); #ifdef CONFIG_EVA @@ -1859,7 +1745,6 @@ void r4k_cache_init(void) __flush_kernel_vmap_range = r4k_flush_kernel_vmap_range; flush_icache_all = r4k_flush_icache_all; - local_flush_data_cache_page = local_r4k_flush_data_cache_page; flush_data_cache_page = r4k_flush_data_cache_page; flush_icache_range = r4k_flush_icache_range; local_flush_icache_range = local_r4k_flush_icache_range; @@ -1867,15 +1752,9 @@ void r4k_cache_init(void) __local_flush_icache_user_range = local_r4k_flush_icache_user_range; #ifdef CONFIG_DMA_NONCOHERENT - if (dma_default_coherent) { - _dma_cache_wback_inv = (void *)cache_noop; - _dma_cache_wback = (void *)cache_noop; - _dma_cache_inv = (void *)cache_noop; - } else { - _dma_cache_wback_inv = r4k_dma_cache_wback_inv; - _dma_cache_wback = r4k_dma_cache_wback_inv; - _dma_cache_inv = r4k_dma_cache_inv; - } + _dma_cache_wback_inv = r4k_dma_cache_wback_inv; + _dma_cache_wback = r4k_dma_cache_wback_inv; + _dma_cache_inv = r4k_dma_cache_inv; #endif /* CONFIG_DMA_NONCOHERENT */ build_clear_page(); @@ -1908,7 +1787,6 @@ void r4k_cache_init(void) /* I$ fills from D$ just by emptying the write buffers */ flush_cache_page = (void *)b5k_instruction_hazard; flush_cache_range = (void *)b5k_instruction_hazard; - local_flush_data_cache_page = (void *)b5k_instruction_hazard; flush_data_cache_page = (void *)b5k_instruction_hazard; flush_icache_range = (void *)b5k_instruction_hazard; local_flush_icache_range = (void *)b5k_instruction_hazard; @@ -1928,7 +1806,6 @@ void r4k_cache_init(void) flush_cache_range = (void *)cache_noop; flush_icache_all = (void *)cache_noop; flush_data_cache_page = (void *)cache_noop; - local_flush_data_cache_page = (void *)cache_noop; break; } } diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 11b3e7ddafd5..d21cf8c6cf6c 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -48,14 +49,30 @@ void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size); EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range); /* MIPS specific cache operations */ -void (*local_flush_data_cache_page)(void * addr); void (*flush_data_cache_page)(unsigned long addr); void (*flush_icache_all)(void); -EXPORT_SYMBOL_GPL(local_flush_data_cache_page); EXPORT_SYMBOL(flush_data_cache_page); EXPORT_SYMBOL(flush_icache_all); +/* + * Dummy cache handling routine + */ + +void cache_noop(void) {} + +#ifdef CONFIG_BOARD_SCACHE + +static struct bcache_ops no_sc_ops = { + .bc_enable = (void *)cache_noop, + .bc_disable = (void *)cache_noop, + .bc_wback_inv = (void *)cache_noop, + .bc_inv = (void *)cache_noop +}; + +struct bcache_ops *bcops = &no_sc_ops; +#endif + #ifdef CONFIG_DMA_NONCOHERENT /* DMA cache operations. */ diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile index 13bbd12bfa65..bb2c706e11b0 100644 --- a/arch/mips/mti-malta/Makefile +++ b/arch/mips/mti-malta/Makefile @@ -14,6 +14,4 @@ obj-y += malta-platform.o obj-y += malta-setup.o obj-y += malta-time.o -obj-$(CONFIG_MIPS_CMP) += malta-amon.o - CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c deleted file mode 100644 index 84ac523b0ce0..000000000000 --- a/arch/mips/mti-malta/malta-amon.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2007 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - * - * Arbitrary Monitor Interface - */ -#include -#include - -#include -#include -#include -#include - -int amon_cpu_avail(int cpu) -{ - struct cpulaunch *launch = (struct cpulaunch *)CKSEG0ADDR(CPULAUNCH); - - if (cpu < 0 || cpu >= NCPULAUNCH) { - pr_debug("avail: cpu%d is out of range\n", cpu); - return 0; - } - - launch += cpu; - if (!(launch->flags & LAUNCH_FREADY)) { - pr_debug("avail: cpu%d is not ready\n", cpu); - return 0; - } - if (launch->flags & (LAUNCH_FGO|LAUNCH_FGONE)) { - pr_debug("avail: too late.. cpu%d is already gone\n", cpu); - return 0; - } - - return 1; -} - -int amon_cpu_start(int cpu, - unsigned long pc, unsigned long sp, - unsigned long gp, unsigned long a0) -{ - volatile struct cpulaunch *launch = - (struct cpulaunch *)CKSEG0ADDR(CPULAUNCH); - - if (!amon_cpu_avail(cpu)) - return -1; - if (cpu == smp_processor_id()) { - pr_debug("launch: I am cpu%d!\n", cpu); - return -1; - } - launch += cpu; - - pr_debug("launch: starting cpu%d\n", cpu); - - launch->pc = pc; - launch->gp = gp; - launch->sp = sp; - launch->a0 = a0; - - smp_wmb(); /* Target must see parameters before go */ - launch->flags |= LAUNCH_FGO; - smp_wmb(); /* Target must see go before we poll */ - - while ((launch->flags & LAUNCH_FGONE) == 0) - ; - smp_rmb(); /* Target will be updating flags soon */ - pr_debug("launch: cpu%d gone!\n", cpu); - - return 0; -} - -#ifdef CONFIG_MIPS_VPE_LOADER_CMP -int vpe_run(struct vpe *v) -{ - struct vpe_notifications *n; - - if (amon_cpu_start(aprp_cpu_index(), v->__start, 0, 0, 0) < 0) - return -1; - - list_for_each_entry(n, &v->notify, list) - n->start(VPE_MODULE_MINOR); - - return 0; -} -#endif diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c index b03cac5fdc02..000d6d50520a 100644 --- a/arch/mips/mti-malta/malta-init.c +++ b/arch/mips/mti-malta/malta-init.c @@ -289,8 +289,6 @@ mips_pci_controller: if (!register_cps_smp_ops()) return; - if (!register_cmp_smp_ops()) - return; if (!register_vsmp_smp_ops()) return; register_up_smp_ops(); diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c index 4ffbcc58c6f6..6961a23aefe9 100644 --- a/arch/mips/mti-malta/malta-platform.c +++ b/arch/mips/mti-malta/malta-platform.c @@ -43,7 +43,6 @@ static struct plat_serial8250_port uart8250_data[] = { SMC_PORT(0x3F8, 4), SMC_PORT(0x2F8, 3), -#ifndef CONFIG_MIPS_CMP { .mapbase = 0x1f000900, /* The CBUS UART */ .irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB2, @@ -53,7 +52,6 @@ static struct plat_serial8250_port uart8250_data[] = { .flags = CBUS_UART_FLAGS, .regshift = 3, }, -#endif { }, }; diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c index d967e4c0cf24..79e29bf42a24 100644 --- a/arch/mips/pci/pci-lantiq.c +++ b/arch/mips/pci/pci-lantiq.c @@ -118,7 +118,7 @@ static int ltq_pci_startup(struct platform_device *pdev) /* and enable the clocks */ clk_enable(clk_pci); - if (of_find_property(node, "lantiq,external-clock", NULL)) + if (of_property_read_bool(node, "lantiq,external-clock")) clk_enable(clk_external); else clk_disable(clk_external); diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c index d59888aaed81..4ac68a534e4f 100644 --- a/arch/mips/pci/pci-rt3883.c +++ b/arch/mips/pci/pci-rt3883.c @@ -419,7 +419,7 @@ static int rt3883_pci_probe(struct platform_device *pdev) /* find the interrupt controller child node */ for_each_child_of_node(np, child) { - if (of_get_property(child, "interrupt-controller", NULL)) { + if (of_property_read_bool(child, "interrupt-controller")) { rpc->intc_of_node = child; break; } diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 83e61e147b90..08c012a2591f 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -29,18 +29,22 @@ choice select MIPS_AUTO_PFN_OFFSET select MIPS_L1_CACHE_SHIFT_4 select HAVE_PCI + select SOC_BUS config SOC_RT305X bool "RT305x" + select SOC_BUS config SOC_RT3883 bool "RT3883" select HAVE_PCI + select SOC_BUS config SOC_MT7620 bool "MT7620/8" select CPU_MIPSR2_IRQ_VI select HAVE_PCI + select SOC_BUS config SOC_MT7621 bool "MT7621" diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index ae1fa0391c88..4435f50b8d24 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include @@ -49,6 +51,8 @@ /* does the board have sdram or ddram */ static int dram_type; +static struct ralink_soc_info *soc_info_ptr; + static __init u32 mt7620_calc_rate(u32 ref_rate, u32 mul, u32 div) { @@ -324,35 +328,76 @@ mt7628_dram_init(struct ralink_soc_info *soc_info) } } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init mt7620_get_soc_name0(void) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(MT7620_SYSC_BASE); - unsigned char *name = NULL; - u32 n0; - u32 n1; - u32 rev; - u32 cfg0; - u32 pmu0; - u32 pmu1; - u32 bga; + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); - rev = __raw_readl(sysc + SYSC_REG_CHIP_REV); - bga = (rev >> CHIP_REV_PKG_SHIFT) & CHIP_REV_PKG_MASK; +static unsigned int __init mt7620_get_soc_name1(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} + +static bool __init mt7620_soc_valid(void) +{ + if (mt7620_get_soc_name0() == MT7620_CHIP_NAME0 && + mt7620_get_soc_name1() == MT7620_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init mt7628_soc_valid(void) +{ + if (mt7620_get_soc_name0() == MT7620_CHIP_NAME0 && + mt7620_get_soc_name1() == MT7628_CHIP_NAME1) + return true; + else + return false; +} + +static unsigned int __init mt7620_get_rev(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_REV); +} + +static unsigned int __init mt7620_get_bga(void) +{ + return (mt7620_get_rev() >> CHIP_REV_PKG_SHIFT) & CHIP_REV_PKG_MASK; +} + +static unsigned int __init mt7620_get_efuse(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_EFUSE_CFG); +} + +static unsigned int __init mt7620_get_soc_ver(void) +{ + return (mt7620_get_rev() >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK; +} + +static unsigned int __init mt7620_get_soc_eco(void) +{ + return (mt7620_get_rev() & CHIP_REV_ECO_MASK); +} + +static const char __init *mt7620_get_soc_name(struct ralink_soc_info *soc_info) +{ + if (mt7620_soc_valid()) { + u32 bga = mt7620_get_bga(); - if (n0 == MT7620_CHIP_NAME0 && n1 == MT7620_CHIP_NAME1) { if (bga) { ralink_soc = MT762X_SOC_MT7620A; - name = "MT7620A"; soc_info->compatible = "ralink,mt7620a-soc"; + return "MT7620A"; } else { ralink_soc = MT762X_SOC_MT7620N; - name = "MT7620N"; soc_info->compatible = "ralink,mt7620n-soc"; + return "MT7620N"; } - } else if (n0 == MT7620_CHIP_NAME0 && n1 == MT7628_CHIP_NAME1) { - u32 efuse = __raw_readl(sysc + SYSC_REG_EFUSE_CFG); + } else if (mt7628_soc_valid()) { + u32 efuse = mt7620_get_efuse(); + unsigned char *name = NULL; if (efuse & EFUSE_MT7688) { ralink_soc = MT762X_SOC_MT7688; @@ -362,17 +407,63 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) name = "MT7628AN"; } soc_info->compatible = "ralink,mt7628an-soc"; + return name; } else { - panic("mt762x: unknown SoC, n0:%08x n1:%08x\n", n0, n1); + panic("mt762x: unknown SoC, n0:%08x n1:%08x\n", + mt7620_get_soc_name0(), mt7620_get_soc_name1()); } +} + +static const char __init *mt7620_get_soc_id_name(void) +{ + if (ralink_soc == MT762X_SOC_MT7620A) + return "mt7620a"; + else if (ralink_soc == MT762X_SOC_MT7620N) + return "mt7620n"; + else if (ralink_soc == MT762X_SOC_MT7688) + return "mt7688"; + else if (ralink_soc == MT762X_SOC_MT7628AN) + return "mt7628n"; + else + return "invalid"; +} + +static int __init mt7620_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = mt7620_get_soc_id_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(mt7620_soc_dev_init); + +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + const char *name = mt7620_get_soc_name(soc_info); + u32 cfg0; + u32 pmu0; + u32 pmu1; snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "MediaTek %s ver:%u eco:%u", - name, - (rev >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK, - (rev & CHIP_REV_ECO_MASK)); + name, mt7620_get_soc_ver(), mt7620_get_soc_eco()); - cfg0 = __raw_readl(sysc + SYSC_REG_SYSTEM_CONFIG0); + cfg0 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_SYSTEM_CONFIG0); if (is_mt76x8()) { dram_type = cfg0 & DRAM_TYPE_MT7628_MASK; } else { @@ -388,11 +479,13 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) else mt7620_dram_init(soc_info); - pmu0 = __raw_readl(sysc + PMU0_CFG); - pmu1 = __raw_readl(sysc + PMU1_CFG); + pmu0 = __raw_readl(MT7620_SYSC_BASE + PMU0_CFG); + pmu1 = __raw_readl(MT7620_SYSC_BASE + PMU1_CFG); pr_info("Analog PMU set to %s control\n", (pmu0 & PMU_SW_SET) ? ("sw") : ("hw")); pr_info("Digital PMU set to %s control\n", (pmu1 & DIG_SW_SEL) ? ("sw") : ("hw")); + + soc_info_ptr = soc_info; } diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index bbf5811afbf2..c3fbab50b95c 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -217,8 +217,6 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) if (!register_cps_smp_ops()) return; - if (!register_cmp_smp_ops()) - return; if (!register_vsmp_smp_ops()) return; } diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c index 493335db2fe1..456ba0b2599e 100644 --- a/arch/mips/ralink/rt288x.c +++ b/arch/mips/ralink/rt288x.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include #include @@ -17,6 +19,8 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + void __init ralink_clk_init(void) { unsigned long cpu_rate, wmac_rate = 40000000; @@ -57,34 +61,90 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } +static unsigned int __init rt2880_get_soc_name0(void) +{ + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} + +static unsigned int __init rt2880_get_soc_name1(void) +{ + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} + +static bool __init rt2880_soc_valid(void) +{ + if (rt2880_get_soc_name0() == RT2880_CHIP_NAME0 && + rt2880_get_soc_name1() == RT2880_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt2880_get_soc_name(void) +{ + if (rt2880_soc_valid()) + return "RT2880"; + else + return "invalid"; +} + +static unsigned int __init rt2880_get_soc_id(void) +{ + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_ID); +} + +static unsigned int __init rt2880_get_soc_ver(void) +{ + return (rt2880_get_soc_id() >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK; +} + +static unsigned int __init rt2880_get_soc_rev(void) +{ + return (rt2880_get_soc_id() & CHIP_ID_REV_MASK); +} + +static int __init rt2880_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt2880_get_soc_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(rt2880_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT2880_SYSC_BASE); - const char *name; - u32 n0; - u32 n1; - u32 id; - - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); - id = __raw_readl(sysc + SYSC_REG_CHIP_ID); - - if (n0 == RT2880_CHIP_NAME0 && n1 == RT2880_CHIP_NAME1) { + if (rt2880_soc_valid()) soc_info->compatible = "ralink,r2880-soc"; - name = "RT2880"; - } else { - panic("rt288x: unknown SoC, n0:%08x n1:%08x", n0, n1); - } + else + panic("rt288x: unknown SoC, n0:%08x n1:%08x", + rt2880_get_soc_name0(), rt2880_get_soc_name1()); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s id:%u rev:%u", - name, - (id >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK, - (id & CHIP_ID_REV_MASK)); + rt2880_get_soc_name(), + rt2880_get_soc_ver(), + rt2880_get_soc_rev()); soc_info->mem_base = RT2880_SDRAM_BASE; soc_info->mem_size_min = RT2880_MEM_SIZE_MIN; soc_info->mem_size_max = RT2880_MEM_SIZE_MAX; ralink_soc = RT2880_SOC; + soc_info_ptr = soc_info; } diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c index 8b095a9dcb15..d8dcc5cc66cc 100644 --- a/arch/mips/ralink/rt305x.c +++ b/arch/mips/ralink/rt305x.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include @@ -19,13 +21,14 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + static unsigned long rt5350_get_mem_size(void) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE); unsigned long ret; u32 t; - t = __raw_readl(sysc + SYSC_REG_SYSTEM_CONFIG); + t = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_SYSTEM_CONFIG); t = (t >> RT5350_SYSCFG0_DRAM_SIZE_SHIFT) & RT5350_SYSCFG0_DRAM_SIZE_MASK; @@ -140,53 +143,149 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init rt305x_get_soc_name0(void) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE); - unsigned char *name; - u32 n0; - u32 n1; - u32 id; + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); +static unsigned int __init rt305x_get_soc_name1(void) +{ + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} - if (n0 == RT3052_CHIP_NAME0 && n1 == RT3052_CHIP_NAME1) { +static bool __init rt3052_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3052_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3052_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init rt3350_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3350_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3350_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init rt3352_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3352_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3352_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init rt5350_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT5350_CHIP_NAME0 && + rt305x_get_soc_name1() == RT5350_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt305x_get_soc_name(struct ralink_soc_info *soc_info) +{ + if (rt3052_soc_valid()) { unsigned long icache_sets; icache_sets = (read_c0_config1() >> 22) & 7; if (icache_sets == 1) { ralink_soc = RT305X_SOC_RT3050; - name = "RT3050"; soc_info->compatible = "ralink,rt3050-soc"; + return "RT3050"; } else { ralink_soc = RT305X_SOC_RT3052; - name = "RT3052"; soc_info->compatible = "ralink,rt3052-soc"; + return "RT3052"; } - } else if (n0 == RT3350_CHIP_NAME0 && n1 == RT3350_CHIP_NAME1) { + } else if (rt3350_soc_valid()) { ralink_soc = RT305X_SOC_RT3350; - name = "RT3350"; soc_info->compatible = "ralink,rt3350-soc"; - } else if (n0 == RT3352_CHIP_NAME0 && n1 == RT3352_CHIP_NAME1) { + return "RT3350"; + } else if (rt3352_soc_valid()) { ralink_soc = RT305X_SOC_RT3352; - name = "RT3352"; soc_info->compatible = "ralink,rt3352-soc"; - } else if (n0 == RT5350_CHIP_NAME0 && n1 == RT5350_CHIP_NAME1) { + return "RT3352"; + } else if (rt5350_soc_valid()) { ralink_soc = RT305X_SOC_RT5350; - name = "RT5350"; soc_info->compatible = "ralink,rt5350-soc"; + return "RT5350"; } else { - panic("rt305x: unknown SoC, n0:%08x n1:%08x", n0, n1); + panic("rt305x: unknown SoC, n0:%08x n1:%08x", + rt305x_get_soc_name0(), rt305x_get_soc_name1()); + } +} + +static unsigned int __init rt305x_get_soc_id(void) +{ + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_ID); +} + +static unsigned int __init rt305x_get_soc_ver(void) +{ + return (rt305x_get_soc_id() >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK; +} + +static unsigned int __init rt305x_get_soc_rev(void) +{ + return (rt305x_get_soc_id() & CHIP_ID_REV_MASK); +} + +static const char __init *rt305x_get_soc_id_name(void) +{ + if (soc_is_rt3050()) + return "rt3050"; + else if (soc_is_rt3052()) + return "rt3052"; + else if (soc_is_rt3350()) + return "rt3350"; + else if (soc_is_rt3352()) + return "rt3352"; + else if (soc_is_rt5350()) + return "rt5350"; + else + return "invalid"; +} + +static int __init rt305x_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt305x_get_soc_id_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); } - id = __raw_readl(sysc + SYSC_REG_CHIP_ID); + return 0; +} +device_initcall(rt305x_soc_dev_init); + +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + const char *name = rt305x_get_soc_name(soc_info); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s id:%u rev:%u", name, - (id >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK, - (id & CHIP_ID_REV_MASK)); + rt305x_get_soc_ver(), + rt305x_get_soc_rev()); soc_info->mem_base = RT305X_SDRAM_BASE; if (soc_is_rt5350()) { @@ -198,4 +297,6 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) soc_info->mem_size_min = RT3352_MEM_SIZE_MIN; soc_info->mem_size_max = RT3352_MEM_SIZE_MAX; } + + soc_info_ptr = soc_info; } diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index d9875f146d66..cca887af378f 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include #include @@ -17,6 +19,8 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + void __init ralink_clk_init(void) { unsigned long cpu_rate, sys_rate; @@ -70,34 +74,90 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } +static unsigned int __init rt3883_get_soc_name0(void) +{ + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID0_3); +} + +static unsigned int __init rt3883_get_soc_name1(void) +{ + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID4_7); +} + +static bool __init rt3883_soc_valid(void) +{ + if (rt3883_get_soc_name0() == RT3883_CHIP_NAME0 && + rt3883_get_soc_name1() == RT3883_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt3883_get_soc_name(void) +{ + if (rt3883_soc_valid()) + return "RT3883"; + else + return "invalid"; +} + +static unsigned int __init rt3883_get_soc_id(void) +{ + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_REVID); +} + +static unsigned int __init rt3883_get_soc_ver(void) +{ + return (rt3883_get_soc_id() >> RT3883_REVID_VER_ID_SHIFT) & RT3883_REVID_VER_ID_MASK; +} + +static unsigned int __init rt3883_get_soc_rev(void) +{ + return (rt3883_get_soc_id() & RT3883_REVID_ECO_ID_MASK); +} + +static int __init rt3883_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt3883_get_soc_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(rt3883_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT3883_SYSC_BASE); - const char *name; - u32 n0; - u32 n1; - u32 id; - - n0 = __raw_readl(sysc + RT3883_SYSC_REG_CHIPID0_3); - n1 = __raw_readl(sysc + RT3883_SYSC_REG_CHIPID4_7); - id = __raw_readl(sysc + RT3883_SYSC_REG_REVID); - - if (n0 == RT3883_CHIP_NAME0 && n1 == RT3883_CHIP_NAME1) { + if (rt3883_soc_valid()) soc_info->compatible = "ralink,rt3883-soc"; - name = "RT3883"; - } else { - panic("rt3883: unknown SoC, n0:%08x n1:%08x", n0, n1); - } + else + panic("rt3883: unknown SoC, n0:%08x n1:%08x", + rt3883_get_soc_name0(), rt3883_get_soc_name1()); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s ver:%u eco:%u", - name, - (id >> RT3883_REVID_VER_ID_SHIFT) & RT3883_REVID_VER_ID_MASK, - (id & RT3883_REVID_ECO_ID_MASK)); + rt3883_get_soc_name(), + rt3883_get_soc_ver(), + rt3883_get_soc_rev()); soc_info->mem_base = RT3883_SDRAM_BASE; soc_info->mem_size_min = RT3883_MEM_SIZE_MIN; soc_info->mem_size_max = RT3883_MEM_SIZE_MAX; ralink_soc = RT3883_SOC; + soc_info_ptr = soc_info; } diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig index 470d46183677..5fb92fe84149 100644 --- a/arch/mips/sibyte/Kconfig +++ b/arch/mips/sibyte/Kconfig @@ -10,15 +10,6 @@ config SIBYTE_SB1250 select SIBYTE_SB1xxx_SOC select SYS_SUPPORTS_SMP -config SIBYTE_BCM1120 - bool - select CEVT_SB1250 - select CSRC_SB1250 - select IRQ_MIPS_CPU - select SIBYTE_BCM112X - select SIBYTE_HAS_ZBUS_PROFILING - select SIBYTE_SB1xxx_SOC - config SIBYTE_BCM1125 bool select CEVT_SB1250 @@ -29,17 +20,6 @@ config SIBYTE_BCM1125 select SIBYTE_HAS_ZBUS_PROFILING select SIBYTE_SB1xxx_SOC -config SIBYTE_BCM1125H - bool - select CEVT_SB1250 - select CSRC_SB1250 - select HAVE_PCI - select IRQ_MIPS_CPU - select SIBYTE_BCM112X - select SIBYTE_ENABLE_LDT_IF_PCI - select SIBYTE_HAS_ZBUS_PROFILING - select SIBYTE_SB1xxx_SOC - config SIBYTE_BCM112X bool select CEVT_SB1250 @@ -58,16 +38,6 @@ config SIBYTE_BCM1x80 select SIBYTE_SB1xxx_SOC select SYS_SUPPORTS_SMP -config SIBYTE_BCM1x55 - bool - select CEVT_BCM1480 - select CSRC_BCM1480 - select HAVE_PCI - select IRQ_MIPS_CPU - select SIBYTE_SB1xxx_SOC - select SIBYTE_HAS_ZBUS_PROFILING - select SYS_SUPPORTS_SMP - config SIBYTE_SB1xxx_SOC bool select IRQ_MIPS_CPU @@ -143,8 +113,7 @@ config SIBYTE_CFE_CONSOLE config SIBYTE_BUS_WATCHER bool "Support for Bus Watcher statistics" depends on SIBYTE_SB1xxx_SOC && \ - (SIBYTE_BCM112X || SIBYTE_SB1250 || \ - SIBYTE_BCM1x55 || SIBYTE_BCM1x80) + (SIBYTE_BCM112X || SIBYTE_SB1250 || SIBYTE_BCM1x80) help Handle and keep statistics on the bus error interrupts (COR_ECC, BAD_ECC, IO_BUS). diff --git a/arch/mips/sibyte/Makefile b/arch/mips/sibyte/Makefile index d015c4d79c3e..47078353fe8a 100644 --- a/arch/mips/sibyte/Makefile +++ b/arch/mips/sibyte/Makefile @@ -6,21 +6,15 @@ obj-$(CONFIG_SIBYTE_BCM112X) += sb1250/ obj-$(CONFIG_SIBYTE_BCM112X) += common/ obj-$(CONFIG_SIBYTE_SB1250) += sb1250/ obj-$(CONFIG_SIBYTE_SB1250) += common/ -obj-$(CONFIG_SIBYTE_BCM1x55) += bcm1480/ -obj-$(CONFIG_SIBYTE_BCM1x55) += common/ obj-$(CONFIG_SIBYTE_BCM1x80) += bcm1480/ obj-$(CONFIG_SIBYTE_BCM1x80) += common/ # -# Sibyte BCM91120x (Carmel) board -# Sibyte BCM91120C (CRhine) board # Sibyte BCM91125C (CRhone) board # Sibyte BCM91125E (Rhone) board # Sibyte SWARM board # Sibyte BCM91x80 (BigSur) board # -obj-$(CONFIG_SIBYTE_CARMEL) += swarm/ -obj-$(CONFIG_SIBYTE_CRHINE) += swarm/ obj-$(CONFIG_SIBYTE_CRHONE) += swarm/ obj-$(CONFIG_SIBYTE_RHONE) += swarm/ obj-$(CONFIG_SIBYTE_SENTOSA) += swarm/ diff --git a/arch/mips/sibyte/Platform b/arch/mips/sibyte/Platform index 65b2225b76b2..937108e41f13 100644 --- a/arch/mips/sibyte/Platform +++ b/arch/mips/sibyte/Platform @@ -13,25 +13,17 @@ cflags-$(CONFIG_SIBYTE_SB1250) += \ -I$(srctree)/arch/mips/include/asm/mach-sibyte \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1250_112x_ALL -cflags-$(CONFIG_SIBYTE_BCM1x55) += \ - -I$(srctree)/arch/mips/include/asm/mach-sibyte \ - -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1480_ALL - cflags-$(CONFIG_SIBYTE_BCM1x80) += \ -I$(srctree)/arch/mips/include/asm/mach-sibyte \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1480_ALL # -# Sibyte BCM91120x (Carmel) board -# Sibyte BCM91120C (CRhine) board # Sibyte BCM91125C (CRhone) board # Sibyte BCM91125E (Rhone) board # Sibyte BCM91250A (SWARM) board # Sibyte BCM91250C2 (LittleSur) board # Sibyte BCM91x80 (BigSur) board # -load-$(CONFIG_SIBYTE_CARMEL) := 0xffffffff80100000 -load-$(CONFIG_SIBYTE_CRHINE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_CRHONE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_RHONE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_SENTOSA) := 0xffffffff80100000 diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c index d43291473f76..a296d2c51841 100644 --- a/arch/mips/sibyte/common/bus_watcher.c +++ b/arch/mips/sibyte/common/bus_watcher.c @@ -24,7 +24,7 @@ #include #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #endif @@ -71,7 +71,7 @@ void check_bus_watcher(void) #if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250) /* Use non-destructive register */ status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS_DEBUG)); -#elif defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#elif defined(CONFIG_SIBYTE_BCM1x80) /* Use non-destructive register */ /* Same as 1250 except BUS_ERR_STATUS_DEBUG is in a different place. */ status = csr_in32(IOADDR(A_BCM1480_BUS_ERR_STATUS_DEBUG)); diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 1a504294d85f..2cb90dbbe843 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -35,11 +35,6 @@ #endif #endif -#define SIBYTE_MAX_MEM_REGIONS 8 -phys_addr_t board_mem_region_addrs[SIBYTE_MAX_MEM_REGIONS]; -phys_addr_t board_mem_region_sizes[SIBYTE_MAX_MEM_REGIONS]; -unsigned int board_mem_region_count; - int cfe_cons_handle; #ifdef CONFIG_BLK_DEV_INITRD @@ -141,16 +136,6 @@ static __init void prom_meminit(void) size -= 512; memblock_add(addr, size); } - board_mem_region_addrs[board_mem_region_count] = addr; - board_mem_region_sizes[board_mem_region_count] = size; - board_mem_region_count++; - if (board_mem_region_count == - SIBYTE_MAX_MEM_REGIONS) { - /* - * Too many regions. Need to configure more - */ - while(1); - } } } #ifdef CONFIG_BLK_DEV_INITRD @@ -310,7 +295,7 @@ void __init prom_init(void) #if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250) register_smp_ops(&sb_smp_ops); #endif -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 register_smp_ops(&bcm1480_smp_ops); #endif } diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c index ac376dfb4e7c..408db45efdc8 100644 --- a/arch/mips/sibyte/common/sb_tbprof.c +++ b/arch/mips/sibyte/common/sb_tbprof.c @@ -23,7 +23,7 @@ #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #include #include @@ -35,7 +35,7 @@ #error invalid SiByte UART configuration #endif -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #undef K_INT_TRACE_FREEZE #define K_INT_TRACE_FREEZE K_BCM1480_INT_TRACE_FREEZE #undef K_INT_PERF_CNT @@ -157,7 +157,7 @@ static void arm_tb(void) * a previous interrupt request. This means that bus profiling * requires ALL of the SCD perf counters. */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq((scdperfcnt & ~M_SPC_CFG_SRC1) | /* keep counters 0,2,3,4,5,6,7 as is */ V_SPC_CFG_SRC1(1), /* counter 1 counts cycles */ @@ -290,7 +290,7 @@ static int sbprof_zbprof_start(struct file *filp) * pass them through. I am exploiting my knowledge that * cp0_status masks out IP[5]. krw */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq(K_BCM1480_INT_MAP_I3, IOADDR(A_BCM1480_IMR_REGISTER(0, R_BCM1480_IMR_INTERRUPT_MAP_BASE_L) + ((K_BCM1480_INT_PERF_CNT & 0x3f) << 3))); @@ -343,7 +343,7 @@ static int sbprof_zbprof_start(struct file *filp) __raw_writeq(0, IOADDR(A_SCD_TRACE_SEQUENCE_7)); /* Now indicate the PERF_CNT interrupt as a trace-relevant interrupt */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq(1ULL << (K_BCM1480_INT_PERF_CNT & 0x3f), IOADDR(A_BCM1480_IMR_REGISTER(0, R_BCM1480_IMR_INTERRUPT_TRACE_L))); #else diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 72a31eeeebba..76683993cdd3 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -24,7 +24,7 @@ #include #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) #include @@ -34,7 +34,7 @@ #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 extern void bcm1480_setup(void); #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) extern void sb1250_setup(void); @@ -114,7 +114,7 @@ int update_persistent_clock64(struct timespec64 now) void __init plat_mem_setup(void) { -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 bcm1480_setup(); #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) sb1250_setup(); @@ -146,12 +146,6 @@ void __init plat_mem_setup(void) #ifdef LEDS_PHYS -#ifdef CONFIG_SIBYTE_CARMEL -/* XXXKW need to detect Monterey/LittleSur/etc */ -#undef LEDS_PHYS -#define LEDS_PHYS MLEDS_PHYS -#endif - void setleds(char *str) { void *reg; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d49a5a7aa10d..9652d367fc37 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -20,6 +20,9 @@ config SUPERH select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_SHOW + select GENERIC_LIB_ASHLDI3 + select GENERIC_LIB_ASHRDI3 + select GENERIC_LIB_LSHRDI3 select GENERIC_PCI_IOMAP if PCI select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 10290e5c1f43..c449e7c1b20f 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -15,7 +15,7 @@ config SH_STANDARD_BIOS config STACK_DEBUG bool "Check for stack overflows" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && PRINTK help This option will cause messages to be printed if free stack space drops below a certain limit. Saying Y here will add overhead to diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 83bcb6d2daca..fafe15d3ba1d 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -358,7 +358,6 @@ config SH_SH2007 intended for embedded applications. It has an Ethernet interface (SMC9118), direct connected Compact Flash socket, two serial ports and PC-104 bus. - More information at . config SH_APSH4A3A bool "AP-SH4A-3A" diff --git a/arch/sh/boot/compressed/ashldi3.c b/arch/sh/boot/compressed/ashldi3.c index 7cebd646df83..7c1212170230 100644 --- a/arch/sh/boot/compressed/ashldi3.c +++ b/arch/sh/boot/compressed/ashldi3.c @@ -1,2 +1,2 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include "../../lib/ashldi3.c" +// SPDX-License-Identifier: GPL-2.0-or-later +#include "../../../../lib/ashldi3.c" diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c index 4f5e49f10805..a78b9a935585 100644 --- a/arch/sh/drivers/pci/pcie-sh7786.c +++ b/arch/sh/drivers/pci/pcie-sh7786.c @@ -31,7 +31,6 @@ struct sh7786_pcie_port { static struct sh7786_pcie_port *sh7786_pcie_ports; static unsigned int nr_ports; -static unsigned long dma_pfn_offset; size_t memsize; u64 memstart; diff --git a/arch/sh/include/asm/types.h b/arch/sh/include/asm/types.h index 68eb24ad2013..9b3fc923ee28 100644 --- a/arch/sh/include/asm/types.h +++ b/arch/sh/include/asm/types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SH_TYPES_H #define __ASM_SH_TYPES_H -#include +#include /* * These aren't exported outside the kernel to avoid name space clashes diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index 27f2e3da5aa2..d289e99dc118 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -372,7 +372,6 @@ static struct subsys_interface sq_interface = { static int __init sq_api_init(void) { unsigned int nr_pages = 0x04000000 >> PAGE_SHIFT; - unsigned int size = (nr_pages + (BITS_PER_LONG - 1)) / BITS_PER_LONG; int ret = -ENOMEM; printk(KERN_NOTICE "sq: Registering store queue API.