diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-01-22 20:13:25 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-02-05 09:54:08 -0800 |
| commit | a182a62ff77f705f7dd3d98cf05cb3d03751a8f0 (patch) | |
| tree | 1bb1f12442bdb77d77acf067fed8ad84c16ec011 | |
| parent | a90f6dcefca6d5ad765435b3188a3a440ed193a1 (diff) | |
| parent | 8fdb05de0e2db89d8f56144c60ab784812e8c3b7 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR (net-6.19-rc9).
No adjacent changes, conflicts:
drivers/net/ethernet/spacemit/k1_emac.c
3125fc1701694 ("net: spacemit: k1-emac: fix jumbo frame support")
f66086798f91f ("net: spacemit: Remove broken flow control support")
https://lore.kernel.org/aYIysFIE9ooavWia@sirena.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
187 files changed, 1545 insertions, 815 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> @@ -851,6 +853,7 @@ Valentin Schneider <vschneid@redhat.com> <valentin.schneider@arm.com> Veera Sundaram Sankaran <quic_veeras@quicinc.com> <veeras@codeaurora.org> Veerabhadrarao Badiganti <quic_vbadigan@quicinc.com> <vbadigan@codeaurora.org> Venkateswara Naralasetty <quic_vnaralas@quicinc.com> <vnaralas@codeaurora.org> +Viacheslav Bocharov <v@baodeep.com> <adeep@lexina.in> Vikash Garodia <vikash.garodia@oss.qualcomm.com> <vgarodia@codeaurora.org> Vikash Garodia <vikash.garodia@oss.qualcomm.com> <quic_vgarodia@quicinc.com> Vincent Mailhol <mailhol@kernel.org> <mailhol.vincent@wanadoo.fr> 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/Documentation/devicetree/bindings/sound/fsl,sai.yaml b/Documentation/devicetree/bindings/sound/fsl,sai.yaml index 0d733e5b08a4..d838ee0b61cb 100644 --- a/Documentation/devicetree/bindings/sound/fsl,sai.yaml +++ b/Documentation/devicetree/bindings/sound/fsl,sai.yaml @@ -44,6 +44,7 @@ properties: - items: - enum: - fsl,imx94-sai + - fsl,imx952-sai - const: fsl,imx95-sai reg: diff --git a/MAINTAINERS b/MAINTAINERS index ce6f49c054c7..34c2ed4da1f9 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 @@ -6514,7 +6514,7 @@ 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 @@ -6610,7 +6610,7 @@ 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) @@ -9819,7 +9819,7 @@ 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/ @@ -10517,7 +10517,7 @@ 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 @@ -11371,6 +11371,11 @@ 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 @@ -15096,7 +15101,7 @@ 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) @@ -20589,7 +20594,7 @@ 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> @@ -20985,6 +20990,18 @@ 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> @@ -23644,7 +23661,7 @@ 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/ @@ -25408,7 +25425,7 @@ 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) @@ -26560,7 +26577,7 @@ 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 @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1624,7 +1624,8 @@ MRPROPER_FILES += include/config include/generated \ certs/x509.genkey \ vmlinux-gdb.py \ rpmbuild \ - rust/libmacros.so rust/libmacros.dylib + rust/libmacros.so rust/libmacros.dylib \ + rust/libpin_init_internal.so rust/libpin_init_internal.dylib # clean - Delete most, but leave enough to build external modules # diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index e5000bef90f2..7cf9310de0ec 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -723,7 +723,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - zone_device_page_init(dpage, 0); + zone_device_page_init(dpage, &kvmppc_uvmem_pgmap, 0); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index 38aac2c47845..d0c61f86cba3 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -75,26 +75,12 @@ static u32 __init_or_module sifive_errata_probe(unsigned long archid, return cpu_req_errata; } -static void __init_or_module warn_miss_errata(u32 miss_errata) -{ - int i; - - pr_warn("----------------------------------------------------------------\n"); - pr_warn("WARNING: Missing the following errata may cause potential issues\n"); - for (i = 0; i < ERRATA_SIFIVE_NUMBER; i++) - if (miss_errata & 0x1 << i) - pr_warn("\tSiFive Errata[%d]:%s\n", i, errata_list[i].name); - pr_warn("Please enable the corresponding Kconfig to apply them\n"); - pr_warn("----------------------------------------------------------------\n"); -} - void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage) { struct alt_entry *alt; u32 cpu_req_errata; - u32 cpu_apply_errata = 0; u32 tmp; BUILD_BUG_ON(ERRATA_SIFIVE_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE); @@ -118,10 +104,6 @@ void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), alt->alt_len); mutex_unlock(&text_mutex); - cpu_apply_errata |= tmp; } } - if (stage != RISCV_ALTERNATIVES_MODULE && - cpu_apply_errata != cpu_req_errata) - warn_miss_errata(cpu_req_errata - cpu_apply_errata); } diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h index 6081327e55f5..28e115eed218 100644 --- a/arch/riscv/include/asm/compat.h +++ b/arch/riscv/include/asm/compat.h @@ -2,7 +2,7 @@ #ifndef __ASM_COMPAT_H #define __ASM_COMPAT_H -#define COMPAT_UTS_MACHINE "riscv\0\0" +#define COMPAT_UTS_MACHINE "riscv32\0\0" /* * Architecture specific compatibility types diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 34313387f977..8067e666a4ca 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -20,7 +20,7 @@ extern void * const sys_call_table[]; extern void * const compat_sys_call_table[]; /* - * Only the low 32 bits of orig_r0 are meaningful, so we return int. + * Only the low 32 bits of orig_a0 are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons * sign-extend the low 32 bits. */ diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 5a956108b1ea..dbb067e345f0 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -145,14 +145,14 @@ struct arch_ext_priv { long (*save)(struct pt_regs *regs, void __user *sc_vec); }; -struct arch_ext_priv arch_ext_list[] = { +static struct arch_ext_priv arch_ext_list[] = { { .magic = RISCV_V_MAGIC, .save = &save_v_state, }, }; -const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list); +static const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list); static long restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) @@ -297,7 +297,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, } else { err |= __put_user(arch_ext->magic, &sc_ext_ptr->magic); err |= __put_user(ext_size, &sc_ext_ptr->size); - sc_ext_ptr = (void *)sc_ext_ptr + ext_size; + sc_ext_ptr = (void __user *)sc_ext_ptr + ext_size; } } /* Write zero to fp-reserved space and check it on restore_sigcontext */ 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/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 8194a970f002..d1c354636315 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1662,6 +1662,7 @@ static void destroy_sysfs(struct rnbd_clt_dev *dev, /* To avoid deadlock firstly remove itself */ sysfs_remove_file_self(&dev->kobj, sysfs_self); kobject_del(&dev->kobj); + kobject_put(&dev->kobj); } } diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c index d8e029e7e53f..3f00d953fb9a 100644 --- a/drivers/bus/simple-pm-bus.c +++ b/drivers/bus/simple-pm-bus.c @@ -142,6 +142,12 @@ static const struct of_device_id simple_pm_bus_of_match[] = { { .compatible = "simple-mfd", .data = ONLY_BUS }, { .compatible = "isa", .data = ONLY_BUS }, { .compatible = "arm,amba-bus", .data = ONLY_BUS }, + { .compatible = "fsl,ls1021a-scfg", }, + { .compatible = "fsl,ls1043a-scfg", }, + { .compatible = "fsl,ls1046a-scfg", }, + { .compatible = "fsl,ls1088a-isc", }, + { .compatible = "fsl,ls2080a-isc", }, + { .compatible = "fsl,lx2160a-isc", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, simple_pm_bus_of_match); diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 81e16b5a0245..b8081acba928 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -263,6 +263,7 @@ static const struct of_device_id qcom_cpufreq_ipq806x_match_list[] __maybe_unuse { .compatible = "qcom,ipq8066", .data = (const void *)QCOM_ID_IPQ8066 }, { .compatible = "qcom,ipq8068", .data = (const void *)QCOM_ID_IPQ8068 }, { .compatible = "qcom,ipq8069", .data = (const void *)QCOM_ID_IPQ8069 }, + { /* sentinel */ } }; static int qcom_cpufreq_ipq8064_name_version(struct device *cpu_dev, 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/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 7fea11a5e359..22ae387ae03c 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -173,20 +173,14 @@ static void split_transaction_timeout_callback(struct timer_list *timer) } } -static void start_split_transaction_timeout(struct fw_transaction *t, - struct fw_card *card) +// card->transactions.lock should be acquired in advance for the linked list. +static void start_split_transaction_timeout(struct fw_transaction *t, unsigned int delta) { - unsigned long delta; - if (list_empty(&t->link) || WARN_ON(t->is_split_transaction)) return; t->is_split_transaction = true; - // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for - // local destination never runs in any type of IRQ context. - scoped_guard(spinlock_irqsave, &card->split_timeout.lock) - delta = card->split_timeout.jiffies; mod_timer(&t->split_timeout_timer, jiffies + delta); } @@ -207,13 +201,20 @@ static void transmit_complete_callback(struct fw_packet *packet, break; case ACK_PENDING: { + unsigned int delta; + // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for // local destination never runs in any type of IRQ context. scoped_guard(spinlock_irqsave, &card->split_timeout.lock) { t->split_timeout_cycle = compute_split_timeout_timestamp(card, packet->timestamp) & 0xffff; + delta = card->split_timeout.jiffies; } - start_split_transaction_timeout(t, card); + + // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for + // local destination never runs in any type of IRQ context. + scoped_guard(spinlock_irqsave, &card->transactions.lock) + start_split_transaction_timeout(t, delta); break; } case ACK_BUSY_X: diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c index af9287ff5dc4..2352d099709c 100644 --- a/drivers/gpio/gpio-brcmstb.c +++ b/drivers/gpio/gpio-brcmstb.c @@ -301,12 +301,10 @@ static struct brcmstb_gpio_bank *brcmstb_gpio_hwirq_to_bank( struct brcmstb_gpio_priv *priv, irq_hw_number_t hwirq) { struct brcmstb_gpio_bank *bank; - int i = 0; - /* banks are in descending order */ - list_for_each_entry_reverse(bank, &priv->bank_list, node) { - i += bank->chip.gc.ngpio; - if (hwirq < i) + list_for_each_entry(bank, &priv->bank_list, node) { + if (hwirq >= bank->chip.gc.offset && + hwirq < (bank->chip.gc.offset + bank->chip.gc.ngpio)) return bank; } return NULL; diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index e136e81794df..e39723b5901b 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -799,10 +799,13 @@ static struct platform_device omap_mpuio_device = { static inline void omap_mpuio_init(struct gpio_bank *bank) { - platform_set_drvdata(&omap_mpuio_device, bank); + static bool registered; - if (platform_driver_register(&omap_mpuio_driver) == 0) - (void) platform_device_register(&omap_mpuio_device); + platform_set_drvdata(&omap_mpuio_device, bank); + if (!registered) { + (void)platform_device_register(&omap_mpuio_device); + registered = true; + } } /*---------------------------------------------------------------------*/ @@ -1575,13 +1578,24 @@ static struct platform_driver omap_gpio_driver = { */ static int __init omap_gpio_drv_reg(void) { - return platform_driver_register(&omap_gpio_driver); + int ret; + + ret = platform_driver_register(&omap_mpuio_driver); + if (ret) + return ret; + + ret = platform_driver_register(&omap_gpio_driver); + if (ret) + platform_driver_unregister(&omap_mpuio_driver); + + return ret; } postcore_initcall(omap_gpio_drv_reg); static void __exit omap_gpio_exit(void) { platform_driver_unregister(&omap_gpio_driver); + platform_driver_unregister(&omap_mpuio_driver); } module_exit(omap_gpio_exit); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 8727ae54bc57..f93a3dbb2daa 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -914,6 +914,8 @@ static void pca953x_irq_shutdown(struct irq_data *d) clear_bit(hwirq, chip->irq_trig_fall); clear_bit(hwirq, chip->irq_trig_level_low); clear_bit(hwirq, chip->irq_trig_level_high); + + pca953x_irq_mask(d); } static void pca953x_irq_print_chip(struct irq_data *data, struct seq_file *p) diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index bae2061f15fc..0fff4a699f12 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -18,7 +18,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/pinctrl/consumer.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/platform_device.h> #include <linux/regmap.h> @@ -164,12 +163,6 @@ static int rockchip_gpio_set_direction(struct gpio_chip *chip, unsigned long flags; u32 data = input ? 