diff options
367 files changed, 3353 insertions, 2137 deletions
diff --git a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml index 3248595dc93c..f04870d84542 100644 --- a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml +++ b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml @@ -85,4 +85,5 @@ examples: <&pd IMX_SC_R_DSP_RAM>; mbox-names = "txdb0", "txdb1", "rxdb0", "rxdb1"; mboxes = <&lsio_mu13 2 0>, <&lsio_mu13 2 1>, <&lsio_mu13 3 0>, <&lsio_mu13 3 1>; + memory-region = <&dsp_reserved>; }; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml index 676ec42e1438..567a33a83dce 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml @@ -43,13 +43,9 @@ properties: dvdd-supply: description: DVdd voltage supply - items: - - const: dvdd avdd-supply: description: AVdd voltage supply - items: - - const: avdd adi,rejection-60-Hz-enable: description: | @@ -99,6 +95,9 @@ required: examples: - | spi0 { + #address-cells = <1>; + #size-cells = <0>; + adc@0 { compatible = "adi,ad7192"; reg = <0>; diff --git a/Documentation/devicetree/bindings/media/rc.yaml b/Documentation/devicetree/bindings/media/rc.yaml index 3d5c154fd230..9054555e6608 100644 --- a/Documentation/devicetree/bindings/media/rc.yaml +++ b/Documentation/devicetree/bindings/media/rc.yaml @@ -73,7 +73,6 @@ properties: - rc-genius-tvgo-a11mce - rc-gotview7135 - rc-hauppauge - - rc-hauppauge - rc-hisi-poplar - rc-hisi-tv-demo - rc-imon-mce diff --git a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml index 8a56a8526cef..a97482179cf5 100644 --- a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml @@ -37,7 +37,7 @@ properties: - description: exclusive PHY reset line - description: shared reset line between the PCIe PHY and PCIe controller - resets-names: + reset-names: items: - const: phy - const: pcie diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 6ba9d5365ff3..b89c88168d6a 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -954,11 +954,6 @@ When kbuild executes, the following steps are followed (roughly): From commandline LDFLAGS_MODULE shall be used (see kbuild.txt). - KBUILD_ARFLAGS Options for $(AR) when creating archives - - $(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic - mode) if this option is supported by $(AR). - KBUILD_LDS The linker script with full path. Assigned by the top-level Makefile. diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index d2ae799237fd..774a998dcf37 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -498,10 +498,11 @@ build. will be written containing all exported symbols that were not defined in the kernel. ---- 6.3 Symbols From Another External Module +6.3 Symbols From Another External Module +---------------------------------------- Sometimes, an external module uses exported symbols from - another external module. kbuild needs to have full knowledge of + another external module. Kbuild needs to have full knowledge of all symbols to avoid spitting out warnings about undefined symbols. Three solutions exist for this situation. @@ -521,7 +522,7 @@ build. The top-level kbuild file would then look like:: #./Kbuild (or ./Makefile): - obj-y := foo/ bar/ + obj-m := foo/ bar/ And executing:: diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index ab92e98c89c8..503393854e2e 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -16,16 +16,21 @@ the kernel may be unreproducible, and how to avoid them. Timestamps ---------- -The kernel embeds a timestamp in two places: +The kernel embeds timestamps in three places: * The version string exposed by ``uname()`` and included in ``/proc/version`` * File timestamps in the embedded initramfs -By default the timestamp is the current time. This must be overridden -using the `KBUILD_BUILD_TIMESTAMP`_ variable. If you are building -from a git commit, you could use its commit date. +* If enabled via ``CONFIG_IKHEADERS``, file timestamps of kernel + headers embedded in the kernel or respective module, + exposed via ``/sys/kernel/kheaders.tar.xz`` + +By default the timestamp is the current time and in the case of +``kheaders`` the various files' modification times. This must +be overridden using the `KBUILD_BUILD_TIMESTAMP`_ variable. +If you are building from a git commit, you could use its commit date. The kernel does *not* use the ``__DATE__`` and ``__TIME__`` macros, and enables warnings if they are used. If you incorporate external diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst index f51f92571e39..c1f7f75e5fd9 100644 --- a/Documentation/networking/device_drivers/index.rst +++ b/Documentation/networking/device_drivers/index.rst @@ -23,6 +23,7 @@ Contents: intel/ice google/gve mellanox/mlx5 + netronome/nfp pensando/ionic .. only:: subproject and html diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst index 67b6839d516b..13935896bee6 100644 --- a/Documentation/networking/device_drivers/pensando/ionic.rst +++ b/Documentation/networking/device_drivers/pensando/ionic.rst @@ -36,8 +36,10 @@ Support ======= For general Linux networking support, please use the netdev mailing list, which is monitored by Pensando personnel:: + netdev@vger.kernel.org For more specific support needs, please use the Pensando driver support email:: - drivers@pensando.io + + drivers@pensando.io diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index ce7e7a044e08..dc60b13fcd09 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -272,7 +272,7 @@ supported flags are: * MSG_DONTWAIT, i.e. non-blocking operation. recvmsg(2) -^^^^^^^^^ +^^^^^^^^^^ In most cases recvmsg(2) is needed if you want to extract more information than recvfrom(2) can provide. For example package priority and timestamp. The diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.txt index 9cb31c5e2dcd..9bdb7d5a3ba3 100644 --- a/Documentation/networking/net_dim.txt +++ b/Documentation/networking/net_dim.txt @@ -92,16 +92,16 @@ under some conditions. Part III: Registering a Network Device to DIM ============================================== -Net DIM API exposes the main function net_dim(struct net_dim *dim, -struct net_dim_sample end_sample). This function is the entry point to the Net +Net DIM API exposes the main function net_dim(struct dim *dim, +struct dim_sample end_sample). This function is the entry point to the Net DIM algorithm and has to be called every time the driver would like to check if it should change interrupt moderation parameters. The driver should provide two -data structures: struct net_dim and struct net_dim_sample. Struct net_dim +data structures: struct dim and struct dim_sample. Struct dim describes the state of DIM for a specific object (RX queue, TX queue, other queues, etc.). This includes the current selected profile, previous data samples, the callback function provided by the driver and more. -Struct net_dim_sample describes a data sample, which will be compared to the -data sample stored in struct net_dim in order to decide on the algorithm's next +Struct dim_sample describes a data sample, which will be compared to the +data sample stored in struct dim in order to decide on the algorithm's next step. The sample should include bytes, packets and interrupts, measured by the driver. @@ -110,9 +110,9 @@ main net_dim() function. The recommended method is to call net_dim() on each interrupt. Since Net DIM has a built-in moderation and it might decide to skip iterations under certain conditions, there is no need to moderate the net_dim() calls as well. As mentioned above, the driver needs to provide an object of type -struct net_dim to the net_dim() function call. It is advised for each entity -using Net DIM to hold a struct net_dim as part of its data structure and use it -as the main Net DIM API object. The struct net_dim_sample should hold the latest +struct dim to the net_dim() function call. It is advised for each entity +using Net DIM to hold a struct dim as part of its data structure and use it +as the main Net DIM API object. The struct dim_sample should hold the latest bytes, packets and interrupts count. No need to perform any calculations, just include the raw data. @@ -132,19 +132,19 @@ usage is not complete but it should make the outline of the usage clear. my_driver.c: -#include <linux/net_dim.h> +#include <linux/dim.h> /* Callback for net DIM to schedule on a decision to change moderation */ void my_driver_do_dim_work(struct work_struct *work) { - /* Get struct net_dim from struct work_struct */ - struct net_dim *dim = container_of(work, struct net_dim, - work); + /* Get struct dim from struct work_struct */ + struct dim *dim = container_of(work, struct dim, + work); /* Do interrupt moderation related stuff */ ... /* Signal net DIM work is done and it should move to next iteration */ - dim->state = NET_DIM_START_MEASURE; + dim->state = DIM_START_MEASURE; } /* My driver's interrupt handler */ @@ -152,13 +152,13 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...) { ... /* A struct to hold current measured data */ - struct net_dim_sample dim_sample; + struct dim_sample dim_sample; ... /* Initiate data sample struct with current data */ - net_dim_sample(my_entity->events, - my_entity->packets, - my_entity->bytes, - &dim_sample); + dim_update_sample(my_entity->events, + my_entity->packets, + my_entity->bytes, + &dim_sample); /* Call net DIM */ net_dim(&my_entity->dim, dim_sample); ... diff --git a/MAINTAINERS b/MAINTAINERS index 296de2b51c83..55199ef7fa74 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6112,7 +6112,10 @@ M: Gao Xiang <gaoxiang25@huawei.com> M: Chao Yu <yuchao0@huawei.com> L: linux-erofs@lists.ozlabs.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git +F: Documentation/filesystems/erofs.txt F: fs/erofs/ +F: include/trace/events/erofs.h ERRSEQ ERROR TRACKING INFRASTRUCTURE M: Jeff Layton <jlayton@kernel.org> @@ -9075,6 +9078,7 @@ F: security/keys/ KGDB / KDB /debug_core M: Jason Wessel <jason.wessel@windriver.com> M: Daniel Thompson <daniel.thompson@linaro.org> +R: Douglas Anderson <dianders@chromium.org> W: http://kgdb.wiki.kernel.org/ L: kgdb-bugreport@lists.sourceforge.net T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git @@ -206,24 +206,8 @@ ifndef KBUILD_CHECKSRC KBUILD_CHECKSRC = 0 endif -# Use make M=dir to specify directory of external module to build -# Old syntax make ... SUBDIRS=$PWD is still supported -# Setting the environment variable KBUILD_EXTMOD take precedence -ifdef SUBDIRS - $(warning ================= WARNING ================) - $(warning 'SUBDIRS' will be removed after Linux 5.3) - $(warning ) - $(warning If you are building an individual subdirectory) - $(warning in the kernel tree, you can do like this:) - $(warning $$ make path/to/dir/you/want/to/build/) - $(warning (Do not forget the trailing slash)) - $(warning ) - $(warning If you are building an external module,) - $(warning Please use 'M=' or 'KBUILD_EXTMOD' instead) - $(warning ==========================================) - KBUILD_EXTMOD ?= $(SUBDIRS) -endif - +# Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the +# directory of external module to build. Setting M= takes precedence. ifeq ("$(origin M)", "command line") KBUILD_EXTMOD := $(M) endif @@ -498,7 +482,6 @@ export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL -export KBUILD_ARFLAGS # Files to ignore in find ... statements @@ -914,9 +897,6 @@ ifdef CONFIG_RETPOLINE KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif -# use the deterministic mode of AR if available -KBUILD_ARFLAGS := $(call ar-option,D) - include scripts/Makefile.kasan include scripts/Makefile.extrawarn include scripts/Makefile.ubsan diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h deleted file mode 100644 index ec154e719b11..000000000000 --- a/arch/arm/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile index 7ed28982c4c3..c32d04713ba0 100644 --- a/arch/arm/xen/Makefile +++ b/arch/arm/xen/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o -obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c deleted file mode 100644 index d687a73044bf..000000000000 --- a/arch/arm/xen/efi.c +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2015, Linaro Limited, Shannon Zhao - */ - -#include <linux/efi.h> -#include <xen/xen-ops.h> -#include <asm/xen/xen-ops.h> - -/* Set XEN EFI runtime services function pointers. Other fields of struct efi, - * e.g. efi.systab, will be set like normal EFI. - */ -void __init xen_efi_runtime_setup(void) -{ - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; -} -EXPORT_SYMBOL_GPL(xen_efi_runtime_setup); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 1e57692552d9..dd6804a64f1a 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -15,7 +15,6 @@ #include <xen/xen-ops.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> -#include <asm/xen/xen-ops.h> #include <asm/system_misc.h> #include <asm/efi.h> #include <linux/interrupt.h> @@ -437,7 +436,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); -EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw); EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist); EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 2b2c208408bb..38fa917c8585 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) for_each_memblock(memory, reg) { if (reg->base < (phys_addr_t)0xffffffff) { - flags |= __GFP_DMA; + if (IS_ENABLED(CONFIG_ZONE_DMA32)) + flags |= __GFP_DMA32; + else + flags |= __GFP_DMA; break; } } diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 86825aa20852..97f21cc66657 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,30 +47,6 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) -/** - * hyp_alternate_select - Generates patchable code sequences that are - * used to switch between two implementations of a function, depending - * on the availability of a feature. - * - * @fname: a symbol name that will be defined as a function returning a - * function pointer whose type will match @orig and @alt - * @orig: A pointer to the default function, as returned by @fname when - * @cond doesn't hold - * @alt: A pointer to the alternate function, as returned by @fname - * when @cond holds - * @cond: a CPU feature (as described in asm/cpufeature.h) - */ -#define hyp_alternate_select(fname, orig, alt, cond) \ -typeof(orig) * __hyp_text fname(void) \ -{ \ - typeof(alt) *val = orig; \ - asm volatile(ALTERNATIVE("nop \n", \ - "mov %0, %1 \n", \ - cond) \ - : "+r" (val) : "r" (alt)); \ - return val; \ -} - int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h deleted file mode 100644 index e6e784051932..000000000000 --- a/arch/arm64/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index bd978ad71936..3d3815020e36 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -229,20 +229,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) } } -static bool __hyp_text __true_value(void) -{ - return true; -} - -static bool __hyp_text __false_value(void) -{ - return false; -} - -static hyp_alternate_select(__check_arm_834220, - __false_value, __true_value, - ARM64_WORKAROUND_834220); - static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) { u64 par, tmp; @@ -298,7 +284,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) * resolve the IPA using the AT instruction. */ if (!(esr & ESR_ELx_S1PTW) && - (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + (cpus_have_const_cap(ARM64_WORKAROUND_834220) || + (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; } else { diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index c466060b76d6..eb0efc5557f3 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -67,10 +67,14 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, isb(); } -static hyp_alternate_select(__tlb_switch_to_guest, - __tlb_switch_to_guest_nvhe, - __tlb_switch_to_guest_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_guest_vhe(kvm, cxt); + else + __tlb_switch_to_guest_nvhe(kvm, cxt); +} static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, struct tlb_inv_context *cxt) @@ -98,10 +102,14 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, write_sysreg(0, vttbr_el2); } -static hyp_alternate_select(__tlb_switch_to_host, - __tlb_switch_to_host_nvhe, - __tlb_switch_to_host_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_host_vhe(kvm, cxt); + else + __tlb_switch_to_host_nvhe(kvm, cxt); +} void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { @@ -111,7 +119,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); /* * We could do so much better if we had the VA as well. @@ -154,7 +162,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) if (!has_vhe() && icache_is_vpipt()) __flush_icache_all(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) @@ -165,13 +173,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) @@ -180,13 +188,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct tlb_inv_context cxt; /* Switch to requested VMID */ - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalle1); dsb(nsh); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile index a4fc65f3928d..b66215e8658e 100644 --- a/arch/arm64/xen/Makefile +++ b/arch/arm64/xen/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o) obj-y := xen-arm.o hypercall.o -obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o) diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi index 63a9f33aa43e..5cfc9d347826 100644 --- a/arch/mips/boot/dts/qca/ar9331.dtsi +++ b/arch/mips/boot/dts/qca/ar9331.dtsi @@ -99,7 +99,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar7240-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index af44b35d79a1..b4328b3b5288 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -160,7 +160,6 @@ void __init prom_meminit(void) void __init prom_free_prom_memory(void) { - unsigned long addr; int i; if (prom_flags & PROM_FLAG_DONT_FREE_TEMP) diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h index cbdc14b77435..adab7b54c3b4 100644 --- a/arch/mips/include/asm/octeon/cvmx-ipd.h +++ b/arch/mips/include/asm/octeon/cvmx-ipd.h @@ -36,6 +36,7 @@ #include <asm/octeon/octeon-feature.h> #include <asm/octeon/cvmx-ipd-defs.h> +#include <asm/octeon/cvmx-pip-defs.h> enum cvmx_ipd_mode { CVMX_IPD_OPC_MODE_STT = 0LL, /* All blocks DRAM, not cached in L2 */ diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 071053ece677..5d70babfc9ee 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -52,6 +52,7 @@ # endif #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 /* whitelists for checksyscalls */ #define __IGNORE_fadvise64_64 diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index fa62cd1dff93..6a7afe7ef4d3 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -24,7 +24,8 @@ static char r4kwar[] __initdata = static char daddiwar[] __initdata = "Enable CPU_DADDI_WORKAROUNDS to rectify."; -static inline void align_mod(const int align, const int mod) +static __always_inline __init +void align_mod(const int align, const int mod) { asm volatile( ".set push\n\t" @@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod) : "n"(align), "n"(mod)); } -static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, - const int align, const int mod) +static __always_inline __init +void mult_sh_align_mod(long *v1, long *v2, long *w, + const int align, const int mod) { unsigned long flags; int m1, m2; @@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, *w = lw; } -static inline void check_mult_sh(void) +static __always_inline __init void check_mult_sh(void) { long v1[8], v2[8], w[8]; int bug, fix, i; @@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs) exception_exit(prev_state); } -static inline void check_daddi(void) +static __init void check_daddi(void) { extern asmlinkage void handle_daddi_ov(void); unsigned long flags; @@ -242,7 +244,7 @@ static inline void check_daddi(void) int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1; -static inline void check_daddiu(void) +static __init void check_daddiu(void) { long v, w, tmp; diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index b8249c233754..5eec13b8d222 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) return; } + if (start < PHYS_OFFSET) + return; + memblock_add(start, size); /* Reserve any memory except the ordinary RAM ranges. */ switch (type) { @@ -321,7 +324,7 @@ static void __init bootmem_init(void) * Reserve any memory between the start of RAM and PHYS_OFFSET */ if (ramstart > PHYS_OFFSET) - memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET); + memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET); if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) { pr_info("Wasting %lu bytes for tracking %lu unused pages\n", diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index b0e25e913bdb..3f16f3823031 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len, save_static_function(sys_fork); save_static_function(sys_clone); +save_static_function(sys_clone3); SYSCALL_DEFINE1(set_thread_area, unsigned long, addr) { diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c9c879ec9b6d..e7c5ab38e403 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -373,4 +373,4 @@ 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick 434 n32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n32 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index bbce9159caa1..13cd66581f3b 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -349,4 +349,4 @@ 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick 434 n64 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n64 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 9653591428ec..353539ea4140 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -422,4 +422,4 @@ 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick 434 o32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 o32 clone3 __sys_clone3 diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c index 4abb92e0fc39..4254ac4ec616 100644 --- a/arch/mips/loongson64/common/mem.c +++ b/arch/mips/loongson64/common/mem.c @@ -3,6 +3,7 @@ */ #include <linux/fs.h> #include <linux/fcntl.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <asm/bootinfo.h> @@ -64,24 +65,22 @@ void __init prom_init_memory(void) node_id = loongson_memmap->map[i].node_id; mem_type = loongson_memmap->map[i].mem_type; - if (node_id == 0) { - switch (mem_type) { - case SYSTEM_RAM_LOW: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_HIGH: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_RESERVED: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RESERVED); - break; - } + if (node_id != 0) + continue; + + switch (mem_type) { + case SYSTEM_RAM_LOW: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_HIGH: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_RESERVED: + memblock_reserve(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; } } } diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c index ffefc1cb2612..98c3a7feb10f 100644 --- a/arch/mips/loongson64/common/serial.c +++ b/arch/mips/loongson64/common/serial.c @@ -110,7 +110,7 @@ static int __init serial_init(void) } module_init(serial_init); -static void __init serial_exit(void) +static void __exit serial_exit(void) { platform_device_unregister(&uart8250_device); } diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 414e97de5dc0..8f20d2cb3767 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -142,8 +142,6 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; @@ -156,16 +154,12 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", (u32)node_id, mem_type, mem_start, mem_size); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RESERVED); memblock_reserve(((node_id << 44) + mem_start), mem_size << 20); break; @@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node) NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; - free_bootmem_with_active_regions(node, end_pfn); - if (node == 0) { /* kernel end address */ unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end)); @@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node) memblock_reserve((node_addrspace_offset | 0xfe000000), 32 << 20); } - - sparse_memory_present_with_active_regions(node); } static __init void prom_meminit(void) @@ -227,6 +217,7 @@ static __init void prom_meminit(void) cpumask_clear(&__node_data[(node)]->cpumask); } } + memblocks_present(); max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) { diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c index dfb527961a27..800a21b8b8b0 100644 --- a/arch/mips/pmcs-msp71xx/msp_prom.c +++ b/arch/mips/pmcs-msp71xx/msp_prom.c @@ -61,6 +61,7 @@ int init_debug = 1; /* memory blocks */ struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS]; +#define MAX_PROM_MEM 5 static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata; static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata; static unsigned int nr_prom_mem __initdata; @@ -358,7 +359,7 @@ void __init prom_meminit(void) p++; if (type == BOOT_MEM_ROM_DATA) { - if (nr_prom_mem >= 5) { + if (nr_prom_mem >= MAX_PROM_MEM) { pr_err("Too many ROM DATA regions"); continue; } @@ -377,7 +378,6 @@ void __init prom_free_prom_memory(void) char *ptr; int len = 0; int i; - unsigned long addr; /* * preserve environment variables and command line from pmon/bbload diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 69cfa0a5339e..807f0f782f75 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -59,7 +59,7 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif endif diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c deleted file mode 100644 index e8243c7fd5b5..000000000000 --- a/arch/mips/vdso/gettimeofday.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2015 Imagination Technologies - * Author: Alex Smith <alex.smith@imgtec.com> - */ - -#include "vdso.h" - -#include <linux/compiler.h> -#include <linux/time.h> - -#include <asm/clocksource.h> -#include <asm/io.h> -#include <asm/unistd.h> -#include <asm/vdso.h> - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -static __always_inline long gettimeofday_fallback(struct timeval *_tv, - struct timezone *_tz) -{ - register struct timezone *tz asm("a1") = _tz; - register struct timeval *tv asm("a0") = _tv; - register long ret asm("v0"); - register long nr asm("v0") = __NR_gettimeofday; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (tv), "r" (tz), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -#endif - -static __always_inline long clock_gettime_fallback(clockid_t _clkid, - struct timespec *_ts) -{ - register struct timespec *ts asm("a1") = _ts; - register clockid_t clkid asm("a0") = _clkid; - register long ret asm("v0"); - register long nr asm("v0") = __NR_clock_gettime; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (clkid), "r" (ts), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -static __always_inline int do_realtime_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - } while (vdso_data_read_retry(data, start_seq)); - - return 0; -} - -static __always_inline int do_monotonic_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - timespec_add_ns(ts, to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_CSRC_R4K - -static __always_inline u64 read_r4k_count(void) -{ - unsigned int count; - - __asm__ __volatile__( - " .set push\n" - " .set mips32r2\n" - " rdhwr %0, $2\n" - " .set pop\n" - : "=r" (count)); - - return count; -} - -#endif - -#ifdef CONFIG_CLKSRC_MIPS_GIC - -static __always_inline u64 read_gic_count(const union mips_vdso_data *data) -{ - void __iomem *gic = get_gic(data); - u32 hi, hi2, lo; - - do { - hi = __raw_readl(gic + sizeof(lo)); - lo = __raw_readl(gic); - hi2 = __raw_readl(gic + sizeof(lo)); - } while (hi2 != hi); - - return (((u64)hi) << 32) + lo; -} - -#endif - -static __always_inline u64 get_ns(const union mips_vdso_data *data) -{ - u64 cycle_now, delta, nsec; - - switch (data->clock_mode) { -#ifdef CONFIG_CSRC_R4K - case VDSO_CLOCK_R4K: - cycle_now = read_r4k_count(); - break; -#endif -#ifdef CONFIG_CLKSRC_MIPS_GIC - case VDSO_CLOCK_GIC: - cycle_now = read_gic_count(data); - break; -#endif - default: - return 0; - } - - delta = (cycle_now - data->cs_cycle_last) & data->cs_mask; - - nsec = (delta * data->cs_mult) + data->xtime_nsec; - nsec >>= data->cs_shift; - - return nsec; -} - -static __always_inline int do_realtime(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_nsec = 0; - timespec_add_ns(ts, ns); - - return 0; -} - -static __always_inline int do_monotonic(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, ns + to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -/* - * This is behind the ifdef so that we don't provide the symbol when there's no - * possibility of there being a usable clocksource, because there's nothing we - * can do without it. When libc fails the symbol lookup it should fall back on - * the standard syscall path. - */ -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) -{ - const union mips_vdso_data *data = get_vdso_data(); - struct timespec ts; - int ret; - - ret = do_realtime(&ts, data); - if (ret) - return gettimeofday_fallback(tv, tz); - - if (tv) { - tv->tv_sec = ts.tv_sec; - tv->tv_usec = ts.tv_nsec / 1000; - } - - if (tz) { - tz->tz_minuteswest = data->tz_minuteswest; - tz->tz_dsttime = data->tz_dsttime; - } - - return 0; -} - -#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ - -int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) -{ - const union mips_vdso_data *data = get_vdso_data(); - int ret = -1; - - switch (clkid) { - case CLOCK_REALTIME_COARSE: - ret = do_realtime_coarse(ts, data); - break; - case CLOCK_MONOTONIC_COARSE: - ret = do_monotonic_coarse(ts, data); - break; - case CLOCK_REALTIME: - ret = do_realtime(ts, data); - break; - case CLOCK_MONOTONIC: - ret = do_monotonic(ts, data); - break; - default: - break; - } - - if (ret) - ret = clock_gettime_fallback(clkid, ts); - - return ret; -} diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6841bd52738b..dfbd7f22eef5 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -50,7 +50,7 @@ endif BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc -BOOTARFLAGS := -cr$(KBUILD_ARFLAGS) +BOOTARFLAGS := -crD ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d7fcdfa7fee4..ec2547cc5ecb 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -36,8 +36,8 @@ #include "book3s.h" #include "trace.h" -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ /* #define EXIT_DEBUG */ @@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "pthru_all", VCPU_STAT(pthru_all) }, { "pthru_host", VCPU_STAT(pthru_host) }, { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, - { "largepages_2M", VM_STAT(num_2M_pages) }, - { "largepages_1G", VM_STAT(num_1G_pages) }, + { "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) }, + { "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) }, { NULL } }; diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 5a02b7d50940..9c992a88d858 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -22,6 +22,7 @@ #define REG_L __REG_SEL(ld, lw) #define REG_S __REG_SEL(sd, sw) +#define REG_SC __REG_SEL(sc.d, sc.w) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index da7aa88113c2..2d592da1e776 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -98,7 +98,26 @@ _save_context: */ .macro RESTORE_ALL REG_L a0, PT_SSTATUS(sp) - REG_L a2, PT_SEPC(sp) + /* + * The current load reservation is effectively part of the processor's + * state, in the sense that load reservations cannot be shared between + * different hart contexts. We can't actually save and restore a load + * reservation, so instead here we clear any existing reservation -- + * it's always legal for implementations to clear load reservations at + * any point (as long as the forward progress guarantee is kept, but + * we'll ignore that here). + * + * Dangling load reservations can be the result of taking a trap in the + * middle of an LR/SC sequence, but can also be the result of a taken + * forward branch around an SC -- which is how we implement CAS. As a + * result we need to clear reservations between the last CAS and the + * jump back to the new context. While it is unlikely the store + * completes, implementations are allowed to expand reservations to be + * arbitrarily large. + */ + REG_L a2, PT_SEPC(sp) + REG_SC x0, a2, PT_SEPC(sp) + csrw CSR_SSTATUS, a0 csrw CSR_SEPC, a2 diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f0ba71304b6e..83f7d12042fb 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/sizes.h> #include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> @@ -82,6 +83,8 @@ disable: } #endif /* CONFIG_BLK_DEV_INITRD */ +static phys_addr_t dtb_early_pa __initdata; + void __init setup_bootmem(void) { struct memblock_region *reg; @@ -117,7 +120,12 @@ void __init setup_bootmem(void) setup_initrd(); #endif /* CONFIG_BLK_DEV_INITRD */ - early_init_fdt_reserve_self(); + /* + * Avoid using early_init_fdt_reserve_self() since __pa() does + * not work for DTB pointers that are fixmap addresses + */ + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + early_init_fdt_scan_reserved_mem(); memblock_allow_resize(); memblock_dump_all(); @@ -393,6 +401,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) /* Save pointer to DTB for early FDT parsing */ dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK); + /* Save physical address for memblock reservation */ + dtb_early_pa = dtb_pa; } static void __init setup_vm_final(void) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 347f48702edb..38d64030aacf 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -69,12 +70,13 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -370,6 +372,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y @@ -424,6 +427,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +439,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_NETDEVICES=y CONFIG_BONDING=m @@ -489,6 +494,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -538,15 +544,16 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -580,6 +587,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -589,6 +598,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -648,12 +658,15 @@ CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -664,10 +677,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -739,7 +748,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8514b8b9500f..25f799849582 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_NUMA=y # CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y @@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -727,7 +735,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index be09a208b608..20c51e5d9353 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -# CONFIG_DIMLIB is not set +CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index d3f09526ee19..61467b9eecc7 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg") #undef __ATOMIC_OP #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier) \ -static inline void op_name(op_type val, op_type *ptr) \ +static __always_inline void op_name(op_type val, op_type *ptr) \ { \ asm volatile( \ op_string " %[ptr],%[val]\n" \ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index b8833ac983fa..eb7eed43e780 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index a092f63aac6a..c0f3bfeddcbe 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -171,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; * * Returns 1 if @func is available for @opcode, 0 otherwise */ -static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) mask; diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index ceeb552d3472..819803a97c2b 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n"); CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \ CPU_MF_INT_SF_LSDA) +#define CPU_MF_SF_RIBM_NOTAV 0x1 /* Sampling unavailable */ + /* CPU measurement facility support */ static inline int cpum_cf_avail(void) { @@ -69,7 +71,8 @@ struct hws_qsi_info_block { /* Bit(s) */ unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/ unsigned long tear; /* 24-31: TEAR contents */ unsigned long dear; /* 32-39: DEAR contents */ - unsigned int rsvrd0; /* 40-43: reserved */ + unsigned int rsvrd0:24; /* 40-42: reserved */ + unsigned int ribm:8; /* 43: Reserved by IBM */ unsigned int cpu_speed; /* 44-47: CPU speed */ unsigned long long rsvrd1; /* 48-55: reserved */ unsigned long long rsvrd2; /* 56-63: reserved */ @@ -220,7 +223,8 @@ enum stcctm_ctr_set { MT_DIAG = 5, MT_DIAG_CLEARING = 9, /* clears loss-of-MT-ctr-data alert */ }; -static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) + +static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) { int cc; diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bb59dd964590..de8f0bf5f238 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -12,8 +12,6 @@ #include <asm/page.h> #include <asm/pgtable.h> - -#define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range free_pgd_range #define hugepages_supported() (MACHINE_HAS_EDAT1) @@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +static inline bool is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + return false; +} + /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index e548ec1ec12c..39f747d63758 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -20,7 +20,7 @@ * We use a brcl 0,2 instruction for jump labels at compile time so it * can be easily distinguished from a hotpatch generated instruction. */ -static inline bool arch_static_branch(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table,\"aw\"\n" @@ -34,7 +34,7 @@ label: return true; } -static inline bool arch_static_branch_jump(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 36c578c0ff96..5ff98d76a66c 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -997,9 +997,9 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static inline void __ptep_ipte(unsigned long address, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, + unsigned long opt, unsigned long asce, + int local) { unsigned long pto = (unsigned long) ptep; @@ -1020,8 +1020,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep, : [r1] "a" (pto), [m4] "i" (local) : "memory"); } -static inline void __ptep_ipte_range(unsigned long address, int nr, - pte_t *ptep, int local) +static __always_inline void __ptep_ipte_range(unsigned long address, int nr, + pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; @@ -1269,7 +1269,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_kernel(pmd, address) pte_offset(pmd, address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_unmap(pte) do { } while (0) + +static inline void pte_unmap(pte_t *pte) { } static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { @@ -1435,9 +1436,9 @@ static inline void __pmdp_csp(pmd_t *pmdp) #define IDTE_NODAT 0x1000 #define IDTE_GUEST_ASCE 0x2000 -static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, + unsigned long opt, unsigned long asce, + int local) { unsigned long sto; @@ -1461,9 +1462,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, } } -static inline void __pudp_idte(unsigned long addr, pud_t *pudp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp, + unsigned long opt, unsigned long asce, + int local) { unsigned long r3o; diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 78e8a888306d..e3f238e8c611 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -111,7 +111,7 @@ struct qib { /* private: */ u8 res[88]; /* public: */ - u8 parm[QDIO_MAX_BUFFERS_PER_Q]; + u8 parm[128]; } __attribute__ ((packed, aligned(256))); /** diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 5f1fd1581330..2654e348801a 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, debug_sprintf_event(cf_diag_dbg, 6, "%s ctrset %d ctrset_size %zu cfvn %d csvn %d" - " need %zd rc:%d\n", + " need %zd rc %d\n", __func__, ctrset, ctrset_size, cpuhw->info.cfvn, cpuhw->info.csvn, need, rc); return need; @@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags) int err = 0; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d flags %#x cpuhw:%p\n", + "%s event %p cpu %d flags %#x cpuhw %p\n", __func__, event, event->cpu, flags, cpuhw); if (cpuhw->flags & PMU_F_IN_USE) { diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 544a02e944c6..3d8b12a9a6ff 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -803,6 +803,12 @@ static int __hw_perf_event_init(struct perf_event *event) goto out; } + if (si.ribm & CPU_MF_SF_RIBM_NOTAV) { + pr_warn("CPU Measurement Facility sampling is temporarily not available\n"); + err = -EBUSY; + goto out; + } + /* Always enable basic sampling */ SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE; @@ -895,7 +901,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event) /* Check online status of the CPU