\n"); @@ -382,7 +381,7 @@ static int __init sq_api_init(void) if (unlikely(!sq_cache)) return ret; - sq_bitmap = kzalloc(size, GFP_KERNEL); + sq_bitmap = bitmap_zalloc(nr_pages, GFP_KERNEL); if (unlikely(!sq_bitmap)) goto out; @@ -393,7 +392,7 @@ static int __init sq_api_init(void) return 0; out: - kfree(sq_bitmap); + bitmap_free(sq_bitmap); kmem_cache_destroy(sq_cache); return ret; @@ -402,7 +401,7 @@ out: static void __exit sq_api_exit(void) { subsys_interface_unregister(&sq_interface); - kfree(sq_bitmap); + bitmap_free(sq_bitmap); kmem_cache_destroy(sq_cache); } diff --git a/arch/sh/kernel/head_32.S b/arch/sh/kernel/head_32.S index 4adbd4ade319..b603b7968b38 100644 --- a/arch/sh/kernel/head_32.S +++ b/arch/sh/kernel/head_32.S @@ -64,7 +64,7 @@ ENTRY(_stext) ldc r0, r6_bank #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov r4, r12 ! Store device tree blob pointer in r12 #endif @@ -315,7 +315,7 @@ ENTRY(_stext) 10: #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov.l 8f, r0 ! Make flat device tree available early. jsr @r0 mov r12, r4 @@ -346,7 +346,7 @@ ENTRY(stack_start) 5: .long start_kernel 6: .long cpu_init 7: .long init_thread_union -#if defined(CONFIG_OF_FLATTREE) +#if defined(CONFIG_OF_EARLY_FLATTREE) 8: .long sh_fdt_init #endif diff --git a/arch/sh/kernel/nmi_debug.c b/arch/sh/kernel/nmi_debug.c index 11777867c6f5..a212b645b4cf 100644 --- a/arch/sh/kernel/nmi_debug.c +++ b/arch/sh/kernel/nmi_debug.c @@ -49,7 +49,7 @@ static int __init nmi_debug_setup(char *str) register_die_notifier(&nmi_debug_nb); if (*str != '=') - return 0; + return 1; for (p = str + 1; *p; p = sep + 1) { sep = strchr(p, ','); @@ -70,6 +70,6 @@ static int __init nmi_debug_setup(char *str) break; } - return 0; + return 1; } __setup("nmi_debug", nmi_debug_setup); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 1fcb6659822a..af977ec4ca5e 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -244,7 +244,7 @@ void __init __weak plat_early_device_setup(void) { } -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE void __ref sh_fdt_init(phys_addr_t dt_phys) { static int done = 0; @@ -326,7 +326,7 @@ void __init setup_arch(char **cmdline_p) /* Let earlyprintk output early console messages */ sh_early_platform_driver_probe("earlyprintk", 1, 1); -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE #ifdef CONFIG_USE_BUILTIN_DTB unflatten_and_copy_device_tree(); #else diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile index eb473d373ca4..d20a0768b31f 100644 --- a/arch/sh/lib/Makefile +++ b/arch/sh/lib/Makefile @@ -7,9 +7,7 @@ lib-y = delay.o memmove.o memchr.o \ checksum.o strlen.o div64.o div64-generic.o # Extracted from libgcc -obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ - ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \ - udiv_qrnnd.o +obj-y += movmem.o ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o udiv_qrnnd.o udivsi3-y := udivsi3_i4i-Os.o diff --git a/arch/sh/lib/ashldi3.c b/arch/sh/lib/ashldi3.c deleted file mode 100644 index e5afe0935847..000000000000 --- a/arch/sh/lib/ashldi3.c +++ /dev/null @@ -1,30 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __ashldi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - w.s.low = 0; - w.s.high = (unsigned int) uu.s.low << -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.low >> bm; - - w.s.low = (unsigned int) uu.s.low << b; - w.s.high = ((unsigned int) uu.s.high << b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__ashldi3); diff --git a/arch/sh/lib/ashrdi3.c b/arch/sh/lib/ashrdi3.c deleted file mode 100644 index ae263fbf2538..000000000000 --- a/arch/sh/lib/ashrdi3.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __ashrdi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - /* w.s.high = 1..1 or 0..0 */ - w.s.high = - uu.s.high >> 31; - w.s.low = uu.s.high >> -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.high << bm; - - w.s.high = uu.s.high >> b; - w.s.low = ((unsigned int) uu.s.low >> b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__ashrdi3); diff --git a/arch/sh/lib/lshrdi3.c b/arch/sh/lib/lshrdi3.c deleted file mode 100644 index 33eaa1edbc3c..000000000000 --- a/arch/sh/lib/lshrdi3.c +++ /dev/null @@ -1,30 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __lshrdi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - w.s.high = 0; - w.s.low = (unsigned int) uu.s.high >> -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.high << bm; - - w.s.high = (unsigned int) uu.s.high >> b; - w.s.low = ((unsigned int) uu.s.low >> b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__lshrdi3); diff --git a/arch/sh/math-emu/sfp-util.h b/arch/sh/math-emu/sfp-util.h index 784f541344f3..bda50762b3d3 100644 --- a/arch/sh/math-emu/sfp-util.h +++ b/arch/sh/math-emu/sfp-util.h @@ -67,7 +67,3 @@ } while (0) #define abort() return 0 - -#define __BYTE_ORDER __LITTLE_ENDIAN - - diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 5d2de10809ae..3a1548054b48 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o +obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o ifdef CONFIG_X86_64 obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index fb8b2c088681..1fbda2f94184 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -96,6 +96,11 @@ static void hv_apic_eoi_write(u32 reg, u32 val) wrmsr(HV_X64_MSR_EOI, val, 0); } +static bool cpu_is_self(int cpu) +{ + return cpu == smp_processor_id(); +} + /* * IPI implementation on Hyper-V. */ @@ -128,10 +133,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, */ if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - if (exclude_self) - nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); - else - nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); + + nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask, + exclude_self ? cpu_is_self : NULL); /* * 'nr_bank <= 0' means some CPUs in cpumask can't be diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index edbc67ec1f3e..a5f9474f08e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -63,7 +63,10 @@ static int hyperv_init_ghcb(void) * memory boundary and map it here. */ rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa); - ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB); + + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary; + ghcb_va = (void *)ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE); if (!ghcb_va) return -ENOMEM; @@ -217,7 +220,7 @@ static int hv_cpu_die(unsigned int cpu) if (hv_ghcb_pg) { ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg); if (*ghcb_va) - memunmap(*ghcb_va); + iounmap(*ghcb_va); *ghcb_va = NULL; } diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c new file mode 100644 index 000000000000..1ba5d3b99b16 --- /dev/null +++ b/arch/x86/hyperv/hv_vtl.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023, Microsoft Corporation. + * + * Author: + * Saurabh Sengar + */ + +#include +#include +#include +#include +#include +#include + +extern struct boot_params boot_params; +static struct real_mode_header hv_vtl_real_mode_header; + +void __init hv_vtl_init_platform(void) +{ + pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); + + x86_init.irqs.pre_vector_init = x86_init_noop; + x86_init.timers.timer_init = x86_init_noop; + + x86_platform.get_wallclock = get_rtc_noop; + x86_platform.set_wallclock = set_rtc_noop; + x86_platform.get_nmi_reason = hv_get_nmi_reason; + + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; + x86_platform.legacy.rtc = 0; + x86_platform.legacy.warm_reset = 0; + x86_platform.legacy.reserve_bios_regions = 0; + x86_platform.legacy.devices.pnpbios = 0; +} + +static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) +{ + return ((u64)desc->base3 << 32) | ((u64)desc->base2 << 24) | + (desc->base1 << 16) | desc->base0; +} + +static inline u32 hv_vtl_system_desc_limit(struct ldttss_desc *desc) +{ + return ((u32)desc->limit1 << 16) | (u32)desc->limit0; +} + +typedef void (*secondary_startup_64_fn)(void*, void*); +static void hv_vtl_ap_entry(void) +{ + ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params); +} + +static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) +{ + u64 status; + int ret = 0; + struct hv_enable_vp_vtl *input; + unsigned long irq_flags; + + struct desc_ptr gdt_ptr; + struct desc_ptr idt_ptr; + + struct ldttss_desc *tss; + struct ldttss_desc *ldt; + struct desc_struct *gdt; + + u64 rsp = current->thread.sp; + u64 rip = (u64)&hv_vtl_ap_entry; + + native_store_gdt(&gdt_ptr); + store_idt(&idt_ptr); + + gdt = (struct desc_struct *)((void *)(gdt_ptr.address)); + tss = (struct ldttss_desc *)(gdt + GDT_ENTRY_TSS); + ldt = (struct ldttss_desc *)(gdt + GDT_ENTRY_LDT); + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + + input->partition_id = HV_PARTITION_ID_SELF; + input->vp_index = target_vp_index; + input->target_vtl.target_vtl = HV_VTL_MGMT; + + /* + * The x86_64 Linux kernel follows the 16-bit -> 32-bit -> 64-bit + * mode transition sequence after waking up an AP with SIPI whose + * vector points to the 16-bit AP startup trampoline code. Here in + * VTL2, we can't perform that sequence as the AP has to start in + * the 64-bit mode. + * + * To make this happen, we tell the hypervisor to load a valid 64-bit + * context (most of which is just magic numbers from the CPU manual) + * so that AP jumps right to the 64-bit entry of the kernel, and the + * control registers are loaded with values that let the AP fetch the + * code and data and carry on with work it gets assigned. + */ + + input->vp_context.rip = rip; + input->vp_context.rsp = rsp; + input->vp_context.rflags = 0x0000000000000002; + input->vp_context.efer = __rdmsr(MSR_EFER); + input->vp_context.cr0 = native_read_cr0(); + input->vp_context.cr3 = __native_read_cr3(); + input->vp_context.cr4 = native_read_cr4(); + input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT); + input->vp_context.idtr.limit = idt_ptr.size; + input->vp_context.idtr.base = idt_ptr.address; + input->vp_context.gdtr.limit = gdt_ptr.size; + input->vp_context.gdtr.base = gdt_ptr.address; + + /* Non-system desc (64bit), long, code, present */ + input->vp_context.cs.selector = __KERNEL_CS; + input->vp_context.cs.base = 0; + input->vp_context.cs.limit = 0xffffffff; + input->vp_context.cs.attributes = 0xa09b; + /* Non-system desc (64bit), data, present, granularity, default */ + input->vp_context.ss.selector = __KERNEL_DS; + input->vp_context.ss.base = 0; + input->vp_context.ss.limit = 0xffffffff; + input->vp_context.ss.attributes = 0xc093; + + /* System desc (128bit), present, LDT */ + input->vp_context.ldtr.selector = GDT_ENTRY_LDT * 8; + input->vp_context.ldtr.base = hv_vtl_system_desc_base(ldt); + input->vp_context.ldtr.limit = hv_vtl_system_desc_limit(ldt); + input->vp_context.ldtr.attributes = 0x82; + + /* System desc (128bit), present, TSS, 0x8b - busy, 0x89 -- default */ + input->vp_context.tr.selector = GDT_ENTRY_TSS * 8; + input->vp_context.tr.base = hv_vtl_system_desc_base(tss); + input->vp_context.tr.limit = hv_vtl_system_desc_limit(tss); + input->vp_context.tr.attributes = 0x8b; + + status = hv_do_hypercall(HVCALL_ENABLE_VP_VTL, input, NULL); + + if (!hv_result_success(status) && + hv_result(status) != HV_STATUS_VTL_ALREADY_ENABLED) { + pr_err("HVCALL_ENABLE_VP_VTL failed for VP : %d ! [Err: %#llx\n]", + target_vp_index, status); + ret = -EINVAL; + goto free_lock; + } + + status = hv_do_hypercall(HVCALL_START_VP, input, NULL); + + if (!hv_result_success(status)) { + pr_err("HVCALL_START_VP failed for VP : %d ! [Err: %#llx]\n", + target_vp_index, status); + ret = -EINVAL; + } + +free_lock: + local_irq_restore(irq_flags); + + return ret; +} + +static int hv_vtl_apicid_to_vp_id(u32 apic_id) +{ + u64 control; + u64 status; + unsigned long irq_flags; + struct hv_get_vp_from_apic_id_in *input; + u32 *output, ret; + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + input->partition_id = HV_PARTITION_ID_SELF; + input->apic_ids[0] = apic_id; + + output = (u32 *)input; + + control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; + status = hv_do_hypercall(control, input, output); + ret = output[0]; + + local_irq_restore(irq_flags); + + if (!hv_result_success(status)) { + pr_err("failed to get vp id from apic id %d, status %#llx\n", + apic_id, status); + return -EINVAL; + } + + return ret; +} + +static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) +{ + int vp_id; + + pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); + vp_id = hv_vtl_apicid_to_vp_id(apicid); + + if (vp_id < 0) { + pr_err("Couldn't find CPU with APIC ID %d\n", apicid); + return -EINVAL; + } + if (vp_id > ms_hyperv.max_vp_index) { + pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid); + return -EINVAL; + } + + return hv_vtl_bringup_vcpu(vp_id, start_eip); +} + +static int __init hv_vtl_early_init(void) +{ + /* + * `boot_cpu_has` returns the runtime feature support, + * and here is the earliest it can be used. + */ + if (cpu_feature_enabled(X86_FEATURE_XSAVE)) + panic("XSAVE has to be disabled as it is not supported by this module.\n" + "Please add 'noxsave' to the kernel command line.\n"); + + real_mode_header = &hv_vtl_real_mode_header; + apic->wakeup_secondary_cpu_64 = hv_vtl_wakeup_secondary_cpu; + + return 0; +} +early_initcall(hv_vtl_early_init); diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index f6a020cb1a24..127d5b7b63de 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -376,34 +376,6 @@ void __init hv_vtom_init(void) #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* - * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM. - */ -void *hv_map_memory(void *addr, unsigned long size) -{ - unsigned long *pfns = kcalloc(size / PAGE_SIZE, - sizeof(unsigned long), GFP_KERNEL); - void *vaddr; - int i; - - if (!pfns) - return NULL; - - for (i = 0; i < size / PAGE_SIZE; i++) - pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) + - (ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT); - - vaddr = vmap_pfn(pfns, size / PAGE_SIZE, pgprot_decrypted(PAGE_KERNEL)); - kfree(pfns); - - return vaddr; -} - -void hv_unmap_memory(void *addr) -{ - vunmap(addr); -} - enum hv_isolation_type hv_get_isolation_type(void) { if (!(ms_hyperv.priv_high & HV_ISOLATION)) diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 0ad2378fe6ad..8460bd35e10c 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -52,6 +52,11 @@ static inline int fill_gva_list(u64 gva_list[], int offset, return gva_n - offset; } +static bool cpu_is_lazy(int cpu) +{ + return per_cpu(cpu_tlbstate_shared.is_lazy, cpu); +} + static void hyperv_flush_tlb_multi(const struct cpumask *cpus, const struct flush_tlb_info *info) { @@ -60,6 +65,7 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, struct hv_tlb_flush *flush; u64 status; unsigned long flags; + bool do_lazy = !info->freed_tables; trace_hyperv_mmu_flush_tlb_multi(cpus, info); @@ -112,6 +118,8 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, goto do_ex_hypercall; for_each_cpu(cpu, cpus) { + if (do_lazy && cpu_is_lazy(cpu)) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) { local_irq_restore(flags); @@ -198,7 +206,8 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); + nr_bank = cpumask_to_vpset_skip(&flush->hv_vp_set, cpus, + info->freed_tables ? NULL : cpu_is_lazy); if (nr_bank < 0) return HV_STATUS_INVALID_PARAMETER; diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 0b73a809e9e1..cea95dcd27c2 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -122,6 +122,9 @@ /* Recommend using enlightened VMCS */ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +/* Use hypercalls for MMIO config space access */ +#define HV_X64_USE_MMIO_HYPERCALLS BIT(21) + /* * CPU management features identification. * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. @@ -713,6 +716,81 @@ union hv_msi_entry { } __packed; }; +struct hv_x64_segment_register { + u64 base; + u32 limit; + u16 selector; + union { + struct { + u16 segment_type : 4; + u16 non_system_segment : 1; + u16 descriptor_privilege_level : 2; + u16 present : 1; + u16 reserved : 4; + u16 available : 1; + u16 _long : 1; + u16 _default : 1; + u16 granularity : 1; + } __packed; + u16 attributes; + }; +} __packed; + +struct hv_x64_table_register { + u16 pad[3]; + u16 limit; + u64 base; +} __packed; + +struct hv_init_vp_context { + u64 rip; + u64 rsp; + u64 rflags; + + struct hv_x64_segment_register cs; + struct hv_x64_segment_register ds; + struct hv_x64_segment_register es; + struct hv_x64_segment_register fs; + struct hv_x64_segment_register gs; + struct hv_x64_segment_register ss; + struct hv_x64_segment_register tr; + struct hv_x64_segment_register ldtr; + + struct hv_x64_table_register idtr; + struct hv_x64_table_register gdtr; + + u64 efer; + u64 cr0; + u64 cr3; + u64 cr4; + u64 msr_cr_pat; +} __packed; + +union hv_input_vtl { + u8 as_uint8; + struct { + u8 target_vtl: 4; + u8 use_target_vtl: 1; + u8 reserved_z: 3; + }; +} __packed; + +struct hv_enable_vp_vtl { + u64 partition_id; + u32 vp_index; + union hv_input_vtl target_vtl; + u8 mbz0; + u16 mbz1; + struct hv_init_vp_context vp_context; +} __packed; + +struct hv_get_vp_from_apic_id_in { + u64 partition_id; + union hv_input_vtl target_vtl; + u8 res[7]; + u32 apic_ids[]; +} __packed; + #include #endif diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index e3cef98a0142..b445e252aa83 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -19,6 +19,10 @@ */ #define HV_IOAPIC_BASE_ADDRESS 0xfec00000 +#define HV_VTL_NORMAL 0x0 +#define HV_VTL_SECURE 0x1 +#define HV_VTL_MGMT 0x2 + union hv_ghcb; DECLARE_STATIC_KEY_FALSE(isolation_type_snp); @@ -29,6 +33,11 @@ typedef int (*hyperv_fill_flush_list_func)( void hyperv_vector_handler(struct pt_regs *regs); +static inline unsigned char hv_get_nmi_reason(void) +{ + return 0; +} + #if IS_ENABLED(CONFIG_HYPERV) extern int hyperv_init_cpuhp; @@ -271,6 +280,12 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; } #endif /* CONFIG_HYPERV */ +#ifdef CONFIG_HYPERV_VTL_MODE +void __init hv_vtl_init_platform(void); +#else +static inline void __init hv_vtl_init_platform(void) {} +#endif + #include #endif diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index acc20ae4079d..88085f369ff6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -330,5 +330,7 @@ extern void x86_init_uint_noop(unsigned int unused); extern bool bool_x86_init_noop(void); extern void x86_op_int_noop(int cpu); extern bool x86_pnpbios_disabled(void); +extern int set_rtc_noop(const struct timespec64 *now); +extern void get_rtc_noop(struct timespec64 *now); #endif diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 315fc358e584..c7969e806c64 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -249,11 +248,6 @@ static uint32_t __init ms_hyperv_platform(void) return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; } -static unsigned char hv_get_nmi_reason(void) -{ - return 0; -} - #ifdef CONFIG_X86_LOCAL_APIC /* * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes @@ -408,12 +402,8 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); - if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) { + if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) static_branch_enable(&isolation_type_snp); -#ifdef CONFIG_SWIOTLB - swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary; -#endif - } } if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { @@ -524,6 +514,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + hv_vtl_init_platform(); #endif /* * TSC should be marked as unstable only after Hyper-V diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ecdeb0974a87..d82f4fa2f1bf 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -33,8 +33,8 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } -static int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } -static void get_rtc_noop(struct timespec64 *now) { } +int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index a5cf7f1e871c..c362f4ad80ab 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -239,9 +239,9 @@ static void put_persistent_gnt(struct xen_blkif_ring *ring, atomic_dec(&ring->persistent_gnt_in_use); } -static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *root, - unsigned int num) +static void free_persistent_gnts(struct xen_blkif_ring *ring) { + struct rb_root *root = &ring->persistent_gnts; struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct persistent_gnt *persistent_gnt; @@ -249,6 +249,9 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro int segs_to_unmap = 0; struct gntab_unmap_queue_data unmap_data; + if (RB_EMPTY_ROOT(root)) + return; + unmap_data.pages = pages; unmap_data.unmap_ops = unmap; unmap_data.kunmap_ops = NULL; @@ -277,9 +280,11 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro rb_erase(&persistent_gnt->node, root); kfree(persistent_gnt); - num--; + ring->persistent_gnt_c--; } - BUG_ON(num != 0); + + BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); + BUG_ON(ring->persistent_gnt_c != 0); } void xen_blkbk_unmap_purged_grants(struct work_struct *work) @@ -631,12 +636,7 @@ purge_gnt_list: void xen_blkbk_free_caches(struct xen_blkif_ring *ring) { /* Free all persistent grant pages */ - if (!RB_EMPTY_ROOT(&ring->persistent_gnts)) - free_persistent_gnts(ring, &ring->persistent_gnts, - ring->persistent_gnt_c); - - BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); - ring->persistent_gnt_c = 0; + free_persistent_gnts(ring); /* Since we are shutting down remove all pages from the buffer */ gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */); @@ -891,7 +891,7 @@ next: out: for (i = last_map; i < num; i++) { /* Don't zap current batch's valid persistent grants. */ - if(i >= map_until) + if (i >= map_until) pages[i]->persistent_gnt = NULL; pages[i]->handle = BLKBACK_INVALID_HANDLE; } @@ -1072,7 +1072,111 @@ static void end_block_io_op(struct bio *bio) bio_put(bio); } +static void blkif_get_x86_32_req(struct blkif_request *dst, + const struct blkif_x86_32_request *src) +{ + unsigned int i, n; + dst->operation = READ_ONCE(src->operation); + + switch (dst->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments); + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST, + dst->u.rw.nr_segments); + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = + READ_ONCE(src->u.indirect.nr_segments); + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + n = min(MAX_INDIRECT_PAGES, + INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < n; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} + +static void blkif_get_x86_64_req(struct blkif_request *dst, + const struct blkif_x86_64_request *src) +{ + unsigned int i, n; + + dst->operation = READ_ONCE(src->operation); + + switch (dst->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments); + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST, + dst->u.rw.nr_segments); + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = + READ_ONCE(src->u.indirect.nr_segments); + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + n = min(MAX_INDIRECT_PAGES, + INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < n; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} /* * Function to copy the from the ring buffer the 'struct blkif_request' diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index a28473470e66..40f67bfc052d 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -296,7 +296,7 @@ struct xen_blkif_ring { struct work_struct free_work; /* Thread shutdown wait queue. */ wait_queue_head_t shutdown_wq; - struct xen_blkif *blkif; + struct xen_blkif *blkif; }; struct xen_blkif { @@ -315,7 +315,7 @@ struct xen_blkif { atomic_t drain; struct work_struct free_work; - unsigned int nr_ring_pages; + unsigned int nr_ring_pages; bool multi_ref; /* All rings for this device. */ struct xen_blkif_ring *rings; @@ -329,7 +329,7 @@ struct seg_buf { }; struct grant_page { - struct page *page; + struct page *page; struct persistent_gnt *persistent_gnt; grant_handle_t handle; grant_ref_t gref; @@ -384,7 +384,6 @@ void xen_blkif_xenbus_fini(void); irqreturn_t xen_blkif_be_int(int irq, void *dev_id); int xen_blkif_schedule(void *arg); -int xen_blkif_purge_persistent(void *arg); void xen_blkbk_free_caches(struct xen_blkif_ring *ring); int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, @@ -395,100 +394,4 @@ int xen_blkbk_barrier(struct xenbus_transaction xbt, struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be); void xen_blkbk_unmap_purged_grants(struct work_struct *work); -static inline void blkif_get_x86_32_req(struct blkif_request *dst, - struct blkif_x86_32_request *src) -{ - int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = READ_ONCE(src->operation); - switch (dst->operation) { - case BLKIF_OP_READ: - case BLKIF_OP_WRITE: - case BLKIF_OP_WRITE_BARRIER: - case BLKIF_OP_FLUSH_DISKCACHE: - dst->u.rw.nr_segments = src->u.rw.nr_segments; - dst->u.rw.handle = src->u.rw.handle; - dst->u.rw.id = src->u.rw.id; - dst->u.rw.sector_number = src->u.rw.sector_number; - barrier(); - if (n > dst->u.rw.nr_segments) - n = dst->u.rw.nr_segments; - for (i = 0; i < n; i++) - dst->u.rw.seg[i] = src->u.rw.seg[i]; - break; - case BLKIF_OP_DISCARD: - dst->u.discard.flag = src->u.discard.flag; - dst->u.discard.id = src->u.discard.id; - dst->u.discard.sector_number = src->u.discard.sector_number; - dst->u.discard.nr_sectors = src->u.discard.nr_sectors; - break; - case BLKIF_OP_INDIRECT: - dst->u.indirect.indirect_op = src->u.indirect.indirect_op; - dst->u.indirect.nr_segments = src->u.indirect.nr_segments; - dst->u.indirect.handle = src->u.indirect.handle; - dst->u.indirect.id = src->u.indirect.id; - dst->u.indirect.sector_number = src->u.indirect.sector_number; - barrier(); - j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); - for (i = 0; i < j; i++) - dst->u.indirect.indirect_grefs[i] = - src->u.indirect.indirect_grefs[i]; - break; - default: - /* - * Don't know how to translate this op. Only get the - * ID so failure can be reported to the frontend. - */ - dst->u.other.id = src->u.other.id; - break; - } -} - -static inline void blkif_get_x86_64_req(struct blkif_request *dst, - struct blkif_x86_64_request *src) -{ - int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = READ_ONCE(src->operation); - switch (dst->operation) { - case BLKIF_OP_READ: - case BLKIF_OP_WRITE: - case BLKIF_OP_WRITE_BARRIER: - case BLKIF_OP_FLUSH_DISKCACHE: - dst->u.rw.nr_segments = src->u.rw.nr_segments; - dst->u.rw.handle = src->u.rw.handle; - dst->u.rw.id = src->u.rw.id; - dst->u.rw.sector_number = src->u.rw.sector_number; - barrier(); - if (n > dst->u.rw.nr_segments) - n = dst->u.rw.nr_segments; - for (i = 0; i < n; i++) - dst->u.rw.seg[i] = src->u.rw.seg[i]; - break; - case BLKIF_OP_DISCARD: - dst->u.discard.flag = src->u.discard.flag; - dst->u.discard.id = src->u.discard.id; - dst->u.discard.sector_number = src->u.discard.sector_number; - dst->u.discard.nr_sectors = src->u.discard.nr_sectors; - break; - case BLKIF_OP_INDIRECT: - dst->u.indirect.indirect_op = src->u.indirect.indirect_op; - dst->u.indirect.nr_segments = src->u.indirect.nr_segments; - dst->u.indirect.handle = src->u.indirect.handle; - dst->u.indirect.id = src->u.indirect.id; - dst->u.indirect.sector_number = src->u.indirect.sector_number; - barrier(); - j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); - for (i = 0; i < j; i++) - dst->u.indirect.indirect_grefs[i] = - src->u.indirect.indirect_grefs[i]; - break; - default: - /* - * Don't know how to translate this op. Only get the - * ID so failure can be reported to the frontend. - */ - dst->u.other.id = src->u.other.id; - break; - } -} - #endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */ diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index c0cef92b12b8..bcd9042a0c9f 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -49,7 +49,7 @@ static bool direct_mode_enabled; static int stimer0_irq = -1; static int stimer0_message_sint; -static DEFINE_PER_CPU(long, stimer0_evt); +static __maybe_unused DEFINE_PER_CPU(long, stimer0_evt); /* * Common code for stimer0 interrupts coming via Direct Mode or @@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(hv_stimer0_isr); * stimer0 interrupt handler for architectures that support * per-cpu interrupts, which also implies Direct Mode. */ -static irqreturn_t hv_stimer0_percpu_isr(int irq, void *dev_id) +static irqreturn_t __maybe_unused hv_stimer0_percpu_isr(int irq, void *dev_id) { hv_stimer0_isr(); return IRQ_HANDLED; @@ -196,6 +196,7 @@ void __weak hv_remove_stimer0_handler(void) { }; +#ifdef CONFIG_ACPI /* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */ static int hv_setup_stimer0_irq(void) { @@ -230,6 +231,16 @@ static void hv_remove_stimer0_irq(void) stimer0_irq = -1; } } +#else +static int hv_setup_stimer0_irq(void) +{ + return 0; +} + +static void hv_remove_stimer0_irq(void) +{ +} +#endif /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ int hv_stimer_alloc(bool have_percpu_irqs) @@ -506,9 +517,6 @@ static bool __init hv_init_tsc_clocksource(void) { union hv_reference_tsc_msr tsc_msr; - if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) - return false; - /* * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly * handles frequency and offset changes due to live migration, @@ -525,6 +533,9 @@ static bool __init hv_init_tsc_clocksource(void) hyperv_cs_msr.rating = 250; } + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return false; + hv_read_reference_counter = read_hv_clock_tsc; /* diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 0747a8f1fcee..00242107d62e 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -4,15 +4,39 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on ACPI && ((X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \ - || (ARM64 && !CPU_BIG_ENDIAN)) + depends on (X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \ + || (ACPI && ARM64 && !CPU_BIG_ENDIAN) select PARAVIRT select X86_HV_CALLBACK_VECTOR if X86 - select VMAP_PFN + select OF_EARLY_FLATTREE if OF help Select this option to run Linux as a Hyper-V client operating system. +config HYPERV_VTL_MODE + bool "Enable Linux to boot in VTL context" + depends on X86_64 && HYPERV + default n + help + Virtual Secure Mode (VSM) is a set of hypervisor capabilities and + enlightenments offered to host and guest partitions which enables + the creation and management of new security boundaries within + operating system software. + + VSM achieves and maintains isolation through Virtual Trust Levels + (VTLs). Virtual Trust Levels are hierarchical, with higher levels + being more privileged than lower levels. VTL0 is the least privileged + level, and currently only other level supported is VTL2. + + Select this option to build a Linux kernel to run at a VTL other than + the normal VTL0, which currently is only VTL2. This option + initializes the x86 platform for VTL2, and adds the ability to boot + secondary CPUs directly into 64-bit context as required for VTLs other + than 0. A kernel built with this option must run at VTL2, and will + not run as a normal guest. + + If unsure, say N + config HYPERV_TIMER def_bool HYPERV && X86 diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index cc23b90cae02..007f26d5f1a4 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -67,7 +67,7 @@ const struct vmbus_device vmbus_devs[] = { { .dev_type = HV_PCIE, HV_PCIE_GUID, .perf_device = false, - .allowed_in_isolated = false, + .allowed_in_isolated = true, }, /* Synthetic Frame Buffer */ diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index da51b50787df..5978e9dbc286 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -104,8 +104,14 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version) vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID; } - msg->monitor_page1 = vmbus_connection.monitor_pages_pa[0]; - msg->monitor_page2 = vmbus_connection.monitor_pages_pa[1]; + /* + * shared_gpa_boundary is zero in non-SNP VMs, so it's safe to always + * bitwise OR it + */ + msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]) | + ms_hyperv.shared_gpa_boundary; + msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]) | + ms_hyperv.shared_gpa_boundary; msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU); @@ -219,72 +225,27 @@ int vmbus_connect(void) * Setup the monitor notification facility. The 1st page for * parent->child and the 2nd page for child->parent */ - vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_zeroed_page(); - vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_zeroed_page(); + vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_page(); + vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_page(); if ((vmbus_connection.monitor_pages[0] == NULL) || (vmbus_connection.monitor_pages[1] == NULL)) { ret = -ENOMEM; goto cleanup; } - vmbus_connection.monitor_pages_original[0] - = vmbus_connection.monitor_pages[0]; - vmbus_connection.monitor_pages_original[1] - = vmbus_connection.monitor_pages[1]; - vmbus_connection.monitor_pages_pa[0] - = virt_to_phys(vmbus_connection.monitor_pages[0]); - vmbus_connection.monitor_pages_pa[1] - = virt_to_phys(vmbus_connection.monitor_pages[1]); + ret = set_memory_decrypted((unsigned long) + vmbus_connection.monitor_pages[0], 1); + ret |= set_memory_decrypted((unsigned long) + vmbus_connection.monitor_pages[1], 1); + if (ret) + goto cleanup; - if (hv_is_isolation_supported()) { - ret = set_memory_decrypted((unsigned long) - vmbus_connection.monitor_pages[0], - 1); - ret |= set_memory_decrypted((unsigned long) - vmbus_connection.monitor_pages[1], - 1); - if (ret) - goto cleanup; - - /* - * Isolation VM with AMD SNP needs to access monitor page via - * address space above shared gpa boundary. - */ - if (hv_isolation_type_snp()) { - vmbus_connection.monitor_pages_pa[0] += - ms_hyperv.shared_gpa_boundary; - vmbus_connection.monitor_pages_pa[1] += - ms_hyperv.shared_gpa_boundary; - - vmbus_connection.monitor_pages[0] - = memremap(vmbus_connection.monitor_pages_pa[0], - HV_HYP_PAGE_SIZE, - MEMREMAP_WB); - if (!vmbus_connection.monitor_pages[0]) { - ret = -ENOMEM; - goto cleanup; - } - - vmbus_connection.monitor_pages[1] - = memremap(vmbus_connection.monitor_pages_pa[1], - HV_HYP_PAGE_SIZE, - MEMREMAP_WB); - if (!vmbus_connection.monitor_pages[1]) { - ret = -ENOMEM; - goto cleanup; - } - } - - /* - * Set memory host visibility hvcall smears memory - * and so zero monitor pages here. - */ - memset(vmbus_connection.monitor_pages[0], 0x00, - HV_HYP_PAGE_SIZE); - memset(vmbus_connection.monitor_pages[1], 0x00, - HV_HYP_PAGE_SIZE); - - } + /* + * Set_memory_decrypted() will change the memory contents if + * decryption occurs, so zero monitor pages here. + */ + memset(vmbus_connection.monitor_pages[0], 0x00, HV_HYP_PAGE_SIZE); + memset(vmbus_connection.monitor_pages[1], 0x00, HV_HYP_PAGE_SIZE); msginfo = kzalloc(sizeof(*msginfo) + sizeof(struct vmbus_channel_initiate_contact), @@ -376,31 +337,13 @@ void vmbus_disconnect(void) vmbus_connection.int_page = NULL; } - if (hv_is_isolation_supported()) { - /* - * memunmap() checks input address is ioremap address or not - * inside. It doesn't unmap any thing in the non-SNP CVM and - * so not check CVM type here. - */ - memunmap(vmbus_connection.monitor_pages[0]); - memunmap(vmbus_connection.monitor_pages[1]); + set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); + set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); - set_memory_encrypted((unsigned long) - vmbus_connection.monitor_pages_original[0], - 1); - set_memory_encrypted((unsigned long) - vmbus_connection.monitor_pages_original[1], - 1); - } - - hv_free_hyperv_page((unsigned long) - vmbus_connection.monitor_pages_original[0]); - hv_free_hyperv_page((unsigned long) - vmbus_connection.monitor_pages_original[1]); - vmbus_connection.monitor_pages_original[0] = - vmbus_connection.monitor_pages[0] = NULL; - vmbus_connection.monitor_pages_original[1] = - vmbus_connection.monitor_pages[1] = NULL; + hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]); + hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]); + vmbus_connection.monitor_pages[0] = NULL; + vmbus_connection.monitor_pages[1] = NULL; } /* diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 8b0dd8e5244d..de6708dbe0df 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -38,42 +38,6 @@ int hv_init(void) return 0; } -/* - * Functions for allocating and freeing memory with size and - * alignment HV_HYP_PAGE_SIZE. These functions are needed because - * the guest page size may not be the same as the Hyper-V page - * size. We depend upon kmalloc() aligning power-of-two size - * allocations to the allocation size boundary, so that the - * allocated memory appears to Hyper-V as a page of the size - * it expects. - */ - -void *hv_alloc_hyperv_page(void) -{ - BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); - - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL); - else - return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); -} - -void *hv_alloc_hyperv_zeroed_page(void) -{ - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - else - return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); -} - -void hv_free_hyperv_page(unsigned long addr) -{ - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - free_page(addr); - else - kfree((void *)addr); -} - /* * hv_post_message - Post a message using the hypervisor message IPC. * @@ -84,14 +48,15 @@ int hv_post_message(union hv_connection_id connection_id, void *payload, size_t payload_size) { struct hv_input_post_message *aligned_msg; - struct hv_per_cpu_context *hv_cpu; + unsigned long flags; u64 status; if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) return -EMSGSIZE; - hv_cpu = get_cpu_ptr(hv_context.cpu_context); - aligned_msg = hv_cpu->post_msg_page; + local_irq_save(flags); + + aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg); aligned_msg->connectionid = connection_id; aligned_msg->reserved = 0; aligned_msg->message_type = message_type; @@ -106,11 +71,7 @@ int hv_post_message(union hv_connection_id connection_id, status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL); - /* Preemption must remain disabled until after the hypercall - * so some other thread can't get scheduled onto this cpu and - * corrupt the per-cpu post_msg_page - */ - put_cpu_ptr(hv_cpu); + local_irq_restore(flags); return hv_result(status); } @@ -162,12 +123,6 @@ int hv_synic_alloc(void) goto err; } } - - hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->post_msg_page == NULL) { - pr_err("Unable to allocate post msg page\n"); - goto err; - } } return 0; @@ -190,7 +145,6 @@ void hv_synic_free(void) free_page((unsigned long)hv_cpu->synic_event_page); free_page((unsigned long)hv_cpu->synic_message_page); - free_page((unsigned long)hv_cpu->post_msg_page); } kfree(hv_context.hv_numa_map); @@ -217,11 +171,13 @@ void hv_synic_enable_regs(unsigned int cpu) simp.simp_enabled = 1; if (hv_isolation_type_snp() || hv_root_partition) { + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & + ~ms_hyperv.shared_gpa_boundary; hv_cpu->synic_message_page - = memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT, - HV_HYP_PAGE_SIZE, MEMREMAP_WB); + = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_message_page) - pr_err("Fail to map syinc message page.\n"); + pr_err("Fail to map synic message page.\n"); } else { simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page) >> HV_HYP_PAGE_SHIFT; @@ -234,12 +190,13 @@ void hv_synic_enable_regs(unsigned int cpu) siefp.siefp_enabled = 1; if (hv_isolation_type_snp() || hv_root_partition) { - hv_cpu->synic_event_page = - memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT, - HV_HYP_PAGE_SIZE, MEMREMAP_WB); - + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & + ~ms_hyperv.shared_gpa_boundary; + hv_cpu->synic_event_page + = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_event_page) - pr_err("Fail to map syinc event page.\n"); + pr_err("Fail to map synic event page.\n"); } else { siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page) >> HV_HYP_PAGE_SHIFT; @@ -316,7 +273,7 @@ void hv_synic_disable_regs(unsigned int cpu) */ simp.simp_enabled = 0; if (hv_isolation_type_snp() || hv_root_partition) { - memunmap(hv_cpu->synic_message_page); + iounmap(hv_cpu->synic_message_page); hv_cpu->synic_message_page = NULL; } else { simp.base_simp_gpa = 0; @@ -328,7 +285,7 @@ void hv_synic_disable_regs(unsigned int cpu) siefp.siefp_enabled = 0; if (hv_isolation_type_snp() || hv_root_partition) { - memunmap(hv_cpu->synic_event_page); + iounmap(hv_cpu->synic_event_page); hv_cpu->synic_event_page = NULL; } else { siefp.base_siefp_gpa = 0; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 52a6f89ccdbd..64f9ceca887b 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -17,8 +17,11 @@ #include #include #include +#include #include #include +#include +#include #include #include #include @@ -54,6 +57,10 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); void * __percpu *hyperv_pcpu_output_arg; EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg); +static void hv_kmsg_dump_unregister(void); + +static struct ctl_table_header *hv_ctl_table_hdr; + /* * Hyper-V specific initialization and shutdown code that is * common across all architectures. Called from architecture @@ -62,6 +69,12 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg); void __init hv_common_free(void) { + unregister_sysctl_table(hv_ctl_table_hdr); + hv_ctl_table_hdr = NULL; + + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + hv_kmsg_dump_unregister(); + kfree(hv_vp_index); hv_vp_index = NULL; @@ -72,10 +85,203 @@ void __init hv_common_free(void) hyperv_pcpu_input_arg = NULL; } +/* + * Functions for allocating and freeing memory with size and + * alignment HV_HYP_PAGE_SIZE. These functions are needed because + * the guest page size may not be the same as the Hyper-V page + * size. We depend upon kmalloc() aligning power-of-two size + * allocations to the allocation size boundary, so that the + * allocated memory appears to Hyper-V as a page of the size + * it expects. + */ + +void *hv_alloc_hyperv_page(void) +{ + BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); + + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + return (void *)__get_free_page(GFP_KERNEL); + else + return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page); + +void *hv_alloc_hyperv_zeroed_page(void) +{ + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + else + return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page); + +void hv_free_hyperv_page(unsigned long addr) +{ + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + free_page(addr); + else + kfree((void *)addr); +} +EXPORT_SYMBOL_GPL(hv_free_hyperv_page); + +static void *hv_panic_page; + +/* + * Boolean to control whether to report panic messages over Hyper-V. + * + * It can be set via /proc/sys/kernel/hyperv_record_panic_msg + */ +static int sysctl_record_panic_msg = 1; + +/* + * sysctl option to allow the user to control whether kmsg data should be + * reported to Hyper-V on panic. + */ +static struct ctl_table hv_ctl_table[] = { + { + .procname = "hyperv_record_panic_msg", + .data = &sysctl_record_panic_msg, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + {} +}; + +static int hv_die_panic_notify_crash(struct notifier_block *self, + unsigned long val, void *args); + +static struct notifier_block hyperv_die_report_block = { + .notifier_call = hv_die_panic_notify_crash, +}; + +static struct notifier_block hyperv_panic_report_block = { + .notifier_call = hv_die_panic_notify_crash, +}; + +/* + * The following callback works both as die and panic notifier; its + * goal is to provide panic information to the hypervisor unless the + * kmsg dumper is used [see hv_kmsg_dump()], which provides more + * information but isn't always available. + * + * Notice that both the panic/die report notifiers are registered only + * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set. + */ +static int hv_die_panic_notify_crash(struct notifier_block *self, + unsigned long val, void *args) +{ + struct pt_regs *regs; + bool is_die; + + /* Don't notify Hyper-V unless we have a die oops event or panic. */ + if (self == &hyperv_panic_report_block) { + is_die = false; + regs = current_pt_regs(); + } else { /* die event */ + if (val != DIE_OOPS) + return NOTIFY_DONE; + + is_die = true; + regs = ((struct die_args *)args)->regs; + } + + /* + * Hyper-V should be notified only once about a panic/die. If we will + * be calling hv_kmsg_dump() later with kmsg data, don't do the + * notification here. + */ + if (!sysctl_record_panic_msg || !hv_panic_page) + hyperv_report_panic(regs, val, is_die); + + return NOTIFY_DONE; +} + +/* + * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg + * buffer and call into Hyper-V to transfer the data. + */ +static void hv_kmsg_dump(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + struct kmsg_dump_iter iter; + size_t bytes_written; + + /* We are only interested in panics. */ + if (reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg) + return; + + /* + * Write dump contents to the page. No need to synchronize; panic should + * be single-threaded. + */ + kmsg_dump_rewind(&iter); + kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, + &bytes_written); + if (!bytes_written) + return; + /* + * P3 to contain the physical address of the panic page & P4 to + * contain the size of the panic data in that page. Rest of the + * registers are no-op when the NOTIFY_MSG flag is set. + */ + hv_set_register(HV_REGISTER_CRASH_P0, 0); + hv_set_register(HV_REGISTER_CRASH_P1, 0); + hv_set_register(HV_REGISTER_CRASH_P2, 0); + hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); + + /* + * Let Hyper-V know there is crash data available along with + * the panic message. + */ + hv_set_register(HV_REGISTER_CRASH_CTL, + (HV_CRASH_CTL_CRASH_NOTIFY | + HV_CRASH_CTL_CRASH_NOTIFY_MSG)); +} + +static struct kmsg_dumper hv_kmsg_dumper = { + .dump = hv_kmsg_dump, +}; + +static void hv_kmsg_dump_unregister(void) +{ + kmsg_dump_unregister(&hv_kmsg_dumper); + unregister_die_notifier(&hyperv_die_report_block); + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_report_block); + + hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_panic_page = NULL; +} + +static void hv_kmsg_dump_register(void) +{ + int ret; + + hv_panic_page = hv_alloc_hyperv_zeroed_page(); + if (!hv_panic_page) { + pr_err("Hyper-V: panic message page memory allocation failed\n"); + return; + } + + ret = kmsg_dump_register(&hv_kmsg_dumper); + if (ret) { + pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); + hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_panic_page = NULL; + } +} + int __init hv_common_init(void) { int i; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Hyper-V expects to get crash register data or kmsg when * crash enlightment is available and system crashes. Set @@ -84,8 +290,33 @@ int __init hv_common_init(void) * kernel. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { + u64 hyperv_crash_ctl; + crash_kexec_post_notifiers = true; pr_info("Hyper-V: enabling crash_kexec_post_notifiers\n"); + + /* + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. + */ + hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table); + if (!hv_ctl_table_hdr) + pr_err("Hyper-V: sysctl table register error"); + + /* + * Register for panic kmsg callback only if the right + * capability is supported by the hypervisor. + */ + hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); + if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) + hv_kmsg_dump_register(); + + register_die_notifier(&hyperv_die_report_block); + atomic_notifier_chain_register(&panic_notifier_list, + &hyperv_panic_report_block); } /* @@ -311,14 +542,3 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_s return HV_STATUS_INVALID_PARAMETER; } EXPORT_SYMBOL_GPL(hv_ghcb_hypercall); - -void __weak *hv_map_memory(void *addr, unsigned long size) -{ - return NULL; -} -EXPORT_SYMBOL_GPL(hv_map_memory); - -void __weak hv_unmap_memory(void *addr) -{ -} -EXPORT_SYMBOL_GPL(hv_unmap_memory); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index dc673edf053c..55f2086841ae 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -122,10 +122,6 @@ enum { struct hv_per_cpu_context { void *synic_message_page; void *synic_event_page; - /* - * buffer to post messages to the host. - */ - void *post_msg_page; /* * Starting with win8, we can take channel interrupts on any CPU; @@ -241,8 +237,6 @@ struct vmbus_connection { * is child->parent notification */ struct hv_monitor_page *monitor_pages[2]; - void *monitor_pages_original[2]; - phys_addr_t monitor_pages_pa[2]; struct list_head chn_msg_list; spinlock_t channelmsg_lock; diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 2111e97c3b63..3c9b02471760 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -186,8 +186,6 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt, u32 max_pkt_size) { struct page **pages_wraparound; - unsigned long *pfns_wraparound; - u64 pfn; int i; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); @@ -196,50 +194,30 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ - if (hv_isolation_type_snp()) { - pfn = page_to_pfn(pages) + - PFN_DOWN(ms_hyperv.shared_gpa_boundary); + pages_wraparound = kcalloc(page_cnt * 2 - 1, + sizeof(struct page *), + GFP_KERNEL); + if (!pages_wraparound) + return -ENOMEM; - pfns_wraparound = kcalloc(page_cnt * 2 - 1, - sizeof(unsigned long), GFP_KERNEL); - if (!pfns_wraparound) - return -ENOMEM; + pages_wraparound[0] = pages; + for (i = 0; i < 2 * (page_cnt - 1); i++) + pages_wraparound[i + 1] = + &pages[i % (page_cnt - 1) + 1]; - pfns_wraparound[0] = pfn; - for (i = 0; i < 2 * (page_cnt - 1); i++) - pfns_wraparound[i + 1] = pfn + i % (page_cnt - 1) + 1; + ring_info->ring_buffer = (struct hv_ring_buffer *) + vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, + pgprot_decrypted(PAGE_KERNEL)); - ring_info->ring_buffer = (struct hv_ring_buffer *) - vmap_pfn(pfns_wraparound, page_cnt * 2 - 1, - pgprot_decrypted(PAGE_KERNEL)); - kfree(pfns_wraparound); - - if (!ring_info->ring_buffer) - return -ENOMEM; - - /* Zero ring buffer after setting memory host visibility. */ - memset(ring_info->ring_buffer, 0x00, PAGE_SIZE * page_cnt); - } else { - pages_wraparound = kcalloc(page_cnt * 2 - 1, - sizeof(struct page *), - GFP_KERNEL); - if (!pages_wraparound) - return -ENOMEM; - - pages_wraparound[0] = pages; - for (i = 0; i < 2 * (page_cnt - 1); i++) - pages_wraparound[i + 1] = - &pages[i % (page_cnt - 1) + 1]; - - ring_info->ring_buffer = (struct hv_ring_buffer *) - vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, - PAGE_KERNEL); - - kfree(pages_wraparound); - if (!ring_info->ring_buffer) - return -ENOMEM; - } + kfree(pages_wraparound); + if (!ring_info->ring_buffer) + return -ENOMEM; + /* + * Ensure the header page is zero'ed since + * encryption status may have changed. + */ + memset(ring_info->ring_buffer, 0, HV_HYP_PAGE_SIZE); ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 1ab4f9115100..1c65a6dfb9fa 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -19,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -28,7 +30,6 @@ #include #include #include -#include #include #include #include @@ -44,30 +45,16 @@ struct vmbus_dynid { struct hv_vmbus_device_id id; }; -static struct acpi_device *hv_acpi_dev; +static struct device *hv_dev; static int hyperv_cpuhp_online; -static void *hv_panic_page; - static long __percpu *vmbus_evt; /* Values parsed from ACPI DSDT */ int vmbus_irq; int vmbus_interrupt; -/* - * Boolean to control whether to report panic messages over Hyper-V. - * - * It can be set via /proc/sys/kernel/hyperv_record_panic_msg - */ -static int sysctl_record_panic_msg = 1; - -static int hyperv_report_reg(void) -{ - return !sysctl_record_panic_msg || !hv_panic_page; -} - /* * The panic notifier below is responsible solely for unloading the * vmbus connection, which is necessary in a panic event. @@ -88,54 +75,6 @@ static struct notifier_block hyperv_panic_vmbus_unload_block = { .priority = INT_MIN + 1, /* almost the latest one to execute */ }; -static int hv_die_panic_notify_crash(struct notifier_block *self, - unsigned long val, void *args); - -static struct notifier_block hyperv_die_report_block = { - .notifier_call = hv_die_panic_notify_crash, -}; -static struct notifier_block hyperv_panic_report_block = { - .notifier_call = hv_die_panic_notify_crash, -}; - -/* - * The following callback works both as die and panic notifier; its - * goal is to provide panic information to the hypervisor unless the - * kmsg dumper is used [see hv_kmsg_dump()], which provides more - * information but isn't always available. - * - * Notice that both the panic/die report notifiers are registered only - * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set. - */ -static int hv_die_panic_notify_crash(struct notifier_block *self, - unsigned long val, void *args) -{ - struct pt_regs *regs; - bool is_die; - - /* Don't notify Hyper-V unless we have a die oops event or panic. */ - if (self == &hyperv_panic_report_block) { - is_die = false; - regs = current_pt_regs(); - } else { /* die event */ - if (val != DIE_OOPS) - return NOTIFY_DONE; - - is_die = true; - regs = ((struct die_args *)args)->regs; - } - - /* - * Hyper-V should be notified only once about a panic/die. If we will - * be calling hv_kmsg_dump() later with kmsg data, don't do the - * notification here. - */ - if (hyperv_report_reg()) - hyperv_report_panic(regs, val, is_die); - - return NOTIFY_DONE; -} - static const char *fb_mmio_name = "fb_range"; static struct resource *fb_mmio; static struct resource *hyperv_mmio; @@ -143,7 +82,7 @@ static DEFINE_MUTEX(hyperv_mmio_lock); static int vmbus_exists(void) { - if (hv_acpi_dev == NULL) + if (hv_dev == NULL) return -ENODEV; return 0; @@ -932,7 +871,7 @@ static int vmbus_dma_configure(struct device *child_device) * On x86/x64 coherence is assumed and these calls have no effect. */ hv_setup_dma_ops(child_device, - device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + device_get_dma_attr(hv_dev) == DEV_DMA_COHERENT); return 0; } @@ -1377,98 +1316,6 @@ static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id) return IRQ_HANDLED; } -/* - * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg - * buffer and call into Hyper-V to transfer the data. - */ -static void hv_kmsg_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) -{ - struct kmsg_dump_iter iter; - size_t bytes_written; - - /* We are only interested in panics. */ - if ((reason != KMSG_DUMP_PANIC) || (!sysctl_record_panic_msg)) - return; - - /* - * Write dump contents to the page. No need to synchronize; panic should - * be single-threaded. - */ - kmsg_dump_rewind(&iter); - kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, - &bytes_written); - if (!bytes_written) - return; - /* - * P3 to contain the physical address of the panic page & P4 to - * contain the size of the panic data in that page. Rest of the - * registers are no-op when the NOTIFY_MSG flag is set. - */ - hv_set_register(HV_REGISTER_CRASH_P0, 0); - hv_set_register(HV_REGISTER_CRASH_P1, 0); - hv_set_register(HV_REGISTER_CRASH_P2, 0); - hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); - hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); - - /* - * Let Hyper-V know there is crash data available along with - * the panic message. - */ - hv_set_register(HV_REGISTER_CRASH_CTL, - (HV_CRASH_CTL_CRASH_NOTIFY | HV_CRASH_CTL_CRASH_NOTIFY_MSG)); -} - -static struct kmsg_dumper hv_kmsg_dumper = { - .dump = hv_kmsg_dump, -}; - -static void hv_kmsg_dump_register(void) -{ - int ret; - - hv_panic_page = hv_alloc_hyperv_zeroed_page(); - if (!hv_panic_page) { - pr_err("Hyper-V: panic message page memory allocation failed\n"); - return; - } - - ret = kmsg_dump_register(&hv_kmsg_dumper); - if (ret) { - pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); - hv_free_hyperv_page((unsigned long)hv_panic_page); - hv_panic_page = NULL; - } -} - -static struct ctl_table_header *hv_ctl_table_hdr; - -/* - * sysctl option to allow the user to control whether kmsg data should be - * reported to Hyper-V on panic. - */ -static struct ctl_table hv_ctl_table[] = { - { - .procname = "hyperv_record_panic_msg", - .data = &sysctl_record_panic_msg, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE - }, - {} -}; - -static struct ctl_table hv_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = hv_ctl_table - }, - {} -}; - /* * vmbus_bus_init -Main vmbus driver initialization routine. * @@ -1532,38 +1379,6 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; - if (hv_is_isolation_supported()) - sysctl_record_panic_msg = 0; - - /* - * Only register if the crash MSRs are available - */ - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { - u64 hyperv_crash_ctl; - /* - * Panic message recording (sysctl_record_panic_msg) - * is enabled by default in non-isolated guests and - * disabled by default in isolated guests; the panic - * message recording won't be available in isolated - * guests should the following registration fail. - */ - hv_ctl_table_hdr = register_sysctl_table(hv_root_table); - if (!hv_ctl_table_hdr) - pr_err("Hyper-V: sysctl table register error"); - - /* - * Register for panic kmsg callback only if the right - * capability is supported by the hypervisor. - */ - hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); - if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) - hv_kmsg_dump_register(); - - register_die_notifier(&hyperv_die_report_block); - atomic_notifier_chain_register(&panic_notifier_list, - &hyperv_panic_report_block); - } - /* * Always register the vmbus unload panic notifier because we * need to shut the VMbus channel connection on panic. @@ -1588,8 +1403,6 @@ err_alloc: } err_setup: bus_unregister(&hv_bus); - unregister_sysctl_table(hv_ctl_table_hdr); - hv_ctl_table_hdr = NULL; return ret; } @@ -2090,7 +1903,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) &child_device_obj->channel->offermsg.offer.if_instance); child_device_obj->device.bus = &hv_bus; - child_device_obj->device.parent = &hv_acpi_dev->dev; + child_device_obj->device.parent = hv_dev; child_device_obj->device.release = vmbus_device_release; child_device_obj->device.dma_parms = &child_device_obj->dma_parms; @@ -2151,7 +1964,7 @@ void vmbus_device_unregister(struct hv_device *device_obj) device_unregister(&device_obj->device); } - +#ifdef CONFIG_ACPI /* * VMBUS is an acpi enumerated device. Get the information we * need from DSDT. @@ -2260,8 +2073,9 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) return AE_OK; } +#endif -static void vmbus_acpi_remove(struct acpi_device *device) +static void vmbus_mmio_remove(void) { struct resource *cur_res; struct resource *next_res; @@ -2280,7 +2094,7 @@ static void vmbus_acpi_remove(struct acpi_device *device) } } -static void vmbus_reserve_fb(void) +static void __maybe_unused vmbus_reserve_fb(void) { resource_size_t start = 0, size; struct pci_dev *pdev; @@ -2440,13 +2254,15 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size) } EXPORT_SYMBOL_GPL(vmbus_free_mmio); -static int vmbus_acpi_add(struct acpi_device *device) +#ifdef CONFIG_ACPI +static int vmbus_acpi_add(struct platform_device *pdev) { acpi_status result; int ret_val = -ENODEV; struct acpi_device *ancestor; + struct acpi_device *device = ACPI_COMPANION(&pdev->dev); - hv_acpi_dev = device; + hv_dev = &device->dev; /* * Older versions of Hyper-V for ARM64 fail to include the _CCA @@ -2488,9 +2304,64 @@ static int vmbus_acpi_add(struct acpi_device *device) acpi_walk_err: if (ret_val) - vmbus_acpi_remove(device); + vmbus_mmio_remove(); return ret_val; } +#else +static int vmbus_acpi_add(struct platform_device *pdev) +{ + return 0; +} +#endif + +static int vmbus_device_add(struct platform_device *pdev) +{ + struct resource **cur_res = &hyperv_mmio; + struct of_range range; + struct of_range_parser parser; + struct device_node *np = pdev->dev.of_node; + int ret; + + hv_dev = &pdev->dev; + + ret = of_range_parser_init(&parser, np); + if (ret) + return ret; + + for_each_of_range(&parser, &range) { + struct resource *res; + + res = kzalloc(sizeof(*res), GFP_KERNEL); + if (!res) { + vmbus_mmio_remove(); + return -ENOMEM; + } + + res->name = "hyperv mmio"; + res->flags = range.flags; + res->start = range.cpu_addr; + res->end = range.cpu_addr + range.size; + + *cur_res = res; + cur_res = &res->sibling; + } + + return ret; +} + +static int vmbus_platform_driver_probe(struct platform_device *pdev) +{ + if (acpi_disabled) + return vmbus_device_add(pdev); + else + return vmbus_acpi_add(pdev); +} + +static int vmbus_platform_driver_remove(struct platform_device *pdev) +{ + vmbus_mmio_remove(); + return 0; +} #ifdef CONFIG_PM_SLEEP static int vmbus_bus_suspend(struct device *dev) @@ -2629,7 +2500,17 @@ static int vmbus_bus_resume(struct device *dev) #define vmbus_bus_resume NULL #endif /* CONFIG_PM_SLEEP */ -static const struct acpi_device_id vmbus_acpi_device_ids[] = { +static const __maybe_unused struct of_device_id vmbus_of_match[] = { + { + .compatible = "microsoft,vmbus", + }, + { + /* sentinel */ + }, +}; +MODULE_DEVICE_TABLE(of, vmbus_of_match); + +static const __maybe_unused struct acpi_device_id vmbus_acpi_device_ids[] = { {"VMBUS", 0}, {"VMBus", 0}, {"", 0}, @@ -2657,15 +2538,16 @@ static const struct dev_pm_ops vmbus_bus_pm = { .restore_noirq = vmbus_bus_resume }; -static struct acpi_driver vmbus_acpi_driver = { - .name = "vmbus", - .ids = vmbus_acpi_device_ids, - .ops = { - .add = vmbus_acpi_add, - .remove = vmbus_acpi_remove, - }, - .drv.pm = &vmbus_bus_pm, - .drv.probe_type = PROBE_FORCE_SYNCHRONOUS, +static struct platform_driver vmbus_platform_driver = { + .probe = vmbus_platform_driver_probe, + .remove = vmbus_platform_driver_remove, + .driver = { + .name = "vmbus", + .acpi_match_table = ACPI_PTR(vmbus_acpi_device_ids), + .of_match_table = of_match_ptr(vmbus_of_match), + .pm = &vmbus_bus_pm, + .probe_type = PROBE_FORCE_SYNCHRONOUS, + } }; static void hv_kexec_handler(void) @@ -2749,12 +2631,11 @@ static int __init hv_acpi_init(void) /* * Get ACPI resources first. */ - ret = acpi_bus_register_driver(&vmbus_acpi_driver); - + ret = platform_driver_register(&vmbus_platform_driver); if (ret) return ret; - if (!hv_acpi_dev) { + if (!hv_dev) { ret = -ENODEV; goto cleanup; } @@ -2784,8 +2665,8 @@ static int __init hv_acpi_init(void) return 0; cleanup: - acpi_bus_unregister_driver(&vmbus_acpi_driver); - hv_acpi_dev = NULL; + platform_driver_unregister(&vmbus_platform_driver); + hv_dev = NULL; return ret; } @@ -2817,13 +2698,6 @@ static void __exit vmbus_exit(void) vmbus_free_channels(); kfree(vmbus_connection.channels); - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { - kmsg_dump_unregister(&hv_kmsg_dumper); - unregister_die_notifier(&hyperv_die_report_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_report_block); - } - /* * The vmbus panic notifier is always registered, hence we should * also unconditionally unregister it here as well. @@ -2831,14 +2705,11 @@ static void __exit vmbus_exit(void) atomic_notifier_chain_unregister(&panic_notifier_list, &hyperv_panic_vmbus_unload_block); - free_page((unsigned long)hv_panic_page); - unregister_sysctl_table(hv_ctl_table_hdr); - hv_ctl_table_hdr = NULL; bus_unregister(&hv_bus); cpuhp_remove_state(hyperv_cpuhp_online); hv_synic_free(); - acpi_bus_unregister_driver(&vmbus_acpi_driver); + platform_driver_unregister(&vmbus_platform_driver); } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 1a6a7a672ad7..046c355e120b 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -54,7 +54,6 @@ static DEFINE_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; -static unsigned int timer_cpu_pin; static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller; #ifdef CONFIG_GENERIC_IRQ_IPI @@ -499,9 +498,6 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, */ switch (intr) { case GIC_LOCAL_INT_TIMER: - /* CONFIG_MIPS_CMP workaround (see __gic_init) */ - map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin; - fallthrough; case GIC_LOCAL_INT_PERFCTR: case GIC_LOCAL_INT_FDC: /* @@ -795,34 +791,12 @@ static int __init gic_of_init(struct device_node *node, if (cpu_has_veic) { /* Always use vector 1 in EIC mode */ gic_cpu_pin = 0; - timer_cpu_pin = gic_cpu_pin; set_vi_handler(gic_cpu_pin + GIC_PIN_TO_VEC_OFFSET, __gic_irq_dispatch); } else { gic_cpu_pin = cpu_vec - GIC_CPU_PIN_OFFSET; irq_set_chained_handler(MIPS_CPU_IRQ_BASE + cpu_vec, gic_irq_dispatch); - /* - * With the CMP implementation of SMP (deprecated), other CPUs - * are started by the bootloader and put into a timer based - * waiting poll loop. We must not re-route those CPU's local - * timer interrupts as the wait instruction will never finish, - * so just handle whatever CPU interrupt it is routed to by - * default. - * - * This workaround should be removed when CMP support is - * dropped. - */ - if (IS_ENABLED(CONFIG_MIPS_CMP) && - gic_local_irq_is_routable(GIC_LOCAL_INT_TIMER)) { - timer_cpu_pin = read_gic_vl_timer_map() & GIC_MAP_PIN_MAP; - irq_set_chained_handler(MIPS_CPU_IRQ_BASE + - GIC_CPU_PIN_OFFSET + - timer_cpu_pin, - gic_irq_dispatch); - } else { - timer_cpu_pin = gic_cpu_pin; - } } gic_irq_domain = irq_domain_add_simple(node, GIC_NUM_LOCAL_INTRS + diff --git a/drivers/md/md.c b/drivers/md/md.c index 2003cf86fb8d..8e344b4b3444 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -322,26 +322,6 @@ static struct ctl_table raid_table[] = { { } }; -static struct ctl_table raid_dir_table[] = { - { - .procname = "raid", - .maxlen = 0, - .mode = S_IRUGO|S_IXUGO, - .child = raid_table, - }, - { } -}; - -static struct ctl_table raid_root_table[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = raid_dir_table, - }, - { } -}; - static int start_readonly; /* @@ -9653,7 +9633,7 @@ static int __init md_init(void) mdp_major = ret; register_reboot_notifier(&md_notifier); - raid_table_header = register_sysctl_table(raid_root_table); + raid_table_header = register_sysctl("dev/raid", raid_table); md_geninit(); return 0; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index dd5919ec408b..33d51e363913 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1139,7 +1139,6 @@ struct netvsc_device { /* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; - void *recv_original_buf; u32 recv_buf_size; /* allocated bytes */ struct vmbus_gpadl recv_buf_gpadl_handle; u32 recv_section_cnt; @@ -1148,7 +1147,6 @@ struct netvsc_device { /* Send buffer allocated by us */ void *send_buf; - void *send_original_buf; u32 send_buf_size; struct vmbus_gpadl send_buf_gpadl_handle; u32 send_section_cnt; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index da737d959e81..82e9796c8f5e 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -154,17 +154,8 @@ static void free_netvsc_device(struct rcu_head *head) int i; kfree(nvdev->extension); - - if (nvdev->recv_original_buf) - vfree(nvdev->recv_original_buf); - else - vfree(nvdev->recv_buf); - - if (nvdev->send_original_buf) - vfree(nvdev->send_original_buf); - else - vfree(nvdev->send_buf); - + vfree(nvdev->recv_buf); + vfree(nvdev->send_buf); bitmap_free(nvdev->send_section_map); for (i = 0; i < VRSS_CHANNEL_MAX; i++) { @@ -347,7 +338,6 @@ static int netvsc_init_buf(struct hv_device *device, struct nvsp_message *init_packet; unsigned int buf_size; int i, ret = 0; - void *vaddr; /* Get receive buffer area. */ buf_size = device_info->recv_sections * device_info->recv_section_size; @@ -383,17 +373,6 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } - if (hv_isolation_type_snp()) { - vaddr = hv_map_memory(net_device->recv_buf, buf_size); - if (!vaddr) { - ret = -ENOMEM; - goto cleanup; - } - - net_device->recv_original_buf = net_device->recv_buf; - net_device->recv_buf = vaddr; - } - /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -497,17 +476,6 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } - if (hv_isolation_type_snp()) { - vaddr = hv_map_memory(net_device->send_buf, buf_size); - if (!vaddr) { - ret = -ENOMEM; - goto cleanup; - } - - net_device->send_original_buf = net_device->send_buf; - net_device->send_buf = vaddr; - } - /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -762,12 +730,6 @@ void netvsc_device_remove(struct hv_device *device) netvsc_teardown_send_gpadl(device, net_device, ndev); } - if (net_device->recv_original_buf) - hv_unmap_memory(net_device->recv_buf); - - if (net_device->send_original_buf) - hv_unmap_memory(net_device->send_buf); - /* Release all resources */ free_netvsc_device_rcu(net_device); } @@ -1844,12 +1806,6 @@ cleanup: netif_napi_del(&net_device->chan_table[0].napi); cleanup2: - if (net_device->recv_original_buf) - hv_unmap_memory(net_device->recv_buf); - - if (net_device->send_original_buf) - hv_unmap_memory(net_device->send_buf); - free_netvsc_device(&net_device->rcu); return ERR_PTR(ret); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f33370b75628..bc32662c6bb7 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -508,19 +508,11 @@ struct hv_pcibus_device { struct msi_domain_info msi_info; struct irq_domain *irq_domain; - spinlock_t retarget_msi_interrupt_lock; - struct workqueue_struct *wq; /* Highest slot of child device with resources allocated */ int wslot_res_allocated; - - /* hypercall arg, must not cross page boundary */ - struct hv_retarget_device_interrupt retarget_msi_interrupt_params; - - /* - * Don't put anything here: retarget_msi_interrupt_params must be last - */ + bool use_calls; /* Use hypercalls to access mmio cfg space */ }; /* @@ -644,9 +636,9 @@ static void hv_arch_irq_unmask(struct irq_data *data) hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; - spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); + local_irq_save(flags); - params = &hbus->retarget_msi_interrupt_params; + params = *this_cpu_ptr(hyperv_pcpu_input_arg); memset(params, 0, sizeof(*params)); params->partition_id = HV_PARTITION_ID_SELF; params->int_entry.source = HV_INTERRUPT_SOURCE_MSI; @@ -679,7 +671,7 @@ static void hv_arch_irq_unmask(struct irq_data *data) if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) { res = 1; - goto exit_unlock; + goto out; } cpumask_and(tmp, dest, cpu_online_mask); @@ -688,7 +680,7 @@ static void hv_arch_irq_unmask(struct irq_data *data) if (nr_bank <= 0) { res = 1; - goto exit_unlock; + goto out; } /* @@ -707,8 +699,8 @@ static void hv_arch_irq_unmask(struct irq_data *data) res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17), params, NULL); -exit_unlock: - spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags); +out: + local_irq_restore(flags); /* * During hibernation, when a CPU is offlined, the kernel tries @@ -1041,6 +1033,70 @@ static int wslot_to_devfn(u32 wslot) return PCI_DEVFN(slot_no.bits.dev, slot_no.bits.func); } +static void hv_pci_read_mmio(struct device *dev, phys_addr_t gpa, int size, u32 *val) +{ + struct hv_mmio_read_input *in; + struct hv_mmio_read_output *out; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument page. Use it for + * both input and output. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + out = *this_cpu_ptr(hyperv_pcpu_input_arg) + sizeof(*in); + in->gpa = gpa; + in->size = size; + + ret = hv_do_hypercall(HVCALL_MMIO_READ, in, out); + if (hv_result_success(ret)) { + switch (size) { + case 1: + *val = *(u8 *)(out->data); + break; + case 2: + *val = *(u16 *)(out->data); + break; + default: + *val = *(u32 *)(out->data); + break; + } + } else + dev_err(dev, "MMIO read hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + +static void hv_pci_write_mmio(struct device *dev, phys_addr_t gpa, int size, u32 val) +{ + struct hv_mmio_write_input *in; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument memory. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + in->gpa = gpa; + in->size = size; + switch (size) { + case 1: + *(u8 *)(in->data) = val; + break; + case 2: + *(u16 *)(in->data) = val; + break; + default: + *(u32 *)(in->data) = val; + break; + } + + ret = hv_do_hypercall(HVCALL_MMIO_WRITE, in, NULL); + if (!hv_result_success(ret)) + dev_err(dev, "MMIO write hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + /* * PCI Configuration Space for these root PCI buses is implemented as a pair * of pages in memory-mapped I/O space. Writing to the first page chooses @@ -1059,8 +1115,10 @@ static int wslot_to_devfn(u32 wslot) static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, int size, u32 *val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; /* * If the attempt is to read the IDs or the ROM BAR, simulate that. @@ -1088,56 +1146,79 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, */ *val = 0; } else if (where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - switch (size) { - case 1: - *val = readb(addr); - break; - case 2: - *val = readw(addr); - break; - default: - *val = readl(addr); - break; + + spin_lock_irqsave(&hbus->config_lock, flags); + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before reading. */ + mb(); + /* Read from that function's config space. */ + switch (size) { + case 1: + *val = readb(addr); + break; + case 2: + *val = readw(addr); + break; + default: + *val = readl(addr); + break; + } + /* + * Make sure the read was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the read was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to read beyond a function's config space.\n"); + dev_err(dev, "Attempt to read beyond a function's config space.\n"); } } static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + u32 val; u16 ret; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + - PCI_VENDOR_ID; - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + spin_lock_irqsave(&hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - ret = readw(addr); - /* - * mb() is not required here, because the spin_unlock_irqrestore() - * is a barrier. - */ + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + + CFG_PAGE_OFFSET + PCI_VENDOR_ID; - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, 2, &val); + ret = val; /* Truncates to 16 bits */ + } else { + void __iomem *addr = hbus->cfg_addr + CFG_PAGE_OFFSET + + PCI_VENDOR_ID; + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + ret = readw(addr); + /* + * mb() is not required here, because the + * spin_unlock_irqrestore() is a barrier. + */ + } + + spin_unlock_irqrestore(&hbus->config_lock, flags); return ret; } @@ -1152,39 +1233,51 @@ static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where, int size, u32 val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <= PCI_CAPABILITY_LIST) { /* SSIDs and ROM BARs are read-only */ } else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be written. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start writing. */ - wmb(); - /* Write to that function's config space. */ - switch (size) { - case 1: - writeb(val, addr); - break; - case 2: - writew(val, addr); - break; - default: - writel(val, addr); - break; + spin_lock_irqsave(&hbus->config_lock, flags); + + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_write_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to write. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before writing. */ + wmb(); + /* Write to that function's config space. */ + switch (size) { + case 1: + writeb(val, addr); + break; + case 2: + writew(val, addr); + break; + default: + writel(val, addr); + break; + } + /* + * Make sure the write was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the write was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to write beyond a function's config space.\n"); + dev_err(dev, "Attempt to write beyond a function's config space.\n"); } } @@ -3496,35 +3589,11 @@ static int hv_pci_probe(struct hv_device *hdev, bool enter_d0_retry = true; int ret; - /* - * hv_pcibus_device contains the hypercall arguments for retargeting in - * hv_irq_unmask(). Those must not cross a page boundary. - */ - BUILD_BUG_ON(sizeof(*hbus) > HV_HYP_PAGE_SIZE); - bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); if (!bridge) return -ENOMEM; - /* - * With the recent 59bb47985c1d ("mm, sl[aou]b: guarantee natural - * alignment for kmalloc(power-of-two)"), kzalloc() is able to allocate - * a 4KB buffer that is guaranteed to be 4KB-aligned. Here the size and - * alignment of hbus is important because hbus's field - * retarget_msi_interrupt_params must not cross a 4KB page boundary. - * - * Here we prefer kzalloc to get_zeroed_page(), because a buffer - * allocated by the latter is not tracked and scanned by kmemleak, and - * hence kmemleak reports the pointer contained in the hbus buffer - * (i.e. the hpdev struct, which is created in new_pcichild_device() and - * is tracked by hbus->children) as memory leak (false positive). - * - * If the kernel doesn't have 59bb47985c1d, get_zeroed_page() *must* be - * used to allocate the hbus buffer and we can avoid the kmemleak false - * positive by using kmemleak_alloc() and kmemleak_free() to ask - * kmemleak to track and scan the hbus buffer. - */ - hbus = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + hbus = kzalloc(sizeof(*hbus), GFP_KERNEL); if (!hbus) return -ENOMEM; @@ -3563,6 +3632,7 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; + hbus->use_calls = !!(ms_hyperv.hints & HV_X64_USE_MMIO_HYPERCALLS); #elif defined(CONFIG_ARM64) /* * Set the PCI bus parent to be the corresponding VMbus @@ -3572,6 +3642,7 @@ static int hv_pci_probe(struct hv_device *hdev, * information to devices created on the bus. */ hbus->sysdata.parent = hdev->device.parent; + hbus->use_calls = false; #endif hbus->hdev = hdev; @@ -3579,7 +3650,6 @@ static int hv_pci_probe(struct hv_device *hdev, INIT_LIST_HEAD(&hbus->dr_list); spin_lock_init(&hbus->config_lock); spin_lock_init(&hbus->device_list_lock); - spin_lock_init(&hbus->retarget_msi_interrupt_lock); hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0, hbus->bridge->domain_nr); if (!hbus->wq) { diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 954fc31b4bc7..02922768b129 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -391,7 +391,7 @@ static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, ccw_device_dma_free(vcdev->cdev, thinint_area, sizeof(*thinint_area)); } -static bool virtio_ccw_kvm_notify(struct virtqueue *vq) +static inline bool virtio_ccw_do_kvm_notify(struct virtqueue *vq, u32 data) { struct virtio_ccw_vq_info *info = vq->priv; struct virtio_ccw_device *vcdev; @@ -402,12 +402,22 @@ static bool virtio_ccw_kvm_notify(struct virtqueue *vq) BUILD_BUG_ON(sizeof(struct subchannel_id) != sizeof(unsigned int)); info->cookie = kvm_hypercall3(KVM_S390_VIRTIO_CCW_NOTIFY, *((unsigned int *)&schid), - vq->index, info->cookie); + data, info->cookie); if (info->cookie < 0) return false; return true; } +static bool virtio_ccw_kvm_notify(struct virtqueue *vq) +{ + return virtio_ccw_do_kvm_notify(vq, vq->index); +} + +static bool virtio_ccw_kvm_notify_with_data(struct virtqueue *vq) +{ + return virtio_ccw_do_kvm_notify(vq, vring_notification_data(vq)); +} + static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev, struct ccw1 *ccw, int index) { @@ -495,6 +505,7 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, struct ccw1 *ccw) { struct virtio_ccw_device *vcdev = to_vc_device(vdev); + bool (*notify)(struct virtqueue *vq); int err; struct virtqueue *vq = NULL; struct virtio_ccw_vq_info *info; @@ -502,6 +513,11 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, unsigned long flags; bool may_reduce; + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = virtio_ccw_kvm_notify_with_data; + else + notify = virtio_ccw_kvm_notify; + /* Allocate queue. */ info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL); if (!info) { @@ -524,7 +540,7 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, may_reduce = vcdev->revision > 0; vq = vring_create_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev, true, may_reduce, ctx, - virtio_ccw_kvm_notify, callback, name); + notify, callback, name); if (!vq) { /* For now, we fail if we can't get the requested size. */ diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 7259704a7f52..7f0914ea168f 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -21,25 +21,11 @@ static struct ctl_table scsi_table[] = { { } }; -static struct ctl_table scsi_dir_table[] = { - { .procname = "scsi", - .mode = 0555, - .child = scsi_table }, - { } -}; - -static struct ctl_table scsi_root_table[] = { - { .procname = "dev", - .mode = 0555, - .child = scsi_dir_table }, - { } -}; - static struct ctl_table_header *scsi_table_header; int __init scsi_init_sysctl(void) { - scsi_table_header = register_sysctl_table(scsi_root_table); + scsi_table_header = register_sysctl("dev/scsi", scsi_table); if (!scsi_table_header) return -ENOMEM; return 0; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 195963b82b63..e29e32b306ad 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -778,12 +778,28 @@ static bool vq_is_tx(u16 idx) return idx % 2; } -static u16 get_features_12_3(u64 features) +enum { + MLX5_VIRTIO_NET_F_MRG_RXBUF = 2, + MLX5_VIRTIO_NET_F_HOST_ECN = 4, + MLX5_VIRTIO_NET_F_GUEST_ECN = 6, + MLX5_VIRTIO_NET_F_GUEST_TSO6 = 7, + MLX5_VIRTIO_NET_F_GUEST_TSO4 = 8, + MLX5_VIRTIO_NET_F_GUEST_CSUM = 9, + MLX5_VIRTIO_NET_F_CSUM = 10, + MLX5_VIRTIO_NET_F_HOST_TSO6 = 11, + MLX5_VIRTIO_NET_F_HOST_TSO4 = 12, +}; + +static u16 get_features(u64 features) { - return (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << 9) | - (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << 8) | - (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << 7) | - (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_CSUM)) << 6); + return (!!(features & BIT_ULL(VIRTIO_NET_F_MRG_RXBUF)) << MLX5_VIRTIO_NET_F_MRG_RXBUF) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_ECN)) << MLX5_VIRTIO_NET_F_HOST_ECN) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_ECN)) << MLX5_VIRTIO_NET_F_GUEST_ECN) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_TSO6)) << MLX5_VIRTIO_NET_F_GUEST_TSO6) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_TSO4)) << MLX5_VIRTIO_NET_F_GUEST_TSO4) | + (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << MLX5_VIRTIO_NET_F_CSUM) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << MLX5_VIRTIO_NET_F_HOST_TSO6) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << MLX5_VIRTIO_NET_F_HOST_TSO4); } static bool counters_supported(const struct mlx5_vdpa_dev *mvdev) @@ -797,6 +813,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in); u32 out[MLX5_ST_SZ_DW(create_virtio_net_q_out)] = {}; void *obj_context; + u16 mlx_features; void *cmd_hdr; void *vq_ctx; void *in; @@ -812,6 +829,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque goto err_alloc; } + mlx_features = get_features(ndev->mvdev.actual_features); cmd_hdr = MLX5_ADDR_OF(create_virtio_net_q_in, in, general_obj_in_cmd_hdr); MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); @@ -822,7 +840,9 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx); MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx); MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_12_3, - get_features_12_3(ndev->mvdev.actual_features)); + mlx_features >> 3); + MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_2_0, + mlx_features & 7); vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context); MLX5_SET(virtio_q, vq_ctx, virtio_q_type, get_queue_type(ndev)); @@ -2171,23 +2191,27 @@ static u32 mlx5_vdpa_get_vq_group(struct vdpa_device *vdev, u16 idx) return MLX5_VDPA_DATAVQ_GROUP; } -enum { MLX5_VIRTIO_NET_F_GUEST_CSUM = 1 << 9, - MLX5_VIRTIO_NET_F_CSUM = 1 << 10, - MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11, - MLX5_VIRTIO_NET_F_HOST_TSO4 = 1 << 12, -}; - static u64 mlx_to_vritio_features(u16 dev_features) { u64 result = 0; - if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_MRG_RXBUF)) + result |= BIT_ULL(VIRTIO_NET_F_MRG_RXBUF); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_ECN)) + result |= BIT_ULL(VIRTIO_NET_F_HOST_ECN); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_ECN)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_ECN); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_TSO6)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_TSO6); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_TSO4)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_TSO4); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_CSUM)) result |= BIT_ULL(VIRTIO_NET_F_GUEST_CSUM); - if (dev_features & MLX5_VIRTIO_NET_F_CSUM) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_CSUM)) result |= BIT_ULL(VIRTIO_NET_F_CSUM); - if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_TSO6)) result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO6); - if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_TSO4)) result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO4); return result; @@ -2298,6 +2322,113 @@ static void update_cvq_info(struct mlx5_vdpa_dev *mvdev) } } +static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) +{ + u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {}; + int err; + + MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE); + MLX5_SET(query_vport_state_in, in, op_mod, opmod); + MLX5_SET(query_vport_state_in, in, vport_number, vport); + if (vport) + MLX5_SET(query_vport_state_in, in, other_vport, 1); + + err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out); + if (err) + return 0; + + return MLX5_GET(query_vport_state_out, out, state); +} + +static bool get_link_state(struct mlx5_vdpa_dev *mvdev) +{ + if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) == + VPORT_STATE_UP) + return true; + + return false; +} + +static void update_carrier(struct work_struct *work) +{ + struct mlx5_vdpa_wq_ent *wqent; + struct mlx5_vdpa_dev *mvdev; + struct mlx5_vdpa_net *ndev; + + wqent = container_of(work, struct mlx5_vdpa_wq_ent, work); + mvdev = wqent->mvdev; + ndev = to_mlx5_vdpa_ndev(mvdev); + if (get_link_state(mvdev)) + ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP); + else + ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP); + + if (ndev->config_cb.callback) + ndev->config_cb.callback(ndev->config_cb.private); + + kfree(wqent); +} + +static int queue_link_work(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_wq_ent *wqent; + + wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); + if (!wqent) + return -ENOMEM; + + wqent->mvdev = &ndev->mvdev; + INIT_WORK(&wqent->work, update_carrier); + queue_work(ndev->mvdev.wq, &wqent->work); + return 0; +} + +static int event_handler(struct notifier_block *nb, unsigned long event, void *param) +{ + struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb); + struct mlx5_eqe *eqe = param; + int ret = NOTIFY_DONE; + + if (event == MLX5_EVENT_TYPE_PORT_CHANGE) { + switch (eqe->sub_type) { + case MLX5_PORT_CHANGE_SUBTYPE_DOWN: + case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: + if (queue_link_work(ndev)) + return NOTIFY_DONE; + + ret = NOTIFY_OK; + break; + default: + return NOTIFY_DONE; + } + return ret; + } + return ret; +} + +static void register_link_notifier(struct mlx5_vdpa_net *ndev) +{ + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_STATUS))) + return; + + ndev->nb.notifier_call = event_handler; + mlx5_notifier_register(ndev->mvdev.mdev, &ndev->nb); + ndev->nb_registered = true; + queue_link_work(ndev); +} + +static void unregister_link_notifier(struct mlx5_vdpa_net *ndev) +{ + if (!ndev->nb_registered) + return; + + ndev->nb_registered = false; + mlx5_notifier_unregister(ndev->mvdev.mdev, &ndev->nb); + if (ndev->mvdev.wq) + flush_workqueue(ndev->mvdev.wq); +} + static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); @@ -2567,10 +2698,11 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) mlx5_vdpa_warn(mvdev, "failed to setup control VQ vring\n"); goto err_setup; } + register_link_notifier(ndev); err = setup_driver(mvdev); if (err) { mlx5_vdpa_warn(mvdev, "failed to setup driver\n"); - goto err_setup; + goto err_driver; } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); @@ -2582,6 +2714,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) up_write(&ndev->reslock); return; +err_driver: + unregister_link_notifier(ndev); err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; @@ -2607,6 +2741,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) mlx5_vdpa_info(mvdev, "performing device reset\n"); down_write(&ndev->reslock); + unregister_link_notifier(ndev); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2861,9 +2996,7 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) mlx5_vdpa_info(mvdev, "suspending device\n"); down_write(&ndev->reslock); - ndev->nb_registered = false; - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); - flush_workqueue(ndev->mvdev.wq); + unregister_link_notifier(ndev); for (i = 0; i < ndev->cur_num_vqs; i++) { mvq = &ndev->vqs[i]; suspend_vq(ndev, mvq); @@ -3000,84 +3133,6 @@ struct mlx5_vdpa_mgmtdev { struct mlx5_vdpa_net *ndev; }; -static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) -{ - u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {}; - int err; - - MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE); - MLX5_SET(query_vport_state_in, in, op_mod, opmod); - MLX5_SET(query_vport_state_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vport_state_in, in, other_vport, 1); - - err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out); - if (err) - return 0; - - return MLX5_GET(query_vport_state_out, out, state); -} - -static bool get_link_state(struct mlx5_vdpa_dev *mvdev) -{ - if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) == - VPORT_STATE_UP) - return true; - - return false; -} - -static void update_carrier(struct work_struct *work) -{ - struct mlx5_vdpa_wq_ent *wqent; - struct mlx5_vdpa_dev *mvdev; - struct mlx5_vdpa_net *ndev; - - wqent = container_of(work, struct mlx5_vdpa_wq_ent, work); - mvdev = wqent->mvdev; - ndev = to_mlx5_vdpa_ndev(mvdev); - if (get_link_state(mvdev)) - ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP); - else - ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP); - - if (ndev->nb_registered && ndev->config_cb.callback) - ndev->config_cb.callback(ndev->config_cb.private); - - kfree(wqent); -} - -static int event_handler(struct notifier_block *nb, unsigned long event, void *param) -{ - struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb); - struct mlx5_eqe *eqe = param; - int ret = NOTIFY_DONE; - struct mlx5_vdpa_wq_ent *wqent; - - if (event == MLX5_EVENT_TYPE_PORT_CHANGE) { - if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_STATUS))) - return NOTIFY_DONE; - switch (eqe->sub_type) { - case MLX5_PORT_CHANGE_SUBTYPE_DOWN: - case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return NOTIFY_DONE; - - wqent->mvdev = &ndev->mvdev; - INIT_WORK(&wqent->work, update_carrier); - queue_work(ndev->mvdev.wq, &wqent->work); - ret = NOTIFY_OK; - break; - default: - return NOTIFY_DONE; - } - return ret; - } - return ret; -} - static int config_func_mtu(struct mlx5_core_dev *mdev, u16 mtu) { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); @@ -3127,6 +3182,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EINVAL; } device_features &= add_config->device_features; + } else { + device_features &= ~BIT_ULL(VIRTIO_NET_F_MRG_RXBUF); } if (!(device_features & BIT_ULL(VIRTIO_F_VERSION_1) && device_features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) { @@ -3258,9 +3315,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, goto err_res2; } - ndev->nb.notifier_call = event_handler; - mlx5_notifier_register(mdev, &ndev->nb); - ndev->nb_registered = true; mvdev->vdev.mdev = &mgtdev->mgtdev; err = _vdpa_register_device(&mvdev->vdev, max_vqs + 1); if (err) @@ -3294,10 +3348,7 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device * mlx5_vdpa_remove_debugfs(ndev->debugfs); ndev->debugfs = NULL; - if (ndev->nb_registered) { - ndev->nb_registered = false; - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); - } + unregister_link_notifier(ndev); wq = mvdev->wq; mvdev->wq = NULL; destroy_workqueue(wq); diff --git a/drivers/vdpa/solidrun/Makefile b/drivers/vdpa/solidrun/Makefile index c0aa3415bf7b..9116252cd5fa 100644 --- a/drivers/vdpa/solidrun/Makefile +++ b/drivers/vdpa/solidrun/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SNET_VDPA) += snet_vdpa.o snet_vdpa-$(CONFIG_SNET_VDPA) += snet_main.o +snet_vdpa-$(CONFIG_SNET_VDPA) += snet_ctrl.o ifdef CONFIG_HWMON snet_vdpa-$(CONFIG_SNET_VDPA) += snet_hwmon.o endif diff --git a/drivers/vdpa/solidrun/snet_ctrl.c b/drivers/vdpa/solidrun/snet_ctrl.c new file mode 100644 index 000000000000..3858738643b4 --- /dev/null +++ b/drivers/vdpa/solidrun/snet_ctrl.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SolidRun DPU driver for control plane + * + * Copyright (C) 2022-2023 SolidRun + * + * Author: Alvaro Karsz + * + */ + +#include + +#include "snet_vdpa.h" + +enum snet_ctrl_opcodes { + SNET_CTRL_OP_DESTROY = 1, + SNET_CTRL_OP_READ_VQ_STATE, + SNET_CTRL_OP_SUSPEND, +}; + +#define SNET_CTRL_TIMEOUT 2000000 + +#define SNET_CTRL_DATA_SIZE_MASK 0x0000FFFF +#define SNET_CTRL_IN_PROCESS_MASK 0x00010000 +#define SNET_CTRL_CHUNK_RDY_MASK 0x00020000 +#define SNET_CTRL_ERROR_MASK 0x0FFC0000 + +#define SNET_VAL_TO_ERR(val) (-(((val) & SNET_CTRL_ERROR_MASK) >> 18)) +#define SNET_EMPTY_CTRL(val) (((val) & SNET_CTRL_ERROR_MASK) || \ + !((val) & SNET_CTRL_IN_PROCESS_MASK)) +#define SNET_DATA_READY(val) ((val) & (SNET_CTRL_ERROR_MASK | SNET_CTRL_CHUNK_RDY_MASK)) + +/* Control register used to read data from the DPU */ +struct snet_ctrl_reg_ctrl { + /* Chunk size in 4B words */ + u16 data_size; + /* We are in the middle of a command */ + u16 in_process:1; + /* A data chunk is ready and can be consumed */ + u16 chunk_ready:1; + /* Error code */ + u16 error:10; + /* Saved for future usage */ + u16 rsvd:4; +}; + +/* Opcode register */ +struct snet_ctrl_reg_op { + u16 opcode; + /* Only if VQ index is relevant for the command */ + u16 vq_idx; +}; + +struct snet_ctrl_regs { + struct snet_ctrl_reg_op op; + struct snet_ctrl_reg_ctrl ctrl; + u32 rsvd; + u32 data[]; +}; + +static struct snet_ctrl_regs __iomem *snet_get_ctrl(struct snet *snet) +{ + return snet->bar + snet->psnet->cfg.ctrl_off; +} + +static int snet_wait_for_empty_ctrl(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->ctrl, val, SNET_EMPTY_CTRL(val), 10, + SNET_CTRL_TIMEOUT); +} + +static int snet_wait_for_empty_op(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->op, val, !val, 10, SNET_CTRL_TIMEOUT); +} + +static int snet_wait_for_data(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->ctrl, val, SNET_DATA_READY(val), 10, + SNET_CTRL_TIMEOUT); +} + +static u32 snet_read32_word(struct snet_ctrl_regs __iomem *ctrl_regs, u16 word_idx) +{ + return ioread32(&ctrl_regs->data[word_idx]); +} + +static u32 snet_read_ctrl(struct snet_ctrl_regs __iomem *ctrl_regs) +{ + return ioread32(&ctrl_regs->ctrl); +} + +static void snet_write_ctrl(struct snet_ctrl_regs __iomem *ctrl_regs, u32 val) +{ + iowrite32(val, &ctrl_regs->ctrl); +} + +static void snet_write_op(struct snet_ctrl_regs __iomem *ctrl_regs, u32 val) +{ + iowrite32(val, &ctrl_regs->op); +} + +static int snet_wait_for_dpu_completion(struct snet_ctrl_regs __iomem *ctrl_regs) +{ + /* Wait until the DPU finishes completely. + * It will clear the opcode register. + */ + return snet_wait_for_empty_op(ctrl_regs); +} + +/* Reading ctrl from the DPU: + * buf_size must be 4B aligned + * + * Steps: + * + * (1) Verify that the DPU is not in the middle of another operation by + * reading the in_process and error bits in the control register. + * (2) Write the request opcode and the VQ idx in the opcode register + * and write the buffer size in the control register. + * (3) Start readind chunks of data, chunk_ready bit indicates that a + * data chunk is available, we signal that we read the data by clearing the bit. + * (4) Detect that the transfer is completed when the in_process bit + * in the control register is cleared or when the an error appears. + */ +static int snet_ctrl_read_from_dpu(struct snet *snet, u16 opcode, u16 vq_idx, void *buffer, + u32 buf_size) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + u32 *bfr_ptr = (u32 *)buffer; + u32 val; + u16 buf_words; + int ret; + u16 words, i, tot_words = 0; + + /* Supported for config 2+ */ + if (!SNET_CFG_VER(snet, 2)) + return -EOPNOTSUPP; + + if (!IS_ALIGNED(buf_size, 4)) + return -EINVAL; + + mutex_lock(&snet->ctrl_lock); + + buf_words = buf_size / 4; + + /* Make sure control register is empty */ + ret = snet_wait_for_empty_ctrl(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control data to be consumed\n"); + goto exit; + } + + /* We need to write the buffer size in the control register, and the opcode + vq index in + * the opcode register. + * We use a spinlock to serialize the writes. + */ + spin_lock(&snet->ctrl_spinlock); + + snet_write_ctrl(regs, buf_words); + snet_write_op(regs, opcode | (vq_idx << 16)); + + spin_unlock(&snet->ctrl_spinlock); + + while (buf_words != tot_words) { + ret = snet_wait_for_data(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for control data\n"); + goto exit; + } + + val = snet_read_ctrl(regs); + + /* Error? */ + if (val & SNET_CTRL_ERROR_MASK) { + ret = SNET_VAL_TO_ERR(val); + SNET_WARN(pdev, "Error while reading control data from DPU, err %d\n", ret); + goto exit; + } + + words = min_t(u16, val & SNET_CTRL_DATA_SIZE_MASK, buf_words - tot_words); + + for (i = 0; i < words; i++) { + *bfr_ptr = snet_read32_word(regs, i); + bfr_ptr++; + } + + tot_words += words; + + /* Is the job completed? */ + if (!