0 : 1; - - if (input) - pinctrl_gpio_direction_input(chip, offset); - else - pinctrl_gpio_direction_output(chip, offset); - raw_spin_lock_irqsave(&bank->slock, flags); rockchip_gpio_writel_bit(bank, offset, data, bank->gpio_regs->port_ddr); raw_spin_unlock_irqrestore(&bank->slock, flags); @@ -593,7 +586,6 @@ static int rockchip_gpiolib_register(struct rockchip_pin_bank *bank) gc->ngpio = bank->nr_pins; gc->label = bank->name; gc->parent = bank->dev; - gc->can_sleep = true; ret = gpiochip_add_data(gc, bank); if (ret) { diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c index 413bcd0a4240..2cc8abe705cd 100644 --- a/drivers/gpio/gpio-sprd.c +++ b/drivers/gpio/gpio-sprd.c @@ -35,7 +35,7 @@ struct sprd_gpio { struct gpio_chip chip; void __iomem *base; - spinlock_t lock; + raw_spinlock_t lock; int irq; }; @@ -54,7 +54,7 @@ static void sprd_gpio_update(struct gpio_chip *chip, unsigned int offset, unsigned long flags; u32 tmp; - spin_lock_irqsave(&sprd_gpio->lock, flags); + raw_spin_lock_irqsave(&sprd_gpio->lock, flags); tmp = readl_relaxed(base + reg); if (val) @@ -63,7 +63,7 @@ static void sprd_gpio_update(struct gpio_chip *chip, unsigned int offset, tmp &= ~BIT(SPRD_GPIO_BIT(offset)); writel_relaxed(tmp, base + reg); - spin_unlock_irqrestore(&sprd_gpio->lock, flags); + raw_spin_unlock_irqrestore(&sprd_gpio->lock, flags); } static int sprd_gpio_read(struct gpio_chip *chip, unsigned int offset, u16 reg) @@ -236,7 +236,7 @@ static int sprd_gpio_probe(struct platform_device *pdev) if (IS_ERR(sprd_gpio->base)) return PTR_ERR(sprd_gpio->base); - spin_lock_init(&sprd_gpio->lock); + raw_spin_lock_init(&sprd_gpio->lock); sprd_gpio->chip.label = dev_name(&pdev->dev); sprd_gpio->chip.ngpio = SPRD_GPIO_NR; diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 37f2ce20f1ae..098e67d70ffa 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1682,10 +1682,10 @@ static void gpio_virtuser_device_config_group_release(struct config_item *item) { struct gpio_virtuser_device *dev = to_gpio_virtuser_device(item); - guard(mutex)(&dev->lock); - - if (gpio_virtuser_device_is_live(dev)) - gpio_virtuser_device_deactivate(dev); + scoped_guard(mutex, &dev->lock) { + if (gpio_virtuser_device_is_live(dev)) + gpio_virtuser_device_deactivate(dev); + } mutex_destroy(&dev->lock); ida_free(&gpio_virtuser_ida, dev->id); diff --git a/drivers/gpio/gpiolib-acpi-core.c b/drivers/gpio/gpiolib-acpi-core.c index 83dd227dbbec..9627b3a9c7f3 100644 --- a/drivers/gpio/gpiolib-acpi-core.c +++ b/drivers/gpio/gpiolib-acpi-core.c @@ -1104,6 +1104,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, unsigned int pin = agpio->pin_table[i]; struct acpi_gpio_connection *conn; struct gpio_desc *desc; + u16 word, shift; bool found; mutex_lock(&achip->conn_lock); @@ -1158,10 +1159,22 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, mutex_unlock(&achip->conn_lock); - if (function == ACPI_WRITE) - gpiod_set_raw_value_cansleep(desc, !!(*value & BIT(i))); - else - *value |= (u64)gpiod_get_raw_value_cansleep(desc) << i; + /* + * For the cases when OperationRegion() consists of more than + * 64 bits calculate the word and bit shift to use that one to + * access the value. + */ + word = i / 64; + shift = i % 64; + + if (function == ACPI_WRITE) { + gpiod_set_raw_value_cansleep(desc, value[word] & BIT_ULL(shift)); + } else { + if (gpiod_get_raw_value_cansleep(desc)) + value[word] |= BIT_ULL(shift); + else + value[word] &= ~BIT_ULL(shift); + } } out: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 7e623f91f2d7..d9c7ad297293 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -498,8 +498,13 @@ void amdgpu_gmc_filter_faults_remove(struct amdgpu_device *adev, uint64_t addr, if (adev->irq.retry_cam_enabled) return; + else if (adev->irq.ih1.ring_size) + ih = &adev->irq.ih1; + else if (adev->irq.ih_soft.enabled) + ih = &adev->irq.ih_soft; + else + return; - ih = &adev->irq.ih1; /* Get the WPTR of the last entry in IH ring */ last_wptr = amdgpu_ih_get_wptr(adev, ih); /* Order wptr with ring data. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 72ec455fa932..44f230d67da2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -235,7 +235,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, amdgpu_ring_ib_begin(ring); - if (ring->funcs->emit_gfx_shadow) + if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow) amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va, init_shadow, vmid); @@ -291,7 +291,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, fence_flags | AMDGPU_FENCE_FLAG_64BIT); } - if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec) { + if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec && + adev->gfx.cp_gfx_shadow) { amdgpu_ring_emit_gfx_shadow(ring, 0, 0, 0, false, 0); amdgpu_ring_init_cond_exec(ring, ring->cond_exe_gpu_addr); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index d75b9940f248..fc65fb36e115 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6879,7 +6879,7 @@ static int gfx_v10_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 8a2ee2de390f..e642236ea2c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4201,7 +4201,7 @@ static int gfx_v11_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } @@ -6823,11 +6823,12 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, struct amdgpu_fence *timedout_fence) { struct amdgpu_device *adev = ring->adev; + bool use_mmio = false; int r; amdgpu_ring_reset_helper_begin(ring, timedout_fence); - r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false); + r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio); if (r) { dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r); @@ -6836,16 +6837,18 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, return r; } - r = gfx_v11_0_kgq_init_queue(ring, true); - if (r) { - dev_err(adev->dev, "failed to init kgq\n"); - return r; - } + if (use_mmio) { + r = gfx_v11_0_kgq_init_queue(ring, true); + if (r) { + dev_err(adev->dev, "failed to init kgq\n"); + return r; + } - r = amdgpu_mes_map_legacy_queue(adev, ring); - if (r) { - dev_err(adev->dev, "failed to remap kgq\n"); - return r; + r = amdgpu_mes_map_legacy_queue(adev, ring); + if (r) { + dev_err(adev->dev, "failed to remap kgq\n"); + return r; + } } return amdgpu_ring_reset_helper_end(ring, timedout_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index b786967022d2..4aab89a9ab40 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -3079,7 +3079,7 @@ static int gfx_v12_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } @@ -5297,11 +5297,12 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, struct amdgpu_fence *timedout_fence) { struct amdgpu_device *adev = ring->adev; + bool use_mmio = false; int r; amdgpu_ring_reset_helper_begin(ring, timedout_fence); - r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false); + r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio); if (r) { dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r); r = gfx_v12_reset_gfx_pipe(ring); @@ -5309,16 +5310,18 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, return r; } - r = gfx_v12_0_kgq_init_queue(ring, true); - if (r) { - dev_err(adev->dev, "failed to init kgq\n"); - return r; - } + if (use_mmio) { + r = gfx_v12_0_kgq_init_queue(ring, true); + if (r) { + dev_err(adev->dev, "failed to init kgq\n"); + return r; + } - r = amdgpu_mes_map_legacy_queue(adev, ring); - if (r) { - dev_err(adev->dev, "failed to remap kgq\n"); - return r; + r = amdgpu_mes_map_legacy_queue(adev, ring); + if (r) { + dev_err(adev->dev, "failed to remap kgq\n"); + return r; + } } return amdgpu_ring_reset_helper_end(ring, timedout_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index ad36c96478a8..25536d89635d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -225,7 +225,13 @@ static u32 soc21_get_config_memsize(struct amdgpu_device *adev) static u32 soc21_get_xclk(struct amdgpu_device *adev) { - return adev->clock.spll.reference_freq; + u32 reference_clock = adev->clock.spll.reference_freq; + + /* reference clock is actually 99.81 Mhz rather than 100 Mhz */ + if ((adev->flags & AMD_IS_APU) && reference_clock == 10000) + return 9981; + + return reference_clock; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index af53e796ea1b..6ada7b4af7c6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -217,7 +217,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - zone_device_page_init(page, 0); + zone_device_page_init(page, page_pgmap(page), 0); } static void diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1ea5a250440f..a8a59126b2d2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7754,10 +7754,12 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); /* Cancel and flush any pending HDMI HPD debounce work */ - cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); - if (aconnector->hdmi_prev_sink) { - dc_sink_release(aconnector->hdmi_prev_sink); - aconnector->hdmi_prev_sink = NULL; + if (aconnector->hdmi_hpd_debounce_delay_ms) { + cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } } if (aconnector->bl_idx != -1) { diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 79b174e5326d..302af1fb6901 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -80,15 +80,15 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON; bool is_vcn = block_type == AMD_IP_BLOCK_TYPE_VCN; + mutex_lock(&adev->pm.mutex); + if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state && (!is_vcn || adev->vcn.num_vcn_inst == 1)) { dev_dbg(adev->dev, "IP block%d already in the target %s state!", block_type, gate ? "gate" : "ungate"); - return 0; + goto out_unlock; } - mutex_lock(&adev->pm.mutex); - switch (block_type) { case AMD_IP_BLOCK_TYPE_UVD: case AMD_IP_BLOCK_TYPE_VCE: @@ -115,6 +115,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, if (!ret) atomic_set(&adev->pm.pwr_state[block_type], pwr_state); +out_unlock: mutex_unlock(&adev->pm.mutex); return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 4263798d716b..8e592a477c33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -56,6 +56,7 @@ #define SMUQ10_TO_UINT(x) ((x) >> 10) #define SMUQ10_FRAC(x) ((x) & 0x3ff) #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) +#define SMU_V13_SOFT_FREQ_ROUND(x) ((x) + 1) extern const int pmfw_decoded_link_speed[5]; extern const int pmfw_decoded_link_width[7]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h index 29a4583db873..0b1e6f25e611 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h @@ -57,6 +57,7 @@ extern const int decoded_link_width[8]; #define DECODE_GEN_SPEED(gen_speed_idx) (decoded_link_speed[gen_speed_idx]) #define DECODE_LANE_WIDTH(lane_width_idx) (decoded_link_width[lane_width_idx]) +#define SMU_V14_SOFT_FREQ_ROUND(x) ((x) + 1) struct smu_14_0_max_sustainable_clocks { uint32_t display_clock; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index a89075e25717..2efd914d81e5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1555,6 +1555,7 @@ int smu_v13_0_set_soft_freq_limited_range(struct smu_context *smu, return clk_id; if (max > 0) { + max = SMU_V13_SOFT_FREQ_ROUND(max); if (automatic) param = (uint32_t)((clk_id << 16) | 0xffff); else diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index f2a16dfee599..06a81533759c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -1178,6 +1178,7 @@ int smu_v14_0_set_soft_freq_limited_range(struct smu_context *smu, return clk_id; if (max > 0) { + max = SMU_V14_SOFT_FREQ_ROUND(max); if (automatic) param = (uint32_t)((clk_id << 16) | 0xffff); else diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index e4df43427394..25f68fed9b48 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -960,16 +960,21 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, { struct drm_gem_change_handle *args = data; struct drm_gem_object *obj; - int ret; + int handle, ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) return -EOPNOTSUPP; + /* idr_alloc() limitation. */ + if (args->new_handle > INT_MAX) + return -EINVAL; + handle = args->new_handle; + obj = drm_gem_object_lookup(file_priv, args->handle); if (!obj) return -ENOENT; - if (args->handle == args->new_handle) { + if (args->handle == handle) { ret = 0; goto out; } @@ -977,18 +982,19 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, mutex_lock(&file_priv->prime.lock); spin_lock(&file_priv->table_lock); - ret = idr_alloc(&file_priv->object_idr, obj, - args->new_handle, args->new_handle + 1, GFP_NOWAIT); + ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1, + GFP_NOWAIT); spin_unlock(&file_priv->table_lock); if (ret < 0) goto out_unlock; if (obj->dma_buf) { - ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, args->new_handle); + ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, + handle); if (ret < 0) { spin_lock(&file_priv->table_lock); - idr_remove(&file_priv->object_idr, args->new_handle); + idr_remove(&file_priv->object_idr, handle); spin_unlock(&file_priv->table_lock); goto out_unlock; } diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 06c1bd8fc4d1..704f2f945019 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -197,7 +197,7 @@ static void drm_pagemap_get_devmem_page(struct page *page, struct drm_pagemap_zdd *zdd) { page->zone_device_data = drm_pagemap_zdd_get(zdd); - zone_device_page_init(page, 0); + zone_device_page_init(page, page_pgmap(page), 0); } /** diff --git a/drivers/gpu/drm/imx/ipuv3/imx-tve.c b/drivers/gpu/drm/imx/ipuv3/imx-tve.c index c5c6e070cc06..e861b8b9d8fa 100644 --- a/drivers/gpu/drm/imx/ipuv3/imx-tve.c +++ b/drivers/gpu/drm/imx/ipuv3/imx-tve.c @@ -528,6 +528,13 @@ static const struct component_ops imx_tve_ops = { .bind = imx_tve_bind, }; +static void imx_tve_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int imx_tve_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -549,6 +556,12 @@ static int imx_tve_probe(struct platform_device *pdev) if (ddc_node) { tve->ddc = of_find_i2c_adapter_by_node(ddc_node); of_node_put(ddc_node); + if (tve->ddc) { + ret = devm_add_action_or_reset(dev, imx_tve_put_device, + &tve->ddc->dev); + if (ret) + return ret; + } } tve->mode = of_get_tve_mode(np); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index ac9a95aab2fb..4c042133261c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -501,8 +501,6 @@ static const struct adreno_reglist a690_hwcg[] = { {REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222}, {REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111}, {REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555}, - {REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, 