diff options
265 files changed, 3405 insertions, 1810 deletions
diff --git a/.clang-format b/.clang-format index fe1aa1a30d40..86c20ee744de 100644 --- a/.clang-format +++ b/.clang-format @@ -92,6 +92,7 @@ ForEachMacros: - '__rq_for_each_bio' - '__shost_for_each_device' - '__sym_for_each' + - '_for_each_counter' - 'apei_estatus_for_each_section' - 'ata_for_each_dev' - 'ata_for_each_link' @@ -141,11 +142,14 @@ ForEachMacros: - 'damon_for_each_target_safe' - 'damos_for_each_filter' - 'damos_for_each_filter_safe' + - 'damos_for_each_ops_filter' + - 'damos_for_each_ops_filter_safe' - 'damos_for_each_quota_goal' - 'damos_for_each_quota_goal_safe' - 'data__for_each_file' - 'data__for_each_file_new' - 'data__for_each_file_start' + - 'def_for_each_cpu' - 'device_for_each_child_node' - 'device_for_each_child_node_scoped' - 'dma_fence_array_for_each' @@ -176,6 +180,7 @@ ForEachMacros: - 'drm_for_each_privobj' - 'drm_gem_for_each_gpuvm_bo' - 'drm_gem_for_each_gpuvm_bo_safe' + - 'drm_gpusvm_for_each_range' - 'drm_gpuva_for_each_op' - 'drm_gpuva_for_each_op_from_reverse' - 'drm_gpuva_for_each_op_reverse' @@ -216,8 +221,10 @@ ForEachMacros: - 'for_each_active_dev_scope' - 'for_each_active_drhd_unit' - 'for_each_active_iommu' + - 'for_each_active_irq' - 'for_each_active_route' - 'for_each_aggr_pgid' + - 'for_each_alloc_capable_rdt_resource' - 'for_each_and_bit' - 'for_each_andnot_bit' - 'for_each_available_child_of_node' @@ -228,6 +235,7 @@ ForEachMacros: - 'for_each_btf_ext_rec' - 'for_each_btf_ext_sec' - 'for_each_bvec' + - 'for_each_capable_rdt_resource' - 'for_each_card_auxs' - 'for_each_card_auxs_safe' - 'for_each_card_components' @@ -241,6 +249,7 @@ ForEachMacros: - 'for_each_cgroup_storage_type' - 'for_each_child_of_node' - 'for_each_child_of_node_scoped' + - 'for_each_child_of_node_with_prefix' - 'for_each_clear_bit' - 'for_each_clear_bit_from' - 'for_each_clear_bitrange' @@ -296,6 +305,7 @@ ForEachMacros: - 'for_each_group_member_head' - 'for_each_hstate' - 'for_each_hwgpio' + - 'for_each_hwgpio_in_range' - 'for_each_if' - 'for_each_inject_fn' - 'for_each_insn' @@ -304,6 +314,7 @@ ForEachMacros: - 'for_each_intid' - 'for_each_iommu' - 'for_each_ip_tunnel_rcu' + - 'for_each_irq_desc' - 'for_each_irq_nr' - 'for_each_lang' - 'for_each_link_ch_maps' @@ -324,6 +335,8 @@ ForEachMacros: - 'for_each_missing_reg' - 'for_each_mle_subelement' - 'for_each_mod_mem_type' + - 'for_each_mon_capable_rdt_resource' + - 'for_each_mp_bvec' - 'for_each_net' - 'for_each_net_continue_reverse' - 'for_each_net_rcu' @@ -351,6 +364,7 @@ ForEachMacros: - 'for_each_node_by_name' - 'for_each_node_by_type' - 'for_each_node_mask' + - 'for_each_node_numadist' - 'for_each_node_state' - 'for_each_node_with_cpus' - 'for_each_node_with_property' @@ -359,6 +373,8 @@ ForEachMacros: - 'for_each_of_allnodes' - 'for_each_of_allnodes_from' - 'for_each_of_cpu_node' + - 'for_each_of_graph_port' + - 'for_each_of_graph_port_endpoint' - 'for_each_of_pci_range' - 'for_each_old_connector_in_state' - 'for_each_old_crtc_in_state' @@ -372,9 +388,11 @@ ForEachMacros: - 'for_each_oldnew_plane_in_state_reverse' - 'for_each_oldnew_private_obj_in_state' - 'for_each_online_cpu' + - 'for_each_online_cpu_wrap' - 'for_each_online_node' - 'for_each_online_pgdat' - 'for_each_or_bit' + - 'for_each_page_ext' - 'for_each_path' - 'for_each_pci_bridge' - 'for_each_pci_dev' @@ -382,8 +400,10 @@ ForEachMacros: - 'for_each_physmem_range' - 'for_each_populated_zone' - 'for_each_possible_cpu' + - 'for_each_possible_cpu_wrap' - 'for_each_present_blessed_reg' - 'for_each_present_cpu' + - 'for_each_present_section_nr' - 'for_each_prime_number' - 'for_each_prime_number_from' - 'for_each_probe_cache_entry' @@ -396,6 +416,7 @@ ForEachMacros: - 'for_each_prop_dlc_cpus' - 'for_each_prop_dlc_platforms' - 'for_each_property_of_node' + - 'for_each_rdt_resource' - 'for_each_reg' - 'for_each_reg_filtered' - 'for_each_reloc' @@ -434,10 +455,10 @@ ForEachMacros: - 'for_each_subelement_id' - 'for_each_sublist' - 'for_each_subsystem' + - 'for_each_suite' - 'for_each_supported_activate_fn' - 'for_each_supported_inject_fn' - 'for_each_sym' - - 'for_each_test' - 'for_each_thread' - 'for_each_token' - 'for_each_unicast_dest_pgid' @@ -499,8 +520,10 @@ ForEachMacros: - 'idr_for_each_entry_continue' - 'idr_for_each_entry_continue_ul' - 'idr_for_each_entry_ul' + - 'iio_for_each_active_channel' - 'in_dev_for_each_ifa_rcu' - 'in_dev_for_each_ifa_rtnl' + - 'in_dev_for_each_ifa_rtnl_net' - 'inet_bind_bucket_for_each' - 'interval_tree_for_each_span' - 'intlist__for_each_entry' @@ -542,7 +565,6 @@ ForEachMacros: - 'list_for_each_prev' - 'list_for_each_prev_safe' - 'list_for_each_rcu' - - 'list_for_each_reverse' - 'list_for_each_safe' - 'llist_for_each' - 'llist_for_each_entry' @@ -552,6 +574,7 @@ ForEachMacros: - 'map__for_each_symbol' - 'map__for_each_symbol_by_name' - 'mas_for_each' + - 'mas_for_each_rev' - 'mci_for_each_dimm' - 'media_device_for_each_entity' - 'media_device_for_each_intf' @@ -561,10 +584,15 @@ ForEachMacros: - 'media_pipeline_for_each_entity' - 'media_pipeline_for_each_pad' - 'mlx5_lag_for_each_peer_mdev' + - 'mptcp_for_each_subflow' - 'msi_domain_for_each_desc' - 'msi_for_each_desc' - 'mt_for_each' + - 'nanddev_io_for_each_block' - 'nanddev_io_for_each_page' + - 'neigh_for_each_in_bucket' + - 'neigh_for_each_in_bucket_rcu' + - 'neigh_for_each_in_bucket_safe' - 'netdev_for_each_lower_dev' - 'netdev_for_each_lower_private' - 'netdev_for_each_lower_private_rcu' @@ -604,11 +632,11 @@ ForEachMacros: - 'perf_evlist__for_each_entry_safe' - 'perf_evlist__for_each_evsel' - 'perf_evlist__for_each_mmap' + - 'perf_evsel_for_each_per_thread_period_safe' - 'perf_hpp_list__for_each_format' - 'perf_hpp_list__for_each_format_safe' - 'perf_hpp_list__for_each_sort_list' - 'perf_hpp_list__for_each_sort_list_safe' - - 'perf_tool_event__for_each_event' - 'plist_for_each' - 'plist_for_each_continue' - 'plist_for_each_entry' @@ -627,7 +655,6 @@ ForEachMacros: - 'rdma_for_each_block' - 'rdma_for_each_port' - 'rdma_umem_for_each_dma_block' - - 'resort_rb__for_each_entry' - 'resource_list_for_each_entry' - 'resource_list_for_each_entry_safe' - 'rhl_for_each_entry_rcu' @@ -658,6 +685,7 @@ ForEachMacros: - 'shost_for_each_device' - 'sk_for_each' - 'sk_for_each_bound' + - 'sk_for_each_bound_safe' - 'sk_for_each_entry_offset_rcu' - 'sk_for_each_from' - 'sk_for_each_rcu' @@ -680,7 +708,11 @@ ForEachMacros: - 'tb_property_for_each' - 'tcf_act_for_each_action' - 'tcf_exts_for_each_action' + - 'test_suite__for_each_test_case' + - 'tool_pmu__for_each_event' + - 'ttm_bo_lru_for_each_reserved_guarded' - 'ttm_resource_manager_for_each_res' + - 'udp_lrpa_for_each_entry_rcu' - 'udp_portaddr_for_each_entry' - 'udp_portaddr_for_each_entry_rcu' - 'usb_hub_for_each_child' @@ -691,6 +723,7 @@ ForEachMacros: - 'v4l2_m2m_for_each_src_buf_safe' - 'virtio_device_for_each_vq' - 'while_for_each_ftrace_op' + - 'workloads__for_each' - 'xa_for_each' - 'xa_for_each_marked' - 'xa_for_each_range' @@ -2071,6 +2071,10 @@ S: 660 Harvard Ave. #7 S: Santa Clara, CA 95051 S: USA +N: Joonsoo Kim +E: iamjoonsoo.kim@lge.com +D: Slab allocators + N: Kukjin Kim E: kgene@kernel.org D: Samsung S3C, S5P and Exynos ARM architectures diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 3879963f0f01..11545c9e2e93 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -77,7 +77,7 @@ Description: What: /sys/block/<disk>/diskseq Date: February 2021 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: The /sys/block/<disk>/diskseq files reports the disk sequence number, which is a monotonically increasing diff --git a/Documentation/ABI/testing/sysfs-kernel-reboot b/Documentation/ABI/testing/sysfs-kernel-reboot index e117aba46be0..52571fd5ddba 100644 --- a/Documentation/ABI/testing/sysfs-kernel-reboot +++ b/Documentation/ABI/testing/sysfs-kernel-reboot @@ -1,7 +1,7 @@ What: /sys/kernel/reboot Date: November 2020 KernelVersion: 5.11 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: Interface to set the kernel reboot behavior, similarly to what can be done via the reboot= cmdline option. (see Documentation/admin-guide/kernel-parameters.txt) @@ -9,25 +9,25 @@ Description: Interface to set the kernel reboot behavior, similarly to What: /sys/kernel/reboot/mode Date: November 2020 KernelVersion: 5.11 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: Reboot mode. Valid values are: cold warm hard soft gpio What: /sys/kernel/reboot/type Date: November 2020 KernelVersion: 5.11 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: Reboot type. Valid values are: bios acpi kbd triple efi pci What: /sys/kernel/reboot/cpu Date: November 2020 KernelVersion: 5.11 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: CPU number to use to reboot. What: /sys/kernel/reboot/force Date: November 2020 KernelVersion: 5.11 -Contact: Matteo Croce <mcroce@microsoft.com> +Contact: Matteo Croce <teknoraver@meta.com> Description: Don't wait for any other CPUs on reboot and avoid anything that could hang. diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index 53607d962653..f60bf5991755 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -51,7 +51,7 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_KEY_MARCHID`: Contains the value of ``marchid``, as defined by the RISC-V privileged architecture specification. -* :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as +* :c:macro:`RISCV_HWPROBE_KEY_MIMPID`: Contains the value of ``mimpid``, as defined by the RISC-V privileged architecture specification. * :c:macro:`RISCV_HWPROBE_KEY_BASE_BEHAVIOR`: A bitmask containing the base diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 12f429359a82..63344bea8393 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -154,7 +154,7 @@ suspending the device are satisfied) and to queue up a suspend request for the device in that case. If there is no idle callback, or if the callback returns 0, then the PM core will attempt to carry out a runtime suspend of the device, also respecting devices configured for autosuspend. In essence this means a -call to __pm_runtime_autosuspend() (do note that drivers needs to update the +call to pm_runtime_autosuspend() (do note that drivers needs to update the device last busy mark, pm_runtime_mark_last_busy(), to control the delay under this circumstance). To prevent this (for example, if the callback routine has started a delayed suspend), the routine must return a non-zero value. Negative diff --git a/MAINTAINERS b/MAINTAINERS index d980da72ec60..f31aeb6b452e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7027,6 +7027,7 @@ L: rust-for-linux@vger.kernel.org S: Supported W: https://rust-for-linux.com T: git https://github.com/Rust-for-Linux/linux.git alloc-next +F: rust/helpers/dma.c F: rust/kernel/dma.rs F: samples/rust/rust_dma.rs @@ -15522,6 +15523,21 @@ F: mm/numa.c F: mm/numa_emulation.c F: mm/numa_memblks.c +MEMORY MANAGEMENT - PAGE ALLOCATOR +M: Andrew Morton <akpm@linux-foundation.org> +R: Vlastimil Babka <vbabka@suse.cz> +R: Suren Baghdasaryan <surenb@google.com> +R: Michal Hocko <mhocko@suse.com> +R: Brendan Jackman <jackmanb@google.com> +R: Johannes Weiner <hannes@cmpxchg.org> +R: Zi Yan <ziy@nvidia.com> +L: linux-mm@kvack.org +S: Maintained +F: mm/compaction.c +F: mm/page_alloc.c +F: include/linux/gfp.h +F: include/linux/compaction.h + MEMORY MANAGEMENT - SECRETMEM M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15549,10 +15565,12 @@ M: Liam R. Howlett <Liam.Howlett@oracle.com> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Vlastimil Babka <vbabka@suse.cz> R: Jann Horn <jannh@google.com> +R: Pedro Falcato <pfalcato@suse.de> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/trace/events/mmap.h F: mm/mlock.c F: mm/mmap.c F: mm/mprotect.c @@ -15563,6 +15581,36 @@ F: mm/vma.h F: mm/vma_internal.h F: tools/testing/vma/ +MEMORY MAPPING - LOCKING +M: Andrew Morton <akpm@linux-foundation.org> +M: Suren Baghdasaryan <surenb@google.com> +M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Shakeel Butt <shakeel.butt@linux.dev> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/mm/process_addrs.rst +F: include/linux/mmap_lock.h +F: include/trace/events/mmap_lock.h +F: mm/mmap_lock.c + +MEMORY MAPPING - MADVISE (MEMORY ADVICE) +M: Andrew Morton <akpm@linux-foundation.org> +M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +M: David Hildenbrand <david@redhat.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Jann Horn <jannh@google.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/uapi/asm-generic/mman-common.h +F: mm/madvise.c + MEMORY TECHNOLOGY DEVICES (MTD) M: Miquel Raynal <miquel.raynal@bootlin.com> M: Richard Weinberger <richard@nod.at> @@ -22258,9 +22306,7 @@ F: drivers/nvmem/layouts/sl28vpd.c SLAB ALLOCATOR M: Christoph Lameter <cl@linux.com> -M: Pekka Enberg <penberg@kernel.org> M: David Rientjes <rientjes@google.com> -M: Joonsoo Kim <iamjoonsoo.kim@lge.com> M: Andrew Morton <akpm@linux-foundation.org> M: Vlastimil Babka <vbabka@suse.cz> R: Roman Gushchin <roman.gushchin@linux.dev> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -477,7 +477,6 @@ export rust_common_flags := --edition=2021 \ -Wclippy::ignored_unit_patterns \ -Wclippy::mut_mut \ -Wclippy::needless_bitwise_bool \ - -Wclippy::needless_continue \ -Aclippy::needless_lifetimes \ -Wclippy::no_mangle_with_rust_abi \ -Wclippy::undocumented_unsafe_blocks \ @@ -1054,9 +1053,12 @@ NOSTDINC_FLAGS += -nostdinc KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3) #Currently, disable -Wstringop-overflow for GCC 11, globally. -KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow) +KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-disable-warning, stringop-overflow) KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow) +#Currently, disable -Wunterminated-string-initialization as broken +KBUILD_CFLAGS += $(call cc-disable-warning, unterminated-string-initialization) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += -fno-strict-overflow diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 4853e8b04c6f..f9dcaa60033d 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -21,10 +21,10 @@ obj-$(CONFIG_CPU_HAS_LBT) += lbt.o obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o -CFLAGS_module.o += $(call cc-option,-Wno-override-init,) -CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,) -CFLAGS_traps.o += $(call cc-option,-Wno-override-init,) -CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,) +CFLAGS_module.o += $(call cc-disable-warning, override-init) +CFLAGS_syscall.o += $(call cc-disable-warning, override-init) +CFLAGS_traps.o += $(call cc-disable-warning, override-init) +CFLAGS_perf_event.o += $(call cc-disable-warning, override-init) ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index f4c8e35c216a..cb41d9265662 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -21,4 +21,4 @@ kvm-y += intc/eiointc.o kvm-y += intc/pch_pic.o kvm-y += irqfd.o -CFLAGS_exit.o += $(call cc-option,-Wno-override-init,) +CFLAGS_exit.o += $(call cc-disable-warning, override-init) diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 721ec275ce57..231d777d936c 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -115,24 +115,19 @@ \old_c .endm -#define _ALTERNATIVE_CFG(old_c, ...) \ - ALTERNATIVE_CFG old_c - -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c #else /* !__ASSEMBLY__ */ -#define __ALTERNATIVE_CFG(old_c) \ - old_c "\n" +#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n" +#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n" -#define _ALTERNATIVE_CFG(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#endif /* __ASSEMBLY__ */ -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c) -#endif /* __ASSEMBLY__ */ #endif /* CONFIG_RISCV_ALTERNATIVE */ /* diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h index 46677daf708b..cc11c4544cff 100644 --- a/arch/riscv/include/asm/kgdb.h +++ b/arch/riscv/include/asm/kgdb.h @@ -19,16 +19,9 @@ #ifndef __ASSEMBLY__ +void arch_kgdb_breakpoint(void); extern unsigned long kgdb_compiled_break; -static inline void arch_kgdb_breakpoint(void) -{ - asm(".global kgdb_compiled_break\n" - ".option norvc\n" - "kgdb_compiled_break: ebreak\n" - ".option rvc\n"); -} - #endif /* !__ASSEMBLY__ */ #define DBG_REG_ZERO "zero" diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 121fff429dce..eceabf59ae48 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -62,8 +62,11 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { args[0] = regs->orig_a0; - args++; - memcpy(args, ®s->a1, 5 * sizeof(args[0])); + args[1] = regs->a1; + args[2] = regs->a2; + args[3] = regs->a3; + args[4] = regs->a4; + args[5] = regs->a5; } static inline int syscall_get_arch(struct task_struct *task) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 8d186bfced45..f7480c9c6f8d 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif -CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) -CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init) +CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init) ifdef CONFIG_KEXEC_CORE AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index 2e0266ae6bd7..9f3db3503dab 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) regs->epc = pc; } +noinline void arch_kgdb_breakpoint(void) +{ + asm(".global kgdb_compiled_break\n" + "kgdb_compiled_break: ebreak\n"); +} + void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, char *remcom_out_buffer) { diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index e264e59e596e..91d0b355ceef 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -73,16 +73,17 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx) static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts, unsigned int *gots) { - unsigned int type, i; - - for (i = 0; i < num; i++) { - type = ELF_RISCV_R_TYPE(relas[i].r_info); - if (type == R_RISCV_CALL_PLT) { + for (int i = 0; i < num; i++) { + switch (ELF_R_TYPE(relas[i].r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_PLT32: if (!duplicate_rela(relas, i)) (*plts)++; - } else if (type == R_RISCV_GOT_HI20) { + break; + case R_RISCV_GOT_HI20: if (!duplicate_rela(relas, i)) (*gots)++; + break; } } } diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 47d0ebeec93c..7f6147c18033 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me, kfree(bucket_iter); } - kfree(*relocation_hashtable); + kvfree(*relocation_hashtable); } static int add_relocation_to_accumulate(struct module *me, int type, @@ -752,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations, hashtable_size <<= should_double_size; - *relocation_hashtable = kmalloc_array(hashtable_size, - sizeof(**relocation_hashtable), - GFP_KERNEL); + /* Number of relocations may be large, so kvmalloc it */ + *relocation_hashtable = kvmalloc_array(hashtable_size, + sizeof(**relocation_hashtable), + GFP_KERNEL); if (!*relocation_hashtable) return 0; @@ -859,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, } j++; - if (j > sechdrs[relsec].sh_size / sizeof(*rel)) + if (j == num_relocations) j = 0; } while (j_idx != j); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c174544eefc8..f7c9a1caa83e 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -66,6 +66,9 @@ static struct resource bss_res = { .name = "Kernel bss", }; static struct resource elfcorehdr_res = { .name = "ELF Core hdr", }; #endif +static int num_standard_resources; +static struct resource *standard_resources; + static int __init add_resource(struct resource *parent, struct resource *res) { @@ -139,7 +142,7 @@ static void __init init_resources(void) struct resource *res = NULL; struct resource *mem_res = NULL; size_t mem_res_sz = 0; - int num_resources = 0, res_idx = 0; + int num_resources = 0, res_idx = 0, non_resv_res = 0; int ret = 0; /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */ @@ -193,6 +196,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { res = &mem_res[res_idx--]; + non_resv_res++; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -210,6 +214,9 @@ static void __init init_resources(void) goto error; } + num_standard_resources = non_resv_res; + standard_resources = &mem_res[res_idx + 1]; + /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); @@ -221,6 +228,33 @@ static void __init init_resources(void) memblock_free(mem_res, mem_res_sz); } +static int __init reserve_memblock_reserved_regions(void) +{ + u64 i, j; + + for (i = 0; i < num_standard_resources; i++) { + struct resource *mem = &standard_resources[i]; + phys_addr_t r_start, r_end, mem_size = resource_size(mem); + + if (!memblock_is_region_reserved(mem->start, mem_size)) + continue; + + for_each_reserved_mem_range(j, &r_start, &r_end) { + resource_size_t start, end; + + start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start); + end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end); + + if (start > mem->end || end < mem->start) + continue; + + reserve_region_with_split(mem, start, end, "Reserved"); + } + } + + return 0; +} +arch_initcall(reserve_memblock_reserved_regions); static void __init parse_dtb(void) { diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 585d2dcf2dab..b8ba13819d05 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -439,29 +439,36 @@ static int __init check_unaligned_access_all_cpus(void) { int cpu; - if (unaligned_scalar_speed_param == RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN && - !check_unaligned_access_emulated_all_cpus()) { - check_unaligned_access_speed_all_cpus(); - } else { - pr_info("scalar unaligned access speed set to '%s' by command line\n", - speed_str[unaligned_scalar_speed_param]); + if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param); for_each_online_cpu(cpu) per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; + } else if (!check_unaligned_access_emulated_all_cpus()) { + check_unaligned_access_speed_all_cpus(); + } + + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + if (!has_vector() && + unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) { + pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n", + speed_str[unaligned_vector_speed_param]); + } else { + pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param); + } } if (!has_vector()) unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; - if (unaligned_vector_speed_param == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN && - !check_vector_unaligned_access_emulated_all_cpus() && - IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { - kthread_run(vec_check_unaligned_access_speed_all_cpus, - NULL, "vec_check_unaligned_access_speed_all_cpus"); - } else { - pr_info("vector unaligned access speed set to '%s' by command line\n", - speed_str[unaligned_vector_speed_param]); + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { for_each_online_cpu(cpu) per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; + } else if (!check_vector_unaligned_access_emulated_all_cpus() && + IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { + kthread_run(vec_check_unaligned_access_speed_all_cpus, + NULL, "vec_check_unaligned_access_speed_all_cpus"); } /* diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index dbba332e4a12..f676156d9f3d 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -34,11 +34,14 @@ static bool early_is_tdx_guest(void) void arch_accept_memory(phys_addr_t start, phys_addr_t end) { + static bool sevsnp; + /* Platform-specific memory-acceptance call goes here */ if (early_is_tdx_guest()) { if (!tdx_accept_memory(start, end)) panic("TDX: Failed to accept memory\n"); - } else if (sev_snp_enabled()) { + } else if (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) { + sevsnp = true; snp_accept_memory(start, end); } else { error("Cannot accept memory: unknown platform\n"); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index bb55934c1cee..89ba168f4f0f 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -164,10 +164,7 @@ bool sev_snp_enabled(void) static void __page_state_change(unsigned long paddr, enum psc_op op) { - u64 val; - - if (!sev_snp_enabled()) - return; + u64 val, msr; /* * If private -> shared then invalidate the page before requesting the @@ -176,6 +173,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if (op == SNP_PAGE_STATE_SHARED) pvalidate_4k_page(paddr, paddr, false); + /* Save the current GHCB MSR value */ + msr = sev_es_rd_ghcb_msr(); + /* Issue VMGEXIT to change the page state in RMP table. */ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); VMGEXIT(); @@ -185,6 +185,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); + /* Restore the GHCB MSR value */ + sev_es_wr_ghcb_msr(msr); + /* * Now that page state is changed in the RMP table, validate it so that it is * consistent with the RMP entry. @@ -195,11 +198,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) void snp_set_page_private(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); } void snp_set_page_shared(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); } @@ -223,56 +232,10 @@ static bool early_setup_ghcb(void) return true; } -static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc, - phys_addr_t pa, phys_addr_t pa_end) -{ - struct psc_hdr *hdr; - struct psc_entry *e; - unsigned int i; - - hdr = &desc->hdr; - memset(hdr, 0, sizeof(*hdr)); - - e = desc->entries; - - i = 0; - while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) { - hdr->end_entry = i; - - e->gfn = pa >> PAGE_SHIFT; - e->operation = SNP_PAGE_STATE_PRIVATE; - if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) { - e->pagesize = RMP_PG_SIZE_2M; - pa += PMD_SIZE; - } else { - e->pagesize = RMP_PG_SIZE_4K; - pa += PAGE_SIZE; - } - - e++; - i++; - } - - if (vmgexit_psc(boot_ghcb, desc)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pvalidate_pages(desc); - - return pa; -} - void snp_accept_memory(phys_addr_t start, phys_addr_t end) { - struct snp_psc_desc desc = {}; - unsigned int i; - phys_addr_t pa; - - if (!boot_ghcb && !early_setup_ghcb()) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pa = start; - while (pa < end) - pa = __snp_accept_memory(&desc, pa, end); + for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE) + __page_state_change(pa, SNP_PAGE_STATE_PRIVATE); } void sev_es_shutdown_ghcb(void) diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h index fc725a981b09..4e463f33186d 100644 --- a/arch/x86/boot/compressed/sev.h +++ b/arch/x86/boot/compressed/sev.h @@ -12,11 +12,13 @@ bool sev_snp_enabled(void); void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 sev_get_status(void); #else static inline bool sev_snp_enabled(void) { return false; } static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 sev_get_status(void) { return 0; } #endif diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 09d2d66c9f21..00dfe487bd00 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3049,7 +3049,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int bit; int handled = 0; - u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl); inc_irq_stat(apic_perf_irqs); @@ -3093,7 +3092,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) handled++; x86_pmu_handle_guest_pebs(regs, &data); static_call(x86_pmu_drain_pebs)(regs, &data); - status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* * PMI throttle may be triggered, which stops the PEBS event. @@ -3104,6 +3102,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (pebs_enabled != cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); + + /* + * Above PEBS handler (PEBS counters snapshotting) has updated fixed + * counter 3 and perf metrics