diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index d515d58962b9..2a3904030dea 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -14,6 +14,12 @@ add_random (RW) This file allows to turn off the disk entropy contribution. Default value of this file is '1'(on). +dax (RO) +-------- +This file indicates whether the device supports Direct Access (DAX), +used by CPU-addressable storage to bypass the pagecache. It shows '1' +if true, '0' if not. + discard_granularity (RO) ----------------------- This shows the size of internal allocation of the device in bytes, if @@ -46,6 +52,12 @@ hw_sector_size (RO) ------------------- This is the hardware sector size of the device, in bytes. +io_poll (RW) +------------ +When read, this file shows the total number of block IO polls and how +many returned success. Writing '0' to this file will disable polling +for this device. Writing any non-zero value will enable this feature. + iostats (RW) ------------- This file is used to control (on/off) the iostats accounting of the @@ -151,5 +163,11 @@ device state. This means that it might not be safe to toggle the setting from "write back" to "write through", since that will also eliminate cache flushes issued by the kernel. +write_same_max_bytes (RO) +------------------------- +This is the number of bytes the device can write in a single write-same +command. A value of '0' means write-same is not supported by this +device. + Jens Axboe , February 2009 diff --git a/MAINTAINERS b/MAINTAINERS index 20bb1d00098c..a306795a7450 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1004,6 +1004,7 @@ N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg M: Antoine Tenart +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-alpine/ F: arch/arm/boot/dts/alpine* diff --git a/Makefile b/Makefile index 8c504f324154..5c18baad7218 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 56ea5c60b318..61f6ccc19cfa 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -260,12 +260,14 @@ machdirs := $(patsubst %,arch/arm/mach-%/,$(machine-y)) platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y))) ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y) +ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y) ifeq ($(KBUILD_SRC),) KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs)) else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs)) endif endif +endif export TEXT_OFFSET GZFLAGS MMUEXT diff --git a/arch/arm/boot/dts/arm-realview-pbx-a9.dts b/arch/arm/boot/dts/arm-realview-pbx-a9.dts index db808f92dd79..90d00b407f85 100644 --- a/arch/arm/boot/dts/arm-realview-pbx-a9.dts +++ b/arch/arm/boot/dts/arm-realview-pbx-a9.dts @@ -70,13 +70,12 @@ * associativity as these may be erroneously set * up by boot loader(s). */ - cache-size = <1048576>; // 1MB - cache-sets = <4096>; + cache-size = <131072>; // 128KB + cache-sets = <512>; cache-line-size = <32>; arm,parity-disable; - arm,tag-latency = <1>; - arm,data-latency = <1 1>; - arm,dirty-latency = <1>; + arm,tag-latency = <1 1 1>; + arm,data-latency = <1 1 1>; }; scu: scu@1f000000 { diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts index cf06e32ee108..4b34b54e09a1 100644 --- a/arch/arm/boot/dts/integratorap.dts +++ b/arch/arm/boot/dts/integratorap.dts @@ -42,7 +42,7 @@ }; syscon { - compatible = "arm,integrator-ap-syscon"; + compatible = "arm,integrator-ap-syscon", "syscon"; reg = <0x11000000 0x100>; interrupt-parent = <&pic>; /* These are the logical module IRQs */ diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts index d43f15b4f79a..79430fbfec3b 100644 --- a/arch/arm/boot/dts/integratorcp.dts +++ b/arch/arm/boot/dts/integratorcp.dts @@ -94,7 +94,7 @@ }; syscon { - compatible = "arm,integrator-cp-syscon"; + compatible = "arm,integrator-cp-syscon", "syscon"; reg = <0xcb000000 0x100>; }; diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi index 00cb314d5e4d..e23f46d15c80 100644 --- a/arch/arm/boot/dts/keystone.dtsi +++ b/arch/arm/boot/dts/keystone.dtsi @@ -70,14 +70,6 @@ cpu_on = <0x84000003>; }; - psci { - compatible = "arm,psci"; - method = "smc"; - cpu_suspend = <0x84000001>; - cpu_off = <0x84000002>; - cpu_on = <0x84000003>; - }; - soc { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts index e52b82449a79..6403e0de540e 100644 --- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts +++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts @@ -1382,7 +1382,7 @@ * Pin 41: BR_UART1_TXD * Pin 44: BR_UART1_RXD */ - serial@70006000 { + serial@0,70006000 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; @@ -1394,7 +1394,7 @@ * Pin 71: UART2_CTS_L * Pin 74: UART2_RTS_L */ - serial@70006040 { + serial@0,70006040 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig index b6e54ee9bdbd..ca39c04fec6b 100644 --- a/arch/arm/configs/aspeed_g4_defconfig +++ b/arch/arm/configs/aspeed_g4_defconfig @@ -58,7 +58,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 892605167357..4f366b0370e9 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -59,7 +59,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d94bb9093ead..75f130ef6504 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + int ret; if (!vgic_present) return -ENXIO; - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig index dc7c6edeab39..61284b9389cf 100644 --- a/arch/arm/mach-clps711x/Kconfig +++ b/arch/arm/mach-clps711x/Kconfig @@ -1,13 +1,13 @@ menuconfig ARCH_CLPS711X bool "Cirrus Logic EP721x/EP731x-based" depends on ARCH_MULTI_V4T - select ARCH_REQUIRE_GPIOLIB select AUTO_ZRELADDR select CLKSRC_OF select CLPS711X_TIMER select COMMON_CLK select CPU_ARM720T select GENERIC_CLOCKEVENTS + select GPIOLIB select MFD_SYSCON select OF_IRQ select USE_OF diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index e53c6cfcab51..6c6497e80a7b 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -1,5 +1,4 @@ -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-orion/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include AFLAGS_coherency_ll.o := -Wa,-march=armv7-a CFLAGS_pmsu.o := -march=armv7-a diff --git a/arch/arm/mach-oxnas/Kconfig b/arch/arm/mach-oxnas/Kconfig index 567496bd250a..29100beb2e7f 100644 --- a/arch/arm/mach-oxnas/Kconfig +++ b/arch/arm/mach-oxnas/Kconfig @@ -11,11 +11,13 @@ if ARCH_OXNAS config MACH_OX810SE bool "Support OX810SE Based Products" + select ARCH_HAS_RESET_CONTROLLER select COMMON_CLK_OXNAS select CPU_ARM926T select MFD_SYSCON select OXNAS_RPS_TIMER select PINCTRL_OXNAS + select RESET_CONTROLLER select RESET_OXNAS select VERSATILE_FPGA_IRQ help diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index dc109dc3a622..10bfdb169366 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -13,6 +13,7 @@ */ #include +#include /* symbol_get ; symbol_put */ #include #include #include diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 1080580b1343..2c150bfc0cd5 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -13,6 +13,7 @@ */ #include +#include /* symbol_get ; symbol_put */ #include #include #include diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile index dae8d86ef4cc..404882130956 100644 --- a/arch/arm/mach-realview/Makefile +++ b/arch/arm/mach-realview/Makefile @@ -1,8 +1,7 @@ # # Makefile for the linux kernel. # -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-versatile/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include obj-y := core.o obj-$(CONFIG_REALVIEW_DT) += realview-dt.o diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile index 72b9e9671507..fa7fb716e388 100644 --- a/arch/arm/mach-s5pv210/Makefile +++ b/arch/arm/mach-s5pv210/Makefile @@ -5,7 +5,7 @@ # # Licensed under GPLv2 -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include # Core diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index f3dba6f356e2..02e21bceb085 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -40,5 +40,8 @@ bool shmobile_smp_cpu_can_disable(unsigned int cpu) bool __init shmobile_smp_init_fallback_ops(void) { /* fallback on PSCI/smp_ops if no other DT based method is detected */ + if (!IS_ENABLED(CONFIG_SMP)) + return false; + return platform_can_secondary_boot() ? true : false; } diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index bb2616b16157..be5d824ebdba 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -8,7 +8,7 @@ config ARCH_SUNXI config ARCH_ALPINE bool "Annapurna Labs Alpine platform" - select ALPINE_MSI + select ALPINE_MSI if PCI help This enables support for the Annapurna Labs Alpine Soc family. @@ -66,7 +66,7 @@ config ARCH_LG1K config ARCH_HISI bool "Hisilicon SoC Family" select ARM_TIMER_SP804 - select HISILICON_IRQ_MBIGEN + select HISILICON_IRQ_MBIGEN if PCI help This enables support for Hisilicon ARMv8 SoC family diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 299f3ce969ab..c528dd52ba2d 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -12,6 +12,7 @@ /dts-v1/; #include "exynos7.dtsi" #include +#include / { model = "Samsung Exynos7 Espresso board based on EXYNOS7"; @@ -43,6 +44,8 @@ &rtc { status = "okay"; + clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; &watchdog { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0555b7caaf2c..eadf4855ad2d 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,4 +1,3 @@ -# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y @@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_HUGETLB=y -# CONFIG_UTS_NS is not set -# CONFIG_IPC_NS is not set -# CONFIG_NET_NS is not set +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y @@ -71,6 +74,7 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_SECCOMP=y CONFIG_XEN=y CONFIG_KEXEC=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -84,10 +88,37 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y +CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set +CONFIG_IPV6=m +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_MANGLE=m +CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_VLAN_8021Q_MVRP=y CONFIG_BPF_JIT=y CONFIG_CFG80211=m CONFIG_MAC80211=m @@ -103,6 +134,7 @@ CONFIG_MTD=y CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m CONFIG_VIRTIO_BLK=y CONFIG_SRAM=y # CONFIG_SCSI_PROC_FS is not set @@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m CONFIG_TUN=y +CONFIG_VETH=m CONFIG_VIRTIO_NET=y CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y @@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y CONFIG_PWM_SAMSUNG=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=y -CONFIG_CUSE=y +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 61b49150dfa3..1737aecfcc5e 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -22,7 +22,6 @@ #define __ARCH_WANT_KPROBES_INSN_SLOT #define MAX_INSN_SIZE 1 -#define MAX_STACK_SIZE 128 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -47,7 +46,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 96e4a2b64cc1..441420ca7d08 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -353,6 +353,8 @@ el1_sync: lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 b.eq el1_da + cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 + b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception @@ -364,6 +366,11 @@ el1_sync: cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 b.ge el1_dbg b el1_inv + +el1_ia: + /* + * Fall through to the Data abort case + */ el1_da: /* * Data abort handling diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 21ab5df9fa76..65d81f965e74 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -35,6 +35,7 @@ #include #include #include +#include #include /* @@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -393,6 +404,38 @@ int swsusp_arch_resume(void) void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *, void *, phys_addr_t, phys_addr_t); + /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. @@ -418,27 +461,6 @@ int swsusp_arch_resume(void) */ __flush_dcache_area(hibernate_exit, exit_size); - /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. @@ -453,12 +475,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bf9768588288..c6b0f40620d8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static inline unsigned long min_stack_size(unsigned long addr) -{ - unsigned long size; - - if (on_irq_stack(addr, raw_smp_processor_id())) - size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr; - else - size = (unsigned long)current_thread_info() + THREAD_START_SP - addr; - - return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack)); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { /* prepare insn slot */ @@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_ptr = kernel_stack_pointer(regs); kcb->jprobe_saved_regs = *regs; /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. + * Since we can't be sure where in the stack frame "stacked" + * pass-by-value arguments are stored we just don't try to + * duplicate any of the stack. Do not use jprobes on functions that + * use more than 64 bytes (after padding each to an 8 byte boundary) + * of arguments, or pass individual arguments larger than 16 bytes. */ - kasan_disable_current(); - memcpy(kcb->jprobes_stack, (void *)stack_ptr, - min_stack_size(stack_ptr)); - kasan_enable_current(); instruction_pointer_set(regs, (unsigned long) jp->entry); preempt_disable(); @@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - kasan_disable_current(); - memcpy((void *)stack_addr, kcb->jprobes_stack, - min_stack_size(stack_addr)); - kasan_enable_current(); preempt_enable_no_resched(); return 1; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 76a6d9263908..d93d43352504 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -661,9 +661,9 @@ void __init smp_init_cpus(void) acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, acpi_parse_gic_cpu_interface, 0); - if (cpu_count > NR_CPUS) - pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu_count, NR_CPUS); + if (cpu_count > nr_cpu_ids) + pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n", + cpu_count, nr_cpu_ids); if (!bootcpu_valid) { pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); @@ -677,7 +677,7 @@ void __init smp_init_cpus(void) * with entries in cpu_logical_map while initializing the cpus. * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 1; i < NR_CPUS; i++) { + for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) cpu_logical_map(i) = INVALID_HWID; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c8beaa0da7df..05d2bd776c69 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma, } #endif +static bool is_el1_instruction_abort(unsigned int esr) +{ + return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; +} + /* * The kernel tried to access some page that wasn't present. */ @@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, { /* * Are we prepared to handle this kernel fault? + * We are almost certainly not prepared to handle instruction faults. */ - if (fixup_exception(regs)) + if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; /* @@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr) unsigned int ec = ESR_ELx_EC(esr); unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; - return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) || + (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM); } static bool is_el0_instruction_abort(unsigned int esr) @@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + if (is_el1_instruction_abort(esr)) + die("Attempting to execute userspace memory", regs, esr); + if (!search_exception_tables(regs->pc)) die("Accessing user space memory outside uaccess.h routines", regs, esr); } diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index 2e221c5f0203..f86918aed9e1 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include + /* H8/300 internal I/O functions */ #define __raw_readb __raw_readb diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 2dcee3a88867..9202f82dfce6 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -213,7 +213,6 @@ static inline int frame_extra_sizes(int f) static inline void adjustformat(struct pt_regs *regs) { - ((struct switch_stack *)regs - 1)->a5 = current->mm->start_data; /* * set format byte to make stack appear modulo 4, which it will * be when doing the rte diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index 11fa51c89617..c0ec116b3993 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -390,7 +390,6 @@ void __init mem_init(void) free_all_bootmem(); mem_init_print_info(NULL); - show_mem(0); } void free_initmem(void) diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 6eb52b9c9818..e788515f766b 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, preempt_disable(); if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) - kvm_mips_handle_kseg0_tlb_fault(va, vcpu); + if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && + kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { + kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", + __func__, va, vcpu, read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; + } } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { int index; @@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, run, vcpu); preempt_enable(); goto dont_update_pc; - } else { - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + } + /* + * We fault an entry from the guest tlb to the + * shadow host TLB + */ + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; } } } else { @@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + } } } diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 57319ee57c4f..6cfdcf55572d 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -99,7 +99,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, } gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if (gfn >= kvm->arch.guest_pmap_npages) { + if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, gfn, badvaddr); kvm_mips_dump_host_tlbs(); @@ -138,35 +138,49 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; kvm_pfn_t pfn0, pfn1; + gfn_t gfn0, gfn1; + long tlb_lo[2]; int ret; - if ((tlb->tlb_hi & VPN2_MASK) == 0) { - pfn0 = 0; - pfn1 = 0; - } else { - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) - >> PAGE_SHIFT) < 0) - return -1; + tlb_lo[0] = tlb->tlb_lo[0]; + tlb_lo[1] = tlb->tlb_lo[1]; - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) - >> PAGE_SHIFT) < 0) - return -1; + /* + * The commpage address must not be mapped to anything else if the guest + * TLB contains entries nearby, or commpage accesses will break. + */ + if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & + VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; - pfn0 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT]; - pfn1 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT]; + gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; + gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; + if (gfn0 >= kvm->arch.guest_pmap_npages || + gfn1 >= kvm->arch.guest_pmap_npages) { + kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", + __func__, gfn0, gfn1, tlb->tlb_hi); + kvm_mips_dump_guest_tlbs(vcpu); + return -1; } + if (kvm_mips_map_page(kvm, gfn0) < 0) + return -1; + + if (kvm_mips_map_page(kvm, gfn1) < 0) + return -1; + + pfn0 = kvm->arch.guest_pmap[gfn0]; + pfn1 = kvm->arch.guest_pmap[gfn1]; + /* Get attributes from the Guest TLB */ entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[0] & ENTRYLO_D) | - (tlb->tlb_lo[0] & ENTRYLO_V); + (tlb_lo[0] & ENTRYLO_D) | + (tlb_lo[0] & ENTRYLO_V); entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[1] & ENTRYLO_D) | - (tlb->tlb_lo[1] & ENTRYLO_V); + (tlb_lo[1] & ENTRYLO_D) | + (tlb_lo[1] & ENTRYLO_V); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo[0], tlb->tlb_lo[1]); @@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu) local_irq_restore(flags); return KVM_INVALID_INST; } - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch. - guest_tlb[index]); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, + &vcpu->arch.guest_tlb[index])) { + kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, opc, index, vcpu, + read_c0_entryhi()); + kvm_mips_dump_guest_tlbs(vcpu); + local_irq_restore(flags); + return KVM_INVALID_INST; + } inst = *(opc); } local_irq_restore(flags); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index ca254546cd05..1934707bf321 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -66,29 +66,28 @@ endif UTS_MACHINE := $(OLDARCH) ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -override CC += -mlittle-endian -ifneq ($(cc-name),clang) -override CC += -mno-strict-align -endif -override AS += -mlittle-endian override LD += -EL -override CROSS32CC += -mlittle-endian override CROSS32AS += -mlittle-endian LDEMULATION := lppc GNUTARGET := powerpcle MULTIPLEWORD := -mno-multiple KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect) else -ifeq ($(call cc-option-yn,-mbig-endian),y) -override CC += -mbig-endian -override AS += -mbig-endian -endif override LD += -EB LDEMULATION := ppc GNUTARGET := powerpc MULTIPLEWORD := -mmultiple endif +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian +ifneq ($(cc-name),clang) + cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align +endif + +aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian + ifeq ($(HAS_BIARCH),y) override AS += -a$(CONFIG_WORD_SIZE) override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) @@ -232,6 +231,9 @@ cpu-as-$(CONFIG_E200) += -Wa,-me200 KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) +KBUILD_AFLAGS += $(aflags-y) +KBUILD_CFLAGS += $(cflags-y) + head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index bfe3d37a24ef..9fa046d56eba 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #define CHKSUM_BLOCK_SIZE 1 @@ -157,7 +158,7 @@ static void __exit crc32c_vpmsum_mod_fini(void) crypto_unregister_shash(&alg); } -module_init(crc32c_vpmsum_mod_init); +module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init); module_exit(crc32c_vpmsum_mod_fini); MODULE_AUTHOR("Anton Blanchard "); diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 3d7fc06532a1..01b8a13f0224 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -19,4 +19,17 @@ extern u64 pnv_first_deep_stop_state; #endif +/* Idle state entry routines */ +#ifdef CONFIG_PPC_P7_NAP +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +1: cmp cr0,r0,r0; \ + bne 1b; \ + IDLE_INST; \ + b . +#endif /* CONFIG_PPC_P7_NAP */ + #endif diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 57fec8ac7b92..ddf54f5bbdd1 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -186,6 +186,7 @@ label##3: \ #ifndef __ASSEMBLY__ void apply_feature_fixups(void); +void setup_feature_keys(void); #endif #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 0a74ebe934e1..17c8380673a6 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -75,14 +75,6 @@ static inline void disable_kernel_spe(void) static inline void __giveup_spe(struct task_struct *t) { } #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -extern void flush_tmregs_to_thread(struct task_struct *); -#else -static inline void flush_tmregs_to_thread(struct task_struct *t) -{ -} -#endif - static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f5f729c11578..f0b238516e9b 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -159,6 +159,8 @@ extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); extern void icp_native_eoi(struct irq_data *d); +extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type); +extern int xics_retrigger(struct irq_data *data); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9bc78e9c610..7429556eb8df 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 41091fdf9bd8..df6d45eb4115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -144,29 +144,14 @@ machine_check_pSeries_1: * vector */ SET_SCRATCH0(r13) /* save r13 */ -#ifdef CONFIG_PPC_P7_NAP -BEGIN_FTR_SECTION - /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + /* + * Running native on arch 2.06 or later, we may wakeup from winkle + * inside machine check. If yes, then last bit of HSPGR0 would be set + * to 1. Hence clear it unconditionally. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - beq 9f - - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal. let's just stay stuck here */ - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - bgt cr1,. -9: - OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ + GET_PACA(r13) + clrrdi r13,r13,1 + SET_PACA(r13) EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION b machine_check_powernv_early @@ -1273,25 +1258,51 @@ machine_check_handle_early: * Check if thread was in power saving mode. We come here when any * of the following is true: * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss or - * supervisor state loss + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. * - * Go back to nap again if (b) is true. + * Go back to nap/sleep/winkle mode again if (b) is true. */ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ beq 4f /* No, it wasn;t */ /* Thread was in power saving mode. Go back to nap again. */ cmpwi r11,2 - bne 3f - /* Supervisor state loss */ + blt 3f + /* Supervisor/Hypervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) 3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - li r3,PNV_THREAD_NAP - b pnv_enter_arch207_idle_mode + /* + * Check what idle state this CPU was in and go back to same mode + * again. + */ + lbz r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi r3,PNV_THREAD_NAP + bgt 10f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +10: + cmpwi r3,PNV_THREAD_SLEEP + bgt 2f + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ + +2: + /* + * Go back to winkle. Please note that this thread was woken up in + * machine check from winkle and have not restored the per-subcore + * state. Hence before going back to winkle, set last bit of HSPGR0 + * to 1. This will make sure that if this thread gets woken up + * again at reset vector 0x100 then it will get chance to restore + * the subcore state. + */ + ori r13,r13,1 + SET_PACA(r13) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + /* No return */ 4: #endif /* diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index ba79d15f4ddd..2265c6398a17 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -44,18 +44,6 @@ PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ PSSCR_MTL_MASK -/* Idle state entry routines */ - -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r0,0(r1); \ - ptesync; \ - ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ - bne 1b; \ - IDLE_INST; \ - b . - .text /* @@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop) * cr3 - set to gt if waking up with partial/complete hypervisor state loss */ _GLOBAL(pnv_restore_hyp_resource) - ld r2,PACATOC(r13); BEGIN_FTR_SECTION + ld r2,PACATOC(r13); /* * POWER ISA 3. Use PSSCR to determine if we * are waking up from deep idle state @@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) */ clrldi r5,r13,63 clrrdi r13,r13,1 + + /* Now that we are sure r13 is corrected, load TOC */ + ld r2,PACATOC(r13); cmpwi cr4,r5,1 mtspr SPRN_HSPRG0,r13 diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index ef267fd9dd22..5e7ece0fda9f 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->in_use = 1; mce->initiator = MCE_INITIATOR_CPU; - if (handled) + /* Mark it recovered if we have handled it and MSR(RI=1). */ + if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index a5c0153ede37..7fdf324d5b51 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops); static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; + u32 prop_32; u64 prop; /* @@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn) * reading "ibm,opal-phbid", only present in OPAL environment. */ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); - if (ret) - ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop); + if (ret) { + ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); + prop = prop_32; + } if (!ret) phb_id = (int)(prop & (MAX_PHBS - 1)); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 58ccf86415b4..9ee2623e0f67 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1074,26 +1074,6 @@ static inline void restore_sprs(struct thread_struct *old_thread, #endif } -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -void flush_tmregs_to_thread(struct task_struct *tsk) -{ - /* - * Process self tracing is not yet supported through - * ptrace interface. Ptrace generic code should have - * prevented this from happening in the first place. - * Warn once here with the message, if some how it - * is attempted. - */ - WARN_ONCE(tsk == current, - "Not expecting ptrace on self: TM regs may be incorrect\n"); - - /* - * If task is not current, it should have been flushed - * already to it's thread_struct during __switch_to(). - */ -} -#endif - struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6ee4b72cda42..4e74fc588a3f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2940,7 +2940,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("Booting Linux via __start() ...\n"); + prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 4f3c5756cc09..bf91658a8a40 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -38,6 +38,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -118,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = { REG_OFFSET_END, }; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * If task is not current, it will have been flushed already to + * it's thread_struct during __switch_to(). + * + * A reclaim flushes ALL the state. + */ + + if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(TM_CAUSE_SIGNAL); + +} +#else +static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } +#endif + /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index c3e861df4b20..24ec3ea4b3a2 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -93,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * and we are running with enough of the MMU enabled to have our * proper kernel virtual addresses * - * Find out what kind of machine we're on and save any data we need - * from the early boot process (devtree is copied on pmac by prom_init()). - * This is called very early on the boot process, after a minimal - * MMU environment has been set up but before MMU_init is called. + * We do the initial parsing of the flat device-tree and prepares + * for the MMU to be fully initialized. */ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + /* Configure static keys first, now that we're relocated. */ + setup_feature_keys(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eafb9a79e011..7ac8e6eaab5b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -300,6 +300,7 @@ void __init early_setup(unsigned long dt_ptr) /* Apply all the dynamic patching */ apply_feature_fixups(); + setup_feature_keys(); /* Initialize the hash table or TLB handling */ early_init_mmu(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 6767605ea8da..4111d30badfa 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index cbabd143acae..78a7449bf489 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index c710802b8fb6..366ae09b14c1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a75ba38a2d81..05aa11399a78 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics->kvm = kvm; /* Already there ? */ - mutex_lock(&kvm->lock); if (kvm->arch.xics) ret = -EEXIST; else kvm->arch.xics = xics; - mutex_unlock(&kvm->lock); if (ret) { kfree(xics); return ret; } - xics_debugfs_init(xics); - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE if (cpu_has_feature(CPU_FTR_ARCH_206)) { /* Enable real mode support */ @@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) return 0; } +static void kvmppc_xics_init(struct kvm_device *dev) +{ + struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private; + + xics_debugfs_init(xics); +} + struct kvm_device_ops kvm_xics_ops = { .name = "kvm-xics", .create = kvmppc_xics_create, + .init = kvmppc_xics_init, .destroy = kvmppc_xics_free, .set_attr = xics_set_attr, .get_attr = xics_get_attr, diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index d90870a66b60..0a57fe6d49cc 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -127,8 +127,9 @@ _GLOBAL(csum_partial_copy_generic) stw r7,12(r1) stw r8,8(r1) - andi. r0,r4,1 /* is destination address even ? */ - cmplwi cr7,r0,0 + rlwinm r0,r4,3,0x8 + rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */ + cmplwi cr7,r0,0 /* is destination address even ? */ addic r12,r6,0 addi r6,r4,-4 neg r0,r4 @@ -237,7 +238,7 @@ _GLOBAL(csum_partial_copy_generic) 66: addze r3,r12 addi r1,r1,16 beqlr+ cr7 - rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */ + rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */ blr /* read fault */ diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 74145f02ad41..043415f0bdb1 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -188,7 +188,10 @@ void __init apply_feature_fixups(void) &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); #endif do_final_fixups(); +} +void __init setup_feature_keys(void) +{ /* * Initialise jump label. This causes all the cpu/mmu_has_feature() * checks to take on their correct polarity based on the current set of diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 5be15cff758d..2975754c65ea 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -496,8 +496,10 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) gang = alloc_spu_gang(); SPUFS_I(inode)->i_ctx = NULL; SPUFS_I(inode)->i_gang = gang; - if (!gang) + if (!gang) { + ret = -ENOMEM; goto out_iput; + } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 309d9ccccd50..c61667e8bb06 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -187,6 +187,11 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) if (dev->vendor == 0x1959 && dev->device == 0xa007 && !firmware_has_feature(FW_FEATURE_LPAR)) { dev->dev.archdata.dma_ops = &dma_direct_ops; + /* + * Set the coherent DMA mask to prevent the iommu + * being used unnecessarily + */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(44); return; } #endif diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index e505223b4ec5..ed8bba68a162 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -228,7 +228,8 @@ int __init opal_event_init(void) } /* Install interrupt handler */ - rc = request_irq(virq, opal_interrupt, 0, "opal", NULL); + rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW, + "opal", NULL); if (rc) { irq_dispose_mapping(virq); pr_warn("Error %d requesting irq %d (0x%x)\n", diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 8b4fc68cebcb..6c9a65b52e63 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -399,6 +399,7 @@ static int opal_recover_mce(struct pt_regs *regs, if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ + pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6b9528307f62..fd9444f9fb0c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -111,10 +111,17 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) +static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) { - return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == - (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)); + /* + * WARNING: We cannot rely on the resource flags. The Linux PCI + * allocation code sometimes decides to put a 64-bit prefetchable + * BAR in the 32-bit window, so we have to compare the addresses. + * + * For simplicity we only test resource start. + */ + return (r->start >= phb->ioda.m64_base && + r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); } static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) @@ -229,7 +236,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev, sgsz = phb->ioda.m64_segsize; for (i = 0; i <= PCI_ROM_RESOURCE; i++) { r = &pdev->resource[i]; - if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags)) + if (!r->parent || !pnv_pci_is_m64(phb, r)) continue; start = _ALIGN_DOWN(r->start - base, sgsz); @@ -1877,7 +1884,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, unsigned shift, unsigned long index, unsigned long npages) { - __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false); + __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm); unsigned long start, end, inc; /* We'll invalidate DMA address in PE scope */ @@ -2863,7 +2870,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) { + if (!pnv_pci_is_m64(phb, res)) { dev_warn(&pdev->dev, "Don't support SR-IOV with" " non M64 VF BAR%d: %pR. \n", i, res); @@ -2958,7 +2965,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, index++; } } else if ((res->flags & IORESOURCE_MEM) && - !pnv_pci_is_mem_pref_64(res->flags)) { + !pnv_pci_is_m64(phb, res)) { region.start = res->start - phb->hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -3083,9 +3090,12 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, bridge = bridge->bus->self; } - /* We fail back to M32 if M64 isn't supported */ - if (phb->ioda.m64_segsize && - pnv_pci_is_mem_pref_64(type)) + /* + * We fall back to M32 if M64 isn't supported. We enforce the M64 + * alignment for any 64-bit resource, PCIe doesn't care and + * bridges only do 64-bit prefetchable anyway. + */ + if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64)) return phb->ioda.m64_segsize; if (type & IORESOURCE_MEM) return phb->ioda.m32_segsize; @@ -3125,7 +3135,7 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus, w = NULL; if (r->flags & type & IORESOURCE_IO) w = &hose->io_resource; - else if (pnv_pci_is_mem_pref_64(r->flags) && + else if (pnv_pci_is_m64(phb, r) && (type & IORESOURCE_PREFETCH) && phb->ioda.m64_segsize) w = &hose->mem_resources[1]; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 43f7beb2902d..76ec104e88be 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -320,19 +320,6 @@ static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb) return dlpar_update_device_tree_lmb(lmb); } -static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) -{ - unsigned long section_nr; - struct mem_section *mem_sect; - struct memory_block *mem_block; - - section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - - mem_block = find_memory_block(mem_sect); - return mem_block; -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -420,6 +407,19 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb) static int dlpar_add_lmb(struct of_drconf_cell *); +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + static int dlpar_remove_lmb(struct of_drconf_cell *lmb) { struct memory_block *mem_block; diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 0031eda320c3..385e7aa9e273 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,6 +1,7 @@ config PPC_XICS def_bool n select PPC_SMP_MUXED_IPI + select HARDIRQS_SW_RESEND config PPC_ICP_NATIVE def_bool n diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 27c936c080a6..1c6bf4b66f56 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -156,7 +156,9 @@ static struct irq_chip ics_opal_irq_chip = { .irq_mask = ics_opal_mask_irq, .irq_unmask = ics_opal_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_opal_set_affinity + .irq_set_affinity = ics_opal_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_opal_map(struct ics *ics, unsigned int virq); diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 3854dd41558d..78ee5c778ef8 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -163,7 +163,9 @@ static struct irq_chip ics_rtas_irq_chip = { .irq_mask = ics_rtas_mask_irq, .irq_unmask = ics_rtas_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_rtas_set_affinity + .irq_set_affinity = ics_rtas_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_rtas_map(struct ics *ics, unsigned int virq) diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index a795a5f0301c..9d530f479588 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -328,8 +328,12 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq, pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); - /* They aren't all level sensitive but we just don't really know */ - irq_set_status_flags(virq, IRQ_LEVEL); + /* + * Mark interrupts as edge sensitive by default so that resend + * actually works. The device-tree parsing will turn the LSIs + * back to level. + */ + irq_clear_status_flags(virq, IRQ_LEVEL); /* Don't call into ICS for IPIs */ if (hw == XICS_IPI) { @@ -351,13 +355,54 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct, irq_hw_number_t *out_hwirq, unsigned int *out_flags) { - /* Current xics implementation translates everything - * to level. It is not technically right for MSIs but this - * is irrelevant at this point. We might get smarter in the future - */ *out_hwirq = intspec[0]; - *out_flags = IRQ_TYPE_LEVEL_LOW; + /* + * If intsize is at least 2, we look for the type in the second cell, + * we assume the LSB indicates a level interrupt. + */ + if (intsize > 1) { + if (intspec[1] & 1) + *out_flags = IRQ_TYPE_LEVEL_LOW; + else + *out_flags = IRQ_TYPE_EDGE_RISING; + } else + *out_flags = IRQ_TYPE_LEVEL_LOW; + + return 0; +} + +int xics_set_irq_type(struct irq_data *d, unsigned int flow_type) +{ + /* + * We only support these. This has really no effect other than setting + * the corresponding descriptor bits mind you but those will in turn + * affect the resend function when re-enabling an edge interrupt. + * + * Set set the default to edge as explained in map(). + */ + if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE) + flow_type = IRQ_TYPE_EDGE_RISING; + + if (flow_type != IRQ_TYPE_EDGE_RISING && + flow_type != IRQ_TYPE_LEVEL_LOW) + return -EINVAL; + + irqd_set_trigger_type(d, flow_type); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +int xics_retrigger(struct irq_data *data) +{ + /* + * We need to push a dummy CPPR when retriggering, since the subsequent + * EOI will try to pop it. Passing 0 works, as the function hard codes + * the priority value anyway. + */ + xics_push_cppr(0); + + /* Tell the core to do a soft retrigger */ return 0; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0e348781327b..e751fe25d6ab 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -872,4 +872,17 @@ config S390_GUEST Select this option if you want to run the kernel as a guest under the KVM hypervisor. +config S390_GUEST_OLD_TRANSPORT + def_bool y + prompt "Guest support for old s390 virtio transport (DEPRECATED)" + depends on S390_GUEST + help + Enable this option to add support for the old s390-virtio + transport (i.e. virtio devices NOT based on virtio-ccw). This + type of virtio devices is only available on the experimental + kuli userspace or with old (< 2.6) qemu. If you are running + with a modern version of qemu (which supports virtio-ccw since + 1.4 and uses it by default since version 2.4), you probably won't + need this. + endmenu diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3f3ae4865d57..f142215ed30d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2361,8 +2362,10 @@ retry: rc = gmap_mprotect_notify(vcpu->arch.gmap, kvm_s390_get_prefix(vcpu), PAGE_SIZE * 2, PROT_WRITE); - if (rc) + if (rc) { + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); return rc; + } goto retry; } diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index e35632ef23c7..62dfc644c908 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, } static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, - bool write, bool foreign) + bool write, bool execute, bool foreign) { /* by default, allow everything */ return true; diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index fe91c25092da..77f28ce9c646 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,6 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y +CFLAGS_syscall_64.o += -Wno-override-init +CFLAGS_syscall_32.o += -Wno-override-init obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b846875aeea6..d172c619c449 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -288,11 +288,15 @@ return_from_SYSCALL_64: jne opportunistic_sysret_failed /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: + * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot + * restore RF properly. If the slowpath sets it for whatever reason, we + * need to restore it correctly. + * + * SYSRET can restore TF, but unlike IRET, restoring TF results in a + * trap from userspace immediately after SYSRET. This would cause an + * infinite loop whenever #DB happens with register state that satisfies + * the opportunistic SYSRET conditions. For example, single-stepping + * this user code: * * movq $stuck_here, %rcx * pushfq @@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) .endm #endif +/* Make sure APIC interrupt handlers end up in the irqentry section: */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +# define POP_SECTION_IRQENTRY .popsection +#else +# define PUSH_SECTION_IRQENTRY +# define POP_SECTION_IRQENTRY +#endif + .macro apicinterrupt num sym do_sym +PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym trace_apicinterrupt \num \sym +POP_SECTION_IRQENTRY .endm #ifdef CONFIG_SMP diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 97a69dbba649..9d35ec0cb8fc 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); +} + static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .enable_box = snb_uncore_msr_enable_box, .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, @@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); +} + static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) static struct intel_uncore_ops skl_uncore_msr_ops = { .init_box = skl_uncore_msr_init_box, + .enable_box = skl_uncore_msr_enable_box, .exit_box = skl_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 824e54086e07..8aee83bcf71f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void) static struct intel_uncore_type hswep_uncore_ha = { .name = "ha", - .num_counters = 5, + .num_counters = 4, .