0x10111}, - {REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, 0x5555}, {} }; diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 58071652679d..3d8031296eed 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -425,7 +425,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm, bool is_large) order = ilog2(DMEM_CHUNK_NPAGES); } - zone_device_folio_init(folio, order); + zone_device_folio_init(folio, page_pgmap(folio_page(folio, 0)), order); return page; } diff --git a/drivers/gpu/drm/tyr/Kconfig b/drivers/gpu/drm/tyr/Kconfig index 4b55308fd2eb..e933e6478027 100644 --- a/drivers/gpu/drm/tyr/Kconfig +++ b/drivers/gpu/drm/tyr/Kconfig @@ -6,6 +6,7 @@ config DRM_TYR depends on RUST depends on ARM || ARM64 || COMPILE_TEST depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE + depends on COMMON_CLK default n help Rust DRM driver for ARM Mali CSF-based GPUs. diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c index 9f6251b1008b..82edd0466005 100644 --- a/drivers/gpu/drm/xe/xe_configfs.c +++ b/drivers/gpu/drm/xe/xe_configfs.c @@ -347,11 +347,10 @@ static bool is_bound(struct xe_config_group_device *dev) return false; ret = pci_get_drvdata(pdev); - pci_dev_put(pdev); - if (ret) pci_dbg(pdev, "Already bound to driver\n"); + pci_dev_put(pdev); return ret; } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index cf29e259861f..9a6d49fcd8e4 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -984,8 +984,6 @@ void xe_device_remove(struct xe_device *xe) { xe_display_unregister(xe); - xe_nvm_fini(xe); - drm_dev_unplug(&xe->drm); xe_bo_pci_dev_remove_all(xe); diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index fd9480031750..8e3614b24010 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -190,9 +190,9 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_syncs; } - if (xe_exec_queue_is_parallel(q)) { - err = copy_from_user(addresses, addresses_user, sizeof(u64) * - q->width); + if (args->num_batch_buffer && xe_exec_queue_is_parallel(q)) { + err = copy_from_user(addresses, addresses_user, + sizeof(u64) * q->width); if (err) { err = -EFAULT; goto err_syncs; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 281286f2b5f9..b8c1dd953665 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1185,7 +1185,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, return -ENOSPC; *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); - *cmd++ = CS_DEBUG_MODE1(0).addr; + *cmd++ = CS_DEBUG_MODE2(0).addr; *cmd++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE); return cmd - batch; diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 33f4ac82fc80..6da42b2b5e46 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -83,6 +83,27 @@ static bool xe_nvm_writable_override(struct xe_device *xe) return writable_override; } +static void xe_nvm_fini(void *arg) +{ + struct xe_device *xe = arg; + struct intel_dg_nvm_dev *nvm = xe->nvm; + + if (!xe->info.has_gsc_nvm) + return; + + /* No access to internal NVM from VFs */ + if (IS_SRIOV_VF(xe)) + return; + + /* Nvm pointer should not be NULL here */ + if (WARN_ON(!nvm)) + return; + + auxiliary_device_delete(&nvm->aux_dev); + auxiliary_device_uninit(&nvm->aux_dev); + xe->nvm = NULL; +} + int xe_nvm_init(struct xe_device *xe) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); @@ -132,39 +153,17 @@ int xe_nvm_init(struct xe_device *xe) ret = auxiliary_device_init(aux_dev); if (ret) { drm_err(&xe->drm, "xe-nvm aux init failed %d\n", ret); - goto err; + kfree(nvm); + xe->nvm = NULL; + return ret; } ret = auxiliary_device_add(aux_dev); if (ret) { drm_err(&xe->drm, "xe-nvm aux add failed %d\n", ret); auxiliary_device_uninit(aux_dev); - goto err; + xe->nvm = NULL; + return ret; } - return 0; - -err: - kfree(nvm); - xe->nvm = NULL; - return ret; -} - -void xe_nvm_fini(struct xe_device *xe) -{ - struct intel_dg_nvm_dev *nvm = xe->nvm; - - if (!xe->info.has_gsc_nvm) - return; - - /* No access to internal NVM from VFs */ - if (IS_SRIOV_VF(xe)) - return; - - /* Nvm pointer should not be NULL here */ - if (WARN_ON(!nvm)) - return; - - auxiliary_device_delete(&nvm->aux_dev); - auxiliary_device_uninit(&nvm->aux_dev); - xe->nvm = NULL; + return devm_add_action_or_reset(xe->drm.dev, xe_nvm_fini, xe); } diff --git a/drivers/gpu/drm/xe/xe_nvm.h b/drivers/gpu/drm/xe/xe_nvm.h index 7f3d5f57bed0..fd3467ad35a4 100644 --- a/drivers/gpu/drm/xe/xe_nvm.h +++ b/drivers/gpu/drm/xe/xe_nvm.h @@ -10,6 +10,4 @@ struct xe_device; int xe_nvm_init(struct xe_device *xe); -void xe_nvm_fini(struct xe_device *xe); - #endif diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 9c9ea10d994c..2aa883f5ef79 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -342,7 +342,6 @@ static const struct xe_device_desc lnl_desc = { .has_display = true, .has_flat_ccs = 1, .has_pxp = true, - .has_mem_copy_instr = true, .max_gt_per_tile = 2, .needs_scratch = true, .va_bits = 48, @@ -363,7 +362,6 @@ static const struct xe_device_desc bmg_desc = { .has_heci_cscfi = 1, .has_late_bind = true, .has_sriov = true, - .has_mem_copy_instr = true, .max_gt_per_tile = 2, .needs_scratch = true, .subplatforms = (const struct xe_subplatform_desc[]) { @@ -380,7 +378,6 @@ static const struct xe_device_desc ptl_desc = { .has_display = true, .has_flat_ccs = 1, .has_sriov = true, - .has_mem_copy_instr = true, .max_gt_per_tile = 2, .needs_scratch = true, .needs_shared_vf_gt_wq = true, @@ -393,7 +390,6 @@ static const struct xe_device_desc nvls_desc = { .dma_mask_size = 46, .has_display = true, .has_flat_ccs = 1, - .has_mem_copy_instr = true, .max_gt_per_tile = 2, .require_force_probe = true, .va_bits = 48, @@ -675,7 +671,6 @@ static int xe_info_init_early(struct xe_device *xe, xe->info.has_pxp = desc->has_pxp; xe->info.has_sriov = xe_configfs_primary_gt_allowed(to_pci_dev(xe->drm.dev)) && desc->has_sriov; - xe->info.has_mem_copy_instr = desc->has_mem_copy_instr; xe->info.skip_guc_pc = desc->skip_guc_pc; xe->info.skip_mtcfg = desc->skip_mtcfg; xe->info.skip_pcode = desc->skip_pcode; @@ -864,6 +859,7 @@ static int xe_info_init(struct xe_device *xe, xe->info.has_range_tlb_inval = graphics_desc->has_range_tlb_inval; xe->info.has_usm = graphics_desc->has_usm; xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp; + xe->info.has_mem_copy_instr = GRAPHICS_VER(xe) >= 20; xe_info_probe_tile_count(xe); diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h index 9892c063a9c5..a4451bdc79fb 100644 --- a/drivers/gpu/drm/xe/xe_pci_types.h +++ b/drivers/gpu/drm/xe/xe_pci_types.h @@ -46,7 +46,6 @@ struct xe_device_desc { u8 has_late_bind:1; u8 has_llc:1; u8 has_mbx_power_limits:1; - u8 has_mem_copy_instr:1; u8 has_pxp:1; u8 has_sriov:1; u8 needs_scratch:1; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 378104cd395e..04cc7a9036e4 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -1078,6 +1078,9 @@ static int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq) { char header[64]; + /* Reset VCMDQ */ + tegra241_vcmdq_hw_deinit(vcmdq); + /* Configure the vcmdq only; User space does the enabling */ writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h index 52ef028ed2db..d575f3ba9d34 100644 --- a/drivers/iommu/generic_pt/iommu_pt.h +++ b/drivers/iommu/generic_pt/iommu_pt.h @@ -931,6 +931,8 @@ static __maybe_unused int __unmap_range(struct pt_range *range, void *arg, struct pt_table_p *table) { struct pt_state pts = pt_init(range, level, table); + unsigned int flush_start_index = UINT_MAX; + unsigned int flush_end_index = UINT_MAX; struct pt_unmap_args *unmap = arg; unsigned int num_oas = 0; unsigned int start_index; @@ -986,6 +988,9 @@ static __maybe_unused int __unmap_range(struct pt_range *range, void *arg, iommu_pages_list_add(&unmap->free_list, pts.table_lower); pt_clear_entries(&pts, ilog2(1)); + if (pts.index < flush_start_index) + flush_start_index = pts.index; + flush_end_index = pts.index + 1; } pts.index++; } else { @@ -999,7 +1004,10 @@ start_oa: num_contig_lg2 = pt_entry_num_contig_lg2(&pts); pt_clear_entries(&pts, num_contig_lg2); num_oas += log2_to_int(num_contig_lg2); + if (pts.index < flush_start_index) + flush_start_index = pts.index; pts.index += log2_to_int(num_contig_lg2); + flush_end_index = pts.index; } if (pts.index >= pts.end_index) break; @@ -1007,7 +1015,8 @@ start_oa: } while (true); unmap->unmapped += log2_mul(num_oas, pt_table_item_lg2sz(&pts)); - flush_writes_range(&pts, start_index, pts.index); + if (flush_start_index != flush_end_index) + flush_writes_range(&pts, flush_start_index, flush_end_index); return ret; } diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index dbe51ecb9a20..f606148920fa 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -289,6 +289,7 @@ static void batch_clear(struct pfn_batch *batch) batch->end = 0; batch->pfns[0] = 0; batch->npfns[0] = 0; + batch->kind = 0; } /* diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c index 50a7b38381b9..96f9c20621cf 100644 --- a/drivers/irqchip/irq-ls-extirq.c +++ b/drivers/irqchip/irq-ls-extirq.c @@ -168,40 +168,34 @@ ls_extirq_parse_map(struct ls_extirq_data *priv, struct device_node *node) return 0; } -static int __init -ls_extirq_of_init(struct device_node *node, struct device_node *parent) +static int ls_extirq_probe(struct platform_device *pdev) { struct irq_domain *domain, *parent_domain; + struct device_node *node, *parent; + struct device *dev = &pdev->dev; struct ls_extirq_data *priv; int ret; + node = dev->of_node; + parent = of_irq_find_parent(node); + if (!parent) + return dev_err_probe(dev, -ENODEV, "Failed to get IRQ parent node\n"); + parent_domain = irq_find_host(parent); - if (!parent_domain) { - pr_err("Cannot find parent domain\n"); - ret = -ENODEV; - goto err_irq_find_host; - } + if (!parent_domain) + return dev_err_probe(dev, -EPROBE_DEFER, "Cannot find parent domain\n"); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto err_alloc_priv; - } + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return dev_err_probe(dev, -ENOMEM, "Failed to allocate memory\n"); - /* - * All extirq OF nodes are under a scfg/syscon node with - * the 'ranges' property - */ - priv->intpcr = of_iomap(node, 0); - if (!priv->intpcr) { - pr_err("Cannot ioremap OF node %pOF\n", node); - ret = -ENOMEM; - goto err_iomap; - } + priv->intpcr = devm_of_iomap(dev, node, 0, NULL); + if (!priv->intpcr) + return dev_err_probe(dev, -ENOMEM, "Cannot ioremap OF node %pOF\n", node); ret = ls_extirq_parse_map(priv, node); if (ret) - goto err_parse_map; + return dev_err_probe(dev, ret, "Failed to parse IRQ map\n"); priv->big_endian = of_device_is_big_endian(node->parent); priv->is_ls1021a_or_ls1043a = of_device_is_compatible(node, "fsl,ls1021a-extirq") || @@ -210,23 +204,26 @@ ls_extirq_of_init(struct device_node *node, struct device_node *parent) domain = irq_domain_create_hierarchy(parent_domain, 0, priv->nirq, of_fwnode_handle(node), &extirq_domain_ops, priv); - if (!domain) { - ret = -ENOMEM; - goto err_add_hierarchy; - } + if (!domain) + return dev_err_probe(dev, -ENOMEM, "Failed to add IRQ domain\n"); return 0; - -err_add_hierarchy: -err_parse_map: - iounmap(priv->intpcr); -err_iomap: - kfree(priv); -err_alloc_priv: -err_irq_find_host: - return ret; } -IRQCHIP_DECLARE(ls1021a_extirq, "fsl,ls1021a-extirq", ls_extirq_of_init); -IRQCHIP_DECLARE(ls1043a_extirq, "fsl,ls1043a-extirq", ls_extirq_of_init); -IRQCHIP_DECLARE(ls1088a_extirq, "fsl,ls1088a-extirq", ls_extirq_of_init); +static const struct of_device_id ls_extirq_dt_ids[] = { + { .compatible = "fsl,ls1021a-extirq" }, + { .compatible = "fsl,ls1043a-extirq" }, + { .compatible = "fsl,ls1088a-extirq" }, + {} +}; +MODULE_DEVICE_TABLE(of, ls_extirq_dt_ids); + +static struct platform_driver ls_extirq_driver = { + .probe = ls_extirq_probe, + .driver = { + .name = "ls-extirq", + .of_match_table = ls_extirq_dt_ids, + } +}; + +builtin_platform_driver(ls_extirq_driver); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index a02aecac05cd..3fa3b13a410f 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1107,17 +1107,13 @@ static void detached_dev_do_request(struct bcache_device *d, if (bio_op(orig_bio) == REQ_OP_DISCARD && !bdev_max_discard_sectors(dc->bdev)) { + bio_end_io_acct(orig_bio, start_time); bio_endio(orig_bio); return; } clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO, &d->bio_detached); - if (!clone_bio) { - orig_bio->bi_status = BLK_STS_RESOURCE; - bio_endio(orig_bio); - return; - } ddip = container_of(clone_bio, struct detached_dev_io_private, bio); /* Count on the bcache device */ diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c index e60e4ac1fd6f..3e86f346f751 100644 --- a/drivers/mtd/nand/spi/esmt.c +++ b/drivers/mtd/nand/spi/esmt.c @@ -215,7 +215,7 @@ static const struct spinand_info esmt_c8_spinand_table[] = { SPINAND_FACT_OTP_INFO(2, 0, &f50l1g41lb_fact_otp_ops)), SPINAND_INFO("F50D1G41LB", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x11, 0x7f, - 0x7f), + 0x7f, 0x7f), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), SPINAND_INFO_OP_VARIANTS(&read_cache_variants, diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 01b1bbcce481..1b4e37d000b9 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 42f0fde07f01..42a0a6f7b296 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 97433829b9ed..0ee864b0afe0 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 3ce8bc7836cd..4da37caa3ec9 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; } @@ -7863,6 +7865,9 @@ 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: @@ -9713,9 +9718,6 @@ 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 1d26be58e29a..22c3986b910a 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; } /** @@ -1379,9 +1334,12 @@ 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__); } @@ -2695,30 +2653,92 @@ 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; } /** @@ -2770,7 +2790,9 @@ 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. */ @@ -2850,6 +2872,20 @@ 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 @@ -2867,10 +2903,15 @@ 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); + } } } } @@ -3016,9 +3057,6 @@ 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; @@ -3223,8 +3261,9 @@ 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 40c9504b7444..dab0772c5b9d 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 @@ -193,7 +194,7 @@ static void emac_reset_hw(struct emac_priv *priv) static void emac_init_hw(struct emac_priv *priv) { - 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, @@ -218,6 +219,15 @@ 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); + /* RX IRQ mitigation */ rxirq = FIELD_PREP(MREGBIT_RECEIVE_IRQ_FRAME_COUNTER_MASK, EMAC_RX_FRAMES); @@ -908,14 +918,14 @@ 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; @@ -1917,7 +1927,7 @@ 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 b756a0f09e1a..c63099a77cc0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -8093,7 +8093,7 @@ int stmmac_suspend(struct device *dev) u32 chan; if (!ndev || !netif_running(ndev)) - return 0; + goto suspend_bsp; mutex_lock(&priv->lock); @@ -8132,6 +8132,7 @@ 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 4746a8af3a8d..43aefdd8b70f 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 e8e6689d2c70..adfc83b7ca6a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8530,19 +8530,6 @@ 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; } @@ -8653,19 +8640,33 @@ 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 3ca3e169738e..743e44ff19cf 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 df8221277d51..3414b04a6953 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1840,6 +1840,8 @@ 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 2375fc76039f..6c225861db61 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 */ @@ -3214,6 +3214,8 @@ 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); @@ -3270,6 +3272,8 @@ 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 58f3097888a7..c2bee32332fe 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -806,8 +806,8 @@ static void nvme_unmap_data(struct request *req) if (!blk_rq_dma_unmap(req, dma_dev, &iod->dma_state, iod->total_len, map)) { if (nvme_pci_cmd_use_sgl(&iod->cmd)) - nvme_free_sgls(req, iod->descriptors[0], - &iod->cmd.common.dptr.sgl, attrs); + nvme_free_sgls(req, &iod->cmd.common.dptr.sgl, + iod->descriptors[0], attrs); else nvme_free_prps(req, attrs); } diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 8d246b8ca604..0103815542d4 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -180,9 +180,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) static void nvmet_bio_done(struct bio *bio) { struct nvmet_req *req = bio->bi_private; + blk_status_t blk_status = bio->bi_status; - nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status)); nvmet_req_bio_put(req, bio); + nvmet_req_complete(req, blk_to_nvme_status(req, blk_status)); } #ifdef CONFIG_BLK_DEV_INTEGRITY diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 5619ec917858..a2a13617c6f4 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -157,13 +157,19 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, phys_addr_t base, size; int i, len; const __be32 *prop; - bool nomap; + bool nomap, default_cma; prop = of_flat_dt_get_addr_size_prop(node, "reg", &len); if (!prop) return -ENOENT; nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL; + default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); + + if (default_cma && cma_skip_dt_default_reserved_mem()) { + pr_err("Skipping dt linux,cma-default for \"cma=\" kernel param.\n"); + return -EINVAL; + } for (i = 0; i < len; i++) { u64 b, s; @@ -248,10 +254,13 @@ void __init fdt_scan_reserved_mem_reg_nodes(void) fdt_for_each_subnode(child, fdt, node) { const char *uname; + bool default_cma = of_get_flat_dt_prop(child, "linux,cma-default", NULL); u64 b, s; if (!of_fdt_device_is_available(fdt, child)) continue; + if (default_cma && cma_skip_dt_default_reserved_mem()) + continue; if (!of_flat_dt_get_addr_size(child, "reg", &b, &s)) continue; @@ -389,7 +398,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam phys_addr_t base = 0, align = 0, size; int i, len; const __be32 *prop; - bool nomap; + bool nomap, default_cma; int ret; prop = of_get_flat_dt_prop(node, "size", &len); @@ -413,6 +422,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam } nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL; + default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); + + if (default_cma && cma_skip_dt_default_reserved_mem()) { + pr_err("Skipping dt linux,cma-default for \"cma=\" kernel param.\n"); + return -EINVAL; + } /* Need adjust the alignment to satisfy the CMA requirement */ if (IS_ENABLED(CONFIG_CMA) 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/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index e44ef262beec..2fc67aeafdb3 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3545,10 +3545,9 @@ static int rockchip_pmx_set(struct pinctrl_dev *pctldev, unsigned selector, return 0; } -static int rockchip_pmx_gpio_set_direction(struct pinctrl_dev *pctldev, - struct pinctrl_gpio_range *range, - unsigned offset, - bool input) +static int rockchip_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) { struct rockchip_pinctrl *info = pinctrl_dev_get_drvdata(pctldev); struct rockchip_pin_bank *bank; @@ -3562,7 +3561,7 @@ static const struct pinmux_ops rockchip_pmx_ops = { .get_function_name = rockchip_pmx_get_func_name, .get_function_groups = rockchip_pmx_get_groups, .set_mux = rockchip_pmx_set, - .gpio_set_direction = rockchip_pmx_gpio_set_direction, + .gpio_request_enable = rockchip_pmx_gpio_request_enable, }; /* 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/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index 4e899ec1477d..b1cba986f0fb 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -1025,6 +1025,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba) &nonemb_cmd->dma, GFP_KERNEL); if (!nonemb_cmd->va) { + free_mcc_wrb(ctrl, tag); mutex_unlock(&ctrl->mbox_lock); return 0; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 16a44c0917e1..e939bc88e151 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4489,7 +4489,7 @@ fail_lsrjt: fail_elsrej: dma_pool_destroy(ha->purex_dma_pool); fail_flt: - dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, + dma_free_coherent(&ha->pdev->dev, sizeof(struct qla_flt_header) + FLT_REGIONS_SIZE, ha->flt, ha->flt_dma); fail_flt_buffer: 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/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 9f167ff8da7b..09120a538a40 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -1960,12 +1960,12 @@ static struct se_portal_group *sbp_make_tpg(struct se_wwn *wwn, container_of(wwn, struct sbp_tport, tport_wwn); struct sbp_tpg *tpg; - unsigned long tpgt; + u16 tpgt; int ret; if (strstr(name, "tpgt_") != name) return ERR_PTR(-EINVAL); - if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX) + if (kstrtou16(name + 5, 10, &tpgt)) return ERR_PTR(-EINVAL); if (tport->tpg) { diff --git a/drivers/ufs/host/ufs-amd-versal2.c b/drivers/ufs/host/ufs-amd-versal2.c index 40543db621a1..6c454ae8a9c8 100644 --- a/drivers/ufs/host/ufs-amd-versal2.c +++ b/drivers/ufs/host/ufs-amd-versal2.c @@ -367,7 +367,7 @@ static int ufs_versal2_hce_enable_notify(struct ufs_hba *hba, { int ret = 0; - if (status == PRE_CHANGE) { + if (status == POST_CHANGE) { ret = ufs_versal2_phy_init(hba); if (ret) dev_err(hba->dev, "Phy init failed (%d)\n", ret); 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/efivarfs/vars.c b/fs/efivarfs/vars.c index 6edc10958ecf..70e13db260db 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -552,7 +552,7 @@ int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, err = __efivar_entry_get(entry, attributes, size, data); efivar_unlock(); - return 0; + return err; } /** 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/cma.h b/include/linux/cma.h index 62d9c1cf6326..2e6931735880 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -57,6 +57,15 @@ extern bool cma_intersects(struct cma *cma, unsigned long start, unsigned long e extern void cma_reserve_pages_on_error(struct cma *cma); +#ifdef CONFIG_DMA_CMA +extern bool cma_skip_dt_default_reserved_mem(void); +#else +static inline bool cma_skip_dt_default_reserved_mem(void) +{ + return false; +} +#endif + #ifdef CONFIG_CMA struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp); bool cma_free_folio(struct cma *cma, const struct folio *folio); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 9c6ac4b62eb9..338a1921a50a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -641,6 +641,17 @@ kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, __kasan_unpoison_vmap_areas(vms, nr_vms, flags); } +void __kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size); + +static __always_inline void kasan_vrealloc(const void *start, + unsigned long old_size, + unsigned long new_size) +{ + if (kasan_enabled()) + __kasan_vrealloc(start, old_size, new_size); +} + #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, @@ -670,6 +681,9 @@ kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, kasan_vmalloc_flags_t flags) { } +static inline void kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size) { } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index cc74de3dbcfe..c328a7b356d0 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -17,6 +17,7 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); * to by vm_flags_ptr. */ int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr); +struct file *memfd_alloc_file(const char *name, unsigned int flags); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -31,6 +32,11 @@ static inline int memfd_check_seals_mmap(struct file *file, { return 0; } + +static inline struct file *memfd_alloc_file(const char *name, unsigned int flags) +{ + return ERR_PTR(-EINVAL); +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 713ec0435b48..e3c2ccf872a8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -224,7 +224,8 @@ static inline bool is_fsdax_page(const struct page *page) } #ifdef CONFIG_ZONE_DEVICE -void zone_device_page_init(struct page *page, unsigned int order); +void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap, + unsigned int order); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); @@ -234,9 +235,11 @@ bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); -static inline void zone_device_folio_init(struct folio *folio, unsigned int order) +static inline void zone_device_folio_init(struct folio *folio, + struct dev_pagemap *pgmap, + unsigned int order) { - zone_device_page_init(&folio->page, order); + zone_device_page_init(&folio->page, pgmap, order); if (order) folio_set_large_rmappable(folio); } 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/sched.h b/include/linux/sched.h index da0133524d08..5f00b5ed0f3b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1776,6 +1776,11 @@ static __always_inline bool is_percpu_thread(void) (current->nr_cpus_allowed == 1); } +static __always_inline bool is_user_task(struct task_struct *task) +{ + return task->mm && !(task->flags & (PF_KTHREAD | PF_USER_WORKER)); +} + /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ef56dc6318d3..daa4e4944ce3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4302,6 +4302,18 @@ 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/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/dma/contiguous.c b/kernel/dma/contiguous.c index d8fd6f779f79..0e266979728b 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -91,6 +91,16 @@ static int __init early_cma(char *p) } early_param("cma", early_cma); +/* + * cma_skip_dt_default_reserved_mem - This is called from the + * reserved_mem framework to detect if the default cma region is being + * set by the "cma=" kernel parameter. + */ +bool __init cma_skip_dt_default_reserved_mem(void) +{ + return size_cmdline != -1; +} + #ifdef CONFIG_DMA_NUMA_CMA static struct cma *dma_contiguous_numa_area[MAX_NUMNODES]; @@ -470,12 +480,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) struct cma *cma; int err; - if (size_cmdline != -1 && default_cma) { - pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", - rmem->name); - return -EBUSY; - } - if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index c5da29ad010c..2b2fbb709242 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -277,15 +277,20 @@ struct page *dma_alloc_from_pool(struct device *dev, size_t size, { struct gen_pool *pool = NULL; struct page *page; + bool pool_found = false; while ((pool = dma_guess_pool(pool, gfp))) { + pool_found = true; page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, phys_addr_ok); if (page) return page; } - WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + if (pool_found) + WARN(!