counts if they are in counter group, + * unnecessary to update again. + */ + if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] && + is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS])) + status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT; } /* @@ -3123,6 +3130,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) static_call(intel_pmu_update_topdown_event)(NULL, NULL); } + status &= hybrid(cpuc->pmu, intel_ctrl); + /* * Checkpointed counters can lead to 'spurious' PMIs because the * rollback caused by the PMI will have cleared the overflow status @@ -7305,8 +7314,17 @@ __init int intel_pmu_init(void) name = "meteorlake_hybrid"; break; + case INTEL_PANTHERLAKE_L: + pr_cont("Pantherlake Hybrid events, "); + name = "pantherlake_hybrid"; + goto lnl_common; + case INTEL_LUNARLAKE_M: case INTEL_ARROWLAKE: + pr_cont("Lunarlake Hybrid events, "); + name = "lunarlake_hybrid"; + + lnl_common: intel_pmu_init_hybrid(hybrid_big_small); x86_pmu.pebs_latency_data = lnl_latency_data; @@ -7328,8 +7346,6 @@ __init int intel_pmu_init(void) intel_pmu_init_skt(&pmu->pmu); intel_pmu_pebs_data_source_lnl(); - pr_cont("Lunarlake Hybrid events, "); - name = "lunarlake_hybrid"; break; case INTEL_ARROWLAKE_H: diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 1f7e1a692a7a..18c3ab579b8b 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1399,8 +1399,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) * + precise_ip < 2 for the non event IP * + For RTM TSX weight we need GPRs for the abort code. */ - gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && - (attr->sample_regs_intr & PEBS_GP_REGS); + gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS)) || + ((sample_type & PERF_SAMPLE_REGS_USER) && + (attr->sample_regs_user & PEBS_GP_REGS)); tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) && ((attr->config & INTEL_ARCH_EVENT_MASK) == @@ -2123,7 +2125,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, regs->flags &= ~PERF_EFLAGS_EXACT; } - if (sample_type & PERF_SAMPLE_REGS_INTR) + if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) adaptive_pebs_save_regs(regs, gprs); } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 60973c209c0e..76d96df1475a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4891,28 +4891,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), /* Free-Running IIO BANDWIDTH IN Counters */ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -5485,37 +5485,6 @@ static struct freerunning_counters icx_iio_freerunning[] = { [ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets }, }; -static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = { - /* Free-Running IIO CLOCKS Counter */ - INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), - /* Free-Running IIO BANDWIDTH IN Counters */ - INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), - { /* end: all zeroes */ }, -}; - static struct intel_uncore_type icx_uncore_iio_free_running = { .name = "iio_free_running", .num_counters = 9, @@ -5523,7 +5492,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = { .num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX, .freerunning = icx_iio_freerunning, .ops = &skx_uncore_iio_freerunning_ops, - .event_descs = icx_uncore_iio_freerunning_events, + .event_descs = snr_uncore_iio_freerunning_events, .format_group = &skx_uncore_iio_freerunning_format_group, }; @@ -6320,69 +6289,13 @@ static struct freerunning_counters spr_iio_freerunning[] = { [SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 }, }; -static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = { - /* Free-Running IIO CLOCKS Counter */ - INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), - /* Free-Running IIO BANDWIDTH IN Counters */ - INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), - /* Free-Running IIO BANDWIDTH OUT Counters */ - INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"), - INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"), - { /* end: all zeroes */ }, -}; - static struct intel_uncore_type spr_uncore_iio_free_running = { .name = "iio_free_running", .num_counters = 17, .num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX, .freerunning = spr_iio_freerunning, .ops = &skx_uncore_iio_freerunning_ops, - .event_descs = spr_uncore_iio_freerunning_events, + .event_descs = snr_uncore_iio_freerunning_events, .format_group = &skx_uncore_iio_freerunning_format_group, }; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 3a97a7eefb51..be10c188614f 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -126,6 +126,8 @@ #define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) /* Redwood Cove */ #define INTEL_GRANITERAPIDS_D IFM(6, 0xAE) +#define INTEL_BARTLETTLAKE IFM(6, 0xD7) /* Raptor Cove */ + /* "Hybrid" Processors (P-Core/E-Core) */ #define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a839ff506f45..2b36379ff675 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -869,6 +869,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c) pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); setup_force_cpu_bug(X86_BUG_DIV0); + + /* + * Turn off the Instructions Retired free counter on machines that are + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (c->x86_model < 0x30) { + msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); + clear_cpu_cap(c, X86_FEATURE_IRPERF); + } } static bool cpu_has_zenbleed_microcode(void) @@ -1052,13 +1062,8 @@ static void init_amd(struct cpuinfo_x86 *c) if (!cpu_feature_enabled(X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); - /* - * Turn on the Instructions Retired free counter on machines not - * susceptible to erratum #1054 "Instructions Retired Performance - * Counter May Be Inaccurate". - */ - if (cpu_has(c, X86_FEATURE_IRPERF) && - (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f)) + /* Enable the Instructions Retired free counter */ + if (cpu_has(c, X86_FEATURE_IRPERF)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b61028cf5c8a..4a10d35e70aa 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -199,6 +199,12 @@ static bool need_sha_check(u32 cur_rev) case 0xa70c0: return cur_rev <= 0xa70C009; break; case 0xaa001: return cur_rev <= 0xaa00116; break; case 0xaa002: return cur_rev <= 0xaa00218; break; + case 0xb0021: return cur_rev <= 0xb002146; break; + case 0xb1010: return cur_rev <= 0xb101046; break; + case 0xb2040: return cur_rev <= 0xb204031; break; + case 0xb4040: return cur_rev <= 0xb404031; break; + case 0xb6000: return cur_rev <= 0xb600031; break; + case 0xb7000: return cur_rev <= 0xb700031; break; default: break; } @@ -214,8 +220,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi struct sha256_state s; int i; - if (x86_family(bsp_cpuid_1_eax) < 0x17 || - x86_family(bsp_cpuid_1_eax) > 0x19) + if (x86_family(bsp_cpuid_1_eax) < 0x17) return true; if (!need_sha_check(cur_rev)) diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 80e262bb627f..cb9852ad6098 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -46,7 +46,8 @@ bool __init pit_timer_init(void) * VMMs otherwise steal CPU time just to pointlessly waggle * the (masked) IRQ. */ - clockevent_i8253_disable(); + scoped_guard(irq) + clockevent_i8253_disable(); return false; } clockevent_i8253_init(true); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 1b7710bd0d05..53282dc7d5ac 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -103,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void) void (*func)(void); /* - * Xen is supported only on CPUs with CPUID, so testing for - * X86_FEATURE_CPUID is a test for early_cpu_init() having been - * run. - * * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty * dependency chain: it is being called via the xen_hypercall static * call when running as a PVH or HVM guest. Hypercalls need to be @@ -118,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void) */ instrumentation_begin(); - if (!boot_cpu_has(X86_FEATURE_CPUID)) - xen_get_vendor(); + xen_get_vendor(); if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) diff --git a/block/bdev.c b/block/bdev.c index 4844d1e27b6f..6a34179192c9 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -1272,8 +1272,7 @@ void sync_bdevs(bool wait) /* * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ -void bdev_statx(struct path *path, struct kstat *stat, - u32 request_mask) +void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask) { struct inode *backing_inode; struct block_device *bdev; diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 608594a154a5..43ef6bd06c85 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -66,16 +66,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, } EXPORT_SYMBOL(bio_integrity_alloc); -static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs, - bool dirty) +static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs) { int i; - for (i = 0; i < nr_vecs; i++) { - if (dirty && !PageCompound(bv[i].bv_page)) - set_page_dirty_lock(bv[i].bv_page); + for (i = 0; i < nr_vecs; i++) unpin_user_page(bv[i].bv_page); - } } static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip) @@ -91,7 +87,7 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip) ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter); WARN_ON_ONCE(ret != bytes); - bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true); + bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs); } /** @@ -111,8 +107,7 @@ void bio_integrity_unmap_user(struct bio *bio) return; } - bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, - bio_data_dir(bio) == READ); + bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt); } /** @@ -198,7 +193,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, } if (write) - bio_integrity_unpin_bvec(bvec, nr_vecs, false); + bio_integrity_unpin_bvec(bvec, nr_vecs); else memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec)); @@ -319,7 +314,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) return 0; release_pages: - bio_integrity_unpin_bvec(bvec, nr_bvecs, false); + bio_integrity_unpin_bvec(bvec, nr_bvecs); free_bvec: if (bvec != stack_vec) kfree(bvec); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index a2882751f0d2..1f9b45b0b9ee 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -909,6 +909,8 @@ out_unregister_ia_ranges: out_debugfs_remove: blk_debugfs_remove(disk); mutex_unlock(&q->sysfs_lock); + if (queue_is_mq(q)) + blk_mq_sysfs_unregister(disk); out_put_queue_kobj: kobject_put(&disk->queue_kobj); return ret; diff --git a/block/blk-throttle.h b/block/blk-throttle.h index 7964cc041e06..f9f8666891ab 100644 --- a/block/blk-throttle.h +++ b/block/blk-throttle.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_THROTTLE_H #define BLK_THROTTLE_H diff --git a/crypto/scompress.c b/crypto/scompress.c index 5762fcc63b51..36934c78d127 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -215,8 +215,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) spage = nth_page(spage, soff / PAGE_SIZE); soff = offset_in_page(soff); - n = slen / PAGE_SIZE; - n += (offset_in_page(slen) + soff - 1) / PAGE_SIZE; + n = (slen - 1) / PAGE_SIZE; + n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE; if (PageHighMem(nth_page(spage, n)) && size_add(soff, slen) > PAGE_SIZE) break; @@ -243,9 +243,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) dpage = nth_page(dpage, doff / PAGE_SIZE); doff = offset_in_page(doff); - n = dlen / PAGE_SIZE; - n += (offset_in_page(dlen) + doff - 1) / PAGE_SIZE; - if (PageHighMem(dpage + n) && + n = (dlen - 1) / PAGE_SIZE; + n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE; + if (PageHighMem(nth_page(dpage, n)) && size_add(doff, dlen) > PAGE_SIZE) break; dst = kmap_local_page(dpage) + doff; diff --git a/crypto/testmgr.c b/crypto/testmgr.c index abd609d4c8ef..82977ea25db3 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -58,9 +58,6 @@ module_param(fuzz_iterations, uint, 0644); MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations"); #endif -/* Multibuffer is unlimited. Set arbitrary limit for testing. */ -#define MAX_MB_MSGS 16 - #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS /* a perfect nop */ @@ -3329,48 +3326,27 @@ static int test_acomp(struct crypto_acomp *tfm, int ctcount, int dtcount) { const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm)); - struct scatterlist *src = NULL, *dst = NULL; - struct acomp_req *reqs[MAX_MB_MSGS] = {}; - char *decomp_out[MAX_MB_MSGS] = {}; - char *output[MAX_MB_MSGS] = {}; - struct crypto_wait wait; - struct acomp_req *req; - int ret = -ENOMEM; unsigned int i; + char *output, *decomp_out; + int ret; + struct scatterlist src, dst; + struct acomp_req *req; + struct crypto_wait wait; - src = kmalloc_array(MAX_MB_MSGS, sizeof(*src), GFP_KERNEL); - if (!src) - goto out; - dst = kmalloc_array(MAX_MB_MSGS, sizeof(*dst), GFP_KERNEL); - if (!dst) - goto out; - - for (i = 0; i < MAX_MB_MSGS; i++) { - reqs[i] = acomp_request_alloc(tfm); - if (!reqs[i]) - goto out; - - acomp_request_set_callback(reqs[i], - CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - if (i) - acomp_request_chain(reqs[i], reqs[0]); - - output[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL); - if (!output[i]) - goto out; + output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL); + if (!output) + return -ENOMEM; - decomp_out[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL); - if (!decomp_out[i]) - goto out; + decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL); + if (!decomp_out) { + kfree(output); + return -ENOMEM; } for (i = 0; i < ctcount; i++) { unsigned int dlen = COMP_BUF_SIZE; int ilen = ctemplate[i].inlen; void *input_vec; - int j; input_vec = kmemdup(ctemplate[i].input, ilen, GFP_KERNEL); if (!input_vec) { @@ -3378,61 +3354,70 @@ static int test_acomp(struct crypto_acomp *tfm, goto out; } + memset(output, 0, dlen); crypto_init_wait(&wait); - sg_init_one(src, input_vec, ilen); + sg_init_one(&src, input_vec, ilen); + sg_init_one(&dst, output, dlen); - for (j = 0; j < MAX_MB_MSGS; j++) { - sg_init_one(dst + j, output[j], dlen); - acomp_request_set_params(reqs[j], src, dst + j, ilen, dlen); + req = acomp_request_alloc(tfm); + if (!req) { + pr_err("alg: acomp: request alloc failed for %s\n", + algo); + kfree(input_vec); + ret = -ENOMEM; + goto out; } - req = reqs[0]; + acomp_request_set_params(req, &src, &dst, ilen, dlen); + acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + ret = crypto_wait_req(crypto_acomp_compress(req), &wait); if (ret) { pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n", i + 1, algo, -ret); kfree(input_vec); + acomp_request_free(req); goto out; } ilen = req->dlen; dlen = COMP_BUF_SIZE; + sg_init_one(&src, output, ilen); + sg_init_one(&dst, decomp_out, dlen); crypto_init_wait(&wait); - for (j = 0; j < MAX_MB_MSGS; j++) { - sg_init_one(src + j, output[j], ilen); - sg_init_one(dst + j, decomp_out[j], dlen); - acomp_request_set_params(reqs[j], src + j, dst + j, ilen, dlen); - } - - crypto_wait_req(crypto_acomp_decompress(req), &wait); - for (j = 0; j < MAX_MB_MSGS; j++) { - ret = reqs[j]->base.err; - if (ret) { - pr_err("alg: acomp: compression failed on test %d (%d) for %s: ret=%d\n", - i + 1, j, algo, -ret); - kfree(input_vec); - goto out; - } + acomp_request_set_params(req, &src, &dst, ilen, dlen); - if (reqs[j]->dlen != ctemplate[i].inlen) { - pr_err("alg: acomp: Compression test %d (%d) failed for %s: output len = %d\n", - i + 1, j, algo, reqs[j]->dlen); - ret = -EINVAL; - kfree(input_vec); - goto out; - } + ret = crypto_wait_req(crypto_acomp_decompress(req), &wait); + if (ret) { + pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n", + i + 1, algo, -ret); + kfree(input_vec); + acomp_request_free(req); + goto out; + } - if (memcmp(input_vec, decomp_out[j], reqs[j]->dlen)) { - pr_err("alg: acomp: Compression test %d (%d) failed for %s\n", - i + 1, j, algo); - hexdump(output[j], reqs[j]->dlen); - ret = -EINVAL; - kfree(input_vec); - goto out; - } + if (req->dlen != ctemplate[i].inlen) { + pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n", + i + 1, algo, req->dlen); + ret = -EINVAL; + kfree(input_vec); + acomp_request_free(req); + goto out; + } + + if (memcmp(input_vec, decomp_out, req->dlen)) { + pr_err("alg: acomp: Compression test %d failed for %s\n", + i + 1, algo); + hexdump(output, req->dlen); + ret = -EINVAL; + kfree(input_vec); + acomp_request_free(req); + goto out; } kfree(input_vec); + acomp_request_free(req); } for (i = 0; i < dtcount; i++) { @@ -3446,9 +3431,10 @@ static int test_acomp(struct crypto_acomp *tfm, goto out; } + memset(output, 0, dlen); crypto_init_wait(&wait); - sg_init_one(src, input_vec, ilen); - sg_init_one(dst, output[0], dlen); + sg_init_one(&src, input_vec, ilen); + sg_init_one(&dst, output, dlen); req = acomp_request_alloc(tfm); if (!req) { @@ -3459,7 +3445,7 @@ static int test_acomp(struct crypto_acomp *tfm, goto out; } - acomp_request_set_params(req, src, dst, ilen, dlen); + acomp_request_set_params(req, &src, &dst, ilen, dlen); acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &wait); @@ -3481,10 +3467,10 @@ static int test_acomp(struct crypto_acomp *tfm, goto out; } - if (memcmp(output[0], dtemplate[i].output, req->dlen)) { + if (memcmp(output, dtemplate[i].output, req->dlen)) { pr_err("alg: acomp: Decompression test %d failed for %s\n", i + 1, algo); - hexdump(output[0], req->dlen); + hexdump(output, req->dlen); ret = -EINVAL; kfree(input_vec); acomp_request_free(req); @@ -3498,13 +3484,8 @@ static int test_acomp(struct crypto_acomp *tfm, ret = 0; out: - acomp_request_free(reqs[0]); - for (i = 0; i < MAX_MB_MSGS; i++) { - kfree(output[i]); - kfree(decomp_out[i]); - } - kfree(dst); - kfree(src); + kfree(decomp_out); + kfree(output); return ret; } diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 4fa73189502e..eff1d3ca075f 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #include <linux/firmware.h> @@ -164,7 +164,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f args->value = vdev->platform; break; case DRM_IVPU_PARAM_CORE_CLOCK_RATE: - args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio); + args->value = ivpu_hw_dpu_max_freq_get(vdev); break; case DRM_IVPU_PARAM_NUM_CONTEXTS: args->value = ivpu_get_context_count(vdev); @@ -421,9 +421,9 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev) { ivpu_hw_irq_disable(vdev); disable_irq(vdev->irq); - cancel_work_sync(&vdev->irq_ipc_work); - cancel_work_sync(&vdev->irq_dct_work); - cancel_work_sync(&vdev->context_abort_work); + flush_work(&vdev->irq_ipc_work); + flush_work(&vdev->irq_dct_work); + flush_work(&vdev->context_abort_work); ivpu_ipc_disable(vdev); ivpu_mmu_disable(vdev); } diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index 7a1bb92d8c81..5e1d709c6a46 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #include <linux/firmware.h> @@ -233,10 +233,20 @@ static int ivpu_fw_parse(struct ivpu_device *vdev) fw->dvfs_mode = 0; fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr); - fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size; - fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size; ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS"); + if (fw_hdr->preemption_buffer_1_max_size) + fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_max_size; + else + fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size; + + if (fw_hdr->preemption_buffer_2_max_size) + fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_max_size; + else + fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size; + ivpu_dbg(vdev, FW_BOOT, "Preemption buffer sizes: primary %u, secondary %u\n", + fw->primary_preempt_buf_size, fw->secondary_preempt_buf_size); + if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address, fw_hdr->ro_section_size, fw_hdr->image_load_address, @@ -566,7 +576,6 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->magic = VPU_BOOT_PARAMS_MAGIC; boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number; - boot_params->frequency = ivpu_hw_pll_freq_get(vdev); /* * This param is a debug firmware feature. It switches default clock diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index 16435f2756d0..d79668fe1609 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #ifndef __IVPU_HW_H__ @@ -82,19 +82,19 @@ static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range) return range->end - range->start; } -static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev) { - return ivpu_hw_btrs_ratio_to_freq(vdev, ratio); + return ivpu_hw_btrs_dpu_max_freq_get(vdev); } -static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev) +static inline u32 ivpu_hw_dpu_freq_get(struct ivpu_device *vdev) { - ivpu_hw_ip_irq_clear(vdev); + return ivpu_hw_btrs_dpu_freq_get(vdev); } -static inline u32 ivpu_hw_pll_freq_get(struct ivpu_device *vdev) +static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev) { - return ivpu_hw_btrs_pll_freq_get(vdev); + ivpu_hw_ip_irq_clear(vdev); } static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c index 56c56012b980..b236c7234daa 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.c +++ b/drivers/accel/ivpu/ivpu_hw_btrs.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ +#include <linux/units.h> + #include "ivpu_drv.h" #include "ivpu_hw.h" #include "ivpu_hw_btrs.h" @@ -28,17 +30,13 @@ #define BTRS_LNL_ALL_IRQ_MASK ((u32)-1) -#define BTRS_MTL_WP_CONFIG_1_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_5_3) -#define BTRS_MTL_WP_CONFIG_1_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_4_3) -#define BTRS_MTL_WP_CONFIG_2_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_5_3) -#define BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3) -#define BTRS_MTL_WP_CONFIG_0_TILE_PLL_OFF WP_CONFIG(0, 0) #define PLL_CDYN_DEFAULT 0x80 #define PLL_EPP_DEFAULT 0x80 #define PLL_CONFIG_DEFAULT 0x0 -#define PLL_SIMULATION_FREQ 10000000 -#define PLL_REF_CLK_FREQ 50000000 +#define PLL_REF_CLK_FREQ 50000000ull +#define PLL_RATIO_TO_FREQ(x) ((x) * PLL_REF_CLK_FREQ) + #define PLL_TIMEOUT_US (1500 * USEC_PER_MSEC) #define IDLE_TIMEOUT_US (5 * USEC_PER_MSEC) #define TIMEOUT_US (150 * USEC_PER_MSEC) @@ -62,6 +60,8 @@ #define DCT_ENABLE 0x1 #define DCT_DISABLE 0x0 +static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio); + int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev) { REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, BTRS_MTL_ALL_IRQ_MASK); @@ -156,7 +156,7 @@ static int info_init_mtl(struct ivpu_device *vdev) hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH; hw->sku = BTRS_MTL_TILE_SKU_BOTH; - hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO; + hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3); return 0; } @@ -334,8 +334,8 @@ int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable) prepare_wp_request(vdev, &wp, enable); - ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n", - PLL_RATIO_TO_FREQ(wp.target), wp.cfg, wp.epp, wp.cdyn); + ivpu_dbg(vdev, PM, "PLL workpoint request: %lu MHz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n", + pll_ratio_to_dpu_freq(vdev, wp.target) / HZ_PER_MHZ, wp.cfg, wp.epp, wp.cdyn); ret = wp_request_send(vdev, &wp); if (ret) { @@ -573,6 +573,47 @@ int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev) return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US); } +static u32 pll_config_get_mtl(struct ivpu_device *vdev) +{ + return REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL); +} + +static u32 pll_config_get_lnl(struct ivpu_device *vdev) +{ + return REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ); +} + +static u32 pll_ratio_to_dpu_freq_mtl(u16 ratio) +{ + return (PLL_RATIO_TO_FREQ(ratio) * 2) / 3; +} + +static u32 pll_ratio_to_dpu_freq_lnl(u16 ratio) +{ + return PLL_RATIO_TO_FREQ(ratio) / 2; +} + +static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio) +{ + if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) + return pll_ratio_to_dpu_freq_mtl(ratio); + else + return pll_ratio_to_dpu_freq_lnl(ratio); +} + +u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev) +{ + return pll_ratio_to_dpu_freq(vdev, vdev->hw->pll.max_ratio); +} + +u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev) +{ + if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) + return pll_ratio_to_dpu_freq_mtl(pll_config_get_mtl(vdev)); + else + return pll_ratio_to_dpu_freq_lnl(pll_config_get_lnl(vdev)); +} + /* Handler for IRQs from Buttress core (irqB) */ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq) { @@ -582,9 +623,12 @@ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq) if (!status) return false; - if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) - ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", - REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL)); + if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) { + u32 pll = pll_config_get_mtl(vdev); + + ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz", + pll, pll_ratio_to_dpu_freq_mtl(pll) / HZ_PER_MHZ); + } if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, status)) { ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0)); @@ -633,8 +677,12 @@ bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq) queue_work(system_wq, &vdev->irq_dct_work); } - if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) - ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ)); + if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) { + u32 pll = pll_config_get_lnl(vdev); + + ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz", + pll, pll_ratio_to_dpu_freq_lnl(pll) / HZ_PER_MHZ); + } if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, status)) { ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n", @@ -717,60 +765,6 @@ void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 acti REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val); } -static u32 pll_ratio_to_freq_mtl(u32 ratio, u32 config) -{ - u32 pll_clock = PLL_REF_CLK_FREQ * ratio; - u32 cpu_clock; - - if ((config & 0xff) == MTL_PLL_RATIO_4_3) - cpu_clock = pll_clock * 2 / 4; - else - cpu_clock = pll_clock * 2 / 5; - - return cpu_clock; -} - -u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) -{ - struct ivpu_hw_info *hw = vdev->hw; - - if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) - return pll_ratio_to_freq_mtl(ratio, hw->config); - else - return PLL_RATIO_TO_FREQ(ratio); -} - -static u32 pll_freq_get_mtl(struct ivpu_device *vdev) -{ - u32 pll_curr_ratio; - - pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL); - pll_curr_ratio &= VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK; - - if (!ivpu_is_silicon(vdev)) - return PLL_SIMULATION_FREQ; - - return pll_ratio_to_freq_mtl(pll_curr_ratio, vdev->hw->config); -} - -static u32 pll_freq_get_lnl(struct ivpu_device *vdev) -{ - u32 pll_curr_ratio; - - pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ); - pll_curr_ratio &= VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK; - - return PLL_RATIO_TO_FREQ(pll_curr_ratio); -} - -u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev) -{ - if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) - return pll_freq_get_mtl(vdev); - else - return pll_freq_get_lnl(vdev); -} - u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev) { if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h index 1fd71b4d4ab0..300f749971d4 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.h +++ b/drivers/accel/ivpu/ivpu_hw_btrs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #ifndef __IVPU_HW_BTRS_H__ @@ -13,7 +13,6 @@ #define PLL_PROFILING_FREQ_DEFAULT 