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), @@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = { static struct intel_uncore_type hswep_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, @@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = { static struct intel_uncore_type hswep_uncore_qpi = { .name = "qpi", - .num_counters = 5, + .num_counters = 4, .num_boxes = 3, .perf_ctr_bits = 48, .perf_ctr = SNBEP_PCI_PMON_CTR0, @@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = { static struct intel_uncore_type hswep_uncore_r3qpi = { .name = "r3qpi", - .num_counters = 4, + .num_counters = 3, .num_boxes = 3, .perf_ctr_bits = 44, .constraints = hswep_uncore_r3qpi_constraints, @@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index f5befd4945f2..124357773ffa 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -135,6 +135,7 @@ extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); +extern void lapic_update_tsc_freq(void); extern int APIC_init_uniprocessor(void); #ifdef CONFIG_X86_64 @@ -170,6 +171,7 @@ static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop +static inline void lapic_update_tsc_freq(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 7178043b0e1d..59405a248fc2 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,10 +22,6 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - /* - * irq_tlb_count is double-counted in irq_call_count, so it must be - * subtracted from irq_call_count when displaying irq_call_count - */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 223042086f4e..737da62bfeb0 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -5,10 +5,10 @@ struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ unsigned long pmd_flag; /* page flag for PMD entry */ - bool kernel_mapping; /* kernel mapping or ident mapping */ + unsigned long offset; /* ident mapping offset */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end); + unsigned long pstart, unsigned long pend); #endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e8ec7ae10fa..1cc82ece9ac1 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names - * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry + * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) #define SWP_TYPE_BITS 5 /* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1) +#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 9c6b890d5e7a..b2988c0ed829 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -58,7 +58,15 @@ extern unsigned char boot_gdt[]; extern unsigned char secondary_startup_64[]; #endif +static inline size_t real_mode_size_needed(void) +{ + if (real_mode_header) + return 0; /* already allocated. */ + + return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); +} + +void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); -void setup_real_mode(void); #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4e5be94e079a..6fa85944af83 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) static inline void __native_flush_tlb(void) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); native_write_cr3(native_read_cr3()); + preempt_enable(); } static inline void __native_flush_tlb_global_irq_disabled(void) diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index c852590254d5..e652a7cc6186 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -79,7 +79,7 @@ struct uv_gam_range_entry { u16 nasid; /* HNasid */ u16 sockid; /* Socket ID, high bits of APIC ID */ u16 pnode; /* Index to MMR and GRU spaces */ - u32 pxm; /* ACPI proximity domain number */ + u32 unused2; u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */ }; @@ -88,7 +88,8 @@ struct uv_gam_range_entry { #define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */ #define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */ #define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */ -#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2 +#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */ +#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3 #define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */ #define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 20abd912f0e4..cea4fc19e844 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -313,7 +313,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 -#define TSC_DIVISOR 32 +#define TSC_DIVISOR 8 /* * This function sets up the local APIC timer, with a timeout of @@ -565,12 +565,36 @@ static void setup_APIC_timer(void) CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; clockevents_config_and_register(levt, - (tsc_khz / TSC_DIVISOR) * 1000, + tsc_khz * (1000 / TSC_DIVISOR), 0xF, ~0UL); } else clockevents_register_device(levt); } +/* + * Install the updated TSC frequency from recalibration at the TSC + * deadline clockevent devices. + */ +static void __lapic_update_tsc_freq(void *info) +{ + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); + + if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR)); +} + +void lapic_update_tsc_freq(void) +{ + /* + * The clockevent device's ->mult and ->shift can both be + * changed. In order to avoid races, schedule the frequency + * update code on each CPU. + */ + on_each_cpu(__lapic_update_tsc_freq, NULL, 0); +} + /* * In this functions we calibrate APIC bus clocks to the external timer. * diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6368fa69d2af..54f35d988025 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -155,7 +155,7 @@ static void init_x2apic_ldr(void) /* * At CPU state changes, update the x2apic cluster sibling info. */ -int x2apic_prepare_cpu(unsigned int cpu) +static int x2apic_prepare_cpu(unsigned int cpu) { if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) return -ENOMEM; @@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu) return 0; } -int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int this_cpu) { int cpu; @@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu) static int x2apic_cluster_probe(void) { int cpu = smp_processor_id(); + int ret; if (!x2apic_mode) return 0; + ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", + x2apic_prepare_cpu, x2apic_dead_cpu); + if (ret < 0) { + pr_err("Failed to register X2APIC_PREPARE\n"); + return 0; + } cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); - cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", - x2apic_prepare_cpu, x2apic_dead_cpu); return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 09b59adaea3f..cb0673c1e940 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (strncmp(oem_id, "SGI", 3) != 0) return 0; + if (numa_off) { + pr_err("UV: NUMA is off, disabling UV support\n"); + return 0; + } + /* Setup early hub type field in uv_hub_info for Node 0 */ uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; @@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void) struct uv_gam_range_entry *gre = uv_gre_table; struct uv_gam_range_s *grt; unsigned long last_limit = 0, ram_limit = 0; - int bytes, i, sid, lsid = -1; + int bytes, i, sid, lsid = -1, indx = 0, lindx = -1; if (!gre) return; @@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void) } sid = gre->sockid - _min_socket; if (lsid < sid) { /* new range */ - grt = &_gr_table[sid]; - grt->base = lsid; + grt = &_gr_table[indx]; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid = sid; + lindx = indx++; continue; } if (lsid == sid && !ram_limit) { /* update range */ @@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void) } if (!ram_limit) { /* non-contiguous ram range */ grt++; - grt->base = sid - 1; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; continue; @@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n", + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", - "SID", "PN", "PXM"); + "SID", "PN"); } pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n", + "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, ((unsigned long)(gre->limit - lgre)) >> (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ - gre->type, gre->nasid, gre->sockid, - gre->pnode, gre->pxm); + gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; if (sock_min > gre->sockid) @@ -1286,7 +1291,7 @@ static void __init build_socket_tables(void) _pnode_to_socket[i] = SOCK_EMPTY; /* fill in pnode/node/addr conversion list values */ - pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n"); + pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; @@ -1294,20 +1299,18 @@ static void __init build_socket_tables(void) if (_socket_to_pnode[i] != SOCK_EMPTY) continue; /* duplicate */ _socket_to_pnode[i] = gre->pnode; - _socket_to_node[i] = gre->pxm; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n", + "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], - _socket_to_node[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* check socket -> node values */ + /* Set socket -> node values */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void) lnid = nid; apicid = per_cpu(x86_cpu_to_apicid, cpu); sockid = apicid >> uv_cpuid.socketid_shift; - i = sockid - minsock; - - if (nid != _socket_to_node[i]) { - pr_warn( - "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n", - i, sockid, gre->type, _socket_to_node[i], nid); - _socket_to_node[i] = nid; - } + _socket_to_node[sockid - minsock] = nid; + pr_info("UV: sid:%02x: apicid:%04x node:%2d\n", + sockid, apicid, nid); } /* Setup physical blade to pnode translation from GAM Range Table */ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 680049aa4593..01567aa87503 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -866,105 +866,17 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } - -/* - * Set xfeatures (aka XSTATE_BV) bit for a feature that we want - * to take out of its "init state". This will ensure that an - * XRSTOR actually restores the state. - */ -static void fpu__xfeature_set_non_init(struct xregs_state *xsave, - int xstate_feature_mask) -{ - xsave->header.xfeatures |= xstate_feature_mask; -} - -/* - * This function is safe to call whether the FPU is in use or not. - * - * Note that this only works on the current task. - * - * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) - * @xsave_state_ptr: a pointer to a copy of the state that you would - * like written in to the current task's FPU xsave state. This pointer - * must not be located in the current tasks's xsave area. - * Output: - * address of the state in the xsave area or NULL if the state - * is not present or is in its 'init state'. - */ -static void fpu__xfeature_set_state(int xstate_feature_mask, - void *xstate_feature_src, size_t len) -{ - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; - struct fpu *fpu = ¤t->thread.fpu; - void *dst; - - if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - WARN_ONCE(1, "%s() attempted with no xsave support", __func__); - return; - } - - /* - * Tell the FPU code that we need the FPU state to be in - * 'fpu' (not in the registers), and that we need it to - * be stable while we write to it. - */ - fpu__current_fpstate_write_begin(); - - /* - * This method *WILL* *NOT* work for compact-format - * buffers. If the 'xstate_feature_mask' is unset in - * xcomp_bv then we may need to move other feature state - * "up" in the buffer. - */ - if (xsave->header.xcomp_bv & xstate_feature_mask) { - WARN_ON_ONCE(1); - goto out; - } - - /* find the location in the xsave buffer of the desired state */ - dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask); - - /* - * Make sure that the pointer being passed in did not - * come from the xsave buffer itself. - */ - WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself"); - - /* put the caller-provided data in the location */ - memcpy(dst, xstate_feature_src, len); - - /* - * Mark the xfeature so that the CPU knows there is state - * in the buffer now. - */ - fpu__xfeature_set_non_init(xsave, xstate_feature_mask); -out: - /* - * We are done writing to the 'fpu'. Reenable preeption - * and (possibly) move the fpstate back in to the fpregs. - */ - fpu__current_fpstate_write_end(); -} - #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* - * This will go out and modify the XSAVE buffer so that PKRU is - * set to a particular state for access to 'pkey'. - * - * PKRU state does affect kernel access to user memory. We do - * not modfiy PKRU *itself* here, only the XSAVE state that will - * be restored in to PKRU when we return back to userspace. + * This will go out and modify PKRU register to set the access + * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; - struct pkru_state *old_pkru_state; - struct pkru_state new_pkru_state; + u32 old_pkru; int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); u32 new_pkru_bits = 0; @@ -974,6 +886,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * For most XSAVE components, this would be an arduous task: + * brining fpstate up to date with fpregs, updating fpstate, + * then re-populating fpregs. But, for components that are + * never lazily managed, we can just access the fpregs + * directly. PKRU is never managed lazily, so we can just + * manipulate it directly. Make sure it stays that way. + */ + WARN_ON_ONCE(!use_eager_fpu()); /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) @@ -984,37 +905,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, /* Shift the bits in to the correct place in PKRU for pkey: */ new_pkru_bits <<= pkey_shift; - /* Locate old copy of the state in the xsave buffer: */ - old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU); + /* Get old PKRU and mask off any old bits in place: */ + old_pkru = read_pkru(); + old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - /* - * When state is not in the buffer, it is in the init - * state, set it manually. Otherwise, copy out the old - * state. - */ - if (!old_pkru_state) - new_pkru_state.pkru = 0; - else - new_pkru_state.pkru = old_pkru_state->pkru; - - /* Mask off any old bits in place: */ - new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - - /* Set the newly-requested bits: */ - new_pkru_state.pkru |= new_pkru_bits; - - /* - * We could theoretically live without zeroing pkru.pad. - * The current XSAVE feature state definition says that - * only bytes 0->3 are used. But we do not want to - * chance leaking kernel stack out to userspace in case a - * memcpy() of the whole xsave buffer was done. - * - * They're in the same cacheline anyway. - */ - new_pkru_state.pad = 0; - - fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state)); + /* Write old part along with new part: */ + write_pkru(old_pkru | new_pkru_bits); return 0; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2dda0bc4576e..f16c55bfc090 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void) /* Initialize 32bit specific setup functions */ x86_init.resources.reserve_resources = i386_reserve_resources; x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; - - reserve_bios_regions(); } asmlinkage __visible void __init i386_start_kernel(void) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 99d48e7d2974..54a2372f5dbb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data) copy_bootdata(__va(real_mode_data)); x86_early_init_platform_quirks(); - reserve_bios_regions(); switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ed16e58658a4..c6dfd801df97 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1242,7 +1242,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) - mc146818_set_time(&curr_time); + mc146818_get_time(&curr_time); if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 61521dc19c10..9f669fdd2010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - - irq_stats(j)->irq_tlb_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 991b77986d57..0fa60f5f5a16 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - kernel_randomize_memory(); - iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); @@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p) max_possible_pfn = max_pfn; + /* + * Define random base addresses for memory sections after max_pfn is + * defined and before each memory section base is used. + */ + kernel_randomize_memory(); + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p) efi_find_mirror(); } + reserve_bios_regions(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p) early_trap_pf_init(); - setup_real_mode(); + /* + * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) + * with the current CR4 value. This may not be necessary, but + * auditing all the early-boot CR4 manipulation would be needed to + * rule it out. + */ + if (boot_cpu_data.cpuid_level >= 0) + /* A CPU has %cr4 if and only if it has CPUID. */ + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); @@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); - if (boot_cpu_data.cpuid_level >= 0) { - /* A CPU has %cr4 if and only if it has CPUID */ - mmu_cr4_features = __read_cr4(); - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - } - #ifdef CONFIG_X86_32 /* sync back kernel address range */ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1ef87e887051..78b9cb5a26af 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -22,6 +22,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1249,6 +1250,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); + /* Inform the TSC deadline clockevent devices about the recalibration */ + lapic_update_tsc_freq(); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 6c1ff31d99ff..495c776de4b4 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) *cursor &= 0xfe; } /* - * Similar treatment for VEX3 prefix. - * TODO: add XOP/EVEX treatment when insn decoder supports them + * Similar treatment for VEX3/EVEX prefix. + * TODO: add XOP treatment when insn decoder supports them */ - if (insn->vex_prefix.nbytes == 3) { + if (insn->vex_prefix.nbytes >= 3) { /* * vex2: c5 rvvvvLpp (has no b bit) * vex3/xop: c4/8f rxbmmmmm wvvvvLpp * evex: 62 rxbR00mm wvvvv1pp zllBVaaa - * (evex will need setting of both b and x since - * in non-sib encoding evex.x is 4th bit of MODRM.rm) - * Setting VEX3.b (setting because it has inverted meaning): + * Setting VEX3.b (setting because it has inverted meaning). + * Setting EVEX.x since (in non-SIB encoding) EVEX.x + * is the 4th bit of MODRM.rm, and needs the same treatment. + * For VEX3-encoded insns, VEX3.x value has no effect in + * non-SIB encoding, the change is superfluous but harmless. */ cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; - *cursor |= 0x20; + *cursor |= 0x60; } /* @@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) reg = MODRM_REG(insn); /* Fetch modrm.reg */ reg2 = 0xff; /* Fetch vex.vvvv */ - if (insn->vex_prefix.nbytes == 2) - reg2 = insn->vex_prefix.bytes[1]; - else if (insn->vex_prefix.nbytes == 3) + if (insn->vex_prefix.nbytes) reg2 = insn->vex_prefix.bytes[2]; /* - * TODO: add XOP, EXEV vvvv reading. + * TODO: add XOP vvvv reading. * * vex.vvvv field is in bits 6-3, bits are inverted. * But in 32-bit mode, high-order bit may be ignored. diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index f7dfeda83e5c..121f59c6ee54 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -19,7 +19,7 @@ #include #include -#define debug_putstr(v) early_printk(v) +#define debug_putstr(v) early_printk("%s", v) #define has_cpuflag(f) boot_cpu_has(f) #define get_boot_seed() kaslr_offset() #endif diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index ec21796ac5fd..4473cb4f8b90 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -3,15 +3,17 @@ * included by both the compressed kernel and the regular kernel. */ -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, +static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { addr &= PMD_MASK; for (; addr < end; addr += PMD_SIZE) { pmd_t *pmd = pmd_page + pmd_index(addr); - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | pmd_flag)); + if (pmd_present(*pmd)) + continue; + + set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag)); } } @@ -30,13 +32,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (pud_present(*pud)) { pmd = pmd_offset(pud, 0); - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); continue; } pmd = (pmd_t *)info->alloc_pgt_page(info->context); if (!pmd) return -ENOMEM; - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); } @@ -44,14 +46,15 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, } int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end) + unsigned long pstart, unsigned long pend) { + unsigned long addr = pstart + info->offset; + unsigned long end = pend + info->offset; unsigned long next; int result; - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; for (; addr < end; addr = next) { - pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pgd_t *pgd = pgd_page + pgd_index(addr); pud_t *pud; next = (addr & PGDIR_MASK) + PGDIR_SIZE; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 620928903be3..d28a2d741f9e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) +/* + * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS. + * With KASLR memory randomization, depending on the machine e820 memory + * and the PUD alignment. We may need twice more pages when KASLR memory + * randomization is enabled. + */ +#ifndef CONFIG_RANDOMIZE_MEMORY +#define INIT_PGD_PAGE_COUNT 6 +#else +#define INIT_PGD_PAGE_COUNT 12 +#endif +#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 26dccd6c0df1..ec8654f117d8 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void) * add padding if needed (especially for memory hotplug support). */ BUG_ON(kaslr_regions[0].base != &page_offset_base); - memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) + + memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; /* Adapt phyiscal memory region size based on available memory */ diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4480c06cade7..89d1146f5a6f 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -254,6 +254,7 @@ void __init efi_free_boot_services(void) for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + size_t rm_size; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) @@ -263,6 +264,26 @@ void __init efi_free_boot_services(void) if (md->attribute & EFI_MEMORY_RUNTIME) continue; + /* + * Nasty quirk: if all sub-1MB memory is used for boot + * services, we can get here without having allocated the + * real mode trampoline. It's too late to hand boot services + * memory back to the memblock allocator, so instead + * try to manually allocate the trampoline if needed. + * + * I've seen this on a Dell XPS 13 9350 with firmware + * 1.4.4 with SGX enabled booting Linux via Fedora 24's + * grub2-efi on a hard disk. (And no, I don't know why + * this happened, but Linux should still try to boot rather + * panicing early.) + */ + rm_size = real_mode_size_needed(); + if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { + set_real_mode_mem(start, rm_size); + start += rm_size; + size -= rm_size; + } + free_bootmem_late(start, size); } diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 66b2166ea4a1..23f2f3e41c7f 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -187,7 +187,8 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); void uv_bios_init(void) { uv_systab = NULL; - if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) { + if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || + !efi.uv_systab || efi_runtime_disabled()) { pr_crit("UV: UVsystab: missing\n"); return; } @@ -199,12 +200,14 @@ void uv_bios_init(void) return; } + /* Starting with UV4 the UV systab size is variable */ if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) { + int size = uv_systab->size; + iounmap(uv_systab); - uv_systab = ioremap(efi.uv_systab, uv_systab->size); + uv_systab = ioremap(efi.uv_systab, size); if (!uv_systab) { - pr_err("UV: UVsystab: ioremap(%d) failed!\n", - uv_systab->size); + pr_err("UV: UVsystab: ioremap(%d) failed!