diff options
581 files changed, 6784 insertions, 3282 deletions
@@ -99,6 +99,8 @@ Linas Vepstas <linas@austin.ibm.com> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> Mark Brown <broonie@sirena.org.uk> +Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> +Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Matthieu CASTET <castet.matthieu@free.fr> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br> Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com> @@ -171,6 +173,7 @@ Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> Takashi YOSHII <takashi.yoshii.zj@renesas.com> +Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> Gustavo Padovan <gustavo@las.ic.unicamp.br> Gustavo Padovan <padovan@profusion.mobi> diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt index b7fa3b97986d..a339dbb15493 100644 --- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt +++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt @@ -44,13 +44,19 @@ Hip05 Example (note that Hip06 is the same except compatible): }; HiSilicon Hip06/Hip07 PCIe host bridge DT (almost-ECAM) description. + +Some BIOSes place the host controller in a mode where it is ECAM +compliant for all devices other than the root complex. In such cases, +the host controller should be described as below. + The properties and their meanings are identical to those described in host-generic-pci.txt except as listed below. Properties of the host controller node that differ from host-generic-pci.txt: -- compatible : Must be "hisilicon,pcie-almost-ecam" +- compatible : Must be "hisilicon,hip06-pcie-ecam", or + "hisilicon,hip07-pcie-ecam" - reg : Two entries: First the ECAM configuration space for any other bus underneath the root bus. Second, the base @@ -59,7 +65,7 @@ host-generic-pci.txt: Example: pcie0: pcie@a0090000 { - compatible = "hisilicon,pcie-almost-ecam"; + compatible = "hisilicon,hip06-pcie-ecam"; reg = <0 0xb0000000 0 0x2000000>, /* ECAM configuration space */ <0 0xa0090000 0 0x10000>; /* host bridge registers */ bus-range = <0 31>; diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index fdcfdd79682a..fe25787ff6d4 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -58,8 +58,7 @@ prototypes: int (*permission) (struct inode *, int, unsigned int); int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct dentry *, struct kstat *, - u32, unsigned int); + int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); void (*update_time)(struct inode *, struct timespec *, int); diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 95280079c0b3..5fb17f49f7a2 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -600,3 +600,9 @@ in your dentry operations instead. [recommended] ->readlink is optional for symlinks. Don't set, unless filesystem needs to fake something for readlink(2). +-- +[mandatory] + ->getattr() is now passed a struct path rather than a vfsmount and + dentry separately, and it now has request_mask and query_flags arguments + to specify the fields and sync type requested by statx. Filesystems not + supporting any statx-specific features may ignore the new arguments. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 569211703721..94dd27ef4a76 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -382,8 +382,7 @@ struct inode_operations { int (*permission) (struct inode *, int); int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct dentry *, struct kstat *, - u32, unsigned int); + int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt index 54bd5faa8782..f2af35f6d6b2 100644 --- a/Documentation/pinctrl.txt +++ b/Documentation/pinctrl.txt @@ -77,9 +77,15 @@ static struct pinctrl_desc foo_desc = { int __init foo_probe(void) { + int error; + struct pinctrl_dev *pctl; - return pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl); + error = pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl); + if (error) + return error; + + return pinctrl_enable(pctl); } To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 11ec2d93a5e0..61e9c78bd6d1 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -124,7 +124,7 @@ specified in the following format in the sign-off area: .. code-block:: none - Cc: <stable@vger.kernel.org> # 3.3.x- + Cc: <stable@vger.kernel.org> # 3.3.x The tag has the meaning of: diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt index 76e61c883347..b2f60ca8b60c 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic.txt +++ b/Documentation/virtual/kvm/devices/arm-vgic.txt @@ -83,6 +83,12 @@ Groups: Bits for undefined preemption levels are RAZ/WI. + For historical reasons and to provide ABI compatibility with userspace we + export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask + field in the lower 5 bits of a word, meaning that userspace must always + use the lower 5 bits to communicate with the KVM device and must shift the + value left by 3 places to obtain the actual priority mask level. + Limitations: - Priorities are not implemented, and registers are RAZ/WI - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2. diff --git a/MAINTAINERS b/MAINTAINERS index 1b0a87ffffab..38d3e4ed7208 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2585,12 +2585,26 @@ F: include/uapi/linux/if_bonding.h BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> +M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org S: Supported +F: arch/x86/net/bpf_jit* +F: Documentation/networking/filter.txt +F: include/linux/bpf* +F: include/linux/filter.h +F: include/uapi/linux/bpf* +F: include/uapi/linux/filter.h F: kernel/bpf/ -F: tools/testing/selftests/bpf/ +F: kernel/trace/bpf_trace.c F: lib/test_bpf.c +F: net/bpf/ +F: net/core/filter.c +F: net/sched/act_bpf.c +F: net/sched/cls_bpf.c +F: samples/bpf/ +F: tools/net/bpf* +F: tools/testing/selftests/bpf/ BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> @@ -4117,14 +4131,13 @@ F: drivers/block/drbd/ F: lib/lru_cache.c F: Documentation/blockdev/drbd/ -DRIVER CORE, KOBJECTS, DEBUGFS, KERNFS AND SYSFS +DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git S: Supported F: Documentation/kobject.txt F: drivers/base/ F: fs/debugfs/ -F: fs/kernfs/ F: fs/sysfs/ F: include/linux/debugfs.h F: include/linux/kobj* @@ -4928,6 +4941,7 @@ F: include/linux/netfilter_bridge/ F: net/bridge/ ETHERNET PHY LIBRARY +M: Andrew Lunn <andrew@lunn.ch> M: Florian Fainelli <f.fainelli@gmail.com> L: netdev@vger.kernel.org S: Maintained @@ -7089,9 +7103,9 @@ S: Maintained F: fs/autofs4/ KERNEL BUILD + files below scripts/ (unless maintained elsewhere) +M: Masahiro Yamada <yamada.masahiro@socionext.com> M: Michal Marek <mmarek@suse.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes +T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git L: linux-kbuild@vger.kernel.org S: Maintained F: Documentation/kbuild/ @@ -7208,6 +7222,14 @@ F: arch/mips/include/uapi/asm/kvm* F: arch/mips/include/asm/kvm* F: arch/mips/kvm/ +KERNFS +M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +M: Tejun Heo <tj@kernel.org> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git +S: Supported +F: include/linux/kernfs.h +F: fs/kernfs/ + KEXEC M: Eric Biederman <ebiederm@xmission.com> W: http://kernel.org/pub/linux/utils/kernel/kexec/ @@ -8753,6 +8775,7 @@ W: http://www.linuxfoundation.org/en/Net Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git +B: mailto:netdev@vger.kernel.org S: Maintained F: net/ F: include/net/ @@ -10814,6 +10837,7 @@ F: drivers/s390/block/dasd* F: block/partitions/ibm.c S390 NETWORK DRIVERS +M: Julian Wiedmann <jwi@linux.vnet.ibm.com> M: Ursula Braun <ubraun@linux.vnet.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ @@ -10844,6 +10868,7 @@ S: Supported F: drivers/s390/scsi/zfcp_* S390 IUCV NETWORK LAYER +M: Julian Wiedmann <jwi@linux.vnet.ibm.com> M: Ursula Braun <ubraun@linux.vnet.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ @@ -12454,7 +12479,6 @@ F: drivers/clk/ti/ F: include/linux/clk/ti.h TI ETHERNET SWITCH DRIVER (CPSW) -M: Mugunthan V N <mugunthanvnm@ti.com> R: Grygorii Strashko <grygorii.strashko@ti.com> L: linux-omap@vger.kernel.org L: netdev@vger.kernel.org @@ -13295,7 +13319,7 @@ F: drivers/virtio/ F: tools/virtio/ F: drivers/net/virtio_net.c F: drivers/block/virtio_blk.c -F: include/linux/virtio_*.h +F: include/linux/virtio*.h F: include/uapi/linux/virtio_*.h F: drivers/crypto/virtio/ @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc8 NAME = Fearless Coyote # *DOCUMENTATION* @@ -372,7 +372,7 @@ LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = LDFLAGS_vmlinux = -CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized +CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,) CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) @@ -653,6 +653,12 @@ KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0409, \ # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) +# check for 'asm goto' +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y) + KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO + KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO +endif + include scripts/Makefile.gcc-plugins ifdef CONFIG_READABLE_ASM @@ -798,12 +804,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) # use the deterministic mode of AR if available KBUILD_ARFLAGS := $(call ar-option,D) -# check for 'asm goto' -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y) - KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO - KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO -endif - include scripts/Makefile.kasan include scripts/Makefile.extrawarn include scripts/Makefile.ubsan diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 0b961093ca5c..6d76e528ab8f 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1290,7 +1290,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) /* copy relevant bits of struct timex. */ if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) || copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) - - offsetof(struct timex32, time))) + offsetof(struct timex32, tick))) return -EFAULT; ret = do_adjtimex(&txc); diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index c9f30f4763ab..5d7fb3e7cb97 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -406,6 +406,14 @@ config ARC_HAS_DIV_REM bool "Insn: div, divu, rem, remu" default y +config ARC_HAS_ACCL_REGS + bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)" + default n + help + Depending on the configuration, CPU can contain accumulator reg-pair + (also referred to as r58:r59). These can also be used by gcc as GPR so + kernel needs to save/restore per process + endif # ISA_ARCV2 endmenu # "ARC CPU Configuration" diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index b65930a49589..54b54da6384c 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -17,10 +17,11 @@ #include <asm/barrier.h> #include <asm/smp.h> +#define ATOMIC_INIT(i) { (i) } + #ifndef CONFIG_ARC_PLAT_EZNPS #define atomic_read(v) READ_ONCE((v)->counter) -#define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_ARC_HAS_LLSC diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index aee1a77934cf..ac85380d14a4 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -16,6 +16,11 @@ ; ; Now manually save: r12, sp, fp, gp, r25 +#ifdef CONFIG_ARC_HAS_ACCL_REGS + PUSH r59 + PUSH r58 +#endif + PUSH r30 PUSH r12 @@ -75,6 +80,11 @@ POP r12 POP r30 +#ifdef CONFIG_ARC_HAS_ACCL_REGS + POP r58 + POP r59 +#endif + .endm /*------------------------------------------------------------------------*/ diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 47111d565a95..5297faa8a378 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -86,6 +86,10 @@ struct pt_regs { unsigned long r12, r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + unsigned long r58, r59; /* ACCL/ACCH used by FPU / DSP MPY */ +#endif + /*------- Below list auto saved by h/w -----------*/ unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index fa62404ba58f..fc8211f338ad 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -319,7 +319,8 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) static void arc_chk_core_config(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; - int fpu_enabled; + int saved = 0, present = 0; + char *opt_nm = NULL;; if (!cpu->extn.timer0) panic("Timer0 is not present!\n"); @@ -346,17 +347,28 @@ static void arc_chk_core_config(void) /* * FP hardware/software config sanity - * -If hardware contains DPFP, kernel needs to save/restore FPU state + * -If hardware present, kernel needs to save/restore FPU state * -If not, it will crash trying to save/restore the non-existant regs - * - * (only DPDP checked since SP has no arch visible regs) */ - fpu_enabled = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE); - if (cpu->extn.fpu_dp && !fpu_enabled) - pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n"); - else if (!cpu->extn.fpu_dp && fpu_enabled) - panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n"); + if (is_isa_arcompact()) { + opt_nm = "CONFIG_ARC_FPU_SAVE_RESTORE"; + saved = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE); + + /* only DPDP checked since SP has no arch visible regs */ + present = cpu->extn.fpu_dp; + } else { + opt_nm = "CONFIG_ARC_HAS_ACCL_REGS"; + saved = IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS); + + /* Accumulator Low:High pair (r58:59) present if DSP MPY or FPU */ + present = cpu->extn_mpy.dsp | cpu->extn.fpu_sp | cpu->extn.fpu_dp; + } + + if (present && !saved) + pr_warn("Enable %s for working apps\n", opt_nm); + else if (!present && saved) + panic("Disable %s, hardware NOT present\n", opt_nm); } /* diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi index efb5eae290a8..d42b98f15e8b 100644 --- a/arch/arm/boot/dts/am335x-baltos.dtsi +++ b/arch/arm/boot/dts/am335x-baltos.dtsi @@ -371,6 +371,8 @@ phy1: ethernet-phy@1 { reg = <7>; + eee-broken-100tx; + eee-broken-1000t; }; }; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 9e43c443738a..9ba4b18c0cb2 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -672,6 +672,7 @@ ti,non-removable; bus-width = <4>; cap-power-off-card; + keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc2_pins>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 2c9e56f4aac5..bbfb9d5a70a9 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -283,6 +283,7 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; + bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; linux,pci-domain = <0>; @@ -319,6 +320,7 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; + bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; linux,pci-domain = <1>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 8f9a69ca818c..efe53998c961 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -121,7 +121,7 @@ &i2c3 { clock-frequency = <400000>; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c64"; readonly; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi index 0467fb365bfc..306af6cadf26 100644 --- a/arch/arm/boot/dts/sun8i-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a33.dtsi @@ -66,12 +66,6 @@ opp-microvolt = <1200000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - - opp@1200000000 { - opp-hz = /bits/ 64 <1200000000>; - opp-microvolt = <1320000>; - clock-latency-ns = <244144>; /* 8 32k periods */ - }; }; cpus { @@ -81,16 +75,22 @@ operating-points-v2 = <&cpu0_opp_table>; }; + cpu@1 { + operating-points-v2 = <&cpu0_opp_table>; + }; + cpu@2 { compatible = "arm,cortex-a7"; device_type = "cpu"; reg = <2>; + operating-points-v2 = <&cpu0_opp_table>; }; cpu@3 { compatible = "arm,cortex-a7"; device_type = "cpu"; reg = <3>; + operating-points-v2 = <&cpu0_opp_table>; }; }; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 96dba7cd8be7..314eb6abe1ff 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1124,6 +1124,9 @@ static void cpu_hyp_reinit(void) if (__hyp_get_vectors() == hyp_default_vectors) cpu_init_hyp_mode(NULL); } + + if (vgic_present) + kvm_vgic_init_cpu_hardware(); } static void cpu_hyp_reset(void) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 962616fd4ddd..582a972371cf 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -292,11 +292,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) phys_addr_t addr = start, end = start + size; phys_addr_t next; + assert_spin_locked(&kvm->mmu_lock); pgd = kvm->arch.pgd + stage2_pgd_index(addr); do { next = stage2_pgd_addr_end(addr, end); if (!stage2_pgd_none(*pgd)) unmap_stage2_puds(kvm, pgd, addr, next); + /* + * If the range is too large, release the kvm->mmu_lock + * to prevent starvation and lockup detector warnings. + */ + if (next != end) + cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } @@ -803,6 +810,7 @@ void stage2_unmap_vm(struct kvm *kvm) int idx; idx = srcu_read_lock(&kvm->srcu); + down_read(¤t->mm->mmap_sem); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); @@ -810,6 +818,7 @@ void stage2_unmap_vm(struct kvm *kvm) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); srcu_read_unlock(&kvm->srcu, idx); } @@ -829,7 +838,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) if (kvm->arch.pgd == NULL) return; + spin_lock(&kvm->mmu_lock); unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + spin_unlock(&kvm->mmu_lock); + /* Free the HW pgd, one page at a time */ free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE); kvm->arch.pgd = NULL; @@ -1801,6 +1813,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, (KVM_PHYS_SIZE >> PAGE_SHIFT)) return -EFAULT; + down_read(¤t->mm->mmap_sem); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we can map @@ -1844,8 +1857,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) - return -EINVAL; + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + ret = -EINVAL; + goto out; + } ret = kvm_phys_addr_ioremap(kvm, gpa, pa, vm_end - vm_start, @@ -1857,7 +1872,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } while (hva < reg_end); if (change == KVM_MR_FLAGS_ONLY) - return ret; + goto out; spin_lock(&kvm->mmu_lock); if (ret) @@ -1865,6 +1880,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, else stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); +out: + up_read(¤t->mm->mmap_sem); return ret; } diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h index c4f2ace91ea2..3089d3bfa19b 100644 --- a/arch/arm/mach-omap2/common.h +++ b/arch/arm/mach-omap2/common.h @@ -270,6 +270,7 @@ extern const struct smp_operations omap4_smp_ops; extern int omap4_mpuss_init(void); extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state); extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state); +extern u32 omap4_get_cpu1_ns_pa_addr(void); #else static inline int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state) diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c index d3fb5661bb5d..433db6d0b073 100644 --- a/arch/arm/mach-omap2/omap-hotplug.c +++ b/arch/arm/mach-omap2/omap-hotplug.c @@ -50,7 +50,7 @@ void omap4_cpu_die(unsigned int cpu) omap4_hotplug_cpu(cpu, PWRDM_POWER_OFF); if (omap_secure_apis_support()) - boot_cpu = omap_read_auxcoreboot0(); + boot_cpu = omap_read_auxcoreboot0() >> 9; else boot_cpu = readl_relaxed(base + OMAP_AUX_CORE_BOOT_0) >> 5; diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index 113ab2dd2ee9..03ec6d307c82 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -64,6 +64,7 @@ #include "prm-regbits-44xx.h" static void __iomem *sar_base; +static u32 old_cpu1_ns_pa_addr; #if defined(CONFIG_PM) && defined(CONFIG_SMP) @@ -212,6 +213,11 @@ static void __init save_l2x0_context(void) {} #endif +u32 omap4_get_cpu1_ns_pa_addr(void) +{ + return old_cpu1_ns_pa_addr; +} + /** * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function * The purpose of this function is to manage low power programming @@ -460,22 +466,30 @@ int __init omap4_mpuss_init(void) void __init omap4_mpuss_early_init(void) { unsigned long startup_pa; + void __iomem *ns_pa_addr; - if (!(cpu_is_omap44xx() || soc_is_omap54xx())) + if (!(soc_is_omap44xx() || soc_is_omap54xx())) return; sar_base = omap4_get_sar_ram_base(); - if (cpu_is_omap443x()) + /* Save old NS_PA_ADDR for validity checks later on */ + if (soc_is_omap44xx()) + ns_pa_addr = sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET; + else + ns_pa_addr = sar_base + OMAP5_CPU1_WAKEUP_NS_PA_ADDR_OFFSET; + old_cpu1_ns_pa_addr = readl_relaxed(ns_pa_addr); + + if (soc_is_omap443x()) startup_pa = __pa_symbol(omap4_secondary_startup); - else if (cpu_is_omap446x()) + else if (soc_is_omap446x()) startup_pa = __pa_symbol(omap4460_secondary_startup); else if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE) startup_pa = __pa_symbol(omap5_secondary_hyp_startup); else startup_pa = __pa_symbol(omap5_secondary_startup); - if (cpu_is_omap44xx()) + if (soc_is_omap44xx()) writel_relaxed(startup_pa, sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET); else diff --git a/arch/arm/mach-omap2/omap-smc.S b/arch/arm/mach-omap2/omap-smc.S index fd90125bffc7..72506e6cf9e7 100644 --- a/arch/arm/mach-omap2/omap-smc.S +++ b/arch/arm/mach-omap2/omap-smc.S @@ -94,6 +94,5 @@ ENTRY(omap_read_auxcoreboot0) ldr r12, =0x103 dsb smc #0 - mov r0, r0, lsr #9 ldmfd sp!, {r2-r12, pc} ENDPROC(omap_read_auxcoreboot0) diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 003353b0b794..3faf454ba487 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -21,6 +21,7 @@ #include <linux/io.h> #include <linux/irqchip/arm-gic.h> +#include <asm/sections.h> #include <asm/smp_scu.h> #include <asm/virt.h> @@ -40,10 +41,14 @@ #define OMAP5_CORE_COUNT 0x2 +#define AUX_CORE_BOOT0_GP_RELEASE 0x020 +#define AUX_CORE_BOOT0_HS_RELEASE 0x200 + struct omap_smp_config { unsigned long cpu1_rstctrl_pa; void __iomem *cpu1_rstctrl_va; void __iomem *scu_base; + void __iomem *wakeupgen_base; void *startup_addr; }; @@ -140,7 +145,6 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) static struct clockdomain *cpu1_clkdm; static bool booted; static struct powerdomain *cpu1_pwrdm; - void __iomem *base = omap_get_wakeupgen_base(); /* * Set synchronisation state between this boot processor @@ -155,9 +159,11 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) * A barrier is added to ensure that write buffer is drained */ if (omap_secure_apis_support()) - omap_modify_auxcoreboot0(0x200, 0xfffffdff); + omap_modify_auxcoreboot0(AUX_CORE_BOOT0_HS_RELEASE, + 0xfffffdff); else - writel_relaxed(0x20, base + OMAP_AUX_CORE_BOOT_0); + writel_relaxed(AUX_CORE_BOOT0_GP_RELEASE, + cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_0); if (!cpu1_clkdm && !cpu1_pwrdm) { cpu1_clkdm = clkdm_lookup("mpu1_clkdm"); @@ -261,9 +267,72 @@ static void __init omap4_smp_init_cpus(void) set_cpu_possible(i, true); } +/* + * For now, just make sure the start-up address is not within the booting + * kernel space as that means we just overwrote whatever secondary_startup() + * code there was. + */ +static bool __init omap4_smp_cpu1_startup_valid(unsigned long addr) +{ + if ((addr >= __pa(PAGE_OFFSET)) && (addr <= __pa(__bss_start))) + return false; + + return true; +} + +/* + * We may need to reset CPU1 before configuring, otherwise kexec boot can end + * up trying to use old kernel startup address or suspend-resume will + * occasionally fail to bring up CPU1 on 4430 if CPU1 fails to enter deeper + * idle states. + */ +static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c) +{ + unsigned long cpu1_startup_pa, cpu1_ns_pa_addr; + bool needs_reset = false; + u32 released; + + if (omap_secure_apis_support()) + released = omap_read_auxcoreboot0() & AUX_CORE_BOOT0_HS_RELEASE; + else + released = readl_relaxed(cfg.wakeupgen_base + + OMAP_AUX_CORE_BOOT_0) & + AUX_CORE_BOOT0_GP_RELEASE; + if (released) { + pr_warn("smp: CPU1 not parked?\n"); + + return; + } + + cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base + + OMAP_AUX_CORE_BOOT_1); + cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr(); + + /* Did the configured secondary_startup() get overwritten? */ + if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa)) + needs_reset = true; + + /* + * If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a + * deeper idle state in WFI and will wake to an invalid address. + */ + if ((soc_is_omap44xx() || soc_is_omap54xx()) && + !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr)) + needs_reset = true; + + if (!needs_reset || !c->cpu1_rstctrl_va) + return; + + pr_info("smp: CPU1 parked within kernel, needs reset (0x%lx 0x%lx)\n", + cpu1_startup_pa, cpu1_ns_pa_addr); + + writel_relaxed(1, c->cpu1_rstctrl_va); + readl_relaxed(c->cpu1_rstctrl_va); + writel_relaxed(0, c->cpu1_rstctrl_va); +} + static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) { - void __iomem *base = omap_get_wakeupgen_base(); const struct omap_smp_config *c = NULL; if (soc_is_omap443x()) @@ -281,6 +350,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) /* Must preserve cfg.scu_base set earlier */ cfg.cpu1_rstctrl_pa = c->cpu1_rstctrl_pa; cfg.startup_addr = c->startup_addr; + cfg.wakeupgen_base = omap_get_wakeupgen_base(); if (soc_is_dra74x() || soc_is_omap54xx()) { if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE) @@ -299,15 +369,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) if (cfg.scu_base) scu_enable(cfg.scu_base); - /* - * Reset CPU1 before configuring, otherwise kexec will - * end up trying to use old kernel startup address. - */ - if (cfg.cpu1_rstctrl_va) { - writel_relaxed(1, cfg.cpu1_rstctrl_va); - readl_relaxed(cfg.cpu1_rstctrl_va); - writel_relaxed(0, cfg.cpu1_rstctrl_va); - } + omap4_smp_maybe_reset_cpu1(&cfg); /* * Write the address of secondary startup routine into the @@ -319,7 +381,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) omap_auxcoreboot_addr(__pa_symbol(cfg.startup_addr)); else writel_relaxed(__pa_symbol(cfg.startup_addr), - base + OMAP_AUX_CORE_BOOT_1); + cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_1); } const struct smp_operations omap4_smp_ops __initconst = { diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index e920dd83e443..f989145480c8 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -222,6 +222,14 @@ static int _omap_device_notifier_call(struct notifier_block *nb, dev_err(dev, "failed to idle\n"); } break; + case BUS_NOTIFY_BIND_DRIVER: + od = to_omap_device(pdev); + if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) && + pm_runtime_status_suspended(dev)) { + od->_driver_status = BUS_NOTIFY_BIND_DRIVER; + pm_runtime_set_active(dev); + } + break; case BUS_NOTIFY_ADD_DEVICE: if (pdev->dev.of_node) omap_device_build_from_dt(pdev); diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig index 633442ad4e4c..2a7bb6ccdcb7 100644 --- a/arch/arm/mach-orion5x/Kconfig +++ b/arch/arm/mach-orion5x/Kconfig @@ -6,6 +6,7 @@ menuconfig ARCH_ORION5X select GPIOLIB select MVEBU_MBUS select PCI + select PHYLIB if NETDEVICES select PLAT_ORION_LEGACY help Support for the following Marvell Orion 5x series SoCs: diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 63eabb06f9f1..475811f5383a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -935,13 +935,31 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); } +/* + * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems + * that the intention is to allow exporting memory allocated via the + * coherent DMA APIs through the dma_buf API, which only accepts a + * scattertable. This presents a couple of problems: + * 1. Not all memory allocated via the coherent DMA APIs is backed by + * a struct page + * 2. Passing coherent DMA memory into the streaming APIs is not allowed + * as we will try to flush the memory through a different alias to that + * actually being used (and the flushes are redundant.) + */ int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, unsigned long attrs) { - struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); + unsigned long pfn = dma_to_pfn(dev, handle); + struct page *page; int ret; + /* If the PFN is not valid, we do not have a struct page */ + if (!pfn_valid(pfn)) + return -ENXIO; + + page = pfn_to_page(pfn); + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); if (unlikely(ret)) return ret; diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 3b5c7aaf9c76..33a45bd96860 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -303,7 +303,10 @@ static inline void set_vbar(unsigned long val) */ static inline bool security_extensions_enabled(void) { - return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4); + /* Check CPUID Identification Scheme before ID_PFR1 read */ + if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) + return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4); + return 0; } static unsigned long __init setup_vectors_base(void) diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index 9255b6d67ba5..aff6994950ba 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -468,6 +468,7 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data, eth_data, &orion_ge11); } +#ifdef CONFIG_ARCH_ORION5X /***************************************************************************** * Ethernet switch ****************************************************************************/ @@ -480,6 +481,9 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d) struct mdio_board_info *bd; unsigned int i; + if (!IS_BUILTIN(CONFIG_PHYLIB)) + return; + for (i = 0; i < ARRAY_SIZE(d->port_names); i++) if (!strcmp(d->port_names[i], "cpu")) break; @@ -493,6 +497,7 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d) mdiobus_register_board_info(&orion_ge00_switch_board_info, 1); } +#endif /***************************************************************************** * I2C diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index b6dc9d838a9a..ad1f4e6a9e33 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -266,11 +266,20 @@ void __kprobes kprobe_handler(struct pt_regs *regs) #endif if (p) { - if (cur) { + if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) { + /* + * Probe hit but conditional execution check failed, + * so just skip the instruction and continue as if + * nothing had happened. + * In this case, we can skip recursing check too. + */ + singlestep_skip(p, regs); + } else if (cur) { /* Kprobe is pending, so we're recursing. */ switch (kcb->kprobe_status) { case KPROBE_HIT_ACTIVE: case KPROBE_HIT_SSDONE: + case KPROBE_HIT_SS: /* A pre- or post-handler probe got us here. */ kprobes_inc_nmissed_count(p); save_previous_kprobe(kcb); @@ -279,11 +288,16 @@ void __kprobes kprobe_handler(struct pt_regs *regs) singlestep(p, regs, kcb); restore_previous_kprobe(kcb); break; + case KPROBE_REENTER: + /* A nested probe was hit in FIQ, it is a BUG */ + pr_warn("Unrecoverable kprobe detected at %p.\n", + p->addr); + /* fall through */ default: /* impossible cases */ BUG(); } - } else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) { + } else { /* Probe hit and conditional execution check ok. */ set_current_kprobe(p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; @@ -304,13 +318,6 @@ void __kprobes kprobe_handler(struct pt_regs *regs) } reset_current_kprobe(); } - } else { - /* - * Probe hit but conditional execution check failed, - * so just skip the instruction and continue as if - * nothing had happened. - */ - singlestep_skip(p, regs); } } else if (cur) { /* We probably hit a jprobe. Call its break handler. */ @@ -434,6 +441,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; + kprobe_opcode_t *correct_ret_addr = NULL; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -456,14 +464,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) /* another task is sharing our hash bucket */ continue; + orig_ret_address = (unsigned long)ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; + ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); __this_cpu_write(current_kprobe, NULL); } - orig_ret_address = (unsigned long)ri->ret_addr; recycle_rp_inst(ri, &empty_rp); if (orig_ret_address != trampoline_address) @@ -475,7 +503,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) break; } - kretprobe_assert(ri, orig_ret_address, trampoline_address); kretprobe_hash_unlock(current, &flags); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index c893726aa52d..1c98a87786ca 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -977,7 +977,10 @@ static void coverage_end(void) void __naked __kprobes_test_case_start(void) { __asm__ __volatile__ ( - "stmdb sp!, {r4-r11} \n\t" + "mov r2, sp \n\t" + "bic r3, r2, #7 \n\t" + "mov sp, r3 \n\t" + "stmdb sp!, {r2-r11} \n\t" "sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" "bic r0, lr, #1 @ r0 = inline data \n\t" "mov r1, sp \n\t" @@ -997,7 +1000,8 @@ void __naked __kprobes_test_case_end_32(void) "movne pc, r0 \n\t" "mov r0, r4 \n\t" "add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" - "ldmia sp!, {r4-r11} \n\t" + "ldmia sp!, {r2-r11} \n\t" + "mov sp, r2 \n\t" "mov pc, r0 \n\t" ); } @@ -1013,7 +1017,8 @@ void __naked __kprobes_test_case_end_16(void) "bxne r0 \n\t" "mov r0, r4 \n\t" "add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" - "ldmia sp!, {r4-r11} \n\t" + "ldmia sp!, {r2-r11} \n\t" + "mov sp, r2 \n\t" "bx r0 \n\t" ); } diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 1c64ea2d23f9..0565779e66fa 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -179,8 +179,10 @@ usbphy: phy@01c19400 { compatible = "allwinner,sun50i-a64-usb-phy"; reg = <0x01c19400 0x14>, + <0x01c1a800 0x4>, <0x01c1b800 0x4>; reg-names = "phy_ctrl", + "pmu0", "pmu1"; clocks = <&ccu CLK_USB_PHY0>, <&ccu CLK_USB_PHY1>; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 4bf899fb451b..1b35b8bddbfb 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -42,7 +42,20 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> -static const char *fault_name(unsigned int esr); +struct fault_info { + int (*fn)(unsigned long addr, unsigned int esr, + struct pt_regs *regs); + int sig; + int code; + const char *name; +}; + +static const struct fault_info fault_info[]; + +static inline const struct fault_info *esr_to_fault_info(unsigned int esr) +{ + return fault_info + (esr & 63); +} #ifdef CONFIG_KPROBES static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) @@ -197,10 +210,12 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, struct pt_regs *regs) { struct siginfo si; + const struct fault_info *inf; if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) { + inf = esr_to_fault_info(esr); pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n", - tsk->comm, task_pid_nr(tsk), fault_name(esr), sig, + tsk->comm, task_pid_nr(tsk), inf->name, sig, addr, esr); show_pte(tsk->mm, addr); show_regs(regs); @@ -219,14 +234,16 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re { struct task_struct *tsk = current; struct mm_struct *mm = tsk->active_mm; + const struct fault_info *inf; /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ - if (user_mode(regs)) - __do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs); - else + if (user_mode(regs)) { + inf = esr_to_fault_info(esr); + __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs); + } else __do_kernel_fault(mm, addr, esr, regs); } @@ -488,12 +505,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) return 1; } -static const struct fault_info { - int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs); - int sig; - int code; - const char *name; -} fault_info[] = { +static const struct fault_info fault_info[] = { { do_bad, SIGBUS, 0, "ttbr address size fault" }, { do_bad, SIGBUS, 0, "level 1 address size fault" }, { do_bad, SIGBUS, 0, "level 2 address size fault" }, @@ -560,19 +572,13 @@ static const struct fault_info { { do_bad, SIGBUS, 0, "unknown 63" }, }; -static const char *fault_name(unsigned int esr) -{ - const struct fault_info *inf = fault_info + (esr & 63); - return inf->name; -} - /* * Dispatch a data abort to the relevant handler. */ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - const struct fault_info *inf = fault_info + (esr & 63); + const struct fault_info *inf = esr_to_fault_info(esr); struct siginfo info; if (!inf->fn(addr, esr, regs)) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index e25584d72396..7514a000e361 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -294,10 +294,6 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); - } else if (ps == (PAGE_SIZE * CONT_PTES)) { - hugetlb_add_hstate(CONT_PTE_SHIFT); - } else if (ps == (PMD_SIZE * CONT_PMDS)) { - hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { hugetlb_bad_size(); pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); @@ -306,13 +302,3 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PTE_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/ia64/include/asm/asm-prototypes.h b/arch/ia64/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..a2c139808cfe --- /dev/null +++ b/arch/ia64/include/asm/asm-prototypes.h @@ -0,0 +1,29 @@ +#ifndef _ASM_IA64_ASM_PROTOTYPES_H +#define _ASM_IA64_ASM_PROTOTYPES_H + +#include <asm/cacheflush.h> +#include <asm/checksum.h> +#include <asm/esi.h> +#include <asm/ftrace.h> +#include <asm/page.h> +#include <asm/pal.h> +#include <asm/string.h> +#include <asm/uaccess.h> +#include <asm/unwind.h> +#include <asm/xor.h> + +extern const char ia64_ivt[]; + +signed int __divsi3(signed int, unsigned int); +signed int __modsi3(signed int, unsigned int); + +signed long long __divdi3(signed long long, unsigned long long); +signed long long __moddi3(signed long long, unsigned long long); + +unsigned int __udivsi3(unsigned int, unsigned int); +unsigned int __umodsi3(unsigned int, unsigned int); + +unsigned long long __udivdi3(unsigned long long, unsigned long long); +unsigned long long __umoddi3(unsigned long long, unsigned long long); + +#endif /* _ASM_IA64_ASM_PROTOTYPES_H */ diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index 1f3d3877618f..0a40b14407b1 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -24,25 +24,25 @@ AFLAGS___modsi3.o = -DMODULO AFLAGS___umodsi3.o = -DUNSIGNED -DMODULO $(obj)/__divdi3.o: $(src)/idiv64.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__udivdi3.o: $(src)/idiv64.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__moddi3.o: $(src)/idiv64.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__umoddi3.o: $(src)/idiv64.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__divsi3.o: $(src)/idiv32.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__udivsi3.o: $(src)/idiv32.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__modsi3.o: $(src)/idiv32.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) $(obj)/__umodsi3.o: $(src)/idiv32.S FORCE - $(call if_changed_dep,as_o_S) + $(call if_changed_rule,as_o_S) diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h index 273e61225c27..07238b39638c 100644 --- a/arch/metag/include/asm/uaccess.h +++ b/arch/metag/include/asm/uaccess.h @@ -197,20 +197,21 @@ extern long __must_check strnlen_user(const char __user *src, long count); #define strlen_user(str) strnlen_user(str, 32767) -extern unsigned long __must_check __copy_user_zeroing(void *to, - const void __user *from, - unsigned long n); +extern unsigned long raw_copy_from_user(void *to, const void __user *from, + unsigned long n); static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res = n; if (likely(access_ok(VERIFY_READ, from, n))) - return __copy_user_zeroing(to, from, n); - memset(to, 0, n); - return n; + res = raw_copy_from_user(to, from, n); + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; } -#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n) +#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n) #define __copy_from_user_inatomic __copy_from_user extern unsigned long __must_check __copy_user(void __user *to, diff --git a/arch/metag/lib/usercopy.c b/arch/metag/lib/usercopy.c index b3ebfe9c8e88..2792fc621088 100644 --- a/arch/metag/lib/usercopy.c +++ b/arch/metag/lib/usercopy.c @@ -29,7 +29,6 @@ COPY \ "1:\n" \ " .section .fixup,\"ax\"\n" \ - " MOV D1Ar1,#0\n" \ FIXUP \ " MOVT D1Ar1,#HI(1b)\n" \ " JUMP D1Ar1,#LO(1b)\n" \ @@ -260,27 +259,31 @@ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "22:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ - "SUB %3, %3, #32\n" \ "23:\n" \ - "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "SUB %3, %3, #32\n" \ "24:\n" \ + "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "25:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "26:\n" \ "SUB %3, %3, #32\n" \ "DCACHE [%1+#-64], D0Ar6\n" \ "BR $Lloop"id"\n" \ \ "MOV RAPF, %1\n" \ - "25:\n" \ + "27:\n" \ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "26:\n" \ + "28:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "29:\n" \ "SUB %3, %3, #32\n" \ - "27:\n" \ + "30:\n" \ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "28:\n" \ + "31:\n" \ "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "32:\n" \ "SUB %0, %0, #8\n" \ - "29:\n" \ + "33:\n" \ "SETL [%0++], D0.7, D1.7\n" \ "SUB %3, %3, #32\n" \ "1:" \ @@ -312,11 +315,15 @@ " .long 26b,3b\n" \ " .long 27b,3b\n" \ " .long 28b,3b\n" \ - " .long 29b,4b\n" \ + " .long 29b,3b\n" \ + " .long 30b,3b\n" \ + " .long 31b,3b\n" \ + " .long 32b,3b\n" \ + " .long 33b,4b\n" \ " .previous\n" \ : "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \ : "0" (to), "1" (from), "2" (ret), "3" (n) \ - : "D1Ar1", "D0Ar2", "memory") + : "D1Ar1", "D0Ar2", "cc", "memory") /* rewind 'to' and 'from' pointers when a fault occurs * @@ -342,7 +349,7 @@ #define __asm_copy_to_user_64bit_rapf_loop(to, from, ret, n, id)\ __asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \ "LSR D0Ar2, D0Ar2, #8\n" \ - "AND D0Ar2, D0Ar2, #0x7\n" \ + "ANDS D0Ar2, D0Ar2, #0x7\n" \ "ADDZ D0Ar2, D0Ar2, #4\n" \ "SUB D0Ar2, D0Ar2, #1\n" \ "MOV D1Ar1, #4\n" \ @@ -403,47 +410,55 @@ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "22:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ - "SUB %3, %3, #16\n" \ "23:\n" \ - "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "24:\n" \ - "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ "SUB %3, %3, #16\n" \ - "25:\n" \ + "24:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "26:\n" \ + "25:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "26:\n" \ "SUB %3, %3, #16\n" \ "27:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ "28:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "29:\n" \ + "SUB %3, %3, #16\n" \ + "30:\n" \ + "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ + "31:\n" \ + "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "32:\n" \ "SUB %3, %3, #16\n" \ "DCACHE [%1+#-64], D0Ar6\n" \ "BR $Lloop"id"\n" \ \ "MOV RAPF, %1\n" \ - "29:\n" \ + "33:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "30:\n" \ + "34:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "35:\n" \ "SUB %3, %3, #16\n" \ - "31:\n" \ + "36:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "32:\n" \ + "37:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "38:\n" \ "SUB %3, %3, #16\n" \ - "33:\n" \ + "39:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "34:\n" \ + "40:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "41:\n" \ "SUB %3, %3, #16\n" \ - "35:\n" \ + "42:\n" \ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \ - "36:\n" \ + "43:\n" \ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \ + "44:\n" \ "SUB %0, %0, #4\n" \ - "37:\n" \ + "45:\n" \ "SETD [%0++], D0.7\n" \ "SUB %3, %3, #16\n" \ "1:" \ @@ -483,11 +498,19 @@ " .long 34b,3b\n" \ " .long 35b,3b\n" \ " .long 36b,3b\n" \ - " .long 37b,4b\n" \ + " .long 37b,3b\n" \ + " .long 38b,3b\n" \ + " .long 39b,3b\n" \ + " .long 40b,3b\n" \ + " .long 41b,3b\n" \ + " .long 42b,3b\n" \ + " .long 43b,3b\n" \ + " .long 44b,3b\n" \ + " .long 45b,4b\n" \ " .previous\n" \ : "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \ : "0" (to), "1" (from), "2" (ret), "3" (n) \ - : "D1Ar1", "D0Ar2", "memory") + : "D1Ar1", "D0Ar2", "cc", "memory") /* rewind 'to' and 'from' pointers when a fault occurs * @@ -513,7 +536,7 @@ #define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\ __asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \ "LSR D0Ar2, D0Ar2, #8\n" \ - "AND D0Ar2, D0Ar2, #0x7\n" \ + "ANDS D0Ar2, D0Ar2, #0x7\n" \ "ADDZ D0Ar2, D0Ar2, #4\n" \ "SUB D0Ar2, D0Ar2, #1\n" \ "MOV D1Ar1, #4\n" \ @@ -538,23 +561,31 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, if ((unsigned long) src & 1) { __asm_copy_to_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } if ((unsigned long) dst & 1) { /* Worst case - byte copy */ while (n > 0) { __asm_copy_to_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } } if (((unsigned long) src & 2) && n >= 2) { __asm_copy_to_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } if ((unsigned long) dst & 2) { /* Second worst case - word copy */ while (n >= 2) { __asm_copy_to_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } } @@ -569,6 +600,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 8) { __asm_copy_to_user_8x64(dst, src, retn); n -= 8; + if (retn) + return retn + n; } } if (n >= RAPF_MIN_BUF_SIZE) { @@ -581,6 +614,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 8) { __asm_copy_to_user_8x64(dst, src, retn); n -= 8; + if (retn) + return retn + n; } } #endif @@ -588,11 +623,15 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, while (n >= 16) { __asm_copy_to_user_16(dst, src, retn); n -= 16; + if (retn) + return retn + n; } while (n >= 4) { __asm_copy_to_user_4(dst, src, retn); n -= 4; + if (retn) + return retn + n; } switch (n) { @@ -609,6 +648,10 @@ unsigned long __copy_user(void __user *pdst, const void *psrc, break; } + /* + * If we get here, retn correctly reflects the number of failing + * bytes. + */ return retn; } EXPORT_SYMBOL(__copy_user); @@ -617,16 +660,14 @@ EXPORT_SYMBOL(__copy_user); __asm_copy_user_cont(to, from, ret, \ " GETB D1Ar1,[%1++]\n" \ "2: SETB [%0++],D1Ar1\n", \ - "3: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ + "3: ADD %2,%2,#1\n", \ " .long 2b,3b\n") #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ __asm_copy_user_cont(to, from, ret, \ " GETW D1Ar1,[%1++]\n" \ "2: SETW [%0++],D1Ar1\n" COPY, \ - "3: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ + "3: ADD %2,%2,#2\n" FIXUP, \ " .long 2b,3b\n" TENTRY) #define __asm_copy_from_user_2(to, from, ret) \ @@ -636,145 +677,26 @@ EXPORT_SYMBOL(__copy_user); __asm_copy_from_user_2x_cont(to, from, ret, \ " GETB D1Ar1,[%1++]\n" \ "4: SETB [%0++],D1Ar1\n", \ - "5: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ + "5: ADD %2,%2,#1\n", \ " .long 4b,5b\n") #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ __asm_copy_user_cont(to, from, ret, \ " GETD D1Ar1,[%1++]\n" \ "2: SETD [%0++],D1Ar1\n" COPY, \ - "3: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ + "3: ADD %2,%2,#4\n" FIXUP, \ " .long 2b,3b\n" TENTRY) #define __asm_copy_from_user_4(to, from, ret) \ __asm_copy_from_user_4x_cont(to, from, ret, "", "", "") -#define __asm_copy_from_user_5(to, from, ret) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "4: SETB [%0++],D1Ar1\n", \ - "5: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 4b,5b\n") - -#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "4: SETW [%0++],D1Ar1\n" COPY, \ - "5: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 4b,5b\n" TENTRY) - -#define __asm_copy_from_user_6(to, from, ret) \ - __asm_copy_from_user_6x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_7(to, from, ret) \ - __asm_copy_from_user_6x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "6: SETB [%0++],D1Ar1\n", \ - "7: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 6b,7b\n") - -#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_4x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "4: SETD [%0++],D1Ar1\n" COPY, \ - "5: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 4b,5b\n" TENTRY) - -#define __asm_copy_from_user_8(to, from, ret) \ - __asm_copy_from_user_8x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_9(to, from, ret) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "6: SETB [%0++],D1Ar1\n", \ - "7: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 6b,7b\n") - -#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "6: SETW [%0++],D1Ar1\n" COPY, \ - "7: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 6b,7b\n" TENTRY) - -#define __asm_copy_from_user_10(to, from, ret) \ - __asm_copy_from_user_10x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_11(to, from, ret) \ - __asm_copy_from_user_10x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "8: SETB [%0++],D1Ar1\n", \ - "9: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 8b,9b\n") - -#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_8x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "6: SETD [%0++],D1Ar1\n" COPY, \ - "7: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 6b,7b\n" TENTRY) - -#define __asm_copy_from_user_12(to, from, ret) \ - __asm_copy_from_user_12x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_13(to, from, ret) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "8: SETB [%0++],D1Ar1\n", \ - "9: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 8b,9b\n") - -#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETW D1Ar1,[%1++]\n" \ - "8: SETW [%0++],D1Ar1\n" COPY, \ - "9: ADD %2,%2,#2\n" \ - " SETW [%0++],D1Ar1\n" FIXUP, \ - " .long 8b,9b\n" TENTRY) - -#define __asm_copy_from_user_14(to, from, ret) \ - __asm_copy_from_user_14x_cont(to, from, ret, "", "", "") - -#define __asm_copy_from_user_15(to, from, ret) \ - __asm_copy_from_user_14x_cont(to, from, ret, \ - " GETB D1Ar1,[%1++]\n" \ - "10: SETB [%0++],D1Ar1\n", \ - "11: ADD %2,%2,#1\n" \ - " SETB [%0++],D1Ar1\n", \ - " .long 10b,11b\n") - -#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \ - __asm_copy_from_user_12x_cont(to, from, ret, \ - " GETD D1Ar1,[%1++]\n" \ - "8: SETD [%0++],D1Ar1\n" COPY, \ - "9: ADD %2,%2,#4\n" \ - " SETD [%0++],D1Ar1\n" FIXUP, \ - " .long 8b,9b\n" TENTRY) - -#define __asm_copy_from_user_16(to, from, ret) \ - __asm_copy_from_user_16x_cont(to, from, ret, "", "", "") - #define __asm_copy_from_user_8x64(to, from, ret) \ asm volatile ( \ " GETL D0Ar2,D1Ar1,[%1++]\n" \ "2: SETL [%0++],D0Ar2,D1Ar1\n" \ "1:\n" \ " .section .fixup,\"ax\"\n" \ - " MOV D1Ar1,#0\n" \ - " MOV D0Ar2,#0\n" \ "3: ADD %2,%2,#8\n" \ - " SETL [%0++],D0Ar2,D1Ar1\n" \ " MOVT D0Ar2,#HI(1b)\n" \ " JUMP D0Ar2,#LO(1b)\n" \ " .previous\n" \ @@ -789,36 +711,57 @@ EXPORT_SYMBOL(__copy_user); * * Rationale: * A fault occurs while reading from user buffer, which is the - * source. Since the fault is at a single address, we only - * need to rewind by 8 bytes. + * source. * Since we don't write to kernel buffer until we read first, * the kernel buffer is at the right state and needn't be - * corrected. + * corrected, but the source must be rewound to the beginning of + * the block, which is LSM_STEP*8 bytes. + * LSM_STEP is bits 10:8 in TXSTATUS which is already read + * and stored in D0Ar2 + * + * NOTE: If a fault occurs at the last operation in M{G,S}ETL + * LSM_STEP will be 0. ie: we do 4 writes in our case, if + * a fault happens at the 4th write, LSM_STEP will be 0 + * instead of 4. The code copes with that. */ #define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id) \ __asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \ - "SUB %1, %1, #8\n") + "LSR D0Ar2, D0Ar2, #5\n" \ + "ANDS D0Ar2, D0Ar2, #0x38\n" \ + "ADDZ D0Ar2, D0Ar2, #32\n" \ + "SUB %1, %1, D0Ar2\n") /* rewind 'from' pointer when a fault occurs * * Rationale: * A fault occurs while reading from user buffer, which is the - * source. Since the fault is at a single address, we only - * need to rewind by 4 bytes. + * source. * Since we don't write to kernel buffer until we read first, * the kernel buffer is at the right state and needn't be - * corrected. + * corrected, but the source must be rewound to the beginning of + * the block, which is LSM_STEP*4 bytes. + * LSM_STEP is bits 10:8 in TXSTATUS which is already read + * and stored in D0Ar2 + * + * NOTE: If a fault occurs at the last operation in M{G,S}ETL + * LSM_STEP will be 0. ie: we do 4 writes in our case, if + * a fault happens at the 4th write, LSM_STEP will be 0 + * instead of 4. The code copes with that. */ #define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id) \ __asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \ - "SUB %1, %1, #4\n") + "LSR D0Ar2, D0Ar2, #6\n" \ + "ANDS D0Ar2, D0Ar2, #0x1c\n" \ + "ADDZ D0Ar2, D0Ar2, #16\n" \ + "SUB %1, %1, D0Ar2\n") -/* Copy from user to kernel, zeroing the bytes that were inaccessible in - userland. The return-value is the number of bytes that were - inaccessible. */ -unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, - unsigned long n) +/* + * Copy from user to kernel. The return-value is the number of bytes that were + * inaccessible. + */ +unsigned long raw_copy_from_user(void *pdst, const void __user *psrc, + unsigned long n) { register char *dst asm ("A0.2") = pdst; register const char __user *src asm ("A1.2") = psrc; @@ -830,6 +773,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, if ((unsigned long) src & 1) { __asm_copy_from_user_1(dst, src, retn); n--; + if (retn) + return retn + n; } if ((unsigned long) dst & 1) { /* Worst case - byte copy */ @@ -837,12 +782,14 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_1(dst, src, retn); n--; if (retn) - goto copy_exception_bytes; + return retn + n; } } if (((unsigned long) src & 2) && n >= 2) { __asm_copy_from_user_2(dst, src, retn); n -= 2; + if (retn) + return retn + n; } if ((unsigned long) dst & 2) { /* Second worst case - word copy */ @@ -850,16 +797,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_2(dst, src, retn); n -= 2; if (retn) - goto copy_exception_bytes; + return retn + n; } } - /* We only need one check after the unalignment-adjustments, - because if both adjustments were done, either both or - neither reference had an exception. */ - if (retn != 0) - goto copy_exception_bytes; - #ifdef USE_RAPF /* 64 bit copy loop */ if (!(((unsigned long) src | (unsigned long) dst) & 7)) { @@ -872,7 +813,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_8x64(dst, src, retn); n -= 8; if (retn) - goto copy_exception_bytes; + return retn + n; } } @@ -888,7 +829,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, __asm_copy_from_user_8x64(dst, src, retn); n -= 8; if (retn) - goto copy_exception_bytes; + return retn + n; } } #endif @@ -898,7 +839,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, n -= 4; if (retn) - goto copy_exception_bytes; + return retn + n; } /* If we get here, there were no memory read faults. */ @@ -924,21 +865,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc, /* If we get here, retn correctly reflects the number of failing bytes. */ return retn; - - copy_exception_bytes: - /* We already have "retn" bytes cleared, and need to clear the - remaining "n" bytes. A non-optimized simple byte-for-byte in-line - memset is preferred here, since this isn't speed-critical code and - we'd rather have this a leaf-function than calling memset. */ - { - char *endp; - for (endp = dst + n; dst < endp; dst++) - *dst = 0; - } - - return retn + n; } -EXPORT_SYMBOL(__copy_user_zeroing); +EXPORT_SYMBOL(raw_copy_from_user); #define __asm_clear_8x64(to, ret) \ asm volatile ( \ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a008a9f03072..e0bb576410bb 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1531,7 +1531,7 @@ config CPU_MIPS64_R6 select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_MSA select GENERIC_CSUM - select MIPS_O32_FP64_SUPPORT if MIPS32_O32 + select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32 select HAVE_KVM help Choose this option to build a kernel for release 6 or later of the diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 8ef9c02747fa..02a1787c888c 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -489,7 +489,7 @@ $(generic_defconfigs): $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/generic_defconfig $^ \ $(foreach board,$(BOARDS),$(generic_config_dir)/board-$(board).config) - $(Q)$(MAKE) olddefconfig + $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig # # Prevent generic merge_config rules attempting to merge single fragments @@ -503,8 +503,8 @@ $(generic_config_dir)/%.config: ; # .PHONY: sead3_defconfig sead3_defconfig: - $(Q)$(MAKE) 32r2el_defconfig BOARDS=sead-3 + $(Q)$(MAKE) -f $(srctree)/Makefile 32r2el_defconfig BOARDS=sead-3 .PHONY: sead3micro_defconfig sead3micro_defconfig: - $(Q)$(MAKE) micro32r2el_defconfig BOARDS=sead-3 + $(Q)$(MAKE) -f $(srctree)/Makefile micro32r2el_defconfig BOARDS=sead-3 diff --git a/arch/mips/include/asm/asm-prototypes.h b/arch/mips/include/asm/asm-prototypes.h index a160cf69bb92..6e28971fe73a 100644 --- a/arch/mips/include/asm/asm-prototypes.h +++ b/arch/mips/include/asm/asm-prototypes.h @@ -3,3 +3,4 @@ #include <asm/fpu.h> #include <asm-generic/asm-prototypes.h> #include <asm/uaccess.h> +#include <asm/ftrace.h> diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index f94455f964ec..a2813fe381cf 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -21,6 +21,7 @@ #include <asm/cpu-features.h> #include <asm/fpu_emulator.h> #include <asm/hazards.h> +#include <asm/ptrace.h> #include <asm/processor.h> #include <asm/current.h> #include <asm/msa.h> diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 956db6e201d1..ddd1c918103b 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -18,9 +18,24 @@ #include <irq.h> #define IRQ_STACK_SIZE THREAD_SIZE +#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long)) extern void *irq_stack[NR_CPUS]; +/* + * The highest address on the IRQ stack contains a dummy frame put down in + * genex.S (handle_int & except_vec_vi_handler) which is structured as follows: + * + * top ------------ + * | task sp | <- irq_stack[cpu] + IRQ_STACK_START + * ------------ + * | | <- First frame of IRQ context + * ------------ + * + * task sp holds a copy of the task stack pointer where the struct pt_regs + * from exception entry can be found. + */ + static inline bool on_irq_stack(int cpu, unsigned long sp) { unsigned long low = (unsigned long)irq_stack[cpu]; diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index f485afe51514..a8df44d60607 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -127,7 +127,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) " andi %[ticket], %[ticket], 0xffff \n" " bne %[ticket], %[my_ticket], 4f \n" " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: \n" + "2: .insn \n" " .subsection 2 \n" "4: andi %[ticket], %[ticket], 0xffff \n" " sll %[ticket], 5 \n" @@ -202,7 +202,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) " sc %[ticket], %[ticket_ptr] \n" " beqz %[ticket], 1b \n" " li %[ticket], 1 \n" - "2: \n" + "2: .insn \n" " .subsection 2 \n" "3: b 2b \n" " li %[ticket], 0 \n" @@ -382,7 +382,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) " .set reorder \n" __WEAK_LLSC_MB " li %2, 1 \n" - "2: \n" + "2: .insn \n" : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) : GCC_OFF_SMALL_ASM() (rw->lock) : "memory"); @@ -422,7 +422,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) " lui %1, 0x8000 \n" " sc %1, %0 \n" " li %2, 1 \n" - "2: \n" + "2: .insn \n" : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) : GCC_OFF_SMALL_ASM() (rw->lock) diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index 3e940dbe0262..78faf4292e90 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -386,17 +386,18 @@ #define __NR_pkey_mprotect (__NR_Linux + 363) #define __NR_pkey_alloc (__NR_Linux + 364) #define __NR_pkey_free (__NR_Linux + 365) +#define __NR_statx (__NR_Linux + 366) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 365 +#define __NR_Linux_syscalls 366 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 365 +#define __NR_O32_Linux_syscalls 366 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -730,16 +731,17 @@ #define __NR_pkey_mprotect (__NR_Linux + 323) #define __NR_pkey_alloc (__NR_Linux + 324) #define __NR_pkey_free (__NR_Linux + 325) +#define __NR_statx (__NR_Linux + 326) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 325 +#define __NR_Linux_syscalls 326 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 325 +#define __NR_64_Linux_syscalls 326 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1077,15 +1079,16 @@ #define __NR_pkey_mprotect (__NR_Linux + 327) #define __NR_pkey_alloc (__NR_Linux + 328) #define __NR_pkey_free (__NR_Linux + 329) +#define __NR_statx (__NR_Linux + 330) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 329 +#define __NR_Linux_syscalls 330 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 329 +#define __NR_N32_Linux_syscalls 330 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index bb5c5d34ba81..a670c0c11875 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -102,6 +102,7 @@ void output_thread_info_defines(void) DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); + DEFINE(_IRQ_STACK_START, IRQ_STACK_START); BLANK(); } diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 804d2a2a19fe..dd6a18bc10ab 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -80,7 +80,7 @@ static unsigned int calculate_min_delta(void) } /* Sorted insert of 75th percentile into buf2 */ - for (k = 0; k < i; ++k) { + for (k = 0; k < i && k < ARRAY_SIZE(buf2); ++k) { if (buf1[ARRAY_SIZE(buf1) - 1] < buf2[k]) { l = min_t(unsigned int, i, ARRAY_SIZE(buf2) - 1); diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 59476a607add..a00e87b0256d 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg) END(mips_cps_get_bootcfg) LEAF(mips_cps_boot_vpes) - PTR_L ta2, COREBOOTCFG_VPEMASK(a0) + lw ta2, COREBOOTCFG_VPEMASK(a0) PTR_L ta3, COREBOOTCFG_VPECONFIG(a0) #if defined(CONFIG_CPU_MIPSR6) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 07718bb5fc9d..12422fd4af23 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1824,7 +1824,7 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) } decode_configs(c); - c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE; + c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE; c->writecombine = _CACHE_UNCACHED_ACCELERATED; break; default: diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 6430bff21fff..5c429d70e17f 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -257,7 +257,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, else if ((prog_req.fr1 && prog_req.frdefault) || (prog_req.single && !prog_req.frdefault)) /* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */ - state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) && + state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) && cpu_has_mips_r2_r6) ? FP_FR1 : FP_FR0; else if (prog_req.fr1) diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 7ec9612cb007..ae810da4d499 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp) beq t0, t1, 2f /* Switch to IRQ stack */ - li t1, _IRQ_STACK_SIZE + li t1, _IRQ_STACK_START PTR_ADD sp, t0, t1 + /* Save task's sp on IRQ stack so that unwinding can follow it */ + LONG_S s1, 0(sp) 2: jal plat_irq_dispatch @@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp) beq t0, t1, 2f /* Switch to IRQ stack */ - li t1, _IRQ_STACK_SIZE + li t1, _IRQ_STACK_START PTR_ADD sp, t0, t1 + /* Save task's sp on IRQ stack so that unwinding can follow it */ + LONG_S s1, 0(sp) 2: jalr v0 @@ -519,7 +523,7 @@ NESTED(nmi_handler, PT_SIZE, sp) BUILD_HANDLER reserved reserved sti verbose /* others */ .align 5 - LEAF(handle_ri_rdhwr_vivt) + LEAF(handle_ri_rdhwr_tlbp) .set push .set noat .set noreorder @@ -538,7 +542,7 @@ NESTED(nmi_handler, PT_SIZE, sp) .set pop bltz k1, handle_ri /* slow path */ /* fall thru */ - END(handle_ri_rdhwr_vivt) + END(handle_ri_rdhwr_tlbp) LEAF(handle_ri_rdhwr) .set push diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 1f4bd222ba76..eb6c0d582626 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -244,9 +244,6 @@ static int compute_signal(int tt) void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) { int reg; - struct thread_info *ti = task_thread_info(p); - unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32; - struct pt_regs *regs = (struct pt_regs *)ksp - 1; #if (KGDB_GDB_REG_SIZE == 32) u32 *ptr = (u32 *)gdb_regs; #else @@ -254,25 +251,46 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) #endif for (reg = 0; reg < 16; reg++) - *(ptr++) = regs->regs[reg]; + *(ptr++) = 0; /* S0 - S7 */ - for (reg = 16; reg < 24; reg++) - *(ptr++) = regs->regs[reg]; + *(ptr++) = p->thread.reg16; + *(ptr++) = p->thread.reg17; + *(ptr++) = p->thread.reg18; + *(ptr++) = p->thread.reg19; + *(ptr++) = p->thread.reg20; + *(ptr++) = p->thread.reg21; + *(ptr++) = p->thread.reg22; + *(ptr++) = p->thread.reg23; for (reg = 24; reg < 28; reg++) *(ptr++) = 0; /* GP, SP, FP, RA */ - for (reg = 28; reg < 32; reg++) - *(ptr++) = regs->regs[reg]; - - *(ptr++) = regs->cp0_status; - *(ptr++) = regs->lo; - *(ptr++) = regs->hi; - *(ptr++) = regs->cp0_badvaddr; - *(ptr++) = regs->cp0_cause; - *(ptr++) = regs->cp0_epc; + *(ptr++) = (long)p; + *(ptr++) = p->thread.reg29; + *(ptr++) = p->thread.reg30; + *(ptr++) = p->thread.reg31; + + *(ptr++) = p->thread.cp0_status; + + /* lo, hi */ + *(ptr++) = 0; + *(ptr++) = 0; + + /* + * BadVAddr, Cause + * Ideally these would come from the last exception frame up the stack + * but that requires unwinding, otherwise we can't know much for sure. + */ + *(ptr++) = 0; + *(ptr++) = 0; + + /* + * PC + * use return address (RA), i.e. the moment after return from resume() + */ + *(ptr++) = p->thread.reg31; } void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 8c35b3152e1e..9452b02ce079 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1446,6 +1446,11 @@ static int mipsxx_pmu_handle_shared_irq(void) HANDLE_COUNTER(0) } +#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS + read_unlock(&pmuint_rwlock); +#endif + resume_local_counters(); + /* * Do all the work for the pending perf events. We can do this * in here because the performance counter interrupt is a regular @@ -1454,10 +1459,6 @@ static int mipsxx_pmu_handle_shared_irq(void) if (handled == IRQ_HANDLED) irq_work_run(); -#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS - read_unlock(&pmuint_rwlock); -#endif - resume_local_counters(); return handled; } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index fb6b6b650719..b68e10fc453d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -488,31 +488,52 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page, unsigned long pc, unsigned long *ra) { + unsigned long low, high, irq_stack_high; struct mips_frame_info info; unsigned long size, ofs; + struct pt_regs *regs; int leaf; - extern void ret_from_irq(void); - extern void ret_from_exception(void); if (!stack_page) return 0; /* - * If we reached the bottom of interrupt context, - * return saved pc in pt_regs. + * IRQ stacks start at IRQ_STACK_START + * task stacks at THREAD_SIZE - 32 */ - if (pc == (unsigned long)ret_from_irq || - pc == (unsigned long)ret_from_exception) { - struct pt_regs *regs; - if (*sp >= stack_page && - *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) { - regs = (struct pt_regs *)*sp; - pc = regs->cp0_epc; - if (!user_mode(regs) && __kernel_text_address(pc)) { - *sp = regs->regs[29]; - *ra = regs->regs[31]; - return pc; - } + low = stack_page; + if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) { + high = stack_page + IRQ_STACK_START; + irq_stack_high = high; + } else { + high = stack_page + THREAD_SIZE - 32; + irq_stack_high = 0; + } + + /* + * If we reached the top of the interrupt stack, start unwinding + * the interrupted task stack. + */ + if (unlikely(*sp == irq_stack_high)) { + unsigned long task_sp = *(unsigned long *)*sp; + + /* + * Check that the pointer saved in the IRQ stack head points to + * something within the stack of the current task + */ + if (!object_is_on_stack((void *)task_sp)) + return 0; + + /* + * Follow pointer to tasks kernel stack frame where interrupted + * state was saved. + */ + regs = (struct pt_regs *)task_sp; + pc = regs->cp0_epc; + if (!user_mode(regs) && __kernel_text_address(pc)) { + *sp = regs->regs[29]; + *ra = regs->regs[31]; + return pc; } return 0; } @@ -533,8 +554,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page, if (leaf < 0) return 0; - if (*sp < stack_page || - *sp + info.frame_size > stack_page + THREAD_SIZE - 32) + if (*sp < low || *sp + info.frame_size > high) return 0; if (leaf) diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 9103bebc9a8e..2d1a0c438771 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -18,7 +18,7 @@ #include <linux/kernel.h> #include <linux/libfdt.h> #include <linux/of_fdt.h> -#include <linux/sched.h> +#include <linux/sched/task.h> #include <linux/start_kernel.h> #include <linux/string.h> #include <linux/printk.h> diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index c29d397eee86..80ed68b2c95e 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -600,3 +600,4 @@ EXPORT(sys_call_table) PTR sys_pkey_mprotect PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ + PTR sys_statx diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 0687f96ee912..49765b44aa9b 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -438,4 +438,5 @@ EXPORT(sys_call_table) PTR sys_pkey_mprotect PTR sys_pkey_alloc PTR sys_pkey_free /* 5325 */ + PTR sys_statx .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 0331ba39a065..90bad2d1b2d3 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -433,4 +433,5 @@ EXPORT(sysn32_call_table) PTR sys_pkey_mprotect PTR sys_pkey_alloc PTR sys_pkey_free + PTR sys_statx /* 6330 */ .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 5a47042dd25f..2dd70bd104e1 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -588,4 +588,5 @@ EXPORT(sys32_call_table) PTR sys_pkey_mprotect PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ + PTR sys_statx .size sys32_call_table,.