38400000 #define PLL_PROFILING_FREQ_HIGH 400000000 -#define PLL_RATIO_TO_FREQ(x) ((x) * PLL_REF_CLK_FREQ) #define DCT_DEFAULT_ACTIVE_PERCENT 15u #define DCT_PERIOD_US 35300u @@ -32,12 +31,12 @@ int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev); void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev); void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev); void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev); +u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev); +u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev); bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq); bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq); int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable); void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 dct_percent); -u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev); -u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio); u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 004059e4f1e8..863e3cd6ace5 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -470,8 +470,8 @@ static void ivpu_job_destroy(struct ivpu_job *job) struct ivpu_device *vdev = job->vdev; u32 i; - ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d", - job->job_id, job->file_priv->ctx.id, job->engine_idx); + ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d cmdq_id %u engine %d", + job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx); for (i = 0; i < job->bo_count; i++) if (job->bos[i]) @@ -564,8 +564,8 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 dma_fence_signal(job->done_fence); trace_job("done", job); - ivpu_dbg(vdev, JOB, "Job complete: id %3u ctx %2d engine %d status 0x%x\n", - job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status); + ivpu_dbg(vdev, JOB, "Job complete: id %3u ctx %2d cmdq_id %u engine %d status 0x%x\n", + job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx, job_status); ivpu_job_destroy(job); ivpu_stop_job_timeout_detection(vdev); @@ -664,8 +664,8 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id) } trace_job("submit", job); - ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d prio %d addr 0x%llx next %d\n", - job->job_id, file_priv->ctx.id, job->engine_idx, cmdq->priority, + ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d cmdq_id %u engine %d prio %d addr 0x%llx next %d\n", + job->job_id, file_priv->ctx.id, cmdq->id, job->engine_idx, cmdq->priority, job->cmd_buf_vpu_addr, cmdq->jobq->header.tail); mutex_unlock(&file_priv->lock); @@ -777,7 +777,8 @@ static int ivpu_submit(struct drm_file *file, struct ivpu_file_priv *file_priv, goto err_free_handles; } - ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n", file_priv->ctx.id, buffer_count); + ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u cmdq_id %u buf_count %u\n", + file_priv->ctx.id, cmdq_id, buffer_count); job = ivpu_job_create(file_priv, engine, buffer_count); if (!job) { diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c index 97102feaf8dd..268ab7744a8b 100644 --- a/drivers/accel/ivpu/ivpu_sysfs.c +++ b/drivers/accel/ivpu/ivpu_sysfs.c @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2024 Intel Corporation + * Copyright (C) 2024-2025 Intel Corporation */ #include <linux/device.h> #include <linux/err.h> +#include <linux/pm_runtime.h> +#include <linux/units.h> #include "ivpu_drv.h" #include "ivpu_gem.h" @@ -90,10 +92,55 @@ sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf) static DEVICE_ATTR_RO(sched_mode); +/** + * DOC: npu_max_frequency + * + * The npu_max_frequency shows maximum frequency in MHz of the NPU's data + * processing unit + */ +static ssize_t +npu_max_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + u32 freq = ivpu_hw_dpu_max_freq_get(vdev); + + return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ); +} + +static DEVICE_ATTR_RO(npu_max_frequency_mhz); + +/** + * DOC: npu_current_frequency_mhz + * + * The npu_current_frequency_mhz shows current frequency in MHz of the NPU's + * data processing unit + */ +static ssize_t +npu_current_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct ivpu_device *vdev = to_ivpu_device(drm); + u32 freq = 0; + + /* Read frequency only if device is active, otherwise frequency is 0 */ + if (pm_runtime_get_if_active(vdev->drm.dev) > 0) { + freq = ivpu_hw_dpu_freq_get(vdev); + + pm_runtime_put_autosuspend(vdev->drm.dev); + } + + return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ); +} + +static DEVICE_ATTR_RO(npu_current_frequency_mhz); + static struct attribute *ivpu_dev_attrs[] = { &dev_attr_npu_busy_time_us.attr, &dev_attr_npu_memory_utilization.attr, &dev_attr_sched_mode.attr, + &dev_attr_npu_max_frequency_mhz.attr, + &dev_attr_npu_current_frequency_mhz.attr, NULL, }; diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h index 908e68ea1c39..218468bbbcad 100644 --- a/drivers/accel/ivpu/vpu_boot_api.h +++ b/drivers/accel/ivpu/vpu_boot_api.h @@ -26,7 +26,7 @@ * Minor version changes when API backward compatibility is preserved. * Resets to 0 if Major version is incremented. */ -#define VPU_BOOT_API_VER_MINOR 26 +#define VPU_BOOT_API_VER_MINOR 28 /* * API header changed (field names, documentation, formatting) but API itself has not been changed @@ -76,8 +76,15 @@ struct vpu_firmware_header { * submission queue size and device capabilities. */ u32 preemption_buffer_2_size; + /* + * Maximum preemption buffer size that the FW can use: no need for the host + * driver to allocate more space than that specified by these fields. + * A value of 0 means no declared limit. + */ + u32 preemption_buffer_1_max_size; + u32 preemption_buffer_2_max_size; /* Space reserved for future preemption-related fields. */ - u32 preemption_reserved[6]; + u32 preemption_reserved[4]; /* FW image read only section start address, 4KB aligned */ u64 ro_section_start_address; /* FW image read only section size, 4KB aligned */ @@ -134,7 +141,7 @@ enum vpu_trace_destination { /* * Processor bit shifts (for loggable HW components). */ -#define VPU_TRACE_PROC_BIT_ARM 0 +#define VPU_TRACE_PROC_BIT_RESERVED 0 #define VPU_TRACE_PROC_BIT_LRT 1 #define VPU_TRACE_PROC_BIT_LNN 2 #define VPU_TRACE_PROC_BIT_SHV_0 3 diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h index 7215c144158c..4b6b2b3d2583 100644 --- a/drivers/accel/ivpu/vpu_jsm_api.h +++ b/drivers/accel/ivpu/vpu_jsm_api.h @@ -22,7 +22,7 @@ /* * Minor version changes when API backward compatibility is preserved. */ -#define VPU_JSM_API_VER_MINOR 25 +#define VPU_JSM_API_VER_MINOR 29 /* * API header changed (field names, documentation, formatting) but API itself has not been changed @@ -53,8 +53,7 @@ * Engine indexes. */ #define VPU_ENGINE_COMPUTE 0 -#define VPU_ENGINE_COPY 1 -#define VPU_ENGINE_NB 2 +#define VPU_ENGINE_NB 1 /* * VPU status values. @@ -126,11 +125,13 @@ enum { * When set, indicates that job queue uses native fences (as inline commands * in job queue). Such queues may also use legacy fences (as commands in batch buffers). * When cleared, indicates the job queue only uses legacy fences. - * NOTE: For queues using native fences, VPU expects that all jobs in the queue - * are immediately followed by an inline command object. This object is expected - * to be a fence signal command in most cases, but can also be a NOP in case the host - * does not need per-job fence signalling. Other inline commands objects can be - * inserted between "job and inline command" pairs. + * NOTES: + * 1. For queues using native fences, VPU expects that all jobs in the queue + * are immediately followed by an inline command object. This object is expected + * to be a fence signal command in most cases, but can also be a NOP in case the host + * does not need per-job fence signalling. Other inline commands objects can be + * inserted between "job and inline command" pairs. + * 2. Native fence queues are only supported on VPU 40xx onwards. */ VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U), @@ -275,6 +276,8 @@ struct vpu_inline_cmd { u64 value; /* User VA of the log buffer in which to add log entry on completion. */ u64 log_buffer_va; + /* NPU private data. */ + u64 npu_private_data; } fence; /* Other commands do not have a payload. */ /* Payload definition for future inline commands can be inserted here. */ @@ -791,12 +794,22 @@ struct vpu_jsm_metric_streamer_update { /** Metric group mask that identifies metric streamer instance. */ u64 metric_group_mask; /** - * Address and size of the buffer where the VPU will write metric data. If - * the buffer address is 0 or same as the currently used buffer the VPU will - * continue writing metric data to the current buffer. In this case the - * buffer size is ignored and the size of the current buffer is unchanged. - * If the address is non-zero and differs from the current buffer address the - * VPU will immediately switch data collection to the new buffer. + * Address and size of the buffer where the VPU will write metric data. + * This member dictates how the update operation should perform: + * 1. client needs information about the number of collected samples and the + * amount of data written to the current buffer + * 2. client wants to switch to a new buffer + * + * Case 1. is identified by the buffer address being 0 or the same as the + * currently used buffer address. In this case the buffer size is ignored and + * the size of the current buffer is unchanged. The VPU will return an update + * in the vpu_jsm_metric_streamer_done structure. The internal writing position + * into the buffer is not changed. + * + * Case 2. is identified by the address being non-zero and differs from the + * current buffer address. The VPU will immediately switch data collection to + * the new buffer. Then the VPU will return an update in the + * vpu_jsm_metric_streamer_done structure. */ u64 buffer_addr; u64 buffer_size; @@ -934,6 +947,7 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup { /* * Default quantum in 100ns units for scheduling across processes * within a priority band + * Minimum value supported by NPU is 1ms (10000 in 100ns units). */ u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS]; /* @@ -946,8 +960,10 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup { * in situations when it's starved by the focus band. */ u32 normal_band_percentage; - /* Reserved */ - u32 reserved_0; + /* + * TDR timeout value in milliseconds. Default value of 0 meaning no timeout. + */ + u32 tdr_timeout; }; /* @@ -1024,7 +1040,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties { s32 in_process_priority; /* Zero padding / Reserved */ u32 reserved_1; - /* Context quantum relative to other contexts of same priority in the same process */ + /* + * Context quantum relative to other contexts of same priority in the same process + * Minimum value supported by NPU is 1ms (10000 in 100ns units). + */ u64 context_quantum; /* Grace period when preempting context of the same priority within the same process */ u64 grace_period_same_priority; diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index 6f4fe47c955b..6481c48c22bb 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state); * expected_return_btypes - Allowed type(s) for the return value */ struct acpi_name_info { - char name[ACPI_NAMESEG_SIZE]; + char name[ACPI_NAMESEG_SIZE] __nonstring; u16 argument_list; u8 expected_btypes; }; @@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node * converted_object); struct acpi_simple_repair_info { - char name[ACPI_NAMESEG_SIZE]; + char name[ACPI_NAMESEG_SIZE] __nonstring; u32 unexpected_btypes; u32 package_index; acpi_object_converter object_converter; diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 1bb7b71f07f1..330b5e4711da 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info, return_object_ptr); typedef struct acpi_repair_info { - char name[ACPI_NAMESEG_SIZE]; + char name[ACPI_NAMESEG_SIZE] __nonstring; acpi_repair_function repair_function; } acpi_repair_info; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 2551ebf88dda..e48b24be45ee 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -388,12 +388,6 @@ config BLK_DEV_UBLK definition isn't finalized yet, and might change according to future requirement, so mark is as experimental now. - Say Y if you want to get better performance because task_work_add() - can be used in IO path for replacing io_uring cmd, which will become - shared between IO tasks and ubq daemon, meantime task_work_add() can - can handle batch more effectively, but task_work_add() isn't exported - for module, so ublk has to be built to kernel. - config BLKDEV_UBLK_LEGACY_OPCODES bool "Support legacy command opcode" depends on BLK_DEV_UBLK diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 674527d770dc..46cba261075f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -211,72 +211,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } -static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) -{ - struct iov_iter i; - ssize_t bw; - - iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len); - - bw = vfs_iter_write(file, &i, ppos, 0); - - if (likely(bw == bvec->bv_len)) - return 0; - - printk_ratelimited(KERN_ERR - "loop: Write error at byte offset %llu, length %i.\n", - (unsigned long long)*ppos, bvec->bv_len); - if (bw >= 0) - bw = -EIO; - return bw; -} - -static int lo_write_simple(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec; - struct req_iterator iter; - int ret = 0; - - rq_for_each_segment(bvec, rq, iter) { - ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos); - if (ret < 0) - break; - cond_resched(); - } - - return ret; -} - -static int lo_read_simple(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec; - struct req_iterator iter; - struct iov_iter i; - ssize_t len; - - rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len); - len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); - if (len < 0) - return len; - - flush_dcache_page(bvec.bv_page); - - if (len != bvec.bv_len) { - struct bio *bio; - - __rq_for_each_bio(bio, rq) - zero_fill_bio(bio); - break; - } - cond_resched(); - } - - return 0; -} - static void loop_clear_limits(struct loop_device *lo, int mode) { struct queue_limits lim = queue_limits_start_update(lo->lo_queue); @@ -342,7 +276,7 @@ static void lo_complete_rq(struct request *rq) struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; - if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || + if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); @@ -358,14 +292,13 @@ static void lo_complete_rq(struct request *rq) cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { - if (cmd->use_aio) { - struct bio *bio = rq->bio; + struct bio *bio = rq->bio; - while (bio) { - zero_fill_bio(bio); - bio = bio->bi_next; - } + while (bio) { + zero_fill_bio(bio); + bio = bio->bi_next; } + ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); @@ -445,9 +378,14 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; - cmd->iocb.ki_complete = lo_rw_aio_complete; - cmd->iocb.ki_flags = IOCB_DIRECT; - cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + cmd->iocb.ki_ioprio = req_get_ioprio(rq); + if (cmd->use_aio) { + cmd->iocb.ki_complete = lo_rw_aio_complete; + cmd->iocb.ki_flags = IOCB_DIRECT; + } else { + cmd->iocb.ki_complete = NULL; + cmd->iocb.ki_flags = 0; + } if (rw == ITER_SOURCE) ret = file->f_op->write_iter(&cmd->iocb, &iter); @@ -458,7 +396,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, if (ret != -EIOCBQUEUED) lo_rw_aio_complete(&cmd->iocb, ret); - return 0; + return -EIOCBQUEUED; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) @@ -466,15 +404,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; - /* - * lo_write_simple and lo_read_simple should have been covered - * by io submit style function like lo_rw_aio(), one blocker - * is that lo_read_simple() need to call flush_dcache_page after - * the page is written from kernel, and it isn't easy to handle - * this in io submit style function which submits all segments - * of the req at one time. And direct read IO doesn't need to - * run flush_dcache_page(). - */ switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); @@ -490,15 +419,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: - if (cmd->use_aio) - return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); - else - return lo_write_simple(lo, rq, pos); + return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); case REQ_OP_READ: - if (cmd->use_aio) - return lo_rw_aio(lo, cmd, pos, ITER_DEST); - else - return lo_read_simple(lo, rq, pos); + return lo_rw_aio(lo, cmd, pos, ITER_DEST); default: WARN_ON_ONCE(1); return -EIO; @@ -662,19 +585,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, * dependency. */ fput(old_file); + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); if (partscan) loop_reread_partitions(lo); error = 0; done: - /* enable and uncork uevent now that we are done */ - dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); goto done; } @@ -1129,8 +1053,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); - /* enable and uncork uevent now that we are done */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); loop_global_unlock(lo, is_loop); if (partscan) @@ -1921,7 +1845,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd) struct loop_device *lo = rq->q->queuedata; int ret = 0; struct mem_cgroup *old_memcg = NULL; - const bool use_aio = cmd->use_aio; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; @@ -1951,7 +1874,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } failed: /* complete non-aio request */ - if (!use_aio || ret) { + if (ret != -EIOCBQUEUED) { if (ret == -EOPNOTSUPP) cmd->ret = ret; else diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index cdb1543fa4a9..2de7b2bd409d 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -123,15 +123,6 @@ struct ublk_uring_cmd_pdu { #define UBLK_IO_FLAG_OWNED_BY_SRV 0x02 /* - * IO command is aborted, so this flag is set in case of - * !UBLK_IO_FLAG_ACTIVE. - * - * After this flag is observed, any pending or new incoming request - * associated with this io command will be failed immediately - */ -#define UBLK_IO_FLAG_ABORTED 0x04 - -/* * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires * get data buffer address from ublksrv. * @@ -199,8 +190,6 @@ struct ublk_device { struct completion completion; unsigned int nr_queues_ready; unsigned int nr_privileged_daemon; - - struct work_struct nosrv_work; }; /* header of ublk_params */ @@ -209,8 +198,8 @@ struct ublk_params_header { __u32 types; }; -static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq); - +static void ublk_stop_dev_unlocked(struct ublk_device *ub); +static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq); static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, struct ublk_queue *ubq, int tag, size_t offset); static inline unsigned int ublk_req_build_flags(struct request *req); @@ -1074,7 +1063,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq) { - return ubq->ubq_daemon->flags & PF_EXITING; + return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING; } /* todo: handle partial completion */ @@ -1085,12 +1074,6 @@ static inline void __ublk_complete_rq(struct request *req) unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; - /* called from ublk_abort_queue() code path */ - if (io->flags & UBLK_IO_FLAG_ABORTED) { - res = BLK_STS_IOERR; - goto exit; - } - /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) io->res = -EIO; @@ -1140,47 +1123,6 @@ static void ublk_complete_rq(struct kref *ref) __ublk_complete_rq(req); } -static void ublk_do_fail_rq(struct request *req) -{ - struct ublk_queue *ubq = req->mq_hctx->driver_data; - - if (ublk_nosrv_should_reissue_outstanding(ubq->dev)) - blk_mq_requeue_request(req, false); - else - __ublk_complete_rq(req); -} - -static void ublk_fail_rq_fn(struct kref *ref) -{ - struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data, - ref); - struct request *req = blk_mq_rq_from_pdu(data); - - ublk_do_fail_rq(req); -} - -/* - * Since ublk_rq_task_work_cb always fails requests immediately during - * exiting, __ublk_fail_req() is only called from abort context during - * exiting. So lock is unnecessary. - * - * Also aborting may not be started yet, keep in mind that one failed - * request may be issued by block layer again. - */ -static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, - struct request *req) -{ - WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); - - if (ublk_need_req_ref(ubq)) { - struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - - kref_put(&data->ref, ublk_fail_rq_fn); - } else { - ublk_do_fail_rq(req); - } -} - static void ubq_complete_io_cmd(struct ublk_io *io, int res, unsigned issue_flags) { @@ -1336,8 +1278,6 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l) static enum blk_eh_timer_return ublk_timeout(struct request *rq) { struct ublk_queue *ubq = rq->mq_hctx->driver_data; - unsigned int nr_inflight = 0; - int i; if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) { if (!ubq->timeout) { @@ -1348,26 +1288,6 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq) return BLK_EH_DONE; } - if (!ubq_daemon_is_dying(ubq)) - return BLK_EH_RESET_TIMER; - - for (i = 0; i < ubq->q_depth; i++) { - struct ublk_io *io = &ubq->ios[i]; - - if (!(io->flags & UBLK_IO_FLAG_ACTIVE)) - nr_inflight++; - } - - /* cancelable uring_cmd can't help us if all commands are in-flight */ - if (nr_inflight == ubq->q_depth) { - struct ublk_device *ub = ubq->dev; - - if (ublk_abort_requests(ub, ubq)) { - schedule_work(&ub->nosrv_work); - } - return BLK_EH_DONE; - } - return BLK_EH_RESET_TIMER; } @@ -1470,6 +1390,37 @@ static const struct blk_mq_ops ublk_mq_ops = { .timeout = ublk_timeout, }; +static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) +{ + int i; + + /* All old ioucmds have to be completed */ + ubq->nr_io_ready = 0; + + /* + * old daemon is PF_EXITING, put it now + * + * It could be NULL in case of closing one quisced device. + */ + if (ubq->ubq_daemon) + put_task_struct(ubq->ubq_daemon); + /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ + ubq->ubq_daemon = NULL; + ubq->timeout = false; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + /* + * UBLK_IO_FLAG_CANCELED is kept for avoiding to touch + * io->cmd + */ + io->flags &= UBLK_IO_FLAG_CANCELED; + io->cmd = NULL; + io->addr = 0; + } +} + static int ublk_ch_open(struct inode *inode, struct file *filp) { struct ublk_device *ub = container_of(inode->i_cdev, @@ -1481,10 +1432,119 @@ static int ublk_ch_open(struct inode *inode, struct file *filp) return 0; } +static void ublk_reset_ch_dev(struct ublk_device *ub) +{ + int i; + + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_queue_reinit(ub, ublk_get_queue(ub, i)); + + /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ + ub->mm = NULL; + ub->nr_queues_ready = 0; + ub->nr_privileged_daemon = 0; +} + +static struct gendisk *ublk_get_disk(struct ublk_device *ub) +{ + struct gendisk *disk; + + spin_lock(&ub->lock); + disk = ub->ub_disk; + if (disk) + get_device(disk_to_dev(disk)); + spin_unlock(&ub->lock); + + return disk; +} + +static void ublk_put_disk(struct gendisk *disk) +{ + if (disk) + put_device(disk_to_dev(disk)); +} + static int ublk_ch_release(struct inode *inode, struct file *filp) { struct ublk_device *ub = filp->private_data; + struct gendisk *disk; + int i; + + /* + * disk isn't attached yet, either device isn't live, or it has + * been removed already, so we needn't to do anything + */ + disk = ublk_get_disk(ub); + if (!disk) + goto out; + + /* + * All uring_cmd are done now, so abort any request outstanding to + * the ublk server + * + * This can be done in lockless way because ublk server has been + * gone + * + * More importantly, we have to provide forward progress guarantee + * without holding ub->mutex, otherwise control task grabbing + * ub->mutex triggers deadlock + * + * All requests may be inflight, so ->canceling may not be set, set + * it now. + */ + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + ubq->canceling = true; + ublk_abort_queue(ub, ubq); + } + blk_mq_kick_requeue_list(disk->queue); + + /* + * All infligh requests have been completed or requeued and any new + * request will be failed or requeued via `->canceling` now, so it is + * fine to grab ub->mutex now. + */ + mutex_lock(&ub->mutex); + + /* double check after grabbing lock */ + if (!ub->ub_disk) + goto unlock; + + /* + * Transition the device to the nosrv state. What exactly this + * means depends on the recovery flags + */ + blk_mq_quiesce_queue(disk->queue); + if (ublk_nosrv_should_stop_dev(ub)) { + /* + * Allow any pending/future I/O to pass through quickly + * with an error. This is needed because del_gendisk + * waits for all pending I/O to complete + */ + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_get_queue(ub, i)->force_abort = true; + blk_mq_unquiesce_queue(disk->queue); + + ublk_stop_dev_unlocked(ub); + } else { + if (ublk_nosrv_dev_should_queue_io(ub)) { + /* ->canceling is set and all requests are aborted */ + ub->dev_info.state = UBLK_S_DEV_QUIESCED; + } else { + ub->dev_info.state = UBLK_S_DEV_FAIL_IO; + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_get_queue(ub, i)->fail_io = true; + } + blk_mq_unquiesce_queue(disk->queue); + } +unlock: + mutex_unlock(&ub->mutex); + ublk_put_disk(disk); + + /* all uring_cmd has been done now, reset device & ubq */ + ublk_reset_ch_dev(ub); +out: clear_bit(UB_STATE_OPEN, &ub->state); return 0; } @@ -1551,10 +1611,26 @@ static void ublk_commit_completion(struct ublk_device *ub, ublk_put_req_ref(ubq, req); } +static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) +{ + WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); + + if (ublk_nosrv_should_reissue_outstanding(ubq->dev)) + blk_mq_requeue_request(req, false); + else { + io->res = -EIO; + __ublk_complete_rq(req); + } +} + /* - * Called from ubq_daemon context via cancel fn, meantime quiesce ublk - * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon - * context, so everything is serialized. + * Called from ublk char device release handler, when any uring_cmd is + * done, meantime request queue is "quiesced" since all inflight requests + * can't be completed because ublk server is dead. + * + * So no one can hold our request IO reference any more, simply ignore the + * reference, and complete the request immediately */ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) { @@ -1571,46 +1647,29 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) * will do it */ rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i); - if (rq && blk_mq_request_started(rq)) { - io->flags |= UBLK_IO_FLAG_ABORTED; + if (rq && blk_mq_request_started(rq)) __ublk_fail_req(ubq, io, rq); - } } } } /* Must be called when queue is frozen */ -static bool ublk_mark_queue_canceling(struct ublk_queue *ubq) +static void ublk_mark_queue_canceling(struct ublk_queue *ubq) { - bool canceled; - spin_lock(&ubq->cancel_lock); - canceled = ubq->canceling; - if (!canceled) + if (!ubq->canceling) ubq->canceling = true; spin_unlock(&ubq->cancel_lock); - - return canceled; } -static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq) +static void ublk_start_cancel(struct ublk_queue *ubq) { - bool was_canceled = ubq->canceling; - struct gendisk *disk; - - if (was_canceled) - return false; - - spin_lock(&ub->lock); - disk = ub->ub_disk; - if (disk) - get_device(disk_to_dev(disk)); - spin_unlock(&ub->lock); + struct ublk_device *ub = ubq->dev; + struct