\n", size); return; } } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f0b5f2d402af..a3e3ccc87138 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -87,7 +87,7 @@ static int set_up_temporary_mappings(void) struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, - .kernel_mapping = true, + .offset = __PAGE_OFFSET, }; unsigned long mstart, mend; pgd_t *pgd; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 705e3fffb4a1..5db706f14111 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,9 +1,11 @@ #include +#include #include #include #include #include +#include struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -11,25 +13,37 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; -void __init reserve_real_mode(void) +void __init set_real_mode_mem(phys_addr_t mem, size_t size) { - phys_addr_t mem; - unsigned char *base; - size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); + void *base = __va(mem); - /* Has to be under 1M so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (!mem) - panic("Cannot allocate trampoline\n"); - - base = __va(mem); - memblock_reserve(mem, size); real_mode_header = (struct real_mode_header *) base; printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", base, (unsigned long long)mem, size); } -void __init setup_real_mode(void) +void __init reserve_real_mode(void) +{ + phys_addr_t mem; + size_t size = real_mode_size_needed(); + + if (!size) + return; + + WARN_ON(slab_is_available()); + + /* Has to be under 1M so we can execute real-mode AP code. */ + mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); + if (!mem) { + pr_info("No sub-1M memory is available for the trampoline\n"); + return; + } + + memblock_reserve(mem, size); + set_real_mode_mem(mem, size); +} + +static void __init setup_real_mode(void) { u16 real_mode_seg; const u32 *rel; @@ -84,7 +98,7 @@ void __init setup_real_mode(void) trampoline_header->start = (u64) secondary_startup_64; trampoline_cr4_features = &trampoline_header->cr4; - *trampoline_cr4_features = __read_cr4(); + *trampoline_cr4_features = mmu_cr4_features; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; @@ -100,7 +114,7 @@ void __init setup_real_mode(void) * need to mark it executable at do_pre_smp_initcalls() at least, * thus run it as a early_initcall(). */ -static int __init set_real_mode_permissions(void) +static void __init set_real_mode_permissions(void) { unsigned char *base = (unsigned char *) real_mode_header; size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); @@ -119,7 +133,16 @@ static int __init set_real_mode_permissions(void) set_memory_nx((unsigned long) base, size >> PAGE_SHIFT); set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT); set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT); +} + +static int __init init_real_mode(void) +{ + if (!real_mode_header) + panic("Real mode trampoline was not allocated"); + + setup_real_mode(); + set_real_mode_permissions(); return 0; } -early_initcall(set_real_mode_permissions); +early_initcall(init_real_mode); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 8c234dd9b8bc..80cc7c089a15 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1527,11 +1527,12 @@ static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) { struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; u64 offset = nfit_blk->stat_offset + mmio->size * bw; + const u32 STATUS_MASK = 0x80000037; if (mmio->num_lines) offset = to_interleave_offset(offset, mmio); - return readl(mmio->addr.base + offset); + return readl(mmio->addr.base + offset) & STATUS_MASK; } static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1a04af6d2421..6c6519f6492a 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3950,6 +3950,7 @@ static void rbd_dev_release(struct device *dev) bool need_put = !!rbd_dev->opts; ceph_oid_destroy(&rbd_dev->header_oid); + ceph_oloc_destroy(&rbd_dev->header_oloc); rbd_put_client(rbd_dev->rbd_client); rbd_spec_put(rbd_dev->spec); @@ -5336,15 +5337,6 @@ static ssize_t do_rbd_add(struct bus_type *bus, } spec->pool_id = (u64)rc; - /* The ceph file layout needs to fit pool id in 32 bits */ - - if (spec->pool_id > (u64)U32_MAX) { - rbd_warn(NULL, "pool id too large (%llu > %u)", - (unsigned long long)spec->pool_id, U32_MAX); - rc = -EIO; - goto err_out_client; - } - rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts); if (!rbd_dev) { rc = -ENOMEM; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1523e05c46fc..93b1aaa5ba3b 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -391,23 +391,17 @@ static int init_vq(struct virtio_blk *vblk) num_vqs = 1; vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL); - if (!vblk->vqs) { + if (!vblk->vqs) + return -ENOMEM; + + names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL); + callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL); + vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL); + if (!names || !callbacks || !vqs) { err = -ENOMEM; goto out; } - names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL); - if (!names) - goto err_names; - - callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL); - if (!callbacks) - goto err_callbacks; - - vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL); - if (!vqs) - goto err_vqs; - for (i = 0; i < num_vqs; i++) { callbacks[i] = virtblk_done; snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); @@ -417,7 +411,7 @@ static int init_vq(struct virtio_blk *vblk) /* Discover virtqueues and write information to configuration. */ err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names); if (err) - goto err_find_vqs; + goto out; for (i = 0; i < num_vqs; i++) { spin_lock_init(&vblk->vqs[i].lock); @@ -425,16 +419,12 @@ static int init_vq(struct virtio_blk *vblk) } vblk->num_vqs = num_vqs; - err_find_vqs: +out: kfree(vqs); - err_vqs: kfree(callbacks); - err_callbacks: kfree(names); - err_names: if (err) kfree(vblk->vqs); - out: return err; } diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 28bce3f4f81d..57700541f951 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -8,6 +8,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#define pr_fmt(fmt) "arm_arch_timer: " fmt + #include #include #include @@ -370,16 +373,33 @@ static bool arch_timer_has_nonsecure_ppi(void) arch_timer_ppi[PHYS_NONSECURE_PPI]); } +static u32 check_ppi_trigger(int irq) +{ + u32 flags = irq_get_trigger_type(irq); + + if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) { + pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq); + pr_warn("WARNING: Please fix your firmware\n"); + flags = IRQF_TRIGGER_LOW; + } + + return flags; +} + static int arch_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); + u32 flags; __arch_timer_setup(ARCH_CP15_TIMER, clk); - enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0); + flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]); + enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags); - if (arch_timer_has_nonsecure_ppi()) - enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0); + if (arch_timer_has_nonsecure_ppi()) { + flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]); + enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags); + } arch_counter_set_user_access(); if (evtstrm_enable) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 87796e0864e9..d3ffde806629 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -145,11 +145,30 @@ static struct powernv_pstate_info { /* Use following macros for conversions between pstate_id and index */ static inline int idx_to_pstate(unsigned int i) { + if (unlikely(i >= powernv_pstate_info.nr_pstates)) { + pr_warn_once("index %u is out of bound\n", i); + return powernv_freqs[powernv_pstate_info.nominal].driver_data; + } + return powernv_freqs[i].driver_data; } static inline unsigned int pstate_to_idx(int pstate) { + int min = powernv_freqs[powernv_pstate_info.min].driver_data; + int max = powernv_freqs[powernv_pstate_info.max].driver_data; + + if (min > 0) { + if (unlikely((pstate < max) || (pstate > min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } else { + if (unlikely((pstate > max) || (pstate < min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } /* * abs() is deliberately used so that is works with * both monotonically increasing and decreasing @@ -593,7 +612,7 @@ void gpstate_timer_handler(unsigned long data) } else { gpstate_idx = calc_global_pstate(gpstates->elapsed_time, gpstates->highest_lpstate_idx, - freq_data.pstate_id); + gpstates->last_lpstate_idx); } /* diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 4fb2eb7c800d..ce0067b7a2f6 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -552,9 +552,9 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { /* Knight's Landing Support */ /* * KNL's memory channels are swizzled between memory controllers. - * MC0 is mapped to CH3,5,6 and MC1 is mapped to CH0,1,2 + * MC0 is mapped to CH3,4,5 and MC1 is mapped to CH0,1,2 */ -#define knl_channel_remap(channel) ((channel + 3) % 6) +#define knl_channel_remap(mc, chan) ((mc) ? (chan) : (chan) + 3) /* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840 @@ -1286,7 +1286,7 @@ static u32 knl_get_mc_route(int entry, u32 reg) mc = GET_BITFIELD(reg, entry*3, (entry*3)+2); chan = GET_BITFIELD(reg, (entry*2) + 18, (entry*2) + 18 + 1); - return knl_channel_remap(mc*3 + chan); + return knl_channel_remap(mc, chan); } /* @@ -2997,8 +2997,15 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, } else { char A = *("A"); - channel = knl_channel_remap(channel); + /* + * Reported channel is in range 0-2, so we can't map it + * back to mc. To figure out mc we check machine check + * bank register that reported this error. + * bank15 means mc0 and bank16 means mc1. + */ + channel = knl_channel_remap(m->bank == 16, channel); channel_mask = 1 << channel; + snprintf(msg, sizeof(msg), "%s%s err_code:%04x:%04x channel:%d (DIMM_%c)", overflow ? " OVERFLOW" : "", diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index c99c24bc79b0..9ae6c116c474 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -16,6 +16,7 @@ #include #include #include +#include #define NO_FURTHER_WRITE_ACTION -1 @@ -108,14 +109,15 @@ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) int ret; void *cap_hdr_temp; - cap_hdr_temp = kmap(cap_info->pages[0]); + cap_hdr_temp = vmap(cap_info->pages, cap_info->index, + VM_MAP, PAGE_KERNEL); if (!cap_hdr_temp) { - pr_debug("%s: kmap() failed\n", __func__); + pr_debug("%s: vmap() failed\n", __func__); return -EFAULT; } ret = efi_capsule_update(cap_hdr_temp, cap_info->pages); - kunmap(cap_info->pages[0]); + vunmap(cap_hdr_temp); if (ret) { pr_err("%s: efi_capsule_update() failed\n", __func__); return ret; diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c index 53b9fd2293ee..6eedff45e6d7 100644 --- a/drivers/firmware/efi/capsule.c +++ b/drivers/firmware/efi/capsule.c @@ -190,9 +190,9 @@ efi_capsule_update_locked(efi_capsule_header_t *capsule, * map the capsule described by @capsule with its data in @pages and * send it to the firmware via the UpdateCapsule() runtime service. * - * @capsule must be a virtual mapping of the first page in @pages - * (@pages[0]) in the kernel address space. That is, a - * capsule_header_t that describes the entire contents of the capsule + * @capsule must be a virtual mapping of the complete capsule update in the + * kernel address space, as the capsule can be consumed immediately. + * A capsule_header_t that describes the entire contents of the capsule * must be at the start of the first data page. * * Even though this function will validate that the firmware supports diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 08a1e2f3690f..00c8a08d56e7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -68,7 +68,8 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) if (!iovad) return; - put_iova_domain(iovad); + if (iovad->granule) + put_iova_domain(iovad); kfree(iovad); domain->iova_cookie = NULL; } @@ -151,12 +152,15 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent) } } -static struct iova *__alloc_iova(struct iova_domain *iovad, size_t size, +static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size, dma_addr_t dma_limit) { + struct iova_domain *iovad = domain->iova_cookie; unsigned long shift = iova_shift(iovad); unsigned long length = iova_align(iovad, size) >> shift; + if (domain->geometry.force_aperture) + dma_limit = min(dma_limit, domain->geometry.aperture_end); /* * Enforce size-alignment to be safe - there could perhaps be an * attribute to control this per-device, or at least per-domain... @@ -314,7 +318,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, if (!pages) return NULL; - iova = __alloc_iova(iovad, size, dev->coherent_dma_mask); + iova = __alloc_iova(domain, size, dev->coherent_dma_mask); if (!iova) goto out_free_pages; @@ -386,7 +390,7 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; size_t iova_off = iova_offset(iovad, phys); size_t len = iova_align(iovad, size + iova_off); - struct iova *iova = __alloc_iova(iovad, len, dma_get_mask(dev)); + struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev)); if (!iova) return DMA_ERROR_CODE; @@ -538,7 +542,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, prev = s; } - iova = __alloc_iova(iovad, iova_len, dma_get_mask(dev)); + iova = __alloc_iova(domain, iova_len, dma_get_mask(dev)); if (!iova) goto out_restore_sg; diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 9ed0a8462ccf..3dab13b4a211 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -55,19 +55,19 @@ struct mtk_iommu_data { bool enable_4GB; }; -static int compare_of(struct device *dev, void *data) +static inline int compare_of(struct device *dev, void *data) { return dev->of_node == data; } -static int mtk_iommu_bind(struct device *dev) +static inline int mtk_iommu_bind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); return component_bind_all(dev, &data->smi_imu); } -static void mtk_iommu_unbind(struct device *dev) +static inline void mtk_iommu_unbind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index bdee9a01ef35..c466ee2b0c97 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -90,8 +90,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master, */ mutex_lock(&afu->contexts_lock); idr_preload(GFP_KERNEL); - i = idr_alloc(&ctx->afu->contexts_idr, ctx, - ctx->afu->adapter->native->sl_ops->min_pe, + i = idr_alloc(&ctx->afu->contexts_idr, ctx, ctx->afu->adapter->min_pe, ctx->afu->num_procs, GFP_NOWAIT); idr_preload_end(); mutex_unlock(&afu->contexts_lock); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index de090533f18c..344a0ff8f8c7 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -561,7 +561,6 @@ struct cxl_service_layer_ops { u64 (*timebase_read)(struct cxl *adapter); int capi_mode; bool needs_reset_before_disable; - int min_pe; }; struct cxl_native { @@ -603,6 +602,7 @@ struct cxl { struct bin_attribute cxl_attr; int adapter_num; int user_irqs; + int min_pe; u64 ps_size; u16 psl_rev; u16 base_image; diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 3bcdaee11ba1..e606fdc4bc9c 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -924,7 +924,7 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data) return fail_psl_irq(afu, &irq_info); } -void native_irq_wait(struct cxl_context *ctx) +static void native_irq_wait(struct cxl_context *ctx) { u64 dsisr; int timeout = 1000; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index d152e2de8c93..6f0c4ac4b649 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -379,7 +379,7 @@ static int calc_capp_routing(struct pci_dev *dev, u64 *chipid, u64 *capp_unit_id static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev) { - u64 psl_dsnctl; + u64 psl_dsnctl, psl_fircntl; u64 chipid; u64 capp_unit_id; int rc; @@ -398,8 +398,11 @@ static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_ cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL); /* snoop write mask */ cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL); - /* set fir_accum */ - cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL); + /* set fir_cntl to recommended value for production env */ + psl_fircntl = (0x2ULL << (63-3)); /* ce_report */ + psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */ + psl_fircntl |= 0x1ULL; /* ce_thresh */ + cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl); /* for debugging with trace arrays */ cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL); @@ -1521,14 +1524,15 @@ static const struct cxl_service_layer_ops xsl_ops = { .write_timebase_ctrl = write_timebase_ctrl_xsl, .timebase_read = timebase_read_xsl, .capi_mode = OPAL_PHB_CAPI_MODE_DMA, - .min_pe = 1, /* Workaround for Mellanox CX4 HW bug */ }; static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev) { if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) { + /* Mellanox CX-4 */ dev_info(&adapter->dev, "Device uses an XSL\n"); adapter->native->sl_ops = &xsl_ops; + adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */ } else { dev_info(&adapter->dev, "Device uses a PSL\n"); adapter->native->sl_ops = &psl_ops; diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index dee8def1c193..7ada5f1b7bb6 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -221,7 +221,7 @@ int cxl_pci_vphb_add(struct cxl_afu *afu) /* Setup the PHB using arch provided callback */ phb->ops = &cxl_pcie_pci_ops; phb->cfg_addr = NULL; - phb->cfg_data = 0; + phb->cfg_data = NULL; phb->private_data = afu; phb->controller_ops = cxl_pci_controller_ops; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 88e91666f145..368795aad5c9 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1269,6 +1269,7 @@ static int btt_blk_init(struct btt *btt) } } set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); + btt->nd_btt->size = btt->nlba * (u64)btt->sector_size; revalidate_disk(btt->btt_disk); return 0; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 3fa7919f94a8..97dd2925ed6e 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -140,10 +140,30 @@ static ssize_t namespace_store(struct device *dev, } static DEVICE_ATTR_RW(namespace); +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_btt *nd_btt = to_nd_btt(dev); + ssize_t rc; + + device_lock(dev); + if (dev->driver) + rc = sprintf(buf, "%llu\n", nd_btt->size); + else { + /* no size to convey if the btt instance is disabled */ + rc = -ENXIO; + } + device_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(size); + static struct attribute *nd_btt_attributes[] = { &dev_attr_sector_size.attr, &dev_attr_namespace.attr, &dev_attr_uuid.attr, + &dev_attr_size.attr, NULL, }; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 40476399d227..8024a0ef86d3 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -143,6 +143,7 @@ struct nd_btt { struct nd_namespace_common *ndns; struct btt *btt; unsigned long lbasize; + u64 size; u8 *uuid; int id; }; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d7c33f9361aa..8dcf5a960951 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1543,15 +1543,10 @@ static void nvme_disable_io_queues(struct nvme_dev *dev) reinit_completion(&dev->ioq_wait); retry: timeout = ADMIN_TIMEOUT; - for (; i > 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - - if (!pass) - nvme_suspend_queue(nvmeq); - if (nvme_delete_queue(nvmeq, opcode)) + for (; i > 0; i--, sent++) + if (nvme_delete_queue(dev->queues[i], opcode)) break; - ++sent; - } + while (sent--) { timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout); if (timeout == 0) @@ -1693,11 +1688,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } + + for (i = dev->queue_count - 1; i > 0; i--) + nvme_suspend_queue(dev->queues[i]); + if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - for (i = dev->queue_count - 1; i >= 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - nvme_suspend_queue(nvmeq); - } + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3e3ce2b0424e..8d2875b4c56d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -12,13 +12,11 @@ * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include #include #include #include #include #include -#include #include #include #include @@ -26,7 +24,6 @@ #include #include #include -#include #include #include @@ -169,7 +166,6 @@ MODULE_PARM_DESC(register_always, static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); -static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl); /* XXX: really should move to a generic header sooner or later.. */ static inline void put_unaligned_le24(u32 val, u8 *p) @@ -687,11 +683,6 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) list_del(&ctrl->list); mutex_unlock(&nvme_rdma_ctrl_mutex); - if (ctrl->ctrl.tagset) { - blk_cleanup_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - nvme_rdma_dev_put(ctrl->device); - } kfree(ctrl->queues); nvmf_free_options(nctrl->opts); free_ctrl: @@ -748,8 +739,11 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); - if (ctrl->queue_count > 1) + if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); + nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); + } dev_info(ctrl->ctrl.device, "Successfully reconnected\n"); @@ -1269,7 +1263,7 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; struct rdma_conn_param param = { }; - struct nvme_rdma_cm_req priv; + struct nvme_rdma_cm_req priv = { }; int ret; param.qp_num = queue->qp->qp_num; @@ -1318,37 +1312,39 @@ out_destroy_queue_ib: * that caught the event. Since we hold the callout until the controller * deletion is completed, we'll deadlock if the controller deletion will * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership - * of destroying this queue before-hand, destroy the queue resources - * after the controller deletion completed with the exception of destroying - * the cm_id implicitely by returning a non-zero rc to the callout. + * of destroying this queue before-hand, destroy the queue resources, + * then queue the controller deletion which won't destroy this queue and + * we destroy the cm_id implicitely by returning a non-zero rc to the callout. */ static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; - int ret, ctrl_deleted = 0; + int ret; - /* First disable the queue so ctrl delete won't free it */ - if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) - goto out; + /* Own the controller deletion */ + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) + return 0; - /* delete the controller */ - ret = __nvme_rdma_del_ctrl(ctrl); - if (!ret) { - dev_warn(ctrl->ctrl.device, - "Got rdma device removal event, deleting ctrl\n"); - flush_work(&ctrl->delete_work); + dev_warn(ctrl->ctrl.device, + "Got rdma device removal event, deleting ctrl\n"); + + /* Get rid of reconnect work if its running */ + cancel_delayed_work_sync(&ctrl->reconnect_work); + + /* Disable the queue so ctrl delete won't free it */ + if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) { + /* Free this queue ourselves */ + nvme_rdma_stop_queue(queue); + nvme_rdma_destroy_queue_ib(queue); /* Return non-zero so the cm_id will destroy implicitly */ - ctrl_deleted = 1; - - /* Free this queue ourselves */ - rdma_disconnect(queue->cm_id); - ib_drain_qp(queue->qp); - nvme_rdma_destroy_queue_ib(queue); + ret = 1; } -out: - return ctrl_deleted; + /* Queue controller deletion */ + queue_work(nvme_rdma_wq, &ctrl->delete_work); + flush_work(&ctrl->delete_work); + return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1648,7 +1644,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_free_io_queues(ctrl); } - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags)) nvme_shutdown_ctrl(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); @@ -1657,15 +1653,27 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_destroy_admin_queue(ctrl); } +static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) +{ + nvme_uninit_ctrl(&ctrl->ctrl); + if (shutdown) + nvme_rdma_shutdown_ctrl(ctrl); + + if (ctrl->ctrl.tagset) { + blk_cleanup_queue(ctrl->ctrl.connect_q); + blk_mq_free_tag_set(&ctrl->tag_set); + nvme_rdma_dev_put(ctrl->device); + } + + nvme_put_ctrl(&ctrl->ctrl); +} + static