-sys32_call_table diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 6d45f05538c8..795b4aaf8927 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -422,13 +422,12 @@ void play_dead(void) local_irq_disable(); idle_task_exit(); cpu = smp_processor_id(); + core = cpu_data[cpu].core; cpu_death = CPU_DEATH_POWER; pr_debug("CPU%d going offline\n", cpu); if (cpu_has_mipsmt || cpu_has_vp) { - core = cpu_data[cpu].core; - /* Look for another online VPE within the core */ for_each_online_cpu(cpu_death_sibling) { if (cpu_data[cpu_death_sibling].core != core) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index c7d17cfb32f6..b49e7bf9f950 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -83,7 +83,7 @@ extern asmlinkage void handle_dbe(void); extern asmlinkage void handle_sys(void); extern asmlinkage void handle_bp(void); extern asmlinkage void handle_ri(void); -extern asmlinkage void handle_ri_rdhwr_vivt(void); +extern asmlinkage void handle_ri_rdhwr_tlbp(void); extern asmlinkage void handle_ri_rdhwr(void); extern asmlinkage void handle_cpu(void); extern asmlinkage void handle_ov(void); @@ -2408,9 +2408,18 @@ void __init trap_init(void) set_except_vector(EXCCODE_SYS, handle_sys); set_except_vector(EXCCODE_BP, handle_bp); - set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri : - (cpu_has_vtag_icache ? - handle_ri_rdhwr_vivt : handle_ri_rdhwr)); + + if (rdhwr_noopt) + set_except_vector(EXCCODE_RI, handle_ri); + else { + if (cpu_has_vtag_icache) + set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp); + else if (current_cpu_type() == CPU_LOONGSON3) + set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp); + else + set_except_vector(EXCCODE_RI, handle_ri_rdhwr); + } + set_except_vector(EXCCODE_CPU, handle_cpu); set_except_vector(EXCCODE_OV, handle_ov); set_except_vector(EXCCODE_TR, handle_tr); diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 3c3aa05891dd..95bec460b651 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -467,7 +467,7 @@ void __init ltq_soc_init(void) if (!np_xbar) panic("Failed to load xbar nodes from devicetree"); - if (of_address_to_resource(np_pmu, 0, &res_xbar)) + if (of_address_to_resource(np_xbar, 0, &res_xbar)) panic("Failed to get xbar resources"); if (!request_mem_region(res_xbar.start, resource_size(&res_xbar), res_xbar.name)) diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index e7f798d55fbc..3fe99cb271a9 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1562,6 +1562,7 @@ static void probe_vcache(void) vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz; c->vcache.waybit = 0; + c->vcache.waysize = vcache_size / c->vcache.ways; pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n", vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz); @@ -1664,6 +1665,7 @@ static void __init loongson3_sc_init(void) /* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */ scache_size *= 4; c->scache.waybit = 0; + c->scache.waysize = scache_size / c->scache.ways; pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n", scache_size >> 10, way_string[c->scache.ways], c->scache.linesz); if (scache_size) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 9bfee8988eaf..4f642e07c2b1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -760,7 +760,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte, static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r, struct uasm_label **l, unsigned int pte, - unsigned int ptr) + unsigned int ptr, + unsigned int flush) { #ifdef CONFIG_SMP UASM_i_SC(p, pte, 0, ptr); @@ -769,6 +770,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r, #else UASM_i_SW(p, pte, 0, ptr); #endif + if (cpu_has_ftlb && flush) { + BUG_ON(!cpu_has_tlbinv); + + UASM_i_MFC0(p, ptr, C0_ENTRYHI); + uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV); + UASM_i_MTC0(p, ptr, C0_ENTRYHI); + build_tlb_write_entry(p, l, r, tlb_indexed); + + uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV); + UASM_i_MTC0(p, ptr, C0_ENTRYHI); + build_huge_update_entries(p, pte, ptr); + build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0); + + return; + } + build_huge_update_entries(p, pte, ptr); build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0); } @@ -2199,7 +2216,7 @@ static void build_r4000_tlb_load_handler(void) uasm_l_tlbl_goaround2(&l, p); } uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID)); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1); #endif uasm_l_nopage_tlbl(&l, p); @@ -2254,7 +2271,7 @@ static void build_r4000_tlb_store_handler(void) build_tlb_probe_entry(&p); uasm_i_ori(&p, wr.r1, wr.r1, _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1); #endif uasm_l_nopage_tlbs(&l, p); @@ -2310,7 +2327,7 @@ static void build_r4000_tlb_modify_handler(void) build_tlb_probe_entry(&p); uasm_i_ori(&p, wr.r1, wr.r1, _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY); - build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2); + build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0); #endif uasm_l_nopage_tlbm(&l, p); diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index cb675ec6f283..54f56d5a96c4 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -232,6 +232,17 @@ void __init arch_init_irq(void) { int corehi_irq; + /* + * Preallocate the i8259's expected virq's here. Since irqchip_init() + * will probe the irqchips in hierarchial order, i8259 is probed last. + * If anything allocates a virq before the i8259 is probed, it will + * be given one of the i8259's expected range and consequently setup + * of the i8259 will fail. + */ + WARN(irq_alloc_descs(I8259A_IRQ_BASE, I8259A_IRQ_BASE, + 16, numa_node_id()) < 0, + "Cannot reserve i8259 virqs at IRQ%d\n", I8259A_IRQ_BASE); + i8259_set_poll(mips_pcibios_iack); irqchip_init(); diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 014649be158d..3a84f6c0c840 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -190,7 +190,7 @@ void register_pci_controller(struct pci_controller *hose) } INIT_LIST_HEAD(&hose->list); - list_add(&hose->list, &controllers); + list_add_tail(&hose->list, &controllers); /* * Do not panic here but later - this might happen before console init. diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index c4ffd43d3996..48ce701557a4 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -35,7 +35,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) }; static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) }; static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) }; static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) }; -static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) }; +static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) }; static struct rt2880_pmx_func pci_func[] = { FUNC("pci-dev", 0, 40, 32), FUNC("pci-host2", 1, 40, 32), @@ -43,7 +43,7 @@ static struct rt2880_pmx_func pci_func[] = { FUNC("pci-fnc", 3, 40, 32) }; static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) }; -static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) }; +static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) }; static struct rt2880_pmx_group rt3883_pinmux_data[] = { GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C), diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 8442727f28d2..cbd4f4af8108 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -39,10 +39,10 @@ #define get_user __get_user #if !defined(CONFIG_64BIT) -#define LDD_USER(ptr) __get_user_asm64(ptr) +#define LDD_USER(val, ptr) __get_user_asm64(val, ptr) #define STD_USER(x, ptr) __put_user_asm64(x, ptr) #else -#define LDD_USER(ptr) __get_user_asm("ldd", ptr) +#define LDD_USER(val, ptr) __get_user_asm(val, "ldd", ptr) #define STD_USER(x, ptr) __put_user_asm("std", x, ptr) #endif @@ -97,63 +97,87 @@ struct exception_data { " mtsp %0,%%sr2\n\t" \ : : "r"(get_fs()) : ) -#define __get_user(x, ptr) \ -({ \ - register long __gu_err __asm__ ("r8") = 0; \ - register long __gu_val; \ - \ - load_sr2(); \ - switch (sizeof(*(ptr))) { \ - case 1: __get_user_asm("ldb", ptr); break; \ - case 2: __get_user_asm("ldh", ptr); break; \ - case 4: __get_user_asm("ldw", ptr); break; \ - case 8: LDD_USER(ptr); break; \ - default: BUILD_BUG(); break; \ - } \ - \ - (x) = (__force __typeof__(*(ptr))) __gu_val; \ - __gu_err; \ +#define __get_user_internal(val, ptr) \ +({ \ + register long __gu_err __asm__ ("r8") = 0; \ + \ + switch (sizeof(*(ptr))) { \ + case 1: __get_user_asm(val, "ldb", ptr); break; \ + case 2: __get_user_asm(val, "ldh", ptr); break; \ + case 4: __get_user_asm(val, "ldw", ptr); break; \ + case 8: LDD_USER(val, ptr); break; \ + default: BUILD_BUG(); \ + } \ + \ + __gu_err; \ }) -#define __get_user_asm(ldx, ptr) \ +#define __get_user(val, ptr) \ +({ \ + load_sr2(); \ + __get_user_internal(val, ptr); \ +}) + +#define __get_user_asm(val, ldx, ptr) \ +{ \ + register long __gu_val; \ + \ __asm__("1: " ldx " 0(%%sr2,%2),%0\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ : "=r"(__gu_val), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); + : "r"(ptr), "1"(__gu_err)); \ + \ + (val) = (__force __typeof__(*(ptr))) __gu_val; \ +} #if !defined(CONFIG_64BIT) -#define __get_user_asm64(ptr) \ +#define __get_user_asm64(val, ptr) \ +{ \ + union { \ + unsigned long long l; \ + __typeof__(*(ptr)) t; \ + } __gu_tmp; \ + \ __asm__(" copy %%r0,%R0\n" \ "1: ldw 0(%%sr2,%2),%0\n" \ "2: ldw 4(%%sr2,%2),%R0\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ - : "=r"(__gu_val), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); + : "=&r"(__gu_tmp.l), "=r"(__gu_err) \ + : "r"(ptr), "1"(__gu_err)); \ + \ + (val) = __gu_tmp.t; \ +} #endif /* !defined(CONFIG_64BIT) */ -#define __put_user(x, ptr) \ +#define __put_user_internal(x, ptr) \ ({ \ register long __pu_err __asm__ ("r8") = 0; \ __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x); \ \ - load_sr2(); \ switch (sizeof(*(ptr))) { \ - case 1: __put_user_asm("stb", __x, ptr); break; \ - case 2: __put_user_asm("sth", __x, ptr); break; \ - case 4: __put_user_asm("stw", __x, ptr); break; \ - case 8: STD_USER(__x, ptr); break; \ - default: BUILD_BUG(); break; \ - } \ + case 1: __put_user_asm("stb", __x, ptr); break; \ + case 2: __put_user_asm("sth", __x, ptr); break; \ + case 4: __put_user_asm("stw", __x, ptr); break; \ + case 8: STD_USER(__x, ptr); break; \ + default: BUILD_BUG(); \ + } \ \ __pu_err; \ }) +#define __put_user(x, ptr) \ +({ \ + load_sr2(); \ + __put_user_internal(x, ptr); \ +}) + + /* * The "__put_user/kernel_asm()" macros tell gcc they read from memory * instead of writing. This is because they do not write to any memory diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S index f01188c044ee..85c28bb80fb7 100644 --- a/arch/parisc/lib/lusercopy.S +++ b/arch/parisc/lib/lusercopy.S @@ -201,7 +201,7 @@ ENTRY_CFI(pa_memcpy) add dst,len,end /* short copy with less than 16 bytes? */ - cmpib,>>=,n 15,len,.Lbyte_loop + cmpib,COND(>>=),n 15,len,.Lbyte_loop /* same alignment? */ xor src,dst,t0 @@ -216,7 +216,7 @@ ENTRY_CFI(pa_memcpy) /* loop until we are 64-bit aligned */ .Lalign_loop64: extru dst,31,3,t1 - cmpib,=,n 0,t1,.Lcopy_loop_16 + cmpib,=,n 0,t1,.Lcopy_loop_16_start 20: ldb,ma 1(srcspc,src),t1 21: stb,ma t1,1(dstspc,dst) b .Lalign_loop64 @@ -225,6 +225,7 @@ ENTRY_CFI(pa_memcpy) ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done) ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done) +.Lcopy_loop_16_start: ldi 31,t0 .Lcopy_loop_16: cmpb,COND(>>=),n t0,len,.Lword_loop @@ -267,7 +268,7 @@ ENTRY_CFI(pa_memcpy) /* loop until we are 32-bit aligned */ .Lalign_loop32: extru dst,31,2,t1 - cmpib,=,n 0,t1,.Lcopy_loop_4 + cmpib,=,n 0,t1,.Lcopy_loop_8 20: ldb,ma 1(srcspc,src),t1 21: stb,ma t1,1(dstspc,dst) b .Lalign_loop32 @@ -277,7 +278,7 @@ ENTRY_CFI(pa_memcpy) ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done) -.Lcopy_loop_4: +.Lcopy_loop_8: cmpib,COND(>>=),n 15,len,.Lbyte_loop 10: ldw 0(srcspc,src),t1 @@ -299,7 +300,7 @@ ENTRY_CFI(pa_memcpy) ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done) ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done) - b .Lcopy_loop_4 + b .Lcopy_loop_8 ldo -16(len),len .Lbyte_loop: @@ -324,7 +325,7 @@ ENTRY_CFI(pa_memcpy) .Lunaligned_copy: /* align until dst is 32bit-word-aligned */ extru dst,31,2,t1 - cmpib,COND(=),n 0,t1,.Lcopy_dstaligned + cmpib,=,n 0,t1,.Lcopy_dstaligned 20: ldb 0(srcspc,src),t1 ldo 1(src),src 21: stb,ma t1,1(dstspc,dst) @@ -362,7 +363,7 @@ ENTRY_CFI(pa_memcpy) cmpiclr,<> 1,t0,%r0 b,n .Lcase1 .Lcase0: - cmpb,= %r0,len,.Lcda_finish + cmpb,COND(=) %r0,len,.Lcda_finish nop 1: ldw,ma 4(srcspc,src), a3 @@ -376,7 +377,7 @@ ENTRY_CFI(pa_memcpy) 1: ldw,ma 4(srcspc,src), a3 ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault) ldo -1(len),len - cmpb,=,n %r0,len,.Ldo0 + cmpb,COND(=),n %r0,len,.Ldo0 .Ldo4: 1: ldw,ma 4(srcspc,src), a0 ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault) @@ -402,7 +403,7 @@ ENTRY_CFI(pa_memcpy) 1: stw,ma t0, 4(dstspc,dst) ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done) ldo -4(len),len - cmpb,<> %r0,len,.Ldo4 + cmpb,COND(<>) %r0,len,.Ldo4 nop .Ldo0: shrpw a2, a3, %sar, t0 @@ -436,14 +437,14 @@ ENTRY_CFI(pa_memcpy) /* fault exception fixup handlers: */ #ifdef CONFIG_64BIT .Lcopy16_fault: -10: b .Lcopy_done - std,ma t1,8(dstspc,dst) + b .Lcopy_done +10: std,ma t1,8(dstspc,dst) ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done) #endif .Lcopy8_fault: -10: b .Lcopy_done - stw,ma t1,4(dstspc,dst) + b .Lcopy_done +10: stw,ma t1,4(dstspc,dst) ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done) .exit diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index 411994551afc..f058e0c3e4d4 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -33,10 +33,13 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len) } if (len & ~VMX_ALIGN_MASK) { + preempt_disable(); pagefault_disable(); enable_kernel_altivec(); crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); + disable_kernel_altivec(); pagefault_enable(); + preempt_enable(); } tail = len & VMX_ALIGN_MASK; diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 14752eee3d0c..ed3beadd2cc5 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -236,9 +236,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtctr reg; \ bctr -#define BRANCH_LINK_TO_FAR(reg, label) \ - __LOAD_FAR_HANDLER(reg, label); \ - mtctr reg; \ +#define BRANCH_LINK_TO_FAR(label) \ + __LOAD_FAR_HANDLER(r12, label); \ + mtctr r12; \ bctrl /* @@ -265,7 +265,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define BRANCH_TO_COMMON(reg, label) \ b label -#define BRANCH_LINK_TO_FAR(reg, label) \ +#define BRANCH_LINK_TO_FAR(label) \ bl label #define BRANCH_TO_KVM(reg, label) \ diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index cbc7c42cdb74..ec7a8b099dd9 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -807,14 +807,25 @@ int fix_alignment(struct pt_regs *regs) nb = aligninfo[instr].len; flags = aligninfo[instr].flags; - /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */ - if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) { - nb = 8; - flags = LD+SW; - } else if (IS_XFORM(instruction) && - ((instruction >> 1) & 0x3ff) == 660) { - nb = 8; - flags = ST+SW; + /* + * Handle some cases which give overlaps in the DSISR values. + */ + if (IS_XFORM(instruction)) { + switch (get_xop(instruction)) { + case 532: /* ldbrx */ + nb = 8; + flags = LD+SW; + break; + case 660: /* stdbrx */ + nb = 8; + flags = ST+SW; + break; + case 20: /* lwarx */ + case 84: /* ldarx */ + case 116: /* lharx */ + case 276: /* lqarx */ + return 0; /* not emulated ever */ + } } /* Byteswap little endian loads and stores */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6432d4bf08c8..767ef6d68c9e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -689,7 +689,7 @@ resume_kernel: addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ - lwz r3,GPR1(r1) + ld r3,GPR1(r1) subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ mr r4,r1 /* src: current exception frame */ mr r1,r3 /* Reroute the trampoline frame to r1 */ @@ -703,8 +703,8 @@ resume_kernel: addi r6,r6,8 bdnz 2b - /* Do real store operation to complete stwu */ - lwz r5,GPR1(r1) + /* Do real store operation to complete stdu */ + ld r5,GPR1(r1) std r8,0(r5) /* Clear _TIF_EMULATE_STACK_STORE flag */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 857bf7c5b946..6353019966e6 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -982,7 +982,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early) EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD - BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode) + BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */ /* Windup the stack. */ /* Move original HSRR0 and HSRR1 into the respective regs */ ld r9,_MSR(r1) diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index ae179cb1bb3c..c119044cad0d 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -67,7 +67,7 @@ PPC64_CACHES: * flush all bytes from start through stop-1 inclusive */ -_GLOBAL(flush_icache_range) +_GLOBAL_TOC(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr @@ -120,7 +120,7 @@ EXPORT_SYMBOL(flush_icache_range) * * flush all bytes from start to stop-1 inclusive */ -_GLOBAL(flush_dcache_range) +_GLOBAL_TOC(flush_dcache_range) /* * Flush the data cache to memory diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 9cfaa8b69b5f..f997154dfc41 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -236,6 +236,15 @@ static void cpu_ready_for_interrupts(void) mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); } + /* + * Fixup HFSCR:TM based on CPU features. The bit is set by our + * early asm init because at that point we haven't updated our + * CPU features from firmware and device-tree. Here we have, + * so let's do it. + */ + if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP)) + mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM); + /* Set IR and DR in PACA MSR */ get_paca()->kernel_msr = MSR_KERNEL; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 8c68145ba1bd..710e491206ed 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -1487,6 +1487,10 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, /* start new resize */ resize = kzalloc(sizeof(*resize), GFP_KERNEL); + if (!resize) { + ret = -ENOMEM; + goto out; + } resize->order = shift; resize->kvm = kvm; INIT_WORK(&resize->work, resize_hpt_prepare_work); diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index cc332608e656..65bb8f33b399 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -638,6 +638,10 @@ static void native_flush_hash_range(unsigned long number, int local) unsigned long psize = batch->psize; int ssize = batch->ssize; int i; + unsigned int use_local; + + use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && + mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use(); local_irq_save(flags); @@ -667,8 +671,7 @@ static void native_flush_hash_range(unsigned long number, int local) } pte_iterate_hashed_end(); } - if (mmu_has_feature(MMU_FTR_TLBIEL) && - mmu_psize_defs[psize].tlbiel && local) { + if (use_local) { asm volatile("ptesync":::"memory"); for (i = 0; i < number; i++) { vpn = batch->vpn[i]; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 93e37b12e882..ecec682bb516 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1051,6 +1051,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { if (!MACHINE_HAS_NX) pte_val(entry) &= ~_PAGE_NOEXEC; + if (pte_present(entry)) + pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) ptep_set_pte_at(mm, addr, ptep, entry); else diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index d55c829a5944..ddbffb715b40 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -168,8 +168,7 @@ union page_table_entry { unsigned long z : 1; /* Zero Bit */ unsigned long i : 1; /* Page-Invalid Bit */ unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long co : 1; /* Change-Recording Override */ - unsigned long : 8; + unsigned long : 9; }; }; @@ -745,8 +744,6 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, return PGM_PAGE_TRANSLATION; if (pte.z) return PGM_TRANSLATION_SPEC; - if (pte.co && !edat1) - return PGM_TRANSLATION_SPEC; dat_protection |= pte.p; raddr.pfra = pte.pfra; real_address: @@ -1182,7 +1179,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val); if (!rc && pte.i) rc = PGM_PAGE_TRANSLATION; - if (!rc && (pte.z || (pte.co && sg->edat_level < 1))) + if (!rc && pte.z) rc = PGM_TRANSLATION_SPEC; shadow_page: pte.p |= dat_protection; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 68ac5c7cd982..3db2543733a5 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,7 +43,7 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select HAVE_ARCH_HARDENED_USERCOPY - select PROVE_LOCKING_SMALL if PROVE_LOCKING + select LOCKDEP_SMALL if LOCKDEP select ARCH_WANT_RELAX_ORDER config SPARC32 @@ -82,6 +82,7 @@ config SPARC64 select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select HAVE_NMI + select HAVE_REGS_AND_STACK_ACCESS_API config ARCH_DEFCONFIG string diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index f294dd42fc7d..5961b2d8398a 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -17,6 +17,7 @@ #define HPAGE_SHIFT 23 #define REAL_HPAGE_SHIFT 22 +#define HPAGE_2GB_SHIFT 31 #define HPAGE_256MB_SHIFT 28 #define HPAGE_64K_SHIFT 16 #define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT) @@ -27,7 +28,7 @@ #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT)) -#define HUGE_MAX_HSTATE 3 +#define HUGE_MAX_HSTATE 4 #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 8a598528ec1f..6fbd931f0570 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -679,26 +679,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return pte_pfn(pte); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_dirty(pmd_t pmd) +#define __HAVE_ARCH_PMD_WRITE +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_dirty(pte); + return pte_write(pte); } -static inline unsigned long pmd_young(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long pmd_dirty(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_dirty(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +static inline unsigned long pmd_young(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_write(pte); + return pte_young(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index 365d4cb267b4..dd27159819eb 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -18,12 +18,6 @@ #include <asm/signal.h> #include <asm/page.h> -/* - * The sparc has no problems with write protection - */ -#define wp_works_ok 1 -#define wp_works_ok__is_a_macro /* for versions in ksyms.c */ - /* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too... * That one page is used to protect kernel from intruders, so that * we can make our access_ok test faster diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 6448cfc8292f..b58ee9018433 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -18,10 +18,6 @@ #include <asm/ptrace.h> #include <asm/page.h> -/* The sparc has no problems with write protection */ -#define wp_works_ok 1 -#define wp_works_ok__is_a_macro /* for versions in ksyms.c */ - /* * User lives in his very own context, and cannot reference us. Note * that TASK_SIZE is a misnomer, it really gives maximum user virtual diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index ca57f08bd3db..d73428e4333c 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -83,7 +83,8 @@ unsigned long profile_pc(struct pt_regs *); #define MAX_REG_OFFSET (offsetof(struct pt_regs, magic)) -extern int regs_query_register_offset(const char *name); +int regs_query_register_offset(const char *name); +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); /** * regs_get_register() - get register value from its offset diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 36eee8132c22..ae77df75bffa 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -425,8 +425,9 @@ #define __NR_copy_file_range 357 #define __NR_preadv2 358 #define __NR_pwritev2 359 +#define __NR_statx 360 -#define NR_syscalls 360 +#define NR_syscalls 361 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 @@ -442,4 +443,9 @@ #define __IGNORE_getresgid #endif +/* Sparc doesn't have protection keys. */ +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free + #endif /* _UAPI_SPARC_UNISTD_H */ diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 6aa3da152c20..44101196d02b 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -96,6 +96,7 @@ sparc64_boot: andn %g1, PSTATE_AM, %g1 wrpr %g1, 0x0, %pstate ba,a,pt %xcc, 1f + nop .globl prom_finddev_name, prom_chosen_path, prom_root_node .globl prom_getprop_name, prom_mmu_name, prom_peer_name @@ -613,6 +614,7 @@ niagara_tlb_fixup: nop ba,a,pt %xcc, 80f + nop niagara4_patch: call niagara4_patch_copyops nop @@ -622,6 +624,7 @@ niagara4_patch: nop ba,a,pt %xcc, 80f + nop niagara2_patch: call niagara2_patch_copyops @@ -632,6 +635,7 @@ niagara2_patch: nop ba,a,pt %xcc, 80f + nop niagara_patch: call niagara_patch_copyops diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S index 34b4933900bf..9276d2f0dd86 100644 --- a/arch/sparc/kernel/misctrap.S +++ b/arch/sparc/kernel/misctrap.S @@ -82,6 +82,7 @@ do_stdfmna: call handle_stdfmna add %sp, PTREGS_OFF, %o0 ba,a,pt %xcc, rtrap + nop .size do_stdfmna,.-do_stdfmna .type breakpoint_trap,#function diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index fc5124ccdb53..e1d965e90e16 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -1162,3 +1162,39 @@ int regs_query_register_offset(const char *name) return roff->offset; return -EINVAL; } + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static inline int regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS; + return ((addr & ~(THREAD_SIZE - 1)) == + (ksp & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS; + unsigned long *addr = (unsigned long *)ksp; + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 216948ca4382..709a82ebd294 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -237,6 +237,7 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 bne,pt %xcc, user_rtt_fill_32bit wrpr %g1, %cwp ba,a,pt %xcc, user_rtt_fill_64bit + nop user_rtt_fill_fixup_dax: ba,pt %xcc, user_rtt_fill_fixup_common diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S index 4a73009f66a5..d7e540842809 100644 --- a/arch/sparc/kernel/spiterrs.S +++ b/arch/sparc/kernel/spiterrs.S @@ -86,6 +86,7 @@ __spitfire_cee_trap_continue: rd %pc, %g7 ba,a,pt %xcc, 2f + nop 1: ba,pt %xcc, etrap_irq rd %pc, %g7 diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index 6179e19bc9b9..c19f352f46c7 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -352,6 +352,7 @@ sun4v_mna: call sun4v_do_mna add %sp, PTREGS_OFF, %o0 ba,a,pt %xcc, rtrap + nop /* Privileged Action. */ sun4v_privact: diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index eac7f0db5c8c..5253e895b81b 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -89,3 +89,4 @@ sys_call_table: /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen /*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 +/*360*/ .long sys_statx diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index b0f17ff2ddba..82339f6be0b2 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -90,6 +90,7 @@ sys_call_table32: .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2 +/*360*/ .word sys_statx #endif /* CONFIG_COMPAT */ @@ -171,3 +172,4 @@ sys_call_table: .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen .word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 +/*360*/ .word sys_statx diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S index 5604a2b051d4..364af3250646 100644 --- a/arch/sparc/kernel/urtt_fill.S +++ b/arch/sparc/kernel/urtt_fill.S @@ -92,6 +92,7 @@ user_rtt_fill_fixup_common: call sun4v_data_access_exception nop ba,a,pt %xcc, rtrap + nop 1: call spitfire_data_access_exception nop diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S index 855019a8590e..1ee173cc3c39 100644 --- a/arch/sparc/kernel/winfixup.S +++ b/arch/sparc/kernel/winfixup.S @@ -152,6 +152,8 @@ fill_fixup_dax: call sun4v_data_access_exception nop ba,a,pt %xcc, rtrap + nop 1: call spitfire_data_access_exception nop ba,a,pt %xcc, rtrap + nop diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index c629dbd121b6..64dcd6cdb606 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -326,11 +326,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ blu 170f nop ba,a,pt %xcc, 180f + nop 4: /* 32 <= low bits < 48 */ blu 150f nop ba,a,pt %xcc, 160f + nop 5: /* 0 < low bits < 32 */ blu,a 6f cmp %g2, 8 @@ -338,6 +340,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ blu 130f nop ba,a,pt %xcc, 140f + nop 6: /* 0 < low bits < 16 */ bgeu 120f nop @@ -475,6 +478,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %o2, 85f sub %o0, %o1, GLOBAL_SPARE ba,a,pt %XCC, 90f + nop .align 64 75: /* 16 < len <= 64 */ diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 75bb93b1437f..78ea962edcbe 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -530,4 +530,5 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ bne,pt %icc, 1b EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1) ba,a,pt %icc, .Lexit + nop .size FUNC_NAME, .-FUNC_NAME diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S index 41da4bdd95cb..7c0c81f18837 100644 --- a/arch/sparc/lib/NG4memset.S +++ b/arch/sparc/lib/NG4memset.S @@ -102,4 +102,5 @@ NG4bzero: bne,pt %icc, 1b add %o0, 0x30, %o0 ba,a,pt %icc, .Lpostloop + nop .size NG4bzero,.-NG4bzero diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S index d88c4ed50a00..cd654a719b27 100644 --- a/arch/sparc/lib/NGmemcpy.S +++ b/arch/sparc/lib/NGmemcpy.S @@ -394,6 +394,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ brz,pt %i2, 85f sub %o0, %i1, %i3 ba,a,pt %XCC, 90f + nop .align 64 70: /* 16 < len <= 64 */ diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 323bc6b6e3ad..7c29d38e6b99 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -143,6 +143,10 @@ static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift) pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V; switch (shift) { + case HPAGE_2GB_SHIFT: + hugepage_size = _PAGE_SZ2GB_4V; + pte_val(entry) |= _PAGE_PMD_HUGE; + break; case HPAGE_256MB_SHIFT: hugepage_size = _PAGE_SZ256MB_4V; pte_val(entry) |= _PAGE_PMD_HUGE; @@ -183,6 +187,9 @@ static unsigned int sun4v_huge_tte_to_shift(pte_t entry) unsigned int shift; switch (tte_szbits) { + case _PAGE_SZ2GB_4V: + shift = HPAGE_2GB_SHIFT; + break; case _PAGE_SZ256MB_4V: shift = HPAGE_256MB_SHIFT; break; @@ -261,7 +268,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, if (!pmd) return NULL; - if (sz == PMD_SHIFT) + if (sz >= PMD_SIZE) pte = (pte_t *)pmd; else pte = pte_alloc_map(mm, pmd, addr); @@ -454,6 +461,22 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index ccd455328989..0cda653ae007 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -337,6 +337,10 @@ static int __init setup_hugepagesz(char *string) hugepage_shift = ilog2(hugepage_size); switch (hugepage_shift) { + case HPAGE_2GB_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_2GB; + hv_pgsz_idx = HV_PGSZ_IDX_2GB; + break; case HPAGE_256MB_SHIFT: hv_pgsz_mask = HV_PGSZ_MASK_256MB; hv_pgsz_idx = HV_PGSZ_IDX_256MB; @@ -1563,7 +1567,7 @@ bool kern_addr_valid(unsigned long addr) if ((long)addr < 0L) { unsigned long pa = __pa(addr); - if ((addr >> max_phys_bits) != 0UL) + if ((pa >> max_phys_bits) != 0UL) return false; return pfn_valid(pa >> PAGE_SHIFT); diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index def82f6d626f..8e76ebba2986 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -54,6 +54,7 @@ enum mbus_module srmmu_modtype; static unsigned int hwbug_bitmask; int vac_cache_size; +EXPORT_SYMBOL(vac_cache_size); int vac_line_size; extern struct resource sparc_iomap; diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index afda3bbf7854..ee8066c3d96c 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -154,7 +154,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, if (pte_val(*pte) & _PAGE_VALID) { bool exec = pte_exec(*pte); - tlb_batch_add_one(mm, vaddr, exec, false); + tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT); } pte++; vaddr += PAGE_SIZE; @@ -209,9 +209,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pte_t orig_pte = __pte(pmd_val(orig)); bool exec = pte_exec(orig_pte); - tlb_batch_add_one(mm, addr, exec, true); + tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT); tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec, - true); + REAL_HPAGE_SHIFT); } else { tlb_batch_pmd_scan(mm, addr, orig); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 0a04811f06b7..bedf08b22a47 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -122,7 +122,7 @@ void flush_tsb_user(struct tlb_batch *tb) spin_lock_irqsave(&mm->context.lock, flags); - if (tb->hugepage_shift < HPAGE_SHIFT) { + if (tb->hugepage_shift < REAL_HPAGE_SHIFT) { base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) @@ -155,7 +155,7 @@ void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, spin_lock_irqsave(&mm->context.lock, flags); - if (hugepage_shift < HPAGE_SHIFT) { + if (hugepage_shift < REAL_HPAGE_SHIFT) { base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 81b321ace8e0..f924629836a8 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].to = msr_lastbranch.to; cpuc->lbr_entries[i].mispred = 0; cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].in_tx = 0; + cpuc->lbr_entries[i].abort = 0; + cpuc->lbr_entries[i].cycles = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index 2c1ebeb4d737..529bb4a6487a 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) - * instruction. + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. */ static inline void arch_wb_cache_pmem(void *addr, size_t size) { @@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size) clwb(p); } -/* - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec - * iterators, so for other types (bvec & kvec) we must do a cache write-back. - */ -static inline bool __iter_needs_pmem_wb(struct iov_iter *i) -{ - return iter_is_iovec(i) == false; -} - /** * arch_copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, /* TODO: skip the write-back by always using non-temporal stores */ len = copy_from_iter_nocache(addr, bytes, i); - if (__iter_needs_pmem_wb(i)) + /* + * In the iovec case on x86_64 copy_from_iter_nocache() uses + * non-temporal stores for the bulk of the transfer, but we need + * to manually flush if the transfer is unaligned. A cached + * memory copy is used when destination or size is not naturally + * aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + * + * In the non-iovec case the entire destination needs to be + * flushed. + */ + if (iter_is_iovec(i)) { + unsigned long flushed, dest = (unsigned long) addr; + + if (bytes < 8) { + if (!IS_ALIGNED(dest, 4) || (bytes != 4)) + arch_wb_cache_pmem(addr, 1); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + arch_wb_cache_pmem(addr, 1); + } + + flushed = dest - (unsigned long) addr; + if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) + arch_wb_cache_pmem(addr + bytes - 1, 1); + } + } else arch_wb_cache_pmem(addr, bytes); return len; diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 1e5a50c11d3c..217cd4449bc9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 903043e6a62b..19592ba1a320 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,7 +13,7 @@ enum severity_level { MCE_PANIC_SEVERITY, }; -extern struct atomic_notifier_head x86_mce_decoder_chain; +extern struct blocking_notifier_head x86_mce_decoder_chain; #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5accfbdee3f0..af44ebeb593f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -123,7 +123,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -220,7 +220,7 @@ void mce_register_decode_chain(struct notifier_block *nb) WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); - atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -228,7 +228,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb) { atomic_dec(&num_notifiers); - atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -321,18 +321,7 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { - int ret = 0; - __print_mce(m); - - /* - * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that) - */ - ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - if (ret == NOTIFY_STOP) - return; - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2ee00dbbbd51..259e9b28ccf8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8198,6 +8198,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); case EXIT_REASON_PREEMPTION_TIMER: return false; + case EXIT_REASON_PML_FULL: + /* We don't expose PML support to L1. */ + return false; default: return true; } @@ -10267,6 +10270,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } + if (enable_pml) { + /* + * Conceptually we want to copy the PML address and index from + * vmcs01 here, and then back to vmcs01 on nested vmexit. But, + * since we always flush the log on each vmexit, this happens + * to be equivalent to simply resetting the fields in vmcs02. + */ + ASSERT(vmx->pml_pg); + vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + if (nested_cpu_has_ept(vmcs12)) { kvm_mmu_unload(vcpu); nested_ept_init_mmu_context(vcpu); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 22af912d66d2..889e7619a091 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -643,21 +643,40 @@ void __init init_mem_mapping(void) * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains BIOS code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. + * On x86, access has to be given to the first megabyte of RAM because that + * area traditionally contains BIOS code and data regions used by X, dosemu, + * and similar apps. Since they map the entire memory range, the whole range + * must be allowed (for mapping), but any areas that would otherwise be + * disallowed are flagged as being "zero filled" instead of rejected. + * Access has to be given to non-kernel-ram areas as well, these contain the + * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr < 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + if (page_is_ram(pagenr)) { + /* + * For disallowed memory regions in the low 1MB range, + * request that the page be shown as all zeros. + */ + if (pagenr < 256) + return 2; + + return 0; + } + + /* + * This must follow RAM test, since System RAM is considered a + * restricted resource under CONFIG_STRICT_IOMEM. + */ + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { + /* Low 1MB bypasses iomem restrictions. */ + if (pagenr < 256) + return 1; + return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; + } + + return 1; } void free_init_pages(char *what, unsigned long begin, unsigned long end) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 30031d5293c4..cdfe8c628959 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -201,6 +201,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } + /* No need to reserve regions that will never be freed. */ + if (md.attribute & EFI_MEMORY_RUNTIME) + return; + size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 09af8ff18719..c974a1bbf4cb 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -171,7 +171,8 @@ void blk_mq_sched_put_request(struct request *rq) void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { - struct elevator_queue *e = hctx->queue->elevator; + struct request_queue *q = hctx->queue; + struct elevator_queue *e = q->elevator; const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request; bool did_work = false; LIST_HEAD(rq_list); @@ -203,10 +204,10 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); - did_work = blk_mq_dispatch_rq_list(hctx, &rq_list); + did_work = blk_mq_dispatch_rq_list(q, &rq_list); } else if (!has_sched_dispatch) { blk_mq_flush_busy_ctxs(hctx, &rq_list); - blk_mq_dispatch_rq_list(hctx, &rq_list); + blk_mq_dispatch_rq_list(q, &rq_list); } /* @@ -222,7 +223,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) if (!rq) break; list_add(&rq->queuelist, &rq_list); - } while (blk_mq_dispatch_rq_list(hctx, &rq_list)); + } while (blk_mq_dispatch_rq_list(q, &rq_list)); } } @@ -317,25 +318,68 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, return true; } -static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) +static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) { if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) { clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - if (blk_mq_hctx_has_pending(hctx)) + if (blk_mq_hctx_has_pending(hctx)) { blk_mq_run_hw_queue(hctx, true); + return true; + } } + return false; } -void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx) -{ - struct request_queue *q = hctx->queue; - unsigned int i; +/** + * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list + * @pos: loop cursor. + * @skip: the list element that will not be examined. Iteration starts at + * @skip->next. + * @head: head of the list to examine. This list must have at least one + * element, namely @skip. + * @member: name of the list_head structure within typeof(*pos). + */ +#define list_for_each_entry_rcu_rr(pos, skip, head, member) \ + for ((pos) = (skip); \ + (pos = (pos)->member.next != (head) ? list_entry_rcu( \ + (pos)->member.next, typeof(*pos), member) : \ + list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \ + (pos) != (skip); ) - if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) { - if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) { - queue_for_each_hw_ctx(q, hctx, i) - blk_mq_sched_restart_hctx(hctx); +/* + * Called after a driver tag has been freed to check whether a hctx needs to + * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware + * queues in a round-robin fashion if the tag set of @hctx is shared with other + * hardware queues. + */ +void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx) +{ + struct blk_mq_tags *const tags = hctx->tags; + struct blk_mq_tag_set *const set = hctx->queue->tag_set; + struct request_queue *const queue = hctx->queue, *q; + struct blk_mq_hw_ctx *hctx2; + unsigned int i, j; + + if (set->flags & BLK_MQ_F_TAG_SHARED) { + rcu_read_lock(); + list_for_each_entry_rcu_rr(q, queue, &set->tag_list, + tag_set_list) { + queue_for_each_hw_ctx(q, hctx2, i) + if (hctx2->tags == tags && + blk_mq_sched_restart_hctx(hctx2)) + goto done; + } + j = hctx->queue_num + 1; + for (i = 0; i < queue->nr_hw_queues; i++, j++) { + if (j == queue->nr_hw_queues) + j = 0; + hctx2 = queue->queue_hw_ctx[j]; + if (hctx2->tags == tags && + blk_mq_sched_restart_hctx(hctx2)) + break; } +done: + rcu_read_unlock(); } else { blk_mq_sched_restart_hctx(hctx); } @@ -431,11 +475,67 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, } } -int blk_mq_sched_setup(struct request_queue *q) +static int blk_mq_sched_alloc_tags(struct request_queue *q, + struct blk_mq_hw_ctx *hctx, + unsigned int hctx_idx) +{ + struct blk_mq_tag_set *set = q->tag_set; + int ret; + + hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, + set->reserved_tags); + if (!hctx->sched_tags) + return -ENOMEM; + + ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); + if (ret) + blk_mq_sched_free_tags(set, hctx, hctx_idx); + + return ret; +} + +static void blk_mq_sched_tags_teardown(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; - int ret, i; + int i; + + queue_for_each_hw_ctx(q, hctx, i) + blk_mq_sched_free_tags(set, hctx, i); +} + +int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, + unsigned int hctx_idx) +{ + struct elevator_queue *e = q->elevator; + + if (!e) + return 0; + + return blk_mq_sched_alloc_tags(q, hctx, hctx_idx); +} + +void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, + unsigned int hctx_idx) +{ + struct elevator_queue *e = q->elevator; + + if (!e) + return; + + blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx); +} + +int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) +{ + struct blk_mq_hw_ctx *hctx; + unsigned int i; + int ret; + + if (!e) { + q->elevator = NULL; + return 0; + } /* * Default to 256, since we don't split into sync/async like the @@ -443,49 +543,30 @@ int blk_mq_sched_setup(struct request_queue *q) */ q->nr_requests = 2 * BLKDEV_MAX_RQ; - /* - * We're switching to using an IO scheduler, so setup the hctx - * scheduler tags and switch the request map from the regular - * tags to scheduler tags. First allocate what we need, so we - * can safely fail and fallback, if needed. - */ - ret = 0; queue_for_each_hw_ctx(q, hctx, i) { - hctx->sched_tags = blk_mq_alloc_rq_map(set, i, - q->nr_requests, set->reserved_tags); - if (!hctx->sched_tags) { - ret = -ENOMEM; - break; - } - ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests); + ret = blk_mq_sched_alloc_tags(q, hctx, i); if (ret) - break; + goto err; } - /* - * If we failed, free what we did allocate - */ - if (ret) { - queue_for_each_hw_ctx(q, hctx, i) { - if (!hctx->sched_tags) - continue; - blk_mq_sched_free_tags(set, hctx, i); - } - - return ret; - } + ret = e->ops.mq.init_sched(q, e); + if (ret) + goto err; return 0; + +err: + blk_mq_sched_tags_teardown(q); + q->elevator = NULL; + return ret; } -void blk_mq_sched_teardown(struct request_queue *q) +void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) { - struct blk_mq_tag_set *set = q->tag_set; - struct blk_mq_hw_ctx *hctx; - int i; - - queue_for_each_hw_ctx(q, hctx, i) - blk_mq_sched_free_tags(set, hctx, i); + if (e->type->ops.mq.exit_sched) + e->type->ops.mq.exit_sched(e); + blk_mq_sched_tags_teardown(q); + q->elevator = NULL; } int blk_mq_sched_init(struct request_queue *q) diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index a75b16b123f7..3a9e6e40558b 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -19,7 +19,7 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio); bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); -void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx); +void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async, bool can_block); @@ -32,8 +32,13 @@ void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx, struct list_head *rq_list, struct request *(*get_rq)(struct blk_mq_hw_ctx *)); -int blk_mq_sched_setup(struct request_queue *q); -void blk_mq_sched_teardown(struct request_queue *q); +int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e); +void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e); + +int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, + unsigned int hctx_idx); +void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, + unsigned int hctx_idx); int blk_mq_sched_init(struct request_queue *q); @@ -131,20 +136,6 @@ static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } -/* - * Mark a hardware queue and the request queue it belongs to as needing a - * restart. - */ -static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx) -{ - struct request_queue *q = hctx->queue; - - if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) - set_bit(QUEUE_FLAG_RESTART, &q->queue_flags); -} - static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); diff --git a/block/blk-mq.c b/block/blk-mq.c index 6b6e7bc041db..c7836a1ded97 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -321,7 +321,6 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data); - blk_mq_put_ctx(alloc_data.ctx); blk_queue_exit(q); if (!rq) @@ -349,7 +348,7 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); if (sched_tag != -1) blk_mq_sched_completed_request(hctx, rq); - blk_mq_sched_restart_queues(hctx); + blk_mq_sched_restart(hctx); blk_queue_exit(q); } @@ -846,12 +845,8 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx, .flags = wait ? 0 : BLK_MQ_REQ_NOWAIT, }; - if (rq->tag != -1) { -done: - if (hctx) - *hctx = data.hctx; - return true; - } + if (rq->tag != -1) + goto done; if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag)) data.flags |= BLK_MQ_REQ_RESERVED; @@ -863,10 +858,12 @@ done: atomic_inc(&data.hctx->nr_active); } data.hctx->tags->rqs[rq->tag] = rq; - goto done; } - return false; +done: + if (hctx) + *hctx = data.hctx; + return rq->tag != -1; } static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, @@ -963,14 +960,17 @@ static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx) return true; } -bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list) +bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) { - struct request_queue *q = hctx->queue; + struct blk_mq_hw_ctx *hctx; struct request *rq; LIST_HEAD(driver_list); struct list_head *dptr; int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK; + if (list_empty(list)) + return false; + /* * Start off with dptr being NULL, so we start the first request * immediately, even if we have more pending. @@ -981,7 +981,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list) * Now process all the entries, sending them to the driver. */ errors = queued = 0; - while (!list_empty(list)) { + do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); @@ -1052,7 +1052,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list) */ if (!dptr && list->next != list->prev) dptr = &driver_list; - } + } while (!list_empty(list)); hctx->dispatched[queued_to_index(queued)]++; @@ -1135,7 +1135,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) return hctx->next_cpu; } -void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) +static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, + unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx) || !blk_mq_hw_queue_mapped(hctx))) @@ -1152,7 +1153,24 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) put_cpu(); } - kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work); + if (msecs == 0) + kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), + &hctx->run_work); + else + kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), + &hctx->delayed_run_work, + msecs_to_jiffies(msecs)); +} + +void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) +{ + __blk_mq_delay_run_hw_queue(hctx, true, msecs); +} +EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); + +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) +{ + __blk_mq_delay_run_hw_queue(hctx, async, 0); } void blk_mq_run_hw_queues(struct request_queue *q, bool async) @@ -1255,6 +1273,15 @@ static void blk_mq_run_work_fn(struct work_struct *work) __blk_mq_run_hw_queue(hctx); } +static void blk_mq_delayed_run_work_fn(struct work_struct *work) +{ + struct blk_mq_hw_ctx *hctx; + + hctx = container_of(work, struct blk_mq_hw_ctx, delayed_run_work.work); + + __blk_mq_run_hw_queue(hctx); +} + static void blk_mq_delay_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx; @@ -1924,6 +1951,8 @@ static void blk_mq_exit_hctx(struct request_queue *q, hctx->fq->flush_rq, hctx_idx, flush_start_tag + hctx_idx); + blk_mq_sched_exit_hctx(q, hctx, hctx_idx); + if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -1960,6 +1989,7 @@ static int blk_mq_init_hctx(struct request_queue *q, node = hctx->numa_node = set->numa_node; INIT_WORK(&hctx->run_work, blk_mq_run_work_fn); + INIT_DELAYED_WORK(&hctx->delayed_run_work, blk_mq_delayed_run_work_fn); INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); @@ -1990,9 +2020,12 @@ static int blk_mq_init_hctx(struct request_queue *q, set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto free_bitmap; + if (blk_mq_sched_init_hctx(q, hctx, hctx_idx)) + goto exit_hctx; + hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size); if (!hctx->fq) - goto exit_hctx; + goto sched_exit_hctx; if (set->ops->init_request && set->ops->init_request(set->driver_data, @@ -2007,6 +2040,8 @@ static int blk_mq_init_hctx(struct request_queue *q, free_fq: kfree(hctx->fq); + sched_exit_hctx: + blk_mq_sched_exit_hctx(q, hctx, hctx_idx); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -2233,8 +2268,6 @@ void blk_mq_release(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned int i; - blk_mq_sched_teardown(q); - /* hctx kobj stays in hctx */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx) @@ -2565,6 +2598,14 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) return 0; } +static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) +{ + if (set->ops->map_queues) + return set->ops->map_queues(set); + else + return blk_mq_map_queues(set); +} + /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the @@ -2619,10 +2660,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (!set->mq_map) goto out_free_tags; - if (set->ops->map_queues) - ret = set->ops->map_queues(set); - else - ret = blk_mq_map_queues(set); + ret = blk_mq_update_queue_map(set); if (ret) goto out_free_mq_map; @@ -2714,6 +2752,7 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) blk_mq_freeze_queue(q); set->nr_hw_queues = nr_hw_queues; + blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); @@ -2889,8 +2928,17 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie) hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; if (!blk_qc_t_is_internal(cookie)) rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); - else + else { rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); + /* + * With scheduling, if the request has completed, we'll + * get a NULL return here, as we clear the sched tag when + * that happens. The request still remains valid, like always, + * so we should be safe with just the NULL check. + */ + if (!rq) + return false; + } return __blk_mq_poll(hctx, rq); } diff --git a/block/blk-mq.h b/block/blk-mq.h index b79f9a7d8cf6..660a17e1d033 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -31,7 +31,7 @@ void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); -bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *); +bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx); bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx, diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index c44b321335f3..37f0b3ad635e 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -816,7 +816,7 @@ static void blk_release_queue(struct kobject *kobj) if (q->elevator) { ioc_clear_queue(q); - elevator_exit(q->elevator); + elevator_exit(q, q->elevator); } blk_exit_rl(&q->root_rl); diff --git a/block/elevator.c b/block/elevator.c index 01139f549b5b..4d9084a14c10 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -242,26 +242,21 @@ int elevator_init(struct request_queue *q, char *name) } } - if (e->uses_mq) { - err = blk_mq_sched_setup(q); - if (!err) - err = e->ops.mq.init_sched(q, e); - } else + if (e->uses_mq) + err = blk_mq_init_sched(q, e); + else err = e->ops.sq.elevator_init_fn(q, e); - if (err) { - if (e->uses_mq) - blk_mq_sched_teardown(q); + if (err) elevator_put(e); - } return err; } EXPORT_SYMBOL(elevator_init); -void elevator_exit(struct elevator_queue *e) +void elevator_exit(struct request_queue *q, struct elevator_queue *e) { mutex_lock(&e->sysfs_lock); if (e->uses_mq && e->type->ops.mq.exit_sched) - e->type->ops.mq.exit_sched(e); + blk_mq_exit_sched(q, e); else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn) e->type->ops.sq.elevator_exit_fn(e); mutex_unlock(&e->sysfs_lock); @@ -946,6 +941,45 @@ void elv_unregister(struct elevator_type *e) } EXPORT_SYMBOL_GPL(elv_unregister); +static int elevator_switch_mq(struct request_queue *q, + struct elevator_type *new_e) +{ + int ret; + + blk_mq_freeze_queue(q); + blk_mq_quiesce_queue(q); + + if (q->elevator) { + if (q->elevator->registered) + elv_unregister_queue(q); + ioc_clear_queue(q); + elevator_exit(q, q->elevator); + } + + ret = blk_mq_init_sched(q, new_e); + if (ret) + goto out; + + if (new_e) { + ret = elv_register_queue(q); + if (ret) { + elevator_exit(q, q->elevator); + goto out; + } + } + + if (new_e) + blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name); + else + blk_add_trace_msg(q, "elv switch: none"); + +out: + blk_mq_unfreeze_queue(q); + blk_mq_start_stopped_hw_queues(q, true); + return ret; + +} + /* * switch to new_e io scheduler. be careful not to introduce deadlocks - * we don't free the old io scheduler, before we have allocated what we @@ -958,10 +992,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) bool old_registered = false; int err; - if (q->mq_ops) { - blk_mq_freeze_queue(q); - blk_mq_quiesce_queue(q); - } + if (q->mq_ops) + return elevator_switch_mq(q, new_e); /* * Turn on BYPASS and drain all requests w/ elevator private data. @@ -973,11 +1005,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) if (old) { old_registered = old->registered; - if (old->uses_mq) - blk_mq_sched_teardown(q); - - if (!q->mq_ops) - blk_queue_bypass_start(q); + blk_queue_bypass_start(q); /* unregister and clear all auxiliary data of the old elevator */ if (old_registered) @@ -987,56 +1015,32 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) } /* allocate, init and register new elevator */ - if (new_e) { - if (new_e->uses_mq) { - err = blk_mq_sched_setup(q); - if (!err) - err = new_e->ops.mq.init_sched(q, new_e); - } else - err = new_e->ops.sq.elevator_init_fn(q, new_e); - if (err) - goto fail_init; + err = new_e->ops.sq.elevator_init_fn(q, new_e); + if (err) + goto fail_init; - err = elv_register_queue(q); - if (err) - goto fail_register; - } else - q->elevator = NULL; + err = elv_register_queue(q); + if (err) + goto fail_register; /* done, kill the old one and finish */ if (old) { - elevator_exit(old); - if (!q->mq_ops) - blk_queue_bypass_end(q); + elevator_exit(q, old); + blk_queue_bypass_end(q); } - if (q->mq_ops) { - blk_mq_unfreeze_queue(q); - blk_mq_start_stopped_hw_queues(q, true); - } - - if (new_e) - blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name); - else - blk_add_trace_msg(q, "elv switch: none"); + blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name); return 0; fail_register: - if (q->mq_ops) - blk_mq_sched_teardown(q); - elevator_exit(q->elevator); + elevator_exit(q, q->elevator); fail_init: /* switch failed, restore and re-register old elevator */ if (old) { q->elevator = old; elv_register_queue(q); - if (!q->mq_ops) - blk_queue_bypass_end(q); - } - if (q->mq_ops) { - blk_mq_unfreeze_queue(q); - blk_mq_start_stopped_hw_queues(q, true); + blk_queue_bypass_end(q); } return err; @@ -1094,12 +1098,20 @@ int elevator_change(struct request_queue *q, const char *name) } EXPORT_SYMBOL(elevator_change); +static inline bool elv_support_iosched(struct request_queue *q) +{ + if (q->mq_ops && q->tag_set && (q->tag_set->flags & + BLK_MQ_F_NO_SCHED)) + return false; + return true; +} + ssize_t elv_iosched_store(struct request_queue *q, const char *name, size_t count) { int ret; - if (!(q->mq_ops || q->request_fn)) + if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q)) return count; ret = __elevator_change(q, name); @@ -1131,7 +1143,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) len += sprintf(name+len, "[%s] ", elv->elevator_name); continue; } - if (__e->uses_mq && q->mq_ops) + if (__e->uses_mq && q->mq_ops && elv_support_iosched(q)) len += sprintf(name+len, "%s ", __e->elevator_name); else if (!__e->uses_mq && !q->mq_ops) len += sprintf(name+len, "%s ", __e->elevator_name); diff --git a/crypto/ahash.c b/crypto/ahash.c index e58c4970c22b..826cd7ab4d4a 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -32,6 +32,7 @@ struct ahash_request_priv { crypto_completion_t complete; void *data; u8 *result; + u32 flags; void *ubuf[] CRYPTO_MINALIGN_ATTR; }; @@ -253,6 +254,8 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) priv->result = req->result; priv->complete = req->base.complete; priv->data = req->base.data; + priv->flags = req->base.flags; + /* * WARNING: We do not backup req->priv here! The req->priv * is for internal use of the Crypto API and the @@ -267,38 +270,44 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) return 0; } -static void ahash_restore_req(struct ahash_request *req) +static void ahash_restore_req(struct ahash_request *req, int err) { struct ahash_request_priv *priv = req->priv; + if (!err) + memcpy(priv->result, req->result, + crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + /* Restore the original crypto request. */ req->result = priv->result; - req->base.complete = priv->complete; - req->base.data = priv->data; + + ahash_request_set_callback(req, priv->flags, + priv->complete, priv->data); req->priv = NULL; /* Free the req->priv.priv from the ADJUSTED request. */ kzfree(priv); } -static void ahash_op_unaligned_finish(struct ahash_request *req, int err) +static void ahash_notify_einprogress(struct ahash_request *req) { struct ahash_request_priv *priv = req->priv; + struct crypto_async_request oreq; - if (err == -EINPROGRESS) - return; - - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + oreq.data = priv->data; - ahash_restore_req(req); + priv->complete(&oreq, -EINPROGRESS); } static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + /* * Restore the original request, see ahash_op_unaligned() for what * goes where. @@ -309,7 +318,7 @@ static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) */ /* First copy req->result into req->priv.result */ - ahash_op_unaligned_finish(areq, err); + ahash_restore_req(areq, err); /* Complete the ORIGINAL request. */ areq->base.complete(&areq->base, err); @@ -325,7 +334,12 @@ static int ahash_op_unaligned(struct ahash_request *req, return err; err = op(req); - ahash_op_unaligned_finish(req, err); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + + ahash_restore_req(req, err); return err; } @@ -360,25 +374,14 @@ int crypto_ahash_digest(struct ahash_request *req) } EXPORT_SYMBOL_GPL(crypto_ahash_digest); -static void ahash_def_finup_finish2(struct ahash_request *req, int err) +static void ahash_def_finup_done2(struct crypto_async_request *req, int err) { - struct ahash_request_priv *priv = req->priv; + struct ahash_request *areq = req->data; if (err == -EINPROGRESS) return; - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); - - ahash_restore_req(req); -} - -static void ahash_def_finup_done2(struct crypto_async_request *req, int err) -{ - struct ahash_request *areq = req->data; - - ahash_def_finup_finish2(areq, err); + ahash_restore_req(areq, err); areq->base.complete(&areq->base, err); } @@ -389,11 +392,15 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err) goto out; req->base.complete = ahash_def_finup_done2; - req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = crypto_ahash_reqtfm(req)->final(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; out: - ahash_def_finup_finish2(req, err); + ahash_restore_req(req, err); return err; } @@ -401,7 +408,16 @@ static void ahash_def_finup_done1(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + + areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = ahash_def_finup_finish1(areq, err); + if (areq->priv) + return; areq->base.complete(&areq->base, err); } @@ -416,6 +432,11 @@ static int ahash_def_finup(struct ahash_request *req) return err; err = tfm->update(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + return ahash_def_finup_finish1(req, err); } diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 5a8053758657..ef59d9926ee9 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -40,6 +40,7 @@ struct aead_async_req { struct aead_async_rsgl first_rsgl; struct list_head list; struct kiocb *iocb; + struct sock *sk; unsigned int tsgls; char iv[]; }; @@ -379,12 +380,10 @@ unlock: static void aead_async_cb(struct crypto_async_request *_req, int err) { - struct sock *sk = _req->data; - struct alg_sock *ask = alg_sk(sk); - struct aead_ctx *ctx = ask->private; - struct crypto_aead *tfm = crypto_aead_reqtfm(&ctx->aead_req); - struct aead_request *req = aead_request_cast(_req); + struct aead_request *req = _req->data; + struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aead_async_req *areq = GET_ASYM_REQ(req, tfm); + struct sock *sk = areq->sk; struct scatterlist *sg = areq->tsgl; struct aead_async_rsgl *rsgl; struct kiocb *iocb = areq->iocb; @@ -447,11 +446,12 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, memset(&areq->first_rsgl, '\0', sizeof(areq->first_rsgl)); INIT_LIST_HEAD(&areq->list); areq->iocb = msg->msg_iocb; + areq->sk = sk; memcpy(areq->iv, ctx->iv, crypto_aead_ivsize(tfm)); aead_request_set_tfm(req, tfm); aead_request_set_ad(req, ctx->aead_assoclen); aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - aead_async_cb, sk); + aead_async_cb, req); used -= ctx->aead_assoclen; /* take over all tx sgls from ctx */ diff --git a/crypto/lrw.c b/crypto/lrw.c index 3ea095adafd9..a8bfae4451bf 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -345,6 +345,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -352,6 +359,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } @@ -389,6 +397,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -396,6 +411,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } diff --git a/crypto/xts.c b/crypto/xts.c index c976bfac29da..89ace5ebc2da 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -286,6 +286,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -293,6 +300,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } @@ -330,6 +338,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -337,6 +352,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c index c86bae7b1d0f..ff096d9755b9 100644 --- a/drivers/acpi/acpica/utresrc.c +++ b/drivers/acpi/acpica/utresrc.c @@ -421,10 +421,8 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state, ACPI_FUNCTION_TRACE(ut_walk_aml_resources); - /* - * The absolute minimum resource template is one end_tag descriptor. - * However, we will treat a lone end_tag as just a simple buffer. - */ + /* The absolute minimum resource template is one end_tag descriptor */ + if (aml_length < sizeof(struct aml_resource_end_tag)) { return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG); } @@ -456,8 +454,9 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state, /* Invoke the user function */ if (user_function) { - status = user_function(aml, length, offset, - resource_index, context); + status = + user_function(aml, length, offset, resource_index, + context); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } @@ -481,12 +480,6 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state, *context = aml; } - /* Check if buffer is defined to be longer than the resource length */ - - if (aml_length > (offset + length)) { - return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG); - } - /* Normal exit */ return_ACPI_STATUS(AE_OK); diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index fb19e1cdb641..edc8663b5db3 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -99,13 +99,13 @@ static int find_child_checks(struct acpi_device *adev, bool check_children) return -ENODEV; /* - * If the device has a _HID (or _CID) returning a valid ACPI/PNP - * device ID, it is better to make it look less attractive here, so that - * the other device with the same _ADR value (that may not have a valid - * device ID) can be matched going forward. [This means a second spec - * violation in a row, so whatever we do here is best effort anyway.] + * If the device has a _HID returning a valid ACPI/PNP device ID, it is + * better to make it look less attractive here, so that the other device + * with the same _ADR value (that may not have a valid device ID) can be + * matched going forward. [This means a second spec violation in a row, + * so whatever we do here is best effort anyway.] */ - return sta_present && list_empty(&adev->pnp.ids) ? + return sta_present && !adev->pnp.type.platform_id ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE; } diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 662036bdc65e..c8ea9d698cd0 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1617,7 +1617,11 @@ static int cmp_map(const void *m0, const void *m1) const struct nfit_set_info_map *map0 = m0; const struct nfit_set_info_map *map1 = m1; - return map0->region_offset - map1->region_offset; + if (map0->region_offset < map1->region_offset) + return -1; + else if (map0->region_offset > map1->region_offset) + return 1; + return 0; } /* Retrieve the nth entry referencing this spa */ diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index fcd4ce6f78d5..1c2b846c5776 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return -EINVAL; /* The state of the list is 'on' IFF all resources are 'on'. */ + cur_state = 0; list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; acpi_handle handle = resource->device.handle; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 192691880d55..2433569b02ef 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1857,15 +1857,20 @@ static void acpi_bus_attach(struct acpi_device *device) return; device->flags.match_driver = true; - if (!ret) { - ret = device_attach(&device->dev); - if (ret < 0) - return; - - if (!ret && device->pnp.type.platform_id) - acpi_default_enumeration(device); + if (ret > 0) { + acpi_device_set_enumerated(device); + goto ok; } + ret = device_attach(&device->dev); + if (ret < 0) + return; + + if (ret > 0 || !device->pnp.type.platform_id) + acpi_device_set_enumerated(device); + else + acpi_default_enumeration(device); + ok: list_for_each_entry(child, &device->children, node) acpi_bus_attach(child); diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c index 6c9aa95a9a05..49d705c9f0f7 100644 --- a/drivers/ata/pata_atiixp.c +++ b/drivers/ata/pata_atiixp.c @@ -278,11 +278,6 @@ static int atiixp_init_one(struct pci_dev *pdev, const struct pci_device_id *id) }; const struct ata_port_info *ppi[] = { &info, &info }; - /* SB600/700 don't have secondary port wired */ - if ((pdev->device == PCI_DEVICE_ID_ATI_IXP600_IDE) || - (pdev->device == PCI_DEVICE_ID_ATI_IXP700_IDE)) - ppi[1] = &ata_dummy_port_info; - return ata_pci_bmdma_init_one(pdev, ppi, &atiixp_sht, NULL, ATA_HOST_PARALLEL_SCAN); } diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c index 0636d84fbefe..f3f538eec7b3 100644 --- a/drivers/ata/sata_via.c +++ b/drivers/ata/sata_via.c @@ -644,14 +644,16 @@ static void svia_configure(struct pci_dev *pdev, int board_id, pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8); } - /* enable IRQ on hotplug */ - pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8); - if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) { - dev_dbg(&pdev->dev, - "enabling SATA hotplug (0x%x)\n", - (int) tmp8); - tmp8 |= SATA_HOTPLUG; - pci_write_config_byte(pdev, SVIA_MISC_3, tmp8); + if (board_id == vt6421) { + /* enable IRQ on hotplug */ + pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8); + if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) { + dev_dbg(&pdev->dev, + "enabling SATA hotplug (0x%x)\n", + (int) tmp8); + tmp8 |= SATA_HOTPLUG; + pci_write_config_byte(pdev, SVIA_MISC_3, tmp8); + } } /* diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index f96ab717534c..1d1dc11aa5fa 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3969,7 +3969,7 @@ static int mtip_block_initialize(struct driver_data *dd) dd->tags.reserved_tags = 1; dd->tags.cmd_size = sizeof(struct mtip_cmd); dd->tags.numa_node = dd->numa_node; - dd->tags.flags = BLK_MQ_F_SHOULD_MERGE; + dd->tags.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_SCHED; dd->tags.driver_data = dd; dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index dceb5edd1e54..0c09d4256108 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -523,7 +523,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index) cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO); if (size == PAGE_SIZE) { - copy_page(mem, cmem); + memcpy(mem, cmem, PAGE_SIZE); } else { struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp); @@ -717,7 +717,7 @@ compress_again: if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) { src = kmap_atomic(page); - copy_page(cmem, src); + memcpy(cmem, src, PAGE_SIZE); kunmap_atomic(src); } else { memcpy(cmem, src, clen); @@ -928,7 +928,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, } index = sector >> SECTORS_PER_PAGE_SHIFT; - offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT; + offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; bv.bv_page = page; bv.bv_len = PAGE_SIZE; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 6d9cc2d39d22..7e4a9d1296bb 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -60,6 +60,10 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) #endif #ifdef CONFIG_STRICT_DEVMEM +static inline int page_is_allowed(unsigned long pfn) +{ + return devmem_is_allowed(pfn); +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { u64 from = ((u64)pfn) << PAGE_SHIFT; @@ -75,6 +79,10 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) return 1; } #else +static inline int page_is_allowed(unsigned long pfn) +{ + return 1; +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { return 1; @@ -122,23 +130,31 @@ static ssize_t read_mem(struct file *file, char __user *buf, while (count > 0) { unsigned long remaining; + int allowed; sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, count)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; + if (allowed == 2) { + /* Show zeros for restricted memory. */ + remaining = clear_user(buf, sz); + } else { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) + return -EFAULT; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) - return -EFAULT; + remaining = copy_to_user(buf, ptr, sz); + + unxlate_dev_mem_ptr(p, ptr); + } - remaining = copy_to_user(buf, ptr, sz); - unxlate_dev_mem_ptr(p, ptr); if (remaining) return -EFAULT; @@ -181,30 +197,36 @@ static ssize_t write_mem(struct file *file, const char __user *buf, #endif while (count > 0) { + int allowed; + sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, sz)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) { - if (written) - break; - return -EFAULT; - } + /* Skip actual writing when a page is marked as restricted. */ + if (allowed == 1) { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) { + if (written) + break; + return -EFAULT; + } - copied = copy_from_user(ptr, buf, sz); - unxlate_dev_mem_ptr(p, ptr); - if (copied) { - written += sz - copied; - if (written) - break; - return -EFAULT; + copied = copy_from_user(ptr, buf, sz); + unxlate_dev_mem_ptr(p, ptr); + if (copied) { + written += sz - copied; + if (written) + break; + return -EFAULT; + } } buf += sz; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index e9b7e0b3cabe..87fe111d0be6 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2202,14 +2202,16 @@ static int virtcons_freeze(struct virtio_device *vdev) vdev->config->reset(vdev); - virtqueue_disable_cb(portdev->c_ivq); + if (use_multiport(portdev)) + virtqueue_disable_cb(portdev->c_ivq); cancel_work_sync(&portdev->control_work); cancel_work_sync(&portdev->config_work); /* * Once more: if control_work_handler() was running, it would * enable the cb as the last step. */ - virtqueue_disable_cb(portdev->c_ivq); + if (use_multiport(portdev)) + virtqueue_disable_cb(portdev->c_ivq); remove_controlq_data(portdev); list_for_each_entry(port, &portdev->ports, list) { diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c index ab609a76706f..cf9449b3dbd9 100644 --- a/drivers/clk/clk-stm32f4.c +++ b/drivers/clk/clk-stm32f4.c @@ -429,6 +429,13 @@ static const struct clk_div_table pll_divp_table[] = { { 0, 2 }, { 1, 4 }, { 2, 6 }, { 3, 8 }, { 0 } }; +static const struct clk_div_table pll_divq_table[] = { + { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, + { 8, 8 }, { 9, 9 }, { 10, 10 }, { 11, 11 }, { 12, 12 }, { 13, 13 }, + { 14, 14 }, { 15, 15 }, + { 0 } +}; + static const struct clk_div_table pll_divr_table[] = { { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, { 0 } }; @@ -496,9 +503,9 @@ struct stm32f4_div_data { #define MAX_PLL_DIV 3 static const struct stm32f4_div_data div_data[MAX_PLL_DIV] = { - { 16, 2, 0, pll_divp_table }, - { 24, 4, CLK_DIVIDER_ONE_BASED, NULL }, - { 28, 3, 0, pll_divr_table }, + { 16, 2, 0, pll_divp_table }, + { 24, 4, 0, pll_divq_table }, + { 28, 3, 0, pll_divr_table }, }; struct stm32f4_pll_data { diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index 72109d2cf41b..a077ab6edffa 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -1,6 +1,7 @@ config SUNXI_CCU bool "Clock support for Allwinner SoCs" depends on ARCH_SUNXI || COMPILE_TEST + select RESET_CONTROLLER default ARCH_SUNXI if SUNXI_CCU @@ -15,7 +16,7 @@ config SUNXI_CCU_FRAC bool config SUNXI_CCU_GATE - bool + def_bool y config SUNXI_CCU_MUX bool @@ -135,6 +136,7 @@ config SUN8I_V3S_CCU config SUN9I_A80_CCU bool "Support for the Allwinner A80 CCU" select SUNXI_CCU_DIV + select SUNXI_CCU_MULT select SUNXI_CCU_GATE select SUNXI_CCU_NKMP select SUNXI_CCU_NM diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c index a7b3c08ed0e2..2c69b631967a 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c @@ -752,6 +752,13 @@ static const struct sunxi_ccu_desc sun8i_a33_ccu_desc = { .num_resets = ARRAY_SIZE(sun8i_a33_ccu_resets), }; +static struct ccu_pll_nb sun8i_a33_pll_cpu_nb = { + .common = &pll_cpux_clk.common, + /* copy from pll_cpux_clk */ + .enable = BIT(31), + .lock = BIT(28), +}; + static struct ccu_mux_nb sun8i_a33_cpu_nb = { .common = &cpux_clk.common, .cm = &cpux_clk.mux, @@ -783,6 +790,10 @@ static void __init sun8i_a33_ccu_setup(struct device_node *node) sunxi_ccu_probe(node, reg, &sun8i_a33_ccu_desc); + /* Gate then ungate PLL CPU after any rate changes */ + ccu_pll_notifier_register(&sun8i_a33_pll_cpu_nb); + + /* Reparent CPU during PLL CPU rate changes */ ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, &sun8i_a33_cpu_nb); } diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index 8a47bafd7890..9d8724715a43 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -14,11 +14,13 @@ * GNU General Public License for more details. */ +#include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> #include <linux/slab.h> #include "ccu_common.h" +#include "ccu_gate.h" #include "ccu_reset.h" static DEFINE_SPINLOCK(ccu_lock); @@ -39,6 +41,53 @@ void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock) WARN_ON(readl_relaxed_poll_timeout(addr, reg, reg & lock, 100, 70000)); } +/* + * This clock notifier is called when the frequency of a PLL clock is + * changed. In common PLL designs, changes to the dividers take effect + * almost immediately, while changes to the multipliers (implemented + * as dividers in the feedback loop) take a few cycles to work into + * the feedback loop for the PLL to stablize. + * + * Sometimes when the PLL clock rate is changed, the decrease in the + * divider is too much for the decrease in the multiplier to catch up. + * The PLL clock rate will spike, and in some cases, might lock up + * completely. + * + * This notifier callback will gate and then ungate the clock, + * effectively resetting it, so it proceeds to work. Care must be + * taken to reparent consumers to other temporary clocks during the + * rate change, and that this notifier callback must be the first + * to be registered. + */ +static int ccu_pll_notifier_cb(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct ccu_pll_nb *pll = to_ccu_pll_nb(nb); + int ret = 0; + + if (event != POST_RATE_CHANGE) + goto out; + + ccu_gate_helper_disable(pll->common, pll->enable); + + ret = ccu_gate_helper_enable(pll->common, pll->enable); + if (ret) + goto out; + + ccu_helper_wait_for_lock(pll->common, pll->lock); + +out: + return notifier_from_errno(ret); +} + +int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb) +{ + pll_nb->clk_nb.notifier_call = ccu_pll_notifier_cb; + + return clk_notifier_register(pll_nb->common->hw.clk, + &pll_nb->clk_nb); +} + int sunxi_ccu_probe(struct device_node *node, void __iomem *reg, const struct sunxi_ccu_desc *desc) { diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h index 73d81dc58fc5..d6fdd7a789aa 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -83,6 +83,18 @@ struct sunxi_ccu_desc { void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock); +struct ccu_pll_nb { + struct notifier_block clk_nb; + struct ccu_common *common; + + u32 enable; + u32 lock; +}; + +#define to_ccu_pll_nb(_nb) container_of(_nb, struct ccu_pll_nb, clk_nb) + +int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb); + int sunxi_ccu_probe(struct device_node *node, void __iomem *reg, const struct sunxi_ccu_desc *desc); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index bc96d423781a..0e3f6496524d 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2398,6 +2398,20 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled); *********************************************************************/ static enum cpuhp_state hp_online; +static int cpuhp_cpufreq_online(unsigned int cpu) +{ + cpufreq_online(cpu); + + return 0; +} + +static int cpuhp_cpufreq_offline(unsigned int cpu) +{ + cpufreq_offline(cpu); + + return 0; +} + /** * cpufreq_register_driver - register a CPU Frequency driver * @driver_data: A struct cpufreq_driver containing the values# @@ -2460,8 +2474,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) } ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online", - cpufreq_online, - cpufreq_offline); + cpuhp_cpufreq_online, + cpuhp_cpufreq_offline); if (ret < 0) goto err_if_unreg; hp_online = ret; diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index 32100c4851dd..49cbdcba7883 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -506,7 +506,7 @@ static int caam_rsa_init_tfm(struct crypto_akcipher *tfm) ctx->dev = caam_jr_alloc(); if (IS_ERR(ctx->dev)) { - dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n"); + pr_err("Job Ring Device allocation for transform failed\n"); return PTR_ERR(ctx->dev); } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index fef39f9f41ee..5d7f73d60515 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -281,7 +281,8 @@ static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask) /* Try to run it through DECO0 */ ret = run_descriptor_deco0(ctrldev, desc, &status); - if (ret || status) { + if (ret || + (status && status != JRSTA_SSRC_JUMP_HALT_CC)) { dev_err(ctrldev, "Failed to deinstantiate RNG4 SH%d\n", sh_idx); @@ -301,15 +302,13 @@ static int caam_remove(struct platform_device *pdev) struct device *ctrldev; struct caam_drv_private *ctrlpriv; struct caam_ctrl __iomem *ctrl; - int ring; ctrldev = &pdev->dev; ctrlpriv = dev_get_drvdata(ctrldev); ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl; - /* Remove platform devices for JobRs */ - for (ring = 0; ring < ctrlpriv->total_jobrs; ring++) - of_device_unregister(ctrlpriv->jrpdev[ring]); + /* Remove platform devices under the crypto node */ + of_platform_depopulate(ctrldev); /* De-initialize RNG state handles initialized by this driver. */ if (ctrlpriv->rng4_sh_init) @@ -418,10 +417,21 @@ DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n"); #endif +static const struct of_device_id caam_match[] = { + { + .compatible = "fsl,sec-v4.0", + }, + { + .compatible = "fsl,sec4.0", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, caam_match); + /* Probe routine for CAAM top (controller) level */ static int caam_probe(struct platform_device *pdev) { - int ret, ring, ridx, rspec, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN; + int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN; u64 caam_id; struct device *dev; struct device_node *nprop, *np; @@ -597,47 +607,24 @@ static int caam_probe(struct platform_device *pdev) goto iounmap_ctrl; } - /* - * Detect and enable JobRs - * First, find out how many ring spec'ed, allocate references - * for all, then go probe each one. - */ - rspec = 0; - for_each_available_child_of_node(nprop, np) - if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") || - of_device_is_compatible(np, "fsl,sec4.0-job-ring")) - rspec++; - - ctrlpriv->jrpdev = devm_kcalloc(&pdev->dev, rspec, - sizeof(*ctrlpriv->jrpdev), GFP_KERNEL); - if (ctrlpriv->jrpdev == NULL) { - ret = -ENOMEM; + ret = of_platform_populate(nprop, caam_match, NULL, dev); + if (ret) { + dev_err(dev, "JR platform devices creation error\n"); goto iounmap_ctrl; } ring = 0; - ridx = 0; - ctrlpriv->total_jobrs = 0; for_each_available_child_of_node(nprop, np) if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") || of_device_is_compatible(np, "fsl,sec4.0-job-ring")) { - ctrlpriv->jrpdev[ring] = - of_platform_device_create(np, NULL, dev); - if (!ctrlpriv->jrpdev[ring]) { - pr_warn("JR physical index %d: Platform device creation error\n", - ridx); - ridx++; - continue; - } ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *) ((__force uint8_t *)ctrl + - (ridx + JR_BLOCK_NUMBER) * + (ring + JR_BLOCK_NUMBER) * BLOCK_OFFSET ); ctrlpriv->total_jobrs++; ring++; - ridx++; - } + } /* Check to see if QI present. If so, enable */ ctrlpriv->qi_present = @@ -847,17 +834,6 @@ disable_caam_ipg: return ret; } -static struct of_device_id caam_match[] = { - { - .compatible = "fsl,sec-v4.0", - }, - { - .compatible = "fsl,sec4.0", - }, - {}, -}; -MODULE_DEVICE_TABLE(of, caam_match); - static struct platform_driver caam_driver = { .driver = { .name = "caam", diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h index e2bcacc1a921..dbed8baeebe5 100644 --- a/drivers/crypto/caam/intern.h +++ b/drivers/crypto/caam/intern.h @@ -66,7 +66,6 @@ struct caam_drv_private_jr { struct caam_drv_private { struct device *dev; - struct platform_device **jrpdev; /* Alloc'ed array per sub-device */ struct platform_device *pdev; /* Physical-presence section */ diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 3e2ab3b14eea..9e95bf94eb13 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -2,6 +2,7 @@ menuconfig DEV_DAX tristate "DAX: direct access to differentiated memory" default m if NVDIMM_DAX depends on TRANSPARENT_HUGEPAGE + select SRCU help Support raw access to differentiated (persistence, bandwidth, latency...) memory via an mmap(2) capable character diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 80c6db279ae1..806f180c80d8 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -25,6 +25,7 @@ #include "dax.h" static dev_t dax_devt; +DEFINE_STATIC_SRCU(dax_srcu); static struct class *dax_class; static DEFINE_IDA(dax_minor_ida); static int nr_dax = CONFIG_NR_DEV_DAX; @@ -60,7 +61,7 @@ struct dax_region { * @region - parent region * @dev - device backing the character device * @cdev - core chardev data - * @alive - !alive + rcu grace period == no new mappings can be established + * @alive - !alive + srcu grace period == no new mappings can be established * @id - child id in the region * @num_resources - number of physical address extents in this device * @res - array of physical address ranges @@ -569,7 +570,7 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) static int dax_dev_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size) { - int rc; + int rc, id; struct file *filp = vmf->vma->vm_file; struct dax_dev *dax_dev = filp->private_data; @@ -578,7 +579,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf, ? "write" : "read", vmf->vma->vm_start, vmf->vma->vm_end); - rcu_read_lock(); + id = srcu_read_lock(&dax_srcu); switch (pe_size) { case PE_SIZE_PTE: rc = __dax_dev_pte_fault(dax_dev, vmf); @@ -592,7 +593,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf, default: return VM_FAULT_FALLBACK; } - rcu_read_unlock(); + srcu_read_unlock(&dax_srcu, id); return rc; } @@ -713,11 +714,11 @@ static void unregister_dax_dev(void *dev) * Note, rcu is not protecting the liveness of dax_dev, rcu is * ensuring that any fault handlers that might have seen * dax_dev->alive == true, have completed. Any fault handlers - * that start after synchronize_rcu() has started will abort + * that start after synchronize_srcu() has started will abort * upon seeing dax_dev->alive == false. */ dax_dev->alive = false; - synchronize_rcu(); + synchronize_srcu(&dax_srcu); unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1); cdev_del(cdev); device_unregister(dev); diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c index 932742e4cf23..24c461dea7af 100644 --- a/drivers/firmware/efi/libstub/gop.c +++ b/drivers/firmware/efi/libstub/gop.c @@ -149,7 +149,8 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, status = __gop_query32(sys_table_arg, gop32, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + if (status == EFI_SUCCESS && (!first_gop || conout_found) && + info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may * provide multiple GOP devices, not all of which are @@ -266,7 +267,8 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, status = __gop_query64(sys_table_arg, gop64, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + if (status == EFI_SUCCESS && (!first_gop || conout_found) && + info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may * provide multiple GOP devices, not all of which are diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index da48819ff2e6..b78d9239e48f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1317,7 +1317,7 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, if (!fence) { event_free(gpu, event); ret = -ENOMEM; - goto out_pm_put; + goto out_unlock; } gpu->event[event].fence = fence; @@ -1357,6 +1357,7 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, hangcheck_timer_reset(gpu); ret = 0; +out_unlock: mutex_unlock(&gpu->lock); out_pm_put: diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index b7d7721e72fa..40af17ec6312 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -285,9 +285,6 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset, { int ret; - if (vgpu->failsafe) - return 0; - if (WARN_ON(bytes > 4)) return -EINVAL; diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index f1f426a97aa9..d186c157f65f 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -775,7 +775,8 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, int ring_id) _EL_OFFSET_STATUS_PTR); ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg); - ctx_status_ptr.read_ptr = ctx_status_ptr.write_ptr = 0x7; + ctx_status_ptr.read_ptr = 0; + ctx_status_ptr.write_ptr = 0x7; vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw; } diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 933a7c211a1c..dce8d15f706f 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -75,11 +75,11 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) struct gvt_firmware_header *h; void *firmware; void *p; - unsigned long size; + unsigned long size, crc32_start; int i; int ret; - size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1; + size = sizeof(*h) + info->mmio_size + info->cfg_space_size; firmware = vzalloc(size); if (!firmware) return -ENOMEM; @@ -112,6 +112,9 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) memcpy(gvt->firmware.mmio, p, info->mmio_size); + crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4; + h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start); + firmware_attr.size = size; firmware_attr.private = firmware; @@ -234,7 +237,7 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt) firmware->mmio = mem; - sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state", + sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%02x.golden_hw_state", GVT_FIRMWARE_PATH, pdev->vendor, pdev->device, pdev->revision); diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 3b9d59e457ba..ef3baa0c4754 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -52,6 +52,8 @@ static const struct intel_gvt_ops intel_gvt_ops = { .vgpu_create = intel_gvt_create_vgpu, .vgpu_destroy = intel_gvt_destroy_vgpu, .vgpu_reset = intel_gvt_reset_vgpu, + .vgpu_activate = intel_gvt_activate_vgpu, + .vgpu_deactivate = intel_gvt_deactivate_vgpu, }; /** diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 6dfc48b63b71..becae2fa3b29 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -382,7 +382,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu); void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, unsigned int engine_mask); void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu); - +void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu); +void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu); /* validating GM functions */ #define vgpu_gmadr_is_aperture(vgpu, gmadr) \ @@ -449,6 +450,8 @@ struct intel_gvt_ops { struct intel_vgpu_type *); void (*vgpu_destroy)(struct intel_vgpu *); void (*vgpu_reset)(struct intel_vgpu *); + void (*vgpu_activate)(struct intel_vgpu *); + void (*vgpu_deactivate)(struct intel_vgpu *); }; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index d641214578a7..e466259034e2 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -544,6 +544,8 @@ static int intel_vgpu_open(struct mdev_device *mdev) if (ret) goto undo_group; + intel_gvt_ops->vgpu_activate(vgpu); + atomic_set(&vgpu->vdev.released, 0); return ret; @@ -569,6 +571,8 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu) if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1)) return; + intel_gvt_ops->vgpu_deactivate(vgpu); + ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY, &vgpu->vdev.iommu_notifier); WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret); @@ -1340,13 +1344,6 @@ static int kvmgt_guest_init(struct mdev_device *mdev) static bool kvmgt_guest_exit(struct kvmgt_guest_info *info) { - struct intel_vgpu *vgpu = info->vgpu; - - if (!info) { - gvt_vgpu_err("kvmgt_guest_info invalid\n"); - return false; - } - kvm_page_track_unregister_notifier(info->kvm, &info->track_node); kvm_put_kvm(info->kvm); kvmgt_protect_table_destroy(info); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 41cfa5ccae84..649ef280cc9a 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -72,7 +72,7 @@ static struct { char *name; } vgpu_types[] = { /* Fixed vGPU type table */ - { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" }, + { MB_TO_BYTES(64), MB_TO_BYTES(384), 4, GVT_EDID_1024_768, "8" }, { MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" }, { MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" }, { MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" }, @@ -179,20 +179,34 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) } /** - * intel_gvt_destroy_vgpu - destroy a virtual GPU + * intel_gvt_active_vgpu - activate a virtual GPU * @vgpu: virtual GPU * - * This function is called when user wants to destroy a virtual GPU. + * This function is called when user wants to activate a virtual GPU. * */ -void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) +void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) +{ + mutex_lock(&vgpu->gvt->lock); + vgpu->active = true; + mutex_unlock(&vgpu->gvt->lock); +} + +/** + * intel_gvt_deactive_vgpu - deactivate a virtual GPU + * @vgpu: virtual GPU + * + * This function is called when user wants to deactivate a virtual GPU. + * All virtual GPU runtime information will be destroyed. + * + */ +void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; mutex_lock(&gvt->lock); vgpu->active = false; - idr_remove(&gvt->vgpu_idr, vgpu->id); if (atomic_read(&vgpu->running_workload_num)) { mutex_unlock(&gvt->lock); @@ -201,6 +215,26 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) } intel_vgpu_stop_schedule(vgpu); + + mutex_unlock(&gvt->lock); +} + +/** + * intel_gvt_destroy_vgpu - destroy a virtual GPU + * @vgpu: virtual GPU + * + * This function is called when user wants to destroy a virtual GPU. + * + */ +void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) +{ + struct intel_gvt *gvt = vgpu->gvt; + + mutex_lock(&gvt->lock); + + WARN(vgpu->active, "vGPU is still active!