gendisk *disk = ublk_get_disk(ub); /* Our disk has been dead */ if (!disk) - return false; - + return; /* * Now we are serialized with ublk_queue_rq() * @@ -1619,15 +1678,9 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq) * touch completed uring_cmd */ blk_mq_quiesce_queue(disk->queue); - was_canceled = ublk_mark_queue_canceling(ubq); - if (!was_canceled) { - /* abort queue is for making forward progress */ - ublk_abort_queue(ub, ubq); - } + ublk_mark_queue_canceling(ubq); blk_mq_unquiesce_queue(disk->queue); - put_device(disk_to_dev(disk)); - - return !was_canceled; + ublk_put_disk(disk); } static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io, @@ -1651,6 +1704,17 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io, /* * The ublk char device won't be closed when calling cancel fn, so both * ublk device and queue are guaranteed to be live + * + * Two-stage cancel: + * + * - make every active uring_cmd done in ->cancel_fn() + * + * - aborting inflight ublk IO requests in ublk char device release handler, + * which depends on 1st stage because device can only be closed iff all + * uring_cmd are done + * + * Do _not_ try to acquire ub->mutex before all inflight requests are + * aborted, otherwise deadlock may be caused. */ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, unsigned int issue_flags) @@ -1658,8 +1722,6 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; struct task_struct *task; - struct ublk_device *ub; - bool need_schedule; struct ublk_io *io; if (WARN_ON_ONCE(!ubq)) @@ -1672,16 +1734,12 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, if (WARN_ON_ONCE(task && task != ubq->ubq_daemon)) return; - ub = ubq->dev; - need_schedule = ublk_abort_requests(ub, ubq); + if (!ubq->canceling) + ublk_start_cancel(ubq); io = &ubq->ios[pdu->tag]; WARN_ON_ONCE(io->cmd != cmd); ublk_cancel_cmd(ubq, io, issue_flags); - - if (need_schedule) { - schedule_work(&ub->nosrv_work); - } } static inline bool ublk_queue_ready(struct ublk_queue *ubq) @@ -1732,33 +1790,20 @@ static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub) } } -static void __ublk_quiesce_dev(struct ublk_device *ub) -{ - pr_devel("%s: quiesce ub: dev_id %d state %s\n", - __func__, ub->dev_info.dev_id, - ub->dev_info.state == UBLK_S_DEV_LIVE ? - "LIVE" : "QUIESCED"); - blk_mq_quiesce_queue(ub->ub_disk->queue); - ublk_wait_tagset_rqs_idle(ub); - ub->dev_info.state = UBLK_S_DEV_QUIESCED; -} - -static void ublk_unquiesce_dev(struct ublk_device *ub) +static void ublk_force_abort_dev(struct ublk_device *ub) { int i; - pr_devel("%s: unquiesce ub: dev_id %d state %s\n", + pr_devel("%s: force abort ub: dev_id %d state %s\n", __func__, ub->dev_info.dev_id, ub->dev_info.state == UBLK_S_DEV_LIVE ? "LIVE" : "QUIESCED"); - /* quiesce_work has run. We let requeued rqs be aborted - * before running fallback_wq. "force_abort" must be seen - * after request queue is unqiuesced. Then del_gendisk() - * can move on. - */ + blk_mq_quiesce_queue(ub->ub_disk->queue); + if (ub->dev_info.state == UBLK_S_DEV_LIVE) + ublk_wait_tagset_rqs_idle(ub); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) ublk_get_queue(ub, i)->force_abort = true; - blk_mq_unquiesce_queue(ub->ub_disk->queue); /* We may have requeued some rqs in ublk_quiesce_queue() */ blk_mq_kick_requeue_list(ub->ub_disk->queue); @@ -1779,61 +1824,51 @@ static struct gendisk *ublk_detach_disk(struct ublk_device *ub) return disk; } -static void ublk_stop_dev(struct ublk_device *ub) +static void ublk_stop_dev_unlocked(struct ublk_device *ub) + __must_hold(&ub->mutex) { struct gendisk *disk; - mutex_lock(&ub->mutex); if (ub->dev_info.state == UBLK_S_DEV_DEAD) - goto unlock; - if (ublk_nosrv_dev_should_queue_io(ub)) { - if (ub->dev_info.state == UBLK_S_DEV_LIVE) - __ublk_quiesce_dev(ub); - ublk_unquiesce_dev(ub); - } + return; + + if (ublk_nosrv_dev_should_queue_io(ub)) + ublk_force_abort_dev(ub); del_gendisk(ub->ub_disk); disk = ublk_detach_disk(ub); put_disk(disk); - unlock: +} + +static void ublk_stop_dev(struct ublk_device *ub) +{ + mutex_lock(&ub->mutex); + ublk_stop_dev_unlocked(ub); mutex_unlock(&ub->mutex); ublk_cancel_dev(ub); } -static void ublk_nosrv_work(struct work_struct *work) +/* reset ublk io_uring queue & io flags */ +static void ublk_reset_io_flags(struct ublk_device *ub) { - struct ublk_device *ub = - container_of(work, struct ublk_device, nosrv_work); - int i; + int i, j; - if (ublk_nosrv_should_stop_dev(ub)) { - ublk_stop_dev(ub); - return; - } + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); - mutex_lock(&ub->mutex); - if (ub->dev_info.state != UBLK_S_DEV_LIVE) - goto unlock; - - if (ublk_nosrv_dev_should_queue_io(ub)) { - __ublk_quiesce_dev(ub); - } else { - blk_mq_quiesce_queue(ub->ub_disk->queue); - ub->dev_info.state = UBLK_S_DEV_FAIL_IO; - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { - ublk_get_queue(ub, i)->fail_io = true; - } - blk_mq_unquiesce_queue(ub->ub_disk->queue); + /* UBLK_IO_FLAG_CANCELED can be cleared now */ + spin_lock(&ubq->cancel_lock); + for (j = 0; j < ubq->q_depth; j++) + ubq->ios[j].flags &= ~UBLK_IO_FLAG_CANCELED; + spin_unlock(&ubq->cancel_lock); + ubq->canceling = false; + ubq->fail_io = false; } - - unlock: - mutex_unlock(&ub->mutex); - ublk_cancel_dev(ub); } /* device can only be started after all IOs are ready */ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) + __must_hold(&ub->mutex) { - mutex_lock(&ub->mutex); ubq->nr_io_ready++; if (ublk_queue_ready(ubq)) { ubq->ubq_daemon = current; @@ -1843,9 +1878,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) if (capable(CAP_SYS_ADMIN)) ub->nr_privileged_daemon++; } - if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) + + if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) { + /* now we are ready for handling ublk io request */ + ublk_reset_io_flags(ub); complete_all(&ub->completion); - mutex_unlock(&ub->mutex); + } } static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, @@ -1929,6 +1967,52 @@ static int ublk_unregister_io_buf(struct io_uring_cmd *cmd, return io_buffer_unregister_bvec(cmd, index, issue_flags); } +static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq, + struct ublk_io *io, __u64 buf_addr) +{ + struct ublk_device *ub = ubq->dev; + int ret = 0; + + /* + * When handling FETCH command for setting up ublk uring queue, + * ub->mutex is the innermost lock, and we won't block for handling + * FETCH, so it is fine even for IO_URING_F_NONBLOCK. + */ + mutex_lock(&ub->mutex); + /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ + if (ublk_queue_ready(ubq)) { + ret = -EBUSY; + goto out; + } + + /* allow each command to be FETCHed at most once */ + if (io->flags & UBLK_IO_FLAG_ACTIVE) { + ret = -EINVAL; + goto out; + } + + WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV); + + if (ublk_need_map_io(ubq)) { + /* + * FETCH_RQ has to provide IO buffer if NEED GET + * DATA is not enabled + */ + if (!buf_addr && !ublk_need_get_data(ubq)) + goto out; + } else if (buf_addr) { + /* User copy requires addr to be unset */ + ret = -EINVAL; + goto out; + } + + ublk_fill_io_cmd(io, cmd, buf_addr); + ublk_mark_io_ready(ub, ubq); +out: + mutex_unlock(&ub->mutex); + return ret; +} + static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags, const struct ublksrv_io_cmd *ub_cmd) @@ -1985,33 +2069,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, case UBLK_IO_UNREGISTER_IO_BUF: return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags); case UBLK_IO_FETCH_REQ: - /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ - if (ublk_queue_ready(ubq)) { - ret = -EBUSY; - goto out; - } - /* - * The io is being handled by server, so COMMIT_RQ is expected - * instead of FETCH_REQ - */ - if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) - goto out; - - if (ublk_need_map_io(ubq)) { - /* - * FETCH_RQ has to provide IO buffer if NEED GET - * DATA is not enabled - */ - if (!ub_cmd->addr && !ublk_need_get_data(ubq)) - goto out; - } else if (ub_cmd->addr) { - /* User copy requires addr to be unset */ - ret = -EINVAL; + ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr); + if (ret) goto out; - } - - ublk_fill_io_cmd(io, cmd, ub_cmd->addr); - ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); @@ -2411,7 +2471,6 @@ static void ublk_remove(struct ublk_device *ub) bool unprivileged; ublk_stop_dev(ub); - cancel_work_sync(&ub->nosrv_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV; ublk_put_device(ub); @@ -2696,7 +2755,6 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) goto out_unlock; mutex_init(&ub->mutex); spin_lock_init(&ub->lock); - INIT_WORK(&ub->nosrv_work, ublk_nosrv_work); ret = ublk_alloc_dev_number(ub, header->dev_id); if (ret < 0) @@ -2828,7 +2886,6 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) static int ublk_ctrl_stop_dev(struct ublk_device *ub) { ublk_stop_dev(ub); - cancel_work_sync(&ub->nosrv_work); return 0; } @@ -2932,42 +2989,14 @@ static int ublk_ctrl_set_params(struct ublk_device *ub, return ret; } -static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) -{ - int i; - - WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); - - /* All old ioucmds have to be completed */ - ubq->nr_io_ready = 0; - /* old daemon is PF_EXITING, put it now */ - put_task_struct(ubq->ubq_daemon); - /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ - ubq->ubq_daemon = NULL; - ubq->timeout = false; - ubq->canceling = false; - - for (i = 0; i < ubq->q_depth; i++) { - struct ublk_io *io = &ubq->ios[i]; - - /* forget everything now and be ready for new FETCH_REQ */ - io->flags = 0; - io->cmd = NULL; - io->addr = 0; - } -} - static int ublk_ctrl_start_recovery(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { int ret = -EINVAL; - int i; mutex_lock(&ub->mutex); if (ublk_nosrv_should_stop_dev(ub)) goto out_unlock; - if (!ub->nr_queues_ready) - goto out_unlock; /* * START_RECOVERY is only allowd after: * @@ -2991,12 +3020,6 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, goto out_unlock; } pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id); - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_queue_reinit(ub, ublk_get_queue(ub, i)); - /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ - ub->mm = NULL; - ub->nr_queues_ready = 0; - ub->nr_privileged_daemon = 0; init_completion(&ub->completion); ret = 0; out_unlock: @@ -3009,7 +3032,6 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, { int ublksrv_pid = (int)header->data[0]; int ret = -EINVAL; - int i; pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", __func__, ub->dev_info.nr_hw_queues, header->dev_id); @@ -3029,24 +3051,10 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, goto out_unlock; } ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.state = UBLK_S_DEV_LIVE; pr_devel("%s: new ublksrv_pid %d, dev id %d\n", __func__, ublksrv_pid, header->dev_id); - - if (ublk_nosrv_dev_should_queue_io(ub)) { - ub->dev_info.state = UBLK_S_DEV_LIVE; - blk_mq_unquiesce_queue(ub->ub_disk->queue); - pr_devel("%s: queue unquiesced, dev id %d.\n", - __func__, header->dev_id); - blk_mq_kick_requeue_list(ub->ub_disk->queue); - } else { - blk_mq_quiesce_queue(ub->ub_disk->queue); - ub->dev_info.state = UBLK_S_DEV_LIVE; - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { - ublk_get_queue(ub, i)->fail_io = false; - } - blk_mq_unquiesce_queue(ub->ub_disk->queue); - } - + blk_mq_kick_requeue_list(ub->ub_disk->queue); ret = 0; out_unlock: mutex_unlock(&ub->mutex); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 5f04951d0dd4..088182e54deb 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1576,8 +1576,8 @@ static void handle_control_message(struct virtio_device *vdev, break; case VIRTIO_CONSOLE_RESIZE: { struct { - __u16 rows; - __u16 cols; + __virtio16 cols; + __virtio16 rows; } size; if (!is_console_port(port)) @@ -1585,7 +1585,8 @@ static void handle_control_message(struct virtio_device *vdev, memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt), sizeof(size)); - set_console_size(port, size.rows, size.cols); + set_console_size(port, virtio16_to_cpu(vdev, size.rows), + virtio16_to_cpu(vdev, size.cols)); port->cons.hvc->irq_requested = 1; resize_console(port); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 6789eed1bb5b..b961f3a3b580 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -607,13 +607,16 @@ static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) union perf_cached perf = READ_ONCE(cpudata->perf); perf.max_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->max); - perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min); + WRITE_ONCE(cpudata->max_limit_freq, policy->max); - if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) { perf.min_limit_perf = min(perf.nominal_perf, perf.max_limit_perf); + WRITE_ONCE(cpudata->min_limit_freq, min(cpudata->nominal_freq, cpudata->max_limit_freq)); + } else { + perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min); + WRITE_ONCE(cpudata->min_limit_freq, policy->min); + } - WRITE_ONCE(cpudata->max_limit_freq, policy->max); - WRITE_ONCE(cpudata->min_limit_freq, policy->min); WRITE_ONCE(cpudata->perf, perf); } @@ -791,16 +794,6 @@ static void amd_perf_ctl_reset(unsigned int cpu) wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); } -/* - * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks - * due to locking, so queue the work for later. - */ -static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) -{ - sched_set_itmt_support(); -} -static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); - #define CPPC_MAX_PERF U8_MAX static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) @@ -811,14 +804,8 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) cpudata->hw_prefcore = true; - /* - * The priorities can be set regardless of whether or not - * sched_set_itmt_support(true) has been called and it is valid to - * update them at any time after it has been called. - */ + /* Priorities must be initialized before ITMT support can be toggled on. */ sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu); - - schedule_work(&sched_prefcore_work); } static void amd_pstate_update_limits(unsigned int cpu) @@ -1193,6 +1180,9 @@ static ssize_t show_energy_performance_preference( static void amd_pstate_driver_cleanup(void) { + if (amd_pstate_prefcore) + sched_clear_itmt_support(); + cppc_state = AMD_PSTATE_DISABLE; current_pstate_driver = NULL; } @@ -1235,6 +1225,10 @@ static int amd_pstate_register_driver(int mode) return ret; } + /* Enable ITMT support once all CPUs have initialized their asym priorities. */ + if (amd_pstate_prefcore) + sched_set_itmt_support(); + return 0; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 3841c9da6cac..acf19b0042bb 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -540,8 +540,6 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, { unsigned int idx; - target_freq = clamp_val(target_freq, policy->min, policy->max); - if (!policy->freq_table) return target_freq; @@ -565,7 +563,22 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq) { - return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE); + unsigned int min = READ_ONCE(policy->min); + unsigned int max = READ_ONCE(policy->max); + + /* + * If this function runs in parallel with cpufreq_set_policy(), it may + * read policy->min before the update and policy->max after the update + * or the other way around, so there is no ordering guarantee. + * + * Resolve this by always honoring the max (in case it comes from + * thermal throttling or similar). + */ + if (unlikely(min > max)) + min = max; + + return __resolve_freq(policy, clamp_val(target_freq, min, max), + CPUFREQ_RELATION_LE); } EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq); @@ -2384,6 +2397,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, if (cpufreq_disabled()) return -ENODEV; + target_freq = clamp_val(target_freq, policy->min, policy->max); target_freq = __resolve_freq(policy, target_freq, relation); pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n", @@ -2708,11 +2722,15 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, * Resolve policy min/max to available frequencies. It ensures * no frequency resolution will neither overshoot the requested maximum * nor undershoot the requested minimum. + * + * Avoid storing intermediate values in policy->max or policy->min and + * compiler optimizations around them because they may be accessed + * concurrently by cpufreq_driver_resolve_freq() during the update. */ - policy->min = new_data.min; - policy->max = new_data.max; - policy->min = __resolve_freq(policy, policy->min, CPUFREQ_RELATION_L); - policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H); + WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max, CPUFREQ_RELATION_H)); + new_data.min = __resolve_freq(policy, new_data.min, CPUFREQ_RELATION_L); + WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min); + trace_cpu_frequency_limits(policy); cpufreq_update_pressure(policy); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4aad79d26c64..f41ed0b9e610 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2209,7 +2209,7 @@ static int knl_get_turbo_pstate(int cpu) static int hwp_get_cpu_scaling(int cpu) { if (hybrid_scaling_factor) { - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + struct cpuinfo_x86 *c = &cpu_data(cpu); u8 cpu_type = c->topo.intel_type; /* diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c index 75bebec2c757..0fcf4a39de27 100644 --- a/drivers/crypto/atmel-sha204a.c +++ b/drivers/crypto/atmel-sha204a.c @@ -163,6 +163,12 @@ static int atmel_sha204a_probe(struct i2c_client *client) i2c_priv->hwrng.name = dev_name(&client->dev); i2c_priv->hwrng.read = atmel_sha204a_rng_read; + /* + * According to review by Bill Cox [1], this HWRNG has very low entropy. + * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html + */ + i2c_priv->hwrng.quality = 1; + ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng); if (ret) dev_warn(&client->dev, "failed to register RNG (%d)\n", ret); diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index f5905d67dedb..22a808995f10 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -438,15 +438,17 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a return -EINVAL; pt = dma_fence_to_sync_pt(fence); - if (!pt) - return -EINVAL; + if (!pt) { + ret = -EINVAL; + goto put_fence; + } spin_lock_irqsave(fence->lock, flags); - if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { - data.deadline_ns = ktime_to_ns(pt->deadline); - } else { + if (!test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { ret = -ENOENT; + goto unlock; } + data.deadline_ns = ktime_to_ns(pt->deadline); spin_unlock_irqrestore(fence->lock, flags); dma_fence_put(fence); @@ -458,6 +460,13 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a return -EFAULT; return 0; + +unlock: + spin_unlock_irqrestore(fence->lock, flags); +put_fence: + dma_fence_put(fence); + + return ret; } static long sw_sync_ioctl(struct file *file, unsigned int cmd, diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index b8197502a5ac..cd4fecbb41f2 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2879,7 +2879,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) * output-only, but if there is then not even a .set() operation it * is pretty tricky to drive the output line. */ - if (!guard.gc->set && !guard.gc->direction_output) { + if (!guard.gc->set && !guard.gc->set_rv && !guard.gc->direction_output) { gpiod_warn(desc, "%s: missing set() and direction_output() operations\n", __func__); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2c04ae133848..ef6e78224fdf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1123,6 +1123,7 @@ struct amdgpu_device { bool in_s3; bool in_s4; bool in_s0ix; + suspend_state_t last_suspend_state; enum pp_mp1_state mp1_state; struct amdgpu_doorbell_index doorbell_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index b34b915203f2..7f354cd532dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3510,6 +3510,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) amdgpu_device_mem_scratch_fini(adev); amdgpu_ib_pool_fini(adev); amdgpu_seq64_fini(adev); + amdgpu_doorbell_fini(adev); } if (adev->ip_blocks[i].version->funcs->sw_fini) { r = adev->ip_blocks[i].version->funcs->sw_fini(&adev->ip_blocks[i]); @@ -4858,7 +4859,6 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) iounmap(adev->rmmio); adev->rmmio = NULL; - amdgpu_doorbell_fini(adev); drm_dev_exit(idx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 26bf896f1444..24ee4710f807 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2548,8 +2548,20 @@ static int amdgpu_pmops_suspend(struct device *dev) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) adev->in_s3 = true; - if (!adev->in_s0ix && !adev->in_s3) + if (!adev->in_s0ix && !adev->in_s3) { + /* don't allow going deep first time followed by s2idle the next time */ + if (adev->last_suspend_state != PM_SUSPEND_ON && + adev->last_suspend_state != pm_suspend_target_state) { + drm_err_once(drm_dev, "Unsupported suspend state %d\n", + pm_suspend_target_state); + return -EINVAL; + } return 0; + } + + /* cache the state last used for suspend */ + adev->last_suspend_state = pm_suspend_target_state; + return amdgpu_device_suspend(drm_dev, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 72af5e5a894a..cf2df7790077 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1438,9 +1438,11 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) struct amdgpu_device *adev = ring->adev; struct drm_gpu_scheduler *sched = &ring->sched; struct drm_sched_entity entity; + static atomic_t counter; struct dma_fence *f; struct amdgpu_job *job; struct amdgpu_ib *ib; + void *owner; int i, r; /* Initialize the scheduler entity */ @@ -1451,9 +1453,15 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) goto err; } - r = amdgpu_job_alloc_with_ib(ring->adev, &entity, NULL, - 64, 0, - &job); + /* + * Use some unique dummy value as the owner to make sure we execute + * the cleaner shader on each submission. The value just need to change + * for each submission and is otherwise meaningless. + */ + owner = (void *)(unsigned long)atomic_inc_return(&counter); + + r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner, + 64, 0, &job); if (r) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index a63ce747863f..23e6a05359c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6114,7 +6114,7 @@ static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, mmCP_PFP_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0); @@ -6192,7 +6192,7 @@ static int gfx_v10_0_cp_gfx_load_ce_microcode(struct amdgpu_device *adev) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, mmCP_CE_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_CE_IC_BASE_CNTL, VMID, 0); @@ -6269,7 +6269,7 @@ static int gfx_v10_0_cp_gfx_load_me_microcode(struct amdgpu_device *adev) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, mmCP_ME_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0); @@ -6644,7 +6644,7 @@ static int gfx_v10_0_cp_compute_load_microcode(struct amdgpu_device *adev) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, mmCP_CPC_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index d57db42f9536..2a5c2a1ae3c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -2428,7 +2428,7 @@ static int gfx_v11_0_config_me_cache(struct amdgpu_device *adev, uint64_t addr) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, regCP_ME_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0); @@ -2472,7 +2472,7 @@ static int gfx_v11_0_config_pfp_cache(struct amdgpu_device *adev, uint64_t addr) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0); @@ -2517,7 +2517,7 @@ static int gfx_v11_0_config_mec_cache(struct amdgpu_device *adev, uint64_t addr) } if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); tmp = RREG32_SOC15(GC, 0, regCP_CPC_IC_BASE_CNTL); tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0); @@ -3153,7 +3153,7 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev) amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj); if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO, lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr)); @@ -3371,7 +3371,7 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev) amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj); if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO, lower_32_bits(adev->gfx.me.me_fw_gpu_addr)); @@ -4541,7 +4541,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev) if (r) return r; - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index e7b58e470292..62a257a4a3e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -2324,7 +2324,7 @@ static int gfx_v12_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev) amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj); if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO, lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr)); @@ -2468,7 +2468,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev) amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj); if (amdgpu_emu_mode == 1) - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO, lower_32_bits(adev->gfx.me.me_fw_gpu_addr)); @@ -3426,7 +3426,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev) if (r) return r; - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 95d894a231fc..809b3a882d0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -268,7 +268,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng; /* flush hdp cache */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); /* This is necessary for SRIOV as well as for GFXOFF to function * properly under bare metal @@ -969,7 +969,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) adev->hdp.funcs->init_registers(adev); /* Flush HDP after it is initialized */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index ad099f136f84..e74e26b6a4f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -229,7 +229,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng; /* flush hdp cache */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); /* This is necessary for SRIOV as well as for GFXOFF to function * properly under bare metal @@ -899,7 +899,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev) return r; /* Flush HDP after it is initialized */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index 05c026d0b0d9..c6f290704d47 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -297,7 +297,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, return; /* flush hdp cache */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); /* This is necessary for SRIOV as well as for GFXOFF to function * properly under bare metal @@ -881,7 +881,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev) return r; /* Flush HDP after it is initialized */ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 783e0c3b86b4..5effe8327d29 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -2435,7 +2435,7 @@ static int gmc_v9_0_hw_init(struct amdgpu_ip_block *ip_block) adev->hdp.funcs->init_registers(adev); /* After HDP is initialized, flush HDP.