diff options
84 files changed, 933 insertions, 525 deletions
@@ -34,6 +34,7 @@ Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com> Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com> Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com> +Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@futurfusion.io> Alexander Sverdlin <alexander.sverdlin@gmail.com> <alexander.sverdlin.ext@nsn.com> Alexander Sverdlin <alexander.sverdlin@gmail.com> <alexander.sverdlin@gmx.de> Alexander Sverdlin <alexander.sverdlin@gmail.com> <alexander.sverdlin@nokia.com> @@ -786,7 +787,8 @@ Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com> <subashab@codeaurora. Subbaraman Narayanamurthy <quic_subbaram@quicinc.com> <subbaram@codeaurora.org> Subhash Jadavani <subhashj@codeaurora.org> Sudarshan Rajagopalan <quic_sudaraja@quicinc.com> <sudaraja@codeaurora.org> -Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> +Sudeep Holla <sudeep.holla@kernel.org> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> +Sudeep Holla <sudeep.holla@kernel.org> <sudeep.holla@arm.com> Sumit Garg <sumit.garg@kernel.org> <sumit.garg@linaro.org> Sumit Semwal <sumit.semwal@ti.com> Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org> diff --git a/Documentation/ABI/testing/sysfs-class-tsm b/Documentation/ABI/testing/sysfs-class-tsm index 6fc1a5ac6da1..2949468deaf7 100644 --- a/Documentation/ABI/testing/sysfs-class-tsm +++ b/Documentation/ABI/testing/sysfs-class-tsm @@ -7,13 +7,3 @@ Description: signals when the PCI layer is able to support establishment of link encryption and other device-security features coordinated through a platform tsm. - -What: /sys/class/tsm/tsmN/streamH.R.E -Contact: linux-pci@vger.kernel.org -Description: - (RO) When a host bridge has established a secure connection via - the platform TSM, symlink appears. The primary function of this - is have a system global review of TSM resource consumption - across host bridges. The link points to the endpoint PCI device - and matches the same link published by the host bridge. See - Documentation/ABI/testing/sysfs-devices-pci-host-bridge. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1058f2a6d6a8..aa0031108bc1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3472,6 +3472,11 @@ Kernel parameters If there are multiple matching configurations changing the same attribute, the last one is used. + liveupdate= [KNL,EARLY] + Format: <bool> + Enable Live Update Orchestrator (LUO). + Default: off. + load_ramdisk= [RAM] [Deprecated] lockd.nlm_grace_period=P [NFS] Assign grace period. diff --git a/MAINTAINERS b/MAINTAINERS index 0efa8cc6775b..e08767323763 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -335,7 +335,7 @@ F: tools/power/acpi/ ACPI FOR ARM64 (ACPI/arm64) M: Lorenzo Pieralisi <lpieralisi@kernel.org> M: Hanjun Guo <guohanjun@huawei.com> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-acpi@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -351,7 +351,7 @@ F: drivers/acpi/riscv/ F: include/linux/acpi_rimt.h ACPI PCC(Platform Communication Channel) MAILBOX DRIVER -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-acpi@vger.kernel.org S: Supported F: drivers/mailbox/pcc.c @@ -2747,14 +2747,14 @@ F: arch/arm/include/asm/hardware/dec21285.h F: arch/arm/mach-footbridge/ ARM/FREESCALE IMX / MXC ARM ARCHITECTURE -M: Shawn Guo <shawnguo@kernel.org> +M: Frank Li <Frank.Li@nxp.com> M: Sascha Hauer <s.hauer@pengutronix.de> R: Pengutronix Kernel Team <kernel@pengutronix.de> R: Fabio Estevam <festevam@gmail.com> L: imx@lists.linux.dev L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/frank.li/linux.git F: Documentation/devicetree/bindings/firmware/fsl* F: Documentation/devicetree/bindings/firmware/nxp* F: arch/arm/boot/dts/nxp/imx/ @@ -2769,22 +2769,22 @@ N: mxs N: \bmxc[^\d] ARM/FREESCALE LAYERSCAPE ARM ARCHITECTURE -M: Shawn Guo <shawnguo@kernel.org> +M: Frank Li <Frank.Li@nxp.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/frank.li/linux.git F: arch/arm/boot/dts/nxp/ls/ F: arch/arm64/boot/dts/freescale/fsl-* F: arch/arm64/boot/dts/freescale/qoriq-* ARM/FREESCALE VYBRID ARM ARCHITECTURE -M: Shawn Guo <shawnguo@kernel.org> +M: Frank Li <Frank.Li@nxp.com> M: Sascha Hauer <s.hauer@pengutronix.de> R: Pengutronix Kernel Team <kernel@pengutronix.de> R: Stefan Agner <stefan@agner.ch> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/frank.li/linux.git F: arch/arm/boot/dts/nxp/vf/ F: arch/arm/mach-imx/*vf610* @@ -3681,7 +3681,7 @@ N: uniphier ARM/VERSATILE EXPRESS PLATFORM M: Liviu Dudau <liviu.dudau@arm.com> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> M: Lorenzo Pieralisi <lpieralisi@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -6513,7 +6513,7 @@ F: drivers/i2c/busses/i2c-cp2615.c CPU FREQUENCY DRIVERS - VEXPRESS SPC ARM BIG LITTLE M: Viresh Kumar <viresh.kumar@linaro.org> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-pm@vger.kernel.org S: Maintained W: http://www.arm.com/products/processors/technologies/biglittleprocessing.php @@ -6609,7 +6609,7 @@ F: include/linux/platform_data/cpuidle-exynos.h CPUIDLE DRIVER - ARM PSCI M: Lorenzo Pieralisi <lpieralisi@kernel.org> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> M: Ulf Hansson <ulf.hansson@linaro.org> L: linux-pm@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -9815,7 +9815,7 @@ F: include/uapi/linux/firewire*.h F: tools/firewire/ FIRMWARE FRAMEWORK FOR ARMV8-A -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/firmware/arm_ffa/ @@ -10513,7 +10513,7 @@ S: Maintained F: scripts/gendwarfksyms/ GENERIC ARCHITECTURE TOPOLOGY -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: drivers/base/arch_topology.c @@ -11375,6 +11375,11 @@ F: Documentation/ABI/testing/sysfs-devices-platform-kunpeng_hccs F: drivers/soc/hisilicon/kunpeng_hccs.c F: drivers/soc/hisilicon/kunpeng_hccs.h +HISILICON SOC HHA DRIVER +M: Yushan Wang <wangyushan12@huawei.com> +S: Maintained +F: drivers/cache/hisi_soc_hha.c + HISILICON LPC BUS DRIVER M: Jay Fang <f.fangjian@huawei.com> S: Maintained @@ -15100,7 +15105,7 @@ F: drivers/mailbox/arm_mhuv2.c F: include/linux/mailbox/arm_mhuv2_message.h MAILBOX ARM MHUv3 -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> M: Cristian Marussi <cristian.marussi@arm.com> L: linux-kernel@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -20577,7 +20582,7 @@ F: drivers/pinctrl/pinctrl-amd.c PIN CONTROLLER - FREESCALE M: Dong Aisheng <aisheng.dong@nxp.com> M: Fabio Estevam <festevam@gmail.com> -M: Shawn Guo <shawnguo@kernel.org> +M: Frank Li <Frank.Li@nxp.com> M: Jacky Bai <ping.bai@nxp.com> R: Pengutronix Kernel Team <kernel@pengutronix.de> R: NXP S32 Linux Team <s32@nxp.com> @@ -20973,6 +20978,18 @@ F: Documentation/devicetree/bindings/net/pse-pd/ F: drivers/net/pse-pd/ F: net/ethtool/pse-pd.c +PSP SECURITY PROTOCOL +M: Daniel Zahka <daniel.zahka@gmail.com> +M: Jakub Kicinski <kuba@kernel.org> +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +F: Documentation/netlink/specs/psp.yaml +F: Documentation/networking/psp.rst +F: include/net/psp/ +F: include/net/psp.h +F: include/uapi/linux/psp.h +F: net/psp/ +K: struct\ psp(_assoc|_dev|hdr)\b + PSTORE FILESYSTEM M: Kees Cook <kees@kernel.org> R: Tony Luck <tony.luck@intel.com> @@ -23630,7 +23647,7 @@ F: include/uapi/linux/sed* SECURE MONITOR CALL(SMC) CALLING CONVENTION (SMCCC) M: Mark Rutland <mark.rutland@arm.com> M: Lorenzo Pieralisi <lpieralisi@kernel.org> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/firmware/smccc/ @@ -25394,7 +25411,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd.git F: drivers/mfd/syscon.c SYSTEM CONTROL & POWER/MANAGEMENT INTERFACE (SCPI/SCMI) Message Protocol drivers -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> R: Cristian Marussi <cristian.marussi@arm.com> L: arm-scmi@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -26546,7 +26563,7 @@ F: samples/tsm-mr/ TRUSTED SERVICES TEE DRIVER M: Balint Dobszay <balint.dobszay@arm.com> -M: Sudeep Holla <sudeep.holla@arm.com> +M: Sudeep Holla <sudeep.holla@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: trusted-services@lists.trustedfirmware.org S: Maintained diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index acf9ffa1a171..dfd5c74ba41a 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -42,7 +42,7 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { unsigned int level; pte_t *pte = lookup_address(addr, &level); - pteval_t val; + pteval_t val, new; if (WARN_ON(!pte || level != PG_LEVEL_4K)) return false; @@ -57,11 +57,12 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) return true; /* - * Otherwise, invert the entire PTE. This avoids writing out an + * Otherwise, flip the Present bit, taking care to avoid writing an * L1TF-vulnerable PTE (not present, without the high address bits * set). */ - set_pte(pte, __pte(~val)); + new = val ^ _PAGE_PRESENT; + set_pte(pte, __pte(flip_protnone_guard(val, new, PTE_PFN_MASK))); /* * If the page was protected (non-present) and we're making it diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 7cc8950005b6..4c7688670c2d 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -514,7 +514,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, */ spin_lock_irq(&kvm->irqfds.lock); - if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI || + WARN_ON_ONCE(irqfd->irq_bypass_vcpu)) { ret = kvm_pi_update_irte(irqfd, NULL); if (ret) pr_info("irq bypass consumer (eventfd %p) unregistration fails: %d\n", diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 6b77b2033208..0f6c8596719b 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -376,6 +376,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) static int avic_init_backing_page(struct kvm_vcpu *vcpu) { + u32 max_id = x2avic_enabled ? x2avic_max_physical_id : AVIC_MAX_PHYSICAL_ID; struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); struct vcpu_svm *svm = to_svm(vcpu); u32 id = vcpu->vcpu_id; @@ -388,8 +389,7 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) * avic_vcpu_load() expects to be called if and only if the vCPU has * fully initialized AVIC. */ - if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || - (id > x2avic_max_physical_id)) { + if (id > max_id) { kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG); vcpu->arch.apic->apicv_active = false; return 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 24d59ccfa40d..4394be40fe78 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -5284,6 +5284,8 @@ static __init void svm_set_cpu_caps(void) */ kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT); kvm_cpu_cap_clear(X86_FEATURE_MSR_IMM); + + kvm_setup_xss_caps(); } static __init int svm_hardware_setup(void) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6b96f7aea20b..8c94241fbcca 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8051,6 +8051,8 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); } + + kvm_setup_xss_caps(); } static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 63afdb6bb078..72d37c8930ad 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9953,6 +9953,23 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif +void kvm_setup_xss_caps(void) +{ + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + kvm_caps.supported_xss = 0; + + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + + if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + } +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_setup_xss_caps); + static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) { memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); @@ -10125,19 +10142,6 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (!tdp_enabled) kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; - if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - kvm_caps.supported_xss = 0; - - if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && - !kvm_cpu_cap_has(X86_FEATURE_IBT)) - kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; - - if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { - kvm_cpu_cap_clear(X86_FEATURE_SHSTK); - kvm_cpu_cap_clear(X86_FEATURE_IBT); - kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; - } - if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index fdab0ad49098..00de24f55b1f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -471,6 +471,8 @@ extern struct kvm_host_values kvm_host; extern bool enable_pmu; +void kvm_setup_xss_caps(void); + /* * Get a filtered version of KVM's supported XCR0 that strips out dynamic * features for which the current process doesn't (yet) have permission to use. diff --git a/drivers/android/binder/rust_binderfs.c b/drivers/android/binder/rust_binderfs.c index c69026df775c..e36011e89116 100644 --- a/drivers/android/binder/rust_binderfs.c +++ b/drivers/android/binder/rust_binderfs.c @@ -391,12 +391,6 @@ static int binderfs_binder_ctl_create(struct super_block *sb) if (!device) return -ENOMEM; - /* If we have already created a binder-control node, return. */ - if (info->control_dentry) { - ret = 0; - goto out; - } - ret = -ENOMEM; inode = new_inode(sb); if (!inode) @@ -431,7 +425,8 @@ static int binderfs_binder_ctl_create(struct super_block *sb) inode->i_private = device; info->control_dentry = dentry; - d_add(dentry, inode); + d_make_persistent(dentry, inode); + dput(dentry); return 0; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bd59c0e9508b..32a3a5b13802 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1225,28 +1225,16 @@ static int loop_clr_fd(struct loop_device *lo) } static int -loop_set_status(struct loop_device *lo, blk_mode_t mode, - struct block_device *bdev, const struct loop_info64 *info) +loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; bool partscan = false; bool size_changed = false; unsigned int memflags; - /* - * If we don't hold exclusive handle for the device, upgrade to it - * here to avoid changing device under exclusive owner. - */ - if (!