(val & SNET_CTRL_IN_PROCESS_MASK)) + break; + + /* Clear the chunk ready bit and continue */ + val &= ~SNET_CTRL_CHUNK_RDY_MASK; + snet_write_ctrl(regs, val); + } + + ret = snet_wait_for_dpu_completion(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for the DPU to complete a control command\n"); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +/* Send a control message to the DPU using the old mechanism + * used with config version 1. + */ +static int snet_send_ctrl_msg_old(struct snet *snet, u32 opcode) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + int ret; + + mutex_lock(&snet->ctrl_lock); + + /* Old mechanism uses just 1 register, the opcode register. + * Make sure that the opcode register is empty, and that the DPU isn't + * processing an old message. + */ + ret = snet_wait_for_empty_op(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control message to be ACKed\n"); + goto exit; + } + + /* Write the message */ + snet_write_op(regs, opcode); + + /* DPU ACKs the message by clearing the opcode register */ + ret = snet_wait_for_empty_op(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for a control message to be ACKed\n"); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +/* Send a control message to the DPU. + * A control message is a message without payload. + */ +static int snet_send_ctrl_msg(struct snet *snet, u16 opcode, u16 vq_idx) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + u32 val; + int ret; + + /* If config version is not 2+, use the old mechanism */ + if (!SNET_CFG_VER(snet, 2)) + return snet_send_ctrl_msg_old(snet, opcode); + + mutex_lock(&snet->ctrl_lock); + + /* Make sure control register is empty */ + ret = snet_wait_for_empty_ctrl(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control data to be consumed\n"); + goto exit; + } + + /* We need to clear the control register and write the opcode + vq index in the opcode + * register. + * We use a spinlock to serialize the writes. + */ + spin_lock(&snet->ctrl_spinlock); + + snet_write_ctrl(regs, 0); + snet_write_op(regs, opcode | (vq_idx << 16)); + + spin_unlock(&snet->ctrl_spinlock); + + /* The DPU ACKs control messages by setting the chunk ready bit + * without data. + */ + ret = snet_wait_for_data(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for control message to be ACKed\n"); + goto exit; + } + + /* Check for errors */ + val = snet_read_ctrl(regs); + ret = SNET_VAL_TO_ERR(val); + + /* Clear the chunk ready bit */ + val &= ~SNET_CTRL_CHUNK_RDY_MASK; + snet_write_ctrl(regs, val); + + ret = snet_wait_for_dpu_completion(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for DPU to complete a control command, err %d\n", + ret); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +void snet_ctrl_clear(struct snet *snet) +{ + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + + snet_write_op(regs, 0); +} + +int snet_destroy_dev(struct snet *snet) +{ + return snet_send_ctrl_msg(snet, SNET_CTRL_OP_DESTROY, 0); +} + +int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state) +{ + return snet_ctrl_read_from_dpu(snet, SNET_CTRL_OP_READ_VQ_STATE, idx, state, + sizeof(*state)); +} + +int snet_suspend_dev(struct snet *snet) +{ + return snet_send_ctrl_msg(snet, SNET_CTRL_OP_SUSPEND, 0); +} diff --git a/drivers/vdpa/solidrun/snet_hwmon.c b/drivers/vdpa/solidrun/snet_hwmon.c index e695e36ff753..42c87387a0f1 100644 --- a/drivers/vdpa/solidrun/snet_hwmon.c +++ b/drivers/vdpa/solidrun/snet_hwmon.c @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 68de727398ed..cdcd84ce4f5a 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * @@ -16,14 +16,12 @@ /* SNET signature */ #define SNET_SIGNATURE 0xD0D06363 /* Max. config version that we can work with */ -#define SNET_CFG_VERSION 0x1 +#define SNET_CFG_VERSION 0x2 /* Queue align */ #define SNET_QUEUE_ALIGNMENT PAGE_SIZE /* Kick value to notify that new data is available */ #define SNET_KICK_VAL 0x1 #define SNET_CONFIG_OFF 0x0 -/* ACK timeout for a message */ -#define SNET_ACK_TIMEOUT 2000000 /* How long we are willing to wait for a SNET device */ #define SNET_DETECT_TIMEOUT 5000000 /* How long should we wait for the DPU to read our config */ @@ -32,61 +30,16 @@ #define SNET_GENERAL_CFG_LEN 36 #define SNET_GENERAL_CFG_VQ_LEN 40 -enum snet_msg { - SNET_MSG_DESTROY = 1, -}; - static struct snet *vdpa_to_snet(struct vdpa_device *vdpa) { return container_of(vdpa, struct snet, vdpa); } -static int snet_wait_for_msg_ack(struct snet *snet) -{ - struct pci_dev *pdev = snet->pdev; - int ret; - u32 val; - - /* The DPU will clear the messages offset once messages - * are processed. - */ - ret = readx_poll_timeout(ioread32, snet->bar + snet->psnet->cfg.msg_off, - val, !val, 10, SNET_ACK_TIMEOUT); - if (ret) - SNET_WARN(pdev, "Timeout waiting for message ACK\n"); - - return ret; -} - -/* Sends a message to the DPU. - * If blocking is set, the function will return once the - * message was processed by the DPU (or timeout). - */ -static int snet_send_msg(struct snet *snet, u32 msg, bool blocking) -{ - int ret = 0; - - /* Make sure the DPU acked last message before issuing a new one */ - ret = snet_wait_for_msg_ack(snet); - if (ret) - return ret; - - /* Write the message */ - snet_write32(snet, snet->psnet->cfg.msg_off, msg); - - if (blocking) - ret = snet_wait_for_msg_ack(snet); - else /* If non-blocking, flush the write by issuing a read */ - snet_read32(snet, snet->psnet->cfg.msg_off); - - return ret; -} - static irqreturn_t snet_cfg_irq_hndlr(int irq, void *data) { struct snet *snet = data; /* Call callback if any */ - if (snet->cb.callback) + if (likely(snet->cb.callback)) return snet->cb.callback(snet->cb.private); return IRQ_HANDLED; @@ -96,7 +49,7 @@ static irqreturn_t snet_vq_irq_hndlr(int irq, void *data) { struct snet_vq *vq = data; /* Call callback if any */ - if (vq->cb.callback) + if (likely(vq->cb.callback)) return vq->cb.callback(vq->cb.private); return IRQ_HANDLED; @@ -153,12 +106,24 @@ static void snet_kick_vq(struct vdpa_device *vdev, u16 idx) { struct snet *snet = vdpa_to_snet(vdev); /* not ready - ignore */ - if (!snet->vqs[idx]->ready) + if (unlikely(!snet->vqs[idx]->ready)) return; iowrite32(SNET_KICK_VAL, snet->vqs[idx]->kick_ptr); } +static void snet_kick_vq_with_data(struct vdpa_device *vdev, u32 data) +{ + struct snet *snet = vdpa_to_snet(vdev); + u16 idx = data & 0xFFFF; + + /* not ready - ignore */ + if (unlikely(!snet->vqs[idx]->ready)) + return; + + iowrite32((data & 0xFFFF0000) | SNET_KICK_VAL, snet->vqs[idx]->kick_ptr); +} + static void snet_set_vq_cb(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb) { struct snet *snet = vdpa_to_snet(vdev); @@ -181,33 +146,48 @@ static bool snet_get_vq_ready(struct vdpa_device *vdev, u16 idx) return snet->vqs[idx]->ready; } -static int snet_set_vq_state(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state) +static bool snet_vq_state_is_initial(struct snet *snet, const struct vdpa_vq_state *state) { - struct snet *snet = vdpa_to_snet(vdev); - /* Setting the VQ state is not supported. - * If the asked state is the same as the initial one - * we can ignore it. - */ if (SNET_HAS_FEATURE(snet, VIRTIO_F_RING_PACKED)) { const struct vdpa_vq_state_packed *p = &state->packed; if (p->last_avail_counter == 1 && p->last_used_counter == 1 && p->last_avail_idx == 0 && p->last_used_idx == 0) - return 0; + return true; } else { const struct vdpa_vq_state_split *s = &state->split; if (s->avail_index == 0) - return 0; + return true; } + return false; +} + +static int snet_set_vq_state(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state) +{ + struct snet *snet = vdpa_to_snet(vdev); + + /* We can set any state for config version 2+ */ + if (SNET_CFG_VER(snet, 2)) { + memcpy(&snet->vqs[idx]->vq_state, state, sizeof(*state)); + return 0; + } + + /* Older config - we can't set the VQ state. + * Return 0 only if this is the initial state we use in the DPU. + */ + if (snet_vq_state_is_initial(snet, state)) + return 0; + return -EOPNOTSUPP; } static int snet_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state) { - /* Not supported */ - return -EOPNOTSUPP; + struct snet *snet = vdpa_to_snet(vdev); + + return snet_read_vq_state(snet, idx, state); } static int snet_get_vq_irq(struct vdpa_device *vdev, u16 idx) @@ -232,9 +212,9 @@ static int snet_reset_dev(struct snet *snet) if (!snet->status) return 0; - /* If DPU started, send a destroy message */ + /* If DPU started, destroy it */ if (snet->status & VIRTIO_CONFIG_S_DRIVER_OK) - ret = snet_send_msg(snet, SNET_MSG_DESTROY, true); + ret = snet_destroy_dev(snet); /* Clear VQs */ for (i = 0; i < snet->cfg->vq_num; i++) { @@ -258,7 +238,7 @@ static int snet_reset_dev(struct snet *snet) snet->dpu_ready = false; if (ret) - SNET_WARN(pdev, "Incomplete reset to SNET[%u] device\n", snet->sid); + SNET_WARN(pdev, "Incomplete reset to SNET[%u] device, err: %d\n", snet->sid, ret); else SNET_DBG(pdev, "Reset SNET[%u] device\n", snet->sid); @@ -356,7 +336,7 @@ static int snet_write_conf(struct snet *snet) * | DESC AREA | * | DEVICE AREA | * | DRIVER AREA | - * | RESERVED | + * | VQ STATE (CFG 2+) | RSVD | * * Magic number should be written last, this is the DPU indication that the data is ready */ @@ -391,12 +371,15 @@ static int snet_write_conf(struct snet *snet) off += 8; snet_write64(snet, off, snet->vqs[i]->driver_area); off += 8; + /* Write VQ state if config version is 2+ */ + if (SNET_CFG_VER(snet, 2)) + snet_write32(snet, off, *(u32 *)&snet->vqs[i]->vq_state); + off += 4; + /* Ignore reserved */ - off += 8; + off += 4; } - /* Clear snet messages address for this device */ - snet_write32(snet, snet->psnet->cfg.msg_off, 0); /* Write magic number - data is ready */ snet_write32(snet, snet->psnet->cfg.host_cfg_off, SNET_SIGNATURE); @@ -512,10 +495,25 @@ static void snet_set_config(struct vdpa_device *vdev, unsigned int offset, iowrite8(*buf_ptr++, cfg_ptr + i); } +static int snet_suspend(struct vdpa_device *vdev) +{ + struct snet *snet = vdpa_to_snet(vdev); + int ret; + + ret = snet_suspend_dev(snet); + if (ret) + SNET_ERR(snet->pdev, "SNET[%u] suspend failed, err: %d\n", snet->sid, ret); + else + SNET_DBG(snet->pdev, "Suspend SNET[%u] device\n", snet->sid); + + return ret; +} + static const struct vdpa_config_ops snet_config_ops = { .set_vq_address = snet_set_vq_address, .set_vq_num = snet_set_vq_num, .kick_vq = snet_kick_vq, + .kick_vq_with_data = snet_kick_vq_with_data, .set_vq_cb = snet_set_vq_cb, .set_vq_ready = snet_set_vq_ready, .get_vq_ready = snet_get_vq_ready, @@ -537,6 +535,7 @@ static const struct vdpa_config_ops snet_config_ops = { .set_status = snet_set_status, .get_config = snet_get_config, .set_config = snet_set_config, + .suspend = snet_suspend, }; static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) @@ -697,7 +696,7 @@ static int psnet_read_cfg(struct pci_dev *pdev, struct psnet *psnet) off += 4; cfg->hwmon_off = psnet_read32(psnet, off); off += 4; - cfg->msg_off = psnet_read32(psnet, off); + cfg->ctrl_off = psnet_read32(psnet, off); off += 4; cfg->flags = psnet_read32(psnet, off); off += 4; @@ -997,6 +996,10 @@ static int snet_vdpa_probe_vf(struct pci_dev *pdev) goto free_irqs; } + /* Init control mutex and spinlock */ + mutex_init(&snet->ctrl_lock); + spin_lock_init(&snet->ctrl_spinlock); + /* Save pci device pointer */ snet->pdev = pdev; snet->psnet = psnet; @@ -1013,6 +1016,9 @@ static int snet_vdpa_probe_vf(struct pci_dev *pdev) /* Create a VirtIO config pointer */ snet->cfg->virtio_cfg = snet->bar + snet->psnet->cfg.virtio_cfg_off; + /* Clear control registers */ + snet_ctrl_clear(snet); + pci_set_master(pdev); pci_set_drvdata(pdev, snet); diff --git a/drivers/vdpa/solidrun/snet_vdpa.h b/drivers/vdpa/solidrun/snet_vdpa.h index b7f34169053f..3c78d4e7d485 100644 --- a/drivers/vdpa/solidrun/snet_vdpa.h +++ b/drivers/vdpa/solidrun/snet_vdpa.h @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * @@ -20,10 +20,15 @@ #define SNET_INFO(pdev, fmt, ...) dev_info(&(pdev)->dev, "%s"fmt, "snet_vdpa: ", ##__VA_ARGS__) #define SNET_DBG(pdev, fmt, ...) dev_dbg(&(pdev)->dev, "%s"fmt, "snet_vdpa: ", ##__VA_ARGS__) #define SNET_HAS_FEATURE(s, f) ((s)->negotiated_features & BIT_ULL(f)) +/* Check if negotiated config version is at least @ver */ +#define SNET_CFG_VER(snet, ver) ((snet)->psnet->negotiated_cfg_ver >= (ver)) + /* VQ struct */ struct snet_vq { /* VQ callback */ struct vdpa_callback cb; + /* VQ state received from bus */ + struct vdpa_vq_state vq_state; /* desc base address */ u64 desc_area; /* device base address */ @@ -51,6 +56,10 @@ struct snet { struct vdpa_device vdpa; /* Config callback */ struct vdpa_callback cb; + /* To lock the control mechanism */ + struct mutex ctrl_lock; + /* Spinlock to protect critical parts in the control mechanism */ + spinlock_t ctrl_spinlock; /* array of virqueues */ struct snet_vq **vqs; /* Used features */ @@ -117,8 +126,8 @@ struct snet_cfg { u32 kick_off; /* Offset in PCI BAR for HW monitoring */ u32 hwmon_off; - /* Offset in PCI BAR for SNET messages */ - u32 msg_off; + /* Offset in PCI BAR for Control mechanism */ + u32 ctrl_off; /* Config general flags - enum snet_cfg_flags */ u32 flags; /* Reserved for future usage */ @@ -191,4 +200,9 @@ static inline void snet_write64(struct snet *snet, u32 off, u64 val) void psnet_create_hwmon(struct pci_dev *pdev); #endif +void snet_ctrl_clear(struct snet *snet); +int snet_destroy_dev(struct snet *snet); +int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state); +int snet_suspend_dev(struct snet *snet); + #endif //_SNET_VDPA_H_ diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index eea23c630f7c..d343af4fa60e 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -11,8 +11,8 @@ #include #include #include +#include #include -#include #include #include #include @@ -35,10 +35,44 @@ module_param(max_iotlb_entries, int, 0444); MODULE_PARM_DESC(max_iotlb_entries, "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)"); +static bool use_va = true; +module_param(use_va, bool, 0444); +MODULE_PARM_DESC(use_va, "Enable/disable the device's ability to use VA"); + #define VDPASIM_QUEUE_ALIGN PAGE_SIZE #define VDPASIM_QUEUE_MAX 256 #define VDPASIM_VENDOR_ID 0 +struct vdpasim_mm_work { + struct kthread_work work; + struct vdpasim *vdpasim; + struct mm_struct *mm_to_bind; + int ret; +}; + +static void vdpasim_mm_work_fn(struct kthread_work *work) +{ + struct vdpasim_mm_work *mm_work = + container_of(work, struct vdpasim_mm_work, work); + struct vdpasim *vdpasim = mm_work->vdpasim; + + mm_work->ret = 0; + + //TODO: should we attach the cgroup of the mm owner? + vdpasim->mm_bound = mm_work->mm_to_bind; +} + +static void vdpasim_worker_change_mm_sync(struct vdpasim *vdpasim, + struct vdpasim_mm_work *mm_work) +{ + struct kthread_work *work = &mm_work->work; + + kthread_init_work(work, vdpasim_mm_work_fn); + kthread_queue_work(vdpasim->worker, work); + + kthread_flush_work(work); +} + static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa) { return container_of(vdpa, struct vdpasim, vdpa); @@ -59,13 +93,20 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; uint16_t last_avail_idx = vq->vring.last_avail_idx; + struct vring_desc *desc = (struct vring_desc *) + (uintptr_t)vq->desc_addr; + struct vring_avail *avail = (struct vring_avail *) + (uintptr_t)vq->driver_addr; + struct vring_used *used = (struct vring_used *) + (uintptr_t)vq->device_addr; - vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, true, - (struct vring_desc *)(uintptr_t)vq->desc_addr, - (struct vring_avail *) - (uintptr_t)vq->driver_addr, - (struct vring_used *) - (uintptr_t)vq->device_addr); + if (use_va && vdpasim->mm_bound) { + vringh_init_iotlb_va(&vq->vring, vdpasim->features, vq->num, + true, desc, avail, used); + } else { + vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, + true, desc, avail, used); + } vq->vring.last_avail_idx = last_avail_idx; @@ -127,6 +168,25 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) static const struct vdpa_config_ops vdpasim_config_ops; static const struct vdpa_config_ops vdpasim_batch_config_ops; +static void vdpasim_work_fn(struct kthread_work *work) +{ + struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); + struct mm_struct *mm = vdpasim->mm_bound; + + if (use_va && mm) { + if (!mmget_not_zero(mm)) + return; + kthread_use_mm(mm); + } + + vdpasim->dev_attr.work_fn(vdpasim); + + if (use_va && mm) { + kthread_unuse_mm(mm); + mmput(mm); + } +} + struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, const struct vdpa_dev_set_config *config) { @@ -155,7 +215,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, vdpa = __vdpa_alloc_device(NULL, ops, dev_attr->ngroups, dev_attr->nas, dev_attr->alloc_size, - dev_attr->name, false); + dev_attr->name, use_va); if (IS_ERR(vdpa)) { ret = PTR_ERR(vdpa); goto err_alloc; @@ -163,11 +223,17 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, vdpasim = vdpa_to_sim(vdpa); vdpasim->dev_attr = *dev_attr; - INIT_WORK(&vdpasim->work, dev_attr->work_fn); - spin_lock_init(&vdpasim->lock); + dev = &vdpasim->vdpa.dev; + + kthread_init_work(&vdpasim->work, vdpasim_work_fn); + vdpasim->worker = kthread_create_worker(0, "vDPA sim worker: %s", + dev_attr->name); + if (IS_ERR(vdpasim->worker)) + goto err_iommu; + + mutex_init(&vdpasim->mutex); spin_lock_init(&vdpasim->iommu_lock); - dev = &vdpasim->vdpa.dev; dev->dma_mask = &dev->coherent_dma_mask; if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) goto err_iommu; @@ -195,10 +261,6 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, for (i = 0; i < vdpasim->dev_attr.nas; i++) vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0); - vdpasim->buffer = kvmalloc(dev_attr->buffer_size, GFP_KERNEL); - if (!vdpasim->buffer) - goto err_iommu; - for (i = 0; i < dev_attr->nvqs; i++) vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0], &vdpasim->iommu_lock); @@ -214,6 +276,12 @@ err_alloc: } EXPORT_SYMBOL_GPL(vdpasim_create); +void vdpasim_schedule_work(struct vdpasim *vdpasim) +{ + kthread_queue_work(vdpasim->worker, &vdpasim->work); +} +EXPORT_SYMBOL_GPL(vdpasim_schedule_work); + static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx, u64 desc_area, u64 driver_area, u64 device_area) @@ -248,7 +316,7 @@ static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx) } if (vq->ready) - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); } static void vdpasim_set_vq_cb(struct vdpa_device *vdpa, u16 idx, @@ -267,13 +335,13 @@ static void vdpasim_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; bool old_ready; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); old_ready = vq->ready; vq->ready = ready; if (vq->ready && !old_ready) { vdpasim_queue_ready(vdpasim, idx); } - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); } static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx) @@ -291,9 +359,9 @@ static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; struct vringh *vrh = &vq->vring; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vrh->last_avail_idx = state->split.avail_index; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -390,9 +458,9 @@ static u8 vdpasim_get_status(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); u8 status; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); status = vdpasim->status; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return status; } @@ -401,19 +469,19 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->status = status; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); } static int vdpasim_reset(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->status = 0; vdpasim_do_reset(vdpasim); - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -422,9 +490,9 @@ static int vdpasim_suspend(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->running = false; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -434,7 +502,7 @@ static int vdpasim_resume(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int i; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->running = true; if (vdpasim->pending_kick) { @@ -445,7 +513,7 @@ static int vdpasim_resume(struct vdpa_device *vdpa) vdpasim->pending_kick = false; } - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -517,14 +585,14 @@ static int vdpasim_set_group_asid(struct vdpa_device *vdpa, unsigned int group, iommu = &vdpasim->iommu[asid]; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); for (i = 0; i < vdpasim->dev_attr.nvqs; i++) if (vdpasim_get_vq_group(vdpa, i) == group) vringh_set_iotlb(&vdpasim->vqs[i].vring, iommu, &vdpasim->iommu_lock); - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -563,6 +631,30 @@ err: return ret; } +static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_mm_work mm_work; + + mm_work.vdpasim = vdpasim; + mm_work.mm_to_bind = mm; + + vdpasim_worker_change_mm_sync(vdpasim, &mm_work); + + return mm_work.ret; +} + +static void vdpasim_unbind_mm(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_mm_work mm_work; + + mm_work.vdpasim = vdpasim; + mm_work.mm_to_bind = NULL; + + vdpasim_worker_change_mm_sync(vdpasim, &mm_work); +} + static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid, u64 iova, u64 size, u64 pa, u32 perm, void *opaque) @@ -610,14 +702,16 @@ static void vdpasim_free(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int i; - cancel_work_sync(&vdpasim->work); + kthread_cancel_work_sync(&vdpasim->work); + kthread_destroy_worker(vdpasim->worker); for (i = 0; i < vdpasim->dev_attr.nvqs; i++) { vringh_kiov_cleanup(&vdpasim->vqs[i].out_iov); vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov); } - kvfree(vdpasim->buffer); + vdpasim->dev_attr.free(vdpasim); + for (i = 0; i < vdpasim->dev_attr.nas; i++) vhost_iotlb_reset(&vdpasim->iommu[i]); kfree(vdpasim->iommu); @@ -658,6 +752,8 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, + .bind_mm = vdpasim_bind_mm, + .unbind_mm = vdpasim_unbind_mm, .free = vdpasim_free, }; @@ -692,6 +788,8 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .get_iova_range = vdpasim_get_iova_range, .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, + .bind_mm = vdpasim_bind_mm, + .unbind_mm = vdpasim_unbind_mm, .free = vdpasim_free, }; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index 144858636c10..bb137e479763 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -39,33 +39,34 @@ struct vdpasim_dev_attr { u64 supported_features; size_t alloc_size; size_t config_size; - size_t buffer_size; int nvqs; u32 id; u32 ngroups; u32 nas; - work_func_t work_fn; + void (*work_fn)(struct vdpasim *vdpasim); void (*get_config)(struct vdpasim *vdpasim, void *config); void (*set_config)(struct vdpasim *vdpasim, const void *config); int (*get_stats)(struct vdpasim *vdpasim, u16 idx, struct sk_buff *msg, struct netlink_ext_ack *extack); + void (*free)(struct vdpasim *vdpasim); }; /* State of each vdpasim device */ struct vdpasim { struct vdpa_device vdpa; struct vdpasim_virtqueue *vqs; - struct work_struct work; + struct kthread_worker *worker; + struct kthread_work work; + struct mm_struct *mm_bound; struct vdpasim_dev_attr dev_attr; - /* spinlock to synchronize virtqueue state */ - spinlock_t lock; + /* mutex to synchronize virtqueue state */ + struct mutex mutex; /* virtio config according to device type */ void *config; struct vhost_iotlb *iommu; bool *iommu_pt; - void *buffer; u32 status; u32 generation; u64 features; @@ -78,6 +79,7 @@ struct vdpasim { struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr, const struct vdpa_dev_set_config *config); +void vdpasim_schedule_work(struct vdpasim *vdpasim); /* TODO: cross-endian support */ static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index 5117959bed8a..00d7d72713be 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -44,8 +43,39 @@ #define VDPASIM_BLK_AS_NUM 1 #define VDPASIM_BLK_GROUP_NUM 1 +struct vdpasim_blk { + struct vdpasim vdpasim; + void *buffer; + bool shared_backend; +}; + +static struct vdpasim_blk *sim_to_blk(struct vdpasim *vdpasim) +{ + return container_of(vdpasim, struct vdpasim_blk, vdpasim); +} + static char vdpasim_blk_id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim"; +static bool shared_backend; +module_param(shared_backend, bool, 0444); +MODULE_PARM_DESC(shared_backend, "Enable the shared backend between virtio-blk devices"); + +static void *shared_buffer; +/* mutex to synchronize shared_buffer access */ +static DEFINE_MUTEX(shared_buffer_mutex); + +static void vdpasim_blk_buffer_lock(struct vdpasim_blk *blk) +{ + if (blk->shared_backend) + mutex_lock(&shared_buffer_mutex); +} + +static void vdpasim_blk_buffer_unlock(struct vdpasim_blk *blk) +{ + if (blk->shared_backend) + mutex_unlock(&shared_buffer_mutex); +} + static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, u64 num_sectors, u64 max_sectors) { @@ -79,6 +109,7 @@ static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, struct vdpasim_virtqueue *vq) { + struct vdpasim_blk *blk = sim_to_blk(vdpasim); size_t pushed = 0, to_pull, to_push; struct virtio_blk_outhdr hdr; bool handled = false; @@ -144,9 +175,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, break; } + vdpasim_blk_buffer_lock(blk); bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, - vdpasim->buffer + offset, - to_push); + blk->buffer + offset, to_push); + vdpasim_blk_buffer_unlock(blk); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_push_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -166,9 +198,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, break; } + vdpasim_blk_buffer_lock(blk); bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, - vdpasim->buffer + offset, - to_pull); + blk->buffer + offset, to_pull); + vdpasim_blk_buffer_unlock(blk); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -248,8 +281,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, } if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - memset(vdpasim->buffer + offset, 0, + vdpasim_blk_buffer_lock(blk); + memset(blk->buffer + offset, 0, num_sectors << SECTOR_SHIFT); + vdpasim_blk_buffer_unlock(blk); } break; @@ -286,13 +321,12 @@ err: return handled; } -static void vdpasim_blk_work(struct work_struct *work) +static void vdpasim_blk_work(struct vdpasim *vdpasim) { - struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); bool reschedule = false; int i; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) goto out; @@ -323,10 +357,10 @@ static void vdpasim_blk_work(struct work_struct *work) } } out: - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); if (reschedule) - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); } static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config) @@ -355,6 +389,14 @@ static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config) } +static void vdpasim_blk_free(struct vdpasim *vdpasim) +{ + struct vdpasim_blk *blk = sim_to_blk(vdpasim); + + if (!blk->shared_backend) + kvfree(blk->buffer); +} + static void vdpasim_blk_mgmtdev_release(struct device *dev) { } @@ -368,6 +410,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; + struct vdpasim_blk *blk; struct vdpasim *simdev; int ret; @@ -378,16 +421,30 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.nvqs = VDPASIM_BLK_VQ_NUM; dev_attr.ngroups = VDPASIM_BLK_GROUP_NUM; dev_attr.nas = VDPASIM_BLK_AS_NUM; - dev_attr.alloc_size = sizeof(struct vdpasim); + dev_attr.alloc_size = sizeof(struct vdpasim_blk); dev_attr.config_size = sizeof(struct virtio_blk_config); dev_attr.get_config = vdpasim_blk_get_config; dev_attr.work_fn = vdpasim_blk_work; - dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT; + dev_attr.free = vdpasim_blk_free; simdev = vdpasim_create(&dev_attr, config); if (IS_ERR(simdev)) return PTR_ERR(simdev); + blk = sim_to_blk(simdev); + blk->shared_backend = shared_backend; + + if (blk->shared_backend) { + blk->buffer = shared_buffer; + } else { + blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + GFP_KERNEL); + if (!blk->buffer) { + ret = -ENOMEM; + goto put_dev; + } + } + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_BLK_VQ_NUM); if (ret) goto put_dev; @@ -437,6 +494,15 @@ static int __init vdpasim_blk_init(void) if (ret) goto parent_err; + if (shared_backend) { + shared_buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + GFP_KERNEL); + if (!shared_buffer) { + ret = -ENOMEM; + goto parent_err; + } + } + return 0; parent_err: @@ -446,6 +512,7 @@ parent_err: static void __exit vdpasim_blk_exit(void) { + kvfree(shared_buffer); vdpa_mgmtdev_unregister(&mgmt_dev); device_unregister(&vdpasim_blk_mgmtdev); } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index dfe2ce341803..cfe962911804 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -59,6 +58,7 @@ struct vdpasim_net{ struct vdpasim_dataq_stats tx_stats; struct vdpasim_dataq_stats rx_stats; struct vdpasim_cq_stats cq_stats; + void *buffer; }; static struct vdpasim_net *sim_to_net(struct vdpasim *vdpasim) @@ -88,14 +88,15 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len) size_t hdr_len = modern ? sizeof(struct virtio_net_hdr_v1) : sizeof(struct virtio_net_hdr); struct virtio_net_config *vio_config = vdpasim->config; + struct vdpasim_net *net = sim_to_net(vdpasim); if (len < ETH_ALEN + hdr_len) return false; - if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) || - is_multicast_ether_addr(vdpasim->buffer + hdr_len)) + if (is_broadcast_ether_addr(net->buffer + hdr_len) || + is_multicast_ether_addr(net->buffer + hdr_len)) return true; - if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN)) + if (!strncmp(net->buffer + hdr_len, vio_config->mac, ETH_ALEN)) return true; return false; @@ -192,9 +193,8 @@ static void vdpasim_handle_cvq(struct vdpasim *vdpasim) u64_stats_update_end(&net->cq_stats.syncp); } -static void vdpasim_net_work(struct work_struct *work) +static void vdpasim_net_work(struct vdpasim *vdpasim) { - struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); struct vdpasim_virtqueue *txq = &vdpasim->vqs[1]; struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0]; struct vdpasim_net *net = sim_to_net(vdpasim); @@ -203,7 +203,7 @@ static void vdpasim_net_work(struct work_struct *work) u64 rx_drops = 0, rx_overruns = 0, rx_errors = 0, tx_errors = 0; int err; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); if (!vdpasim->running) goto out; @@ -227,8 +227,7 @@ static void vdpasim_net_work(struct work_struct *work) ++tx_pkts; read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov, - vdpasim->buffer, - PAGE_SIZE); + net->buffer, PAGE_SIZE); tx_bytes += read; @@ -247,7 +246,7 @@ static void vdpasim_net_work(struct work_struct *work) } write = vringh_iov_push_iotlb(&rxq->vring, &rxq->in_iov, - vdpasim->buffer, read); + net->buffer, read); if (write <= 0) { ++rx_errors; break; @@ -260,13 +259,13 @@ static void vdpasim_net_work(struct work_struct *work) vdpasim_net_complete(rxq, write); if (tx_pkts > 4) { - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); goto out; } } out: - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); u64_stats_update_begin(&net->tx_stats.syncp); net->tx_stats.pkts += tx_pkts; @@ -429,6 +428,13 @@ static void vdpasim_net_setup_config(struct vdpasim *vdpasim, vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500); } +static void vdpasim_net_free(struct vdpasim *vdpasim) +{ + struct vdpasim_net *net = sim_to_net(vdpasim); + + kvfree(net->buffer); +} + static void vdpasim_net_mgmtdev_release(struct device *dev) { } @@ -458,7 +464,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.get_config = vdpasim_net_get_config; dev_attr.work_fn = vdpasim_net_work; dev_attr.get_stats = vdpasim_net_get_stats; - dev_attr.buffer_size = PAGE_SIZE; + dev_attr.free = vdpasim_net_free; simdev = vdpasim_create(&dev_attr, config); if (IS_ERR(simdev)) @@ -472,6 +478,12 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, u64_stats_init(&net->rx_stats.syncp); u64_stats_init(&net->cq_stats.syncp); + net->buffer = kvmalloc(PAGE_SIZE, GFP_KERNEL); + if (!net->buffer) { + ret = -ENOMEM; + goto reg_err; + } + /* * Initialization must be completed before this call, since it can * connect the device to the vDPA bus, so requests can arrive after diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index c421b83f6fa2..de97e38c3b82 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -37,10 +37,15 @@ #define DRV_LICENSE "GPL v2" #define VDUSE_DEV_MAX (1U << MINORBITS) +#define VDUSE_MAX_BOUNCE_SIZE (1024 * 1024 * 1024) +#define VDUSE_MIN_BOUNCE_SIZE (1024 * 1024) #define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024) -#define VDUSE_IOVA_SIZE (128 * 1024 * 1024) +/* 128 MB reserved for virtqueue creation */ +#define VDUSE_IOVA_SIZE (VDUSE_MAX_BOUNCE_SIZE + 128 * 1024 * 1024) #define VDUSE_MSG_DEFAULT_TIMEOUT 30 +#define IRQ_UNBOUND -1 + struct vduse_virtqueue { u16 index; u16 num_max; @@ -57,6 +62,9 @@ struct vduse_virtqueue { struct vdpa_callback cb; struct work_struct inject; struct work_struct kick; + int irq_effective_cpu; + struct cpumask irq_affinity; + struct kobject kobj; }; struct vduse_dev; @@ -76,7 +84,7 @@ struct vduse_umem { struct vduse_dev { struct vduse_vdpa *vdev; struct device *dev; - struct vduse_virtqueue *vqs; + struct vduse_virtqueue **vqs; struct vduse_iova_domain *domain; char *name; struct mutex lock; @@ -106,6 +114,8 @@ struct vduse_dev { u32 vq_align; struct vduse_umem *umem; struct mutex mem_lock; + unsigned int bounce_size; + struct mutex domain_lock; }; struct vduse_dev_msg { @@ -128,6 +138,7 @@ static struct class *vduse_class; static struct cdev vduse_ctrl_cdev; static struct cdev vduse_cdev; static struct workqueue_struct *vduse_irq_wq; +static struct workqueue_struct *vduse_irq_bound_wq; static u32 allowed_device_id[] = { VIRTIO_ID_BLOCK, @@ -419,7 +430,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) struct vduse_iova_domain *domain = dev->domain; /* The coherent mappings are handled in vduse_dev_free_coherent() */ - if (domain->bounce_map) + if (domain && domain->bounce_map) vduse_domain_reset_bounce_map(domain); down_write(&dev->rwsem); @@ -434,7 +445,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) flush_work(&dev->inject); for (i = 0; i < dev->vq_num; i++) { - struct vduse_virtqueue *vq = &dev->vqs[i]; + struct vduse_virtqueue *vq = dev->vqs[i]; vq->ready = false; vq->desc_addr = 0; @@ -453,6 +464,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) spin_lock(&vq->irq_lock); vq->cb.callback = NULL; vq->cb.private = NULL; + vq->cb.trigger = NULL; spin_unlock(&vq->irq_lock); flush_work(&vq->inject); flush_work(&vq->kick); @@ -466,7 +478,7 @@ static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx, u64 device_area) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->desc_addr = desc_area; vq->driver_addr = driver_area; @@ -500,7 +512,7 @@ static void vduse_vq_kick_work(struct work_struct *work) static void vduse_vdpa_kick_vq(struct vdpa_device *vdpa, u16 idx) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (!eventfd_signal_allowed()) { schedule_work(&vq->kick); @@ -513,18 +525,19 @@ static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx, struct vdpa_callback *cb) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; spin_lock(&vq->irq_lock); vq->cb.callback = cb->callback; vq->cb.private = cb->private; + vq->cb.trigger = cb->trigger; spin_unlock(&vq->irq_lock); } static void vduse_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->num = num; } @@ -533,7 +546,7 @@ static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->ready = ready; } @@ -541,7 +554,7 @@ static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa, static bool vduse_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 idx) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; return vq->ready; } @@ -550,7 +563,7 @@ static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx, const struct vdpa_vq_state *state) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) { vq->state.packed.last_avail_counter = @@ -569,7 +582,7 @@ static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx, struct vdpa_vq_state *state) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) return vduse_dev_get_vq_state_packed(dev, vq, &state->packed); @@ -624,8 +637,8 @@ static u16 vduse_vdpa_get_vq_num_max(struct vdpa_device *vdpa) int i; for (i = 0; i < dev->vq_num; i++) - if (num_max < dev->vqs[i].num_max) - num_max = dev->vqs[i].num_max; + if (num_max < dev->vqs[i]->num_max) + num_max = dev->vqs[i]->num_max; return num_max; } @@ -708,6 +721,23 @@ static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa) return dev->generation; } +static int vduse_vdpa_set_vq_affinity(struct vdpa_device *vdpa, u16 idx, + const struct cpumask *cpu_mask) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + cpumask_copy(&dev->vqs[idx]->irq_affinity, cpu_mask); + return 0; +} + +static const struct cpumask * +vduse_vdpa_get_vq_affinity(struct vdpa_device *vdpa, u16 idx) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return &dev->vqs[idx]->irq_affinity; +} + static int vduse_vdpa_set_map(struct vdpa_device *vdpa, unsigned int asid, struct vhost_iotlb *iotlb) @@ -758,6 +788,8 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = { .get_config = vduse_vdpa_get_config, .set_config = vduse_vdpa_set_config, .get_generation = vduse_vdpa_get_generation, + .set_vq_affinity = vduse_vdpa_set_vq_affinity, + .get_vq_affinity = vduse_vdpa_get_vq_affinity, .reset = vduse_vdpa_reset, .set_map = vduse_vdpa_set_map, .free = vduse_vdpa_free, @@ -863,7 +895,7 @@ static int vduse_kickfd_setup(struct vduse_dev *dev, return -EINVAL; index = array_index_nospec(eventfd->index, dev->vq_num); - vq = &dev->vqs[index]; + vq = dev->vqs[index]; if (eventfd->fd >= 0) { ctx = eventfd_ctx_fdget(eventfd->fd); if (IS_ERR(ctx)) @@ -889,7 +921,7 @@ static bool vduse_dev_is_ready(struct vduse_dev *dev) int i; for (i = 0; i < dev->vq_num; i++) - if (!dev->vqs[i].num_max) + if (!dev->vqs[i]->num_max) return false; return true; @@ -916,8 +948,26 @@ static void vduse_vq_irq_inject(struct work_struct *work) spin_unlock_irq(&vq->irq_lock); } +static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq) +{ + bool signal = false; + + if (!vq->cb.trigger) + return false; + + spin_lock_irq(&vq->irq_lock); + if (vq->ready && vq->cb.trigger) { + eventfd_signal(vq->cb.trigger, 1); + signal = true; + } + spin_unlock_irq(&vq->irq_lock); + + return signal; +} + static int vduse_dev_queue_irq_work(struct vduse_dev *dev, - struct work_struct *irq_work) + struct work_struct *irq_work, + int irq_effective_cpu) { int ret = -EINVAL; @@ -926,7 +976,11 @@ static int vduse_dev_queue_irq_work(struct vduse_dev *dev, goto unlock; ret = 0; - queue_work(vduse_irq_wq, irq_work); + if (irq_effective_cpu == IRQ_UNBOUND) + queue_work(vduse_irq_wq, irq_work); + else + queue_work_on(irq_effective_cpu, + vduse_irq_bound_wq, irq_work); unlock: up_read(&dev->rwsem); @@ -944,6 +998,9 @@ static int vduse_dev_dereg_umem(struct vduse_dev *dev, goto unlock; ret = -EINVAL; + if (!dev->domain) + goto unlock; + if (dev->umem->iova != iova || size != dev->domain->bounce_size) goto unlock; @@ -970,7 +1027,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev, unsigned long npages, lock_limit; int ret; - if (!dev->domain->bounce_map || + if (!dev->domain || !dev->domain->bounce_map || size != dev->domain->bounce_size || iova != 0 || uaddr & ~PAGE_MASK) return -EINVAL; @@ -1029,6 +1086,22 @@ unlock: return ret; } +static void vduse_vq_update_effective_cpu(struct vduse_virtqueue *vq) +{ + int curr_cpu = vq->irq_effective_cpu; + + while (true) { + curr_cpu = cpumask_next(curr_cpu, &vq->irq_affinity); + if (cpu_online(curr_cpu)) + break; + + if (curr_cpu >= nr_cpu_ids) + curr_cpu = IRQ_UNBOUND; + } + + vq->irq_effective_cpu = curr_cpu; +} + static long vduse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1044,7 +1117,6 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, struct vduse_iotlb_entry entry; struct vhost_iotlb_map *map; struct vdpa_map_file *map_file; - struct vduse_iova_domain *domain = dev->domain; struct file *f = NULL; ret = -EFAULT; @@ -1055,8 +1127,13 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (entry.start > entry.last) break; - spin_lock(&domain->iotlb_lock); - map = vhost_iotlb_itree_first(domain->iotlb, + mutex_lock(&dev->domain_lock); + if (!dev->domain) { + mutex_unlock(&dev->domain_lock); + break; + } + spin_lock(&dev->domain->iotlb_lock); + map = vhost_iotlb_itree_first(dev->domain->iotlb, entry.start, entry.last); if (map) { map_file = (struct vdpa_map_file *)map->opaque; @@ -1066,7 +1143,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, entry.last = map->last; entry.perm = map->perm; } - spin_unlock(&domain->iotlb_lock); + spin_unlock(&dev->domain->iotlb_lock); + mutex_unlock(&dev->domain_lock); ret = -EINVAL; if (!f) break; @@ -1111,7 +1189,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; } case VDUSE_DEV_INJECT_CONFIG_IRQ: - ret = vduse_dev_queue_irq_work(dev, &dev->inject); + ret = vduse_dev_queue_irq_work(dev, &dev->inject, IRQ_UNBOUND); break; case VDUSE_VQ_SETUP: { struct vduse_vq_config config; @@ -1130,7 +1208,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(config.index, dev->vq_num); - dev->vqs[index].num_max = config.max_size; + dev->vqs[index]->num_max = config.max_size; ret = 0; break; } @@ -1148,7 +1226,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(vq_info.index, dev->vq_num); - vq = &dev->vqs[index]; + vq = dev->vqs[index]; vq_info.desc_addr = vq->desc_addr; vq_info.driver_addr = vq->driver_addr; vq_info.device_addr = vq->device_addr; @@ -1197,8 +1275,14 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (index >= dev->vq_num) break; + ret = 0; index = array_index_nospec(index, dev->vq_num); - ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject); + if (!vduse_vq_signal_irqfd(dev->vqs[index])) { + vduse_vq_update_effective_cpu(dev->vqs[index]); + ret = vduse_dev_queue_irq_work(dev, + &dev->vqs[index]->inject, + dev->vqs[index]->irq_effective_cpu); + } break; } case VDUSE_IOTLB_REG_UMEM: { @@ -1213,8 +1297,10 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, sizeof(umem.reserved))) break; + mutex_lock(&dev->domain_lock); ret = vduse_dev_reg_umem(dev, umem.iova, umem.uaddr, umem.size); + mutex_unlock(&dev->domain_lock); break; } case VDUSE_IOTLB_DEREG_UMEM: { @@ -1228,15 +1314,15 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (!is_mem_zero((const char *)umem.reserved, sizeof(umem.reserved))) break; - + mutex_lock(&dev->domain_lock); ret = vduse_dev_dereg_umem(dev, umem.iova, umem.size); + mutex_unlock(&dev->domain_lock); break; } case VDUSE_IOTLB_GET_INFO: { struct vduse_iova_info info; struct vhost_iotlb_map *map; - struct vduse_iova_domain *domain = dev->domain; ret = -EFAULT; if (copy_from_user(&info, argp, sizeof(info))) @@ -1250,18 +1336,24 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, sizeof(info.reserved))) break; - spin_lock(&domain->iotlb_lock); - map = vhost_iotlb_itree_first(domain->iotlb, + mutex_lock(&dev->domain_lock); + if (!dev->domain) { + mutex_unlock(&dev->domain_lock); + break; + } + spin_lock(&dev->domain->iotlb_lock); + map = vhost_iotlb_itree_first(dev->domain->iotlb, info.start, info.last); if (map) { info.start = map->start; info.last = map->last; info.capability = 0; - if (domain->bounce_map && map->start == 0 && - map->last == domain->bounce_size - 1) + if (dev->domain->bounce_map && map->start == 0 && + map->last == dev->domain->bounce_size - 1) info.capability |= VDUSE_IOVA_CAP_UMEM; } - spin_unlock(&domain->iotlb_lock); + spin_unlock(&dev->domain->iotlb_lock); + mutex_unlock(&dev->domain_lock); if (!map) break; @@ -1284,7 +1376,10 @@ static int vduse_dev_release(struct inode *inode, struct file *file) { struct vduse_dev *dev = file->private_data; - vduse_dev_dereg_umem(dev, 0, dev->domain->bounce_size); + mutex_lock(&dev->domain_lock); + if (dev->domain) + vduse_dev_dereg_umem(dev, 0, dev->domain->bounce_size); + mutex_unlock(&dev->domain_lock); spin_lock(&dev->msg_lock); /* Make sure the inflight messages can processed after reconncection */ list_splice_init(&dev->recv_list, &dev->send_list); @@ -1339,6 +1434,151 @@ static const struct file_operations vduse_dev_fops = { .llseek = noop_llseek, }; +static ssize_t irq_cb_affinity_show(struct vduse_virtqueue *vq, char *buf) +{ + return sprintf(buf, "%*pb\n", cpumask_pr_args(&vq->irq_affinity)); +} + +static ssize_t irq_cb_affinity_store(struct vduse_virtqueue *vq, + const char *buf, size_t count) +{ + cpumask_var_t new_value; + int ret; + + if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + + ret = cpumask_parse(buf, new_value); + if (ret) + goto free_mask; + + ret = -EINVAL; + if (!cpumask_intersects(new_value, cpu_online_mask)) + goto free_mask; + + cpumask_copy(&vq->irq_affinity, new_value); + ret = count; +free_mask: + free_cpumask_var(new_value); + return ret; +} + +struct vq_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct vduse_virtqueue *vq, char *buf); + ssize_t (*store)(struct vduse_virtqueue *vq, const char *buf, + size_t count); +}; + +static struct vq_sysfs_entry irq_cb_affinity_attr = __ATTR_RW(irq_cb_affinity); + +static struct attribute *vq_attrs[] = { + &irq_cb_affinity_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(vq); + +static ssize_t vq_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + struct vq_sysfs_entry *entry = container_of(attr, + struct vq_sysfs_entry, attr); + + if (!entry->show) + return -EIO; + + return entry->show(vq, buf); +} + +static ssize_t vq_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + struct vq_sysfs_entry *entry = container_of(attr, + struct vq_sysfs_entry, attr); + + if (!entry->store) + return -EIO; + + return entry->store(vq, buf, count); +} + +static const struct sysfs_ops vq_sysfs_ops = { + .show = vq_attr_show, + .store = vq_attr_store, +}; + +static void vq_release(struct kobject *kobj) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + kfree(vq); +} + +static const struct kobj_type vq_type = { + .release = vq_release, + .sysfs_ops = &vq_sysfs_ops, + .default_groups = vq_groups, +}; + +static void vduse_dev_deinit_vqs(struct vduse_dev *dev) +{ + int i; + + if (!dev->vqs) + return; + + for (i = 0; i < dev->vq_num; i++) + kobject_put(&dev->vqs[i]->kobj); + kfree(dev->vqs); +} + +static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) +{ + int ret, i; + + dev->vq_align = vq_align; + dev->vq_num = vq_num; + dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL); + if (!dev->vqs) + return -ENOMEM; + + for (i = 0; i < vq_num; i++) { + dev->vqs[i] = kzalloc(sizeof(*dev->vqs[i]), GFP_KERNEL); + if (!dev->vqs[i]) { + ret = -ENOMEM; + goto err; + } + + dev->vqs[i]->index = i; + dev->vqs[i]->irq_effective_cpu = IRQ_UNBOUND; + INIT_WORK(&dev->vqs[i]->inject, vduse_vq_irq_inject); + INIT_WORK(&dev->vqs[i]->kick, vduse_vq_kick_work); + spin_lock_init(&dev->vqs[i]->kick_lock); + spin_lock_init(&dev->vqs[i]->irq_lock); + cpumask_setall(&dev->vqs[i]->irq_affinity); + + kobject_init(&dev->vqs[i]->kobj, &vq_type); + ret = kobject_add(&dev->vqs[i]->kobj, + &dev->dev->kobj, "vq%d", i); + if (ret) { + kfree(dev->vqs[i]); + goto err; + } + } + + return 0; +err: + while (i--) + kobject_put(&dev->vqs[i]->kobj); + kfree(dev->vqs); + dev->vqs = NULL; + return ret; +} + static struct vduse_dev *vduse_dev_create(void) { struct vduse_dev *dev = kzalloc(sizeof(*dev), GFP_KERNEL); @@ -1348,6 +1588,7 @@ static struct vduse_dev *vduse_dev_create(void) mutex_init(&dev->lock); mutex_init(&dev->mem_lock); + mutex_init(&dev->domain_lock); spin_lock_init(&dev->msg_lock); INIT_LIST_HEAD(&dev->send_list); INIT_LIST_HEAD(&dev->recv_list); @@ -1396,8 +1637,9 @@ static int vduse_destroy_dev(char *name) device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor)); idr_remove(&vduse_idr, dev->minor); kvfree(dev->config); - kfree(dev->vqs); - vduse_domain_destroy(dev->domain); + vduse_dev_deinit_vqs(dev); + if (dev->domain) + vduse_domain_destroy(dev->domain); kfree(dev->name); vduse_dev_destroy(dev); module_put(THIS_MODULE); @@ -1476,8 +1718,48 @@ static ssize_t msg_timeout_store(struct device *device, static DEVICE_ATTR_RW(msg_timeout); +static ssize_t bounce_size_show(struct device *device, + struct device_attribute *attr, char *buf) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + + return sysfs_emit(buf, "%u\n", dev->bounce_size); +} + +static ssize_t bounce_size_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + unsigned int bounce_size; + int ret; + + ret = -EPERM; + mutex_lock(&dev->domain_lock); + if (dev->domain) + goto unlock; + + ret = kstrtouint(buf, 10, &bounce_size); + if (ret < 0) + goto unlock; + + ret = -EINVAL; + if (bounce_size > VDUSE_MAX_BOUNCE_SIZE || + bounce_size < VDUSE_MIN_BOUNCE_SIZE) + goto unlock; + + dev->bounce_size = bounce_size & PAGE_MASK; + ret = count; +unlock: + mutex_unlock(&dev->domain_lock); + return ret; +} + +static DEVICE_ATTR_RW(bounce_size); + static struct attribute *vduse_dev_attrs[] = { &dev_attr_msg_timeout.attr, + &dev_attr_bounce_size.attr, NULL }; @@ -1486,7 +1768,7 @@ ATTRIBUTE_GROUPS(vduse_dev); static int vduse_create_dev(struct vduse_dev_config *config, void *config_buf, u64 api_version) { - int i, ret; + int ret; struct vduse_dev *dev; ret = -EEXIST; @@ -1506,26 +1788,9 @@ static int vduse_create_dev(struct vduse_dev_config *config, if (!dev->name) goto err_str; - dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1, - VDUSE_BOUNCE_SIZE); - if (!dev->domain) - goto err_domain; - + dev->bounce_size = VDUSE_BOUNCE_SIZE; dev->config = config_buf; dev->config_size = config->config_size; - dev->vq_align = config->vq_align; - dev->vq_num = config->vq_num; - dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL); - if (!dev->vqs) - goto err_vqs; - - for (i = 0; i < dev->vq_num; i++) { - dev->vqs[i].index = i; - INIT_WORK(&dev->vqs[i].inject, vduse_vq_irq_inject); - INIT_WORK(&dev->vqs[i].kick, vduse_vq_kick_work); - spin_lock_init(&dev->vqs[i].kick_lock); - spin_lock_init(&dev->vqs[i].irq_lock); - } ret = idr_alloc(&vduse_idr, dev, 1, VDUSE_DEV_MAX, GFP_KERNEL); if (ret < 0) @@ -1540,16 +1805,19 @@ static int vduse_create_dev(struct vduse_dev_config *config, ret = PTR_ERR(dev->dev); goto err_dev; } + + ret = vduse_dev_init_vqs(dev, config->vq_align, config->vq_num); + if (ret) + goto err_vqs; + __module_get(THIS_MODULE); return 0; +err_vqs: + device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor)); err_dev: idr_remove(&vduse_idr, dev->minor); err_idr: - kfree(dev->vqs); -err_vqs: - vduse_domain_destroy(dev->domain); -err_domain: kfree(dev->name); err_str: vduse_dev_destroy(dev); @@ -1716,9 +1984,23 @@ static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, if (ret) return ret; + mutex_lock(&dev->domain_lock); + if (!dev->domain) + dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1, + dev->bounce_size); + mutex_unlock(&dev->domain_lock); + if (!dev->domain) { + put_device(&dev->vdev->vdpa.dev); + return -ENOMEM; + } + ret = _vdpa_register_device(&dev->vdev->vdpa, dev->vq_num); if (ret) { put_device(&dev->vdev->vdpa.dev); + mutex_lock(&dev->domain_lock); + vduse_domain_destroy(dev->domain); + dev->domain = NULL; + mutex_unlock(&dev->domain_lock); return ret; } @@ -1824,12 +2106,15 @@ static int vduse_init(void) if (ret) goto err_cdev; + ret = -ENOMEM; vduse_irq_wq = alloc_workqueue("vduse-irq", WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0); - if (!vduse_irq_wq) { - ret = -ENOMEM; + if (!vduse_irq_wq) goto err_wq; - } + + vduse_irq_bound_wq = alloc_workqueue("vduse-irq-bound", WQ_HIGHPRI, 0); + if (!vduse_irq_bound_wq) + goto err_bound_wq; ret = vduse_domain_init(); if (ret) @@ -1843,6 +2128,8 @@ static int vduse_init(void) err_mgmtdev: vduse_domain_exit(); err_domain: + destroy_workqueue(vduse_irq_bound_wq); +err_bound_wq: destroy_workqueue(vduse_irq_wq); err_wq: cdev_del(&vduse_cdev); @@ -1862,6 +2149,7 @@ static void vduse_exit(void) { vduse_mgmtdev_exit(); vduse_domain_exit(); + destroy_workqueue(vduse_irq_bound_wq); destroy_workqueue(vduse_irq_wq); cdev_del(&vduse_cdev); device_destroy(vduse_class, vduse_major); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 139ad52d0aa1..bb10fa4bb4f6 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -229,7 +229,10 @@ struct vhost_scsi_ctx { struct iov_iter out_iter; }; -/* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ +/* + * Global mutex to protect vhost_scsi TPG list for vhost IOCTLs and LIO + * configfs management operations. + */ static DEFINE_MUTEX(vhost_scsi_mutex); static LIST_HEAD(vhost_scsi_list); @@ -1501,7 +1504,7 @@ out: * vhost_scsi_tpg with an active struct vhost_scsi_nexus * * The lock nesting rule is: - * vhost_scsi_mutex -> vs->dev.mutex -> tpg->tv_tpg_mutex -> vq->mutex + * vs->dev.mutex -> vhost_scsi_mutex -> tpg->tv_tpg_mutex -> vq->mutex */ static int vhost_scsi_set_endpoint(struct vhost_scsi *vs, @@ -1515,7 +1518,6 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, int index, ret, i, len; bool match = false; - mutex_lock(&vhost_scsi_mutex); mutex_lock(&vs->dev.mutex); /* Verify that ring has been setup correctly. */ @@ -1536,6 +1538,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (vs->vs_tpg) memcpy(vs_tpg, vs->vs_tpg, len); + mutex_lock(&vhost_scsi_mutex); list_for_each_entry(tpg, &vhost_scsi_list, tv_tpg_list) { mutex_lock(&tpg->tv_tpg_mutex); if (!tpg->tpg_nexus) { @@ -1551,6 +1554,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { mutex_unlock(&tpg->tv_tpg_mutex); + mutex_unlock(&vhost_scsi_mutex); ret = -EEXIST; goto undepend; } @@ -1565,6 +1569,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); mutex_unlock(&tpg->tv_tpg_mutex); + mutex_unlock(&vhost_scsi_mutex); goto undepend; } tpg->tv_tpg_vhost_count++; @@ -1574,6 +1579,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, } mutex_unlock(&tpg->tv_tpg_mutex); } + mutex_unlock(&vhost_scsi_mutex); if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, @@ -1629,7 +1635,6 @@ undepend: kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return ret; } @@ -1645,7 +1650,6 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, int index, ret, i; u8 target; - mutex_lock(&vhost_scsi_mutex); mutex_lock(&vs->dev.mutex); /* Verify that ring has been setup correctly. */ for (index = 0; index < vs->dev.nvqs; ++index) { @@ -1666,11 +1670,10 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, if (!tpg) continue; - mutex_lock(&tpg->tv_tpg_mutex); tv_tport = tpg->tport; if (!tv_tport) { ret = -ENODEV; - goto err_tpg; + goto err_dev; } if (strcmp(tv_tport->tport_name, t->vhost_wwpn)) { @@ -1679,35 +1682,51 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, tv_tport->tport_name, tpg->tport_tpgt, t->vhost_wwpn, t->vhost_tpgt); ret = -EINVAL; - goto err_tpg; + goto err_dev; } + match = true; + } + if (!match) + goto free_vs_tpg; + + /* Prevent new cmds from starting and accessing the tpgs/sessions */ + for (i = 0; i < vs->dev.nvqs; i++) { + vq = &vs->vqs[i].vq; + mutex_lock(&vq->mutex); + vhost_vq_set_backend(vq, NULL); + mutex_unlock(&vq->mutex); + } + /* Make sure cmds are not running before tearing them down. */ + vhost_scsi_flush(vs); + + for (i = 0; i < vs->dev.nvqs; i++) { + vq = &vs->vqs[i].vq; + vhost_scsi_destroy_vq_cmds(vq); + } + + /* + * We can now release our hold on the tpg and sessions and userspace + * can free them after this point. + */ + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + target = i; + tpg = vs->vs_tpg[target]; + if (!tpg) + continue; + + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_vhost_count--; tpg->vhost_scsi = NULL; vs->vs_tpg[target] = NULL; - match = true; + mutex_unlock(&tpg->tv_tpg_mutex); - /* - * Release se_tpg->tpg_group.cg_item configfs dependency now - * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur. - */ + se_tpg = &tpg->se_tpg; target_undepend_item(&se_tpg->tpg_group.cg_item); } - if (match) { - for (i = 0; i < vs->dev.nvqs; i++) { - vq = &vs->vqs[i].vq; - mutex_lock(&vq->mutex); - vhost_vq_set_backend(vq, NULL); - mutex_unlock(&vq->mutex); - } - /* Make sure cmds are not running before tearing them down. */ - vhost_scsi_flush(vs); - for (i = 0; i < vs->dev.nvqs; i++) { - vq = &vs->vqs[i].vq; - vhost_scsi_destroy_vq_cmds(vq); - } - } +free_vs_tpg: /* * Act as synchronize_rcu to make sure access to * old vs->vs_tpg is finished. @@ -1717,14 +1736,10 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, vs->vs_tpg = NULL; WARN_ON(vs->vs_events_nr); mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return 0; -err_tpg: - mutex_unlock(&tpg->tv_tpg_mutex); err_dev: mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return ret; } @@ -1965,8 +1980,6 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg, if (!vs) return; - mutex_lock(&vs->dev.mutex); - if (plug) reason = VIRTIO_SCSI_EVT_RESET_RESCAN; else @@ -1974,11 +1987,18 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg, vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq; mutex_lock(&vq->mutex); + /* + * We can't queue events if the backend has been cleared, because + * we could end up queueing an event after the flush. + */ + if (!vhost_vq_get_backend(vq)) + goto unlock; + if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG)) vhost_scsi_send_evt(vs, tpg, lun, VIRTIO_SCSI_T_TRANSPORT_RESET, reason); +unlock: mutex_unlock(&vq->mutex); - mutex_unlock(&vs->dev.mutex); } static void vhost_scsi_hotplug(struct vhost_scsi_tpg *tpg, struct se_lun *lun) @@ -1997,15 +2017,10 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - mutex_lock(&vhost_scsi_mutex); - mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; - mutex_unlock(&tpg->tv_tpg_mutex); - vhost_scsi_hotplug(tpg, lun); - - mutex_unlock(&vhost_scsi_mutex); + mutex_unlock(&tpg->tv_tpg_mutex); return 0; } @@ -2016,15 +2031,10 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - mutex_lock(&vhost_scsi_mutex); - mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - vhost_scsi_hotunplug(tpg, lun); - - mutex_unlock(&vhost_scsi_mutex); + mutex_unlock(&tpg->tv_tpg_mutex); } static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 135ad39958cc..8c1aefc865f0 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -219,6 +219,28 @@ static int vhost_vdpa_reset(struct vhost_vdpa *v) return vdpa_reset(vdpa); } +static long vhost_vdpa_bind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->bind_mm) + return 0; + + return ops->bind_mm(vdpa, v->vdev.mm); +} + +static void vhost_vdpa_unbind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->unbind_mm) + return; + + ops->unbind_mm(vdpa); +} + static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) { struct vdpa_device *vdpa = v->vdpa; @@ -599,9 +621,11 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, if (vq->call_ctx.ctx) { cb.callback = vhost_vdpa_virtqueue_cb; cb.private = vq; + cb.trigger = vq->call_ctx.ctx; } else { cb.callback = NULL; cb.private = NULL; + cb.trigger = NULL; } ops->set_vq_cb(vdpa, idx, &cb); vhost_vdpa_setup_vq_irq(v, idx); @@ -716,6 +740,17 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, break; } + if (r) + goto out; + + switch (cmd) { + case VHOST_SET_OWNER: + r = vhost_vdpa_bind_mm(v); + if (r) + vhost_dev_reset_owner(d, NULL); + break; + } +out: mutex_unlock(&d->mutex); return r; } @@ -851,11 +886,7 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, if (!v->in_batch) ops->set_map(vdpa, asid, iotlb); } - /* If we are in the middle of batch processing, delay the free - * of AS until BATCH_END. - */ - if (!v->in_batch && !iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); + } static int vhost_vdpa_va_map(struct vhost_vdpa *v, @@ -1112,8 +1143,6 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, if (v->in_batch && ops->set_map) ops->set_map(vdpa, asid, iotlb); v->in_batch = false; - if (!iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); break; default: r = -EINVAL; @@ -1287,6 +1316,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); + vhost_vdpa_unbind_mm(v); vhost_vdpa_config_put(v); vhost_vdpa_cleanup(v); mutex_unlock(&d->mutex); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 6d07b42833be..10bf35a3db6e 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -434,8 +434,7 @@ static size_t vhost_get_avail_size(struct vhost_virtqueue *vq, size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - return sizeof(*vq->avail) + - sizeof(*vq->avail->ring) * num + event; + return size_add(struct_size(vq->avail, ring, num), event); } static size_t vhost_get_used_size(struct vhost_virtqueue *vq, @@ -444,8 +443,7 @@ static size_t vhost_get_used_size(struct vhost_virtqueue *vq, size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - return sizeof(*vq->used) + - sizeof(*vq->used->ring) * num + event; + return size_add(struct_size(vq->used, ring, num), event); } static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index a1e27da54481..955d938eb663 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -636,9 +636,9 @@ static inline int xfer_to_user(const struct vringh *vrh, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid: you should check pointers * yourself! @@ -911,9 +911,9 @@ static inline int kern_xfer(const struct vringh *vrh, void *dst, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid. */ @@ -1094,10 +1094,17 @@ EXPORT_SYMBOL(vringh_need_notify_kern); #if IS_REACHABLE(CONFIG_VHOST_IOTLB) +struct iotlb_vec { + union { + struct iovec *iovec; + struct bio_vec *bvec; + } iov; + size_t count; +}; + static int iotlb_translate(const struct vringh *vrh, u64 addr, u64 len, u64 *translated, - struct bio_vec iov[], - int iov_size, u32 perm) + struct iotlb_vec *ivec, u32 perm) { struct vhost_iotlb_map *map; struct vhost_iotlb *iotlb = vrh->iotlb; @@ -1107,9 +1114,11 @@ static int iotlb_translate(const struct vringh *vrh, spin_lock(vrh->iotlb_lock); while (len > s) { - u64 size, pa, pfn; + uintptr_t io_addr; + size_t io_len; + u64 size; - if (unlikely(ret >= iov_size)) { + if (unlikely(ret >= ivec->count)) { ret = -ENOBUFS; break; } @@ -1124,10 +1133,22 @@ static int iotlb_translate(const struct vringh *vrh, } size = map->size - addr + map->start; - pa = map->addr + addr - map->start; - pfn = pa >> PAGE_SHIFT; - bvec_set_page(&iov[ret], pfn_to_page(pfn), min(len - s, size), - pa & (PAGE_SIZE - 1)); + io_len = min(len - s, size); + io_addr = map->addr - map->start + addr; + + if (vrh->use_va) { + struct iovec *iovec = ivec->iov.iovec; + + iovec[ret].iov_len = io_len; + iovec[ret].iov_base = (void __user *)io_addr; + } else { + u64 pfn = io_addr >> PAGE_SHIFT; + struct bio_vec *bvec = ivec->iov.bvec; + + bvec_set_page(&bvec[ret], pfn_to_page(pfn), io_len, + io_addr & (PAGE_SIZE - 1)); + } + s += size; addr += size; ++ret; @@ -1141,26 +1162,41 @@ static int iotlb_translate(const struct vringh *vrh, return ret; } +#define IOTLB_IOV_STRIDE 16 + static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; u64 total_translated = 0; + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + while (total_translated < len) { - struct bio_vec iov[16]; struct iov_iter iter; u64 translated; int ret; ret = iotlb_translate(vrh, (u64)(uintptr_t)src, len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_RO); + &ivec, VHOST_MAP_RO); if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); + ret = IOTLB_IOV_STRIDE; else if (ret < 0) return ret; - iov_iter_bvec(&iter, ITER_SOURCE, iov, ret, translated); + if (vrh->use_va) { + iov_iter_init(&iter, ITER_SOURCE, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_SOURCE, ivec.iov.bvec, ret, + translated); + } ret = copy_from_iter(dst, translated, &iter); if (ret < 0) @@ -1177,23 +1213,36 @@ static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; u64 total_translated = 0; + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + while (total_translated < len) { - struct bio_vec iov[16]; struct iov_iter iter; u64 translated; int ret; ret = iotlb_translate(vrh, (u64)(uintptr_t)dst, len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_WO); + &ivec, VHOST_MAP_WO); if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); + ret = IOTLB_IOV_STRIDE; else if (ret < 0) return ret; - iov_iter_bvec(&iter, ITER_DEST, iov, ret, translated); + if (vrh->use_va) { + iov_iter_init(&iter, ITER_DEST, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_DEST, ivec.iov.bvec, ret, + translated); + } ret = copy_to_iter(src, translated, &iter); if (ret < 0) @@ -1210,20 +1259,36 @@ static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, static inline int getu16_iotlb(const struct vringh *vrh, u16 *val, const __virtio16 *p) { - struct bio_vec iov; - void *kaddr, *from; + struct iotlb_vec ivec; + union { + struct iovec iovec[1]; + struct bio_vec bvec[1]; + } iov; + __virtio16 tmp; int ret; + ivec.iov.iovec = iov.iovec; + ivec.count = 1; + /* Atomic read is needed for getu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_RO); + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); if (ret < 0) return ret; - kaddr = kmap_atomic(iov.bv_page); - from = kaddr + iov.bv_offset; - *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); - kunmap_atomic(kaddr); + if (vrh->use_va) { + ret = __get_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + void *kaddr = kmap_local_page(ivec.iov.bvec[0].bv_page); + void *from = kaddr + ivec.iov.bvec[0].bv_offset; + + tmp = READ_ONCE(*(__virtio16 *)from); + kunmap_local(kaddr); + } + + *val = vringh16_to_cpu(vrh, tmp); return 0; } @@ -1231,20 +1296,36 @@ static inline int getu16_iotlb(const struct vringh *vrh, static inline int putu16_iotlb(const struct vringh *vrh, __virtio16 *p, u16 val) { - struct bio_vec iov; - void *kaddr, *to; + struct iotlb_vec ivec; + union { + struct iovec iovec; + struct bio_vec bvec; + } iov; + __virtio16 tmp; int ret; + ivec.iov.iovec = &iov.iovec; + ivec.count = 1; + /* Atomic write is needed for putu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_WO); + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); if (ret < 0) return ret; - kaddr = kmap_atomic(iov.bv_page); - to = kaddr + iov.bv_offset; - WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); - kunmap_atomic(kaddr); + tmp = cpu_to_vringh16(vrh, val); + + if (vrh->use_va) { + ret = __put_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + void *kaddr = kmap_local_page(ivec.iov.bvec[0].bv_page); + void *to = kaddr + ivec.iov.bvec[0].bv_offset; + + WRITE_ONCE(*(__virtio16 *)to, tmp); + kunmap_local(kaddr); + } return 0; } @@ -1306,9 +1387,9 @@ static inline int putused_iotlb(const struct vringh *vrh, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid. */ @@ -1318,11 +1399,39 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used) { + vrh->use_va = false; + return vringh_init_kern(vrh, features, num, weak_barriers, desc, avail, used); } EXPORT_SYMBOL(vringh_init_iotlb); +/** + * vringh_init_iotlb_va - initialize a vringh for a ring with IOTLB containing + * user VA. + * @vrh: the vringh to initialize. + * @features: the feature bits for this ring. + * @num: the number of elements. + * @weak_barriers: true if we only need memory barriers, not I/O. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. + * + * Returns an error if num is invalid. + */ +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used) +{ + vrh->use_va = true; + + return vringh_init_kern(vrh, features, num, weak_barriers, + desc, avail, used); +} +EXPORT_SYMBOL(vringh_init_iotlb_va); + /** * vringh_set_iotlb - initialize a vringh for a ring with IOTLB. * @vrh: the vring diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 4b5e883055ee..a46a4a29e929 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -286,6 +286,16 @@ static bool vm_notify(struct virtqueue *vq) return true; } +static bool vm_notify_with_data(struct virtqueue *vq) +{ + struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev); + u32 data = vring_notification_data(vq); + + writel(data, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY); + + return true; +} + /* Notify all virtqueues on an interrupt. */ static irqreturn_t vm_interrupt(int irq, void *opaque) { @@ -364,12 +374,18 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in const char *name, bool ctx) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); + bool (*notify)(struct virtqueue *vq); struct virtio_mmio_vq_info *info; struct virtqueue *vq; unsigned long flags; unsigned int num; int err; + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = vm_notify_with_data; + else + notify = vm_notify; + if (!name) return NULL; @@ -398,7 +414,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in /* Create the vring */ vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev, - true, true, ctx, vm_notify, callback, name); + true, true, ctx, notify, callback, name); if (!vq) { err = -ENOMEM; goto error_new_virtqueue; diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 9e496e288cfa..d6bb68ba84e5 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -288,6 +288,15 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) return vp_modern_config_vector(&vp_dev->mdev, vector); } +static bool vp_notify_with_data(struct virtqueue *vq) +{ + u32 data = vring_notification_data(vq); + + iowrite32(data, (void __iomem *)vq->priv); + + return true; +} + static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, struct virtio_pci_vq_info *info, unsigned int index, @@ -298,10 +307,16 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, { struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + bool (*notify)(struct virtqueue *vq); struct virtqueue *vq; u16 num; int err; + if (__virtio_test_bit(&vp_dev->vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = vp_notify_with_data; + else + notify = vp_notify; + if (index >= vp_modern_get_num_queues(mdev)) return ERR_PTR(-EINVAL); @@ -310,18 +325,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); - if (!is_power_of_2(num)) { - dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num); - return ERR_PTR(-EINVAL); - } - info->msix_vector = msix_vec; /* create the vring */ vq = vring_create_virtqueue(index, num, SMP_CACHE_BYTES, &vp_dev->vdev, true, true, ctx, - vp_notify, callback, name); + notify, callback, name); if (!vq) return ERR_PTR(-ENOMEM); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 41144b5246a8..c5310eaf8b46 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -231,10 +231,10 @@ static void vring_free(struct virtqueue *_vq); * Helpers. */ -#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) +#define to_vvq(_vq) container_of_const(_vq, struct vring_virtqueue, vq) -static inline bool virtqueue_use_indirect(struct vring_virtqueue *vq, - unsigned int total_sg) +static bool virtqueue_use_indirect(const struct vring_virtqueue *vq, + unsigned int total_sg) { /* * If the host supports indirect descriptor tables, and we have multiple @@ -269,7 +269,7 @@ static inline bool virtqueue_use_indirect(struct vring_virtqueue *vq, * unconditionally on data path. */ -static bool vring_use_dma_api(struct virtio_device *vdev) +static bool vring_use_dma_api(const struct virtio_device *vdev) { if (!virtio_has_dma_quirk(vdev)) return true; @@ -289,7 +289,7 @@ static bool vring_use_dma_api(struct virtio_device *vdev) return false; } -size_t virtio_max_dma_size(struct virtio_device *vdev) +size_t virtio_max_dma_size(const struct virtio_device *vdev) { size_t max_segment_size = SIZE_MAX; @@ -349,7 +349,7 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size, * making all of the arch DMA ops work on the vring device itself * is a mess. */ -static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq) +static struct device *vring_dma_dev(const struct vring_virtqueue *vq) { return vq->dma_dev; } @@ -423,7 +423,7 @@ static void virtqueue_init(struct vring_virtqueue *vq, u32 num) */ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq, - struct vring_desc *desc) + const struct vring_desc *desc) { u16 flags; @@ -784,7 +784,7 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head, } } -static inline bool more_used_split(const struct vring_virtqueue *vq) +static bool more_used_split(const struct vring_virtqueue *vq) { return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->split.vring.used->idx); @@ -854,6 +854,14 @@ static void virtqueue_disable_cb_split(struct virtqueue *_vq) if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + + /* + * If device triggered an event already it won't trigger one again: + * no need to disable. + */ + if (vq->event_triggered) + return; + if (vq->event) /* TODO: this is a hack. Figure out a cleaner value to write. */ vring_used_event(&vq->split.vring) = 0x0; @@ -1172,18 +1180,18 @@ err: /* * Packed ring specific functions - *_packed(). */ -static inline bool packed_used_wrap_counter(u16 last_used_idx) +static bool packed_used_wrap_counter(u16 last_used_idx) { return !!(last_used_idx & (1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } -static inline u16 packed_last_used(u16 last_used_idx) +static u16 packed_last_used(u16 last_used_idx) { return last_used_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, - struct vring_desc_extra *extra) + const struct vring_desc_extra *extra) { u16 flags; @@ -1206,7 +1214,7 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, } static void vring_unmap_desc_packed(const struct vring_virtqueue *vq, - struct vring_packed_desc *desc) + const struct vring_packed_desc *desc) { u16 flags; @@ -1612,7 +1620,7 @@ static inline bool is_used_desc_packed(const struct vring_virtqueue *vq, return avail == used && used == used_wrap_counter; } -static inline bool more_used_packed(const struct vring_virtqueue *vq) +static bool more_used_packed(const struct vring_virtqueue *vq) { u16 last_used; u16 last_used_idx; @@ -1699,6 +1707,14 @@ static void virtqueue_disable_cb_packed(struct virtqueue *_vq) if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; + + /* + * If device triggered an event already it won't trigger one again: + * no need to disable. + */ + if (vq->event_triggered) + return; + vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } @@ -2330,12 +2346,6 @@ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - /* If device triggered an event already it won't trigger one again: - * no need to disable. - */ - if (vq->event_triggered) - return; - if (vq->packed_ring) virtqueue_disable_cb_packed(_vq); else @@ -2752,6 +2762,23 @@ void vring_del_virtqueue(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(vring_del_virtqueue); +u32 vring_notification_data(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + u16 next; + + if (vq->packed_ring) + next = (vq->packed.next_avail_idx & + ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR))) | + vq->packed.avail_wrap_counter << + VRING_PACKED_EVENT_F_WRAP_CTR; + else + next = vq->split.avail_idx_shadow; + + return next << 16 | _vq->index; +} +EXPORT_SYMBOL_GPL(vring_notification_data); + /* Manipulates transport-specific feature bits. */ void vring_transport_features(struct virtio_device *vdev) { @@ -2771,6 +2798,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_ORDER_PLATFORM: break; + case VIRTIO_F_NOTIFICATION_DATA: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); @@ -2786,10 +2815,10 @@ EXPORT_SYMBOL_GPL(vring_transport_features); * Returns the size of the vring. This is mainly used for boasting to * userspace. Unlike other operations, this need not be serialized. */ -unsigned int virtqueue_get_vring_size(struct virtqueue *_vq) +unsigned int virtqueue_get_vring_size(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num; } @@ -2819,9 +2848,9 @@ void __virtqueue_unbreak(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(__virtqueue_unbreak); -bool virtqueue_is_broken(struct virtqueue *_vq) +bool virtqueue_is_broken(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); return READ_ONCE(vq->broken); } @@ -2868,9 +2897,9 @@ void __virtio_unbreak_device(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(__virtio_unbreak_device); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2881,9 +2910,9 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2895,9 +2924,9 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2910,7 +2939,7 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq) EXPORT_SYMBOL_GPL(virtqueue_get_used_addr); /* Only available for split ring */ -const struct vring *virtqueue_get_vring(struct virtqueue *vq) +const struct vring *virtqueue_get_vring(const struct virtqueue *vq) { return &to_vvq(vq)->split.vring; } diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index d7f5af62ddaa..eb6aee8c06b2 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -112,6 +113,17 @@ static bool virtio_vdpa_notify(struct virtqueue *vq) return true; } +static bool virtio_vdpa_notify_with_data(struct virtqueue *vq) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev); + const struct vdpa_config_ops *ops = vdpa->config; + u32 data = vring_notification_data(vq); + + ops->kick_vq_with_data(vdpa, data); + + return true; +} + static irqreturn_t virtio_vdpa_config_cb(void *private) { struct virtio_vdpa_device *vd_dev = private; @@ -138,6 +150,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, struct device *dma_dev; const struct vdpa_config_ops *ops = vdpa->config; struct virtio_vdpa_vq_info *info; + bool (*notify)(struct virtqueue *vq) = virtio_vdpa_notify; struct vdpa_callback cb; struct virtqueue *vq; u64 desc_addr, driver_addr, device_addr; @@ -154,6 +167,14 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, if (index >= vdpa->nvqs) return ERR_PTR(-ENOENT); + /* We cannot accept VIRTIO_F_NOTIFICATION_DATA without kick_vq_with_data */ + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) { + if (ops->kick_vq_with_data) + notify = virtio_vdpa_notify_with_data; + else + __virtio_clear_bit(vdev, VIRTIO_F_NOTIFICATION_DATA); + } + /* Queue shouldn't already be set up. */ if (ops->get_vq_ready(vdpa, index)) return ERR_PTR(-ENOENT); @@ -183,8 +204,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, dma_dev = vdpa_get_dma_dev(vdpa); vq = vring_create_virtqueue_dma(index, max_num, align, vdev, true, may_reduce_num, ctx, - virtio_vdpa_notify, callback, - name, dma_dev); + notify, callback, name, dma_dev); if (!vq) { err = -ENOMEM; goto error_new_virtqueue; @@ -195,6 +215,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, /* Setup virtqueue callback */ cb.callback = callback ? virtio_vdpa_virtqueue_cb : NULL; cb.private = info; + cb.trigger = NULL; ops->set_vq_cb(vdpa, index, &cb); ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq)); @@ -272,6 +293,66 @@ static void virtio_vdpa_del_vqs(struct virtio_device *vdev) virtio_vdpa_del_vq(vq); } +static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) +{ + affd->nr_sets = 1; + affd->set_size[0] = affvecs; +} + +static struct cpumask * +create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd) +{ + unsigned int affvecs = 0, curvec, usedvecs, i; + struct cpumask *masks = NULL; + + if (nvecs > affd->pre_vectors + affd->post_vectors) + affvecs = nvecs - affd->pre_vectors - affd->post_vectors; + + if (!affd->calc_sets) + affd->calc_sets = default_calc_sets; + + affd->calc_sets(affd, affvecs); + + if (!affvecs) + return NULL; + + masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL); + if (!masks) + return NULL; + + /* Fill out vectors at the beginning that don't need affinity */ + for (curvec = 0; curvec < affd->pre_vectors; curvec++) + cpumask_setall(&masks[curvec]); + + for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) { + unsigned int this_vecs = affd->set_size[i]; + int j; + struct cpumask *result = group_cpus_evenly(this_vecs); + + if (!result) { + kfree(masks); + return NULL; + } + + for (j = 0; j < this_vecs; j++) + cpumask_copy(&masks[curvec + j], &result[j]); + kfree(result); + + curvec += this_vecs; + usedvecs += this_vecs; + } + + /* Fill out vectors at the end that don't need affinity */ + if (usedvecs >= affvecs) + curvec = affd->pre_vectors + affvecs; + else + curvec = affd->pre_vectors + usedvecs; + for (; curvec < nvecs; curvec++) + cpumask_setall(&masks[curvec]); + + return masks; +} + static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], @@ -282,9 +363,15 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev); struct vdpa_device *vdpa = vd_get_vdpa(vdev); const struct vdpa_config_ops *ops = vdpa->config; + struct irq_affinity default_affd = { 0 }; + struct cpumask *masks; struct vdpa_callback cb; int i, err, queue_idx = 0; + masks = create_affinity_masks(nvqs, desc ? desc : &default_affd); + if (!masks) + return -ENOMEM; + for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; @@ -298,6 +385,7 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, err = PTR_ERR(vqs[i]); goto err_setup_vq; } + ops->set_vq_affinity(vdpa, i, &masks[i]); } cb.callback = virtio_vdpa_config_cb; @@ -337,6 +425,32 @@ static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) return dev_name(&vdpa->dev); } +static int virtio_vdpa_set_vq_affinity(struct virtqueue *vq, + const struct cpumask *cpu_mask) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev); + struct vdpa_device *vdpa = vd_dev->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + unsigned int index = vq->index; + + if (ops->set_vq_affinity) + return ops->set_vq_affinity(vdpa, index, cpu_mask); + + return 0; +} + +static const struct cpumask * +virtio_vdpa_get_vq_affinity(struct virtio_device *vdev, int index) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + if (ops->get_vq_affinity) + return ops->get_vq_affinity(vdpa, index); + + return NULL; +} + static const struct virtio_config_ops virtio_vdpa_config_ops = { .get = virtio_vdpa_get, .set = virtio_vdpa_set, @@ -349,6 +463,8 @@ static const struct virtio_config_ops virtio_vdpa_config_ops = { .get_features = virtio_vdpa_get_features, .finalize_features = virtio_vdpa_finalize_features, .bus_name = virtio_vdpa_bus_name, + .set_vq_affinity = virtio_vdpa_set_vq_affinity, + .get_vq_affinity = virtio_vdpa_get_vq_affinity, }; static void virtio_vdpa_release_dev(struct device *_d) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 617a7f4f07a8..586a1673459e 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -97,24 +97,6 @@ static struct ctl_table balloon_table[] = { { } }; -static struct ctl_table balloon_root[] = { - { - .procname = "balloon", - .mode = 0555, - .child = balloon_table, - }, - { } -}; - -static struct ctl_table xen_root[] = { - { - .procname = "xen", - .mode = 0555, - .child = balloon_root, - }, - { } -}; - #else #define xen_hotplug_unpopulated 0 #endif @@ -747,7 +729,7 @@ static int __init balloon_init(void) #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG set_online_page_callback(&xen_online_page); register_memory_notifier(&xen_memory_nb); - register_sysctl_table(xen_root); + register_sysctl_init("xen/balloon", balloon_table); #endif balloon_add_regions(); diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index d5d589bda243..b72ee9379d77 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -227,22 +227,30 @@ again: static void free_active_ring(struct sock_mapping *map); -static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, - struct sock_mapping *map) +static void pvcalls_front_destroy_active(struct pvcalls_bedata *bedata, + struct sock_mapping *map) { int i; unbind_from_irqhandler(map->active.irq, map); - spin_lock(&bedata->socket_lock); - if (!list_empty(&map->list)) - list_del_init(&map->list); - spin_unlock(&bedata->socket_lock); + if (bedata) { + spin_lock(&bedata->socket_lock); + if (!list_empty(&map->list)) + list_del_init(&map->list); + spin_unlock(&bedata->socket_lock); + } for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++) gnttab_end_foreign_access(map->active.ring->ref[i], NULL); gnttab_end_foreign_access(map->active.ref, NULL); free_active_ring(map); +} + +static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, + struct sock_mapping *map) +{ + pvcalls_front_destroy_active(bedata, map); kfree(map); } @@ -433,19 +441,18 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } + ret = create_active(map, &evtchn); + if (ret < 0) { + free_active_ring(map); + pvcalls_exit_sock(sock); + return ret; + } spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - free_active_ring(map); - pvcalls_exit_sock(sock); - return ret; - } - ret = create_active(map, &evtchn); - if (ret < 0) { - spin_unlock(&bedata->socket_lock); - free_active_ring(map); + pvcalls_front_destroy_active(NULL, map); pvcalls_exit_sock(sock); return ret; } @@ -821,28 +828,27 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) pvcalls_exit_sock(sock); return ret; } - spin_lock(&bedata->socket_lock); - ret = get_request(bedata, &req_id); - if (ret < 0) { - clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, - (void *)&map->passive.flags); - spin_unlock(&bedata->socket_lock); - free_active_ring(map2); - kfree(map2); - pvcalls_exit_sock(sock); - return ret; - } - ret = create_active(map2, &evtchn); if (ret < 0) { free_active_ring(map2); kfree(map2); clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); - spin_unlock(&bedata->socket_lock); pvcalls_exit_sock(sock); return ret; } + + spin_lock(&bedata->socket_lock); + ret = get_request(bedata, &req_id); + if (ret < 0) { + clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, + (void *)&map->passive.flags); + spin_unlock(&bedata->socket_lock); + pvcalls_front_free_map(bedata, map2); + pvcalls_exit_sock(sock); + return ret; + } + list_add_tail(&map2->list, &bedata->socket_mappings); req = RING_GET_REQUEST(&bedata->ring, req_id); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index bba527620507..e34b623e4b41 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -194,8 +194,6 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *pci_dev = NULL; unsigned long flags; - pcistub_device_get(psdev); - spin_lock_irqsave(&psdev->lock, flags); if (!psdev->pdev) { psdev->pdev = pdev; @@ -203,8 +201,8 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, } spin_unlock_irqrestore(&psdev->lock, flags); - if (!pci_dev) - pcistub_device_put(psdev); + if (pci_dev) + pcistub_device_get(psdev); return pci_dev; } diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index a7e7e02c415d..8b77e4c06e43 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1010,12 +1010,6 @@ out_free: return err; } -static void __scsiback_del_translation_entry(struct v2p_entry *entry) -{ - list_del(&entry->l); - kref_put(&entry->kref, scsiback_free_translation_entry); -} - /* Delete the translation entry specified */ @@ -1024,18 +1018,20 @@ static int scsiback_del_translation_entry(struct vscsibk_info *info, { struct v2p_entry *entry; unsigned long flags; - int ret = 0; spin_lock_irqsave(&info->v2p_lock, flags); /* Find out the translation entry specified */ entry = scsiback_chk_translation_entry(info, v); if (entry) - __scsiback_del_translation_entry(entry); - else - ret = -ENOENT; + list_del(&entry->l); spin_unlock_irqrestore(&info->v2p_lock, flags); - return ret; + + if (!entry) + return -ENOENT; + + kref_put(&entry->kref, scsiback_free_translation_entry); + return 0; } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, @@ -1239,14 +1235,19 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info) { struct v2p_entry *entry, *tmp; struct list_head *head = &(info->v2p_entry_lists); + struct list_head tmp_list; unsigned long flags; spin_lock_irqsave(&info->v2p_lock, flags); - list_for_each_entry_safe(entry, tmp, head, l) - __scsiback_del_translation_entry(entry); + list_cut_before(&tmp_list, head, head); spin_unlock_irqrestore(&info->v2p_lock, flags); + + list_for_each_entry_safe(entry, tmp, &tmp_list, l) { + list_del(&entry->l); + kref_put(&entry->kref, scsiback_free_translation_entry); + } } static void scsiback_remove(struct xenbus_device *dev) diff --git a/fs/Makefile b/fs/Makefile index 8e217f1494de..e9ca83d2fb48 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -6,7 +6,6 @@ # Rewritten to use lists instead of if-statements. # -obj-$(CONFIG_SYSCTL) += sysctls.o obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ @@ -50,7 +49,7 @@ obj-$(CONFIG_FS_MBCACHE) += mbcache.o obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_COREDUMP) += coredump.o -obj-$(CONFIG_SYSCTL) += drop_caches.o +obj-$(CONFIG_SYSCTL) += drop_caches.o sysctls.o obj-$(CONFIG_FHANDLE) += fhandle.o obj-y += iomap/ diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c index 58f8aec964e4..18de8a876b02 100644 --- a/fs/cachefiles/error_inject.c +++ b/fs/cachefiles/error_inject.c @@ -22,18 +22,9 @@ static struct ctl_table cachefiles_sysctls[] = { {} }; -static struct ctl_table cachefiles_sysctls_root[] = { - { - .procname = "cachefiles", - .mode = 0555, - .child = cachefiles_sysctls, - }, - {} -}; - int __init cachefiles_register_error_injection(void) { - cachefiles_sysctl = register_sysctl_table(cachefiles_sysctls_root); + cachefiles_sysctl = register_sysctl("cachefiles", cachefiles_sysctls); if (!cachefiles_sysctl) return -ENOMEM; return 0; diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index fda3b702b1c5..a247c14aaab7 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -39,19 +39,10 @@ static struct ctl_table coda_table[] = { {} }; -static struct ctl_table fs_table[] = { - { - .procname = "coda", - .mode = 0555, - .child = coda_table - }, - {} -}; - void coda_sysctl_init(void) { if ( !fs_table_header ) - fs_table_header = register_sysctl_table(fs_table); + fs_table_header = register_sysctl("coda", coda_table); } void coda_sysctl_clean(void) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a47303b2cba..bb94949bc223 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -510,24 +510,6 @@ static struct ctl_table nlm_sysctls[] = { { } }; -static struct ctl_table nlm_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nlm_sysctls, - }, - { } -}; - -static struct ctl_table nlm_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nlm_sysctl_dir, - }, - { } -}; - #endif /* CONFIG_SYSCTL */ /* @@ -644,7 +626,7 @@ static int __init init_nlm(void) #ifdef CONFIG_SYSCTL err = -ENOMEM; - nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root); + nlm_sysctl_table = register_sysctl("fs/nfs", nlm_sysctls); if (nlm_sysctl_table == NULL) goto err_sysctl; #endif diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index c394e4447100..e776200e9a11 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -37,27 +37,10 @@ static struct ctl_table nfs4_cb_sysctls[] = { { } }; -static struct ctl_table nfs4_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs4_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs4_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs4_cb_sysctl_dir, - }, - { } -}; - int nfs4_register_sysctl(void) { - nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root); + nfs4_callback_sysctl_table = register_sysctl("fs/nfs", + nfs4_cb_sysctls); if (nfs4_callback_sysctl_table == NULL) return -ENOMEM; return 0; diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index 7aea195ddb35..f39e2089bc4c 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -32,27 +32,9 @@ static struct ctl_table nfs_cb_sysctls[] = { { } }; -static struct ctl_table nfs_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs_cb_sysctl_dir, - }, - { } -}; - int nfs_register_sysctl(void) { - nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root); + nfs_callback_sysctl_table = register_sysctl("fs/nfs", nfs_cb_sysctls); if (nfs_callback_sysctl_table == NULL) return -ENOMEM; return 0; diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c index a030d00af90c..174fe536a1c0 100644 --- a/fs/ntfs/sysctl.c +++ b/fs/ntfs/sysctl.c @@ -31,16 +31,6 @@ static struct ctl_table ntfs_sysctls[] = { {} }; -/* Define the parent directory /proc/sys/fs. */ -static struct ctl_table sysctls_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = ntfs_sysctls - }, - {} -}; - /* Storage for the sysctls header. */ static struct ctl_table_header *sysctls_root_table; @@ -54,7 +44,7 @@ int ntfs_sysctl(int add) { if (add) { BUG_ON(sysctls_root_table); - sysctls_root_table = register_sysctl_table(sysctls_root); + sysctls_root_table = register_sysctl("fs", ntfs_sysctls); if (!sysctls_root_table) return -ENOMEM; } else { diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5851eb5bc726..7ad07435828f 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1283,11 +1283,43 @@ out: return err; } +/* Find the directory for the ctl_table. If one is not found create it. */ +static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path) +{ + const char *name, *nextname; + + for (name = path; name; name = nextname) { + int namelen; + nextname = strchr(name, '/'); + if (nextname) { + namelen = nextname - name; + nextname++; + } else { + namelen = strlen(name); + } + if (namelen == 0) + continue; + + /* + * namelen ensures if name is "foo/bar/yay" only foo is + * registered first. We traverse as if using mkdir -p and + * return a ctl_dir for the last directory entry. + */ + dir = get_subdir(dir, name, namelen); + if (IS_ERR(dir)) + break; + } + return dir; +} + /** * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure + * @table: the top-level table structure without any child. This table + * should not be free'd after registration. So it should not be + * used on stack. It can either be a global or dynamically allocated + * by the caller and free'd later after sysctl unregistration. * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. @@ -1308,9 +1340,12 @@ out: * proc_handler - the text handler routine (described below) * * extra1, extra2 - extra pointers usable by the proc handler routines + * XXX: we should eventually modify these to use long min / max [0] + * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org * * Leaf nodes in the sysctl tree will be represented by a single file - * under /proc; non-leaf nodes will be represented by directories. + * under /proc; non-leaf nodes (where child is not NULL) are not allowed, + * sysctl_check_table() verifies this. * * There must be a proc_handler routine for any terminal nodes. * Several default handlers are available to cover common cases - @@ -1331,7 +1366,6 @@ struct ctl_table_header *__register_sysctl_table( { struct ctl_table_root *root = set->dir.header.root; struct ctl_table_header *header; - const char *name, *nextname; struct ctl_dir *dir; struct ctl_table *entry; struct ctl_node *node; @@ -1352,28 +1386,13 @@ struct ctl_table_header *__register_sysctl_table( spin_lock(&sysctl_lock); dir = &set->dir; - /* Reference moved down the diretory tree get_subdir */ + /* Reference moved down the directory tree get_subdir */ dir->header.nreg++; spin_unlock(&sysctl_lock); - /* Find the directory for the ctl_table */ - for (name = path; name; name = nextname) { - int namelen; - nextname = strchr(name, '/'); - if (nextname) { - namelen = nextname - name; - nextname++; - } else { - namelen = strlen(name); - } - if (namelen == 0) - continue; - - dir = get_subdir(dir, name, namelen); - if (IS_ERR(dir)) - goto fail; - } - + dir = sysctl_mkdir_p(dir, path); + if (IS_ERR(dir)) + goto fail; spin_lock(&sysctl_lock); if (insert_header(dir, header)) goto fail_put_dir_locked; @@ -1394,8 +1413,15 @@ fail: /** * register_sysctl - register a sysctl table - * @path: The path to the directory the sysctl table is in. - * @table: the table structure + * @path: The path to the directory the sysctl table is in. If the path + * doesn't exist we will create it for you. + * @table: the table structure. The calller must ensure the life of the @table + * will be kept during the lifetime use of the syctl. It must not be freed + * until unregister_sysctl_table() is called with the given returned table + * with this registration. If your code is non modular then you don't need + * to call unregister_sysctl_table() and can instead use something like + * register_sysctl_init() which does not care for the result of the syctl + * registration. * * Register a sysctl table. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. @@ -1411,8 +1437,11 @@ EXPORT_SYMBOL(register_sysctl); /** * __register_sysctl_init() - register sysctl table to path - * @path: path name for sysctl base - * @table: This is the sysctl table that needs to be registered to the path + * @path: path name for sysctl base. If that path doesn't exist we will create + * it for you. + * @table: This is the sysctl table that needs to be registered to the path. + * The caller must ensure the life of the @table will be kept during the + * lifetime use of the sysctl. * @table_name: The name of sysctl table, only used for log printing when * registration fails * @@ -1424,10 +1453,7 @@ EXPORT_SYMBOL(register_sysctl); * register_sysctl() failing on init are extremely low, and so for both reasons * this function does not return any error as it is used by initialization code. * - * Context: Can only be called after your respective sysctl base path has been - * registered. So for instance, most base directories are registered early on - * init before init levels are processed through proc_sys_init() and - * sysctl_init_bases(). + * Context: if your base directory does not exist it will be created for you. */ void __init __register_sysctl_init(const char *path, struct ctl_table *table, const char *table_name) @@ -1557,6 +1583,7 @@ out: * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. + * We are slowly deprecating this call so avoid its use. * * See __register_sysctl_table for more details. */ @@ -1628,6 +1655,7 @@ err_register_leaves: * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. + * We are slowly deprecating this caller so avoid future uses of it. * * See __register_sysctl_paths for more details. */ diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index aa178304bc03..55f139afa327 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -7,10 +7,9 @@ #include #include #include -#include #include "internal.h" -static DEFINE_RT_MUTEX(pmsg_lock); +static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -29,9 +28,9 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (!access_ok(buf, count)) return -EFAULT; - rt_mutex_lock(&pmsg_lock); + mutex_lock(&pmsg_lock); ret = psinfo->write_user(&record, buf); - rt_mutex_unlock(&pmsg_lock); + mutex_unlock(&pmsg_lock); return ret ? ret : count; } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 40f9e1a2ebdd..28e942feacc8 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -32,7 +32,22 @@ #include #include -int sysctl_unprivileged_userfaultfd __read_mostly; +static int sysctl_unprivileged_userfaultfd __read_mostly; + +#ifdef CONFIG_SYSCTL +static struct ctl_table vm_userfaultfd_table[] = { + { + .procname = "unprivileged_userfaultfd", + .data = &sysctl_unprivileged_userfaultfd, + .maxlen = sizeof(sysctl_unprivileged_userfaultfd), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; +#endif static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; @@ -2180,6 +2195,9 @@ static int __init userfaultfd_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); +#ifdef CONFIG_SYSCTL + register_sysctl_init("vm", vm_userfaultfd_table); +#endif return 0; } __initcall(userfaultfd_init); diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index 546a6cd96729..fade33735393 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -210,28 +210,10 @@ static struct ctl_table xfs_table[] = { {} }; -static struct ctl_table xfs_dir_table[] = { - { - .procname = "xfs", - .mode = 0555, - .child = xfs_table - }, - {} -}; - -static struct ctl_table xfs_root_table[] = { - { - .procname = "fs", - .mode = 0555, - .child = xfs_dir_table - }, - {} -}; - int xfs_sysctl_register(void) { - xfs_table_header = register_sysctl_table(xfs_root_table); + xfs_table_header = register_sysctl("fs/xfs", xfs_table); if (!xfs_table_header) return -ENOMEM; return 0; diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index b870983596b9..f4e4cc4f965f 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -146,6 +146,7 @@ union hv_reference_tsc_msr { /* Declare the various hypercall operations. */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 +#define HVCALL_ENABLE_VP_VTL 0x000f #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 #define HVCALL_SEND_IPI 0x000b #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 @@ -165,9 +166,13 @@ union hv_reference_tsc_msr { #define HVCALL_MAP_DEVICE_INTERRUPT 0x007c #define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d #define HVCALL_RETARGET_INTERRUPT 0x007e +#define HVCALL_START_VP 0x0099 +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db +#define HVCALL_MMIO_READ 0x0106 +#define HVCALL_MMIO_WRITE 0x0107 /* Extended hypercalls */ #define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 @@ -218,6 +223,7 @@ enum HV_GENERIC_SET_FORMAT { #define HV_STATUS_INVALID_PORT_ID 17 #define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 +#define HV_STATUS_VTL_ALREADY_ENABLED 134 /* * The Hyper-V TimeRefCount register and the TSC @@ -796,4 +802,24 @@ struct hv_memory_hint { union hv_gpa_page_range ranges[]; } __packed; +/* Data structures for HVCALL_MMIO_READ and HVCALL_MMIO_WRITE */ +#define HV_HYPERCALL_MMIO_MAX_DATA_LENGTH 64 + +struct hv_mmio_read_input { + u64 gpa; + u32 size; + u32 reserved; +} __packed; + +struct hv_mmio_read_output { + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + +struct hv_mmio_write_input { + u64 gpa; + u32 size; + u32 reserved; + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + #endif diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 90d7f68ed39d..402a8c1c202d 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -210,10 +210,9 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) static inline int __cpumask_to_vpset(struct hv_vpset *vpset, const struct cpumask *cpus, - bool exclude_self) + bool (*func)(int cpu)) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; - int this_cpu = smp_processor_id(); int max_vcpu_bank = hv_max_vp_index / HV_VCPUS_PER_SPARSE_BANK; /* vpset.valid_bank_mask can represent up to HV_MAX_SPARSE_VCPU_BANKS banks */ @@ -232,7 +231,7 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { - if (exclude_self && cpu == this_cpu) + if (func && func(cpu)) continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) @@ -248,17 +247,24 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +/* + * Convert a Linux cpumask into a Hyper-V VPset. In the _skip variant, + * 'func' is called for each CPU present in cpumask. If 'func' returns + * true, that CPU is skipped -- i.e., that CPU from cpumask is *not* + * added to the Hyper-V VPset. If 'func' is NULL, no CPUs are + * skipped. + */ static inline int cpumask_to_vpset(struct hv_vpset *vpset, const struct cpumask *cpus) { - return __cpumask_to_vpset(vpset, cpus, false); + return __cpumask_to_vpset(vpset, cpus, NULL); } -static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int cpumask_to_vpset_skip(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool (*func)(int cpu)) { - WARN_ON_ONCE(preemptible()); - return __cpumask_to_vpset(vpset, cpus, true); + return __cpumask_to_vpset(vpset, cpus, func); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); @@ -271,8 +277,6 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); void hv_setup_dma_ops(struct device *dev, bool coherent); -void *hv_map_memory(void *addr, unsigned long size); -void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ static inline bool hv_is_hyperv_initialized(void) { return false; } static inline bool hv_is_hibernation_supported(void) { return false; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 96bd672dc336..7b71dd74baeb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1077,6 +1077,11 @@ static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) return 0; } +static inline bool acpi_sleep_state_supported(u8 sleep_state) +{ + return false; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 52a9ff65faee..a6e512cfb670 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern unsigned int sysctl_compaction_proactiveness; -extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); -extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, - int write, void *buffer, size_t *length, loff_t *ppos); -extern int sysctl_extfrag_threshold; -extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..4056b05d81ed 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); - int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..98da268b834a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3442,8 +3442,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int sysctl_memory_failure_early_kill; -extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..2ef25e6fa1b4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -180,6 +180,4 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ -extern phys_addr_t swiotlb_unencrypted_base; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..fff49fec0258 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,8 +36,6 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int sysctl_unprivileged_userfaultfd; - extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 43f59ef10cc9..db1b0eaef4eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -10,13 +10,19 @@ #include /** - * struct vdpa_calllback - vDPA callback definition. + * struct vdpa_callback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function + * @trigger: the eventfd for the callback (Optional). + * When it is set, the vDPA driver must guarantee that + * signaling it is functional equivalent to triggering + * the callback. Then vDPA parent can signal it directly + * instead of triggering the callback. */ struct vdpa_callback { irqreturn_t (*callback)(void *data); void *private; + struct eventfd_ctx *trigger; }; /** @@ -114,7 +120,7 @@ struct vdpa_dev_set_config { }; /** - * Corresponding file area for device memory mapping + * struct vdpa_map_file - file area for device memory mapping * @file: vma->vm_file for the mapping * @offset: mapping offset in the vm_file */ @@ -143,6 +149,14 @@ struct vdpa_map_file { * @kick_vq: Kick the virtqueue * @vdev: vdpa device * @idx: virtqueue index + * @kick_vq_with_data: Kick the virtqueue and supply extra data + * (only if VIRTIO_F_NOTIFICATION_DATA is negotiated) + * @vdev: vdpa device + * @data for split virtqueue: + * 16 bits vqn and 16 bits next available index. + * @data for packed virtqueue: + * 16 bits vqn, 15 least significant bits of + * next available index and 1 bit next_wrap. * @set_vq_cb: Set the interrupt callback function for * a virtqueue * @vdev: vdpa device @@ -165,10 +179,16 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) + * @get_vendor_vq_stats: Get the vendor statistics of a device. + * @vdev: vdpa device + * @idx: virtqueue index + * @msg: socket buffer holding stats message + * @extack: extack for reporting error messages + * Returns integer: success (0) or error (< 0) * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index - * Returns the notifcation area + * Returns the notification area * @get_vq_irq: Get the irq number of a virtqueue (optional, * but must implemented if require vq irq offloading) * @vdev: vdpa device @@ -250,6 +270,15 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_vq_affinity: Set the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * @cpu_mask: the affinity mask + * Returns integer: success (0) or error (< 0) + * @get_vq_affinity: Get the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the affinity mask * @set_group_asid: Set address space identifier for a * virtqueue group (optional) * @vdev: vdpa device @@ -290,6 +319,14 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * Returns pointer to structure device or error (NULL) + * @bind_mm: Bind the device to a specific address space + * so the vDPA framework can use VA when this + * callback is implemented. (optional) + * @vdev: vdpa device + * @mm: address space to bind + * @unbind_mm: Unbind the device from the address space + * bound using the bind_mm callback. (optional) + * @vdev: vdpa device * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -300,6 +337,7 @@ struct vdpa_config_ops { u64 device_area); void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num); void (*kick_vq)(struct vdpa_device *vdev, u16 idx); + void (*kick_vq_with_data)(struct vdpa_device *vdev, u32 data); void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); @@ -340,6 +378,10 @@ struct vdpa_config_ops { const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); + int (*set_vq_affinity)(struct vdpa_device *vdev, u16 idx, + const struct cpumask *cpu_mask); + const struct cpumask *(*get_vq_affinity)(struct vdpa_device *vdev, + u16 idx); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, unsigned int asid, @@ -351,6 +393,8 @@ struct vdpa_config_ops { int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); + int (*bind_mm)(struct vdpa_device *vdev, struct mm_struct *mm); + void (*unbind_mm)(struct vdpa_device *vdev); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -506,6 +550,8 @@ struct vdpa_mgmtdev_ops { * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that * management device support during dev_add callback * @list: list entry + * @supported_features: features supported by device + * @max_supported_vqs: maximum number of virtqueues supported by device */ struct vdpa_mgmt_dev { struct device *device; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 2b472514c49b..b93238db94e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,8 +34,8 @@ struct virtqueue { unsigned int index; unsigned int num_free; unsigned int num_max; - void *priv; bool reset; + void *priv; }; int virtqueue_add_outbuf(struct virtqueue *vq, @@ -84,14 +84,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *vq); void *virtqueue_detach_unused_buf(struct virtqueue *vq); -unsigned int virtqueue_get_vring_size(struct virtqueue *vq); +unsigned int virtqueue_get_vring_size(const struct virtqueue *vq); -bool virtqueue_is_broken(struct virtqueue *vq); +bool virtqueue_is_broken(const struct virtqueue *vq); -const struct vring *virtqueue_get_vring(struct virtqueue *vq); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(const struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); @@ -147,7 +147,7 @@ int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); -size_t virtio_max_dma_size(struct virtio_device *vdev); +size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ list_for_each_entry(vq, &vdev->vqs, list) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b95b69ef694..9b33df741b63 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -58,6 +58,7 @@ do { \ struct virtio_device; struct virtqueue; +struct device; /* * Creates a virtqueue and allocates the descriptor ring. If @@ -117,4 +118,6 @@ void vring_del_virtqueue(struct virtqueue *vq); void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); + +u32 vring_notification_data(struct virtqueue *_vq); #endif /* _LINUX_VIRTIO_RING_H */ diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 1991a02c6431..c3a8117dabe8 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -54,6 +57,9 @@ struct vringh { void (*notify)(struct vringh *); }; +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); + /** * struct vringh_config_ops - ops for creating a host vring from a virtio driver * @find_vrhs: find the host vrings and instantiate them @@ -65,8 +71,6 @@ struct vringh { * Returns 0 on success or error status * @del_vrhs: free the host vrings found by find_vrhs(). */ -struct virtio_device; -typedef void vrh_callback_t(struct virtio_device *, struct vringh *); struct vringh_config_ops { int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, struct vringh *vrhs[], vrh_callback_t *callbacks[]); @@ -81,6 +85,12 @@ struct vringh_range { /** * struct vringh_iov - iovec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles iovec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -93,6 +103,12 @@ struct vringh_iov { /** * struct vringh_kiov - kvec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -284,6 +300,12 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used); +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 3c05162bc988..2c712c654165 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -99,6 +99,12 @@ */ #define VIRTIO_F_SR_IOV 37 +/* + * This feature indicates that the driver passes extra data (besides + * identifying the virtqueue) in its device notifications. + */ +#define VIRTIO_F_NOTIFICATION_DATA 38 + /* * This feature indicates that the driver can reset a queue individually. */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index dac42a2ad588..0fb16bdbbcae 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -73,8 +73,6 @@ static bool swiotlb_force_disable; struct io_tlb_mem io_tlb_default_mem; -phys_addr_t swiotlb_unencrypted_base; - static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; static unsigned long default_nareas; @@ -201,34 +199,6 @@ static inline unsigned long nr_slots(u64 val) return DIV_ROUND_UP(val, IO_TLB_SIZE); } -/* - * Remap swioltb memory in the unencrypted physical address space - * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP - * Isolation VMs). - */ -#ifdef CONFIG_HAS_IOMEM -static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) -{ - void *vaddr = NULL; - - if (swiotlb_unencrypted_base) { - phys_addr_t paddr = mem->start + swiotlb_unencrypted_base; - - vaddr = memremap(paddr, bytes, MEMREMAP_WB); - if (!vaddr) - pr_err("Failed to map the unencrypted memory %pa size %lx.\n", - &paddr, bytes); - } - - return vaddr; -} -#else -static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) -{ - return NULL; -} -#endif - /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to @@ -238,18 +208,12 @@ static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) void __init swiotlb_update_mem_attributes(void) { struct io_tlb_mem *mem = &io_tlb_default_mem; - void *vaddr; unsigned long bytes; if (!mem->nslabs || mem->late_alloc) return; - vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); - set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - - mem->vaddr = swiotlb_mem_remap(mem, bytes); - if (!mem->vaddr) - mem->vaddr = vaddr; + set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT); } static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, @@ -280,13 +244,6 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->slots[i].alloc_size = 0; } - /* - * If swiotlb_unencrypted_base is set, the bounce buffer memory will - * be remapped and cleared in swiotlb_update_mem_attributes. - */ - if (swiotlb_unencrypted_base) - return; - memset(vaddr, 0, bytes); mem->vaddr = vaddr; return; diff --git a/kernel/kheaders.c b/kernel/kheaders.c index 8f69772af77b..42163c9e94e5 100644 --- a/kernel/kheaders.c +++ b/kernel/kheaders.c @@ -26,15 +26,15 @@ asm ( " .popsection \n" ); -extern char kernel_headers_data; -extern char kernel_headers_data_end; +extern char kernel_headers_data[]; +extern char kernel_headers_data_end[]; static ssize_t ikheaders_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { - memcpy(buf, &kernel_headers_data + off, len); + memcpy(buf, &kernel_headers_data[off], len); return len; } @@ -48,8 +48,8 @@ static struct bin_attribute kheaders_attr __ro_after_init = { static int __init ikheaders_init(void) { - kheaders_attr.size = (&kernel_headers_data_end - - &kernel_headers_data); + kheaders_attr.size = (kernel_headers_data_end - + kernel_headers_data); return sysfs_create_bin_file(kernel_kobj, &kheaders_attr); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index cebf26445f9e..d3e584065c7f 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2368,12 +2368,6 @@ static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, return ret; } -static struct ctl_path seccomp_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "seccomp", }, - { } -}; - static struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", @@ -2392,14 +2386,7 @@ static struct ctl_table seccomp_sysctl_table[] = { static int __init seccomp_sysctl_init(void) { - struct ctl_table_header *hdr; - - hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); - if (!hdr) - pr_warn("sysctl registration failed\n"); - else - kmemleak_not_leak(hdr); - + register_sysctl_init("kernel/seccomp", seccomp_sysctl_table); return 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1c240d2c99bc..bfe53e835524 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include @@ -746,27 +745,6 @@ int proc_dointvec(struct ctl_table *table, int write, void *buffer, return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); } -#ifdef CONFIG_COMPACTION -static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, - int write, void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret, old; - - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - old = *(int *)table->data; - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret) - return ret; - if (old != *(int *)table->data) - pr_warn_once("sysctl attribute %s changed by %s[%d]\n", - table->procname, current->comm, - task_pid_nr(current)); - return ret; -} -#endif - /** * proc_douintvec - read a vector of unsigned integers * @table: the sysctl table @@ -2140,38 +2118,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -#endif -#ifdef CONFIG_HUGETLB_PAGE - { - .procname = "nr_hugepages", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_sysctl_handler, - }, -#ifdef CONFIG_NUMA - { - .procname = "nr_hugepages_mempolicy", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = &hugetlb_mempolicy_sysctl_handler, - }, -#endif - { - .procname = "hugetlb_shm_group", - .data = &sysctl_hugetlb_shm_group, - .maxlen = sizeof(gid_t), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nr_overcommit_hugepages", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_overcommit_handler, - }, #endif { .procname = "lowmem_reserve_ratio", @@ -2189,43 +2135,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_FOUR, }, -#ifdef CONFIG_COMPACTION - { - .procname = "compact_memory", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0200, - .proc_handler = sysctl_compaction_handler, - }, - { - .procname = "compaction_proactiveness", - .data = &sysctl_compaction_proactiveness, - .maxlen = sizeof(sysctl_compaction_proactiveness), - .mode = 0644, - .proc_handler = compaction_proactiveness_sysctl_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "extfrag_threshold", - .data = &sysctl_extfrag_threshold, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_THOUSAND, - }, - { - .procname = "compact_unevictable_allowed", - .data = &sysctl_compact_unevictable_allowed, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_warn_RT_change, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - -#endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", .data = &min_free_kbytes, @@ -2382,26 +2291,6 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec, .extra1 = SYSCTL_ZERO, }, -#endif -#ifdef CONFIG_MEMORY_FAILURE - { - .procname = "memory_failure_early_kill", - .data = &sysctl_memory_failure_early_kill, - .maxlen = sizeof(sysctl_memory_failure_early_kill), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "memory_failure_recovery", - .data = &sysctl_memory_failure_recovery, - .maxlen = sizeof(sysctl_memory_failure_recovery), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { .procname = "user_reserve_kbytes", @@ -2438,17 +2327,6 @@ static struct ctl_table vm_table[] = { .extra1 = (void *)&mmap_rnd_compat_bits_min, .extra2 = (void *)&mmap_rnd_compat_bits_max, }, -#endif -#ifdef CONFIG_USERFAULTFD - { - .procname = "unprivileged_userfaultfd", - .data = &sysctl_unprivileged_userfaultfd, - .maxlen = sizeof(sysctl_unprivileged_userfaultfd), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { } }; diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index f50398cb790d..019e3a1566cf 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -123,15 +123,6 @@ static struct ctl_table uts_kern_table[] = { {} }; -static struct ctl_table uts_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = uts_kern_table, - }, - {} -}; - #ifdef CONFIG_PROC_SYSCTL /* * Notify userspace about a change in a certain entry of uts_kern_table, @@ -147,7 +138,7 @@ void uts_proc_notify(enum uts_proc proc) static int __init utsname_sysctl_init(void) { - register_sysctl_table(uts_root_table); + register_sysctl("kernel", uts_kern_table); return 0; } diff --git a/lib/group_cpus.c b/lib/group_cpus.c index 9c837a35fef7..aa3f6815bb12 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -426,3 +426,4 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) return masks; } #endif /* CONFIG_SMP */ +EXPORT_SYMBOL_GPL(group_cpus_evenly); diff --git a/mm/compaction.c b/mm/compaction.c index 5a9501e0ae01..9ff71239b1fc 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1716,7 +1716,14 @@ typedef enum { * Allow userspace to control policy on scanning the unevictable LRU for * compactable pages. */ -int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; +static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; +/* + * Tunable for proactive compaction. It determines how + * aggressively the kernel should compact memory in the + * background. It takes values in the range [0, 100]. + */ +static unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +static int sysctl_extfrag_threshold = 500; static inline void update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) @@ -2572,8 +2579,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, return ret; } -int sysctl_extfrag_threshold = 500; - /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation @@ -2730,14 +2735,7 @@ static void compact_nodes(void) compact_node(nid); } -/* - * Tunable for proactive compaction. It determines how - * aggressively the kernel should compact memory in the - * background. It takes values in the range [0, 100]. - */ -unsigned int __read_mostly sysctl_compaction_proactiveness = 20; - -int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, +static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc, nid; @@ -2767,7 +2765,7 @@ int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory */ -int sysctl_compaction_handler(struct ctl_table *table, int write, +static int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { if (write) @@ -3063,6 +3061,63 @@ static int kcompactd_cpu_online(unsigned int cpu) return 0; } +static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, + int write, void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, old; + + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + old = *(int *)table->data; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret) + return ret; + if (old != *(int *)table->data) + pr_warn_once("sysctl attribute %s changed by %s[%d]\n", + table->procname, current->comm, + task_pid_nr(current)); + return ret; +} + +static struct ctl_table vm_compaction[] = { + { + .procname = "compact_memory", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, + { + .procname = "compaction_proactiveness", + .data = &sysctl_compaction_proactiveness, + .maxlen = sizeof(sysctl_compaction_proactiveness), + .mode = 0644, + .proc_handler = compaction_proactiveness_sysctl_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, + }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_THOUSAND, + }, + { + .procname = "compact_unevictable_allowed", + .data = &sysctl_compact_unevictable_allowed, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_warn_RT_change, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + static int __init kcompactd_init(void) { int nid; @@ -3078,6 +3133,7 @@ static int __init kcompactd_init(void) for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); + register_sysctl_init("vm", vm_compaction); return 0; } subsys_initcall(kcompactd_init) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 245038a9fe4e..a93e070ab175 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4202,6 +4202,12 @@ static void __init hugetlb_sysfs_init(void) hugetlb_register_all_nodes(); } +#ifdef CONFIG_SYSCTL +static void hugetlb_sysctl_init(void); +#else +static inline void hugetlb_sysctl_init(void) { } +#endif + static int __init hugetlb_init(void) { int i; @@ -4257,6 +4263,7 @@ static int __init hugetlb_init(void) hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); + hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); @@ -4588,7 +4595,7 @@ out: return ret; } -int hugetlb_sysctl_handler(struct ctl_table *table, int write, +static int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { @@ -4597,7 +4604,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, } #ifdef CONFIG_NUMA -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, +static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, @@ -4605,7 +4612,7 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, } #endif /* CONFIG_NUMA */ -int hugetlb_overcommit_handler(struct ctl_table *table, int write, +static int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -4634,6 +4641,44 @@ out: return ret; } +static struct ctl_table hugetlb_table[] = { + { + .procname = "nr_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_sysctl_handler, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + }, +#endif + { + .procname = "hugetlb_shm_group", + .data = &sysctl_hugetlb_shm_group, + .maxlen = sizeof(gid_t), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "nr_overcommit_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_overcommit_handler, + }, + { } +}; + +static void hugetlb_sysctl_init(void) +{ + register_sysctl_init("vm", hugetlb_table); +} #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fae9baf3be16..10e60b6b2447 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -62,13 +62,14 @@ #include #include #include +#include #include "swap.h" #include "internal.h" #include "ras/ras_event.h" -int sysctl_memory_failure_early_kill __read_mostly = 0; +static int sysctl_memory_failure_early_kill __read_mostly; -int sysctl_memory_failure_recovery __read_mostly = 1; +static int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); @@ -122,6 +123,37 @@ const struct attribute_group memory_failure_attr_group = { .attrs = memory_failure_attr, }; +#ifdef CONFIG_SYSCTL +static struct ctl_table memory_failure_table[] = { + { + .procname = "memory_failure_early_kill", + .data = &sysctl_memory_failure_early_kill, + .maxlen = sizeof(sysctl_memory_failure_early_kill), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "memory_failure_recovery", + .data = &sysctl_memory_failure_recovery, + .maxlen = sizeof(sysctl_memory_failure_recovery), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static int __init memory_failure_sysctl_init(void) +{ + register_sysctl_init("vm", memory_failure_table); + return 0; +} +late_initcall(memory_failure_sysctl_init); +#endif /* CONFIG_SYSCTL */ + /* * Return values: * 1: the page is dissolved (if needed) and taken off from buddy, diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl index d48dfed6d3db..84f5fb7f1cec 100755 --- a/scripts/checkstack.pl +++ b/scripts/checkstack.pl @@ -10,7 +10,6 @@ # Mips port by Juan Quintela # IA64 port via Andreas Dilger # Arm port by Holger Schurig -# sh64 port by Paul Mundt # Random bits by Matt Mackall # M68k port by Geert Uytterhoeven and Andreas Schwab # AArch64, PARISC ports by Kyle McMartin @@ -100,12 +99,6 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack); # 100092: e3 f0 ff c8 ff 71 lay %r15,-56(%r15) $re = qr/.*(?:lay|ag?hi).*\%r15,-(([0-9]{2}|[3-9])[0-9]{2}) (?:\(\%r15\))?$/ox; - } elsif ($arch =~ /^sh64$/) { - #XXX: we only check for the immediate case presently, - # though we will want to check for the movi/sub - # pair for larger users. -- PFM. - #a00048e0: d4fc40f0 addi.l r15,-240,r15 - $re = qr/.*addi\.l.*r15,-(([0-9]{2}|[3-9])[0-9]{2}),r15/o; } elsif ($arch eq 'sparc' || $arch eq 'sparc64') { # f0019d10: 9d e3 bf 90 save %sp, -112, %sp $re = qr/.*save.*%sp, -(([0-9]{2}|[3-9])[0-9]{2}), %sp/o; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index cebba4824e60..f431251ffb91 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1764,11 +1764,6 @@ static int apparmor_dointvec(struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } -static struct ctl_path apparmor_sysctl_path[] = { - { .procname = "kernel", }, - { } -}; - static struct ctl_table apparmor_sysctl_table[] = { { .procname = "unprivileged_userns_apparmor_policy", @@ -1790,8 +1785,7 @@ static struct ctl_table apparmor_sysctl_table[] = { static int __init apparmor_init_sysctl(void) { - return register_sysctl_paths(apparmor_sysctl_path, - apparmor_sysctl_table) ? 0 : -ENOMEM; + return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM; } #else static inline int apparmor_init_sysctl(void) diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index b9d773f11232..ebae964f7cc9 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -52,12 +52,6 @@ static bool deny_reading_verity_digests; #endif #ifdef CONFIG_SYSCTL -static struct ctl_path loadpin_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "loadpin", }, - { } -}; - static struct ctl_table loadpin_sysctl_table[] = { { .procname = "enforce", @@ -262,7 +256,7 @@ static int __init loadpin_init(void) enforce ? "" : "not "); parse_exclude(); #ifdef CONFIG_SYSCTL - if (!register_sysctl_paths(loadpin_sysctl_path, loadpin_sysctl_table)) + if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table)) pr_notice("sysctl registration failed!\n"); #endif security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin"); diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 478be269571a..2503cf153d4a 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -447,12 +447,6 @@ static int yama_dointvec_minmax(struct ctl_table *table, int write, static int max_scope = YAMA_SCOPE_NO_ATTACH; -static struct ctl_path yama_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "yama", }, - { } -}; - static struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", @@ -467,7 +461,7 @@ static struct ctl_table yama_sysctl_table[] = { }; static void __init yama_init_sysctl(void) { - if (!register_sysctl_paths(yama_sysctl_path, yama_sysctl_table)) + if (!register_sysctl("kernel/yama", yama_sysctl_table)) panic("Yama: sysctl registration failed.\n"); } #else diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h index 051fdeaf2670..8519386acd23 100644 --- a/tools/include/linux/types.h +++ b/tools/include/linux/types.h @@ -49,7 +49,12 @@ typedef __s8 s8; #endif #define __force +/* This is defined in linux/compiler_types.h and is left for backward + * compatibility. + */ +#ifndef __user #define __user +#endif #define __must_check #define __cold diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 59dd875fd5e4..cfe63dfab03a 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -51,9 +51,7 @@ const char *const s390_triplets[] = { const char *const sh_triplets[] = { "sh-unknown-linux-gnu-", - "sh64-unknown-linux-gnu-", "sh-linux-gnu-", - "sh64-linux-gnu-", NULL }; diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 1c72d07cb9fe..f6a50f06dfc4 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -29,11 +29,6 @@ ifeq ($(ARCH),sparc64) SRCARCH := sparc endif -# Additional ARCH settings for sh -ifeq ($(ARCH),sh64) - SRCARCH := sh -endif - # Additional ARCH settings for loongarch ifeq ($(ARCH),loongarch32) SRCARCH := loongarch diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index c31d952cff68..fc35050b5542 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -90,7 +90,7 @@ endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) +ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..a9d6d52596f2 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -132,7 +132,7 @@ else fi # filter 64bit architectures -ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" +ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sparc64 x86_64" if [ -z "$ARCH" ]; then ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h index 2c51bccb97bb..1f3a15b954b9 100644 --- a/tools/virtio/linux/compiler.h +++ b/tools/virtio/linux/compiler.h @@ -2,6 +2,8 @@ #ifndef LINUX_COMPILER_H #define LINUX_COMPILER_H +#include "../../../include/linux/compiler_types.h" + #define WRITE_ONCE(var, val) \ (*((volatile typeof(val) *)(&(var))) = (val)) diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 8b877167933d..6702008f7f5c 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include #include +#include "../../../include/linux/container_of.h" #include #include #include @@ -107,10 +108,6 @@ static inline void free_page(unsigned long addr) free((void *)addr); } -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) - # ifndef likely # define likely(x) (__builtin_expect(!!(x), 1)) # endif diff --git a/tools/virtio/linux/uaccess.h b/tools/virtio/linux/uaccess.h index 991dfb263998..f13828e0c409 100644 --- a/tools/virtio/linux/uaccess.h +++ b/tools/virtio/linux/uaccess.h @@ -6,15 +6,10 @@ extern void *__user_addr_min, *__user_addr_max; -static inline void __chk_user_ptr(const volatile void *p, size_t size) -{ - assert(p >= __user_addr_min && p + size <= __user_addr_max); -} - #define put_user(x, ptr) \ ({ \ typeof(ptr) __pu_ptr = (ptr); \ - __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \ + __chk_user_ptr(__pu_ptr); \ WRITE_ONCE(*(__pu_ptr), x); \ 0; \ }) @@ -22,7 +17,7 @@ static inline void __chk_user_ptr(const volatile void *p, size_t size) #define get_user(x, ptr) \ ({ \ typeof(ptr) __pu_ptr = (ptr); \ - __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \ + __chk_user_ptr(__pu_ptr); \ x = READ_ONCE(*(__pu_ptr)); \ 0; \ }) @@ -37,7 +32,6 @@ static void volatile_memcpy(volatile char *to, const volatile char *from, static inline int copy_from_user(void *to, const void __user volatile *from, unsigned long n) { - __chk_user_ptr(from, n); volatile_memcpy(to, from, n); return 0; } @@ -45,7 +39,6 @@ static inline int copy_from_user(void *to, const void __user volatile *from, static inline int copy_to_user(void __user volatile *to, const void *from, unsigned long n) { - __chk_user_ptr(to, n); volatile_memcpy(to, from, n); return 0; } diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 120062f94590..028f54e6854a 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -134,7 +134,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); - dev->control = open("/dev/vhost-test", O_RDWR); + dev->control = open("/dev/vhost-test", O_RDWR); assert(dev->control >= 0); r = ioctl(dev->control, VHOST_SET_OWNER, NULL); assert(r >= 0); @@ -327,7 +327,7 @@ const struct option longopts[] = { } }; -static void help(void) +static void help(int status) { fprintf(stderr, "Usage: virtio_test [--help]" " [--no-indirect]" @@ -337,6 +337,8 @@ static void help(void) " [--batch=random/N]" " [--reset=N]" "\n"); + + exit(status); } int main(int argc, char **argv) @@ -354,14 +356,12 @@ int main(int argc, char **argv) case -1: goto done; case '?': - help(); - exit(2); + help(2); case 'e': features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX); break; case 'h': - help(); - goto done; + help(0); case 'i': features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC); break;