\n"); + + idr_remove(&gvt->vgpu_idr, vgpu->id); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_gvt_context(vgpu); intel_vgpu_clean_execlist(vgpu); @@ -277,7 +311,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_shadow_ctx; - vgpu->active = true; mutex_unlock(&gvt->lock); return vgpu; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 1c75402a59c1..5c089b3c2a7e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1434,8 +1434,6 @@ static int i915_drm_suspend(struct drm_device *dev) goto out; } - intel_guc_suspend(dev_priv); - intel_display_suspend(dev); intel_dp_mst_suspend(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 1e53c31b6826..46fcd8b7080a 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -806,6 +806,7 @@ struct intel_csr { func(has_resource_streamer); \ func(has_runtime_pm); \ func(has_snoop); \ + func(unfenced_needs_alignment); \ func(cursor_needs_physical); \ func(hws_needs_physical); \ func(overlay_needs_physical); \ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 67b1fc5a0331..fe531f904062 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -4348,6 +4348,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) i915_gem_context_lost(dev_priv); mutex_unlock(&dev->struct_mutex); + intel_guc_suspend(dev_priv); + cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work); cancel_delayed_work_sync(&dev_priv->gt.retire_work); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 30e0675fd7da..15a15d00a6bf 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -888,6 +888,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *engine, struct list_head ordered_vmas; struct list_head pinned_vmas; bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4; + bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment; int retry; vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm; @@ -908,7 +909,8 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *engine, if (!has_fenced_gpu_access) entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE; need_fence = - entry->flags & EXEC_OBJECT_NEEDS_FENCE && + (entry->flags & EXEC_OBJECT_NEEDS_FENCE || + needs_unfenced_map) && i915_gem_object_is_tiled(obj); need_mappable = need_fence || need_reloc_mappable(vma); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 2801a4d56324..96e45a4d5441 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2704,7 +2704,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj, struct i915_ggtt *ggtt = &dev_priv->ggtt; if (unlikely(ggtt->do_idle_maps)) { - if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) { + if (i915_gem_wait_for_idle(dev_priv, 0)) { DRM_ERROR("Failed to wait for idle; VT'd may hang.\n"); /* Wait a bit, in hopes it avoids the hang */ udelay(10); diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index e7c3c0318ff6..da70bfe97ec5 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -37,6 +37,17 @@ static const char *i915_fence_get_driver_name(struct dma_fence *fence) static const char *i915_fence_get_timeline_name(struct dma_fence *fence) { + /* The timeline struct (as part of the ppgtt underneath a context) + * may be freed when the request is no longer in use by the GPU. + * We could extend the life of a context to beyond that of all + * fences, possibly keeping the hw resource around indefinitely, + * or we just give them a false name. Since + * dma_fence_ops.get_timeline_name is a debug feature, the occasional + * lie seems justifiable. + */ + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return "signaled"; + return to_request(fence)->timeline->common->name; } diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index d5d2b4c6ed38..70b3832a79dd 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -53,6 +53,17 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) BUG(); } +static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock) +{ + if (!unlock) + return; + + mutex_unlock(&dev->struct_mutex); + + /* expedite the RCU grace period to free some request slabs */ + synchronize_rcu_expedited(); +} + static bool any_vma_pinned(struct drm_i915_gem_object *obj) { struct i915_vma *vma; @@ -232,11 +243,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, intel_runtime_pm_put(dev_priv); i915_gem_retire_requests(dev_priv); - if (unlock) - mutex_unlock(&dev_priv->drm.struct_mutex); - /* expedite the RCU grace period to free some request slabs */ - synchronize_rcu_expedited(); + i915_gem_shrinker_unlock(&dev_priv->drm, unlock); return count; } @@ -293,8 +301,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; } - if (unlock) - mutex_unlock(&dev->struct_mutex); + i915_gem_shrinker_unlock(dev, unlock); return count; } @@ -321,8 +328,8 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) sc->nr_to_scan - freed, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); - if (unlock) - mutex_unlock(&dev->struct_mutex); + + i915_gem_shrinker_unlock(dev, unlock); return freed; } @@ -364,8 +371,7 @@ i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv, struct shrinker_lock_uninterruptible *slu) { dev_priv->mm.interruptible = slu->was_interruptible; - if (slu->unlock) - mutex_unlock(&dev_priv->drm.struct_mutex); + i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock); } static int diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index ecb487b5356f..9bbbd4e83e3c 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -60,6 +60,7 @@ .has_overlay = 1, .overlay_needs_physical = 1, \ .has_gmch_display = 1, \ .hws_needs_physical = 1, \ + .unfenced_needs_alignment = 1, \ .ring_mask = RENDER_RING, \ GEN_DEFAULT_PIPEOFFSETS, \ CURSOR_OFFSETS @@ -101,6 +102,7 @@ static const struct intel_device_info intel_i915g_info = { .platform = INTEL_I915G, .cursor_needs_physical = 1, .has_overlay = 1, .overlay_needs_physical = 1, .hws_needs_physical = 1, + .unfenced_needs_alignment = 1, }; static const struct intel_device_info intel_i915gm_info = { @@ -112,6 +114,7 @@ static const struct intel_device_info intel_i915gm_info = { .supports_tv = 1, .has_fbc = 1, .hws_needs_physical = 1, + .unfenced_needs_alignment = 1, }; static const struct intel_device_info intel_i945g_info = { @@ -120,6 +123,7 @@ static const struct intel_device_info intel_i945g_info = { .has_hotplug = 1, .cursor_needs_physical = 1, .has_overlay = 1, .overlay_needs_physical = 1, .hws_needs_physical = 1, + .unfenced_needs_alignment = 1, }; static const struct intel_device_info intel_i945gm_info = { @@ -130,6 +134,7 @@ static const struct intel_device_info intel_i945gm_info = { .supports_tv = 1, .has_fbc = 1, .hws_needs_physical = 1, + .unfenced_needs_alignment = 1, }; static const struct intel_device_info intel_g33_info = { diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index a1b7eec58be2..70964ca9251e 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1705,7 +1705,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, */ if (WARN_ON(stream->sample_flags != props->sample_flags)) { ret = -ENODEV; - goto err_alloc; + goto err_flags; } list_add(&stream->link, &dev_priv->perf.streams); @@ -1728,6 +1728,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, err_open: list_del(&stream->link); +err_flags: if (stream->ops->destroy) stream->ops->destroy(stream); err_alloc: @@ -1793,6 +1794,11 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv, if (ret) return ret; + if (id == 0 || id >= DRM_I915_PERF_PROP_MAX) { + DRM_DEBUG("Unknown i915 perf property ID\n"); + return -EINVAL; + } + switch ((enum drm_i915_perf_property_id)id) { case DRM_I915_PERF_PROP_CTX_HANDLE: props->single_context = 1; @@ -1862,9 +1868,8 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv, props->oa_periodic = true; props->oa_period_exponent = value; break; - default: + case DRM_I915_PERF_PROP_MAX: MISSING_CASE(id); - DRM_DEBUG("Unknown i915 perf property ID\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 471af3b480ad..47517a02f0a4 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -670,15 +670,14 @@ static void execlists_submit_request(struct drm_i915_gem_request *request) static struct intel_engine_cs * pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked) { - struct intel_engine_cs *engine; + struct intel_engine_cs *engine = + container_of(pt, struct drm_i915_gem_request, priotree)->engine; + + GEM_BUG_ON(!locked); - engine = container_of(pt, - struct drm_i915_gem_request, - priotree)->engine; if (engine != locked) { - if (locked) - spin_unlock_irq(&locked->timeline->lock); - spin_lock_irq(&engine->timeline->lock); + spin_unlock(&locked->timeline->lock); + spin_lock(&engine->timeline->lock); } return engine; @@ -686,7 +685,7 @@ pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked) static void execlists_schedule(struct drm_i915_gem_request *request, int prio) { - struct intel_engine_cs *engine = NULL; + struct intel_engine_cs *engine; struct i915_dependency *dep, *p; struct i915_dependency stack; LIST_HEAD(dfs); @@ -720,26 +719,23 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) list_for_each_entry_safe(dep, p, &dfs, dfs_link) { struct i915_priotree *pt = dep->signaler; - list_for_each_entry(p, &pt->signalers_list, signal_link) + /* Within an engine, there can be no cycle, but we may + * refer to the same dependency chain multiple times + * (redundant dependencies are not eliminated) and across + * engines. + */ + list_for_each_entry(p, &pt->signalers_list, signal_link) { + GEM_BUG_ON(p->signaler->priority < pt->priority); if (prio > READ_ONCE(p->signaler->priority)) list_move_tail(&p->dfs_link, &dfs); + } list_safe_reset_next(dep, p, dfs_link); - if (!RB_EMPTY_NODE(&pt->node)) - continue; - - engine = pt_lock_engine(pt, engine); - - /* If it is not already in the rbtree, we can update the - * priority inplace and skip over it (and its dependencies) - * if it is referenced *again* as we descend the dfs. - */ - if (prio > pt->priority && RB_EMPTY_NODE(&pt->node)) { - pt->priority = prio; - list_del_init(&dep->dfs_link); - } } + engine = request->engine; + spin_lock_irq(&engine->timeline->lock); + /* Fifo and depth-first replacement ensure our deps execute before us */ list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) { struct i915_priotree *pt = dep->signaler; @@ -751,16 +747,15 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) if (prio <= pt->priority) continue; - GEM_BUG_ON(RB_EMPTY_NODE(&pt->node)); - pt->priority = prio; - rb_erase(&pt->node, &engine->execlist_queue); - if (insert_request(pt, &engine->execlist_queue)) - engine->execlist_first = &pt->node; + if (!RB_EMPTY_NODE(&pt->node)) { + rb_erase(&pt->node, &engine->execlist_queue); + if (insert_request(pt, &engine->execlist_queue)) + engine->execlist_first = &pt->node; + } } - if (engine) - spin_unlock_irq(&engine->timeline->lock); + spin_unlock_irq(&engine->timeline->lock); /* XXX Do we need to preempt to make room for us and our deps? */ } @@ -1440,7 +1435,9 @@ static void reset_common_ring(struct intel_engine_cs *engine, GEM_BUG_ON(request->ctx != port[0].request->ctx); /* Reset WaIdleLiteRestore:bdw,skl as well */ - request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32); + request->tail = + intel_ring_wrap(request->ring, + request->wa_tail - WA_TAIL_DWORDS*sizeof(u32)); } static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 13dccb18cd43..8cb2078c5bfc 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -521,11 +521,17 @@ static inline void intel_ring_advance(struct intel_ring *ring) */ } +static inline u32 +intel_ring_wrap(const struct intel_ring *ring, u32 pos) +{ + return pos & (ring->size - 1); +} + static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr) { /* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */ u32 offset = addr - ring->vaddr; - return offset & (ring->size - 1); + return intel_ring_wrap(ring, offset); } int __intel_ring_space(int head, int tail, int size); diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 0b4440ffbeae..a9182d5e6011 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -995,7 +995,6 @@ nv50_wndw_atomic_destroy_state(struct drm_plane *plane, { struct nv50_wndw_atom *asyw = nv50_wndw_atom(state); __drm_atomic_helper_plane_destroy_state(&asyw->state); - dma_fence_put(asyw->state.fence); kfree(asyw); } @@ -1007,7 +1006,6 @@ nv50_wndw_atomic_duplicate_state(struct drm_plane *plane) if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL))) return NULL; __drm_atomic_helper_plane_duplicate_state(plane, &asyw->state); - asyw->state.fence = NULL; asyw->interval = 1; asyw->sema = armw->sema; asyw->ntfy = armw->ntfy; @@ -2036,6 +2034,7 @@ nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh) u32 vbackp = (mode->vtotal - mode->vsync_end) * vscan / ilace; u32 hfrontp = mode->hsync_start - mode->hdisplay; u32 vfrontp = (mode->vsync_start - mode->vdisplay) * vscan / ilace; + u32 blankus; struct nv50_head_mode *m = &asyh->mode; m->h.active = mode->htotal; @@ -2049,9 +2048,10 @@ nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh) m->v.blanks = m->v.active - vfrontp - 1; /*XXX: Safe underestimate, even "0" works */ - m->v.blankus = (m->v.active - mode->vdisplay - 2) * m->h.active; - m->v.blankus *= 1000; - m->v.blankus /= mode->clock; + blankus = (m->v.active - mode->vdisplay - 2) * m->h.active; + blankus *= 1000; + blankus /= mode->clock; + m->v.blankus = blankus; if (mode->flags & DRM_MODE_FLAG_INTERLACE) { m->v.blank2e = m->v.active + m->v.synce + vbackp; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 273562dd6bbd..3b86a7399567 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -714,7 +714,7 @@ nv4a_chipset = { .i2c = nv04_i2c_new, .imem = nv40_instmem_new, .mc = nv44_mc_new, - .mmu = nv44_mmu_new, + .mmu = nv04_mmu_new, .pci = nv40_pci_new, .therm = nv40_therm_new, .timer = nv41_timer_new, @@ -2271,6 +2271,35 @@ nv136_chipset = { .fifo = gp100_fifo_new, }; +static const struct nvkm_device_chip +nv137_chipset = { + .name = "GP107", + .bar = gf100_bar_new, + .bios = nvkm_bios_new, + .bus = gf100_bus_new, + .devinit = gm200_devinit_new, + .fb = gp102_fb_new, + .fuse = gm107_fuse_new, + .gpio = gk104_gpio_new, + .i2c = gm200_i2c_new, + .ibus = gm200_ibus_new, + .imem = nv50_instmem_new, + .ltc = gp100_ltc_new, + .mc = gp100_mc_new, + .mmu = gf100_mmu_new, + .pci = gp100_pci_new, + .pmu = gp102_pmu_new, + .timer = gk20a_timer_new, + .top = gk104_top_new, + .ce[0] = gp102_ce_new, + .ce[1] = gp102_ce_new, + .ce[2] = gp102_ce_new, + .ce[3] = gp102_ce_new, + .disp = gp102_disp_new, + .dma = gf119_dma_new, + .fifo = gp100_fifo_new, +}; + static int nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size, struct nvkm_notify *notify) @@ -2708,6 +2737,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x132: device->chip = &nv132_chipset; break; case 0x134: device->chip = &nv134_chipset; break; case 0x136: device->chip = &nv136_chipset; break; + case 0x137: device->chip = &nv137_chipset; break; default: nvdev_error(device, "unknown chipset (%08x)\n", boot0); goto done; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c index 003ac915eaad..8a8895246d26 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c @@ -198,7 +198,7 @@ nv31_mpeg_intr(struct nvkm_engine *engine) } if (type == 0x00000010) { - if (!nv31_mpeg_mthd(mpeg, mthd, data)) + if (nv31_mpeg_mthd(mpeg, mthd, data)) show &= ~0x01000000; } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c index e536f37e24b0..c3cf02ed468e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c @@ -172,7 +172,7 @@ nv44_mpeg_intr(struct nvkm_engine *engine) } if (type == 0x00000010) { - if (!nv44_mpeg_mthd(subdev->device, mthd, data)) + if (nv44_mpeg_mthd(subdev->device, mthd, data)) show &= ~0x01000000; } } diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c index 917dcb978c2c..0c87b1ac6b68 100644 --- a/drivers/gpu/drm/udl/udl_transfer.c +++ b/drivers/gpu/drm/udl/udl_transfer.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/fb.h> #include <linux/prefetch.h> +#include <asm/unaligned.h> #include <drm/drmP.h> #include "udl_drv.h" @@ -163,7 +164,7 @@ static void udl_compress_hline16( const u8 *const start = pixel; const uint16_t repeating_pixel_val16 = pixel_val16; - *(uint16_t *)cmd = cpu_to_be16(pixel_val16); + put_unaligned_be16(pixel_val16, cmd); cmd += 2; pixel += bpp; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 63ec1993eaaa..d162f0dc76e3 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -819,8 +819,7 @@ static int hid_scan_report(struct hid_device *hid) hid->group = HID_GROUP_WACOM; break; case USB_VENDOR_ID_SYNAPTICS: - if (hid->group == HID_GROUP_GENERIC || - hid->group == HID_GROUP_MULTITOUCH_WIN_8) + if (hid->group == HID_GROUP_GENERIC) if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC) && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER)) /* @@ -2096,6 +2095,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) }, { HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SMARTJOY_PLUS) }, { HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SUPER_JOY_BOX_3) }, { HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 4e2648c86c8c..b26c030926c1 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1028,6 +1028,9 @@ #define USB_DEVICE_ID_UGEE_TABLET_45 0x0045 #define USB_DEVICE_ID_YIYNOVA_TABLET 0x004d +#define USB_VENDOR_ID_UGEE 0x28bd +#define USB_DEVICE_ID_UGEE_TABLET_EX07S 0x0071 + #define USB_VENDOR_ID_UNITEC 0x227d #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0709 0x0709 #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19 0x0a19 diff --git a/drivers/hid/hid-uclogic.c b/drivers/hid/hid-uclogic.c index 1509d7287ff3..e3e6e5c893cc 100644 --- a/drivers/hid/hid-uclogic.c +++ b/drivers/hid/hid-uclogic.c @@ -977,6 +977,7 @@ static int uclogic_probe(struct hid_device *hdev, } break; case USB_DEVICE_ID_UGTIZER_TABLET_GP0610: + case USB_DEVICE_ID_UGEE_TABLET_EX07S: /* If this is the pen interface */ if (intf->cur_altsetting->desc.bInterfaceNumber == 1) { rc = uclogic_tablet_enable(hdev); @@ -1069,6 +1070,7 @@ static const struct hid_device_id uclogic_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) }, { } }; MODULE_DEVICE_TABLE(hid, uclogic_devices); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 94250c293be2..c68ac65db7ff 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2006,7 +2006,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field return; case HID_DG_TOOLSERIALNUMBER: wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= value; + wacom_wac->serial[0] |= (__u32)value; return; case WACOM_HID_WD_SENSE: wacom_wac->hid_data.sense_state = value; @@ -2176,6 +2176,16 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev, wacom_wac->hid_data.cc_index = field->index; wacom_wac->hid_data.cc_value_index = usage->usage_index; break; + case HID_DG_CONTACTID: + if ((field->logical_maximum - field->logical_minimum) < touch_max) { + /* + * The HID descriptor for G11 sensors leaves logical + * maximum set to '1' despite it being a multitouch + * device. Override to a sensible number. + */ + field->logical_maximum = 255; + } + break; } } diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index ca5759c0c318..43a6cb078193 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -370,10 +370,12 @@ static int hid_accel_3d_probe(struct platform_device *pdev) name = "accel_3d"; channel_spec = accel_3d_channels; channel_size = sizeof(accel_3d_channels); + indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels); } else { name = "gravity"; channel_spec = gravity_channels; channel_size = sizeof(gravity_channels); + indio_dev->num_channels = ARRAY_SIZE(gravity_channels); } ret = hid_sensor_parse_common_attributes(hsdev, hsdev->usage, &accel_state->common_attributes); @@ -395,7 +397,6 @@ static int hid_accel_3d_probe(struct platform_device *pdev) goto error_free_dev_mem; } - indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels); indio_dev->dev.parent = &pdev->dev; indio_dev->info = &accel_3d_info; indio_dev->name = name; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index d6c372bb433b..c17596f7ed2c 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -61,7 +61,7 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, ret = st->core.read_ec_sensors_data(indio_dev, 1 << idx, &data); if (ret < 0) break; - + ret = IIO_VAL_INT; *val = data; break; case IIO_CHAN_INFO_CALIBBIAS: @@ -76,7 +76,7 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++) st->core.calib[i] = st->core.resp->sensor_offset.offset[i]; - + ret = IIO_VAL_INT; *val = st->core.calib[idx]; break; case IIO_CHAN_INFO_SCALE: diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c index 7afdac42ed42..01e02b9926d4 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c @@ -379,6 +379,8 @@ int hid_sensor_parse_common_attributes(struct hid_sensor_hub_device *hsdev, { struct hid_sensor_hub_attribute_info timestamp; + s32 value; + int ret; hid_sensor_get_reporting_interval(hsdev, usage_id, st); @@ -417,6 +419,14 @@ int hid_sensor_parse_common_attributes(struct hid_sensor_hub_device *hsdev, st->sensitivity.index, st->sensitivity.report_id, timestamp.index, timestamp.report_id); + ret = sensor_hub_get_feature(hsdev, + st->power_state.report_id, + st->power_state.index, sizeof(value), &value); + if (ret < 0) + return ret; + if (value < 0) + return -EINVAL; + return 0; } EXPORT_SYMBOL(hid_sensor_parse_common_attributes); diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index f7fcfa886f72..821919dd245b 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -27,6 +27,7 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> #include <linux/regmap.h> +#include <linux/delay.h> #include "bmg160.h" #define BMG160_IRQ_NAME "bmg160_event" @@ -52,6 +53,9 @@ #define BMG160_DEF_BW 100 #define BMG160_REG_PMU_BW_RES BIT(7) +#define BMG160_GYRO_REG_RESET 0x14 +#define BMG160_GYRO_RESET_VAL 0xb6 + #define BMG160_REG_INT_MAP_0 0x17 #define BMG160_INT_MAP_0_BIT_ANY BIT(1) @@ -236,6 +240,14 @@ static int bmg160_chip_init(struct bmg160_data *data) int ret; unsigned int val; + /* + * Reset chip to get it in a known good state. A delay of 30ms after + * reset is required according to the datasheet. + */ + regmap_write(data->regmap, BMG160_GYRO_REG_RESET, + BMG160_GYRO_RESET_VAL); + usleep_range(30000, 30700); + ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val); if (ret < 0) { dev_err(dev, "Error reading reg_chip_id\n"); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d18ded45bedd..3ff91e02fee3 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -610,10 +610,9 @@ static ssize_t __iio_format_value(char *buf, size_t len, unsigned int type, tmp0 = (int)div_s64_rem(tmp, 1000000000, &tmp1); return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1)); case IIO_VAL_FRACTIONAL_LOG2: - tmp = (s64)vals[0] * 1000000000LL >> vals[1]; - tmp1 = do_div(tmp, 1000000000LL); - tmp0 = tmp; - return snprintf(buf, len, "%d.%09u", tmp0, tmp1); + tmp = shift_right((s64)vals[0] * 1000000000LL, vals[1]); + tmp0 = (int)div_s64_rem(tmp, 1000000000LL, &tmp1); + return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1)); case IIO_VAL_INT_MULTIPLE: { int i; diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 5f2680855552..fd0edca0e656 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -457,6 +457,7 @@ static const struct st_sensor_settings st_press_sensors_settings[] = { .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, .multi_read_bit = true, + .bootime = 2, }, }; diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 91cbe86b25c8..fcbed35e95a8 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -817,6 +817,7 @@ isert_post_recvm(struct isert_conn *isert_conn, u32 count) rx_wr->sg_list = &rx_desc->rx_sg; rx_wr->num_sge = 1; rx_wr->next = rx_wr + 1; + rx_desc->in_use = false; } rx_wr--; rx_wr->next = NULL; /* mark end of work requests list */ @@ -835,6 +836,15 @@ isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc) struct ib_recv_wr *rx_wr_failed, rx_wr; int ret; + if (!rx_desc->in_use) { + /* + * if the descriptor is not in-use we already reposted it + * for recv, so just silently return + */ + return 0; + } + + rx_desc->in_use = false; rx_wr.wr_cqe = &rx_desc->rx_cqe; rx_wr.sg_list = &rx_desc->rx_sg; rx_wr.num_sge = 1; @@ -1397,6 +1407,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } + rx_desc->in_use = true; + ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr, ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); @@ -1659,10 +1671,23 @@ isert_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) ret = isert_check_pi_status(cmd, isert_cmd->rw.sig->sig_mr); isert_rdma_rw_ctx_destroy(isert_cmd, isert_conn); - if (ret) - transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0); - else - isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd); + if (ret) { + /* + * transport_generic_request_failure() expects to have + * plus two references to handle queue-full, so re-add + * one here as target-core will have already dropped + * it after the first isert_put_datain() callback. + */ + kref_get(&cmd->cmd_kref); + transport_generic_request_failure(cmd, cmd->pi_err); + } else { + /* + * XXX: isert_put_response() failure is not retried. + */ + ret = isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd); + if (ret) + pr_warn_ratelimited("isert_put_response() ret: %d\n", ret); + } } static void @@ -1699,13 +1724,15 @@ isert_rdma_read_done(struct ib_cq *cq, struct ib_wc *wc) cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT; spin_unlock_bh(&cmd->istate_lock); - if (ret) { - target_put_sess_cmd(se_cmd); - transport_send_check_condition_and_sense(se_cmd, - se_cmd->pi_err, 0); - } else { + /* + * transport_generic_request_failure() will drop the extra + * se_cmd->cmd_kref reference after T10-PI error, and handle + * any non-zero ->queue_status() callback error retries. + */ + if (ret) + transport_generic_request_failure(se_cmd, se_cmd->pi_err); + else target_execute_cmd(se_cmd); - } } static void @@ -2171,26 +2198,28 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) chain_wr = &isert_cmd->tx_desc.send_wr; } - isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr); - isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ\n", isert_cmd); - return 1; + rc = isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr); + isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ rc: %d\n", + isert_cmd, rc); + return rc; } static int isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); + int ret; isert_dbg("Cmd: %p RDMA_READ data_length: %u write_data_done: %u\n", isert_cmd, cmd->se_cmd.data_length, cmd->write_data_done); isert_cmd->tx_desc.tx_cqe.done = isert_rdma_read_done; - isert_rdma_rw_ctx_post(isert_cmd, conn->context, - &isert_cmd->tx_desc.tx_cqe, NULL); + ret = isert_rdma_rw_ctx_post(isert_cmd, conn->context, + &isert_cmd->tx_desc.tx_cqe, NULL); - isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n", - isert_cmd); - return 0; + isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE rc: %d\n", + isert_cmd, ret); + return ret; } static int diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index c02ada57d7f5..87d994de8c91 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -60,7 +60,7 @@ #define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \ (ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \ - sizeof(struct ib_cqe))) + sizeof(struct ib_cqe) + sizeof(bool))) #define ISCSI_ISER_SG_TABLESIZE 256 @@ -85,6 +85,7 @@ struct iser_rx_desc { u64 dma_addr; struct ib_sge rx_sg; struct ib_cqe rx_cqe; + bool in_use; char pad[ISER_RX_PAD_SIZE]; } __packed; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 155fcb3b6230..153b1ee13e03 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -202,6 +202,7 @@ static const struct xpad_device { { 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 }, { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 }, + { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 }, @@ -326,6 +327,7 @@ static struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */ XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */ + XPAD_XBOXONE_VENDOR(0x1532), /* Razer Wildcat */ XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index efc8ec342351..e73d968023f7 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1118,6 +1118,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) @@ -1524,6 +1525,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"), + }, + }, + { /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 312bd6ca9198..09720d950686 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -620,6 +620,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "20046"), }, }, + { + /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), + }, + }, { } }; diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 15af9a9753e5..2d203b422129 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -230,6 +230,8 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node, return -ENOMEM; } + raw_spin_lock_init(&cd->rlock); + cd->gpc_base = of_iomap(node, 0); if (!cd->gpc_base) { pr_err("fsl-gpcv2: unable to map gpc registers\n"); diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 1dfd1085a04f..9ca691d6c13b 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -1032,6 +1032,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data) sizeof(avmb1_carddef)))) return -EFAULT; cdef.cardtype = AVM_CARDTYPE_B1; + cdef.cardnr = 0; } else { if ((retval = copy_from_user(&cdef, data, sizeof(avmb1_extcarddef)))) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index e4c2c1a1e993..6735c8d6a445 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -932,7 +932,7 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd, *result = true; r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root, - from_cblock(begin), &cmd->dirty_cursor); + from_cblock(cmd->cache_blocks), &cmd->dirty_cursor); if (r) { DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__); return r; @@ -959,14 +959,16 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd, return 0; } + begin = to_cblock(from_cblock(begin) + 1); + if (begin == end) + break; + r = dm_bitset_cursor_next(&cmd->dirty_cursor); if (r) { DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__); dm_bitset_cursor_end(&cmd->dirty_cursor); return r; } - - begin = to_cblock(from_cblock(begin) + 1); } dm_bitset_cursor_end(&cmd->dirty_cursor); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index f8564d63982f..1e217ba84d09 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3726,7 +3726,7 @@ static int raid_preresume(struct dm_target *ti) return r; /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */ - if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && + if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) { r = bitmap_resize(mddev->bitmap, mddev->dev_sectors, to_bytes(rs->requested_bitmap_chunk_sectors), 0); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 28955b94d2b2..0b081d170087 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -755,6 +755,7 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, /* Undo dm_start_request() before requeuing */ rq_end_stats(md, rq); rq_completed(md, rq_data_dir(rq), false); + blk_mq_delay_run_hw_queue(hctx, 100/*ms*/); return BLK_MQ_RQ_QUEUE_BUSY; } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 0f0eb8a3d922..78f36012eaca 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -146,8 +146,6 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, block = fec_buffer_rs_block(v, fio, n, i); res = fec_decode_rs8(v, fio, block, &par[offset], neras); if (res < 0) { - dm_bufio_release(buf); - r = res; goto error; } @@ -172,6 +170,8 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, done: r = corrected; error: + dm_bufio_release(buf); + if (r < 0 && neras) DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", v->data_dev->name, (unsigned long long)rsb, r); @@ -269,7 +269,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, &is_zero) == 0) { /* skip known zero blocks entirely */ if (is_zero) - continue; + goto done; /* * skip if we have already found the theoretical @@ -439,6 +439,13 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, if (!verity_fec_is_enabled(v)) return -EOPNOTSUPP; + if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) { + DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name); + return -EIO; + } + + fio->level++; + if (type == DM_VERITY_BLOCK_TYPE_METADATA) block += v->data_blocks; @@ -470,7 +477,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, if (r < 0) { r = fec_decode_rsb(v, io, fio, rsb, offset, true); if (r < 0) - return r; + goto done; } if (dest) @@ -480,6 +487,8 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, r = verity_for_bv_block(v, io, iter, fec_bv_copy); } +done: + fio->level--; return r; } @@ -520,6 +529,7 @@ void verity_fec_init_io(struct dm_verity_io *io) memset(fio->bufs, 0, sizeof(fio->bufs)); fio->nbufs = 0; fio->output = NULL; + fio->level = 0; } /* diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 7fa0298b995e..bb31ce87a933 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -27,6 +27,9 @@ #define DM_VERITY_FEC_BUF_MAX \ (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) +/* maximum recursion level for verity_fec_decode */ +#define DM_VERITY_FEC_MAX_RECURSION 4 + #define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" #define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" #define DM_VERITY_OPT_FEC_START "fec_start" @@ -58,6 +61,7 @@ struct dm_verity_fec_io { unsigned nbufs; /* number of buffers allocated */ u8 *output; /* buffer for corrected output */ size_t output_pos; + unsigned level; /* recursion level */ }; #ifdef CONFIG_DM_VERITY_FEC diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index e992a7f8a16f..2b32b88949ba 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -267,7 +267,7 @@ static void sdio_release_func(struct device *dev) sdio_free_func_cis(func); kfree(func->info); - + kfree(func->tmpbuf); kfree(func); } @@ -282,6 +282,16 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card) if (!func) return ERR_PTR(-ENOMEM); + /* + * allocate buffer separately to make sure it's properly aligned for + * DMA usage (incl. 64 bit DMA) + */ + func->tmpbuf = kmalloc(4, GFP_KERNEL); + if (!func->tmpbuf) { + kfree(func); + return ERR_PTR(-ENOMEM); + } + func->card = card; device_initialize(&func->dev); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index a9ac0b457313..8718432751c5 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -22,6 +22,7 @@ #include <linux/ioport.h> #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/stat.h> @@ -1621,10 +1622,16 @@ static void dw_mci_init_card(struct mmc_host *mmc, struct mmc_card *card) if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) { - set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + if (!test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) { + pm_runtime_get_noresume(mmc->parent); + set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + } clk_en_a = clk_en_a_old & ~clken_low_pwr; } else { - clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + if (test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) { + pm_runtime_put_noidle(mmc->parent); + clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + } clk_en_a = clk_en_a_old | clken_low_pwr; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 7123ef96ed18..445fc47dc3e7 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -830,6 +830,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host, switch (uhs) { case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_DDR50: pinctrl = imx_data->pins_100mhz; break; case MMC_TIMING_UHS_SDR104: diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 0134ba32a057..39712560b4c1 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, return err; } - if (bytes == 0) { - err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); - if (err) - return err; + err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); + if (err) + return err; + if (bytes == 0) { err = clear_update_marker(ubi, vol, 0); if (err) return err; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8a4ba8b88e52..34481c9be1d1 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1104,11 +1104,11 @@ static void bond_compute_features(struct bonding *bond) gso_max_size = min(gso_max_size, slave->dev->gso_max_size); gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs); } + bond_dev->hard_header_len = max_hard_header_len; done: bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL; - bond_dev->hard_header_len = max_hard_header_len; bond_dev->gso_max_segs = gso_max_segs; netif_set_gso_max_size(bond_dev, gso_max_size); diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 138f5ae75c0b..4d1fe8d95042 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -557,7 +557,7 @@ static int ifi_canfd_poll(struct napi_struct *napi, int quota) int work_done = 0; u32 stcmd = readl(priv->base + IFI_CANFD_STCMD); - u32 rxstcmd = readl(priv->base + IFI_CANFD_STCMD); + u32 rxstcmd = readl(priv->base + IFI_CANFD_RXSTCMD); u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR); /* Handle bus state changes */ diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index caed4e6960f8..11662f479e76 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -826,8 +826,7 @@ static int rcar_can_probe(struct platform_device *pdev) devm_can_led_init(ndev); - dev_info(&pdev->dev, "device registered (regs @ %p, IRQ%d)\n", - priv->regs, ndev->irq); + dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq); return 0; fail_candev: diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index 8483a40e7e9e..5f9e0e6301d0 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -72,6 +72,8 @@ config CAN_PEAK_USB PCAN-USB Pro dual CAN 2.0b channels USB adapter PCAN-USB FD single CAN-FD channel USB adapter PCAN-USB Pro FD dual CAN-FD channels USB adapter + PCAN-Chip USB CAN-FD to USB stamp module + PCAN-USB X6 6 CAN-FD channels USB adapter (see also http://www.peak-system.com). diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 300349fe8dc0..eecee7f8dfb7 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -739,13 +739,18 @@ static const struct net_device_ops gs_usb_netdev_ops = { static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) { struct gs_can *dev = netdev_priv(netdev); - struct gs_identify_mode imode; + struct gs_identify_mode *imode; int rc; + imode = kmalloc(sizeof(*imode), GFP_KERNEL); + + if (!imode) + return -ENOMEM; + if (do_identify) - imode.mode = GS_CAN_IDENTIFY_ON; + imode->mode = GS_CAN_IDENTIFY_ON; else - imode.mode = GS_CAN_IDENTIFY_OFF; + imode->mode = GS_CAN_IDENTIFY_OFF; rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), @@ -755,10 +760,12 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) USB_RECIP_INTERFACE, dev->channel, 0, - &imode, - sizeof(imode), + imode, + sizeof(*imode), 100); + kfree(imode); + return (rc > 0) ? 0 : rc; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 0b0302af3bd2..57913dbbae0a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -39,6 +39,7 @@ static struct usb_device_id peak_usb_table[] = { {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBCHIP_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)}, {} /* Terminating entry */ }; @@ -51,6 +52,7 @@ static const struct peak_usb_adapter *const peak_usb_adapters_list[] = { &pcan_usb_pro, &pcan_usb_fd, &pcan_usb_pro_fd, + &pcan_usb_chip, &pcan_usb_x6, }; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index 3cbfb069893d..c01316cac354 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -27,6 +27,7 @@ #define PCAN_USBPRO_PRODUCT_ID 0x000d #define PCAN_USBPROFD_PRODUCT_ID 0x0011 #define PCAN_USBFD_PRODUCT_ID 0x0012 +#define PCAN_USBCHIP_PRODUCT_ID 0x0013 #define PCAN_USBX6_PRODUCT_ID 0x0014 #define PCAN_USB_DRIVER_NAME "peak_usb" @@ -90,6 +91,7 @@ struct peak_usb_adapter { extern const struct peak_usb_adapter pcan_usb; extern const struct peak_usb_adapter pcan_usb_pro; extern const struct peak_usb_adapter pcan_usb_fd; +extern const struct peak_usb_adapter pcan_usb_chip; extern const struct peak_usb_adapter pcan_usb_pro_fd; extern const struct peak_usb_adapter pcan_usb_x6; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 304732550f0a..528d3bb4917f 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -1061,6 +1061,78 @@ const struct peak_usb_adapter pcan_usb_fd = { .do_get_berr_counter = pcan_usb_fd_get_berr_counter, }; +/* describes the PCAN-CHIP USB */ +static const struct can_bittiming_const pcan_usb_chip_const = { + .name = "pcan_chip_usb", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), + .brp_inc = 1, +}; + +static const struct can_bittiming_const pcan_usb_chip_data_const = { + .name = "pcan_chip_usb", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), + .brp_inc = 1, +}; + +const struct peak_usb_adapter pcan_usb_chip = { + .name = "PCAN-Chip USB", + .device_id = PCAN_USBCHIP_PRODUCT_ID, + .ctrl_count = PCAN_USBFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = &pcan_usb_chip_const, + .data_bittiming_const = &pcan_usb_chip_data_const, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; + /* describes the PCAN-USB Pro FD adapter */ static const struct can_bittiming_const pcan_usb_pro_fd_const = { .name = "pcan_usb_pro_fd", diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 8cf4801994e8..fa0eece21eef 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -326,6 +326,7 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid, static void b53_set_forwarding(struct b53_device *dev, int enable) { + struct dsa_switch *ds = dev->ds; u8 mgmt; b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt); @@ -336,6 +337,15 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) mgmt &= ~SM_SW_FWD_EN; b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt); + + /* Include IMP port in dumb forwarding mode when no tagging protocol is + * set + */ + if (ds->ops->get_tag_protocol(ds) == DSA_TAG_PROTO_NONE) { + b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt); + mgmt |= B53_MII_DUMB_FWDG_EN; + b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); + } } static void b53_enable_vlan(struct b53_device *dev, bool enable) @@ -598,7 +608,8 @@ static void b53_switch_reset_gpio(struct b53_device *dev) static int b53_switch_reset(struct b53_device *dev) { - u8 mgmt; + unsigned int timeout = 1000; + u8 mgmt, reg; b53_switch_reset_gpio(dev); @@ -607,6 +618,28 @@ static int b53_switch_reset(struct b53_device *dev) b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x00); } + /* This is specific to 58xx devices here, do not use is58xx() which + * covers the larger Starfigther 2 family, including 7445/7278 which + * still use this driver as a library and need to perform the reset + * earlier. + */ + if (dev->chip_id == BCM58XX_DEVICE_ID) { + b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, ®); + reg |= SW_RST | EN_SW_RST | EN_CH_RST; + b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, reg); + + do { + b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, ®); + if (!(reg & SW_RST)) + break; + + usleep_range(1000, 2000); + } while (timeout-- > 0); + + if (timeout == 0) + return -ETIMEDOUT; + } + b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt); if (!(mgmt & SM_SW_FWD_EN)) { @@ -1731,7 +1764,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .vlans = 4096, .enabled_ports = 0x1ff, .arl_entries = 4, - .cpu_port = B53_CPU_PORT_25, + .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 9fd24c418fa4..e5c86d44667a 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -104,6 +104,10 @@ #define B53_UC_FWD_EN BIT(6) #define B53_MC_FWD_EN BIT(7) +/* Switch control (8 bit) */ +#define B53_SWITCH_CTRL 0x22 +#define B53_MII_DUMB_FWDG_EN BIT(6) + /* (16 bit) */ #define B53_UC_FLOOD_MASK 0x32 #define B53_MC_FLOOD_MASK 0x34 @@ -139,6 +143,7 @@ /* Software reset register (8 bit) */ #define B53_SOFTRESET 0x79 #define SW_RST BIT(7) +#define EN_CH_RST BIT(6) #define EN_SW_RST BIT(4) /* Fast Aging Control register (8 bit) */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index d05fbfdce5e5..5d6c40d86775 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -100,11 +100,6 @@ static int aq_ndev_change_mtu(struct net_device *ndev, int new_mtu) goto err_exit; ndev->mtu = new_mtu; - if (netif_running(ndev)) { - aq_ndev_close(ndev); - aq_ndev_open(ndev); - } - err_exit: return err; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index ee78444bfb88..cdb02991f249 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -487,6 +487,9 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, dx_buff->mss = skb_shinfo(skb)->gso_size; dx_buff->is_txc = 1U; + dx_buff->is_ipv6 = + (ip_hdr(skb)->version == 6) ? 1U : 0U; + dx = aq_ring_next_dx(ring, dx); dx_buff = &ring->buff_ring[dx]; ++ret; @@ -510,10 +513,22 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, if (skb->ip_summed == CHECKSUM_PARTIAL) { dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ? 1U : 0U; - dx_buff->is_tcp_cso = - (ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U; - dx_buff->is_udp_cso = - (ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U; + + if (ip_hdr(skb)->version == 4) { + dx_buff->is_tcp_cso = + (ip_hdr(skb)->protocol == IPPROTO_TCP) ? + 1U : 0U; + dx_buff->is_udp_cso = + (ip_hdr(skb)->protocol == IPPROTO_UDP) ? + 1U : 0U; + } else if (ip_hdr(skb)->version == 6) { + dx_buff->is_tcp_cso = + (ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ? + 1U : 0U; + dx_buff->is_udp_cso = + (ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ? + 1U : 0U; + } } for (; nr_frags--; ++frag_count) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 0358e6072d45..3a8a4aa13687 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -101,6 +101,7 @@ int aq_ring_init(struct aq_ring_s *self) self->hw_head = 0; self->sw_head = 0; self->sw_tail = 0; + spin_lock_init(&self->header.lock); return 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 257254645068..eecd6d1c4d73 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -58,7 +58,8 @@ struct __packed aq_ring_buff_s { u8 len_l2; u8 len_l3; u8 len_l4; - u8 rsvd2; + u8 is_ipv6:1; + u8 rsvd2:7; u32 len_pkt; }; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index a2b746a2dd50..4ee15ff06a44 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -433,6 +433,9 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self, buff->len_l3 + buff->len_l2); is_gso = true; + + if (buff->is_ipv6) + txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6; } else { buff_pa_len = buff->len; @@ -458,6 +461,7 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self, if (unlikely(buff->is_eop)) { txd->ctl |= HW_ATL_A0_TXD_CTL_EOP; txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB; + is_gso = false; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index cab2931dab9a..42150708191d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -471,6 +471,9 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, buff->len_l3 + buff->len_l2); is_gso = true; + + if (buff->is_ipv6) + txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6; } else { buff_pa_len = buff->len; @@ -496,6 +499,7 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, if (unlikely(buff->is_eop)) { txd->ctl |= HW_ATL_B0_TXD_CTL_EOP; txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB; + is_gso = false; } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 0a23034bbe3f..352beff796ae 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -2277,7 +2277,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \ GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC)) -#define HW_INTERRUT_ASSERT_SET_0 \ +#define HW_INTERRUPT_ASSERT_SET_0 \ (AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \ @@ -2290,7 +2290,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR) -#define HW_INTERRUT_ASSERT_SET_1 \ +#define HW_INTERRUPT_ASSERT_SET_1 \ (AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \ @@ -2318,7 +2318,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \ AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\ AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR) -#define HW_INTERRUT_ASSERT_SET_2 \ +#define HW_INTERRUPT_ASSERT_SET_2 \ (AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \ AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ac76fc251d26..a851f95c307a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -4166,14 +4166,14 @@ static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn) bnx2x_release_phy_lock(bp); } - if (attn & HW_INTERRUT_ASSERT_SET_0) { + if (attn & HW_INTERRUPT_ASSERT_SET_0) { val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_0); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set0 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_0)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_0)); bnx2x_panic(); } } @@ -4191,7 +4191,7 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn) BNX2X_ERR("FATAL error from DORQ\n"); } - if (attn & HW_INTERRUT_ASSERT_SET_1) { + if (attn & HW_INTERRUPT_ASSERT_SET_1) { int port = BP_PORT(bp); int reg_offset; @@ -4200,11 +4200,11 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn) MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1); val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_1); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set1 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_1)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_1)); bnx2x_panic(); } } @@ -4235,7 +4235,7 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn) } } - if (attn & HW_INTERRUT_ASSERT_SET_2) { + if (attn & HW_INTERRUPT_ASSERT_SET_2) { int port = BP_PORT(bp); int reg_offset; @@ -4244,11 +4244,11 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn) MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2); val = REG_RD(bp, reg_offset); - val &= ~(attn & HW_INTERRUT_ASSERT_SET_2); + val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2); REG_WR(bp, reg_offset, val); BNX2X_ERR("FATAL HW block attention set2 0x%x\n", - (u32)(attn & HW_INTERRUT_ASSERT_SET_2)); + (u32)(attn & HW_INTERRUPT_ASSERT_SET_2)); bnx2x_panic(); } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 32de4589d16a..1f1e54ba0ecb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1983,20 +1983,25 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) for (j = 0; j < max_idx; j++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j]; + dma_addr_t mapping = rx_buf->mapping; void *data = rx_buf->data; if (!data) continue; - dma_unmap_single(&pdev->dev, rx_buf->mapping, - bp->rx_buf_use_size, bp->rx_dir); - rx_buf->data = NULL; - if (BNXT_RX_PAGE_MODE(bp)) + if (BNXT_RX_PAGE_MODE(bp)) { + mapping -= bp->rx_dma_offset; + dma_unmap_page(&pdev->dev, mapping, + PAGE_SIZE, bp->rx_dir); __free_page(data); - else + } else { + dma_unmap_single(&pdev->dev, mapping, + bp->rx_buf_use_size, + bp->rx_dir); kfree(data); + } } for (j = 0; j < max_agg_idx; j++) { @@ -2455,6 +2460,18 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) return 0; } +static void bnxt_init_cp_rings(struct bnxt *bp) +{ + int i; + + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + + ring->fw_ring_id = INVALID_HW_RING_ID; + } +} + static int bnxt_init_rx_rings(struct bnxt *bp) { int i, rc = 0; @@ -4732,7 +4749,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); if (rc) { netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n", - rc, i); + i, rc); return rc; } } @@ -5006,6 +5023,7 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init) static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init) { + bnxt_init_cp_rings(bp); bnxt_init_rx_rings(bp); bnxt_init_tx_rings(bp); bnxt_init_ring_grps(bp, irq_re_init); diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index 9e59663a6ead..0f6811860ad5 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -1930,13 +1930,13 @@ static void bfa_ioc_send_enable(struct bfa_ioc *ioc) { struct bfi_ioc_ctrl_req enable_req; - struct timeval tv; bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ, bfa_ioc_portid(ioc)); enable_req.clscode = htons(ioc->clscode); - do_gettimeofday(&tv); - enable_req.tv_sec = ntohl(tv.tv_sec); + enable_req.rsvd = htons(0); + /* overflow in 2106 */ + enable_req.tv_sec = ntohl(ktime_get_real_seconds()); bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req)); } @@ -1947,6 +1947,10 @@ bfa_ioc_send_disable(struct bfa_ioc *ioc) bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ, bfa_ioc_portid(ioc)); + disable_req.clscode = htons(ioc->clscode); + disable_req.rsvd = htons(0); + /* overflow in 2106 */ + disable_req.tv_sec = ntohl(ktime_get_real_seconds()); bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req)); } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 64a1095e4d14..a0ca68ce3fbb 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -134,6 +134,7 @@ static void set_max_bgx_per_node(struct pci_dev *pdev) pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid); switch (sdevid) { case PCI_SUBSYS_DEVID_81XX_BGX: + case PCI_SUBSYS_DEVID_81XX_RGX: max_bgx_per_node = MAX_BGX_PER_CN81XX; break; case PCI_SUBSYS_DEVID_83XX_BGX: diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index c5080f2cead5..6b7fe6fdd13b 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -16,6 +16,7 @@ /* Subsystem device IDs */ #define PCI_SUBSYS_DEVID_88XX_BGX 0xA126 #define PCI_SUBSYS_DEVID_81XX_BGX 0xA226 +#define PCI_SUBSYS_DEVID_81XX_RGX 0xA254 #define PCI_SUBSYS_DEVID_83XX_BGX 0xA326 #define MAX_BGX_THUNDER 8 /* Max 2 nodes, 4 per node */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 30e855004c57..02dd5246dfae 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -4939,8 +4939,9 @@ static int __be_cmd_set_logical_link_config(struct be_adapter *adapter, int link_state, int version, u8 domain) { - struct be_mcc_wrb *wrb; struct be_cmd_req_set_ll_link *req; + struct be_mcc_wrb *wrb; + u32 link_config = 0; int status; mutex_lock(&adapter->mcc_lock); @@ -4962,10 +4963,12 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter, if (link_state == IFLA_VF_LINK_STATE_ENABLE || link_state == IFLA_VF_LINK_STATE_AUTO) - req->link_config |= PLINK_ENABLE; + link_config |= PLINK_ENABLE; if (link_state == IFLA_VF_LINK_STATE_AUTO) - req->link_config |= PLINK_TRACK; + link_config |= PLINK_TRACK; + + req->link_config = cpu_to_le32(link_config); status = be_mcc_notify_wait(adapter); err: diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 992ebe973d25..f819843e2bae 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -189,11 +189,9 @@ static int nps_enet_poll(struct napi_struct *napi, int budget) nps_enet_tx_handler(ndev); work_done = nps_enet_rx_handler(ndev); - if (work_done < budget) { + if ((work_done < budget) && napi_complete_done(napi, work_done)) { u32 buf_int_enable_value = 0; - napi_complete_done(napi, work_done); - /* set tx_done and rx_rdy bits */ buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT; buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 928b0df2b8e0..ade6b3e4ed13 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -28,8 +28,10 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/of.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <net/ip.h> #include <net/ncsi.h> diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 3239d27143b9..bdd8cdd732fb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -82,9 +82,12 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) else *link_status = 0; - ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt); - if (!ret) - *link_status = *link_status && sfp_prsnt; + if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) { + ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, + &sfp_prsnt); + if (!ret) + *link_status = *link_status && sfp_prsnt; + } mac_cb->link = *link_status; } @@ -855,7 +858,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) of_node_put(np); np = of_parse_phandle(to_of_node(mac_cb->fw_port), - "serdes-syscon", 0); + "serdes-syscon", 0); syscon = syscon_node_to_regmap(np); of_node_put(np); if (IS_ERR_OR_NULL(syscon)) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 90dbda792614..403ea9db6dbd 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -1519,6 +1519,7 @@ static void hns_dsaf_set_mac_key( mac_key->high.bits.mac_3 = addr[3]; mac_key->low.bits.mac_4 = addr[4]; mac_key->low.bits.mac_5 = addr[5]; + mac_key->low.bits.port_vlan = 0; dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M, DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id); dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M, @@ -2924,10 +2925,11 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, /* find the tcam entry index for promisc */ entry_index = dsaf_promisc_tcam_entry(port); + memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data)); + memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask)); + /* config key mask */ if (enable) { - memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data)); - memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask)); dsaf_set_field(tbl_tcam_data.low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M, DSAF_TBL_TCAM_KEY_PORT_S, port); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index a2c22d084ce9..e13aa064a8e9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -461,6 +461,32 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) return 0; } +int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) +{ + union acpi_object *obj; + union acpi_object obj_args, argv4; + + obj_args.integer.type = ACPI_TYPE_INTEGER; + obj_args.integer.value = mac_cb->mac_id; + + argv4.type = ACPI_TYPE_PACKAGE, + argv4.package.count = 1, + argv4.package.elements = &obj_args, + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + hns_dsaf_acpi_dsm_uuid, 0, + HNS_OP_GET_SFP_STAT_FUNC, &argv4); + + if (!obj || obj->type != ACPI_TYPE_INTEGER) + return -ENODEV; + + *sfp_prsnt = obj->integer.value; + + ACPI_FREE(obj); + + return 0; +} + /** * hns_mac_config_sds_loopback - set loop back for serdes * @mac_cb: mac control block @@ -592,7 +618,7 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi; misc_op->get_phy_if = hns_mac_get_phy_if_acpi; - misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt; + misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi; misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi; } else { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 2175cced402f..e9af89ad039c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6274,8 +6274,8 @@ static int e1000e_pm_freeze(struct device *dev) /* Quiesce the device without resetting the hardware */ e1000e_down(adapter, false); e1000_free_irq(adapter); - e1000e_reset_interrupt_capability(adapter); } + e1000e_reset_interrupt_capability(adapter); /* Allow time for pending master requests to run */ e1000e_disable_pcie_master(&adapter->hw); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e8a8351c8ea9..82a95cc2c8ee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4438,8 +4438,12 @@ static void i40e_napi_enable_all(struct i40e_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_enable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_enable(&q_vector->napi); + } } /** @@ -4453,8 +4457,12 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_disable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_disable(&q_vector->napi); + } } /** diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 9e757684816d..93949139e62c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -613,7 +613,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; struct mtk_tx_dma *itxd, *txd; - struct mtk_tx_buf *tx_buf; + struct mtk_tx_buf *itx_buf, *tx_buf; dma_addr_t mapped_addr; unsigned int nr_frags; int i, n_desc = 1; @@ -627,8 +627,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT; txd4 |= fport; - tx_buf = mtk_desc_to_tx_buf(ring, itxd); - memset(tx_buf, 0, sizeof(*tx_buf)); + itx_buf = mtk_desc_to_tx_buf(ring, itxd); + memset(itx_buf, 0, sizeof(*itx_buf)); if (gso) txd4 |= TX_DMA_TSO; @@ -647,9 +647,11 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, return -ENOMEM; WRITE_ONCE(itxd->txd1, mapped_addr); - tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); + itx_buf->flags |= MTK_TX_FLAGS_SINGLE0; + itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb)); /* TX SG offload */ txd = itxd; @@ -685,11 +687,13 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, last_frag * TX_DMA_LS0)); WRITE_ONCE(txd->txd4, fport); - tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf = mtk_desc_to_tx_buf(ring, txd); memset(tx_buf, 0, sizeof(*tx_buf)); - + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf->flags |= MTK_TX_FLAGS_PAGE0; + tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); frag_size -= frag_map_size; @@ -698,7 +702,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, } /* store skb to cleanup */ - tx_buf->skb = skb; + itx_buf->skb = skb; WRITE_ONCE(itxd->txd4, txd4); WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | @@ -1012,17 +1016,16 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) while ((cpu != dma) && budget) { u32 next_cpu = desc->txd2; - int mac; + int mac = 0; desc = mtk_qdma_phys_to_virt(ring, desc->txd2); if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0) break; - mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) & - TX_DMA_FPORT_MASK; - mac--; - tx_buf = mtk_desc_to_tx_buf(ring, desc); + if (tx_buf->flags & MTK_TX_FLAGS_FPORT1) + mac = 1; + skb = tx_buf->skb; if (!skb) { condition = 1; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 99b1c8e9f16f..08285a96ff70 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -406,12 +406,18 @@ struct mtk_hw_stats { struct u64_stats_sync syncp; }; -/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how - * memory was allocated so that it can be freed properly - */ enum mtk_tx_flags { + /* PDMA descriptor can point at 1-2 segments. This enum allows us to + * track how memory was allocated so that it can be freed properly. + */ MTK_TX_FLAGS_SINGLE0 = 0x01, MTK_TX_FLAGS_PAGE0 = 0x02, + + /* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted + * SKB out instead of looking up through hardware TX descriptor. + */ + MTK_TX_FLAGS_FPORT0 = 0x04, + MTK_TX_FLAGS_FPORT1 = 0x08, }; /* This enum allows us to identify how the clock is defined on the array of the diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index dc52053128bc..3d9490cd2db1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -90,7 +90,7 @@ #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX) #define MLX5_UMR_ALIGN (2048) -#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128) +#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256) #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) #define MLX5E_DEFAULT_LRO_TIMEOUT 32 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index d55fff0ba388..26fc77e80f7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -564,6 +564,7 @@ int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *i int idx = 0; int err = 0; + info->data = MAX_NUM_OF_ETHTOOL_RULES; while ((!err || err == -ENOENT) && idx < info->rule_cnt) { err = mlx5e_ethtool_get_flow(priv, info, location); if (!err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 66c133757a5e..15cc7b469d2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -174,7 +174,7 @@ unlock: static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) { - struct mlx5e_sw_stats *s = &priv->stats.sw; + struct mlx5e_sw_stats temp, *s = &temp; struct mlx5e_rq_stats *rq_stats; struct mlx5e_sq_stats *sq_stats; u64 tx_offload_none = 0; @@ -229,6 +229,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->link_down_events_phy = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters, counter_set.phys_layer_cntrs.link_down_events); + memcpy(&priv->stats.sw, s, sizeof(*s)); } static void mlx5e_update_vport_counters(struct mlx5e_priv *priv) @@ -243,7 +244,6 @@ static void mlx5e_update_vport_counters(struct mlx5e_priv *priv) MLX5_SET(query_vport_counter_in, in, op_mod, 0); MLX5_SET(query_vport_counter_in, in, other_vport, 0); - memset(out, 0, outlen); mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fade7233dac5..5436866798f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -639,7 +639,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH) && rep->vport != FDB_UPLINK_VPORT) { - if (min_inline > esw->offloads.inline_mode) { + if (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && + esw->offloads.inline_mode < min_inline) { netdev_warn(priv->netdev, "Flow is not offloaded due to min inline setting, required %d actual %d\n", min_inline, esw->offloads.inline_mode); @@ -785,16 +786,15 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, return 0; } -static int gen_vxlan_header_ipv4(struct net_device *out_dev, - char buf[], - unsigned char h_dest[ETH_ALEN], - int ttl, - __be32 daddr, - __be32 saddr, - __be16 udp_dst_port, - __be32 vx_vni) +static void gen_vxlan_header_ipv4(struct net_device *out_dev, + char buf[], int encap_size, + unsigned char h_dest[ETH_ALEN], + int ttl, + __be32 daddr, + __be32 saddr, + __be16 udp_dst_port, + __be32 vx_vni) { - int encap_size = VXLAN_HLEN + sizeof(struct iphdr) + ETH_HLEN; struct ethhdr *eth = (struct ethhdr *)buf; struct iphdr *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr)); struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr)); @@ -817,20 +817,17 @@ static int gen_vxlan_header_ipv4(struct net_device *out_dev, udp->dest = udp_dst_port; vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vx_vni); - - return encap_size; } -static int gen_vxlan_header_ipv6(struct net_device *out_dev, - char buf[], - unsigned char h_dest[ETH_ALEN], - int ttl, - struct in6_addr *daddr, - struct in6_addr *saddr, - __be16 udp_dst_port, - __be32 vx_vni) +static void gen_vxlan_header_ipv6(struct net_device *out_dev, + char buf[], int encap_size, + unsigned char h_dest[ETH_ALEN], + int ttl, + struct in6_addr *daddr, + struct in6_addr *saddr, + __be16 udp_dst_port, + __be32 vx_vni) { - int encap_size = VXLAN_HLEN + sizeof(struct ipv6hdr) + ETH_HLEN; struct ethhdr *eth = (struct ethhdr *)buf; struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr)); struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr)); @@ -852,8 +849,6 @@ static int gen_vxlan_header_ipv6(struct net_device *out_dev, udp->dest = udp_dst_port; vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vx_vni); - - return encap_size; } static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, @@ -862,13 +857,20 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, struct net_device **out_dev) { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + int ipv4_encap_size = ETH_HLEN + sizeof(struct iphdr) + VXLAN_HLEN; struct ip_tunnel_key *tun_key = &e->tun_info.key; - int encap_size, ttl, err; struct neighbour *n = NULL; struct flowi4 fl4 = {}; char *encap_header; + int ttl, err; + + if (max_encap_size < ipv4_encap_size) { + mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", + ipv4_encap_size, max_encap_size); + return -EOPNOTSUPP; + } - encap_header = kzalloc(max_encap_size, GFP_KERNEL); + encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); if (!encap_header) return -ENOMEM; @@ -903,11 +905,11 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, switch (e->tunnel_type) { case MLX5_HEADER_TYPE_VXLAN: - encap_size = gen_vxlan_header_ipv4(*out_dev, encap_header, - e->h_dest, ttl, - fl4.daddr, - fl4.saddr, tun_key->tp_dst, - tunnel_id_to_key32(tun_key->tun_id)); + gen_vxlan_header_ipv4(*out_dev, encap_header, + ipv4_encap_size, e->h_dest, ttl, + fl4.daddr, + fl4.saddr, tun_key->tp_dst, + tunnel_id_to_key32(tun_key->tun_id)); break; default: err = -EOPNOTSUPP; @@ -915,7 +917,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, } err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, - encap_size, encap_header, &e->encap_id); + ipv4_encap_size, encap_header, &e->encap_id); out: if (err && n) neigh_release(n); @@ -930,13 +932,20 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + int ipv6_encap_size = ETH_HLEN + sizeof(struct ipv6hdr) + VXLAN_HLEN; struct ip_tunnel_key *tun_key = &e->tun_info.key; - int encap_size, err, ttl = 0; struct neighbour *n = NULL; struct flowi6 fl6 = {}; char *encap_header; + int err, ttl = 0; + + if (max_encap_size < ipv6_encap_size) { + mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", + ipv6_encap_size, max_encap_size); + return -EOPNOTSUPP; + } - encap_header = kzalloc(max_encap_size, GFP_KERNEL); + encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); if (!encap_header) return -ENOMEM; @@ -972,11 +981,11 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, switch (e->tunnel_type) { case MLX5_HEADER_TYPE_VXLAN: - encap_size = gen_vxlan_header_ipv6(*out_dev, encap_header, - e->h_dest, ttl, - &fl6.daddr, - &fl6.saddr, tun_key->tp_dst, - tunnel_id_to_key32(tun_key->tun_id)); + gen_vxlan_header_ipv6(*out_dev, encap_header, + ipv6_encap_size, e->h_dest, ttl, + &fl6.daddr, + &fl6.saddr, tun_key->tp_dst, + tunnel_id_to_key32(tun_key->tun_id)); break; default: err = -EOPNOTSUPP; @@ -984,7 +993,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, } err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, - encap_size, encap_header, &e->encap_id); + ipv6_encap_size, encap_header, &e->encap_id); out: if (err && n) neigh_release(n); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 307ec6c5fd3b..d111cebca9f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -911,8 +911,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; int num_vports = esw->enabled_vports; - int err; - int vport; + int err, vport; u8 mlx5_mode; if (!MLX5_CAP_GEN(dev, vport_group_manager)) @@ -921,9 +920,17 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) if (esw->mode == SRIOV_NONE) return -EOPNOTSUPP; - if (MLX5_CAP_ETH(dev, wqe_inline_mode) != - MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) + switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: + if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE) + return 0; + /* fall through */ + case MLX5_CAP_INLINE_MODE_L2: + esw_warn(dev, "Inline mode can't be set\n"); return -EOPNOTSUPP; + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + break; + } if (esw->offloads.num_flows > 0) { esw_warn(dev, "Can't set inline mode when flows are configured\n"); @@ -966,18 +973,14 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) if (esw->mode == SRIOV_NONE) return -EOPNOTSUPP; - if (MLX5_CAP_ETH(dev, wqe_inline_mode) != - MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) - return -EOPNOTSUPP; - return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode) { + u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2; struct mlx5_core_dev *dev = esw->dev; int vport; - u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2; if (!MLX5_CAP_GEN(dev, vport_group_manager)) return -EOPNOTSUPP; @@ -985,10 +988,18 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode) if (esw->mode == SRIOV_NONE) return -EOPNOTSUPP; - if (MLX5_CAP_ETH(dev, wqe_inline_mode) != - MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) - return -EOPNOTSUPP; + switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: + mlx5_mode = MLX5_INLINE_MODE_NONE; + goto out; + case MLX5_CAP_INLINE_MODE_L2: + mlx5_mode = MLX5_INLINE_MODE_L2; + goto out; + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + goto query_vports; + } +query_vports: for (vport = 1; vport <= nvfs; vport++) { mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode); if (vport > 1 && prev_mlx5_mode != mlx5_mode) @@ -996,6 +1007,7 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode) prev_mlx5_mode = mlx5_mode; } +out: *mode = mlx5_mode; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 55957246c0e8..b5d5519542e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, struct netdev_notifier_changeupper_info *info) { struct net_device *upper = info->upper_dev, *ndev_tmp; - struct netdev_lag_upper_info *lag_upper_info; + struct netdev_lag_upper_info *lag_upper_info = NULL; bool is_bonded; int bond_status = 0; int num_slaves = 0; @@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, if (!netif_is_lag_master(upper)) return 0; - lag_upper_info = info->upper_info; + if (info->linking) + lag_upper_info = info->upper_info; /* The event may still be of interest if the slave does not belong to * us, but is enslaved to a master which has one or more of our netdevs diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 60154a175bd3..0ad66324247f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1029,7 +1029,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (err) { dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n", FW_INIT_TIMEOUT_MILI); - goto out_err; + goto err_cmd_cleanup; } err = mlx5_core_enable_hca(dev, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 2e6b0f290ddc..222b25908d01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -87,6 +87,7 @@ static void up_rel_func(struct kref *kref) struct mlx5_uars_page *up = container_of(kref, struct mlx5_uars_page, ref_count); list_del(&up->list); + iounmap(up->map); if (mlx5_cmd_free_uar(up->mdev, up->index)) mlx5_core_warn(up->mdev, "failed to free uar index %d\n", up->index); kfree(up->reg_bitmap); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 06c9f4100cb9..6ad44be08b33 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -25,6 +25,7 @@ #include <linux/of_irq.h> #include <linux/crc32.h> #include <linux/crc32c.h> +#include <linux/circ_buf.h> #include "moxart_ether.h" @@ -278,6 +279,13 @@ rx_next: return rx; } +static int moxart_tx_queue_space(struct net_device *ndev) +{ + struct moxart_mac_priv_t *priv = netdev_priv(ndev); + + return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM); +} + static void moxart_tx_finished(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); @@ -297,6 +305,9 @@ static void moxart_tx_finished(struct net_device *ndev) tx_tail = TX_NEXT(tx_tail); } priv->tx_tail = tx_tail; + if (netif_queue_stopped(ndev) && + moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD) + netif_wake_queue(ndev); } static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id) @@ -324,13 +335,18 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct moxart_mac_priv_t *priv = netdev_priv(ndev); void *desc; unsigned int len; - unsigned int tx_head = priv->tx_head; + unsigned int tx_head; u32 txdes1; int ret = NETDEV_TX_BUSY; + spin_lock_irq(&priv->txlock); + + tx_head = priv->tx_head; desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head); - spin_lock_irq(&priv->txlock); + if (moxart_tx_queue_space(ndev) == 1) + netif_stop_queue(ndev); + if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { net_dbg_ratelimited("no TX space for packet\n"); priv->stats.tx_dropped++; diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index 93a9563ac7c6..afc32ec998c0 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -59,6 +59,7 @@ #define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK)) #define TX_BUF_SIZE 1600 #define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1) +#define TX_WAKE_THRESHOLD 16 #define RX_DESC_NUM 64 #define RX_DESC_NUM_MASK (RX_DESC_NUM-1) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 9179a99563af..a41377e26c07 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3275,9 +3275,10 @@ void nfp_net_netdev_clean(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); + unregister_netdev(nn->netdev); + if (nn->xdp_prog) bpf_prog_put(nn->xdp_prog); if (nn->bpf_offload_xdp) nfp_net_xdp_offload(nn, NULL); - unregister_netdev(nn->netdev); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 5bd36a4a8fcd..cfdadb658ade 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -64,11 +64,11 @@ ((u32)(prio_tc_tbl >> ((7 - prio) * 4)) & 0x7) static const struct qed_dcbx_app_metadata qed_dcbx_app_update[] = { - {DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_DEFAULT}, - {DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_DEFAULT}, - {DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_DEFAULT}, - {DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_DEFAULT}, - {DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH} + {DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_ISCSI}, + {DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_FCOE}, + {DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_ETH_ROCE}, + {DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_ETH_ROCE}, + {DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH}, }; static bool qed_dcbx_app_ethtype(u32 app_info_bitmap) @@ -583,6 +583,13 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn, p_params->ets_cbs, p_ets->pri_tc_tbl[0], p_params->max_ets_tc); + if (p_params->ets_enabled && !p_params->max_ets_tc) { + p_params->max_ets_tc = QED_MAX_PFC_PRIORITIES; + DP_VERBOSE(p_hwfn, QED_MSG_DCB, + "ETS params: max_ets_tc is forced to %d\n", + p_params->max_ets_tc); + } + /* 8 bit tsa and bw data corresponding to each of the 8 TC's are * encoded in a type u32 array of size 2. */ @@ -1001,6 +1008,8 @@ qed_dcbx_set_pfc_data(struct qed_hwfn *p_hwfn, u8 pfc_map = 0; int i; + *pfc &= ~DCBX_PFC_ERROR_MASK; + if (p_params->pfc.willing) *pfc |= DCBX_PFC_WILLING_MASK; else @@ -1255,7 +1264,7 @@ static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn, { struct qed_dcbx_get *dcbx_info; - dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL); + dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_ATOMIC); if (!dcbx_info) return NULL; @@ -2073,6 +2082,8 @@ static int qed_dcbnl_ieee_setpfc(struct qed_dev *cdev, struct ieee_pfc *pfc) for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i)); + dcbx_set.config.params.pfc.max_tc = pfc->pfc_cap; + ptt = qed_ptt_acquire(hwfn); if (!ptt) return -EINVAL; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8cfc4a54f2dc..3cd7989c007d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1516,11 +1516,12 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) spin_unlock_irqrestore(&priv->lock, flags); return NETDEV_TX_BUSY; } - entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC); - priv->tx_skb[q][entry / NUM_TX_DESC] = skb; if (skb_put_padto(skb, ETH_ZLEN)) - goto drop; + goto exit; + + entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC); + priv->tx_skb[q][entry / NUM_TX_DESC] = skb; buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + entry / NUM_TX_DESC * DPTR_ALIGN; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 54248775f227..f68c4db656ed 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,12 +1127,70 @@ static struct mdiobb_ops bb_ops = { .get_mdio_data = sh_get_mdio, }; +/* free Tx skb function */ +static int sh_eth_tx_free(struct net_device *ndev, bool sent_only) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + struct sh_eth_txdesc *txdesc; + int free_num = 0; + int entry; + bool sent; + + for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { + entry = mdp->dirty_tx % mdp->num_tx_ring; + txdesc = &mdp->tx_ring[entry]; + sent = !