*/ - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) value = false; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index bb5dfc410a66..215543575f47 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -533,7 +533,7 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops) } memcpy_toio(adev->mman.aper_base_kaddr, buf, sz); - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); vfree(buf); drm_dev_exit(idx); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index cc621064610f..afdf8ce3b4c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -610,7 +610,7 @@ static int psp_v13_0_memory_training(struct psp_context *psp, uint32_t ops) } memcpy_toio(adev->mman.aper_base_kaddr, buf, sz); - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); vfree(buf); drm_dev_exit(idx); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c index 7c49c3f3c388..256288c6cd78 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c @@ -498,7 +498,7 @@ static int psp_v14_0_memory_training(struct psp_context *psp, uint32_t ops) } memcpy_toio(adev->mman.aper_base_kaddr, buf, sz); - adev->hdp.funcs->flush_hdp(adev, NULL); + amdgpu_device_flush_hdp(adev, NULL); vfree(buf); drm_dev_exit(idx); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 86d8bc10d90a..9b3510e53112 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -239,6 +239,13 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] = .max_pixels_per_frame = 4096 * 4096, .max_level = 186, }, + { + .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, + .max_width = 4096, + .max_height = 4096, + .max_pixels_per_frame = 4096 * 4096, + .max_level = 0, + }, }; static const struct amdgpu_video_codecs cz_video_codecs_decode = diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c index 94e99e540691..5d16f36ec95c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c @@ -2,6 +2,7 @@ // // Copyright 2024 Advanced Micro Devices, Inc. +#include <linux/vmalloc.h> #include "dml2_internal_types.h" #include "dml_top.h" @@ -13,11 +14,11 @@ static bool dml21_allocate_memory(struct dml2_context **dml_ctx) { - *dml_ctx = kzalloc(sizeof(struct dml2_context), GFP_KERNEL); + *dml_ctx = vzalloc(sizeof(struct dml2_context)); if (!(*dml_ctx)) return false; - (*dml_ctx)->v21.dml_init.dml2_instance = kzalloc(sizeof(struct dml2_instance), GFP_KERNEL); + (*dml_ctx)->v21.dml_init.dml2_instance = vzalloc(sizeof(struct dml2_instance)); if (!((*dml_ctx)->v21.dml_init.dml2_instance)) return false; @@ -27,7 +28,7 @@ static bool dml21_allocate_memory(struct dml2_context **dml_ctx) (*dml_ctx)->v21.mode_support.display_config = &(*dml_ctx)->v21.display_config; (*dml_ctx)->v21.mode_programming.display_config = (*dml_ctx)->v21.mode_support.display_config; - (*dml_ctx)->v21.mode_programming.programming = kzalloc(sizeof(struct dml2_display_cfg_programming), GFP_KERNEL); + (*dml_ctx)->v21.mode_programming.programming = vzalloc(sizeof(struct dml2_display_cfg_programming)); if (!((*dml_ctx)->v21.mode_programming.programming)) return false; @@ -115,8 +116,8 @@ bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const s void dml21_destroy(struct dml2_context *dml2) { - kfree(dml2->v21.dml_init.dml2_instance); - kfree(dml2->v21.mode_programming.programming); + vfree(dml2->v21.dml_init.dml2_instance); + vfree(dml2->v21.mode_programming.programming); } static void dml21_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *context, struct resource_context *out_new_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index f549a778f6f1..e89571874185 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -24,6 +24,8 @@ * */ +#include <linux/vmalloc.h> + #include "display_mode_core.h" #include "dml2_internal_types.h" #include "dml2_utils.h" @@ -747,7 +749,7 @@ bool dml2_validate(const struct dc *in_dc, struct dc_state *context, struct dml2 static inline struct dml2_context *dml2_allocate_memory(void) { - return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL); + return (struct dml2_context *) vzalloc(sizeof(struct dml2_context)); } static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) @@ -821,7 +823,7 @@ void dml2_destroy(struct dml2_context *dml2) if (dml2->architecture == dml2_architecture_21) dml21_destroy(dml2); - kfree(dml2); + vfree(dml2); } void dml2_extract_dram_and_fclk_change_support(struct dml2_context *dml2, diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index 717286981687..7a3bb77c7af7 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -161,6 +161,7 @@ struct intel_display_platforms { #define HAS_DPT(__display) (DISPLAY_VER(__display) >= 13) #define HAS_DSB(__display) (DISPLAY_INFO(__display)->has_dsb) #define HAS_DSC(__display) (DISPLAY_RUNTIME_INFO(__display)->has_dsc) +#define HAS_DSC_3ENGINES(__display) (DISPLAY_VERx100(__display) == 1401 && HAS_DSC(__display)) #define HAS_DSC_MST(__display) (DISPLAY_VER(__display) >= 12 && HAS_DSC(__display)) #define HAS_FBC(__display) (DISPLAY_RUNTIME_INFO(__display)->fbc_mask != 0) #define HAS_FBC_DIRTY_RECT(__display) (DISPLAY_VER(__display) >= 30) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 9476aaa91900..392c3653d0d7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1050,10 +1050,11 @@ u8 intel_dp_dsc_get_slice_count(const struct intel_connector *connector, u8 test_slice_count = valid_dsc_slicecount[i] * num_joined_pipes; /* - * 3 DSC Slices per pipe need 3 DSC engines, - * which is supported only with Ultrajoiner. + * 3 DSC Slices per pipe need 3 DSC engines, which is supported only + * with Ultrajoiner only for some platforms. */ - if (valid_dsc_slicecount[i] == 3 && num_joined_pipes != 4) + if (valid_dsc_slicecount[i] == 3 && + (!HAS_DSC_3ENGINES(display) || num_joined_pipes != 4)) continue; if (test_slice_count > diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index fb71658c3117..6067d08aeee3 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -223,7 +223,7 @@ void mgag200_set_mode_regs(struct mga_device *mdev, const struct drm_display_mod vsyncstr = mode->crtc_vsync_start - 1; vsyncend = mode->crtc_vsync_end - 1; vtotal = mode->crtc_vtotal - 2; - vblkstr = mode->crtc_vblank_start; + vblkstr = mode->crtc_vblank_start - 1; vblkend = vtotal + 1; linecomp = vdispend; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 06465bc2d0b4..242d02d48c0c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -242,10 +242,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) break; fallthrough; case MSM_SUBMIT_CMD_BUF: - OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); + OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); OUT_RING(ring, upper_32_bits(submit->cmd[i].iova)); - OUT_RING(ring, submit->cmd[i].size); + OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size)); ibs++; break; } @@ -377,10 +377,10 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) break; fallthrough; case MSM_SUBMIT_CMD_BUF: - OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); + OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); OUT_RING(ring, upper_32_bits(submit->cmd[i].iova)); - OUT_RING(ring, submit->cmd[i].size); + OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size)); ibs++; break; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h index 1f32807bb5e5..ad60089f18ea 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h @@ -132,7 +132,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -141,7 +140,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h index 42131959ff22..a1cf89a0a42d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h @@ -118,7 +118,6 @@ static const struct dpu_intf_cfg msm8917_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h index 2b4723a5c676..eea9b80e2287 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h @@ -131,7 +131,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x268, @@ -140,7 +139,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -149,7 +147,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h index 5cf19de71f06..ae18a354e5d2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h @@ -241,7 +241,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x268, @@ -250,7 +249,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -259,7 +257,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, { .name = "intf_3", .id = INTF_3, .base = 0x6b800, .len = 0x268, @@ -267,7 +264,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h index 4f2f68b07f20..bb89da0a481d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h @@ -202,7 +202,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x280, @@ -211,7 +210,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x280, @@ -220,7 +218,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h index c70bef025ac4..7caf876ca3e3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h @@ -147,7 +147,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x280, @@ -156,7 +155,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 8610bbf2b87c..862e9e6bf0a5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1666,7 +1666,7 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, */ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) { - struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys->parent); + struct dpu_encoder_virt *dpu_enc; if (!phys) { DPU_ERROR("invalid argument(s)\n"); @@ -1678,6 +1678,8 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) return; } + dpu_enc = to_dpu_encoder_virt(phys->parent); + if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL && dpu_enc->cwb_mask) { DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent)); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index af3e541f60c3..e03d6091f736 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -729,12 +729,40 @@ static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu, static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe, struct dpu_sw_pipe_cfg *pipe_cfg, - const struct msm_format *fmt, - const struct drm_display_mode *mode) + const struct drm_display_mode *mode, + struct drm_plane_state *new_plane_state) { uint32_t min_src_size; struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); int ret; + const struct msm_format *fmt; + uint32_t supported_rotations; + const struct dpu_sspp_cfg *pipe_hw_caps; + const struct dpu_sspp_sub_blks *sblk; + + pipe_hw_caps = pipe->sspp->cap; + sblk = pipe->sspp->cap->sblk; + + /* + * We already have verified scaling against platform limitations. + * Now check if the SSPP supports scaling at all. + */ + if (!sblk->scaler_blk.len && + ((drm_rect_width(&new_plane_state->src) >> 16 != + drm_rect_width(&new_plane_state->dst)) || + (drm_rect_height(&new_plane_state->src) >> 16 != + drm_rect_height(&new_plane_state->dst)))) + return -ERANGE; + + fmt = msm_framebuffer_format(new_plane_state->fb); + + supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0; + + if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) + supported_rotations |= DRM_MODE_ROTATE_90; + + pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation, + supported_rotations); min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1; @@ -923,47 +951,20 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); struct dpu_sw_pipe *pipe = &pstate->pipe; struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - const struct msm_format *fmt; struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; - uint32_t supported_rotations; - const struct dpu_sspp_cfg *pipe_hw_caps; - const struct dpu_sspp_sub_blks *sblk; int ret = 0; - pipe_hw_caps = pipe->sspp->cap; - sblk = pipe->sspp->cap->sblk; - - /* - * We already have verified scaling against platform limitations. - * Now check if the SSPP supports scaling at all. - */ - if (!sblk->scaler_blk.len && - ((drm_rect_width(&new_plane_state->src) >> 16 != - drm_rect_width(&new_plane_state->dst)) || - (drm_rect_height(&new_plane_state->src) >> 16 != - drm_rect_height(&new_plane_state->dst)))) - return -ERANGE; - - fmt = msm_framebuffer_format(new_plane_state->fb); - - supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0; - - if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) - supported_rotations |= DRM_MODE_ROTATE_90; - - pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation, - supported_rotations); - r_pipe_cfg->rotation = pipe_cfg->rotation; - - ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, - &crtc_state->adjusted_mode); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, + &crtc_state->adjusted_mode, + new_plane_state); if (ret) return ret; if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt, - &crtc_state->adjusted_mode); + ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, + &crtc_state->adjusted_mode, + new_plane_state); if (ret) return ret; } @@ -1059,6 +1060,9 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, struct drm_crtc_state *crtc_state; int ret; + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + if (plane_state->crtc) crtc_state = drm_atomic_get_new_crtc_state(state, plane_state->crtc); diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 55a35182858c..5a6ae9fc3194 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -2259,5 +2259,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </domain> +<domain name="CP_INDIRECT_BUFFER" width="32" varset="chip" prefix="chip" variants="A5XX-"> + <reg64 offset="0" name="IB_BASE" type="address"/> + <reg32 offset="2" name="2"> + <bitfield name="IB_SIZE" low="0" high="19"/> + </reg32> +</domain> + </database> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 34c42d6e12cd..4a7701a33cf8 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -428,7 +428,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job) struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]); struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect); struct drm_v3d_submit_csd *args = &indirect_csd->job->args; - u32 *wg_counts; + struct v3d_dev *v3d = job->base.v3d; + u32 num_batches, *wg_counts; v3d_get_bo_vaddr(bo); v3d_get_bo_vaddr(indirect); @@ -441,8 +442,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job) args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT; args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT; args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT; - args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) * - (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1; + + num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) * + (wg_counts[0] * wg_counts[1] * wg_counts[2]); + + /* V3D 7.1.6 and later don't subtract 1 from the number of batches */ + if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6)) + args->cfg[4] = num_batches - 1; + else + args->cfg[4] = num_batches; + + WARN_ON(args->cfg[4] == ~0); for (int i = 0; i < 3; i++) { /* 0xffffffff indicates that the uniform rewrite is not needed */ diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 2d88e390feb4..e32e680c7197 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -128,6 +128,14 @@ static void virtio_gpu_remove(struct virtio_device *vdev) drm_dev_put(dev); } +static void virtio_gpu_shutdown(struct virtio_device *vdev) +{ + /* + * drm does its own synchronization on shutdown. + * Do nothing here, opt out of device reset. + */ +} + static void virtio_gpu_config_changed(struct virtio_device *vdev) { struct drm_device *dev = vdev->priv; @@ -162,6 +170,7 @@ static struct virtio_driver virtio_gpu_driver = { .id_table = id_table, .probe = virtio_gpu_probe, .remove = virtio_gpu_remove, + .shutdown = virtio_gpu_shutdown, .config_changed = virtio_gpu_config_changed }; diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index f67803e15a0e..f7a20264ea33 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -145,10 +145,7 @@ static void xe_dma_buf_unmap(struct dma_buf_attachment *attach, struct sg_table *sgt, enum dma_data_direction dir) { - struct dma_buf *dma_buf = attach->dmabuf; - struct xe_bo *bo = gem_to_xe_bo(dma_buf->priv); - - if (!xe_bo_is_vram(bo)) { + if (sg_page(sgt->sgl)) { dma_unmap_sgtable(attach->dev, sgt, dir, 0); sg_free_table(sgt); kfree(sgt); diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index e7c9e095a19f..7031542a70ce 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -490,24 +490,52 @@ static void fill_engine_enable_masks(struct xe_gt *gt, engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER)); } -static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads) +/* + * Write the offsets corresponding to the golden LRCs. The actual data is + * populated later by guc_golden_lrc_populate() + */ +static void guc_golden_lrc_init(struct xe_guc_ads *ads) { struct xe_device *xe = ads_to_xe(ads); + struct xe_gt *gt = ads_to_gt(ads); struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads), offsetof(struct __guc_ads_blob, system_info)); - u8 guc_class; + size_t alloc_size, real_size; + u32 addr_ggtt, offset; + int class; + + offset = guc_ads_golden_lrc_offset(ads); + addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset; + + for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) { + u8 guc_class; + + guc_class = xe_engine_class_to_guc_class(class); - for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) { if (!info_map_read(xe, &info_map, engine_enabled_masks[guc_class])) continue; + real_size = xe_gt_lrc_size(gt, class); + alloc_size = PAGE_ALIGN(real_size); + + /* + * This interface is slightly confusing. We need to pass the + * base address of the full golden context and the size of just + * the engine state, which is the section of the context image + * that starts after the execlists LRC registers. This is + * required to allow the GuC to restore just the engine state + * when a watchdog reset occurs. + * We calculate the engine state size by removing the size of + * what comes before it in the context image (which is identical + * on all engines). + */ ads_blob_write(ads, ads.eng_state_size[guc_class], - guc_ads_golden_lrc_size(ads) - - xe_lrc_skip_size(xe)); + real_size - xe_lrc_skip_size(xe)); ads_blob_write(ads, ads.golden_context_lrca[guc_class], - xe_bo_ggtt_addr(ads->bo) + - guc_ads_golden_lrc_offset(ads)); + addr_ggtt); + + addr_ggtt += alloc_size; } } @@ -857,7 +885,7 @@ void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads) xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size); guc_policies_init(ads); - guc_prep_golden_lrc_null(ads); + guc_golden_lrc_init(ads); guc_mapping_table_init_invalid(gt, &info_map); guc_doorbell_init(ads); @@ -883,7 +911,7 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads) guc_policies_init(ads); fill_engine_enable_masks(gt, &info_map); guc_mmio_reg_state_init(ads); - guc_prep_golden_lrc_null(ads); + guc_golden_lrc_init(ads); guc_mapping_table_init(gt, &info_map); guc_capture_prep_lists(ads); guc_doorbell_init(ads); @@ -903,18 +931,22 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads) guc_ads_private_data_offset(ads)); } -static void guc_populate_golden_lrc(struct xe_guc_ads *ads) +/* + * After the golden LRC's are recorded for each engine class by the first + * submission, copy them to the ADS, as initialized earlier by + * guc_golden_lrc_init(). + */ +static void guc_golden_lrc_populate(struct xe_guc_ads *ads) { struct xe_device *xe = ads_to_xe(ads); struct xe_gt *gt = ads_to_gt(ads); struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads), offsetof(struct __guc_ads_blob, system_info)); size_t total_size = 0, alloc_size, real_size; - u32 addr_ggtt, offset; + u32 offset; int class; offset = guc_ads_golden_lrc_offset(ads); - addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset; for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) { u8 guc_class; @@ -931,26 +963,9 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads) alloc_size = PAGE_ALIGN(real_size); total_size += alloc_size; - /* - * This interface is slightly confusing. We need to pass the - * base address of the full golden context and the size of just - * the engine state, which is the section of the context image - * that starts after the execlists LRC registers. This is - * required to allow the GuC to restore just the engine state - * when a watchdog reset occurs. - * We calculate the engine state size by removing the size of - * what comes before it in the context image (which is identical - * on all engines). - */ - ads_blob_write(ads, ads.eng_state_size[guc_class], - real_size - xe_lrc_skip_size(xe)); - ads_blob_write(ads, ads.golden_context_lrca[guc_class], - addr_ggtt); - xe_map_memcpy_to(xe, ads_to_map(ads), offset, gt->default_lrc[class], real_size); - addr_ggtt += alloc_size; offset += alloc_size; } @@ -959,7 +974,7 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads) void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads) { - guc_populate_golden_lrc(ads); + guc_golden_lrc_populate(ads); } static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset) diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c index c3cc0fa105e8..57b71956ddf4 100644 --- a/drivers/gpu/drm/xe/xe_hmm.c +++ b/drivers/gpu/drm/xe/xe_hmm.c @@ -19,29 +19,6 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end) return (end - start) >> PAGE_SHIFT; } -/** - * xe_mark_range_accessed() - mark a range is accessed, so core mm - * have such information for memory eviction or write back to - * hard disk - * @range: the range to mark - * @write: if write to this range, we mark pages in this range - * as dirty - */ -static void xe_mark_range_accessed(struct hmm_range *range, bool write) -{ - struct page *page; - u64 i, npages; - - npages = xe_npages_in_range(range->start, range->end); - for (i = 0; i < npages; i++) { - page = hmm_pfn_to_page(range->hmm_pfns[i]); - if (write) - set_page_dirty_lock(page); - - mark_page_accessed(page); - } -} - static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st, struct hmm_range *range, struct rw_semaphore *notifier_sem) { @@ -331,7 +308,6 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, if (ret) goto out_unlock; - xe_mark_range_accessed(&hmm_range, write); userptr->sg = &userptr->sgt; xe_hmm_userptr_set_mapped(uvma); userptr->notifier_seq = hmm_range.notifier_seq; diff --git a/drivers/gpu/drm/xe/xe_pxp_debugfs.c b/drivers/gpu/drm/xe/xe_pxp_debugfs.c index ccfbacf08efc..525a2f6bb076 100644 --- a/drivers/gpu/drm/xe/xe_pxp_debugfs.c +++ b/drivers/gpu/drm/xe/xe_pxp_debugfs.c @@ -66,9 +66,18 @@ static int pxp_terminate(struct seq_file *m, void *data) { struct xe_pxp *pxp = node_to_pxp(m->private); struct drm_printer p = drm_seq_file_printer(m); + int ready = xe_pxp_get_readiness_status(pxp); - if (!xe_pxp_is_enabled(pxp)) - return -ENODEV; + if (ready < 0) + return ready; /* disabled or error occurred */ + else if (!ready) + return -EBUSY; /* init still in progress */ + + /* no need for a termination if PXP is not active */ + if (pxp->status != XE_PXP_ACTIVE) { + drm_printf(&p, "PXP not active\n"); + return 0; + } /* simulate a termination interrupt */ spin_lock_irq(&pxp->xe->irq.lock); diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c index 43bf90d90eeb..208ce4f9e782 100644 --- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c +++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c @@ -247,6 +247,9 @@ static int ec_i2c_probe(struct platform_device *pdev) u32 remote_bus; int err; + if (!ec) + return dev_err_probe(dev, -EPROBE_DEFER, "couldn't find parent EC device\n"); + if (!ec->cmd_xfer) { dev_err(dev, "Missing sendrecv\n"); return -EINVAL; diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c index 8fe9ddff8e96..783fb8df2ebe 100644 --- a/drivers/i2c/i2c-atr.c +++ b/drivers/i2c/i2c-atr.c @@ -8,12 +8,12 @@ * Originally based on i2c-mux.c */ -#include <linux/fwnode.h> #include <linux/i2c-atr.h> #include <linux/i2c.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/property.h> #include <linux/slab.h> #include <linux/spinlock.h> diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c index 08975c60e325..7bc341c69697 100644 --- a/drivers/iio/magnetometer/ak8974.c +++ b/drivers/iio/magnetometer/ak8974.c @@ -535,8 +535,8 @@ static int ak8974_detect(struct ak8974 *ak8974) fab_data2, sizeof(fab_data2)); for (i = 0; i < 3; ++i) { - static const char axis[3] = "XYZ"; - static const char pgaxis[6] = "ZYZXYX"; + static const char axis[] = "XYZ"; + static const char pgaxis[] = "ZYZXYX"; unsigned offz = le16_to_cpu(fab_data2[i]) & 0x7F; unsigned fine = le16_to_cpu(fab_data1[i]); unsigned sens = le16_to_cpu(fab_data1[i + 3]); diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c index 2eaa25c9c68c..d73389af4dd5 100644 --- a/drivers/input/joystick/magellan.c +++ b/drivers/input/joystick/magellan.c @@ -48,7 +48,7 @@ struct magellan { static int magellan_crunch_nibbles(unsigned char *data, int count) { - static unsigned char nibbles[16] = "0AB3D56GH9:K<MN?"; + static unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?"; do { if (data[count] == nibbles[data[count] & 0xf]) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index cec05e443083..08bb3b031f23 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -114,8 +114,8 @@ config I8259 config BCM2712_MIP tristate "Broadcom BCM2712 MSI-X Interrupt Peripheral support" - depends on ARCH_BRCMSTB || COMPILE_TEST - default m if ARCH_BRCMSTB + depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST + default m if ARCH_BRCMSTB || ARCH_BCM2835 depends on ARM_GIC select GENERIC_IRQ_CHIP select IRQ_DOMAIN_HIERARCHY diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c index 3d5b5fdf9bde..0f0fd7d4dfdf 100644 --- a/drivers/irqchip/irq-renesas-rzv2h.c +++ b/drivers/irqchip/irq-renesas-rzv2h.c @@ -170,6 +170,14 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable) else tssr &= ~ICU_TSSR_TIEN(tssel_n, priv->info->field_width); writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(k)); + + /* + * A glitch in the edge detection circuit can cause a spurious + * interrupt. Clear the status flag after setting the ICU_TSSRk + * registers, which is recommended by the hardware manual as a + * countermeasure. + */ + writel_relaxed(BIT(tint_nr), priv->base + priv->info->t_offs + ICU_TSCLR); } static void rzv2h_icu_irq_disable(struct irq_data *d) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e42f1400cea9..813b38aec3e4 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -546,7 +546,7 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid) static struct uuid_entry *uuid_find_empty(struct cache_set *c) { - static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; + static const char zero_uuid[16] = { 0 }; return uuid_find(c, zero_uuid); } diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 44ec9b17cfd3..37b08f26c62f 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2357,9 +2357,8 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - if (bitmap->mddev->bitmap_info.external) - return -ENOENT; - if (!bitmap->storage.sb_page) /* no superblock */ + if (!bitmap->mddev->bitmap_info.external && + !bitmap->storage.sb_page) return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0efc03cea24e..de9bccbe7337 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2200,14 +2200,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio) if (!rdev_set_badblocks(rdev, sect, s, 0)) abort = 1; } - if (abort) { - conf->recovery_disabled = - mddev->recovery_disabled; - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_done_sync(mddev, r1_bio->sectors, 0); - put_buf(r1_bio); + if (abort) return 0; - } + /* Try next page */ sectors -= s; sect += s; @@ -2346,10 +2341,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) int disks = conf->raid_disks * 2; struct bio *wbio; - if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - /* ouch - failed to read all of that. */ - if (!fix_sync_read_error(r1_bio)) + if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) { + /* + * ouch - failed to read all of that. + * No need to fix read error for check/repair + * because all member disks are read. + */ + if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) || + !fix_sync_read_error(r1_bio)) { + conf->recovery_disabled = mddev->recovery_disabled; + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_done_sync(mddev, r1_bio->sectors, 0); + put_buf(r1_bio); return; + } + } if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) process_checks(r1_bio); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 846c5f29486e..ba32bac975b8 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1735,6 +1735,7 @@ retry_discard: * The discard bio returns only first r10bio finishes */ if (first_copy) { + md_account_bio(mddev, &bio); r10_bio->master_bio = bio; set_bit(R10BIO_Discard, &r10_bio->state); first_copy = false; diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 73c07f10f053..379b6e90121d 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9064,6 +9064,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map) msi_vec[i].entry = i; } + pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST; + num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs); if (num_irqs < 0) { np->flags &= ~NIU_FLAGS_MSIX; diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c index 4c1aecd1163c..419f5530f885 100644 --- a/drivers/net/wireless/ath/carl9170/fw.c +++ b/drivers/net/wireless/ath/carl9170/fw.c @@ -15,7 +15,7 @@ #include "fwcmd.h" #include "version.h" -static const u8 otus_magic[4] = { OTUS_MAGIC }; +static const u8 otus_magic[4] __nonstring = { OTUS_MAGIC }; static const void *carl9170_fw_find_desc(struct ar9170 *ar, const u8 descid[4], const unsigned int len, const u8 compatible_revision) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c index 2c6e8ecd93b7..ee99298eebf5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c @@ -1099,7 +1099,8 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld, if (!match) return; - netdetect_info->matches[netdetect_info->n_matches++] = match; + netdetect_info->matches[netdetect_info->n_matches] = match; + netdetect_info->n_matches++; /* We inverted the order of the SSIDs in the scan * request, so invert the index here. @@ -1116,9 +1117,11 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld, for_each_set_bit(j, (unsigned long *)&matches[i].matching_channels[0], - sizeof(matches[i].matching_channels)) - match->channels[match->n_channels++] = + sizeof(matches[i].matching_channels)) { + match->channels[match->n_channels] = netdetect_cfg->channels[j]->center_freq; + match->n_channels++; + } } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index b502ac07483b..eb6ea8acb3cc 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4300,7 +4300,7 @@ static void nvme_scan_work(struct work_struct *work) if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) nvme_queue_scan(ctrl); #ifdef CONFIG_NVME_MULTIPATH - else + else if (ctrl->ana_log_buf) /* Re-read the ANA log page to not miss updates */ queue_work(nvme_wq, &ctrl->ana_work); #endif diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 05eccd96d34a..250f3da67cc9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -1051,6 +1051,13 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head) list_for_each_entry_rcu(ns, &head->list, siblings) { /* + * Ensure that ns path disk node is already added otherwise we + * may get invalid kobj name for target + */ + if (!test_bit(GD_ADDED, &ns->disk->state)) + continue; + + /* * Avoid creating link if it already exists for the given path. * When path ana state transitions from optimized to non- * optimized or vice-versa, the nvme_mpath_set_live() is @@ -1065,13 +1072,6 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head) if (test_and_set_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags)) continue; - /* - * Ensure that ns path disk node is already added otherwise we - * may get invalid kobj name for target - */ - if (!test_bit(GD_ADDED, &ns->disk->state)) - continue; - target = disk_to_dev(ns->disk); /* * Create sysfs link from head gendisk kobject @kobj to the diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 0b0645ac5df4..cef8d77f477b 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -240,7 +240,7 @@ void nvmet_auth_sq_free(struct nvmet_sq *sq) { cancel_delayed_work(&sq->auth_expired_work); #ifdef CONFIG_NVME_TARGET_TCP_TLS - sq->tls_key = 0; + sq->tls_key = NULL; #endif kfree(sq->dhchap_c1); sq->dhchap_c1 = NULL; diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c index 51c27b32248d..7fab7f3d79b7 100644 --- a/drivers/nvme/target/pci-epf.c +++ b/drivers/nvme/target/pci-epf.c @@ -1648,16 +1648,17 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl, { struct nvmet_pci_epf_iod *iod; int ret, n = 0; + u16 head = sq->head; sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db); - while (sq->head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) { + while (head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) { iod = nvmet_pci_epf_alloc_iod(sq); if (!iod) break; /* Get the NVMe command submitted by the host. */ ret = nvmet_pci_epf_transfer(ctrl, &iod->cmd, - sq->pci_addr + sq->head * sq->qes, + sq->pci_addr + head * sq->qes, sq->qes, DMA_FROM_DEVICE); if (ret) { /* Not much we can do... */ @@ -1666,12 +1667,13 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl, } dev_dbg(ctrl->dev, "SQ[%u]: head %u, tail %u, command %s\n", - sq->qid, sq->head, sq->tail, + sq->qid, head, sq->tail, nvmet_pci_epf_iod_name(iod)); - sq->head++; - if (sq->head == sq->depth) - sq->head = 0; + head++; + if (head == sq->depth) + head = 0; + WRITE_ONCE(sq->head, head); n++; queue_work_on(WORK_CPU_UNBOUND, sq->iod_wq, &iod->work); @@ -1761,8 +1763,17 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work) if (!iod) break; - /* Post the IOD completion entry. */ + /* + * Post the IOD completion entry. If the IOD request was + * executed (req->execute() called), the CQE is already + * initialized. However, the IOD may have been failed before + * that, leaving the CQE not properly initialized. So always + * initialize it here. + */ cqe = &iod->cqe; + cqe->sq_head = cpu_to_le16(READ_ONCE(iod->sq->head)); + cqe->sq_id = cpu_to_le16(iod->sq->qid); + cqe->command_id = iod->cmd.common.command_id; cqe->status = cpu_to_le16((iod->status << 1) | cq->phase); dev_dbg(ctrl->dev, @@ -1800,6 +1811,21 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work) NVMET_PCI_EPF_CQ_RETRY_INTERVAL); } +static void nvmet_pci_epf_clear_ctrl_config(struct nvmet_pci_epf_ctrl *ctrl) +{ + struct nvmet_ctrl *tctrl = ctrl->tctrl; + + /* Initialize controller status. */ + tctrl->csts = 0; + ctrl->csts = 0; + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts); + + /* Initialize controller configuration and start polling. */ + tctrl->cc = 0; + ctrl->cc = 0; + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc); +} + static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) { u64 pci_addr, asq, acq; @@ -1865,18 +1891,20 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) return 0; err: - ctrl->csts = 0; + nvmet_pci_epf_clear_ctrl_config(ctrl); return -EINVAL; } -static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) +static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl, + bool shutdown) { int qid; if (!ctrl->enabled) return; - dev_info(ctrl->dev, "Disabling controller\n"); + dev_info(ctrl->dev, "%s controller\n", + shutdown ? "Shutting down" : "Disabling"); ctrl->enabled = false; cancel_delayed_work_sync(&ctrl->poll_sqs); @@ -1893,6 +1921,11 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) nvmet_pci_epf_delete_cq(ctrl->tctrl, 0); ctrl->csts &= ~NVME_CSTS_RDY; + if (shutdown) { + ctrl->csts |= NVME_CSTS_SHST_CMPLT; + ctrl->cc &= ~NVME_CC_ENABLE; + nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc); + } } static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) @@ -1919,12 +1952,10 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) } if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) - nvmet_pci_epf_disable_ctrl(ctrl); + nvmet_pci_epf_disable_ctrl(ctrl, false); - if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) { - nvmet_pci_epf_disable_ctrl(ctrl); - ctrl->csts |= NVME_CSTS_SHST_CMPLT; - } + if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) + nvmet_pci_epf_disable_ctrl(ctrl, true); if (!nvmet_cc_shn(new_cc) && nvmet_cc_shn(old_cc)) ctrl->csts &= ~NVME_CSTS_SHST_CMPLT; @@ -1963,16 +1994,10 @@ static void nvmet_pci_epf_init_bar(struct nvmet_pci_epf_ctrl *ctrl) /* Clear Controller Memory Buffer Supported (CMBS). */ ctrl->cap &= ~(0x1ULL << 57); - /* Controller configuration. */ - ctrl->cc = tctrl->cc & (~NVME_CC_ENABLE); - - /* Controller status. */ - ctrl->csts = ctrl->tctrl->csts; - nvmet_pci_epf_bar_write64(ctrl, NVME_REG_CAP, ctrl->cap); nvmet_pci_epf_bar_write32(ctrl, NVME_REG_VS, tctrl->subsys->ver); - nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts); - nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc); + + nvmet_pci_epf_clear_ctrl_config(ctrl); } static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf, @@ -2070,14 +2095,22 @@ out_mempool_exit: static void nvmet_pci_epf_start_ctrl(struct nvmet_pci_epf_ctrl *ctrl) { + + dev_info(ctrl->dev, "PCI link up\n"); + ctrl->link_up = true; + schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL); } static void nvmet_pci_epf_stop_ctrl(struct nvmet_pci_epf_ctrl *ctrl) { + dev_info(ctrl->dev, "PCI link down\n"); + ctrl->link_up = false; + cancel_delayed_work_sync(&ctrl->poll_cc); - nvmet_pci_epf_disable_ctrl(ctrl); + nvmet_pci_epf_disable_ctrl(ctrl, false); + nvmet_pci_epf_clear_ctrl_config(ctrl); } static void nvmet_pci_epf_destroy_ctrl(struct nvmet_pci_epf_ctrl *ctrl) @@ -2300,10 +2333,8 @@ static int nvmet_pci_epf_epc_init(struct pci_epf *epf) if (ret) goto out_clear_bar; - if (!epc_features->linkup_notifier) { - ctrl->link_up = true; + if (!epc_features->linkup_notifier) nvmet_pci_epf_start_ctrl(&nvme_epf->ctrl); - } return 0; @@ -2319,7 +2350,6 @@ static void nvmet_pci_epf_epc_deinit(struct pci_epf *epf) struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; - ctrl->link_up = false; nvmet_pci_epf_destroy_ctrl(ctrl); nvmet_pci_epf_deinit_dma(nvme_epf); @@ -2331,7 +2361,6 @@ static int nvmet_pci_epf_link_up(struct pci_epf *epf) struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; - ctrl->link_up = true; nvmet_pci_epf_start_ctrl(ctrl); return 0; @@ -2342,7 +2371,6 @@ static int nvmet_pci_epf_link_down(struct pci_epf *epf) struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf); struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl; - ctrl->link_up = false; nvmet_pci_epf_stop_ctrl(ctrl); return 0; diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6569ba3577fe..8b8848788618 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -615,6 +615,9 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc) void __iomem *addr = pci_msix_desc_addr(desc); desc->pci.msi_attrib.can_mask = 1; + /* Workaround for SUN NIU insanity, which requires write before read */ + if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST) + writel(0, addr + PCI_MSIX_ENTRY_DATA); desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 4d7c9f64ea24..e77d5b53c0ce 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5429,8 +5429,6 @@ static bool pci_bus_resettable(struct pci_bus *bus) return false; list_for_each_entry(dev, &bus->devices, bus_list) { - if (!pci_reset_supported(dev)) - return false; if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; @@ -5507,8 +5505,6 @@ static bool pci_slot_resettable(struct pci_slot *slot) list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - if (!pci_reset_supported(dev)) - return false; if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index edb058c19c9c..439dd0bf8644 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -33,7 +33,7 @@ struct power_supply_attr { [POWER_SUPPLY_PROP_ ## _name] = \ { \ .prop_name = #_name, \ - .attr_name = #_name "\0", \ + .attr_name = #_name, \ .text_values = _text, \ .text_values_len = _len, \ } diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 3fcb1ad3b070..1d7901a8f0e4 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc, char *desc = NULL; u16 event; + if (!(mrioc->logging_level & MPI3_DEBUG_EVENT)) + return; + event = event_reply->event; switch (event) { @@ -451,6 +454,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc) return 0; } + atomic_set(&mrioc->admin_pend_isr, 0); reply_desc = (struct mpi3_default_reply_descriptor *)mrioc->admin_reply_base + admin_reply_ci; @@ -565,7 +569,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc, WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci)); mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma, reply_qidx); - atomic_dec(&op_reply_q->pend_ios); + if (reply_dma) mpi3mr_repost_reply_buf(mrioc, reply_dma); num_op_reply++; @@ -2925,6 +2929,7 @@ static int mpi3mr_setup_admin_qpair(struct mpi3mr_ioc *mrioc) mrioc->admin_reply_ci = 0; mrioc->admin_reply_ephase = 1; atomic_set(&mrioc->admin_reply_q_in_use, 0); + atomic_set(&mrioc->admin_pend_isr, 0); if (!mrioc->admin_req_base) { mrioc->admin_req_base = dma_alloc_coherent(&mrioc->pdev->dev, @@ -4653,6 +4658,7 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc) if (mrioc->admin_reply_base) memset(mrioc->admin_reply_base, 0, mrioc->admin_reply_q_sz); atomic_set(&mrioc->admin_reply_q_in_use, 0); + atomic_set(&mrioc->admin_pend_isr, 0); if (mrioc->init_cmds.reply) { memset(mrioc->init_cmds.reply, 0, sizeof(*mrioc->init_cmds.reply)); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0d29470e86b0..1b43013d72c0 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1253,8 +1253,12 @@ EXPORT_SYMBOL_GPL(scsi_alloc_request); */ static void scsi_cleanup_rq(struct request *rq) { + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); + + cmd->flags = 0; + if (rq->rq_flags & RQF_DONTPREP) { - scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq)); + scsi_mq_uninit_cmd(cmd); rq->rq_flags &= ~RQF_DONTPREP; } } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 832d6e9009eb..c93d80a4d734 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1695,9 +1695,12 @@ static int spi_imx_transfer_one(struct spi_controller *controller, struct spi_device *spi, struct spi_transfer *transfer) { + int ret; struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller); - spi_imx_setupxfer(spi, transfer); + ret = spi_imx_setupxfer(spi, transfer); + if (ret < 0) + return ret; transfer->effective_speed_hz = spi_imx->spi_bus_clk; /* flush rxfifo before transfer */ diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index fcbe864c9b7d..f89826d7dc49 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -462,6 +462,7 @@ static int sun4i_spi_probe(struct platform_device *pdev) sspi->host = host; host->max_speed_hz = 100 * 1000 * 1000; host->min_speed_hz = 3 * 1000; + host->use_gpio_descriptors = true; host->set_cs = sun4i_spi_set_cs; host->transfer_one = sun4i_spi_transfer_one; host->num_chipselect = 4; diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c index 08e49a876894..64e1b2f8a000 100644 --- a/drivers/spi/spi-tegra210-quad.c +++ b/drivers/spi/spi-tegra210-quad.c @@ -1117,9 +1117,9 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi, (&tqspi->xfer_completion, QSPI_DMA_TIMEOUT); - if (WARN_ON(ret == 0)) { - dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n", - ret); + if (WARN_ON_ONCE(ret == 0)) { + dev_err_ratelimited(tqspi->dev, + "QSPI Transfer failed with timeout\n"); if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_TX)) dmaengine_terminate_all diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 1244ef3aa86c..620ba6e0ab07 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4263,8 +4263,8 @@ int iscsit_close_connection( spin_unlock(&iscsit_global->ts_bitmap_lock); iscsit_stop_timers_for_cmds(conn); - iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + iscsit_stop_nopin_response_timer(conn); if (conn->conn_transport->iscsit_wait_conn) conn->conn_transport->iscsit_wait_conn(conn); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index a55aaa8cef42..2097aae39946 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -485,7 +485,7 @@ static const struct pci_device_id proc_thermal_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) }, { PCI_DEVICE_DATA(INTEL, LNLM_THERMAL, PROC_THERMAL_FEATURE_MSI_SUPPORT | - PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | + PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) }, { PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR | @@ -495,8 +495,9 @@ static const struct pci_device_id proc_thermal_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) }, { PCI_DEVICE_DATA(INTEL, PTL_THERMAL, PROC_THERMAL_FEATURE_RAPL | - PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_MSI_SUPPORT | - PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) }, + PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS | + PROC_THERMAL_FEATURE_MSI_SUPPORT | PROC_THERMAL_FEATURE_WT_HINT | + PROC_THERMAL_FEATURE_POWER_FLOOR) }, { }, }; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c index dad63f2d5f90..3a028b78d9af 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c @@ -166,15 +166,18 @@ static const struct mmio_reg adl_dvfs_mmio_regs[] = { { 0, 0x5A40, 1, 0x1, 0}, /* rfi_disable */ }; +static const struct mapping_table *dlvr_mapping; +static const struct mmio_reg *dlvr_mmio_regs_table; + #define RFIM_SHOW(suffix, table)\ static ssize_t suffix##_show(struct device *dev,\ struct device_attribute *attr,\ char *buf)\ {\ - const struct mapping_table *mapping = NULL;\ + const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\ + const struct mapping_table *mapping = dlvr_mapping;\ struct proc_thermal_device *proc_priv;\ struct pci_dev *pdev = to_pci_dev(dev);\ - const struct mmio_reg *mmio_regs;\ const char **match_strs;\ int ret, err;\ u32 reg_val;\ @@ -186,12 +189,6 @@ static ssize_t suffix##_show(struct device *dev,\ mmio_regs = adl_dvfs_mmio_regs;\ } else if (table == 2) { \ match_strs = (const char **)dlvr_strings;\ - if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\ - mmio_regs = lnl_dlvr_mmio_regs;\ - mapping = lnl_dlvr_mapping;\ - } else {\ - mmio_regs = dlvr_mmio_regs;\ - } \ } else {\ match_strs = (const char **)fivr_strings;\ mmio_regs = tgl_fivr_mmio_regs;\ @@ -214,12 +211,12 @@ static ssize_t suffix##_store(struct device *dev,\ struct device_attribute *attr,\ const char *buf, size_t count)\ {\ - const struct mapping_table *mapping = NULL;\ + const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\ + const struct mapping_table *mapping = dlvr_mapping;\ struct proc_thermal_device *proc_priv;\ struct pci_dev *pdev = to_pci_dev(dev);\ unsigned int input;\ const char **match_strs;\ - const struct mmio_reg *mmio_regs;\ int ret, err;\ u32 reg_val;\ u32 mask;\ @@ -230,12 +227,6 @@ static ssize_t suffix##_store(struct device *dev,\ mmio_regs = adl_dvfs_mmio_regs;\ } else if (table == 2) { \ match_strs = (const char **)dlvr_strings;\ - if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\ - mmio_regs = lnl_dlvr_mmio_regs;\ - mapping = lnl_dlvr_mapping;\ - } else {\ - mmio_regs = dlvr_mmio_regs;\ - } \ } else {\ match_strs = (const char **)fivr_strings;\ mmio_regs = tgl_fivr_mmio_regs;\ @@ -448,6 +439,16 @@ int proc_thermal_rfim_add(struct pci_dev *pdev, struct proc_thermal_device *proc } if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_DLVR) { + switch (pdev->device) { + case PCI_DEVICE_ID_INTEL_LNLM_THERMAL: + case PCI_DEVICE_ID_INTEL_PTL_THERMAL: + dlvr_mmio_regs_table = lnl_dlvr_mmio_regs; + dlvr_mapping = lnl_dlvr_mapping; + break; + default: + dlvr_mmio_regs_table = dlvr_mmio_regs; + break; + } ret = sysfs_create_group(&pdev->dev.kobj, &dlvr_attribute_group); if (ret) return ret; diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 240ce135bbfb..f1294c29f484 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -677,13 +677,6 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) unsigned long flags; int err; - if (!ufshcd_cmd_inflight(lrbp->cmd)) { - dev_err(hba->dev, - "%s: skip abort. cmd at tag %d already completed.\n", - __func__, tag); - return FAILED; - } - /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n", @@ -692,6 +685,11 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) } hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); + if (!hwq) { + dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n", + __func__, tag); + return FAILED; + } if (ufshcd_mcq_sqe_search(hba, hwq, tag)) { /* diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 44156041d88f..5cb6132b8147 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -278,6 +278,7 @@ static const struct ufs_dev_quirk ufs_fixups[] = { .model = UFS_ANY_MODEL, .quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM | UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE | + UFS_DEVICE_QUIRK_PA_HIBER8TIME | UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS }, { .wmanufacturerid = UFS_VENDOR_SKHYNIX, .model = UFS_ANY_MODEL, @@ -5677,6 +5678,8 @@ static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba, continue; hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); + if (!hwq) + continue; if (force_compl) { ufshcd_mcq_compl_all_cqes_lock(hba, hwq); @@ -8470,6 +8473,31 @@ out: return ret; } +/** + * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME. + * @hba: per-adapter instance + * + * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter + * to ensure proper hibernation timing. This function retrieves the current + * PA_HIBERN8TIME value and increments it by 100us. + */ +static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba) +{ + u32 pa_h8time; + int ret; + + ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time); + if (ret) { + dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret); + return; + } + + /* Increment by 1 to increase hibernation time by 100 µs */ + ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1); + if (ret) + dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret); +} + static void ufshcd_tune_unipro_params(struct ufs_hba *hba) { ufshcd_vops_apply_dev_quirks(hba); @@ -8480,6 +8508,9 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba) if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE) ufshcd_quirk_tune_host_pa_tactivate(hba); + + if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME) + ufshcd_quirk_override_pa_h8time(hba); } static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba) diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 1b37449fbffc..c0761ccc1381 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -33,6 +33,10 @@ ((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT) #define MCQ_QCFG_SIZE 0x40 +/* De-emphasis for gear-5 */ +#define DEEMPHASIS_3_5_dB 0x04 +#define NO_DEEMPHASIS 0x0 + enum { TSTBUS_UAWM, TSTBUS_UARM, @@ -795,6 +799,23 @@ static int ufs_qcom_icc_update_bw(struct ufs_qcom_host *host) return ufs_qcom_icc_set_bw(host, bw_table.mem_bw, bw_table.cfg_bw); } +static void ufs_qcom_set_tx_hs_equalizer(struct ufs_hba *hba, u32 gear, u32 tx_lanes) +{ + u32 equalizer_val; + int ret, i; + + /* Determine the equalizer value based on the gear */ + equalizer_val = (gear == 5) ? DEEMPHASIS_3_5_dB : NO_DEEMPHASIS; + + for (i = 0; i < tx_lanes; i++) { + ret = ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(TX_HS_EQUALIZER, i), + equalizer_val); + if (ret) + dev_err(hba->dev, "%s: failed equalizer lane %d\n", + __func__, i); + } +} + static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, enum ufs_notify_change_status status, const struct ufs_pa_layer_attr *dev_max_params, @@ -846,6 +867,11 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, dev_req_params->gear_tx, PA_INITIAL_ADAPT); } + + if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING) + ufs_qcom_set_tx_hs_equalizer(hba, + dev_req_params->gear_tx, dev_req_params->lane_tx); + break; case POST_CHANGE: if (ufs_qcom_cfg_timers(hba, false)) { @@ -893,6 +919,16 @@ static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba) (pa_vs_config_reg1 | (1 << 12))); } +static void ufs_qcom_override_pa_tx_hsg1_sync_len(struct ufs_hba *hba) +{ + int err; + + err = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TX_HSG1_SYNC_LENGTH), + PA_TX_HSG1_SYNC_LENGTH_VAL); + if (err) + dev_err(hba->dev, "Failed (%d) set PA_TX_HSG1_SYNC_LENGTH\n", err); +} + static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba) { int err = 0; @@ -900,6 +936,9 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba) if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME) err = ufs_qcom_quirk_host_pa_saveconfigtime(hba); + if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH) + ufs_qcom_override_pa_tx_hsg1_sync_len(hba); + return err; } @@ -914,6 +953,10 @@ static struct ufs_dev_quirk ufs_qcom_dev_fixups[] = { { .wmanufacturerid = UFS_VENDOR_WDC, .model = UFS_ANY_MODEL, .quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE }, + { .wmanufacturerid = UFS_VENDOR_SAMSUNG, + .model = UFS_ANY_MODEL, + .quirk = UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH | + UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING }, {} }; diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index d0e6ec9128e7..05d4cb569c50 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -122,8 +122,11 @@ enum { TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN) /* QUniPro Vendor specific attributes */ +#define PA_TX_HSG1_SYNC_LENGTH 0x1552 #define PA_VS_CONFIG_REG1 0x9000 #define DME_VS_CORE_CLK_CTRL 0xD002 +#define TX_HS_EQUALIZER 0x0037 + /* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */ #define CLK_1US_CYCLES_MASK_V4 GENMASK(27, 16) #define CLK_1US_CYCLES_MASK GENMASK(7, 0) @@ -141,6 +144,21 @@ enum { #define UNIPRO_CORE_CLK_FREQ_201_5_MHZ 202 #define UNIPRO_CORE_CLK_FREQ_403_MHZ 403 +/* TX_HSG1_SYNC_LENGTH attr value */ +#define PA_TX_HSG1_SYNC_LENGTH_VAL 0x4A + +/* + * Some ufs device vendors need a different TSync length. + * Enable this quirk to give an additional TX_HS_SYNC_LENGTH. + */ +#define UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH BIT(16) + +/* + * Some ufs device vendors need a different Deemphasis setting. + * Enable this quirk to tune TX Deemphasis parameters. + */ +#define UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING BIT(17) + /* ICE allocator type to share AES engines among TX stream and RX stream */ #define ICE_ALLOCATOR_TYPE 2 diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 14437396d721..8f02f236b5b4 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1815,7 +1815,7 @@ int vfio_config_init(struct vfio_pci_core_device *vdev) } if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx || - vdev->pdev->irq == IRQ_NOTCONNECTED) + !vdev->pdev->irq || vdev->pdev->irq == IRQ_NOTCONNECTED) vconfig[PCI_INTERRUPT_PIN] = 0; ret = vfio_cap_init(vdev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index f6f5a7ac7894..26bcf3a7f70c 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -627,6 +627,9 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) int ret; llnode = llist_del_all(&svq->completion_list); + + mutex_lock(&svq->vq.mutex); + llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) { se_cmd = &cmd->tvc_se_cmd; @@ -660,6 +663,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) vhost_scsi_release_cmd_res(se_cmd); } + mutex_unlock(&svq->vq.mutex); + if (signal) vhost_signal(&svq->vs->dev, &svq->vq); } @@ -994,39 +999,66 @@ static void vhost_scsi_target_queue_cmd(struct vhost_scsi_nexus *nexus, static void vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq, - int head, unsigned int out, u8 status) + struct vhost_scsi_ctx *vc, u8 status) { - struct virtio_scsi_cmd_resp __user *resp; struct virtio_scsi_cmd_resp rsp; + struct iov_iter