to which the event is pinned */ if (event->cpu >= 0 && !cpu_online(event->cpu)) - return -ENODEV; + return -ENODEV; /* Force reset of idle/hv excludes regardless of what the * user requested. diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f6db0f1bc867..d047e846e1b9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static inline void __insn32_query(unsigned int opcode, u8 query[32]) +static __always_inline void __insn32_query(unsigned int opcode, u8 *query) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) query; @@ -340,9 +340,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32]) asm volatile( /* Parameter regs are ignored */ " .insn rrf,%[opc] << 16,2,4,6,0\n" - : "=m" (*query) + : : "d" (r0), "a" (r1), [opc] "i" (opcode) - : "cc"); + : "cc", "memory"); } #define INSN_SORTL 0xb938 diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..e585a62d6530 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp) /* * Call Logical Processor with c=0, the give constant lps and an lpcb request. */ -static inline int clp_req(void *data, unsigned int lps) +static __always_inline int clp_req(void *data, unsigned int lps) { struct { u8 _[CLP_BLK_SIZE]; } *req = data; u64 ignored; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 23edf56cf577..50eb430b0ad8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -219,13 +219,6 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) -/* - * The mask used to denote special SPTEs, which can be either MMIO SPTEs or - * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting - * with the SVE bit in EPT PTEs. - */ -#define SPTE_SPECIAL_MASK (1ULL << 62) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 63316036f85a..9c5029cf6f3f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -485,6 +485,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); @@ -618,16 +619,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, */ case 0x1f: case 0xb: { - int i, level_type; + int i; - /* read more entries until level_type is zero */ - for (i = 1; ; ++i) { + /* + * We filled in entry[0] for CPUID(EAX=<function>, + * ECX=00H) above. If its level type (ECX[15:8]) is + * zero, then the leaf is unimplemented, and we're + * done. Otherwise, continue to populate entries + * until the level type (ECX[15:8]) of the previously + * added entry is zero. + */ + for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { if (*nent >= maxnent) goto out; - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; do_host_cpuid(&entry[i], function, i); ++*nent; } @@ -969,53 +974,66 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. + * If the basic or extended CPUID leaf requested is higher than the + * maximum supported basic or extended leaf, respectively, then it is + * out of range. */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) +static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) { - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); + struct kvm_cpuid_entry2 *max; + + max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + return max && function <= max->eax; } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) { u32 function = *eax, index = *ecx; - struct kvm_cpuid_entry2 *best; - bool entry_found = true; - - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) { - entry_found = false; - if (!check_limit) - goto out; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *max; + bool found; - best = check_cpuid_limit(vcpu, function, index); + entry = kvm_find_cpuid_entry(vcpu, function, index); + found = entry; + /* + * Intel CPUID semantics treats any query for an out-of-range + * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were + * requested. AMD CPUID semantics returns all zeroes for any + * undefined leaf, whether or not the leaf is in range. + */ + if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && + !cpuid_function_in_range(vcpu, function)) { + max = kvm_find_cpuid_entry(vcpu, 0, 0); + if (max) { + function = max->eax; + entry = kvm_find_cpuid_entry(vcpu, function, index); + } } - -out: - if (best) { - *eax = best->eax; - *ebx = best->ebx; - *ecx = best->ecx; - *edx = best->edx; - } else + if (entry) { + *eax = entry->eax; + *ebx = entry->ebx; + *ecx = entry->ecx; + *edx = entry->edx; + } else { *eax = *ebx = *ecx = *edx = 0; - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found); - return entry_found; + /* + * When leaf 0BH or 1FH is defined, CL is pass-through + * and EDX is always the x2APIC ID, even for undefined + * subleaves. Index 1 will exist iff the leaf is + * implemented, so we pass through CL iff leaf 1 + * exists. EDX can be copied from any existing index. + */ + if (function == 0xb || function == 0x1f) { + entry = kvm_find_cpuid_entry(vcpu, function, 1); + if (entry) { + *ecx = index & 0xff; + *edx = entry->edx; + } + } + } + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); + return found; } EXPORT_SYMBOL_GPL(kvm_cpuid); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3a3a6854dcca..87b0fcc23ef8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -66,9 +66,10 @@ #define X2APIC_BROADCAST 0xFFFFFFFFul static bool lapic_timer_advance_dynamic __read_mostly; -#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 -#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000 -#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 +#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_NS_INIT 1000 +#define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -1504,8 +1505,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } - if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX)) - timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) + timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } @@ -2302,7 +2303,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5269aa057dfa..24c23c66b226 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -83,7 +83,17 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 #define PT_FIRST_AVAIL_BITS_SHIFT 10 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 +#define PT64_SECOND_AVAIL_BITS_SHIFT 54 + +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. + */ +#define SPTE_SPECIAL_MASK (3ULL << 52) +#define SPTE_AD_ENABLED_MASK (0ULL << 52) +#define SPTE_AD_DISABLED_MASK (1ULL << 52) +#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52) +#define SPTE_MMIO_MASK (3ULL << 52) #define PT64_LEVEL_BITS 9 @@ -219,12 +229,11 @@ static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; /* - * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. - * Non-present SPTEs with shadow_acc_track_value set are in place for access - * tracking. + * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK; + * shadow_acc_track_mask is the set of bits to be cleared in non-accessed + * pages. */ static u64 __read_mostly shadow_acc_track_mask; -static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; /* * The mask/shift to use for saving the original R/X bits when marking the PTE @@ -304,7 +313,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); - shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; + shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; shadow_mmio_access_mask = access_mask; } @@ -320,10 +329,27 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) return sp->role.ad_disabled; } +static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +{ + /* + * When using the EPT page-modification log, the GPAs in the log + * would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages. This also bypasses + * PML, since writes now result in a vmexit. + */ + return vcpu->arch.mmu == &vcpu->arch.guest_mmu; +} + static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(is_mmio_spte(spte)); - return !(spte & shadow_acc_track_value); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK; +} + +static inline bool spte_ad_need_write_protect(u64 spte) +{ + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -461,7 +487,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); - BUG_ON(acc_track_mask & shadow_acc_track_value); + BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -1589,16 +1615,16 @@ static bool spte_clear_dirty(u64 *sptep) rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; - return mmu_spte_update(sptep, spte); } -static bool wrprot_ad_disabled_spte(u64 *sptep) +static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable) + if (was_writable && !spte_ad_enabled(*sptep)) kvm_set_pfn_dirty(spte_to_pfn(*sptep)); return was_writable; @@ -1617,10 +1643,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_clear_dirty(sptep); + if (spte_ad_need_write_protect(*sptep)) + flush |= spte_wrprot_for_clear_dirty(sptep); else - flush |= wrprot_ad_disabled_spte(sptep); + flush |= spte_clear_dirty(sptep); return flush; } @@ -1631,6 +1657,11 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); + /* + * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * do not bother adding back write access to pages marked + * SPTE_AD_WRPROT_ONLY_MASK. + */ spte |= shadow_dirty_mask; return mmu_spte_update(sptep, spte); @@ -2622,7 +2653,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; else spte |= shadow_accessed_mask; @@ -2968,7 +2999,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, sp = page_header(__pa(sptep)); if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; + else if (kvm_vcpu_ad_need_write_protect(vcpu)) + spte |= SPTE_AD_WRPROT_ONLY_MASK; /* * For the EPT case, shadow_present_mask is 0 if hardware diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 41abc62c9a8a..e76eb4f07f6c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, /* VM-entry exception error code */ if (CC(has_error_code && - vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))) + vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 4dea0e0e7e39..3e9c059099e9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (!pmu->version) return; + perf_get_x86_pmu_capability(&x86_pmu); + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) } else { pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d4575ffb3cec..e7970a2e8eae 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) struct page *page; unsigned int i; + if (!boot_cpu_has_bug(X86_BUG_L1TF)) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; @@ -7995,12 +8000,10 @@ static int __init vmx_init(void) * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ - if (boot_cpu_has(X86_BUG_L1TF)) { - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; } #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ed07d8d2caa..661e2bf38526 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -212,7 +212,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - if (cr4 & CR4_RESERVED_BITS) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + return -EINVAL; + + return 0; +} + +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + + if (kvm_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -1161,13 +1169,6 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, - MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19, - MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21, - MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23, - MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25, - MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27, - MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29, - MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, @@ -1177,13 +1178,6 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, - MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19, - MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21, - MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23, - MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25, - MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27, - MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29, - MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31, }; static unsigned num_msrs_to_save; @@ -5097,13 +5091,14 @@ out: static void kvm_init_msr_list(void) { + struct x86_pmu_capability x86_pmu; u32 dummy[2]; unsigned i, j; BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, "Please update the fixed PMCs in msrs_to_save[]"); - BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32, - "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]"); + + perf_get_x86_pmu_capability(&x86_pmu); for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) @@ -5145,6 +5140,15 @@ static void kvm_init_msr_list(void) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; } default: break; @@ -8714,10 +8718,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8736,7 +8736,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return -EINVAL; } - return 0; + return kvm_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 0d3365cb64de..a04551ee5568 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void) return NULL; /* Here we know that Xen runs on EFI platform. */ - - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; + xen_efi_runtime_setup(); efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/block/blk-mq.c b/block/blk-mq.c index 6e3b15f70cd7..ec791156e9cc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1992,10 +1992,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) /* bypass scheduler for flush rq */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); - } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) { + } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || + !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. + * + * Use normal plugging if this disk is slow HDD, as sequential + * IO may benefit a lot from plug merging. */ unsigned int request_count = plug->rq_count; struct request *last = NULL; @@ -2012,6 +2016,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } blk_add_rq_to_plug(plug, rq); + } else if (q->elevator) { + blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { /* * We do limited plugging. If the bio can be merged, do that. @@ -2035,8 +2041,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_try_issue_directly(data.hctx, same_queue_rq, &cookie); } - } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator && - !data.hctx->dispatch_busy)) { + } else if ((q->nr_hw_queues > 1 && is_sync) || + !data.hctx->dispatch_busy) { blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { blk_mq_sched_insert_request(rq, false, true, true); diff --git a/block/sed-opal.c b/block/sed-opal.c index 4e95a9792162..b4c761973ac1 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -129,7 +129,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { { 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 }, /* tables */ - [OPAL_TABLE_TABLE] + [OPAL_TABLE_TABLE] = { 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 }, [OPAL_LOCKINGRANGE_GLOBAL] = { 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 }, @@ -372,8 +372,8 @@ static void check_geometry(struct opal_dev *dev, const void *data) { const struct d0_geometry_features *geo = data; - dev->align = geo->alignment_granularity; - dev->lowest_lba = geo->lowest_aligned_lba; + dev->align = be64_to_cpu(geo->alignment_granularity); + dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba); } static int execute_step(struct opal_dev *dev, diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1410fa893653..f6f77eaa7217 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -994,6 +994,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); + if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) { + /* In case of direct I/O, match underlying block size */ + unsigned short bsize = bdev_logical_block_size( + inode->i_sb->s_bdev); + + blk_queue_logical_block_size(lo->lo_queue, bsize); + blk_queue_physical_block_size(lo->lo_queue, bsize); + blk_queue_io_min(lo->lo_queue, bsize); + } + loop_update_rotational(lo); loop_update_dio(lo); set_capacity(lo->lo_disk, size); diff --git a/drivers/char/random.c b/drivers/char/random.c index c2f7de9dc543..de434feb873a 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2520,4 +2520,4 @@ void add_bootloader_randomness(const void *buf, unsigned int size) else add_device_randomness(buf, size); } -EXPORT_SYMBOL_GPL(add_bootloader_randomness);
\ No newline at end of file +EXPORT_SYMBOL_GPL(add_bootloader_randomness); diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index d8c2bd4391d0..11ff701ff4bb 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -25,7 +25,9 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) struct clock_event_device *clkevt = &to->clkevt; - of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) : + if (of_irq->percpu) + free_percpu_irq(of_irq->irq, clkevt); + else free_irq(of_irq->irq, clkevt); } diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 42e2c1f57152..00962a659009 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -54,7 +54,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \ amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \ amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \ - amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o + amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index eba42c752bca..82155ac3288a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -189,7 +189,7 @@ static int acp_hw_init(void *handle) u32 val = 0; u32 count = 0; struct device *dev; - struct i2s_platform_data *i2s_pdata; + struct i2s_platform_data *i2s_pdata = NULL; struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -231,20 +231,21 @@ static int acp_hw_init(void *handle) adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell), GFP_KERNEL); - if (adev->acp.acp_cell == NULL) - return -ENOMEM; + if (adev->acp.acp_cell == NULL) { + r = -ENOMEM; + goto failure; + } adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL); if (adev->acp.acp_res == NULL) { - kfree(adev->acp.acp_cell); - return -ENOMEM; + r = -ENOMEM; + goto failure; } i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL); if (i2s_pdata == NULL) { - kfree(adev->acp.acp_res); - kfree(adev->acp.acp_cell); - return -ENOMEM; + r = -ENOMEM; + goto failure; } switch (adev->asic_type) { @@ -341,14 +342,14 @@ static int acp_hw_init(void *handle) r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, ACP_DEVS); if (r) - return r; + goto failure; for (i = 0; i < ACP_DEVS ; i++) { dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i); r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev); if (r) { dev_err(dev, "Failed to add dev to genpd\n"); - return r; + goto failure; } } @@ -367,7 +368,8 @@ static int acp_hw_init(void *handle) break; if (--count == 0) { dev_err(&adev->pdev->dev, "Failed to reset ACP\n"); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto failure; } udelay(100); } @@ -384,7 +386,8 @@ static int acp_hw_init(void *handle) break; if (--count == 0) { dev_err(&adev->pdev->dev, "Failed to reset ACP\n"); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto failure; } udelay(100); } @@ -393,6 +396,13 @@ static int acp_hw_init(void *handle) val &= ~ACP_SOFT_RESET__SoftResetAud_MASK; cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val); return 0; + +failure: + kfree(i2s_pdata); + kfree(adev->acp.acp_res); + kfree(adev->acp.acp_cell); + kfree(adev->acp.acp_genpd); + return r; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 264677ab248a..6f8aaf655a9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -81,9 +81,10 @@ * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS. * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS. * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches + * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 34 +#define KMS_DRIVER_MINOR 35 #define KMS_DRIVER_PATCHLEVEL 0 #define AMDGPU_MAX_TIMEOUT_PARAM_LENTH 256 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 554a59b3c4a6..6ee4021910e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -165,6 +165,7 @@ struct amdgpu_gfx_config { uint32_t num_sc_per_sh; uint32_t num_packer_per_sc; uint32_t pa_sc_tile_steering_override; + uint64_t tcc_disabled_mask; }; struct amdgpu_cu_info { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index f6147528be64..f2c097983f48 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -787,6 +787,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file dev_info.pa_sc_tile_steering_override = adev->gfx.config.pa_sc_tile_steering_override; + dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask; + return copy_to_user(out, &dev_info, min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index e2fb141ff2e5..5251352f5922 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct ttm_bo_global *glob = adev->mman.bdev.glob; struct amdgpu_vm_bo_base *bo_base; -#if 0 if (vm->bulk_moveable) { spin_lock(&glob->lru_lock); ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move); spin_unlock(&glob->lru_lock); return; } -#endif memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 638c821611ab..957811b73672 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1691,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) } } +static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev) +{ + /* TCCs are global (not instanced). */ + uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) | + RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE); + + adev->gfx.config.tcc_disabled_mask = + REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) | + (REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16); +} + static void gfx_v10_0_constants_init(struct amdgpu_device *adev) { u32 tmp; @@ -1702,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev) gfx_v10_0_setup_rb(adev); gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info); + gfx_v10_0_get_tcc_info(adev); adev->gfx.config.pa_sc_tile_steering_override = gfx_v10_0_init_pa_sc_tile_steering_override(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 85393a99a848..de9b995b65b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -317,10 +317,12 @@ static int nv_asic_reset(struct amdgpu_device *adev) struct smu_context *smu = &adev->smu; if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); ret = smu_baco_reset(smu); } else { - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); ret = nv_asic_mode1_reset(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f70658a536a9..f8ab80c8801b 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev) { switch (soc15_asic_reset_method(adev)) { case AMD_RESET_METHOD_BACO: - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); return soc15_asic_baco_reset(adev); case AMD_RESET_METHOD_MODE2: return soc15_mode2_reset(adev); default: - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); return soc15_asic_mode1_reset(adev); } } @@ -771,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev) #if defined(CONFIG_DRM_AMD_DC) else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); -#else -# warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15." #endif amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); break; 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 8cab6da512a0..a52f0b13a2c8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2385,8 +2385,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY) dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true; - if (adev->asic_type == CHIP_RENOIR) - dm->dc->debug.disable_stutter = true; return 0; fail: @@ -6019,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev, struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state, *new_crtc_state; int i; +#ifdef CONFIG_DEBUG_FS enum amdgpu_dm_pipe_crc_source source; +#endif for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index 1787b9bf800a..76d54885374a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index 318e9c2e2ca8..89620adc81d8 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c index 83e1878161c9..21a657e79306 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c @@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 8b85e5274bba..7c52f7f9196c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 4625df9f9fd2..643ccb0ade00 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 59305e411a66..1599bb971111 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index b4e3ce22ed52..5a2763daff4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index 8cd9de8b1a7a..ef673bffc241 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -3,7 +3,17 @@ DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4 +ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) + cc_stack_align := -mpreferred-stack-boundary=4 +else ifneq ($(call cc-option, -mstack-alignment=16),) + cc_stack_align := -mstack-alignment=16 +endif + +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align) + +ifdef CONFIG_CC_IS_CLANG +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2 +endif AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21)) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index 456cd0e3289c..3b6ed60dcd35 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -39,9 +39,6 @@ * ways. Unless there is something clearly wrong with it the code should * remain as-is as it provides us with a guarantee from HW that it is correct. */ - -typedef unsigned int uint; - typedef struct { double DPPCLK; double DISPCLK; @@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0; mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - uint m; + unsigned int m; locals->cursor_bw[k] = 0; locals->cursor_bw_pre[k] = 0; @@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank; double FullDETBufferingTimeYStutterCriticalPlane = 0; double TimeToFinishSwathTransferStutterCriticalPlane = 0; - uint k, j; + unsigned int k, j; mode_lib->vba.TotalActiveDPP = 0; mode_lib->vba.TotalDCCActiveDPP = 0; @@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep( double DPPCLK[], double *DCFCLKDeepSleep) { - uint k; + unsigned int k; double DisplayPipeLineDeliveryTimeLuma; double DisplayPipeLineDeliveryTimeChroma; //double DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX]; @@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes( double DisplayPipeRequestDeliveryTimeChromaPrefetch[]) { double req_per_swath_ub; - uint k; + unsigned int k; for (k = 0; k < NumberOfActivePlanes; ++k) { if (VRatio[k] <= 1) { @@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes( unsigned int dpte_groups_per_row_chroma_ub; unsigned int num_group_per_lower_vm_stage; unsigned int num_req_per_lower_vm_stage; - uint k; + unsigned int k; for (k = 0; k < NumberOfActivePlanes; ++k) { if (GPUVMEnable == true) { diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 33960fb38a5d..4acf139ea014 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -843,6 +843,8 @@ static int smu_sw_init(void *handle) smu->smu_baco.state = SMU_BACO_STATE_EXIT; smu->smu_baco.platform_support = false; + mutex_init(&smu->sensor_lock); + smu->watermarks_bitmap = 0; smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index f1f072012fac..d493a3f8c07a 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu, if (!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 6109815a0401..23171a4d9a31 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -344,6 +344,7 @@ struct smu_context const struct smu_funcs *funcs; const struct pptable_funcs *ppt_funcs; struct mutex mutex; + struct mutex sensor_lock; uint64_t pool_size; struct smu_table_context smu_table; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 12c0e469bf35..0b461404af6b 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; - if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { + if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { @@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu, if(!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 64386ee3f878..bbd8ebd58434 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu, if(!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c index 2851cac94d86..b72840c06ab7 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c @@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder, struct komeda_data_flow_cfg dflow; int err; - if (!writeback_job || !writeback_job->fb) { + if (!writeback_job) return 0; - } if (!crtc_st->active) { DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n"); @@ -166,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms, &komeda_wb_encoder_helper_funcs, formats, n_formats); komeda_put_fourcc_list(formats); - if (err) + if (err) { + kfree(kwb_conn); return err; + } drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs); diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 22c0847986df..875a3a9eabfa 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -131,7 +131,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder, struct drm_framebuffer *fb; int i, n_planes; - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; fb = conn_state->writeback_job->fb; @@ -248,7 +248,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm, mw_state = to_mw_state(conn_state); - if (conn_state->writeback_job && conn_state->writeback_job->fb) { + if (conn_state->writeback_job) { struct drm_framebuffer *fb = conn_state->writeback_job->fb; DRM_DEV_DEBUG_DRIVER(drm->dev, diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 419381abbdd1..14aeaf736321 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector, return -EINVAL; } - if (writeback_job->out_fence && !writeback_job->fb) { - DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n", - connector->base.id, connector->name); - return -EINVAL; + if (!writeback_job->fb) { + if (writeback_job->out_fence) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n", + connector->base.id, connector->name); + return -EINVAL; + } + + drm_writeback_cleanup_job(writeback_job); + state->writeback_job = NULL; } return 0; diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index ff138b6ec48b..43d9e3bb3a94 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job) if (job->fb) drm_framebuffer_put(job->fb); + if (job->out_fence) + dma_fence_put(job->out_fence); + kfree(job); } EXPORT_SYMBOL(drm_writeback_cleanup_job); @@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector, { unsigned long flags; struct drm_writeback_job *job; + struct dma_fence *out_fence; spin_lock_irqsave(&wb_connector->job_lock, flags); job = list_first_entry_or_null(&wb_connector->job_queue, struct drm_writeback_job, list_entry); - if (job) { + if (job) list_del(&job->list_entry); - if (job->out_fence) { - if (status) - dma_fence_set_error(job->out_fence, status); - dma_fence_signal(job->out_fence); - dma_fence_put(job->out_fence); - } - } + spin_unlock_irqrestore(&wb_connector->job_lock, flags); if (WARN_ON(!job)) return; + out_fence = job->out_fence; + if (out_fence) { + if (status) + dma_fence_set_error(out_fence, status); + dma_fence_signal(out_fence); + dma_fence_put(out_fence); + job->out_fence = NULL; + } + INIT_WORK(&job->cleanup_work, cleanup_work); queue_work(system_long_wq, &job->cleanup_work); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index b51d1ceb8739..ce05e805b08f 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7261,7 +7261,7 @@ retry: pipe_config->fdi_lanes = lane; intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock, - link_bw, &pipe_config->fdi_m_n, false); + link_bw, &pipe_config->fdi_m_n, false, false); ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config); if (ret == -EDEADLK) @@ -7508,11 +7508,15 @@ void intel_link_compute_m_n(u16 bits_per_pixel, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n) + bool constant_n, bool fec_enable) { - m_n->tu = 64; + u32 data_clock = bits_per_pixel * pixel_clock; + + if (fec_enable) + data_clock = intel_dp_mode_to_fec_clock(data_clock); - compute_m_n(bits_per_pixel * pixel_clock, + m_n->tu = 64; + compute_m_n(data_clock, link_clock * nlanes * 8, &m_n->gmch_m, &m_n->gmch_n, constant_n); diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index e57e6969051d..01fa87ad3270 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -414,7 +414,7 @@ enum phy_fia { void intel_link_compute_m_n(u16 bpp, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n); + bool constant_n, bool fec_enable); bool is_ccs_modifier(u64 modifier); void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv); u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 921ad0a2f7ba..57e9f0ba331b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -78,8 +78,8 @@ #define DP_DSC_MAX_ENC_THROUGHPUT_0 340000 #define DP_DSC_MAX_ENC_THROUGHPUT_1 400000 -/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */ -#define DP_DSC_FEC_OVERHEAD_FACTOR 976 +/* DP DSC FEC Overhead factor = 1/(0.972261) */ +#define DP_DSC_FEC_OVERHEAD_FACTOR 972261 /* Compliance test status bits */ #define INTEL_DP_RESOLUTION_SHIFT_MASK 0 @@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, return 0; } +u32 intel_dp_mode_to_fec_clock(u32 mode_clock) +{ + return div_u64(mul_u32_u32(mode_clock, 1000000U), + DP_DSC_FEC_OVERHEAD_FACTOR); +} + +static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count, + u32 mode_clock, u32 mode_hdisplay) +{ + u32 bits_per_pixel, max_bpp_small_joiner_ram; + int i; + + /* + * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)* + * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP) + * for SST -> TimeSlotsPerMTP is 1, + * for MST -> TimeSlotsPerMTP has to be calculated + */ + bits_per_pixel = (link_clock * lane_count * 8) / + intel_dp_mode_to_fec_clock(mode_clock); + DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel); + + /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */ + max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay; + DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram); + + /* + * Greatest allowed DSC BPP = MIN (output BPP from available Link BW + * check, output bpp from small joiner RAM check) + */ + bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram); + + /* Error out if the max bpp is less than smallest allowed valid bpp */ + if (bits_per_pixel < valid_dsc_bpp[0]) { + DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n", + bits_per_pixel, valid_dsc_bpp[0]); + return 0; + } + + /* Find the nearest match in the array of known BPPs from VESA */ + for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) { + if (bits_per_pixel < valid_dsc_bpp[i + 1]) + break; + } + bits_per_pixel = valid_dsc_bpp[i]; + + /* + * Compressed BPP in U6.4 format so multiply by 16, for Gen 11, + * fractional part is 0 + */ + return bits_per_pixel << 4; +} + +static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, + int mode_clock, int mode_hdisplay) +{ + u8 min_slice_count, i; + int max_slice_width; + + if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE) + min_slice_count = DIV_ROUND_UP(mode_clock, + DP_DSC_MAX_ENC_THROUGHPUT_0); + else + min_slice_count = DIV_ROUND_UP(mode_clock, + DP_DSC_MAX_ENC_THROUGHPUT_1); + + max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd); + if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) { + DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n", + max_slice_width); + return 0; + } + /* Also take into account max slice width */ + min_slice_count = min_t(u8, min_slice_count, + DIV_ROUND_UP(mode_hdisplay, + max_slice_width)); + + /* Find the closest match to the valid slice count values */ + for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) { + if (valid_dsc_slicecount[i] > + drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, + false)) + break; + if (min_slice_count <= valid_dsc_slicecount[i]) + return valid_dsc_slicecount[i]; + } + + DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count); + return 0; +} + static enum drm_mode_status intel_dp_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) @@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, pipe_config->port_clock, &pipe_config->dp_m_n, - constant_n); + constant_n, pipe_config->fec_enable); if (intel_connector->panel.downclock_mode != NULL && dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) { @@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_connector->panel.downclock_mode->clock, pipe_config->port_clock, &pipe_config->dp_m2_n2, - constant_n); + constant_n, pipe_config->fec_enable); } if (!HAS_DDI(dev_priv)) @@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector) DP_DPRX_ESI_LEN; } -u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count, - int mode_clock, int mode_hdisplay) -{ - u16 bits_per_pixel, max_bpp_small_joiner_ram; - int i; - - /* - * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)* - * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP) - * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1, - * for MST -> TimeSlotsPerMTP has to be calculated - */ - bits_per_pixel = (link_clock * lane_count * 8 * - DP_DSC_FEC_OVERHEAD_FACTOR) / - mode_clock; - - /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */ - max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / - mode_hdisplay; - - /* - * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW - * check, output bpp from small joiner RAM check) - */ - bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram); - - /* Error out if the max bpp is less than smallest allowed valid bpp */ - if (bits_per_pixel < valid_dsc_bpp[0]) { - DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel); - return 0; - } - - /* Find the nearest match in the array of known BPPs from VESA */ - for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) { - if (bits_per_pixel < valid_dsc_bpp[i + 1]) - break; - } - bits_per_pixel = valid_dsc_bpp[i]; - - /* - * Compressed BPP in U6.4 format so multiply by 16, for Gen 11, - * fractional part is 0 - */ - return bits_per_pixel << 4; -} - -u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, - int mode_clock, - int mode_hdisplay) -{ - u8 min_slice_count, i; - int max_slice_width; - - if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE) - min_slice_count = DIV_ROUND_UP(mode_clock, - DP_DSC_MAX_ENC_THROUGHPUT_0); - else - min_slice_count = DIV_ROUND_UP(mode_clock, - DP_DSC_MAX_ENC_THROUGHPUT_1); - - max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd); - if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) { - DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n", - max_slice_width); - return 0; - } - /* Also take into account max slice width */ - min_slice_count = min_t(u8, min_slice_count, - DIV_ROUND_UP(mode_hdisplay, - max_slice_width)); - - /* Find the closest match to the valid slice count values */ - for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) { - if (valid_dsc_slicecount[i] > - drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, - false)) - break; - if (min_slice_count <= valid_dsc_slicecount[i]) - return valid_dsc_slicecount[i]; - } - - DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count); - return 0; -} - static void intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 657bbb1f5ed0..00981fb9414b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp); bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp); bool intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status); -u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count, - int mode_clock, int mode_hdisplay); -u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock, - int mode_hdisplay); bool intel_dp_read_dpcd(struct intel_dp *intel_dp); bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp); @@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count) return ~((1 << lane_count) - 1) & 0xf; } +u32 intel_dp_mode_to_fec_clock(u32 mode_clock); + #endif /* __INTEL_DP_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 6df240a01b8c..600873c796d0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, crtc_state->port_clock, &crtc_state->dp_m_n, - constant_n); + constant_n, crtc_state->fec_enable); crtc_state->dp_m_n.tu = slots; return 0; @@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum intel_encoder->type = INTEL_OUTPUT_DP_MST; intel_encoder->power_domain = intel_dig_port->base.power_domain; intel_encoder->port = intel_dig_port->base.port; - intel_encoder->crtc_mask = BIT(pipe); + intel_encoder->crtc_mask = 0x7; intel_encoder->cloneable = 0; intel_encoder->compute_config = intel_dp_mst_compute_config; diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index dea63be1964f..cae25e493128 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state, int src_x, src_w, src_h, crtc_w, crtc_h; const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode; + unsigned int stride = plane_state->color_plane[0].stride; unsigned int cpp = fb->format->cpp[0]; unsigned int width_bytes; int min_width, min_height; @@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state, return -EINVAL; } - if (width_bytes > 4096 || fb->pitches[0] > 4096) { + if (stride > 4096) { DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n", - fb->pitches[0], 4096); + stride, 4096); return -EINVAL; } diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index e226324adb69..4bdd63b57100 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1083,7 +1083,7 @@ static const struct dss_features omap34xx_dss_feats = { static const struct dss_features omap3630_dss_feats = { .model = DSS_MODEL_OMAP3, - .fck_div_max = 32, + .fck_div_max = 31, .fck_freq_max = 173000000, .dss_fck_multiplier = 1, .parent_clk_name = "dpll4_ck", diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c index ae07290bba6a..04efa78d70b6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c @@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct drm_framebuffer *fb; - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; fb = conn_state->writeback_job->fb; @@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc, unsigned int i; state = rcrtc->writeback.base.state; - if (!state || !state->writeback_job || !state->writeback_job->fb) + if (!state || !state->writeback_job) return; fb = state->writeback_job->fb; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index 525dc1c0f1c1..530edb3b51cc 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -7,6 +7,7 @@ #include <linux/gpio.h> #include <linux/mod_devicetable.h> #include <linux/of_gpio.h> +#include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index 1ce4d7142b6e..bf720206727f 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -231,7 +231,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn, int i; conn_state = drm_atomic_get_new_connector_state(state, conn); - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); @@ -271,8 +271,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn, u32 ctrl; int i; - if (WARN_ON(!conn_state->writeback_job || - !conn_state->writeback_job->fb)) + if (WARN_ON(!conn_state->writeback_job)) return; mode = &conn_state->crtc->state->adjusted_mode; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 931d9d935686..21d8fcc83c9c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4039,7 +4039,7 @@ out: * this to-be-skipped slave to send a packet out. */ old_arr = rtnl_dereference(bond->slave_arr); - for (idx = 0; idx < old_arr->count; idx++) { + for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) { if (skipslave == old_arr->arr[idx]) { old_arr->arr[idx] = old_arr->arr[old_arr->count-1]; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 526ba2ab66f1..cc3536315eff 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1845,7 +1845,6 @@ int b53_mirror_add(struct dsa_switch *ds, int port, loc = B53_EG_MIR_CTL; b53_read16(dev, B53_MGMT_PAGE, loc, ®); - reg &= ~MIRROR_MASK; reg |= BIT(port); b53_write16(dev, B53_MGMT_PAGE, loc, reg); diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 684aa51684db..b00274caae4f 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -705,7 +705,7 @@ qca8k_setup(struct dsa_switch *ds) BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); /* Setup connection between CPU port & user ports */ - for (i = 0; i < DSA_MAX_PORTS; i++) { + for (i = 0; i < QCA8K_NUM_PORTS; i++) { /* CPU port gets connected to all user ports of the switch */ if (dsa_is_cpu_port(ds, i)) { qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), @@ -1077,7 +1077,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev) if (id != QCA8K_ID_QCA8337) return -ENODEV; - priv->ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS); + priv->ds = dsa_switch_alloc(&mdiodev->dev, QCA8K_NUM_PORTS); if (!priv->ds) return -ENOMEM; diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index ca3d17e43ed8..ac88caca5ad4 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -339,10 +339,12 @@ int rtl8366_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct realtek_smi *smi = ds->priv; + u16 vid; int ret; - if (!smi->ops->is_vlan_valid(smi, port)) - return -EINVAL; + for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++) + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; dev_info(smi->dev, "prepare VLANs %04x..