void nvme_rdma_del_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, true); } static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) @@ -1698,9 +1706,7 @@ static void nvme_rdma_remove_ctrl_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, false); } static void nvme_rdma_reset_ctrl_work(struct work_struct *work) @@ -1739,6 +1745,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); } return; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2fac17a5ad53..47c564b5a289 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -13,7 +13,6 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include #include #include "nvmet.h" @@ -83,7 +82,6 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; - u64 serial; u16 status = 0; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -96,10 +94,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->vid = 0; id->ssvid = 0; - /* generate a random serial number as our controllers are ephemeral: */ - get_random_bytes(&serial, sizeof(serial)); memset(id->sn, ' ', sizeof(id->sn)); - snprintf(id->sn, sizeof(id->sn), "%llx", serial); + snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial); memset(id->mn, ' ', sizeof(id->mn)); strncpy((char *)id->mn, "Linux", sizeof(id->mn)); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8a891ca53367..6559d5afa7bf 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -13,6 +13,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include "nvmet.h" static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX]; @@ -728,6 +729,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); + /* generate a random serial number as our controllers are ephemeral: */ + get_random_bytes(&ctrl->serial, sizeof(ctrl->serial)); + kref_init(&ctrl->ref); ctrl->subsys = subsys; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 94e782987cc9..7affd40a6b33 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -414,9 +414,8 @@ static void nvme_loop_del_ctrl_work(struct work_struct *work) struct nvme_loop_ctrl *ctrl = container_of(work, struct nvme_loop_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_loop_shutdown_ctrl(ctrl); nvme_uninit_ctrl(&ctrl->ctrl); + nvme_loop_shutdown_ctrl(ctrl); nvme_put_ctrl(&ctrl->ctrl); } @@ -501,7 +500,6 @@ out_free_queues: nvme_loop_destroy_admin_queue(ctrl); out_disable: dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 57dd6d834c28..76b6eedccaf9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -113,6 +113,7 @@ struct nvmet_ctrl { struct mutex lock; u64 cap; + u64 serial; u32 cc; u32 csts; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index e06d504bdf0c..b4d648536c3e 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -77,6 +77,7 @@ enum nvmet_rdma_queue_state { NVMET_RDMA_Q_CONNECTING, NVMET_RDMA_Q_LIVE, NVMET_RDMA_Q_DISCONNECTING, + NVMET_RDMA_IN_DEVICE_REMOVAL, }; struct nvmet_rdma_queue { @@ -615,15 +616,10 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, if (!len) return 0; - /* use the already allocated data buffer if possible */ - if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) { - nvmet_rdma_use_inline_sg(rsp, len, 0); - } else { - status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, - len); - if (status) - return status; - } + status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, + len); + if (status) + return status; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, @@ -984,7 +980,10 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w) struct nvmet_rdma_device *dev = queue->dev; nvmet_rdma_free_queue(queue); - rdma_destroy_id(cm_id); + + if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL) + rdma_destroy_id(cm_id); + kref_put(&dev->ref, nvmet_rdma_free_dev); } @@ -1233,8 +1232,9 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) switch (queue->state) { case NVMET_RDMA_Q_CONNECTING: case NVMET_RDMA_Q_LIVE: - disconnect = true; queue->state = NVMET_RDMA_Q_DISCONNECTING; + case NVMET_RDMA_IN_DEVICE_REMOVAL: + disconnect = true; break; case NVMET_RDMA_Q_DISCONNECTING: break; @@ -1272,6 +1272,62 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, schedule_work(&queue->release_work); } +/** + * nvme_rdma_device_removal() - Handle RDMA device removal + * @queue: nvmet rdma queue (cm id qp_context) + * @addr: nvmet address (cm_id context) + * + * DEVICE_REMOVAL event notifies us that the RDMA device is about + * to unplug so we should take care of destroying our RDMA resources. + * This event will be generated for each allocated cm_id. + * + * Note that this event can be generated on a normal queue cm_id + * and/or a device bound listener cm_id (where in this case + * queue will be null). + * + * we claim ownership on destroying the cm_id. For queues we move + * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port + * we nullify the priv to prevent double cm_id destruction and destroying + * the cm_id implicitely by returning a non-zero rc to the callout. + */ +static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, + struct nvmet_rdma_queue *queue) +{ + unsigned long flags; + + if (!queue) { + struct nvmet_port *port = cm_id->context; + + /* + * This is a listener cm_id. Make sure that + * future remove_port won't invoke a double + * cm_id destroy. use atomic xchg to make sure + * we don't compete with remove_port. + */ + if (xchg(&port->priv, NULL) != cm_id) + return 0; + } else { + /* + * This is a queue cm_id. Make sure that + * release queue will not destroy the cm_id + * and schedule all ctrl queues removal (only + * if the queue is not disconnecting already). + */ + spin_lock_irqsave(&queue->state_lock, flags); + if (queue->state != NVMET_RDMA_Q_DISCONNECTING) + queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL; + spin_unlock_irqrestore(&queue->state_lock, flags); + nvmet_rdma_queue_disconnect(queue); + flush_scheduled_work(); + } + + /* + * We need to return 1 so that the core will destroy + * it's own ID. What a great API design.. + */ + return 1; +} + static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { @@ -1294,20 +1350,11 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_CHANGE: case RDMA_CM_EVENT_DISCONNECTED: - case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_TIMEWAIT_EXIT: - /* - * We can get the device removal callback even for a - * CM ID that we aren't actually using. In that case - * the context pointer is NULL, so we shouldn't try - * to disconnect a non-existing queue. But we also - * need to return 1 so that the core will destroy - * it's own ID. What a great API design.. - */ - if (queue) - nvmet_rdma_queue_disconnect(queue); - else - ret = 1; + nvmet_rdma_queue_disconnect(queue); + break; + case RDMA_CM_EVENT_DEVICE_REMOVAL: + ret = nvmet_rdma_device_removal(cm_id, queue); break; case RDMA_CM_EVENT_REJECTED: case RDMA_CM_EVENT_UNREACHABLE: @@ -1396,9 +1443,10 @@ out_destroy_id: static void nvmet_rdma_remove_port(struct nvmet_port *port) { - struct rdma_cm_id *cm_id = port->priv; + struct rdma_cm_id *cm_id = xchg(&port->priv, NULL); - rdma_destroy_id(cm_id); + if (cm_id) + rdma_destroy_id(cm_id); } static struct nvmet_fabrics_ops nvmet_rdma_ops = { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a02981efdad5..eafa6138a6b8 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1411,6 +1411,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); + info->flags |= MSI_FLAG_ACTIVATE_EARLY; + domain = msi_create_irq_domain(fwnode, info, parent); if (!domain) return NULL; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 6ccb994bdfcb..c494613c1909 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -688,7 +688,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return 0; } -static DEFINE_MUTEX(arm_pmu_mutex); +static DEFINE_SPINLOCK(arm_pmu_lock); static LIST_HEAD(arm_pmu_list); /* @@ -701,7 +701,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) { struct arm_pmu *pmu; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_for_each_entry(pmu, &arm_pmu_list, entry) { if (!cpumask_test_cpu(cpu, &pmu->supported_cpus)) @@ -709,7 +709,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) if (pmu->reset) pmu->reset(pmu); } - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); return 0; } @@ -821,9 +821,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) if (!cpu_hw_events) return -ENOMEM; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_add_tail(&cpu_pmu->entry, &arm_pmu_list); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); err = cpu_pm_pmu_register(cpu_pmu); if (err) @@ -859,9 +859,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) return 0; out_unregister: - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_hw_events); return err; } @@ -869,9 +869,9 @@ out_unregister: static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) { cpu_pm_pmu_unregister(cpu_pmu); - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_pmu->hw_events); } @@ -967,11 +967,12 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) /* If we didn't manage to parse anything, try the interrupt affinity */ if (cpumask_weight(&pmu->supported_cpus) == 0) { - if (!using_spi) { - /* If using PPIs, check the affinity of the partition */ - int ret, irq; + int irq = platform_get_irq(pdev, 0); + + if (irq_is_percpu(irq)) { + /* If using PPIs, check the affinity of the partition */ + int ret; - irq = platform_get_irq(pdev, 0); ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus); if (ret) { kfree(irqs); diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index cecc15a880de..3fa17ac8df54 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -1080,8 +1080,8 @@ static int riocm_send_ack(struct rio_channel *ch) static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, long timeout) { - struct rio_channel *ch = NULL; - struct rio_channel *new_ch = NULL; + struct rio_channel *ch; + struct rio_channel *new_ch; struct conn_req *req; struct cm_peer *peer; int found = 0; @@ -1155,6 +1155,7 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, spin_unlock_bh(&ch->lock); riocm_put_channel(ch); + ch = NULL; kfree(req); down_read(&rdev_sem); @@ -1172,7 +1173,7 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, if (!found) { /* If peer device object not found, simply ignore the request */ err = -ENODEV; - goto err_nodev; + goto err_put_new_ch; } new_ch->rdev = peer->rdev; @@ -1184,15 +1185,16 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, *new_ch_id = new_ch->id; return new_ch; + +err_put_new_ch: + spin_lock_bh(&idr_lock); + idr_remove(&ch_idr, new_ch->id); + spin_unlock_bh(&idr_lock); + riocm_put_channel(new_ch); + err_put: - riocm_put_channel(ch); -err_nodev: - if (new_ch) { - spin_lock_bh(&idr_lock); - idr_remove(&ch_idr, new_ch->id); - spin_unlock_bh(&idr_lock); - riocm_put_channel(new_ch); - } + if (ch) + riocm_put_channel(ch); *new_ch_id = 0; return ERR_PTR(err); } diff --git a/drivers/s390/virtio/Makefile b/drivers/s390/virtio/Makefile index 241891a57caf..df40692a9011 100644 --- a/drivers/s390/virtio/Makefile +++ b/drivers/s390/virtio/Makefile @@ -6,4 +6,8 @@ # it under the terms of the GNU General Public License (version 2 only) # as published by the Free Software Foundation. -obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o +s390-virtio-objs := virtio_ccw.o +ifdef CONFIG_S390_GUEST_OLD_TRANSPORT +s390-virtio-objs += kvm_virtio.o +endif +obj-$(CONFIG_S390_GUEST) += $(s390-virtio-objs) diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c index 1d060fd293a3..5e5c11f37b24 100644 --- a/drivers/s390/virtio/kvm_virtio.c +++ b/drivers/s390/virtio/kvm_virtio.c @@ -458,6 +458,8 @@ static int __init kvm_devices_init(void) if (test_devices_support(total_memory_size) < 0) return -ENODEV; + pr_warn("The s390-virtio transport is deprecated. Please switch to a modern host providing virtio-ccw.\n"); + rc = vmem_add_mapping(total_memory_size, PAGE_SIZE); if (rc) return rc; @@ -482,7 +484,7 @@ static int __init kvm_devices_init(void) } /* code for early console output with virtio_console */ -static __init int early_put_chars(u32 vtermno, const char *buf, int count) +static int early_put_chars(u32 vtermno, const char *buf, int count) { char scratch[17]; unsigned int len = count; diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c index 1b4ff0f4c716..ed5dd0e88657 100644 --- a/drivers/thermal/clock_cooling.c +++ b/drivers/thermal/clock_cooling.c @@ -426,6 +426,7 @@ clock_cooling_register(struct device *dev, const char *clock_name) if (!ccdev) return ERR_PTR(-ENOMEM); + mutex_init(&ccdev->lock); ccdev->dev = dev; ccdev->clk = devm_clk_get(dev, clock_name); if (IS_ERR(ccdev->clk)) diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index 34fe36504a55..68bd1b569118 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -116,7 +116,9 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip) instance->target = get_target_state(tz, cdev, percentage, cur_trip_level); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(cdev); } return 0; diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index fc52016d4e85..bb118a152cbb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -71,7 +71,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) dev_dbg(&instance->cdev->device, "target=%d\n", (int)instance->target); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c index 6a6ec1c95a7a..9b4815e81b0d 100644 --- a/drivers/thermal/intel_pch_thermal.c +++ b/drivers/thermal/intel_pch_thermal.c @@ -21,6 +21,7 @@ #include #include #include +#include /* Intel PCH thermal Device IDs */ #define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */ @@ -65,6 +66,7 @@ struct pch_thermal_device { unsigned long crt_temp; int hot_trip_id; unsigned long hot_temp; + bool bios_enabled; }; static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) @@ -75,8 +77,10 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) *nr_trips = 0; /* Check if BIOS has already enabled thermal sensor */ - if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) + if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) { + ptd->bios_enabled = true; goto read_trips; + } tsel = readb(ptd->hw_base + WPT_TSEL); /* @@ -130,9 +134,39 @@ static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp) return 0; } +static int pch_wpt_suspend(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel & 0xFE, ptd->hw_base + WPT_TSEL); + + return 0; +} + +static int pch_wpt_resume(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel | WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL); + + return 0; +} + struct pch_dev_ops { int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips); int (*get_temp)(struct pch_thermal_device *ptd, int *temp); + int (*suspend)(struct pch_thermal_device *ptd); + int (*resume)(struct pch_thermal_device *ptd); }; @@ -140,6 +174,8 @@ struct pch_dev_ops { static const struct pch_dev_ops pch_dev_ops_wpt = { .hw_init = pch_wpt_init, .get_temp = pch_wpt_get_temp, + .suspend = pch_wpt_suspend, + .resume = pch_wpt_resume, }; static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) @@ -269,6 +305,22 @@ static void intel_pch_thermal_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static int intel_pch_thermal_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->suspend(ptd); +} + +static int intel_pch_thermal_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->resume(ptd); +} + static struct pci_device_id intel_pch_thermal_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) }, @@ -276,11 +328,17 @@ static struct pci_device_id intel_pch_thermal_id[] = { }; MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); +static const struct dev_pm_ops intel_pch_pm_ops = { + .suspend = intel_pch_thermal_suspend, + .resume = intel_pch_thermal_resume, +}; + static struct pci_driver intel_pch_thermal_driver = { .name = "intel_pch_thermal", .id_table = intel_pch_thermal_id, .probe = intel_pch_thermal_probe, .remove = intel_pch_thermal_remove, + .driver.pm = &intel_pch_pm_ops, }; module_pci_driver(intel_pch_thermal_driver); diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 015ce2eb6eb7..0e4dc0afcfd2 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -388,7 +388,7 @@ static int clamp_thread(void *arg) int sleeptime; unsigned long target_jiffies; unsigned int guard; - unsigned int compensation = 0; + unsigned int compensated_ratio; int interval; /* jiffies to sleep for each attempt */ unsigned int duration_jiffies = msecs_to_jiffies(duration); unsigned int window_size_now; @@ -409,8 +409,11 @@ static int clamp_thread(void *arg) * c-states, thus we need to compensate the injected idle ratio * to achieve the actual target reported by the HW. */ - compensation = get_compensation(target_ratio); - interval = duration_jiffies*100/(target_ratio+compensation); + compensated_ratio = target_ratio + + get_compensation(target_ratio); + if (compensated_ratio <= 0) + compensated_ratio = 1; + interval = duration_jiffies * 100 / compensated_ratio; /* align idle time */ target_jiffies = roundup(jiffies, interval); @@ -647,8 +650,8 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev, goto exit_set; } else if (set_target_ratio > 0 && new_target_ratio == 0) { pr_info("Stop forced idle injection\n"); - set_target_ratio = 0; end_power_clamp(); + set_target_ratio = 0; } else /* adjust currently running */ { set_target_ratio = new_target_ratio; /* make new set_target_ratio visible to other cpus */ diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 2f1a863a8e15..b4d3116cfdaf 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -529,7 +529,9 @@ static void allow_maximum_power(struct thermal_zone_device *tz) continue; instance->target = 0; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(instance->cdev); } } diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index ea9366ad3e6b..bcef2e7c4ec9 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -175,7 +175,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) update_passive_instance(tz, trip_type, -1); instance->initialized = true; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 5133cd1e10b7..e2fc6161dded 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1093,7 +1093,9 @@ int power_actor_set_power(struct thermal_cooling_device *cdev, return ret; instance->target = state; + mutex_lock(&cdev->lock); cdev->updated = false; + mutex_unlock(&cdev->lock); thermal_cdev_update(cdev); return 0; @@ -1623,11 +1625,13 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) struct thermal_instance *instance; unsigned long target = 0; - /* cooling device is updated*/ - if (cdev->updated) - return; - mutex_lock(&cdev->lock); + /* cooling device is updated*/ + if (cdev->updated) { + mutex_unlock(&cdev->lock); + return; + } + /* Make sure cdev enters the deepest cooling state */ list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) { dev_dbg(&cdev->device, "zone%d->target=%lu\n", @@ -1637,9 +1641,9 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) if (instance->target > target) target = instance->target; } - mutex_unlock(&cdev->lock); cdev->ops->set_cur_state(cdev, target); cdev->updated = true; + mutex_unlock(&cdev->lock); trace_cdev_update(cdev, target); dev_dbg(&cdev->device, "set to state %lu\n", target); } diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 06fd2ed9ef9d..c41c7742903a 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -232,6 +232,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) return result; } +EXPORT_SYMBOL_GPL(thermal_add_hwmon_sysfs); void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) { @@ -270,3 +271,4 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) hwmon_device_unregister(hwmon->device); kfree(hwmon); } +EXPORT_SYMBOL_GPL(thermal_remove_hwmon_sysfs); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 15ecfc9c5f6c..152b43822ef1 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -564,67 +564,80 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev, } static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, - uint32_t flags, void *data) + unsigned int count, uint32_t flags, + void *data) { - int32_t fd = *(int32_t *)data; - - if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK)) - return -EINVAL; - /* DATA_NONE/DATA_BOOL enables loopback testing */ if (flags & VFIO_IRQ_SET_DATA_NONE) { - if (*ctx) - eventfd_signal(*ctx, 1); - return 0; + if (*ctx) { + if (count) { + eventfd_signal(*ctx, 1); + } else { + eventfd_ctx_put(*ctx); + *ctx = NULL; + } + return 0; + } } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { - uint8_t trigger = *(uint8_t *)data; + uint8_t trigger; + + if (!count) + return -EINVAL; + + trigger = *(uint8_t *)data; if (trigger && *ctx) eventfd_signal(*ctx, 1); + + return 0; + } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + int32_t fd; + + if (!count) + return -EINVAL; + + fd = *(int32_t *)data; + if (fd == -1) { + if (*ctx) + eventfd_ctx_put(*ctx); + *ctx = NULL; + } else if (fd >= 0) { + struct eventfd_ctx *efdctx; + + efdctx = eventfd_ctx_fdget(fd); + if (IS_ERR(efdctx)) + return PTR_ERR(efdctx); + + if (*ctx) + eventfd_ctx_put(*ctx); + + *ctx = efdctx; + } return 0; } - /* Handle SET_DATA_EVENTFD */ - if (fd == -1) { - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = NULL; - return 0; - } else if (fd >= 0) { - struct eventfd_ctx *efdctx; - efdctx = eventfd_ctx_fdget(fd); - if (IS_ERR(efdctx)) - return PTR_ERR(efdctx); - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = efdctx; - return 0; - } else - return -EINVAL; + return -EINVAL; } static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_ERR_IRQ_INDEX) + if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - /* - * We should sanitize start & count, but that wasn't caught - * originally, so this IRQ index must forever ignore them :-( - */ - - return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, + count, flags, data); } static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1) + if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, + count, flags, data); } int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags, diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 0ddf3a2dbfc4..e3b30ea9ece5 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -307,6 +307,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) vhost_disable_notify(&vsock->dev, vq); for (;;) { + u32 len; + if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue @@ -334,13 +336,15 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) continue; } + len = pkt->len; + /* Only accept correctly addressed packets */ if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) virtio_transport_recv_pkt(pkt); else virtio_transport_free_pkt(pkt); - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + len); added = true; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 114a0c88afb8..e383ecdaca59 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -327,6 +327,8 @@ static inline int virtqueue_add(struct virtqueue *_vq, * host should service the ring ASAP. */ if (out_sgs) vq->notify(&vq->vq); + if (indirect) + kfree(desc); END_USE(vq); return -ENOSPC; } @@ -426,6 +428,7 @@ unmap_release: if (indirect) kfree(desc); + END_USE(vq); return -EIO; } diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index b6d210e7a993..d9ddcfc18c91 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -862,33 +862,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, return 