(gfp & __GFP_NOWARN), "DMA pool exhausted for %s\n", dev_name(dev)); + else + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); return NULL; } diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 1f6589578703..9d24b6e0c91f 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -246,7 +246,7 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, if (user && !crosstask) { if (!user_mode(regs)) { - if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) + if (!is_user_task(current)) goto exit_put; regs = task_pt_regs(current); } diff --git a/kernel/events/core.c b/kernel/events/core.c index a0fa488bce84..8cca80094624 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7460,7 +7460,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user, if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; - } else if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + } else if (is_user_task(current)) { perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; @@ -8100,7 +8100,7 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe get_user_page_fast_only first. * If failed, leave phys_addr as 0. */ - if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + if (is_user_task(current)) { struct page *p; pagefault_disable(); @@ -8215,7 +8215,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; bool user = !event->attr.exclude_callchain_user && - !(current->flags & (PF_KTHREAD | PF_USER_WORKER)); + is_user_task(current); /* Disallow cross-task user callchains. */ bool crosstask = event->ctx->task && event->ctx->task != current; bool defer_user = IS_ENABLED(CONFIG_UNWIND_USER) && user && diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index d4482b6e3cae..90d411a59f76 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -255,6 +255,14 @@ static struct page *kho_restore_page(phys_addr_t phys, bool is_folio) if (is_folio && info.order) prep_compound_page(page, info.order); + /* Always mark headpage's codetag as empty to avoid accounting mismatch */ + clear_page_tag_ref(page); + if (!is_folio) { + /* Also do that for the non-compound tail pages */ + for (unsigned int i = 1; i < nr_pages; i++) + clear_page_tag_ref(page + i); + } + adjust_managed_page_count(page, nr_pages); return page; } @@ -1006,8 +1014,10 @@ int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation) chunk->phys[idx++] = phys; if (idx == ARRAY_SIZE(chunk->phys)) { chunk = new_vmalloc_chunk(chunk); - if (!chunk) + if (!chunk) { + err = -ENOMEM; goto err_free; + } idx = 0; } } 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/deadline.c b/kernel/sched/deadline.c index c509f2e7d69d..7bcde7114f1b 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1034,6 +1034,12 @@ static void update_dl_entity(struct sched_dl_entity *dl_se) return; } + /* + * When [4] D->A is followed by [1] A->B, dl_defer_running + * needs to be cleared, otherwise it will fail to properly + * start the zero-laxity timer. + */ + dl_se->dl_defer_running = 0; replenish_dl_new_period(dl_se, rq); } else if (dl_server(dl_se) && dl_se->dl_defer) { /* @@ -1655,6 +1661,12 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * dl_server_active = 1; * enqueue_dl_entity() * update_dl_entity(WAKEUP) + * if (dl_time_before() || dl_entity_overflow()) + * dl_defer_running = 0; + * replenish_dl_new_period(); + * // fwd period + * dl_throttled = 1; + * dl_defer_armed = 1; * if (!dl_defer_running) * dl_defer_armed = 1; * dl_throttled = 1; 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/kernel/vmcore_info.c b/kernel/vmcore_info.c index fe9bf8db1922..e2784038bbed 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -36,7 +36,11 @@ struct hwerr_info { time64_t timestamp; }; -static struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; +/* + * The hwerr_data[] array is declared with global scope so that it remains + * accessible to vmcoreinfo even when Link Time Optimization (LTO) is enabled. + */ +struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index 84ecccddc771..012d5614efb9 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -64,13 +64,14 @@ void fprop_global_destroy(struct fprop_global *p) bool fprop_new_period(struct fprop_global *p, int periods) { s64 events = percpu_counter_sum(&p->events); + unsigned long flags; /* * Don't do anything if there are no events. */ if (events <= 1) return false; - preempt_disable_nested(); + local_irq_save(flags); write_seqcount_begin(&p->sequence); if (periods < 64) events -= events >> periods; @@ -78,7 +79,7 @@ bool fprop_new_period(struct fprop_global *p, int periods) percpu_counter_add(&p->events, -events); p->period += periods; write_seqcount_end(&p->sequence); - preempt_enable_nested(); + local_irq_restore(flags); return true; } diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 8af169d3873a..455a6862ae50 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -662,7 +662,9 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror *dmirror, goto error; } - zone_device_folio_init(page_folio(dpage), order); + zone_device_folio_init(page_folio(dpage), + page_pgmap(folio_page(page_folio(dpage), 0)), + order); dpage->zone_device_data = rpage; return dpage; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index ed489a14dddf..b7d05c2a6d93 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -606,4 +606,25 @@ void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, __kasan_unpoison_vmalloc(addr, size, flags | KASAN_VMALLOC_KEEP_TAG); } } + +void __kasan_vrealloc(const void *addr, unsigned long old_size, + unsigned long new_size) +{ + if (new_size < old_size) { + kasan_poison_last_granule(addr, new_size); + + new_size = round_up(new_size, KASAN_GRANULE_SIZE); + old_size = round_up(old_size, KASAN_GRANULE_SIZE); + if (new_size < old_size) + __kasan_poison_vmalloc(addr + new_size, + old_size - new_size); + } else if (new_size > old_size) { + old_size = round_down(old_size, KASAN_GRANULE_SIZE); + __kasan_unpoison_vmalloc(addr + old_size, + new_size - old_size, + KASAN_VMALLOC_PROT_NORMAL | + KASAN_VMALLOC_VM_ALLOC | + KASAN_VMALLOC_KEEP_TAG); + } +} #endif diff --git a/mm/kfence/core.c b/mm/kfence/core.c index da0f5b6f5744..4f79ec720752 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -596,7 +596,7 @@ static void rcu_guarded_free(struct rcu_head *h) static unsigned long kfence_init_pool(void) { unsigned long addr, start_pfn; - int i; + int i, rand; if (!arch_kfence_init_pool()) return (unsigned long)__kfence_pool; @@ -647,13 +647,27 @@ static unsigned long kfence_init_pool(void) INIT_LIST_HEAD(&meta->list); raw_spin_lock_init(&meta->lock); meta->state = KFENCE_OBJECT_UNUSED; - meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ - list_add_tail(&meta->list, &kfence_freelist); + /* Use addr to randomize the freelist. */ + meta->addr = i; /* Protect the right redzone. */ - if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + if (unlikely(!kfence_protect(addr + 2 * i * PAGE_SIZE + PAGE_SIZE))) goto reset_slab; + } + + for (i = CONFIG_KFENCE_NUM_OBJECTS; i > 0; i--) { + rand = get_random_u32_below(i); + swap(kfence_metadata_init[i - 1].addr, kfence_metadata_init[rand].addr); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta_1 = &kfence_metadata_init[i]; + struct kfence_metadata *meta_2 = &kfence_metadata_init[meta_1->addr]; + + list_add_tail(&meta_2->list, &kfence_freelist); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + kfence_metadata_init[i].addr = addr; addr += 2 * PAGE_SIZE; } @@ -666,6 +680,7 @@ static unsigned long kfence_init_pool(void) return 0; reset_slab: + addr += 2 * i * PAGE_SIZE; for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { struct page *page; diff --git a/mm/memfd.c b/mm/memfd.c index ab5312aff14b..f032c6052926 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -456,7 +456,7 @@ err_name: return ERR_PTR(error); } -static struct file *alloc_file(const char *name, unsigned int flags) +struct file *memfd_alloc_file(const char *name, unsigned int flags) { unsigned int *file_seals; struct file *file; @@ -520,5 +520,5 @@ SYSCALL_DEFINE2(memfd_create, return PTR_ERR(name); fd_flags = (flags & MFD_CLOEXEC) ? O_CLOEXEC : 0; - return FD_ADD(fd_flags, alloc_file(name, flags)); + return FD_ADD(fd_flags, memfd_alloc_file(name, flags)); } diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index 4f6ba63b4310..a34fccc23b6a 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -78,6 +78,7 @@ #include <linux/liveupdate.h> #include <linux/shmem_fs.h> #include <linux/vmalloc.h> +#include <linux/memfd.h> #include "internal.h" static int memfd_luo_preserve_folios(struct file *file, @@ -443,11 +444,11 @@ static int memfd_luo_retrieve(struct liveupdate_file_op_args *args) if (!ser) return -EINVAL; - file = shmem_file_setup("", 0, VM_NORESERVE); - + file = memfd_alloc_file("", 0); if (IS_ERR(file)) { pr_err("failed to setup file: %pe\n", file); - return PTR_ERR(file); + err = PTR_ERR(file); + goto free_ser; } vfs_setpos(file, ser->pos, MAX_LFS_FILESIZE); @@ -473,7 +474,8 @@ static int memfd_luo_retrieve(struct liveupdate_file_op_args *args) put_file: fput(file); - +free_ser: + kho_restore_free(ser); return err; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c80c2907da33..cf0d526e6d41 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -692,6 +692,8 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, unsigned long poisoned_pfn, struct to_kill *tk) { unsigned long pfn = 0; + unsigned long hwpoison_vaddr; + unsigned long mask; if (pte_present(pte)) { pfn = pte_pfn(pte); @@ -702,10 +704,12 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, pfn = softleaf_to_pfn(entry); } - if (!pfn || pfn != poisoned_pfn) + mask = ~((1UL << (shift - PAGE_SHIFT)) - 1); + if (!pfn || pfn != (poisoned_pfn & mask)) return 0; - set_to_kill(tk, addr, shift); + hwpoison_vaddr = addr + ((poisoned_pfn - pfn) << PAGE_SHIFT); + set_to_kill(tk, hwpoison_vaddr, shift); return 1; } @@ -1883,12 +1887,22 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag) return count; } -static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) +#define MF_HUGETLB_FREED 0 /* freed hugepage */ +#define MF_HUGETLB_IN_USED 1 /* in-use hugepage */ +#define MF_HUGETLB_NON_HUGEPAGE 2 /* not a hugepage */ +#define MF_HUGETLB_FOLIO_PRE_POISONED 3 /* folio already poisoned */ +#define MF_HUGETLB_PAGE_PRE_POISONED 4 /* exact page already poisoned */ +#define MF_HUGETLB_RETRY 5 /* hugepage is busy, retry */ +/* + * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list + * to keep track of the poisoned pages. + */ +static int hugetlb_update_hwpoison(struct folio *folio, struct page *page) { struct llist_head *head; struct raw_hwp_page *raw_hwp; struct raw_hwp_page *p; - int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0; + int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_FOLIO_PRE_POISONED : 0; /* * Once the hwpoison hugepage has lost reliable raw error info, @@ -1896,20 +1910,17 @@ static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) * so skip to add additional raw error info. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) - return -EHWPOISON; + return MF_HUGETLB_FOLIO_PRE_POISONED; head = raw_hwp_list_head(folio); llist_for_each_entry(p, head->first, node) { if (p->page == page) - return -EHWPOISON; + return MF_HUGETLB_PAGE_PRE_POISONED; } raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC); if (raw_hwp) { raw_hwp->page = page; llist_add(&raw_hwp->node, head); - /* the first error event will be counted in action_result(). */ - if (ret) - num_poisoned_pages_inc(page_to_pfn(page)); } else { /* * Failed to save raw error info. We no longer trace all @@ -1957,42 +1968,39 @@ void folio_clear_hugetlb_hwpoison(struct folio *folio) /* * Called from hugetlb code with hugetlb_lock held. - * - * Return values: - * 0 - free hugepage - * 1 - in-use hugepage - * 2 - not a hugepage - * -EBUSY - the hugepage is busy (try to retry) - * -EHWPOISON - the hugepage is already hwpoisoned */ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); - int ret = 2; /* fallback to normal page handling */ bool count_increased = false; + int ret, rc; - if (!folio_test_hugetlb(folio)) + if (!folio_test_hugetlb(folio)) { + ret = MF_HUGETLB_NON_HUGEPAGE; goto out; - - if (flags & MF_COUNT_INCREASED) { - ret = 1; + } else if (flags & MF_COUNT_INCREASED) { + ret = MF_HUGETLB_IN_USED; count_increased = true; } else if (folio_test_hugetlb_freed(folio)) { - ret = 0; + ret = MF_HUGETLB_FREED; } else if (folio_test_hugetlb_migratable(folio)) { - ret = folio_try_get(folio); - if (ret) + if (folio_try_get(folio)) { + ret = MF_HUGETLB_IN_USED; count_increased = true; + } else { + ret = MF_HUGETLB_FREED; + } } else { - ret = -EBUSY; + ret = MF_HUGETLB_RETRY; if (!(flags & MF_NO_RETRY)) goto out; } - if (folio_set_hugetlb_hwpoison(folio, page)) { - ret = -EHWPOISON; + rc = hugetlb_update_hwpoison(folio, page); + if (rc >= MF_HUGETLB_FOLIO_PRE_POISONED) { + ret = rc; goto out; } @@ -2017,10 +2025,16 @@ out: * with basic operations like hugepage allocation/free/demotion. * So some of prechecks for hwpoison (pinning, and testing/setting * PageHWPoison) should be done in single hugetlb_lock range. + * Returns: + * 0 - not hugetlb, or recovered + * -EBUSY - not recovered + * -EOPNOTSUPP - hwpoison_filter'ed + * -EHWPOISON - folio or exact page already poisoned + * -EFAULT - kill_accessing_process finds current->mm null */ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - int res; + int res, rv; struct page *p = pfn_to_page(pfn); struct folio *folio; unsigned long page_flags; @@ -2029,22 +2043,29 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb *hugetlb = 1; retry: res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); - if (res == 2) { /* fallback to normal page handling */ + switch (res) { + case MF_HUGETLB_NON_HUGEPAGE: /* fallback to normal page handling */ *hugetlb = 0; return 0; - } else if (res == -EHWPOISON) { - if (flags & MF_ACTION_REQUIRED) { - folio = page_folio(p); - res = kill_accessing_process(current, folio_pfn(folio), flags); - } - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); - return res; - } else if (res == -EBUSY) { + case MF_HUGETLB_RETRY: if (!