%04x\n", vlan->vid_begin, vlan->vid_end); @@ -370,8 +372,9 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, u16 vid; int ret; - if (!smi->ops->is_vlan_valid(smi, port)) - return; + for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++) + if (!smi->ops->is_vlan_valid(smi, vid)) + return; dev_info(smi->dev, "add VLAN on port %d, %s, %s\n", port, diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index a268085ffad2..f5cc8b0a7c74 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -507,7 +507,8 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) irq = of_irq_get(intc, 0); if (irq <= 0) { dev_err(smi->dev, "failed to get parent IRQ\n"); - return irq ? irq : -EINVAL; + ret = irq ? irq : -EINVAL; + goto out_put_node; } /* This clears the IRQ status register */ @@ -515,7 +516,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) &val); if (ret) { dev_err(smi->dev, "can't read interrupt status\n"); - return ret; + goto out_put_node; } /* Fetch IRQ edge information from the descriptor */ @@ -537,7 +538,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) val); if (ret) { dev_err(smi->dev, "could not configure IRQ polarity\n"); - return ret; + goto out_put_node; } ret = devm_request_threaded_irq(smi->dev, irq, NULL, @@ -545,7 +546,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) "RTL8366RB", smi); if (ret) { dev_err(smi->dev, "unable to request irq: %d\n", ret); - return ret; + goto out_put_node; } smi->irqdomain = irq_domain_add_linear(intc, RTL8366RB_NUM_INTERRUPT, @@ -553,12 +554,15 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) smi); if (!smi->irqdomain) { dev_err(smi->dev, "failed to create IRQ domain\n"); - return -EINVAL; + ret = -EINVAL; + goto out_put_node; } for (i = 0; i < smi->num_ports; i++) irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq); - return 0; +out_put_node: + of_node_put(intc); + return ret; } static int rtl8366rb_set_addr(struct realtek_smi *smi) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index b9def744bcb3..7687ddcae159 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1897,7 +1897,9 @@ static int sja1105_set_ageing_time(struct dsa_switch *ds, return sja1105_static_config_reload(priv); } -/* Caller must hold priv->tagger_data.meta_lock */ +/* Must be called only with priv->tagger_data.state bit + * SJA1105_HWTS_RX_EN cleared + */ static int sja1105_change_rxtstamping(struct sja1105_private *priv, bool on) { @@ -1954,16 +1956,17 @@ static int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, break; } - if (rx_on != priv->tagger_data.hwts_rx_en) { - spin_lock(&priv->tagger_data.meta_lock); + if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) { + clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + rc = sja1105_change_rxtstamping(priv, rx_on); - spin_unlock(&priv->tagger_data.meta_lock); if (rc < 0) { dev_err(ds->dev, "Failed to change RX timestamping: %d\n", rc); - return -EFAULT; + return rc; } - priv->tagger_data.hwts_rx_en = rx_on; + if (rx_on) + set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); } if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) @@ -1982,7 +1985,7 @@ static int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; - if (priv->tagger_data.hwts_rx_en) + if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; else config.rx_filter = HWTSTAMP_FILTER_NONE; @@ -2005,12 +2008,12 @@ static void sja1105_rxtstamp_work(struct work_struct *work) mutex_lock(&priv->ptp_lock); - now = priv->tstamp_cc.read(&priv->tstamp_cc); - while ((skb = skb_dequeue(&data->skb_rxtstamp_queue)) != NULL) { struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb); u64 ts; + now = priv->tstamp_cc.read(&priv->tstamp_cc); + *shwt = (struct skb_shared_hwtstamps) {0}; ts = SJA1105_SKB_CB(skb)->meta_tstamp; @@ -2031,7 +2034,7 @@ static bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, struct sja1105_private *priv = ds->priv; struct sja1105_tagger_data *data = &priv->tagger_data; - if (!data->hwts_rx_en) + if (!test_bit(SJA1105_HWTS_RX_EN, &data->state)) return false; /* We need to read the full PTP clock to reconstruct the Rx @@ -2201,6 +2204,7 @@ static int sja1105_probe(struct spi_device *spi) tagger_data = &priv->tagger_data; skb_queue_head_init(&tagger_data->skb_rxtstamp_queue); INIT_WORK(&tagger_data->rxtstamp_work, sja1105_rxtstamp_work); + spin_lock_init(&tagger_data->meta_lock); /* Connections between dsa_port and sja1105_port */ for (i = 0; i < SJA1105_NUM_PORTS; i++) { diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 84dc603138cf..58dd37ecde17 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -409,7 +409,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv) rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len); if (rc < 0) { dev_err(dev, "Invalid config, cannot upload\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* Prevent PHY jabbering during switch reset by inhibiting * Tx on all ports and waiting for current packet to drain. @@ -418,7 +419,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv) rc = sja1105_inhibit_tx(priv, port_bitmap, true); if (rc < 0) { dev_err(dev, "Failed to inhibit Tx on ports\n"); - return -ENXIO; + rc = -ENXIO; + goto out; } /* Wait for an eventual egress packet to finish transmission * (reach IFG). It is guaranteed that a second one will not diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index b4a0fb281e69..bb65dd39f847 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -194,9 +194,7 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); - aq_nic_set_packet_filter(aq_nic, ndev->flags); - - aq_nic_set_multicast_list(aq_nic, ndev); + (void)aq_nic_set_multicast_list(aq_nic, ndev); } static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 8f66e7817811..2a18439b36fb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -631,9 +631,12 @@ err_exit: int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) { - unsigned int packet_filter = self->packet_filter; + const struct aq_hw_ops *hw_ops = self->aq_hw_ops; + struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg; + unsigned int packet_filter = ndev->flags; struct netdev_hw_addr *ha = NULL; unsigned int i = 0U; + int err = 0; self->mc_list.count = 0; if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { @@ -641,29 +644,26 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) } else { netdev_for_each_uc_addr(ha, ndev) { ether_addr_copy(self->mc_list.ar[i++], ha->addr); - - if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) - break; } } - if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { - packet_filter |= IFF_ALLMULTI; - } else { - netdev_for_each_mc_addr(ha, ndev) { - ether_addr_copy(self->mc_list.ar[i++], ha->addr); - - if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) - break; + cfg->is_mc_list_enabled = !!(packet_filter & IFF_MULTICAST); + if (cfg->is_mc_list_enabled) { + if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_ALLMULTI; + } else { + netdev_for_each_mc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], + ha->addr); + } } } if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) { - packet_filter |= IFF_MULTICAST; self->mc_list.count = i; - self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + err = hw_ops->hw_multicast_list_set(self->aq_hw, + self->mc_list.ar, + self->mc_list.count); } return aq_nic_set_packet_filter(self, packet_filter); } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3901d7994ca1..76bdbe1596d6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -313,6 +313,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, break; buff->is_error |= buff_->is_error; + buff->is_cso_err |= buff_->is_cso_err; } while (!buff_->is_eop); @@ -320,7 +321,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error) { + if (buff->is_error || buff->is_cso_err) { buff_ = buff; do { next_ = buff_->next, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 30f7fc4c97ff..2ad3fa6316ce 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -818,14 +818,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, cfg->is_vlan_force_promisc); hw_atl_rpfl2multicast_flr_en_set(self, - IS_FILTER_ENABLED(IFF_ALLMULTI), 0); + IS_FILTER_ENABLED(IFF_ALLMULTI) && + IS_FILTER_ENABLED(IFF_MULTICAST), 0); hw_atl_rpfl2_accept_all_mc_packets_set(self, - IS_FILTER_ENABLED(IFF_ALLMULTI)); + IS_FILTER_ENABLED(IFF_ALLMULTI) && + IS_FILTER_ENABLED(IFF_MULTICAST)); hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST)); - cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST); for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i) hw_atl_rpfl2_uc_flr_en_set(self, @@ -968,14 +969,26 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { + int err; + u32 val; + hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); /* Invalidate Descriptor Cache to prevent writing to the cached * descriptors and to the data pointer of those descriptors */ - hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1); + hw_atl_rdm_rx_dma_desc_cache_init_tgl(self); - return aq_hw_err_from_flags(self); + err = aq_hw_err_from_flags(self); + + if (err) + goto err_exit; + + readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get, + self, val, val == 1, 1000U, 10000U); + +err_exit: + return err; } static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 1149812ae463..6f340695e6bd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -606,12 +606,25 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode); } -void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init) +void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw) { + u32 val; + + val = aq_hw_read_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT); + aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT, - init); + val ^ 1); +} + +u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw) +{ + return aq_hw_read_reg_bit(aq_hw, RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR, + RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK, + RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT); } void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 0c37abbabca5..c3ee278c3747 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -313,8 +313,11 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer); -/* set rdm rx dma descriptor cache init */ -void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init); +/* toggle rdm rx dma descriptor cache init */ +void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw); + +/* get rdm rx dma descriptor cache init done */ +u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw); /* set rx xoff enable (per tc) */ void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index c3febcdfa92e..35887ad89025 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -318,6 +318,25 @@ /* default value of bitfield rdm_desc_init_i */ #define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0 +/* rdm_desc_init_done_i bitfield definitions + * preprocessor definitions for the bitfield rdm_desc_init_done_i. + * port="pif_rdm_desc_init_done_i" + */ + +/* register address for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR 0x00005a10 +/* bitmask for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK 0x00000001U +/* inverted bitmask for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSKN 0xfffffffe +/* lower bit position of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT 0U +/* width of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_WIDTH 1 +/* default value of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_DEFAULT 0x0 + + /* rx int_desc_wrb_en bitfield definitions * preprocessor definitions for the bitfield "int_desc_wrb_en". * port="pif_rdm_int_desc_wrb_en_i" diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index da726489e3c8..7bc51f8d6f2f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -337,7 +337,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp) /* Convert PHY temperature from 1/256 degree Celsius * to 1/1000 degree Celsius. */ - *temp = temp_res * 1000 / 256; + *temp = (temp_res & 0xFFFF) * 1000 / 256; return 0; } diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 7548247455d7..1b1a09095c0d 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -526,7 +526,7 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) struct device *dev = &ag->pdev->dev; struct net_device *ndev = ag->ndev; static struct mii_bus *mii_bus; - struct device_node *np; + struct device_node *np, *mnp; int err; np = dev->of_node; @@ -571,7 +571,9 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) msleep(200); } - err = of_mdiobus_register(mii_bus, np); + mnp = of_get_child_by_name(np, "mdio"); + err = of_mdiobus_register(mii_bus, mnp); + of_node_put(mnp); if (err) goto mdio_err_put_clk; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index 5b602243d573..a4dead4ab0ed 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -137,13 +137,12 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp, static int alloc_uld_rxqs(struct adapter *adap, struct sge_uld_rxq_info *rxq_info, bool lro) { - struct sge *s = &adap->sge; unsigned int nq = rxq_info->nrxq + rxq_info->nciq; + int i, err, msi_idx, que_idx = 0, bmap_idx = 0; struct sge_ofld_rxq *q = rxq_info->uldrxq; unsigned short *ids = rxq_info->rspq_id; - unsigned int bmap_idx = 0; + struct sge *s = &adap->sge; unsigned int per_chan; - int i, err, msi_idx, que_idx = 0; per_chan = rxq_info->nrxq / adap->params.nports; @@ -161,6 +160,10 @@ static int alloc_uld_rxqs(struct adapter *adap, if (msi_idx >= 0) { bmap_idx = get_msix_idx_from_bmap(adap); + if (bmap_idx < 0) { + err = -ENOSPC; + goto freeout; + } msi_idx = adap->msix_info_ulds[bmap_idx].idx; } err = t4_sge_alloc_rxq(adap, &q->rspq, false, diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 3e863a71c513..7df5d7d211d4 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -148,11 +148,15 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev, { u32 time_cnt; u32 reg_value; + int ret; regmap_write(mdio_dev->subctrl_vbase, cfg_reg, set_val); for (time_cnt = MDIO_TIMEOUT; time_cnt; time_cnt--) { - regmap_read(mdio_dev->subctrl_vbase, st_reg, ®_value); + ret = regmap_read(mdio_dev->subctrl_vbase, st_reg, ®_value); + if (ret) + return ret; + reg_value &= st_msk; if ((!!check_st) == (!!reg_value)) break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2b073a3c0b84..f59d9a8e35e2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2878,12 +2878,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { - u64 val = (0xff000000) | scrq->hw_irq; + struct irq_desc *desc = irq_to_desc(scrq->irq); + struct irq_chip *chip = irq_desc_get_chip(desc); - rc = plpar_hcall_norets(H_EOI, val); - if (rc) - dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", - val, rc); + chip->irq_eoi(&desc->irq_data); } rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 913f1e5aaaf2..d7c7467e2d53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -137,7 +137,8 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool, icm_mr->icm_start_addr = icm_mr->dm.addr; - align_diff = icm_mr->icm_start_addr % align_base; + /* align_base is always a power of 2 */ + align_diff = icm_mr->icm_start_addr & (align_base - 1); if (align_diff) icm_mr->used_length = align_base - align_diff; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 4187f2b112b8..e8b656075c6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -788,12 +788,10 @@ again: * it means that all the previous stes are the same, * if so, this rule is duplicated. */ - if (mlx5dr_ste_is_last_in_rule(nic_matcher, - matched_ste->ste_chain_location)) { - mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n"); - return NULL; - } - return matched_ste; + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste_location)) + return matched_ste; + + mlx5dr_dbg(dmn, "Duplicate rule inserted\n"); } if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) { diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index b063eb78fa0c..aac115136720 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -388,13 +388,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) continue; phy = of_phy_find_device(phy_node); + of_node_put(phy_node); if (!phy) continue; err = ocelot_probe_port(ocelot, port, regs, phy); if (err) { of_node_put(portnp); - return err; + goto out_put_ports; } phy_mode = of_get_phy_mode(portnp); @@ -422,7 +423,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) "invalid phy mode for port%d, (Q)SGMII only\n", port); of_node_put(portnp); - return -EINVAL; + err = -EINVAL; + goto out_put_ports; } serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); @@ -435,7 +437,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) "missing SerDes phys for port%d\n", port); - goto err_probe_ports; + of_node_put(portnp); + goto out_put_ports; } ocelot->ports[port]->serdes = serdes; @@ -447,9 +450,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) dev_info(&pdev->dev, "Ocelot switch probed\n"); - return 0; - -err_probe_ports: +out_put_ports: + of_node_put(ports); return err; } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 141571e2ec11..544012a67221 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1356,9 +1356,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) if (!is_valid_ether_addr(ndev->dev_addr)) eth_hw_addr_random(ndev); - /* Reset the ethernet controller */ - __lpc_eth_reset(pldat); - /* then shut everything down to save power */ __lpc_eth_shutdown(pldat); diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index bd0583e409df..d25b88f53de4 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI + select NET_DEVLINK help This enables the support for the Pensando family of Ethernet adapters. More specific information on this driver can be diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 812190e729c2..6a95b42a8d8c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -182,6 +182,8 @@ struct ionic_lif { #define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) #define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) +#define lif_to_txstats(lif, i) ((lif)->txqcqs[i].stats->tx) +#define lif_to_rxstats(lif, i) ((lif)->rxqcqs[i].stats->rx) #define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) #define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index e2907884f843..03916b6d47f2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -117,7 +117,8 @@ static u64 ionic_sw_stats_get_count(struct ionic_lif *lif) /* rx stats */ total += MAX_Q(lif) * IONIC_NUM_RX_STATS; - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { /* tx debug stats */ total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + IONIC_NUM_TX_Q_STATS + @@ -149,7 +150,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) *buf += ETH_GSTRING_LEN; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { snprintf(*buf, ETH_GSTRING_LEN, "txq_%d_%s", @@ -187,7 +189,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) *buf += ETH_GSTRING_LEN; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { snprintf(*buf, ETH_GSTRING_LEN, "rxq_%d_cq_%s", @@ -223,6 +226,8 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) { struct ionic_lif_sw_stats lif_stats; struct ionic_qcq *txqcq, *rxqcq; + struct ionic_tx_stats *txstats; + struct ionic_rx_stats *rxstats; int i, q_num; ionic_get_lif_stats(lif, &lif_stats); @@ -233,15 +238,17 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txqcq = lif_to_txqcq(lif, q_num); + txstats = &lif_to_txstats(lif, q_num); for (i = 0; i < IONIC_NUM_TX_STATS; i++) { - **buf = IONIC_READ_STAT64(&txqcq->stats->tx, + **buf = IONIC_READ_STAT64(txstats, &ionic_tx_stats_desc[i]); (*buf)++; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + txqcq = lif_to_txqcq(lif, q_num); for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { **buf = IONIC_READ_STAT64(&txqcq->q, &ionic_txq_stats_desc[i]); @@ -258,22 +265,24 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) (*buf)++; } for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { - **buf = txqcq->stats->tx.sg_cntr[i]; + **buf = txstats->sg_cntr[i]; (*buf)++; } } } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - rxqcq = lif_to_rxqcq(lif, q_num); + rxstats = &lif_to_rxstats(lif, q_num); for (i = 0; i < IONIC_NUM_RX_STATS; i++) { - **buf = IONIC_READ_STAT64(&rxqcq->stats->rx, + **buf = IONIC_READ_STAT64(rxstats, &ionic_rx_stats_desc[i]); (*buf)++; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + rxqcq = lif_to_rxqcq(lif, q_num); for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { **buf = IONIC_READ_STAT64(&rxqcq->cq, &ionic_dbg_cq_stats_desc[i]); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 457444894d80..b4b8ba00ee01 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2787,6 +2787,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", err); + dev_kfree_skb_irq(skb); ql_free_large_buffers(qdev); return -ENOMEM; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 74f81fe03810..350b0d949611 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4146,6 +4146,14 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) rtl_lock_config_regs(tp); } +static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu) +{ + if (mtu > ETH_DATA_LEN) + rtl_hw_jumbo_enable(tp); + else + rtl_hw_jumbo_disable(tp); +} + DECLARE_RTL_COND(rtl_chipcmd_cond) { return RTL_R8(tp, ChipCmd) & CmdReset; @@ -4442,11 +4450,6 @@ static void rtl8168g_set_pause_thresholds(struct rtl8169_private *tp, static void rtl_hw_start_8168bb(struct rtl8169_private *tp) { RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - - if (tp->dev->mtu <= ETH_DATA_LEN) { - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B | - PCI_EXP_DEVCTL_NOSNOOP_EN); - } } static void rtl_hw_start_8168bef(struct rtl8169_private *tp) @@ -4462,9 +4465,6 @@ static void __rtl_hw_start_8168cp(struct rtl8169_private *tp) RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_disable_clock_request(tp); } @@ -4490,9 +4490,6 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) @@ -4503,9 +4500,6 @@ static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) /* Magic. */ RTL_W8(tp, DBG_REG, 0x20); - - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) @@ -4611,9 +4605,6 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_1); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_disable_clock_request(tp); /* Reset tx FIFO pointer */ @@ -4636,9 +4627,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_2); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06); @@ -5485,6 +5473,8 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_tx_desc_registers(tp); rtl_lock_config_regs(tp); + rtl_jumbo_config(tp, tp->dev->mtu); + /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ RTL_R16(tp, CPlusCmd); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); @@ -5498,10 +5488,7 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) { struct rtl8169_private *tp = netdev_priv(dev); - if (new_mtu > ETH_DATA_LEN) - rtl_hw_jumbo_enable(tp); - else - rtl_hw_jumbo_disable(tp); + rtl_jumbo_config(tp, new_mtu); dev->mtu = new_mtu; netdev_update_features(dev); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 55db7fbd43cc..f9e6744d8fd6 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -282,7 +282,6 @@ struct netsec_desc_ring { void *vaddr; u16 head, tail; u16 xdp_xmit; /* netsec_xdp_xmit packets */ - bool is_xdp; struct page_pool *page_pool; struct xdp_rxq_info xdp_rxq; spinlock_t lock; /* XDP tx queue locking */ @@ -634,8 +633,7 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv) unsigned int bytes; int cnt = 0; - if (dring->is_xdp) - spin_lock(&dring->lock); + spin_lock(&dring->lock); bytes = 0; entry = dring->vaddr + DESC_SZ * tail; @@ -682,8 +680,8 @@ next: entry = dring->vaddr + DESC_SZ * tail; cnt++; } - if (dring->is_xdp) - spin_unlock(&dring->lock); + + spin_unlock(&dring->lock); if (!cnt) return false; @@ -799,9 +797,6 @@ static void netsec_set_tx_de(struct netsec_priv *priv, de->data_buf_addr_lw = lower_32_bits(desc->dma_addr); de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len; de->attr = attr; - /* under spin_lock if using XDP */ - if (!dring->is_xdp) - dma_wmb(); dring->desc[idx] = *desc; if (desc->buf_type == TYPE_NETSEC_SKB) @@ -1123,12 +1118,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, u16 tso_seg_len = 0; int filled; - if (dring->is_xdp) - spin_lock_bh(&dring->lock); + spin_lock_bh(&dring->lock); filled = netsec_desc_used(dring); if (netsec_check_stop_tx(priv, filled)) { - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); net_warn_ratelimited("%s %s Tx queue full\n", dev_name(priv->dev), ndev->name); return NETDEV_TX_BUSY; @@ -1161,8 +1154,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, tx_desc.dma_addr = dma_map_single(priv->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) { - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); netif_err(priv, drv, priv->ndev, "%s: DMA mapping failed\n", __func__); ndev->stats.tx_dropped++; @@ -1177,8 +1169,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, netdev_sent_queue(priv->ndev, skb->len); netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb); - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */ return NETDEV_TX_OK; @@ -1262,7 +1253,6 @@ err: static void netsec_setup_tx_dring(struct netsec_priv *priv) { struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX]; - struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog); int i; for (i = 0; i < DESC_NUM; i++) { @@ -1275,12 +1265,6 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv) */ de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD; } - - if (xdp_prog) - dring->is_xdp = true; - else - dring->is_xdp = false; - } static int netsec_setup_rx_dring(struct netsec_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 9b4b5f69fc02..5a7b0aca1d31 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -401,8 +401,11 @@ static void dwmac4_set_filter(struct mac_device_info *hw, int numhashregs = (hw->multicast_filter_bins >> 5); int mcbitslog2 = hw->mcast_bits_log2; unsigned int value; + u32 mc_filter[8]; int i; + memset(mc_filter, 0, sizeof(mc_filter)); + value = readl(ioaddr + GMAC_PACKET_FILTER); value &= ~GMAC_PACKET_FILTER_HMC; value &= ~GMAC_PACKET_FILTER_HPF; @@ -416,16 +419,13 @@ static void dwmac4_set_filter(struct mac_device_info *hw, /* Pass all multi */ value |= GMAC_PACKET_FILTER_PM; /* Set all the bits of the HASH tab */ - for (i = 0; i < numhashregs; i++) - writel(0xffffffff, ioaddr + GMAC_HASH_TAB(i)); + memset(mc_filter, 0xff, sizeof(mc_filter)); } else if (!netdev_mc_empty(dev)) { struct netdev_hw_addr *ha; - u32 mc_filter[8]; /* Hash filter for multicast */ value |= GMAC_PACKET_FILTER_HMC; - memset(mc_filter, 0, sizeof(mc_filter)); netdev_for_each_mc_addr(ha, dev) { /* The upper n bits of the calculated CRC are used to * index the contents of the hash table. The number of @@ -440,14 +440,15 @@ static void dwmac4_set_filter(struct mac_device_info *hw, */ mc_filter[bit_nr >> 5] |= (1 << (bit_nr & 0x1f)); } - for (i = 0; i < numhashregs; i++) - writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i)); } + for (i = 0; i < numhashregs; i++) + writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i)); + value |= GMAC_PACKET_FILTER_HPF; /* Handle multiple unicast addresses */ - if (netdev_uc_count(dev) > GMAC_MAX_PERFECT_ADDRESSES) { + if (netdev_uc_count(dev) > hw->unicast_filter_entries) { /* Switch to promiscuous mode if more than 128 addrs * are required */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 3f4f3132e16b..e436fa160c7d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -515,6 +515,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, if (!enable) { val |= PPSCMDx(index, 0x5); + val |= PPSEN0; writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 5923ca62d793..99037386080a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -84,7 +84,7 @@ #define XGMAC_TSIE BIT(12) #define XGMAC_LPIIE BIT(5) #define XGMAC_PMTIE BIT(4) -#define XGMAC_INT_DEFAULT_EN (XGMAC_LPIIE | XGMAC_PMTIE | XGMAC_TSIE) +#define XGMAC_INT_DEFAULT_EN (XGMAC_LPIIE | XGMAC_PMTIE) #define XGMAC_Qx_TX_FLOW_CTRL(x) (0x00000070 + (x) * 4) #define XGMAC_PT GENMASK(31, 16) #define XGMAC_PT_SHIFT 16 @@ -122,6 +122,7 @@ #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 #define XGMAC_HWFEAT_L3L4FNUM GENMASK(30, 27) +#define XGMAC_HWFEAT_HASHTBLSZ GENMASK(25, 24) #define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) #define XGMAC_HWFEAT_SPHEN BIT(17) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 2b277b2c586b..5031398e612c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -472,7 +472,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw, dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2); /* Handle multiple unicast addresses */ - if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) { + if (netdev_uc_count(dev) > hw->unicast_filter_entries) { value |= XGMAC_FILTER_PR; } else { struct netdev_hw_addr *ha; @@ -523,8 +523,8 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw, struct stmmac_rss *cfg, u32 num_rxq) { void __iomem *ioaddr = hw->pcsr; + u32 value, *key; int i, ret; - u32 value; value = readl(ioaddr + XGMAC_RSS_CTRL); if (!cfg || !cfg->enable) { @@ -533,8 +533,9 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw, return 0; } - for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { - ret = dwxgmac2_rss_write_reg(ioaddr, true, i, cfg->key[i]); + key = (u32 *)cfg->key; + for (i = 0; i < (ARRAY_SIZE(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, key[i]); if (ret) return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 53c4a40d8386..965cbe3e6f51 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -380,6 +380,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); dma_cap->l3l4fnum = (hw_cap & XGMAC_HWFEAT_L3L4FNUM) >> 27; + dma_cap->hash_tb_sz = (hw_cap & XGMAC_HWFEAT_HASHTBLSZ) >> 24; dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3232738fb25..c76a1336a451 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -629,6 +629,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + ts_event_en = PTP_TCR_TSEVNTENA; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; ptp_over_ethernet = PTP_TCR_TSIPENA; @@ -4715,11 +4716,9 @@ int stmmac_suspend(struct device *dev) if (!ndev || !netif_running(ndev)) return 0; - mutex_lock(&priv->lock); + phylink_mac_change(priv->phylink, false); - rtnl_lock(); - phylink_stop(priv->phylink); - rtnl_unlock(); + mutex_lock(&priv->lock); netif_device_detach(ndev); stmmac_stop_all_queues(priv); @@ -4734,6 +4733,12 @@ int stmmac_suspend(struct device *dev) stmmac_pmt(priv, priv->hw, priv->wolopts); priv->irq_wake = 1; } else { + mutex_unlock(&priv->lock); + rtnl_lock(); + phylink_stop(priv->phylink); + rtnl_unlock(); + mutex_lock(&priv->lock); + stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); /* Disable clock in case of PWM is off */ @@ -4824,12 +4829,16 @@ int stmmac_resume(struct device *dev) stmmac_start_all_queues(priv); - rtnl_lock(); - phylink_start(priv->phylink); - rtnl_unlock(); - mutex_unlock(&priv->lock); + if (!device_may_wakeup(priv->device)) { + rtnl_lock(); + phylink_start(priv->phylink); + rtnl_unlock(); + } + + phylink_mac_change(priv->phylink, true); + return 0; } EXPORT_SYMBOL_GPL(stmmac_resume); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 173493db038c..df638b18b72c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -164,7 +164,7 @@ static int stmmac_enable(struct ptp_clock_info *ptp, /* structure describing a PTP hardware clock */ static struct ptp_clock_info stmmac_ptp_clock_ops = { .owner = THIS_MODULE, - .name = "stmmac_ptp_clock", + .name = "stmmac ptp", .max_adj = 62500000, .n_alarm = 0, .n_ext_ts = 0, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index 5f66f6161629..e4ac3c401432 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -487,8 +487,8 @@ static int stmmac_filter_check(struct stmmac_priv *priv) static int stmmac_test_hfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x01, 0x00, 0xcc, 0xcc, 0xdd, 0xdd}; - unsigned char bd_addr[ETH_ALEN] = {0x09, 0x00, 0xaa, 0xaa, 0xbb, 0xbb}; + unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; + unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05}; struct stmmac_packet_attrs attr = { }; int ret; @@ -496,6 +496,9 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv) if (ret) return ret; + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; + ret = dev_mc_add(priv->dev, gd_addr); if (ret) return ret; @@ -573,6 +576,8 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (!priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; /* Remove all MC addresses */ __dev_mc_unsync(priv->dev, NULL); @@ -611,6 +616,8 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (!priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; /* Remove all UC addresses */ __dev_uc_unsync(priv->dev, NULL); @@ -1564,10 +1571,6 @@ static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue) struct stmmac_packet_attrs attr = { }; int size = priv->dma_buf_sz; - /* Only XGMAC has SW support for multiple RX descs in same packet */ - if (priv->plat->has_xgmac) - size = priv->dev->max_mtu; - attr.dst = priv->dev->dev_addr; attr.max_size = size - ETH_FCS_LEN; attr.queue_mapping = queue; diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index ceddb424f887..0dd0ba915ab9 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -1137,10 +1137,11 @@ static void atusb_disconnect(struct usb_interface *interface) ieee802154_unregister_hw(atusb->hw); + usb_put_dev(atusb->usb_dev); + ieee802154_free_hw(atusb->hw); usb_set_intfdata(interface, NULL); - usb_put_dev(atusb->usb_dev); pr_debug("%s done\n", __func__); } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 11402dc347db..430c93786153 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3145,12 +3145,12 @@ static int ca8210_probe(struct spi_device *spi_device) goto error; } + priv->spi->dev.platform_data = pdata; ret = ca8210_get_platform_data(priv->spi, pdata); if (ret) { dev_crit(&spi_device->dev, "ca8210_get_platform_data failed\n"); goto error; } - priv->spi->dev.platform_data = pdata; ret = ca8210_dev_com_init(priv); if (ret) { diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 17f2300e63ee..8dc04e2590b1 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -800,7 +800,7 @@ mcr20a_handle_rx_read_buf_complete(void *context) if (!skb) return; - memcpy(skb_put(skb, len), lp->rx_buf, len); + __skb_put_data(skb, lp->rx_buf, len); ieee802154_rx_irqsafe(lp->hw, skb, lp->rx_lqi[0]); print_hex_dump_debug("mcr20a rx: ", DUMP_PREFIX_OFFSET, 16, 1, diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094746c0..1a251f76d09b 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static struct pernet_operations nsim_fib_net_ops = { void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -258,6 +258,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { pr_err("Failed to register fib notifier\n"); + unregister_pernet_subsys(&nsim_fib_net_ops); goto err_out; } diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 2aa7b2e60046..1eb5d4fb8925 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -15,6 +15,15 @@ #include <linux/of_gpio.h> #include <linux/gpio/consumer.h> +#define AT803X_SPECIFIC_STATUS 0x11 +#define AT803X_SS_SPEED_MASK (3 << 14) +#define AT803X_SS_SPEED_1000 (2 << 14) +#define AT803X_SS_SPEED_100 (1 << 14) +#define AT803X_SS_SPEED_10 (0 << 14) +#define AT803X_SS_DUPLEX BIT(13) +#define AT803X_SS_SPEED_DUPLEX_RESOLVED BIT(11) +#define AT803X_SS_MDIX BIT(6) + #define AT803X_INTR_ENABLE 0x12 #define AT803X_INTR_ENABLE_AUTONEG_ERR BIT(15) #define AT803X_INTR_ENABLE_SPEED_CHANGED BIT(14) @@ -357,6 +366,64 @@ static int at803x_aneg_done(struct phy_device *phydev) return aneg_done; } +static int at803x_read_status(struct phy_device *phydev) +{ + int ss, err, old_link = phydev->link; + + /* Update the link, but return if there was an error */ + err = genphy_update_link(phydev); + if (err) + return err; + + /* why bother the PHY if nothing can have changed */ + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + return 0; + + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + + err = genphy_read_lpa(phydev); + if (err < 0) + return err; + + /* Read the AT8035 PHY-Specific Status register, which indicates the + * speed and duplex that the PHY is actually using, irrespective of + * whether we are in autoneg mode or not. + */ + ss = phy_read(phydev, AT803X_SPECIFIC_STATUS); + if (ss < 0) + return ss; + + if (ss & AT803X_SS_SPEED_DUPLEX_RESOLVED) { + switch (ss & AT803X_SS_SPEED_MASK) { + case AT803X_SS_SPEED_10: + phydev->speed = SPEED_10; + break; + case AT803X_SS_SPEED_100: + phydev->speed = SPEED_100; + break; + case AT803X_SS_SPEED_1000: + phydev->speed = SPEED_1000; + break; + } + if (ss & AT803X_SS_DUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + if (ss & AT803X_SS_MDIX) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + } + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) + phy_resolve_aneg_pause(phydev); + + return 0; +} + static struct phy_driver at803x_driver[] = { { /* ATHEROS 8035 */ @@ -370,6 +437,7 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_GBIT_FEATURES */ + .read_status = at803x_read_status, .ack_interrupt = at803x_ack_interrupt, .config_intr = at803x_config_intr, }, { @@ -399,6 +467,7 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_GBIT_FEATURES */ + .read_status = at803x_read_status, .aneg_done = at803x_aneg_done, .ack_interrupt = &at803x_ack_interrupt, .config_intr = &at803x_config_intr, diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index e282600bd83e..c1d345c3cab3 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -121,7 +121,7 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value) return; if (mdiodev->reset_gpio) - gpiod_set_value(mdiodev->reset_gpio, value); + gpiod_set_value_cansleep(mdiodev->reset_gpio, value); if (mdiodev->reset_ctrl) { if (value) diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 369903d9b6ec..9412669b579c 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -283,6 +283,18 @@ void of_set_phy_eee_broken(struct phy_device *phydev) phydev->eee_broken_modes = broken; } +void phy_resolve_aneg_pause(struct phy_device *phydev) +{ + if (phydev->duplex == DUPLEX_FULL) { + phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + phydev->lp_advertising); + phydev->asym_pause = linkmode_test_bit( + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydev->lp_advertising); + } +} +EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause); + /** * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings * @phydev: The phy_device struct @@ -305,13 +317,7 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev) break; } - if (phydev->duplex == DUPLEX_FULL) { - phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->lp_advertising); - phydev->asym_pause = linkmode_test_bit( - ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->lp_advertising); - } + phy_resolve_aneg_pause(phydev); } EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 7c92afd36bbe..119e6f466056 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -457,6 +457,11 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) val); change_autoneg = true; break; + case MII_CTRL1000: + mii_ctrl1000_mod_linkmode_adv_t(phydev->advertising, + val); + change_autoneg = true; + break; default: /* do nothing */ break; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d347ddcac45b..9d2bbb13293e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1783,32 +1783,9 @@ done: } EXPORT_SYMBOL(genphy_update_link); -/** - * genphy_read_status - check the link status and update current link state - * @phydev: target phy_device struct - * - * Description: Check the link, then figure out the current state - * by comparing what we advertise with what the link partner - * advertises. Start by checking the gigabit possibilities, - * then move on to 10/100. - */ -int genphy_read_status(struct phy_device *phydev) +int genphy_read_lpa(struct phy_device *phydev) { - int lpa, lpagb, err, old_link = phydev->link; - - /* Update the link, but return if there was an error */ - err = genphy_update_link(phydev); - if (err) - return err; - - /* why bother the PHY if nothing can have changed */ - if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) - return 0; - - phydev->speed = SPEED_UNKNOWN; - phydev->duplex = DUPLEX_UNKNOWN; - phydev->pause = 0; - phydev->asym_pause = 0; + int lpa, lpagb; if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (phydev->is_gigabit_capable) { @@ -1838,6 +1815,44 @@ int genphy_read_status(struct phy_device *phydev) return lpa; mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa); + } + + return 0; +} +EXPORT_SYMBOL(genphy_read_lpa); + +/** + * genphy_read_status - check the link status and update current link state + * @phydev: target phy_device struct + * + * Description: Check the link, then figure out the current state + * by comparing what we advertise with what the link partner + * advertises. Start by checking the gigabit possibilities, + * then move on to 10/100. + */ +int genphy_read_status(struct phy_device *phydev) +{ + int err, old_link = phydev->link; + + /* Update the link, but return if there was an error */ + err = genphy_update_link(phydev); + if (err) + return err; + + /* why bother the PHY if nothing can have changed */ + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + return 0; + + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + + err = genphy_read_lpa(phydev); + if (err < 0) + return err; + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { phy_resolve_aneg_linkmode(phydev); } else if (phydev->autoneg == AUTONEG_DISABLE) { int bmcr = phy_read(phydev, MII_BMCR); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a5a57ca94c1a..20e2ebe458f2 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -576,7 +576,7 @@ static int phylink_register_sfp(struct phylink *pl, /** * phylink_create() - create a phylink instance - * @ndev: a pointer to the &struct net_device + * @config: a pointer to the target &struct phylink_config * @fwnode: a pointer to a &struct fwnode_handle describing the network * interface * @iface: the desired link mode defined by &typedef phy_interface_t diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 734de7de03f7..e1fabb3e3246 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -238,7 +238,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); - nf_reset(skb); + nf_reset_ct(skb); skb->ip_summed = CHECKSUM_NONE; ip_select_ident(net, skb, NULL); @@ -358,7 +358,7 @@ static int pptp_rcv(struct sk_buff *skb) po = lookup_chan(htons(header->call_id), iph->saddr); if (po) { skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk_pppox(po), skb, 0); } drop: diff --git a/drivers/net/tun.c b/drivers/net/tun.c index aab0be40d443..a8d3141582a5 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -526,8 +526,8 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ - if (e->queue_index != queue_index) - e->queue_index = queue_index; + if (READ_ONCE(e->queue_index) != queue_index) + WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); @@ -1104,7 +1104,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) */ skb_orphan(skb); - nf_reset(skb); + nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index ce78714f536f..a505b2ab88b8 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2620,14 +2620,18 @@ static struct hso_device *hso_create_bulk_serial_device( */ if (serial->tiocmget) { tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; + } + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); if (tiocmget->urb) { mutex_init(&tiocmget->mutex); init_waitqueue_head(&tiocmget->waitq); - tiocmget->endp = hso_get_ep( - interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); } else hso_free_tiomget(serial); } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b6dc5d714b5e..596428ec71df 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1327,6 +1327,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ @@ -1350,6 +1351,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1e2d, 0x0082, 4)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 5)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0083, 4)}, /* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/ + {QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)}, /* Cinterion CLS8 */ {QMI_FIXED_INTF(0x413c, 0x81a2, 8)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a3, 8)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 08726090570e..cee9fef925cd 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4799,10 +4799,9 @@ static int rtl8152_reset_resume(struct usb_interface *intf) struct r8152 *tp = usb_get_intfdata(intf); clear_bit(SELECTIVE_SUSPEND, &tp->flags); - mutex_lock(&tp->control); tp->rtl_ops.init(tp); queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - mutex_unlock(&tp->control); + set_ethernet_addr(tp); return rtl8152_resume(intf); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ba98e0971b84..5a635f028bdc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1585,7 +1585,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); - nf_reset(skb); + nf_reset_ct(skb); } /* If running out of space, stop queue to avoid getting packets that we diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index a4b38a980c3c..ee52bde058df 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -366,7 +366,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, struct neighbour *neigh; int ret; - nf_reset(skb); + nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -459,7 +459,7 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, /* reset skb device */ if (likely(err == 1)) - nf_reset(skb); + nf_reset_ct(skb); else skb = NULL; @@ -560,7 +560,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s bool is_v6gw = false; int ret = -EINVAL; - nf_reset(skb); + nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { @@ -670,7 +670,7 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, /* reset skb device */ if (likely(err == 1)) - nf_reset(skb); + nf_reset_ct(skb); else skb = NULL; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 635956024e88..14f562cd715c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1261,8 +1261,8 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw, skb_orphan(skb); skb_dst_drop(skb); skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); /* * Get absolute mactime here so all HWs RX at the "same time", and @@ -4026,7 +4026,7 @@ static int __init init_mac80211_hwsim(void) err = dev_alloc_name(hwsim_mon, hwsim_mon->name); if (err < 0) { rtnl_unlock(); - goto out_free_radios; + goto out_free_mon; } err = register_netdevice(hwsim_mon); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e14ec75b61d6..482c6c8b0fb7 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -887,9 +887,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb, return 0; } -static RING_IDX xennet_fill_frags(struct netfront_queue *queue, - struct sk_buff *skb, - struct sk_buff_head *list) +static int xennet_fill_frags(struct netfront_queue *queue, + struct sk_buff *skb, + struct sk_buff_head *list) { RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; @@ -908,7 +908,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { queue->rx.rsp_cons = ++cons + skb_queue_len(list); kfree_skb(nskb); - return ~0U; + return -ENOENT; } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, @@ -919,7 +919,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, kfree_skb(nskb); } - return cons; + queue->rx.rsp_cons = cons; + + return 0; } static int checksum_setup(struct net_device *dev, struct sk_buff *skb) @@ -1045,8 +1047,7 @@ err: skb->data_len = rx->status; skb->len += rx->status; - i = xennet_fill_frags(queue, skb, &tmpq); - if (unlikely(i == ~0U)) + if (unlikely(xennet_fill_frags(queue, skb, &tmpq))) goto err; if (rx->flags & XEN_NETRXF_csum_blank) @@ -1056,7 +1057,7 @@ err: __skb_queue_tail(&rxq, skb); - queue->rx.rsp_cons = ++i; + i = ++queue->rx.rsp_cons; work_done++; } diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index c5289eaf17ee..e897e4d768ef 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -547,18 +547,25 @@ static int pn533_usb_probe(struct usb_interface *interface, rc = pn533_finalize_setup(priv); if (rc) - goto error; + goto err_deregister; usb_set_intfdata(interface, phy); return 0; +err_deregister: + pn533_unregister_device(phy->priv); error: + usb_kill_urb(phy->in_urb); + usb_kill_urb(phy->out_urb); + usb_kill_urb(phy->ack_urb); + usb_free_urb(phy->in_urb); usb_free_urb(phy->out_urb); usb_free_urb(phy->ack_urb); usb_put_dev(phy->udev); kfree(in_buf); + kfree(phy->ack_buffer); return rc; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 108f60b46804..fd7dea36c3b6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns) */ if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) return; - revalidate_disk(ns->disk); blk_set_queue_dying(ns->queue); /* Forcibly unquiesce queues to avoid blocking dispatch */ blk_mq_unquiesce_queue(ns->queue); + /* + * Revalidate after unblocking dispatchers that may be holding bd_butex + */ + revalidate_disk(ns->disk); } static void nvme_queue_scan(struct nvme_ctrl *ctrl) @@ -847,7 +850,7 @@ out: static int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, u32 *result, unsigned timeout) + u32 meta_seed, u64 *result, unsigned timeout) { bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; @@ -888,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, else ret = nvme_req(req)->status; if (result) - *result = le32_to_cpu(nvme_req(req)->result.u32); + *result = le64_to_cpu(nvme_req(req)->result.u64); if (meta && !ret && !write) { if (copy_to_user(meta_buffer, meta, meta_len)) ret = -EFAULT; @@ -1335,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_command c; unsigned timeout = 0; u32 effects; + u64 result; + int status; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + if (copy_from_user(&cmd, ucmd, sizeof(cmd))) + return -EFAULT; + if (cmd.flags) + return -EINVAL; + + memset(&c, 0, sizeof(c)); + c.common.opcode = cmd.opcode; + c.common.flags = cmd.flags; + c.common.nsid = cpu_to_le32(cmd.nsid); + c.common.cdw2[0] = cpu_to_le32(cmd.cdw2); + c.common.cdw2[1] = cpu_to_le32(cmd.cdw3); + c.common.cdw10 = cpu_to_le32(cmd.cdw10); + c.common.cdw11 = cpu_to_le32(cmd.cdw11); + c.common.cdw12 = cpu_to_le32(cmd.cdw12); + c.common.cdw13 = cpu_to_le32(cmd.cdw13); + c.common.cdw14 = cpu_to_le32(cmd.cdw14); + c.common.cdw15 = cpu_to_le32(cmd.cdw15); + + if (cmd.timeout_ms) + timeout = msecs_to_jiffies(cmd.timeout_ms); + + effects = nvme_passthru_start(ctrl, ns, cmd.opcode); + status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, + (void __user *)(uintptr_t)cmd.addr, cmd.data_len, + (void __user *)(uintptr_t)cmd.metadata, + cmd.metadata_len, 0, &result, timeout); + nvme_passthru_end(ctrl, effects); + + if (status >= 0) { + if (put_user(result, &ucmd->result)) + return -EFAULT; + } + + return status; +} + +static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, + struct nvme_passthru_cmd64 __user *ucmd) +{ + struct nvme_passthru_cmd64 cmd; + struct nvme_command c; + unsigned timeout = 0; + u32 effects; int status; if (!capable(CAP_SYS_ADMIN)) @@ -1405,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx) srcu_read_unlock(&head->srcu, idx); } +static bool is_ctrl_ioctl(unsigned int cmd) +{ + if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD) + return true; + if (is_sed_ioctl(cmd)) + return true; + return false; +} + +static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, + void __user *argp, + struct nvme_ns_head *head, + int srcu_idx) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + int ret; + + nvme_get_ctrl(ns->ctrl); + nvme_put_ns_from_disk(head, srcu_idx); + + switch (cmd) { + case NVME_IOCTL_ADMIN_CMD: + ret = nvme_user_cmd(ctrl, NULL, argp); + break; + case NVME_IOCTL_ADMIN64_CMD: + ret = nvme_user_cmd64(ctrl, NULL, argp); + break; + default: + ret = sed_ioctl(ctrl->opal_dev, cmd, argp); + break; + } + nvme_put_ctrl(ctrl); + return ret; +} + static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1422,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, * seperately and drop the ns SRCU reference early. This avoids a * deadlock when deleting namespaces using the passthrough interface. */ - if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) { - struct nvme_ctrl *ctrl = ns->ctrl; - - nvme_get_ctrl(ns->ctrl); - nvme_put_ns_from_disk(head, srcu_idx); - - if (cmd == NVME_IOCTL_ADMIN_CMD) - ret = nvme_user_cmd(ctrl, NULL, argp); - else - ret = sed_ioctl(ctrl->opal_dev, cmd, argp); - - nvme_put_ctrl(ctrl); - return ret; - } + if (is_ctrl_ioctl(cmd)) + return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx); switch (cmd) { case NVME_IOCTL_ID: @@ -1448,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, case NVME_IOCTL_SUBMIT_IO: ret = nvme_submit_io(ns, argp); break; + case NVME_IOCTL_IO64_CMD: + ret = nvme_user_cmd64(ns->ctrl, ns, argp); + break; default: if (ns->ndev) ret = nvme_nvm_ioctl(ns, cmd, arg); @@ -2289,6 +2366,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x14a4, .fr = "22301111", .quirks = NVME_QUIRK_SIMPLE_SUSPEND, + }, + { + /* + * This Kingston E8FK11.T firmware version has no interrupt + * after resume with actions related to suspend to idle + * https://bugzilla.kernel.org/show_bug.cgi?id=204887 + */ + .vid = 0x2646, + .fr = "E8FK11.T", + .quirks = NVME_QUIRK_SIMPLE_SUSPEND, } }; @@ -2540,8 +2627,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) list_add_tail(&subsys->entry, &nvme_subsystems); } - if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj, - dev_name(ctrl->device))) { + ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj, + dev_name(ctrl->device)); + if (ret) { dev_err(ctrl->device, "failed to create sysfs link from subsystem.\n"); goto out_put_subsystem; @@ -2838,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case NVME_IOCTL_ADMIN_CMD: return nvme_user_cmd(ctrl, NULL, argp); + case NVME_IOCTL_ADMIN64_CMD: + return nvme_user_cmd64(ctrl, NULL, argp); case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: @@ -3045,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); nvme_show_int_function(cntlid); nvme_show_int_function(numa_node); +nvme_show_int_function(queue_count); +nvme_show_int_function(sqsize); static ssize_t nvme_sysfs_delete(struct device *dev, struct device_attribute *attr, const char *buf, @@ -3125,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_address.attr, &dev_attr_state.attr, &dev_attr_numa_node.attr, + &dev_attr_queue_count.attr, + &dev_attr_sqsize.attr, NULL }; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index b5013c101b35..38a83ef5bcd3 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -221,6 +221,7 @@ struct nvme_ctrl { u16 oacs; u16 nssa; u16 nr_streams; + u16 sqsize; u32 max_namespaces; atomic_t abort_limit; u8 vwc; @@ -269,7 +270,6 @@ struct nvme_ctrl { u16 hmmaxd; /* Fabrics only */ - u16 sqsize; u32 ioccsz; u32 iorcsz; u16 icdoff; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c0808f9eb8ab..bb88681f4dc3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2946,11 +2946,21 @@ static int nvme_suspend(struct device *dev) if (ret < 0) goto unfreeze; + /* + * A saved state prevents pci pm from generically controlling the + * device's power. If we're using protocol specific settings, we don't + * want pci interfering. + */ + pci_save_state(pdev); + ret = nvme_set_power_state(ctrl, ctrl->npss); if (ret < 0) goto unfreeze; if (ret) { + /* discard the saved state */ + pci_load_saved_state(pdev, NULL); + /* * Clearing npss forces a controller reset on resume. The * correct value will be resdicovered then. @@ -2958,14 +2968,7 @@ static int nvme_suspend(struct device *dev) nvme_dev_disable(ndev, true); ctrl->npss = 0; ret = 0; - goto unfreeze; } - /* - * A saved state prevents pci pm from generically controlling the - * device's power. If we're using protocol specific settings, we don't - * want pci interfering. - */ - pci_save_state(pdev); unfreeze: nvme_unfreeze(ctrl); return ret; @@ -3090,6 +3093,9 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index dfa07bb9dfeb..4d280160dd3f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue) static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev) { return min_t(u32, NVME_RDMA_MAX_SEGMENTS, - ibdev->attrs.max_fast_reg_page_list_len); + ibdev->attrs.max_fast_reg_page_list_len - 1); } static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) @@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) const int cq_factor = send_wr_factor + 1; /* + RECV */ int comp_vector, idx = nvme_rdma_queue_idx(queue); enum ib_poll_context poll_ctx; - int ret; + int ret, pages_per_mr; queue->device = nvme_rdma_find_get_device(queue->cm_id); if (!queue->device) { @@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) goto out_destroy_qp; } + /* + * Currently we don't use SG_GAPS MR's so if the first entry is + * misaligned we'll end up using two entries for a single data page, + * so one additional entry is required. + */ + pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1; ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs, queue->queue_size, IB_MR_TYPE_MEM_REG, - nvme_rdma_get_max_fr_pages(ibdev), 0); + pages_per_mr, 0); if (ret) { dev_err(queue->ctrl->ctrl.device, "failed to initialize MR pool sized %d for QID %d\n", @@ -614,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx) if (!ret) { set_bit(NVME_RDMA_Q_LIVE, &queue->flags); } else { - __nvme_rdma_stop_queue(queue); + if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) + __nvme_rdma_stop_queue(queue); dev_info(ctrl->ctrl.device, "failed to connect queue: %d ret=%d\n", idx, ret); } @@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, if (error) goto out_stop_queue; - ctrl->ctrl.max_hw_sectors = - (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9); + ctrl->ctrl.max_segments = ctrl->max_fr_pages; + ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9); blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 4ffd5957637a..385a5212c10f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w) { struct nvme_tcp_queue *queue = container_of(w, struct nvme_tcp_queue, io_work); - unsigned long start = jiffies + msecs_to_jiffies(1); + unsigned long deadline = jiffies + msecs_to_jiffies(1); do { bool pending = false; @@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w) if (!pending) return; - } while (time_after(jiffies, start)); /* quota is exhausted */ + } while (!time_after(jiffies, deadline)); /* quota is exhausted */ queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index de0bff70ebb6..32008d85172b 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -11,10 +11,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) { const struct queue_limits *ql = &bdev_get_queue(bdev)->limits; - /* Number of physical blocks per logical block. */ - const u32 ppl = ql->physical_block_size / ql->logical_block_size; - /* Physical blocks per logical block, 0's based. */ - const __le16 ppl0b = to0based(ppl); + /* Number of logical blocks per physical block. */ + const u32 lpp = ql->physical_block_size / ql->logical_block_size; + /* Logical blocks per physical block, 0's based. */ + const __le16 lpp0b = to0based(lpp); /* * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN, @@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) * field from the identify controller data structure should be used. */ id->nsfeat |= 1 << 1; - id->nawun = ppl0b; - id->nawupf = ppl0b; - id->nacwu = ppl0b; + id->nawun = lpp0b; + id->nawupf = lpp0b; + id->nacwu = lpp0b; /* * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and @@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) */ id->nsfeat |= 1 << 4; /* NPWG = Namespace Preferred Write Granularity. 0's based */ - id->npwg = ppl0b; + id->npwg = lpp0b; /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index bf4f03474e89..d535080b781f 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) return 0; err: - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); return NVME_SC_INTERNAL; } @@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) if (queue->nvme_sq.sqhd_disabled) { kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); } return 1; @@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd, return -EAGAIN; kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); cmd->queue->snd_cmd = NULL; nvmet_tcp_put_cmd(cmd); return 1; @@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd) nvmet_req_uninit(&cmd->req); nvmet_tcp_unmap_pdu_iovec(cmd); kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); } static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 960961fb0d7c..0517272a268e 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -97,8 +97,8 @@ config PTP_1588_CLOCK_PCH help This driver adds support for using the PCH EG20T as a PTP clock. The hardware supports time stamping of PTP packets - when using the end-to-end delay (E2E) mechansim. The peer - delay mechansim (P2P) is not supported. + when using the end-to-end delay (E2E) mechanism. The peer + delay mechanism (P2P) is not supported. This clock is only useful if your PTP programs are getting hardware time stamps on the PTP Ethernet packets using the diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index c61f00b72e15..a577218d1ab7 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -507,6 +507,8 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET; } + spin_lock_init(&ptp_qoriq->lock); + ktime_get_real_ts64(&now); ptp_qoriq_settime(&ptp_qoriq->caps, &now); @@ -514,7 +516,6 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT | (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT; - spin_lock_init(&ptp_qoriq->lock); spin_lock_irqsave(&ptp_qoriq->lock, flags); regs = &ptp_qoriq->regs; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index fc53e1e221f0..c94184d080f8 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1553,8 +1553,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device) if (rc == 0) { memcpy(&private->vsq, vsq, sizeof(*vsq)); } else { - dev_warn(&device->cdev->dev, - "Reading the volume storage information failed with rc=%d\n", rc); + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "Reading the volume storage information failed with rc=%d", rc); } if (useglobal) @@ -1737,8 +1737,8 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) if (rc == 0) { dasd_eckd_cpy_ext_pool_data(device, lcq); } else { - dev_warn(&device->cdev->dev, - "Reading the logical configuration failed with rc=%d\n", rc); + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "Reading the logical configuration failed with rc=%d", rc); } dasd_sfree_request(cqr, cqr->memdev); @@ -2020,14 +2020,10 @@ dasd_eckd_check_characteristics(struct dasd_device *device) dasd_eckd_read_features(device); /* Read Volume Information */ - rc = dasd_eckd_read_vol_info(device); - if (rc) - goto out_err3; + dasd_eckd_read_vol_info(device); /* Read Extent Pool Information */ - rc = dasd_eckd_read_ext_pool_info(device); - if (rc) - goto out_err3; + dasd_eckd_read_ext_pool_info(device); /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, @@ -2059,9 +2055,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device) if (readonly) set_bit(DASD_FLAG_DEVICE_RO, &device->flags); - if (dasd_eckd_is_ese(device)) - dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1); - dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) " "with %d cylinders, %d heads, %d sectors%s\n", private->rdc_data.dev_type, @@ -3695,14 +3688,6 @@ static int dasd_eckd_release_space(struct dasd_device *device, return -EINVAL; } -static struct dasd_ccw_req * -dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block, - struct request *req, sector_t first_trk, - sector_t last_trk) -{ - return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1); -} - static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( struct dasd_device *startdev, struct dasd_block *block, @@ -4447,10 +4432,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev, cmdwtd = private->features.feature[12] & 0x40; use_prefix = private->features.feature[8] & 0x01; - if (req_op(req) == REQ_OP_DISCARD) - return dasd_eckd_build_cp_discard(startdev, block, req, - first_trk, last_trk); - cqr = NULL; if (cdlspecial || dasd_page_cache) { /* do nothing, just fall through to the cmd mode single case */ @@ -4729,14 +4710,12 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base, struct dasd_block *block, struct request *req) { - struct dasd_device *startdev = NULL; struct dasd_eckd_private *private; - struct dasd_ccw_req *cqr; + struct dasd_device *startdev; unsigned long flags; + struct dasd_ccw_req *cqr; - /* Discard requests can only be processed on base devices */ - if (req_op(req) != REQ_OP_DISCARD) - startdev = dasd_alias_get_start_dev(base); + startdev = dasd_alias_get_start_dev(base); if (!startdev) startdev = base; private = startdev->private; @@ -5663,14 +5642,10 @@ static int dasd_eckd_restore_device(struct dasd_device *device) dasd_eckd_read_features(device); /* Read Volume Information */ - rc = dasd_eckd_read_vol_info(device); - if (rc) - goto out_err2; + dasd_eckd_read_vol_info(device); /* Read Extent Pool Information */ - rc = dasd_eckd_read_ext_pool_info(device); - if (rc) - goto out_err2; + dasd_eckd_read_ext_pool_info(device); /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, @@ -6521,20 +6496,8 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) unsigned int logical_block_size = block->bp_block; struct request_queue *q = block->request_queue; struct dasd_device *device = block->base; - struct dasd_eckd_private *private; - unsigned int max_discard_sectors; - unsigned int max_bytes; - unsigned int ext_bytes; /* Extent Size in Bytes */ - int recs_per_trk; - int trks_per_cyl; - int ext_limit; - int ext_size; /* Extent Size in Cylinders */ int max; - private = device->private; - trks_per_cyl = private->rdc_data.trk_per_cyl; - recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size); - if (device->features & DASD_FEATURE_USERAW) { /* * the max_blocks value for raw_track access is 256 @@ -6555,28 +6518,6 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) /* With page sized segments each segment can be translated into one idaw/tidaw */ blk_queue_max_segment_size(q, PAGE_SIZE); blk_queue_segment_boundary(q, PAGE_SIZE - 1); - - if (dasd_eckd_is_ese(device)) { - /* - * Depending on the extent size, up to UINT_MAX bytes can be - * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the - * device limits should be exceeded. - */ - ext_size = dasd_eckd_ext_size(device); - ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX); - ext_bytes = ext_size * trks_per_cyl * recs_per_trk * - logical_block_size; - max_bytes = UINT_MAX - (UINT_MAX % ext_bytes); - if (max_bytes / ext_bytes > ext_limit) - max_bytes = ext_bytes * ext_limit; - - max_discard_sectors = max_bytes / 512; - - blk_queue_max_discard_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.discard_granularity = ext_bytes; - q->limits.discard_alignment = ext_bytes; - } } static struct ccw_driver dasd_eckd_driver = { diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index f4ca1d29d61b..cd164886132f 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -113,7 +113,7 @@ static void set_impl_params(struct qdio_irq *irq_ptr, irq_ptr->qib.pfmt = qib_param_field_format; if (qib_param_field) memcpy(irq_ptr->qib.parm, qib_param_field, - QDIO_MAX_BUFFERS_PER_Q); + sizeof(irq_ptr->qib.parm)); if (!input_slib_elements) goto output; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a7868c8133ee..dda274351c21 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4715,8 +4715,7 @@ static int qeth_qdio_establish(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "qdioest"); - qib_param_field = kzalloc(QDIO_MAX_BUFFERS_PER_Q, - GFP_KERNEL); + qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL); if (!qib_param_field) { rc = -ENOMEM; goto out_free_nothing; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index b8799cd3e7aa..bd8143e51747 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2021,10 +2021,10 @@ static bool qeth_l2_vnicc_recover_char(struct qeth_card *card, u32 vnicc, static void qeth_l2_vnicc_init(struct qeth_card *card) { u32 *timeout = &card->options.vnicc.learning_timeout; + bool enable, error = false; unsigned int chars_len, i; unsigned long chars_tmp; u32 sup_cmds, vnicc; - bool enable, error; QETH_CARD_TEXT(card, 2, "vniccini"); /* reset rx_bcast */ @@ -2045,17 +2045,24 @@ static void qeth_l2_vnicc_init(struct qeth_card *card) chars_len = sizeof(card->options.vnicc.sup_chars) * BITS_PER_BYTE; for_each_set_bit(i, &chars_tmp, chars_len) { vnicc = BIT(i); - qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds); - if (!(sup_cmds & IPA_VNICC_SET_TIMEOUT) || - !(sup_cmds & IPA_VNICC_GET_TIMEOUT)) + if (qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds)) { + sup_cmds = 0; + error = true; + } + if ((sup_cmds & IPA_VNICC_SET_TIMEOUT) && + (sup_cmds & IPA_VNICC_GET_TIMEOUT)) + card->options.vnicc.getset_timeout_sup |= vnicc; + else card->options.vnicc.getset_timeout_sup &= ~vnicc; - if (!(sup_cmds & IPA_VNICC_ENABLE) || - !(sup_cmds & IPA_VNICC_DISABLE)) + if ((sup_cmds & IPA_VNICC_ENABLE) && + (sup_cmds & IPA_VNICC_DISABLE)) + card->options.vnicc.set_char_sup |= vnicc; + else card->options.vnicc.set_char_sup &= ~vnicc; } /* enforce assumed default values and recover settings, if changed */ - error = qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, - timeout); + error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, + timeout); chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT; chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE; chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE; diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index da00ca5fa5dc..401743e2b429 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -1923,6 +1923,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, struct fcoe_fcp_rsp_payload *fcp_rsp; struct bnx2fc_rport *tgt = io_req->tgt; struct scsi_cmnd *sc_cmd; + u16 scope = 0, qualifier = 0; /* scsi_cmd_cmpl is called with tgt lock held */ @@ -1990,12 +1991,30 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, if (io_req->cdb_status == SAM_STAT_TASK_SET_FULL || io_req->cdb_status == SAM_STAT_BUSY) { - /* Set the jiffies + retry_delay_timer * 100ms - for the rport/tgt */ - tgt->retry_delay_timestamp = jiffies + - fcp_rsp->retry_delay_timer * HZ / 10; + /* Newer array firmware with BUSY or + * TASK_SET_FULL may return a status that needs + * the scope bits masked. + * Or a huge delay timestamp up to 27 minutes + * can result. + */ + if (fcp_rsp->retry_delay_timer) { + /* Upper 2 bits */ + scope = fcp_rsp->retry_delay_timer + & 0xC000; + /* Lower 14 bits */ + qualifier = fcp_rsp->retry_delay_timer + & 0x3FFF; + } + if (scope > 0 && qualifier > 0 && + qualifier <= 0x3FEF) { + /* Set the jiffies + + * retry_delay_timer * 100ms + * for the rport/tgt + */ + tgt->retry_delay_timestamp = jiffies + + (qualifier * HZ / 10); + } } - } if (io_req->fcp_resid) scsi_set_resid(sc_cmd, io_req->fcp_resid); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index d1513fdf1e00..0847e682797b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -3683,7 +3683,7 @@ void hisi_sas_debugfs_work_handler(struct work_struct *work) } EXPORT_SYMBOL_GPL(hisi_sas_debugfs_work_handler); -void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) +static void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) { struct device *dev = hisi_hba->dev; int i; @@ -3705,7 +3705,7 @@ void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) devm_kfree(dev, hisi_hba->debugfs_port_reg[i]); } -int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba) +static int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba) { const struct hisi_sas_hw *hw = hisi_hba->hw; struct device *dev = hisi_hba->dev; @@ -3796,7 +3796,7 @@ fail: return -ENOMEM; } -void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba) +static void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba) { hisi_hba->debugfs_bist_dentry = debugfs_create_dir("bist", hisi_hba->debugfs_dir); diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 45a66048801b..ff6d4aa92421 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4183,11 +4183,11 @@ megaraid_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) */ if (pdev->subsystem_vendor == PCI_VENDOR_ID_COMPAQ && pdev->subsystem_device == 0xC000) - return -ENODEV; + goto out_disable_device; /* Now check the magic signature byte */ pci_read_config_word(pdev, PCI_CONF_AMISIG, &magic); if (magic != HBA_SIGNATURE_471 && magic != HBA_SIGNATURE) - return -ENODEV; + goto out_disable_device; /* Ok it is probably a megaraid */ } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 1659d35cd37b..59ca98f12afd 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -596,7 +596,7 @@ static void qedf_dcbx_handler(void *dev, struct qed_dcbx_get *get, u32 mib_type) tmp_prio = get->operational.app_prio.fcoe; if (qedf_default_prio > -1) qedf->prio = qedf_default_prio; - else if (tmp_prio < 0 || tmp_prio > 7) { + else if (tmp_prio > 7) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "FIP/FCoE prio %d out of range, setting to %d.\n", tmp_prio, QEDF_DEFAULT_PRIO); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 8190c2a27584..30bafd9d21e9 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2920,6 +2920,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) struct qla_hw_data *ha = vha->hw; uint16_t id = vha->vp_idx; + set_bit(VPORT_DELETE, &vha->dpc_flags); + while (test_bit(LOOP_RESYNC_ACTIVE, &vha->dpc_flags) || test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 873a6aef1c5c..6ffa9877c28b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -2396,6 +2396,7 @@ typedef struct fc_port { unsigned int query:1; unsigned int id_changed:1; unsigned int scan_needed:1; + unsigned int n2n_flag:1; struct completion nvme_del_done; uint32_t nvme_prli_service_param; @@ -2446,7 +2447,6 @@ typedef struct fc_port { uint8_t fc4_type; uint8_t fc4f_nvme; uint8_t scan_state; - uint8_t n2n_flag; unsigned long last_queue_full; unsigned long last_ramp_up; @@ -3036,6 +3036,7 @@ enum scan_flags_t { enum fc4type_t { FS_FC4TYPE_FCP = BIT_0, FS_FC4TYPE_NVME = BIT_1, + FS_FCP_IS_N2N = BIT_7, }; struct fab_scan_rp { @@ -4394,6 +4395,7 @@ typedef struct scsi_qla_host { #define IOCB_WORK_ACTIVE 31 #define SET_ZIO_THRESHOLD_NEEDED 32 #define ISP_ABORT_TO_ROM 33 +#define VPORT_DELETE 34 unsigned long pci_flags; #define PFLG_DISCONNECTED 0 /* PCI device removed */ diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index dc0e36676313..5298ed10059f 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3102,7 +3102,8 @@ int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id) { struct qla_work_evt *e; - if (test_bit(UNLOADING, &vha->dpc_flags)) + if (test_bit(UNLOADING, &vha->dpc_flags) || + (vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags))) return 0; e = qla2x00_alloc_work(vha, QLA_EVT_GPNID); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 643d2324082e..1d041313ec52 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -746,12 +746,15 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, break; default: if ((id.b24 != fcport->d_id.b24 && - fcport->d_id.b24) || + fcport->d_id.b24 && + fcport->loop_id != FC_NO_LOOP_ID) || (fcport->loop_id != FC_NO_LOOP_ID && fcport->loop_id != loop_id)) { ql_dbg(ql_dbg_disc, vha, 0x20e3, "%s %d %8phC post del sess\n", __func__, __LINE__, fcport->port_name); + if (fcport->n2n_flag) + fcport->d_id.b24 = 0; qlt_schedule_sess_for_deletion(fcport); return; } @@ -759,6 +762,8 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, } fcport->loop_id = loop_id; + if (fcport->n2n_flag) + fcport->d_id.b24 = id.b24; wwn = wwn_to_u64(fcport->port_name); qlt_find_sess_invalidate_other(vha, wwn, @@ -972,7 +977,7 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) wwn = wwn_to_u64(e->port_name); ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x20e8, - "%s %8phC %02x:%02x:%02x state %d/%d lid %x \n", + "%s %8phC %02x:%02x:%02x CLS %x/%x lid %x \n", __func__, (void *)&wwn, e->port_id[2], e->port_id[1], e->port_id[0], e->current_login_state, e->last_login_state, (loop_id & 0x7fff)); @@ -1499,7 +1504,8 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) (fcport->fw_login_state == DSC_LS_PRLI_PEND))) return 0; - if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) { + if (fcport->fw_login_state == DSC_LS_PLOGI_COMP && + !N2N_TOPO(vha->hw)) { if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline)) { set_bit(RELOGIN_NEEDED, &vha->dpc_flags); return 0; @@ -1570,8 +1576,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) qla24xx_post_gpdb_work(vha, fcport, 0); } else { ql_dbg(ql_dbg_disc, vha, 0x2118, - "%s %d %8phC post NVMe PRLI\n", - __func__, __LINE__, fcport->port_name); + "%s %d %8phC post %s PRLI\n", + __func__, __LINE__, fcport->port_name, + fcport->fc4f_nvme ? "NVME" : "FC"); qla24xx_post_prli_work(vha, fcport); } break; @@ -1853,17 +1860,38 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea) break; } - if (ea->fcport->n2n_flag) { + if (ea->fcport->fc4f_nvme) { ql_dbg(ql_dbg_disc, vha, 0x2118, "%s %d %8phC post fc4 prli\n", __func__, __LINE__, ea->fcport->port_name); ea->fcport->fc4f_nvme = 0; - ea->fcport->n2n_flag = 0; qla24xx_post_prli_work(vha, ea->fcport); + return; + } + + /* at this point both PRLI NVME & PRLI FCP failed */ + if (N2N_TOPO(vha->hw)) { + if (ea->fcport->n2n_link_reset_cnt < 3) { + ea->fcport->n2n_link_reset_cnt++; + /* + * remote port is not sending Plogi. Reset + * link to kick start his state machine + */ + set_bit(N2N_LINK_RESET, &vha->dpc_flags); + } else { + ql_log(ql_log_warn, vha, 0x2119, + "%s %d %8phC Unable to reconnect\n", + __func__, __LINE__, ea->fcport->port_name); + } + } else { + /* + * switch connect. login failed. Take connection + * down and allow relogin to retrigger + */ + ea->fcport->flags &= ~FCF_ASYNC_SENT; + ea->fcport->keep_nport_handle = 0; + qlt_schedule_sess_for_deletion(ea->fcport); } - ql_dbg(ql_dbg_disc, vha, 0x2119, - "%s %d %8phC unhandle event of %x\n", - __func__, __LINE__, ea->fcport->port_name, ea->data[0]); break; } } @@ -3190,7 +3218,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) for (j = 0; j < 2; j++, fwdt++) { if (!fwdt->template) { - ql_log(ql_log_warn, vha, 0x00ba, + ql_dbg(ql_dbg_init, vha, 0x00ba, "-> fwdt%u no template\n", j); continue; } @@ -4986,28 +5014,47 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) unsigned long flags; /* Inititae N2N login. */ - if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) { - /* borrowing */ - u32 *bp, i, sz; - - memset(ha->init_cb, 0, ha->init_cb_size); - sz = min_t(int, sizeof(struct els_plogi_payload), - ha->init_cb_size); - rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma, - (void *)ha->init_cb, sz); - if (rval == QLA_SUCCESS) { - bp = (uint32_t *)ha->init_cb; - for (i = 0; i < sz/4 ; i++, bp++) - *bp = cpu_to_be32(*bp); + if (N2N_TOPO(ha)) { + if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) { + /* borrowing */ + u32 *bp, i, sz; + + memset(ha->init_cb, 0, ha->init_cb_size); + sz = min_t(int, sizeof(struct els_plogi_payload), + ha->init_cb_size); + rval = qla24xx_get_port_login_templ(vha, + ha->init_cb_dma, (void *)ha->init_cb, sz); + if (rval == QLA_SUCCESS) { + bp = (uint32_t *)ha->init_cb; + for (i = 0; i < sz/4 ; i++, bp++) + *bp = cpu_to_be32(*bp); - memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb, - sizeof(ha->plogi_els_payld.data)); - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - } else { - ql_dbg(ql_dbg_init, vha, 0x00d1, - "PLOGI ELS param read fail.