(mode & BLK_OPEN_EXCL)) { - err = bd_prepare_to_claim(bdev, loop_set_status, NULL); - if (err) - goto out_reread_partitions; - } - err = mutex_lock_killable(&lo->lo_mutex); if (err) - goto out_abort_claiming; - + return err; if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; @@ -1285,10 +1273,6 @@ out_unfreeze: } out_unlock: mutex_unlock(&lo->lo_mutex); -out_abort_claiming: - if (!(mode & BLK_OPEN_EXCL)) - bd_abort_claiming(bdev, loop_set_status); -out_reread_partitions: if (partscan) loop_reread_partitions(lo); @@ -1368,9 +1352,7 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) } static int -loop_set_status_old(struct loop_device *lo, blk_mode_t mode, - struct block_device *bdev, - const struct loop_info __user *arg) +loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; @@ -1378,19 +1360,17 @@ loop_set_status_old(struct loop_device *lo, blk_mode_t mode, if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); - return loop_set_status(lo, mode, bdev, &info64); + return loop_set_status(lo, &info64); } static int -loop_set_status64(struct loop_device *lo, blk_mode_t mode, - struct block_device *bdev, - const struct loop_info64 __user *arg) +loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; - return loop_set_status(lo, mode, bdev, &info64); + return loop_set_status(lo, &info64); } static int @@ -1569,14 +1549,14 @@ static int lo_ioctl(struct block_device *bdev, blk_mode_t mode, case LOOP_SET_STATUS: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_status_old(lo, mode, bdev, argp); + err = loop_set_status_old(lo, argp); break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_status64(lo, mode, bdev, argp); + err = loop_set_status64(lo, argp); break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); @@ -1670,9 +1650,8 @@ loop_info64_to_compat(const struct loop_info64 *info64, } static int -loop_set_status_compat(struct loop_device *lo, blk_mode_t mode, - struct block_device *bdev, - const struct compat_loop_info __user *arg) +loop_set_status_compat(struct loop_device *lo, + const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; @@ -1680,7 +1659,7 @@ loop_set_status_compat(struct loop_device *lo, blk_mode_t mode, ret = loop_info64_from_compat(arg, &info64); if (ret < 0) return ret; - return loop_set_status(lo, mode, bdev, &info64); + return loop_set_status(lo, &info64); } static int @@ -1706,7 +1685,7 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, switch(cmd) { case LOOP_SET_STATUS: - err = loop_set_status_compat(lo, mode, bdev, + err = loop_set_status_compat(lo, (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: diff --git a/drivers/crypto/ccp/sev-dev-tsm.c b/drivers/crypto/ccp/sev-dev-tsm.c index ea29cd5d0ff9..40d02adaf3f6 100644 --- a/drivers/crypto/ccp/sev-dev-tsm.c +++ b/drivers/crypto/ccp/sev-dev-tsm.c @@ -19,12 +19,6 @@ MODULE_IMPORT_NS("PCI_IDE"); -#define TIO_DEFAULT_NR_IDE_STREAMS 1 - -static uint nr_ide_streams = TIO_DEFAULT_NR_IDE_STREAMS; -module_param_named(ide_nr, nr_ide_streams, uint, 0644); -MODULE_PARM_DESC(ide_nr, "Set the maximum number of IDE streams per PHB"); - #define dev_to_sp(dev) ((struct sp_device *)dev_get_drvdata(dev)) #define dev_to_psp(dev) ((struct psp_device *)(dev_to_sp(dev)->psp_data)) #define dev_to_sev(dev) ((struct sev_device *)(dev_to_psp(dev)->sev_data)) @@ -193,7 +187,6 @@ static void streams_teardown(struct pci_ide **ide) static int stream_alloc(struct pci_dev *pdev, struct pci_ide **ide, unsigned int tc) { - struct pci_dev *rp = pcie_find_root_port(pdev); struct pci_ide *ide1; if (ide[tc]) { @@ -201,17 +194,11 @@ static int stream_alloc(struct pci_dev *pdev, struct pci_ide **ide, return -EBUSY; } - /* FIXME: find a better way */ - if (nr_ide_streams != TIO_DEFAULT_NR_IDE_STREAMS) - pci_notice(pdev, "Enable non-default %d streams", nr_ide_streams); - pci_ide_set_nr_streams(to_pci_host_bridge(rp->bus->bridge), nr_ide_streams); - ide1 = pci_ide_stream_alloc(pdev); if (!ide1) return -EFAULT; - /* Blindly assign streamid=0 to TC=0, and so on */ - ide1->stream_id = tc; + ide1->stream_id = ide1->host_bridge_stream; ide[tc] = ide1; diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 30f9d271e595..71a2397edf2b 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1089,6 +1089,9 @@ static int adin1110_check_spi(struct adin1110_priv *priv) reset_gpio = devm_gpiod_get_optional(&priv->spidev->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(reset_gpio)) + return dev_err_probe(&priv->spidev->dev, PTR_ERR(reset_gpio), + "failed to get reset gpio\n"); if (reset_gpio) { /* MISO pin is used for internal configuration, can't have * anyone else disturbing the SDO line. diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 0732440eeacd..c1a3df225254 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3505,6 +3505,23 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) */ netdev->netdev_ops = &lionetdevops; + lio = GET_LIO(netdev); + + memset(lio, 0, sizeof(struct lio)); + + lio->ifidx = ifidx_or_pfnum; + + props = &octeon_dev->props[i]; + props->gmxport = resp->cfg_info.linfo.gmxport; + props->netdev = netdev; + + /* Point to the properties for octeon device to which this + * interface belongs. + */ + lio->oct_dev = octeon_dev; + lio->octprops = props; + lio->netdev = netdev; + retval = netif_set_real_num_rx_queues(netdev, num_oqueues); if (retval) { dev_err(&octeon_dev->pci_dev->dev, @@ -3521,16 +3538,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) goto setup_nic_dev_free; } - lio = GET_LIO(netdev); - - memset(lio, 0, sizeof(struct lio)); - - lio->ifidx = ifidx_or_pfnum; - - props = &octeon_dev->props[i]; - props->gmxport = resp->cfg_info.linfo.gmxport; - props->netdev = netdev; - lio->linfo.num_rxpciq = num_oqueues; lio->linfo.num_txpciq = num_iqueues; for (j = 0; j < num_oqueues; j++) { @@ -3596,13 +3603,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->min_mtu = LIO_MIN_MTU_SIZE; netdev->max_mtu = LIO_MAX_MTU_SIZE; - /* Point to the properties for octeon device to which this - * interface belongs. - */ - lio->oct_dev = octeon_dev; - lio->octprops = props; - lio->netdev = netdev; - dev_dbg(&octeon_dev->pci_dev->dev, "if%d gmx: %d hw_addr: 0x%llx\n", i, lio->linfo.gmxport, CVM_CAST64(lio->linfo.hw_addr)); @@ -3750,6 +3750,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (!devlink) { device_unlock(&octeon_dev->pci_dev->dev); dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n"); + i--; goto setup_nic_dev_free; } @@ -3765,11 +3766,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index e02942dbbcce..43c595f3b84e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2212,11 +2212,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index b1e1ad9e4b48..66240c340492 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1531,6 +1531,10 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) } if_id = (status & 0xFFFF0000) >> 16; + if (if_id >= ethsw->sw_attr.num_ifs) { + dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); + goto out; + } port_priv = ethsw->ports[if_id]; if (status & DPSW_IRQ_EVENT_LINK_CHANGED) @@ -3024,6 +3028,12 @@ static int dpaa2_switch_init(struct fsl_mc_device *sw_dev) goto err_close; } + if (!ethsw->sw_attr.num_ifs) { + dev_err(dev, "DPSW device has no interfaces\n"); + err = -ENODEV; + goto err_close; + } + err = dpsw_get_api_version(ethsw->mc_io, 0, ðsw->major, ðsw->minor); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 53b26cece16a..e380a4f39855 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2512,10 +2512,13 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) struct enetc_hw *hw = &si->hw; int err; - /* set SI cache attributes */ - enetc_wr(hw, ENETC_SICAR0, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + if (is_enetc_rev1(si)) { + /* set SI cache attributes */ + enetc_wr(hw, ENETC_SICAR0, + ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); + enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + } + /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 498346dd996a..5850540634b0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -59,10 +59,10 @@ static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si, if (si != 0) { __raw_writel(upper, hw->port + ENETC4_PSIPMAR0(si)); - __raw_writew(lower, hw->port + ENETC4_PSIPMAR1(si)); + __raw_writel(lower, hw->port + ENETC4_PSIPMAR1(si)); } else { __raw_writel(upper, hw->port + ENETC4_PMAR0); - __raw_writew(lower, hw->port + ENETC4_PMAR1); + __raw_writel(lower, hw->port + ENETC4_PMAR1); } } @@ -73,7 +73,7 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si, u16 lower; upper = __raw_readl(hw->port + ENETC4_PSIPMAR0(si)); - lower = __raw_readw(hw->port + ENETC4_PSIPMAR1(si)); + lower = __raw_readl(hw->port + ENETC4_PSIPMAR1(si)); put_unaligned_le32(upper, addr); put_unaligned_le16(lower, addr + 4); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c index 3d5f31879d5c..a635bfdc30af 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c @@ -74,10 +74,6 @@ int enetc4_setup_cbdr(struct enetc_si *si) if (!user->ring) return -ENOMEM; - /* set CBDR cache attributes */ - enetc_wr(hw, ENETC_SICAR2, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - regs.pir = hw->reg + ENETC_SICBDRPIR; regs.cir = hw->reg + ENETC_SICBDRCIR; regs.mr = hw->reg + ENETC_SICBDRMR; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 7b882b8921fe..662e4fbafb74 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -708,13 +708,24 @@ struct enetc_cmd_rfse { #define ENETC_RFSE_EN BIT(15) #define ENETC_RFSE_MODE_BD 2 +static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr) +{ + u32 upper; + u16 lower; + + upper = __raw_readl(hw->reg + ENETC_SIPMAR0); + lower = __raw_readl(hw->reg + ENETC_SIPMAR1); + + put_unaligned_le32(upper, addr); + put_unaligned_le16(lower, addr + 4); +} + static inline void enetc_load_primary_mac_addr(struct enetc_hw *hw, struct net_device *ndev) { - u8 addr[ETH_ALEN] __aligned(4); + u8 addr[ETH_ALEN]; - *(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0); - *(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1); + enetc_get_primary_mac_addr(hw, addr); eth_hw_addr_set(ndev, addr); } diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 311b106160b2..66ddc4413f8d 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -152,11 +152,13 @@ gve_get_ethtool_stats(struct net_device *netdev, u64 tmp_rx_pkts, tmp_rx_hsplit_pkt, tmp_rx_bytes, tmp_rx_hsplit_bytes, tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt, tmp_rx_hsplit_unsplit_pkt, - tmp_tx_pkts, tmp_tx_bytes; + tmp_tx_pkts, tmp_tx_bytes, + tmp_xdp_tx_errors, tmp_xdp_redirect_errors; u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_hsplit_unsplit_pkt, rx_pkts, rx_hsplit_pkt, rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, - tx_dropped; - int stats_idx, base_stats_idx, max_stats_idx; + tx_dropped, xdp_tx_errors, xdp_redirect_errors; + int rx_base_stats_idx, max_rx_stats_idx, max_tx_stats_idx; + int stats_idx, stats_region_len, nic_stats_len; struct stats *report_stats; int *rx_qid_to_stats_idx; int *tx_qid_to_stats_idx; @@ -198,6 +200,7 @@ gve_get_ethtool_stats(struct net_device *netdev, for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0, rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0, + xdp_tx_errors = 0, xdp_redirect_errors = 0, ring = 0; ring < priv->rx_cfg.num_queues; ring++) { if (priv->rx) { @@ -215,6 +218,9 @@ gve_get_ethtool_stats(struct net_device *netdev, rx->rx_desc_err_dropped_pkt; tmp_rx_hsplit_unsplit_pkt = rx->rx_hsplit_unsplit_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; @@ -224,6 +230,8 @@ gve_get_ethtool_stats(struct net_device *netdev, rx_buf_alloc_fail += tmp_rx_buf_alloc_fail; rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; rx_hsplit_unsplit_pkt += tmp_rx_hsplit_unsplit_pkt; + xdp_tx_errors += tmp_xdp_tx_errors; + xdp_redirect_errors += tmp_xdp_redirect_errors; } } for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; @@ -249,8 +257,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx_bytes; data[i++] = tx_bytes; /* total rx dropped packets */ - data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail + - rx_desc_err_dropped_pkt; + data[i++] = rx_skb_alloc_fail + rx_desc_err_dropped_pkt + + xdp_tx_errors + xdp_redirect_errors; data[i++] = tx_dropped; data[i++] = priv->tx_timeo_cnt; data[i++] = rx_skb_alloc_fail; @@ -265,20 +273,38 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->stats_report_trigger_cnt; i = GVE_MAIN_STATS_LEN; - /* For rx cross-reporting stats, start from nic rx stats in report */ - base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues + - GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; - /* The boundary between driver stats and NIC stats shifts if there are - * stopped queues. - */ - base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs + - NIC_TX_STATS_REPORT_NUM * num_stopped_txqs; - max_stats_idx = NIC_RX_STATS_REPORT_NUM * - (priv->rx_cfg.num_queues - num_stopped_rxqs) + - base_stats_idx; + rx_base_stats_idx = 0; + max_rx_stats_idx = 0; + max_tx_stats_idx = 0; + stats_region_len = priv->stats_report_len - + sizeof(struct gve_stats_report); + nic_stats_len = (NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues + + NIC_TX_STATS_REPORT_NUM * num_tx_queues) * sizeof(struct stats); + if (unlikely((stats_region_len - + nic_stats_len) % sizeof(struct stats))) { + net_err_ratelimited("Starting index of NIC stats should be multiple of stats size"); + } else { + /* For rx cross-reporting stats, + * start from nic rx stats in report + */ + rx_base_stats_idx = (stats_region_len - nic_stats_len) / + sizeof(struct stats); + /* The boundary between driver stats and NIC stats + * shifts if there are stopped queues + */ + rx_base_stats_idx += NIC_RX_STATS_REPORT_NUM * + num_stopped_rxqs + NIC_TX_STATS_REPORT_NUM * + num_stopped_txqs; + max_rx_stats_idx = NIC_RX_STATS_REPORT_NUM * + (priv->rx_cfg.num_queues - num_stopped_rxqs) + + rx_base_stats_idx; + max_tx_stats_idx = NIC_TX_STATS_REPORT_NUM * + (num_tx_queues - num_stopped_txqs) + + max_rx_stats_idx; + } /* Preprocess the stats report for rx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + for (stats_idx = rx_base_stats_idx; stats_idx < max_rx_stats_idx; stats_idx += NIC_RX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); @@ -311,6 +337,9 @@ gve_get_ethtool_stats(struct net_device *netdev, tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; @@ -321,8 +350,9 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx->rx_frag_alloc_cnt; /* rx dropped packets */ data[i++] = tmp_rx_skb_alloc_fail + - tmp_rx_buf_alloc_fail + - tmp_rx_desc_err_dropped_pkt; + tmp_rx_desc_err_dropped_pkt + + tmp_xdp_tx_errors + + tmp_xdp_redirect_errors; data[i++] = rx->rx_copybreak_pkt; data[i++] = rx->rx_copied_pkt; /* stats from NIC */ @@ -354,14 +384,9 @@ gve_get_ethtool_stats(struct net_device *netdev, i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; } - /* For tx cross-reporting stats, start from nic tx stats in report */ - base_stats_idx = max_stats_idx; - max_stats_idx = NIC_TX_STATS_REPORT_NUM * - (num_tx_queues - num_stopped_txqs) + - max_stats_idx; - /* Preprocess the stats report for tx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + /* NIC TX stats start right after NIC RX stats */ + for (stats_idx = max_rx_stats_idx; stats_idx < max_tx_stats_idx; stats_idx += NIC_TX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 52c5e4942cd4..dbc84de39b70 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -283,9 +283,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv) int tx_stats_num, rx_stats_num; tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) * - gve_num_tx_queues(priv); + priv->tx_cfg.max_queues; rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) * - priv->rx_cfg.num_queues; + priv->rx_cfg.max_queues; priv->stats_report_len = struct_size(priv->stats_report, stats, size_add(tx_stats_num, rx_stats_num)); priv->stats_report = diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0b1cc0481027..d3bc3207054f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9030,7 +9030,6 @@ int i40e_open(struct net_device *netdev) TCP_FLAG_FIN | TCP_FLAG_CWR) >> 16); wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); - udp_tunnel_get_rx_info(netdev); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 71c6d53b461e..d04605d3e61a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3314,18 +3314,20 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) if (ice_is_reset_in_progress(pf->state)) goto skip_irq; - if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) { - /* Process outstanding Tx timestamps. If there is more work, - * re-arm the interrupt to trigger again. - */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { - wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); - ice_flush(hw); - } - } + if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) + ice_ptp_process_ts(pf); skip_irq: ice_irq_dynamic_ena(hw, NULL, NULL); + ice_flush(hw); + + if (ice_ptp_tx_tstamps_pending(pf)) { + /* If any new Tx timestamps happened while in interrupt, + * re-arm the interrupt to trigger it again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } return IRQ_HANDLED; } @@ -7807,6 +7809,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* Restore timestamp mode settings after VSI rebuild */ ice_ptp_restore_timestamp_mode(pf); + + /* Start PTP periodic work after VSI is fully rebuilt */ + ice_ptp_queue_work(pf); return; err_vsi_rebuild: @@ -9657,9 +9662,6 @@ int ice_open_internal(struct net_device *netdev) netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); - /* Update existing tunnels information */ - udp_tunnel_get_rx_info(netdev); - return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 4c8d20f2d2c0..272683001476 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -573,6 +573,9 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) pf = ptp_port_to_pf(ptp_port); hw = &pf->hw; + if (!tx->init) + return; + /* Read the Tx ready status first */ if (tx->has_ready_bitmap) { err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); @@ -674,14 +677,9 @@ skip_ts_read: pf->ptp.tx_hwtstamp_good += tstamp_good; } -/** - * ice_ptp_tx_tstamp_owner - Process Tx timestamps for all ports on the device - * @pf: Board private structure - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) +static void ice_ptp_tx_tstamp_owner(struct ice_pf *pf) { struct ice_ptp_port *port; - unsigned int i; mutex_lock(&pf->adapter->ports.lock); list_for_each_entry(port, &pf->adapter->ports.ports, list_node) { @@ -693,49 +691,6 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) ice_ptp_process_tx_tstamp(tx); } mutex_unlock(&pf->adapter->ports.lock); - - for (i = 0; i < ICE_GET_QUAD_NUM(pf->hw.ptp.num_lports); i++) { - u64 tstamp_ready; - int err; - - /* Read the Tx ready status first */ - err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (err) - break; - else if (tstamp_ready) - return ICE_TX_TSTAMP_WORK_PENDING; - } - - return ICE_TX_TSTAMP_WORK_DONE; -} - -/** - * ice_ptp_tx_tstamp - Process Tx timestamps for this function. - * @tx: Tx tracking structure to initialize - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding incomplete - * Tx timestamps, or ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) -{ - bool more_timestamps; - unsigned long flags; - - if (!tx->init) - return ICE_TX_TSTAMP_WORK_DONE; - - /* Process the Tx timestamp tracker */ - ice_ptp_process_tx_tstamp(tx); - - /* Check if there are outstanding Tx timestamps */ - spin_lock_irqsave(&tx->lock, flags); - more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len); - spin_unlock_irqrestore(&tx->lock, flags); - - if (more_timestamps) - return ICE_TX_TSTAMP_WORK_PENDING; - - return ICE_TX_TSTAMP_WORK_DONE; } /** @@ -1347,9 +1302,12 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Do not reconfigure E810 or E830 PHY */ return; case ICE_MAC_GENERIC: - case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; + case ICE_MAC_GENERIC_3K_E825: + if (linkup) + ice_ptp_port_phy_restart(ptp_port); + return; default: dev_warn(ice_pf_to_dev(pf), "%s: Unknown PHY type\n", __func__); } @@ -2663,30 +2621,92 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) return idx + tx->offset; } -/** - * ice_ptp_process_ts - Process the PTP Tx timestamps - * @pf: Board private structure - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding Tx - * timestamps that need processing, and ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) +void ice_ptp_process_ts(struct ice_pf *pf) { switch (pf->ptp.tx_interrupt_mode) { case ICE_PTP_TX_INTERRUPT_NONE: /* This device has the clock owner handle timestamps for it */ - return ICE_TX_TSTAMP_WORK_DONE; + return; case ICE_PTP_TX_INTERRUPT_SELF: /* This device handles its own timestamps */ - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + ice_ptp_process_tx_tstamp(&pf->ptp.port.tx); + return; case ICE_PTP_TX_INTERRUPT_ALL: /* This device handles timestamps for all ports */ - return ice_ptp_tx_tstamp_owner(pf); + ice_ptp_tx_tstamp_owner(pf); + return; + default: + WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", + pf->ptp.tx_interrupt_mode); + return; + } +} + +static bool ice_port_has_timestamps(struct ice_ptp_tx *tx) +{ + bool more_timestamps; + + scoped_guard(spinlock_irqsave, &tx->lock) { + if (!tx->init) + return false; + + more_timestamps = !bitmap_empty(tx->in_use, tx->len); + } + + return more_timestamps; +} + +static bool ice_any_port_has_timestamps(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + + scoped_guard(mutex, &pf->adapter->ports.lock) { + list_for_each_entry(port, &pf->adapter->ports.ports, + list_node) { + struct ice_ptp_tx *tx = &port->tx; + + if (ice_port_has_timestamps(tx)) + return true; + } + } + + return false; +} + +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + unsigned int i; + + /* Check software indicator */ + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_NONE: + return false; + case ICE_PTP_TX_INTERRUPT_SELF: + if (ice_port_has_timestamps(&pf->ptp.port.tx)) + return true; + break; + case ICE_PTP_TX_INTERRUPT_ALL: + if (ice_any_port_has_timestamps(pf)) + return true; + break; default: WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", pf->ptp.tx_interrupt_mode); - return ICE_TX_TSTAMP_WORK_DONE; + break; + } + + /* Check hardware indicator */ + for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { + u64 tstamp_ready = 0; + int err; + + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (err || tstamp_ready) + return true; } + + return false; } /** @@ -2738,7 +2758,9 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) return IRQ_WAKE_THREAD; case ICE_MAC_E830: /* E830 can read timestamps in the top half using rd32() */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + ice_ptp_process_ts(pf); + + if (ice_ptp_tx_tstamps_pending(pf)) { /* Process outstanding Tx timestamps. If there * is more work, re-arm the interrupt to trigger again. */ @@ -2818,6 +2840,20 @@ static void ice_ptp_periodic_work(struct kthread_work *work) } /** + * ice_ptp_queue_work - Queue PTP periodic work for a PF + * @pf: Board private structure + * + * Helper function to queue PTP periodic work after VSI rebuild completes. + * This ensures that PTP work only runs when VSI structures are ready. + */ +void ice_ptp_queue_work(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags) && + pf->ptp.state == ICE_PTP_READY) + kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, 0); +} + +/** * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild * @pf: Board private structure * @rebuild: rebuild if true, prepare if false @@ -2835,10 +2871,15 @@ static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild, struct ice_pf *peer_pf = ptp_port_to_pf(port); if (!ice_is_primary(&peer_pf->hw)) { - if (rebuild) + if (rebuild) { + /* TODO: When implementing rebuild=true: + * 1. Ensure secondary PFs' VSIs are rebuilt + * 2. Call ice_ptp_queue_work(peer_pf) after