(flags & MF_NO_RETRY)) { flags |= MF_NO_RETRY; goto retry; } return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + case MF_HUGETLB_FOLIO_PRE_POISONED: + case MF_HUGETLB_PAGE_PRE_POISONED: + rv = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + rv = kill_accessing_process(current, pfn, flags); + if (res == MF_HUGETLB_PAGE_PRE_POISONED) + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + else + action_result(pfn, MF_MSG_HUGE, MF_FAILED); + return rv; + default: + WARN_ON((res != MF_HUGETLB_FREED) && (res != MF_HUGETLB_IN_USED)); + break; } folio = page_folio(p); @@ -2055,7 +2076,7 @@ retry: if (migratable_cleared) folio_set_hugetlb_migratable(folio); folio_unlock(folio); - if (res == 1) + if (res == MF_HUGETLB_IN_USED) folio_put(folio); return -EOPNOTSUPP; } @@ -2064,7 +2085,7 @@ retry: * Handling free hugepage. The possible race with hugepage allocation * or demotion can be prevented by PageHWPoison flag. */ - if (res == 0) { + if (res == MF_HUGETLB_FREED) { folio_unlock(folio); if (__page_handle_poison(p) > 0) { page_ref_inc(p); diff --git a/mm/memremap.c b/mm/memremap.c index 63c6ab4fdf08..ac7be07e3361 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -477,10 +477,43 @@ void free_zone_device_folio(struct folio *folio) } } -void zone_device_page_init(struct page *page, unsigned int order) +void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap, + unsigned int order) { + struct page *new_page = page; + unsigned int i; + VM_WARN_ON_ONCE(order > MAX_ORDER_NR_PAGES); + for (i = 0; i < (1UL << order); ++i, ++new_page) { + struct folio *new_folio = (struct folio *)new_page; + + /* + * new_page could have been part of previous higher order folio + * which encodes the order, in page + 1, in the flags bits. We + * blindly clear bits which could have set my order field here, + * including page head. + */ + new_page->flags.f &= ~0xffUL; /* Clear possible order, page head */ + +#ifdef NR_PAGES_IN_LARGE_FOLIO + /* + * This pointer math looks odd, but new_page could have been + * part of a previous higher order folio, which sets _nr_pages + * in page + 1 (new_page). Therefore, we use pointer casting to + * correctly locate the _nr_pages bits within new_page which + * could have modified by previous higher order folio. + */ + ((struct folio *)(new_page - 1))->_nr_pages = 0; +#endif + + new_folio->mapping = NULL; + new_folio->pgmap = pgmap; /* Also clear compound head */ + new_folio->share = 0; /* fsdax only, unused for device private */ + VM_WARN_ON_FOLIO(folio_ref_count(new_folio), new_folio); + VM_WARN_ON_FOLIO(!folio_is_zone_device(new_folio), new_folio); + } + /* * Drivers shouldn't be allocating pages after calling * memunmap_pages(). diff --git a/mm/mm_init.c b/mm/mm_init.c index fc2a6f1e518f..2a809cd8e7fa 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2059,7 +2059,7 @@ static unsigned long __init deferred_init_pages(struct zone *zone, */ static unsigned long __init deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, - struct zone *zone) + struct zone *zone, bool can_resched) { int nid = zone_to_nid(zone); unsigned long nr_pages = 0; @@ -2085,10 +2085,10 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, spfn = chunk_end; - if (irqs_disabled()) - touch_nmi_watchdog(); - else + if (can_resched) cond_resched(); + else + touch_nmi_watchdog(); } } @@ -2101,7 +2101,7 @@ deferred_init_memmap_job(unsigned long start_pfn, unsigned long end_pfn, { struct zone *zone = arg; - deferred_init_memmap_chunk(start_pfn, end_pfn, zone); + deferred_init_memmap_chunk(start_pfn, end_pfn, zone, true); } static unsigned int __init @@ -2216,7 +2216,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) for (spfn = first_deferred_pfn, epfn = SECTION_ALIGN_UP(spfn + 1); nr_pages < nr_pages_needed && spfn < zone_end_pfn(zone); spfn = epfn, epfn += PAGES_PER_SECTION) { - nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone); + nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone, false); } /* diff --git a/mm/shmem.c b/mm/shmem.c index ec6c01378e9d..79af5f9f8b90 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -962,17 +962,29 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) * being freed). */ static long shmem_free_swap(struct address_space *mapping, - pgoff_t index, void *radswap) + pgoff_t index, pgoff_t end, void *radswap) { - int order = xa_get_order(&mapping->i_pages, index); - void *old; + XA_STATE(xas, &mapping->i_pages, index); + unsigned int nr_pages = 0; + pgoff_t base; + void *entry; - old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); - if (old != radswap) - return 0; - free_swap_and_cache_nr(radix_to_swp_entry(radswap), 1 << order); + xas_lock_irq(&xas); + entry = xas_load(&xas); + if (entry == radswap) { + nr_pages = 1 << xas_get_order(&xas); + base = round_down(xas.xa_index, nr_pages); + if (base < index || base + nr_pages - 1 > end) + nr_pages = 0; + else + xas_store(&xas, NULL); + } + xas_unlock_irq(&xas); - return 1 << order; + if (nr_pages) + free_swap_and_cache_nr(radix_to_swp_entry(radswap), nr_pages); + + return nr_pages; } /* @@ -1124,8 +1136,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, uoff_t lend, if (xa_is_value(folio)) { if (unfalloc) continue; - nr_swaps_freed += shmem_free_swap(mapping, - indices[i], folio); + nr_swaps_freed += shmem_free_swap(mapping, indices[i], + end - 1, folio); continue; } @@ -1191,14 +1203,30 @@ whole_folios: folio = fbatch.folios[i]; if (xa_is_value(folio)) { + int order; long swaps_freed; if (unfalloc) continue; - swaps_freed = shmem_free_swap(mapping, indices[i], folio); + swaps_freed = shmem_free_swap(mapping, indices[i], + end - 1, folio); if (!swaps_freed) { - /* Swap was replaced by page: retry */ - index = indices[i]; + pgoff_t base = indices[i]; + + order = shmem_confirm_swap(mapping, indices[i], + radix_to_swp_entry(folio)); + /* + * 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/mm/swap.h b/mm/swap.h index d034c13d8dd2..1bd466da3039 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -198,7 +198,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug); void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug); /* linux/mm/swap_state.c */ -extern struct address_space swap_space __ro_after_init; +extern struct address_space swap_space __read_mostly; static inline struct address_space *swap_address_space(swp_entry_t entry) { return &swap_space; diff --git a/mm/swap_state.c b/mm/swap_state.c index 5f97c6ae70a2..44d228982521 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,8 +37,7 @@ static const struct address_space_operations swap_aops = { #endif }; -/* Set swap_space as read only as swap cache is handled by swap table */ -struct address_space swap_space __ro_after_init = { +struct address_space swap_space __read_mostly = { .a_ops = &swap_aops, }; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 628f96e83b11..e286c2d2068c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4322,7 +4322,7 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); vm->requested_size = size; - kasan_poison_vmalloc(p + size, old_size - size); + kasan_vrealloc(p, old_size, size); return (void *)p; } @@ -4330,16 +4330,13 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align * We already have the bytes available in the allocation; use them. */ if (size <= alloced_size) { - kasan_unpoison_vmalloc(p + old_size, size - old_size, - KASAN_VMALLOC_PROT_NORMAL | - KASAN_VMALLOC_VM_ALLOC | - KASAN_VMALLOC_KEEP_TAG); /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during * realloc shrink time. */ vm->requested_size = size; + kasan_vrealloc(p, old_size, size); return (void *)p; } 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 ad326c7cdc0a..ef61695fbdbb 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 c5ed88bccbb4..5fae329795c8 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -901,9 +901,6 @@ 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 174d38c70ac4..9880d608392b 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 be4924aeaf0e..58d9940a596a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5915,7 +5915,7 @@ 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/rust/Makefile b/rust/Makefile index 5d357dce1704..4dcc2eff51cb 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -383,6 +383,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ -fstrict-flex-arrays=% -fmin-function-alignment=% \ -fzero-init-padding-bits=% -mno-fdpic \ + -fdiagnostics-show-context -fdiagnostics-show-context=% \ --param=% --param asan-% -fno-isolate-erroneous-paths-dereference # Derived from `scripts/Makefile.clang`. diff --git a/rust/kernel/bits.rs b/rust/kernel/bits.rs index 553d50265883..2daead125626 100644 --- a/rust/kernel/bits.rs +++ b/rust/kernel/bits.rs @@ -27,7 +27,8 @@ macro_rules! impl_bit_fn { /// /// This version is the default and should be used if `n` is known at /// compile time. - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub const fn [<bit_ $ty>](n: u32) -> $ty { build_assert!(n < <$ty>::BITS); (1 as $ty) << n @@ -75,7 +76,8 @@ macro_rules! impl_genmask_fn { /// This version is the default and should be used if the range is known /// at compile time. $(#[$genmask_ex])* - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub const fn [<genmask_ $ty>](range: RangeInclusive<u32>) -> $ty { let start = *range.start(); let end = *range.end(); diff --git a/rust/kernel/fmt.rs b/rust/kernel/fmt.rs index 84d634201d90..1e8725eb44ed 100644 --- a/rust/kernel/fmt.rs +++ b/rust/kernel/fmt.rs @@ -6,7 +6,7 @@ pub use core::fmt::{Arguments, Debug, Error, Formatter, Result, Write}; -/// Internal adapter used to route allow implementations of formatting traits for foreign types. +/// Internal adapter used to route and allow implementations of formatting traits for foreign types. /// /// It is inserted automatically by the [`fmt!`] macro and is not meant to be used directly. /// diff --git a/rust/kernel/num/bounded.rs b/rust/kernel/num/bounded.rs index f870080af8ac..fa81acbdc8c2 100644 --- a/rust/kernel/num/bounded.rs +++ b/rust/kernel/num/bounded.rs @@ -40,11 +40,11 @@ fn fits_within<T: Integer>(value: T, num_bits: u32) -> bool { fits_within!(value, T, num_bits) } -/// An integer value that requires only the `N` less significant bits of the wrapped type to be +/// An integer value that requires only the `N` least significant bits of the wrapped type to be /// encoded. /// /// This limits the number of usable bits in the wrapped integer type, and thus the stored value to -/// a narrower range, which provides guarantees that can be useful when working with in e.g. +/// a narrower range, which provides guarantees that can be useful when working within e.g. /// bitfields. /// /// # Invariants @@ -56,7 +56,7 @@ fn fits_within<T: Integer>(value: T, num_bits: u32) -> bool { /// # Examples /// /// The preferred way to create values is through constants and the [`Bounded::new`] family of -/// constructors, as they trigger a build error if the type invariants cannot be withheld. +/// constructors, as they trigger a build error if the type invariants cannot be upheld. /// /// ``` /// use kernel::num::Bounded; @@ -82,7 +82,7 @@ fn fits_within<T: Integer>(value: T, num_bits: u32) -> bool { /// ``` /// use kernel::num::Bounded; /// -/// // This succeeds because `15` can be represented with 4 unsigned bits. +/// // This succeeds because `15` can be represented with 4 unsigned bits. /// assert!(Bounded::<u8, 4>::try_new(15).is_some()); /// /// // This fails because `16` cannot be represented with 4 unsigned bits. @@ -221,7 +221,7 @@ fn fits_within<T: Integer>(value: T, num_bits: u32) -> bool { /// let v: Option<Bounded<u16, 8>> = 128u32.try_into_bounded(); /// assert_eq!(v.as_deref().copied(), Some(128)); /// -/// // Fails because `128` doesn't fits into 6 bits. +/// // Fails because `128` doesn't fit into 6 bits. /// let v: Option<Bounded<u16, 6>> = 128u32.try_into_bounded(); /// assert_eq!(v, None); /// ``` @@ -259,9 +259,9 @@ macro_rules! impl_const_new { assert!(fits_within!(VALUE, $type, N)); } - // INVARIANT: `fits_within` confirmed that `VALUE` can be represented within + // SAFETY: `fits_within` confirmed that `VALUE` can be represented within // `N` bits. - Self::__new(VALUE) + unsafe { Self::__new(VALUE) } } } )* @@ -282,9 +282,10 @@ where /// All instances of [`Bounded`] must be created through this method as it enforces most of the /// type invariants. /// - /// The caller remains responsible for checking, either statically or dynamically, that `value` - /// can be represented as a `T` using at most `N` bits. - const fn __new(value: T) -> Self { + /// # Safety + /// + /// The caller must ensure that `value` can be represented within `N` bits. + const unsafe fn __new(value: T) -> Self { // Enforce the type invariants. const { // `N` cannot be zero. @@ -293,6 +294,7 @@ where assert!(N <= T::BITS); } + // INVARIANT: The caller ensures `value` fits within `N` bits. Self(value) } @@ -328,8 +330,8 @@ where /// ``` pub fn try_new(value: T) -> Option<Self> { fits_within(value, N).then(|| { - // INVARIANT: `fits_within` confirmed that `value` can be represented within `N` bits. - Self::__new(value) + // SAFETY: `fits_within` confirmed that `value` can be represented within `N` bits. + unsafe { Self::__new(value) } }) } @@ -363,6 +365,7 @@ where /// assert_eq!(Bounded::<u8, 1>::from_expr(1).get(), 1); /// assert_eq!(Bounded::<u16, 8>::from_expr(0xff).get(), 0xff); /// ``` + // Always inline to optimize out error path of `build_assert`. #[inline(always)] pub fn from_expr(expr: T) -> Self { crate::build_assert!