(txdesc->status & cpu_to_le32(TD_TACT)); + if (sent_only && !sent) + break; + /* TACT bit must be checked before all the following reads */ + dma_rmb(); + netif_info(mdp, tx_done, ndev, + "tx entry %d status 0x%08x\n", + entry, le32_to_cpu(txdesc->status)); + /* Free the original skb. */ + if (mdp->tx_skbuff[entry]) { + dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), + le32_to_cpu(txdesc->len) >> 16, + DMA_TO_DEVICE); + dev_kfree_skb_irq(mdp->tx_skbuff[entry]); + mdp->tx_skbuff[entry] = NULL; + free_num++; + } + txdesc->status = cpu_to_le32(TD_TFP); + if (entry >= mdp->num_tx_ring - 1) + txdesc->status |= cpu_to_le32(TD_TDLE); + + if (sent) { + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; + } + } + return free_num; +} + /* free skb and descriptor buffer */ static void sh_eth_ring_free(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); int ringsize, i; + if (mdp->rx_ring) { + for (i = 0; i < mdp->num_rx_ring; i++) { + if (mdp->rx_skbuff[i]) { + struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i]; + + dma_unmap_single(&ndev->dev, + le32_to_cpu(rxdesc->addr), + ALIGN(mdp->rx_buf_sz, 32), + DMA_FROM_DEVICE); + } + } + ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; + dma_free_coherent(NULL, ringsize, mdp->rx_ring, + mdp->rx_desc_dma); + mdp->rx_ring = NULL; + } + /* Free Rx skb ringbuffer */ if (mdp->rx_skbuff) { for (i = 0; i < mdp->num_rx_ring; i++) @@ -1141,27 +1199,18 @@ static void sh_eth_ring_free(struct net_device *ndev) kfree(mdp->rx_skbuff); mdp->rx_skbuff = NULL; - /* Free Tx skb ringbuffer */ - if (mdp->tx_skbuff) { - for (i = 0; i < mdp->num_tx_ring; i++) - dev_kfree_skb(mdp->tx_skbuff[i]); - } - kfree(mdp->tx_skbuff); - mdp->tx_skbuff = NULL; - - if (mdp->rx_ring) { - ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; - dma_free_coherent(NULL, ringsize, mdp->rx_ring, - mdp->rx_desc_dma); - mdp->rx_ring = NULL; - } - if (mdp->tx_ring) { + sh_eth_tx_free(ndev, false); + ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring; dma_free_coherent(NULL, ringsize, mdp->tx_ring, mdp->tx_desc_dma); mdp->tx_ring = NULL; } + + /* Free Tx skb ringbuffer */ + kfree(mdp->tx_skbuff); + mdp->tx_skbuff = NULL; } /* format skb and descriptor buffer */ @@ -1409,43 +1458,6 @@ static void sh_eth_dev_exit(struct net_device *ndev) update_mac_address(ndev); } -/* free Tx skb function */ -static int sh_eth_txfree(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - struct sh_eth_txdesc *txdesc; - int free_num = 0; - int entry; - - for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { - entry = mdp->dirty_tx % mdp->num_tx_ring; - txdesc = &mdp->tx_ring[entry]; - if (txdesc->status & cpu_to_le32(TD_TACT)) - break; - /* TACT bit must be checked before all the following reads */ - dma_rmb(); - netif_info(mdp, tx_done, ndev, - "tx entry %d status 0x%08x\n", - entry, le32_to_cpu(txdesc->status)); - /* Free the original skb. */ - if (mdp->tx_skbuff[entry]) { - dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), - le32_to_cpu(txdesc->len) >> 16, - DMA_TO_DEVICE); - dev_kfree_skb_irq(mdp->tx_skbuff[entry]); - mdp->tx_skbuff[entry] = NULL; - free_num++; - } - txdesc->status = cpu_to_le32(TD_TFP); - if (entry >= mdp->num_tx_ring - 1) - txdesc->status |= cpu_to_le32(TD_TDLE); - - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; - } - return free_num; -} - /* Packet receive function */ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) { @@ -1690,7 +1702,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status) intr_status, mdp->cur_tx, mdp->dirty_tx, (u32)ndev->state, edtrr); /* dirty buffer free */ - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); /* SH7712 BUG */ if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) { @@ -1751,7 +1763,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev) /* Clear Tx interrupts */ sh_eth_write(ndev, intr_status & cd->tx_check, EESR); - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); netif_wake_queue(ndev); } @@ -2412,7 +2424,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) spin_lock_irqsave(&mdp->lock, flags); if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) { - if (!sh_eth_txfree(ndev)) { + if (!sh_eth_tx_free(ndev, true)) { netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n"); netif_stop_queue(ndev); spin_unlock_irqrestore(&mdp->lock, flags); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 7cd76b6b5cb9..2ae852454780 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2216,18 +2216,15 @@ static int ofdpa_port_stp_update(struct ofdpa_port *ofdpa_port, { bool want[OFDPA_CTRL_MAX] = { 0, }; bool prev_ctrls[OFDPA_CTRL_MAX]; - u8 uninitialized_var(prev_state); + u8 prev_state; int err; int i; - if (switchdev_trans_ph_prepare(trans)) { - memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls)); - prev_state = ofdpa_port->stp_state; - } - - if (ofdpa_port->stp_state == state) + prev_state = ofdpa_port->stp_state; + if (prev_state == state) return 0; + memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls)); ofdpa_port->stp_state = state; switch (state) { diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 50d28261b6b9..b9cb697b2818 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1371,6 +1371,13 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx) free_cpumask_var(thread_mask); } + if (count > EFX_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EFX_MAX_RX_QUEUES); + count = EFX_MAX_RX_QUEUES; + } + /* If RSS is requested for the PF *and* VFs then we can't write RSS * table entries that are inaccessible to VFs */ diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index ee14662415c5..a0c52e328102 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -74,7 +74,10 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); #define EFX_RXQ_MIN_ENT 128U #define EFX_TXQ_MIN_ENT(efx) (2 * efx_tx_max_skb_descs(efx)) -#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \ +/* All EF10 architecture NICs steal one bit of the DMAQ size for various + * other purposes when counting TxQ entries, so we halve the queue size. + */ +#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_EF10(efx) ? \ EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE) static inline bool efx_rss_enabled(struct efx_nic *efx) diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index f5e5cd1659a1..29614da91cbf 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -1354,6 +1354,13 @@ static unsigned int ef4_wanted_parallelism(struct ef4_nic *efx) free_cpumask_var(thread_mask); } + if (count > EF4_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EF4_MAX_RX_QUEUES); + count = EF4_MAX_RX_QUEUES; + } + return count; } diff --git a/drivers/net/ethernet/sfc/workarounds.h b/drivers/net/ethernet/sfc/workarounds.h index 103f827a1623..c67fa18b8121 100644 --- a/drivers/net/ethernet/sfc/workarounds.h +++ b/drivers/net/ethernet/sfc/workarounds.h @@ -16,6 +16,7 @@ */ #define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0) +#define EFX_WORKAROUND_EF10(efx) (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) #define EFX_WORKAROUND_10G(efx) 1 /* Bit-bashed I2C reads cause performance drop */ diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 9e631952b86f..48a541eb0af2 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -76,7 +76,7 @@ config TI_CPSW config TI_CPTS bool "TI Common Platform Time Sync (CPTS) Support" depends on TI_CPSW || TI_KEYSTONE_NETCP - depends on PTP_1588_CLOCK + depends on POSIX_TIMERS ---help--- This driver supports the Common Platform Time Sync unit of the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem. @@ -87,6 +87,8 @@ config TI_CPTS_MOD tristate depends on TI_CPTS default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y + select NET_PTP_CLASSIFY + imply PTP_1588_CLOCK default m config TI_KEYSTONE_NETCP diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9f3d9c67e3fe..fa674a8bda0c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1267,6 +1267,7 @@ static void soft_reset_slave(struct cpsw_slave *slave) static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) { u32 slave_port; + struct phy_device *phy; struct cpsw_common *cpsw = priv->cpsw; soft_reset_slave(slave); @@ -1300,27 +1301,28 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); if (slave->data->phy_node) { - slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node, + phy = of_phy_connect(priv->ndev, slave->data->phy_node, &cpsw_adjust_link, 0, slave->data->phy_if); - if (!slave->phy) { + if (!phy) { dev_err(priv->dev, "phy \"%s\" not found on slave %d\n", slave->data->phy_node->full_name, slave->slave_num); return; } } else { - slave->phy = phy_connect(priv->ndev, slave->data->phy_id, + phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); - if (IS_ERR(slave->phy)) { + if (IS_ERR(phy)) { dev_err(priv->dev, "phy \"%s\" not found on slave %d, err %ld\n", slave->data->phy_id, slave->slave_num, - PTR_ERR(slave->phy)); - slave->phy = NULL; + PTR_ERR(phy)); return; } } + slave->phy = phy; + phy_attached_info(slave->phy); phy_start(slave->phy); @@ -1817,6 +1819,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) } cpsw_intr_enable(cpsw); + netif_trans_update(ndev); + netif_tx_wake_all_queues(ndev); } static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index a45f98fa4aa7..3dadee1080b9 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -1017,8 +1017,8 @@ tc35815_free_queues(struct net_device *dev) BUG_ON(lp->tx_skbs[i].skb != skb); #endif if (skb) { - dev_kfree_skb(skb); pci_unmap_single(lp->pci_dev, lp->tx_skbs[i].skb_dma, skb->len, PCI_DMA_TODEVICE); + dev_kfree_skb(skb); lp->tx_skbs[i].skb = NULL; lp->tx_skbs[i].skb_dma = 0; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index f9f3dba7a588..db23cb36ae5c 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -751,7 +751,6 @@ struct netvsc_device { u32 send_section_cnt; u32 send_section_size; unsigned long *send_section_map; - int map_words; /* Used for NetVSP initialization protocol */ struct completion channel_init_wait; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 8dd0b8770328..15ef713d96c0 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -236,6 +236,7 @@ static int netvsc_init_buf(struct hv_device *device) struct netvsc_device *net_device; struct nvsp_message *init_packet; struct net_device *ndev; + size_t map_words; int node; net_device = get_outbound_net_device(device); @@ -401,11 +402,9 @@ static int netvsc_init_buf(struct hv_device *device) net_device->send_section_size, net_device->send_section_cnt); /* Setup state for managing the send buffer. */ - net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt, - BITS_PER_LONG); + map_words = DIV_ROUND_UP(net_device->send_section_cnt, BITS_PER_LONG); - net_device->send_section_map = kcalloc(net_device->map_words, - sizeof(ulong), GFP_KERNEL); + net_device->send_section_map = kcalloc(map_words, sizeof(ulong), GFP_KERNEL); if (net_device->send_section_map == NULL) { ret = -ENOMEM; goto cleanup; @@ -683,7 +682,7 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device) unsigned long *map_addr = net_device->send_section_map; unsigned int i; - for_each_clear_bit(i, map_addr, net_device->map_words) { + for_each_clear_bit(i, map_addr, net_device->send_section_cnt) { if (sync_test_and_set_bit(i, map_addr) == 0) return i; } diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c index ffedad2a360a..15b920086251 100644 --- a/drivers/net/irda/vlsi_ir.c +++ b/drivers/net/irda/vlsi_ir.c @@ -418,8 +418,9 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr memset(rd, 0, sizeof(*rd)); rd->hw = hwmap + i; rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA); - if (rd->buf == NULL || - !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) { + if (rd->buf) + busaddr = pci_map_single(pdev, rd->buf, len, dir); + if (rd->buf == NULL || pci_dma_mapping_error(pdev, busaddr)) { if (rd->buf) { net_err_ratelimited("%s: failed to create PCI-MAP for %p\n", __func__, rd->buf); @@ -430,8 +431,7 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr rd = r->rd + j; busaddr = rd_get_addr(rd); rd_set_addr_status(rd, 0, 0); - if (busaddr) - pci_unmap_single(pdev, busaddr, len, dir); + pci_unmap_single(pdev, busaddr, len, dir); kfree(rd->buf); rd->buf = NULL; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index ff0a5ed3ca80..49ce4e9f4a0f 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -617,7 +617,8 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err) static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, unsigned char **iv, - struct scatterlist **sg) + struct scatterlist **sg, + int num_frags) { size_t size, iv_offset, sg_offset; struct aead_request *req; @@ -629,7 +630,7 @@ static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, size = ALIGN(size, __alignof__(struct scatterlist)); sg_offset = size; - size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1); + size += sizeof(struct scatterlist) * num_frags; tmp = kmalloc(size, GFP_ATOMIC); if (!tmp) @@ -649,6 +650,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, { int ret; struct scatterlist *sg; + struct sk_buff *trailer; unsigned char *iv; struct ethhdr *eth; struct macsec_eth_header *hh; @@ -723,7 +725,14 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, return ERR_PTR(-EINVAL); } - req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg); + ret = skb_cow_data(skb, 0, &trailer); + if (unlikely(ret < 0)) { + macsec_txsa_put(tx_sa); + kfree_skb(skb); + return ERR_PTR(ret); + } + + req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret); if (!req) { macsec_txsa_put(tx_sa); kfree_skb(skb); @@ -732,7 +741,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, macsec_fill_iv(iv, secy->sci, pn); - sg_init_table(sg, MAX_SKB_FRAGS + 1); + sg_init_table(sg, ret); skb_to_sgvec(skb, sg, 0, skb->len); if (tx_sc->encrypt) { @@ -917,6 +926,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, { int ret; struct scatterlist *sg; + struct sk_buff *trailer; unsigned char *iv; struct aead_request *req; struct macsec_eth_header *hdr; @@ -927,7 +937,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, if (!skb) return ERR_PTR(-ENOMEM); - req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg); + ret = skb_cow_data(skb, 0, &trailer); + if (unlikely(ret < 0)) { + kfree_skb(skb); + return ERR_PTR(ret); + } + req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret); if (!req) { kfree_skb(skb); return ERR_PTR(-ENOMEM); @@ -936,7 +951,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, hdr = (struct macsec_eth_header *)skb->data; macsec_fill_iv(iv, sci, ntohl(hdr->packet_number)); - sg_init_table(sg, MAX_SKB_FRAGS + 1); + sg_init_table(sg, ret); skb_to_sgvec(skb, sg, 0, skb->len); if (hdr->tci_an & MACSEC_TCI_E) { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 9261722960a7..b34eaaae03fd 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1139,6 +1139,7 @@ static int macvlan_port_create(struct net_device *dev) static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); + struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); @@ -1147,7 +1148,15 @@ static void macvlan_port_destroy(struct net_device *dev) * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); - __skb_queue_purge(&port->bc_queue); + + while ((skb = __skb_dequeue(&port->bc_queue))) { + const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; + + if (src) + dev_put(src->dev); + + kfree_skb(skb); + } kfree(port); } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index e2460a57e4b1..ed0d10f54f26 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1438,8 +1438,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->rx_queue, skb); schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT); - } else { - netif_rx_ni(skb); } return true; diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c index 6b988f77da08..61941e29daae 100644 --- a/drivers/net/phy/mdio-boardinfo.c +++ b/drivers/net/phy/mdio-boardinfo.c @@ -84,3 +84,4 @@ int mdiobus_register_board_info(const struct mdio_board_info *info, return 0; } +EXPORT_SYMBOL(mdiobus_register_board_info); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 6742070ca676..da5b39268370 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -297,17 +297,6 @@ static int kszphy_config_init(struct phy_device *phydev) if (priv->led_mode >= 0) kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode); - if (phy_interrupt_is_valid(phydev)) { - int ctl = phy_read(phydev, MII_BMCR); - - if (ctl < 0) - return ctl; - - ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE); - if (ret < 0) - return ret; - } - return 0; } @@ -798,9 +787,6 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -940,9 +926,6 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -952,6 +935,7 @@ static struct phy_driver ksphy_driver[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, .driver_data = &ksz9021_type, + .probe = kszphy_probe, .config_init = ksz9021_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -971,6 +955,7 @@ static struct phy_driver ksphy_driver[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, .driver_data = &ksz9021_type, + .probe = kszphy_probe, .config_init = ksz9031_config_init, .config_aneg = genphy_config_aneg, .read_status = ksz9031_read_status, @@ -989,9 +974,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -1003,9 +985,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -1017,9 +996,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 1be69d8bc909..97ff1278167b 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -591,16 +591,18 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) EXPORT_SYMBOL(phy_mii_ioctl); /** - * phy_start_aneg - start auto-negotiation for this PHY device + * phy_start_aneg_priv - start auto-negotiation for this PHY device * @phydev: the phy_device struct + * @sync: indicate whether we should wait for the workqueue cancelation * * Description: Sanitizes the settings (if we're not autonegotiating * them), and then calls the driver's config_aneg function. * If the PHYCONTROL Layer is operating, we change the state to * reflect the beginning of Auto-negotiation or forcing. */ -int phy_start_aneg(struct phy_device *phydev) +static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) { + bool trigger = 0; int err; if (!phydev->drv) @@ -628,10 +630,40 @@ int phy_start_aneg(struct phy_device *phydev) } } + /* Re-schedule a PHY state machine to check PHY status because + * negotiation may already be done and aneg interrupt may not be + * generated. + */ + if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + err = phy_aneg_done(phydev); + if (err > 0) { + trigger = true; + err = 0; + } + } + out_unlock: mutex_unlock(&phydev->lock); + + if (trigger) + phy_trigger_machine(phydev, sync); + return err; } + +/** + * phy_start_aneg - start auto-negotiation for this PHY device + * @phydev: the phy_device struct + * + * Description: Sanitizes the settings (if we're not autonegotiating + * them), and then calls the driver's config_aneg function. + * If the PHYCONTROL Layer is operating, we change the state to + * reflect the beginning of Auto-negotiation or forcing. + */ +int phy_start_aneg(struct phy_device *phydev) +{ + return phy_start_aneg_priv(phydev, true); +} EXPORT_SYMBOL(phy_start_aneg); /** @@ -659,7 +691,7 @@ void phy_start_machine(struct phy_device *phydev) * state machine runs. */ -static void phy_trigger_machine(struct phy_device *phydev, bool sync) +void phy_trigger_machine(struct phy_device *phydev, bool sync) { if (sync) cancel_delayed_work_sync(&phydev->state_queue); @@ -681,7 +713,7 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (phydev->state > PHY_UP) + if (phydev->state > PHY_UP && phydev->state != PHY_HALTED) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); } @@ -1154,7 +1186,7 @@ void phy_state_machine(struct work_struct *work) mutex_unlock(&phydev->lock); if (needs_aneg) - err = phy_start_aneg(phydev); + err = phy_start_aneg_priv(phydev, false); else if (do_suspend) phy_suspend(phydev); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 1b52520715ae..85c01247f2e3 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -990,7 +990,7 @@ static void team_port_disable(struct team *team, #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_ALL_TSO) -static void ___team_compute_features(struct team *team) +static void __team_compute_features(struct team *team) { struct team_port *port; u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; @@ -1023,16 +1023,10 @@ static void ___team_compute_features(struct team *team) team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; } -static void __team_compute_features(struct team *team) -{ - ___team_compute_features(team); - netdev_change_features(team->dev); -} - static void team_compute_features(struct team *team) { mutex_lock(&team->lock); - ___team_compute_features(team); + __team_compute_features(team); mutex_unlock(&team->lock); netdev_change_features(team->dev); } @@ -1641,6 +1635,7 @@ static void team_uninit(struct net_device *dev) team_notify_peers_fini(team); team_queue_override_fini(team); mutex_unlock(&team->lock); + netdev_change_features(dev); } static void team_destructor(struct net_device *dev) @@ -1928,6 +1923,10 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev) mutex_lock(&team->lock); err = team_port_add(team, port_dev); mutex_unlock(&team->lock); + + if (!err) + netdev_change_features(dev); + return err; } @@ -1939,6 +1938,10 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev) mutex_lock(&team->lock); err = team_port_del(team, port_dev); mutex_unlock(&team->lock); + + if (!err) + netdev_change_features(dev); + return err; } @@ -2358,8 +2361,10 @@ start_again: hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(skb); return -EMSGSIZE; + } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; @@ -2631,8 +2636,10 @@ start_again: hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_PORT_LIST_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(skb); return -EMSGSIZE; + } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 3dd490f53e48..f28bd74ac275 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -369,7 +369,7 @@ config USB_NET_NET1080 optionally with LEDs that indicate traffic config USB_NET_PLUSB - tristate "Prolific PL-2301/2302/25A1 based cables" + tristate "Prolific PL-2301/2302/25A1/27A1 based cables" # if the handshake/init/reset problems, from original 'plusb', # are ever resolved ... then remove "experimental" depends on USB_USBNET diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index f5552aaaa77a..f3ae88fdf332 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -532,6 +532,7 @@ static const struct driver_info wwan_info = { #define LENOVO_VENDOR_ID 0x17ef #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 +#define MICROSOFT_VENDOR_ID 0x045e static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -761,6 +762,20 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* Microsoft Surface 2 dock (based on Realtek RTL8152) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + +/* Microsoft Surface 3 dock (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* WHITELIST!!! * * CDC Ether uses two interfaces, not necessarily consecutive. diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index 8a40202c0a17..c4f1c363e24b 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -254,14 +254,9 @@ static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb, tx_overhead = 0x40; len = skb->len; - if (skb_headroom(skb) < tx_overhead) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, tx_overhead, 0, flags); + if (skb_cow_head(skb, tx_overhead)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } __skb_push(skb, tx_overhead); diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index e221bfcee76b..947bea81d924 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -293,12 +293,9 @@ static struct sk_buff *cx82310_tx_fixup(struct usbnet *dev, struct sk_buff *skb, { int len = skb->len; - if (skb_headroom(skb) < 2) { - struct sk_buff *skb2 = skb_copy_expand(skb, 2, 0, flags); + if (skb_cow_head(skb, 2)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } skb_push(skb, 2); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 4f2e8141dbe2..00067a0c51ca 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2534,13 +2534,6 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, SET_NETDEV_DEV(net, &interface->dev); SET_NETDEV_DEVTYPE(net, &hso_type); - /* registering our net device */ - result = register_netdev(net); - if (result) { - dev_err(&interface->dev, "Failed to register device\n"); - goto exit; - } - /* start allocating */ for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) { hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL); @@ -2560,6 +2553,13 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface, add_net_device(hso_dev); + /* registering our net device */ + result = register_netdev(net); + if (result) { + dev_err(&interface->dev, "Failed to register device\n"); + goto exit; + } + hso_log_port(hso_dev); hso_create_rfkill(hso_dev, interface); @@ -3279,9 +3279,9 @@ static void __exit hso_exit(void) pr_info("unloaded\n"); tty_unregister_driver(tty_drv); - put_tty_driver(tty_drv); /* deregister the usb driver */ usb_deregister(&hso_driver); + put_tty_driver(tty_drv); } /* Module definitions */ diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 876f02f4945e..2a2c3edb6bad 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -803,18 +803,12 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb, } /* We now decide whether we can put our special header into the sk_buff */ - if (skb_cloned(skb) || skb_headroom(skb) < 2) { - /* no such luck - we make our own */ - struct sk_buff *copied_skb; - copied_skb = skb_copy_expand(skb, 2, 0, GFP_ATOMIC); - dev_kfree_skb_irq(skb); - skb = copied_skb; - if (!copied_skb) { - kaweth->stats.tx_errors++; - netif_start_queue(net); - spin_unlock_irq(&kaweth->device_lock); - return NETDEV_TX_OK; - } + if (skb_cow_head(skb, 2)) { + kaweth->stats.tx_errors++; + netif_start_queue(net); + spin_unlock_irq(&kaweth->device_lock); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; } private_header = (__le16 *)__skb_push(skb, 2); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 9889a70ff4f6..636f48f19d1e 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2607,14 +2607,9 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } if (lan78xx_linearize(skb) < 0) diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 22e1a9a99a7d..6fe59373cba9 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -102,7 +102,7 @@ static int pl_reset(struct usbnet *dev) } static const struct driver_info prolific_info = { - .description = "Prolific PL-2301/PL-2302/PL-25A1", + .description = "Prolific PL-2301/PL-2302/PL-25A1/PL-27A1", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT, /* some PL-2302 versions seem to fail usb_set_interface() */ .reset = pl_reset, @@ -139,6 +139,17 @@ static const struct usb_device_id products [] = { * Host-to-Host Cable */ .driver_info = (unsigned long) &prolific_info, + +}, + +/* super speed cables */ +{ + USB_DEVICE(0x067b, 0x27a1), /* PL-27A1, no eeprom + * also: goobay Active USB 3.0 + * Data Link, + * Unitek Y-3501 + */ + .driver_info = (unsigned long) &prolific_info, }, { }, // END @@ -158,5 +169,5 @@ static struct usb_driver plusb_driver = { module_usb_driver(plusb_driver); MODULE_AUTHOR("David Brownell"); -MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1 USB Host to Host Link Driver"); +MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1/27A1 USB Host to Host Link Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 156f7f85e486..2474618404f5 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -908,7 +908,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ - {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0b1b9188625d..07f788c49d57 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -517,6 +517,7 @@ enum rtl8152_flags { /* Define these values to match your device */ #define VENDOR_ID_REALTEK 0x0bda +#define VENDOR_ID_MICROSOFT 0x045e #define VENDOR_ID_SAMSUNG 0x04e8 #define VENDOR_ID_LENOVO 0x17ef #define VENDOR_ID_NVIDIA 0x0955 @@ -1294,6 +1295,7 @@ static void intr_callback(struct urb *urb) } } else { if (netif_carrier_ok(tp->netdev)) { + netif_stop_queue(tp->netdev); set_bit(RTL8152_LINK_CHG, &tp->flags); schedule_delayed_work(&tp->schedule, 0); } @@ -3169,6 +3171,9 @@ static void set_carrier(struct r8152 *tp) napi_enable(&tp->napi); netif_wake_queue(netdev); netif_info(tp, link, netdev, "carrier on\n"); + } else if (netif_queue_stopped(netdev) && + skb_queue_len(&tp->tx_queue) < tp->tx_qlen) { + netif_wake_queue(netdev); } } else { if (netif_carrier_ok(netdev)) { @@ -3702,8 +3707,18 @@ static int rtl8152_resume(struct usb_interface *intf) tp->rtl_ops.autosuspend_en(tp, false); napi_disable(&tp->napi); set_bit(WORK_ENABLE, &tp->flags); - if (netif_carrier_ok(tp->netdev)) - rtl_start_rx(tp); + + if (netif_carrier_ok(tp->netdev)) { + if (rtl8152_get_speed(tp) & LINK_STATUS) { + rtl_start_rx(tp); + } else { + netif_carrier_off(tp->netdev); + tp->rtl_ops.disable(tp); + netif_info(tp, link, tp->netdev, + "linking down\n"); + } + } + napi_enable(&tp->napi); clear_bit(SELECTIVE_SUSPEND, &tp->flags); smp_mb__after_atomic(); @@ -4507,6 +4522,8 @@ static void rtl8152_disconnect(struct usb_interface *intf) static struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)}, {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)}, + {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)}, + {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)}, {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)}, diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 0b17b40d7a4f..190de9a90f73 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2203,13 +2203,9 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) { - struct sk_buff *skb2 = - skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN) | TX_CMD_A_FCS; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 831aa33d078a..5f19fb0f025d 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -2001,13 +2001,13 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev, /* We do not advertise SG, so skbs should be already linearized */ BUG_ON(skb_shinfo(skb)->nr_frags); - if (skb_headroom(skb) < overhead) { - struct sk_buff *skb2 = skb_copy_expand(skb, - overhead, 0, flags); + /* Make writable and expand header space by overhead if required */ + if (skb_cow_head(skb, overhead)) { + /* Must deallocate here as returning NULL to indicate error + * means the skb won't be deallocated in the caller. + */ dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } if (csum) { diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 4a1e9c489f1f..aadfe1d1c37e 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -456,14 +456,9 @@ static struct sk_buff *sr9700_tx_fixup(struct usbnet *dev, struct sk_buff *skb, len = skb->len; - if (skb_headroom(skb) < SR_TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, SR_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SR_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } __skb_push(skb, SR_TX_OVERHEAD); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 3de65ea6531a..453244805c52 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1929,7 +1929,7 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype, " value=0x%04x index=0x%04x size=%d\n", cmd, reqtype, value, index, size); - if (data) { + if (size) { buf = kmalloc(size, GFP_KERNEL); if (!buf) goto out; @@ -1938,8 +1938,13 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype, err = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), cmd, reqtype, value, index, buf, size, USB_CTRL_GET_TIMEOUT); - if (err > 0 && err <= size) - memcpy(data, buf, err); + if (err > 0 && err <= size) { + if (data) + memcpy(data, buf, err); + else + netdev_dbg(dev->net, + "Huh? Data requested but thrown away.\n"); + } kfree(buf); out: return err; @@ -1960,7 +1965,13 @@ static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype, buf = kmemdup(data, size, GFP_KERNEL); if (!buf) goto out; - } + } else { + if (size) { + WARN_ON_ONCE(1); + err = -EINVAL; + goto out; + } + } err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), cmd, reqtype, value, index, buf, size, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ea9890d61967..f36584616e7d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2230,14 +2230,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev) #define MIN_MTU ETH_MIN_MTU #define MAX_MTU ETH_MAX_MTU -static int virtnet_probe(struct virtio_device *vdev) +static int virtnet_validate(struct virtio_device *vdev) { - int i, err; - struct net_device *dev; - struct virtnet_info *vi; - u16 max_queue_pairs; - int mtu; - if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", __func__); @@ -2247,6 +2241,25 @@ static int virtnet_probe(struct virtio_device *vdev) if (!virtnet_validate_features(vdev)) return -EINVAL; + if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) { + int mtu = virtio_cread16(vdev, + offsetof(struct virtio_net_config, + mtu)); + if (mtu < MIN_MTU) + __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU); + } + + return 0; +} + +static int virtnet_probe(struct virtio_device *vdev) +{ + int i, err; + struct net_device *dev; + struct virtnet_info *vi; + u16 max_queue_pairs; + int mtu; + /* Find if host supports multiqueue virtio_net device */ err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ, struct virtio_net_config, @@ -2362,11 +2375,20 @@ static int virtnet_probe(struct virtio_device *vdev) offsetof(struct virtio_net_config, mtu)); if (mtu < dev->min_mtu) { - __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU); - } else { - dev->mtu = mtu; - dev->max_mtu = mtu; + /* Should never trigger: MTU was previously validated + * in virtnet_validate. + */ + dev_err(&vdev->dev, "device MTU appears to have changed " + "it is now %d < %d", mtu, dev->min_mtu); + goto free_stats; } + + dev->mtu = mtu; + dev->max_mtu = mtu; + + /* TODO: size buffers correctly in this case. */ + if (dev->mtu > ETH_DATA_LEN) + vi->big_packets = true; } if (vi->any_header_sg) @@ -2544,6 +2566,7 @@ static struct virtio_driver virtio_net_driver = { .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, + .validate = virtnet_validate, .probe = virtnet_probe, .remove = virtnet_remove, .config_changed = virtnet_config_changed, diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index d6988db1930d..7d909c8183e9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1128,7 +1128,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) goto nla_put_failure; /* rule only needs to appear once */ - nlh->nlmsg_flags &= NLM_F_EXCL; + nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index de19c7c92bc6..85d949e03f79 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -2238,14 +2238,16 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev) struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy); struct brcmf_p2p_info *p2p = &cfg->p2p; struct brcmf_cfg80211_vif *vif; + enum nl80211_iftype iftype; bool wait_for_disable = false; int err; brcmf_dbg(TRACE, "delete P2P vif\n"); vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev); + iftype = vif->wdev.iftype; brcmf_cfg80211_arm_vif_event(cfg, vif); - switch (vif->wdev.iftype) { + switch (iftype) { case NL80211_IFTYPE_P2P_CLIENT: if (test_bit(BRCMF_VIF_STATUS_DISCONNECTING, &vif->sme_state)) wait_for_disable = true; @@ -2275,7 +2277,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev) BRCMF_P2P_DISABLE_TIMEOUT); err = 0; - if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) { + if (iftype != NL80211_IFTYPE_P2P_DEVICE) { brcmf_vif_clear_mgmt_ies(vif); err = brcmf_p2p_release_p2p_if(vif); } @@ -2291,7 +2293,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev) brcmf_remove_interface(vif->ifp, true); brcmf_cfg80211_arm_vif_event(cfg, NULL); - if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) + if (iftype != NL80211_IFTYPE_P2P_DEVICE) p2p->bss_idx[P2PAPI_BSSCFG_CONNECTION].vif = NULL; return err; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index a260cd503200..077bfd8f4c0c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1056,6 +1056,8 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm, if (ret) return ret; + if (count == 0) + return 0; iwl_mvm_fw_dbg_collect(mvm, FW_DBG_TRIGGER_USER, buf, (count - 1), NULL); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 99132ea16ede..c5734e1a02d2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -216,7 +216,8 @@ u32 iwl_mvm_mac_get_queues_mask(struct ieee80211_vif *vif) qmask |= BIT(vif->hw_queue[ac]); } - if (vif->type == NL80211_IFTYPE_AP) + if (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_ADHOC) qmask |= BIT(vif->cab_queue); return qmask; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 6927caecd48e..486dcceed17a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2401,7 +2401,7 @@ void iwl_mvm_sta_pm_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) return; rcu_read_lock(); - sta = mvm->fw_id_to_mac_id[notif->sta_id]; + sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]); if (WARN_ON(IS_ERR_OR_NULL(sta))) { rcu_read_unlock(); return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index b51a2853cc80..9d28db7f56aa 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1806,7 +1806,8 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) iwl_mvm_get_wd_timeout(mvm, vif, false, false); int queue; - if (vif->type == NL80211_IFTYPE_AP) + if (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_ADHOC) queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE; else if (vif->type == NL80211_IFTYPE_P2P_DEVICE) queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE; @@ -1837,7 +1838,8 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * enabled-cab_queue to the mask) */ if (iwl_mvm_is_dqa_supported(mvm) && - vif->type == NL80211_IFTYPE_AP) { + (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_ADHOC)) { struct iwl_trans_txq_scd_cfg cfg = { .fifo = IWL_MVM_TX_FIFO_MCAST, .sta_id = mvmvif->bcast_sta.sta_id, @@ -1862,7 +1864,8 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); - if (vif->type == NL80211_IFTYPE_AP) + if (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_ADHOC) iwl_mvm_disable_txq(mvm, vif->cab_queue, vif->cab_queue, IWL_MAX_TID_COUNT, 0); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 3f37075f4cde..1ba0a6f55503 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -506,6 +506,7 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, switch (info->control.vif->type) { case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_ADHOC: /* * Handle legacy hostapd as well, where station may be added * only after assoc. Take care of the case where we send a @@ -517,7 +518,8 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, if (info->hw_queue == info->control.vif->cab_queue) return info->hw_queue; - WARN_ONCE(1, "fc=0x%02x", le16_to_cpu(fc)); + WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC, + "fc=0x%02x", le16_to_cpu(fc)); return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE; case NL80211_IFTYPE_P2P_DEVICE: if (ieee80211_is_mgmt(fc)) @@ -584,7 +586,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) iwl_mvm_vif_from_mac80211(info.control.vif); if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE || - info.control.vif->type == NL80211_IFTYPE_AP) { + info.control.vif->type == NL80211_IFTYPE_AP || + info.control.vif->type == NL80211_IFTYPE_ADHOC) { sta_id = mvmvif->bcast_sta.sta_id; queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info, hdr->frame_control); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index caea350f05aa..bdc379178e87 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -1742,12 +1742,14 @@ void rtl_c2hcmd_enqueue(struct ieee80211_hw *hw, u8 tag, u8 len, u8 *val) unsigned long flags; struct rtl_c2hcmd *c2hcmd; - c2hcmd = kmalloc(sizeof(*c2hcmd), GFP_KERNEL); + c2hcmd = kmalloc(sizeof(*c2hcmd), + in_interrupt() ? GFP_ATOMIC : GFP_KERNEL); if (!c2hcmd) goto label_err; - c2hcmd->val = kmalloc(len, GFP_KERNEL); + c2hcmd->val = kmalloc(len, + in_interrupt() ? GFP_ATOMIC : GFP_KERNEL); if (!c2hcmd->val) goto label_err2; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 23d4a1728cdf..351bac8f6503 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -934,8 +934,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL); if (rc < 0) goto out_unlock; + nvdimm_bus_unlock(&nvdimm_bus->dev); + if (copy_to_user(p, buf, buf_len)) rc = -EFAULT; + + vfree(buf); + return rc; + out_unlock: nvdimm_bus_unlock(&nvdimm_bus->dev); out: diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index b3323c0697f6..ca6d572c48fc 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -243,7 +243,15 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns, } if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) { - if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)) { + /* + * FIXME: nsio_rw_bytes() may be called from atomic + * context in the btt case and nvdimm_clear_poison() + * takes a sleeping lock. Until the locking can be + * reworked this capability requires that the namespace + * is not claimed by btt. + */ + if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512) + && (!ndns->claim || !is_nd_btt(ndns->claim))) { long cleared; cleared = nvdimm_clear_poison(&ndns->dev, offset, size); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 0eedc49e0d47..8b721321be5b 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -395,7 +395,7 @@ EXPORT_SYMBOL_GPL(nvdimm_create); int alias_dpa_busy(struct device *dev, void *data) { - resource_size_t map_end, blk_start, new, busy; + resource_size_t map_end, blk_start, new; struct blk_alloc_info *info = data; struct nd_mapping *nd_mapping; struct nd_region *nd_region; @@ -436,29 +436,19 @@ int alias_dpa_busy(struct device *dev, void *data) retry: /* * Find the free dpa from the end of the last pmem allocation to - * the end of the interleave-set mapping that is not already - * covered by a blk allocation. + * the end of the interleave-set mapping. */ - busy = 0; for_each_dpa_resource(ndd, res) { + if (strncmp(res->name, "pmem", 4) != 0) + continue; if ((res->start >= blk_start && res->start < map_end) || (res->end >= blk_start && res->end <= map_end)) { - if (strncmp(res->name, "pmem", 4) == 0) { - new = max(blk_start, min(map_end + 1, - res->end + 1)); - if (new != blk_start) { - blk_start = new; - goto retry; - } - } else - busy += min(map_end, res->end) - - max(nd_mapping->start, res->start) + 1; - } else if (nd_mapping->start > res->start - && map_end < res->end) { - /* total eclipse of the PMEM region mapping */ - busy += nd_mapping->size; - break; + new = max(blk_start, min(map_end + 1, res->end + 1)); + if (new != blk_start) { + blk_start = new; + goto retry; + } } } @@ -470,52 +460,11 @@ int alias_dpa_busy(struct device *dev, void *data) return 1; } - info->available -= blk_start - nd_mapping->start + busy; + info->available -= blk_start - nd_mapping->start; return 0; } -static int blk_dpa_busy(struct device *dev, void *data) -{ - struct blk_alloc_info *info = data; - struct nd_mapping *nd_mapping; - struct nd_region *nd_region; - resource_size_t map_end; - int i; - - if (!is_nd_pmem(dev)) - return 0; - - nd_region = to_nd_region(dev); - for (i = 0; i < nd_region->ndr_mappings; i++) { - nd_mapping = &nd_region->mapping[i]; - if (nd_mapping->nvdimm == info->nd_mapping->nvdimm) - break; - } - - if (i >= nd_region->ndr_mappings) - return 0; - - map_end = nd_mapping->start + nd_mapping->size - 1; - if (info->res->start >= nd_mapping->start - && info->res->start < map_end) { - if (info->res->end <= map_end) { - info->busy = 0; - return 1; - } else { - info->busy -= info->res->end - map_end; - return 0; - } - } else if (info->res->end >= nd_mapping->start - && info->res->end <= map_end) { - info->busy -= nd_mapping->start - info->res->start; - return 0; - } else { - info->busy -= nd_mapping->size; - return 0; - } -} - /** * nd_blk_available_dpa - account the unused dpa of BLK region * @nd_mapping: container of dpa-resource-root + labels @@ -545,11 +494,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) for_each_dpa_resource(ndd, res) { if (strncmp(res->name, "blk", 3) != 0) continue; - - info.res = res; - info.busy = resource_size(res); - device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy); - info.available -= info.busy; + info.available -= resource_size(res); } return info.available; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9b3b57fef446..eeb409c287b8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -270,7 +270,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, memset(cmnd, 0, sizeof(*cmnd)); cmnd->dsm.opcode = nvme_cmd_dsm; cmnd->dsm.nsid = cpu_to_le32(ns->ns_id); - cmnd->dsm.nr = segments - 1; + cmnd->dsm.nr = cpu_to_le32(segments - 1); cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD); req->special_vec.bv_page = virt_to_page(range); @@ -1316,6 +1316,14 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) table->entries[state] = target; /* + * Don't allow transitions to the deepest state + * if it's quirked off. + */ + if (state == ctrl->npss && + (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) + continue; + + /* * Is this state a useful non-operational state for * higher-power states to autonomously transition to? */ @@ -1387,16 +1395,15 @@ struct nvme_core_quirk_entry { }; static const struct nvme_core_quirk_entry core_quirks[] = { - /* - * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes - * the controller to go out to lunch. It dies when the watchdog - * timer reads CSTS and gets 0xffffffff. - */ { - .vid = 0x144d, - .fr = "BXW75D0Q", + /* + * This Toshiba device seems to die using any APST states. See: + * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11 + */ + .vid = 0x1179, + .mn = "THNSF5256GPUK TOSHIBA", .quirks = NVME_QUIRK_NO_APST, - }, + } }; /* match is null-terminated but idstr is space-padded. */ diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9690beb15e69..d996ca73d3be 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2023,7 +2023,7 @@ nvme_fc_configure_admin_queue(struct nvme_fc_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize); error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap); if (error) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 2aa20e3e5675..ab2d6ec7eb5c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -83,6 +83,11 @@ enum nvme_quirks { * APST should not be used. */ NVME_QUIRK_NO_APST = (1 << 4), + + /* + * The deepest sleep state should not be used. + */ + NVME_QUIRK_NO_DEEPEST_PS = (1 << 5), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 26a5fd05fe88..5d309535abbd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -19,6 +19,7 @@ #include <linux/blk-mq-pci.h> #include <linux/cpu.h> #include <linux/delay.h> +#include <linux/dmi.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/genhd.h> @@ -1943,10 +1944,31 @@ static int nvme_dev_map(struct nvme_dev *dev) return -ENODEV; } +static unsigned long check_dell_samsung_bug(struct pci_dev *pdev) +{ + if (pdev->vendor == 0x144d && pdev->device == 0xa802) { + /* + * Several Samsung devices seem to drop off the PCIe bus + * randomly when APST is on and uses the deepest sleep state. + * This has been observed on a Samsung "SM951 NVMe SAMSUNG + * 256GB", a "PM951 NVMe SAMSUNG 512GB", and a "Samsung SSD + * 950 PRO 256GB", but it seems to be restricted to two Dell + * laptops. + */ + if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") && + (dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") || + dmi_match(DMI_PRODUCT_NAME, "Precision 5510"))) + return NVME_QUIRK_NO_DEEPEST_PS; + } + + return 0; +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; struct nvme_dev *dev; + unsigned long quirks = id->driver_data; node = dev_to_node(&pdev->dev); if (node == NUMA_NO_NODE) @@ -1978,8 +2000,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto put_pci; + quirks |= check_dell_samsung_bug(pdev); + result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - id->driver_data); + quirks); if (result) goto release_pools; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 47a479f26e5d..16f84eb0b95e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1606,7 +1606,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize); error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap); if (error) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index a7bcff45f437..76450b0c55f1 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -100,7 +100,7 @@ static u16 nvmet_get_smart_log(struct nvmet_req *req, u16 status; WARN_ON(req == NULL || slog == NULL); - if (req->cmd->get_log_page.nsid == 0xFFFFFFFF) + if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF)) status = nvmet_get_smart_log_all(req, slog); else status = nvmet_get_smart_log_nsid(req, slog); diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c index 4195115c7e54..6b0baa9caab9 100644 --- a/drivers/nvme/target/io-cmd.c +++ b/drivers/nvme/target/io-cmd.c @@ -180,7 +180,7 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req) sector = le64_to_cpu(write_zeroes->slba) << (req->ns->blksize_shift - 9); - nr_sector = (((sector_t)le32_to_cpu(write_zeroes->length)) << + nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) << (req->ns->blksize_shift - 9)) + 1; if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector, @@ -230,7 +230,7 @@ int nvmet_parse_io_cmd(struct nvmet_req *req) return 0; case nvme_cmd_dsm: req->execute = nvmet_execute_dsm; - req->data_len = le32_to_cpu(cmd->dsm.nr + 1) * + req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 22f7bc6bac7f..c7b0b6a52708 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -392,7 +392,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize); error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap); if (error) diff --git a/drivers/pci/dwc/Kconfig b/drivers/pci/dwc/Kconfig index dfb8a69afc28..d2d2ba5b8a68 100644 --- a/drivers/pci/dwc/Kconfig +++ b/drivers/pci/dwc/Kconfig @@ -89,6 +89,7 @@ config PCI_HISI depends on PCI_MSI_IRQ_DOMAIN select PCIEPORTBUS select PCIE_DW_HOST + select PCI_HOST_COMMON help Say Y here if you want PCIe controller support on HiSilicon Hip05 and Hip06 SoCs diff --git a/drivers/pci/dwc/pcie-artpec6.c b/drivers/pci/dwc/pcie-artpec6.c index fcd3ef845883..6d23683c0892 100644 --- a/drivers/pci/dwc/pcie-artpec6.c +++ b/drivers/pci/dwc/pcie-artpec6.c @@ -234,6 +234,9 @@ static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie, return 0; } +static const struct dw_pcie_ops dw_pcie_ops = { +}; + static int artpec6_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -252,6 +255,7 @@ static int artpec6_pcie_probe(struct platform_device *pdev) return -ENOMEM; pci->dev = dev; + pci->ops = &dw_pcie_ops; artpec6_pcie->pci = pci; diff --git a/drivers/pci/dwc/pcie-designware-plat.c b/drivers/pci/dwc/pcie-designware-plat.c index b6c832ba39dd..f20d494922ab 100644 --- a/drivers/pci/dwc/pcie-designware-plat.c +++ b/drivers/pci/dwc/pcie-designware-plat.c @@ -86,6 +86,9 @@ static int dw_plat_add_pcie_port(struct pcie_port *pp, return 0; } +static const struct dw_pcie_ops dw_pcie_ops = { +}; + static int dw_plat_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -103,6 +106,7 @@ static int dw_plat_pcie_probe(struct platform_device *pdev) return -ENOMEM; pci->dev = dev; + pci->ops = &dw_pcie_ops; dw_plat_pcie->pci = pci; diff --git a/drivers/pci/dwc/pcie-hisi.c b/drivers/pci/dwc/pcie-hisi.c index fd66a3199db7..cf9d6a9d9fd4 100644 --- a/drivers/pci/dwc/pcie-hisi.c +++ b/drivers/pci/dwc/pcie-hisi.c @@ -380,9 +380,13 @@ struct pci_ecam_ops hisi_pcie_platform_ops = { static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = { { - .compatible = "hisilicon,pcie-almost-ecam", + .compatible = "hisilicon,hip06-pcie-ecam", .data = (void *) &hisi_pcie_platform_ops, }, + { + .compatible = "hisilicon,hip07-pcie-ecam", + .data = (void *) &hisi_pcie_platform_ops, + }, {}, }; diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c index b89c373555c5..6e031b522529 100644 --- a/drivers/pci/host/pci-thunder-pem.c +++ b/drivers/pci/host/pci-thunder-pem.c @@ -375,7 +375,6 @@ static void thunder_pem_legacy_fw(struct acpi_pci_root *root, index -= node * PEM_MAX_DOM_IN_NODE; res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) | FIELD_PREP(PEM_INDX_MASK, index); - res_pem->end = res_pem->start + SZ_16M - 1; res_pem->flags = IORESOURCE_MEM; } @@ -399,8 +398,15 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg) */ if (ret) { thunder_pem_legacy_fw(root, res_pem); - /* Reserve PEM-specific resources and PCI configuration space */ + /* + * Reserve 64K size PEM specific resources. The full 16M range + * size is required for thunder_pem_init() call. + */ + res_pem->end = res_pem->start + SZ_64K - 1; thunder_pem_reserve_range(dev, root->segment, res_pem); + res_pem->end = res_pem->start + SZ_16M - 1; + + /* Reserve PCI configuration space as well. */ thunder_pem_reserve_range(dev, root->segment, &cfg->res); } diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index d69046537b75..32822b0d9cd0 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2010,29 +2010,57 @@ out_err: return ERR_PTR(ret); } -static int pinctrl_create_and_start(struct pinctrl_dev *pctldev) +static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev) { pctldev->p = create_pinctrl(pctldev->dev, pctldev); - if (!IS_ERR(pctldev->p)) { - kref_get(&pctldev->p->users); - pctldev->hog_default = - pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); - if (IS_ERR(pctldev->hog_default)) { - dev_dbg(pctldev->dev, - "failed to lookup the default state\n"); - } else { - if (pinctrl_select_state(pctldev->p, - pctldev->hog_default)) - dev_err(pctldev->dev, - "failed to select default state\n"); - } + if (PTR_ERR(pctldev->p) == -ENODEV) { + dev_dbg(pctldev->dev, "no hogs found\n"); - pctldev->hog_sleep = - pinctrl_lookup_state(pctldev->p, - PINCTRL_STATE_SLEEP); - if (IS_ERR(pctldev->hog_sleep)) - dev_dbg(pctldev->dev, - "failed to lookup the sleep state\n"); + return 0; + } + + if (IS_ERR(pctldev->p)) { + dev_err(pctldev->dev, "error claiming hogs: %li\n", + PTR_ERR(pctldev->p)); + + return PTR_ERR(pctldev->p); + } + + kref_get(&pctldev->p->users); + pctldev->hog_default = + pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); + if (IS_ERR(pctldev->hog_default)) { + dev_dbg(pctldev->dev, + "failed to lookup the default state\n"); + } else { + if (pinctrl_select_state(pctldev->p, + pctldev->hog_default)) + dev_err(pctldev->dev, + "failed to select default state\n"); + } + + pctldev->hog_sleep = + pinctrl_lookup_state(pctldev->p, + PINCTRL_STATE_SLEEP); + if (IS_ERR(pctldev->hog_sleep)) + dev_dbg(pctldev->dev, + "failed to lookup the sleep state\n"); + + return 0; +} + +int pinctrl_enable(struct pinctrl_dev *pctldev) +{ + int error; + + error = pinctrl_claim_hogs(pctldev); + if (error) { + dev_err(pctldev->dev, "could not claim hogs: %i\n", + error); + mutex_destroy(&pctldev->mutex); + kfree(pctldev); + + return error; } mutex_lock(&pinctrldev_list_mutex); @@ -2043,6 +2071,7 @@ static int pinctrl_create_and_start(struct pinctrl_dev *pctldev) return 0; } +EXPORT_SYMBOL_GPL(pinctrl_enable); /** * pinctrl_register() - register a pin controller device @@ -2065,25 +2094,30 @@ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, if (IS_ERR(pctldev)) return pctldev; - error = pinctrl_create_and_start(pctldev); - if (error) { - mutex_destroy(&pctldev->mutex); - kfree(pctldev); - + error = pinctrl_enable(pctldev); + if (error) return ERR_PTR(error); - } return pctldev; } EXPORT_SYMBOL_GPL(pinctrl_register); +/** + * pinctrl_register_and_init() - register and init pin controller device + * @pctldesc: descriptor for this pin controller + * @dev: parent device for this pin controller + * @driver_data: private pin controller data for this pin controller + * @pctldev: pin controller device + * + * Note that pinctrl_enable() still needs to be manually called after + * this once the driver is ready. + */ int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data, struct pinctrl_dev **pctldev) { struct pinctrl_dev *p; - int error; p = pinctrl_init_controller(pctldesc, dev, driver_data); if (IS_ERR(p)) @@ -2097,15 +2131,6 @@ int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, */ *pctldev = p; - error = pinctrl_create_and_start(p); - if (error) { - mutex_destroy(&p->mutex); - kfree(p); - *pctldev = NULL; - - return error; - } - return 0; } EXPORT_SYMBOL_GPL(pinctrl_register_and_init); diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index a7ace9e1ad81..74bd90dfd7b1 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -790,7 +790,7 @@ int imx_pinctrl_probe(struct platform_device *pdev, dev_info(&pdev->dev, "initialized IMX pinctrl driver\n"); - return 0; + return pinctrl_enable(ipctl->pctl); free: imx_free_resources(ipctl); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index f80134e3e0b6..9ff790174906 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -13,6 +13,7 @@ * published by the Free Software Foundation. */ +#include <linux/dmi.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -1524,10 +1525,31 @@ static void chv_gpio_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } +/* + * Certain machines seem to hardcode Linux IRQ numbers in their ACPI + * tables. Since we leave GPIOs that are not capable of generating + * interrupts out of the irqdomain the numbering will be different and + * cause devices using the hardcoded IRQ numbers fail. In order not to + * break such machines we will only mask pins from irqdomain if the machine + * is not listed below. + */ +static const struct dmi_system_id chv_no_valid_mask[] = { + { + /* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */ + .ident = "Acer Chromebook (CYAN)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"), + DMI_MATCH(DMI_BIOS_DATE, "05/21/2016"), + }, + } +}; + static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) { const struct chv_gpio_pinrange *range; struct gpio_chip *chip = &pctrl->chip; + bool need_valid_mask = !dmi_check_system(chv_no_valid_mask); int ret, i, offset; *chip = chv_gpio_chip; @@ -1536,7 +1558,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) chip->label = dev_name(pctrl->dev); chip->parent = pctrl->dev; chip->base = -1; - chip->irq_need_valid_mask = true; + chip->irq_need_valid_mask = need_valid_mask; ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl); if (ret) { @@ -1567,7 +1589,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) intsel &= CHV_PADCTRL0_INTSEL_MASK; intsel >>= CHV_PADCTRL0_INTSEL_SHIFT; - if (intsel >= pctrl->community->nirqs) + if (need_valid_mask && intsel >= pctrl->community->nirqs) clear_bit(i, chip->irq_valid_mask); } diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 8b2d45e85bae..9c267dcda094 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1781,7 +1781,7 @@ static int pcs_probe(struct platform_device *pdev) dev_info(pcs->dev, "%i pins at pa %p size %u\n", pcs->desc.npins, pcs->base, pcs->size); - return 0; + return pinctrl_enable(pcs->pctl); free: pcs_free_resources(pcs); diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index f9b49967f512..63e51b56a22a 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -1468,82 +1468,82 @@ const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = { /* pin banks of exynos5433 pin-controller - ALIVE */ static const struct samsung_pin_bank_data exynos5433_pin_banks0[] __initconst = { - EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00), - EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04), - EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08), - EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c), - EXYNOS_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1), - EXYNOS_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1), - EXYNOS_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1), - EXYNOS_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1), - EXYNOS_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1), + EXYNOS5433_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00), + EXYNOS5433_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04), + EXYNOS5433_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08), + EXYNOS5433_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c), + EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1), + EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1), + EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1), + EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1), + EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1), }; /* pin banks of exynos5433 pin-controller - AUD */ static const struct samsung_pin_bank_data exynos5433_pin_banks1[] __initconst = { - EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00), - EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04), + EXYNOS5433_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00), + EXYNOS5433_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04), }; /* pin banks of exynos5433 pin-controller - CPIF */ static const struct samsung_pin_bank_data exynos5433_pin_banks2[] __initconst = { - EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00), + EXYNOS5433_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00), }; /* pin banks of exynos5433 pin-controller - eSE */ static const struct samsung_pin_bank_data exynos5433_pin_banks3[] __initconst = { - EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00), + EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00), }; /* pin banks of exynos5433 pin-controller - FINGER */ static const struct samsung_pin_bank_data exynos5433_pin_banks4[] __initconst = { - EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00), + EXYNOS5433_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00), }; /* pin banks of exynos5433 pin-controller - FSYS */ static const struct samsung_pin_bank_data exynos5433_pin_banks5[] __initconst = { - EXYNOS_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00), - EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04), - EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08), - EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c), - EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10), - EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14), + EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00), + EXYNOS5433_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04), + EXYNOS5433_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08), + EXYNOS5433_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c), + EXYNOS5433_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10), + EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14), }; /* pin banks of exynos5433 pin-controller - IMEM */ static const struct samsung_pin_bank_data exynos5433_pin_banks6[] __initconst = { - EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00), + EXYNOS5433_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00), }; /* pin banks of exynos5433 pin-controller - NFC */ static const struct samsung_pin_bank_data exynos5433_pin_banks7[] __initconst = { - EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00), + EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00), }; /* pin banks of exynos5433 pin-controller - PERIC */ static const struct samsung_pin_bank_data exynos5433_pin_banks8[] __initconst = { - EXYNOS_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00), - EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04), - EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08), - EXYNOS_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c), - EXYNOS_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10), - EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14), - EXYNOS_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18), - EXYNOS_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c), - EXYNOS_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20), - EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24), - EXYNOS_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28), - EXYNOS_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c), - EXYNOS_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30), - EXYNOS_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34), - EXYNOS_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38), - EXYNOS_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c), - EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40), + EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00), + EXYNOS5433_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04), + EXYNOS5433_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08), + EXYNOS5433_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c), + EXYNOS5433_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10), + EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14), + EXYNOS5433_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18), + EXYNOS5433_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c), + EXYNOS5433_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20), + EXYNOS5433_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24), + EXYNOS5433_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28), + EXYNOS5433_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c), + EXYNOS5433_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30), + EXYNOS5433_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34), + EXYNOS5433_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38), + EXYNOS5433_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c), + EXYNOS5433_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40), }; /* pin banks of exynos5433 pin-controller - TOUCH */ static const struct samsung_pin_bank_data exynos5433_pin_banks9[] __initconst = { - EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00), + EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00), }; /* diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h index a473092fb8d2..cd046eb7d705 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.h +++ b/drivers/pinctrl/samsung/pinctrl-exynos.h @@ -79,17 +79,6 @@ .name = id \ } -#define EXYNOS_PIN_BANK_EINTW_EXT(pins, reg, id, offs, pctl_idx) \ - { \ - .type = &bank_type_alive, \ - .pctl_offset = reg, \ - .nr_pins = pins, \ - .eint_type = EINT_TYPE_WKUP, \ - .eint_offset = offs, \ - .name = id, \ - .pctl_res_idx = pctl_idx, \ - } \ - #define EXYNOS5433_PIN_BANK_EINTG(pins, reg, id, offs) \ { \ .type = &exynos5433_bank_type_off, \ diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c index 08150a321be6..a70157f0acf4 100644 --- a/drivers/pinctrl/sh-pfc/pinctrl.c +++ b/drivers/pinctrl/sh-pfc/pinctrl.c @@ -816,6 +816,13 @@ int sh_pfc_register_pinctrl(struct sh_pfc *pfc) pmx->pctl_desc.pins = pmx->pins; pmx->pctl_desc.npins = pfc->info->nr_pins; - return devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx, - &pmx->pctl); + ret = devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx, + &pmx->pctl); + if (ret) { + dev_err(pfc->dev, "could not register: %i\n", ret); + + return ret; + } + + return pinctrl_enable(pmx->pctl); } diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c index 717e3404900c..362c50918c13 100644 --- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c +++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c @@ -893,6 +893,8 @@ static int ti_iodelay_probe(struct platform_device *pdev) platform_set_drvdata(pdev, iod); + return pinctrl_enable(iod->pctl); + exit_out: of_node_put(np); return ret; diff --git a/drivers/pwm/pwm-lpss-pci.c b/drivers/pwm/pwm-lpss-pci.c index 053088b9b66e..c1527cb645be 100644 --- a/drivers/pwm/pwm-lpss-pci.c +++ b/drivers/pwm/pwm-lpss-pci.c @@ -36,6 +36,14 @@ static const struct pwm_lpss_boardinfo pwm_lpss_bxt_info = { .clk_rate = 19200000, .npwm = 4, .base_unit_bits = 22, + .bypass = true, +}; + +/* Tangier */ +static const struct pwm_lpss_boardinfo pwm_lpss_tng_info = { + .clk_rate = 19200000, + .npwm = 4, + .base_unit_bits = 22, }; static int pwm_lpss_probe_pci(struct pci_dev *pdev, @@ -97,7 +105,7 @@ static const struct pci_device_id pwm_lpss_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x0ac8), (unsigned long)&pwm_lpss_bxt_info}, { PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&pwm_lpss_byt_info}, { PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&pwm_lpss_byt_info}, - { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_bxt_info}, + { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_tng_info}, { PCI_VDEVICE(INTEL, 0x1ac8), (unsigned long)&pwm_lpss_bxt_info}, { PCI_VDEVICE(INTEL, 0x2288), (unsigned long)&pwm_lpss_bsw_info}, { PCI_VDEVICE(INTEL, 0x2289), (unsigned long)&pwm_lpss_bsw_info}, diff --git a/drivers/pwm/pwm-lpss-platform.c b/drivers/pwm/pwm-lpss-platform.c index b22b6fdadb9a..5d6ed1507d29 100644 --- a/drivers/pwm/pwm-lpss-platform.c +++ b/drivers/pwm/pwm-lpss-platform.c @@ -37,6 +37,7 @@ static const struct pwm_lpss_boardinfo pwm_lpss_bxt_info = { .clk_rate = 19200000, .npwm = 4, .base_unit_bits = 22, + .bypass = true, }; static int pwm_lpss_probe_platform(struct platform_device *pdev) diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c index 689d2c1cbead..8db0d40ccacd 100644 --- a/drivers/pwm/pwm-lpss.c +++ b/drivers/pwm/pwm-lpss.c @@ -57,7 +57,7 @@ static inline void pwm_lpss_write(const struct pwm_device *pwm, u32 value) writel(value, lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM); } -static int pwm_lpss_update(struct pwm_device *pwm) +static int pwm_lpss_wait_for_update(struct pwm_device *pwm) { struct pwm_lpss_chip *lpwm = to_lpwm(pwm->chip); const void __iomem *addr = lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM; @@ -65,8 +65,6 @@ static int pwm_lpss_update(struct pwm_device *pwm) u32 val; int err; - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); - /* * PWM Configuration register has SW_UPDATE bit that is set when a new * configuration is written to the register. The bit is automatically @@ -122,6 +120,12 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, pwm_lpss_write(pwm, ctrl); } +static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond) +{ + if (cond) + pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE); +} + static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state) { @@ -137,18 +141,21 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, return ret; } pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - ret = pwm_lpss_update(pwm); + pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); + pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false); + ret = pwm_lpss_wait_for_update(pwm); if (ret) { pm_runtime_put(chip->dev); return ret; } - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE); + pwm_lpss_cond_enable(pwm, lpwm->info->bypass == true); } else { ret = pwm_lpss_is_updating(pwm); if (ret) return ret; pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - return pwm_lpss_update(pwm); + pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); + return pwm_lpss_wait_for_update(pwm); } } else if (pwm_is_enabled(pwm)) { pwm_lpss_write(pwm, pwm_lpss_read(pwm) & ~PWM_ENABLE); diff --git a/drivers/pwm/pwm-lpss.h b/drivers/pwm/pwm-lpss.h index c94cd7c2695d..98306bb02cfe 100644 --- a/drivers/pwm/pwm-lpss.h +++ b/drivers/pwm/pwm-lpss.h @@ -22,6 +22,7 @@ struct pwm_lpss_boardinfo { unsigned long clk_rate; unsigned int npwm; unsigned long base_unit_bits; + bool bypass; }; struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev, struct resource *r, diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c index ef89df1f7336..744d56197286 100644 --- a/drivers/pwm/pwm-rockchip.c +++ b/drivers/pwm/pwm-rockchip.c @@ -191,6 +191,28 @@ static int rockchip_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } +static int rockchip_pwm_enable(struct pwm_chip *chip, + struct pwm_device *pwm, + bool enable, + enum pwm_polarity polarity) +{ + struct rockchip_pwm_chip *pc = to_rockchip_pwm_chip(chip); + int ret; + + if (enable) { + ret = clk_enable(pc->clk); + if (ret) + return ret; + } + + pc->data->set_enable(chip, pwm, enable, polarity); + + if (!enable) + clk_disable(pc->clk); + + return 0; +} + static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state) { @@ -207,22 +229,26 @@ static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return ret; if (state->polarity != curstate.polarity && enabled) { - pc->data->set_enable(chip, pwm, false, state->polarity); + ret = rockchip_pwm_enable(chip, pwm, false, state->polarity); + if (ret) + goto out; enabled = false; } ret = rockchip_pwm_config(chip, pwm, state->duty_cycle, state->period); if (ret) { if (enabled != curstate.enabled) - pc->data->set_enable(chip, pwm, !enabled, - state->polarity); - + rockchip_pwm_enable(chip, pwm, !enabled, + state->polarity); goto out; } - if (state->enabled != enabled) - pc->data->set_enable(chip, pwm, state->enabled, - state->polarity); + if (state->enabled != enabled) { + ret = rockchip_pwm_enable(chip, pwm, state->enabled, + state->polarity); + if (ret) + goto out; + } /* * Update the state with the real hardware, which can differ a bit diff --git a/drivers/reset/core.c b/drivers/reset/core.c index f1e5e65388bb..cd739d2fa160 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -275,7 +275,7 @@ int reset_control_status(struct reset_control *rstc) } EXPORT_SYMBOL_GPL(reset_control_status); -static struct reset_control *__reset_control_get( +static struct reset_control *__reset_control_get_internal( struct reset_controller_dev *rcdev, unsigned int index, bool shared) { @@ -308,7 +308,7 @@ static struct reset_control *__reset_control_get( return rstc; } -static void __reset_control_put(struct reset_control *rstc) +static void __reset_control_put_internal(struct reset_control *rstc) { lockdep_assert_held(&reset_list_mutex); @@ -377,7 +377,7 @@ struct reset_control *__of_reset_control_get(struct device_node *node, } /* reset_list_mutex also protects the rcdev's reset_control list */ - rstc = __reset_control_get(rcdev, rstc_id, shared); + rstc = __reset_control_get_internal(rcdev, rstc_id, shared); mutex_unlock(&reset_list_mutex); @@ -385,6 +385,17 @@ struct reset_control *__of_reset_control_get(struct device_node *node, } EXPORT_SYMBOL_GPL(__of_reset_control_get); +struct reset_control *__reset_control_get(struct device *dev, const char *id, + int index, bool shared, bool optional) +{ + if (dev->of_node) + return __of_reset_control_get(dev->of_node, id, index, shared, + optional); + + return optional ? NULL : ERR_PTR(-EINVAL); +} +EXPORT_SYMBOL_GPL(__reset_control_get); + /** * reset_control_put - free the reset controller * @rstc: reset controller @@ -396,7 +407,7 @@ void reset_control_put(struct reset_control *rstc) return; mutex_lock(&reset_list_mutex); - __reset_control_put(rstc); + __reset_control_put_internal(rstc); mutex_unlock(&reset_list_mutex); } EXPORT_SYMBOL_GPL(reset_control_put); @@ -417,8 +428,7 @@ struct reset_control *__devm_reset_control_get(struct device *dev, if (!ptr) return ERR_PTR(-ENOMEM); - rstc = __of_reset_control_get(dev ? dev->of_node : NULL, - id, index, shared, optional); + rstc = __reset_control_get(dev, id, index, shared, optional); if (!IS_ERR(rstc)) { *ptr = rstc; devres_add(dev, ptr); diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index e7addea8741b..d9561e39c3b2 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -961,7 +961,8 @@ int qeth_bridgeport_query_ports(struct qeth_card *card, int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role); int qeth_bridgeport_an_set(struct qeth_card *card, int enable); int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int); -int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int); +int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, + int extra_elems, int data_offset); int qeth_get_elements_for_frags(struct sk_buff *); int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *, struct sk_buff *, struct qeth_hdr *, int, int, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 315d8a2db7c0..9a5f99ccb122 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -3837,6 +3837,7 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); * @card: qeth card structure, to check max. elems. * @skb: SKB address * @extra_elems: extra elems needed, to check against max. + * @data_offset: range starts at skb->data + data_offset * * Returns the number of pages, and thus QDIO buffer elements, needed to cover * skb data, including linear part and fragments. Checks if the result plus @@ -3844,10 +3845,10 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); * Note: extra_elems is not included in the returned result. */ int qeth_get_elements_no(struct qeth_card *card, - struct sk_buff *skb, int extra_elems) + struct sk_buff *skb, int extra_elems, int data_offset) { int elements = qeth_get_elements_for_range( - (addr_t)skb->data, + (addr_t)skb->data + data_offset, (addr_t)skb->data + skb_headlen(skb)) + qeth_get_elements_for_frags(skb); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index bea483307618..af4e6a639fec 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -849,7 +849,7 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) * chaining we can not send long frag lists */ if ((card->info.type != QETH_CARD_TYPE_IQD) && - !qeth_get_elements_no(card, new_skb, 0)) { + !qeth_get_elements_no(card, new_skb, 0, 0)) { int lin_rc = skb_linearize(new_skb); if (card->options.performance_stats) { @@ -894,7 +894,8 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) } } - elements = qeth_get_elements_no(card, new_skb, elements_needed); + elements = qeth_get_elements_no(card, new_skb, elements_needed, + (data_offset > 0) ? data_offset : 0); if (!elements) { if (data_offset >= 0) kmem_cache_free(qeth_core_header_cache, hdr); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 06d0addcc058..653f0fb76573 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2609,17 +2609,13 @@ static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card, char daddr[16]; struct af_iucv_trans_hdr *iucv_hdr; - skb_pull(skb, 14); - card->dev->header_ops->create(skb, card->dev, 0, - card->dev->dev_addr, card->dev->dev_addr, - card->dev->addr_len); - skb_pull(skb, 14); - iucv_hdr = (struct af_iucv_trans_hdr *)skb->data; memset(hdr, 0, sizeof(struct qeth_hdr)); hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; hdr->hdr.l3.ext_flags = 0; - hdr->hdr.l3.length = skb->len; + hdr->hdr.l3.length = skb->len - ETH_HLEN; hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST; + + iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN); memset(daddr, 0, sizeof(daddr)); daddr[0] = 0xfe; daddr[1] = 0x80; @@ -2823,10 +2819,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) if ((card->info.type == QETH_CARD_TYPE_IQD) && !skb_is_nonlinear(skb)) { new_skb = skb; - if (new_skb->protocol == ETH_P_AF_IUCV) - data_offset = 0; - else - data_offset = ETH_HLEN; + data_offset = ETH_HLEN; hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC); if (!hdr) goto tx_drop; @@ -2867,7 +2860,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) */ if ((card->info.type != QETH_CARD_TYPE_IQD) && ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) || - (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) { + (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) { int lin_rc = skb_linearize(new_skb); if (card->options.performance_stats) { @@ -2909,7 +2902,8 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) elements = use_tso ? qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) : - qeth_get_elements_no(card, new_skb, hdr_elements); + qeth_get_elements_no(card, new_skb, hdr_elements, + (data_offset > 0) ? data_offset : 0); if (!elements) { if (data_offset >= 0) kmem_cache_free(qeth_core_header_cache, hdr); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index d036a806f31c..d281492009fb 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1690,9 +1690,6 @@ struct aac_dev #define aac_adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4) \ (dev)->a_ops.adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4) -#define aac_adapter_check_health(dev) \ - (dev)->a_ops.adapter_check_health(dev) - #define aac_adapter_restart(dev, bled, reset_type) \ ((dev)->a_ops.adapter_restart(dev, bled, reset_type)) @@ -2615,6 +2612,14 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor) return capacity; } +static inline int aac_adapter_check_health(struct aac_dev *dev) +{ + if (unlikely(pci_channel_offline(dev->pdev))) + return -1; + + return (dev)->a_ops.adapter_check_health(dev); +} + /* SCp.phase values */ #define AAC_OWNER_MIDLEVEL 0x101 #define AAC_OWNER_LOWLEVEL 0x102 diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index c8172f16cf33..1f4918355fdb 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -1873,7 +1873,8 @@ int aac_check_health(struct aac_dev * aac) spin_unlock_irqrestore(&aac->fib_lock, flagv); if (BlinkLED < 0) { - printk(KERN_ERR "%s: Host adapter dead %d\n", aac->name, BlinkLED); + printk(KERN_ERR "%s: Host adapter is dead (or got a PCI error) %d\n", + aac->name, BlinkLED); goto out; } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index b29afafc2885..5d5e272fd815 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6293,7 +6293,12 @@ static void ipr_erp_start(struct ipr_ioa_cfg *ioa_cfg, break; case IPR_IOASC_MED_DO_NOT_REALLOC: /* prevent retries */ case IPR_IOASA_IR_DUAL_IOA_DISABLED: - scsi_cmd->result |= (DID_PASSTHROUGH << 16); + /* + * exception: do not set DID_PASSTHROUGH on CHECK CONDITION + * so SCSI mid-layer and upper layers handle it accordingly. + */ + if (scsi_cmd->result != SAM_STAT_CHECK_CONDITION) + scsi_cmd->result |= (DID_PASSTHROUGH << 16); break; case IPR_IOASC_BUS_WAS_RESET: case IPR_IOASC_BUS_WAS_RESET_BY_OTHER: diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c index ed58b9104f58..e10b91cc3c62 100644 --- a/drivers/scsi/qedf/qedf_fip.c +++ b/drivers/scsi/qedf/qedf_fip.c @@ -99,7 +99,8 @@ static void qedf_fcoe_process_vlan_resp(struct qedf_ctx *qedf, qedf_set_vlan_id(qedf, vid); /* Inform waiter that it's ok to call fcoe_ctlr_link up() */ - complete(&qedf->fipvlan_compl); + if (!completion_done(&qedf->fipvlan_compl)) + complete(&qedf->fipvlan_compl); } } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 8e2a160490e6..cceddd995a4b 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2803,6 +2803,7 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) atomic_set(&qedf->num_offloads, 0); qedf->stop_io_on_error = false; pci_set_drvdata(pdev, qedf); + init_completion(&qedf->fipvlan_compl); QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_INFO, "QLogic FastLinQ FCoE Module qedf %s, " diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 3e7011757c82..83d61d2142e9 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1160,8 +1160,13 @@ static inline uint32_t qla2x00_isp_reg_stat(struct qla_hw_data *ha) { struct device_reg_24xx __iomem *reg = &ha->iobase->isp24; + struct device_reg_82xx __iomem *reg82 = &ha->iobase->isp82; - return ((RD_REG_DWORD(®->host_status)) == ISP_REG_DISCONNECT); + if (IS_P3P_TYPE(ha)) + return ((RD_REG_DWORD(®82->host_int)) == ISP_REG_DISCONNECT); + else + return ((RD_REG_DWORD(®->host_status)) == + ISP_REG_DISCONNECT); } /************************************************************************** diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 19125d72f322..15c9fe766071 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -496,7 +496,7 @@ static void scsi_run_queue(struct request_queue *q) scsi_starved_list_run(sdev->host); if (q->mq_ops) - blk_mq_start_stopped_hw_queues(q, false); + blk_mq_run_hw_queues(q, false); else blk_run_queue(q); } @@ -667,7 +667,7 @@ static bool scsi_end_request(struct request *req, int error, !list_empty(&sdev->host->starved_list)) kblockd_schedule_work(&sdev->requeue_work); else - blk_mq_start_stopped_hw_queues(q, true); + blk_mq_run_hw_queues(q, true); } else { unsigned long flags; @@ -1061,10 +1061,10 @@ int scsi_init_io(struct scsi_cmnd *cmd) struct scsi_device *sdev = cmd->device; struct request *rq = cmd->request; bool is_mq = (rq->mq_ctx != NULL); - int error; + int error = BLKPREP_KILL; if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq))) - return -EINVAL; + goto err_exit; error = scsi_init_sgtable(rq, &cmd->sdb); if (error) @@ -1974,7 +1974,7 @@ out: case BLK_MQ_RQ_QUEUE_BUSY: if (atomic_read(&sdev->device_busy) == 0 && !scsi_device_blocked(sdev)) - blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY); + blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY); break; case BLK_MQ_RQ_QUEUE_ERROR: /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fcfeddc79331..35ad5e8a31ab 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2102,6 +2102,22 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 +/* + * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set + * and the reported logical block size is bigger than 512 bytes. Note + * that last_sector is a u64 and therefore logical_to_sectors() is not + * applicable. + */ +static bool sd_addressable_capacity(u64 lba, unsigned int sector_size) +{ + u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9); + + if (sizeof(sector_t) == 4 && last_sector > U32_MAX) + return false; + + return true; +} + static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { @@ -2167,7 +2183,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, return -ENODEV; } - if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) { + if (!sd_addressable_capacity(lba, sector_size)) { sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " "kernel compiled with support for large block " "devices.