VSI rebuild + */ ice_ptp_rebuild(peer_pf, reset_type); - else + } else { ice_ptp_prepare_for_reset(peer_pf, reset_type); + } } } } @@ -2984,9 +3025,6 @@ void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ptp->state = ICE_PTP_READY; - /* Start periodic work going */ - kthread_queue_delayed_work(ptp->kworker, &ptp->work, 0); - dev_info(ice_pf_to_dev(pf), "PTP reset successful\n"); return; @@ -3191,8 +3229,9 @@ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { switch (pf->hw.mac_type) { case ICE_MAC_GENERIC: - /* E822 based PHY has the clock owner process the interrupt - * for all ports. + case ICE_MAC_GENERIC_3K_E825: + /* E82x hardware has the clock owner process timestamps for + * all ports. */ if (ice_pf_src_tmr_owned(pf)) pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_ALL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 27016aac4f1e..8c44bd758a4f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -304,8 +304,9 @@ void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +void ice_ptp_process_ts(struct ice_pf *pf); irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf); u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts); @@ -317,6 +318,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); void ice_ptp_link_change(struct ice_pf *pf, bool linkup); +void ice_ptp_queue_work(struct ice_pf *pf); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_hwtstamp_get(struct net_device *netdev, @@ -345,16 +347,18 @@ static inline void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) static inline void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { } -static inline bool ice_ptp_process_ts(struct ice_pf *pf) -{ - return true; -} +static inline void ice_ptp_process_ts(struct ice_pf *pf) { } static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) { return IRQ_HANDLED; } +static inline bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + return false; +} + static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) { @@ -383,6 +387,10 @@ static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } +static inline void ice_ptp_queue_work(struct ice_pf *pf) +{ +} + static inline int ice_ptp_clock_index(struct ice_pf *pf) { return -1; diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 88e9424d2d51..b49c4708bf9e 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -12,6 +12,7 @@ #include <linux/dma-mapping.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> @@ -38,7 +39,7 @@ #define EMAC_DEFAULT_BUFSIZE 1536 #define EMAC_RX_BUF_2K 2048 -#define EMAC_RX_BUF_4K 4096 +#define EMAC_RX_BUF_MAX FIELD_MAX(RX_DESC_1_BUFFER_SIZE_1_MASK) /* Tuning parameters from SpacemiT */ #define EMAC_TX_FRAMES 64 @@ -202,8 +203,7 @@ static void emac_init_hw(struct emac_priv *priv) { /* Destination address for 802.3x Ethernet flow control */ u8 fc_dest_addr[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x01 }; - - u32 rxirq = 0, dma = 0; + u32 rxirq = 0, dma = 0, frame_sz; regmap_set_bits(priv->regmap_apmu, priv->regmap_apmu_offset + APMU_EMAC_CTRL_REG, @@ -228,6 +228,15 @@ static void emac_init_hw(struct emac_priv *priv) DEFAULT_TX_THRESHOLD); emac_wr(priv, MAC_RECEIVE_PACKET_START_THRESHOLD, DEFAULT_RX_THRESHOLD); + /* Set maximum frame size and jabber size based on configured MTU, + * accounting for Ethernet header, double VLAN tags, and FCS. + */ + frame_sz = priv->ndev->mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; + + emac_wr(priv, MAC_MAXIMUM_FRAME_SIZE, frame_sz); + emac_wr(priv, MAC_TRANSMIT_JABBER_SIZE, frame_sz); + emac_wr(priv, MAC_RECEIVE_JABBER_SIZE, frame_sz); + /* Configure flow control (enabled in emac_adjust_link() later) */ emac_set_mac_addr_reg(priv, fc_dest_addr, MAC_FC_SOURCE_ADDRESS_HIGH); emac_wr(priv, MAC_FC_PAUSE_HIGH_THRESHOLD, DEFAULT_FC_FIFO_HIGH); @@ -924,14 +933,14 @@ static int emac_change_mtu(struct net_device *ndev, int mtu) return -EBUSY; } - frame_len = mtu + ETH_HLEN + ETH_FCS_LEN; + frame_len = mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; if (frame_len <= EMAC_DEFAULT_BUFSIZE) priv->dma_buf_sz = EMAC_DEFAULT_BUFSIZE; else if (frame_len <= EMAC_RX_BUF_2K) priv->dma_buf_sz = EMAC_RX_BUF_2K; else - priv->dma_buf_sz = EMAC_RX_BUF_4K; + priv->dma_buf_sz = EMAC_RX_BUF_MAX; ndev->mtu = mtu; @@ -2025,7 +2034,7 @@ static int emac_probe(struct platform_device *pdev) ndev->hw_features = NETIF_F_SG; ndev->features |= ndev->hw_features; - ndev->max_mtu = EMAC_RX_BUF_4K - (ETH_HLEN + ETH_FCS_LEN); + ndev->max_mtu = EMAC_RX_BUF_MAX - (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN); ndev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3f42843cd9ed..a379221b96a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -8042,7 +8042,7 @@ int stmmac_suspend(struct device *dev) u32 chan; if (!ndev || !netif_running(ndev)) - return 0; + goto suspend_bsp; mutex_lock(&priv->lock); @@ -8082,6 +8082,7 @@ int stmmac_suspend(struct device *dev) if (stmmac_fpe_supported(priv)) ethtool_mmsv_stop(&priv->fpe_cfg.mmsv); +suspend_bsp: if (priv->plat->suspend) return priv->plat->suspend(dev, priv->plat->bsp_priv); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 54c24cd3d3be..b0e18bdc2c85 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -305,12 +305,19 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; int slave_port = -1; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); + if (cpsw->data.dual_emac) slave_port = priv->emac_port + 1; @@ -318,7 +325,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, slave_port); - return; + goto unlock_addr; } else { /* Disable promiscuous mode */ cpsw_set_promiscious(ndev, false); @@ -331,6 +338,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1472,6 +1491,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) priv_sl2->ndev = ndev; priv_sl2->dev = &ndev->dev; priv_sl2->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); + INIT_WORK(&priv_sl2->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[1].mac_addr)) { memcpy(priv_sl2->mac_addr, data->slave_data[1].mac_addr, @@ -1653,6 +1673,7 @@ static int cpsw_probe(struct platform_device *pdev) priv->dev = dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = 0; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[0].mac_addr)) { memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN); @@ -1758,6 +1779,8 @@ clean_runtime_disable_ret: static void cpsw_remove(struct platform_device *pdev) { struct cpsw_common *cpsw = platform_get_drvdata(pdev); + struct net_device *ndev; + struct cpsw_priv *priv; int i, ret; ret = pm_runtime_resume_and_get(&pdev->dev); @@ -1770,9 +1793,15 @@ static void cpsw_remove(struct platform_device *pdev) return; } - for (i = 0; i < cpsw->data.slaves; i++) - if (cpsw->slaves[i].ndev) - unregister_netdev(cpsw->slaves[i].ndev); + for (i = 0; i < cpsw->data.slaves; i++) { + ndev = cpsw->slaves[i].ndev; + if (!ndev) + continue; + + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); + } cpts_release(cpsw->cpts); cpdma_ctlr_destroy(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index ab88d4c02cbd..21af0a10626a 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -248,16 +248,22 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, priv->emac_port); - return; + goto unlock_addr; } /* Disable promiscuous mode */ @@ -270,6 +276,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1398,6 +1416,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = i + 1; priv->tx_packet_min = CPSW_MIN_PACKET_SIZE; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(slave_data->mac_addr)) { ether_addr_copy(priv->mac_addr, slave_data->mac_addr); @@ -1447,13 +1466,18 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) static void cpsw_unregister_ports(struct cpsw_common *cpsw) { + struct net_device *ndev; + struct cpsw_priv *priv; int i = 0; for (i = 0; i < cpsw->data.slaves; i++) { - if (!cpsw->slaves[i].ndev) + ndev = cpsw->slaves[i].ndev; + if (!ndev) continue; - unregister_netdev(cpsw->slaves[i].ndev); + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); } } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 91add8925e23..acb6181c5c9e 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -391,6 +391,7 @@ struct cpsw_priv { u32 tx_packet_min; struct cpsw_ale_ratelimit ale_bc_ratelimit; struct cpsw_ale_ratelimit ale_mc_ratelimit; + struct work_struct rx_mode_work; }; #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b4df7e184791..c509228be84d 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1567,9 +1567,10 @@ destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(lowerdev)) { + if (macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); - macvlan_port_destroy(port->dev); + if (create) + macvlan_port_destroy(port->dev); } return err; } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 47f095bd91ce..3e023723887c 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -479,6 +479,8 @@ static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id, linkmode_zero(caps->link_modes); linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, caps->link_modes); + phy_interface_zero(caps->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces); } #define SFP_QUIRK(_v, _p, _s, _f) \ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index fa5192583860..2f3baa5f6e9c 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8535,19 +8535,6 @@ static int rtl8152_system_resume(struct r8152 *tp) usb_submit_urb(tp->intr_urb, GFP_NOIO); } - /* If the device is RTL8152_INACCESSIBLE here then we should do a - * reset. This is important because the usb_lock_device_for_reset() - * that happens as a result of usb_queue_reset_device() will silently - * fail if the device was suspended or if too much time passed. - * - * NOTE: The device is locked here so we can directly do the reset. - * We don't need usb_lock_device_for_reset() because that's just a - * wrapper over device_lock() and device_resume() (which calls us) - * does that for us. - */ - if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) - usb_reset_device(tp->udev); - return 0; } @@ -8658,19 +8645,33 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); + bool runtime_resume = test_bit(SELECTIVE_SUSPEND, &tp->flags); int ret; mutex_lock(&tp->control); rtl_reset_ocp_base(tp); - if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) + if (runtime_resume) ret = rtl8152_runtime_resume(tp); else ret = rtl8152_system_resume(tp); mutex_unlock(&tp->control); + /* If the device is RTL8152_INACCESSIBLE here then we should do a + * reset. This is important because the usb_lock_device_for_reset() + * that happens as a result of usb_queue_reset_device() will silently + * fail if the device was suspended or if too much time passed. + * + * NOTE: The device is locked here so we can directly do the reset. + * We don't need usb_lock_device_for_reset() because that's just a + * wrapper over device_lock() and device_resume() (which calls us) + * does that for us. + */ + if (!runtime_resume && test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + usb_reset_device(tp->udev); + return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c index a5ececfc13e4..f15d1f5d1bf5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c @@ -55,8 +55,6 @@ void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif) ieee80211_iter_keys(mld->hw, vif, iwl_mld_cleanup_keys_iter, NULL); - wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->mlo_scan_start_wk); - CLEANUP_STRUCT(mld_vif); } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 55b484c16280..cd0dce8de856 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1759,6 +1759,8 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld, wiphy_work_cancel(mld->wiphy, &mld_vif->emlsr.unblock_tpt_wk); wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->emlsr.check_tpt_wk); + wiphy_delayed_work_cancel(mld->wiphy, + &mld_vif->mlo_scan_start_wk); iwl_mld_reset_cca_40mhz_workaround(mld, vif); iwl_mld_smps_workaround(mld, vif, true); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 07f1a84c274e..af1a45845999 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3239,6 +3239,8 @@ void iwl_mvm_fast_suspend(struct iwl_mvm *mvm) IWL_DEBUG_WOWLAN(mvm, "Starting fast suspend flow\n"); + iwl_mvm_pause_tcm(mvm, true); + mvm->fast_resume = true; set_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); @@ -3295,6 +3297,8 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm) mvm->trans->state = IWL_TRANS_NO_FW; } + iwl_mvm_resume_tcm(mvm); + out: clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); mvm->fast_resume = false; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c2bee32332fe..d86f2565a92c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -816,6 +816,32 @@ static void nvme_unmap_data(struct request *req) nvme_free_descriptors(req); } +static bool nvme_pci_prp_save_mapping(struct request *req, + struct device *dma_dev, + struct blk_dma_iter *iter) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + + if (dma_use_iova(&iod->dma_state) || !dma_need_unmap(dma_dev)) + return true; + + if (!iod->nr_dma_vecs) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; + + iod->dma_vecs = mempool_alloc(nvmeq->dev->dmavec_mempool, + GFP_ATOMIC); + if (!iod->dma_vecs) { + iter->status = BLK_STS_RESOURCE; + return false; + } + } + + iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; + iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; + iod->nr_dma_vecs++; + return true; +} + static bool nvme_pci_prp_iter_next(struct request *req, struct device *dma_dev, struct blk_dma_iter *iter) { @@ -825,12 +851,7 @@ static bool nvme_pci_prp_iter_next(struct request *req, struct device *dma_dev, return true; if (!blk_rq_dma_map_iter_next(req, dma_dev, &iod->dma_state, iter)) return false; - if (!dma_use_iova(&iod->dma_state) && dma_need_unmap(dma_dev)) { - iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; - iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; - iod->nr_dma_vecs++; - } - return true; + return nvme_pci_prp_save_mapping(req, dma_dev, iter); } static blk_status_t nvme_pci_setup_data_prp(struct request *req, @@ -843,15 +864,8 @@ static blk_status_t nvme_pci_setup_data_prp(struct request *req, unsigned int prp_len, i; __le64 *prp_list; - if (!dma_use_iova(&iod->dma_state) && dma_need_unmap(nvmeq->dev->dev)) { - iod->dma_vecs = mempool_alloc(nvmeq->dev->dmavec_mempool, - GFP_ATOMIC); - if (!iod->dma_vecs) - return BLK_STS_RESOURCE; - iod->dma_vecs[0].addr = iter->addr; - iod->dma_vecs[0].len = iter->len; - iod->nr_dma_vecs = 1; - } + if (!nvme_pci_prp_save_mapping(req, nvmeq->dev->dev, iter)) + return iter->status; /* * PRP1 always points to the start of the DMA transfers. @@ -1219,6 +1233,7 @@ static blk_status_t nvme_prep_rq(struct request *req) iod->nr_descriptors = 0; iod->total_len = 0; iod->meta_total_len = 0; + iod->nr_dma_vecs = 0; ret = nvme_setup_cmd(req->q->queuedata, req); if (ret) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 549a4786d1c3..bda816d66846 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -349,11 +349,14 @@ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) cmd->req.sg = NULL; } +static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); + static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct bio_vec *iov = cmd->iov; struct scatterlist *sg; u32 length, offset, sg_offset; + unsigned int sg_remaining; int nr_pages; length = cmd->pdu_len; @@ -361,9 +364,22 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } sg = &cmd->req.sg[cmd->sg_idx]; + sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { + if (!sg_remaining) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } + if (!sg->length || sg->length <= sg_offset) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } u32 iov_len = min_t(u32, length, sg->length - sg_offset); bvec_set_page(iov, sg_page(sg), iov_len, @@ -371,6 +387,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) length -= iov_len; sg = sg_next(sg); + sg_remaining--; iov++; sg_offset = 0; } diff --git a/drivers/pci/ide.c b/drivers/pci/ide.c index f0ef474e1a0d..23f554490539 100644 --- a/drivers/pci/ide.c +++ b/drivers/pci/ide.c @@ -11,7 +11,6 @@ #include <linux/pci_regs.h> #include <linux/slab.h> #include <linux/sysfs.h> -#include <linux/tsm.h> #include "pci.h" @@ -168,7 +167,7 @@ void pci_ide_init(struct pci_dev *pdev) for (u16 i = 0; i < nr_streams; i++) { int pos = __sel_ide_offset(ide_cap, nr_link_ide, i, nr_ide_mem); - pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CAP, &val); + pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CTL, &val); if (val & PCI_IDE_SEL_CTL_EN) continue; val &= ~PCI_IDE_SEL_CTL_ID; @@ -283,8 +282,8 @@ struct pci_ide *pci_ide_stream_alloc(struct pci_dev *pdev) /* for SR-IOV case, cover all VFs */ num_vf = pci_num_vf(pdev); if (num_vf) - rid_end = PCI_DEVID(pci_iov_virtfn_bus(pdev, num_vf), - pci_iov_virtfn_devfn(pdev, num_vf)); + rid_end = PCI_DEVID(pci_iov_virtfn_bus(pdev, num_vf - 1), + pci_iov_virtfn_devfn(pdev, num_vf - 1)); else rid_end = pci_dev_id(pdev); @@ -373,9 +372,6 @@ void pci_ide_stream_release(struct pci_ide *ide) if (ide->partner[PCI_IDE_EP].enable) pci_ide_stream_disable(pdev, ide); - if (ide->tsm_dev) - tsm_ide_stream_unregister(ide); - if (ide->partner[PCI_IDE_RP].setup) pci_ide_stream_teardown(rp, ide); diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 404e62ad293a..ed285afaf9b0 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -302,6 +302,13 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), } }, + { + .ident = "MECHREVO Wujie 15X Pro", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE Series-X5SP4NAG"), + } + }, {} }; diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c index 6b1b8e444e24..74d3eb83f56a 100644 --- a/drivers/platform/x86/classmate-laptop.c +++ b/drivers/platform/x86/classmate-laptop.c @@ -207,7 +207,12 @@ static ssize_t cmpc_accel_sensitivity_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->sensitivity); } @@ -224,7 +229,12 @@ static ssize_t cmpc_accel_sensitivity_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) @@ -256,7 +266,12 @@ static ssize_t cmpc_accel_g_select_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->g_select); } @@ -273,7 +288,12 @@ static ssize_t cmpc_accel_g_select_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &g_select); if (r) @@ -302,6 +322,8 @@ static int cmpc_accel_open_v4(struct input_dev *input) acpi = to_acpi_device(input->dev.parent); accel = dev_get_drvdata(&input->dev); + if (!accel) + return -ENXIO; cmpc_accel_set_sensitivity_v4(acpi->handle, accel->sensitivity); cmpc_accel_set_g_select_v4(acpi->handle, accel->g_select); @@ -549,7 +571,12 @@ static ssize_t cmpc_accel_sensitivity_show(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->sensitivity); } @@ -566,7 +593,12 @@ static ssize_t cmpc_accel_sensitivity_store(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index dbe096eefa75..51e8977d3eb4 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -696,6 +696,11 @@ static int hp_init_bios_package_attribute(enum hp_wmi_data_type attr_type, return ret; } + if (!str_value || !str_value[0]) { + pr_debug("Ignoring attribute with empty name\n"); + goto pack_attr_exit; + } + /* All duplicate attributes found are ignored */ duplicate = kset_find_obj(temp_kset, str_value); if (duplicate) { diff --git a/drivers/platform/x86/intel/plr_tpmi.c b/drivers/platform/x86/intel/plr_tpmi.c index 58132da47745..05727169f49c 100644 --- a/drivers/platform/x86/intel/plr_tpmi.c +++ b/drivers/platform/x86/intel/plr_tpmi.c @@ -316,7 +316,7 @@ static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxilia snprintf(name, sizeof(name), "domain%d", i); dentry = debugfs_create_dir(name, plr->dbgfs_dir); - debugfs_create_file("status", 0444, dentry, &plr->die_info[i], + debugfs_create_file("status", 0644, dentry, &plr->die_info[i], &plr_status_fops); } diff --git a/drivers/platform/x86/intel/telemetry/debugfs.c b/drivers/platform/x86/intel/telemetry/debugfs.c index 70e5736c44c7..189c61ff7ff0 100644 --- a/drivers/platform/x86/intel/telemetry/debugfs.c +++ b/drivers/platform/x86/intel/telemetry/debugfs.c @@ -449,7 +449,7 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) for (index = 0; index < debugfs_conf->pss_ltr_evts; index++) { seq_printf(s, "%-32s\t%u\n", debugfs_conf->pss_ltr_data[index].name, - pss_s0ix_wakeup[index]); + pss_ltr_blkd[index]); } seq_puts(s, "\n--------------------------------------\n"); @@ -459,7 +459,7 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) for (index = 0; index < debugfs_conf->pss_wakeup_evts; index++) { seq_printf(s, "%-32s\t%u\n", debugfs_conf->pss_wakeup[index].name, - pss_ltr_blkd[index]); + pss_s0ix_wakeup[index]); } return 0; diff --git a/drivers/platform/x86/intel/telemetry/pltdrv.c b/drivers/platform/x86/intel/telemetry/pltdrv.c index f23c170a55dc..d9aa349f81e4 100644 --- a/drivers/platform/x86/intel/telemetry/pltdrv.c +++ b/drivers/platform/x86/intel/telemetry/pltdrv.c @@ -610,7 +610,7 @@ static int telemetry_setup(struct platform_device *pdev) /* Get telemetry Info */ events = (read_buf & TELEM_INFO_SRAMEVTS_MASK) >> TELEM_INFO_SRAMEVTS_SHIFT; - event_regs = read_buf & TELEM_INFO_SRAMEVTS_MASK; + event_regs = read_buf & TELEM_INFO_NENABLES_MASK; if ((events < TELEM_MAX_EVENTS_SRAM) || (event_regs < TELEM_MAX_EVENTS_SRAM)) { dev_err(&pdev->dev, "PSS:Insufficient Space for SRAM Trace\n"); diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index ecfc7703f201..012d87878afd 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -766,6 +766,7 @@ static const struct intel_vsec_platform_info lnl_info = { #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d #define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d #define PCI_DEVICE_ID_INTEL_VSEC_WCL 0xfd7d +#define PCI_DEVICE_ID_INTEL_VSEC_NVL 0xd70d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, @@ -778,6 +779,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_WCL, &mtl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_NVL, &mtl_info) }, { } }; MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids); diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c index f92e89c75db9..61ef7a218a80 100644 --- a/drivers/platform/x86/lg-laptop.c +++ b/drivers/platform/x86/lg-laptop.c @@ -838,8 +838,17 @@ static int acpi_add(struct acpi_device *device) case 'P': year = 2021; break; - default: + case 'Q': year = 2022; + break; + case 'R': + year = 2023; + break; + case 'S': + year = 2024; + break; + default: + year = 2025; } break; default: diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 255317e6fec8..937f1a5b78ed 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -1089,7 +1089,7 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) PLATFORM_DEVID_NONE, NULL, 0); if (IS_ERR(pcc->platform)) { result = PTR_ERR(pcc->platform); - goto out_backlight; + goto out_sysfs; } result = device_create_file(&pcc->platform->dev, &dev_attr_cdpower); @@ -1105,6 +1105,8 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) out_platform: platform_device_unregister(pcc->platform); +out_sysfs: + sysfs_remove_group(&device->dev.kobj, &pcc_attr_group); out_backlight: backlight_device_unregister(pcc->backlight); out_input: diff --git a/drivers/platform/x86/toshiba_haps.c b/drivers/platform/x86/toshiba_haps.c index 03dfddeee0c0..e9324bf16aea 100644 --- a/drivers/platform/x86/toshiba_haps.c +++ b/drivers/platform/x86/toshiba_haps.c @@ -183,7 +183,7 @@ static int toshiba_haps_add(struct acpi_device *acpi_dev) pr_info("Toshiba HDD Active Protection Sensor device\n"); - haps = kzalloc(sizeof(struct toshiba_haps_dev), GFP_KERNEL); + haps = devm_kzalloc(&acpi_dev->dev, sizeof(*haps), GFP_KERNEL); if (!haps) return -ENOMEM; diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c index fef840b54574..c18a0c946f76 100644 --- a/drivers/soc/qcom/smem.c +++ b/drivers/soc/qcom/smem.c @@ -396,7 +396,7 @@ EXPORT_SYMBOL_GPL(qcom_smem_bust_hwspin_lock_by_host); */ bool qcom_smem_is_available(void) { - return !!