( @@ -370,8 +373,8 @@ where "Requested value larger than maximal representable value." ); - // INVARIANT: `fits_within` confirmed that `expr` can be represented within `N` bits. - Self::__new(expr) + // SAFETY: `fits_within` confirmed that `expr` can be represented within `N` bits. + unsafe { Self::__new(expr) } } /// Returns the wrapped value as the backing type. @@ -410,9 +413,9 @@ where ); } - // INVARIANT: The value did fit within `N` bits, so it will all the more fit within + // SAFETY: The value did fit within `N` bits, so it will all the more fit within // the larger `M` bits. - Bounded::__new(self.0) + unsafe { Bounded::__new(self.0) } } /// Attempts to shrink the number of bits usable for `self`. @@ -466,9 +469,9 @@ where // `U` and `T` have the same sign, hence this conversion cannot fail. let value = unsafe { U::try_from(self.get()).unwrap_unchecked() }; - // INVARIANT: Although the backing type has changed, the value is still represented within + // SAFETY: Although the backing type has changed, the value is still represented within // `N` bits, and with the same signedness. - Bounded::__new(value) + unsafe { Bounded::__new(value) } } } @@ -501,7 +504,7 @@ where /// let v: Option<Bounded<u16, 8>> = 128u32.try_into_bounded(); /// assert_eq!(v.as_deref().copied(), Some(128)); /// -/// // Fails because `128` doesn't fits into 6 bits. +/// // Fails because `128` doesn't fit into 6 bits. /// let v: Option<Bounded<u16, 6>> = 128u32.try_into_bounded(); /// assert_eq!(v, None); /// ``` @@ -944,9 +947,9 @@ macro_rules! impl_from_primitive { Self: AtLeastXBits<{ <$type as Integer>::BITS as usize }>, { fn from(value: $type) -> Self { - // INVARIANT: The trait bound on `Self` guarantees that `N` bits is + // SAFETY: The trait bound on `Self` guarantees that `N` bits is // enough to hold any value of the source type. - Self::__new(T::from(value)) + unsafe { Self::__new(T::from(value)) } } } )* @@ -1051,8 +1054,8 @@ where T: Integer + From<bool>, { fn from(value: bool) -> Self { - // INVARIANT: A boolean can be represented using a single bit, and thus fits within any + // SAFETY: A boolean can be represented using a single bit, and thus fits within any // integer type for any `N` > 0. - Self::__new(T::from(value)) + unsafe { Self::__new(T::from(value)) } } } diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index 4729eb56827a..312cecab72e7 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -985,7 +985,7 @@ impl<'a, K, V> CursorMut<'a, K, V> { self.peek(Direction::Prev) } - /// Access the previous node without moving the cursor. + /// Access the next node without moving the cursor. pub fn peek_next(&self) -> Option<(&K, &V)> { self.peek(Direction::Next) } @@ -1130,7 +1130,7 @@ pub struct IterMut<'a, K, V> { } // SAFETY: The [`IterMut`] has exclusive access to both `K` and `V`, so it is sufficient to require them to be `Send`. -// The iterator only gives out immutable references to the keys, but since the iterator has excusive access to those same +// The iterator only gives out immutable references to the keys, but since the iterator has exclusive access to those same // keys, `Send` is sufficient. `Sync` would be okay, but it is more restrictive to the user. unsafe impl<'a, K: Send, V: Send> Send for IterMut<'a, K, V> {} diff --git a/rust/kernel/sync/atomic/predefine.rs b/rust/kernel/sync/atomic/predefine.rs index 45a17985cda4..0fca1ba3c2db 100644 --- a/rust/kernel/sync/atomic/predefine.rs +++ b/rust/kernel/sync/atomic/predefine.rs @@ -35,12 +35,23 @@ unsafe impl super::AtomicAdd<i64> for i64 { // as `isize` and `usize`, and `isize` and `usize` are always bi-directional transmutable to // `isize_atomic_repr`, which also always implements `AtomicImpl`. #[allow(non_camel_case_types)] +#[cfg(not(testlib))] #[cfg(not(CONFIG_64BIT))] type isize_atomic_repr = i32; #[allow(non_camel_case_types)] +#[cfg(not(testlib))] #[cfg(CONFIG_64BIT)] type isize_atomic_repr = i64; +#[allow(non_camel_case_types)] +#[cfg(testlib)] +#[cfg(target_pointer_width = "32")] +type isize_atomic_repr = i32; +#[allow(non_camel_case_types)] +#[cfg(testlib)] +#[cfg(target_pointer_width = "64")] +type isize_atomic_repr = i64; + // Ensure size and alignment requirements are checked. static_assert!(size_of::<isize>() == size_of::<isize_atomic_repr>()); static_assert!(align_of::<isize>() == align_of::<isize_atomic_repr>()); diff --git a/rust/kernel/sync/refcount.rs b/rust/kernel/sync/refcount.rs index 19236a5bccde..6c7ae8b05a0b 100644 --- a/rust/kernel/sync/refcount.rs +++ b/rust/kernel/sync/refcount.rs @@ -23,7 +23,8 @@ impl Refcount { /// Construct a new [`Refcount`] from an initial value. /// /// The initial value should be non-saturated. - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub fn new(value: i32) -> Self { build_assert!(value >= 0, "initial value saturated"); // SAFETY: There are no safety requirements for this FFI call. diff --git a/rust/macros/fmt.rs b/rust/macros/fmt.rs index 2f4b9f6e2211..8354abd54502 100644 --- a/rust/macros/fmt.rs +++ b/rust/macros/fmt.rs @@ -67,7 +67,7 @@ pub(crate) fn fmt(input: TokenStream) -> TokenStream { } (None, acc) })(); - args.extend(quote_spanned!(first_span => #lhs #adapter(&#rhs))); + args.extend(quote_spanned!(first_span => #lhs #adapter(&(#rhs)))); } }; diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index b38002151871..33f66e86418a 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -59,7 +59,7 @@ use proc_macro::TokenStream; /// /// # Examples /// -/// ``` +/// ```ignore /// use kernel::prelude::*; /// /// module!{ diff --git a/rust/proc-macro2/lib.rs b/rust/proc-macro2/lib.rs index 7b78d065d51c..5d408943fa0d 100644 --- a/rust/proc-macro2/lib.rs +++ b/rust/proc-macro2/lib.rs @@ -1,5 +1,9 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT +// When fixdep scans this, it will find this string `CONFIG_RUSTC_VERSION_TEXT` +// and thus add a dependency on `include/config/RUSTC_VERSION_TEXT`, which is +// touched by Kconfig when the version string from the compiler changes. + //! [![github]](https://github.com/dtolnay/proc-macro2) [![crates-io]](https://crates.io/crates/proc-macro2) [![docs-rs]](crate) //! //! [github]: https://img.shields.io/badge/github-8da0cb?style=for-the-badge&labelColor=555555&logo=github diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 5037f4715d74..32e209bc7985 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -166,11 +166,13 @@ else ifeq ($(KBUILD_CHECKSRC),2) cmd_force_checksrc = $(CHECK) $(CHECKFLAGS) $(c_flags) $< endif +ifeq ($(KBUILD_EXTMOD),) ifneq ($(KBUILD_EXTRA_WARN),) cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(KDOCFLAGS) \ $(if $(findstring 2, $(KBUILD_EXTRA_WARN)), -Wall) \ $< endif +endif # Compile C sources (.c) # --------------------------------------------------------------------------- @@ -356,7 +358,7 @@ $(obj)/%.o: $(obj)/%.rs FORCE quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_rsi_rs = \ $(rust_common_cmd) -Zunpretty=expanded $< >$@; \ - command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@ + command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) --config-path $(srctree)/.rustfmt.toml $@ $(obj)/%.rsi: $(obj)/%.rs FORCE +$(call if_changed_dep,rustc_rsi_rs) diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index cd788cac9d91..276c3134a563 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -113,7 +113,8 @@ vmlinux: vmlinux.unstripped FORCE # what kmod expects to parse. quiet_cmd_modules_builtin_modinfo = GEN $@ cmd_modules_builtin_modinfo = $(cmd_objcopy); \ - sed -i 's/\x00\+$$/\x00/g' $@ + sed -i 's/\x00\+$$/\x00/g' $@; \ + chmod -x $@ OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index 147d0cc94068..766c2d91cd81 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -61,7 +61,6 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit display_name, deps, cfg=[], - edition="2021", ): append_crate( display_name, @@ -69,13 +68,37 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit deps, cfg, is_workspace_member=False, - edition=edition, + # Miguel Ojeda writes: + # + # > ... in principle even the sysroot crates may have different + # > editions. + # > + # > For instance, in the move to 2024, it seems all happened at once + # > in 1.87.0 in these upstream commits: + # > + # > 0e071c2c6a58 ("Migrate core to Rust 2024") + # > f505d4e8e380 ("Migrate alloc to Rust 2024") + # > 0b2489c226c3 ("Migrate proc_macro to Rust 2024") + # > 993359e70112 ("Migrate std to Rust 2024") + # > + # > But in the previous move to 2021, `std` moved in 1.59.0, while + # > the others in 1.60.0: + # > + # > b656384d8398 ("Update stdlib to the 2021 edition") + # > 06a1c14d52a8 ("Switch all libraries to the 2021 edition") + # + # Link: https://lore.kernel.org/all/CANiq72kd9bHdKaAm=8xCUhSHMy2csyVed69bOc4dXyFAW4sfuw@mail.gmail.com/ + # + # At the time of writing all rust versions we support build the + # sysroot crates with the same edition. We may need to relax this + # assumption if future edition moves span multiple rust versions. + edition=core_edition, ) # NB: sysroot crates reexport items from one another so setting up our transitive dependencies # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`. - append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []), edition=core_edition) + append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", [])) append_sysroot_crate("alloc", ["core"]) append_sysroot_crate("std", ["alloc", "core"]) append_sysroot_crate("proc_macro", ["core", "std"]) @@ -83,7 +106,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit append_crate( "compiler_builtins", srctree / "rust" / "compiler_builtins.rs", - [], + ["core"], ) append_crate( @@ -96,14 +119,15 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit append_crate( "quote", srctree / "rust" / "quote" / "lib.rs", - ["alloc", "proc_macro", "proc_macro2"], + ["core", "alloc", "std", "proc_macro", "proc_macro2"], cfg=crates_cfgs["quote"], + edition="2018", ) append_crate( "syn", srctree / "rust" / "syn" / "lib.rs", - ["proc_macro", "proc_macro2", "quote"], + ["std", "proc_macro", "proc_macro2", "quote"], cfg=crates_cfgs["syn"], ) @@ -123,7 +147,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit append_crate( "pin_init_internal", srctree / "rust" / "pin-init" / "internal" / "src" / "lib.rs", - [], + ["std", "proc_macro"], cfg=["kernel"], is_proc_macro=True, ) @@ -131,7 +155,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit append_crate( "pin_init", srctree / "rust" / "pin-init" / "src" / "lib.rs", - ["core", "pin_init_internal", "macros"], + ["core", "compiler_builtins", "pin_init_internal", "macros"], cfg=["kernel"], ) @@ -190,7 +214,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edit append_crate( name, path, - ["core", "kernel"], + ["core", "kernel", "pin_init"], cfg=cfg, ) @@ -213,9 +237,6 @@ def main(): level=logging.INFO if args.verbose else logging.WARNING ) - # Making sure that the `sysroot` and `sysroot_src` belong to the same toolchain. - assert args.sysroot in args.sysroot_src.parents - rust_project = { "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs, args.core_edition), "sysroot": str(args.sysroot), diff --git a/scripts/livepatch/klp-build b/scripts/livepatch/klp-build index 882272120c9e..a73515a82272 100755 --- a/scripts/livepatch/klp-build +++ b/scripts/livepatch/klp-build @@ -555,13 +555,11 @@ copy_orig_objects() { local file_dir="$(dirname "$file")" local orig_file="$ORIG_DIR/$rel_file" local orig_dir="$(dirname "$orig_file")" - local cmd_file="$file_dir/.$(basename "$file").cmd" [[ ! -f "$file" ]] && die "missing $(basename "$file") for $_file" mkdir -p "$orig_dir" cp -f "$file" "$orig_dir" - [[ -e "$cmd_file" ]] && cp -f "$cmd_file" "$orig_dir" done xtrace_restore @@ -740,15 +738,17 @@ build_patch_module() { local orig_dir="$(dirname "$orig_file")" local kmod_file="$KMOD_DIR/$rel_file" local kmod_dir="$(dirname "$kmod_file")" - local cmd_file="$orig_dir/.$(basename "$file").cmd" + local cmd_file="$kmod_dir/.$(basename "$file").cmd" mkdir -p "$kmod_dir" cp -f "$file" "$kmod_dir" - [[ -e "$cmd_file" ]] && cp -f "$cmd_file" "$kmod_dir" # Tell kbuild this is a prebuilt object cp -f "$file" "${kmod_file}_shipped" + # Make modpost happy + touch "$cmd_file" + echo -n " $rel_file" >> "$makefile" done diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index 98f206cb7c60..0f1c8de1bd95 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -2,6 +2,8 @@ %{!?_arch: %define _arch dummy} %{!?make: %define make make} %define makeflags %{?_smp_mflags} ARCH=%{ARCH} +%define __spec_install_post /usr/lib/rpm/brp-compress || : +%define debug_package %{nil} Name: kernel Summary: The Linux Kernel @@ -46,34 +48,12 @@ against the %{version} kernel package. %endif %if %{with_debuginfo} -# list of debuginfo-related options taken from distribution kernel.spec -# files -%undefine _include_minidebuginfo -%undefine _find_debuginfo_dwz_opts -%undefine _unique_build_ids -%undefine _unique_debug_names -%undefine _unique_debug_srcs -%undefine _debugsource_packages -%undefine _debuginfo_subpackages -%global _find_debuginfo_opts -r -%global _missing_build_ids_terminate_build 1 -%global _no_recompute_build_ids 1 -%{debug_package} +%package debuginfo +Summary: Debug information package for the Linux kernel +%description debuginfo +This package provides debug information for the kernel image and modules from the +%{version} package. %endif -# some (but not all) versions of rpmbuild emit %%debug_package with -# %%install. since we've already emitted it manually, that would cause -# a package redefinition error. ensure that doesn't happen -%define debug_package %{nil} - -# later, we make all modules executable so that find-debuginfo.sh strips -# them up. but they don't actually need to be executable, so remove the -# executable bit, taking care to do it _after_ find-debuginfo.sh has run -%define __spec_install_post \ - %{?