\n"); @@ -2256,7 +2272,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, return sector_size; } - if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) { + if (!sd_addressable_capacity(lba, sector_size)) { sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " "kernel compiled with support for large block " "devices.\n"); @@ -2956,7 +2972,8 @@ static int sd_revalidate_disk(struct gendisk *disk) q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); } else - rw_max = BLK_DEF_MAX_SECTORS; + rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), + (sector_t)BLK_DEF_MAX_SECTORS); /* Combine with controller limits */ q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 0b29b9329b1c..a8f630213a1a 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -836,6 +836,7 @@ static void get_capabilities(struct scsi_cd *cd) unsigned char *buffer; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; + unsigned int ms_len = 128; int rc, n; static const char *loadmech[] = @@ -862,10 +863,11 @@ static void get_capabilities(struct scsi_cd *cd) scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr); /* ask for mode page 0x2a */ - rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, 128, + rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len, SR_TIMEOUT, 3, &data, NULL); - if (!scsi_status_is_good(rc)) { + if (!scsi_status_is_good(rc) || data.length > ms_len || + data.header_length + data.block_descriptor_length > data.length) { /* failed, drive doesn't have capabilities mode page */ cd->cdi.speed = 1; cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R | diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 7cbad0d45b9c..6ba270e0494d 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -409,6 +409,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) ret = PTR_ERR(vmfile); goto out; } + vmfile->f_mode |= FMODE_LSEEK; asma->file = vmfile; } get_file(asma->file); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index a91802432f2f..e3f9ed3690b7 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -485,8 +485,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *); int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { - iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state); - return 0; + return iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state); } EXPORT_SYMBOL(iscsit_queue_rsp); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index bf40f03755dd..344e8448869c 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1398,11 +1398,10 @@ static u32 lio_sess_get_initiator_sid( static int lio_queue_data_in(struct se_cmd *se_cmd) { struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_conn *conn = cmd->conn; cmd->i_state = ISTATE_SEND_DATAIN; - cmd->conn->conn_transport->iscsit_queue_data_in(cmd->conn, cmd); - - return 0; + return conn->conn_transport->iscsit_queue_data_in(conn, cmd); } static int lio_write_pending(struct se_cmd *se_cmd) @@ -1431,16 +1430,14 @@ static int lio_write_pending_status(struct se_cmd *se_cmd) static int lio_queue_status(struct se_cmd *se_cmd) { struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_conn *conn = cmd->conn; cmd->i_state = ISTATE_SEND_STATUS; if (cmd->se_cmd.scsi_status || cmd->sense_reason) { - iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state); - return 0; + return iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state); } - cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd); - - return 0; + return conn->conn_transport->iscsit_queue_status(conn, cmd); } static void lio_queue_tm_rsp(struct se_cmd *se_cmd) diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index e65bf78ceef3..fce627628200 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -782,22 +782,6 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param) if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH)) SET_PSTATE_REPLY_OPTIONAL(param); /* - * The GlobalSAN iSCSI Initiator for MacOSX does - * not respond to MaxBurstLength, FirstBurstLength, - * DefaultTime2Wait or DefaultTime2Retain parameter keys. - * So, we set them to 'reply optional' here, and assume the - * the defaults from iscsi_parameters.h if the initiator - * is not RFC compliant and the keys are not negotiated. - */ - if (!strcmp(param->name, MAXBURSTLENGTH)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, FIRSTBURSTLENGTH)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, DEFAULTTIME2WAIT)) - SET_PSTATE_REPLY_OPTIONAL(param); - if (!strcmp(param->name, DEFAULTTIME2RETAIN)) - SET_PSTATE_REPLY_OPTIONAL(param); - /* * Required for gPXE iSCSI boot client */ if (!strcmp(param->name, MAXCONNECTIONS)) diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 5041a9c8bdcb..7d3e2fcc26a0 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -567,7 +567,7 @@ static void iscsit_remove_cmd_from_immediate_queue( } } -void iscsit_add_cmd_to_response_queue( +int iscsit_add_cmd_to_response_queue( struct iscsi_cmd *cmd, struct iscsi_conn *conn, u8 state) @@ -578,7 +578,7 @@ void iscsit_add_cmd_to_response_queue( if (!qr) { pr_err("Unable to allocate memory for" " struct iscsi_queue_req\n"); - return; + return -ENOMEM; } INIT_LIST_HEAD(&qr->qr_list); qr->cmd = cmd; @@ -590,6 +590,7 @@ void iscsit_add_cmd_to_response_queue( spin_unlock_bh(&conn->response_queue_lock); wake_up(&conn->queues_wq); + return 0; } struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *conn) @@ -737,21 +738,23 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) { struct se_cmd *se_cmd = NULL; int rc; + bool op_scsi = false; /* * Determine if a struct se_cmd is associated with * this struct iscsi_cmd. */ switch (cmd->iscsi_opcode) { case ISCSI_OP_SCSI_CMD: - se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, true, shutdown); + op_scsi = true; /* * Fallthrough */ case ISCSI_OP_SCSI_TMFUNC: - rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); - if (!rc && shutdown && se_cmd && se_cmd->se_sess) { - __iscsit_free_cmd(cmd, true, shutdown); + se_cmd = &cmd->se_cmd; + __iscsit_free_cmd(cmd, op_scsi, shutdown); + rc = transport_generic_free_cmd(se_cmd, shutdown); + if (!rc && shutdown && se_cmd->se_sess) { + __iscsit_free_cmd(cmd, op_scsi, shutdown); target_put_sess_cmd(se_cmd); } break; diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 8ff08856516a..9e4197af8708 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -31,7 +31,7 @@ extern int iscsit_find_cmd_for_recovery(struct iscsi_session *, struct iscsi_cmd struct iscsi_conn_recovery **, itt_t); extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8); extern struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *); -extern void iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8); +extern int iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8); extern struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *); extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_conn *); extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *); diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index fd7c16a7ca6e..fc4a9c303d55 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -197,8 +197,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd) /* * Set the ASYMMETRIC ACCESS State */ - buf[off++] |= (atomic_read( - &tg_pt_gp->tg_pt_gp_alua_access_state) & 0xff); + buf[off++] |= tg_pt_gp->tg_pt_gp_alua_access_state & 0xff; /* * Set supported ASYMMETRIC ACCESS State bits */ @@ -710,7 +709,7 @@ target_alua_state_check(struct se_cmd *cmd) spin_lock(&lun->lun_tg_pt_gp_lock); tg_pt_gp = lun->lun_tg_pt_gp; - out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state); + out_alua_state = tg_pt_gp->tg_pt_gp_alua_access_state; nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs; // XXX: keeps using tg_pt_gp witout reference after unlock @@ -911,7 +910,7 @@ static int core_alua_write_tpg_metadata( } /* - * Called with tg_pt_gp->tg_pt_gp_md_mutex held + * Called with tg_pt_gp->tg_pt_gp_transition_mutex held */ static int core_alua_update_tpg_primary_metadata( struct t10_alua_tg_pt_gp *tg_pt_gp) @@ -934,7 +933,7 @@ static int core_alua_update_tpg_primary_metadata( "alua_access_state=0x%02x\n" "alua_access_status=0x%02x\n", tg_pt_gp->tg_pt_gp_id, - tg_pt_gp->tg_pt_gp_alua_pending_state, + tg_pt_gp->tg_pt_gp_alua_access_state, tg_pt_gp->tg_pt_gp_alua_access_status); snprintf(path, ALUA_METADATA_PATH_LEN, @@ -1013,93 +1012,41 @@ static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp) spin_unlock(&tg_pt_gp->tg_pt_gp_lock); } -static void core_alua_do_transition_tg_pt_work(struct work_struct *work) -{ - struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work, - struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work); - struct se_device *dev = tg_pt_gp->tg_pt_gp_dev; - bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status == - ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG); - - /* - * Update the ALUA metadata buf that has been allocated in - * core_alua_do_port_transition(), this metadata will be written - * to struct file. - * - * Note that there is the case where we do not want to update the - * metadata when the saved metadata is being parsed in userspace - * when setting the existing port access state and access status. - * - * Also note that the failure to write out the ALUA metadata to - * struct file does NOT affect the actual ALUA transition. - */ - if (tg_pt_gp->tg_pt_gp_write_metadata) { - mutex_lock(&tg_pt_gp->tg_pt_gp_md_mutex); - core_alua_update_tpg_primary_metadata(tg_pt_gp); - mutex_unlock(&tg_pt_gp->tg_pt_gp_md_mutex); - } - /* - * Set the current primary ALUA access state to the requested new state - */ - atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, - tg_pt_gp->tg_pt_gp_alua_pending_state); - - pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu" - " from primary access state %s to %s\n", (explicit) ? "explicit" : - "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item), - tg_pt_gp->tg_pt_gp_id, - core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state), - core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state)); - - core_alua_queue_state_change_ua(tg_pt_gp); - - spin_lock(&dev->t10_alua.tg_pt_gps_lock); - atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt); - spin_unlock(&dev->t10_alua.tg_pt_gps_lock); - - if (tg_pt_gp->tg_pt_gp_transition_complete) - complete(tg_pt_gp->tg_pt_gp_transition_complete); -} - static int core_alua_do_transition_tg_pt( struct t10_alua_tg_pt_gp *tg_pt_gp, int new_state, int explicit) { - struct se_device *dev = tg_pt_gp->tg_pt_gp_dev; - DECLARE_COMPLETION_ONSTACK(wait); + int prev_state; + mutex_lock(&tg_pt_gp->tg_pt_gp_transition_mutex); /* Nothing to be done here */ - if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state) + if (tg_pt_gp->tg_pt_gp_alua_access_state == new_state) { + mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; + } - if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) + if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) { + mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return -EAGAIN; - - /* - * Flush any pending transitions - */ - if (!explicit) - flush_work(&tg_pt_gp->tg_pt_gp_transition_work); + } /* * Save the old primary ALUA access state, and set the current state * to ALUA_ACCESS_STATE_TRANSITION. */ - atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, - ALUA_ACCESS_STATE_TRANSITION); + prev_state = tg_pt_gp->tg_pt_gp_alua_access_state; + tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_TRANSITION; tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ? ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG : ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA; core_alua_queue_state_change_ua(tg_pt_gp); - if (new_state == ALUA_ACCESS_STATE_TRANSITION) + if (new_state == ALUA_ACCESS_STATE_TRANSITION) { + mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; - - tg_pt_gp->tg_pt_gp_alua_previous_state = - atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state); - tg_pt_gp->tg_pt_gp_alua_pending_state = new_state; + } /* * Check for the optional ALUA primary state transition delay @@ -1108,19 +1055,36 @@ static int core_alua_do_transition_tg_pt( msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs); /* - * Take a reference for workqueue item + * Set the current primary ALUA access state to the requested new state */ - spin_lock(&dev->t10_alua.tg_pt_gps_lock); - atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt); - spin_unlock(&dev->t10_alua.tg_pt_gps_lock); + tg_pt_gp->tg_pt_gp_alua_access_state = new_state; - schedule_work(&tg_pt_gp->tg_pt_gp_transition_work); - if (explicit) { - tg_pt_gp->tg_pt_gp_transition_complete = &wait; - wait_for_completion(&wait); - tg_pt_gp->tg_pt_gp_transition_complete = NULL; + /* + * Update the ALUA metadata buf that has been allocated in + * core_alua_do_port_transition(), this metadata will be written + * to struct file. + * + * Note that there is the case where we do not want to update the + * metadata when the saved metadata is being parsed in userspace + * when setting the existing port access state and access status. + * + * Also note that the failure to write out the ALUA metadata to + * struct file does NOT affect the actual ALUA transition. + */ + if (tg_pt_gp->tg_pt_gp_write_metadata) { + core_alua_update_tpg_primary_metadata(tg_pt_gp); } + pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu" + " from primary access state %s to %s\n", (explicit) ? "explicit" : + "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item), + tg_pt_gp->tg_pt_gp_id, + core_alua_dump_state(prev_state), + core_alua_dump_state(new_state)); + + core_alua_queue_state_change_ua(tg_pt_gp); + + mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; } @@ -1685,14 +1649,12 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev, } INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list); INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list); - mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex); + mutex_init(&tg_pt_gp->tg_pt_gp_transition_mutex); spin_lock_init(&tg_pt_gp->tg_pt_gp_lock); atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0); - INIT_WORK(&tg_pt_gp->tg_pt_gp_transition_work, - core_alua_do_transition_tg_pt_work); tg_pt_gp->tg_pt_gp_dev = dev; - atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, - ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED); + tg_pt_gp->tg_pt_gp_alua_access_state = + ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED; /* * Enable both explicit and implicit ALUA support by default */ @@ -1797,8 +1759,6 @@ void core_alua_free_tg_pt_gp( dev->t10_alua.alua_tg_pt_gps_counter--; spin_unlock(&dev->t10_alua.tg_pt_gps_lock); - flush_work(&tg_pt_gp->tg_pt_gp_transition_work); - /* * Allow a struct t10_alua_tg_pt_gp_member * referenced by * core_alua_get_tg_pt_gp_by_name() in @@ -1938,8 +1898,8 @@ ssize_t core_alua_show_tg_pt_gp_info(struct se_lun *lun, char *page) "Primary Access Status: %s\nTG Port Secondary Access" " State: %s\nTG Port Secondary Access Status: %s\n", config_item_name(tg_pt_ci), tg_pt_gp->tg_pt_gp_id, - core_alua_dump_state(atomic_read( - &tg_pt_gp->tg_pt_gp_alua_access_state)), + core_alua_dump_state( + tg_pt_gp->tg_pt_gp_alua_access_state), core_alua_dump_status( tg_pt_gp->tg_pt_gp_alua_access_status), atomic_read(&lun->lun_tg_pt_secondary_offline) ? diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 38b5025e4c7a..70657fd56440 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2392,7 +2392,7 @@ static ssize_t target_tg_pt_gp_alua_access_state_show(struct config_item *item, char *page) { return sprintf(page, "%d\n", - atomic_read(&to_tg_pt_gp(item)->tg_pt_gp_alua_access_state)); + to_tg_pt_gp(item)->tg_pt_gp_alua_access_state); } static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item, diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index d8a16ca6baa5..d1e6cab8e3d3 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -92,6 +92,11 @@ static int target_fabric_mappedlun_link( pr_err("Source se_lun->lun_se_dev does not exist\n"); return -EINVAL; } + if (lun->lun_shutdown) { + pr_err("Unable to create mappedlun symlink because" + " lun->lun_shutdown=true\n"); + return -EINVAL; + } se_tpg = lun->lun_tpg; nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item; diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 6fb191914f45..dfaef4d3b2d2 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -642,6 +642,8 @@ void core_tpg_remove_lun( */ struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev); + lun->lun_shutdown = true; + core_clear_lun_from_tpg(lun, tpg); /* * Wait for any active I/O references to percpu se_lun->lun_ref to @@ -663,6 +665,8 @@ void core_tpg_remove_lun( } if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) hlist_del_rcu(&lun->link); + + lun->lun_shutdown = false; mutex_unlock(&tpg->tpg_lun_mutex); percpu_ref_exit(&lun->lun_ref); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index b1a3cdb29468..a0cd56ee5fe9 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -64,8 +64,9 @@ struct kmem_cache *t10_alua_lba_map_cache; struct kmem_cache *t10_alua_lba_map_mem_cache; static void transport_complete_task_attr(struct se_cmd *cmd); +static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason); static void transport_handle_queue_full(struct se_cmd *cmd, - struct se_device *dev); + struct se_device *dev, int err, bool write_pending); static int transport_put_cmd(struct se_cmd *cmd); static void target_complete_ok_work(struct work_struct *work); @@ -804,7 +805,8 @@ void target_qf_do_work(struct work_struct *work) if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP) transport_write_pending_qf(cmd); - else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK) + else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK || + cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) transport_complete_qf(cmd); } } @@ -1719,7 +1721,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, } trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_status(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; goto check_stop; default: @@ -1730,7 +1732,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, } ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; check_stop: @@ -1739,8 +1741,7 @@ check_stop: return; queue_full: - cmd->t_state = TRANSPORT_COMPLETE_QF_OK; - transport_handle_queue_full(cmd, cmd->se_dev); + transport_handle_queue_full(cmd, cmd->se_dev, ret, false); } EXPORT_SYMBOL(transport_generic_request_failure); @@ -1977,13 +1978,29 @@ static void transport_complete_qf(struct se_cmd *cmd) int ret = 0; transport_complete_task_attr(cmd); + /* + * If a fabric driver ->write_pending() or ->queue_data_in() callback + * has returned neither -ENOMEM or -EAGAIN, assume it's fatal and + * the same callbacks should not be retried. Return CHECK_CONDITION + * if a scsi_status is not already set. + * + * If a fabric driver ->queue_status() has returned non zero, always + * keep retrying no matter what.. + */ + if (cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) { + if (cmd->scsi_status) + goto queue_status; - if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) { - trace_target_cmd_complete(cmd); - ret = cmd->se_tfo->queue_status(cmd); - goto out; + cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE; + cmd->scsi_status = SAM_STAT_CHECK_CONDITION; + cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER; + translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE); + goto queue_status; } + if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) + goto queue_status; + switch (cmd->data_direction) { case DMA_FROM_DEVICE: if (cmd->scsi_status) @@ -2007,19 +2024,33 @@ queue_status: break; } -out: if (ret < 0) { - transport_handle_queue_full(cmd, cmd->se_dev); + transport_handle_queue_full(cmd, cmd->se_dev, ret, false); return; } transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); } -static void transport_handle_queue_full( - struct se_cmd *cmd, - struct se_device *dev) +static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev, + int err, bool write_pending) { + /* + * -EAGAIN or -ENOMEM signals retry of ->write_pending() and/or + * ->queue_data_in() callbacks from new process context. + * + * Otherwise for other errors, transport_complete_qf() will send + * CHECK_CONDITION via ->queue_status() instead of attempting to + * retry associated fabric driver data-transfer callbacks. + */ + if (err == -EAGAIN || err == -ENOMEM) { + cmd->t_state = (write_pending) ? TRANSPORT_COMPLETE_QF_WP : + TRANSPORT_COMPLETE_QF_OK; + } else { + pr_warn_ratelimited("Got unknown fabric queue status: %d\n", err); + cmd->t_state = TRANSPORT_COMPLETE_QF_ERR; + } + spin_lock_irq(&dev->qf_cmd_lock); list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list); atomic_inc_mb(&dev->dev_qf_count); @@ -2083,7 +2114,7 @@ static void target_complete_ok_work(struct work_struct *work) WARN_ON(!cmd->scsi_status); ret = transport_send_check_condition_and_sense( cmd, 0, 1); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; transport_lun_remove_cmd(cmd); @@ -2109,7 +2140,7 @@ static void target_complete_ok_work(struct work_struct *work) } else if (rc) { ret = transport_send_check_condition_and_sense(cmd, rc, 0); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; transport_lun_remove_cmd(cmd); @@ -2134,7 +2165,7 @@ queue_rsp: if (target_read_prot_action(cmd)) { ret = transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; transport_lun_remove_cmd(cmd); @@ -2144,7 +2175,7 @@ queue_rsp: trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_data_in(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; break; case DMA_TO_DEVICE: @@ -2157,7 +2188,7 @@ queue_rsp: atomic_long_add(cmd->data_length, &cmd->se_lun->lun_stats.tx_data_octets); ret = cmd->se_tfo->queue_data_in(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; break; } @@ -2166,7 +2197,7 @@ queue_rsp: queue_status: trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_status(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; break; default: @@ -2180,8 +2211,8 @@ queue_status: queue_full: pr_debug("Handling complete_ok QUEUE_FULL: se_cmd: %p," " data_direction: %d\n", cmd, cmd->data_direction); - cmd->t_state = TRANSPORT_COMPLETE_QF_OK; - transport_handle_queue_full(cmd, cmd->se_dev); + + transport_handle_queue_full(cmd, cmd->se_dev, ret, false); } void target_free_sgl(struct scatterlist *sgl, int nents) @@ -2449,18 +2480,14 @@ transport_generic_new_cmd(struct se_cmd *cmd) spin_unlock_irqrestore(&cmd->t_state_lock, flags); ret = cmd->se_tfo->write_pending(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) + if (ret) goto queue_full; - /* fabric drivers should only return -EAGAIN or -ENOMEM as error */ - WARN_ON(ret); - - return (!ret) ? 0 : TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + return 0; queue_full: pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd); - cmd->t_state = TRANSPORT_COMPLETE_QF_WP; - transport_handle_queue_full(cmd, cmd->se_dev); + transport_handle_queue_full(cmd, cmd->se_dev, ret, true); return 0; } EXPORT_SYMBOL(transport_generic_new_cmd); @@ -2470,10 +2497,10 @@ static void transport_write_pending_qf(struct se_cmd *cmd) int ret; ret = cmd->se_tfo->write_pending(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) { + if (ret) { pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd); - transport_handle_queue_full(cmd, cmd->se_dev); + transport_handle_queue_full(cmd, cmd->se_dev, ret, true); } } @@ -3011,6 +3038,8 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status) __releases(&cmd->t_state_lock) __acquires(&cmd->t_state_lock) { + int ret; + assert_spin_locked(&cmd->t_state_lock); WARN_ON_ONCE(!irqs_disabled()); @@ -3034,7 +3063,9 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status) trace_target_cmd_complete(cmd); spin_unlock_irq(&cmd->t_state_lock); - cmd->se_tfo->queue_status(cmd); + ret = cmd->se_tfo->queue_status(cmd); + if (ret) + transport_handle_queue_full(cmd, cmd->se_dev, ret, false); spin_lock_irq(&cmd->t_state_lock); return 1; @@ -3055,6 +3086,7 @@ EXPORT_SYMBOL(transport_check_aborted_status); void transport_send_task_abort(struct se_cmd *cmd) { unsigned long flags; + int ret; spin_lock_irqsave(&cmd->t_state_lock, flags); if (cmd->se_cmd_flags & (SCF_SENT_CHECK_CONDITION)) { @@ -3090,7 +3122,9 @@ send_abort: cmd->t_task_cdb[0], cmd->tag); trace_target_cmd_complete(cmd); - cmd->se_tfo->queue_status(cmd); + ret = cmd->se_tfo->queue_status(cmd); + if (ret) + transport_handle_queue_full(cmd, cmd->se_dev, ret, false); } static void target_tmr_work(struct work_struct *work) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index c6874c38a10b..f615c3bbb73e 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -311,24 +311,50 @@ static void free_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd) DATA_BLOCK_BITS); } -static void gather_data_area(struct tcmu_dev *udev, unsigned long *cmd_bitmap, - struct scatterlist *data_sg, unsigned int data_nents) +static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, + bool bidi) { + struct se_cmd *se_cmd = cmd->se_cmd; int i, block; int block_remaining = 0; void *from, *to; size_t copy_bytes, from_offset; - struct scatterlist *sg; + struct scatterlist *sg, *data_sg; + unsigned int data_nents; + DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS); + + bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS); + + if (!bidi) { + data_sg = se_cmd->t_data_sg; + data_nents = se_cmd->t_data_nents; + } else { + uint32_t count; + + /* + * For bidi case, the first count blocks are for Data-Out + * buffer blocks, and before gathering the Data-In buffer + * the Data-Out buffer blocks should be discarded. + */ + count = DIV_ROUND_UP(se_cmd->data_length, DATA_BLOCK_SIZE); + while (count--) { + block = find_first_bit(bitmap, DATA_BLOCK_BITS); + clear_bit(block, bitmap); + } + + data_sg = se_cmd->t_bidi_data_sg; + data_nents = se_cmd->t_bidi_data_nents; + } for_each_sg(data_sg, sg, data_nents, i) { int sg_remaining = sg->length; to = kmap_atomic(sg_page(sg)) + sg->offset; while (sg_remaining > 0) { if (block_remaining == 0) { - block = find_first_bit(cmd_bitmap, + block = find_first_bit(bitmap, DATA_BLOCK_BITS); block_remaining = DATA_BLOCK_SIZE; - clear_bit(block, cmd_bitmap); + clear_bit(block, bitmap); } copy_bytes = min_t(size_t, sg_remaining, block_remaining); @@ -394,6 +420,27 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, size_t cmd_size, size_t d return true; } +static inline size_t tcmu_cmd_get_data_length(struct tcmu_cmd *tcmu_cmd) +{ + struct se_cmd *se_cmd = tcmu_cmd->se_cmd; + size_t data_length = round_up(se_cmd->data_length, DATA_BLOCK_SIZE); + + if (se_cmd->se_cmd_flags & SCF_BIDI) { + BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents)); + data_length += round_up(se_cmd->t_bidi_data_sg->length, + DATA_BLOCK_SIZE); + } + + return data_length; +} + +static inline uint32_t tcmu_cmd_get_block_cnt(struct tcmu_cmd *tcmu_cmd) +{ + size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd); + + return data_length / DATA_BLOCK_SIZE; +} + static sense_reason_t tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) { @@ -407,7 +454,7 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) uint32_t cmd_head; uint64_t cdb_off; bool copy_to_data_area; - size_t data_length; + size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd); DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS); if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags)) @@ -421,8 +468,7 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) * expensive to tell how many regions are freed in the bitmap */ base_command_size = max(offsetof(struct tcmu_cmd_entry, - req.iov[se_cmd->t_bidi_data_nents + - se_cmd->t_data_nents]), + req.iov[tcmu_cmd_get_block_cnt(tcmu_cmd)]), sizeof(struct tcmu_cmd_entry)); command_size = base_command_size + round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE); @@ -433,11 +479,6 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) mb = udev->mb_addr; cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */ - data_length = se_cmd->data_length; - if (se_cmd->se_cmd_flags & SCF_BIDI) { - BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents)); - data_length += se_cmd->t_bidi_data_sg->length; - } if ((command_size > (udev->cmdr_size / 2)) || data_length > udev->data_size) { pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu " @@ -511,11 +552,14 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) entry->req.iov_dif_cnt = 0; /* Handle BIDI commands */ - iov_cnt = 0; - alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg, - se_cmd->t_bidi_data_nents, &iov, &iov_cnt, false); - entry->req.iov_bidi_cnt = iov_cnt; - + if (se_cmd->se_cmd_flags & SCF_BIDI) { + iov_cnt = 0; + iov++; + alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg, + se_cmd->t_bidi_data_nents, &iov, &iov_cnt, + false); + entry->req.iov_bidi_cnt = iov_cnt; + } /* cmd's data_bitmap is what changed in process */ bitmap_xor(tcmu_cmd->data_bitmap, old_bitmap, udev->data_bitmap, DATA_BLOCK_BITS); @@ -592,19 +636,11 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * se_cmd->scsi_sense_length); free_data_area(udev, cmd); } else if (se_cmd->se_cmd_flags & SCF_BIDI) { - DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS); - /* Get Data-In buffer before clean up */ - bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS); - gather_data_area(udev, bitmap, - se_cmd->t_bidi_data_sg, se_cmd->t_bidi_data_nents); + gather_data_area(udev, cmd, true); free_data_area(udev, cmd); } else if (se_cmd->data_direction == DMA_FROM_DEVICE) { - DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS); - - bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS); - gather_data_area(udev, bitmap, - se_cmd->t_data_sg, se_cmd->t_data_nents); + gather_data_area(udev, cmd, false); free_data_area(udev, cmd); } else if (se_cmd->data_direction == DMA_TO_DEVICE) { free_data_area(udev, cmd); @@ -1196,11 +1232,6 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag if (ret < 0) return ret; - if (!val) { - pr_err("Illegal value for cmd_time_out\n"); - return -EINVAL; - } - udev->cmd_time_out = val * MSEC_PER_SEC; return count; } diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index b0500a0a87b8..e4603b09863a 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -492,6 +492,41 @@ static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld) } /** + * tty_ldisc_restore - helper for tty ldisc change + * @tty: tty to recover + * @old: previous ldisc + * + * Restore the previous line discipline or N_TTY when a line discipline + * change fails due to an open error + */ + +static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old) +{ + struct tty_ldisc *new_ldisc; + int r; + + /* There is an outstanding reference here so this is safe */ + old = tty_ldisc_get(tty, old->ops->num); + WARN_ON(IS_ERR(old)); + tty->ldisc = old; + tty_set_termios_ldisc(tty, old->ops->num); + if (tty_ldisc_open(tty, old) < 0) { + tty_ldisc_put(old); + /* This driver is always present */ + new_ldisc = tty_ldisc_get(tty, N_TTY); + if (IS_ERR(new_ldisc)) + panic("n_tty: get"); + tty->ldisc = new_ldisc; + tty_set_termios_ldisc(tty, N_TTY); + r = tty_ldisc_open(tty, new_ldisc); + if (r < 0) + panic("Couldn't open N_TTY ldisc for " + "%s --- error %d.", + tty_name(tty), r); + } +} + +/** * tty_set_ldisc - set line discipline * @tty: the terminal to set * @ldisc: the line discipline @@ -504,7 +539,12 @@ static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld) int tty_set_ldisc(struct tty_struct *tty, int disc) { - int retval, old_disc; + int retval; + struct tty_ldisc *old_ldisc, *new_ldisc; + + new_ldisc = tty_ldisc_get(tty, disc); + if (IS_ERR(new_ldisc)) + return PTR_ERR(new_ldisc); tty_lock(tty); retval = tty_ldisc_lock(tty, 5 * HZ); @@ -517,8 +557,7 @@ int tty_set_ldisc(struct tty_struct *tty, int disc) } /* Check the no-op case */ - old_disc = tty->ldisc->ops->num; - if (old_disc == disc) + if (tty->ldisc->ops->num == disc) goto out; if (test_bit(TTY_HUPPED, &tty->flags)) { @@ -527,25 +566,34 @@ int tty_set_ldisc(struct tty_struct *tty, int disc) goto out; } - retval = tty_ldisc_reinit(tty, disc); + old_ldisc = tty->ldisc; + + /* Shutdown the old discipline. */ + tty_ldisc_close(tty, old_ldisc); + + /* Now set up the new line discipline. */ + tty->ldisc = new_ldisc; + tty_set_termios_ldisc(tty, disc); + + retval = tty_ldisc_open(tty, new_ldisc); if (retval < 0) { /* Back to the old one or N_TTY if we can't */ - if (tty_ldisc_reinit(tty, old_disc) < 0) { - pr_err("tty: TIOCSETD failed, reinitializing N_TTY\n"); - if (tty_ldisc_reinit(tty, N_TTY) < 0) { - /* At this point we have tty->ldisc == NULL. */ - pr_err("tty: reinitializing N_TTY failed\n"); - } - } + tty_ldisc_put(new_ldisc); + tty_ldisc_restore(tty, old_ldisc); } - if (tty->ldisc && tty->ldisc->ops->num != old_disc && - tty->ops->set_ldisc) { + if (tty->ldisc->ops->num != old_ldisc->ops->num && tty->ops->set_ldisc) { down_read(&tty->termios_rwsem); tty->ops->set_ldisc(tty); up_read(&tty->termios_rwsem); } + /* At this point we hold a reference to the new ldisc and a + reference to the old ldisc, or we hold two references to + the old ldisc (if it was restored as part of error cleanup + above). In either case, releasing a single reference from + the old ldisc is correct. */ + new_ldisc = old_ldisc; out: tty_ldisc_unlock(tty); @@ -553,6 +601,7 @@ out: already running */ tty_buffer_restart_work(tty->port); err: + tty_ldisc_put(new_ldisc); /* drop the extra reference */ tty_unlock(tty); return retval; } @@ -613,8 +662,10 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc) int retval; ld = tty_ldisc_get(tty, disc); - if (IS_ERR(ld)) + if (IS_ERR(ld)) { + BUG_ON(disc == N_TTY); return PTR_ERR(ld); + } if (tty->ldisc) { tty_ldisc_close(tty, tty->ldisc); @@ -626,8 +677,10 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc) tty_set_termios_ldisc(tty, disc); retval = tty_ldisc_open(tty, tty->ldisc); if (retval) { - tty_ldisc_put(tty->ldisc); - tty->ldisc = NULL; + if (!WARN_ON(disc == N_TTY)) { + tty_ldisc_put(tty->ldisc); + tty->ldisc = NULL; + } } return retval; } diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index d2351139342f..a82e2bd5ea34 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -373,7 +373,7 @@ static void bot_cleanup_old_alt(struct f_uas *fu) usb_ep_free_request(fu->ep_in, fu->bot_req_in); usb_ep_free_request(fu->ep_out, fu->bot_req_out); usb_ep_free_request(fu->ep_out, fu->cmd.req); - usb_ep_free_request(fu->ep_out, fu->bot_status.req); + usb_ep_free_request(fu->ep_in, fu->bot_status.req); kfree(fu->cmd.buf); diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index d7efcb632f7d..002f1ce22bd0 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -297,14 +297,15 @@ static int pwm_backlight_probe(struct platform_device *pdev) } /* - * If the GPIO is configured as input, change the direction to output - * and set the GPIO as active. + * If the GPIO is not known to be already configured as output, that + * is, if gpiod_get_direction returns either GPIOF_DIR_IN or -EINVAL, + * change the direction to output and set the GPIO as active. * Do not force the GPIO to active when it was already output as it * could cause backlight flickering or we would enable the backlight too * early. Leave the decision of the initial backlight state for later. */ if (pb->enable_gpio && - gpiod_get_direction(pb->enable_gpio) == GPIOF_DIR_IN) + gpiod_get_direction(pb->enable_gpio) != GPIOF_DIR_OUT) gpiod_direction_output(pb->enable_gpio, 1); pb->power_supply = devm_regulator_get(&pdev->dev, "power"); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 8c4dc1e1f94f..b827a8113e26 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/errno.h> #include <linux/fb.h> +#include <linux/pci.h> #include <linux/platform_device.h> #include <linux/screen_info.h> #include <video/vga.h> @@ -143,6 +144,8 @@ static struct attribute *efifb_attrs[] = { }; ATTRIBUTE_GROUPS(efifb); +static bool pci_dev_disabled; /* FB base matches BAR of a disabled device */ + static int efifb_probe(struct platform_device *dev) { struct fb_info *info; @@ -152,7 +155,7 @@ static int efifb_probe(struct platform_device *dev) unsigned int size_total; char *option = NULL; - if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled) return -ENODEV; if (fb_get_options("efifb", &option)) @@ -360,3 +363,64 @@ static struct platform_driver efifb_driver = { }; builtin_platform_driver(efifb_driver); + +#if defined(CONFIG_PCI) && !defined(CONFIG_X86) + +static bool pci_bar_found; /* did we find a BAR matching the efifb base? */ + +static void claim_efifb_bar(struct pci_dev *dev, int idx) +{ + u16 word; + + pci_bar_found = true; + + pci_read_config_word(dev, PCI_COMMAND, &word); + if (!(word & PCI_COMMAND_MEMORY)) { + pci_dev_disabled = true; + dev_err(&dev->dev, + "BAR %d: assigned to efifb but device is disabled!\n", + idx); + return; + } + + if (pci_claim_resource(dev, idx)) { + pci_dev_disabled = true; + dev_err(&dev->dev, + "BAR %d: failed to claim resource for efifb!\n", idx); + return; + } + + dev_info(&dev->dev, "BAR %d: assigned to efifb\n", idx); +} + +static void efifb_fixup_resources(struct pci_dev *dev) +{ + u64 base = screen_info.lfb_base; + u64 size = screen_info.lfb_size; + int i; + + if (pci_bar_found || screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) + return; + + if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) + base |= (u64)screen_info.ext_lfb_base << 32; + + if (!base) + return; + + for (i = 0; i < PCI_STD_RESOURCE_END; i++) { + struct resource *res = &dev->resource[i]; + + if (!(res->flags & IORESOURCE_MEM)) + continue; + + if (res->start <= base && res->end >= base + size - 1) { + claim_efifb_bar(dev, i); + break; + } + } +} +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY, + 16, efifb_fixup_resources); + +#endif diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index 1abba07b84b3..f4cbfb3b8a09 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -1608,19 +1608,6 @@ static int omapfb_find_ctrl(struct omapfb_device *fbdev) return 0; } -static void check_required_callbacks(struct omapfb_device *fbdev) -{ -#define _C(x) (fbdev->ctrl->x != NULL) -#define _P(x) (fbdev->panel->x != NULL) - BUG_ON(fbdev->ctrl == NULL || fbdev->panel == NULL); - BUG_ON(!(_C(init) && _C(cleanup) && _C(get_caps) && - _C(set_update_mode) && _C(setup_plane) && _C(enable_plane) && - _P(init) && _P(cleanup) && _P(enable) && _P(disable) && - _P(get_caps))); -#undef _P -#undef _C -} - /* * Called by LDM binding to probe and attach a new device. * Initialization sequence: @@ -1705,8 +1692,6 @@ static int omapfb_do_probe(struct platform_device *pdev, omapfb_ops.fb_mmap = omapfb_mmap; init_state++; - check_required_callbacks(fbdev); - r = planes_init(fbdev); if (r) goto cleanup; diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index bd017b57c47f..f599520374dd 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -578,10 +578,14 @@ static int ssd1307fb_probe(struct i2c_client *client, par->vbat_reg = devm_regulator_get_optional(&client->dev, "vbat"); if (IS_ERR(par->vbat_reg)) { - dev_err(&client->dev, "failed to get VBAT regulator: %ld\n", - PTR_ERR(par->vbat_reg)); ret = PTR_ERR(par->vbat_reg); - goto fb_alloc_error; + if (ret == -ENODEV) { + par->vbat_reg = NULL; + } else { + dev_err(&client->dev, "failed to get VBAT regulator: %d\n", + ret); + goto fb_alloc_error; + } } if (of_property_read_u32(node, "solomon,width", &par->width)) @@ -668,10 +672,13 @@ static int ssd1307fb_probe(struct i2c_client *client, udelay(4); } - ret = regulator_enable(par->vbat_reg); - if (ret) { - dev_err(&client->dev, "failed to enable VBAT: %d\n", ret); - goto reset_oled_error; + if (par->vbat_reg) { + ret = regulator_enable(par->vbat_reg); + if (ret) { + dev_err(&client->dev, "failed to enable VBAT: %d\n", + ret); + goto reset_oled_error; + } } ret = ssd1307fb_init(par); @@ -710,7 +717,8 @@ panel_init_error: pwm_put(par->pwm); }; regulator_enable_error: - regulator_disable(par->vbat_reg); + if (par->vbat_reg) + regulator_disable(par->vbat_reg); reset_oled_error: fb_deferred_io_cleanup(info); fb_alloc_error: diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index d0115a7af0a9..3ee309c50b2d 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -643,7 +643,6 @@ static void xenfb_backend_changed(struct xenbus_device *dev, break; case XenbusStateInitWait: -InitWait: xenbus_switch_state(dev, XenbusStateConnected); break; @@ -654,7 +653,8 @@ InitWait: * get Connected twice here. */ if (dev->state != XenbusStateConnected) - goto InitWait; /* no InitWait seen yet, fudge it */ + /* no InitWait seen yet, fudge it */ + xenbus_switch_state(dev, XenbusStateConnected); if (xenbus_read_unsigned(info->xbdev->otherend, "request-update", 0)) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 400d70b69379..48230a5e12f2 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -232,6 +232,12 @@ static int virtio_dev_probe(struct device *_d) if (device_features & (1ULL << i)) __virtio_set_bit(dev, i); + if (drv->validate) { + err = drv->validate(dev); + if (err) + goto err; + } + err = virtio_finalize_features(dev); if (err) goto err; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 590534910dc6..698d5d06fa03 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -33,8 +33,10 @@ void vp_synchronize_vectors(struct virtio_device *vdev) struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; - synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0)); - for (i = 1; i < vp_dev->msix_vectors; i++) + if (vp_dev->intx_enabled) + synchronize_irq(vp_dev->pci_dev->irq); + + for (i = 0; i < vp_dev->msix_vectors; ++i) synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } @@ -60,13 +62,16 @@ static irqreturn_t vp_config_changed(int irq, void *opaque) static irqreturn_t vp_vring_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; + struct virtio_pci_vq_info *info; irqreturn_t ret = IRQ_NONE; - struct virtqueue *vq; + unsigned long flags; - list_for_each_entry(vq, &vp_dev->vdev.vqs, list) { - if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED) + spin_lock_irqsave(&vp_dev->lock, flags); + list_for_each_entry(info, &vp_dev->virtqueues, node) { + if (vring_interrupt(irq, info->vq) == IRQ_HANDLED) ret = IRQ_HANDLED; } + spin_unlock_irqrestore(&vp_dev->lock, flags); return ret; } @@ -97,186 +102,244 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) return vp_vring_interrupt(irq, opaque); } -static void vp_remove_vqs(struct virtio_device *vdev) +static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, + bool per_vq_vectors, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtqueue *vq, *n; + const char *name = dev_name(&vp_dev->vdev.dev); + unsigned i, v; + int err = -ENOMEM; - list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - if (vp_dev->msix_vector_map) { - int v = vp_dev->msix_vector_map[vq->index]; + vp_dev->msix_vectors = nvectors; - if (v != VIRTIO_MSI_NO_VECTOR) - free_irq(pci_irq_vector(vp_dev->pci_dev, v), - vq); - } - vp_dev->del_vq(vq); + vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names, + GFP_KERNEL); + if (!vp_dev->msix_names) + goto error; + vp_dev->msix_affinity_masks + = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks, + GFP_KERNEL); + if (!vp_dev->msix_affinity_masks) + goto error; + for (i = 0; i < nvectors; ++i) + if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], + GFP_KERNEL)) + goto error; + + err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, + nvectors, PCI_IRQ_MSIX | + (desc ? PCI_IRQ_AFFINITY : 0), + desc); + if (err < 0) + goto error; + vp_dev->msix_enabled = 1; + + /* Set the vector used for configuration */ + v = vp_dev->msix_used_vectors; + snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, + "%s-config", name); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), + vp_config_changed, 0, vp_dev->msix_names[v], + vp_dev); + if (err) + goto error; + ++vp_dev->msix_used_vectors; + + v = vp_dev->config_vector(vp_dev, v); + /* Verify we had enough resources to assign the vector */ + if (v == VIRTIO_MSI_NO_VECTOR) { + err = -EBUSY; + goto error; } + + if (!per_vq_vectors) { + /* Shared vector for all VQs */ + v = vp_dev->msix_used_vectors; + snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, + "%s-virtqueues", name); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), + vp_vring_interrupt, 0, vp_dev->msix_names[v], + vp_dev); + if (err) + goto error; + ++vp_dev->msix_used_vectors; + } + return 0; +error: + return err; +} + +static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index, + void (*callback)(struct virtqueue *vq), + const char *name, + u16 msix_vec) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); + struct virtqueue *vq; + unsigned long flags; + + /* fill out our structure that represents an active queue */ + if (!info) + return ERR_PTR(-ENOMEM); + + vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, + msix_vec); + if (IS_ERR(vq)) + goto out_info; + + info->vq = vq; + if (callback) { + spin_lock_irqsave(&vp_dev->lock, flags); + list_add(&info->node, &vp_dev->virtqueues); + spin_unlock_irqrestore(&vp_dev->lock, flags); + } else { + INIT_LIST_HEAD(&info->node); + } + + vp_dev->vqs[index] = info; + return vq; + +out_info: + kfree(info); + return vq; +} + +static void vp_del_vq(struct virtqueue *vq) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; + unsigned long flags; + + spin_lock_irqsave(&vp_dev->lock, flags); + list_del(&info->node); + spin_unlock_irqrestore(&vp_dev->lock, flags); + + vp_dev->del_vq(info); + kfree(info); } /* the config->del_vqs() implementation */ void vp_del_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtqueue *vq, *n; int i; - if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs))) - return; + list_for_each_entry_safe(vq, n, &vdev->vqs, list) { + if (vp_dev->per_vq_vectors) { + int v = vp_dev->vqs[vq->index]->msix_vector; - vp_remove_vqs(vdev); + if (v != VIRTIO_MSI_NO_VECTOR) { + int irq = pci_irq_vector(vp_dev->pci_dev, v); + + irq_set_affinity_hint(irq, NULL); + free_irq(irq, vq); + } + } + vp_del_vq(vq); + } + vp_dev->per_vq_vectors = false; + + if (vp_dev->intx_enabled) { + free_irq(vp_dev->pci_dev->irq, vp_dev); + vp_dev->intx_enabled = 0; + } - if (vp_dev->pci_dev->msix_enabled) { - for (i = 0; i < vp_dev->msix_vectors; i++) + for (i = 0; i < vp_dev->msix_used_vectors; ++i) + free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev); + + for (i = 0; i < vp_dev->msix_vectors; i++) + if (vp_dev->msix_affinity_masks[i]) free_cpumask_var(vp_dev->msix_affinity_masks[i]); + if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); - kfree(vp_dev->msix_affinity_masks); - kfree(vp_dev->msix_names); - kfree(vp_dev->msix_vector_map); + pci_free_irq_vectors(vp_dev->pci_dev); + vp_dev->msix_enabled = 0; } - free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); - pci_free_irq_vectors(vp_dev->pci_dev); + vp_dev->msix_vectors = 0; + vp_dev->msix_used_vectors = 0; + kfree(vp_dev->msix_names); + vp_dev->msix_names = NULL; + kfree(vp_dev->msix_affinity_masks); + vp_dev->msix_affinity_masks = NULL; + kfree(vp_dev->vqs); + vp_dev->vqs = NULL; } static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], struct irq_affinity *desc) + const char * const names[], bool per_vq_vectors, + struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - const char *name = dev_name(&vp_dev->vdev.dev); - int i, j, err = -ENOMEM, allocated_vectors, nvectors; - unsigned flags = PCI_IRQ_MSIX; - bool shared = false; u16 msix_vec; + int i, err, nvectors, allocated_vectors; - if (desc) { - flags |= PCI_IRQ_AFFINITY; - desc->pre_vectors++; /* virtio config vector */ - } - - nvectors = 1; - for (i = 0; i < nvqs; i++) - if (callbacks[i]) - nvectors++; - - /* Try one vector per queue first. */ - err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, - nvectors, flags, desc); - if (err < 0) { - /* Fallback to one vector for config, one shared for queues. */ - shared = true; - err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2, - PCI_IRQ_MSIX); - if (err < 0) - return err; - } - if (err < 0) - return err; - - vp_dev->msix_vectors = nvectors; - vp_dev->msix_names = kmalloc_array(nvectors, - sizeof(*vp_dev->msix_names), GFP_KERNEL); - if (!vp_dev->msix_names) - goto out_free_irq_vectors; - - vp_dev->msix_affinity_masks = kcalloc(nvectors, - sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL); - if (!vp_dev->msix_affinity_masks) - goto out_free_msix_names; + vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); + if (!vp_dev->vqs) + return -ENOMEM; - for (i = 0; i < nvectors; ++i) { - if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], - GFP_KERNEL)) - goto out_free_msix_affinity_masks; + if (per_vq_vectors) { + /* Best option: one for change interrupt, one per vq. */ + nvectors = 1; + for (i = 0; i < nvqs; ++i) + if (callbacks[i]) + ++nvectors; + } else { + /* Second best: one for change, shared for all vqs. */ + nvectors = 2; } - /* Set the vector used for configuration */ - snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names), - "%s-config", name); - err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed, - 0, vp_dev->msix_names[0], vp_dev); + err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, + per_vq_vectors ? desc : NULL); if (err) - goto out_free_msix_affinity_masks; + goto error_find; - /* Verify we had enough resources to assign the vector */ - if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) { - err = -EBUSY; - goto out_free_config_irq; - } - - vp_dev->msix_vector_map = kmalloc_array(nvqs, - sizeof(*vp_dev->msix_vector_map), GFP_KERNEL); - if (!vp_dev->msix_vector_map) - goto out_disable_config_irq; - - allocated_vectors = j = 1; /* vector 0 is the config interrupt */ + vp_dev->per_vq_vectors = per_vq_vectors; + allocated_vectors = vp_dev->msix_used_vectors; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } - if (callbacks[i]) - msix_vec = allocated_vectors; - else + if (!callbacks[i]) msix_vec = VIRTIO_MSI_NO_VECTOR; - - vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], - msix_vec); + else if (vp_dev->per_vq_vectors) + msix_vec = allocated_vectors++; + else + msix_vec = VP_MSIX_VQ_VECTOR; + vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], + msix_vec); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); - goto out_remove_vqs; + goto error_find; } - if (msix_vec == VIRTIO_MSI_NO_VECTOR) { - vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; + if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR) continue; - } - snprintf(vp_dev->msix_names[j], - sizeof(*vp_dev->msix_names), "%s-%s", + /* allocate per-vq irq if available and necessary */ + snprintf(vp_dev->msix_names[msix_vec], + sizeof *vp_dev->msix_names, + "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]); err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), - vring_interrupt, IRQF_SHARED, - vp_dev->msix_names[j], vqs[i]); - if (err) { - /* don't free this irq on error */ - vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; - goto out_remove_vqs; - } - vp_dev->msix_vector_map[i] = msix_vec; - j++; - - /* - * Use a different vector for each queue if they are available, - * else share the same vector for all VQs. - */ - if (!shared) - allocated_vectors++; + vring_interrupt, 0, + vp_dev->msix_names[msix_vec], + vqs[i]); + if (err) + goto error_find; } - return 0; -out_remove_vqs: - vp_remove_vqs(vdev); - kfree(vp_dev->msix_vector_map); -out_disable_config_irq: - vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); -out_free_config_irq: - free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); -out_free_msix_affinity_masks: - for (i = 0; i < nvectors; i++) { - if (vp_dev->msix_affinity_masks[i]) - free_cpumask_var(vp_dev->msix_affinity_masks[i]); - } - kfree(vp_dev->msix_affinity_masks); -out_free_msix_names: - kfree(vp_dev->msix_names); -out_free_irq_vectors: - pci_free_irq_vectors(vp_dev->pci_dev); +error_find: + vp_del_vqs(vdev); return err; } @@ -287,29 +350,33 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs, struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i, err; + vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); + if (!vp_dev->vqs) + return -ENOMEM; + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) - return err; + goto out_del_vqs; + vp_dev->intx_enabled = 1; + vp_dev->per_vq_vectors = false; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } - vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], - VIRTIO_MSI_NO_VECTOR); + vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], + VIRTIO_MSI_NO_VECTOR); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); - goto out_remove_vqs; + goto out_del_vqs; } } return 0; - -out_remove_vqs: - vp_remove_vqs(vdev); - free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); +out_del_vqs: + vp_del_vqs(vdev); return err; } @@ -320,9 +387,15 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, { int err; - err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc); + /* Try MSI-X with one vector per queue. */ + err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc); if (!err) return 0; + /* Fallback: MSI-X with one vector for config, one shared for queues. */ + err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc); + if (!err) + return 0; + /* Finally fall back to regular interrupts. */ return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names); } @@ -342,15 +415,16 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; + struct cpumask *mask; + unsigned int irq; if (!vq->callback) return -EINVAL; - if (vp_dev->pci_dev->msix_enabled) { - int vec = vp_dev->msix_vector_map[vq->index]; - struct cpumask *mask = vp_dev->msix_affinity_masks[vec]; - unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec); - + if (vp_dev->msix_enabled) { + mask = vp_dev->msix_affinity_masks[info->msix_vector]; + irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector); if (cpu == -1) irq_set_affinity_hint(irq, NULL); else { @@ -365,12 +439,13 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - unsigned int *map = vp_dev->msix_vector_map; - if (!map || map[index] == VIRTIO_MSI_NO_VECTOR) + if (!vp_dev->per_vq_vectors || + vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR) return NULL; - return pci_irq_get_affinity(vp_dev->pci_dev, map[index]); + return pci_irq_get_affinity(vp_dev->pci_dev, + vp_dev->vqs[index]->msix_vector); } #ifdef CONFIG_PM_SLEEP @@ -441,6 +516,8 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; + INIT_LIST_HEAD(&vp_dev->virtqueues); + spin_lock_init(&vp_dev->lock); /* enable the device */ rc = pci_enable_device(pci_dev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index ac8c9d788964..e96334aec1e0 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -31,6 +31,17 @@ #include <linux/highmem.h> #include <linux/spinlock.h> +struct virtio_pci_vq_info { + /* the actual virtqueue */ + struct virtqueue *vq; + + /* the list node for the virtqueues list */ + struct list_head node; + + /* MSI-X vector (or none) */ + unsigned msix_vector; +}; + /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; @@ -64,25 +75,47 @@ struct virtio_pci_device { /* the IO mapping for the PCI config space */ void __iomem *ioaddr; + /* a list of queues so we can dispatch IRQs */ + spinlock_t lock; + struct list_head virtqueues; + + /* array of all queues for house-keeping */ + struct virtio_pci_vq_info **vqs; + + /* MSI-X support */ + int msix_enabled; + int intx_enabled; cpumask_var_t *msix_affinity_masks; /* Name strings for interrupts. This size should be enough, * and I'm too lazy to allocate each name separately. */ char (*msix_names)[256]; - /* Total Number of MSI-X vectors (including per-VQ ones). */ - int msix_vectors; - /* Map of per-VQ MSI-X vectors, may be NULL */ - unsigned *msix_vector_map; + /* Number of available vectors */ + unsigned msix_vectors; + /* Vectors allocated, excluding per-vq vectors if any */ + unsigned msix_used_vectors; + + /* Whether we have vector per vq */ + bool per_vq_vectors; struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev, + struct virtio_pci_vq_info *info, unsigned idx, void (*callback)(struct virtqueue *vq), const char *name, u16 msix_vec); - void (*del_vq)(struct virtqueue *vq); + void (*del_vq)(struct virtio_pci_vq_info *info); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); }; +/* Constants for MSI-X */ +/* Use first vector for configuration changes, second and the rest for + * virtqueues Thus, we need at least 2 vectors for MSI. */ +enum { + VP_MSIX_CONFIG_VECTOR = 0, + VP_MSIX_VQ_VECTOR = 1, +}; + /* Convert a generic virtio device to our structure */ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev) { diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index f7362c5fe18a..4bfa48fb1324 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -112,6 +112,7 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, + struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -129,6 +130,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN)) return ERR_PTR(-ENOENT); + info->msix_vector = msix_vec; + /* create the vring */ vq = vring_create_virtqueue(index, num, VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev, @@ -159,13 +162,14 @@ out_deactivate: return ERR_PTR(err); } -static void del_vq(struct virtqueue *vq) +static void del_vq(struct virtio_pci_vq_info *info) { + struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL); - if (vp_dev->pci_dev->msix_enabled) { + if (vp_dev->msix_enabled) { iowrite16(VIRTIO_MSI_NO_VECTOR, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); /* Flush the write out to device */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 7bc3004b840e..8978f109d2d7 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -293,6 +293,7 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, + struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -322,6 +323,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, /* get offset of notification word for this vq */ off = vp_ioread16(&cfg->queue_notify_off); + info->msix_vector = msix_vec; + /* create the vring */ vq = vring_create_virtqueue(index, num, SMP_CACHE_BYTES, &vp_dev->vdev, @@ -405,13 +408,14 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, return 0; } -static void del_vq(struct virtqueue *vq) +static void del_vq(struct virtio_pci_vq_info *info) { + struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); vp_iowrite16(vq->index, &vp_dev->common->queue_select); - if (vp_dev->pci_dev->msix_enabled) { + if (vp_dev->msix_enabled) { vp_iowrite16(VIRTIO_MSI_NO_VECTOR, &vp_dev->common->queue_msix_vector); /* Flush the write out to device */ diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 1f4733b80c87..f3b089b7c0b6 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -442,8 +442,10 @@ static int xenbus_write_transaction(unsigned msg_type, return xenbus_command_reply(u, XS_ERROR, "ENOENT"); rc = xenbus_dev_request_and_reply(&u->u.msg, u); - if (rc) + if (rc && trans) { + list_del(&trans->list); kfree(trans); + } out: return rc; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a18510be76c1..5e71f1ea3391 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7910,7 +7910,6 @@ struct btrfs_retry_complete { static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; - struct inode *inode; struct bio_vec *bvec; int i; @@ -7918,12 +7917,12 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) goto end; ASSERT(bio->bi_vcnt == 1); - inode = bio->bi_io_vec->bv_page->mapping->host; - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); done->uptodate = 1; bio_for_each_segment_all(bvec, bio, i) - clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0); + clean_io_failure(BTRFS_I(done->inode), done->start, + bvec->bv_page, 0); end: complete(&done->done); bio_put(bio); @@ -7973,8 +7972,10 @@ next_block_or_try_again: start += sectorsize; - if (nr_sectors--) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block_or_try_again; } } @@ -7986,9 +7987,7 @@ static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - struct inode *inode; struct bio_vec *bvec; - u64 start; int uptodate; int ret; int i; @@ -7998,11 +7997,8 @@ static void btrfs_retry_endio(struct bio *bio) uptodate = 1; - start = done->start; - ASSERT(bio->bi_vcnt == 1); - inode = bio->bi_io_vec->bv_page->mapping->host; - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); bio_for_each_segment_all(bvec, bio, i) { ret = __readpage_endio_check(done->inode, io_bio, i, @@ -8080,8 +8076,10 @@ next: ASSERT(nr_sectors); - if (--nr_sectors) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block; } } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a59801dc2a34..afbea61d957e 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1042,9 +1042,12 @@ static void report_reserved_underflow(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup, u64 num_bytes) { - btrfs_warn(fs_info, +#ifdef CONFIG_BTRFS_DEBUG + WARN_ON(qgroup->reserved < num_bytes); + btrfs_debug(fs_info, "qgroup %llu reserved space underflow, have: %llu, to free: %llu", qgroup->qgroupid, qgroup->reserved, num_bytes); +#endif qgroup->reserved = 0; } /* @@ -1075,7 +1078,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, qgroup->excl += sign * num_bytes; qgroup->excl_cmpr += sign * num_bytes; if (sign > 0) { - if (WARN_ON(qgroup->reserved < num_bytes)) + if (qgroup->reserved < num_bytes) report_reserved_underflow(fs_info, qgroup, num_bytes); else qgroup->reserved -= num_bytes; @@ -1100,7 +1103,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, WARN_ON(sign < 0 && qgroup->excl < num_bytes); qgroup->excl += sign * num_bytes; if (sign > 0) { - if (WARN_ON(qgroup->reserved < num_bytes)) + if (qgroup->reserved < num_bytes) report_reserved_underflow(fs_info, qgroup, num_bytes); else @@ -2469,7 +2472,7 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, qg = unode_aux_to_qgroup(unode); - if (WARN_ON(qg->reserved < num_bytes)) + if (qg->reserved < num_bytes) report_reserved_underflow(fs_info, qg, num_bytes); else qg->reserved -= num_bytes; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index da687dc79cce..9530a333d302 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -549,16 +549,19 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_ssd: btrfs_set_and_info(info, SSD, "use ssd allocation scheme"); + btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_ssd_spread: btrfs_set_and_info(info, SSD_SPREAD, "use spread ssd allocation scheme"); btrfs_set_opt(info->mount_opt, SSD); + btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_nossd: btrfs_set_and_info(info, NOSSD, "not using ssd allocation scheme"); btrfs_clear_opt(info->mount_opt, SSD); + btrfs_clear_opt(info->mount_opt, SSD_SPREAD); break; case Opt_barrier: btrfs_clear_and_info(info, NOBARRIER, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 73d56eef5e60..ab8a66d852f9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6213,7 +6213,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, for (dev_nr = 0; dev_nr < total_devs; dev_nr++) { dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || - (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) { + (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) { bbio_error(bbio, first_bio, logical); continue; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d449e1c03cbd..d3119fe3ab45 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2071,11 +2071,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); - if (ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, attr->ia_mode); - if (err) - goto out_put; - } if (mask) { req->r_inode = inode; @@ -2089,13 +2084,11 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) ceph_cap_string(dirtied), mask); ceph_mdsc_put_request(req); - if (mask & CEPH_SETATTR_SIZE) - __ceph_do_pending_vmtruncate(inode); - ceph_free_cap_flush(prealloc_cf); - return err; -out_put: - ceph_mdsc_put_request(req); ceph_free_cap_flush(prealloc_cf); + + if (err >= 0 && (mask & CEPH_SETATTR_SIZE)) + __ceph_do_pending_vmtruncate(inode); + return err; } @@ -2114,7 +2107,12 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (err != 0) return err; - return __ceph_setattr(inode, attr); + err = __ceph_setattr(inode, attr); + + if (err >= 0 && (attr->ia_valid & ATTR_MODE)) + err = posix_acl_chmod(inode, attr->ia_mode); + + return err; } /* diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 15e1db8738ae..dd3f5fabfdf6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -972,6 +972,86 @@ out: return rc; } +ssize_t cifs_file_copychunk_range(unsigned int xid, + struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags) +{ + struct inode *src_inode = file_inode(src_file); + struct inode *target_inode = file_inode(dst_file); + struct cifsFileInfo *smb_file_src; + struct cifsFileInfo *smb_file_target; + struct cifs_tcon *src_tcon; + struct cifs_tcon *target_tcon; + ssize_t rc; + + cifs_dbg(FYI, "copychunk range\n"); + + if (src_inode == target_inode) { + rc = -EINVAL; + goto out; + } + + if (!src_file->private_data || !dst_file->private_data) { + rc = -EBADF; + cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); + goto out; + } + + rc = -EXDEV; + smb_file_target = dst_file->private_data; + smb_file_src = src_file->private_data; + src_tcon = tlink_tcon(smb_file_src->tlink); + target_tcon = tlink_tcon(smb_file_target->tlink); + + if (src_tcon->ses != target_tcon->ses) { + cifs_dbg(VFS, "source and target of copy not on same server\n"); + goto out; + } + + /* + * Note: cifs case is easier than btrfs since server responsible for + * checks for proper open modes and file type and if it wants + * server could even support copy of range where source = target + */ + lock_two_nondirectories(target_inode, src_inode); + + cifs_dbg(FYI, "about to flush pages\n"); + /* should we flush first and last page first */ + truncate_inode_pages(&target_inode->i_data, 0); + + if (target_tcon->ses->server->ops->copychunk_range) + rc = target_tcon->ses->server->ops->copychunk_range(xid, + smb_file_src, smb_file_target, off, len, destoff); + else + rc = -EOPNOTSUPP; + + /* force revalidate of size and timestamps of target file now + * that target is updated on the server + */ + CIFS_I(target_inode)->time = 0; + /* although unlocking in the reverse order from locking is not + * strictly necessary here it is a little cleaner to be consistent + */ + unlock_two_nondirectories(src_inode, target_inode); + +out: + return rc; +} + +static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags) +{ + unsigned int xid = get_xid(); + ssize_t rc; + + rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, + len, flags); + free_xid(xid); + return rc; +} + const struct file_operations cifs_file_ops = { .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, @@ -984,6 +1064,7 @@ const struct file_operations cifs_file_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1001,6 +1082,7 @@ const struct file_operations cifs_file_strict_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1018,6 +1100,7 @@ const struct file_operations cifs_file_direct_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, @@ -1035,6 +1118,7 @@ const struct file_operations cifs_file_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1051,6 +1135,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1067,6 +1152,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, @@ -1078,6 +1164,7 @@ const struct file_operations cifs_dir_ops = { .release = cifs_closedir, .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, + .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = generic_file_llseek, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index da717fee3026..30bf89b1fd9a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -139,6 +139,11 @@ extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); # define cifs_listxattr NULL #endif +extern ssize_t cifs_file_copychunk_range(unsigned int xid, + struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, + size_t len, unsigned int flags); + extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); #ifdef CONFIG_CIFS_NFSD_EXPORT extern const struct export_operations cifs_export_ops; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index d42dd3288647..37f5a41cc50c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -243,6 +243,7 @@ struct smb_version_operations { /* verify the message */ int (*check_message)(char *, unsigned int, struct TCP_Server_Info *); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); + int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); void (*downgrade_oplock)(struct TCP_Server_Info *, struct cifsInodeInfo *, bool); /* process transaction2 response */ @@ -407,9 +408,10 @@ struct smb_version_operations { char * (*create_lease_buf)(u8 *, u8); /* parse lease context buffer and return oplock/epoch info */ __u8 (*parse_lease_buf)(void *, unsigned int *); - int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file, - struct cifsFileInfo *target_file, u64 src_off, u64 len, - u64 dest_off); + ssize_t (*copychunk_range)(const unsigned int, + struct cifsFileInfo *src_file, + struct cifsFileInfo *target_file, + u64 src_off, u64 len, u64 dest_off); int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src, struct cifsFileInfo *target_file, u64 src_off, u64 len, u64 dest_off); @@ -946,7 +948,6 @@ struct cifs_tcon { bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ - bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ __le32 capabilities; __u32 share_flags; __u32 maximal_access; @@ -1343,6 +1344,7 @@ struct mid_q_entry { void *callback_data; /* general purpose pointer for callback */ void *resp_buf; /* pointer to received SMB header */ int mid_state; /* wish this were enum but can not pass to wait_event */ + unsigned int mid_flags; __le16 command; /* smb command code */ bool large_buf:1; /* if valid response, is pointer to large buf */ bool multiRsp:1; /* multiple trans2 responses for one request */ @@ -1350,6 +1352,12 @@ struct mid_q_entry { bool decrypted:1; /* decrypted entry */ }; +struct close_cancelled_open { + struct cifs_fid fid; + struct cifs_tcon *tcon; + struct work_struct work; +}; + /* Make code in transport.c a little cleaner by moving update of optional stats into function below */ #ifdef CONFIG_CIFS_STATS2 @@ -1481,6 +1489,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +/* Flags */ +#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ + /* Types of response buffer returned from SendReceive2 */ #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ #define CIFS_SMALL_BUFFER 1 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 066950671929..5d21f00ae341 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1428,6 +1428,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) length = cifs_discard_remaining_data(server); dequeue_mid(mid, rdata->result); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } @@ -1541,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return cifs_readv_discard(server, mid); dequeue_mid(mid, false); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; return length; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9ae695ae3ed7..d82467cfb0e2 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -904,10 +904,19 @@ cifs_demultiplex_thread(void *p) server->lstrp = jiffies; if (mid_entry != NULL) { + if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) && + mid_entry->mid_state == MID_RESPONSE_RECEIVED && + server->ops->handle_cancelled_mid) + server->ops->handle_cancelled_mid( + mid_entry->resp_buf, + server); + if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); - } else if (!server->ops->is_oplock_break || - !server->ops->is_oplock_break(buf, server)) { + } else if (server->ops->is_oplock_break && + server->ops->is_oplock_break(buf, server)) { + cifs_dbg(FYI, "Received oplock break\n"); + } else { cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n", atomic_read(&midCount)); cifs_dump_mem("Received Data is: ", buf, @@ -3744,6 +3753,9 @@ try_mount_again: if (IS_ERR(tcon)) { rc = PTR_ERR(tcon); tcon = NULL; + if (rc == -EACCES) + goto mount_fail_check; + goto remote_path_check; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index aa3debbba826..21d404535739 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2597,7 +2597,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, wdata->credits = credits; if (!wdata->cfile->invalidHandle || - !cifs_reopen_file(wdata->cfile, false)) + !(rc = cifs_reopen_file(wdata->cfile, false))) rc = server->ops->async_writev(wdata, cifs_uncached_writedata_release); if (rc) { @@ -3022,7 +3022,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, rdata->credits = credits; if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); error: if (rc) { @@ -3617,7 +3617,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } if (!rdata->cfile->invalidHandle || - !cifs_reopen_file(rdata->cfile, true)) + !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 001528781b6b..265c45fe4ea5 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -34,71 +34,14 @@ #include "cifs_ioctl.h" #include <linux/btrfs.h> -static int cifs_file_clone_range(unsigned int xid, struct file *src_file, - struct file *dst_file) -{ - struct inode *src_inode = file_inode(src_file); - struct inode *target_inode = file_inode(dst_file); - struct cifsFileInfo *smb_file_src; - struct cifsFileInfo *smb_file_target; - struct cifs_tcon *src_tcon; - struct cifs_tcon *target_tcon; - int rc; - - cifs_dbg(FYI, "ioctl clone range\n"); - - if (!src_file->private_data || !dst_file->private_data) { - rc = -EBADF; - cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); - goto out; - } - - rc = -EXDEV; - smb_file_target = dst_file->private_data; - smb_file_src = src_file->private_data; - src_tcon = tlink_tcon(smb_file_src->tlink); - target_tcon = tlink_tcon(smb_file_target->tlink); - - if (src_tcon->ses != target_tcon->ses) { - cifs_dbg(VFS, "source and target of copy not on same server\n"); - goto out; - } - - /* - * Note: cifs case is easier than btrfs since server responsible for - * checks for proper open modes and file type and if it wants - * server could even support copy of range where source = target - */ - lock_two_nondirectories(target_inode, src_inode); - - cifs_dbg(FYI, "about to flush pages\n"); - /* should we flush first and last page first */ - truncate_inode_pages(&target_inode->i_data, 0); - - if (target_tcon->ses->server->ops->clone_range) - rc = target_tcon->ses->server->ops->clone_range(xid, - smb_file_src, smb_file_target, 0, src_inode->i_size, 0); - else - rc = -EOPNOTSUPP; - - /* force revalidate of size and timestamps of target file now - that target is updated on the server */ - CIFS_I(target_inode)->time = 0; - /* although unlocking in the reverse order from locking is not - strictly necessary here it is a little cleaner to be consistent */ - unlock_two_nondirectories(src_inode, target_inode); -out: - return rc; -} - -static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, +static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file, unsigned long srcfd) { int rc; struct fd src_file; struct inode *src_inode; - cifs_dbg(FYI, "ioctl clone range\n"); + cifs_dbg(FYI, "ioctl copychunk range\n"); /* the destination must be opened for writing */ if (!(dst_file->f_mode & FMODE_WRITE)) { cifs_dbg(FYI, "file target not open for write\n"); @@ -129,7 +72,8 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, if (S_ISDIR(src_inode->i_mode)) goto out_fput; - rc = cifs_file_clone_range(xid, src_file.file, dst_file); + rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0, + src_inode->i_size, 0); out_fput: fdput(src_file); @@ -251,7 +195,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) } break; case CIFS_IOC_COPYCHUNK_FILE: - rc = cifs_ioctl_clone(xid, filep, arg); + rc = cifs_ioctl_copychunk(xid, filep, arg); break; case CIFS_IOC_SET_INTEGRITY: if (pSMBFile == NULL) diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index cc93ba4da9b5..27bc360c7ffd 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile) return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; } +static bool +cifs_can_echo(struct TCP_Server_Info *server) +{ + if (server->tcpStatus == CifsGood) + return true; + + return false; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = { .get_dfs_refer = CIFSGetDFSRefer, .qfs_tcon = cifs_qfs_tcon, .is_path_accessible = cifs_is_path_accessible, + .