__smem; + return !IS_ERR(__smem); } EXPORT_SYMBOL_GPL(qcom_smem_is_available); @@ -1247,7 +1247,8 @@ static void qcom_smem_remove(struct platform_device *pdev) { platform_device_unregister(__smem->socinfo); - __smem = NULL; + /* Set to -EPROBE_DEFER to signal unprobed state */ + __smem = ERR_PTR(-EPROBE_DEFER); } static const struct of_device_id qcom_smem_of_match[] = { diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 05c6750702b6..fa467a40949d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -59,7 +59,6 @@ static struct ffs_data *__must_check ffs_data_new(const char *dev_name) __attribute__((malloc)); /* Opened counter handling. */ -static void ffs_data_opened(struct ffs_data *ffs); static void ffs_data_closed(struct ffs_data *ffs); /* Called with ffs->mutex held; take over ownership of data. */ @@ -636,23 +635,25 @@ done_mutex: return ret; } + +static void ffs_data_reset(struct ffs_data *ffs); + static int ffs_ep0_open(struct inode *inode, struct file *file) { struct ffs_data *ffs = inode->i_sb->s_fs_info; - int ret; - /* Acquire mutex */ - ret = ffs_mutex_lock(&ffs->mutex, file->f_flags & O_NONBLOCK); - if (ret < 0) - return ret; - - ffs_data_opened(ffs); + spin_lock_irq(&ffs->eps_lock); if (ffs->state == FFS_CLOSING) { - ffs_data_closed(ffs); - mutex_unlock(&ffs->mutex); + spin_unlock_irq(&ffs->eps_lock); return -EBUSY; } - mutex_unlock(&ffs->mutex); + if (!ffs->opened++ && ffs->state == FFS_DEACTIVATED) { + ffs->state = FFS_CLOSING; + spin_unlock_irq(&ffs->eps_lock); + ffs_data_reset(ffs); + } else { + spin_unlock_irq(&ffs->eps_lock); + } file->private_data = ffs; return stream_open(inode, file); @@ -1202,15 +1203,10 @@ ffs_epfile_open(struct inode *inode, struct file *file) { struct ffs_data *ffs = inode->i_sb->s_fs_info; struct ffs_epfile *epfile; - int ret; - - /* Acquire mutex */ - ret = ffs_mutex_lock(&ffs->mutex, file->f_flags & O_NONBLOCK); - if (ret < 0) - return ret; - if (!atomic_inc_not_zero(&ffs->opened)) { - mutex_unlock(&ffs->mutex); + spin_lock_irq(&ffs->eps_lock); + if (!ffs->opened) { + spin_unlock_irq(&ffs->eps_lock); return -ENODEV; } /* @@ -1220,11 +1216,11 @@ ffs_epfile_open(struct inode *inode, struct file *file) */ epfile = smp_load_acquire(&inode->i_private); if (unlikely(ffs->state != FFS_ACTIVE || !epfile)) { - mutex_unlock(&ffs->mutex); - ffs_data_closed(ffs); + spin_unlock_irq(&ffs->eps_lock); return -ENODEV; } - mutex_unlock(&ffs->mutex); + ffs->opened++; + spin_unlock_irq(&ffs->eps_lock); file->private_data = epfile; return stream_open(inode, file); @@ -2092,8 +2088,6 @@ static int ffs_fs_init_fs_context(struct fs_context *fc) return 0; } -static void ffs_data_reset(struct ffs_data *ffs); - static void ffs_fs_kill_sb(struct super_block *sb) { @@ -2150,15 +2144,6 @@ static void ffs_data_get(struct ffs_data *ffs) refcount_inc(&ffs->ref); } -static void ffs_data_opened(struct ffs_data *ffs) -{ - if (atomic_add_return(1, &ffs->opened) == 1 && - ffs->state == FFS_DEACTIVATED) { - ffs->state = FFS_CLOSING; - ffs_data_reset(ffs); - } -} - static void ffs_data_put(struct ffs_data *ffs) { if (refcount_dec_and_test(&ffs->ref)) { @@ -2176,28 +2161,29 @@ static void ffs_data_put(struct ffs_data *ffs) static void ffs_data_closed(struct ffs_data *ffs) { - if (atomic_dec_and_test(&ffs->opened)) { - if (ffs->no_disconnect) { - struct ffs_epfile *epfiles; - unsigned long flags; - - ffs->state = FFS_DEACTIVATED; - spin_lock_irqsave(&ffs->eps_lock, flags); - epfiles = ffs->epfiles; - ffs->epfiles = NULL; - spin_unlock_irqrestore(&ffs->eps_lock, - flags); - - if (epfiles) - ffs_epfiles_destroy(ffs->sb, epfiles, - ffs->eps_count); - - if (ffs->setup_state == FFS_SETUP_PENDING) - __ffs_ep0_stall(ffs); - } else { - ffs->state = FFS_CLOSING; - ffs_data_reset(ffs); - } + spin_lock_irq(&ffs->eps_lock); + if (--ffs->opened) { // not the last opener? + spin_unlock_irq(&ffs->eps_lock); + return; + } + if (ffs->no_disconnect) { + struct ffs_epfile *epfiles; + + ffs->state = FFS_DEACTIVATED; + epfiles = ffs->epfiles; + ffs->epfiles = NULL; + spin_unlock_irq(&ffs->eps_lock); + + if (epfiles) + ffs_epfiles_destroy(ffs->sb, epfiles, + ffs->eps_count); + + if (ffs->setup_state == FFS_SETUP_PENDING) + __ffs_ep0_stall(ffs); + } else { + ffs->state = FFS_CLOSING; + spin_unlock_irq(&ffs->eps_lock); + ffs_data_reset(ffs); } } @@ -2214,7 +2200,7 @@ static struct ffs_data *ffs_data_new(const char *dev_name) } refcount_set(&ffs->ref, 1); - atomic_set(&ffs->opened, 0); + ffs->opened = 0; ffs->state = FFS_READ_DESCRIPTORS; mutex_init(&ffs->mutex); spin_lock_init(&ffs->eps_lock); @@ -2266,6 +2252,7 @@ static void ffs_data_reset(struct ffs_data *ffs) { ffs_data_clear(ffs); + spin_lock_irq(&ffs->eps_lock); ffs->raw_descs_data = NULL; ffs->raw_descs = NULL; ffs->raw_strings = NULL; @@ -2289,6 +2276,7 @@ static void ffs_data_reset(struct ffs_data *ffs) ffs->ms_os_descs_ext_prop_count = 0; ffs->ms_os_descs_ext_prop_name_len = 0; ffs->ms_os_descs_ext_prop_data_len = 0; + spin_unlock_irq(&ffs->eps_lock); } @@ -3756,6 +3744,7 @@ static int ffs_func_set_alt(struct usb_function *f, { struct ffs_function *func = ffs_func_from_usb(f); struct ffs_data *ffs = func->ffs; + unsigned long flags; int ret = 0, intf; if (alt > MAX_ALT_SETTINGS) @@ -3768,12 +3757,15 @@ static int ffs_func_set_alt(struct usb_function *f, if (ffs->func) ffs_func_eps_disable(ffs->func); + spin_lock_irqsave(&ffs->eps_lock, flags); if (ffs->state == FFS_DEACTIVATED) { ffs->state = FFS_CLOSING; + spin_unlock_irqrestore(&ffs->eps_lock, flags); INIT_WORK(&ffs->reset_work, ffs_reset_work); schedule_work(&ffs->reset_work); return -ENODEV; } + spin_unlock_irqrestore(&ffs->eps_lock, flags); if (ffs->state != FFS_ACTIVE) return -ENODEV; @@ -3791,16 +3783,20 @@ static void ffs_func_disable(struct usb_function *f) { struct ffs_function *func = ffs_func_from_usb(f); struct ffs_data *ffs = func->ffs; + unsigned long flags; if (ffs->func) ffs_func_eps_disable(ffs->func); + spin_lock_irqsave(&ffs->eps_lock, flags); if (ffs->state == FFS_DEACTIVATED) { ffs->state = FFS_CLOSING; + spin_unlock_irqrestore(&ffs->eps_lock, flags); INIT_WORK(&ffs->reset_work, ffs_reset_work); schedule_work(&ffs->reset_work); return; } + spin_unlock_irqrestore(&ffs->eps_lock, flags); if (ffs->state == FFS_ACTIVE) { ffs->func = NULL; diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index 4b3365f23fd7..6a80182aadd7 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -176,7 +176,7 @@ struct ffs_data { /* reference counter */ refcount_t ref; /* how many files are opened (EP0 and others) */ - atomic_t opened; + int opened; /* EP0 state */ enum ffs_state state; diff --git a/drivers/virt/coco/tsm-core.c b/drivers/virt/coco/tsm-core.c index f027876a2f19..8712df8596a1 100644 --- a/drivers/virt/coco/tsm-core.c +++ b/drivers/virt/coco/tsm-core.c @@ -4,16 +4,12 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/tsm.h> -#include <linux/pci.h> -#include <linux/rwsem.h> #include <linux/device.h> #include <linux/module.h> #include <linux/cleanup.h> #include <linux/pci-tsm.h> -#include <linux/pci-ide.h> static struct class *tsm_class; -static DECLARE_RWSEM(tsm_rwsem); static DEFINE_IDA(tsm_ida); static int match_id(struct device *dev, const void *data) @@ -108,32 +104,6 @@ void tsm_unregister(struct tsm_dev *tsm_dev) } EXPORT_SYMBOL_GPL(tsm_unregister); -/* must be invoked between tsm_register / tsm_unregister */ -int tsm_ide_stream_register(struct pci_ide *ide) -{ - struct pci_dev *pdev = ide->pdev; - struct pci_tsm *tsm = pdev->tsm; - struct tsm_dev *tsm_dev = tsm->tsm_dev; - int rc; - - rc = sysfs_create_link(&tsm_dev->dev.kobj, &pdev->dev.kobj, ide->name); - if (rc) - return rc; - - ide->tsm_dev = tsm_dev; - return 0; -} -EXPORT_SYMBOL_GPL(tsm_ide_stream_register); - -void tsm_ide_stream_unregister(struct pci_ide *ide) -{ - struct tsm_dev *tsm_dev = ide->tsm_dev; - - ide->tsm_dev = NULL; - sysfs_remove_link(&tsm_dev->dev.kobj, ide->name); -} -EXPORT_SYMBOL_GPL(tsm_ide_stream_unregister); - static void tsm_release(struct device *dev) { struct tsm_dev *tsm_dev = container_of(dev, typeof(*tsm_dev), dev); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index f38d8305e46d..baadaaa189c0 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -150,6 +150,7 @@ static void scrub_rbio_work_locked(struct work_struct *work); static void free_raid_bio_pointers(struct btrfs_raid_bio *rbio) { bitmap_free(rbio->error_bitmap); + bitmap_free(rbio->stripe_uptodate_bitmap); kfree(rbio->stripe_pages); kfree(rbio->bio_paddrs); kfree(rbio->stripe_paddrs); diff --git a/fs/smb/client/cifstransport.c b/fs/smb/client/cifstransport.c index 28d1cee90625..98287132626e 100644 --- a/fs/smb/client/cifstransport.c +++ b/fs/smb/client/cifstransport.c @@ -251,13 +251,15 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = cifs_send_recv(xid, ses, ses->server, &rqst, &resp_buf_type, flags, &resp_iov); if (rc < 0) - return rc; + goto out; if (out_buf) { *pbytes_returned = resp_iov.iov_len; if (resp_iov.iov_len) memcpy(out_buf, resp_iov.iov_base, resp_iov.iov_len); } + +out: free_rsp_buf(resp_buf_type, resp_iov.iov_base); return rc; } diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 7f11ae6bb785..2dd08388ea87 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -178,6 +178,7 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); if (rc == -EACCES && retry_without_read_attributes) { + free_rsp_buf(err_buftype, err_iov.iov_base); oparms->desired_access &= ~FILE_READ_ATTRIBUTES; rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); diff --git a/include/linux/pci-ide.h b/include/linux/pci-ide.h index 37a1ad9501b0..ae07d9f699c0 100644 --- a/include/linux/pci-ide.h +++ b/include/linux/pci-ide.h @@ -26,7 +26,7 @@ enum pci_ide_partner_select { /** * struct pci_ide_partner - Per port pair Selective IDE Stream settings * @rid_start: Partner Port Requester ID range start - * @rid_end: Partner Port Requester ID range end + * @rid_end: Partner Port Requester ID range end (inclusive) * @stream_index: Selective IDE Stream Register Block selection * @mem_assoc: PCI bus memory address association for targeting peer partner * @pref_assoc: PCI bus prefetchable memory address association for @@ -82,7 +82,6 @@ struct pci_ide_regs { * @host_bridge_stream: allocated from host bridge @ide_stream_ida pool * @stream_id: unique Stream ID (within Partner Port pairing) * @name: name of the established Selective IDE Stream in sysfs - * @tsm_dev: For TSM established IDE, the TSM device context * * Negative @stream_id values indicate "uninitialized" on the * expectation that with TSM established IDE the TSM owns the stream_id @@ -94,7 +93,6 @@ struct pci_ide { u8 host_bridge_stream; int stream_id; const char *name; - struct tsm_dev *tsm_dev; }; /* diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 86737076101d..112e48970338 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4301,6 +4301,18 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) skb_headlen(skb), buffer); } +/* Variant of skb_header_pointer() where @offset is user-controlled + * and potentially negative. + */ +static inline void * __must_check +skb_header_pointer_careful(const struct sk_buff *skb, int offset, + int len, void *buffer) +{ + if (unlikely(offset < 0 && -offset > skb_headroom(skb))) + return NULL; + return skb_header_pointer(skb, offset, len, buffer); +} + static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { diff --git a/include/linux/tsm.h b/include/linux/tsm.h index a3b7ab668eff..22e05b2aac69 100644 --- a/include/linux/tsm.h +++ b/include/linux/tsm.h @@ -123,7 +123,4 @@ int tsm_report_unregister(const struct tsm_report_ops *ops); struct tsm_dev *tsm_register(struct device *parent, struct pci_tsm_ops *ops); void tsm_unregister(struct tsm_dev *tsm_dev); struct tsm_dev *find_tsm_dev(int id); -struct pci_ide; -int tsm_ide_stream_register(struct pci_ide *ide); -void tsm_ide_stream_unregister(struct pci_ide *ide); #endif /* __TSM_H */ diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index a87d4e26eee8..80178b69e05a 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -67,7 +67,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); unsigned int sq_shift = 0; - unsigned int sq_entries; + unsigned int cq_entries, sq_entries; int sq_pid = -1, sq_cpu = -1; u64 sq_total_time = 0, sq_work_time = 0; unsigned int i; @@ -146,9 +146,11 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) } } seq_printf(m, "\n"); + cond_resched(); } seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); - while (cq_head < cq_tail) { + cq_entries = min(cq_tail - cq_head, ctx->cq_entries); + for (i = 0; i < cq_entries; i++) { struct io_uring_cqe *cqe; bool cqe32 = false; @@ -159,12 +161,15 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) cq_head & cq_mask, cqe->user_data, cqe->res, cqe->flags); if (cqe32) - seq_printf(m, ", extra1:%llu, extra2:%llu\n", + seq_printf(m, ", extra1:%llu, extra2:%llu", cqe->big_cqe[0], cqe->big_cqe[1]); seq_printf(m, "\n"); cq_head++; - if (cqe32) + if (cqe32) { cq_head++; + i++; + } + cond_resched(); } if (ctx->flags & IORING_SETUP_SQPOLL) { diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index b99cf2c6670a..3d398283cf34 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -197,6 +197,7 @@ static int io_import_umem(struct io_zcrx_ifq *ifq, GFP_KERNEL_ACCOUNT); if (ret) { unpin_user_pages(pages, nr_pages); + kvfree(pages); return ret; } @@ -1068,8 +1069,6 @@ static unsigned zcrx_parse_rq(netmem_ref *netmem_array, unsigned nr, unsigned int mask = zcrx->rq_entries - 1; unsigned int i; - guard(spinlock_bh)(&zcrx->rq_lock); - nr = min(nr, io_zcrx_rqring_entries(zcrx)); for (i = 0; i < nr; i++) { struct io_uring_zcrx_rqe *rqe = io_zcrx_get_rqe(zcrx, mask); @@ -1114,9 +1113,11 @@ static int zcrx_flush_rq(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, return -EINVAL; do { - nr = zcrx_parse_rq(netmems, ZCRX_FLUSH_BATCH, zcrx); + scoped_guard(spinlock_bh, &zcrx->rq_lock) { + nr = zcrx_parse_rq(netmems, ZCRX_FLUSH_BATCH, zcrx); + zcrx_return_buffers(netmems, nr); + } - zcrx_return_buffers(netmems, nr); total += nr; if (fatal_signal_pending(current)) diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index e12b946278b6..1ea6afffa985 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -14,6 +14,7 @@ #include <linux/mutex.h> #include <linux/page_counter.h> #include <linux/parser.h> +#include <linux/refcount.h> #include <linux/rculist.h> #include <linux/slab.h> @@ -71,7 +72,9 @@ struct dmem_cgroup_pool_state { struct rcu_head rcu; struct page_counter cnt; + struct dmem_cgroup_pool_state *parent; + refcount_t ref; bool inited; }; @@ -88,6 +91,9 @@ struct dmem_cgroup_pool_state { static DEFINE_SPINLOCK(dmemcg_lock); static LIST_HEAD(dmem_cgroup_regions); +static void dmemcg_free_region(struct kref *ref); +static void dmemcg_pool_free_rcu(struct rcu_head *rcu); + static inline struct dmemcg_state * css_to_dmemcs(struct cgroup_subsys_state *css) { @@ -104,10 +110,38 @@ static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg) return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL; } +static void dmemcg_pool_get(struct dmem_cgroup_pool_state *pool) +{ + refcount_inc(&pool->ref); +} + +static bool dmemcg_pool_tryget(struct dmem_cgroup_pool_state *pool) +{ + return refcount_inc_not_zero(&pool->ref); +} + +static void dmemcg_pool_put(struct dmem_cgroup_pool_state *pool) +{ + if (!refcount_dec_and_test(&pool->ref)) + return; + + call_rcu(&pool->rcu, dmemcg_pool_free_rcu); +} + +static void dmemcg_pool_free_rcu(struct rcu_head *rcu) +{ + struct dmem_cgroup_pool_state *pool = container_of(rcu, typeof(*pool), rcu); + + if (pool->parent) + dmemcg_pool_put(pool->parent); + kref_put(&pool->region->ref, dmemcg_free_region); + kfree(pool); +} + static void free_cg_pool(struct dmem_cgroup_pool_state *pool) { list_del(&pool->region_node); - kfree(pool); + dmemcg_pool_put(pool); } static void @@ -342,6 +376,12 @@ alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region page_counter_init(&pool->cnt, ppool ? &ppool->cnt : NULL, true); reset_all_resource_limits(pool); + refcount_set(&pool->ref, 1); + kref_get(®ion->ref); + if (ppool && !pool->parent) { + pool->parent = ppool; + dmemcg_pool_get(ppool); + } list_add_tail_rcu(&pool->css_node, &dmemcs->pools); list_add_tail(&pool->region_node, ®ion->pools); @@ -389,6 +429,10 @@ get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *regio /* Fix up parent links, mark as inited. */ pool->cnt.parent = &ppool->cnt; + if (ppool && !pool->parent) { + pool->parent = ppool; + dmemcg_pool_get(ppool); + } pool->inited = true; pool = ppool; @@ -423,7 +467,7 @@ static void dmemcg_free_region(struct kref *ref) */ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) { - struct list_head *entry; + struct dmem_cgroup_pool_state *pool, *next; if (!region) return; @@ -433,11 +477,10 @@ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) /* Remove from global region list */ list_del_rcu(®ion->region_node); - list_for_each_rcu(entry, ®ion->pools) { - struct dmem_cgroup_pool_state *pool = - container_of(entry, typeof(*pool), region_node); - + list_for_each_entry_safe(pool, next, ®ion->pools, region_node) { list_del_rcu(&pool->css_node); + list_del(&pool->region_node); + dmemcg_pool_put(pool); } /* @@ -518,8 +561,10 @@ static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name) */ void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) { - if (pool) + if (pool) { css_put(&pool->cs->css); + dmemcg_pool_put(pool); + } } EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put); @@ -533,6 +578,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = find_cg_pool_locked(cg, region); if (pool && !READ_ONCE(pool->inited)) pool = NULL; + if (pool && !dmemcg_pool_tryget(pool)) + pool = NULL; rcu_read_unlock(); while (!pool) { @@ -541,6 +588,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = get_cg_pool_locked(cg, region, &allocpool); else pool = ERR_PTR(-ENODEV); + if (!IS_ERR(pool)) + dmemcg_pool_get(pool); spin_unlock(&dmemcg_lock); if (pool == ERR_PTR(-ENOMEM)) { @@ -576,6 +625,7 @@ void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) page_counter_uncharge(&pool->cnt, size); css_put(&pool->cs->css); + dmemcg_pool_put(pool); } EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge); @@ -627,7 +677,9 @@ int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, if (ret_limit_pool) { *ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt); css_get(&(*ret_limit_pool)->cs->css); + dmemcg_pool_get(*ret_limit_pool); } + dmemcg_pool_put(pool); ret = -EAGAIN; goto err; } @@ -700,6 +752,9 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, if (!region_name[0]) continue; + if (!options || !*options) + return -EINVAL; + rcu_read_lock(); region = dmemcg_get_region_by_name(region_name); rcu_read_unlock(); @@ -719,6 +774,7 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, /* And commit */ apply(pool, new_limit); + dmemcg_pool_put(pool); out_put: kref_put(®ion->ref, dmemcg_free_region); diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index a32a777f6df8..9f7283379ebc 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -402,8 +402,6 @@ static void luo_file_unfreeze_one(struct luo_file_set *file_set, luo_file->fh->ops->unfreeze(&args); } - - luo_file->serialized_data = 0; } static void __luo_file_unfreeze(struct luo_file_set *file_set, diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index afe28c04d5aa..0bb8fa927e9e 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -194,6 +194,7 @@ MODULE_PARM_DESC(bypass_lb_intv_us, "bypass load balance interval in microsecond #include <trace/events/sched_ext.h> static void process_ddsp_deferred_locals(struct rq *rq); +static bool task_dead_and_done(struct task_struct *p); static u32 reenq_local(struct rq *rq); static void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags); static bool scx_vexit(struct scx_sched *sch, enum scx_exit_kind kind, @@ -2619,6 +2620,9 @@ static void set_cpus_allowed_scx(struct task_struct *p, set_cpus_allowed_common(p, ac); + if (task_dead_and_done(p)) + return; + /* * The effective cpumask is stored in @p->cpus_ptr which may temporarily * differ from the configured one in @p->cpus_mask. Always tell the bpf @@ -3034,10 +3038,45 @@ void scx_cancel_fork(struct task_struct *p) percpu_up_read(&scx_fork_rwsem); } +/** + * task_dead_and_done - Is a task dead and done running? + * @p: target task + * + * Once sched_ext_dead() removes the dead task from scx_tasks and exits it, the + * task no longer exists from SCX's POV. However, certain sched_class ops may be + * invoked on these dead tasks leading to failures - e.g. sched_setscheduler() + * may try to switch a task which finished sched_ext_dead() back into SCX + * triggering invalid SCX task state transitions and worse. + * + * Once a task has finished the final switch, sched_ext_dead() is the only thing + * that needs to happen on the task. Use this test to short-circuit sched_class + * operations which may be called on dead tasks. + */ +static bool task_dead_and_done(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); + + /* + * In do_task_dead(), a dying task sets %TASK_DEAD with preemption + * disabled and __schedule(). If @p has %TASK_DEAD set and off CPU, @p + * won't ever run again. + */ + return unlikely(READ_ONCE(p->__state) == TASK_DEAD) && + !task_on_cpu(rq, p); +} + void sched_ext_dead(struct task_struct *p) { unsigned long flags; + /* + * By the time control reaches here, @p has %TASK_DEAD set, switched out + * for the last time and then dropped the rq lock - task_dead_and_done() + * should be returning %true nullifying the straggling sched_class ops. + * Remove from scx_tasks and exit @p. + */ raw_spin_lock_irqsave(&scx_tasks_lock, flags); list_del_init(&p->scx.tasks_node); raw_spin_unlock_irqrestore(&scx_tasks_lock, flags); @@ -3063,6 +3102,9 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, lockdep_assert_rq_held(task_rq(p)); + if (task_dead_and_done(p)) + return; + p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); if (SCX_HAS_OP(sch, set_weight)) SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_weight, rq, @@ -3077,6 +3119,9 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) { struct scx_sched *sch = scx_root; + if (task_dead_and_done(p)) + return; + scx_enable_task(p); /* @@ -3090,6 +3135,9 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) static void switched_from_scx(struct rq *rq, struct task_struct *p) { + if (task_dead_and_done(p)) + return; + scx_disable_task(p); } diff --git a/mm/shmem.c b/mm/shmem.c index 6c3485d24d66..79af5f9f8b90 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1211,17 +1211,22 @@ whole_folios: swaps_freed = shmem_free_swap(mapping, indices[i], end - 1, folio); if (!swaps_freed) { - /* - * If found a large swap entry cross the end border, - * skip it as the truncate_inode_partial_folio above - * should have at least zerod its content once. - */ + pgoff_t base = indices[i]; + order = shmem_confirm_swap(mapping, indices[i], radix_to_swp_entry(folio)); - if (order > 0 && indices[i] + (1 << order) > end) - continue; - /* Swap was replaced by page: retry */ - index = indices[i]; + /* + * If found a large swap entry cross the end or start + * border, skip it as the truncate_inode_partial_folio + * above should have at least zerod its content once. + */ + if (order > 0) { + base = round_down(base, 1 << order); + if (base < start || base + (1 << order) > end) + continue; + } + /* Swap was replaced by page or extended, retry */ + index = base; break; } nr_swaps_freed += swaps_freed; diff --git a/net/core/filter.c b/net/core/filter.c index bcd73d9bd764..029e560e32ce 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2289,12 +2289,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; @@ -2396,12 +2396,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; diff --git a/net/core/gro.c b/net/core/gro.c index 76f9c3712422..482fa7d7f598 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -265,6 +265,8 @@ static void gro_complete(struct gro_node *gro, struct sk_buff *skb) goto out; } + /* NICs can feed encapsulated packets into GRO */ + skb->encapsulation = 0; rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { if (ptype->type != type || !ptype->callbacks.gro_complete) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 212cde35affa..25c455c10a01 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -185,10 +185,6 @@ static void linkwatch_do_dev(struct net_device *dev) netif_state_change(dev); } - /* Note: our callers are responsible for calling netdev_tracker_free(). - * This is the reason we use __dev_put() instead of dev_put(). - */ - __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) @@ -243,6 +239,11 @@ static void __linkwatch_run_queue(int urgent_only) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called above. Must be after netdev_unlock_ops() to prevent + * netdev_run_todo() from freeing the device while still in use. + */ + __dev_put(dev); do_dev--; spin_lock_irq(&lweventlist_lock); } @@ -278,8 +279,13 @@ void __linkwatch_sync_dev(struct net_device *dev) { netdev_ops_assert_locked(dev); - if (linkwatch_clean_dev(dev)) + if (linkwatch_clean_dev(dev)) { linkwatch_do_dev(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); + } } void linkwatch_sync_dev(struct net_device *dev) @@ -288,6 +294,10 @@ void linkwatch_sync_dev(struct net_device *dev) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); } } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 70e0e9a3b650..7dbfa6109f0b 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -170,8 +170,14 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, }; +struct ptype_iter_state { + struct seq_net_private p; + struct net_device *dev; +}; + static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct ptype_iter_state *iter = seq->private; struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; @@ -181,12 +187,16 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { - if (i == pos) + if (i == pos) { + iter->dev = dev; return pt; + } ++i; } } + iter->dev = NULL; + list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) { if (i == pos) return pt; @@ -218,6 +228,7 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct ptype_iter_state *iter = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct packet_type *pt; @@ -229,19 +240,21 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ptype_get_idx(seq, 0); pt = v; - nxt = pt->list.next; - if (pt->dev) { - if (nxt != &pt->dev->ptype_all) + nxt = READ_ONCE(pt->list.next); + dev = iter->dev; + if (dev) { + if (nxt != &dev->ptype_all) goto found; - dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { - if (!list_empty(&dev->ptype_all)) { - nxt = dev->ptype_all.next; + nxt = READ_ONCE(dev->ptype_all.next); + if (nxt != &dev->ptype_all) { + iter->dev = dev; goto found; } } - nxt = net->ptype_all.next; + iter->dev = NULL; + nxt = READ_ONCE(net->ptype_all.next); goto net_ptype_all; } @@ -252,20 +265,20 @@ net_ptype_all: if (nxt == &net->ptype_all) { /* continue with ->ptype_specific if it's not empty */ - nxt = net->ptype_specific.next; + nxt = READ_ONCE(net->ptype_specific.next); if (nxt != &net->ptype_specific) goto found; } hash = 0; - nxt = ptype_base[0].next; + nxt = READ_ONCE(ptype_base[0].next); } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; - nxt = ptype_base[hash].next; + nxt = READ_ONCE(ptype_base[hash].next); } found: return list_entry(nxt, struct packet_type, list); @@ -279,19 +292,24 @@ static void ptype_seq_stop(struct seq_file *seq, void *v) static int ptype_seq_show(struct seq_file *seq, void *v) { + struct ptype_iter_state *iter = seq->private; struct packet_type *pt = v; + struct net_device *dev; - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { seq_puts(seq, "Type Device Function\n"); - else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && - (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { + return 0; + } + dev = iter->dev; + if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!dev || net_eq(dev_net(dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", - pt->dev ? pt->dev->name : "", pt->func); + dev ? dev->name : "", pt->func); } return 0; @@ -315,7 +333,7 @@ static int __net_init dev_proc_net_init(struct net *net) &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, - sizeof(struct seq_net_private))) + sizeof(struct ptype_iter_state))) goto out_softnet; if (wext_proc_init(net)) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 369c05cf8163..d47a279eb8b9 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -862,9 +862,6 @@ ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, ctx->key_off = key_off; ctx->priv_size = ops->rxfh_priv_size; - ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; - ctx->input_xfrm = RXH_XFRM_NO_CHANGE; - return ctx; } diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 4dced53be4b3..da5934cceb07 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -824,8 +824,8 @@ rss_set_ctx_update(struct ethtool_rxfh_context *ctx, struct nlattr **tb, static int ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) { - bool indir_reset = false, indir_mod, xfrm_sym = false; struct rss_req_info *request = RSS_REQINFO(req_info); + bool indir_reset = false, indir_mod, xfrm_sym; struct ethtool_rxfh_context *ctx = NULL; struct net_device *dev = req_info->dev; bool mod = false, fields_mod = false; @@ -860,12 +860,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) rxfh.input_xfrm = data.input_xfrm; ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); - /* For drivers which don't support input_xfrm it will be set to 0xff - * in the RSS context info. In all other case input_xfrm != 0 means - * symmetric hashing is requested. - */ - if (!request->rss_context || ops->rxfh_per_ctx_key) - xfrm_sym = rxfh.input_xfrm || data.input_xfrm; + xfrm_sym = rxfh.input_xfrm || data.input_xfrm; if (rxfh.input_xfrm == data.input_xfrm) rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2111af022d94..c6439e30e892 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1138,7 +1138,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } - if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT))) { + if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT)) && + !iter->fib6_nh->fib_nh_gw_family) { iter->fib6_flags &= ~RTF_ADDRCONF; iter->fib6_flags &= ~RTF_PREFIX_RT; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 729a92781a1a..be92750e2af3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5914,7 +5914,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (nft_set_elem_active(ext, genmask)) continue; nft_clear(ctx->net, ext); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 2a1c00048fd6..58e849c0acf4 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -161,10 +161,8 @@ next_knode: int toff = off + key->off + (off2 & key->offmask); __be32 *data, hdata; - if (skb_headroom(skb) + toff > INT_MAX) - goto out; - - data = skb_header_pointer(skb, toff, 4, &hdata); + data = skb_header_pointer_careful(skb, toff, 4, + &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { @@ -214,8 +212,9 @@ check_terminal: if (ht->divisor) { __be32 *data, hdata; - data = skb_header_pointer(skb, off + n->sel.hoff, 4, - &hdata); + data = skb_header_pointer_careful(skb, + off + n->sel.hoff, + 4, &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, @@ -229,7 +228,7 @@ check_terminal: if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, hdata; - data = skb_header_pointer(skb, + data = skb_header_pointer_careful(skb, off + n->sel.offoff, 2, &hdata); if (!data) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 751904f10aab..970db62bd029 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1219,7 +1219,7 @@ void tipc_crypto_key_flush(struct tipc_crypto *c) rx = c; tx = tipc_net(rx->net)->crypto_tx; if (cancel_delayed_work(&rx->work)) { - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; atomic_xchg(&rx->key_distr, 0); tipc_node_put(rx->node); @@ -2394,7 +2394,7 @@ static void tipc_crypto_work_rx(struct work_struct *work) break; default: synchronize_rcu(); - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; break; } diff --git a/security/lsm.h b/security/lsm.h index 81aadbc61685..db77cc83e158 100644 --- a/security/lsm.h +++ b/security/lsm.h @@ -37,15 +37,6 @@ int lsm_task_alloc(struct task_struct *task); /* LSM framework initializers */ -#ifdef CONFIG_MMU -int min_addr_init(void); -#else -static inline int min_addr_init(void) -{ - return 0; -} -#endif /* CONFIG_MMU */ - #ifdef CONFIG_SECURITYFS int securityfs_init(void); #else diff --git a/security/lsm_init.c b/security/lsm_init.c index 05bd52e6b1f2..573e2a7250c4 100644 --- a/security/lsm_init.c +++ b/security/lsm_init.c @@ -489,12 +489,7 @@ int __init security_init(void) */ static int __init security_initcall_pure(void) { - int rc_adr, rc_lsm; - - rc_adr = min_addr_init(); - rc_lsm = lsm_initcall(pure); - - return (rc_adr ? rc_adr : rc_lsm); + return lsm_initcall(pure); } pure_initcall(security_initcall_pure); diff --git a/security/min_addr.c b/security/min_addr.c index 0fde5ec9abc8..56e4f9d25929 100644 --- a/security/min_addr.c +++ b/security/min_addr.c @@ -5,8 +5,6 @@ #include <linux/sysctl.h> #include <linux/minmax.h> -#include "lsm.h" - /* amount of vm to protect from userspace access by both DAC and the LSM*/ unsigned long mmap_min_addr; /* amount of vm to protect from userspace using CAP_SYS_RAWIO (DAC) */ @@ -54,10 +52,11 @@ static const struct ctl_table min_addr_sysctl_table[] = { }, }; -int __init min_addr_init(void) +static int __init mmap_min_addr_init(void) { register_sysctl_init("vm", min_addr_sysctl_table); update_mmap_min_addr(); return 0; } +pure_initcall(mmap_min_addr_init); diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index ba5c2b643efa..d45bf4ccb3bf 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -251,6 +251,7 @@ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ + -U_FORTIFY_SOURCE \ -fno-builtin-memcmp -fno-builtin-memcpy \ -fno-builtin-memset -fno-builtin-strnlen \ -fno-stack-protector -fno-PIE -fno-strict-aliasing \ diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index a39fdc4aa2ff..9b722c1e4b0f 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -162,6 +162,39 @@ run_test() { echo " ok" } +run_test_csum() { + local -r msg="$1" + local -r dst="$2" + local csum_error_filter=UdpInCsumErrors + local csum_errors + + printf "%-40s" "$msg" + + is_ipv6 "$dst" && csum_error_filter=Udp6InCsumErrors + + ip netns exec "$NS_DST" iperf3 -s -1 >/dev/null & + wait_local_port_listen "$NS_DST" 5201 tcp + local spid="$!" + ip netns exec "$NS_SRC" iperf3 -c "$dst" -t 2 >/dev/null + local retc="$?" + wait "$spid" + local rets="$?" + if [ "$rets" -ne 0 ] || [ "$retc" -ne 0 ]; then + echo " fail client exit code $retc, server $rets" + ret=1 + return + fi + + csum_errors=$(ip netns exec "$NS_DST" nstat -as "$csum_error_filter" | + grep "$csum_error_filter" | awk '{print $2}') + if [ -n "$csum_errors" ] && [ "$csum_errors" -gt 0 ]; then + echo " fail - csum error on receive $csum_errors, expected 0" + ret=1 + return + fi + echo " ok" +} + run_bench() { local -r msg=$1 local -r dst=$2 @@ -260,6 +293,37 @@ for family in 4 6; do ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup + + # force segmentation and re-aggregation + create_vxlan_pair + ip netns exec "$NS_DST" ethtool -K veth"$DST" generic-receive-offload on + ip netns exec "$NS_SRC" ethtool -K veth"$SRC" tso off + ip -n "$NS_SRC" link set dev veth"$SRC" mtu 1430 + + # forward to a 2nd veth pair + ip -n "$NS_DST" link add br0 type bridge + ip -n "$NS_DST" link set dev veth"$DST" master br0 + + # segment the aggregated TSO packet, without csum offload + ip -n "$NS_DST" link add veth_segment type veth peer veth_rx + for FEATURE in tso tx-udp-segmentation tx-checksumming; do + ip netns exec "$NS_DST" ethtool -K veth_segment "$FEATURE" off + done + ip -n "$NS_DST" link set dev veth_segment master br0 up + ip -n "$NS_DST" link set dev br0 up + ip -n "$NS_DST" link set dev veth_rx up + + # move the lower layer IP in the last added veth + for ADDR in "$BM_NET_V4$DST/24" "$BM_NET_V6$DST/64"; do + # the dad argument will let iproute emit a unharmful warning + # with ipv4 addresses + ip -n "$NS_DST" addr del dev veth"$DST" "$ADDR" + ip -n "$NS_DST" addr add dev veth_rx "$ADDR" \ + nodad 2>/dev/null + done + + run_test_csum "GSO after GRO" "$OL_NET$DST" + cleanup done exit $ret diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 0e8b5277be3b..a369b20d47f0 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -157,21 +157,28 @@ irqfd_shutdown(struct work_struct *work) } -/* assumes kvm->irqfds.lock is held */ -static bool -irqfd_is_active(struct kvm_kernel_irqfd *irqfd) +static bool irqfd_is_active(struct kvm_kernel_irqfd *irqfd) { + /* + * Assert that either irqfds.lock or SRCU is held, as irqfds.lock must + * be held to prevent false positives (on the irqfd being active), and + * while false negatives are impossible as irqfds are never added back + * to the list once they're deactivated, the caller must at least hold + * SRCU to guard against routing changes if the irqfd is deactivated. + */ + lockdep_assert_once(lockdep_is_held(&irqfd->kvm->irqfds.lock) || + srcu_read_lock_held(&irqfd->kvm->irq_srcu)); + return list_empty(&irqfd->list) ? false : true; } /* * Mark the irqfd as inactive and schedule it for removal - * - * assumes kvm->irqfds.lock is held */ -static void -irqfd_deactivate(struct kvm_kernel_irqfd *irqfd) +static void irqfd_deactivate(struct kvm_kernel_irqfd *irqfd) { + lockdep_assert_held(&irqfd->kvm->irqfds.lock); + BUG_ON(!irqfd_is_active(irqfd)); list_del_init(&irqfd->list); @@ -217,8 +224,15 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) seq = read_seqcount_begin(&irqfd->irq_entry_sc); irq = irqfd->irq_entry; } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq)); - /* An event has been signaled, inject an interrupt */ - if (kvm_arch_set_irq_inatomic(&irq, kvm, + + /* + * An event has been signaled, inject an interrupt unless the + * irqfd is being deassigned (isn't active), in which case the + * routing information may be stale (once the irqfd is removed + * from the list, it will stop receiving routing updates). + */ + if (unlikely(!irqfd_is_active(irqfd)) || + kvm_arch_set_irq_inatomic(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false) == -EWOULDBLOCK) schedule_work(&irqfd->inject); @@ -585,18 +599,8 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) spin_lock_irq(&kvm->irqfds.lock); list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) { - if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) { - /* - * This clearing of irq_entry.type is needed for when - * another thread calls kvm_irq_routing_update before - * we flush workqueue below (we synchronize with - * kvm_irq_routing_update using irqfds.lock). - */ - write_seqcount_begin(&irqfd->irq_entry_sc); - irqfd->irq_entry.type = 0; - write_seqcount_end(&irqfd->irq_entry_sc); + if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) irqfd_deactivate(irqfd); - } } spin_unlock_irq(&kvm->irqfds.lock); |