__debug_package:%{__debug_install_post}} \ - %{__arch_install_post} \ - %{__os_install_post} \ - find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \\\ - | xargs --no-run-if-empty chmod u-x %prep %setup -q -n linux @@ -87,7 +67,7 @@ patch -p1 < %{SOURCE2} mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE} cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz # DEPMOD=true makes depmod no-op. We do not package depmod-generated files. -%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install +%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} INSTALL_MOD_STRIP=1 DEPMOD=true modules_install %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE} cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config @@ -118,22 +98,31 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA echo "%exclude /lib/modules/%{KERNELRELEASE}/build" } > %{buildroot}/kernel.list -# make modules executable so that find-debuginfo.sh strips them. this -# will be undone later in %%__spec_install_post -find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \ - | xargs --no-run-if-empty chmod u+x - %if %{with_debuginfo} # copying vmlinux directly to the debug directory means it will not get # stripped (but its source paths will still be collected + fixed up) mkdir -p %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} cp vmlinux %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} + +echo /usr/lib/debug/lib/modules/%{KERNELRELEASE}/vmlinux > %{buildroot}/debuginfo.list + +while read -r mod; do + mod="${mod%.o}.ko" + dbg="%{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE}/kernel/${mod}" + buildid=$("${READELF}" -n "${mod}" | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p') + link="%{buildroot}/usr/lib/debug/.build-id/${buildid}.debug" + + mkdir -p "${dbg%/*}" "${link%/*}" + "${OBJCOPY}" --only-keep-debug "${mod}" "${dbg}" + ln -sf --relative "${dbg}" "${link}" + + echo "${dbg#%{buildroot}}" >> %{buildroot}/debuginfo.list + echo "${link#%{buildroot}}" >> %{buildroot}/debuginfo.list +done < modules.order %endif %clean rm -rf %{buildroot} -rm -f debugfiles.list debuglinks.list debugsourcefiles.list debugsources.list \ - elfbins.list %post if [ -x /usr/bin/kernel-install ]; then @@ -172,3 +161,9 @@ fi /usr/src/kernels/%{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/build %endif + +%if %{with_debuginfo} +%files -f %{buildroot}/debuginfo.list debuginfo +%defattr (-, root, root) +%exclude /debuginfo.list +%endif diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs index be0561049660..6fd9f5c84e2e 100644 --- a/scripts/rustdoc_test_gen.rs +++ b/scripts/rustdoc_test_gen.rs @@ -206,7 +206,7 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut ::kernel::bindings::kunit) {{ /// The anchor where the test code body starts. #[allow(unused)] - static __DOCTEST_ANCHOR: i32 = ::core::line!() as i32 + {body_offset} + 1; + static __DOCTEST_ANCHOR: i32 = ::core::line!() as i32 + {body_offset} + 2; {{ #![allow(unreachable_pub, clippy::disallowed_names)] {body} 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/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index cafa48b5aceb..0a0496deb9c8 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3383,11 +3383,22 @@ static void alc287_alc1318_playback_pcm_hook(struct hda_pcm_stream *hinfo, struct snd_pcm_substream *substream, int action) { + static const struct coef_fw dis_coefs[] = { + WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), + WRITE_COEF(0x28, 0x0004), WRITE_COEF(0x29, 0xb023), + }; /* Disable AMP silence detection */ + static const struct coef_fw en_coefs[] = { + WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), + WRITE_COEF(0x28, 0x0084), WRITE_COEF(0x29, 0xb023), + }; /* Enable AMP silence detection */ + switch (action) { case HDA_GEN_PCM_ACT_OPEN: + alc_process_coef_fw(codec, dis_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x954f); /* write gpio3 to high */ break; case HDA_GEN_PCM_ACT_CLOSE: + alc_process_coef_fw(codec, en_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x554f); /* write gpio3 as default value */ break; } @@ -6739,6 +6750,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8d, "HP ProBook 440 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8e, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8f, "HP EliteBook 630 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -7336,6 +7348,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x300f, "TongFang X6AR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3019, "TongFang X6FR5xxY", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -7346,6 +7359,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1ee7, 0x2078, "HONOR BRB-X M1010", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x2039, 0x0001, "Inspur S14-G1", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), @@ -7805,10 +7819,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60140}, {0x19, 0x04a11030}, {0x21, 0x04211020}), - SND_HDA_PIN_QUIRK(0x10ec0274, 0x1d05, "TongFang", ALC274_FIXUP_HP_HEADSET_MIC, - {0x17, 0x90170110}, - {0x19, 0x03a11030}, - {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0282, 0x1025, "Acer", ALC282_FIXUP_ACER_DISABLE_LINEOUT, ALC282_STANDARD_PINS, {0x12, 0x90a609c0}, diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 0294177acc66..c18da0915baa 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -545,6 +545,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK PM1503CDA"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16z-n000"), } @@ -675,6 +682,14 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "GOH-X"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_BOARD_NAME, "XyloD5_RBU"), + } + }, + {} }; diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index e33f11435980..7aa558d6362f 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -453,7 +453,7 @@ static const struct snd_soc_dapm_widget cs35l45_dapm_widgets[] = { SND_SOC_DAPM_AIF_OUT("ASP_TX2", NULL, 1, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX2_EN_SHIFT, 0), SND_SOC_DAPM_AIF_OUT("ASP_TX3", NULL, 2, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX3_EN_SHIFT, 0), SND_SOC_DAPM_AIF_OUT("ASP_TX4", NULL, 3, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX4_EN_SHIFT, 0), - SND_SOC_DAPM_AIF_OUT("ASP_TX5", NULL, 3, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX5_EN_SHIFT, 0), + SND_SOC_DAPM_AIF_OUT("ASP_TX5", NULL, 4, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX5_EN_SHIFT, 0), SND_SOC_DAPM_MUX("ASP_TX1 Source", SND_SOC_NOPM, 0, 0, &cs35l45_asp_muxes[0]), SND_SOC_DAPM_MUX("ASP_TX2 Source", SND_SOC_NOPM, 0, 0, &cs35l45_asp_muxes[1]), diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 28699d7b75ca..05b4e971a366 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -346,7 +346,6 @@ static int imx_aif_hw_params(struct snd_pcm_substream *substream, SND_SOC_DAIFMT_PDM; } else { slots = 2; - slot_width = params_physical_width(params); fmt = (rtd->dai_link->dai_fmt & ~SND_SOC_DAIFMT_FORMAT_MASK) | SND_SOC_DAIFMT_I2S; } diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 774fff58d51b..fce50fd9f093 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -120,7 +120,7 @@ static void pcm_pop_work_events(struct work_struct *work) gpiod_set_value_cansleep(priv->gpio_speakers, priv->speaker_en); if (quirk & SOF_ES8336_HEADPHONE_GPIO) - gpiod_set_value_cansleep(priv->gpio_headphone, priv->speaker_en); + gpiod_set_value_cansleep(priv->gpio_headphone, !priv->speaker_en); } diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 8721a098d53f..50b838be24e9 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -838,6 +838,7 @@ static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC), + SND_PCI_QUIRK(0x17aa, 0x3821, "Lenovo 0x3821", SOC_SDW_SIDECAR_AMPS), {} }; diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index 060955825fe0..e297c8ecedb7 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -442,7 +442,7 @@ static const struct snd_soc_acpi_adr_device rt1320_2_group2_adr[] = { .adr = 0x000230025D132001ull, .num_endpoints = 1, .endpoints = &spk_r_endpoint, - .name_prefix = "rt1320-1" + .name_prefix = "rt1320-2" } }; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3f7999317f4d..719ec727efd4 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -197,7 +197,8 @@ static bool is_rust_noreturn(const struct symbol *func) * as well as changes to the source code itself between versions (since * these come from the Rust standard library). */ - return str_ends_with(func->name, "_4core5sliceSp15copy_from_slice17len_mismatch_fail") || + return str_ends_with(func->name, "_4core3num22from_ascii_radix_panic") || + str_ends_with(func->name, "_4core5sliceSp15copy_from_slice17len_mismatch_fail") || str_ends_with(func->name, "_4core6option13expect_failed") || str_ends_with(func->name, "_4core6option13unwrap_failed") || str_ends_with(func->name, "_4core6result13unwrap_failed") || diff --git a/tools/objtool/disas.c b/tools/objtool/disas.c index 2b5059f55e40..26f08d41f2b1 100644 --- a/tools/objtool/disas.c +++ b/tools/objtool/disas.c @@ -108,6 +108,8 @@ static int sprint_name(char *str, const char *name, unsigned long offset) #define DINFO_FPRINTF(dinfo, ...) \ ((*(dinfo)->fprintf_func)((dinfo)->stream, __VA_ARGS__)) +#define bfd_vma_fmt \ + __builtin_choose_expr(sizeof(bfd_vma) == sizeof(unsigned long), "%#lx <%s>", "%#llx <%s>") static int disas_result_fprintf(struct disas_context *dctx, const char *fmt, va_list ap) @@ -170,10 +172,10 @@ static void disas_print_addr_sym(struct section *sec, struct symbol *sym, if (sym) { sprint_name(symstr, sym->name, addr - sym->offset); - DINFO_FPRINTF(dinfo, "0x%lx <%s>", addr, symstr); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, symstr); } else { str = offstr(sec, addr); - DINFO_FPRINTF(dinfo, "0x%lx <%s>", addr, str); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, str); free(str); } } @@ -252,7 +254,7 @@ static void disas_print_addr_reloc(bfd_vma addr, struct disassemble_info *dinfo) * example: "lea 0x0(%rip),%rdi". The kernel can reference * the next IP with _THIS_IP_ macro. */ - DINFO_FPRINTF(dinfo, "0x%lx <_THIS_IP_>", addr); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, "_THIS_IP_"); return; } @@ -264,11 +266,11 @@ static void disas_print_addr_reloc(bfd_vma addr, struct disassemble_info *dinfo) */ if (reloc->sym->type == STT_SECTION) { str = offstr(reloc->sym->sec, reloc->sym->offset + offset); - DINFO_FPRINTF(dinfo, "0x%lx <%s>", addr, str); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, str); free(str); } else { sprint_name(symstr, reloc->sym->name, offset); - DINFO_FPRINTF(dinfo, "0x%lx <%s>", addr, symstr); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, symstr); } } @@ -311,7 +313,7 @@ static void disas_print_address(bfd_vma addr, struct disassemble_info *dinfo) */ sym = insn_call_dest(insn); if (sym && (sym->offset == addr || (sym->offset == 0 && is_reloc))) { - DINFO_FPRINTF(dinfo, "0x%lx <%s>", addr, sym->name); + DINFO_FPRINTF(dinfo, bfd_vma_fmt, addr, sym->name); return; } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 6a8ed9c62323..2c02c7b49265 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -18,15 +18,14 @@ #include <errno.h> #include <libgen.h> #include <ctype.h> +#include <linux/align.h> +#include <linux/kernel.h> #include <linux/interval_tree_generic.h> +#include <linux/log2.h> #include <objtool/builtin.h> #include <objtool/elf.h> #include <objtool/warn.h> -#define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) -#define ALIGN_UP_POW2(x) (1U << ((8 * sizeof(x)) - __builtin_clz((x) - 1U))) -#define MAX(a, b) ((a) > (b) ? (a) : (b)) - static inline u32 str_hash(const char *str) { return jhash(str, strlen(str), 0); @@ -1336,7 +1335,7 @@ unsigned int elf_add_string(struct elf *elf, struct section *strtab, const char return -1; } - offset = ALIGN_UP(strtab->sh.sh_size, strtab->sh.sh_addralign); + offset = ALIGN(strtab->sh.sh_size, strtab->sh.sh_addralign); if (!elf_add_data(elf, strtab, str, strlen(str) + 1)) return -1; @@ -1378,7 +1377,7 @@ void *elf_add_data(struct elf *elf, struct section *sec, const void *data, size_ sec->data->d_size = size; sec->data->d_align = 1; - offset = ALIGN_UP(sec->sh.sh_size, sec->sh.sh_addralign); + offset = ALIGN(sec->sh.sh_size, sec->sh.sh_addralign); sec->sh.sh_size = offset + size; mark_sec_changed(elf, sec, true); @@ -1502,7 +1501,7 @@ static int elf_alloc_reloc(struct elf *elf, struct section *rsec) rsec->data->d_size = nr_relocs_new * elf_rela_size(elf); rsec->sh.sh_size = rsec->data->d_size; - nr_alloc = MAX(64, ALIGN_UP_POW2(nr_relocs_new)); + nr_alloc = max(64UL, roundup_pow_of_two(nr_relocs_new)); if (nr_alloc <= rsec->nr_alloc_relocs) return 0; diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c index 4d1f9e9977eb..d94531e3f64e 100644 --- a/tools/objtool/klp-diff.c +++ b/tools/objtool/klp-diff.c @@ -1425,9 +1425,6 @@ static int clone_special_sections(struct elfs *e) { struct section *patched_sec; - if (create_fake_symbols(e->patched)) - return -1; - for_each_sec(e->patched, patched_sec) { if (is_special_section(patched_sec)) { if (clone_special_section(e, patched_sec)) @@ -1704,6 +1701,17 @@ int cmd_klp_diff(int argc, const char **argv) if (!e.out) return -1; + /* + * Special section fake symbols are needed so that individual special + * section entries can be extracted by clone_special_sections(). + * + * Note the fake symbols are also needed by clone_included_functions() + * because __WARN_printf() call sites add references to bug table + * entries in the calling functions. + */ + if (create_fake_symbols(e.patched)) + return -1; + if (clone_included_functions(&e)) return -1; 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); |