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index fd516ea8b8f8..1a04b3a5beb1 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -659,3 +659,49 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); return false; } + +void +smb2_cancelled_close_fid(struct work_struct *work) +{ + struct close_cancelled_open *cancelled = container_of(work, + struct close_cancelled_open, work); + + cifs_dbg(VFS, "Close unmatched open\n"); + + SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid, + cancelled->fid.volatile_fid); + cifs_put_tcon(cancelled->tcon); + kfree(cancelled); +} + +int +smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server) +{ + struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer); + struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer; + struct cifs_tcon *tcon; + struct close_cancelled_open *cancelled; + + if (sync_hdr->Command != SMB2_CREATE || + sync_hdr->Status != STATUS_SUCCESS) + return 0; + + cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); + if (!cancelled) + return -ENOMEM; + + tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId, + sync_hdr->TreeId); + if (!tcon) { + kfree(cancelled); + return -ENOENT; + } + + cancelled->fid.persistent_fid = rsp->PersistentFileId; + cancelled->fid.volatile_fid = rsp->VolatileFileId; + cancelled->tcon = tcon; + INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); + queue_work(cifsiod_wq, &cancelled->work); + + return 0; +} diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0231108d9387..152e37f2ad92 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -21,6 +21,7 @@ #include <linux/vfs.h> #include <linux/falloc.h> #include <linux/scatterlist.h> +#include <linux/uuid.h> #include <crypto/aead.h> #include "cifsglob.h" #include "smb2pdu.h" @@ -592,8 +593,8 @@ req_res_key_exit: return rc; } -static int -smb2_clone_range(const unsigned int xid, +static ssize_t +smb2_copychunk_range(const unsigned int xid, struct cifsFileInfo *srcfile, struct cifsFileInfo *trgtfile, u64 src_off, u64 len, u64 dest_off) @@ -605,13 +606,14 @@ smb2_clone_range(const unsigned int xid, struct cifs_tcon *tcon; int chunks_copied = 0; bool chunk_sizes_updated = false; + ssize_t bytes_written, total_bytes_written = 0; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); if (pcchunk == NULL) return -ENOMEM; - cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n"); + cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n"); /* Request a key from the server to identify the source of the copy */ rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), srcfile->fid.persistent_fid, @@ -669,14 +671,16 @@ smb2_clone_range(const unsigned int xid, } chunks_copied++; - src_off += le32_to_cpu(retbuf->TotalBytesWritten); - dest_off += le32_to_cpu(retbuf->TotalBytesWritten); - len -= le32_to_cpu(retbuf->TotalBytesWritten); + bytes_written = le32_to_cpu(retbuf->TotalBytesWritten); + src_off += bytes_written; + dest_off += bytes_written; + len -= bytes_written; + total_bytes_written += bytes_written; - cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n", + cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n", le32_to_cpu(retbuf->ChunksWritten), le32_to_cpu(retbuf->ChunkBytesWritten), - le32_to_cpu(retbuf->TotalBytesWritten)); + bytes_written); } else if (rc == -EINVAL) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) goto cchunk_out; @@ -713,7 +717,10 @@ smb2_clone_range(const unsigned int xid, cchunk_out: kfree(pcchunk); kfree(retbuf); - return rc; + if (rc) + return rc; + else + return total_bytes_written; } static int @@ -2322,6 +2329,7 @@ struct smb_version_operations smb20_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2377,7 +2385,7 @@ struct smb_version_operations smb20_operations = { .set_oplock_level = smb2_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .get_dfs_refer = smb2_get_dfs_refer, @@ -2404,6 +2412,7 @@ struct smb_version_operations smb21_operations = { .clear_stats = smb2_clear_stats, .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2459,7 +2468,7 @@ struct smb_version_operations smb21_operations = { .set_oplock_level = smb21_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .enum_snapshots = smb3_enum_snapshots, @@ -2488,6 +2497,7 @@ struct smb_version_operations smb30_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2545,7 +2555,7 @@ struct smb_version_operations smb30_operations = { .set_oplock_level = smb3_set_oplock_level, .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .duplicate_extents = smb2_duplicate_extents, .validate_negotiate = smb3_validate_negotiate, .wp_retry_size = smb2_wp_retry_size, @@ -2582,6 +2592,7 @@ struct smb_version_operations smb311_operations = { .print_stats = smb2_print_stats, .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, + .handle_cancelled_mid = smb2_handle_cancelled_mid, .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, @@ -2639,7 +2650,7 @@ struct smb_version_operations smb311_operations = { .set_oplock_level = smb3_set_oplock_level, .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, - .clone_range = smb2_clone_range, + .copychunk_range = smb2_copychunk_range, .duplicate_extents = smb2_duplicate_extents, /* .validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */ .wp_retry_size = smb2_wp_retry_size, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7446496850a3..02da648041fc 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -562,8 +562,10 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) * but for time being this is our only auth choice so doesn't matter. * We just found a server which sets blob length to zero expecting raw. */ - if (blob_length == 0) + if (blob_length == 0) { cifs_dbg(FYI, "missing security blob on negprot\n"); + server->sec_ntlmssp = true; + } rc = cifs_enable_signing(server, ses->sign); if (rc) @@ -1171,9 +1173,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, else return -EIO; - if (tcon && tcon->bad_network_name) - return -ENOENT; - unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL); if (unc_path == NULL) return -ENOMEM; @@ -1185,6 +1184,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, return -EINVAL; } + /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */ + if (tcon) + tcon->tid = 0; + rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req); if (rc) { kfree(unc_path); @@ -1273,8 +1276,6 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - if (tcon) - tcon->bad_network_name = true; } goto tcon_exit; } @@ -2177,6 +2178,9 @@ void smb2_reconnect_server(struct work_struct *work) struct cifs_tcon *tcon, *tcon2; struct list_head tmp_list; int tcon_exist = false; + int rc; + int resched = false; + /* Prevent simultaneous reconnects that can corrupt tcon->rlist list */ mutex_lock(&server->reconnect_mutex); @@ -2204,13 +2208,18 @@ void smb2_reconnect_server(struct work_struct *work) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) { - if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon)) + rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon); + if (!rc) cifs_reopen_persistent_handles(tcon); + else + resched = true; list_del_init(&tcon->rlist); cifs_put_tcon(tcon); } cifs_dbg(FYI, "Reconnecting tcons finished\n"); + if (resched) + queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ); mutex_unlock(&server->reconnect_mutex); /* now we can safely release srv struct */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 69e35873b1de..6853454fc871 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -48,6 +48,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst); extern struct mid_q_entry *smb2_setup_async_request( struct TCP_Server_Info *server, struct smb_rqst *rqst); +extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, + __u64 ses_id); +extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, + __u64 ses_id, __u32 tid); extern int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server); extern int smb3_calc_signature(struct smb_rqst *rqst, @@ -164,6 +168,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, const u64 persistent_fid, const u64 volatile_fid, const __u8 oplock_level); +extern int smb2_handle_cancelled_mid(char *buffer, + struct TCP_Server_Info *server); +void smb2_cancelled_close_fid(struct work_struct *work); extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct kstatfs *FSData); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 7c3bb1bd7eed..506b67fc93d9 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -115,23 +115,70 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server) return 0; } -struct cifs_ses * -smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id) +static struct cifs_ses * +smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) { struct cifs_ses *ses; - spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { if (ses->Suid != ses_id) continue; - spin_unlock(&cifs_tcp_ses_lock); return ses; } + + return NULL; +} + +struct cifs_ses * +smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id) +{ + struct cifs_ses *ses; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); spin_unlock(&cifs_tcp_ses_lock); + return ses; +} + +static struct cifs_tcon * +smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) +{ + struct cifs_tcon *tcon; + + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (tcon->tid != tid) + continue; + ++tcon->tc_count; + return tcon; + } + return NULL; } +/* + * Obtain tcon corresponding to the tid in the given + * cifs_ses + */ + +struct cifs_tcon * +smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) +{ + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + spin_lock(&cifs_tcp_ses_lock); + ses = smb2_find_smb_ses_unlocked(server, ses_id); + if (!ses) { + spin_unlock(&cifs_tcp_ses_lock); + return NULL; + } + tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); + spin_unlock(&cifs_tcp_ses_lock); + + return tcon; +} + int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 526f0533cb4e..f6e13a977fc8 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -752,9 +752,11 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(ses->server, midQ); if (rc != 0) { + cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid); send_cancel(ses->server, rqst, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + midQ->mid_flags |= MID_WAIT_CANCELLED; midQ->callback = DeleteMidQEntry; spin_unlock(&GlobalMid_Lock); add_credits(ses->server, 1, optype); @@ -373,6 +373,22 @@ restart: } spin_lock_irq(&mapping->tree_lock); + if (!entry) { + /* + * We needed to drop the page_tree lock while calling + * radix_tree_preload() and we didn't have an entry to + * lock. See if another thread inserted an entry at + * our index during this time. + */ + entry = __radix_tree_lookup(&mapping->page_tree, index, + NULL, &slot); + if (entry) { + radix_tree_preload_end(); + spin_unlock_irq(&mapping->tree_lock); + goto restart; + } + } + if (pmd_downgrade) { radix_tree_delete(&mapping->page_tree, index); mapping->nrexceptional--; @@ -388,19 +404,12 @@ restart: if (err) { spin_unlock_irq(&mapping->tree_lock); /* - * Someone already created the entry? This is a - * normal failure when inserting PMDs in a range - * that already contains PTEs. In that case we want - * to return -EEXIST immediately. - */ - if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD)) - goto restart; - /* - * Our insertion of a DAX PMD entry failed, most - * likely because it collided with a PTE sized entry - * at a different index in the PMD range. We haven't - * inserted anything into the radix tree and have no - * waiters to wake. + * Our insertion of a DAX entry failed, most likely + * because we were inserting a PMD entry and it + * collided with a PTE sized entry at a different + * index in the PMD range. We haven't inserted + * anything into the radix tree and have no waiters to + * wake. */ return ERR_PTR(err); } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f493af666591..fb69ee2388db 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2466,6 +2466,7 @@ extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); +extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8210c1f43556..cefa9835f275 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -744,7 +744,7 @@ const struct file_operations ext4_file_operations = { const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, - .getattr = ext4_getattr, + .getattr = ext4_file_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4247d8d25687..b9ffa9f4191f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5390,11 +5390,46 @@ err_out: int ext4_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct inode *inode; - unsigned long long delalloc_blocks; + struct inode *inode = d_inode(path->dentry); + struct ext4_inode *raw_inode; + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int flags; + + if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = ei->i_crtime.tv_sec; + stat->btime.tv_nsec = ei->i_crtime.tv_nsec; + } + + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + if (flags & EXT4_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & EXT4_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (flags & EXT4_ENCRYPT_FL) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (flags & EXT4_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & EXT4_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); - inode = d_inode(path->dentry); generic_fillattr(inode, stat); + return 0; +} + +int ext4_file_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + u64 delalloc_blocks; + + ext4_getattr(path, stat, request_mask, query_flags); /* * If there is inline data in the inode, the inode will normally not diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6ad612c576fc..07e5e1405771 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3912,6 +3912,7 @@ const struct inode_operations ext4_dir_inode_operations = { .tmpfile = ext4_tmpfile, .rename = ext4_rename2, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, @@ -3920,6 +3921,7 @@ const struct inode_operations ext4_dir_inode_operations = { const struct inode_operations ext4_special_inode_operations = { .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 73b184d161fc..5c8fc53cb0e5 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -85,17 +85,20 @@ errout: const struct inode_operations ext4_encrypted_symlink_inode_operations = { .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; const struct inode_operations ext4_symlink_inode_operations = { .get_link = page_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; const struct inode_operations ext4_fast_symlink_inode_operations = { .get_link = simple_get_link, .setattr = ext4_setattr, + .getattr = ext4_getattr, .listxattr = ext4_listxattr, }; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 7163fe014b57..dde861387a40 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -136,17 +136,26 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; + /* + * Offset passed to mmap (before page shift) could have been + * negative when represented as a (l)off_t. + */ + if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + return -EINVAL; + if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); + len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + /* check for overflow */ + if (len < vma_len) + return -EINVAL; inode_lock(inode); file_accessed(file); ret = -ENOMEM; - len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - if (hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, @@ -155,7 +164,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) ret = 0; if (vma->vm_flags & VM_WRITE && inode->i_size < len) - inode->i_size = len; + i_size_write(inode, len); out: inode_unlock(inode); diff --git a/fs/namei.c b/fs/namei.c index d41fab78798b..19dcf62133cc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2145,6 +2145,9 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int retval = 0; const char *s = nd->name->name; + if (!*s) + flags &= ~LOOKUP_RCU; + nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; nd->depth = 0; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index aab32fc3d6a8..c1b5fed7c863 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -537,7 +537,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, if (put_dreq(dreq)) nfs_direct_complete(dreq); - return 0; + return requested_bytes; } /** @@ -566,7 +566,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; - ssize_t result = -EINVAL; + ssize_t result = -EINVAL, requested; size_t count = iov_iter_count(iter); nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); @@ -600,14 +600,19 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; - result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); + requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); nfs_end_io_direct(inode); - if (!result) { + if (requested > 0) { result = nfs_direct_wait(dreq); - if (result > 0) + if (result > 0) { + requested -= result; iocb->ki_pos += result; + } + iov_iter_revert(iter, requested); + } else { + result = requested; } out_release: @@ -954,7 +959,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, if (put_dreq(dreq)) nfs_direct_write_complete(dreq); - return 0; + return requested_bytes; } /** @@ -979,7 +984,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, */ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t result = -EINVAL; + ssize_t result = -EINVAL, requested; size_t count; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -1022,7 +1027,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) nfs_start_io_direct(inode); - result = nfs_direct_write_schedule_iovec(dreq, iter, pos); + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos); if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, @@ -1031,13 +1036,17 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) nfs_end_io_direct(inode); - if (!result) { + if (requested > 0) { result = nfs_direct_wait(dreq); if (result > 0) { + requested -= result; iocb->ki_pos = pos + result; /* XXX: should check the generic_write_sync retval */ generic_write_sync(iocb, result); } + iov_iter_revert(iter, requested); + } else { + result = requested; } out_release: nfs_direct_req_release(dreq); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index dba2ff8eaa68..452334694a5d 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -358,6 +358,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, { unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); + struct kvec *head = rqstp->rq_arg.head; + struct kvec *tail = rqstp->rq_arg.tail; p = decode_fh(p, &args->fh); if (!p) @@ -367,6 +369,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, args->count = ntohl(*p++); args->stable = ntohl(*p++); len = args->len = ntohl(*p++); + if ((void *)p > head->iov_base + head->iov_len) + return 0; /* * The count must equal the amount of data passed. */ @@ -377,9 +381,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - + rqstp->rq_arg.tail[0].iov_len - hdr; + hdr = (void*)p - head->iov_base; + dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr; /* * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that @@ -396,7 +399,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, len = args->len = max_blocksize; } rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; @@ -471,6 +474,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, /* first copy and check from the first page */ old = (char*)p; vec = &rqstp->rq_arg.head[0]; + if ((void *)old > vec->iov_base + vec->iov_len) + return 0; avail = vec->iov_len - (old - (char*)vec->iov_base); while (len && avail && *old) { *new++ = *old++; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index cbeeda1e94a2..d86031b6ad79 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2489,7 +2489,7 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op) { - if (op->opnum == OP_ILLEGAL) + if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp) return op_encode_hdr_size * sizeof(__be32); BUG_ON(OPDESC(op)->op_rsize_bop == NULL); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 31e1f9593457..59979f0bbd4b 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -747,6 +747,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) return nfserr; } +/* + * A write procedure can have a large argument, and a read procedure can + * have a large reply, but no NFSv2 or NFSv3 procedure has argument and + * reply that can both be larger than a page. The xdr code has taken + * advantage of this assumption to be a sloppy about bounds checking in + * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that + * problem, we enforce these assumptions here: + */ +static bool nfs_request_too_big(struct svc_rqst *rqstp, + struct svc_procedure *proc) +{ + /* + * The ACL code has more careful bounds-checking and is not + * susceptible to this problem: + */ + if (rqstp->rq_prog != NFS_PROGRAM) + return false; + /* + * Ditto NFSv4 (which can in theory have argument and reply both + * more than a page): + */ + if (rqstp->rq_vers >= 4) + return false; + /* The reply will be small, we're OK: */ + if (proc->pc_xdrressize > 0 && + proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE)) + return false; + + return rqstp->rq_arg.len > PAGE_SIZE; +} + int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -759,6 +790,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_vers, rqstp->rq_proc); proc = rqstp->rq_procinfo; + if (nfs_request_too_big(rqstp, proc)) { + dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers); + *statp = rpc_garbage_args; + return 1; + } /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 41b468a6a90f..de07ff625777 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_writeargs *args) { unsigned int len, hdr, dlen; + struct kvec *head = rqstp->rq_arg.head; int v; p = decode_fh(p, &args->fh); @@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Check to make sure that we got the right number of * bytes. */ - hdr = (void*)p - rqstp->rq_arg.head[0].iov_base; - dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len - - hdr; + hdr = (void*)p - head->iov_base; + if (hdr > head->iov_len) + return 0; + dlen = head->iov_len + rqstp->rq_arg.page_len - hdr; /* * Round the length of the data which was specified up to @@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, return 0; rqstp->rq_vec[0].iov_base = (void*)p; - rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr; + rqstp->rq_vec[0].iov_len = head->iov_len - hdr; v = 0; while (len > rqstp->rq_vec[v].iov_len) { len -= rqstp->rq_vec[v].iov_len; diff --git a/fs/nsfs.c b/fs/nsfs.c index 1656843e87d2..323f492e0822 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -91,6 +91,7 @@ slow: return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index c4ab6fdf17a0..e1534c9bab16 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -208,14 +208,19 @@ restart: continue; /* * Skip ops whose filesystem we don't know about unless - * it is being mounted. + * it is being mounted or unmounted. It is possible for + * a filesystem we don't know about to be unmounted if + * it fails to mount in the kernel after userspace has + * been sent the mount request. */ /* XXX: is there a better way to detect this? */ } else if (ret == -1 && !(op->upcall.type == ORANGEFS_VFS_OP_FS_MOUNT || op->upcall.type == - ORANGEFS_VFS_OP_GETATTR)) { + ORANGEFS_VFS_OP_GETATTR || + op->upcall.type == + ORANGEFS_VFS_OP_FS_UMOUNT)) { gossip_debug(GOSSIP_DEV_DEBUG, "orangefs: skipping op tag %llu %s\n", llu(op->tag), get_opname_string(op)); diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 6333cbbdfef7..83b506020718 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -521,13 +521,11 @@ int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter, size_t n = size; if (n > PAGE_SIZE) n = PAGE_SIZE; - n = copy_page_from_iter(page, 0, n, iter); - if (!n) + if (copy_page_from_iter(page, 0, n, iter) != n) return -EFAULT; size -= n; } return 0; - } /* diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 5e48a0be9761..8afac46fcc87 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -249,6 +249,7 @@ struct orangefs_sb_info_s { char devname[ORANGEFS_MAX_SERVER_ADDR_LEN]; struct super_block *sb; int mount_pending; + int no_list; struct list_head list; }; diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 67c24351a67f..629d8c917fa6 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -263,8 +263,13 @@ int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb) if (!new_op) return -ENOMEM; new_op->upcall.req.features.features = 0; - ret = service_operation(new_op, "orangefs_features", 0); - orangefs_features = new_op->downcall.resp.features.features; + ret = service_operation(new_op, "orangefs_features", + ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX); + if (!ret) + orangefs_features = + new_op->downcall.resp.features.features; + else + orangefs_features = 0; op_release(new_op); } else { orangefs_features = 0; @@ -488,7 +493,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, if (ret) { d = ERR_PTR(ret); - goto free_op; + goto free_sb_and_op; } /* @@ -514,6 +519,9 @@ struct dentry *orangefs_mount(struct file_system_type *fst, spin_unlock(&orangefs_superblocks_lock); op_release(new_op); + /* Must be removed from the list now. */ + ORANGEFS_SB(sb)->no_list = 0; + if (orangefs_userspace_version >= 20906) { new_op = op_alloc(ORANGEFS_VFS_OP_FEATURES); if (!new_op) @@ -528,6 +536,10 @@ struct dentry *orangefs_mount(struct file_system_type *fst, return dget(sb->s_root); +free_sb_and_op: + /* Will call orangefs_kill_sb with sb not in list. */ + ORANGEFS_SB(sb)->no_list = 1; + deactivate_locked_super(sb); free_op: gossip_err("orangefs_mount: mount request failed with %d\n", ret); if (ret == -EINVAL) { @@ -553,12 +565,14 @@ void orangefs_kill_sb(struct super_block *sb) */ orangefs_unmount_sb(sb); - /* remove the sb from our list of orangefs specific sb's */ - - spin_lock(&orangefs_superblocks_lock); - __list_del_entry(&ORANGEFS_SB(sb)->list); /* not list_del_init */ - ORANGEFS_SB(sb)->list.prev = NULL; - spin_unlock(&orangefs_superblocks_lock); + if (!ORANGEFS_SB(sb)->no_list) { + /* remove the sb from our list of orangefs specific sb's */ + spin_lock(&orangefs_superblocks_lock); + /* not list_del_init */ + __list_del_entry(&ORANGEFS_SB(sb)->list); + ORANGEFS_SB(sb)->list.prev = NULL; + spin_unlock(&orangefs_superblocks_lock); + } /* * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 8f91ec66baa3..d04ea4349909 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1074,6 +1074,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || + (table->proc_handler == proc_douintvec) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f08bd31c1081..312578089544 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -900,7 +900,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); + pmd_t pmd = *pmdp; + + /* See comment in change_huge_pmd() */ + pmdp_invalidate(vma, addr, pmdp); + if (pmd_dirty(*pmdp)) + pmd = pmd_mkdirty(pmd); + if (pmd_young(*pmdp)) + pmd = pmd_mkyoung(pmd); pmd = pmd_wrprotect(pmd); pmd = pmd_clear_soft_dirty(pmd); diff --git a/fs/stat.c b/fs/stat.c index fa0be59340cc..a257b872a53d 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -130,9 +130,13 @@ EXPORT_SYMBOL(vfs_getattr); int vfs_statx_fd(unsigned int fd, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct fd f = fdget_raw(fd); + struct fd f; int error = -EBADF; + if (query_flags & ~KSTAT_QUERY_FLAGS) + return -EINVAL; + + f = fdget_raw(fd); if (f.file) { error = vfs_getattr(&f.file->f_path, stat, request_mask, query_flags); @@ -155,9 +159,6 @@ EXPORT_SYMBOL(vfs_statx_fd); * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * - * The caller must have preset stat->request_mask as for vfs_getattr(). The - * flags are also used to load up stat->query_flags. - * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_statx(int dfd, const char __user *filename, int flags, @@ -509,58 +510,50 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ -static inline int __put_timestamp(struct timespec *kts, - struct statx_timestamp __user *uts) -{ - return (__put_user(kts->tv_sec, &uts->tv_sec ) || - __put_user(kts->tv_nsec, &uts->tv_nsec ) || - __put_user(0, &uts->__reserved )); -} - -/* - * Set the statx results. - */ -static long statx_set_result(struct kstat *stat, struct statx __user *buffer) +static noinline_for_stack int +cp_statx(const struct kstat *stat, struct statx __user *buffer) { - uid_t uid = from_kuid_munged(current_user_ns(), stat->uid); - gid_t gid = from_kgid_munged(current_user_ns(), stat->gid); - - if (__put_user(stat->result_mask, &buffer->stx_mask ) || - __put_user(stat->mode, &buffer->stx_mode ) || - __clear_user(&buffer->__spare0, sizeof(buffer->__spare0)) || - __put_user(stat->nlink, &buffer->stx_nlink ) || - __put_user(uid, &buffer->stx_uid ) || - __put_user(gid, &buffer->stx_gid ) || - __put_user(stat->attributes, &buffer->stx_attributes ) || - __put_user(stat->blksize, &buffer->stx_blksize ) || - __put_user(MAJOR(stat->rdev), &buffer->stx_rdev_major ) || - __put_user(MINOR(stat->rdev), &buffer->stx_rdev_minor ) || - __put_user(MAJOR(stat->dev), &buffer->stx_dev_major ) || - __put_user(MINOR(stat->dev), &buffer->stx_dev_minor ) || - __put_timestamp(&stat->atime, &buffer->stx_atime ) || - __put_timestamp(&stat->btime, &buffer->stx_btime ) || - __put_timestamp(&stat->ctime, &buffer->stx_ctime ) || - __put_timestamp(&stat->mtime, &buffer->stx_mtime ) || - __put_user(stat->ino, &buffer->stx_ino ) || - __put_user(stat->size, &buffer->stx_size ) || - __put_user(stat->blocks, &buffer->stx_blocks ) || - __clear_user(&buffer->__spare1, sizeof(buffer->__spare1)) || - __clear_user(&buffer->__spare2, sizeof(buffer->__spare2))) - return -EFAULT; - - return 0; + struct statx tmp; + + memset(&tmp, 0, sizeof(tmp)); + + tmp.stx_mask = stat->result_mask; + tmp.stx_blksize = stat->blksize; + tmp.stx_attributes = stat->attributes; + tmp.stx_nlink = stat->nlink; + tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); + tmp.stx_mode = stat->mode; + tmp.stx_ino = stat->ino; + tmp.stx_size = stat->size; + tmp.stx_blocks = stat->blocks; + tmp.stx_attributes_mask = stat->attributes_mask; + tmp.stx_atime.tv_sec = stat->atime.tv_sec; + tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; + tmp.stx_btime.tv_sec = stat->btime.tv_sec; + tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; + tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; + tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; + tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; + tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; + tmp.stx_rdev_major = MAJOR(stat->rdev); + tmp.stx_rdev_minor = MINOR(stat->rdev); + tmp.stx_dev_major = MAJOR(stat->dev); + tmp.stx_dev_minor = MINOR(stat->dev); + + return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. - * @filename: File to stat *or* NULL. + * @filename: File to stat or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * - * Note that if filename is NULL, then it does the equivalent of fstat() using - * dfd to indicate the file of interest. + * Note that fstat() can be emulated by setting dfd to the fd of interest, + * supplying "" as the filename and setting AT_EMPTY_PATH in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, @@ -570,18 +563,16 @@ SYSCALL_DEFINE5(statx, struct kstat stat; int error; + if (mask & STATX__RESERVED) + return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; - if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer))) - return -EFAULT; - if (filename) - error = vfs_statx(dfd, filename, flags, &stat, mask); - else - error = vfs_statx_fd(dfd, &stat, mask, flags); + error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; - return statx_set_result(&stat, buffer); + + return cp_statx(&stat, buffer); } /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index b803213d1307..39c75a86c67f 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; - size_t len; + ssize_t len; /* * If buf != of->prealloc_buf, we don't know how @@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); + if (len < 0) + return len; if (pos) { if (len <= pos) return 0; len -= pos; memmove(buf, buf + pos, len); } - return min(count, len); + return min_t(ssize_t, count, len); } /* kernfs write callback for regular sysfs files */ diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 1e712a364680..718b749fa11a 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -32,6 +32,7 @@ #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/random.h> +#include <linux/ctype.h> #include "ubifs.h" static DEFINE_SPINLOCK(dbg_lock); @@ -286,8 +287,10 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode) break; } - pr_err("\t%d: %s (%s)\n", - count++, dent->name, get_dent_type(dent->type)); + pr_err("\t%d: inode %llu, type %s, len %d\n", + count++, (unsigned long long) le64_to_cpu(dent->inum), + get_dent_type(dent->type), + le16_to_cpu(dent->nlen)); fname_name(&nm) = dent->name; fname_len(&nm) = le16_to_cpu(dent->nlen); @@ -464,7 +467,8 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node) pr_err("(bad name length, not printing, bad or corrupted node)"); else { for (i = 0; i < nlen && dent->name[i]; i++) - pr_cont("%c", dent->name[i]); + pr_cont("%c", isprint(dent->name[i]) ? + dent->name[i] : '?'); } pr_cont("\n"); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 30825d882aa9..b777bddaa1dd 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -606,8 +606,8 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } while (1) { - dbg_gen("feed '%s', ino %llu, new f_pos %#x", - dent->name, (unsigned long long)le64_to_cpu(dent->inum), + dbg_gen("ino %llu, new f_pos %#x", + (unsigned long long)le64_to_cpu(dent->inum), key_hash_flash(c, &dent->key)); ubifs_assert(le64_to_cpu(dent->ch.sqnum) > ubifs_inode(dir)->creat_sqnum); @@ -748,6 +748,11 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, goto out_fname; lock_2_inodes(dir, inode); + + /* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */ + if (inode->i_nlink == 0) + ubifs_delete_orphan(c, inode->i_ino); + inc_nlink(inode); ihold(inode); inode->i_ctime = ubifs_current_time(inode); @@ -768,6 +773,8 @@ out_cancel: dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; drop_nlink(inode); + if (inode->i_nlink == 0) + ubifs_add_orphan(c, inode->i_ino); unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); iput(inode); @@ -1068,8 +1075,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, } err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); - if (err) + if (err) { + kfree(dev); goto out_budg; + } sz_change = CALC_DENT_SIZE(fname_len(&nm)); @@ -1316,9 +1325,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int uninitialized_var(saved_nlink); struct fscrypt_name old_nm, new_nm; - if (flags & ~RENAME_NOREPLACE) - return -EINVAL; - /* * Budget request settings: deletion direntry, new direntry, removing * the old inode, and changing old and new parent directory inodes. diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1d227b0fcf49..f7555fc25877 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1756,7 +1756,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", - pending, total, UFFD_API, UFFD_API_FEATURES, + pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index eb00bc133bca..39f8604f764e 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -125,8 +125,7 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino); extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); extern int xfs_dir2_sf_removename(struct xfs_da_args *args); extern int xfs_dir2_sf_replace(struct xfs_da_args *args); -extern int xfs_dir2_sf_verify(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp, - int size); +extern int xfs_dir2_sf_verify(struct xfs_inode *ip); /* xfs_dir2_readdir.c */ extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx, diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 96b45cd6c63f..e84af093b2ab 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -632,36 +632,49 @@ xfs_dir2_sf_check( /* Verify the consistency of an inline directory. */ int xfs_dir2_sf_verify( - struct xfs_mount *mp, - struct xfs_dir2_sf_hdr *sfp, - int size) + struct xfs_inode *ip) { + struct xfs_mount *mp = ip->i_mount; + struct xfs_dir2_sf_hdr *sfp; struct xfs_dir2_sf_entry *sfep; struct xfs_dir2_sf_entry *next_sfep; char *endp; const struct xfs_dir_ops *dops; + struct xfs_ifork *ifp; xfs_ino_t ino; int i; int i8count; int offset; + int size; + int error; __uint8_t filetype; + ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL); + /* + * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops, + * so we can only trust the mountpoint to have the right pointer. + */ dops = xfs_dir_get_ops(mp, NULL); + ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data; + size = ifp->if_bytes; + /* * Give up if the directory is way too short. */ - XFS_WANT_CORRUPTED_RETURN(mp, size > - offsetof(struct xfs_dir2_sf_hdr, parent)); - XFS_WANT_CORRUPTED_RETURN(mp, size >= - xfs_dir2_sf_hdr_size(sfp->i8count)); + if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) || + size < xfs_dir2_sf_hdr_size(sfp->i8count)) + return -EFSCORRUPTED; endp = (char *)sfp + size; /* Check .. entry */ ino = dops->sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; - XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino)); + error = xfs_dir_ino_validate(mp, ino); + if (error) + return error; offset = dops->data_first_offset; /* Check all reported entries */ @@ -672,12 +685,12 @@ xfs_dir2_sf_verify( * Check the fixed-offset parts of the structure are * within the data buffer. */ - XFS_WANT_CORRUPTED_RETURN(mp, - ((char *)sfep + sizeof(*sfep)) < endp); + if (((char *)sfep + sizeof(*sfep)) >= endp) + return -EFSCORRUPTED; /* Don't allow names with known bad length. */ - XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0); - XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN); + if (sfep->namelen == 0) + return -EFSCORRUPTED; /* * Check that the variable-length part of the structure is @@ -685,33 +698,39 @@ xfs_dir2_sf_verify( * name component, so nextentry is an acceptable test. */ next_sfep = dops->sf_nextentry(sfp, sfep); - XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep); + if (endp < (char *)next_sfep) + return -EFSCORRUPTED; /* Check that the offsets always increase. */ - XFS_WANT_CORRUPTED_RETURN(mp, - xfs_dir2_sf_get_offset(sfep) >= offset); + if (xfs_dir2_sf_get_offset(sfep) < offset) + return -EFSCORRUPTED; /* Check the inode number. */ ino = dops->sf_get_ino(sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; - XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino)); + error = xfs_dir_ino_validate(mp, ino); + if (error) + return error; /* Check the file type. */ filetype = dops->sf_get_ftype(sfep); - XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX); + if (filetype >= XFS_DIR3_FT_MAX) + return -EFSCORRUPTED; offset = xfs_dir2_sf_get_offset(sfep) + dops->data_entsize(sfep->namelen); sfep = next_sfep; } - XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count); - XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp); + if (i8count != sfp->i8count) + return -EFSCORRUPTED; + if ((void *)sfep != (void *)endp) + return -EFSCORRUPTED; /* Make sure this whole thing ought to be in local format. */ - XFS_WANT_CORRUPTED_RETURN(mp, offset + - (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + - (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize); + if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + + (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize) + return -EFSCORRUPTED; return 0; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 9653e964eda4..8a37efe04de3 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -212,6 +212,16 @@ xfs_iformat_fork( if (error) return error; + /* Check inline dir contents. */ + if (S_ISDIR(VFS_I(ip)->i_mode) && + dip->di_format == XFS_DINODE_FMT_LOCAL) { + error = xfs_dir2_sf_verify(ip); + if (error) { + xfs_idestroy_fork(ip, XFS_DATA_FORK); + return error; + } + } + if (xfs_is_reflink_inode(ip)) { ASSERT(ip->i_cowfp == NULL); xfs_ifork_init_cow(ip); @@ -322,8 +332,6 @@ xfs_iformat_local( int whichfork, int size) { - int error; - /* * If the size is unreasonable, then something * is wrong and we just bail out rather than crash in @@ -339,14 +347,6 @@ xfs_iformat_local( return -EFSCORRUPTED; } - if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) { - error = xfs_dir2_sf_verify(ip->i_mount, - (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip), - size); - if (error) - return error; - } - xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size); return 0; } @@ -867,7 +867,7 @@ xfs_iextents_copy( * In these cases, the format always takes precedence, because the * format indicates the current state of the fork. */ -int +void xfs_iflush_fork( xfs_inode_t *ip, xfs_dinode_t *dip, @@ -877,7 +877,6 @@ xfs_iflush_fork( char *cp; xfs_ifork_t *ifp; xfs_mount_t *mp; - int error; static const short brootflag[2] = { XFS_ILOG_DBROOT, XFS_ILOG_ABROOT }; static const short dataflag[2] = @@ -886,7 +885,7 @@ xfs_iflush_fork( { XFS_ILOG_DEXT, XFS_ILOG_AEXT }; if (!iip) - return 0; + return; ifp = XFS_IFORK_PTR(ip, whichfork); /* * This can happen if we gave up in iformat in an error path, @@ -894,19 +893,12 @@ xfs_iflush_fork( */ if (!ifp) { ASSERT(whichfork == XFS_ATTR_FORK); - return 0; + return; } cp = XFS_DFORK_PTR(dip, whichfork); mp = ip->i_mount; switch (XFS_IFORK_FORMAT(ip, whichfork)) { case XFS_DINODE_FMT_LOCAL: - if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) { - error = xfs_dir2_sf_verify(mp, - (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data, - ifp->if_bytes); - if (error) - return error; - } if ((iip->ili_fields & dataflag[whichfork]) && (ifp->if_bytes > 0)) { ASSERT(ifp->if_u1.if_data != NULL); @@ -959,7 +951,6 @@ xfs_iflush_fork( ASSERT(0); break; } - return 0; } /* diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 132dc59fdde6..7fb8365326d1 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -140,7 +140,7 @@ typedef struct xfs_ifork { struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state); int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *); -int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, +void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_inode *, int); void xfs_idata_realloc(struct xfs_inode *, int, int); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 8b75dcea5966..828532ce0adc 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1311,8 +1311,16 @@ xfs_free_file_space( /* * Now that we've unmap all full blocks we'll have to zero out any * partial block at the beginning and/or end. xfs_zero_range is - * smart enough to skip any holes, including those we just created. + * smart enough to skip any holes, including those we just created, + * but we must take care not to zero beyond EOF and enlarge i_size. */ + + if (offset >= XFS_ISIZE(ip)) + return 0; + + if (offset + len > XFS_ISIZE(ip)) + len = XFS_ISIZE(ip) - offset; + return xfs_zero_range(ip, offset, len, NULL); } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c7fe2c2123ab..7605d8396596 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -50,6 +50,7 @@ #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_reflink.h" +#include "xfs_dir2_priv.h" kmem_zone_t *xfs_inode_zone; @@ -3475,7 +3476,6 @@ xfs_iflush_int( struct xfs_inode_log_item *iip = ip->i_itemp; struct xfs_dinode *dip; struct xfs_mount *mp = ip->i_mount; - int error; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); ASSERT(xfs_isiflocked(ip)); @@ -3547,6 +3547,12 @@ xfs_iflush_int( if (ip->i_d.di_version < 3) ip->i_d.di_flushiter++; + /* Check the inline directory data. */ + if (S_ISDIR(VFS_I(ip)->i_mode) && + ip->i_d.di_format == XFS_DINODE_FMT_LOCAL && + xfs_dir2_sf_verify(ip)) + goto corrupt_out; + /* * Copy the dirty parts of the inode into the on-disk inode. We always * copy out the core of the inode, because if the inode is dirty at all @@ -3558,14 +3564,9 @@ xfs_iflush_int( if (ip->i_d.di_flushiter == DI_MAX_FLUSH) ip->i_d.di_flushiter = 0; - error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); - if (error) - return error; - if (XFS_IFORK_Q(ip)) { - error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); - if (error) - return error; - } + xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); + if (XFS_IFORK_Q(ip)) + xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); xfs_inobp_check(mp, bp); /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 229cc6a6d8ef..ebfc13350f9a 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -516,6 +516,20 @@ xfs_vn_getattr( stat->blocks = XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks); + if (ip->i_d.di_version == 3) { + if (request_mask & STATX_BTIME) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = ip->i_d.di_crtime.t_sec; + stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec; + } + } + + if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (ip->i_d.di_flags & XFS_DIFLAG_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP) + stat->attributes |= STATX_ATTR_NODUMP; switch (inode->i_mode & S_IFMT) { case S_IFBLK: diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 2a6d9b1558e0..26d67ce3c18d 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -583,7 +583,7 @@ xfs_inumbers( return error; bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer))); - buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP); + buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP); do { struct xfs_inobt_rec_incore r; int stat; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7cdfe167074f..143db9c523e2 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -261,9 +261,9 @@ */ #ifndef RO_AFTER_INIT_DATA #define RO_AFTER_INIT_DATA \ - __start_ro_after_init = .; \ + VMLINUX_SYMBOL(__start_ro_after_init) = .; \ *(.data..ro_after_init) \ - __end_ro_after_init = .; + VMLINUX_SYMBOL(__end_ro_after_init) = .; #endif /* diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 1d4f365d8f03..f6d9af3efa45 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -166,6 +166,16 @@ static inline struct ahash_instance *ahash_alloc_instance( return crypto_alloc_instance2(name, alg, ahash_instance_headroom()); } +static inline void ahash_request_complete(struct ahash_request *req, int err) +{ + req->base.complete(&req->base, err); +} + +static inline u32 ahash_request_flags(struct ahash_request *req) +{ + return req->base.flags; +} + static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index b72dd2ad5f44..c0b3d999c266 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -295,6 +295,7 @@ void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu); void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_vgic_map_resources(struct kvm *kvm); int kvm_vgic_hyp_init(void); +void kvm_vgic_init_cpu_hardware(void); int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, bool level); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b296a9006117..9382c5da7a2e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -51,6 +51,7 @@ struct blk_mq_hw_ctx { atomic_t nr_active; + struct delayed_work delayed_run_work; struct delayed_work delay_work; struct hlist_node cpuhp_dead; @@ -238,6 +239,7 @@ void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); +void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5a7da607ca04..01a696b0a4d3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -610,7 +610,6 @@ struct request_queue { #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DAX 26 /* device supports DAX */ #define QUEUE_FLAG_STATS 27 /* track rq completion times */ -#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -1673,12 +1672,36 @@ static inline bool bios_segs_mergeable(struct request_queue *q, return true; } -static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, - struct bio *next) +static inline bool bio_will_gap(struct request_queue *q, + struct request *prev_rq, + struct bio *prev, + struct bio *next) { if (bio_has_data(prev) && queue_virt_boundary(q)) { struct bio_vec pb, nb; + /* + * don't merge if the 1st bio starts with non-zero + * offset, otherwise it is quite difficult to respect + * sg gap limit. We work hard to merge a huge number of small + * single bios in case of mkfs. + */ + if (prev_rq) + bio_get_first_bvec(prev_rq->bio, &pb); + else + bio_get_first_bvec(prev, &pb); + if (pb.bv_offset) + return true; + + /* + * We don't need to worry about the situation that the + * merged segment ends in unaligned virt boundary: + * + * - if 'pb' ends aligned, the merged segment ends aligned + * - if 'pb' ends unaligned, the next bio must include + * one single bvec of 'nb', otherwise the 'nb' can't + * merge with 'pb' + */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); @@ -1691,12 +1714,12 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { - return bio_will_gap(req->q, req->biotail, bio); + return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { - return bio_will_gap(req->q, bio, req->bio); + return bio_will_gap(req->q, NULL, bio, req->bio); } int kblockd_schedule_work(struct work_struct *work); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f6b43fbb141c..af9c86e958bd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -570,6 +570,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline void cgroup_init_kthreadd(void) +{ + /* + * kthreadd is inherited by all kthreads, keep it in the root so + * that the new kthreads are guaranteed to stay in the root until + * initialization is finished. + */ + current->no_cgroup_migration = 1; +} + +static inline void cgroup_kthread_ready(void) +{ + /* + * This kthread finished initialization. The creator should have + * set PF_NO_SETAFFINITY if this kthread should stay in the root. + */ + current->no_cgroup_migration = 0; +} + #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -590,6 +609,8 @@ static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } +static inline void cgroup_init_kthreadd(void) {} +static inline void cgroup_kthread_ready(void) {} static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index aebecc4ed088..22d39e8d4de1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -211,7 +211,7 @@ extern ssize_t elv_iosched_show(struct request_queue *, char *); extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); -extern void elevator_exit(struct elevator_queue *); +extern void elevator_exit(struct request_queue *, struct elevator_queue *); extern int elevator_change(struct request_queue *, const char *); extern bool elv_bio_merge_ok(struct request *, struct bio *); extern struct elevator_queue *elevator_alloc(struct request_queue *, diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index eafc965b3eb8..dc30f3d057eb 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -96,6 +96,9 @@ #define GICH_MISR_EOI (1 << 0) #define GICH_MISR_U (1 << 1) +#define GICV_PMR_PRIORITY_SHIFT 3 +#define GICV_PMR_PRIORITY_MASK (0x1f << GICV_PMR_PRIORITY_SHIFT) + #ifndef __ASSEMBLY__ #include <linux/irqdomain.h> diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 7a01c94496f1..3eef9fb9968a 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -35,10 +35,11 @@ * Max bus-specific overhead incurred by request/responses. * I2C requires 1 additional byte for requests. * I2C requires 2 additional bytes for responses. + * SPI requires up to 32 additional bytes for responses. * */ #define EC_PROTO_VERSION_UNKNOWN 0 #define EC_MAX_REQUEST_OVERHEAD 1 -#define EC_MAX_RESPONSE_OVERHEAD 2 +#define EC_MAX_RESPONSE_OVERHEAD 32 /* * Command interface between EC and AP, for LPC, I2C and SPI interfaces. diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index aab032a6ae61..97ca105347a6 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -53,7 +53,7 @@ struct sdio_func { unsigned int state; /* function state */ #define SDIO_STATE_PRESENT (1<<0) /* present in sysfs */ - u8 tmpbuf[4]; /* DMA:able scratch buffer */ + u8 *tmpbuf; /* DMA:able scratch buffer */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 51891fb0d3ce..c91b3bcd158f 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -394,18 +394,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) ___pud; \ }) -#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \ -({ \ - unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ - pmd_t ___pmd; \ - \ - ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \ - mmu_notifier_invalidate_range(__mm, ___haddr, \ - ___haddr + HPAGE_PMD_SIZE); \ - \ - ___pmd; \ -}) - /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU @@ -489,7 +477,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush -#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c43d435d4225..9061780b141f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -64,26 +64,26 @@ enum { * RDMA_QPTYPE field */ enum { - NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */ - NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */ + NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */ + NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */ }; /* RDMA QP Service Type codes for Discovery Log Page entry TSAS * RDMA_QPTYPE field */ enum { - NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */ - NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */ - NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */ - NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */ - NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */ + NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */ + NVMF_RDMA_PRTYPE_IB = 2, /* InfiniBand */ + NVMF_RDMA_PRTYPE_ROCE = 3, /* InfiniBand RoCE */ + NVMF_RDMA_PRTYPE_ROCEV2 = 4, /* InfiniBand RoCEV2 */ + NVMF_RDMA_PRTYPE_IWARP = 5, /* IWARP */ }; /* RDMA Connection Management Service Type codes for Discovery Log Page * entry TSAS RDMA_CMS field */ enum { - NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */ + NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */ }; #define NVMF_AQ_DEPTH 32 diff --git a/include/linux/phy.h b/include/linux/phy.h index 43a774873aa9..fb3857337151 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -852,6 +852,7 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); +void phy_trigger_machine(struct phy_device *phydev, bool sync); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); int phy_ethtool_ksettings_get(struct phy_device *phydev, diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 8ce2d87a238b..5e45385c5bdc 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -145,8 +145,9 @@ struct pinctrl_desc { extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data, struct pinctrl_dev **pctldev); +extern int pinctrl_enable(struct pinctrl_dev *pctldev); -/* Please use pinctrl_register_and_init() instead */ +/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */ extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data); diff --git a/include/linux/reset.h b/include/linux/reset.h index 96fb139bdd08..13d8681210d5 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -15,6 +15,9 @@ int reset_control_status(struct reset_control *rstc); struct reset_control *__of_reset_control_get(struct device_node *node, const char *id, int index, bool shared, bool optional); +struct reset_control *__reset_control_get(struct device *dev, const char *id, + int index, bool shared, + bool optional); void reset_control_put(struct reset_control *rstc); struct reset_control *__devm_reset_control_get(struct device *dev, const char *id, int index, bool shared, @@ -72,6 +75,13 @@ static inline struct reset_control *__of_reset_control_get( return optional ? NULL : ERR_PTR(-ENOTSUPP); } +static inline struct reset_control *__reset_control_get( + struct device *dev, const char *id, + int index, bool shared, bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + static inline struct reset_control *__devm_reset_control_get( struct device *dev, const char *id, int index, bool shared, bool optional) @@ -102,8 +112,7 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id) #ifndef CONFIG_RESET_CONTROLLER WARN_ON(1); #endif - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false, - false); + return __reset_control_get(dev, id, 0, false, false); } /** @@ -131,22 +140,19 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id) static inline struct reset_control *reset_control_get_shared( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true, - false); + return __reset_control_get(dev, id, 0, true, false); } static inline struct reset_control *reset_control_get_optional_exclusive( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false, - true); + return __reset_control_get(dev, id, 0, false, true); } static inline struct reset_control *reset_control_get_optional_shared( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true, - true); + return __reset_control_get(dev, id, 0, true, true); } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index d67eee84fd43..4cf9a59a4d08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -604,6 +604,10 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif +#ifdef CONFIG_CGROUPS + /* disallow userland-initiated cgroup migration */ + unsigned no_cgroup_migration:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ diff --git a/include/linux/stat.h b/include/linux/stat.h index c76e524fb34b..64b6b3aece21 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -26,6 +26,7 @@ struct kstat { unsigned int nlink; uint32_t blksize; /* Preferred I/O size */ u64 attributes; + u64 attributes_mask; #define KSTAT_ATTR_FS_IOC_FLAGS \ (STATX_ATTR_COMPRESSED | \ STATX_ATTR_IMMUTABLE | \ diff --git a/include/linux/uio.h b/include/linux/uio.h index 804e34c6f981..f2d36a3d3005 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -39,7 +39,10 @@ struct iov_iter { }; union { unsigned long nr_segs; - int idx; + struct { + int idx; + int start_idx; + }; }; }; @@ -81,6 +84,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); +void iov_iter_revert(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 04b0d3f95043..7edfbdb55a99 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -167,6 +167,7 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; + int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); void (*remove)(struct virtio_device *dev); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 1f71ee5ab518..069582ee5d7f 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -448,10 +448,9 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu) return frag; } -static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc) +static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc) { - - sctp_assoc_sync_pmtu(sk, asoc); + sctp_assoc_sync_pmtu(asoc); asoc->pmtu_pending = 0; } @@ -596,12 +595,23 @@ static inline void sctp_v4_map_v6(union sctp_addr *addr) */ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t) { - if (t->dst && (!dst_check(t->dst, t->dst_cookie) || - t->pathmtu != max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)), - SCTP_DEFAULT_MINSEGMENT))) + if (t->dst && !dst_check(t->dst, t->dst_cookie)) sctp_transport_dst_release(t); return t->dst; } +static inline bool sctp_transport_pmtu_check(struct sctp_transport *t) +{ + __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)), + SCTP_DEFAULT_MINSEGMENT); + + if (t->pathmtu == pmtu) + return true; + + t->pathmtu = pmtu; + + return false; +} + #endif /* __net_sctp_h__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 592decebac75..138f8615acf0 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -377,7 +377,8 @@ typedef struct sctp_sender_hb_info { __u64 hb_nonce; } sctp_sender_hb_info_t; -struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp); +int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp); +int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); @@ -499,7 +500,6 @@ struct sctp_datamsg { /* Did the messenge fail to send? */ int send_error; u8 send_failed:1, - force_delay:1, can_delay; /* should this message be Nagle delayed */ }; @@ -952,8 +952,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t); void sctp_transport_burst_limited(struct sctp_transport *); void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); -void sctp_transport_reset(struct sctp_transport *); -void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32); +void sctp_transport_reset(struct sctp_transport *t); +void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); @@ -1878,6 +1878,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ + force_delay:1, prsctp_enable:1, reconf_enable:1; @@ -1953,7 +1954,7 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); -void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); +void sctp_assoc_sync_pmtu(struct sctp_association *asoc); void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); void sctp_assoc_set_primary(struct sctp_association *, diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 4b784b6e21c0..ccfad0e9c2cd 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -117,6 +117,7 @@ enum transport_state_table { TRANSPORT_ISTATE_PROCESSING = 11, TRANSPORT_COMPLETE_QF_WP = 18, TRANSPORT_COMPLETE_QF_OK = 19, + TRANSPORT_COMPLETE_QF_ERR = 20, }; /* Used for struct se_cmd->se_cmd_flags */ @@ -279,8 +280,6 @@ struct t10_alua_tg_pt_gp { u16 tg_pt_gp_id; int tg_pt_gp_valid_id; int tg_pt_gp_alua_supported_states; - int tg_pt_gp_alua_pending_state; - int tg_pt_gp_alua_previous_state; int tg_pt_gp_alua_access_status; int tg_pt_gp_alua_access_type; int tg_pt_gp_nonop_delay_msecs; @@ -289,18 +288,16 @@ struct t10_alua_tg_pt_gp { int tg_pt_gp_pref; int tg_pt_gp_write_metadata; u32 tg_pt_gp_members; - atomic_t tg_pt_gp_alua_access_state; + int tg_pt_gp_alua_access_state; atomic_t tg_pt_gp_ref_cnt; spinlock_t tg_pt_gp_lock; - struct mutex tg_pt_gp_md_mutex; + struct mutex tg_pt_gp_transition_mutex; struct se_device *tg_pt_gp_dev; struct config_group tg_pt_gp_group; struct list_head tg_pt_gp_list; struct list_head tg_pt_gp_lun_list; struct se_lun *tg_pt_gp_alua_lun; struct se_node_acl *tg_pt_gp_alua_nacl; - struct work_struct tg_pt_gp_transition_work; - struct completion *tg_pt_gp_transition_complete; }; struct t10_vpd { @@ -705,6 +702,7 @@ struct se_lun { u64 unpacked_lun; #define SE_LUN_LINK_MAGIC 0xffff7771 u32 lun_link_magic; + bool lun_shutdown; bool lun_access_ro; u32 lun_index; diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index dd9820b1c779..f8d9fed17ba9 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -445,6 +445,7 @@ header-y += unistd.h header-y += unix_diag.h header-y += usbdevice_fs.h header-y += usbip.h +header-y += userio.h header-y += utime.h header-y += utsname.h header-y += uuid.h diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index 85bbb1799df3..d496c02e14bc 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -35,7 +35,7 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 -#define RTF_PCPU 0x40000000 +#define RTF_PCPU 0x40000000 /* read-only: can not be set by user */ #define RTF_LOCAL 0x80000000 diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 51a6b86e3700..17b10304c393 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -48,17 +48,13 @@ * tv_sec holds the number of seconds before (negative) or after (positive) * 00:00:00 1st January 1970 UTC. * - * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is - * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time. - * - * Note that if both tv_sec and tv_nsec are non-zero, then the two values must - * either be both positive or both negative. + * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time. * * __reserved is held in case we need a yet finer resolution. */ struct statx_timestamp { __s64 tv_sec; - __s32 tv_nsec; + __u32 tv_nsec; __s32 __reserved; }; @@ -114,7 +110,7 @@ struct statx { __u64 stx_ino; /* Inode number */ __u64 stx_size; /* File size */ __u64 stx_blocks; /* Number of 512-byte blocks allocated */ - __u64 __spare1[1]; + __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */ /* 0x40 */ struct statx_timestamp stx_atime; /* Last access time */ struct statx_timestamp stx_btime; /* File creation time */ @@ -152,9 +148,10 @@ struct statx { #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_ALL 0x00000fffU /* All currently supported flags */ +#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ /* - * Attributes to be found in stx_attributes + * Attributes to be found in stx_attributes and masked in stx_attributes_mask. * * These give information about the features or the state of a file that might * be of use to ordinary userspace programs such as GUIs or ls rather than diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 15b4385a2be1..90007a1abcab 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -79,7 +79,7 @@ * configuration space */ #define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20) /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */ -#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled) +#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled) /* Virtio ABI version, this must match exactly */ #define VIRTIO_PCI_ABI_VERSION 0 diff --git a/kernel/audit.c b/kernel/audit.c index 2f4964cfde0b..a871bf80fde1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -160,7 +160,6 @@ static LIST_HEAD(audit_freelist); /* queue msgs to send via kauditd_task */ static struct sk_buff_head audit_queue; -static void kauditd_hold_skb(struct sk_buff *skb); /* queue msgs due to temporary unicast send problems */ static struct sk_buff_head audit_retry_queue; /* queue msgs waiting for new auditd connection */ @@ -454,30 +453,6 @@ static void auditd_set(int pid, u32 portid, struct net *net) } /** - * auditd_reset - Disconnect the auditd connection - * - * Description: - * Break the auditd/kauditd connection and move all the queued records into the - * hold queue in case auditd reconnects. - */ -static void auditd_reset(void) -{ - struct sk_buff *skb; - - /* if it isn't already broken, break the connection */ - rcu_read_lock(); - if (auditd_conn.pid) - auditd_set(0, 0, NULL); - rcu_read_unlock(); - - /* flush all of the main and retry queues to the hold queue */ - while ((skb = skb_dequeue(&audit_retry_queue))) - kauditd_hold_skb(skb); - while ((skb = skb_dequeue(&audit_queue))) - kauditd_hold_skb(skb); -} - -/** * kauditd_print_skb - Print the audit record to the ring buffer * @skb: audit record * @@ -505,9 +480,6 @@ static void kauditd_rehold_skb(struct sk_buff *skb) { /* put the record back in the queue at the same place */ skb_queue_head(&audit_hold_queue, skb); - - /* fail the auditd connection */ - auditd_reset(); } /** @@ -544,9 +516,6 @@ static void kauditd_hold_skb(struct sk_buff *skb) /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); kfree_skb(skb); - - /* fail the auditd connection */ - auditd_reset(); } /** @@ -567,6 +536,30 @@ static void kauditd_retry_skb(struct sk_buff *skb) } /** + * auditd_reset - Disconnect the auditd connection + * + * Description: + * Break the auditd/kauditd connection and move all the queued records into the + * hold queue in case auditd reconnects. + */ +static void auditd_reset(void) +{ + struct sk_buff *skb; + + /* if it isn't already broken, break the connection */ + rcu_read_lock(); + if (auditd_conn.pid) + auditd_set(0, 0, NULL); + rcu_read_unlock(); + + /* flush all of the main and retry queues to the hold queue */ + while ((skb = skb_dequeue(&audit_retry_queue))) + kauditd_hold_skb(skb); + while ((skb = skb_dequeue(&audit_queue))) + kauditd_hold_skb(skb); +} + +/** * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record * @@ -758,6 +751,7 @@ static int kauditd_thread(void *dummy) NULL, kauditd_rehold_skb); if (rc < 0) { sk = NULL; + auditd_reset(); goto main_queue; } @@ -767,6 +761,7 @@ static int kauditd_thread(void *dummy) NULL, kauditd_hold_skb); if (rc < 0) { sk = NULL; + auditd_reset(); goto main_queue; } @@ -775,16 +770,18 @@ main_queue: * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the * multicast send and move the record to the retry queue */ - kauditd_send_queue(sk, portid, &audit_queue, 1, - kauditd_send_multicast_skb, - kauditd_retry_skb); + rc = kauditd_send_queue(sk, portid, &audit_queue, 1, + kauditd_send_multicast_skb, + kauditd_retry_skb); + if (sk == NULL || rc < 0) + auditd_reset(); + sk = NULL; /* drop our netns reference, no auditd sends past this line */ if (net) { put_net(net); net = NULL; } - sk = NULL; /* we have processed all the queues so wake everyone */ wake_up(&audit_backlog_wait); diff --git a/kernel/audit.h b/kernel/audit.h index 0f1cf6d1878a..0d87f8ab8778 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -333,13 +333,7 @@ extern u32 audit_sig_sid; extern int audit_filter(int msgtype, unsigned int listtype); #ifdef CONFIG_AUDITSYSCALL -extern int __audit_signal_info(int sig, struct task_struct *t); -static inline int audit_signal_info(int sig, struct task_struct *t) -{ - if (auditd_test_task(t) || (audit_signals && !audit_dummy_context())) - return __audit_signal_info(sig, t); - return 0; -} +extern int audit_signal_info(int sig, struct task_struct *t); extern void audit_filter_inodes(struct task_struct *, struct audit_context *); extern struct list_head *audit_killed_trees(void); #else diff --git a/kernel/auditsc.c b/kernel/auditsc.c index e59ffc7fc522..1c2333155893 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2249,26 +2249,27 @@ void __audit_ptrace(struct task_struct *t) * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ -int __audit_signal_info(int sig, struct task_struct *t) +int audit_signal_info(int sig, struct task_struct *t) { struct audit_aux_data_pids *axp; struct task_struct *tsk = current; struct audit_context *ctx = tsk->audit_context; kuid_t uid = current_uid(), t_uid = task_uid(t); - if (auditd_test_task(t)) { - if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { - audit_sig_pid = task_tgid_nr(tsk); - if (uid_valid(tsk->loginuid)) - audit_sig_uid = tsk->loginuid; - else - audit_sig_uid = uid; - security_task_getsecid(tsk, &audit_sig_sid); - } - if (!audit_signals || audit_dummy_context()) - return 0; + if (auditd_test_task(t) && + (sig == SIGTERM || sig == SIGHUP || + sig == SIGUSR1 || sig == SIGUSR2)) { + audit_sig_pid = task_tgid_nr(tsk); + if (uid_valid(tsk->loginuid)) + audit_sig_uid = tsk->loginuid; + else + audit_sig_uid = uid; + security_task_getsecid(tsk, &audit_sig_sid); } + if (!audit_signals || audit_dummy_context()) + return 0; + /* optimize the common case by putting first signal recipient directly * in audit_context */ if (!ctx->target_pid) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f45827e205d3..b4f1cb0c5ac7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1162,12 +1162,12 @@ out: LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ off = IMM; load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are - * only appearing in the programs where ctx == - * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] - * == BPF_R6, bpf_convert_filter() saves it in BPF_R6, - * internal BPF verifier will check that BPF_R6 == - * ctx. + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only + * appearing in the programs where ctx == skb + * (see may_access_skb() in the verifier). All programs + * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6, + * bpf_convert_filter() saves it in BPF_R6, internal BPF + * verifier will check that BPF_R6 == ctx. * * BPF_ABS and BPF_IND are wrappers of function calls, * so they scratch BPF_R1-BPF_R5 registers, preserve diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7af0dcc5d755..821f9e807de5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -617,6 +617,14 @@ static void fixup_bpf_calls(struct bpf_prog *prog) if (insn->imm == BPF_FUNC_xdp_adjust_head) prog->xdp_adjust_head = 1; if (insn->imm == BPF_FUNC_tail_call) { + /* If we tail call into other programs, we + * cannot make any assumptions since they + * can be replaced dynamically during runtime + * in the program array. + */ + prog->cb_access = 1; + prog->xdp_adjust_head = 1; + /* mark bpf_tail_call as different opcode * to avoid conditional branch in * interpeter for every normal call diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 796b68d00119..a834068a400e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -765,38 +765,56 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } } -static int check_ptr_alignment(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, int off, int size) +static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, + int off, int size) { - if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) { - if (off % size != 0) { - verbose("misaligned access off %d size %d\n", - off, size); - return -EACCES; - } else { - return 0; - } - } - - if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) - /* misaligned access to packet is ok on x86,arm,arm64 */ - return 0; - if (reg->id && size != 1) { - verbose("Unknown packet alignment. Only byte-sized access allowed\n"); + verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n"); return -EACCES; } /* skb->data is NET_IP_ALIGN-ed */ - if (reg->type == PTR_TO_PACKET && - (NET_IP_ALIGN + reg->off + off) % size != 0) { + if ((NET_IP_ALIGN + reg->off + off) % size != 0) { verbose("misaligned packet access off %d+%d+%d size %d\n", NET_IP_ALIGN, reg->off, off, size); return -EACCES; } + return 0; } +static int check_val_ptr_alignment(const struct bpf_reg_state *reg, + int size) +{ + if (size != 1) { + verbose("Unknown alignment. Only byte-sized access allowed in value access.\n"); + return -EACCES; + } + + return 0; +} + +static int check_ptr_alignment(const struct bpf_reg_state *reg, + int off, int size) +{ + switch (reg->type) { + case PTR_TO_PACKET: + return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : + check_pkt_ptr_alignment(reg, off, size); + case PTR_TO_MAP_VALUE_ADJ: + return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : + check_val_ptr_alignment(reg, size); + default: + if (off % size != 0) { + verbose("misaligned access off %d size %d\n", + off, size); + return -EACCES; + } + + return 0; + } +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -818,7 +836,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, if (size < 0) return size; - err = check_ptr_alignment(env, reg, off, size); + err = check_ptr_alignment(reg, off, size); if (err) return err; @@ -1925,6 +1943,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * register as unknown. */ if (env->allow_ptr_leaks && + BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD && (dst_reg->type == PTR_TO_MAP_VALUE || dst_reg->type == PTR_TO_MAP_VALUE_ADJ)) dst_reg->type = PTR_TO_MAP_VALUE_ADJ; @@ -1973,14 +1992,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) - regs[i].range = dst_reg->off; + /* keep the maximum range already checked */ + regs[i].range = max(regs[i].range, dst_reg->off); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = dst_reg->off; + reg->range = max(reg->range, dst_reg->off); } } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 48851327a15e..687f5e0194ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2425,11 +2425,12 @@ ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, tsk = tsk->group_leader; /* - * Workqueue threads may acquire PF_NO_SETAFFINITY and become - * trapped in a cpuset, or RT worker may be born in a cgroup - * with no rt_runtime allocated. Just say no. + * kthreads may acquire PF_NO_SETAFFINITY during initialization. + * If userland migrates such a kthread to a non-root cgroup, it can + * become trapped in a cpuset, or RT kthread may be born in a + * cgroup with no rt_runtime allocated. Just say no. */ - if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { + if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out_unlock_rcu; } diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index 4544b115f5eb..e2d356dd7581 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -59,7 +59,7 @@ static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk) struct cpumask * irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) { - int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec; + int n, nodes, cpus_per_vec, extra_vecs, curvec; int affv = nvecs - affd->pre_vectors - affd->post_vectors; int last_affv = affv + affd->pre_vectors; nodemask_t nodemsk = NODE_MASK_NONE; @@ -94,19 +94,21 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) goto done; } - /* Spread the vectors per node */ - vecs_per_node = affv / nodes; - /* Account for rounding errors */ - extra_vecs = affv - (nodes * vecs_per_node); - for_each_node_mask(n, nodemsk) { - int ncpus, v, vecs_to_assign = vecs_per_node; + int ncpus, v, vecs_to_assign, vecs_per_node; + + /* Spread the vectors per node */ + vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n)); /* Calculate the number of cpus per vector */ ncpus = cpumask_weight(nmsk); + vecs_to_assign = min(vecs_per_node, ncpus); + + /* Account for rounding errors */ + extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign); for (v = 0; curvec < last_affv && v < vecs_to_assign; curvec++, v++) { @@ -115,14 +117,14 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) /* Account for extra vectors to compensate rounding errors */ if (extra_vecs) { cpus_per_vec++; - if (!--extra_vecs) - vecs_per_node++; + --extra_vecs; } irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec); } if (curvec >= last_affv) break; + --nodes; } done: diff --git a/kernel/kthread.c b/kernel/kthread.c index 2f26adea0f84..26db528c1d88 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -20,6 +20,7 @@ #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> +#include <linux/cgroup.