0; } -int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, - u64 ref_root, u64 bytenr, u64 num_bytes) -{ - struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_delayed_ref_head *ref_head; - int ret = 0; - - if (!fs_info->quota_enabled || !is_fstree(ref_root)) - return 0; - - delayed_refs = &trans->transaction->delayed_refs; - - spin_lock(&delayed_refs->lock); - ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0); - if (!ref_head) { - ret = -ENOENT; - goto out; - } - WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root); - ref_head->qgroup_ref_root = ref_root; - ref_head->qgroup_reserved = num_bytes; -out: - spin_unlock(&delayed_refs->lock); - return ret; -} - int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 5fca9534a271..43f3629760e9 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -250,9 +250,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, u64 parent, u64 ref_root, u64 owner, u64 offset, u64 reserved, int action, struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, - u64 ref_root, u64 bytenr, u64 num_bytes); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9404121fd5f7..5842423f8f47 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2033,6 +2033,14 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); + /* + * An ordered extent might have started before and completed + * already with io errors, in which case the inode was not + * updated and we end up here. So check the inode's mapping + * flags for any errors that might have happened while doing + * writeback of file data. + */ + ret = btrfs_inode_check_errors(inode); inode_unlock(inode); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2f5975954ccf..08dfc57e2270 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3435,10 +3435,10 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.offset = 0; inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL); ret = PTR_ERR_OR_ZERO(inode); - if (ret && ret != -ESTALE) + if (ret && ret != -ENOENT) goto out; - if (ret == -ESTALE && root == root->fs_info->tree_root) { + if (ret == -ENOENT && root == root->fs_info->tree_root) { struct btrfs_root *dead_root; struct btrfs_fs_info *fs_info = root->fs_info; int is_dead_root = 0; @@ -3474,7 +3474,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * Inode is already gone but the orphan item is still there, * kill the orphan item. */ - if (ret == -ESTALE) { + if (ret == -ENOENT) { trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -3633,7 +3633,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static void btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode) { struct btrfs_path *path; struct extent_buffer *leaf; @@ -3652,14 +3652,19 @@ static void btrfs_read_locked_inode(struct inode *inode) filled = true; path = btrfs_alloc_path(); - if (!path) + if (!path) { + ret = -ENOMEM; goto make_bad; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); - if (ret) + if (ret) { + if (ret > 0) + ret = -ENOENT; goto make_bad; + } leaf = path->nodes[0]; @@ -3812,11 +3817,12 @@ cache_acl: } btrfs_update_iflags(inode); - return; + return 0; make_bad: btrfs_free_path(path); make_bad_inode(inode); + return ret; } /* @@ -4204,6 +4210,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) int err = 0; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_trans_handle *trans; + u64 last_unlink_trans; if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; @@ -4226,11 +4233,27 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) if (err) goto out; + last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; + /* now the directory is empty */ err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry), dentry->d_name.name, dentry->d_name.len); - if (!err) + if (!err) { btrfs_i_size_write(inode, 0); + /* + * Propagate the last_unlink_trans value of the deleted dir to + * its parent directory. This is to prevent an unrecoverable + * log tree in the case we do something like this: + * 1) create dir foo + * 2) create snapshot under dir foo + * 3) delete the snapshot + * 4) rmdir foo + * 5) mkdir foo + * 6) fsync foo or some file inside foo + */ + if (last_unlink_trans >= trans->transid) + BTRFS_I(dir)->last_unlink_trans = last_unlink_trans; + } out: btrfs_end_transaction(trans, root); btrfs_btree_balance_dirty(root); @@ -5606,7 +5629,9 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { - btrfs_read_locked_inode(inode); + int ret; + + ret = btrfs_read_locked_inode(inode); if (!is_bad_inode(inode)) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5615,7 +5640,8 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, } else { unlock_new_inode(inode); iput(inode); - inode = ERR_PTR(-ESTALE); + ASSERT(ret < 0); + inode = ERR_PTR(ret < 0 ? ret : -ESTALE); } } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index b71dd298385c..efe129fe2678 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -231,7 +231,6 @@ struct pending_dir_move { u64 parent_ino; u64 ino; u64 gen; - bool is_orphan; struct list_head update_refs; }; @@ -274,6 +273,39 @@ struct name_cache_entry { char name[]; }; +static void inconsistent_snapshot_error(struct send_ctx *sctx, + enum btrfs_compare_tree_result result, + const char *what) +{ + const char *result_string; + + switch (result) { + case BTRFS_COMPARE_TREE_NEW: + result_string = "new"; + break; + case BTRFS_COMPARE_TREE_DELETED: + result_string = "deleted"; + break; + case BTRFS_COMPARE_TREE_CHANGED: + result_string = "updated"; + break; + case BTRFS_COMPARE_TREE_SAME: + ASSERT(0); + result_string = "unchanged"; + break; + default: + ASSERT(0); + result_string = "unexpected"; + } + + btrfs_err(sctx->send_root->fs_info, + "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu", + result_string, what, sctx->cmp_key->objectid, + sctx->send_root->root_key.objectid, + (sctx->parent_root ? + sctx->parent_root->root_key.objectid : 0)); +} + static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * @@ -1861,7 +1893,8 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, * was already unlinked/moved, so we can safely assume that we will not * overwrite anything at this point in time. */ - if (other_inode > sctx->send_progress) { + if (other_inode > sctx->send_progress || + is_waiting_for_move(sctx, other_inode)) { ret = get_inode_info(sctx->parent_root, other_inode, NULL, who_gen, NULL, NULL, NULL, NULL); if (ret < 0) @@ -2502,6 +2535,8 @@ verbose_printk("btrfs: send_utimes %llu\n", ino); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0); + if (ret > 0) + ret = -ENOENT; if (ret < 0) goto out; @@ -2947,6 +2982,10 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, } if (loc.objectid > send_progress) { + struct orphan_dir_info *odi; + + odi = get_orphan_dir_info(sctx, dir); + free_orphan_dir_info(sctx, odi); ret = 0; goto out; } @@ -3047,7 +3086,6 @@ static int add_pending_dir_move(struct send_ctx *sctx, pm->parent_ino = parent_ino; pm->ino = ino; pm->gen = ino_gen; - pm->is_orphan = is_orphan; INIT_LIST_HEAD(&pm->list); INIT_LIST_HEAD(&pm->update_refs); RB_CLEAR_NODE(&pm->node); @@ -3113,6 +3151,48 @@ static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx, return NULL; } +static int path_loop(struct send_ctx *sctx, struct fs_path *name, + u64 ino, u64 gen, u64 *ancestor_ino) +{ + int ret = 0; + u64 parent_inode = 0; + u64 parent_gen = 0; + u64 start_ino = ino; + + *ancestor_ino = 0; + while (ino != BTRFS_FIRST_FREE_OBJECTID) { + fs_path_reset(name); + + if (is_waiting_for_rm(sctx, ino)) + break; + if (is_waiting_for_move(sctx, ino)) { + if (*ancestor_ino == 0) + *ancestor_ino = ino; + ret = get_first_ref(sctx->parent_root, ino, + &parent_inode, &parent_gen, name); + } else { + ret = __get_cur_name_and_parent(sctx, ino, gen, + &parent_inode, + &parent_gen, name); + if (ret > 0) { + ret = 0; + break; + } + } + if (ret < 0) + break; + if (parent_inode == start_ino) { + ret = 1; + if (*ancestor_ino == 0) + *ancestor_ino = ino; + break; + } + ino = parent_inode; + gen = parent_gen; + } + return ret; +} + static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) { struct fs_path *from_path = NULL; @@ -3123,6 +3203,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 ancestor; + bool is_orphan; int ret; name = fs_path_alloc(); @@ -3135,9 +3217,10 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); - if (pm->is_orphan) { + if (is_orphan) { ret = gen_unique_name(sctx, pm->ino, pm->gen, from_path); } else { @@ -3155,6 +3238,24 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) goto out; sctx->send_progress = sctx->cur_ino + 1; + ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor); + if (ret < 0) + goto out; + if (ret) { + LIST_HEAD(deleted_refs); + ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID); + ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor, + &pm->update_refs, &deleted_refs, + is_orphan); + if (ret < 0) + goto out; + if (rmdir_ino) { + dm = get_waiting_dir_move(sctx, pm->ino); + ASSERT(dm); + dm->rmdir_ino = rmdir_ino; + } + goto out; + } fs_path_reset(name); to_path = name; name = NULL; @@ -3174,7 +3275,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) /* already deleted */ goto finish; } - ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino + 1); + ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino); if (ret < 0) goto out; if (!ret) @@ -3204,8 +3305,18 @@ finish: * and old parent(s). */ list_for_each_entry(cur, &pm->update_refs, list) { - if (cur->dir == rmdir_ino) + /* + * The parent inode might have been deleted in the send snapshot + */ + ret = get_inode_info(sctx->send_root, cur->dir, NULL, + NULL, NULL, NULL, NULL, NULL); + if (ret == -ENOENT) { + ret = 0; continue; + } + if (ret < 0) + goto out; + ret = send_utimes(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; @@ -3325,6 +3436,7 @@ static int wait_for_dest_dir_move(struct send_ctx *sctx, u64 left_gen; u64 right_gen; int ret = 0; + struct waiting_dir_move *wdm; if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves)) return 0; @@ -3383,7 +3495,8 @@ static int wait_for_dest_dir_move(struct send_ctx *sctx, goto out; } - if (is_waiting_for_move(sctx, di_key.objectid)) { + wdm = get_waiting_dir_move(sctx, di_key.objectid); + if (wdm && !wdm->orphanized) { ret = add_pending_dir_move(sctx, sctx->cur_ino, sctx->cur_inode_gen, @@ -3470,7 +3583,8 @@ static int wait_for_parent_move(struct send_ctx *sctx, ret = is_ancestor(sctx->parent_root, sctx->cur_ino, sctx->cur_inode_gen, ino, path_before); - break; + if (ret) + break; } fs_path_reset(path_before); @@ -3643,11 +3757,26 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); goto out; if (ret) { struct name_cache_entry *nce; + struct waiting_dir_move *wdm; ret = orphanize_inode(sctx, ow_inode, ow_gen, cur->full_path); if (ret < 0) goto out; + + /* + * If ow_inode has its rename operation delayed + * make sure that its orphanized name is used in + * the source path when performing its rename + * operation. + */ + if (is_waiting_for_move(sctx, ow_inode)) { + wdm = get_waiting_dir_move(sctx, + ow_inode); + ASSERT(wdm); + wdm->orphanized = true; + } + /* * Make sure we clear our orphanized inode's * name from the name cache. This is because the @@ -3663,6 +3792,19 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); name_cache_delete(sctx, nce); kfree(nce); } + + /* + * ow_inode might currently be an ancestor of + * cur_ino, therefore compute valid_path (the + * current path of cur_ino) again because it + * might contain the pre-orphanization name of + * ow_inode, which is no longer valid. + */ + fs_path_reset(valid_path); + ret = get_cur_path(sctx, sctx->cur_ino, + sctx->cur_inode_gen, valid_path); + if (ret < 0) + goto out; } else { ret = send_unlink(sctx, cur->full_path); if (ret < 0) @@ -5602,7 +5744,10 @@ static int changed_ref(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "reference"); + return -EIO; + } if (!sctx->cur_inode_new_gen && sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) { @@ -5627,7 +5772,10 @@ static int changed_xattr(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "xattr"); + return -EIO; + } if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result == BTRFS_COMPARE_TREE_NEW) @@ -5651,7 +5799,10 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "extent"); + return -EIO; + } if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d31a0c4f56be..fff3f3efa436 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4469,7 +4469,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, - struct inode *inode) + struct inode *inode, + u64 *other_ino) { int ret; struct btrfs_path *search_path; @@ -4528,7 +4529,16 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, search_path, parent, name, this_name_len, 0); if (di && !IS_ERR(di)) { - ret = 1; + struct btrfs_key di_key; + + btrfs_dir_item_key_to_cpu(search_path->nodes[0], + di, &di_key); + if (di_key.type == BTRFS_INODE_ITEM_KEY) { + ret = 1; + *other_ino = di_key.objectid; + } else { + ret = -EAGAIN; + } goto out; } else if (IS_ERR(di)) { ret = PTR_ERR(di); @@ -4722,16 +4732,71 @@ again: if ((min_key.type == BTRFS_INODE_REF_KEY || min_key.type == BTRFS_INODE_EXTREF_KEY) && BTRFS_I(inode)->generation == trans->transid) { + u64 other_ino = 0; + ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], - &min_key, inode); + &min_key, inode, + &other_ino); if (ret < 0) { err = ret; goto out_unlock; } else if (ret > 0) { - err = 1; - btrfs_set_log_full_commit(root->fs_info, trans); - goto out_unlock; + struct btrfs_key inode_key; + struct inode *other_inode; + + if (ins_nr > 0) { + ins_nr++; + } else { + ins_nr = 1; + ins_start_slot = path->slots[0]; + } + ret = copy_items(trans, inode, dst_path, path, + &last_extent, ins_start_slot, + ins_nr, inode_only, + logged_isize); + if (ret < 0) { + err = ret; + goto out_unlock; + } + ins_nr = 0; + btrfs_release_path(path); + inode_key.objectid = other_ino; + inode_key.type = BTRFS_INODE_ITEM_KEY; + inode_key.offset = 0; + other_inode = btrfs_iget(root->fs_info->sb, + &inode_key, root, + NULL); + /* + * If the other inode that had a conflicting dir + * entry was deleted in the current transaction, + * we don't need to do more work nor fallback to + * a transaction commit. + */ + if (IS_ERR(other_inode) && + PTR_ERR(other_inode) == -ENOENT) { + goto next_key; + } else if (IS_ERR(other_inode)) { + err = PTR_ERR(other_inode); + goto out_unlock; + } + /* + * We are safe logging the other inode without + * acquiring its i_mutex as long as we log with + * the LOG_INODE_EXISTS mode. We're safe against + * concurrent renames of the other inode as well + * because during a rename we pin the log and + * update the log with the new name before we + * unpin it. + */ + err = btrfs_log_inode(trans, root, other_inode, + LOG_INODE_EXISTS, + 0, LLONG_MAX, ctx); + iput(other_inode); + if (err) + goto out_unlock; + else + goto next_key; } } @@ -4799,7 +4864,7 @@ next_slot: ins_nr = 0; } btrfs_release_path(path); - +next_key: if (min_key.offset < (u64)-1) { min_key.offset++; } else if (min_key.type < max_key.type) { @@ -4993,8 +5058,12 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; - if (IS_ROOT(parent)) + if (IS_ROOT(parent)) { + inode = d_inode(parent); + if (btrfs_must_commit_transaction(trans, inode)) + ret = 1; break; + } parent = dget_parent(parent); dput(old_parent); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 99115cae1652..16e6ded0b7f2 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1347,9 +1347,12 @@ void ceph_flush_snaps(struct ceph_inode_info *ci, { struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - struct ceph_mds_session *session = *psession; + struct ceph_mds_session *session = NULL; int mds; + dout("ceph_flush_snaps %p\n", inode); + if (psession) + session = *psession; retry: spin_lock(&ci->i_ceph_lock); if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa59a85226b2..f72d4ae303b2 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2759,6 +2759,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, } else { path = NULL; pathlen = 0; + pathbase = 0; } spin_lock(&ci->i_ceph_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4d09d4441e3e..05713a5da083 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1949,6 +1949,12 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; + /* + * If we are expecting writeback progress we must submit plugged IO. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + if (!nr_pages) nr_pages = get_nr_dirty_pages(); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 33da841a21bb..6f4752734804 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -338,6 +338,8 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) case 0: break; case -NFS4ERR_EXPIRED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 324bfdc21250..9bf64eacba5b 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -396,6 +396,10 @@ extern void nfs4_schedule_state_renewal(struct nfs_client *); extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); +extern void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed); + /* nfs4state.c */ struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a036e93bdf96..1949bbd806eb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4237,12 +4237,9 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str err = _nfs4_do_fsinfo(server, fhandle, fsinfo); trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); if (err == 0) { - struct nfs_client *clp = server->nfs_client; - - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo->lease_time * HZ; - clp->cl_last_renewal = now; - spin_unlock(&clp->cl_lock); + nfs4_set_lease_period(server->nfs_client, + fsinfo->lease_time * HZ, + now); break; } err = nfs4_handle_exception(server, err, &exception); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index e1ba58c3d1ad..82e77198d17e 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -136,6 +136,26 @@ nfs4_kill_renewd(struct nfs_client *clp) cancel_delayed_work_sync(&clp->cl_renewd); } +/** + * nfs4_set_lease_period - Sets the lease period on a nfs_client + * + * @clp: pointer to nfs_client + * @lease: new value for lease period + * @lastrenewed: time at which lease was last renewed + */ +void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed) +{ + spin_lock(&clp->cl_lock); + clp->cl_lease_time = lease; + clp->cl_last_renewal = lastrenewed; + spin_unlock(&clp->cl_lock); + + /* Cap maximum reconnect timeout at 1/2 lease period */ + rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1); +} + /* * Local variables: * c-basic-offset: 8 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 834b875900d6..cada00aa5096 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -277,20 +277,17 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp) { int status; struct nfs_fsinfo fsinfo; + unsigned long now; if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { nfs4_schedule_state_renewal(clp); return 0; } + now = jiffies; status = nfs4_proc_get_lease_time(clp, &fsinfo); if (status == 0) { - /* Update lease time and schedule renewal */ - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo.lease_time * HZ; - clp->cl_last_renewal = jiffies; - spin_unlock(&clp->cl_lock); - + nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now); nfs4_schedule_state_renewal(clp); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8410ca275db1..a204d7e109d4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4903,6 +4903,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } +static __be32 +nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) +{ + struct nfs4_ol_stateid *stp = openlockstateid(s); + __be32 ret; + + mutex_lock(&stp->st_mutex); + + ret = check_stateid_generation(stateid, &s->sc_stateid, 1); + if (ret) + goto out; + + ret = nfserr_locks_held; + if (check_for_locks(stp->st_stid.sc_file, + lockowner(stp->st_stateowner))) + goto out; + + release_lock_stateid(stp); + ret = nfs_ok; + +out: + mutex_unlock(&stp->st_mutex); + nfs4_put_stid(s); + return ret; +} + __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *free_stateid) @@ -4910,7 +4936,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_ol_stateid *stp; struct nfs4_client *cl = cstate->session->se_client; __be32 ret = nfserr_bad_stateid; @@ -4929,18 +4954,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ret = nfserr_locks_held; break; case NFS4_LOCK_STID: - ret = check_stateid_generation(stateid, &s->sc_stateid, 1); - if (ret) - break; - stp = openlockstateid(s); - ret = nfserr_locks_held; - if (check_for_locks(stp->st_stid.sc_file, - lockowner(stp->st_stateowner))) - break; - WARN_ON(!unhash_lock_stateid(stp)); + atomic_inc(&s->sc_count); spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; + ret = nfsd4_free_lock_stateid(stateid, s); goto out; case NFS4_REVOKED_DELEG_STID: dp = delegstateid(s); @@ -5507,7 +5523,7 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, - struct nfs4_ol_stateid **lst, bool *new) + struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; @@ -5515,7 +5531,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; + struct nfs4_ol_stateid *lst; unsigned int strhashval; + bool hashed; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { @@ -5531,12 +5549,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, goto out; } - *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); - if (*lst == NULL) { +retry: + lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); + if (lst == NULL) { status = nfserr_jukebox; goto out; } + + mutex_lock(&lst->st_mutex); + + /* See if it's still hashed to avoid race with FREE_STATEID */ + spin_lock(&cl->cl_lock); + hashed = !list_empty(&lst->st_perfile); + spin_unlock(&cl->cl_lock); + + if (!hashed) { + mutex_unlock(&lst->st_mutex); + nfs4_put_stid(&lst->st_stid); + goto retry; + } status = nfs_ok; + *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; @@ -5603,8 +5636,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); - if (status == nfs_ok) - mutex_lock(&lock_stp->st_mutex); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ba944123167b..ff476e654b8f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1252,10 +1252,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dchild)) return nfserrno(host_err); err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) { - dput(dchild); + /* + * We unconditionally drop our ref to dchild as fh_compose will have + * already grabbed its own ref for it. + */ + dput(dchild); + if (err) return err; - } return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, rdev, resfhp); } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 09e18fdf61e5..b9a8c813e5e6 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -46,7 +46,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) cached = 0; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_page_state(NR_LRU_BASE + lru); + pages[lru] = global_node_page_state(NR_LRU_BASE + lru); available = si_mem_available(); diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 54a8e65e18b6..7d026bf27713 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -25,7 +25,20 @@ #include /* - * Writer states & reader shift and bias + * Writer states & reader shift and bias. + * + * | +0 | +1 | +2 | +3 | + * ----+----+----+----+----+ + * LE | 78 | 56 | 34 | 12 | 0x12345678 + * ----+----+----+----+----+ + * | wr | rd | + * +----+----+----+----+ + * + * ----+----+----+----+----+ + * BE | 12 | 34 | 56 | 78 | 0x12345678 + * ----+----+----+----+----+ + * | rd | wr | + * +----+----+----+----+ */ #define _QW_WAITING 1 /* A writer is waiting */ #define _QW_LOCKED 0xff /* A writer holds the lock */ @@ -133,13 +146,23 @@ static inline void queued_read_unlock(struct qrwlock *lock) (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts); } +/** + * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: the write byte address of a queue rwlock + */ +static inline u8 *__qrwlock_write_byte(struct qrwlock *lock) +{ + return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN); +} + /** * queued_write_unlock - release write lock of a queue rwlock * @lock : Pointer to queue rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { - smp_store_release((u8 *)&lock->cnts, 0); + smp_store_release(__qrwlock_write_byte(lock), 0); } /* diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 701b64a3b7c5..89b65b82d98f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -74,7 +74,8 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, "Attempted to advance past end of bvec iter\n"); while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + unsigned iter_len = bvec_iter_len(bv, *iter); + unsigned len = min(bytes, iter_len); bytes -= len; iter->bi_size -= len; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01e908ac4a39..