\n"); + memcpy(&ha->plogi_els_payld.data, + (void *)ha->init_cb, + sizeof(ha->plogi_els_payld.data)); + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + } else { + ql_dbg(ql_dbg_init, vha, 0x00d1, + "PLOGI ELS param read fail.\n"); + goto skip_login; + } + } + + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->n2n_flag) { + qla24xx_fcport_handle_login(vha, fcport); + return QLA_SUCCESS; + } + } +skip_login: + spin_lock_irqsave(&vha->work_lock, flags); + vha->scan.scan_retry++; + spin_unlock_irqrestore(&vha->work_lock, flags); + + if (vha->scan.scan_retry < MAX_SCAN_RETRIES) { + set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); + set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); } - return QLA_SUCCESS; } found_devs = 0; diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index e92e52aa6e9b..518eb954cf42 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2656,9 +2656,10 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) els_iocb->port_id[0] = sp->fcport->d_id.b.al_pa; els_iocb->port_id[1] = sp->fcport->d_id.b.area; els_iocb->port_id[2] = sp->fcport->d_id.b.domain; - els_iocb->s_id[0] = vha->d_id.b.al_pa; - els_iocb->s_id[1] = vha->d_id.b.area; - els_iocb->s_id[2] = vha->d_id.b.domain; + /* For SID the byte order is different than DID */ + els_iocb->s_id[1] = vha->d_id.b.al_pa; + els_iocb->s_id[2] = vha->d_id.b.area; + els_iocb->s_id[0] = vha->d_id.b.domain; if (elsio->u.els_logo.els_cmd == ELS_DCMD_PLOGI) { els_iocb->control_flags = 0; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4c858e2d0ea8..1cc6913f76c4 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -2249,7 +2249,7 @@ qla2x00_lip_reset(scsi_qla_host_t *vha) mbx_cmd_t mc; mbx_cmd_t *mcp = &mc; - ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x105a, + ql_dbg(ql_dbg_disc, vha, 0x105a, "Entered %s.\n", __func__); if (IS_CNA_CAPABLE(vha->hw)) { @@ -3883,14 +3883,24 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, case TOPO_N2N: ha->current_topology = ISP_CFG_N; spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + list_for_each_entry(fcport, &vha->vp_fcports, list) { + fcport->scan_state = QLA_FCPORT_SCAN; + fcport->n2n_flag = 0; + } + fcport = qla2x00_find_fcport_by_wwpn(vha, rptid_entry->u.f1.port_name, 1); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); if (fcport) { fcport->plogi_nack_done_deadline = jiffies + HZ; - fcport->dm_login_expire = jiffies + 3*HZ; + fcport->dm_login_expire = jiffies + 2*HZ; fcport->scan_state = QLA_FCPORT_FOUND; + fcport->n2n_flag = 1; + fcport->keep_nport_handle = 1; + if (vha->flags.nvme_enabled) + fcport->fc4f_nvme = 1; + switch (fcport->disc_state) { case DSC_DELETED: set_bit(RELOGIN_NEEDED, @@ -3924,7 +3934,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, rptid_entry->u.f1.port_name, rptid_entry->u.f1.node_name, NULL, - FC4_TYPE_UNKNOWN); + FS_FCP_IS_N2N); } /* if our portname is higher then initiate N2N login */ @@ -4023,6 +4033,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, list_for_each_entry(fcport, &vha->vp_fcports, list) { fcport->scan_state = QLA_FCPORT_SCAN; + fcport->n2n_flag = 0; } fcport = qla2x00_find_fcport_by_wwpn(vha, @@ -4032,6 +4043,14 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, fcport->login_retry = vha->hw->login_retry_count; fcport->plogi_nack_done_deadline = jiffies + HZ; fcport->scan_state = QLA_FCPORT_FOUND; + fcport->keep_nport_handle = 1; + fcport->n2n_flag = 1; + fcport->d_id.b.domain = + rptid_entry->u.f2.remote_nport_id[2]; + fcport->d_id.b.area = + rptid_entry->u.f2.remote_nport_id[1]; + fcport->d_id.b.al_pa = + rptid_entry->u.f2.remote_nport_id[0]; } } } diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 1a9a11ae7285..6afad68e5ba2 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -66,6 +66,7 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) uint16_t vp_id; struct qla_hw_data *ha = vha->hw; unsigned long flags = 0; + u8 i; mutex_lock(&ha->vport_lock); /* @@ -75,8 +76,9 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) * ensures no active vp_list traversal while the vport is removed * from the queue) */ - wait_event_timeout(vha->vref_waitq, !atomic_read(&vha->vref_count), - 10*HZ); + for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++) + wait_event_timeout(vha->vref_waitq, + atomic_read(&vha->vref_count), HZ); spin_lock_irqsave(&ha->vport_slock, flags); if (atomic_read(&vha->vref_count)) { @@ -262,6 +264,9 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb) spin_lock_irqsave(&ha->vport_slock, flags); list_for_each_entry(vha, &ha->vp_list, list) { if (vha->vp_idx) { + if (test_bit(VPORT_DELETE, &vha->dpc_flags)) + continue; + atomic_inc(&vha->vref_count); spin_unlock_irqrestore(&ha->vport_slock, flags); @@ -300,6 +305,20 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb) int qla2x00_vp_abort_isp(scsi_qla_host_t *vha) { + fc_port_t *fcport; + + /* + * To exclusively reset vport, we need to log it out first. + * Note: This control_vp can fail if ISP reset is already + * issued, this is expected, as the vp would be already + * logged out due to ISP reset. + */ + if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) { + qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); + list_for_each_entry(fcport, &vha->vp_fcports, list) + fcport->logout_on_delete = 0; + } + /* * Physical port will do most of the abort and recovery work. We can * just treat it as a loop down @@ -312,16 +331,9 @@ qla2x00_vp_abort_isp(scsi_qla_host_t *vha) atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); } - /* - * To exclusively reset vport, we need to log it out first. Note: this - * control_vp can fail if ISP reset is already issued, this is - * expected, as the vp would be already logged out due to ISP reset. - */ - if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) - qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); - ql_dbg(ql_dbg_taskm, vha, 0x801d, "Scheduling enable of Vport %d.\n", vha->vp_idx); + return qla24xx_enable_vp(vha); } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 73db01e3b4e4..3568031c6504 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1115,9 +1115,15 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) { + u8 i; + qla2x00_mark_all_devices_lost(vha, 0); - wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), 10*HZ); + for (i = 0; i < 10; i++) + wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), + HZ); + + flush_workqueue(vha->hw->wq); } /* @@ -5036,6 +5042,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) memcpy(fcport->port_name, e->u.new_sess.port_name, WWN_SIZE); + + if (e->u.new_sess.fc4_type & FS_FCP_IS_N2N) + fcport->n2n_flag = 1; + } else { ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %8phC mem alloc fail.\n", @@ -5134,11 +5144,9 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) if (dfcp) qlt_schedule_sess_for_deletion(tfcp); - - if (N2N_TOPO(vha->hw)) - fcport->flags &= ~FCF_FABRIC_DEVICE; - if (N2N_TOPO(vha->hw)) { + fcport->flags &= ~FCF_FABRIC_DEVICE; + fcport->keep_nport_handle = 1; if (vha->flags.nvme_enabled) { fcport->fc4f_nvme = 1; fcport->n2n_flag = 1; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0ffda6171614..a06e56224a55 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -953,7 +953,7 @@ void qlt_free_session_done(struct work_struct *work) struct qla_hw_data *ha = vha->hw; unsigned long flags; bool logout_started = false; - scsi_qla_host_t *base_vha; + scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev); struct qlt_plogi_ack_t *own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN]; @@ -1020,6 +1020,7 @@ void qlt_free_session_done(struct work_struct *work) if (logout_started) { bool traced = false; + u16 cnt = 0; while (!READ_ONCE(sess->logout_completed)) { if (!traced) { @@ -1029,6 +1030,9 @@ void qlt_free_session_done(struct work_struct *work) traced = true; } msleep(100); + cnt++; + if (cnt > 200) + break; } ql_dbg(ql_dbg_disc, vha, 0xf087, @@ -1101,6 +1105,7 @@ void qlt_free_session_done(struct work_struct *work) } spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + sess->free_pending = 0; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, "Unregistration of sess %p %8phC finished fcp_cnt %d\n", @@ -1109,17 +1114,9 @@ void qlt_free_session_done(struct work_struct *work) if (tgt && (tgt->sess_count == 0)) wake_up_all(&tgt->waitQ); - if (vha->fcport_count == 0) - wake_up_all(&vha->fcport_waitQ); - - base_vha = pci_get_drvdata(ha->pdev); - - sess->free_pending = 0; - - if (test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags)) - return; - - if ((!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) { + if (!test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags) && + !(vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags)) && + (!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) { switch (vha->host->active_mode) { case MODE_INITIATOR: case MODE_DUAL: @@ -1132,6 +1129,9 @@ void qlt_free_session_done(struct work_struct *work) break; } } + + if (vha->fcport_count == 0) + wake_up_all(&vha->fcport_waitQ); } /* ha->tgt.sess_lock supposed to be held on entry */ @@ -1161,7 +1161,7 @@ void qlt_unreg_sess(struct fc_port *sess) sess->last_login_gen = sess->login_gen; INIT_WORK(&sess->free_work, qlt_free_session_done); - schedule_work(&sess->free_work); + queue_work(sess->vha->hw->wq, &sess->free_work); } EXPORT_SYMBOL(qlt_unreg_sess); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index ed8b9ac805e6..542d2bac2922 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1837,8 +1837,7 @@ static int storvsc_probe(struct hv_device *device, /* * Set the number of HW queues we are supporting. */ - if (stor_device->num_sc != 0) - host->nr_hw_queues = stor_device->num_sc + 1; + host->nr_hw_queues = num_present_cpus(); /* * Set the error handler work queue. diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 034dd9cb9ec8..11a87f51c442 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8143,6 +8143,9 @@ int ufshcd_shutdown(struct ufs_hba *hba) { int ret = 0; + if (!hba->is_powered) + goto out; + if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba)) goto out; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index c64728fc21f2..a62057555d1b 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -349,10 +349,8 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) */ dst_release(skb_dst(skb)); skb_dst_set(skb, NULL); -#ifdef CONFIG_XFRM - secpath_reset(skb); -#endif - nf_reset(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); #ifdef CONFIG_NET_SCHED skb->tc_index = 0; diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile index 228a89b9bdd1..16f60c1e1766 100644 --- a/drivers/video/logo/Makefile +++ b/drivers/video/logo/Makefile @@ -18,23 +18,6 @@ obj-$(CONFIG_SPU_BASE) += logo_spe_clut224.o # How to generate logo's -# Use logo-cfiles to retrieve list of .c files to be built -logo-cfiles = $(notdir $(patsubst %.$(2), %.c, \ - $(wildcard $(srctree)/$(src)/*$(1).$(2)))) - - -# Mono logos -extra-y += $(call logo-cfiles,_mono,pbm) - -# VGA16 logos -extra-y += $(call logo-cfiles,_vga16,ppm) - -# 224 Logos -extra-y += $(call logo-cfiles,_clut224,ppm) - -# Gray 256 -extra-y += $(call logo-cfiles,_gray256,pgm) - pnmtologo := scripts/pnmtologo # Create commands like "pnmtologo -t mono -n logo_mac_mono -o ..." @@ -55,5 +38,5 @@ $(obj)/%_clut224.c: $(src)/%_clut224.ppm $(pnmtologo) FORCE $(obj)/%_gray256.c: $(src)/%_gray256.pgm $(pnmtologo) FORCE $(call if_changed,logo) -# Files generated that shall be removed upon make clean -clean-files := *.o *_mono.c *_vga16.c *_clut224.c *_gray256.c +# generated C files +targets += *_mono.c *_vga16.c *_clut224.c *_gray256.c diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 4e11de6cde81..5bae515c8e25 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -156,8 +156,10 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); (GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC) /* balloon_append: add the given page to the balloon. */ -static void __balloon_append(struct page *page) +static void balloon_append(struct page *page) { + __SetPageOffline(page); + /* Lowmem is re-populated first, so highmem pages go at list tail. */ if (PageHighMem(page)) { list_add_tail(&page->lru, &ballooned_pages); @@ -169,11 +171,6 @@ static void __balloon_append(struct page *page) wake_up(&balloon_wq); } -static void balloon_append(struct page *page) -{ - __balloon_append(page); -} - /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */ static struct page *balloon_retrieve(bool require_lowmem) { @@ -192,6 +189,7 @@ static struct page *balloon_retrieve(bool require_lowmem) else balloon_stats.balloon_low--; + __ClearPageOffline(page); return page; } @@ -377,8 +375,7 @@ static void xen_online_page(struct page *page, unsigned int order) for (i = 0; i < size; i++) { p = pfn_to_page(start_pfn + i); __online_page_set_limits(p); - __SetPageOffline(p); - __balloon_append(p); + balloon_append(p); } mutex_unlock(&balloon_mutex); } @@ -444,7 +441,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages) xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]); /* Relinquish the page back to the allocator. */ - __ClearPageOffline(page); free_reserved_page(page); } @@ -471,7 +467,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } - __SetPageOffline(page); adjust_managed_page_count(page, -1); xenmem_reservation_scrub_page(page); list_add(&page->lru, &pages); @@ -611,7 +606,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) while (pgno < nr_pages) { page = balloon_retrieve(true); if (page) { - __ClearPageOffline(page); pages[pgno++] = page; #ifdef CONFIG_XEN_HAVE_PVMMU /* @@ -653,10 +647,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages) mutex_lock(&balloon_mutex); for (i = 0; i < nr_pages; i++) { - if (pages[i]) { - __SetPageOffline(pages[i]); + if (pages[i]) balloon_append(pages[i]); - } } balloon_stats.target_unpopulated -= nr_pages; @@ -674,7 +666,6 @@ static void __init balloon_add_region(unsigned long start_pfn, unsigned long pages) { unsigned long pfn, extra_pfn_end; - struct page *page; /* * If the amount of usable memory has been limited (e.g., with @@ -684,11 +675,10 @@ static void __init balloon_add_region(unsigned long start_pfn, extra_pfn_end = min(max_pfn, start_pfn + pages); for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - page = pfn_to_page(pfn); /* totalram_pages and totalhigh_pages do not include the boot-time balloon extension, so don't subtract from it. */ - __balloon_append(page); + balloon_append(pfn_to_page(pfn)); } balloon_stats.total_pages += extra_pfn_end - start_pfn; diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index 89d60f8e3c18..d1ff2186ebb4 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -40,7 +40,7 @@ #define efi_data(op) (op.u.efi_runtime_call) -efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) +static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { struct xen_platform_op op = INIT_EFI_OP(get_time); @@ -61,9 +61,8 @@ efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_time); -efi_status_t xen_efi_set_time(efi_time_t *tm) +static efi_status_t xen_efi_set_time(efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_time); @@ -75,10 +74,10 @@ efi_status_t xen_efi_set_time(efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_time); -efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, - efi_time_t *tm) +static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, + efi_bool_t *pending, + efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time); @@ -98,9 +97,8 @@ efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_wakeup_time); -efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time); @@ -117,11 +115,10 @@ efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_wakeup_time); -efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 *attr, unsigned long *data_size, - void *data) +static efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(get_variable); @@ -141,11 +138,10 @@ efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_variable); -efi_status_t xen_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, - efi_guid_t *vendor) +static efi_status_t xen_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) { struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name); @@ -165,11 +161,10 @@ efi_status_t xen_efi_get_next_variable(unsigned long *name_size, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_variable); -efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, - void *data) +static efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(set_variable); @@ -186,11 +181,10 @@ efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_variable); -efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size) +static efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) { struct xen_platform_op op = INIT_EFI_OP(query_variable_info); @@ -208,9 +202,8 @@ efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_variable_info); -efi_status_t xen_efi_get_next_high_mono_count(u32 *count) +static efi_status_t xen_efi_get_next_high_mono_count(u32 *count) { struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count); @@ -221,10 +214,9 @@ efi_status_t xen_efi_get_next_high_mono_count(u32 *count) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_high_mono_count); -efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, unsigned long sg_list) +static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list) { struct xen_platform_op op = INIT_EFI_OP(update_capsule); @@ -241,11 +233,9 @@ efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_update_capsule); -efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, u64 *max_size, - int *reset_type) +static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, int *reset_type) { struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities); @@ -264,10 +254,9 @@ efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps); -void xen_efi_reset_system(int reset_type, efi_status_t status, - unsigned long data_size, efi_char16_t *data) +static void xen_efi_reset_system(int reset_type, efi_status_t status, + unsigned long data_size, efi_char16_t *data) { switch (reset_type) { case EFI_RESET_COLD: @@ -281,4 +270,25 @@ void xen_efi_reset_system(int reset_type, efi_status_t status, BUG(); } } -EXPORT_SYMBOL_GPL(xen_efi_reset_system); + +/* + * Set XEN EFI runtime services function pointers. Other fields of struct efi, + * e.g. efi.systab, will be set like normal EFI. + */ +void __init xen_efi_runtime_setup(void) +{ + efi.get_time = xen_efi_get_time; + efi.set_time = xen_efi_set_time; + efi.get_wakeup_time = xen_efi_get_wakeup_time; + efi.set_wakeup_time = xen_efi_set_wakeup_time; + efi.get_variable = xen_efi_get_variable; + efi.get_next_variable = xen_efi_get_next_variable; + efi.set_variable = xen_efi_set_variable; + efi.set_variable_nonblocking = xen_efi_set_variable; + efi.query_variable_info = xen_efi_query_variable_info; + efi.query_variable_info_nonblocking = xen_efi_query_variable_info; + efi.update_capsule = xen_efi_update_capsule; + efi.query_capsule_caps = xen_efi_query_capsule_caps; + efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; + efi.reset_system = xen_efi_reset_system; +} diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 69a626b0e594..c57c71b7d53d 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -775,7 +775,7 @@ static int pvcalls_back_poll(struct xenbus_device *dev, mappass->reqcopy = *req; icsk = inet_csk(mappass->sock->sk); queue = &icsk->icsk_accept_queue; - data = queue->rskq_accept_head != NULL; + data = READ_ONCE(queue->rskq_accept_head) != NULL; if (data) { mappass->reqcopy.cmd = 0; ret = 0; diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 08adc590f631..597af455a522 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -55,6 +55,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/miscdevice.h> +#include <linux/workqueue.h> #include <xen/xenbus.h> #include <xen/xen.h> @@ -116,6 +117,8 @@ struct xenbus_file_priv { wait_queue_head_t read_waitq; struct kref kref; + + struct work_struct wq; }; /* Read out any raw xenbus messages queued up. */ @@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch, mutex_unlock(&adap->dev_data->reply_mutex); } -static void xenbus_file_free(struct kref *kref) +static void xenbus_worker(struct work_struct *wq) { struct xenbus_file_priv *u; struct xenbus_transaction_holder *trans, *tmp; struct watch_adapter *watch, *tmp_watch; struct read_buffer *rb, *tmp_rb; - u = container_of(kref, struct xenbus_file_priv, kref); + u = container_of(wq, struct xenbus_file_priv, wq); /* * No need for locking here because there are no other users, @@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref) kfree(u); } +static void xenbus_file_free(struct kref *kref) +{ + struct xenbus_file_priv *u; + + /* + * We might be called in xenbus_thread(). + * Use workqueue to avoid deadlock. + */ + u = container_of(kref, struct xenbus_file_priv, kref); + schedule_work(&u->wq); +} + static struct xenbus_transaction_holder *xenbus_get_transaction( struct xenbus_file_priv *u, uint32_t tx_id) { @@ -650,6 +665,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) INIT_LIST_HEAD(&u->watches); INIT_LIST_HEAD(&u->read_buffers); init_waitqueue_head(&u->read_waitq); + INIT_WORK(&u->wq, xenbus_worker); mutex_init(&u->reply_mutex); mutex_init(&u->msgbuffer_mutex); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 8a9fcbd0e8ac..fc3a8d8064f8 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -34,11 +34,15 @@ static void erofs_readendio(struct bio *bio) struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr) { - struct inode *const bd_inode = sb->s_bdev->bd_inode; - struct address_space *const mapping = bd_inode->i_mapping; + struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping; + struct page *page; - return read_cache_page_gfp(mapping, blkaddr, + page = read_cache_page_gfp(mapping, blkaddr, mapping_gfp_constraint(mapping, ~__GFP_FS)); + /* should already be PageUptodate */ + if (!IS_ERR(page)) + lock_page(page); + return page; } static int erofs_map_blocks_flatmode(struct inode *inode, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index caf9a95173b0..0e369494f2f2 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -105,9 +105,9 @@ static int erofs_read_superblock(struct super_block *sb) int ret; page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL); - if (!page) { + if (IS_ERR(page)) { erofs_err(sb, "cannot read erofs superblock"); - return -EIO; + return PTR_ERR(page); } sbi = EROFS_SB(sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 96e34c90f814..fad80c97d247 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -575,7 +575,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, struct erofs_map_blocks *const map = &fe->map; struct z_erofs_collector *const clt = &fe->clt; const loff_t offset = page_offset(page); - bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED); + bool tight = true; enum z_erofs_cache_alloctype cache_strategy; enum z_erofs_page_type page_type; @@ -628,8 +628,16 @@ restart_now: preload_compressed_pages(clt, MNGD_MAPPING(sbi), cache_strategy, pagepool); - tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED); hitted: + /* + * Ensure the current partial page belongs to this submit chain rather + * than other concurrent submit chains or the noio(bypass) chain since + * those chains are handled asynchronously thus the page cannot be used + * for inplace I/O or pagevec (should be processed in strict order.) + */ + tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED && + clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE); + cur = end - min_t(unsigned int, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); diff --git a/fs/io_uring.c b/fs/io_uring.c index aa8ac557493c..8a0381f1a43b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1892,15 +1892,15 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned count, req_dist, tail_index; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; - struct timespec ts; + struct timespec64 ts; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags || sqe->len != 1) return -EINVAL; - if (copy_from_user(&ts, (void __user *) (unsigned long) sqe->addr, - sizeof(ts))) + + if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; /* @@ -1934,7 +1934,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); req->timeout.timer.function = io_timeout_fn; - hrtimer_start(&req->timeout.timer, timespec_to_ktime(ts), + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), HRTIMER_MODE_REL); return 0; } diff --git a/fs/readdir.c b/fs/readdir.c index 2f6a4534e0df..19bea591c3f1 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -20,9 +20,63 @@ #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/compat.h> - #include <linux/uaccess.h> +#include <asm/unaligned.h> + +/* + * Note the "unsafe_put_user() semantics: we goto a + * label for errors. + * + * Also note how we use a "while()" loop here, even though + * only the biggest size needs to loop. The compiler (well, + * at least gcc) is smart enough to turn the smaller sizes + * into just if-statements, and this way we don't need to + * care whether 'u64' or 'u32' is the biggest size. + */ +#define unsafe_copy_loop(dst, src, len, type, label) \ + while (len >= sizeof(type)) { \ + unsafe_put_user(get_unaligned((type *)src), \ + (type __user *)dst, label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +/* + * We avoid doing 64-bit copies on 32-bit architectures. They + * might be better, but the component names are mostly small, + * and the 64-bit cases can end up being much more complex and + * put much more register pressure on the code, so it's likely + * not worth the pain of unaligned accesses etc. + * + * So limit the copies to "unsigned long" size. I did verify + * that at least the x86-32 case is ok without this limiting, + * but I worry about random other legacy 32-bit cases that + * might not do as well. + */ +#define unsafe_copy_type(dst, src, len, type, label) do { \ + if (sizeof(type) <= sizeof(unsigned long)) \ + unsafe_copy_loop(dst, src, len, type, label); \ +} while (0) + +/* + * Copy the dirent name to user space, and NUL-terminate + * it. This should not be a function call, since we're doing + * the copy inside a "user_access_begin/end()" section. + */ +#define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ + char __user *dst = (_dst); \ + const char *src = (_src); \ + size_t len = (_len); \ + unsafe_copy_type(dst, src, len, u64, label); \ + unsafe_copy_type(dst, src, len, u32, label); \ + unsafe_copy_type(dst, src, len, u16, label); \ + unsafe_copy_type(dst, src, len, u8, label); \ + unsafe_put_user(0, dst, label); \ +} while (0) + + int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); @@ -65,6 +119,40 @@ out: EXPORT_SYMBOL(iterate_dir); /* + * POSIX says that a dirent name cannot contain NULL or a '/'. + * + * It's not 100% clear what we should really do in this case. + * The filesystem is clearly corrupted, but returning a hard + * error means that you now don't see any of the other names + * either, so that isn't a perfect alternative. + * + * And if you return an error, what error do you use? Several + * filesystems seem to have decided on EUCLEAN being the error + * code for EFSCORRUPTED, and that may be the error to use. Or + * just EIO, which is perhaps more obvious to users. + * + * In order to see the other file names in the directory, the + * caller might want to make this a "soft" error: skip the + * entry, and return the error at the end instead. + * + * Note that this should likely do a "memchr(name, 0, len)" + * check too, since that would be filesystem corruption as + * well. However, that case can't actually confuse user space, + * which has to do a strlen() on the name anyway to find the + * filename length, and the above "soft error" worry means + * that it's probably better left alone until we have that + * issue clarified. + */ +static int verify_dirent_name(const char *name, int len) +{ + if (WARN_ON_ONCE(!len)) + return -EIO; + if (WARN_ON_ONCE(memchr(name, '/', len))) + return -EIO; + return 0; +} + +/* * Traditional linux readdir() handling.. * * "count=1" is a special case, meaning that the buffer is one @@ -173,6 +261,9 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; @@ -182,28 +273,31 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, return -EOVERFLOW; } dirent = buf->previous; - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user(d_ino, &dirent->d_ino)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) - goto efault; - if (__put_user(d_type, (char __user *) dirent + reclen - 1)) + if (dirent && signal_pending(current)) + return -EINTR; + + /* + * Note! This range-checks 'previous' (which may be NULL). + * The real range was checked in getdents + */ + if (!user_access_begin(dirent, sizeof(*dirent))) goto efault; + if (dirent) + unsafe_put_user(offset, &dirent->d_off, efault_end); + dirent = buf->current_dir; + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_access_end(); + buf->previous = dirent; dirent = (void __user *)dirent + reclen; buf->current_dir = dirent; buf->count -= reclen; return 0; +efault_end: + user_access_end(); efault: buf->error = -EFAULT; return -EFAULT; @@ -259,34 +353,38 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; dirent = buf->previous; - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user(ino, &dirent->d_ino)) - goto efault; - if (__put_user(0, &dirent->d_off)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (__put_user(d_type, &dirent->d_type)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) + if (dirent && signal_pending(current)) + return -EINTR; + + /* + * Note! This range-checks 'previous' (which may be NULL). + * The real range was checked in getdents + */ + if (!user_access_begin(dirent, sizeof(*dirent))) goto efault; + if (dirent) + unsafe_put_user(offset, &dirent->d_off, efault_end); + dirent = buf->current_dir; + unsafe_put_user(ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, &dirent->d_type, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_access_end(); + buf->previous = dirent; dirent = (void __user *)dirent + reclen; buf->current_dir = dirent; buf->count -= reclen; return 0; +efault_end: + user_access_end(); efault: buf->error = -EFAULT; return -EFAULT; diff --git a/fs/statfs.c b/fs/statfs.c index eea7af6f2f22..2616424012ea 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -318,19 +318,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { struct compat_statfs64 buf; - if (sizeof(ubuf->f_bsize) == 4) { - if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | - kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) - return -EOVERFLOW; - /* f_files and f_ffree may be -1; it's okay - * to stuff that into 32 bits */ - if (kbuf->f_files != 0xffffffffffffffffULL - && (kbuf->f_files & 0xffffffff00000000ULL)) - return -EOVERFLOW; - if (kbuf->f_ffree != 0xffffffffffffffffULL - && (kbuf->f_ffree & 0xffffffff00000000ULL)) - return -EOVERFLOW; - } + + if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) + return -EOVERFLOW; + memset(&buf, 0, sizeof(struct compat_statfs64)); buf.f_type = kbuf->f_type; buf.f_bsize = kbuf->f_bsize; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index cf074bce3eb3..c94a9ff9f082 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,13 @@ #include <asm/types.h> #include <linux/bits.h> +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 79435cfc20eb..897e799dbcb9 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -31,6 +31,8 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull +#define SJA1105_HWTS_RX_EN 0 + /* Global tagger data: each struct sja1105_port has a reference to * the structure defined in struct sja1105_private. */ @@ -42,7 +44,7 @@ struct sja1105_tagger_data { * from taggers running on multiple ports on SMP systems */ spinlock_t meta_lock; - bool hwts_rx_en; + unsigned long state; }; struct sja1105_skb_cb { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fcb46b3374c6..719fc3e15ea4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1090,6 +1090,7 @@ enum kvm_stat_kind { struct kvm_stat_data { int offset; + int mode; struct kvm *kvm; }; @@ -1097,6 +1098,7 @@ struct kvm_stats_debugfs_item { const char *name; int offset; enum kvm_stat_kind kind; + int mode; }; extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/mii.h b/include/linux/mii.h index 5cd824c1c0ca..4ce8901a1af6 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -455,6 +455,15 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, lp_advertising, lpa & LPA_LPACK); } +static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, + u32 ctrl1000) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertising, + ctrl1000 & ADVERTISE_1000HALF); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertising, + ctrl1000 & ADVERTISE_1000FULL); +} + /** * linkmode_adv_to_lcl_adv_t * @advertising:pointer to linkmode advertising diff --git a/include/linux/phy.h b/include/linux/phy.h index a7ecbe0e55aa..9a0e981df502 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -678,6 +678,7 @@ static inline bool phy_is_started(struct phy_device *phydev) return phydev->state >= PHY_UP; } +void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** @@ -1076,6 +1077,7 @@ int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); +int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e7d3b1a513ef..4351577b14d7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4160,15 +4160,12 @@ static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} #endif /* CONFIG_SKB_EXTENSIONS */ -static inline void nf_reset(struct sk_buff *skb) +static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - skb_ext_del(skb, SKB_EXT_BRIDGE_NF); -#endif } static inline void nf_reset_trace(struct sk_buff *skb) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 99617e528ea2..668e25a76d69 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -393,7 +393,7 @@ struct tcp_sock { /* fastopen_rsk points to request_sock that resulted in this big * socket. Used to retransmit SYNACKs etc. */ - struct request_sock *fastopen_rsk; + struct request_sock __rcu *fastopen_rsk; u32 *saved_syn; }; @@ -447,8 +447,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) static inline bool tcp_passive_fastopen(const struct sock *sk) { - return (sk->sk_state == TCP_SYN_RECV && - tcp_sk(sk)->fastopen_rsk != NULL); + return sk->sk_state == TCP_SYN_RECV && + rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL; } static inline void fastopen_queue_tune(struct sock *sk, int backlog) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70bbdc38dc37..e47d0522a1f4 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, #endif /* ARCH_HAS_NOCACHE_UACCESS */ +extern __must_check int check_zeroed_user(const void __user *from, size_t size); + +/** + * copy_struct_from_user: copy a struct from userspace + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @src: Source address, in userspace. + * @usize: (Alleged) size of @src struct. + * + * Copies a struct from userspace to kernel space, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) + * { + * int err; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + * if (err) + * return err; + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) + * are to be zero-filled. + * * If @usize > @ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * + * Returns (in all cases, some data may have been copied): + * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_from_user(void *dst, size_t ksize, const void __user *src, + size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Deal with trailing bytes. */ + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + int ret = check_zeroed_user(src + size, rest); + if (ret <= 0) + return ret ?: -E2BIG; + } + /* Copy the interoperable parts of the struct. */ + if (copy_from_user(dst, src, size)) + return -EFAULT; + return 0; +} + /* * probe_kernel_read(): safely attempt to read from a location * @dst: pointer to the buffer that shall take the data diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ff45c3e1abff..4ab2c49423dc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5550,6 +5550,14 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, const char *reg_initiator_name(enum nl80211_reg_initiator initiator); /** + * regulatory_pre_cac_allowed - check if pre-CAC allowed in the current regdom + * @wiphy: wiphy for which pre-CAC capability is checked. + * + * Pre-CAC is allowed only in some regdomains (notable ETSI). + */ +bool regulatory_pre_cac_allowed(struct wiphy *wiphy); + +/** * DOC: Internal regulatory db functions * */ diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index df528a623548..ea985aa7a6c5 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -104,7 +104,7 @@ void llc_sk_reset(struct sock *sk); /* Access to a connection */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb); -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index fd178d58fa84..cf8b33213bbc 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -185,7 +185,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) { - return queue->rskq_accept_head == NULL; + return READ_ONCE(queue->rskq_accept_head) == NULL; } static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, @@ -197,7 +197,7 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue req = queue->rskq_accept_head; if (req) { sk_acceptq_removed(parent); - queue->rskq_accept_head = req->dl_next; + WRITE_ONCE(queue->rskq_accept_head, req->dl_next); if (queue->rskq_accept_head == NULL) queue->rskq_accept_tail = NULL; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 5d60f13d2347..3ab5c6bbb90b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -610,4 +610,9 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize); } +static inline bool sctp_newsk_ready(const struct