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); @@ -225,6 +226,7 @@ static int kthread(void *_create) ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { + cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } @@ -538,6 +540,7 @@ int kthreadd(void *unused) set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; + cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index c2b88490d857..c08fbd2f5ba9 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,13 +46,13 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* - * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text, * .data and .bss to fit in required 32MB limit for the kernel. With - * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems. * So, reduce the static allocations for lockdeps related structures so that * everything fits in current required size limit. */ -#ifdef CONFIG_PROVE_LOCKING_SMALL +#ifdef CONFIG_LOCKDEP_SMALL /* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 0af928712174..266ddcc1d8bb 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -184,11 +184,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task) WARN_ON(!task->ptrace || task->parent != current); + /* + * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. + * Recheck state under the lock to close this race. + */ spin_lock_irq(&task->sighand->siglock); - if (__fatal_signal_pending(task)) - wake_up_state(task, __TASK_TRACED); - else - task->state = TASK_TRACED; + if (task->state == __TASK_TRACED) { + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + } spin_unlock_irq(&task->sighand->siglock); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index f3778e2b46c8..aea3135c5d90 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -34,6 +34,18 @@ void disable_sched_clock_irqtime(void) sched_clock_irqtime = 0; } +static void irqtime_account_delta(struct irqtime *irqtime, u64 delta, + enum cpu_usage_stat idx) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + u64_stats_update_begin(&irqtime->sync); + cpustat[idx] += delta; + irqtime->total += delta; + irqtime->tick_delta += delta; + u64_stats_update_end(&irqtime->sync); +} + /* * Called before incrementing preempt_count on {soft,}irq_enter * and before decrementing preempt_count on {soft,}irq_exit. @@ -41,7 +53,6 @@ void disable_sched_clock_irqtime(void) void irqtime_account_irq(struct task_struct *curr) { struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); - u64 *cpustat = kcpustat_this_cpu->cpustat; s64 delta; int cpu; @@ -52,22 +63,16 @@ void irqtime_account_irq(struct task_struct *curr) delta = sched_clock_cpu(cpu) - irqtime->irq_start_time; irqtime->irq_start_time += delta; - u64_stats_update_begin(&irqtime->sync); /* * We do not account for softirq time from ksoftirqd here. * We want to continue accounting softirq time to ksoftirqd thread * in that case, so as not to confuse scheduler with a special task * that do not consume any time, but still wants to run. */ - if (hardirq_count()) { - cpustat[CPUTIME_IRQ] += delta; - irqtime->tick_delta += delta; - } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) { - cpustat[CPUTIME_SOFTIRQ] += delta; - irqtime->tick_delta += delta; - } - - u64_stats_update_end(&irqtime->sync); + if (hardirq_count()) + irqtime_account_delta(irqtime, delta, CPUTIME_IRQ); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ); } EXPORT_SYMBOL_GPL(irqtime_account_irq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5cbf92214ad8..767aab3505a8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1869,6 +1869,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { } #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { + u64 total; u64 tick_delta; u64 irq_start_time; struct u64_stats_sync sync; @@ -1876,16 +1877,20 @@ struct irqtime { DECLARE_PER_CPU(struct irqtime, cpu_irqtime); +/* + * Returns the irqtime minus the softirq time computed by ksoftirqd. + * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime + * and never move forward. + */ static inline u64 irq_time_read(int cpu) { struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu); - u64 *cpustat = kcpustat_cpu(cpu).cpustat; unsigned int seq; u64 total; do { seq = __u64_stats_fetch_begin(&irqtime->sync); - total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ]; + total = irqtime->total; } while (__u64_stats_fetch_retry(&irqtime->sync, seq)); return total; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index acf0a5a06da7..8c8714fcb53c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2133,9 +2133,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, if (write) { if (*negp) return -EINVAL; + if (*lvalp > UINT_MAX) + return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; + *negp = false; *lvalp = (unsigned long)val; } return 0; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b9691ee8f6c1..dd3e91d68dc7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3755,23 +3755,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) ftrace_probe_registered = 1; } -static void __disable_ftrace_function_probe(void) +static bool __disable_ftrace_function_probe(void) { int i; if (!ftrace_probe_registered) - return; + return false; for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; if (hhd->first) - return; + return false; } /* no more funcs left */ ftrace_shutdown(&trace_probe_ops, 0); ftrace_probe_registered = 0; + return true; } @@ -3901,6 +3902,7 @@ static void __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { + struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; struct ftrace_func_probe *p; @@ -3912,6 +3914,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int i, ret; + bool disabled; if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) func_g.search = NULL; @@ -3930,6 +3933,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) /* Hmm, should report this somehow */ @@ -3967,12 +3974,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } } mutex_lock(&ftrace_lock); - __disable_ftrace_function_probe(); + disabled = __disable_ftrace_function_probe(); /* * Remove after the disable is called. Otherwise, if the last * probe is removed, a null hash means *all enabled*. */ ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + /* still need to update the function call sites */ + if (ftrace_enabled && !disabled) + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, + &old_hash_ops); synchronize_sched(); if (!ret) free_ftrace_hash_rcu(old_hash); @@ -5554,6 +5566,15 @@ static void clear_ftrace_pids(struct trace_array *tr) trace_free_pid_list(pid_list); } +void ftrace_clear_pids(struct trace_array *tr) +{ + mutex_lock(&ftrace_lock); + + clear_ftrace_pids(tr); + + mutex_unlock(&ftrace_lock); +} + static void ftrace_pid_reset(struct trace_array *tr) { mutex_lock(&ftrace_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 96fc3c043ad6..ca47a4fa2986 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3405,11 +3405,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -4826,9 +4838,9 @@ static __init int test_ringbuffer(void) rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], "rbtester/%d", cpu); - if (WARN_ON(!rb_threads[cpu])) { + if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_threads[cpu]); goto out_free; } @@ -4838,9 +4850,9 @@ static __init int test_ringbuffer(void) /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); - if (WARN_ON(!rb_hammer)) { + if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_hammer); goto out_free; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f35109514a01..0ad75e9698f6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6733,11 +6733,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, ops, count); + out: return ret < 0 ? ret : 0; } @@ -7402,6 +7404,7 @@ static int instance_rmdir(const char *name) tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove_recursive(tr->dir); free_trace_buffers(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ae1cce91fead..d19d52d600d6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -896,6 +896,7 @@ int using_ftrace_ops_list_func(void); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_clear_pids(struct trace_array *tr); #else static inline int ftrace_trace_task(struct trace_array *tr) { @@ -914,6 +915,7 @@ ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_clear_pids(struct trace_array *tr) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 97d62c2da6c2..fa16c0f82d6e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1103,9 +1103,6 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.txt. -config PROVE_LOCKING_SMALL - bool - config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT @@ -1114,6 +1111,9 @@ config LOCKDEP select KALLSYMS select KALLSYMS_ALL +config LOCKDEP_SMALL + bool + config LOCK_STAT bool "Lock usage statistics" depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e68604ae3ced..cc001a542cb5 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -786,6 +786,68 @@ void iov_iter_advance(struct iov_iter *i, size_t size) } EXPORT_SYMBOL(iov_iter_advance); +void iov_iter_revert(struct iov_iter *i, size_t unroll) +{ + if (!unroll) + return; + i->count += unroll; + if (unlikely(i->type & ITER_PIPE)) { + struct pipe_inode_info *pipe = i->pipe; + int idx = i->idx; + size_t off = i->iov_offset; + while (1) { + size_t n = off - pipe->bufs[idx].offset; + if (unroll < n) { + off -= unroll; + break; + } + unroll -= n; + if (!unroll && idx == i->start_idx) { + off = 0; + break; + } + if (!idx--) + idx = pipe->buffers - 1; + off = pipe->bufs[idx].offset + pipe->bufs[idx].len; + } + i->iov_offset = off; + i->idx = idx; + pipe_truncate(i); + return; + } + if (unroll <= i->iov_offset) { + i->iov_offset -= unroll; + return; + } + unroll -= i->iov_offset; + if (i->type & ITER_BVEC) { + const struct bio_vec *bvec = i->bvec; + while (1) { + size_t n = (--bvec)->bv_len; + i->nr_segs++; + if (unroll <= n) { + i->bvec = bvec; + i->iov_offset = n - unroll; + return; + } + unroll -= n; + } + } else { /* same logics for iovec and kvec */ + const struct iovec *iov = i->iov; + while (1) { + size_t n = (--iov)->iov_len; + i->nr_segs++; + if (unroll <= n) { + i->iov = iov; + i->iov_offset = n - unroll; + return; + } + unroll -= n; + } + } +} +EXPORT_SYMBOL(iov_iter_revert); + /* * Return the count of just the current iov_iter segment. */ @@ -839,6 +901,7 @@ void iov_iter_pipe(struct iov_iter *i, int direction, i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); i->iov_offset = 0; i->count = count; + i->start_idx = i->idx; } EXPORT_SYMBOL(iov_iter_pipe); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1ebc93e179f3..f3c4f9d22821 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -240,18 +240,18 @@ static ssize_t defrag_store(struct kobject *kobj, clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("defer+madvise", buf, min(sizeof("defer+madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("defer", buf, + min(sizeof("defer")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("madvise", buf, min(sizeof("madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); @@ -1568,8 +1568,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, deactivate_page(page); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { - orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, - tlb->fullmm); + pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); @@ -1724,37 +1723,69 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; - int ret = 0; + pmd_t entry; + bool preserve_write; + int ret; ptl = __pmd_trans_huge_lock(pmd, vma); - if (ptl) { - pmd_t entry; - bool preserve_write = prot_numa && pmd_write(*pmd); - ret = 1; + if (!ptl) + return 0; - /* - * Avoid trapping faults against the zero page. The read-only - * data is likely to be read-cached on the local CPU and - * local/remote hits to the zero page are not interesting. - */ - if (prot_numa && is_huge_zero_pmd(*pmd)) { - spin_unlock(ptl); - return ret; - } + preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; - if (!prot_numa || !pmd_protnone(*pmd)) { - entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd); - entry = pmd_modify(entry, newprot); - if (preserve_write) - entry = pmd_mk_savedwrite(entry); - ret = HPAGE_PMD_NR; - set_pmd_at(mm, addr, pmd, entry); - BUG_ON(vma_is_anonymous(vma) && !preserve_write && - pmd_write(entry)); - } - spin_unlock(ptl); - } + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) + goto unlock; + + if (prot_numa && pmd_protnone(*pmd)) + goto unlock; + + /* + * In case prot_numa, we are under down_read(mmap_sem). It's critical + * to not clear pmd intermittently to avoid race with MADV_DONTNEED + * which is also under down_read(mmap_sem): + * + * CPU0: CPU1: + * change_huge_pmd(prot_numa=1) + * pmdp_huge_get_and_clear_notify() + * madvise_dontneed() + * zap_pmd_range() + * pmd_trans_huge(*pmd) == 0 (without ptl) + * // skip the pmd + * set_pmd_at(); + * // pmd is re-established + * + * The race makes MADV_DONTNEED miss the huge pmd and don't clear it + * which may break userspace. + * + * pmdp_invalidate() is required to make sure we don't miss + * dirty/young flags set by hardware. + */ + entry = *pmd; + pmdp_invalidate(vma, addr, pmd); + /* + * Recover dirty/young flags. It relies on pmdp_invalidate to not + * corrupt them. + */ + if (pmd_dirty(*pmd)) + entry = pmd_mkdirty(entry); + if (pmd_young(*pmd)) + entry = pmd_mkyoung(entry); + + entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mk_savedwrite(entry); + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); +unlock: + spin_unlock(ptl); return ret; } diff --git a/mm/internal.h b/mm/internal.h index ccfc2a2969f4..266efaeaa370 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -481,6 +481,13 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, enum ttu_flags; struct tlbflush_unmap_batch; + +/* + * only for MM internal work items which do not depend on + * any allocations or locks which might depend on allocations + */ +extern struct workqueue_struct *mm_percpu_wq; + #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 75b2745bac41..37d0b334bfe9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1529,7 +1529,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); @@ -1538,14 +1537,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(bm, nmask, nr_bits); + if (compat_get_bitmap(bm, nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, bm, alloc_size); + if (copy_to_user(nm, bm, alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_set_mempolicy(mode, nm, nr_bits+1); } @@ -1553,7 +1551,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; @@ -1562,14 +1559,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits); + if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, nodes_addr(bm), alloc_size); + if (copy_to_user(nm, nodes_addr(bm), alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_mbind(start, len, mode, nm, nr_bits+1, flags); } diff --git a/mm/migrate.c b/mm/migrate.c index ed97c2c14fa8..738f1d5f8350 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -184,9 +184,9 @@ void putback_movable_pages(struct list_head *l) unlock_page(page); put_page(page); } else { - putback_lru_page(page); dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); + putback_lru_page(page); } } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6cbde310abed..07efbc3a8656 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1090,10 +1090,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - unsigned long nr_scanned, flags; + unsigned long nr_scanned; bool isolated_pageblocks; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) @@ -1142,7 +1142,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, trace_mm_page_pcpu_drain(page, 0, mt); } while (--count && --batch_free && !list_empty(list)); } - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, @@ -1150,9 +1150,8 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { - unsigned long nr_scanned, flags; - spin_lock_irqsave(&zone->lock, flags); - __count_vm_events(PGFREE, 1 << order); + unsigned long nr_scanned; + spin_lock(&zone->lock); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); @@ -1162,7 +1161,7 @@ static void free_one_page(struct zone *zone, migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1240,6 +1239,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) static void __free_pages_ok(struct page *page, unsigned int order) { + unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); @@ -1247,7 +1247,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) return; migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); + __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype); + local_irq_restore(flags); } static void __init __free_pages_boot_core(struct page *page, unsigned int order) @@ -2219,9 +2222,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, int migratetype, bool cold) { int i, alloced = 0; - unsigned long flags; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); if (unlikely(page == NULL)) @@ -2257,7 +2259,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); return alloced; } @@ -2373,6 +2375,13 @@ void drain_all_pages(struct zone *zone) */ static cpumask_t cpus_with_pcps; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON_ONCE(!mm_percpu_wq)) + return; + /* Workqueues cannot recurse */ if (current->flags & PF_WQ_WORKER) return; @@ -2422,7 +2431,7 @@ void drain_all_pages(struct zone *zone) for_each_cpu(cpu, &cpus_with_pcps) { struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); INIT_WORK(work, drain_local_pages_wq); - schedule_work_on(cpu, work); + queue_work_on(cpu, mm_percpu_wq, work); } for_each_cpu(cpu, &cpus_with_pcps) flush_work(per_cpu_ptr(&pcpu_drain, cpu)); @@ -2478,20 +2487,17 @@ void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; + unsigned long flags; unsigned long pfn = page_to_pfn(page); int migratetype; - if (in_interrupt()) { - __free_pages_ok(page, 0); - return; - } - if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); set_pcppage_migratetype(page, migratetype); - preempt_disable(); + local_irq_save(flags); + __count_vm_event(PGFREE); /* * We only track unmovable, reclaimable and movable on pcp lists. @@ -2508,7 +2514,6 @@ void free_hot_cold_page(struct page *page, bool cold) migratetype = MIGRATE_MOVABLE; } - __count_vm_event(PGFREE); pcp = &this_cpu_ptr(zone->pageset)->pcp; if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); @@ -2522,7 +2527,7 @@ void free_hot_cold_page(struct page *page, bool cold) } out: - preempt_enable(); + local_irq_restore(flags); } /* @@ -2647,8 +2652,6 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, { struct page *page; - VM_BUG_ON(in_interrupt()); - do { if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, @@ -2679,8 +2682,9 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; bool cold = ((gfp_flags & __GFP_COLD) != 0); struct page *page; + unsigned long flags; - preempt_disable(); + local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list); @@ -2688,7 +2692,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); } - preempt_enable(); + local_irq_restore(flags); return page; } @@ -2704,7 +2708,7 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0) && !in_interrupt()) { + if (likely(order == 0)) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype); goto out; @@ -4519,13 +4523,13 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_FILE_MAPPED)), K(node_page_state(pgdat, NR_FILE_DIRTY)), K(node_page_state(pgdat, NR_WRITEBACK)), + K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), #endif - K(node_page_state(pgdat, NR_SHMEM)), K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), K(node_page_state(pgdat, NR_UNSTABLE_NFS)), node_page_state(pgdat, NR_PAGES_SCANNED), diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index c4c9def8ffea..de9c40d7304a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -111,12 +111,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - /* Only for THP, seek to next pte entry makes sense */ - if (pvmw->pte) { - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); + if (pvmw->pte) goto next_pte; - } if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ @@ -165,9 +161,14 @@ restart: while (1) { if (check_pte(pvmw)) return true; -next_pte: do { +next_pte: + /* Seek to next pte only makes sense for THP */ + if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) + return not_found(pvmw); + do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= + if (pvmw->address >= pvmw->vma->vm_end || + pvmw->address >= __vma_address(pvmw->page, pvmw->vma) + hpage_nr_pages(pvmw->page) * PAGE_SIZE) return not_found(pvmw); diff --git a/mm/swap.c b/mm/swap.c index c4910f14f957..5dabf444d724 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -670,30 +670,19 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); -/* - * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM - * workqueue, aiding in getting memory freed. - */ -static struct workqueue_struct *lru_add_drain_wq; - -static int __init lru_init(void) -{ - lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0); - - if (WARN(!lru_add_drain_wq, - "Failed to create workqueue lru_add_drain_wq")) - return -ENOMEM; - - return 0; -} -early_initcall(lru_init); - void lru_add_drain_all(void) { static DEFINE_MUTEX(lock); static struct cpumask has_work; int cpu; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON(!mm_percpu_wq)) + return; + mutex_lock(&lock); get_online_cpus(); cpumask_clear(&has_work); @@ -707,7 +696,7 @@ void lru_add_drain_all(void) pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); - queue_work_on(cpu, lru_add_drain_wq, work); + queue_work_on(cpu, mm_percpu_wq, work); cpumask_set_cpu(cpu, &has_work); } } diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index 310ac0b8f974..ac6318a064d3 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -201,6 +201,8 @@ void swap_cgroup_swapoff(int type) struct page *page = map[i]; if (page) __free_page(page); + if (!(i % SWAP_CLUSTER_MAX)) + cond_resched(); } vfree(map); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 89f95396ec46..5a4f5c5a31e8 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1552,7 +1552,6 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP -static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; @@ -1623,7 +1622,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - queue_delayed_work_on(smp_processor_id(), vmstat_wq, + queue_delayed_work_on(smp_processor_id(), mm_percpu_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } @@ -1702,7 +1701,7 @@ static void vmstat_shepherd(struct work_struct *w) struct delayed_work *dw = &per_cpu(vmstat_work, cpu); if (!delayed_work_pending(dw) && need_update(cpu)) - queue_delayed_work_on(cpu, vmstat_wq, dw, 0); + queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0); } put_online_cpus(); @@ -1718,7 +1717,6 @@ static void __init start_shepherd_timer(void) INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -1764,11 +1762,15 @@ static int vmstat_cpu_dead(unsigned int cpu) #endif +struct workqueue_struct *mm_percpu_wq; + void __init init_mm_internals(void) { -#ifdef CONFIG_SMP - int ret; + int ret __maybe_unused; + mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0); + +#ifdef CONFIG_SMP ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead", NULL, vmstat_cpu_dead); if (ret < 0) diff --git a/mm/z3fold.c b/mm/z3fold.c index f9492bccfd79..54f63c4a809a 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -185,6 +185,12 @@ static inline void z3fold_page_lock(struct z3fold_header *zhdr) spin_lock(&zhdr->page_lock); } +/* Try to lock a z3fold page */ +static inline int z3fold_page_trylock(struct z3fold_header *zhdr) +{ + return spin_trylock(&zhdr->page_lock); +} + /* Unlock a z3fold page */ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) { @@ -385,7 +391,7 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_lock(&pool->lock); zhdr = list_first_entry_or_null(&pool->unbuddied[i], struct z3fold_header, buddy); - if (!zhdr) { + if (!zhdr || !z3fold_page_trylock(zhdr)) { spin_unlock(&pool->lock); continue; } @@ -394,7 +400,6 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_unlock(&pool->lock); page = virt_to_page(zhdr); - z3fold_page_lock(zhdr); if (zhdr->first_chunks == 0) { if (zhdr->middle_chunks != 0 && chunks >= zhdr->start_middle) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b7ee9c34dbd6..d41edd28298b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -276,7 +276,7 @@ struct zs_pool { struct zspage { struct { unsigned int fullness:FULLNESS_BITS; - unsigned int class:CLASS_BITS; + unsigned int class:CLASS_BITS + 1; unsigned int isolated:ISOLATED_BITS; unsigned int magic:MAGIC_VAL_BITS; }; diff --git a/net/9p/client.c b/net/9p/client.c index 3ce672af1596..8e5c6a8d0a37 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2101,6 +2101,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) trace_9p_protocol_dump(clnt, req->rc); goto free_and_error; } + if (rsize < count) { + pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); + count = rsize; + } p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ea71513fca21..430b53e7d941 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -119,6 +119,16 @@ static int br_dev_init(struct net_device *dev) return err; } +static void br_dev_uninit(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + br_multicast_dev_del(br); + br_multicast_uninit_stats(br); + br_vlan_flush(br); + free_percpu(br->stats); +} + static int br_dev_open(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -332,6 +342,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, .ndo_init = br_dev_init, + .ndo_uninit = br_dev_uninit, .ndo_start_xmit = br_dev_xmit, .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, @@ -356,14 +367,6 @@ static const struct net_device_ops br_netdev_ops = { .ndo_features_check = passthru_features_check, }; -static void br_dev_free(struct net_device *dev) -{ - struct net_bridge *br = netdev_priv(dev); - - free_percpu(br->stats); - free_netdev(dev); -} - static struct device_type br_type = { .name = "bridge", }; @@ -376,7 +379,7 @@ void br_dev_setup(struct net_device *dev) ether_setup(dev); dev->netdev_ops = &br_netdev_ops; - dev->destructor = br_dev_free; + dev->destructor = free_netdev; dev->ethtool_ops = &br_ethtool_ops; SET_NETDEV_DEVTYPE(dev, &br_type); dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 8ac1770aa222..a8d0ed282a10 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -311,8 +311,6 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) br_fdb_delete_by_port(br, NULL, 0, 1); - br_vlan_flush(br); - br_multicast_dev_del(br); cancel_delayed_work_sync(&br->gc_work); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b760f2620abf..faa7261a992f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2031,8 +2031,6 @@ void br_multicast_dev_del(struct net_bridge *br) out: spin_unlock_bh(&br->multicast_lock); - - free_percpu(br->mcast_stats); } int br_multicast_set_router(struct net_bridge *br, unsigned long val) @@ -2531,6 +2529,11 @@ int br_multicast_init_stats(struct net_bridge *br) return 0; } +void br_multicast_uninit_stats(struct net_bridge *br) +{ + free_percpu(br->mcast_stats); +} + static void mcast_stats_add_dir(u64 *dst, u64 *src) { dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX]; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a8f6acd23e30..225ef7d53701 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1165,11 +1165,14 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, spin_unlock_bh(&br->lock); } - err = br_changelink(dev, tb, data); + err = register_netdevice(dev); if (err) return err; - return register_netdevice(dev); + err = br_changelink(dev, tb, data); + if (err) + unregister_netdevice(dev); + return err; } static size_t br_get_size(const struct net_device *brdev) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 61368186edea..0d177280aa84 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -620,6 +620,7 @@ void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir); int br_multicast_init_stats(struct net_bridge *br); +void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); @@ -760,6 +761,10 @@ static inline int br_multicast_init_stats(struct net_bridge *br) return 0; } +static inline void br_multicast_uninit_stats(struct net_bridge *br) +{ +} + static inline int br_multicast_igmp_type(const struct sk_buff *skb) { return 0; diff --git a/net/core/datagram.c b/net/core/datagram.c index ea633342ab0d..f4947e737f34 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -398,7 +398,7 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len) { int start = skb_headlen(skb); - int i, copy = start - offset; + int i, copy = start - offset, start_off = offset, n; struct sk_buff *frag_iter; trace_skb_copy_datagram_iovec(skb, len); @@ -407,11 +407,12 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, if (copy > 0) { if (copy > len) copy = len; - if (copy_to_iter(skb->data + offset, copy, to) != copy) + n = copy_to_iter(skb->data + offset, copy, to); + offset += n; + if (n != copy) goto short_copy; if ((len -= copy) == 0) return 0; - offset += copy; } /* Copy paged appendix. Hmm... why does this look so complicated? */ @@ -425,13 +426,14 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, if ((copy = end - offset) > 0) { if (copy > len) copy = len; - if (copy_page_to_iter(skb_frag_page(frag), + n = copy_page_to_iter(skb_frag_page(frag), frag->page_offset + offset - - start, copy, to) != copy) + start, copy, to); + offset += n; + if (n != copy) goto short_copy; if (!(len -= copy)) return 0; - offset += copy; } start = end; } @@ -463,6 +465,7 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset, */ fault: + iov_iter_revert(to, offset - start_off); return -EFAULT; short_copy: @@ -613,7 +616,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, __wsum *csump) { int start = skb_headlen(skb); - int i, copy = start - offset; + int i, copy = start - offset, start_off = offset; struct sk_buff *frag_iter; int pos = 0; int n; @@ -623,11 +626,11 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, if (copy > len) copy = len; n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to); + offset += n; if (n != copy) goto fault; if ((len -= copy) == 0) return 0; - offset += copy; pos = copy; } @@ -649,12 +652,12 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, offset - start, copy, &csum2, to); kunmap(page); + offset += n; if (n != copy) goto fault; *csump = csum_block_add(*csump, csum2, pos); if (!(len -= copy)) return 0; - offset += copy; pos += copy; } start = end; @@ -687,6 +690,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, return 0; fault: + iov_iter_revert(to, offset - start_off); return -EFAULT; } @@ -771,6 +775,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, } return 0; csum_error: + iov_iter_revert(&msg->msg_iter, chunk); return -EINVAL; fault: return -EFAULT; diff --git a/net/core/dev.c b/net/core/dev.c index 7869ae3837ca..9b5875388c23 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2450,6 +2450,9 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) { unsigned long flags; + if (unlikely(!skb)) + return; + if (likely(atomic_read(&skb->users) == 1)) { smp_rmb(); atomic_set(&skb->users, 0); @@ -6757,7 +6760,6 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) return err; } -EXPORT_SYMBOL(dev_change_xdp_fd); /** * dev_new_index - allocate an ifindex diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index c35aae13c8d2..d98d4998213d 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -390,7 +390,7 @@ mpls: unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; - struct arphdr *_arp; + struct arphdr _arp; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e7c12caa20c8..4526cbd7e28a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -860,7 +860,8 @@ static void neigh_probe(struct neighbour *neigh) if (skb) skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); + if (neigh->ops->solicit) + neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); kfree_skb(skb); } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 9424673009c1..29be2466970c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; + unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } - txq = skb_get_tx_queue(dev, skb); - local_irq_save(flags); + /* check if skb->queue_mapping is still valid */ + q_index = skb_get_queue_mapping(skb); + if (unlikely(q_index >= dev->real_num_tx_queues)) { + q_index = q_index % dev->real_num_tx_queues; + skb_set_queue_mapping(skb, q_index); + } + txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 758f140b6bed..d28da7d363f1 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -20,9 +20,11 @@ #include <net/tcp.h> static siphash_key_t net_secret __read_mostly; +static siphash_key_t ts_secret __read_mostly; static __always_inline void net_secret_init(void) { + net_get_random_once(&ts_secret, sizeof(ts_secret)); net_get_random_once(&net_secret, sizeof(net_secret)); } #endif @@ -45,6 +47,23 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) +static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) +{ + const struct { + struct in6_addr saddr; + struct in6_addr daddr; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *(struct in6_addr *)saddr, + .daddr = *(struct in6_addr *)daddr, + }; + + if (sysctl_tcp_timestamps != 1) + return 0; + + return siphash(&combined, offsetofend(typeof(combined), daddr), + &ts_secret); +} + u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport, u32 *tsoff) { @@ -63,7 +82,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, net_secret_init(); hash = siphash(&combined, offsetofend(typeof(combined), dport), &net_secret); - *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; + *tsoff = secure_tcpv6_ts_off(saddr, daddr); return seq_scale(hash); } EXPORT_SYMBOL(secure_tcpv6_sequence_number); @@ -88,6 +107,14 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET +static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) +{ + if (sysctl_tcp_timestamps != 1) + return 0; + + return siphash_2u32((__force u32)saddr, (__force u32)daddr, + &ts_secret); +} /* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, @@ -103,7 +130,7 @@ u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, &net_secret); - *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; + *tsoff = secure_tcp_ts_off(saddr, daddr); return seq_scale(hash); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9f781092fda9..f1d04592ace0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1576,6 +1576,8 @@ done: skb_set_tail_pointer(skb, len); } + if (!skb->sk || skb->destructor == sock_edemux) + skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); @@ -3082,22 +3084,32 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; + unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; - /* Split the buffer at the frag_list pointer. - * This is based on the assumption that all - * buffers in the chain excluding the last - * containing the same amount of data. + /* If we get here then all the required + * GSO features except frag_list are supported. + * Try to split the SKB to multiple GSO SKBs + * with no frag_list. + * Currently we can do that only when the buffers don't + * have a linear part and all the buffers except + * the last are of the same length. */ + frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { + if (frag_len != iter->len && iter->next) + goto normal; if (skb_headlen(iter)) goto normal; len -= iter->len; } + + if (len != frag_len) + goto normal; } /* GSO partial only requires that we trim off any excess that @@ -3807,6 +3819,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; + serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 4ead336e14ea..7f9cc400eca0 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -408,14 +408,16 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_net_busy_poll, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { .procname = "busy_read", .data = &sysctl_net_busy_read, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, #endif #ifdef CONFIG_NET_SCHED diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6b1fc6e4278e..13a9a3297eae 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1343,6 +1343,9 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) if (*(u8 *)iph != 0x45) goto out_unlock; + if (ip_is_fragment(iph)) + goto out_unlock; + if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out_unlock; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ebd953bc5607..1d46d05efb0f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -488,16 +488,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk, return false; /* Support IP_PKTINFO on tstamp packets if requested, to correlate - * timestamp with egress dev. Not possible for packets without dev + * timestamp with egress dev. Not possible for packets without iif * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ - if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) || - (!skb->dev)) + info = PKTINFO_SKB_CB(skb); + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) || + !info->ipi_ifindex) return false; - info = PKTINFO_SKB_CB(skb); info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; - info->ipi_ifindex = skb->dev->ifindex; return true; } @@ -591,6 +590,7 @@ static bool setsockopt_needs_rtnl(int optname) case MCAST_LEAVE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_UNBLOCK_SOURCE: + case IP_ROUTER_ALERT: return true; } return false; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index fd9f34bbd740..dfb2ab2dd3c8 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -306,7 +306,7 @@ static void __init ic_close_devs(void) while ((d = next)) { next = d->next; dev = d->dev; - if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) { + if (d != ic_dev && !netdev_uses_dsa(dev)) { pr_debug("IP-Config: Downing %s\n", dev->name); dev_change_flags(dev, d->flags); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c0317c940bcd..b036e85e093b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1278,7 +1278,7 @@ static void mrtsock_destruct(struct sock *sk) struct net *net = sock_net(sk); struct mr_table *mrt; - rtnl_lock(); + ASSERT_RTNL(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; @@ -1289,7 +1289,6 @@ static void mrtsock_destruct(struct sock *sk) mroute_clean_tables(mrt, false); } } - rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole @@ -1353,13 +1352,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { - /* We need to unlock here because mrtsock_destruct takes - * care of rtnl itself and we can't change that due to - * the IP_ROUTER_ALERT setsockopt which runs without it. - */ - rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); - goto out; + goto out_unlock; } break; case MRT_ADD_VIF: @@ -1470,7 +1464,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, } out_unlock: rtnl_unlock(); -out: return ret; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 52f26459efc3..9b8841316e7b 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -461,7 +461,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) clusterip_config_put(cipinfo->config); - nf_ct_netns_get(par->net, par->family); + nf_ct_netns_put(par->net, par->family); } #ifdef CONFIG_COMPAT diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index c9b52c361da2..53e49f5011d3 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1260,16 +1260,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = { .timeout = 180, }; -static struct nf_conntrack_helper snmp_helper __read_mostly = { - .me = THIS_MODULE, - .help = help, - .expect_policy = &snmp_exp_policy, - .name = "snmp", - .tuple.src.l3num = AF_INET, - .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT), - .tuple.dst.protonum = IPPROTO_UDP, -}; - static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { .me = THIS_MODULE, .help = help, @@ -1288,22 +1278,16 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { static int __init nf_nat_snmp_basic_init(void) { - int ret = 0; - BUG_ON(nf_nat_snmp_hook != NULL); RCU_INIT_POINTER(nf_nat_snmp_hook, help); - ret = nf_conntrack_helper_register(&snmp_trap_helper); - if (ret < 0) { - nf_conntrack_helper_unregister(&snmp_helper); - return ret; - } - return ret; + return nf_conntrack_helper_register(&snmp_trap_helper); } static void __exit nf_nat_snmp_basic_fini(void) { RCU_INIT_POINTER(nf_nat_snmp_hook, NULL); + synchronize_rcu(); nf_conntrack_helper_unregister(&snmp_trap_helper); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2af6244b83e2..ccfbce13a633 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -156,17 +156,18 @@ int ping_hash(struct sock *sk) void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); + pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); + write_lock_bh(&ping_table.lock); if (sk_hashed(sk)) { - write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - write_unlock_bh(&ping_table.lock); } + write_unlock_bh(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_unhash); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8119e1f66e03..9d943974de2b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -682,7 +682,9 @@ static void raw_close(struct sock *sk, long timeout) /* * Raw sockets may have direct kernel references. Kill them. */ + rtnl_lock(); ip_ra_control(sk, 0, NULL); + rtnl_unlock(); sk_common_release(sk); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8471dd116771..d9724889ff09 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2359,7 +2359,8 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, } /* L3 master device is the loopback for that domain */ - dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev; + dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? : + net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; @@ -2620,7 +2621,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) skb_reset_network_header(skb); /* Bugfix: need to give ip_route_input enough of an IP header to not gag. */ - ip_hdr(skb)->protocol = IPPROTO_ICMP; + ip_hdr(skb)->protocol = IPPROTO_UDP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1e319a525d51..40ba4249a586 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2322,6 +2322,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); + tcp_saved_syn_free(tp); /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 79c4817abc94..6e3c512054a6 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -168,12 +168,8 @@ void tcp_assign_congestion_control(struct sock *sk) } out: rcu_read_unlock(); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - /* Clear out private data before diag gets it and - * the ca has not been initialized. - */ - if (ca->get_info) - memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else @@ -200,11 +196,10 @@ static void tcp_reinit_congestion_control(struct sock *sk, tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) { - memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (sk->sk_state != TCP_CLOSE) tcp_init_congestion_control(sk); - } } /* Manage refcounts on socket close. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c43119726a62..659d1baefb2b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ -static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) +static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, + unsigned int len) { static bool __once __read_mostly; @@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); - pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", - dev ? dev->name : "Unknown driver"); + if (!dev || len >= dev->mtu) + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); rcu_read_unlock(); } } @@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); - if (unlikely(icsk->icsk_ack.rcv_mss != len)) - tcp_gro_dev_warn(sk, skb); + /* Account for possibly-removed options */ + if (unlikely(len > icsk->icsk_ack.rcv_mss + + MAX_TCP_OPTION_SPACE)) + tcp_gro_dev_warn(sk, skb, len); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. @@ -874,22 +878,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric, const int ts) { struct tcp_sock *tp = tcp_sk(sk); - if (metric > tp->reordering) { - int mib_idx; + int mib_idx; + if (metric > tp->reordering) { tp->reordering = min(sysctl_tcp_max_reordering, metric); - /* This exciting event is worth to be remembered. 8) */ - if (ts) - mib_idx = LINUX_MIB_TCPTSREORDER; - else if (tcp_is_reno(tp)) - mib_idx = LINUX_MIB_TCPRENOREORDER; - else if (tcp_is_fack(tp)) - mib_idx = LINUX_MIB_TCPFACKREORDER; - else - mib_idx = LINUX_MIB_TCPSACKREORDER; - - NET_INC_STATS(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 pr_debug("Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, @@ -902,6 +895,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric, } tp->rack.reord = 1; + + /* This exciting event is worth to be remembered. 8) */ + if (ts) + mib_idx = LINUX_MIB_TCPTSREORDER; + else if (tcp_is_reno(tp)) + mib_idx = LINUX_MIB_TCPRENOREORDER; + else if (tcp_is_fack(tp)) + mib_idx = LINUX_MIB_TCPFACKREORDER; + else + mib_idx = LINUX_MIB_TCPSACKREORDER; + + NET_INC_STATS(sock_net(sk), mib_idx); } /* This must be called before lost_out is incremented */ @@ -1930,6 +1935,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sk_buff *skb; + bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ bool mark_lost; @@ -1989,15 +1995,18 @@ void tcp_enter_loss(struct sock *sk) tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); - /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO - * if a previous recovery is underway, otherwise it may incorrectly - * call a timeout spurious if some previously retransmitted packets - * are s/acked (sec 3.2). We do not apply that retriction since - * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS - * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO - * on PTMU discovery to avoid sending new data. + /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous + * loss recovery is underway except recurring timeout(s) on + * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing + * + * In theory F-RTO can be used repeatedly during loss recovery. + * In practice this interacts badly with broken middle-boxes that + * falsely raise the receive window, which results in repeated + * timeouts and stop-and-go behavior. */ - tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size; + tp->frto = sysctl_tcp_frto && + (new_recovery || icsk->icsk_retransmits) && + !inet_csk(sk)->icsk_mtup.probe_size; } /* If ACK arrived pointing to a remembered SACK, it means that our diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 22548b5f05cb..a85d863c4419 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1267,7 +1267,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, * eventually). The difference is that pulled data not copied, but * immediately discarded. */ -static void __pskb_trim_head(struct sk_buff *skb, int len) +static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; @@ -1277,7 +1277,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) __skb_pull(skb, eat); len -= eat; if (!len) - return; + return 0; } eat = len; k = 0; @@ -1303,23 +1303,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) skb_reset_tail_pointer(skb); skb->data_len -= len; skb->len = skb->data_len; + return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { + u32 delta_truesize; + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; - __pskb_trim_head(skb, len); + delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; - skb->truesize -= len; - sk->sk_wmem_queued -= len; - sk_mem_uncharge(sk, len); - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); + if (delta_truesize) { + skb->truesize -= delta_truesize; + sk->sk_wmem_queued -= delta_truesize; + sk_mem_uncharge(sk, delta_truesize); + sock_set_flag(sk, SOCK_QUEUE_SHRUNK); + } /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) @@ -2999,6 +3004,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); + /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { @@ -3014,8 +3021,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); - - TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); } /* Send a crossed SYN-ACK during socket establishment. diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 4ecb38ae8504..d8acbd9f477a 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -12,7 +12,8 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) /* Account for retransmits that are lost again */ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT, + tcp_skb_pcount(skb)); } } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b2be1d9757ef..781250151d40 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -29,6 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; + bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; @@ -62,8 +63,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); + need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && + !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 363172527e43..0ea96c4d334d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3271,14 +3271,24 @@ static void addrconf_gre_config(struct net_device *dev) static int fixup_permanent_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - if (!ifp->rt) { - struct rt6_info *rt; + /* rt6i_ref == 0 means the host route was removed from the + * FIB, for example, if 'lo' device is taken down. In that + * case regenerate the host route. + */ + if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) { + struct rt6_info *rt, *prev; rt = addrconf_dst_alloc(idev, &ifp->addr, false); if (unlikely(IS_ERR(rt))) return PTR_ERR(rt); + /* ifp->rt can be accessed outside of rtnl */ + spin_lock(&ifp->lock); + prev = ifp->rt; ifp->rt = rt; + spin_unlock(&ifp->lock); + + ip6_rt_put(prev); } if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { @@ -3626,14 +3636,19 @@ restart: INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct rt6_info *rt = NULL; + bool keep; addrconf_del_dad_work(ifa); + keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && + !addr_is_local(&ifa->addr); + if (!keep) + list_move(&ifa->if_list, &del_list); + write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); - if (keep_addr && (ifa->flags & IFA_F_PERMANENT) && - !addr_is_local(&ifa->addr)) { + if (keep) { /* set state to skip the notifier below */ state = INET6_IFADDR_STATE_DEAD; ifa->state = 0; @@ -3645,8 +3660,6 @@ restart: } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; - - list_move(&ifa->if_list, &del_list); } spin_unlock_bh(&ifa->lock); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a9a9553ee63d..e82e59f22dfc 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -933,8 +933,6 @@ static int __init inet6_init(void) if (err) goto igmp_fail; - ipv6_stub = &ipv6_stub_impl; - err = ipv6_netfilter_init(); if (err) goto netfilter_fail; @@ -1010,6 +1008,10 @@ static int __init inet6_init(void) if (err) goto sysctl_fail; #endif + + /* ensure that ipv6 stubs are visible only after ipv6 is ready */ + wmb(); + ipv6_stub = &ipv6_stub_impl; out: return err; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index eec27f87efac..e011122ebd43 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -405,9 +405,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr) * At one point, excluding local errors was a quick test to identify icmp/icmp6 * errors. This is no longer true, but the test remained, so the v6 stack, * unlike v4, also honors cmsg requests on all wifi and timestamp errors. - * - * Timestamp code paths do not initialize the fields expected by cmsg: - * the PKTINFO fields in skb->cb[]. Fill those in here. */ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, struct sock_exterr_skb *serr) @@ -419,14 +416,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) return false; - if (!skb->dev) + if (!IP6CB(skb)->iif) return false; - if (skb->protocol == htons(ETH_P_IPV6)) - IP6CB(skb)->iif = skb->dev->ifindex; - else - PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex; - return true; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 275cac628a95..d32e2110aff2 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -388,7 +388,6 @@ looped_back: icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); - kfree_skb(skb); return -1; } @@ -910,6 +909,8 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, { switch (opt->type) { case IPV6_SRCRT_TYPE_0: + case IPV6_SRCRT_STRICT: + case IPV6_SRCRT_TYPE_2: ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr); break; case IPV6_SRCRT_TYPE_4: @@ -1164,6 +1165,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, switch (opt->srcrt->type) { case IPV6_SRCRT_TYPE_0: + case IPV6_SRCRT_STRICT: + case IPV6_SRCRT_TYPE_2: fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; break; case IPV6_SRCRT_TYPE_4: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index aacfb4bce153..c45b12b4431c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -122,11 +122,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); /* * RFC4291 2.5.3 + * The loopback address must not be used as the source address in IPv6 + * packets that are sent outside of a single node. [..] * A packet received on an interface with a destination address * of loopback must be dropped. */ - if (!(dev->flags & IFF_LOOPBACK) && - ipv6_addr_loopback(&hdr->daddr)) + if ((ipv6_addr_loopback(&hdr->saddr) || + ipv6_addr_loopback(&hdr->daddr)) && + !(dev->flags & IFF_LOOPBACK)) goto err; /* RFC4291 Errata ID: 3480 diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 75fac933c209..a9692ec0cd6d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; @@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { - struct in6_addr *addr6; - struct neighbour *neigh; - int addr_type; + if (skb->protocol == htons(ETH_P_IPV6)) { + struct in6_addr *addr6; + struct neighbour *neigh; + int addr_type; - if (!skb_dst(skb)) - goto tx_err_link_failure; + if (!skb_dst(skb)) + goto tx_err_link_failure; - neigh = dst_neigh_lookup(skb_dst(skb), - &ipv6_hdr(skb)->daddr); - if (!neigh) - goto tx_err_link_failure; + neigh = dst_neigh_lookup(skb_dst(skb), + &ipv6_hdr(skb)->daddr); + if (!neigh) + goto tx_err_link_failure; - addr6 = (struct in6_addr *)&neigh->primary_key; - addr_type = ipv6_addr_type(addr6); + addr6 = (struct in6_addr *)&neigh->primary_key; + addr_type = ipv6_addr_type(addr6); - if (addr_type == IPV6_ADDR_ANY) - addr6 = &ipv6_hdr(skb)->daddr; + if (addr_type == IPV6_ADDR_ANY) + addr6 = &ipv6_hdr(skb)->daddr; - memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); - neigh_release(neigh); + memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); + neigh_release(neigh); + } } else if (!(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only only if the routing decision does diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 6ba6c900ebcf..bf34d0950752 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -774,7 +774,8 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, + struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev->ifindex, &in6_dev->cnf); } - if (v->flags & MIFF_REGISTER) + if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); @@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct notifier_block *this, struct mr6_table *mrt; struct mif_device *v; int ct; - LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct notifier_block *this, v = &mrt->vif6_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(mrt, ct, &list); + mif6_delete(mrt, ct, 1, NULL); } } - unregister_netdevice_many(&list); return NOTIFY_DONE; } @@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all) for (i = 0; i < mrt->maxvif; i++) { if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) continue; - mif6_delete(mrt, i, &list); + mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -1707,7 +1706,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(mrt, mifi, NULL); + ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7ebac630d3c6..cb1766724a4c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1749,7 +1749,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, idev = in6_dev_get(dev); if (!idev) break; - if (idev->cnf.ndisc_notify) + if (idev->cnf.ndisc_notify || + net->ipv6.devconf_all->ndisc_notify) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index f174e76e6505..0da6a12b5472 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1178,8 +1178,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) - amount = skb_tail_pointer(skb) - - skb_transport_header(skb); + amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9db1418993f2..fb174b590fd3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1854,6 +1854,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int addr_type; int err = -EINVAL; + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) + goto out; + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) goto out; #ifndef CONFIG_IPV6_SUBTREES diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index a855eb325b03..5f44ffed2576 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -53,6 +53,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) struct sr6_tlv *tlv; unsigned int tlv_len; + if (trailing < sizeof(*tlv)) + return false; + tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 309062f3debe..31762f76cdb5 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1687,7 +1687,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct kcm_attach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) - err = -EFAULT; + return -EFAULT; err = kcm_attach_ioctl(sock, &info); @@ -1697,7 +1697,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct kcm_unattach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) - err = -EFAULT; + return -EFAULT; err = kcm_unattach_ioctl(sock, &info); @@ -1708,7 +1708,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct socket *newsock = NULL; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) - err = -EFAULT; + return -EFAULT; err = kcm_clone(sock, &info, &newsock); diff --git a/net/key/af_key.c b/net/key/af_key.c index c6252ed42c1d..be8cecc65002 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -63,8 +63,13 @@ struct pfkey_sock { } u; struct sk_buff *skb; } dump; + struct mutex dump_lock; }; +static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, + xfrm_address_t *saddr, xfrm_address_t *daddr, + u16 *family); + static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; @@ -139,6 +144,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; + struct pfkey_sock *pfk; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -153,6 +159,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) goto out; + pfk = pfkey_sk(sk); + mutex_init(&pfk->dump_lock); + sock->ops = &pfkey_ops; sock_init_data(sock, sk); @@ -281,13 +290,23 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) struct sadb_msg *hdr; int rc; + mutex_lock(&pfk->dump_lock); + if (!pfk->dump.dump) { + rc = 0; + goto out; + } + rc = pfk->dump.dump(pfk); - if (rc == -ENOBUFS) - return 0; + if (rc == -ENOBUFS) { + rc = 0; + goto out; + } if (pfk->dump.skb) { - if (!pfkey_can_dump(&pfk->sk)) - return 0; + if (!pfkey_can_dump(&pfk->sk)) { + rc = 0; + goto out; + } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; @@ -298,6 +317,9 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) } pfkey_terminate_dump(pfk); + +out: + mutex_unlock(&pfk->dump_lock); return rc; } @@ -1793,19 +1815,26 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } proto = pfkey_satype2proto(hdr->sadb_msg_satype); - if (proto == 0) + if (proto == 0) { + mutex_unlock(&pfk->dump_lock); return -EINVAL; + } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; filter = kmalloc(sizeof(*filter), GFP_KERNEL); - if (filter == NULL) + if (filter == NULL) { + mutex_unlock(&pfk->dump_lock); return -ENOMEM; + } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); @@ -1821,6 +1850,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } @@ -1913,19 +1943,14 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { - u8 *sa = (u8 *) (rq + 1); - int family, socklen; + int err; - family = pfkey_sockaddr_extract((struct sockaddr *)sa, - &t->saddr); - if (!family) - return -EINVAL; - - socklen = pfkey_sockaddr_len(family); - if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen), - &t->id.daddr) != family) - return -EINVAL; - t->encap_family = family; + err = parse_sockaddr_pair( + (struct sockaddr *)(rq + 1), + rq->sadb_x_ipsecrequest_len - sizeof(*rq), + &t->saddr, &t->id.daddr, &t->encap_family); + if (err) + return err; } else t->encap_family = xp->family; @@ -1945,7 +1970,11 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; - while (len >= sizeof(struct sadb_x_ipsecrequest)) { + while (len >= sizeof(*rq)) { + if (len < rq->sadb_x_ipsecrequest_len || + rq->sadb_x_ipsecrequest_len < sizeof(*rq)) + return -EINVAL; + if ((err = parse_ipsecrequest(xp, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; @@ -2408,7 +2437,6 @@ out: return err; } -#ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); @@ -2420,7 +2448,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, { int af, socklen; - if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) + if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); @@ -2436,6 +2464,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, return 0; } +#ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { @@ -2443,13 +2472,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct sadb_x_ipsecrequest *rq2; int mode; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq1->sadb_x_ipsecrequest_len) + if (len < sizeof(*rq1) || + len < rq1->sadb_x_ipsecrequest_len || + rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), - rq1->sadb_x_ipsecrequest_len, + rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) @@ -2458,13 +2488,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq2->sadb_x_ipsecrequest_len) + if (len <= sizeof(*rq2) || + len < rq2->sadb_x_ipsecrequest_len || + rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), - rq2->sadb_x_ipsecrequest_len, + rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) @@ -2679,14 +2710,18 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb { struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 8adab6335ced..e37d9554da7b 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -278,7 +278,57 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn } EXPORT_SYMBOL_GPL(l2tp_session_find); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) +/* Like l2tp_session_find() but takes a reference on the returned session. + * Optionally calls session->ref() too if do_ref is true. + */ +struct l2tp_session *l2tp_session_get(struct net *net, + struct l2tp_tunnel *tunnel, + u32 session_id, bool do_ref) +{ + struct hlist_head *session_list; + struct l2tp_session *session; + + if (!tunnel) { + struct l2tp_net *pn = l2tp_pernet(net); + + session_list = l2tp_session_id_hash_2(pn, session_id); + + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(session, session_list, global_hlist) { + if (session->session_id == session_id) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); + rcu_read_unlock_bh(); + + return session; + } + } + rcu_read_unlock_bh(); + + return NULL; + } + + session_list = l2tp_session_id_hash(tunnel, session_id); + read_lock_bh(&tunnel->hlist_lock); + hlist_for_each_entry(session, session_list, hlist) { + if (session->session_id == session_id) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); + read_unlock_bh(&tunnel->hlist_lock); + + return session; + } + } + read_unlock_bh(&tunnel->hlist_lock); + + return NULL; +} +EXPORT_SYMBOL_GPL(l2tp_session_get); + +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref) { int hash; struct l2tp_session *session; @@ -288,6 +338,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); read_unlock_bh(&tunnel->hlist_lock); return session; } @@ -298,12 +351,13 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_find_nth); +EXPORT_SYMBOL_GPL(l2tp_session_get_nth); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ -struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname) +struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname, + bool do_ref) { struct l2tp_net *pn = l2tp_pernet(net); int hash; @@ -313,7 +367,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname) for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { if (!strcmp(session->ifname, ifname)) { + l2tp_session_inc_refcount(session); + if (do_ref && session->ref) + session->ref(session); rcu_read_unlock_bh(); + return session; } } @@ -323,7 +381,49 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname) return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname); +EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); + +static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel, + struct l2tp_session *session) +{ + struct l2tp_session *session_walk; + struct hlist_head *g_head; + struct hlist_head *head; + struct l2tp_net *pn; + + head = l2tp_session_id_hash(tunnel, session->session_id); + + write_lock_bh(&tunnel->hlist_lock); + hlist_for_each_entry(session_walk, head, hlist) + if (session_walk->session_id == session->session_id) + goto exist; + + if (tunnel->version == L2TP_HDR_VER_3) { + pn = l2tp_pernet(tunnel->l2tp_net); + g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net), + session->session_id); + + spin_lock_bh(&pn->l2tp_session_hlist_lock); + hlist_for_each_entry(session_walk, g_head, global_hlist) + if (session_walk->session_id == session->session_id) + goto exist_glob; + + hlist_add_head_rcu(&session->global_hlist, g_head); + spin_unlock_bh(&pn->l2tp_session_hlist_lock); + } + + hlist_add_head(&session->hlist, head); + write_unlock_bh(&tunnel->hlist_lock); + + return 0; + +exist_glob: + spin_unlock_bh(&pn->l2tp_session_hlist_lock); +exist: + write_unlock_bh(&tunnel->hlist_lock); + + return -EEXIST; +} /* Lookup a tunnel by id */ @@ -633,6 +733,9 @@ discard: * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. + * + * session->ref() must have been called prior to l2tp_recv_common(). + * session->deref() will be called automatically after skb is processed. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, @@ -642,14 +745,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int offset; u32 ns, nr; - /* The ref count is increased since we now hold a pointer to - * the session. Take care to decrement the refcnt when exiting - * this function from now on... - */ - l2tp_session_inc_refcount(session); - if (session->ref) - (*session->ref)(session); - /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { @@ -802,8 +897,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, /* Try to dequeue as many skbs from reorder_q as we can. */ l2tp_recv_dequeue(session); - l2tp_session_dec_refcount(session); - return; discard: @@ -812,8 +905,6 @@ discard: if (session->deref) (*session->deref)(session); - - l2tp_session_dec_refcount(session); } EXPORT_SYMBOL(l2tp_recv_common); @@ -920,8 +1011,14 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, } /* Find the session context */ - session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id); + session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true); if (!session || !session->recv_skb) { + if (session) { + if (session->deref) + session->deref(session); + l2tp_session_dec_refcount(session); + } + /* Not found? Pass to userspace to deal with */ l2tp_info(tunnel, L2TP_MSG_DATA, "%s: no session found (%u/%u). Passing up.\n", @@ -930,6 +1027,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook); + l2tp_session_dec_refcount(session); return 0; @@ -1738,6 +1836,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { struct l2tp_session *session; + int err; session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL); if (session != NULL) { @@ -1793,6 +1892,13 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn l2tp_session_set_header_len(session, tunnel->version); + err = l2tp_session_add_to_tunnel(tunnel, session); + if (err) { + kfree(session); + + return ERR_PTR(err); + } + /* Bump the reference count. The session context is deleted * only when this drops to zero. */ @@ -1802,28 +1908,14 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn /* Ensure tunnel socket isn't deleted */ sock_hold(tunnel->sock); - /* Add session to the tunnel's hash list */ - write_lock_bh(&tunnel->hlist_lock); - hlist_add_head(&session->hlist, - l2tp_session_id_hash(tunnel, session_id)); - write_unlock_bh(&tunnel->hlist_lock); - - /* And to the global session list if L2TPv3 */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_add_head_rcu(&session->global_hlist, - l2tp_session_id_hash_2(pn, session_id)); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); - } - /* Ignore management session in session count value */ if (session->session_id != 0) atomic_inc(&l2tp_session_count); + + return session; } - return session; + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(l2tp_session_create); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index aebf281d09ee..8ce7818c7a9d 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -230,11 +230,16 @@ out: return tunnel; } +struct l2tp_session *l2tp_session_get(struct net *net, + struct l2tp_tunnel *tunnel, + u32 session_id, bool do_ref); struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); -struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); -struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, + bool do_ref); +struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname, + bool do_ref); struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 2d6760a2ae34..d100aed3d06f 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) } /* Show the tunnel or session context */ - if (pd->session == NULL) + if (!pd->session) { l2tp_dfs_seq_tunnel_show(m, pd->tunnel); - else + } else { l2tp_dfs_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 8bf18a5f66e0..6fd41d7afe1e 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -221,12 +221,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p goto out; } - session = l2tp_session_find(net, tunnel, session_id); - if (session) { - rc = -EEXIST; - goto out; - } - if (cfg->ifname) { dev = dev_get_by_name(net, cfg->ifname); if (dev) { @@ -240,8 +234,8 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p session = l2tp_session_create(sizeof(*spriv), tunnel, session_id, peer_session_id, cfg); - if (!session) { - rc = -ENOMEM; + if (IS_ERR(session)) { + rc = PTR_ERR(session); goto out; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index d25038cfd64e..4d322c1b7233 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -143,19 +143,19 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_find(net, NULL, session_id); - if (session == NULL) + session = l2tp_session_get(net, NULL, session_id, true); + if (!session) goto discard; tunnel = session->tunnel; - if (tunnel == NULL) - goto discard; + if (!tunnel) + goto discard_sess; /* Trace packet contents, if enabled */ if (tunnel->debug & L2TP_MSG_DATA) { length = min(32u, skb->len); if (!pskb_may_pull(skb, length)) - goto discard; + goto discard_sess; /* Point to L2TP header */ optr = ptr = skb->data; @@ -165,6 +165,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook); + l2tp_session_dec_refcount(session); return 0; @@ -178,9 +179,10 @@ pass_up: tunnel_id = ntohl(*(__be32 *) &skb->data[4]); tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel != NULL) + if (tunnel) { sk = tunnel->sock; - else { + sock_hold(sk); + } else { struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); @@ -202,6 +204,12 @@ pass_up: return sk_receive_skb(sk, skb, 1); +discard_sess: + if (session->deref) + session->deref(session); + l2tp_session_dec_refcount(session); + goto discard; + discard_put: sock_put(sk); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index a4abcbc4c09a..88b397c30d86 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -156,19 +156,19 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_find(net, NULL, session_id); - if (session == NULL) + session = l2tp_session_get(net, NULL, session_id, true); + if (!session) goto discard; tunnel = session->tunnel; - if (tunnel == NULL) - goto discard; + if (!tunnel) + goto discard_sess; /* Trace packet contents, if enabled */ if (tunnel->debug & L2TP_MSG_DATA) { length = min(32u, skb->len); if (!pskb_may_pull(skb, length)) - goto discard; + goto discard_sess; /* Point to L2TP header */ optr = ptr = skb->data; @@ -179,6 +179,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb) l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook); + l2tp_session_dec_refcount(session); + return 0; pass_up: @@ -191,9 +193,10 @@ pass_up: tunnel_id = ntohl(*(__be32 *) &skb->data[4]); tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel != NULL) + if (tunnel) { sk = tunnel->sock; - else { + sock_hold(sk); + } else { struct ipv6hdr *iph = ipv6_hdr(skb); read_lock_bh(&l2tp_ip6_lock); @@ -215,6 +218,12 @@ pass_up: return sk_receive_skb(sk, skb, 1); +discard_sess: + if (session->deref) + session->deref(session); + l2tp_session_dec_refcount(session); + goto discard; + discard_put: sock_put(sk); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 3620fba31786..7e3e669baac4 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -48,7 +48,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, /* Accessed under genl lock */ static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX]; -static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info) +static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info, + bool do_ref) { u32 tunnel_id; u32 session_id; @@ -59,14 +60,15 @@ static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info) if (info->attrs[L2TP_ATTR_IFNAME]) { ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); - session = l2tp_session_find_by_ifname(net, ifname); + session = l2tp_session_get_by_ifname(net, ifname, do_ref); } else if ((info->attrs[L2TP_ATTR_SESSION_ID]) && (info->attrs[L2TP_ATTR_CONN_ID])) { tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); tunnel = l2tp_tunnel_find(net, tunnel_id); if (tunnel) - session = l2tp_session_find(net, tunnel, session_id); + session = l2tp_session_get(net, tunnel, session_id, + do_ref); } return session; @@ -642,10 +644,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf session_id, peer_session_id, &cfg); if (ret >= 0) { - session = l2tp_session_find(net, tunnel, session_id); - if (session) + session = l2tp_session_get(net, tunnel, session_id, false); + if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); + l2tp_session_dec_refcount(session); + } } out: @@ -658,7 +662,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf struct l2tp_session *session; u16 pw_type; - session = l2tp_nl_session_find(info); + session = l2tp_nl_session_get(info, true); if (session == NULL) { ret = -ENODEV; goto out; @@ -672,6 +676,10 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session); + if (session->deref) + session->deref(session); + l2tp_session_dec_refcount(session); + out: return ret; } @@ -681,7 +689,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf int ret = 0; struct l2tp_session *session; - session = l2tp_nl_session_find(info); + session = l2tp_nl_session_get(info, false); if (session == NULL) { ret = -ENODEV; goto out; @@ -716,6 +724,8 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); + l2tp_session_dec_refcount(session); + out: return ret; } @@ -811,29 +821,34 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; int ret; - session = l2tp_nl_session_find(info); + session = l2tp_nl_session_get(info, false); if (session == NULL) { ret = -ENODEV; - goto out; + goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; - goto out; + goto err_ref; } ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, 0, session, L2TP_CMD_SESSION_GET); if (ret < 0) - goto err_out; + goto err_ref_msg; - return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); + ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); -err_out: - nlmsg_free(msg); + l2tp_session_dec_refcount(session); -out: + return ret; + +err_ref_msg: + nlmsg_free(msg); +err_ref: + l2tp_session_dec_refcount(session); +err: return ret; } @@ -852,7 +867,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback goto out; } - session = l2tp_session_find_nth(tunnel, si); + session = l2tp_session_get_nth(tunnel, si, false); if (session == NULL) { ti++; tunnel = NULL; @@ -862,8 +877,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - session, L2TP_CMD_SESSION_GET) < 0) + session, L2TP_CMD_SESSION_GET) < 0) { + l2tp_session_dec_refcount(session); break; + } + l2tp_session_dec_refcount(session); si++; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 36cc56fd0418..32ea0f3d868c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -450,6 +450,10 @@ static void pppol2tp_session_close(struct l2tp_session *session) static void pppol2tp_session_destruct(struct sock *sk) { struct l2tp_session *session = sk->sk_user_data; + + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); + if (session) { sk->sk_user_data = NULL; BUG_ON(session->magic != L2TP_SESSION_MAGIC); @@ -488,9 +492,6 @@ static int pppol2tp_release(struct socket *sock) l2tp_session_queue_purge(session); sock_put(sk); } - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - release_sock(sk); /* This will delete the session context via @@ -582,6 +583,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, int error = 0; u32 tunnel_id, peer_tunnel_id; u32 session_id, peer_session_id; + bool drop_refcnt = false; int ver = 2; int fd; @@ -683,36 +685,36 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = peer_tunnel_id; - /* Create session if it doesn't already exist. We handle the - * case where a session was previously created by the netlink - * interface by checking that the session doesn't already have - * a socket and its tunnel socket are what we expect. If any - * of those checks fail, return EEXIST to the caller. - */ - session = l2tp_session_find(sock_net(sk), tunnel, session_id); - if (session == NULL) { - /* Default MTU must allow space for UDP/L2TP/PPP - * headers. + session = l2tp_session_get(sock_net(sk), tunnel, session_id, false); + if (session) { + drop_refcnt = true; + ps = l2tp_session_priv(session); + + /* Using a pre-existing session is fine as long as it hasn't + * been connected yet. */ - cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD; + if (ps->sock) { + error = -EEXIST; + goto end; + } - /* Allocate and initialize a new session context. */ - session = l2tp_session_create(sizeof(struct pppol2tp_session), - tunnel, session_id, - peer_session_id, &cfg); - if (session == NULL) { - error = -ENOMEM; + /* consistency checks */ + if (ps->tunnel_sock != tunnel->sock) { + error = -EEXIST; goto end; } } else { - ps = l2tp_session_priv(session); - error = -EEXIST; - if (ps->sock != NULL) - goto end; + /* Default MTU must allow space for UDP/L2TP/PPP headers */ + cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; + cfg.mru = cfg.mtu; - /* consistency checks */ - if (ps->tunnel_sock != tunnel->sock) + session = l2tp_session_create(sizeof(struct pppol2tp_session), + tunnel, session_id, + peer_session_id, &cfg); + if (IS_ERR(session)) { + error = PTR_ERR(session); goto end; + } } /* Associate session with its PPPoL2TP socket */ @@ -777,6 +779,8 @@ out_no_ppp: session->name); end: + if (drop_refcnt) + l2tp_session_dec_refcount(session); release_sock(sk); return error; @@ -804,12 +808,6 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i if (tunnel->sock == NULL) goto out; - /* Check that this session doesn't already exist */ - error = -EEXIST; - session = l2tp_session_find(net, tunnel, session_id); - if (session != NULL) - goto out; - /* Default MTU values. */ if (cfg->mtu == 0) cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; @@ -817,12 +815,13 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i cfg->mru = cfg->mtu; /* Allocate and initialize a new session context. */ - error = -ENOMEM; session = l2tp_session_create(sizeof(struct pppol2tp_session), tunnel, session_id, peer_session_id, cfg); - if (session == NULL) + if (IS_ERR(session)) { + error = PTR_ERR(session); goto out; + } ps = l2tp_session_priv(session); ps->tunnel_sock = tunnel->sock; @@ -1140,11 +1139,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, if (stats.session_id != 0) { /* resend to session ioctl handler */ struct l2tp_session *session = - l2tp_session_find(sock_net(sk), tunnel, stats.session_id); - if (session != NULL) - err = pppol2tp_session_ioctl(session, cmd, arg); - else + l2tp_session_get(sock_net(sk), tunnel, + stats.session_id, true); + + if (session) { + err = pppol2tp_session_ioctl(session, cmd, + arg); + if (session->deref) + session->deref(session); + l2tp_session_dec_refcount(session); + } else { err = -EBADR; + } break; } #ifdef CONFIG_XFRM @@ -1377,8 +1383,6 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, } else err = pppol2tp_session_setsockopt(sk, session, optname, val); - err = 0; - end_put_sess: sock_put(sk); end: @@ -1501,8 +1505,13 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val); sock_put(ps->tunnel_sock); - } else + if (err) + goto end_put_sess; + } else { err = pppol2tp_session_getsockopt(sk, session, optname, &val); + if (err) + goto end_put_sess; + } err = -EFAULT; if (put_user(len, optlen)) @@ -1554,7 +1563,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { - pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); pd->session_idx++; if (pd->session == NULL) { @@ -1681,10 +1690,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) /* Show the tunnel or session context. */ - if (pd->session == NULL) + if (!pd->session) { pppol2tp_seq_tunnel_show(m, pd->tunnel); - else + } else { pppol2tp_seq_session_show(m, pd->session); + if (pd->session->deref) + pd->session->deref(pd->session); + l2tp_session_dec_refcount(pd->session); + } out: return 0; @@ -1843,4 +1856,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP"); MODULE_LICENSE("GPL"); MODULE_VERSION(PPPOL2TP_DRV_VERSION); MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP); -MODULE_ALIAS_L2TP_PWTYPE(11); +MODULE_ALIAS_L2TP_PWTYPE(7); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 40813dd3301c..5bb0c5012819 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -718,7 +718,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) ieee80211_recalc_ps(local); if (sdata->vif.type == NL80211_IFTYPE_MONITOR || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + local->ops->wake_tx_queue) { /* XXX: for AP_VLAN, actually track AP queues */ netif_tx_start_all_queues(dev); } else if (dev) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e48724a6725e..4d7543d1a62c 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -208,6 +208,51 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, return len; } +static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + int rtap_vendor_space) +{ + struct { + struct ieee80211_hdr_3addr hdr; + u8 category; + u8 action_code; + } __packed action; + + if (!sdata) + return; + + BUILD_BUG_ON(sizeof(action) != IEEE80211_MIN_ACTION_SIZE + 1); + + if (skb->len < rtap_vendor_space + sizeof(action) + + VHT_MUMIMO_GROUPS_DATA_LEN) + return; + + if (!is_valid_ether_addr(sdata->u.mntr.mu_follow_addr)) + return; + + skb_copy_bits(skb, rtap_vendor_space, &action, sizeof(action)); + + if (!ieee80211_is_action(action.hdr.frame_control)) + return; + + if (action.category != WLAN_CATEGORY_VHT) + return; + + if (action.action_code != WLAN_VHT_ACTION_GROUPID_MGMT) + return; + + if (!ether_addr_equal(action.hdr.addr1, sdata->u.mntr.mu_follow_addr)) + return; + + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) + return; + + skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&sdata->local->hw, &sdata->work); +} + /* * ieee80211_add_rx_radiotap_header - add radiotap header * @@ -515,7 +560,6 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, struct net_device *prev_dev = NULL; int present_fcs_len = 0; unsigned int rtap_vendor_space = 0; - struct ieee80211_mgmt *mgmt; struct ieee80211_sub_if_data *monitor_sdata = rcu_dereference(local->monitor_sdata); @@ -553,6 +597,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return remove_monitor_info(local, origskb, rtap_vendor_space); } + ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_vendor_space); + /* room for the radiotap header based on driver features */ rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb); needed_headroom = rt_hdrlen - rtap_vendor_space; @@ -618,23 +664,6 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, ieee80211_rx_stats(sdata->dev, skb->len); } - mgmt = (void *)skb->data; - if (monitor_sdata && - skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + VHT_MUMIMO_GROUPS_DATA_LEN && - ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_VHT && - mgmt->u.action.u.vht_group_notif.action_code == WLAN_VHT_ACTION_GROUPID_MGMT && - is_valid_ether_addr(monitor_sdata->u.mntr.mu_follow_addr) && - ether_addr_equal(mgmt->da, monitor_sdata->u.mntr.mu_follow_addr)) { - struct sk_buff *mu_skb = skb_copy(skb, GFP_ATOMIC); - - if (mu_skb) { - mu_skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; - skb_queue_tail(&monitor_sdata->skb_queue, mu_skb); - ieee80211_queue_work(&local->hw, &monitor_sdata->work); - } - } - if (prev_dev) { skb->dev = prev_dev; netif_receive_skb(skb); @@ -3610,6 +3639,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) !ether_addr_equal(bssid, hdr->addr1)) return false; } + + /* + * 802.11-2016 Table 9-26 says that for data frames, A1 must be + * the BSSID - we've