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,8 +1113,20 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); + /* + * init is called after create if create is successful and is called + * outside of holding kvm->lock. + */ + void (*init)(struct kvm_device *dev); + /* * Destroy is responsible for freeing dev. * diff --git a/include/linux/msi.h b/include/linux/msi.h index 4f0bfe5912b2..e8c81fbd5f9c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -270,6 +270,8 @@ enum { MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ MSI_FLAG_PCI_MSIX = (1 << 3), + /* Needs early activate, required for PCI */ + MSI_FLAG_ACTIVATE_EARLY = (1 << 4), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8ed4326164cc..2b6b43cc0dd5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,7 +743,9 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; +#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ +#endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; @@ -769,7 +771,9 @@ struct perf_cpu_context { unsigned int hrtimer_active; struct pmu *unique_pmu; +#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b6810c92b8bb..5c02b0691587 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -195,6 +195,8 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); +void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + unsigned long timeo); const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5e3e1b63dbb3..a16070dd03ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -218,7 +218,8 @@ struct rpc_xprt { struct work_struct task_cleanup; struct timer_list timer; unsigned long last_used, - idle_timeout; + idle_timeout, + max_reconnect_timeout; /* * Send stuff diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 6b011c19b50f..1d57ed3d84d2 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -32,7 +32,7 @@ */ #ifndef _UAPI_LINUX_VIRTIO_VSOCK_H -#define _UAPI_LINUX_VIRTIO_VOSCK_H +#define _UAPI_LINUX_VIRTIO_VSOCK_H #include #include diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index cbae529b7ce0..180d526a55c3 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -136,8 +136,8 @@ struct cxl_event_afu_driver_reserved { * * Of course the contents will be ABI, but that's up the AFU driver. */ - size_t data_size; - u8 data[]; + __u32 data_size; + __u8 data[]; }; struct cxl_event { diff --git a/kernel/events/core.c b/kernel/events/core.c index a19550d80ab1..1903b8f3a705 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -843,6 +843,32 @@ perf_cgroup_mark_enabled(struct perf_event *event, } } } + +/* + * Update cpuctx->cgrp so that it is set when first cgroup event is added and + * cleared when last cgroup event is removed. + */ +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ + struct perf_cpu_context *cpuctx; + + if (!is_cgroup_event(event)) + return; + + if (add && ctx->nr_cgroups++) + return; + else if (!add && --ctx->nr_cgroups) + return; + /* + * Because cgroup events are always per-cpu events, + * this will always be called from the right CPU. + */ + cpuctx = __get_cpu_context(ctx); + cpuctx->cgrp = add ? event->cgrp : NULL; +} + #else /* !CONFIG_CGROUP_PERF */ static inline bool @@ -920,6 +946,13 @@ perf_cgroup_mark_enabled(struct perf_event *event, struct perf_event_context *ctx) { } + +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ +} + #endif /* @@ -1392,6 +1425,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); @@ -1412,8 +1446,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_tail(&event->group_entry, list); } - if (is_cgroup_event(event)) - ctx->nr_cgroups++; + list_update_cgroup_event(event, ctx, true); list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; @@ -1581,8 +1614,6 @@ static void perf_group_attach(struct perf_event *event) static void list_del_event(struct perf_event *event, struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx; - WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); @@ -1594,20 +1625,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; - if (is_cgroup_event(event)) { - ctx->nr_cgroups--; - /* - * Because cgroup events are always per-cpu events, this will - * always be called from the right CPU. - */ - cpuctx = __get_cpu_context(ctx); - /* - * If there are no more cgroup events then clear cgrp to avoid - * stale pointer in update_cgrp_time_from_cpuctx(). - */ - if (!ctx->nr_cgroups) - cpuctx->cgrp = NULL; - } + list_update_cgroup_event(event, ctx, false); ctx->nr_events--; if (event->attr.inherit_stat) @@ -1716,8 +1734,8 @@ static inline int pmu_filter_match(struct perf_event *event) static inline int event_filter_match(struct perf_event *event) { - return (event->cpu == -1 || event->cpu == smp_processor_id()) - && perf_cgroup_match(event) && pmu_filter_match(event); + return (event->cpu == -1 || event->cpu == smp_processor_id()) && + perf_cgroup_match(event) && pmu_filter_match(event); } static void @@ -1737,8 +1755,8 @@ event_sched_out(struct perf_event *event, * maintained, otherwise bogus information is return * via read() for time_enabled, time_running: */ - if (event->state == PERF_EVENT_STATE_INACTIVE - && !event_filter_match(event)) { + if (event->state == PERF_EVENT_STATE_INACTIVE && + !event_filter_match(event)) { delta = tstamp - event->tstamp_stopped; event->tstamp_running += delta; event->tstamp_stopped = tstamp; @@ -2236,10 +2254,15 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); - event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; + /* + * Ensures that if we can observe event->ctx, both the event and ctx + * will be 'complete'. See perf_iterate_sb_cpu(). + */ + smp_store_release(&event->ctx, ctx); + if (!task) { cpu_function_call(cpu, __perf_install_in_context, event); return; @@ -5969,6 +5992,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data) struct perf_event *event; list_for_each_entry_rcu(event, &pel->list, sb_list) { + /* + * Skip events that are not fully formed yet; ensure that + * if we observe event->ctx, both event and ctx will be + * complete enough. See perf_install_in_context(). + */ + if (!smp_load_acquire(&event->ctx)) + continue; + if (event->state < PERF_EVENT_STATE_INACTIVE) continue; if (!event_filter_match(event)) diff --git a/kernel/futex.c b/kernel/futex.c index 33664f70e2d2..46cb3a301bc1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled; * Futex flags used to encode options to functions and preserve them across * restarts. */ -#define FLAGS_SHARED 0x01 +#ifdef CONFIG_MMU +# define FLAGS_SHARED 0x01 +#else +/* + * NOMMU does not have per process address space. Let the compiler optimize + * code away. + */ +# define FLAGS_SHARED 0x00 +#endif #define FLAGS_CLOCKRT 0x02 #define FLAGS_HAS_TIMEOUT 0x04 @@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key) if (!key->both.ptr) return; + /* + * On MMU less systems futexes are always "private" as there is no per + * process address space. We need the smp wmb nevertheless - yes, + * arch/blackfin has MMU less SMP ... + */ + if (!IS_ENABLED(CONFIG_MMU)) { + smp_mb(); /* explicit smp_mb(); (B) */ + return; + } + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: ihold(key->shared.inode); /* implies smp_mb(); (B) */ @@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key) return; } + if (!IS_ENABLED(CONFIG_MMU)) + return; + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: iput(key->shared.inode); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 54999350162c..19e9dfbe97fa 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -359,6 +359,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, else dev_dbg(dev, "irq [%d-%d] for MSI\n", virq, virq + desc->nvec_used - 1); + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (info->flags & MSI_FLAG_ACTIVATE_EARLY) { + struct irq_data *irq_data; + + irq_data = irq_domain_get_irq_data(domain, desc->irq); + irq_domain_activate_irq(irq_data); + } } return 0; diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 37649e69056c..8a99abf58080 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) goto gotlock; } } - WRITE_ONCE(pn->state, vcpu_halted); + WRITE_ONCE(pn->state, vcpu_hashed); qstat_inc(qstat_pv_wait_head, true); qstat_inc(qstat_pv_wait_again, waitcnt); pv_wait(&l->locked, _Q_SLOW_VAL); diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 22e025309845..b9d031516254 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, */ if ((counter == qstat_pv_latency_kick) || (counter == qstat_pv_latency_wake)) { - stat = 0; if (kicks) stat = DIV_ROUND_CLOSEST_ULL(stat, kicks); } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a881c6a7ba74..33c79b6105c5 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -300,12 +300,12 @@ static int create_image(int platform_mode) save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); + /* Restore control flow magically appears here */ + restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) printk(KERN_ERR "PM: Error %d creating hibernation image\n", error); - /* Restore control flow magically appears here */ - restore_processor_state(); if (!in_suspend) events_check_enabled = false; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1934f658c036..a846cf89eb96 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime) cpustat[CPUTIME_IDLE] += (__force u64) cputime; } +/* + * When a guest is interrupted for a longer amount of time, missed clock + * ticks are not redelivered later. Due to that, this function may on + * occasion account more time than the calling functions think elapsed. + */ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) { #ifdef CONFIG_PARAVIRT @@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, * idle, or potentially user or system time. Due to rounding, * other time can exceed ticks occasionally. */ - other = account_other_time(cputime); + other = account_other_time(ULONG_MAX); if (other >= cputime) return; cputime -= other; @@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick) } cputime = cputime_one_jiffy; - steal = steal_account_process_time(cputime); + steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) return; @@ -508,13 +513,21 @@ void account_process_tick(struct task_struct *p, int user_tick) */ void account_idle_ticks(unsigned long ticks) { + cputime_t cputime, steal; if (sched_clock_irqtime) { irqtime_account_idle_ticks(ticks); return; } - account_idle_time(jiffies_to_cputime(ticks)); + cputime = jiffies_to_cputime(ticks); + steal = steal_account_process_time(ULONG_MAX); + + if (steal >= cputime) + return; + + cputime -= steal; + account_idle_time(cputime); } /* @@ -606,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr, stime = curr->stime; utime = curr->utime; - if (utime == 0) { - stime = rtime; + /* + * If either stime or both stime and utime are 0, assume all runtime is + * userspace. Once a task gets some ticks, the monotonicy code at + * 'update' will ensure things converge to the observed ratio. + */ + if (stime == 0) { + utime = rtime; goto update; } - if (stime == 0) { - utime = rtime; + if (utime == 0) { + stime = rtime; goto update; } stime = scale_stime((__force u64)stime, (__force u64)rtime, (__force u64)(stime + utime)); +update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. @@ -641,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr, stime = rtime - utime; } -update: prev->stime = stime; prev->utime = utime; out: @@ -686,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) unsigned long now = READ_ONCE(jiffies); cputime_t delta, other; + /* + * Unlike tick based timing, vtime based timing never has lost + * ticks, and no need for steal time accounting to make up for + * lost ticks. Vtime accounts a rounded version of actual + * elapsed time. Limit account_other_time to prevent rounding + * errors from causing elapsed vtime to go negative. + */ delta = jiffies_to_cputime(now - tsk->vtime_snap); other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 555670a5143c..32bf6f75a8fe 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1496,6 +1496,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; + bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1506,6 +1507,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) spin_lock(&base->lock); nextevt = __next_timer_interrupt(base); + is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); base->next_expiry = nextevt; /* * We have a fresh next event. Check whether we can forward the base: @@ -1519,7 +1521,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - expires = basem + (nextevt - basej) * TICK_NSEC; + if (!is_max_delta) + expires = basem + (nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle: */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b9aa1b0b38b0..87e11d8ad536 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1448,6 +1448,7 @@ static void dissolve_free_huge_page(struct page *page) list_del(&page->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; + h->max_huge_pages--; update_and_free_page(h, page); } spin_unlock(&hugetlb_lock); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index b6728a33a4ac..baabaad4a4aa 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -217,11 +217,8 @@ void quarantine_reduce(void) new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) / QUARANTINE_FRACTION; percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus(); - if (WARN_ONCE(new_quarantine_size < percpu_quarantines, - "Too little memory, disabling global KASAN quarantine.\n")) - new_quarantine_size = 0; - else - new_quarantine_size -= percpu_quarantines; + new_quarantine_size = (new_quarantine_size < percpu_quarantines) ? + 0 : new_quarantine_size - percpu_quarantines; WRITE_ONCE(quarantine_size, new_quarantine_size); last = global_quarantine.head; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e74d7080ec9e..2ff0289ad061 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4077,14 +4077,32 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); -static void mem_cgroup_id_get(struct mem_cgroup *memcg) +static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { - atomic_inc(&memcg->id.ref); + atomic_add(n, &memcg->id.ref); } -static void mem_cgroup_id_put(struct mem_cgroup *memcg) +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) { - if (atomic_dec_and_test(&memcg->id.ref)) { + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + +static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) +{ + if (atomic_sub_and_test(n, &memcg->id.ref)) { idr_remove(&mem_cgroup_idr, memcg->id.id); memcg->id.id = 0; @@ -4093,6 +4111,16 @@ static void mem_cgroup_id_put(struct mem_cgroup *memcg) } } +static inline void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + mem_cgroup_id_get_many(memcg, 1); +} + +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + mem_cgroup_id_put_many(memcg, 1); +} + /** * mem_cgroup_from_id - look up a memcg from a memcg id * @id: the memcg id to look up @@ -4727,6 +4755,8 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.from)) page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + mem_cgroup_id_put_many(mc.from, mc.moved_swap); + /* * we charged both to->memory and to->memsw, so we * should uncharge to->memory. @@ -4734,9 +4764,9 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - css_put_many(&mc.from->css, mc.moved_swap); + mem_cgroup_id_get_many(mc.to, mc.moved_swap); + css_put_many(&mc.to->css, mc.moved_swap); - /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } memcg_oom_recover(from); @@ -5800,7 +5830,7 @@ subsys_initcall(mem_cgroup_init); */ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg, *swap_memcg; unsigned short oldid; VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5815,16 +5845,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; - mem_cgroup_id_get(memcg); - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + /* + * In case the memcg owning these pages has been offlined and doesn't + * have an ID allocated to it anymore, charge the closest online + * ancestor for the swap instead and transfer the memory+swap charge. + */ + swap_memcg = mem_cgroup_id_get_online(memcg); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg)); VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(memcg, true); + mem_cgroup_swap_statistics(swap_memcg, true); page->mem_cgroup = NULL; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, 1); + if (memcg != swap_memcg) { + if (!mem_cgroup_is_root(swap_memcg)) + page_counter_charge(&swap_memcg->memsw, 1); + page_counter_uncharge(&memcg->memsw, 1); + } + /* * Interrupts should be disabled here because the caller holds the * mapping->tree_lock lock which is taken with interrupts-off. It is @@ -5863,11 +5904,14 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!memcg) return 0; - if (!mem_cgroup_is_root(memcg) && - !page_counter_try_charge(&memcg->swap, 1, &counter)) - return -ENOMEM; + memcg = mem_cgroup_id_get_online(memcg); + + if (!mem_cgroup_is_root(memcg) && + !page_counter_try_charge(&memcg->swap, 1, &counter)) { + mem_cgroup_id_put(memcg); + return -ENOMEM; + } - mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3894b65b1555..41266dc29f33 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1219,6 +1219,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) /* init node's zones as empty zones, we don't have any present pages.*/ free_area_init_node(nid, zones_size, start_pfn, zholes_size); + pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); /* * The node we allocated has no zone fallback lists. For avoiding @@ -1249,6 +1250,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) static void rollback_node_hotadd(int nid, pg_data_t *pgdat) { arch_refresh_nodedata(nid, NULL); + free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); return; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7d0a275df822..d53a9aa00977 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -764,7 +764,7 @@ bool task_will_free_mem(struct task_struct *task) { struct mm_struct *mm = task->mm; struct task_struct *p; - bool ret; + bool ret = true; /* * Skip tasks without mm because it might have passed its exit_mm and diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ee744fa3b93d..3fbe73a6fe4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4060,7 +4060,7 @@ long si_mem_available(void) int lru; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_page_state(NR_LRU_BASE + lru); + pages[lru] = global_node_page_state(NR_LRU_BASE + lru); for_each_zone(zone) wmark_low += zone->watermark[WMARK_LOW]; @@ -4757,6 +4757,8 @@ int local_memory_node(int node) } #endif +static void setup_min_unmapped_ratio(void); +static void setup_min_slab_ratio(void); #else /* CONFIG_NUMA */ static void set_zonelist_order(void) @@ -5878,9 +5880,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) zone->managed_pages = is_highmem_idx(j) ? realsize : freesize; #ifdef CONFIG_NUMA zone->node = nid; - pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio) - / 100; - pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; zone->zone_pgdat = pgdat; @@ -6801,6 +6800,12 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); + +#ifdef CONFIG_NUMA + setup_min_unmapped_ratio(); + setup_min_slab_ratio(); +#endif + return 0; } core_initcall(init_per_zone_wmark_min) @@ -6842,43 +6847,58 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, } #ifdef CONFIG_NUMA -int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static void setup_min_unmapped_ratio(void) { - struct pglist_data *pgdat; + pg_data_t *pgdat; struct zone *zone; - int rc; - - rc = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (rc) - return rc; for_each_online_pgdat(pgdat) - pgdat->min_slab_pages = 0; + pgdat->min_unmapped_pages = 0; for_each_zone(zone) zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages * sysctl_min_unmapped_ratio) / 100; - return 0; } -int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, + +int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - struct pglist_data *pgdat; - struct zone *zone; int rc; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; + setup_min_unmapped_ratio(); + + return 0; +} + +static void setup_min_slab_ratio(void) +{ + pg_data_t *pgdat; + struct zone *zone; + for_each_online_pgdat(pgdat) pgdat->min_slab_pages = 0; for_each_zone(zone) zone->zone_pgdat->min_slab_pages += (zone->managed_pages * sysctl_min_slab_ratio) / 100; +} + +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + setup_min_slab_ratio(); + return 0; } #endif diff --git a/mm/rmap.c b/mm/rmap.c index 709bc83703b1..1ef36404e7b2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1284,8 +1284,9 @@ void page_add_file_rmap(struct page *page, bool compound) VM_BUG_ON_PAGE(!PageSwapBacked(page), page); __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); } else { - if (PageTransCompound(page)) { - VM_BUG_ON_PAGE(!PageLocked(page), page); + if (PageTransCompound(page) && page_mapping(page)) { + VM_WARN_ON_ONCE(!PageLocked(page)); + SetPageDoubleMap(compound_head(page)); if (PageMlocked(page)) clear_page_mlock(compound_head(page)); @@ -1303,7 +1304,7 @@ static void page_remove_file_rmap(struct page *page, bool compound) { int i, nr = 1; - VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); + VM_BUG_ON_PAGE(compound && !PageHead(page), page); lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ diff --git a/mm/shmem.c b/mm/shmem.c index 7f7748a0f9e1..fd8b2b5741b1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3975,7 +3975,9 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute shmem_enabled_attr = __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */ +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE bool shmem_huge_enabled(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); @@ -4006,7 +4008,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma) return false; } } -#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */ +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */ #else /* !CONFIG_SHMEM */ diff --git a/mm/slub.c b/mm/slub.c index cead06394e9e..9adae58462f8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3629,6 +3629,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { + LIST_HEAD(discard); struct page *page, *h; BUG_ON(irqs_disabled()); @@ -3636,13 +3637,16 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { remove_partial(n, page); - discard_slab(s, page); + list_add(&page->lru, &discard); } else { list_slab_objects(s, page, "Objects remaining in %s on __kmem_cache_shutdown()"); } } spin_unlock_irq(&n->list_lock); + + list_for_each_entry_safe(page, h, &discard, lru) + discard_slab(s, page); } /* diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 4acb1d5417aa..f24b25c25106 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -507,8 +507,8 @@ err_out: /* wakeup anybody waiting for slots to pin pages */ wake_up(&vp_wq); } - kfree(in_pages); - kfree(out_pages); + kvfree(in_pages); + kvfree(out_pages); return err; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c83326c5ba58..ef34a02719d7 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -574,7 +574,7 @@ static void complete_generic_request(struct ceph_mon_generic_request *req) put_generic_request(req); } -void cancel_generic_request(struct ceph_mon_generic_request *req) +static void cancel_generic_request(struct ceph_mon_generic_request *req) { struct ceph_mon_client *monc = req->monc; struct ceph_mon_generic_request *lookup_req; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b5ec09612ff7..a97e7b506612 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -4220,7 +4220,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); - if (!pages) { + if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c index ca53c8319209..22fb96efcf34 100644 --- a/net/ceph/string_table.c +++ b/net/ceph/string_table.c @@ -84,12 +84,6 @@ retry: } EXPORT_SYMBOL(ceph_find_or_create_string); -static void ceph_free_string(struct rcu_head *head) -{ - struct ceph_string *cs = container_of(head, struct ceph_string, rcu); - kfree(cs); -} - void ceph_release_string(struct kref *ref) { struct ceph_string *cs = container_of(ref, struct ceph_string, kref); @@ -101,7 +95,7 @@ void ceph_release_string(struct kref *ref) } spin_unlock(&string_tree_lock); - call_rcu(&cs->rcu, ceph_free_string); + kfree_rcu(cs, rcu); } EXPORT_SYMBOL(ceph_release_string); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23c8e7c39656..976c7812bbd5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; + if (auth && pos->auth->service != auth->service) + continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; @@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) struct gss_upcall_msg *old; spin_lock(&pipe->lock); - old = __gss_find_upcall(pipe, gss_msg->uid); + old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { atomic_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); @@ -714,7 +716,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid); + gss_msg = __gss_find_upcall(pipe, uid, NULL); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cb49898a5a58..7f79fb7dc6a0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2638,6 +2638,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; + unsigned long reconnect_timeout; unsigned char resvport; int ret = 0; @@ -2649,6 +2650,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); xprt = xprt_create_transport(xprtargs); @@ -2657,6 +2659,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->max_reconnect_timeout = reconnect_timeout; rpc_xprt_switch_set_roundrobin(xps); if (setup) { @@ -2673,6 +2676,27 @@ out_put_switch: } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); +static int +rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data) +{ + unsigned long timeout = *((unsigned long *)data); + + if (timeout < xprt->max_reconnect_timeout) + xprt->max_reconnect_timeout = timeout; + return 0; +} + +void +rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo) +{ + rpc_clnt_iterate_for_each_xprt(clnt, + rpc_xprt_cap_max_reconnect_timeout, + &timeo); +} +EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8313960cac52..ea244b29138b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,6 +680,20 @@ out: spin_unlock_bh(&xprt->transport_lock); } +static bool +xprt_has_timer(const struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + +static void +xprt_schedule_autodisconnect(struct rpc_xprt *xprt) + __must_hold(&xprt->transport_lock) +{ + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); +} + static void xprt_init_autodisconnect(unsigned long data) { @@ -688,6 +702,8 @@ xprt_init_autodisconnect(unsigned long data) spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) goto out_abort; + /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ + xprt->last_used = jiffies; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); @@ -725,6 +741,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) goto out; xprt->snd_task =NULL; xprt->ops->release_xprt(xprt, NULL); + xprt_schedule_autodisconnect(xprt); out: spin_unlock_bh(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); @@ -888,11 +905,6 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static inline int xprt_has_timer(struct rpc_xprt *xprt) -{ - return xprt->idle_timeout != 0; -} - /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1280,9 +1292,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) - mod_timer(&xprt->timer, - xprt->last_used + xprt->idle_timeout); + xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); if (req->rq_buffer) xprt->ops->buf_free(req->rq_buffer); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 111767ab124a..8ede3bc52481 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -177,7 +177,6 @@ static struct ctl_table sunrpc_table[] = { * increase over time if the server is down or not responding. */ #define XS_TCP_INIT_REEST_TO (3U * HZ) -#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ) /* * TCP idle timeout; client drops the transport socket if it is idle @@ -2173,6 +2172,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); + + xprt->stat.connect_start = jiffies; } static void xs_udp_setup_socket(struct work_struct *work) @@ -2236,6 +2237,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) unsigned int keepcnt = xprt->timeout->to_retries + 1; unsigned int opt_on = 1; unsigned int timeo; + unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* TCP Keepalive options */ kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, @@ -2247,6 +2249,16 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, (char *)&keepcnt, sizeof(keepcnt)); + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, + (char *)&addr_pref, sizeof(addr_pref)); + /* TCP user timeout (see RFC5482) */ timeo = jiffies_to_msecs(xprt->timeout->to_initval) * (xprt->timeout->to_retries + 1); @@ -2295,6 +2307,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + break; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; } out: return ret; @@ -2369,6 +2385,25 @@ out: xprt_wake_pending_tasks(xprt, status); } +static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt) +{ + unsigned long start, now = jiffies; + + start = xprt->stat.connect_start + xprt->reestablish_timeout; + if (time_after(start, now)) + return start - now; + return 0; +} + +static void xs_reconnect_backoff(struct rpc_xprt *xprt) +{ + xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout > xprt->max_reconnect_timeout) + xprt->reestablish_timeout = xprt->max_reconnect_timeout; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2386,6 +2421,7 @@ out: static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + unsigned long delay = 0; WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); @@ -2397,19 +2433,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) /* Start by resetting any existing state */ xs_reset_transport(transport); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, - xprt->reestablish_timeout); - xprt->reestablish_timeout <<= 1; - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) - xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; - } else { + delay = xs_reconnect_delay(xprt); + xs_reconnect_backoff(xprt); + + } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, 0); - } + + queue_delayed_work(xprtiod_workqueue, + &transport->connect_worker, + delay); } /** @@ -2961,6 +2993,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->ops = &xs_tcp_ops; xprt->timeout = &xs_tcp_default_timeout; + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn); INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket); diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 122fcdaf42c8..49a00d54b835 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -432,7 +432,7 @@ foreach my $file (@ARGV) { die "$P: file '${file}' not found\n"; } } - if ($from_filename || vcs_file_exists($file)) { + if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) { $file =~ s/^\Q${cur_path}\E//; #strip any absolute path $file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree push(@files, $file); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 89dacf9b4e6c..160c7f713722 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -906,20 +906,23 @@ static int azx_resume(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; struct hda_intel *hda; + struct hdac_bus *bus; if (!card) return 0; chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed || !chip->running) return 0; - if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL - && hda->need_i915_power) { - snd_hdac_display_power(azx_bus(chip), true); - snd_hdac_i915_set_bclk(azx_bus(chip)); + if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) + snd_hdac_i915_set_bclk(bus); } + if (chip->msi) if (pci_enable_msi(pci) < 0) chip->msi = 0; @@ -929,6 +932,11 @@ static int azx_resume(struct device *dev) hda_intel_init_chip(chip, true); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); @@ -1008,6 +1016,7 @@ static int azx_runtime_resume(struct device *dev) chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed) return 0; @@ -1015,15 +1024,9 @@ static int azx_runtime_resume(struct device *dev) return 0; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { - bus = azx_bus(chip); - if (hda->need_i915_power) { - snd_hdac_display_power(bus, true); + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) snd_hdac_i915_set_bclk(bus); - } else { - /* toggle codec wakeup bit for STATESTS read */ - snd_hdac_set_codec_wakeup(bus, true); - snd_hdac_set_codec_wakeup(bus, false); - } } /* Read STATESTS before controller reset */ @@ -1043,6 +1046,11 @@ static int azx_runtime_resume(struct device *dev) azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + trace_azx_runtime_resume(chip); return 0; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 6adde457b602..6cf1f3597455 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1128,6 +1128,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) { /* devices which do not support reading the sample rate. */ switch (chip->usb_id) { + case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */ case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */ @@ -1138,6 +1139,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ + case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..92a8308b96f6 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -225,7 +225,6 @@ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -301,10 +300,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +307,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif - +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 911e9358ceb1..85599ad4d024 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,5 +56,7 @@ #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK17 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 4916144e3c42..fac9a5c0abe9 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,5 +99,7 @@ #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 +#define REQUIRED_MASK17 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 5b15d94a33f8..37fee272618f 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -78,7 +78,6 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 -#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -127,8 +126,7 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" }, \ - { EXIT_REASON_PCOMMIT, "PCOMMIT" } + { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 406459b935a2..da218fec6056 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { @@ -93,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -313,6 +315,66 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; @@ -347,9 +409,11 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure @@ -386,4 +450,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 736da44596e4..b303bcdd8ed1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -176,10 +176,18 @@ Each probe argument follows below syntax. 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters. -'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail) On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. +TYPES +----- +Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe. +String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is; + + b@/ + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 1f6c70594f0f..053bbbd84ece 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,8 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags. - Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, + callindent. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index c6d0f91731a1..8d4dc97d80ba 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 -bool arch__prefers_symtab(void) -{ - return true; -} #ifdef HAVE_LIBELF_SUPPORT void arch__sym_update(struct symbol *s, GElf_Sym *sym) @@ -100,4 +96,27 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, tev->point.offset += lep_offset; } } + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs) +{ + struct probe_trace_event *tev; + struct map *map; + struct symbol *sym = NULL; + struct rb_node *tmp; + int i = 0; + + map = get_target_map(pev->target, pev->uprobes); + if (!map || map__load(map, NULL) < 0) + return; + + for (i = 0; i < ntevs; i++) { + tev = &pev->tevs[i]; + map__for_each_symbol(map, sym, tmp) { + if (map->unmap_ip(map, sym->start) == tev->point.address) + arch__fix_tev_from_maps(pev, tev, map, sym); + } + } +} + #endif diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 971ff91b16cb..9c640a8081c7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2116,7 +2116,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "callindent", parse_output_fields), + "bpf-output,callindent", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0c16d20d7e32..3c7452b39f57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(bool close_counters) +static void read_counters(void) { struct perf_evsel *counter; @@ -341,11 +341,6 @@ static void read_counters(bool close_counters) if (perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); - - if (close_counters) { - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } } } @@ -353,7 +348,7 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(false); + read_counters(); clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); @@ -380,6 +375,17 @@ static void enable_counters(void) perf_evlist__enable(evsel_list); } +static void disable_counters(void) +{ + /* + * If we don't have tracee (attaching to task or cpu), counters may + * still be running. To get accurate group ratios, we must stop groups + * from counting before reading their constituent counters. + */ + if (!target__none(&target)) + perf_evlist__disable(evsel_list); +} + static volatile int workload_exec_errno; /* @@ -657,11 +663,20 @@ try_again: } } + disable_counters(); + t1 = rdclock(); update_stats(&walltime_nsecs_stats, t1 - t0); - read_counters(true); + /* + * Closing a group leader splits the group, and as we only disable + * group leaders, results in remaining events becoming enabled. To + * avoid arbitrary skew, we must read all counters before closing any + * group leaders. + */ + read_counters(); + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 953dc1ab2ed7..28733962cd80 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module) module = "kernel"; for (pos = maps__first(maps); pos; pos = map__next(pos)) { + /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, - pos->dso->short_name_len - 2) == 0) { + pos->dso->short_name_len - 2) == 0 && + module[pos->dso->short_name_len - 2] == '\0') { return pos; } } return NULL; } -static struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, bool user) { /* Init maps of given executable or kernel */ if (user) @@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (uprobes) address = sym->start; else - address = map->unmap_ip(map, sym->start); + address = map->unmap_ip(map, sym->start) - map->reloc; break; } if (!address) { @@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -/* Post processing the probe events */ -static int post_process_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *module, - bool uprobe) +static int +post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, + int ntevs) { struct ref_reloc_sym *reloc_sym; char *tmp; int i, skipped = 0; - if (uprobe) - return add_exec_to_probe_trace_events(tevs, ntevs, module); - - /* Note that currently ref_reloc_sym based probe is not for drivers */ - if (module) - return add_module_to_probe_trace_events(tevs, ntevs, module); - reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, return skipped; } +void __weak +arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused, + int ntevs __maybe_unused) +{ +} + +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) +{ + int ret; + + if (uprobe) + ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + else if (module) + /* Currently ref_reloc_sym based probe is not for drivers */ + ret = add_module_to_probe_trace_events(tevs, ntevs, module); + else + ret = post_process_kernel_probe_trace_events(tevs, ntevs); + + if (ret >= 0) + arch__post_process_probe_trace_events(pev, ntevs); + + return ret; +} + /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) @@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("Found %d probe_trace_events.\n", ntevs); - ret = post_process_probe_trace_events(*tevs, ntevs, + ret = post_process_probe_trace_events(pev, *tevs, ntevs, pev->target, pev->uprobes); if (ret < 0 || ret == ntevs) { clear_probe_trace_events(*tevs, ntevs); @@ -2936,8 +2958,6 @@ errout: return err; } -bool __weak arch__prefers_symtab(void) { return false; } - /* Concatinate two arrays */ static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) { @@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */ return ret == 0 ? -ENOENT : ret; /* Found in probe cache */ - if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { - ret = find_probe_trace_events_from_map(pev, tevs); - if (ret > 0) - return ret; /* Found in symbol table */ - } - /* Convert perf_probe_event with debuginfo */ ret = try_to_find_probe_trace_events(pev, tevs); if (ret != 0) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e18ea9fe6385..f4f45db77c1c 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); int show_available_funcs(const char *module, struct strfilter *filter, bool user); -bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); @@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...) int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); +struct map *get_target_map(const char *target, bool user); + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs); + #endif /*_PROBE_EVENT_H */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index f2d9ff064e2d..5c290c682afe 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; + char sign; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0) { + if (cast && strcmp(cast, "string") != 0 && + strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ + /* and respect signedness cast */ tvar->type = strdup(cast); return (tvar->type == NULL) ? -ENOMEM : 0; } @@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + if (cast && (strcmp(cast, "u") == 0)) + sign = 'u'; + else if (cast && (strcmp(cast, "s") == 0)) + sign = 's'; + else + sign = die_is_signed_type(&type) ? 's' : 'u'; + ret = dwarf_bytesize(&type); if (ret <= 0) /* No size ... try to use default type */ @@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(&type), MAX_BASIC_TYPE_BITS); ret = MAX_BASIC_TYPE_BITS; } - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); + ret = snprintf(buf, 16, "%c%d", sign, ret); formatted: if (ret < 0 || ret >= 16) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 947d21f38398..3d3cb8392c86 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he) } else { pevent_event_info(&seq, evsel->tp_format, &rec); } - return seq.buffer; + /* + * Trim the buffer, it starts at 4KB and we're not going to + * add anything more to this buffer. + */ + return realloc(seq.buffer, seq.len + 1); } static int64_t diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 5404efa578a3..dd48f421844c 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -13,6 +13,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include +#include #include #include #include @@ -1474,6 +1475,7 @@ static int nfit_test_probe(struct platform_device *pdev) if (nfit_test->setup != nfit_test0_setup) return 0; + flush_work(&acpi_desc->work); nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 3c40c9d0e6c7..1cc6d64c39b7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,7 +8,7 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) +CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) export CFLAGS diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index fb4b0a79a950..83777c1cbae0 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -73,12 +73,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) int i, vcpu_lock_idx = -1, ret; struct kvm_vcpu *vcpu; - mutex_lock(&kvm->lock); - - if (irqchip_in_kernel(kvm)) { - ret = -EEXIST; - goto out; - } + if (irqchip_in_kernel(kvm)) + return -EEXIST; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, @@ -87,10 +83,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && - !kvm_vgic_global_state.can_emulate_gicv2) { - ret = -ENODEV; - goto out; - } + !kvm_vgic_global_state.can_emulate_gicv2) + return -ENODEV; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the @@ -138,9 +132,6 @@ out_unlock: vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&vcpu->mutex); } - -out: - mutex_unlock(&kvm->lock); return ret; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cc081ccfcaa3..195078225aa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -696,6 +696,11 @@ static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; + /* + * We do not need to take the kvm->lock here, because nobody else + * has a reference to the struct kvm at this point and therefore + * cannot access the devices list anyhow. + */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); @@ -2832,19 +2837,28 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->ops = ops; dev->kvm = kvm; + mutex_lock(&kvm->lock); ret = ops->create(dev, cd->type); if (ret < 0) { + mutex_unlock(&kvm->lock); kfree(dev); return ret; } + list_add(&dev->vm_node, &kvm->devices); + mutex_unlock(&kvm->lock); + + if (ops->init) + ops->init(dev); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { ops->destroy(dev); + mutex_lock(&kvm->lock); + list_del(&dev->vm_node); + mutex_unlock(&kvm->lock); return ret; } - list_add(&dev->vm_node, &kvm->devices); kvm_get_kvm(kvm); cd->fd = ret; return 0;