sock *sk) +{ + return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; +} + #endif /* __net_sctp_h__ */ diff --git a/include/net/sock.h b/include/net/sock.h index 2c53f1a1d905..f69b58bff7e5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -878,12 +878,17 @@ static inline bool sk_acceptq_is_full(const struct sock *sk) */ static inline int sk_stream_min_wspace(const struct sock *sk) { - return sk->sk_wmem_queued >> 1; + return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { - return sk->sk_sndbuf - sk->sk_wmem_queued; + return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); +} + +static inline void sk_wmem_queued_add(struct sock *sk, int val) +{ + WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } void sk_stream_write_space(struct sock *sk); @@ -1207,7 +1212,7 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { - if (sk->sk_wmem_queued >= sk->sk_sndbuf) + if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? @@ -1467,7 +1472,7 @@ DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - sk->sk_wmem_queued -= skb->truesize; + sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && !sk->sk_tx_skb_cache && !skb_cloned(skb)) { @@ -2014,7 +2019,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } @@ -2220,10 +2225,14 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) static inline void sk_stream_moderate_sndbuf(struct sock *sk) { - if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) { - sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); - sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF); - } + u32 val; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + + WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, @@ -2251,7 +2260,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); */ static inline bool sock_writeable(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); + return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) @@ -2271,7 +2280,9 @@ static inline long sock_sndtimeo(const struct sock *sk, bool noblock) static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { - return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1; + int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); + + return v ?: 1; } /* Alas, with timeout socket operations are not restartable. diff --git a/include/net/tcp.h b/include/net/tcp.h index c9a3f9688223..ab4eb5eb5d07 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -258,7 +258,7 @@ static inline bool tcp_under_memory_pressure(const struct sock *sk) mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; - return tcp_memory_pressure; + return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints @@ -1380,13 +1380,14 @@ static inline int tcp_win_from_space(const struct sock *sk, int space) /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len - + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - + READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf); + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } extern void tcp_openreq_init_rwin(struct request_sock *req, @@ -1916,7 +1917,8 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); - u32 notsent_bytes = tp->write_seq - tp->snd_nxt; + u32 notsent_bytes = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a13a62db3565..191fe447f990 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -519,10 +519,10 @@ TRACE_EVENT(rxrpc_local, ); TRACE_EVENT(rxrpc_peer, - TP_PROTO(struct rxrpc_peer *peer, enum rxrpc_peer_trace op, + TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op, int usage, const void *where), - TP_ARGS(peer, op, usage, where), + TP_ARGS(peer_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, peer ) @@ -532,7 +532,7 @@ TRACE_EVENT(rxrpc_peer, ), TP_fast_assign( - __entry->peer = peer->debug_id; + __entry->peer = peer_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; @@ -546,10 +546,10 @@ TRACE_EVENT(rxrpc_peer, ); TRACE_EVENT(rxrpc_conn, - TP_PROTO(struct rxrpc_connection *conn, enum rxrpc_conn_trace op, + TP_PROTO(unsigned int conn_debug_id, enum rxrpc_conn_trace op, int usage, const void *where), - TP_ARGS(conn, op, usage, where), + TP_ARGS(conn_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, conn ) @@ -559,7 +559,7 @@ TRACE_EVENT(rxrpc_conn, ), TP_fast_assign( - __entry->conn = conn->debug_id; + __entry->conn = conn_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; @@ -606,10 +606,10 @@ TRACE_EVENT(rxrpc_client, ); TRACE_EVENT(rxrpc_call, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_call_trace op, + TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op, int usage, const void *where, const void *aux), - TP_ARGS(call, op, usage, where, aux), + TP_ARGS(call_debug_id, op, usage, where, aux), TP_STRUCT__entry( __field(unsigned int, call ) @@ -620,7 +620,7 @@ TRACE_EVENT(rxrpc_call, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; @@ -1068,7 +1068,7 @@ TRACE_EVENT(rxrpc_recvmsg, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call ? call->debug_id : 0; __entry->why = why; __entry->seq = seq; __entry->offset = offset; diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index a0c4b8a30966..51fe9f6719eb 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -82,7 +82,7 @@ TRACE_EVENT(sock_rcvqueue_full, TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; - __entry->sk_rcvbuf = sk->sk_rcvbuf; + __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", @@ -115,7 +115,7 @@ TRACE_EVENT(sock_exceed_buf_limit, __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); - __entry->wmem_queued = sk->sk_wmem_queued; + __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index c99b4f2482c6..4fe35d600ab8 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device { __u64 high_va_max; /* gfx10 pa_sc_tile_steering_override */ __u32 pa_sc_tile_steering_override; + /* disabled TCCs */ + __u64 tcc_disabled_mask; }; struct drm_amdgpu_info_hw_ip { diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 1c215ea1798e..e168dc59e9a0 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -45,6 +45,27 @@ struct nvme_passthru_cmd { __u32 result; }; +struct nvme_passthru_cmd64 { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u64 result; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -54,5 +75,7 @@ struct nvme_passthru_cmd { #define NVME_IOCTL_RESET _IO('N', 0x44) #define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45) #define NVME_IOCTL_RESCAN _IO('N', 0x46) +#define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64) +#define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h index 364c350e85cd..62b6f69bd9fb 100644 --- a/include/uapi/linux/pg.h +++ b/include/uapi/linux/pg.h @@ -35,6 +35,9 @@ */ +#ifndef _UAPI_LINUX_PG_H +#define _UAPI_LINUX_PG_H + #define PG_MAGIC 'P' #define PG_RESET 'Z' #define PG_COMMAND 'C' @@ -61,4 +64,4 @@ struct pg_read_hdr { }; -/* end of pg.h */ +#endif /* _UAPI_LINUX_PG_H */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index b3105ac1381a..99335e1f4a27 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -33,8 +33,31 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ -/* - * Arguments for the clone3 syscall +#ifndef __ASSEMBLY__ +/** + * struct clone_args - arguments for the clone3 syscall + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * + * The structure is versioned by size and thus extensible. + * New struct members must go at the end of the struct and + * must be properly 64bit aligned. */ struct clone_args { __aligned_u64 flags; @@ -46,6 +69,9 @@ struct clone_args { __aligned_u64 stack_size; __aligned_u64 tls; }; +#endif + +#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ /* * Scheduling policies diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 98b30c1613b2..d89969aa9942 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -212,30 +212,7 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr, bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); -efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc); -efi_status_t xen_efi_set_time(efi_time_t *tm); -efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, - efi_time_t *tm); -efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm); -efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 *attr, unsigned long *data_size, - void *data); -efi_status_t xen_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, efi_guid_t *vendor); -efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, - void *data); -efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size); -efi_status_t xen_efi_get_next_high_mono_count(u32 *count); -efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, unsigned long sg_list); -efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, u64 *max_size, - int *reset_type); -void xen_efi_reset_system(int reset_type, efi_status_t status, - unsigned long data_size, efi_char16_t *data); +void xen_efi_runtime_setup(void); #ifdef CONFIG_PREEMPT diff --git a/kernel/events/core.c b/kernel/events/core.c index 4655adbbae10..3f0cb82e4fbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, u32 size; int ret; - if (!access_ok(uattr, PERF_ATTR_SIZE_VER0)) - return -EFAULT; - - /* - * zero the full structure, so that a short copy will be nice. - */ + /* Zero the full structure, so that a short copy will be nice. */ memset(attr, 0, sizeof(*attr)); ret = get_user(size, &uattr->size); if (ret) return ret; - if (size > PAGE_SIZE) /* silly large */ - goto err_size; - - if (!size) /* abi compat */ + /* ABI compatibility quirk: */ + if (!size) size = PERF_ATTR_SIZE_VER0; - - if (size < PERF_ATTR_SIZE_VER0) + if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - attr->size = size; if (attr->__reserved_1) diff --git a/kernel/fork.c b/kernel/fork.c index f9572f416126..1f6c45f6a734 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, - size_t size) + size_t usize) { + int err; struct clone_args args; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(usize > PAGE_SIZE)) return -E2BIG; - - if (unlikely(size < sizeof(struct clone_args))) + if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; - if (unlikely(!access_ok(uargs, size))) - return -EFAULT; - - if (size > sizeof(struct clone_args)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uargs + sizeof(struct clone_args); - end = (void __user *)uargs + size; - - for (; addr < end; addr++) { - if (get_user(val, addr)) - return -EFAULT; - if (val) - return -E2BIG; - } - - size = sizeof(struct clone_args); - } - - if (copy_from_user(&args, uargs, size)) - return -EFAULT; + err = copy_struct_from_user(&args, sizeof(args), uargs, usize); + if (err) + return err; /* * Verify that higher 32bits of exit_signal are unset and that @@ -2604,6 +2584,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs) return true; } +/** + * clone3 - create a new process with specific properties + * @uargs: argument structure + * @size: size of @uargs + * + * clone3() is the extensible successor to clone()/clone2(). + * It takes a struct as argument that is versioned by its size. + * + * Return: On success, a positive PID for the child process. + * On error, a negative errno number. + */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 9ff449888d9c..aff79e461fc9 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -71,7 +71,10 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 find $cpio_dir -type f -print0 | xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' -tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null +# Create archive and try to normalize metadata for reproducibility +tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --owner=0 --group=0 --sort=name --numeric-owner \ + -Jcf $tarfile -C $cpio_dir/ . > /dev/null echo "$src_files_md5" > kernel/kheaders.md5 echo "$obj_files_md5" >> kernel/kheaders.md5 diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7880f4f64d0e..dd05a378631a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a u32 size; int ret; - if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0)) - return -EFAULT; - /* Zero the full structure, so that a short copy will be nice: */ memset(attr, 0, sizeof(*attr)); @@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a if (ret) return ret; - /* Bail out on silly large: */ - if (size > PAGE_SIZE) - goto err_size; - /* ABI compatibility quirk: */ if (!size) size = SCHED_ATTR_SIZE_VER0; - - if (size < SCHED_ATTR_SIZE_VER0) + if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && size < SCHED_ATTR_SIZE_VER1) return -EINVAL; @@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr, * sys_sched_getattr - similar to sched_getparam, but with sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. - * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility. + * @usize: sizeof(attr) for fwd/bwd comp. * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a39bed2c784f..168479a7d61b 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags) */ if (cpu == raw_smp_processor_id()) continue; - rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index c1f5bb590b5e..b5a65e212df2 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt) */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { - int bc_moved; /* - * We try to cancel the timer first. If the callback is on - * flight on some other cpu then we let it handle it. If we - * were able to cancel the timer nothing can rearm it as we - * own broadcast_lock. + * This is called either from enter/exit idle code or from the + * broadcast handler. In all cases tick_broadcast_lock is held. * - * However we can also be called from the event handler of - * ce_broadcast_hrtimer itself when it expires. We cannot - * restart the timer because we are in the callback, but we - * can set the expiry time and let the callback return - * HRTIMER_RESTART. + * hrtimer_cancel() cannot be called here neither from the + * broadcast handler nor from the enter/exit idle code. The idle + * code can run into the problem described in bc_shutdown() and the + * broadcast handler cannot wait for itself to complete for obvious + * reasons. * - * Since we are in the idle loop at this point and because - * hrtimer_{start/cancel} functions call into tracing, - * calls to these functions must be bound within RCU_NONIDLE. + * Each caller tries to arm the hrtimer on its own CPU, but if the + * hrtimer callbback function is currently running, then + * hrtimer_start() cannot move it and the timer stays on the CPU on + * which it is assigned at the moment. + * + * As this can be called from idle code, the hrtimer_start() + * invocation has to be wrapped with RCU_NONIDLE() as + * hrtimer_start() can call into tracing. */ - RCU_NONIDLE( - { - bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0; - if (bc_moved) { - hrtimer_start(&bctimer, expires, - HRTIMER_MODE_ABS_PINNED_HARD); - } - } - ); - - if (bc_moved) { - /* Bind the "device" to the cpu */ - bc->bound_on = smp_processor_id(); - } else if (bc->bound_on == smp_processor_id()) { - hrtimer_set_expires(&bctimer, expires); - } + RCU_NONIDLE( { + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD); + /* + * The core tick broadcast mode expects bc->bound_on to be set + * correctly to prevent a CPU which has the broadcast hrtimer + * armed from going deep idle. + * + * As tick_broadcast_lock is held, nothing can change the cpu + * base which was just established in hrtimer_start() above. So + * the below access is safe even without holding the hrtimer + * base lock. + */ + bc->bound_on = bctimer.base->cpu_base->cpu; + } ); return 0; } @@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); - if (clockevent_state_oneshot(&ce_broadcast_hrtimer)) - if (ce_broadcast_hrtimer.next_event != KTIME_MAX) - return HRTIMER_RESTART; - return HRTIMER_NORESTART; } diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 28ff554a1be8..6c0005d5dd5c 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -3,16 +3,10 @@ #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> +#include <linux/bitops.h> #include <asm/word-at-a-time.h> -/* Set bits in the first 'n' bytes when loaded from memory */ -#ifdef __LITTLE_ENDIAN -# define aligned_byte_mask(n) ((1ul << 8*(n))-1) -#else -# define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n))) -#endif - /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c index 67bcd5dfd847..e365ace06538 100644 --- a/lib/test_user_copy.c +++ b/lib/test_user_copy.c @@ -31,14 +31,133 @@ # define TEST_U64 #endif -#define test(condition, msg) \ -({ \ - int cond = (condition); \ - if (cond) \ - pr_warn("%s\n", msg); \ - cond; \ +#define test(condition, msg, ...) \ +({ \ + int cond = (condition); \ + if (cond) \ + pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \ + cond; \ }) +static bool is_zeroed(void *from, size_t size) +{ + return memchr_inv(from, 0x0, size) == NULL; +} + +static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) +{ + int ret = 0; + size_t start, end, i; + size_t zero_start = size / 4; + size_t zero_end = size - zero_start; + + /* + * We conduct a series of check_nonzero_user() tests on a block of memory + * with the following byte-pattern (trying every possible [start,end] + * pair): + * + * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] + * + * And we verify that check_nonzero_user() acts identically to memchr_inv(). + */ + + memset(kmem, 0x0, size); + for (i = 1; i < zero_start; i += 2) + kmem[i] = 0xff; + for (i = zero_end; i < size; i += 2) + kmem[i] = 0xff; + + ret |= test(copy_to_user(umem, kmem, size), + "legitimate copy_to_user failed"); + + for (start = 0; start <= size; start++) { + for (end = start; end <= size; end++) { + size_t len = end - start; + int retval = check_zeroed_user(umem + start, len); + int expected = is_zeroed(kmem + start, len); + + ret |= test(retval != expected, + "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", + retval, expected, start, end); + } + } + + return ret; +} + +static int test_copy_struct_from_user(char *kmem, char __user *umem, + size_t size) +{ + int ret = 0; + char *umem_src = NULL, *expected = NULL; + size_t ksize, usize; + + umem_src = kmalloc(size, GFP_KERNEL); + if ((ret |= test(umem_src == NULL, "kmalloc failed"))) + goto out_free; + + expected = kmalloc(size, GFP_KERNEL); + if ((ret |= test(expected == NULL, "kmalloc failed"))) + goto out_free; + + /* Fill umem with a fixed byte pattern. */ + memset(umem_src, 0x3e, size); + ret |= test(copy_to_user(umem, umem_src, size), + "legitimate copy_to_user failed"); + + /* Check basic case -- (usize == ksize). */ + ksize = size; + usize = size; + + memcpy(expected, umem_src, ksize); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize == ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize == ksize) gives unexpected copy"); + + /* Old userspace case -- (usize < ksize). */ + ksize = size; + usize = size / 2; + + memcpy(expected, umem_src, usize); + memset(expected + usize, 0x0, ksize - usize); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize < ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize < ksize) gives unexpected copy"); + + /* New userspace (-E2BIG) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG, + "copy_struct_from_user(usize > ksize) didn't give E2BIG"); + + /* New userspace (success) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memcpy(expected, umem_src, ksize); + ret |= test(clear_user(umem + ksize, usize - ksize), + "legitimate clear_user failed"); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize > ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize > ksize) gives unexpected copy"); + +out_free: + kfree(expected); + kfree(umem_src); + return ret; +} + static int __init test_user_copy_init(void) { int ret = 0; @@ -106,6 +225,11 @@ static int __init test_user_copy_init(void) #endif #undef test_legit + /* Test usage of check_nonzero_user(). */ + ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE); + /* Test usage of copy_struct_from_user(). */ + ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE); + /* * Invalid usage: none of these copies should succeed. */ diff --git a/lib/textsearch.c b/lib/textsearch.c index 4f16eec5d554..f68dea8806be 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -89,9 +89,9 @@ * goto errout; * } * - * pos = textsearch_find_continuous(conf, \&state, example, strlen(example)); + * pos = textsearch_find_continuous(conf, &state, example, strlen(example)); * if (pos != UINT_MAX) - * panic("Oh my god, dancing chickens at \%d\n", pos); + * panic("Oh my god, dancing chickens at %d\n", pos); * * textsearch_destroy(conf); */ diff --git a/lib/usercopy.c b/lib/usercopy.c index c2bfbcaeb3dc..cbb4d9ec00f2 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/uaccess.h> +#include <linux/bitops.h> /* out-of-line parts */ @@ -31,3 +32,57 @@ unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) } EXPORT_SYMBOL(_copy_to_user); #endif + +/** + * check_zeroed_user: check if a userspace buffer only contains zero bytes + * @from: Source address, in userspace. + * @size: Size of buffer. + * + * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for + * userspace addresses (and is more efficient because we don't care where the + * first non-zero byte is). + * + * Returns: + * * 0: There were non-zero bytes present in the buffer. + * * 1: The buffer was full of zero bytes. + * * -EFAULT: access to userspace failed. + */ +int check_zeroed_user(const void __user *from, size_t size) +{ + unsigned long val; + uintptr_t align = (uintptr_t) from % sizeof(unsigned long); + + if (unlikely(size == 0)) + return 1; + + from -= align; + size += align; + + if (!user_access_begin(from, size)) + return -EFAULT; + + unsafe_get_user(val, (unsigned long __user *) from, err_fault); + if (align) + val &= ~aligned_byte_mask(align); + + while (size > sizeof(unsigned long)) { + if (unlikely(val)) + goto done; + + from += sizeof(unsigned long); + size -= sizeof(unsigned long); + + unsafe_get_user(val, (unsigned long __user *) from, err_fault); + } + + if (size < sizeof(unsigned long)) + val &= aligned_byte_mask(size); + +done: + user_access_end(); + return (val == 0); +err_fault: + user_access_end(); + return -EFAULT; +} +EXPORT_SYMBOL(check_zeroed_user); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a1146cb10919..9cbed6f5a85a 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -436,7 +436,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* clean the netfilter state now that the batman-adv header has been * removed */ - nf_reset(skb); + nf_reset_ct(skb); if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) goto dropped; diff --git a/net/core/datagram.c b/net/core/datagram.c index 4cc8dc5db2b7..c210fc116103 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->len += copied; skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { - sk->sk_wmem_queued += truesize; + sk_wmem_queued_add(sk, truesize); sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); diff --git a/net/core/devlink.c b/net/core/devlink.c index e48680efe54a..f80151eeaf51 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3172,7 +3172,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -3432,7 +3432,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -4088,7 +4088,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err) + if (err && err != -EOPNOTSUPP) break; idx++; } diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..3fed5755494b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4252,12 +4252,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) @@ -4274,7 +4276,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_MARK: if (sk->sk_mark != val) { diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a0e0d298c991..6d3e4821b02d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -245,7 +245,8 @@ static int __peernet2id(struct net *net, struct net *peer) return __peernet2id_alloc(net, peer, &no); } -static void rtnl_net_notifyid(struct net *net, int cmd, int id); +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ @@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id); + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL); if (alive) put_net(peer); return id; @@ -532,7 +533,7 @@ static void unhash_nsid(struct net *net, struct net *last) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) - rtnl_net_notifyid(tmp, RTM_DELNSID, id); + rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL); if (tmp == last) break; } @@ -764,7 +765,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { - rtnl_net_notifyid(net, RTM_NEWNSID, err); + rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, + nlh); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; @@ -1051,9 +1053,12 @@ end: return err < 0 ? err : skb->len; } -static void rtnl_net_notifyid(struct net *net, int cmd, int id) +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh) { struct net_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; @@ -1068,7 +1073,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id) if (err < 0) goto err_out; - rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0); + rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0); return; err_out: diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c9bb00008528..f35c2e998406 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; - tcp_sk(sk)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL); spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; tcp_rsk(req)->tfo_listener = false; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 01d65206f4fb..8c178703467b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) + (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); @@ -5120,7 +5120,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); - nf_reset(skb); + nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV diff --git a/net/core/sock.c b/net/core/sock.c index 07863edbe6fc..a515392ba84b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; @@ -785,7 +785,8 @@ set_sndbuf: */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -831,7 +832,8 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_RCVBUFFORCE: @@ -974,7 +976,7 @@ set_rcvbuf: if (sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_RCVTIMEO_OLD: @@ -1700,8 +1702,6 @@ static void __sk_destruct(struct rcu_head *head) sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } - if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); @@ -1728,7 +1728,14 @@ static void __sk_destruct(struct rcu_head *head) void sk_destruct(struct sock *sk) { - if (sock_flag(sk, SOCK_RCU_FREE)) + bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); + + if (rcu_access_pointer(sk->sk_reuseport_cb)) { + reuseport_detach_sock(sk); + use_call_rcu = true; + } + + if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); @@ -2083,8 +2090,10 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || + refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); + if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -2185,7 +2194,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2220,7 +2229,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) + if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -2329,8 +2338,8 @@ static void sk_leave_memory_pressure(struct sock *sk) } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; - if (memory_pressure && *memory_pressure) - *memory_pressure = 0; + if (memory_pressure && READ_ONCE(*memory_pressure)) + WRITE_ONCE(*memory_pressure, 0); } } @@ -2801,7 +2810,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | @@ -3199,13 +3208,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); - mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); - mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; - mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } @@ -3492,7 +3501,7 @@ static long sock_prot_memory_allocated(struct proto *proto) return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } -static char *sock_prot_memory_pressure(struct proto *proto) +static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b685bc82f8d0..d9b4200ed12d 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -871,7 +871,7 @@ lookup: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - nf_reset(skb); + nf_reset_ct(skb); return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9c9aff3e52cf..63ef2a14c934 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -156,7 +156,11 @@ static struct sk_buff /* Step 1: A timestampable frame was received. * Buffer it until we get its meta frame. */ - if (is_link_local && sp->data->hwts_rx_en) { + if (is_link_local) { + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + /* Do normal processing. */ + return skb; + spin_lock(&sp->data->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? @@ -187,6 +191,12 @@ static struct sk_buff } else if (is_meta) { struct sk_buff *stampable_skb; + /* Drop the meta frame if we're not in the right state + * to process it. + */ + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + return NULL; + spin_lock(&sp->data->meta_lock); stampable_skb = sp->data->stampable_skb; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a9183543ca30..eb30fc1770de 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,7 +906,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, percpu_counter_inc(sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if @@ -915,7 +915,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ - tcp_sk(child)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } @@ -934,7 +934,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk, req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; + WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bbb005eb5218..7dc79b973e6e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), - .idiag_wmem = sk->sk_wmem_queued, + .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a53a543fe055..52690bb3e40f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1446,6 +1446,7 @@ static void erspan_setup(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1e2392b7c64e..c59a78a267c3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -199,7 +199,7 @@ resubmit: kfree_skb(skb); return; } - nf_reset(skb); + nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv, skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 313470f6bb14..716d5472c022 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1794,7 +1794,7 @@ static void ip_encap(struct net *net, struct sk_buff *skb, ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - nf_reset(skb); + nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, @@ -2140,7 +2140,7 @@ int ip_mr_input(struct sk_buff *skb) mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { - nf_reset(skb); + nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index af3fbf76dbd3..6cc5743c553a 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -65,7 +65,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Avoid counting cloned packets towards the original connection. */ - nf_reset(skb); + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); #endif /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 80da5a66d5d7..3183413ebc6c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -332,7 +332,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - nf_reset(skb); + nf_reset_ct(skb); skb_push(skb, skb->data - skb_network_header(skb)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7dcce724c78b..14654876127e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -916,16 +916,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (peer->rate_tokens == 0 || time_after(jiffies, (peer->rate_last + - (ip_rt_redirect_load << peer->rate_tokens)))) { + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; - ++peer->rate_tokens; ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number) + peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 79c325a07ba5..b2ac4f074e2d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; - if (tcp_memory_pressure) + if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; @@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; - if (!tcp_memory_pressure) + if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) @@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || + return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || (sk->sk_prot->stream_memory_read ? sk->sk_prot->stream_memory_read(sk) : false); } @@ -543,10 +543,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -616,7 +617,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -625,7 +626,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@ -657,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@ -1032,10 +1034,10 @@ new_segment: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1362,7 +1364,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1668,9 +1670,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1699,7 +1701,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) else cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; val = min(val, cap); - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); @@ -1709,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@ -1798,13 +1800,11 @@ static int tcp_zerocopy_receive(struct sock *sk, } if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; - int size = skb_frag_size(frags); - while (remaining && (size != PAGE_SIZE || + while (remaining && (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags))) { - remaining -= size; + remaining -= skb_frag_size(frags); frags++; - size = skb_frag_size(frags); } zc->recv_skip_hint -= remaining; break; @@ -1821,7 +1821,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -2119,7 +2119,7 @@ found_ok_skb: if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2141,7 +2141,7 @@ found_ok_skb: } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2168,7 +2168,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2489,7 +2489,10 @@ adjudge_to_death: } if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@ -2561,6 +2564,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2587,7 +2591,7 @@ int tcp_disconnect(struct sock *sk, int flags) __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2603,9 +2607,12 @@ int tcp_disconnect(struct sock *sk, int flags) tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; @@ -2932,9 +2939,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; + WRITE_ONCE(tp->write_seq, val); else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->rcv_nxt, val); else err = -EINVAL; break; @@ -3833,8 +3840,10 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 81a8221d650a..549506162dde 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3fd451271a70..a915ade0c818 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ tp = tcp_sk(child); - tp->fastopen_rsk = req; + rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3578357abe30..a2e52ad7cdab 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); + WRITE_ONCE(sk->sk_sndbuf, + min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -483,8 +484,9 @@ static void tcp_clamp_window(struct sock *sk) !