checked that already but may have accepted + * the wildcard (ff:ff:ff:ff:ff:ff). + * + * It also says: + * The BSSID of the Data frame is determined as follows: + * a) If the STA is contained within an AP or is associated + * with an AP, the BSSID is the address currently in use + * by the STA contained in the AP. + * + * So we should not accept data frames with an address that's + * multicast. + * + * Accepting it also opens a security problem because stations + * could encrypt it with the GTK and inject traffic that way. + */ + if (ieee80211_is_data(hdr->frame_control) && multicast) + return false; + return true; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index da9df2d56e66..22fc32143e9c 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -290,6 +290,7 @@ void nf_conntrack_unregister_notifier(struct net *net, BUG_ON(notify != new); RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); + /* synchronize_rcu() is called from ctnetlink_exit. */ } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); @@ -326,6 +327,7 @@ void nf_ct_expect_unregister_notifier(struct net *net, BUG_ON(notify != new); RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); + /* synchronize_rcu() is called from ctnetlink_exit. */ } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4b2e1fb28bb4..d80073037856 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -57,7 +57,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, hlist_del_rcu(&exp->hnode); net->ct.expect_count--; - hlist_del(&exp->lnode); + hlist_del_rcu(&exp->lnode); master_help->expecting[exp->class]--; nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report); @@ -363,7 +363,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) /* two references : one for hash insert, one for the timer */ atomic_add(2, &exp->use); - hlist_add_head(&exp->lnode, &master_help->expectations); + hlist_add_head_rcu(&exp->lnode, &master_help->expectations); master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 02bcf00c2492..008299b7f78f 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -53,7 +53,11 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); - BUG_ON(t == NULL); + if (!t) { + rcu_read_unlock(); + return NULL; + } + off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len + var_alloc_len; alloc_size = t->alloc_size + var_alloc_len; @@ -88,7 +92,10 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); - BUG_ON(t == NULL); + if (!t) { + rcu_read_unlock(); + return NULL; + } newoff = ALIGN(old->len, t->align); newlen = newoff + t->len + var_alloc_len; @@ -175,6 +182,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type) RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); - rcu_barrier(); /* Wait for completion of call_rcu()'s */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 6dc44d9b4190..4eeb3418366a 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -158,16 +158,25 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; + rcu_read_lock(); + h = __nf_conntrack_helper_find(name, l3num, protonum); #ifdef CONFIG_MODULES if (h == NULL) { - if (request_module("nfct-helper-%s", name) == 0) + rcu_read_unlock(); + if (request_module("nfct-helper-%s", name) == 0) { + rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); + } else { + return h; + } } #endif if (h != NULL && !try_module_get(h->me)) h = NULL; + rcu_read_unlock(); + return h; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); @@ -311,38 +320,36 @@ void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); +/* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name) { struct nf_ct_helper_expectfn *cur; bool found = false; - rcu_read_lock(); list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (!strcmp(cur->name, name)) { found = true; break; } } - rcu_read_unlock(); return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name); +/* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_symbol(const void *symbol) { struct nf_ct_helper_expectfn *cur; bool found = false; - rcu_read_lock(); list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (cur->expectfn == symbol) { found = true; break; } } - rcu_read_unlock(); return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6806b5e73567..dc7dfd68fafe 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1488,11 +1488,16 @@ static int ctnetlink_change_helper(struct nf_conn *ct, * treat the second attempt as a no-op instead of returning * an error. */ - if (help && help->helper && - !strcmp(help->helper->name, helpname)) - return 0; - else - return -EBUSY; + err = -EBUSY; + if (help) { + rcu_read_lock(); + helper = rcu_dereference(help->helper); + if (helper && !strcmp(helper->name, helpname)) + err = 0; + rcu_read_unlock(); + } + + return err; } if (!strcmp(helpname, "")) { @@ -1929,9 +1934,9 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, err = 0; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) - events = IPCT_RELATED; + events = 1 << IPCT_RELATED; else - events = IPCT_NEW; + events = 1 << IPCT_NEW; if (cda[CTA_LABELS] && ctnetlink_attach_labels(ct, cda) == 0) @@ -2675,8 +2680,8 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: - hlist_for_each_entry(exp, &nf_ct_expect_hash[cb->args[0]], - hnode) { + hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], + hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; @@ -2727,7 +2732,7 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; restart: - hlist_for_each_entry(exp, &help->expectations, lnode) { + hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { @@ -2789,6 +2794,12 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); + /* No expectation linked to this connection tracking. */ + if (!nfct_help(ct)) { + nf_ct_put(ct); + return 0; + } + c.data = ct; err = netlink_dump_start(ctnl, skb, nlh, &c); @@ -3133,23 +3144,27 @@ ctnetlink_create_expect(struct net *net, return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); + rcu_read_lock(); if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper == NULL) { + rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err_ct; } + rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; - goto err_ct; + goto err_rcu; } + rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err_ct; @@ -3159,11 +3174,13 @@ ctnetlink_create_expect(struct net *net, exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); - goto err_ct; + goto err_rcu; } err = nf_ct_expect_related_report(exp, portid, report); nf_ct_expect_put(exp); +err_rcu: + rcu_read_unlock(); err_ct: nf_ct_put(ct); return err; @@ -3442,6 +3459,7 @@ static void __exit ctnetlink_exit(void) #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif + synchronize_rcu(); } module_init(ctnetlink_init); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 94b14c5a8b17..82802e4a6640 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -903,6 +903,8 @@ static void __exit nf_nat_cleanup(void) #ifdef CONFIG_XFRM RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); #endif + synchronize_rcu(); + for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c index d43869879fcf..86067560a318 100644 --- a/net/netfilter/nf_nat_redirect.c +++ b/net/netfilter/nf_nat_redirect.c @@ -101,11 +101,13 @@ nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, rcu_read_lock(); idev = __in6_dev_get(skb->dev); if (idev != NULL) { + read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { newdst = ifa->addr; addr = true; break; } + read_unlock_bh(&idev->lock); } rcu_read_unlock(); diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index de8782345c86..d45558178da5 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -32,6 +32,13 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers"); +struct nfnl_cthelper { + struct list_head list; + struct nf_conntrack_helper helper; +}; + +static LIST_HEAD(nfnl_cthelper_list); + static int nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo) @@ -161,6 +168,7 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, int i, ret; struct nf_conntrack_expect_policy *expect_policy; struct nlattr *tb[NFCTH_POLICY_SET_MAX+1]; + unsigned int class_max; ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, nfnl_cthelper_expect_policy_set); @@ -170,19 +178,18 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, if (!tb[NFCTH_POLICY_SET_NUM]) return -EINVAL; - helper->expect_class_max = - ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM])); - - if (helper->expect_class_max != 0 && - helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES) + class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM])); + if (class_max == 0) + return -EINVAL; + if (class_max > NF_CT_MAX_EXPECT_CLASSES) return -EOVERFLOW; expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) * - helper->expect_class_max, GFP_KERNEL); + class_max, GFP_KERNEL); if (expect_policy == NULL) return -ENOMEM; - for (i=0; i<helper->expect_class_max; i++) { + for (i = 0; i < class_max; i++) { if (!tb[NFCTH_POLICY_SET+i]) goto err; @@ -191,6 +198,8 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, if (ret < 0) goto err; } + + helper->expect_class_max = class_max - 1; helper->expect_policy = expect_policy; return 0; err: @@ -203,18 +212,20 @@ nfnl_cthelper_create(const struct nlattr * const tb[], struct nf_conntrack_tuple *tuple) { struct nf_conntrack_helper *helper; + struct nfnl_cthelper *nfcth; int ret; if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN]) return -EINVAL; - helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL); - if (helper == NULL) + nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL); + if (nfcth == NULL) return -ENOMEM; + helper = &nfcth->helper; ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]); if (ret < 0) - goto err; + goto err1; strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); @@ -245,15 +256,101 @@ nfnl_cthelper_create(const struct nlattr * const tb[], ret = nf_conntrack_helper_register(helper); if (ret < 0) - goto err; + goto err2; + list_add_tail(&nfcth->list, &nfnl_cthelper_list); return 0; -err: - kfree(helper); +err2: + kfree(helper->expect_policy); +err1: + kfree(nfcth); return ret; } static int +nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy, + struct nf_conntrack_expect_policy *new_policy, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_POLICY_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, + nfnl_cthelper_expect_pol); + if (err < 0) + return err; + + if (!tb[NFCTH_POLICY_NAME] || + !tb[NFCTH_POLICY_EXPECT_MAX] || + !tb[NFCTH_POLICY_EXPECT_TIMEOUT]) + return -EINVAL; + + if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name)) + return -EBUSY; + + new_policy->max_expected = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); + new_policy->timeout = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT])); + + return 0; +} + +static int nfnl_cthelper_update_policy_all(struct nlattr *tb[], + struct nf_conntrack_helper *helper) +{ + struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1]; + struct nf_conntrack_expect_policy *policy; + int i, err; + + /* Check first that all policy attributes are well-formed, so we don't + * leave things in inconsistent state on errors. + */ + for (i = 0; i < helper->expect_class_max + 1; i++) { + + if (!tb[NFCTH_POLICY_SET + i]) + return -EINVAL; + + err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i], + &new_policy[i], + tb[NFCTH_POLICY_SET + i]); + if (err < 0) + return err; + } + /* Now we can safely update them. */ + for (i = 0; i < helper->expect_class_max + 1; i++) { + policy = (struct nf_conntrack_expect_policy *) + &helper->expect_policy[i]; + policy->max_expected = new_policy->max_expected; + policy->timeout = new_policy->timeout; + } + + return 0; +} + +static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1]; + unsigned int class_max; + int err; + + err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, + nfnl_cthelper_expect_policy_set); + if (err < 0) + return err; + + if (!tb[NFCTH_POLICY_SET_NUM]) + return -EINVAL; + + class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM])); + if (helper->expect_class_max + 1 != class_max) + return -EBUSY; + + return nfnl_cthelper_update_policy_all(tb, helper); +} + +static int nfnl_cthelper_update(const struct nlattr * const tb[], struct nf_conntrack_helper *helper) { @@ -263,8 +360,7 @@ nfnl_cthelper_update(const struct nlattr * const tb[], return -EBUSY; if (tb[NFCTH_POLICY]) { - ret = nfnl_cthelper_parse_expect_policy(helper, - tb[NFCTH_POLICY]); + ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]); if (ret < 0) return ret; } @@ -293,7 +389,8 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; struct nf_conntrack_tuple tuple; - int ret = 0, i; + struct nfnl_cthelper *nlcth; + int ret = 0; if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) return -EINVAL; @@ -304,31 +401,22 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, if (ret < 0) return ret; - rcu_read_lock(); - for (i = 0; i < nf_ct_helper_hsize && !helper; i++) { - hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { + list_for_each_entry(nlcth, &nfnl_cthelper_list, list) { + cur = &nlcth->helper; - /* skip non-userspace conntrack helpers. */ - if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) - continue; + if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN)) + continue; - if (strncmp(cur->name, helper_name, - NF_CT_HELPER_NAME_LEN) != 0) - continue; + if ((tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; - if ((tuple.src.l3num != cur->tuple.src.l3num || - tuple.dst.protonum != cur->tuple.dst.protonum)) - continue; + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; - if (nlh->nlmsg_flags & NLM_F_EXCL) { - ret = -EEXIST; - goto err; - } - helper = cur; - break; - } + helper = cur; + break; } - rcu_read_unlock(); if (helper == NULL) ret = nfnl_cthelper_create(tb, &tuple); @@ -336,9 +424,6 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, ret = nfnl_cthelper_update(tb, helper); return ret; -err: - rcu_read_unlock(); - return ret; } static int @@ -377,10 +462,10 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb, goto nla_put_failure; if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM, - htonl(helper->expect_class_max))) + htonl(helper->expect_class_max + 1))) goto nla_put_failure; - for (i=0; i<helper->expect_class_max; i++) { + for (i = 0; i < helper->expect_class_max + 1; i++) { nest_parms2 = nla_nest_start(skb, (NFCTH_POLICY_SET+i) | NLA_F_NESTED); if (nest_parms2 == NULL) @@ -502,11 +587,12 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { - int ret = -ENOENT, i; + int ret = -ENOENT; struct nf_conntrack_helper *cur; struct sk_buff *skb2; char *helper_name = NULL; struct nf_conntrack_tuple tuple; + struct nfnl_cthelper *nlcth; bool tuple_set = false; if (nlh->nlmsg_flags & NLM_F_DUMP) { @@ -527,45 +613,39 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, tuple_set = true; } - for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { + list_for_each_entry(nlcth, &nfnl_cthelper_list, list) { + cur = &nlcth->helper; + if (helper_name && + strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN)) + continue; - /* skip non-userspace conntrack helpers. */ - if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) - continue; + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; - if (helper_name && strncmp(cur->name, helper_name, - NF_CT_HELPER_NAME_LEN) != 0) { - continue; - } - if (tuple_set && - (tuple.src.l3num != cur->tuple.src.l3num || - tuple.dst.protonum != cur->tuple.dst.protonum)) - continue; - - skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { - ret = -ENOMEM; - break; - } + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { + ret = -ENOMEM; + break; + } - ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), - NFNL_MSG_CTHELPER_NEW, cur); - if (ret <= 0) { - kfree_skb(skb2); - break; - } + ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + NFNL_MSG_CTHELPER_NEW, cur); + if (ret <= 0) { + kfree_skb(skb2); + break; + } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); + if (ret > 0) + ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; - } + /* this avoids a loop in nfnetlink. */ + return ret == -EAGAIN ? -ENOBUFS : ret; } return ret; } @@ -576,10 +656,10 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, { char *helper_name = NULL; struct nf_conntrack_helper *cur; - struct hlist_node *tmp; struct nf_conntrack_tuple tuple; bool tuple_set = false, found = false; - int i, j = 0, ret; + struct nfnl_cthelper *nlcth, *n; + int j = 0, ret; if (tb[NFCTH_NAME]) helper_name = nla_data(tb[NFCTH_NAME]); @@ -592,28 +672,27 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, tuple_set = true; } - for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], - hnode) { - /* skip non-userspace conntrack helpers. */ - if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) - continue; + list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) { + cur = &nlcth->helper; + j++; - j++; + if (helper_name && + strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN)) + continue; - if (helper_name && strncmp(cur->name, helper_name, - NF_CT_HELPER_NAME_LEN) != 0) { - continue; - } - if (tuple_set && - (tuple.src.l3num != cur->tuple.src.l3num || - tuple.dst.protonum != cur->tuple.dst.protonum)) - continue; + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; - found = true; - nf_conntrack_helper_unregister(cur); - } + found = true; + nf_conntrack_helper_unregister(cur); + kfree(cur->expect_policy); + + list_del(&nlcth->list); + kfree(nlcth); } + /* Make sure we return success if we flush and there is no helpers */ return (found || j == 0) ? 0 : -ENOENT; } @@ -662,20 +741,16 @@ err_out: static void __exit nfnl_cthelper_exit(void) { struct nf_conntrack_helper *cur; - struct hlist_node *tmp; - int i; + struct nfnl_cthelper *nlcth, *n; nfnetlink_subsys_unregister(&nfnl_cthelper_subsys); - for (i=0; i<nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], - hnode) { - /* skip non-userspace conntrack helpers. */ - if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) - continue; + list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) { + cur = &nlcth->helper; - nf_conntrack_helper_unregister(cur); - } + nf_conntrack_helper_unregister(cur); + kfree(cur->expect_policy); + kfree(nlcth); } } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 139e0867e56e..47d6656c9119 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -646,8 +646,8 @@ static void __exit cttimeout_exit(void) #ifdef CONFIG_NF_CONNTRACK_TIMEOUT RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); + synchronize_rcu(); #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - rcu_barrier(); } module_init(cttimeout_init); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 3ee0b8a000a4..933509ebf3d3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -443,7 +443,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); - return NULL; + goto nlmsg_failure; } nlh = nlmsg_put(skb, 0, 0, @@ -452,7 +452,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); - return NULL; + goto nlmsg_failure; } nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = entry->state.pf; @@ -598,12 +598,17 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } nlh->nlmsg_len = skb->len; + if (seclen) + security_release_secctx(secdata, seclen); return skb; nla_put_failure: skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); +nlmsg_failure: + if (seclen) + security_release_secctx(secdata, seclen); return NULL; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index eb2721af898d..c4dad1254ead 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -21,6 +21,7 @@ struct nft_hash { enum nft_registers sreg:8; enum nft_registers dreg:8; u8 len; + bool autogen_seed:1; u32 modulus; u32 seed; u32 offset; @@ -82,10 +83,12 @@ static int nft_hash_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - if (tb[NFTA_HASH_SEED]) + if (tb[NFTA_HASH_SEED]) { priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); - else + } else { + priv->autogen_seed = true; get_random_bytes(&priv->seed, sizeof(priv->seed)); + } return nft_validate_register_load(priv->sreg, len) && nft_validate_register_store(ctx, priv->dreg, NULL, @@ -105,7 +108,8 @@ static int nft_hash_dump(struct sk_buff *skb, goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) + if (!priv->autogen_seed && + nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) goto nla_put_failure; if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 27241a767f17..c64aca611ac5 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -104,7 +104,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); tcp_hdrlen = tcph->doff * 4; - if (len < tcp_hdrlen) + if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr)) return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { @@ -152,6 +152,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (len > tcp_hdrlen) return 0; + /* tcph->doff has 4 bits, do not wrap it to 0 */ + if (tcp_hdrlen >= 15 * 4) + return 0; + /* * MSS Option not found ?! add it.. */ diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 80cb7babeb64..df7f1df00330 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -393,7 +393,8 @@ tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, rcu_read_lock(); indev = __in6_dev_get(skb->dev); - if (indev) + if (indev) { + read_lock_bh(&indev->lock); list_for_each_entry(ifa, &indev->addr_list, if_list) { if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED)) continue; @@ -401,6 +402,8 @@ tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, laddr = &ifa->addr; break; } + read_unlock_bh(&indev->lock); + } rcu_read_unlock(); return laddr ? laddr : daddr; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e0a87776a010..7b2c2fce408a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -643,8 +643,8 @@ static bool skb_nfct_cached(struct net *net, */ if (nf_ct_is_confirmed(ct)) nf_ct_delete(ct, 0, 0); - else - nf_conntrack_put(&ct->ct_general); + + nf_conntrack_put(&ct->ct_general); nf_ct_set(skb, NULL, 0); return false; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 9d4bb8eb63f2..3f76cb765e5b 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -527,7 +527,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) /* Link layer. */ clear_vlan(key); - if (key->mac_proto == MAC_PROTO_NONE) { + if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { if (unlikely(eth_type_vlan(skb->protocol))) return -EINVAL; @@ -745,7 +745,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) { - return key_extract(skb, key); + int res; + + res = key_extract(skb, key); + if (!res) + key->mac_proto &= ~SW_FLOW_KEY_INVALID; + + return res; } static int key_extract_mac_proto(struct sk_buff *skb) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a0dbe7ca8f72..ea81ccf3c7d6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3665,6 +3665,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + if (val > INT_MAX) + return -EINVAL; po->tp_reserve = val; return 0; } @@ -3834,6 +3836,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); + if (len < sizeof(int)) + return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { @@ -4193,8 +4197,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; if (po->tp_version >= TPACKET_V3 && - (int)(req->tp_block_size - - BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + req->tp_block_size <= + BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv)) goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) @@ -4205,6 +4209,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; + if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index ae5ac175b2be..9da7368b0140 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -658,7 +658,9 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } if (plen != len) { - skb_pad(skb, plen - len); + rc = skb_pad(skb, plen - len); + if (rc) + goto out_node; skb_put(skb, plen - len); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b70aa57319ea..e05b924618a0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -529,20 +529,20 @@ errout: return err; } -static int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb) +static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) { - a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL); - if (!a->act_cookie) - return -ENOMEM; + struct tc_cookie *c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return NULL; - a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL); - if (!a->act_cookie->data) { - kfree(a->act_cookie); - return -ENOMEM; + c->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL); + if (!c->data) { + kfree(c); + return NULL; } - a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]); + c->len = nla_len(tb[TCA_ACT_COOKIE]); - return 0; + return c; } struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, @@ -551,6 +551,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, { struct tc_action *a; struct tc_action_ops *a_o; + struct tc_cookie *cookie = NULL; char act_name[IFNAMSIZ]; struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; @@ -566,6 +567,18 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, goto err_out; if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) goto err_out; + if (tb[TCA_ACT_COOKIE]) { + int cklen = nla_len(tb[TCA_ACT_COOKIE]); + + if (cklen > TC_COOKIE_MAX_SIZE) + goto err_out; + + cookie = nla_memdup_cookie(tb); + if (!cookie) { + err = -ENOMEM; + goto err_out; + } + } } else { err = -EINVAL; if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) @@ -604,20 +617,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, if (err < 0) goto err_mod; - if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) { - err = -EINVAL; - tcf_hash_release(a, bind); - goto err_mod; - } - - if (nla_memdup_cookie(a, tb) < 0) { - err = -ENOMEM; - tcf_hash_release(a, bind); - goto err_mod; + if (name == NULL && tb[TCA_ACT_COOKIE]) { + if (a->act_cookie) { + kfree(a->act_cookie->data); + kfree(a->act_cookie); } + a->act_cookie = cookie; } /* module count goes up only when brand new policy is created @@ -632,6 +637,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, err_mod: module_put(a_o->owner); err_out: + if (cookie) { + kfree(cookie->data); + kfree(cookie); + } return ERR_PTR(err); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b052b27a984e..1a2f9e964330 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -794,7 +794,7 @@ static void attach_default_qdiscs(struct net_device *dev) } } #ifdef CONFIG_NET_SCHED - if (dev->qdisc) + if (dev->qdisc != &noop_qdisc) qdisc_hash_add(dev->qdisc); #endif } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 0439a1a68367..a9708da28eb5 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -246,6 +246,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; + if (sctp_stream_new(asoc, gfp)) + goto fail_init; + /* Assume that peer would support both address types unless we are * told otherwise. */ @@ -264,7 +267,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp)) - goto fail_init; + goto stream_free; asoc->active_key_id = ep->active_key_id; asoc->prsctp_enable = ep->prsctp_enable; @@ -287,6 +290,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a return asoc; +stream_free: + sctp_stream_free(asoc->stream); fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); @@ -1407,7 +1412,7 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc, /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ -void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) +void sctp_assoc_sync_pmtu(struct sctp_association *asoc) { struct sctp_transport *t; __u32 pmtu = 0; @@ -1419,8 +1424,8 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { - sctp_transport_update_pmtu(sk, t, - SCTP_TRUNC4(dst_mtu(t->dst))); + sctp_transport_update_pmtu( + t, SCTP_TRUNC4(dst_mtu(t->dst))); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) diff --git a/net/sctp/input.c b/net/sctp/input.c index 2a28ab20487f..0e06a278d2a9 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -401,10 +401,10 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, if (t->param_flags & SPP_PMTUD_ENABLE) { /* Update transports view of the MTU */ - sctp_transport_update_pmtu(sk, t, pmtu); + sctp_transport_update_pmtu(t, pmtu); /* Update association pmtu. */ - sctp_assoc_sync_pmtu(sk, asoc); + sctp_assoc_sync_pmtu(asoc); } /* Retransmit with the new pmtu setting. diff --git a/net/sctp/output.c b/net/sctp/output.c index 1224421036b3..1409a875ad8e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -86,43 +86,53 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, { struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; + struct sock *sk; pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); - packet->vtag = vtag; - if (asoc && tp->dst) { - struct sock *sk = asoc->base.sk; - - rcu_read_lock(); - if (__sk_dst_get(sk) != tp->dst) { - dst_hold(tp->dst); - sk_setup_caps(sk, tp->dst); - } - - if (sk_can_gso(sk)) { - struct net_device *dev = tp->dst->dev; + /* do the following jobs only once for a flush schedule */ + if (!sctp_packet_empty(packet)) + return; - packet->max_size = dev->gso_max_size; - } else { - packet->max_size = asoc->pathmtu; - } - rcu_read_unlock(); + /* set packet max_size with pathmtu */ + packet->max_size = tp->pathmtu; + if (!asoc) + return; - } else { - packet->max_size = tp->pathmtu; + /* update dst or transport pathmtu if in need */ + sk = asoc->base.sk; + if (!sctp_transport_dst_check(tp)) { + sctp_transport_route(tp, NULL, sctp_sk(sk)); + if (asoc->param_flags & SPP_PMTUD_ENABLE) + sctp_assoc_sync_pmtu(asoc); + } else if (!sctp_transport_pmtu_check(tp)) { + if (asoc->param_flags & SPP_PMTUD_ENABLE) + sctp_assoc_sync_pmtu(asoc); } - if (ecn_capable && sctp_packet_empty(packet)) { - struct sctp_chunk *chunk; + /* If there a is a prepend chunk stick it on the list before + * any other chunks get appended. + */ + if (ecn_capable) { + struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc); - /* If there a is a prepend chunk stick it on the list before - * any other chunks get appended. - */ - chunk = sctp_get_ecne_prepend(asoc); if (chunk) sctp_packet_append_chunk(packet, chunk); } + + if (!tp->dst) + return; + + /* set packet max_size with gso_max_size if gso is enabled*/ + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size + : asoc->pathmtu; + rcu_read_unlock(); } /* Initialize the packet structure. */ @@ -582,12 +592,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sh->vtag = htonl(packet->vtag); sh->checksum = 0; - /* update dst if in need */ - if (!sctp_transport_dst_check(tp)) { - sctp_transport_route(tp, NULL, sctp_sk(sk)); - if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE) - sctp_assoc_sync_pmtu(sk, asoc); - } + /* drop packet if no dst */ dst = dst_clone(tp->dst); if (!dst) { IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -704,7 +709,7 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, */ if ((sctp_sk(asoc->base.sk)->nodelay || inflight == 0) && - !chunk->msg->force_delay) + !asoc->force_delay) /* Nothing unacked */ return SCTP_XMIT_OK; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 025ccff67072..8081476ed313 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1026,8 +1026,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. */ - if (chunk->sinfo.sinfo_stream >= - asoc->c.sinit_num_ostreams) { + if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) { /* Mark as failed send. */ sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 206377fe91ec..a0b29d43627f 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -361,8 +361,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sctp_seq_dump_remote_addrs(seq, assoc); seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " "%8d %8d %8d %8d", - assoc->hbinterval, assoc->c.sinit_max_instreams, - assoc->c.sinit_num_ostreams, assoc->max_retrans, + assoc->hbinterval, assoc->stream->incnt, + assoc->stream->outcnt, assoc->max_retrans, assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, atomic_read(&sk->sk_wmem_alloc), diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 969a30c7bb54..118faff6a332 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2460,15 +2460,10 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * association. */ if (!asoc->temp) { - int error; - - asoc->stream = sctp_stream_new(asoc->c.sinit_max_instreams, - asoc->c.sinit_num_ostreams, gfp); - if (!asoc->stream) + if (sctp_stream_init(asoc, gfp)) goto clean_up; - error = sctp_assoc_set_id(asoc, gfp); - if (error) + if (sctp_assoc_set_id(asoc, gfp)) goto clean_up; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index e03bb1aab4d0..24c6ccce7539 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3946,7 +3946,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams) + if (ntohs(skip->stream) >= asoc->stream->incnt) goto discard_noforce; } @@ -4017,7 +4017,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast( /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams) + if (ntohs(skip->stream) >= asoc->stream->incnt) goto gen_shutdown; } @@ -6353,7 +6353,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and discard the DATA chunk. */ sid = ntohs(data_hdr->stream); - if (sid >= asoc->c.sinit_max_instreams) { + if (sid >= asoc->stream->incnt) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0f378ea2ae38..d9d4c92e06b3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1907,7 +1907,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) } if (asoc->pmtu_pending) - sctp_assoc_pending_pmtu(sk, asoc); + sctp_assoc_pending_pmtu(asoc); /* If fragmentation is disabled and the message length exceeds the * association fragmentation point, return EMSGSIZE. The I-D @@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) } /* Check for invalid stream. */ - if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) { + if (sinfo->sinfo_stream >= asoc->stream->outcnt) { err = -EINVAL; goto out_free; } @@ -1965,7 +1965,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) err = PTR_ERR(datamsg); goto out_free; } - datamsg->force_delay = !!(msg->msg_flags & MSG_MORE); + asoc->force_delay = !!(msg->msg_flags & MSG_MORE); /* Now send the (possibly) fragmented message. */ list_for_each_entry(chunk, &datamsg->chunks, frag_list) { @@ -2435,7 +2435,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) { if (trans) { trans->pathmtu = params->spp_pathmtu; - sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc); + sctp_assoc_sync_pmtu(asoc); } else if (asoc) { asoc->pathmtu = params->spp_pathmtu; } else { @@ -2451,7 +2451,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, (trans->param_flags & ~SPP_PMTUD) | pmtud_change; if (update) { sctp_transport_pmtu(trans, sctp_opt2sk(sp)); - sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc); + sctp_assoc_sync_pmtu(asoc); } } else if (asoc) { asoc->param_flags = @@ -4461,8 +4461,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - info->sctpi_instrms = asoc->c.sinit_max_instreams; - info->sctpi_outstrms = asoc->c.sinit_num_ostreams; + info->sctpi_instrms = asoc->stream->incnt; + info->sctpi_outstrms = asoc->stream->outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) @@ -4691,8 +4691,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - status.sstat_instrms = asoc->c.sinit_max_instreams; - status.sstat_outstrms = asoc->c.sinit_num_ostreams; + status.sstat_instrms = asoc->stream->incnt; + status.sstat_outstrms = asoc->stream->outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, @@ -7034,6 +7034,9 @@ int sctp_inet_listen(struct socket *sock, int backlog) if (sock->state != SS_UNCONNECTED) goto out; + if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED)) + goto out; + /* If backlog is zero, disable listening. */ if (!backlog) { if (sctp_sstate(sk, CLOSED)) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 1c6cc04fa3a4..bbed997e1c5f 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -35,33 +35,60 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> -struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp) +int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) { struct sctp_stream *stream; int i; stream = kzalloc(sizeof(*stream), gfp); if (!stream) - return NULL; + return -ENOMEM; - stream->outcnt = outcnt; + stream->outcnt = asoc->c.sinit_num_ostreams; stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); if (!stream->out) { kfree(stream); - return NULL; + return -ENOMEM; } for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - stream->incnt = incnt; + asoc->stream = stream; + + return 0; +} + +int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) +{ + struct sctp_stream *stream = asoc->stream; + int i; + + /* Initial stream->out size may be very big, so free it and alloc + * a new one with new outcnt to save memory. + */ + kfree(stream->out); + stream->outcnt = asoc->c.sinit_num_ostreams; + stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); + if (!stream->out) + goto nomem; + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + stream->incnt = asoc->c.sinit_max_instreams; stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); - kfree(stream); - return NULL; + goto nomem; } - return stream; + return 0; + +nomem: + asoc->stream = NULL; + kfree(stream); + + return -ENOMEM; } void sctp_stream_free(struct sctp_stream *stream) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 3379668af368..721eeebfcd8a 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -251,14 +251,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } -void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu) +void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { - struct dst_entry *dst; + struct dst_entry *dst = sctp_transport_dst_check(t); if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n", - __func__, pmtu, - SCTP_DEFAULT_MINSEGMENT); + __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); /* Use default minimum segment size and disable * pmtu discovery on this transport. */ @@ -267,17 +266,13 @@ void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 p t->pathmtu = pmtu; } - dst = sctp_transport_dst_check(t); - if (!dst) - t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); - if (dst) { - dst->ops->update_pmtu(dst, sk, NULL, pmtu); - + dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu); dst = sctp_transport_dst_check(t); - if (!dst) - t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); } + + if (!dst) + t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk); } /* Caches the dst entry and source address for a transport's destination diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 7130e73bd42c..bdce99f9407a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -866,6 +866,14 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, if (!tsk_peer_msg(tsk, hdr)) goto exit; + if (unlikely(msg_errcode(hdr))) { + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk), + tsk_peer_port(tsk)); + sk->sk_state_change(sk); + goto exit; + } + tsk->probe_unacked = false; if (mtyp == CONN_PROBE) { @@ -1083,7 +1091,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) } } while (sent < dlen && !rc); - return rc ? rc : sent; + return sent ? sent : rc; } /** @@ -1259,7 +1267,10 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) struct sock *sk = sock->sk; DEFINE_WAIT(wait); long timeo = *timeop; - int err; + int err = sock_error(sk); + + if (err) + return err; for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); @@ -1281,6 +1292,10 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) err = sock_intr_errno(timeo); if (signal_pending(current)) break; + + err = sock_error(sk); + if (err) + break; } finish_wait(sk_sleep(sk), &wait); *timeop = timeo; @@ -1484,7 +1499,7 @@ restart: if (unlikely(flags & MSG_PEEK)) goto exit; - tsk->rcv_unacked += tsk_inc(tsk, hlen + sz); + tsk->rcv_unacked += tsk_inc(tsk, hlen + msg_data_sz(msg)); if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4))) tipc_sk_send_ack(tsk); tsk_advance_rx_queue(sk); @@ -1551,6 +1566,8 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); struct tipc_msg *hdr = buf_msg(skb); + u32 pport = msg_origport(hdr); + u32 pnode = msg_orignode(hdr); if (unlikely(msg_mcast(hdr))) return false; @@ -1558,18 +1575,28 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) switch (sk->sk_state) { case TIPC_CONNECTING: /* Accept only ACK or NACK message */ - if (unlikely(!msg_connected(hdr))) - return false; + if (unlikely(!msg_connected(hdr))) { + if (pport != tsk_peer_port(tsk) || + pnode != tsk_peer_node(tsk)) + return false; + + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + sk->sk_err = ECONNREFUSED; + sk->sk_state_change(sk); + return true; + } if (unlikely(msg_errcode(hdr))) { tipc_set_sk_state(sk, TIPC_DISCONNECTING); sk->sk_err = ECONNREFUSED; + sk->sk_state_change(sk); return true; } if (unlikely(!msg_isdata(hdr))) { tipc_set_sk_state(sk, TIPC_DISCONNECTING); sk->sk_err = EINVAL; + sk->sk_state_change(sk); return true; } @@ -1581,8 +1608,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) return true; /* If empty 'ACK-' message, wake up sleeping connect() */ - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); + sk->sk_data_ready(sk); /* 'ACK-' message is neither accepted nor rejected: */ msg_set_dest_droppable(hdr, 1); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 16b6b5988be9..570a2b67ca10 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -132,12 +132,10 @@ static int wiphy_resume(struct device *dev) /* Age scan results with time spent in suspend */ cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at); - if (rdev->ops->resume) { - rtnl_lock(); - if (rdev->wiphy.registered) - ret = rdev_resume(rdev); - rtnl_unlock(); - } + rtnl_lock(); + if (rdev->wiphy.registered && rdev->ops->resume) + ret = rdev_resume(rdev); + rtnl_unlock(); return ret; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 46bdb4fbed0b..e23570b647ae 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -395,7 +395,7 @@ resume: if (xo) xfrm_gro = xo->flags & XFRM_GRO; - err = x->inner_mode->afinfo->transport_finish(skb, async); + err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async); if (xfrm_gro) { skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 236cbbc0ab9c..dfc77b9c5e5a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1006,6 +1006,10 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + + if (cnt) + xfrm_garbage_collect(net); + return err; } EXPORT_SYMBOL(xfrm_policy_flush); diff --git a/samples/statx/test-statx.c b/samples/statx/test-statx.c index 8571d766331d..d4d77b09412c 100644 --- a/samples/statx/test-statx.c +++ b/samples/statx/test-statx.c @@ -141,8 +141,8 @@ static void dump_statx(struct statx *stx) if (stx->stx_mask & STATX_BTIME) print_time(" Birth: ", &stx->stx_btime); - if (stx->stx_attributes) { - unsigned char bits; + if (stx->stx_attributes_mask) { + unsigned char bits, mbits; int loop, byte; static char attr_representation[64 + 1] = @@ -160,14 +160,18 @@ static void dump_statx(struct statx *stx) printf("Attributes: %016llx (", stx->stx_attributes); for (byte = 64 - 8; byte >= 0; byte -= 8) { bits = stx->stx_attributes >> byte; + mbits = stx->stx_attributes_mask >> byte; for (loop = 7; loop >= 0; loop--) { int bit = byte + loop; - if (bits & 0x80) + if (!(mbits & 0x80)) + putchar('.'); /* Not supported */ + else if (bits & 0x80) putchar(attr_representation[63 - bit]); else - putchar('-'); + putchar('-'); /* Not set */ bits <<= 1; + mbits <<= 1; } if (byte) putchar(' '); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 0a07f9014944..7234e61e7ce3 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -155,7 +155,7 @@ else # $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files # and locates generated .h files # FIXME: Replace both with specific CFLAGS* statements in the makefiles -__c_flags = $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \ +__c_flags = $(if $(obj),$(call addtree,-I$(src)) -I$(obj)) \ $(call flags,_c_flags) __a_flags = $(call flags,_a_flags) __cpp_flags = $(call flags,_cpp_flags) diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c index 26d208b435a0..cfddddb9c9d7 100644 --- a/scripts/kconfig/gconf.c +++ b/scripts/kconfig/gconf.c @@ -914,7 +914,7 @@ on_treeview2_button_press_event(GtkWidget * widget, current = menu; display_tree_part(); gtk_widget_set_sensitive(back_btn, TRUE); - } else if ((col == COL_OPTION)) { + } else if (col == COL_OPTION) { toggle_sym_value(menu); gtk_tree_view_expand_row(view, path, TRUE); } diff --git a/security/keys/gc.c b/security/keys/gc.c index addf060399e0..9cb4fe4478a1 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -46,7 +46,7 @@ static unsigned long key_gc_flags; * immediately unlinked. */ struct key_type key_type_dead = { - .name = "dead", + .name = ".dead", }; /* diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 52c34532c785..4ad3212adebe 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -273,7 +273,8 @@ error: * Create and join an anonymous session keyring or join a named session * keyring, creating it if necessary. A named session keyring must have Search * permission for it to be joined. Session keyrings without this permit will - * be skipped over. + * be skipped over. It is not permitted for userspace to create or join + * keyrings whose name begin with a dot. * * If successful, the ID of the joined session keyring will be returned. */ @@ -290,12 +291,16 @@ long keyctl_join_session_keyring(const char __user *_name) ret = PTR_ERR(name); goto error; } + + ret = -EPERM; + if (name[0] == '.') + goto error_name; } /* join the session */ ret = join_session_keyring(name); +error_name: kfree(name); - error: return ret; } @@ -1253,8 +1258,8 @@ error: * Read or set the default keyring in which request_key() will cache keys and * return the old setting. * - * If a process keyring is specified then this will be created if it doesn't - * yet exist. The old setting will be returned if successful. + * If a thread or process keyring is specified then it will be created if it + * doesn't yet exist. The old setting will be returned if successful. */ long keyctl_set_reqkey_keyring(int reqkey_defl) { @@ -1279,11 +1284,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl) case KEY_REQKEY_DEFL_PROCESS_KEYRING: ret = install_process_keyring_to_cred(new); - if (ret < 0) { - if (ret != -EEXIST) - goto error; - ret = 0; - } + if (ret < 0) + goto error; goto set; case KEY_REQKEY_DEFL_DEFAULT: diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index b6fdd22205b1..9139b18fc863 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -128,13 +128,18 @@ error: } /* - * Install a fresh thread keyring directly to new credentials. This keyring is - * allowed to overrun the quota. + * Install a thread keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ int install_thread_keyring_to_cred(struct cred *new) { struct key *keyring; + if (new->thread_keyring) + return 0; + keyring = keyring_alloc("_tid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, @@ -147,7 +152,9 @@ int install_thread_keyring_to_cred(struct cred *new) } /* - * Install a fresh thread keyring, discarding the old one. + * Install a thread keyring to the current task if it didn't have one already. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ static int install_thread_keyring(void) { @@ -158,8 +165,6 @@ static int install_thread_keyring(void) if (!new) return -ENOMEM; - BUG_ON(new->thread_keyring); - ret = install_thread_keyring_to_cred(new); if (ret < 0) { abort_creds(new); @@ -170,17 +175,17 @@ static int install_thread_keyring(void) } /* - * Install a process keyring directly to a credentials struct. + * Install a process keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. * - * Returns -EEXIST if there was already a process keyring, 0 if one installed, - * and other value on any other error + * Return: 0 if a process keyring is now present; -errno on failure. */ int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->process_keyring) - return -EEXIST; + return 0; keyring = keyring_alloc("_pid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, @@ -194,11 +199,9 @@ int install_process_keyring_to_cred(struct cred *new) } /* - * Make sure a process keyring is installed for the current process. The - * existing process keyring is not replaced. + * Install a process keyring to the current task if it didn't have one already. * - * Returns 0 if there is a process keyring by the end of this function, some - * error otherwise. + * Return: 0 if a process keyring is now present; -errno on failure. */ static int install_process_keyring(void) { @@ -212,14 +215,18 @@ static int install_process_keyring(void) ret = install_process_keyring_to_cred(new); if (ret < 0) { abort_creds(new); - return ret != -EEXIST ? ret : 0; + return ret; } return commit_creds(new); } /* - * Install a session keyring directly to a credentials struct. + * Install the given keyring as the session keyring of the given credentials + * struct, replacing the existing one if any. If the given keyring is NULL, + * then install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) { @@ -254,8 +261,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) } /* - * Install a session keyring, discarding the old one. If a keyring is not - * supplied, an empty one is invented. + * Install the given keyring as the session keyring of the current task, + * replacing the existing one if any. If the given keyring is NULL, then + * install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ static int install_session_keyring(struct key *keyring) { diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c index 3b693e924db7..12ba83367b1b 100644 --- a/sound/core/seq/seq_lock.c +++ b/sound/core/seq/seq_lock.c @@ -28,19 +28,16 @@ /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { - int max_count = 5 * HZ; + int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { - if (max_count == 0) { - pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line); - break; - } + if (warn_count-- == 0) + pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); - max_count--; } } diff --git a/sound/firewire/lib.h b/sound/firewire/lib.h index f6769312ebfc..c3768cd494a5 100644 --- a/sound/firewire/lib.h +++ b/sound/firewire/lib.h @@ -45,7 +45,7 @@ struct snd_fw_async_midi_port { struct snd_rawmidi_substream *substream; snd_fw_async_midi_port_fill fill; - unsigned int consume_bytes; + int consume_bytes; }; int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port, diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 74d7fb6efce6..413ab6313bb6 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -227,11 +227,11 @@ static void do_registration(struct work_struct *work) if (err < 0) goto error; - err = detect_quirks(oxfw); + err = snd_oxfw_stream_discover(oxfw); if (err < 0) goto error; - err = snd_oxfw_stream_discover(oxfw); + err = detect_quirks(oxfw); if (err < 0) goto error; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 5c7219fb3aa8..9e2a3404a836 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -621,7 +621,7 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = { .codec_dai_name = "snd-soc-dummy-dai", .codec_name = "snd-soc-dummy", .platform_name = "sst-mfld-platform", - .ignore_suspend = 1, + .nonatomic = true, .dynamic = 1, .dpcm_playback = 1, .dpcm_capture = 1, @@ -634,7 +634,6 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = { .codec_dai_name = "snd-soc-dummy-dai", .codec_name = "snd-soc-dummy", .platform_name = "sst-mfld-platform", - .ignore_suspend = 1, .nonatomic = true, .dynamic = 1, .dpcm_playback = 1, @@ -661,6 +660,7 @@ static struct snd_soc_dai_link byt_rt5640_dais[] = { | SND_SOC_DAIFMT_CBS_CFS, .be_hw_params_fixup = byt_rt5640_codec_fixup, .ignore_suspend = 1, + .nonatomic = true, .dpcm_playback = 1, .dpcm_capture = 1, .init = byt_rt5640_init, diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index 3186f015939f..8164bec63bf1 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -235,7 +235,6 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = { .codec_dai_name = "snd-soc-dummy-dai", .codec_name = "snd-soc-dummy", .platform_name = "sst-mfld-platform", - .ignore_suspend = 1, .nonatomic = true, .dynamic = 1, .dpcm_playback = 1, @@ -249,7 +248,6 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = { .codec_dai_name = "snd-soc-dummy-dai", .codec_name = "snd-soc-dummy", .platform_name = "sst-mfld-platform", - .ignore_suspend = 1, .nonatomic = true, .dynamic = 1, .dpcm_playback = 1, diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 3e9b1c0bb1ce..058bc99c6c34 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -933,6 +933,7 @@ static int soc_tplg_denum_create_texts(struct soc_enum *se, } } + se->texts = (const char * const *)se->dobj.control.dtexts; return 0; err: diff --git a/sound/soc/sti/uniperif.h b/sound/soc/sti/uniperif.h index d487dd2ef016..cfcb0ea9d99d 100644 --- a/sound/soc/sti/uniperif.h +++ b/sound/soc/sti/uniperif.h @@ -1299,6 +1299,7 @@ struct uniperif { int ver; /* IP version, used by register access macros */ struct regmap_field *clk_sel; struct regmap_field *valid_sel; + spinlock_t irq_lock; /* use to prevent race condition with IRQ */ /* capabilities */ const struct snd_pcm_hardware *hw; diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c index 60ae31a303ab..d7e8dd46d2cc 100644 --- a/sound/soc/sti/uniperif_player.c +++ b/sound/soc/sti/uniperif_player.c @@ -65,10 +65,13 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id) unsigned int status; unsigned int tmp; - if (player->state == UNIPERIF_STATE_STOPPED) { - /* Unexpected IRQ: do nothing */ - return IRQ_NONE; - } + spin_lock(&player->irq_lock); + if (!player->substream) + goto irq_spin_unlock; + + snd_pcm_stream_lock(player->substream); + if (player->state == UNIPERIF_STATE_STOPPED) + goto stream_unlock; /* Get interrupt status & clear them immediately */ status = GET_UNIPERIF_ITS(player); @@ -88,9 +91,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id) SET_UNIPERIF_ITM_BCLR_FIFO_ERROR(player); /* Stop the player */ - snd_pcm_stream_lock(player->substream); snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN); - snd_pcm_stream_unlock(player->substream); } ret = IRQ_HANDLED; @@ -104,9 +105,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id) SET_UNIPERIF_ITM_BCLR_DMA_ERROR(player); /* Stop the player */ - snd_pcm_stream_lock(player->substream); snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN); - snd_pcm_stream_unlock(player->substream); ret = IRQ_HANDLED; } @@ -116,7 +115,8 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id) if (!player->underflow_enabled) { dev_err(player->dev, "unexpected Underflow recovering\n"); - return -EPERM; + ret = -EPERM; + goto stream_unlock; } /* Read the underflow recovery duration */ tmp = GET_UNIPERIF_STATUS_1_UNDERFLOW_DURATION(player); @@ -138,13 +138,16 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id) dev_err(player->dev, "Underflow recovery failed\n"); /* Stop the player */ - snd_pcm_stream_lock(player->substream); snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN); - snd_pcm_stream_unlock(player->substream); ret = IRQ_HANDLED; } +stream_unlock: + snd_pcm_stream_unlock(player->substream); +irq_spin_unlock: + spin_unlock(&player->irq_lock); + return ret; } @@ -588,6 +591,7 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol, struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *player = priv->dai_data.uni; struct snd_aes_iec958 *iec958 = &player->stream_settings.iec958; + unsigned long flags; mutex_lock(&player->ctrl_lock); iec958->status[0] = ucontrol->value.iec958.status[0]; @@ -596,12 +600,14 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol, iec958->status[3] = ucontrol->value.iec958.status[3]; mutex_unlock(&player->ctrl_lock); + spin_lock_irqsave(&player->irq_lock, flags); if (player->substream && player->substream->runtime) uni_player_set_channel_status(player, player->substream->runtime); else uni_player_set_channel_status(player, NULL); + spin_unlock_irqrestore(&player->irq_lock, flags); return 0; } @@ -686,9 +692,12 @@ static int uni_player_startup(struct snd_pcm_substream *substream, { struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *player = priv->dai_data.uni; + unsigned long flags; int ret; + spin_lock_irqsave(&player->irq_lock, flags); player->substream = substream; + spin_unlock_irqrestore(&player->irq_lock, flags); player->clk_adj = 0; @@ -986,12 +995,15 @@ static void uni_player_shutdown(struct snd_pcm_substream *substream, { struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *player = priv->dai_data.uni; + unsigned long flags; + spin_lock_irqsave(&player->irq_lock, flags); if (player->state != UNIPERIF_STATE_STOPPED) /* Stop the player */ uni_player_stop(player); player->substream = NULL; + spin_unlock_irqrestore(&player->irq_lock, flags); } static int uni_player_parse_dt_audio_glue(struct platform_device *pdev, @@ -1096,6 +1108,7 @@ int uni_player_init(struct platform_device *pdev, } mutex_init(&player->ctrl_lock); + spin_lock_init(&player->irq_lock); /* Ensure that disabled by default */ SET_UNIPERIF_CONFIG_BACK_STALL_REQ_DISABLE(player); diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c index 93a8df6ed880..ee0055e60852 100644 --- a/sound/soc/sti/uniperif_reader.c +++ b/sound/soc/sti/uniperif_reader.c @@ -46,10 +46,15 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id) struct uniperif *reader = dev_id; unsigned int status; + spin_lock(&reader->irq_lock); + if (!reader->substream) + goto irq_spin_unlock; + + snd_pcm_stream_lock(reader->substream); if (reader->state == UNIPERIF_STATE_STOPPED) { /* Unexpected IRQ: do nothing */ dev_warn(reader->dev, "unexpected IRQ\n"); - return IRQ_HANDLED; + goto stream_unlock; } /* Get interrupt status & clear them immediately */ @@ -60,13 +65,16 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id) if (unlikely(status & UNIPERIF_ITS_FIFO_ERROR_MASK(reader))) { dev_err(reader->dev, "FIFO error detected\n"); - snd_pcm_stream_lock(reader->substream); snd_pcm_stop(reader->substream, SNDRV_PCM_STATE_XRUN); - snd_pcm_stream_unlock(reader->substream); - return IRQ_HANDLED; + ret = IRQ_HANDLED; } +stream_unlock: + snd_pcm_stream_unlock(reader->substream); +irq_spin_unlock: + spin_unlock(&reader->irq_lock); + return ret; } @@ -347,9 +355,12 @@ static int uni_reader_startup(struct snd_pcm_substream *substream, { struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *reader = priv->dai_data.uni; + unsigned long flags; int ret; + spin_lock_irqsave(&reader->irq_lock, flags); reader->substream = substream; + spin_unlock_irqrestore(&reader->irq_lock, flags); if (!UNIPERIF_TYPE_IS_TDM(reader)) return 0; @@ -375,12 +386,15 @@ static void uni_reader_shutdown(struct snd_pcm_substream *substream, { struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai); struct uniperif *reader = priv->dai_data.uni; + unsigned long flags; + spin_lock_irqsave(&reader->irq_lock, flags); if (reader->state != UNIPERIF_STATE_STOPPED) { /* Stop the reader */ uni_reader_stop(reader); } reader->substream = NULL; + spin_unlock_irqrestore(&reader->irq_lock, flags); } static const struct snd_soc_dai_ops uni_reader_dai_ops = { @@ -415,6 +429,8 @@ int uni_reader_init(struct platform_device *pdev, return -EBUSY; } + spin_lock_init(&reader->irq_lock); + return 0; } EXPORT_SYMBOL_GPL(uni_reader_init); diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 122153b16ea4..390d7c9685fd 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -168,6 +168,16 @@ .off = OFF, \ .imm = 0 }) +/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ + +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 273f21fa32b5..7aa57225cbf7 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -130,6 +130,12 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "s390", + .objdump = { + .comment_char = '#', + }, + }, }; static void ins__delete(struct ins_operands *ops) diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 93b0aa74ca03..39c2c7d067bb 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -156,6 +156,7 @@ out: */ case 0x2C: /* Westmere EP - Gulftown */ cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO; + break; case 0x2A: /* SNB */ case 0x2D: /* SNB Xeon */ case 0x3A: /* IVB */ diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index fedca3285326..ccf2a69365cc 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -100,6 +100,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. +\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. +\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. \fBPkgWatt\fP Watts consumed by the whole package. \fBCorWatt\fP Watts consumed by the core part of the package. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 828dccd3f01e..b11294730771 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1142,7 +1142,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, * it is possible for mperf's non-halted cycles + idle states * to exceed TSC's all cycles: show c1 = 0% in that case. */ - if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc) + if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak)) old->c1 = 0; else { /* normal case, derive c1 */ @@ -2485,8 +2485,10 @@ int snapshot_gfx_mhz(void) if (fp == NULL) fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); - else + else { rewind(fp); + fflush(fp); + } retval = fscanf(fp, "%d", &gfx_cur_mhz); if (retval != 1) @@ -3111,7 +3113,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx " - "(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n", + "(high %d guar %d eff %d low %d)\n", cpu, msr, (unsigned int)HWP_HIGHEST_PERF(msr), (unsigned int)HWP_GUARANTEED_PERF(msr), @@ -3122,7 +3124,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx " - "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n", + "(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n", cpu, msr, (unsigned int)(((msr) >> 0) & 0xff), (unsigned int)(((msr) >> 8) & 0xff), @@ -3136,7 +3138,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx " - "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n", + "(min %d max %d des %d epp 0x%x window 0x%x)\n", cpu, msr, (unsigned int)(((msr) >> 0) & 0xff), (unsigned int)(((msr) >> 8) & 0xff), @@ -3353,17 +3355,19 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ - do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; BIC_PRESENT(BIC_PKG__); BIC_PRESENT(BIC_RAM__); if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); BIC_PRESENT(BIC_Cor_J); BIC_PRESENT(BIC_RAM_J); + BIC_PRESENT(BIC_GFX_J); } else { BIC_PRESENT(BIC_PkgWatt); BIC_PRESENT(BIC_CorWatt); BIC_PRESENT(BIC_RAMWatt); + BIC_PRESENT(BIC_GFXWatt); } break; case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -3478,7 +3482,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; - unsigned int dts; + unsigned int dts, dts2; int cpu; if (!(do_dts || do_ptm)) @@ -3503,7 +3507,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tcc_activation_temp - dts); -#ifdef THERM_DEBUG if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr)) return 0; @@ -3511,11 +3514,10 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p dts2 = (msr >> 8) & 0x7F; fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2); -#endif } - if (do_dts) { + if (do_dts && debug) { unsigned int resolution; if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) @@ -3526,7 +3528,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n", cpu, msr, tcc_activation_temp - dts, resolution); -#ifdef THERM_DEBUG if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr)) return 0; @@ -3534,7 +3535,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p dts2 = (msr >> 8) & 0x7F; fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2); -#endif } return 0; @@ -4578,7 +4578,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 17.02.24" + fprintf(outf, "turbostat version 17.04.12" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6a1ad58cb66f..9af09e8099c0 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,7 +1,14 @@ LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf +APIDIR := ../../../include/uapi +GENDIR := ../../../../include/generated +GENHDR := $(GENDIR)/autoconf.h -CFLAGS += -Wall -O2 -I../../../include/uapi -I$(LIBDIR) +ifneq ($(wildcard $(GENHDR)),) + GENFLAGS := -DHAVE_GENHDR +endif + +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) LDLIBS += -lcap TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index a0aa2009b0e0..20f1871874df 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -282,7 +282,7 @@ static void test_arraymap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); int key, next_key, fd, i; - long values[nr_cpus]; + long long values[nr_cpus]; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), sizeof(values[0]), 2, 0); @@ -340,7 +340,7 @@ static void test_arraymap_percpu_many_keys(void) * allocator more than anything else */ unsigned int nr_keys = 2000; - long values[nr_cpus]; + long long values[nr_cpus]; int key, fd, i; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index d1555e4240c0..c848e90b6421 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -30,6 +30,14 @@ #include <bpf/bpf.h> +#ifdef HAVE_GENHDR +# include "autoconf.h" +#else +# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__) +# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 +# endif +#endif + #include "../../../include/linux/filter.h" #ifndef ARRAY_SIZE @@ -39,6 +47,8 @@ #define MAX_INSNS 512 #define MAX_FIXUPS 8 +#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -53,6 +63,7 @@ struct bpf_test { REJECT } result, result_unpriv; enum bpf_prog_type prog_type; + uint8_t flags; }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -2432,6 +2443,30 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "direct packet access: test15 (spill with xadd)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_5, 4096), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), + BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R2 invalid mem access 'inv'", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to packet: test1, valid packet_ptr range", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -2934,6 +2969,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "valid map access into an array with a variable", @@ -2957,6 +2993,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "valid map access into an array with a signed variable", @@ -2984,6 +3021,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a constant", @@ -3025,6 +3063,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is outside of the array range", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a variable", @@ -3048,6 +3087,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with no floor check", @@ -3074,6 +3114,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a invalid max check", @@ -3100,6 +3141,7 @@ static struct bpf_test tests[] = { .errstr = "invalid access to map value, value_size=48 off=44 size=8", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a invalid max check", @@ -3129,6 +3171,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "multiple registers share map_lookup_elem result", @@ -3252,6 +3295,7 @@ static struct bpf_test tests[] = { .result = REJECT, .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "constant register |= constant should keep constant type", @@ -3418,6 +3462,26 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_LWT_XMIT, }, { + "overlapping checks for direct packet access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { "invalid access of tc_classid for LWT_IN", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, @@ -3961,7 +4025,208 @@ static struct bpf_test tests[] = { .result_unpriv = REJECT, }, { - "map element value (adjusted) is preserved across register spilling", + "map element value or null is marked on register spilling", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result = ACCEPT, + .result_unpriv = REJECT, + }, + { + "map element value store of cleared call register", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R1 !read_ok", + .errstr = "R1 !read_ok", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value with unaligned store", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43), + BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33), + BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23), + BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22), + BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23), + BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result = ACCEPT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map element value with unaligned load", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result = ACCEPT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map element value illegal alu op, 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 3", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 4", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 5", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_IMM(BPF_REG_3, 4096), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), @@ -3983,6 +4248,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result = ACCEPT, .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "helper access to variable memory: stack, bitwise AND + JMP, correct bounds", @@ -4421,6 +4687,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result = REJECT, .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid range check", @@ -4452,6 +4719,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result = REJECT, .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, } }; @@ -4530,11 +4798,11 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { + int fd_prog, expected_ret, reject_from_alignment; struct bpf_insn *prog = test->insns; int prog_len = probe_filter_length(prog); int prog_type = test->prog_type; int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1; - int fd_prog, expected_ret; const char *expected_err; do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3); @@ -4547,8 +4815,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv, test->result_unpriv : test->result; expected_err = unpriv && test->errstr_unpriv ? test->errstr_unpriv : test->errstr; + + reject_from_alignment = fd_prog < 0 && + (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) && + strstr(bpf_vlog, "Unknown alignment."); +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (reject_from_alignment) { + printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n", + strerror(errno)); + goto fail_log; + } +#endif if (expected_ret == ACCEPT) { - if (fd_prog < 0) { + if (fd_prog < 0 && !reject_from_alignment) { printf("FAIL\nFailed to load prog '%s'!\n", strerror(errno)); goto fail_log; @@ -4558,14 +4837,15 @@ static void do_test_single(struct bpf_test *test, bool unpriv, printf("FAIL\nUnexpected success to load!\n"); goto fail_log; } - if (!strstr(bpf_vlog, expected_err)) { + if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) { printf("FAIL\nUnexpected error message!\n"); goto fail_log; } } (*passes)++; - printf("OK\n"); + printf("OK%s\n", reject_from_alignment ? + " (NOTE: reject due to unknown alignment)" : ""); close_fds: close(fd_prog); close(fd_f1); diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc new file mode 100644 index 000000000000..bab5ff7c607e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -0,0 +1,117 @@ +#!/bin/sh +# description: ftrace - function pid filters + +# Make sure that function pid matching filter works. +# Also test it on an instance directory + +if ! grep -q function available_tracers; then + echo "no function tracer configured" + exit_unsupported +fi + +if [ ! -f set_ftrace_pid ]; then + echo "set_ftrace_pid not found? Is function tracer not set?" + exit_unsupported +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is function tracer not set?" + exit_unsupported +fi + +do_function_fork=1 + +if [ ! -f options/function-fork ]; then + do_function_fork=0 + echo "no option for function-fork found. Option will not be tested." +fi + +read PID _ < /proc/self/stat + +if [ $do_function_fork -eq 1 ]; then + # default value of function-fork option + orig_value=`grep function-fork trace_options` +fi + +do_reset() { + reset_tracer + clear_trace + enable_tracing + echo > set_ftrace_filter + echo > set_ftrace_pid + + if [ $do_function_fork -eq 0 ]; then + return + fi + + echo $orig_value > trace_options +} + +fail() { # msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +do_test() { + disable_tracing + + echo do_execve* > set_ftrace_filter + echo *do_fork >> set_ftrace_filter + + echo $PID > set_ftrace_pid + echo function > current_tracer + + if [ $do_function_fork -eq 1 ]; then + # don't allow children to be traced + echo nofunction-fork > trace_options + fi + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should be 0 + if [ $count_pid -eq 0 -o $count_other -ne 0 ]; then + fail "PID filtering not working?" + fi + + disable_tracing + clear_trace + + if [ $do_function_fork -eq 0 ]; then + return + fi + + # allow children to be traced + echo function-fork > trace_options + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should NOT be 0 + if [ $count_pid -eq 0 -o $count_other -eq 0 ]; then + fail "PID filtering not following fork?" + fi +} + +do_test + +mkdir instances/foo +cd instances/foo +do_test +cd ../../ +rmdir instances/foo + +do_reset + +exit 0 diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 412459369686..e62bb354820c 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -75,7 +75,7 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) { int fd, val; - fd = socket(PF_PACKET, SOCK_DGRAM, htons(ETH_P_IP)); + fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); if (fd < 0) { perror("socket packet"); exit(1); @@ -95,6 +95,24 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) return fd; } +static void sock_fanout_set_cbpf(int fd) +{ + struct sock_filter bpf_filter[] = { + BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */ + BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */ + }; + struct sock_fprog bpf_prog; + + bpf_prog.filter = bpf_filter; + bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + + if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, + sizeof(bpf_prog))) { + perror("fanout data cbpf"); + exit(1); + } +} + static void sock_fanout_set_ebpf(int fd) { const int len_off = __builtin_offsetof(struct __sk_buff, len); @@ -270,7 +288,7 @@ static int test_datapath(uint16_t typeflags, int port_off, exit(1); } if (type == PACKET_FANOUT_CBPF) - sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA); + sock_fanout_set_cbpf(fds[0]); else if (type == PACKET_FANOUT_EBPF) sock_fanout_set_ebpf(fds[0]); diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index a77da88bf946..7d990d6c861b 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -38,7 +38,7 @@ # define __maybe_unused __attribute__ ((__unused__)) #endif -static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) +static __maybe_unused void pair_udp_setfilter(int fd) { /* the filter below checks for all of the following conditions that * are based on the contents of create_payload() @@ -76,23 +76,16 @@ static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) }; struct sock_fprog bpf_prog; - if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA) - bpf_filter[5].code = 0x16; /* RET A */ - bpf_prog.filter = bpf_filter; bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); - if (setsockopt(fd, lvl, optnum, &bpf_prog, + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog, sizeof(bpf_prog))) { perror("setsockopt SO_ATTACH_FILTER"); exit(1); } } -static __maybe_unused void pair_udp_setfilter(int fd) -{ - sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER); -} - static __maybe_unused void pair_udp_open(int fds[], uint16_t port) { struct sockaddr_in saddr, daddr; diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 1c5d0575802e..bf13fc2297aa 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -34,34 +34,34 @@ endif all: $(SUB_DIRS) $(SUB_DIRS): - BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all + BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all include ../lib.mk override define RUN_TESTS @for TARGET in $(SUB_DIRS); do \ - BUILD_TARGET=$$OUTPUT/$$TARGET; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; endef override define INSTALL_RULE @for TARGET in $(SUB_DIRS); do \ - BUILD_TARGET=$$OUTPUT/$$TARGET; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\ done; endef override define EMIT_TESTS @for TARGET in $(SUB_DIRS); do \ - BUILD_TARGET=$$OUTPUT/$$TARGET; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ done; endef clean: @for TARGET in $(SUB_DIRS); do \ - BUILD_TARGET=$$OUTPUT/$$TARGET; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \ done; rm -f tags diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 276139a24e6f..702f8108608d 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -392,6 +392,25 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) } /** + * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware + * + * For a specific CPU, initialize the GIC VE hardware. + */ +void kvm_vgic_init_cpu_hardware(void) +{ + BUG_ON(preemptible()); + + /* + * We want to make sure the list registers start out clear so that we + * only have the program the used registers. + */ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_init_lrs(); + else + kvm_call_hyp(__vgic_v3_init_lrs); +} + +/** * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable * according to the host GIC model. Accordingly calls either * vgic_v2/v3_probe which registers the KVM_DEVICE that can be diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index a3ad7ff95c9b..0a4283ed9aa7 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -229,7 +229,15 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu, val = vmcr.ctlr; break; case GIC_CPU_PRIMASK: - val = vmcr.pmr; + /* + * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the + * the PMR field as GICH_VMCR.VMPriMask rather than + * GICC_PMR.Priority, so we expose the upper five bits of + * priority mask to userspace using the lower bits in the + * unsigned long. + */ + val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >> + GICV_PMR_PRIORITY_SHIFT; break; case GIC_CPU_BINPOINT: val = vmcr.bpr; @@ -262,7 +270,15 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu, vmcr.ctlr = val; break; case GIC_CPU_PRIMASK: - vmcr.pmr = val; + /* + * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the + * the PMR field as GICH_VMCR.VMPriMask rather than + * GICC_PMR.Priority, so we expose the upper five bits of + * priority mask to userspace using the lower bits in the + * unsigned long. + */ + vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) & + GICV_PMR_PRIORITY_MASK; break; case GIC_CPU_BINPOINT: vmcr.bpr = val; diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index b834ecdf3225..b637d9c7afe3 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -36,6 +36,21 @@ static unsigned long *u64_to_bitmask(u64 *val) return (unsigned long *)val; } +static inline void vgic_v2_write_lr(int lr, u32 val) +{ + void __iomem *base = kvm_vgic_global_state.vctrl_base; + + writel_relaxed(val, base + GICH_LR0 + (lr * 4)); +} + +void vgic_v2_init_lrs(void) +{ + int i; + + for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) + vgic_v2_write_lr(i, 0); +} + void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu) { struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; @@ -191,8 +206,8 @@ void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) GICH_VMCR_ALIAS_BINPOINT_MASK; vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK; - vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & - GICH_VMCR_PRIMASK_MASK; + vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) << + GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK; vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr; } @@ -207,8 +222,8 @@ void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) GICH_VMCR_ALIAS_BINPOINT_SHIFT; vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT; - vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >> - GICH_VMCR_PRIMASK_SHIFT; + vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >> + GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT; } void vgic_v2_enable(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index db28f7cadab2..6cf557e9f718 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -81,11 +81,18 @@ static inline bool irq_is_pending(struct vgic_irq *irq) return irq->pending_latch || irq->line_level; } +/* + * This struct provides an intermediate representation of the fields contained + * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC + * state to userspace can generate either GICv2 or GICv3 CPU interface + * registers regardless of the hardware backed GIC used. + */ struct vgic_vmcr { u32 ctlr; u32 abpr; u32 bpr; - u32 pmr; + u32 pmr; /* Priority mask field in the GICC_PMR and + * ICC_PMR_EL1 priority field format */ /* Below member variable are valid only for GICv3 */ u32 grpen0; u32 grpen1; @@ -130,6 +137,8 @@ int vgic_v2_map_resources(struct kvm *kvm); int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type); +void vgic_v2_init_lrs(void); + static inline void vgic_get_irq_kref(struct vgic_irq *irq) { if (irq->intid < VGIC_MIN_LPI) |