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { - sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2]); + WRITE_ONCE(sk->sk_rcvbuf, + min(atomic_read(&sk->sk_rmem_alloc), + net->ipv4.sysctl_tcp_rmem[2])); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -648,7 +650,7 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, rcvwin * rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { - sk->sk_rcvbuf = rcvbuf; + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(sk, rcvbuf); @@ -2666,7 +2668,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); - if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) && + if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) && tcp_try_undo_loss(sk, false)) return; @@ -2990,7 +2992,7 @@ void tcp_rearm_rto(struct sock *sk) /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return; if (!tp->packets_out) { @@ -3362,7 +3364,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; - tp->rcv_nxt = seq; + WRITE_ONCE(tp->rcv_nxt, seq); } /* Update our send window. @@ -5356,7 +5358,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = ptr; + WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ tp->pred_flags = 0; @@ -5932,7 +5934,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Ok.. it's good. Set up sequence numbers and * move to established. */ - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -5961,7 +5963,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -6035,8 +6037,8 @@ discard: tp->tcp_header_len = sizeof(struct tcphdr); } - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6087,6 +6089,8 @@ reset_and_undo: static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { + struct request_sock *req; + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ @@ -6096,7 +6100,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, * we no longer need req so release it. */ - reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false); + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); + reqsk_fastopen_remove(sk, req, false); /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case @@ -6171,7 +6177,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; - req = tp->fastopen_rsk; + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); if (req) { bool req_stolen; @@ -6211,7 +6218,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2ee45e3755e9..6be568334848 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); @@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1644,7 +1647,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -1916,7 +1919,7 @@ process: if (tcp_v4_inbound_md5_hash(sk, skb)) goto discard_and_relse; - nf_reset(skb); + nf_reset_ct(skb); if (tcp_filter(sk, skb)) goto discard_and_relse; @@ -2121,7 +2124,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk); + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2455,12 +2458,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bb140a5db8c0..c802bc80c400 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk; struct tcp_sock *oldtp, *newtp; + u32 seq; if (!newsk) return NULL; @@ -475,12 +476,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, /* Now setup tcp_sock */ newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; + seq = treq->rcv_isn + 1; + newtp->rcv_wup = seq; + WRITE_ONCE(newtp->copied_seq, seq); + WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + seq = treq->snt_isn + 1; + newtp->snd_sml = newtp->snd_una = seq; + WRITE_ONCE(newtp->snd_nxt, seq); + newtp->snd_up = seq; INIT_LIST_HEAD(&newtp->tsq_node); INIT_LIST_HEAD(&newtp->tsorted_sent_queue); @@ -495,7 +500,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, @@ -541,7 +546,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; + RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fec6d67bfd14..0488607c5cd3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); @@ -1196,10 +1196,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } @@ -1333,7 +1333,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; @@ -1443,7 +1443,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; - sk->sk_wmem_queued -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } @@ -1888,7 +1888,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return -ENOMEM; skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; @@ -2152,7 +2152,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); @@ -2482,7 +2482,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; @@ -3142,7 +3142,7 @@ void tcp_send_fin(struct sock *sk) * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ - tp->snd_nxt++; + WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { @@ -3222,7 +3222,7 @@ int tcp_send_synack(struct sock *sk) tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } @@ -3426,14 +3426,14 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3447,9 +3447,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3586,11 +3586,11 @@ int tcp_connect(struct sock *sk) /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { - tp->snd_nxt = TCP_SKB_CB(buff)->seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 40de2d2364a1..dd5a6317a801 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (likely(timeout == 0)) - timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN); + if (likely(timeout == 0)) { + unsigned int rto_base = TCP_RTO_MIN; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + timeout = tcp_model_timeout(sk, boundary, rto_base); + } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } @@ -381,15 +386,13 @@ abort: tcp_write_err(sk); * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; - req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { @@ -430,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf755156a684..14bc654b6842 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -821,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); __wsum csum = 0; /* @@ -854,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh), - cork->gso_size); + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + } goto csum_partial; } @@ -1969,7 +1972,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) */ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); @@ -2298,7 +2301,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a576ff92c39..34ccef18b40e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5964,13 +5964,20 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: /* - * If the address was optimistic - * we inserted the route at the start of - * our DAD process, so we don't need - * to do it again + * If the address was optimistic we inserted the route at the + * start of our DAD process, so we don't need to do it again. + * If the device was taken down in the middle of the DAD + * cycle there is a race where we could get here without a + * host route, so nothing to insert. That will be fixed when + * the device is brought up. */ - if (!rcu_access_pointer(ifp->rt->fib6_node)) + if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) { ip6_ins_rt(net, ifp->rt); + } else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) { + pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n", + &ifp->addr, ifp->idev->dev->name); + } + if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d5779d6a6065..787d9f2a6e99 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2192,6 +2192,7 @@ static void ip6erspan_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6erspan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index d432d0011c16..3d71c7d6102c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -223,6 +223,16 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; + /* While RFC4291 is not explicit about v4mapped addresses + * in IPv6 headers, it seems clear linux dual-stack + * model can not deal properly with these. + * Security models could be fooled by ::ffff:127.0.0.1 for example. + * + * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02 + */ + if (ipv6_addr_v4mapped(&hdr->saddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); @@ -371,7 +381,7 @@ resubmit_final: /* Free reference early: we don't need it any more, and it may hold ip_conntrack module loaded indefinitely. */ - nf_reset(skb); + nf_reset_ct(skb); skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index e6c9da9866b1..a0a2de30be3e 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -54,7 +54,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, return; #if IS_ENABLED(CONFIG_NF_CONNTRACK) - nf_reset(skb); + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); #endif if (hooknum == NF_INET_PRE_ROUTING || diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6e1888ee4036..a77f6b7d3a7c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -215,7 +215,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) /* Not releasing hash table! */ if (clone) { - nf_reset(clone); + nf_reset_ct(clone); rawv6_rcv(sk, clone); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e3d9f4559c99..4804b6dc5e65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; @@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport); + WRITE_ONCE(tp->write_seq, + secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); @@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1895,7 +1896,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " @@ -1906,7 +1908,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index aae4938f3dea..6324d3a8cb53 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1109,6 +1109,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, __wsum csum = 0; int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); /* * Create a UDP header @@ -1141,8 +1142,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + } goto csum_partial; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 105e5a7092e7..f82ea12bac37 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1078,7 +1078,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - nf_reset(skb); + nf_reset_ct(skb); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index bd3f39349d40..fd5ac2788e45 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -151,7 +151,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, skb->ip_summed = CHECKSUM_NONE; skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); rcu_read_lock(); dev = rcu_dereference(spriv->dev); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 622833317dcb..0d7c887a2b75 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -193,7 +193,7 @@ pass_up: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 687e23a8b326..802f19aba7e3 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -206,7 +206,7 @@ pass_up: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2017b7d780f5..c74f44dfaa22 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -113,22 +113,26 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. + * + * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); - int rc = 0; if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); + int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); + if (rc) { + kfree_skb(skb); + return rc; + } } - if (unlikely(!rc)) - rc = llc_build_and_send_pkt(sk, skb); - return rc; + return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) @@ -899,7 +903,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; - struct sk_buff *skb; + struct sk_buff *skb = NULL; size_t size = 0; int rc = -EINVAL, copied = 0, hdrlen; @@ -908,10 +912,10 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) - goto release; + goto out; } else { if (llc_ui_addr_null(&llc->addr)) - goto release; + goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ @@ -919,7 +923,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) - goto release; + goto out; } hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); size = hdrlen + len; @@ -928,12 +932,12 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) copied = size - hdrlen; rc = -EINVAL; if (copied < 0) - goto release; + goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (!skb) - goto release; + goto out; skb->dev = llc->dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hdrlen); @@ -943,29 +947,31 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); + skb = NULL; out: - if (rc) { - kfree_skb(skb); -release: + kfree_skb(skb); + if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); - } release_sock(sk); return rc ? : copied; } diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 4d78375f9872..647c0554d04c 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; @@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 4ff89cb7c86f..7b620acaca9e 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -30,7 +30,7 @@ #endif static int llc_find_offset(int state, int ev_type); -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb); +static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, @@ -55,6 +55,8 @@ int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ; * (executing it's actions and changing state), upper layer will be * indicated or confirmed, if needed. Returns 0 for success, 1 for * failure. The socket lock has to be held before calling this function. + * + * This function always consumes a reference to the skb. */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) { @@ -62,12 +64,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(skb->sk); struct llc_conn_state_ev *ev = llc_conn_ev(skb); - /* - * We have to hold the skb, because llc_conn_service will kfree it in - * the sending path and we need to look at the skb->cb, where we encode - * llc_conn_state_ev. - */ - skb_get(skb); ev->ind_prim = ev->cfm_prim = 0; /* * Send event to state machine @@ -75,21 +71,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) rc = llc_conn_service(skb->sk, skb); if (unlikely(rc != 0)) { printk(KERN_ERR "%s: llc_conn_service failed\n", __func__); - goto out_kfree_skb; - } - - if (unlikely(!ev->ind_prim && !ev->cfm_prim)) { - /* indicate or confirm not required */ - if (!skb->next) - goto out_kfree_skb; goto out_skb_put; } - if (unlikely(ev->ind_prim && ev->cfm_prim)) /* Paranoia */ - skb_get(skb); - switch (ev->ind_prim) { case LLC_DATA_PRIM: + skb_get(skb); llc_save_primitive(sk, skb, LLC_DATA_PRIM); if (unlikely(sock_queue_rcv_skb(sk, skb))) { /* @@ -106,6 +93,7 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * skb->sk pointing to the newly created struct sock in * llc_conn_handler. -acme */ + skb_get(skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_state_change(sk); break; @@ -121,7 +109,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) sk->sk_state_change(sk); } } - kfree_skb(skb); sock_put(sk); break; case LLC_RESET_PRIM: @@ -130,14 +117,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset ind!\n", __func__); - kfree_skb(skb); break; default: - if (ev->ind_prim) { + if (ev->ind_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->ind_prim); - kfree_skb(skb); - } /* No indication */ break; } @@ -179,25 +163,22 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) printk(KERN_INFO "%s: received a reset conf!\n", __func__); break; default: - if (ev->cfm_prim) { + if (ev->cfm_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->cfm_prim); - break; - } - goto out_skb_put; /* No confirmation */ + /* No confirmation */ + break; } -out_kfree_skb: - kfree_skb(skb); out_skb_put: kfree_skb(skb); return rc; } -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); - return llc_conn_send_pdus(sk, skb); + llc_conn_send_pdus(sk); } /** @@ -255,7 +236,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -296,7 +277,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -340,16 +321,12 @@ out: /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection - * @hold_skb: the skb held by caller, or NULL if does not care * - * Sends queued pdus to MAC layer for transmission. When @hold_skb is - * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent - * successfully, or 1 for failure. + * Sends queued pdus to MAC layer for transmission. */ -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) +static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; - int ret = 0; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); @@ -361,20 +338,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; - dev_queue_xmit(skb2); - } else { - bool is_target = skb == hold_skb; - int rc; - - if (is_target) - skb_get(skb); - rc = dev_queue_xmit(skb); - if (is_target) - ret = rc; + skb = skb2; } + dev_queue_xmit(skb); } - - return ret; } /** @@ -846,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) goto drop_unlock; } out: diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index 8db03c2d5440..ad6547736c21 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -38,6 +38,8 @@ * closed and -EBUSY when sending data is not permitted in this state or * LLC has send an I pdu with p bit set to 1 and is waiting for it's * response. + * + * This function always consumes a reference to the skb. */ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) { @@ -46,20 +48,22 @@ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(sk); if (unlikely(llc->state == LLC_CONN_STATE_ADM)) - goto out; + goto out_free; rc = -EBUSY; if (unlikely(llc_data_accept_state(llc->state) || /* data_conn_refuse */ llc->p_flag)) { llc->failed_data_req = 1; - goto out; + goto out_free; } ev = llc_conn_ev(skb); ev->type = LLC_CONN_EV_TYPE_PRIM; ev->prim = LLC_DATA_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; skb->dev = llc->dev; - rc = llc_conn_state_process(sk, skb); -out: + return llc_conn_state_process(sk, skb); + +out_free: + kfree_skb(skb); return rc; } diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index a94bd56bcac6..7ae4cc684d3a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a7f7b8ff4729..be419062e19a 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -197,29 +197,22 @@ out: * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. + * + * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - /* - * We have to hold the skb, because llc_sap_next_state - * will kfree it in the sending path and we need to - * look at the skb->cb, where we encode llc_sap_state_ev. - */ - skb_get(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); - if (ev->ind_cfm_flag == LLC_IND) { - if (skb->sk->sk_state == TCP_LISTEN) - kfree_skb(skb); - else { - llc_save_primitive(skb->sk, skb, ev->prim); - /* queue skb to the user. */ - if (sock_queue_rcv_skb(skb->sk, skb)) - kfree_skb(skb); - } + if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { + llc_save_primitive(skb->sk, skb, ev->prim); + + /* queue skb to the user. */ + if (sock_queue_rcv_skb(skb->sk, skb) == 0) + return; } kfree_skb(skb); } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index b1438fd4d876..64b544ae9966 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -487,9 +487,14 @@ static ssize_t ieee80211_if_fmt_aqm( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; - struct txq_info *txqi = to_txq_info(sdata->vif.txq); + struct txq_info *txqi; int len; + if (!sdata->vif.txq) + return 0; + + txqi = to_txq_info(sdata->vif.txq); + spin_lock_bh(&local->fq.lock); rcu_read_lock(); @@ -658,7 +663,9 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); - if (sdata->local->ops->wake_tx_queue) + if (sdata->local->ops->wake_tx_queue && + sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && + sdata->vif.type != NL80211_IFTYPE_NAN) DEBUGFS_ADD(aqm); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 26a2f49208b6..54dd8849d1cc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2633,7 +2633,8 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, rcu_read_lock(); ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); - if (WARN_ON_ONCE(ssid == NULL)) + if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN, + "invalid SSID element (len=%d)", ssid ? ssid[1] : -1)) ssid_len = 0; else ssid_len = ssid[1]; @@ -5233,7 +5234,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); - if (!ssidie) { + if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) { rcu_read_unlock(); kfree(assoc_data); return -EINVAL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 768d14c9a716..0e05ff037672 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3467,9 +3467,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) case cpu_to_le16(IEEE80211_STYPE_PROBE_RESP): /* process for all: mesh, mlme, ibss */ break; + case cpu_to_le16(IEEE80211_STYPE_DEAUTH): + if (is_multicast_ether_addr(mgmt->da) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + + /* process only for station/IBSS */ + if (sdata->vif.type != NL80211_IFTYPE_STATION && + sdata->vif.type != NL80211_IFTYPE_ADHOC) + return RX_DROP_MONITOR; + break; case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP): case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP): - case cpu_to_le16(IEEE80211_STYPE_DEAUTH): case cpu_to_le16(IEEE80211_STYPE_DISASSOC): if (is_multicast_ether_addr(mgmt->da) && !is_broadcast_ether_addr(mgmt->da)) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index adf94ba1ed77..4d31d9688dc2 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -520,10 +520,33 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, return 0; } +static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *sdata_iter; + + if (!ieee80211_is_radar_required(local)) + return true; + + if (!regulatory_pre_cac_allowed(local->hw.wiphy)) + return false; + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata_iter, &local->interfaces, list) { + if (sdata_iter->wdev.cac_started) { + mutex_unlock(&local->iflist_mtx); + return false; + } + } + mutex_unlock(&local->iflist_mtx); + + return true; +} + static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - if (ieee80211_is_radar_required(local)) + if (!__ieee80211_can_leave_ch(sdata)) return false; if (!list_empty(&local->roc_list)) @@ -630,7 +653,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&local->mtx); - if (local->scan_req || ieee80211_is_radar_required(local)) + if (local->scan_req) + return -EBUSY; + + if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; if (!ieee80211_can_scan(local, sdata)) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 051a02ddcb85..32a7a53833c0 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -247,7 +247,8 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) struct sta_info *sta; int i; - spin_lock_bh(&fq->lock); + local_bh_disable(); + spin_lock(&fq->lock); if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; @@ -273,9 +274,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) &txqi->flags)) continue; - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); - spin_lock_bh(&fq->lock); + spin_lock(&fq->lock); } } @@ -288,12 +289,14 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) goto out; - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); + local_bh_enable(); return; out: - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); + local_bh_enable(); } static void diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9c464d24beec..888d3068a492 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -613,7 +613,7 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (unlikely(cp->flags & IP_VS_CONN_F_NFCT)) ret = ip_vs_confirm_conntrack(skb); if (ret == NF_ACCEPT) { - nf_reset(skb); + nf_reset_ct(skb); skb_forward_csum(skb); } return ret; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0c63120b2db2..5cd610b547e0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index af1497ab9464..69d6173f91e2 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -218,8 +218,13 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); + bool ret; - return nf_conncount_gc_list(net, &priv->list); + local_bh_disable(); + ret = nf_conncount_gc_list(net, &priv->list); + local_bh_enable(); + + return ret; } static struct nft_expr_type nft_connlimit_type; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 8dfea26536c9..ccdd790e163a 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -107,9 +107,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) llcp_sock->service_name = kmemdup(llcp_addr.service_name, llcp_sock->service_name_len, GFP_KERNEL); - + if (!llcp_sock->service_name) { + ret = -ENOMEM; + goto put_dev; + } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { + kfree(llcp_sock->service_name); + llcp_sock->service_name = NULL; ret = -EADDRINUSE; goto put_dev; } diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index d2437b5b2f6a..21c90d3a7ebf 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -237,7 +237,7 @@ static netdev_tx_t internal_dev_recv(struct sk_buff *skb) } skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); secpath_reset(skb); skb->pkt_type = PACKET_HOST; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e2742b006d25..82a50e850245 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1821,7 +1821,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* drop conntrack reference */ - nf_reset(skb); + nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; @@ -2121,7 +2121,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* drop conntrack reference */ - nf_reset(skb); + nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; diff --git a/net/rds/ib.c b/net/rds/ib.c index 45acab2de0cf..9de2ae22d583 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -143,6 +143,9 @@ static void rds_ib_add_one(struct ib_device *device) refcount_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); + INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); + INIT_LIST_HEAD(&rds_ibdev->conn_list); + rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE); @@ -203,9 +206,6 @@ static void rds_ib_add_one(struct ib_device *device) device->name, rds_ibdev->use_fastreg ? "FRMR" : "FMR"); - INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); - INIT_LIST_HEAD(&rds_ibdev->conn_list); - down_write(&rds_ib_devices_lock); list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices); up_write(&rds_ib_devices_lock); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1091bf35a199..ecc17dabec8f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -556,6 +556,7 @@ struct rxrpc_call { struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ + const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ unsigned long ack_at; /* When deferred ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 00c095d74145..135bf5cd8dd5 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -84,7 +84,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), here); } @@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call, rxrpc_call_new_service, + trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, atomic_read(&call->usage), here, (const void *)user_call_ID); @@ -307,6 +307,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; + call->security = conn->security; call->peer = rxrpc_get_peer(conn->params.peer); call->cong_cwnd = call->peer->cong_cwnd; return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 32d8dc677142..a31c18c09894 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -240,7 +240,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (p->intr) __set_bit(RXRPC_CALL_IS_INTR, &call->flags); call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, + atomic_read(&call->usage), here, (const void *)p->user_call_ID); /* We need to protect a partially set up call against the user as we @@ -290,8 +291,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error; - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_connected, + atomic_read(&call->usage), here, NULL); rxrpc_start_call_timer(call); @@ -313,8 +314,8 @@ error_dup_user_ID: error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); @@ -376,7 +377,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call) if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -391,7 +393,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call) int n = atomic_read(&call->usage); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -406,7 +409,8 @@ void rxrpc_see_call(struct rxrpc_call *call) if (call) { int n = atomic_read(&call->usage); - trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, + here, NULL); } } @@ -418,7 +422,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n, here, NULL); } /* @@ -445,7 +449,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_release, + atomic_read(&call->usage), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -488,10 +493,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) { + if (conn) rxrpc_disconnect_call(call); - conn->security->free_call_crypto(call); - } + if (call->security) + call->security->free_call_crypto(call); rxrpc_cleanup_ring(call); _leave(""); @@ -534,12 +539,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); + unsigned int debug_id = call->debug_id; int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(debug_id, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3f1da1b49f69..376370cd9285 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -212,7 +212,8 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) rxrpc_get_local(conn->params.local); key_get(conn->params.key); - trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage), + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, + atomic_read(&conn->usage), __builtin_return_address(0)); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); @@ -352,6 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, if (cp->exclusive) { call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; _leave(" = 0 [exclusive %d]", candidate->debug_id); @@ -403,6 +405,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, candidate_published: set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; spin_unlock(&local->client_conns_lock); @@ -425,6 +428,7 @@ found_extant_conn: spin_lock(&conn->channel_lock); call->conn = conn; + call->security = conn->security; call->security_ix = conn->security_ix; call->service_id = conn->service_id; list_add_tail(&call->chan_wait_link, &conn->waiting_calls); @@ -985,11 +989,12 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) void rxrpc_put_client_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; do { n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); if (n > 0) return; ASSERTCMP(n, >=, 0); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ed05b6922132..38d718e90dc6 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -269,7 +269,7 @@ bool rxrpc_queue_conn(struct rxrpc_connection *conn) if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here); else rxrpc_put_connection(conn); return true; @@ -284,7 +284,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) if (conn) { int n = atomic_read(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); } } @@ -296,7 +296,7 @@ void rxrpc_get_connection(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_got, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); } /* @@ -310,7 +310,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) if (conn) { int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) - trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here); else conn = NULL; } @@ -333,10 +333,11 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, void rxrpc_put_service_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here); ASSERTCMP(n, >=, 0); if (n == 1) rxrpc_set_service_reap_timer(conn->params.local->rxnet, @@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) continue; - trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); if (rxrpc_conn_is_client(conn)) BUG(); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index b30e13f6d95f..123d6ceab15c 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -134,7 +134,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), __builtin_return_address(0)); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index c97ebdc043e4..61451281d74a 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -151,6 +151,9 @@ void rxrpc_error_report(struct sock *sk) struct rxrpc_peer *peer; struct sk_buff *skb; + if (unlikely(!local)) + return; + _enter("%p{%d}", sk, local->debug_id); /* Clear the outstanding error value on the socket so that it doesn't diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9c3ac96f71cb..64830d8c1fdb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { atomic_set(&peer->usage, 1); - peer->local = local; + peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - peer->local = local; rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); @@ -382,7 +381,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) int n; n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); return peer; } @@ -396,7 +395,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) if (peer) { int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) - trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); else peer = NULL; } @@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } @@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n; if (peer) { + debug_id = peer->debug_id; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) __rxrpc_put_peer(peer); } @@ -443,13 +445,15 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id = peer->debug_id; int n; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3b0becb12041..a4090797c9b2 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -251,8 +251,8 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, seq += subpacket; } - return call->conn->security->verify_packet(call, skb, offset, len, - seq, cksum); + return call->security->verify_packet(call, skb, offset, len, + seq, cksum); } /* @@ -291,7 +291,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, *_offset = offset; *_len = len; - call->conn->security->locate_data(call, skb, _offset, _len); + call->security->locate_data(call, skb, _offset, _len); return 0; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6a1547b270fe..813fd6888142 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -419,7 +419,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, call->tx_winsize) sp->hdr.flags |= RXRPC_MORE_PACKETS; - ret = conn->security->secure_packet( + ret = call->security->secure_packet( call, skb, skb->mark, skb->head); if (ret < 0) goto out; @@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: case RXRPC_CALL_SERVER_ACCEPTING: + rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; default: diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2558f00f6b3e..4e7429c6f864 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -832,8 +832,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) } static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { - [TCA_ACT_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_ACT_KIND] = { .type = NLA_STRING }, [TCA_ACT_INDEX] = { .type = NLA_U32 }, [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, @@ -865,8 +864,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; } - nla_strlcpy(act_name, kind, IFNAMSIZ); - + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + goto err_out; + } if (tb[TCA_ACT_COOKIE]) { cookie = nla_memdup_cookie(tb); if (!cookie) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9ce073a05414..08923b21e566 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -484,7 +484,11 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, &mirred_net_ops); + err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); + if (err) + unregister_netdevice_notifier(&mirred_device_notifier); + + return err; } static void __exit mirred_cleanup_module(void) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 64584a1df425..8717c0b26c90 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -162,11 +162,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ; + memset(name, 0, IFNAMSIZ); + return false; +} + static bool tcf_proto_is_unlocked(const char *kind) { const struct tcf_proto_ops *ops; bool ret; + if (strlen(kind) == 0) + return false; + ops = tcf_proto_lookup_ops(kind, false, NULL); /* On error return false to take rtnl lock. Proto lookup/create * functions will perform lookup again and properly handle errors. @@ -1843,6 +1854,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1899,13 +1911,19 @@ replay: if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, * block is shared (no qdisc found), qdisc is not unlocked, classifier * type is not specified, classifier is not unlocked. */ if (rtnl_held || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2063,6 +2081,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2102,13 +2121,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc * found), qdisc is not unlocked, classifier type is not specified, * classifier is not unlocked. */ if (!prio || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2216,6 +2240,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2252,12 +2277,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not * unlocked, classifier type is not specified, classifier is not * unlocked. */ if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 82bd14e7ac93..3177dcb17316 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) @@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat) *err = -1; return; } - dst->value = sk->sk_rcvlowat; + dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 81d58b280612..1047825d9f48 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 06c7a2da21bc..39b427dc7512 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, }; +static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, + cbq_policy, extack); + if (err < 0) + return err; + + if (tb[TCA_CBQ_WRROPT]) { + const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); + + if (wrr->priority > TC_CBQ_MAXPRIO) { + NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); + err = -EINVAL; + } + } + return err; +} + static int cbq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt, hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); q->delay_timer.function = cbq_undelay; - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; @@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t struct cbq_class *parent; struct qdisc_rate_table *rtab = NULL; - if (!opt) { - NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 1bef152c5721..b2905b03a432 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index bad1cbe59a56..05605b30bef3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, goto errout; err = -EINVAL; + if (!tb[TCA_DSMARK_INDICES]) + goto errout; indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); if (hweight32(indices) != 1) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2f7b34205c82..6719a65169d4 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1044,12 +1044,11 @@ static void taprio_set_picos_per_byte(struct net_device *dev, if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - speed * 1000 * 1000); + picos_per_byte = (USEC_PER_SEC * 8) / speed; atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", @@ -1342,6 +1341,10 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } + + /* Everything went ok, return success. */ + err = 0; + out: return err; } diff --git a/net/sctp/diag.c b/net/sctp/diag.c index fc9a4c6629ce..0851166b9175 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0) diff --git a/net/sctp/input.c b/net/sctp/input.c index 1008cdc44dd6..2277981559d0 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -201,7 +201,7 @@ int sctp_rcv(struct sk_buff *skb) if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family)) goto discard_release; - nf_reset(skb); + nf_reset_ct(skb); if (sk_filter(sk, skb)) goto discard_release; @@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb) bh_lock_sock(sk); } - if (sock_owned_by_user(sk)) { + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); @@ -321,8 +321,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) local_bh_disable(); bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) sctp_chunk_free(chunk); else backloged = 1; @@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) if (backloged) return 0; } else { - sctp_inq_push(inqueue, chunk); + if (!sctp_newsk_ready(sk)) { + if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) + return 0; + sctp_chunk_free(chunk); + } else { + sctp_inq_push(inqueue, chunk); + } } done: @@ -358,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) struct sctp_ep_common *rcvr = chunk->rcvr; int ret; - ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf); + ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4ca50ddf8d16..88556f0251ab 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -213,7 +213,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; - goto out; + goto ism_put_vlan; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; @@ -289,6 +289,9 @@ clear_llc_lnk: smc_llc_link_clear(lnk); free_lgr: kfree(lgr); +ism_put_vlan: + if (ini->is_smcd && ini->vlan_id) + smc_ism_put_vlan(ini->ism_dev, ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 413a6abf227e..97e8369002d7 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -211,8 +211,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, rc = sk_wait_event(sk, timeo, sk->sk_err || sk->sk_shutdown & RCV_SHUTDOWN || - fcrit(conn) || - smc_cdc_rxed_any_close_or_senddone(conn), + fcrit(conn), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); @@ -262,6 +261,18 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, return -EAGAIN; } +static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) +{ + struct smc_connection *conn = &smc->conn; + + if (smc_rx_data_available(conn)) + return true; + else if (conn->urg_state == SMC_URG_VALID) + /* we received a single urgent Byte - skip */ + smc_rx_update_cons(smc, 0); + return false; +} + /* smc_rx_recvmsg - receive data from RMBE * @msg: copy data to receive buffer * @pipe: copy data to pipe if set - indicates splice() call @@ -303,16 +314,18 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, if (read_done >= target || (pipe && read_done)) break; - if (atomic_read(&conn->bytes_to_rcv)) + if (smc_rx_recvmsg_data_available(smc)) goto copy; - else if (conn->urg_state == SMC_URG_VALID) - /* we received a single urgent Byte - skip */ - smc_rx_update_cons(smc, 0); if (sk->sk_shutdown & RCV_SHUTDOWN || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) { + /* smc_cdc_msg_recv_action() could have run after + * above smc_rx_recvmsg_data_available() + */ + if (smc_rx_recvmsg_data_available(smc)) + goto copy; break; + } if (read_done) { if (sk->sk_err || diff --git a/net/tipc/link.c b/net/tipc/link.c index 6cc75ffd9e2c..999eab592de8 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -160,6 +160,7 @@ struct tipc_link { struct { u16 len; u16 limit; + struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; u16 window; @@ -880,6 +881,7 @@ static void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; + u32 imp; __skb_queue_head_init(&list); @@ -901,11 +903,10 @@ void tipc_link_reset(struct tipc_link *l) __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); __skb_queue_purge(&l->failover_deferdq); - l->backlog[TIPC_LOW_IMPORTANCE].len = 0; - l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; - l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; - l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; - l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; + for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) { + l->backlog[imp].len = 0; + l->backlog[imp].target_bskb = NULL; + } kfree_skb(l->reasm_buf); kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); @@ -947,7 +948,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; struct sk_buff_head *transmq = &l->transmq; struct sk_buff_head *backlogq = &l->backlogq; - struct sk_buff *skb, *_skb, *bskb; + struct sk_buff *skb, *_skb, **tskb; int pkt_cnt = skb_queue_len(list); int rc = 0; @@ -999,19 +1000,21 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, seqno++; continue; } - if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { + tskb = &l->backlog[imp].target_bskb; + if (tipc_msg_bundle(*tskb, hdr, mtu)) { kfree_skb(__skb_dequeue(list)); l->stats.sent_bundled++; continue; } - if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { + if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) { kfree_skb(__skb_dequeue(list)); - __skb_queue_tail(backlogq, bskb); - l->backlog[msg_importance(buf_msg(bskb))].len++; + __skb_queue_tail(backlogq, *tskb); + l->backlog[imp].len++; l->stats.sent_bundled++; l->stats.sent_bundles++; continue; } + l->backlog[imp].target_bskb = NULL; l->backlog[imp].len += skb_queue_len(list); skb_queue_splice_tail_init(list, backlogq); } @@ -1027,6 +1030,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l, u16 seqno = l->snd_nxt; u16 ack = l->rcv_nxt - 1; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u32 imp; while (skb_queue_len(&l->transmq) < l->window) { skb = skb_peek(&l->backlogq); @@ -1037,7 +1041,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l, break; __skb_dequeue(&l->backlogq); hdr = buf_msg(skb); - l->backlog[msg_importance(hdr)].len--; + imp = msg_importance(hdr); + l->backlog[imp].len--; + if (unlikely(skb == l->backlog[imp].target_bskb)) + l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); /* next retransmit attempt */ if (link_is_bc_sndlink(l)) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index e6d49cdc61b4..922d262e153f 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -543,10 +543,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, bmsg = buf_msg(_skb); tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); - if (msg_isdata(msg)) - msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE); - else - msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE); + msg_set_importance(bmsg, msg_importance(msg)); msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3b9f8cc328f5..f8bbc4aab213 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_msg *hdr = buf_msg(skb); if (unlikely(msg_in_group(hdr))) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); if (unlikely(!msg_connected(hdr))) - return sk->sk_rcvbuf << msg_importance(hdr); + return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr); if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL)) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); return FLOWCTL_MSG_LIM; } @@ -3790,7 +3790,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf); i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk)); i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf); - i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len); + i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len)); if (dqueues & TIPC_DUMP_SK_SNDQ) { i += scnprintf(buf + i, sz - i, "sk_write_queue: "); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ab47bf3ab66e..2ab43b2bba31 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -638,7 +638,7 @@ struct sock *__vsock_create(struct net *net, } EXPORT_SYMBOL_GPL(__vsock_create); -static void __vsock_release(struct sock *sk) +static void __vsock_release(struct sock *sk, int level) { if (sk) { struct sk_buff *skb; @@ -648,9 +648,17 @@ static void __vsock_release(struct sock *sk) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ + /* The release call is supposed to use lock_sock_nested() + * rather than lock_sock(), if a sock lock should be acquired. + */ transport->release(vsk); - lock_sock(sk); + /* When "level" is SINGLE_DEPTH_NESTING, use the nested + * version to avoid the warning "possible recursive locking + * detected". When "level" is 0, lock_sock_nested(sk, level) + * is the same as lock_sock(sk). + */ + lock_sock_nested(sk, level); sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; @@ -659,7 +667,7 @@ static void __vsock_release(struct sock *sk) /* Clean up any sockets that never were accepted. */ while ((pending = vsock_dequeue_accept(sk)) != NULL) { - __vsock_release(pending); + __vsock_release(pending, SINGLE_DEPTH_NESTING); sock_put(pending); } @@ -708,7 +716,7 @@ EXPORT_SYMBOL_GPL(vsock_stream_has_space); static int vsock_release(struct socket *sock) { - __vsock_release(sock->sk); + __vsock_release(sock->sk, 0); sock->sk = NULL; sock->state = SS_FREE; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 261521d286d6..c443db7af8d4 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -559,7 +559,7 @@ static void hvs_release(struct vsock_sock *vsk) struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); release_sock(sk); if (remove_sock) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 5bb70c692b1e..a666ef8fc54e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -820,7 +820,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d21b1581a665..4453dd375de9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -201,6 +201,38 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info) return __cfg80211_rdev_from_attrs(netns, info->attrs); } +static int validate_beacon_head(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const u8 *data = nla_data(attr); + unsigned int len = nla_len(attr); + const struct element *elem; + const struct ieee80211_mgmt *mgmt = (void *)data; + unsigned int fixedlen = offsetof(struct ieee80211_mgmt, + u.beacon.variable); + + if (len < fixedlen) + goto err; + + if (ieee80211_hdrlen(mgmt->frame_control) != + offsetof(struct ieee80211_mgmt, u.beacon)) + goto err; + + data += fixedlen; + len -= fixedlen; + + for_each_element(elem, data, len) { + /* nothing */ + } + + if (for_each_element_completed(elem, data, len)) + return 0; + +err: + NL_SET_ERR_MSG_ATTR(extack, attr, "malformed beacon head"); + return -EINVAL; +} + static int validate_ie_attr(const struct nlattr *attr, struct netlink_ext_ack *extack) { @@ -338,8 +370,9 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BEACON_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_DTIM_PERIOD] = { .type = NLA_U32 }, - [NL80211_ATTR_BEACON_HEAD] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_BEACON_HEAD] = + NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_beacon_head, + IEEE80211_MAX_DATA_LEN), [NL80211_ATTR_BEACON_TAIL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_ie_attr, IEEE80211_MAX_DATA_LEN), @@ -2636,6 +2669,8 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, control_freq = nla_get_u32(attrs[NL80211_ATTR_WIPHY_FREQ]); + memset(chandef, 0, sizeof(*chandef)); + chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq); chandef->width = NL80211_CHAN_WIDTH_20_NOHT; chandef->center_freq1 = control_freq; @@ -3176,7 +3211,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag if (rdev->ops->get_channel) { int ret; - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; ret = rdev_get_channel(rdev, wdev, &chandef); if (ret == 0) { @@ -6270,6 +6305,9 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->del_mpath) return -EOPNOTSUPP; + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + return rdev_del_mpath(rdev, dev, dst); } @@ -13644,7 +13682,7 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb, hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_FTM_RESPONDER_STATS); if (!hdr) - return -ENOBUFS; + goto nla_put_failure; if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5311d0ae2454..446c76d44e65 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2108,7 +2108,7 @@ static void reg_call_notifier(struct wiphy *wiphy, static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) { - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; @@ -3883,6 +3883,7 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) return pre_cac_allowed; } +EXPORT_SYMBOL(regulatory_pre_cac_allowed); void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 504133d76de4..dc8f689bd469 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -156,14 +156,6 @@ bool regulatory_indoor_allowed(void); #define REG_PRE_CAC_EXPIRY_GRACE_MS 2000 /** - * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain - * @wiphy: wiphy for which pre-CAC capability is checked. - - * Pre-CAC is allowed only in ETSI domain. - */ -bool regulatory_pre_cac_allowed(struct wiphy *wiphy); - -/** * regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys * @wiphy - wiphy on which radar is detected and the event will be propagated * to other available wiphys having the same DFS domain diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d313c9befa23..aef240fdf8df 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1703,8 +1703,7 @@ cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy, static void cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, struct cfg80211_bss *nontrans_bss, - struct ieee80211_mgmt *mgmt, size_t len, - gfp_t gfp) + struct ieee80211_mgmt *mgmt, size_t len) { u8 *ie, *new_ie, *pos; const u8 *nontrans_ssid, *trans_ssid, *mbssid; @@ -1715,6 +1714,8 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, const struct cfg80211_bss_ies *old; u8 cpy_len; + lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock); + ie = mgmt->u.probe_resp.variable; new_ie_len = ielen; @@ -1723,26 +1724,30 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, return; new_ie_len -= trans_ssid[1]; mbssid = cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen); - if (!mbssid) + /* + * It's not valid to have the MBSSID element before SSID + * ignore if that happens - the code below assumes it is + * after (while copying things inbetween). + */ + if (!mbssid || mbssid < trans_ssid) return; new_ie_len -= mbssid[1]; - rcu_read_lock(); + nontrans_ssid = ieee80211_bss_get_ie(nontrans_bss, WLAN_EID_SSID); - if (!nontrans_ssid) { - rcu_read_unlock(); + if (!nontrans_ssid) return; - } + new_ie_len += nontrans_ssid[1]; - rcu_read_unlock(); /* generate new ie for nontrans BSS * 1. replace SSID with nontrans BSS' SSID * 2. skip MBSSID IE */ - new_ie = kzalloc(new_ie_len, gfp); + new_ie = kzalloc(new_ie_len, GFP_ATOMIC); if (!new_ie) return; - new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, gfp); + + new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC); if (!new_ies) goto out_free; @@ -1896,6 +1901,8 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len, &non_tx_data, gfp); + spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock); + /* check if the res has other nontransmitting bss which is not * in MBSSID IE */ @@ -1910,8 +1917,9 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, ies2 = rcu_access_pointer(tmp_bss->ies); if (ies2->tsf < ies1->tsf) cfg80211_update_notlisted_nontrans(wiphy, tmp_bss, - mgmt, len, gfp); + mgmt, len); } + spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock); return res; } diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 7b6529d81c61..cac9e28d852b 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -798,7 +798,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; int ret; switch (wdev->iftype) { diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index c67d7a82ab13..73fd0eae08ca 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -202,6 +202,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) @@ -219,7 +220,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, if (ie) { data->flags = 1; data->length = ie[1]; - memcpy(ssid, ie + 2, data->length); + if (data->length > IW_ESSID_MAX_SIZE) + ret = -EINVAL; + else + memcpy(ssid, ie + 2, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { @@ -229,7 +233,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, } wdev_unlock(wdev); - return 0; + return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 5c111bc3c8ea..00e782335cb0 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) if (!sock_owned_by_user(sk)) { queued = x25_process_rx_frame(sk, skb); } else { - queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf); + queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); } bh_unlock_sock(sk); sock_put(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index fa8fbb8fa3c8..9044073fbf22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -305,9 +305,8 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct sock *sk) +static int xsk_zc_xmit(struct xdp_sock *xs) { - struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev = xs->dev; return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, @@ -327,11 +326,10 @@ static void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, - size_t total_len) +static int xsk_generic_xmit(struct sock *sk) { - u32 max_batch = TX_BATCH_SIZE; struct xdp_sock *xs = xdp_sk(sk); + u32 max_batch = TX_BATCH_SIZE; bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; @@ -394,6 +392,18 @@ out: return err; } +static int __xsk_sendmsg(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; + + return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); +} + static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); @@ -402,21 +412,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (unlikely(!xsk_is_bound(xs))) return -ENXIO; - if (unlikely(!(xs->dev->flags & IFF_UP))) - return -ENETDOWN; - if (unlikely(!xs->tx)) - return -ENOBUFS; - if (need_wait) + if (unlikely(need_wait)) return -EOPNOTSUPP; - return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len); + return __xsk_sendmsg(sk); } static unsigned int xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { unsigned int mask = datagram_poll(file, sock, wait); - struct xdp_sock *xs = xdp_sk(sock->sk); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; struct xdp_umem *umem; @@ -426,9 +433,14 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock, dev = xs->dev; umem = xs->umem; - if (umem->need_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (umem->need_wakeup) { + if (dev->netdev_ops->ndo_xsk_wakeup) + dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + umem->need_wakeup); + else + /* Poll needs to drive Tx also in copy mode */ + __xsk_sendmsg(sk); + } if (xs->rx && !xskq_empty_desc(xs->rx)) mask |= POLLIN | POLLRDNORM; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 6088bc2dc11e..9b599ed66d97 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -706,7 +706,7 @@ resume: if (err) goto drop; - nf_reset(skb); + nf_reset_ct(skb); if (decaps) { sp = skb_sec_path(skb); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 2ab4859df55a..0f5131bc3342 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -185,7 +185,7 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); nf_reset_trace(skb); if (!xnet) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9499b35feb92..b1db55b50ba1 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -502,7 +502,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { - nf_reset(skb); + nf_reset_ct(skb); err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); if (unlikely(err != 1)) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 21e939235b39..f2d1e573ea55 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2808,7 +2808,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) continue; } - nf_reset(skb); + nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7409722727ca..7048bb3594d6 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -3,7 +3,8 @@ #ifndef __ASM_GOTO_WORKAROUND_H #define __ASM_GOTO_WORKAROUND_H -/* this will bring in asm_volatile_goto macro definition +/* + * This will bring in asm_volatile_goto and asm_inline macro definitions * if enabled by compiler and config options. */ #include <linux/types.h> @@ -13,5 +14,15 @@ #define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") #endif +/* + * asm_inline is defined as asm __inline in "include/linux/compiler_types.h" + * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not + * supported by CLANG. + */ +#ifdef asm_inline +#undef asm_inline +#define asm_inline asm +#endif + #define volatile(x...) volatile("") #endif diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index e39938058223..4c31b305e6ef 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -13,6 +13,7 @@ #include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> +#include <linux/perf_event.h> #include "libbpf.h" #include "bpf_load.h" diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 4b0432e095ae..10ba926ae292 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -143,11 +143,6 @@ cc-ifversion = $(shell [ $(CONFIG_GCC_VERSION)0 $(1) $(2)000 ] && echo $(3) || e # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) -# ar-option -# Usage: KBUILD_ARFLAGS := $(call ar-option,D) -# Important: no spaces around options -ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2)) - # ld-version # Note this is mainly for HJ Lu's 3 number binutil versions ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index f72aba64d611..a9e47953ca53 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -389,7 +389,7 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ; ifdef builtin-target quiet_cmd_ar_builtin = AR $@ - cmd_ar_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(real-prereqs) + cmd_ar_builtin = rm -f $@; $(AR) cDPrST $@ $(real-prereqs) $(builtin-target): $(real-obj-y) FORCE $(call if_changed,ar_builtin) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 4a0cdd6f5909..179d55af5852 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -232,7 +232,7 @@ quiet_cmd_ld = LD $@ # --------------------------------------------------------------------------- quiet_cmd_ar = AR $@ - cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(real-prereqs) + cmd_ar = rm -f $@; $(AR) cDPrsT $@ $(real-prereqs) # Objcopy # --------------------------------------------------------------------------- diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 3961941e8e7a..442d5e2ad688 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2652,15 +2652,20 @@ int main(int argc, char **argv) fatal("modpost: Section mismatches detected.\n" "Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.\n"); for (n = 0; n < SYMBOL_HASH_SIZE; n++) { - struct symbol *s = symbolhash[n]; + struct symbol *s; + + for (s = symbolhash[n]; s; s = s->next) { + /* + * Do not check "vmlinux". This avoids the same warnings + * shown twice, and false-positives for ARCH=um. + */ + if (is_vmlinux(s->module->name) && !s->module->is_dot_o) + continue; - while (s) { if (s->is_static) warn("\"%s\" [%s] is a static %s\n", s->name, s->module->name, export_str(s->export)); - - s = s->next; } } diff --git a/scripts/namespace.pl b/scripts/namespace.pl index 6135574a6f39..1da7bca201a4 100755 --- a/scripts/namespace.pl +++ b/scripts/namespace.pl @@ -65,13 +65,14 @@ use warnings; use strict; use File::Find; +use File::Spec; my $nm = ($ENV{'NM'} || "nm") . " -p"; my $objdump = ($ENV{'OBJDUMP'} || "objdump") . " -s -j .comment"; -my $srctree = ""; -my $objtree = ""; -$srctree = "$ENV{'srctree'}/" if (exists($ENV{'srctree'})); -$objtree = "$ENV{'objtree'}/" if (exists($ENV{'objtree'})); +my $srctree = File::Spec->curdir(); +my $objtree = File::Spec->curdir(); +$srctree = File::Spec->rel2abs($ENV{'srctree'}) if (exists($ENV{'srctree'})); +$objtree = File::Spec->rel2abs($ENV{'objtree'}) if (exists($ENV{'objtree'})); if ($#ARGV != -1) { print STDERR "usage: $0 takes no parameters\n"; @@ -231,9 +232,9 @@ sub do_nm } ($source = $basename) =~ s/\.o$//; if (-e "$source.c" || -e "$source.S") { - $source = "$objtree$File::Find::dir/$source"; + $source = File::Spec->catfile($objtree, $File::Find::dir, $source) } else { - $source = "$srctree$File::Find::dir/$source"; + $source = File::Spec->catfile($srctree, $File::Find::dir, $source) } if (! -e "$source.c" && ! -e "$source.S") { # No obvious source, exclude the object if it is conglomerate diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 365b3c2b8f43..220dae0db3f1 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -126,7 +126,7 @@ scm_version() collect_files() { - local file res + local file res= for file; do case "$file" in diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 19faace69644..35e6ca773734 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -13,9 +13,6 @@ integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyrin integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \ platform_certs/load_uefi.o integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o -$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar -subdir-$(CONFIG_IMA) += ima obj-$(CONFIG_IMA) += ima/ -subdir-$(CONFIG_EVM) += evm obj-$(CONFIG_EVM) += evm/ diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index fbf5e4a0cb9c..5d1995fd369c 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -12,7 +12,11 @@ INSTALL ?= install CFLAGS += -Wall -O2 CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include -ifeq ($(srctree),) +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is set to ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index c6f94cffe06e..56ce6292071b 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -8,7 +8,11 @@ LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory -ifeq ($(srctree),) +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is a ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) srctree := $(patsubst %/,%,$(dir $(srctree))) @@ -110,6 +114,9 @@ override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +# flags specific for shared library +SHLIB_FLAGS := -DSHARED + ifeq ($(VERBOSE),1) Q = else @@ -126,14 +133,17 @@ all: export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include -BPF_IN := $(OUTPUT)libbpf-in.o +SHARED_OBJDIR := $(OUTPUT)sharedobjs/ +STATIC_OBJDIR := $(OUTPUT)staticobjs/ +BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o +BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) -GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ +GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \ sort -u | wc -l) @@ -155,7 +165,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN): force elfdep bpfdep +$(BPF_IN_SHARED): force elfdep bpfdep @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -171,17 +181,20 @@ $(BPF_IN): force elfdep bpfdep @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true - $(Q)$(MAKE) $(build)=libbpf + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" + +$(BPF_IN_STATIC): force elfdep bpfdep + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) -$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) -$(OUTPUT)libbpf.a: $(BPF_IN) +$(OUTPUT)libbpf.a: $(BPF_IN_STATIC) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a @@ -197,7 +210,7 @@ check: check_abi check_abi: $(OUTPUT)libbpf.so @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ - echo "Warning: Num of global symbols in $(BPF_IN)" \ + echo "Warning: Num of global symbols in $(BPF_IN_SHARED)" \ "($(GLOBAL_SYM_COUNT)) does NOT match with num of" \ "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \ "Please make sure all LIBBPF_API symbols are" \ @@ -255,9 +268,9 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(TARGETS) $(CXX_TEST_TARGET) \ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS + *.pc LIBBPF-CFLAGS $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2e83a34f8c79..98216a69c32f 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -34,6 +34,22 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +/* Symbol versioning is different between static and shared library. + * Properly versioned symbols are needed for shared library, but + * only the symbol of the new version is needed for static library. + */ +#ifdef SHARED +# define COMPAT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@" #version); +# define DEFAULT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@@" #version); +#else +# define COMPAT_VERSION(internal_name, api_name, version) +# define DEFAULT_VERSION(internal_name, api_name, version) \ + extern typeof(internal_name) api_name \ + __attribute__((alias(#internal_name))); +#endif + extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) __attribute__((format(printf, 2, 3))); diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 24fa313524fb..a902838f9fcc 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -261,8 +261,8 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, &config); } -asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2"); -asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4"); +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static int xsk_load_xdp_prog(struct xsk_socket *xsk) { diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 6cbeea7b4bf1..8547ecbdc61f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -195,7 +195,7 @@ static void run_test(int cgroup_fd) if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) - goto close_bpf_object; + goto close_server_fd; pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index a82da555b1b0..f4cd60d6fba2 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -260,13 +260,14 @@ void test_tcp_rtt(void) if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) - goto close_cgroup_fd; + goto close_server_fd; pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); pthread_mutex_unlock(&server_started_mtx); CHECK_FAIL(run_test(cgroup_fd, server_fd)); +close_server_fd: close(server_fd); close_cgroup_fd: close(cgroup_fd); diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index d23d4da66b83..e2d06191bd35 100755 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -63,6 +63,9 @@ fi # Setup tc qdisc add dev lo ingress +echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter +echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter +echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter echo "Testing IPv4..." # Drops all IP/UDP packets coming from port 9 diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index acf7a74f97cd..59ea56945e6c 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -314,15 +314,15 @@ test_gso() command -v nc >/dev/null 2>&1 || \ { echo >&2 "nc is not available: skipping TSO tests"; return; } - # listen on IPv*_DST, capture TCP into $TMPFILE + # listen on port 9000, capture TCP into $TMPFILE if [ "${PROTO}" == "IPv4" ] ; then IP_DST=${IPv4_DST} ip netns exec ${NS3} bash -c \ - "nc -4 -l -s ${IPv4_DST} -p 9000 > ${TMPFILE} &" + "nc -4 -l -p 9000 > ${TMPFILE} &" elif [ "${PROTO}" == "IPv6" ] ; then IP_DST=${IPv6_DST} ip netns exec ${NS3} bash -c \ - "nc -6 -l -s ${IPv6_DST} -p 9000 > ${TMPFILE} &" + "nc -6 -l -p 9000 > ${TMPFILE} &" RET=$? else echo " test_gso: unknown PROTO: ${PROTO}" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 62c591f87dab..c5ec868fa1e5 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -22,6 +22,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test @@ -48,7 +49,7 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ - $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) # On s390, build the testcases KVM-enabled pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 0c17f2ee685e..ff234018219c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1083,6 +1083,9 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); #define VMX_BASIC_MEM_TYPE_WB 6LLU #define VMX_BASIC_INOUT 0x0040000000000000LLU +/* VMX_EPT_VPID_CAP bits */ +#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) + /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 69b17055f63d..6ae5a47fe067 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -569,6 +569,10 @@ struct vmx_pages { void *enlightened_vmcs_hva; uint64_t enlightened_vmcs_gpa; void *enlightened_vmcs; + + void *eptp_hva; + uint64_t eptp_gpa; + void *eptp; }; struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); @@ -576,4 +580,14 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); +void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot); +void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint64_t size, + uint32_t eptp_memslot); +void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t memslot, uint32_t eptp_memslot); +void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t eptp_memslot); + #endif /* SELFTEST_KVM_VMX_H */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 80a338b5403c..41cf45416060 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -705,7 +705,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, * on error (e.g. currently no memory region using memslot as a KVM * memory slot ID). */ -static struct userspace_mem_region * +struct userspace_mem_region * memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index f36262e0f655..ac50c42750cf 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -68,4 +68,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); +struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot); + #endif /* SELFTEST_KVM_UTIL_INTERNAL_H */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c53dbc6bc568..6698cb741e10 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1085,7 +1085,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) for (i = 0; i < nmsrs; i++) state->msrs.entries[i].index = list->indices[i]; r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs); - TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)", + TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)", r, r == nmsrs ? -1 : list->indices[r]); r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 9cef0455b819..fab8f6b0bf52 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -7,11 +7,39 @@ #include "test_util.h" #include "kvm_util.h" +#include "../kvm_util_internal.h" #include "processor.h" #include "vmx.h" +#define PAGE_SHIFT_4K 12 + +#define KVM_EPT_PAGE_TABLE_MIN_PADDR 0x1c0000 + bool enable_evmcs; +struct eptPageTableEntry { + uint64_t readable:1; + uint64_t writable:1; + uint64_t executable:1; + uint64_t memory_type:3; + uint64_t ignore_pat:1; + uint64_t page_size:1; + uint64_t accessed:1; + uint64_t dirty:1; + uint64_t ignored_11_10:2; + uint64_t address:40; + uint64_t ignored_62_52:11; + uint64_t suppress_ve:1; +}; + +struct eptPageTablePointer { + uint64_t memory_type:3; + uint64_t page_walk_length:3; + uint64_t ad_enabled:1; + uint64_t reserved_11_07:5; + uint64_t address:40; + uint64_t reserved_63_52:12; +}; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) { uint16_t evmcs_ver; @@ -174,15 +202,35 @@ bool load_vmcs(struct vmx_pages *vmx) */ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) { + uint32_t sec_exec_ctl = 0; + vmwrite(VIRTUAL_PROCESSOR_ID, 0); vmwrite(POSTED_INTR_NV, 0); vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS)); - if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0)) + + if (vmx->eptp_gpa) { + uint64_t ept_paddr; + struct eptPageTablePointer eptp = { + .memory_type = VMX_BASIC_MEM_TYPE_WB, + .page_walk_length = 3, /* + 1 */ + .ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS), + .address = vmx->eptp_gpa >> PAGE_SHIFT_4K, + }; + + memcpy(&ept_paddr, &eptp, sizeof(ept_paddr)); + vmwrite(EPT_POINTER, ept_paddr); + sec_exec_ctl |= SECONDARY_EXEC_ENABLE_EPT; + } + + if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, sec_exec_ctl)) vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS); - else + else { vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS)); + GUEST_ASSERT(!sec_exec_ctl); + } + vmwrite(EXCEPTION_BITMAP, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */ @@ -327,3 +375,152 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) init_vmcs_host_state(); init_vmcs_guest_state(guest_rip, guest_rsp); } + +void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot) +{ + uint16_t index[4]; + struct eptPageTableEntry *pml4e; + + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " + "unknown or unsupported guest mode, mode: 0x%x", vm->mode); + + TEST_ASSERT((nested_paddr % vm->page_size) == 0, + "Nested physical address not on page boundary,\n" + " nested_paddr: 0x%lx vm->page_size: 0x%x", + nested_paddr, vm->page_size); + TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", + paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + index[0] = (nested_paddr >> 12) & 0x1ffu; + index[1] = (nested_paddr >> 21) & 0x1ffu; + index[2] = (nested_paddr >> 30) & 0x1ffu; + index[3] = (nested_paddr >> 39) & 0x1ffu; + + /* Allocate page directory pointer table if not present. */ + pml4e = vmx->eptp_hva; + if (!pml4e[index[3]].readable) { + pml4e[index[3]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pml4e[index[3]].writable = true; + pml4e[index[3]].readable = true; + pml4e[index[3]].executable = true; + } + + /* Allocate page directory table if not present. */ + struct eptPageTableEntry *pdpe; + pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size); + if (!pdpe[index[2]].readable) { + pdpe[index[2]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pdpe[index[2]].writable = true; + pdpe[index[2]].readable = true; + pdpe[index[2]].executable = true; + } + + /* Allocate page table if not present. */ + struct eptPageTableEntry *pde; + pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size); + if (!pde[index[1]].readable) { + pde[index[1]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pde[index[1]].writable = true; + pde[index[1]].readable = true; + pde[index[1]].executable = true; + } + + /* Fill in page table entry. */ + struct eptPageTableEntry *pte; + pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size); + pte[index[0]].address = paddr >> vm->page_shift; + pte[index[0]].writable = true; + pte[index[0]].readable = true; + pte[index[0]].executable = true; + + /* + * For now mark these as accessed and dirty because the only + * testcase we have needs that. Can be reconsidered later. + */ + pte[index[0]].accessed = true; + pte[index[0]].dirty = true; +} + +/* + * Map a range of EPT guest physical addresses to the VM's physical address + * + * Input Args: + * vm - Virtual Machine + * nested_paddr - Nested guest physical address to map + * paddr - VM Physical Address + * size - The size of the range to map + * eptp_memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within the VM given by vm, creates a nested guest translation for the + * page range starting at nested_paddr to the page range starting at paddr. + */ +void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint64_t size, + uint32_t eptp_memslot) +{ + size_t page_size = vm->page_size; + size_t npages = size / page_size; + + TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow"); + TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + + while (npages--) { + nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot); + nested_paddr += page_size; + paddr += page_size; + } +} + +/* Prepare an identity extended page table that maps all the + * physical pages in VM. + */ +void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t memslot, uint32_t eptp_memslot) +{ + sparsebit_idx_t i, last; + struct userspace_mem_region *region = + memslot2region(vm, memslot); + + i = (region->region.guest_phys_addr >> vm->page_shift) - 1; + last = i + (region->region.memory_size >> vm->page_shift); + for (;;) { + i = sparsebit_next_clear(region->unused_phy_pages, i); + if (i > last) + break; + + nested_map(vmx, vm, + (uint64_t)i << vm->page_shift, + (uint64_t)i << vm->page_shift, + 1 << vm->page_shift, + eptp_memslot); + } +} + +void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t eptp_memslot) +{ + vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); + vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c new file mode 100644 index 000000000000..0bca1cfe2c1e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging test + * + * Copyright (C) 2018, Red Hat, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#define VCPU_ID 1 + +/* The memory slot index to track dirty pages */ +#define TEST_MEM_SLOT_INDEX 1 +#define TEST_MEM_SIZE 3 + +/* L1 guest test virtual memory offset */ +#define GUEST_TEST_MEM 0xc0000000 + +/* L2 guest test virtual memory offset */ +#define NESTED_TEST_MEM1 0xc0001000 +#define NESTED_TEST_MEM2 0xc0002000 + +static void l2_guest_code(void) +{ + *(volatile uint64_t *)NESTED_TEST_MEM1; + *(volatile uint64_t *)NESTED_TEST_MEM1 = 1; + GUEST_SYNC(true); + GUEST_SYNC(false); + + *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + GUEST_SYNC(true); + *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + GUEST_SYNC(true); + GUEST_SYNC(false); + + /* Exit to L1 and never come back. */ + vmcall(); +} + +void l1_guest_code(struct vmx_pages *vmx) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(vmx->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx)); + GUEST_ASSERT(load_vmcs(vmx)); + + prepare_vmcs(vmx, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(false); + GUEST_ASSERT(!vmlaunch()); + GUEST_SYNC(false); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva = 0; + struct vmx_pages *vmx; + unsigned long *bmap; + uint64_t *host_test_mem; + + struct kvm_vm *vm; + struct kvm_run *run; + struct ucall uc; + bool done = false; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + run = vcpu_state(vm, VCPU_ID); + + /* Add an extra memory slot for testing dirty logging */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + GUEST_TEST_MEM, + TEST_MEM_SLOT_INDEX, + TEST_MEM_SIZE, + KVM_MEM_LOG_DIRTY_PAGES); + + /* + * Add an identity map for GVA range [0xc0000000, 0xc0002000). This + * affects both L1 and L2. However... + */ + virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, + TEST_MEM_SIZE * 4096, 0); + + /* + * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to + * 0xc0000000. + * + * Note that prepare_eptp should be called only L1's GPA map is done, + * meaning after the last call to virt_map. + */ + prepare_eptp(vmx, vm, 0); + nested_map_memslot(vmx, vm, 0, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0); + + bmap = bitmap_alloc(TEST_MEM_SIZE); + host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); + + while (!done) { + memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096); + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + /* + * The nested guest wrote at offset 0x1000 in the memslot, but the + * dirty bitmap must be filled in according to L1 GPA, not L2. + */ + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + if (uc.args[1]) { + TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n"); + TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n"); + } else { + TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n"); + } + + TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n"); + TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n"); + break; + case UCALL_DONE: + done = true; + break; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + } +} diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c7cced739c34..8aefd81fbc86 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -21,3 +21,4 @@ ipv6_flowlabel ipv6_flowlabel_mgr so_txtime tcp_fastopen_backup_key +nettest diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index b8265ee9923f..614b31aad168 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -89,12 +89,9 @@ struct testcase testcases_v4[] = { .tfail = true, }, { - /* send a single MSS: will fail with GSO, because the segment - * logic in udp4_ufo_fragment demands a gso skb to be > MTU - */ + /* send a single MSS: will fall back to no GSO */ .tlen = CONST_MSS_V4, .gso_len = CONST_MSS_V4, - .tfail = true, .r_num_mss = 1, }, { @@ -139,10 +136,9 @@ struct testcase testcases_v4[] = { .tfail = true, }, { - /* send a single 1B MSS: will fail, see single MSS above */ + /* send a single 1B MSS: will fall back to no GSO */ .tlen = 1, .gso_len = 1, - .tfail = true, .r_num_mss = 1, }, { @@ -196,12 +192,9 @@ struct testcase testcases_v6[] = { .tfail = true, }, { - /* send a single MSS: will fail with GSO, because the segment - * logic in udp4_ufo_fragment demands a gso skb to be > MTU - */ + /* send a single MSS: will fall back to no GSO */ .tlen = CONST_MSS_V6, .gso_len = CONST_MSS_V6, - .tfail = true, .r_num_mss = 1, }, { @@ -246,10 +239,9 @@ struct testcase testcases_v6[] = { .tfail = true, }, { - /* send a single 1B MSS: will fail, see single MSS above */ + /* send a single 1B MSS: will fall back to no GSO */ .tlen = 1, .gso_len = 1, - .tfail = true, .r_num_mss = 1, }, { diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 464c9b76148f..7550f08822a3 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -lpthread +CFLAGS += -g -I../../../../usr/include/ -pthread TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait diff --git a/usr/include/Makefile b/usr/include/Makefile index c9449aaf438d..57b20f7b6729 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -29,13 +29,11 @@ header-test- += linux/android/binderfs.h header-test-$(CONFIG_CPU_BIG_ENDIAN) += linux/byteorder/big_endian.h header-test-$(CONFIG_CPU_LITTLE_ENDIAN) += linux/byteorder/little_endian.h header-test- += linux/coda.h -header-test- += linux/coda_psdev.h header-test- += linux/elfcore.h header-test- += linux/errqueue.h header-test- += linux/fsmap.h header-test- += linux/hdlc/ioctl.h header-test- += linux/ivtv.h -header-test- += linux/jffs2.h header-test- += linux/kexec.h header-test- += linux/matroxfb.h header-test- += linux/netfilter_ipv4/ipt_LOG.h @@ -55,20 +53,12 @@ header-test- += linux/v4l2-mediabus.h header-test- += linux/v4l2-subdev.h header-test- += linux/videodev2.h header-test- += linux/vm_sockets.h -header-test- += scsi/scsi_bsg_fc.h -header-test- += scsi/scsi_netlink.h -header-test- += scsi/scsi_netlink_fc.h header-test- += sound/asequencer.h header-test- += sound/asoc.h header-test- += sound/asound.h header-test- += sound/compress_offload.h header-test- += sound/emu10k1.h header-test- += sound/sfnt_info.h -header-test- += sound/sof/eq.h -header-test- += sound/sof/fw.h -header-test- += sound/sof/header.h -header-test- += sound/sof/manifest.h -header-test- += sound/sof/trace.h header-test- += xen/evtchn.h header-test- += xen/gntdev.h header-test- += xen/privcmd.h diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h index 55fed77a9f73..4fd4f6db181b 100644 --- a/virt/kvm/arm/vgic/trace.h +++ b/virt/kvm/arm/vgic/trace.h @@ -30,7 +30,7 @@ TRACE_EVENT(vgic_update_irq_pending, #endif /* _TRACE_VGIC_H */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic +#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e6de3159e682..fd68fbe0a75d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -617,8 +617,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) stat_data->kvm = kvm; stat_data->offset = p->offset; + stat_data->mode = p->mode ? p->mode : 0644; kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - debugfs_create_file(p->name, 0644, kvm->debugfs_dentry, + debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry, stat_data, stat_fops_per_vm[p->kind]); } return 0; @@ -3929,7 +3930,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, if (!refcount_inc_not_zero(&stat_data->kvm->users_count)) return -ENOENT; - if (simple_attr_open(inode, file, get, set, fmt)) { + if (simple_attr_open(inode, file, get, + stat_data->mode & S_IWUGO ? set : NULL, + fmt)) { kvm_put_kvm(stat_data->kvm); return -ENOMEM; } @@ -4177,7 +4180,8 @@ static void kvm_init_debug(void) kvm_debugfs_num_entries = 0; for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - debugfs_create_file(p->name, 0644, kvm_debugfs_dir, + int mode = p->mode ? p->mode : 0644; + debugfs_create_file(p->name, mode, kvm_debugfs_dir, (void *)(long)p->offset, stat_fops[p->kind]); } |