iov_iter; int ret; memset(&rsp, 0, sizeof(rsp)); rsp.status = status; - resp = vq->iov[out].iov_base; - ret = __copy_to_user(resp, &rsp, sizeof(rsp)); - if (!ret) - vhost_add_used_and_signal(&vs->dev, vq, head, 0); + + iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in, + sizeof(rsp)); + + ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter); + + if (likely(ret == sizeof(rsp))) + vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); else pr_err("Faulted on virtio_scsi_cmd_resp\n"); } +#define TYPE_IO_CMD 0 +#define TYPE_CTRL_TMF 1 +#define TYPE_CTRL_AN 2 + static void vhost_scsi_send_bad_target(struct vhost_scsi *vs, struct vhost_virtqueue *vq, - int head, unsigned out) + struct vhost_scsi_ctx *vc, int type) { - struct virtio_scsi_cmd_resp __user *resp; - struct virtio_scsi_cmd_resp rsp; + union { + struct virtio_scsi_cmd_resp cmd; + struct virtio_scsi_ctrl_tmf_resp tmf; + struct virtio_scsi_ctrl_an_resp an; + } rsp; + struct iov_iter iov_iter; + size_t rsp_size; int ret; memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_BAD_TARGET; - resp = vq->iov[out].iov_base; - ret = __copy_to_user(resp, &rsp, sizeof(rsp)); - if (!ret) - vhost_add_used_and_signal(&vs->dev, vq, head, 0); + + if (type == TYPE_IO_CMD) { + rsp_size = sizeof(struct virtio_scsi_cmd_resp); + rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET; + } else if (type == TYPE_CTRL_TMF) { + rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp); + rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET; + } else { + rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp); + rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET; + } + + iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in, + rsp_size); + + ret = copy_to_iter(&rsp, rsp_size, &iov_iter); + + if (likely(ret == rsp_size)) + vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); else - pr_err("Faulted on virtio_scsi_cmd_resp\n"); + pr_err("Faulted on virtio scsi type=%d\n", type); } static int @@ -1390,9 +1422,9 @@ err: if (ret == -ENXIO) break; else if (ret == -EIO) - vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out); + vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD); else if (ret == -ENOMEM) - vhost_scsi_send_status(vs, vq, vc.head, vc.out, + vhost_scsi_send_status(vs, vq, &vc, SAM_STAT_TASK_SET_FULL); } while (likely(!vhost_exceeds_weight(vq, ++c, 0))); out: @@ -1432,8 +1464,11 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work) else resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; + mutex_lock(&tmf->svq->vq.mutex); vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs, tmf->vq_desc, &tmf->resp_iov, resp_code); + mutex_unlock(&tmf->svq->vq.mutex); + vhost_scsi_release_tmf_res(tmf); } @@ -1623,7 +1658,10 @@ err: if (ret == -ENXIO) break; else if (ret == -EIO) - vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out); + vhost_scsi_send_bad_target(vs, vq, &vc, + v_req.type == VIRTIO_SCSI_T_TMF ? + TYPE_CTRL_TMF : + TYPE_CTRL_AN); } while (likely(!vhost_exceeds_weight(vq, ++c, 0))); out: mutex_unlock(&vq->mutex); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 150753c3b578..95d5d7993e5b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -407,6 +407,12 @@ static void virtio_dev_shutdown(struct device *_d) if (!drv) return; + /* If the driver has its own shutdown method, use that. */ + if (drv->shutdown) { + drv->shutdown(dev); + return; + } + /* * Some devices get wedged if you kick them after they are * reset. Mark all vqs as broken to make sure we don't. diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 5eaade757860..d50fe030d825 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -247,7 +247,7 @@ virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev) sg_init_one(&data_sg, get_data, sizeof(*get_data)); sg_init_one(&result_sg, result, sizeof(*result)); cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET); - cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); cmd.data_sg = &data_sg; cmd.result_sg = &result_sg; ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); @@ -305,7 +305,7 @@ static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev) sg_init_one(&result_sg, data, sizeof(*data)); cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY); - cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); cmd.result_sg = &result_sg; ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index fdd2d2b07b5a..b784aab66867 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2650,7 +2650,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) - vq->event_triggered = false; + data_race(vq->event_triggered = false); return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) : virtqueue_enable_cb_delayed_split(_vq); diff --git a/fs/Kconfig b/fs/Kconfig index c718b2e2de0e..5b4847bd2fbb 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -368,6 +368,7 @@ config GRACE_PERIOD config LOCKD tristate depends on FILE_LOCKING + select CRC32 select GRACE_PERIOD config LOCKD_V4 diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 5cb0fc384ac0..75f7408da173 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -788,6 +788,8 @@ struct bch_fs { unsigned long errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)]; u64 btrees_lost_data; } sb; + DARRAY(enum bcachefs_metadata_version) + incompat_versions_requested; #ifdef CONFIG_UNICODE struct unicode_map *cf_encoding; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 55fbeeb8eaaa..44b5fe430370 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1221,7 +1221,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, ret = bch2_disk_reservation_get(c, &as->disk_res, (nr_nodes[0] + nr_nodes[1]) * btree_sectors(c), - c->opts.metadata_replicas, + READ_ONCE(c->opts.metadata_replicas), disk_res_flags); if (ret) goto err; diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index fea61e60a9ee..4ef261e8db4f 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -37,7 +37,8 @@ void bch2_dev_usage_read_fast(struct bch_dev *ca, struct bch_dev_usage *usage) void bch2_dev_usage_full_read_fast(struct bch_dev *ca, struct bch_dev_usage_full *usage) { memset(usage, 0, sizeof(*usage)); - acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage, dev_usage_u64s()); + acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage, + sizeof(struct bch_dev_usage_full) / sizeof(u64)); } static u64 reserve_factor(u64 r) diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 1c38b165f48b..8d75b27a1418 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -242,11 +242,6 @@ static inline u64 dev_buckets_available(struct bch_dev *ca, /* Filesystem usage: */ -static inline unsigned dev_usage_u64s(void) -{ - return sizeof(struct bch_dev_usage) / sizeof(u64); -} - struct bch_fs_usage_short bch2_fs_usage_read_short(struct bch_fs *); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index c8696f01eb14..a615e4852ded 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -287,7 +287,7 @@ x(EIO, mark_stripe) \ x(EIO, stripe_reconstruct) \ x(EIO, key_type_error) \ - x(EIO, extent_poisened) \ + x(EIO, extent_poisoned) \ x(EIO, missing_indirect_extent) \ x(EIO, invalidate_stripe_to_dev) \ x(EIO, no_encryption_key) \ diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index ae7c7a177e10..dca2b8425cc0 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -139,7 +139,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k, struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); if (bch2_bkey_extent_ptrs_flags(ptrs) & BIT_ULL(BCH_EXTENT_FLAG_poisoned)) - return -BCH_ERR_extent_poisened; + return -BCH_ERR_extent_poisoned; rcu_read_lock(); const union bch_extent_entry *entry; diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index c1553e44e049..14886e1d4d6d 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -69,7 +69,7 @@ static int bch2_inode_flags_set(struct btree_trans *trans, if (ret < 0) return ret; - ret = bch2_request_incompat_feature(c,bcachefs_metadata_version_casefolding); + ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding); if (ret) return ret; diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 18308f3d64a1..7b25cedd3e40 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -321,6 +321,31 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode) inode->bi_subvol == BCACHEFS_ROOT_SUBVOL) return false; + /* + * Subvolume roots are special: older versions of subvolume roots may be + * disconnected, it's only the newest version that matters. + * + * We only keep a single dirent pointing to a subvolume root, i.e. + * older versions of snapshots will not have a different dirent pointing + * to the same subvolume root. + * + * This is because dirents that point to subvolumes are only visible in + * the parent subvolume - versioning is not needed - and keeping them + * around would break fsck, because when we're crossing subvolumes we + * don't have a consistent snapshot ID to do check the inode <-> dirent + * relationships. + * + * Thus, a subvolume root that's been renamed after a snapshot will have + * a disconnected older version - that's expected. + * + * Note that taking a snapshot always updates the root inode (to update + * the dirent backpointer), so a subvolume root inode with + * BCH_INODE_has_child_snapshot is never visible. + */ + if (inode->bi_subvol && + (inode->bi_flags & BCH_INODE_has_child_snapshot)) + return false; + return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked); } @@ -1007,6 +1032,23 @@ static int check_inode_dirent_inode(struct btree_trans *trans, if (ret && !bch2_err_matches(ret, ENOENT)) return ret; + if ((ret || dirent_points_to_inode_nowarn(d, inode)) && + inode->bi_subvol && + (inode->bi_flags & BCH_INODE_has_child_snapshot)) { + /* Older version of a renamed subvolume root: we won't have a + * correct dirent for it. That's expected, see + * inode_should_reattach(). + * + * We don't clear the backpointer field when doing the rename + * because there might be arbitrarily many versions in older + * snapshots. + */ + inode->bi_dir = 0; + inode->bi_dir_offset = 0; + *write_inode = true; + goto out; + } + if (fsck_err_on(ret, trans, inode_points_to_missing_dirent, "inode points to missing dirent\n%s", @@ -1027,7 +1069,7 @@ static int check_inode_dirent_inode(struct btree_trans *trans, inode->bi_dir_offset = 0; *write_inode = true; } - +out: ret = 0; fsck_err: bch2_trans_iter_exit(trans, &dirent_iter); diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index fd627c8d1053..def4a26a3b45 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -487,6 +487,8 @@ static void bch2_rbio_retry(struct work_struct *work) .inum = rbio->read_pos.inode, }; struct bch_io_failures failed = { .nr = 0 }; + int orig_error = rbio->ret; + struct btree_trans *trans = bch2_trans_get(c); trace_io_read_retry(&rbio->bio); @@ -519,7 +521,9 @@ static void bch2_rbio_retry(struct work_struct *work) if (ret) { rbio->ret = ret; rbio->bio.bi_status = BLK_STS_IOERR; - } else { + } else if (orig_error != -BCH_ERR_data_read_retry_csum_err_maybe_userspace && + orig_error != -BCH_ERR_data_read_ptr_stale_race && + !failed.nr) { struct printbuf buf = PRINTBUF; lockrestart_do(trans, @@ -1345,14 +1349,16 @@ err: bch2_trans_iter_exit(trans, &iter); - if (ret) { - struct printbuf buf = PRINTBUF; - lockrestart_do(trans, - bch2_inum_offset_err_msg_trans(trans, &buf, inum, - bvec_iter.bi_sector << 9)); - prt_printf(&buf, "read error: %s", bch2_err_str(ret)); - bch_err_ratelimited(c, "%s", buf.buf); - printbuf_exit(&buf); + if (unlikely(ret)) { + if (ret != -BCH_ERR_extent_poisoned) { + struct printbuf buf = PRINTBUF; + lockrestart_do(trans, + bch2_inum_offset_err_msg_trans(trans, &buf, inum, + bvec_iter.bi_sector << 9)); + prt_printf(&buf, "data read error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } rbio->bio.bi_status = BLK_STS_IOERR; rbio->ret = ret; diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index d2b07f602da9..606d684e6f23 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -1125,7 +1125,10 @@ int bch2_fs_initialize(struct bch_fs *c) * journal_res_get() will crash if called before this has * set up the journal.pin FIFO and journal.cur pointer: */ - bch2_fs_journal_start(&c->journal, 1); + ret = bch2_fs_journal_start(&c->journal, 1); + if (ret) + goto err; + set_bit(BCH_FS_accounting_replay_done, &c->flags); bch2_journal_set_replay_done(&c->journal); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 5d43e3504386..dc53d25c7cbb 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -290,8 +290,8 @@ enum bch_fsck_flags { x(btree_node_bkey_bad_u64s, 260, 0) \ x(btree_node_topology_empty_interior_node, 261, 0) \ x(btree_ptr_v2_min_key_bad, 262, 0) \ - x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ - x(snapshot_node_missing, 264, 0) \ + x(btree_root_unreadable_and_scan_found_nothing, 263, FSCK_AUTOFIX) \ + x(snapshot_node_missing, 264, FSCK_AUTOFIX) \ x(dup_backpointer_to_bad_csum_extent, 265, 0) \ x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \ x(sb_clean_entry_overrun, 267, 0) \ diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index e27422b6d9c6..25b6bce05c3c 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -73,14 +73,30 @@ int bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version v ? 0 : -BCH_ERR_may_not_use_incompat_feature; + mutex_lock(&c->sb_lock); if (!ret) { - mutex_lock(&c->sb_lock); SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb, max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version)); bch2_write_super(c); - mutex_unlock(&c->sb_lock); + } else { + darray_for_each(c->incompat_versions_requested, i) + if (version == *i) + goto out; + + darray_push(&c->incompat_versions_requested, version); + struct printbuf buf = PRINTBUF; + prt_str(&buf, "requested incompat feature "); + bch2_version_to_text(&buf, version); + prt_str(&buf, " currently not enabled"); + prt_printf(&buf, "\n set version_upgrade=incompat to enable"); + + bch_notice(c, "%s", buf.buf); + printbuf_exit(&buf); } +out: + mutex_unlock(&c->sb_lock); + return ret; } diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index b79e80a435e0..e8a17ed1615d 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -589,6 +589,7 @@ static void __bch2_fs_free(struct bch_fs *c) free_percpu(c->online_reserved); } + darray_exit(&c->incompat_versions_requested); darray_exit(&c->btree_roots_extra); free_percpu(c->pcpu); free_percpu(c->usage); @@ -1013,6 +1014,11 @@ static void print_mount_opts(struct bch_fs *c) bch2_opt_to_text(&p, c, c->disk_sb.sb, opt, v, OPT_SHOW_MOUNT_STYLE); } + if (c->sb.version_incompat_allowed != c->sb.version) { + prt_printf(&p, "\n allowing incompatible features above "); + bch2_version_to_text(&p, c->sb.version_incompat_allowed); + } + bch_info(c, "%s", p.buf); printbuf_exit(&p); } @@ -1757,7 +1763,8 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags) up_write(&c->state_lock); return 0; err: - if (ca->mi.state == BCH_MEMBER_STATE_rw && + if (test_bit(BCH_FS_rw, &c->flags) && + ca->mi.state == BCH_MEMBER_STATE_rw && !percpu_ref_is_zero(&ca->io_ref[READ])) __bch2_dev_read_write(c, ca); up_write(&c->state_lock); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 262a707d8990..71b8a825c447 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2104,15 +2104,20 @@ static void btrfs_punch_hole_lock_range(struct inode *inode, * will always return true. * So here we need to do extra page alignment for * filemap_range_has_page(). + * + * And do not decrease page_lockend right now, as it can be 0. */ const u64 page_lockstart = round_up(lockstart, PAGE_SIZE); - const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1; + const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE); while (1) { truncate_pagecache_range(inode, lockstart, lockend); lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); + /* The same page or adjacent pages. */ + if (page_lockend <= page_lockstart) + break; /* * We can't have ordered extents in the range, nor dirty/writeback * pages, because we have locked the inode's VFS lock in exclusive @@ -2124,7 +2129,7 @@ static void btrfs_punch_hole_lock_range(struct inode *inode, * we do, unlock the range and retry. */ if (!filemap_range_has_page(inode->i_mapping, page_lockstart, - page_lockend)) + page_lockend - 1)) break; unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f948f4f6431c..e17bcb034595 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3803,7 +3803,7 @@ out: if (ret) { if (inode) iput(&inode->vfs_inode); - inode = ERR_PTR(ret); + return ERR_PTR(ret); } return &inode->vfs_inode; } diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 11dbd7be6a3b..c0a0b8b063d0 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -204,7 +204,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, btrfs_blocks_per_folio(fs_info, folio); \ \ btrfs_subpage_assert(fs_info, folio, start, len); \ - __start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \ + __start_bit = offset_in_folio(folio, start) >> fs_info->sectorsize_bits; \ __start_bit += blocks_per_folio * btrfs_bitmap_nr_##name; \ __start_bit; \ }) @@ -666,7 +666,7 @@ IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked, btrfs_blocks_per_folio(fs_info, folio); \ const struct btrfs_subpage *subpage = folio_get_private(folio); \ \ - ASSERT(blocks_per_folio < BITS_PER_LONG); \ + ASSERT(blocks_per_folio <= BITS_PER_LONG); \ *dst = bitmap_read(subpage->bitmaps, \ blocks_per_folio * btrfs_bitmap_nr_##name, \ blocks_per_folio); \ diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 43979891f7c8..2b66a6130269 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -2235,7 +2235,7 @@ int btrfs_verify_level_key(struct extent_buffer *eb, btrfs_err(fs_info, "tree level mismatch detected, bytenr=%llu level expected=%u has=%u", eb->start, check->level, found_level); - return -EIO; + return -EUCLEAN; } if (!check->has_first_key) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index fb8b8b29c169..4a3e02b49f29 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1277,7 +1277,7 @@ struct zone_info { static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, struct zone_info *info, unsigned long *active, - struct btrfs_chunk_map *map) + struct btrfs_chunk_map *map, bool new) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; struct btrfs_device *device; @@ -1307,6 +1307,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, return 0; } + ASSERT(!new || btrfs_dev_is_empty_zone(device, info->physical)); + /* This zone will be used for allocation, so mark this zone non-empty. */ btrfs_dev_clear_zone_empty(device, info->physical); @@ -1319,6 +1321,18 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, * to determine the allocation offset within the zone. */ WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size)); + + if (new) { + sector_t capacity; + + capacity = bdev_zone_capacity(device->bdev, info->physical >> SECTOR_SHIFT); + up_read(&dev_replace->rwsem); + info->alloc_offset = 0; + info->capacity = capacity << SECTOR_SHIFT; + + return 0; + } + nofs_flag = memalloc_nofs_save(); ret = btrfs_get_dev_zone(device, info->physical, &zone); memalloc_nofs_restore(nofs_flag); @@ -1588,7 +1602,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } for (i = 0; i < map->num_stripes; i++) { - ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map); + ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map, new); if (ret) goto out; @@ -1659,7 +1673,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) * stripe. */ cache->alloc_offset = cache->zone_capacity; - ret = 0; } out: diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c index bf935e25bdbe..b48525680e73 100644 --- a/fs/cachefiles/key.c +++ b/fs/cachefiles/key.c @@ -8,7 +8,7 @@ #include <linux/slab.h> #include "internal.h" -static const char cachefiles_charmap[64] = +static const char cachefiles_charmap[64] __nonstring = "0123456789" /* 0 - 9 */ "abcdefghijklmnopqrstuvwxyz" /* 10 - 35 */ "ABCDEFGHIJKLMNOPQRSTUVWXYZ" /* 36 - 61 */ @@ -396,6 +396,7 @@ static inline unsigned long dax_folio_put(struct folio *folio) order = folio_order(folio); if (!order) return 0; + folio_reset_order(folio); for (i = 0; i < (1UL << order); i++) { struct dev_pagemap *pgmap = page_pgmap(&folio->page); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 100376863a44..4bc264b854c4 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1996,6 +1996,14 @@ static int ep_try_send_events(struct eventpoll *ep, return res; } +static int ep_schedule_timeout(ktime_t *to) +{ + if (to) + return ktime_after(*to, ktime_get()); + else + return 1; +} + /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. @@ -2103,7 +2111,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, write_unlock_irq(&ep->lock); - if (!eavail) + if (!eavail && ep_schedule_timeout(to)) timed_out = !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); diff --git a/fs/namei.c b/fs/namei.c index 8510ff53f12e..84a0e0b0111c 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1665,27 +1665,20 @@ static struct dentry *lookup_dcache(const struct qstr *name, return dentry; } -/* - * Parent directory has inode locked exclusive. This is one - * and only case when ->lookup() gets called on non in-lookup - * dentries - as the matter of fact, this only gets called - * when directory is guaranteed to have no in-lookup children - * at all. - * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed. - * Will return -EEXIST if name is found and LOOKUP_EXCL was passed. - */ -struct dentry *lookup_one_qstr_excl(const struct qstr *name, - struct dentry *base, - unsigned int flags) +static struct dentry *lookup_one_qstr_excl_raw(const struct qstr *name, + struct dentry *base, + unsigned int flags) { - struct dentry *dentry = lookup_dcache(name, base, flags); + struct dentry *dentry; struct dentry *old; - struct inode *dir = base->d_inode; + struct inode *dir; + dentry = lookup_dcache(name, base, flags); if (dentry) - goto found; + return dentry; /* Don't create child dentry for a dead directory. */ + dir = base->d_inode; if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); @@ -1698,7 +1691,24 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name, dput(dentry); dentry = old; } -found: + return dentry; +} + +/* + * Parent directory has inode locked exclusive. This is one + * and only case when ->lookup() gets called on non in-lookup + * dentries - as the matter of fact, this only gets called + * when directory is guaranteed to have no in-lookup children + * at all. + * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed. + * Will return -EEXIST if name is found and LOOKUP_EXCL was passed. + */ +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, unsigned int flags) +{ + struct dentry *dentry; + + dentry = lookup_one_qstr_excl_raw(name, base, flags); if (IS_ERR(dentry)) return dentry; if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) { @@ -2742,23 +2752,48 @@ static int filename_parentat(int dfd, struct filename *name, /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path) { + struct path parent_path __free(path_put) = {}; struct dentry *d; struct qstr last; int type, error; - error = filename_parentat(dfd, name, 0, path, &last, &type); + error = filename_parentat(dfd, name, 0, &parent_path, &last, &type); if (error) return ERR_PTR(error); - if (unlikely(type != LAST_NORM)) { - path_put(path); + if (unlikely(type != LAST_NORM)) return ERR_PTR(-EINVAL); + inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT); + d = lookup_one_qstr_excl(&last, parent_path.dentry, 0); + if (IS_ERR(d)) { + inode_unlock(parent_path.dentry->d_inode); + return d; } - inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - d = lookup_one_qstr_excl(&last, path->dentry, 0); + path->dentry = no_free_ptr(parent_path.dentry); + path->mnt = no_free_ptr(parent_path.mnt); + return d; +} + +struct dentry *kern_path_locked_negative(const char *name, struct path *path) +{ + struct path parent_path __free(path_put) = {}; + struct filename *filename __free(putname) = getname_kernel(name); + struct dentry *d; + struct qstr last; + int type, error; + + error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type); + if (error) + return ERR_PTR(error); + if (unlikely(type != LAST_NORM)) + return ERR_PTR(-EINVAL); + inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT); + d = lookup_one_qstr_excl_raw(&last, parent_path.dentry, 0); if (IS_ERR(d)) { - inode_unlock(path->dentry->d_inode); - path_put(path); + inode_unlock(parent_path.dentry->d_inode); + return d; } + path->dentry = no_free_ptr(parent_path.dentry); + path->mnt = no_free_ptr(parent_path.mnt); return d; } diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c index 9397ed39b0b4..8f70f8da064b 100644 --- a/fs/netfs/fscache_cache.c +++ b/fs/netfs/fscache_cache.c @@ -372,7 +372,7 @@ void fscache_withdraw_cache(struct fscache_cache *cache) EXPORT_SYMBOL(fscache_withdraw_cache); #ifdef CONFIG_PROC_FS -static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; +static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] __nonstring = "-PAEW"; /* * Generate a list of caches in /proc/fs/fscache/caches diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c index d4d4b3a8b106..3d56fc73435f 100644 --- a/fs/netfs/fscache_cookie.c +++ b/fs/netfs/fscache_cookie.c @@ -29,7 +29,7 @@ static LIST_HEAD(fscache_cookie_lru); static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); -static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] __nonstring = "-LCAIFUWRD"; static unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index d3f76101ad4b..07932ce9246c 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -2,6 +2,7 @@ config NFS_FS tristate "NFS client support" depends on INET && FILE_LOCKING && MULTIUSER + select CRC32 select LOCKD select SUNRPC select NFS_COMMON @@ -196,7 +197,6 @@ config NFS_USE_KERNEL_DNS config NFS_DEBUG bool depends on NFS_FS && SUNRPC_DEBUG - select CRC32 default y config NFS_DISABLE_UDP_SUPPORT diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ec8d32d0e2e9..6655e5f32ec6 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -899,18 +899,11 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } -#ifdef CONFIG_CRC32 static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } -#else -static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) -{ - return 0; -} -#endif static inline bool nfs_current_task_exiting(void) { diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 351616c61df5..f9c291e2165c 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -148,16 +148,12 @@ static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst, memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN); } -#ifdef CONFIG_CRC32 /* * nfs_session_id_hash - calculate the crc32 hash for the session id * @session - pointer to session */ #define nfs_session_id_hash(sess_id) \ (~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data))) -#else -#define nfs_session_id_hash(session) (0) -#endif #else /* defined(CONFIG_NFS_V4_1) */ static inline int nfs4_init_session(struct nfs_client *clp) diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 792d3fed1b45..731a88f6313e 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -4,6 +4,7 @@ config NFSD depends on INET depends on FILE_LOCKING depends on FSNOTIFY + select CRC32 select LOCKD select SUNRPC select EXPORTFS diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2041268b398a..59a693f22452 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5430,7 +5430,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) queued = nfsd4_run_cb(&dp->dl_recall); WARN_ON_ONCE(!queued); if (!queued) - nfs4_put_stid(&dp->dl_stid); + refcount_dec(&dp->dl_stid.sc_count); } /* Called from break_lease() with flc_lock held. */ diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 876152a91f12..5103c2f4d225 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -267,7 +267,6 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1, return true; } -#ifdef CONFIG_CRC32 /** * knfsd_fh_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle @@ -279,12 +278,6 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) { return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size); } -#else -static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) -{ - return 0; -} -#endif /** * fh_clear_pre_post_attrs - Reset pre/post attributes diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index cfcc07905bdf..59f6fdfe560e 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -163,6 +163,8 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); +extern int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file); extern unsigned int smbCalcSize(void *buf); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 4a0b2d220fe8..df976ce6aed9 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -300,7 +300,6 @@ cifs_abort_connection(struct TCP_Server_Info *server) server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; - put_net(cifs_net_ns(server)); } server->sequence_number = 0; server->session_estab = false; @@ -1074,13 +1073,9 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); - if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; - - /* Release netns reference for the socket. */ - put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1128,7 +1123,6 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } - /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); kfree(server->hostname); @@ -1774,8 +1768,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; - - /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->sign = ctx->sign; @@ -1903,7 +1895,6 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); - /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1912,10 +1903,8 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) { + if (tcp_ses->ssocket) sock_release(tcp_ses->ssocket); - put_net(cifs_net_ns(tcp_ses)); - } kfree(tcp_ses); } return ERR_PTR(rc); @@ -3359,24 +3348,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); + struct sock *sk; - rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); + rc = __sock_create(net, sfamily, SOCK_STREAM, + IPPROTO_TCP, &server->ssocket, 1); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - /* - * Grab netns reference for the socket. - * - * This reference will be released in several situations: - * - In the failure path before the cifsd thread is started. - * - In the all place where server->socket is released, it is - * also set to NULL. - * - Ultimately in clean_demultiplex_info(), during the final - * teardown. - */ - get_net(net); + sk = server->ssocket->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3428,7 +3413,6 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); - put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 8407fb108664..9e8f404b9e56 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1007,6 +1007,11 @@ int cifs_open(struct inode *inode, struct file *file) } else { _cifsFileInfo_put(cfile, true, false); } + } else { + /* hard link on the defeered close file */ + rc = cifs_get_hardlink_path(tcon, inode, file); + if (rc) + cifs_close_deferred_file(CIFS_I(inode)); } if (server->oplocks) @@ -2071,6 +2076,29 @@ cifs_move_llist(struct list_head *source, struct list_head *dest) list_move(li, dest); } +int +cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file) +{ + struct cifsFileInfo *open_file = NULL; + struct cifsInodeInfo *cinode = CIFS_I(inode); + int rc = 0; + + spin_lock(&tcon->open_file_lock); + spin_lock(&cinode->open_file_lock); + + list_for_each_entry(open_file, &cinode->openFileList, flist) { + if (file->f_flags == open_file->f_flags) { + rc = -EINVAL; + break; + } + } + + spin_unlock(&cinode->open_file_lock); + spin_unlock(&tcon->open_file_lock); + return rc; +} + void cifs_free_llist(struct list_head *llist) { diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c1f22c129111..83764c230e9d 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -39,8 +39,10 @@ void ksmbd_conn_free(struct ksmbd_conn *conn) xa_destroy(&conn->sessions); kvfree(conn->request_buf); kfree(conn->preauth_info); - if (atomic_dec_and_test(&conn->refcnt)) + if (atomic_dec_and_test(&conn->refcnt)) { + ksmbd_free_transport(conn->transport); kfree(conn); + } } /** diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index f103b1bd0400..81a29857b1e3 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -129,14 +129,6 @@ static void free_opinfo(struct oplock_info *opinfo) kfree(opinfo); } -static inline void opinfo_free_rcu(struct rcu_head *rcu_head) -{ - struct oplock_info *opinfo; - - opinfo = container_of(rcu_head, struct oplock_info, rcu_head); - free_opinfo(opinfo); -} - struct oplock_info *opinfo_get(struct ksmbd_file *fp) { struct oplock_info *opinfo; @@ -157,8 +149,8 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) if (list_empty(&ci->m_op_list)) return NULL; - rcu_read_lock(); - opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info, + down_read(&ci->m_lock); + opinfo = list_first_entry(&ci->m_op_list, struct oplock_info, op_entry); if (opinfo) { if (opinfo->conn == NULL || @@ -171,8 +163,7 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) } } } - - rcu_read_unlock(); + up_read(&ci->m_lock); return opinfo; } @@ -185,7 +176,7 @@ void opinfo_put(struct oplock_info *opinfo) if (!atomic_dec_and_test(&opinfo->refcount)) return; - call_rcu(&opinfo->rcu_head, opinfo_free_rcu); + free_opinfo(opinfo); } static void opinfo_add(struct oplock_info *opinfo) @@ -193,7 +184,7 @@ static void opinfo_add(struct oplock_info *opinfo) struct ksmbd_inode *ci = opinfo->o_fp->f_ci; down_write(&ci->m_lock); - list_add_rcu(&opinfo->op_entry, &ci->m_op_list); + list_add(&opinfo->op_entry, &ci->m_op_list); up_write(&ci->m_lock); } @@ -207,7 +198,7 @@ static void opinfo_del(struct oplock_info *opinfo) write_unlock(&lease_list_lock); } down_write(&ci->m_lock); - list_del_rcu(&opinfo->op_entry); + list_del(&opinfo->op_entry); up_write(&ci->m_lock); } @@ -1347,8 +1338,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, ci = fp->f_ci; op = opinfo_get(fp); - rcu_read_lock(); - list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) { + down_read(&ci->m_lock); + list_for_each_entry(brk_op, &ci->m_op_list, op_entry) { if (brk_op->conn == NULL) continue; @@ -1358,7 +1349,6 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, if (ksmbd_conn_releasing(brk_op->conn)) continue; - rcu_read_unlock(); if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE)))) { @@ -1388,9 +1378,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL); next: opinfo_put(brk_op); - rcu_read_lock(); } - rcu_read_unlock(); + up_read(&ci->m_lock); if (op) opinfo_put(op); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 3f64f0787263..9a56eaadd0dd 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -71,7 +71,6 @@ struct oplock_info { struct list_head lease_entry; wait_queue_head_t oplock_q; /* Other server threads */ wait_queue_head_t oplock_brk; /* oplock breaking wait */ - struct rcu_head rcu_head; }; struct lease_break_info { diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d24d95d15d87..57839f9708bb 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1602,8 +1602,10 @@ static int krb5_authenticate(struct ksmbd_work *work, if (prev_sess_id && prev_sess_id != sess->id) destroy_previous_session(conn, sess->user, prev_sess_id); - if (sess->state == SMB2_SESSION_VALID) + if (sess->state == SMB2_SESSION_VALID) { ksmbd_free_user(sess->user); + sess->user = NULL; + } retval = ksmbd_krb5_authenticate(sess, in_blob, in_len, out_blob, &out_len); diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 3f185ae60dc5..2a3e2b0ce557 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -310,7 +310,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) server_conf.signing = req->signing; server_conf.tcp_port = req->tcp_port; server_conf.ipc_timeout = req->ipc_timeout * HZ; - server_conf.deadtime = req->deadtime * SMB_ECHO_INTERVAL; + if (check_mul_overflow(req->deadtime, SMB_ECHO_INTERVAL, + &server_conf.deadtime)) { + ret = -EINVAL; + goto out; + } server_conf.share_fake_fscaps = req->share_fake_fscaps; ksmbd_init_domain(req->sub_auth); @@ -337,6 +341,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) server_conf.bind_interfaces_only = req->bind_interfaces_only; ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req), req->ifc_list_sz); +out: if (ret) { pr_err("Server configuration error: %s %s %s\n", req->netbios_name, req->server_string, diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 7f38a3c3f5bd..abedf510899a 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -93,17 +93,21 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk) return t; } -static void free_transport(struct tcp_transport *t) +void ksmbd_free_transport(struct ksmbd_transport *kt) { - kernel_sock_shutdown(t->sock, SHUT_RDWR); - sock_release(t->sock); - t->sock = NULL; + struct tcp_transport *t = TCP_TRANS(kt); - ksmbd_conn_free(KSMBD_TRANS(t)->conn); + sock_release(t->sock); kfree(t->iov); kfree(t); } +static void free_transport(struct tcp_transport *t) +{ + kernel_sock_shutdown(t->sock, SHUT_RDWR); + ksmbd_conn_free(KSMBD_TRANS(t)->conn); +} + /** * kvec_array_init() - initialize a IO vector segment * @new: IO vector to be initialized diff --git a/fs/smb/server/transport_tcp.h b/fs/smb/server/transport_tcp.h index 8c9aa624cfe3..1e51675ee1b2 100644 --- a/fs/smb/server/transport_tcp.h +++ b/fs/smb/server/transport_tcp.h @@ -8,6 +8,7 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz); struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name); +void ksmbd_free_transport(struct ksmbd_transport *kt); int ksmbd_tcp_init(void); void ksmbd_tcp_destroy(void); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 8554aa5a1059..391d07da586c 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -479,7 +479,8 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, int err = 0; if (work->conn->connection_type) { - if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE))) { + if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE)) || + S_ISDIR(file_inode(fp->filp)->i_mode)) { pr_err("no right to write(%pD)\n", fp->filp); err = -EACCES; goto out; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 8d1f30dcba7e..1f8fa3468173 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -713,12 +713,8 @@ static bool tree_conn_fd_check(struct ksmbd_tree_connect *tcon, static bool ksmbd_durable_scavenger_alive(void) { - mutex_lock(&durable_scavenger_lock); - if (!durable_scavenger_running) { - mutex_unlock(&durable_scavenger_lock); + if (!durable_scavenger_running) return false; - } - mutex_unlock(&durable_scavenger_lock); if (kthread_should_stop()) return false; @@ -799,9 +795,7 @@ static int ksmbd_durable_scavenger(void *dummy) break; } - mutex_lock(&durable_scavenger_lock); durable_scavenger_running = false; - mutex_unlock(&durable_scavenger_lock); module_put(THIS_MODULE); diff --git a/fs/stat.c b/fs/stat.c index f13308bfdc98..3d9222807214 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -204,12 +204,25 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, STATX_ATTR_DAX); idmap = mnt_idmap(path->mnt); - if (inode->i_op->getattr) - return inode->i_op->getattr(idmap, path, stat, - request_mask, - query_flags); + if (inode->i_op->getattr) { + int ret; + + ret = inode->i_op->getattr(idmap, path, stat, request_mask, + query_flags); + if (ret) + return ret; + } else { + generic_fillattr(idmap, request_mask, inode, stat); + } + + /* + * If this is a block device inode, override the filesystem attributes + * with the block device specific parameters that need to be obtained + * from the bdev backing inode. + */ + if (S_ISBLK(stat->mode)) + bdev_statx(path, stat, request_mask); - generic_fillattr(idmap, request_mask, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); @@ -295,15 +308,6 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat, if (path_mounted(path)) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; - - /* - * If this is a block device inode, override the filesystem - * attributes with the block device specific parameters that need to be - * obtained from the bdev backing inode. - */ - if (S_ISBLK(stat->mode)) - bdev_statx(path, stat, request_mask); - return 0; } diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index 451f6276da49..2fc89704be17 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -66,7 +66,7 @@ ******************************************************************************/ struct acpi_table_header { - char signature[ACPI_NAMESEG_SIZE]; /* ASCII table signature */ + char signature[ACPI_NAMESEG_SIZE] __nonstring; /* ASCII table signature */ u32 length; /* Length of table in bytes, including this header */ u8 revision; /* ACPI Specification minor version number */ u8 checksum; /* To make sum of entire table == 0 */ diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 2bf893eabb4b..bcd54020d6ba 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -585,8 +585,7 @@ static inline bool drm_gem_object_is_shared_for_memory_stats(struct drm_gem_obje */ static inline bool drm_gem_is_imported(const struct drm_gem_object *obj) { - /* The dma-buf's priv field points to the original GEM object. */ - return obj->dma_buf && (obj->dma_buf->priv != obj); + return !!obj->import_attach; } #ifdef CONFIG_LOCKDEP diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 8e7af9a03b41..e721148c95d0 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -249,6 +249,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && + (inode->i_sb->s_iflags & SB_I_CGROUPWB) && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e39c45bc0a97..2b8875a82ff8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -712,23 +712,6 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) (q->limits.features & BLK_FEAT_ZONED); } -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return disk->nr_zones; -} -bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return 0; -} -static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) -{ - return false; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { if (!blk_queue_is_zoned(disk->queue)) @@ -736,11 +719,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return disk_nr_zones(bdev->bd_disk); -} - static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_open_zones; @@ -847,6 +825,51 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb) (sb->s_blocksize_bits - SECTOR_SHIFT); } +#ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int disk_nr_zones(struct gendisk *disk) +{ + return disk->nr_zones; +} +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); + +/** + * disk_zone_capacity - returns the zone capacity of zone containing @sector + * @disk: disk to work with + * @sector: sector number within the querying zone + * + * Returns the zone capacity of a zone containing @sector. @sector can be any + * sector in the zone. + */ +static inline unsigned int disk_zone_capacity(struct gendisk *disk, + sector_t sector) +{ + sector_t zone_sectors = disk->queue->limits.chunk_sectors; + + if (sector + zone_sectors >= get_capacity(disk)) + return disk->last_zone_capacity; + return disk->zone_capacity; +} +static inline unsigned int bdev_zone_capacity(struct block_device *bdev, + sector_t pos) +{ + return disk_zone_capacity(bdev->bd_disk, pos); +} +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int disk_nr_zones(struct gendisk *disk) +{ + return 0; +} +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +static inline unsigned int bdev_nr_zones(struct block_device *bdev) +{ + return disk_nr_zones(bdev->bd_disk); +} + int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); @@ -1685,7 +1708,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx(struct path *, struct kstat *, u32); +void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1703,8 +1726,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx(struct path *path, struct kstat *stat, - u32 request_mask) +static inline void bdev_statx(const struct path *path, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index bf2bf40d7b18..8d5ac16a9b17 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -102,11 +102,11 @@ do { \ l = (local_lock_t *)this_cpu_ptr(lock); \ tl = (local_trylock_t *)l; \ _Generic((lock), \ - local_trylock_t *: ({ \ + __percpu local_trylock_t *: ({ \ lockdep_assert(tl->acquired == 0); \ WRITE_ONCE(tl->acquired, 1); \ }), \ - default:(void)0); \ + __percpu local_lock_t *: (void)0); \ local_lock_acquire(l); \ } while (0) @@ -171,11 +171,11 @@ do { \ tl = (local_trylock_t *)l; \ local_lock_release(l); \ _Generic((lock), \ - local_trylock_t *: ({ \ + __percpu local_trylock_t *: ({ \ lockdep_assert(tl->acquired == 1); \ WRITE_ONCE(tl->acquired, 0); \ }), \ - default:(void)0); \ + __percpu local_lock_t *: (void)0); \ } while (0) #define __local_unlock(lock) \ diff --git a/include/linux/mm.h b/include/linux/mm.h index b7f13f087954..bf55206935c4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1218,6 +1218,23 @@ static inline unsigned int folio_order(const struct folio *folio) return folio_large_order(folio); } +/** + * folio_reset_order - Reset the folio order and derived _nr_pages + * @folio: The folio. + * + * Reset the order and derived _nr_pages to 0. Must only be used in the + * process of splitting large folios. + */ +static inline void folio_reset_order(struct folio *folio) +{ + if (WARN_ON_ONCE(!folio_test_large(folio))) + return; + folio->_flags_1 &= ~0xffUL; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif +} + #include <linux/huge_mm.h> /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 25e80b2ca7f4..6ccec1bf2896 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -967,6 +967,9 @@ struct zone { #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; + + /* To be called once the last page in the zone is accepted */ + struct work_struct unaccepted_cleanup; #endif /* zone flags, see below */ @@ -1499,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. diff --git a/include/linux/namei.h b/include/linux/namei.h index e3042176cdf4..bbaf55fb3101 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -62,6 +62,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +extern struct dentry *kern_path_locked_negative(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 9ad727ddfedb..0906a0b40c6a 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -55,7 +55,6 @@ enum nfs3_stable_how { NFS_INVALID_STABLE_HOW = -1 }; -#ifdef CONFIG_CRC32 /** * nfs_fhandle_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle @@ -67,10 +66,4 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); } -#else /* CONFIG_CRC32 */ -static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) -{ - return 0; -} -#endif /* CONFIG_CRC32 */ #endif /* _LINUX_NFS_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e8e3fd77e96..51e2bd6405cd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -245,6 +245,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11), /* Device does honor MSI masking despite saying otherwise */ PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12), + /* Device requires write to PCI_MSIX_ENTRY_DATA before any MSIX reads */ + PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST = (__force pci_dev_flags_t) (1 << 13), }; enum pci_irq_reroute_variant { diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4d16c13d0df5..64cb4b04be7a 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -220,6 +220,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); * occurs. * @reset_done: optional function to call after transport specific reset * operation has finished. + * @shutdown: synchronize with the device on shutdown. If provided, replaces + * the virtio core implementation. */ struct virtio_driver { struct device_driver driver; @@ -237,6 +239,7 @@ struct virtio_driver { int (*restore)(struct virtio_device *dev); int (*reset_prepare)(struct virtio_device *dev); int (*reset_done)(struct virtio_device *dev); + void (*shutdown)(struct virtio_device *dev); }; #define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver) diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h index 746c43bd3eb6..2f24103f4533 100644 --- a/include/uapi/drm/ivpu_accel.h +++ b/include/uapi/drm/ivpu_accel.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* - * Copyright (C) 2020-2024 Intel Corporation + * Copyright (C) 2020-2025 Intel Corporation */ #ifndef __UAPI_IVPU_DRM_H__ @@ -147,7 +147,7 @@ struct drm_ivpu_param { * platform type when executing on a simulator or emulator (read-only) * * %DRM_IVPU_PARAM_CORE_CLOCK_RATE: - * Current PLL frequency (read-only) + * Maximum frequency of the NPU data processing unit clock (read-only) * * %DRM_IVPU_PARAM_NUM_CONTEXTS: * Maximum number of simultaneously existing contexts (read-only) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ed2beb4def3f..8f1fc12bac46 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1010,7 +1010,9 @@ struct io_uring_zcrx_ifq_reg { __u64 region_ptr; /* struct io_uring_region_desc * */ struct io_uring_zcrx_offsets offsets; - __u64 __resv[4]; + __u32 zcrx_id; + __u32 __resv2; + __u64 __resv[3]; }; #ifdef __cplusplus diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index d9d0cb827117..f030adc462ee 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -53,43 +53,70 @@ struct landlock_ruleset_attr { __u64 scoped; }; -/* - * sys_landlock_create_ruleset() flags: +/** + * DOC: landlock_create_ruleset_flags + * + * **Flags** * - * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI - * version. - * - %LANDLOCK_CREATE_RULESET_ERRATA: Get a bitmask of fixed issues. + * %LANDLOCK_CREATE_RULESET_VERSION + * Get the highest supported Landlock ABI version (starting at 1). + * + * %LANDLOCK_CREATE_RULESET_ERRATA + * Get a bitmask of fixed issues for the current Landlock ABI version. */ /* clang-format off */ #define LANDLOCK_CREATE_RULESET_VERSION (1U << 0) #define LANDLOCK_CREATE_RULESET_ERRATA (1U << 1) /* clang-format on */ -/* - * sys_landlock_restrict_self() flags: - * - * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF: Do not create any log related to the - * enforced restrictions. This should only be set by tools launching unknown - * or untrusted programs (e.g. a sandbox tool, container runtime, system - * service manager). Because programs sandboxing themselves should fix any - * denied access, they should not set this flag to be aware of potential - * issues reported by system's logs (i.e. audit). - * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON: Explicitly ask to continue - * logging denied access requests even after an :manpage:`execve(2)` call. - * This flag should only be set if all the programs than can legitimately be - * executed will not try to request a denied access (which could spam audit - * logs). - * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF: Do not create any log related - * to the enforced restrictions coming from future nested domains created by - * the caller or its descendants. This should only be set according to a - * runtime configuration (i.e. not hardcoded) by programs launching other - * unknown or untrusted programs that may create their own Landlock domains - * and spam logs. The main use case is for container runtimes to enable users - * to mute buggy sandboxed programs for a specific container image. Other use - * cases include sandboxer tools and init systems. Unlike - * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF, - * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF does not impact the requested - * restriction (if any) but only the future nested domains. +/** + * DOC: landlock_restrict_self_flags + * + * **Flags** + * + * By default, denied accesses originating from programs that sandbox themselves + * are logged via the audit subsystem. Such events typically indicate unexpected + * behavior, such as bugs or exploitation attempts. However, to avoid excessive + * logging, access requests denied by a domain not created by the originating + * program are not logged by default. The rationale is that programs should know + * their own behavior, but not necessarily the behavior of other programs. This + * default configuration is suitable for most programs that sandbox themselves. + * For specific use cases, the following flags allow programs to modify this + * default logging behavior. + * + * The %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF and + * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON flags apply to the newly created + * Landlock domain. + * + * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF + * Disables logging of denied accesses originating from the thread creating + * the Landlock domain, as well as its children, as long as they continue + * running the same executable code (i.e., without an intervening + * :manpage:`execve(2)` call). This is intended for programs that execute + * unknown code without invoking :manpage:`execve(2)`, such as script + * interpreters. Programs that only sandbox themselves should not set this + * flag, so users can be notified of unauthorized access attempts via system + * logs. + * + * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON + * Enables logging of denied accesses after an :manpage:`execve(2)` call, + * providing visibility into unauthorized access attempts by newly executed + * programs within the created Landlock domain. This flag is recommended + * only when all potential executables in the domain are expected to comply + * with the access restrictions, as excessive audit log entries could make + * it more difficult to identify critical events. + * + * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF + * Disables logging of denied accesses originating from nested Landlock + * domains created by the caller or its descendants. This flag should be set + * according to runtime configuration, not hardcoded, to avoid suppressing + * important security events. It is useful for container runtimes or + * sandboxing tools that may launch programs which themselves create + * Landlock domains and could otherwise generate excessive logs. Unlike + * ``LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF``, this flag only affects + * future nested domains, not the one being created. It can also be used + * with a @ruleset_fd value of -1 to mute subdomain logs without creating a + * domain. */ /* clang-format off */ #define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF (1U << 0) diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index b95dd84eef2d..d4b3e2ae1314 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -28,10 +28,10 @@ /* Set current process as the (exclusive) owner of this file descriptor. This * must be called before any other vhost command. Further calls to - * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */ + * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */ #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) /* Give up ownership, and reset the device to default values. - * Allows subsequent call to VHOST_OWNER_SET to succeed. */ + * Allows subsequent call to VHOST_SET_OWNER to succeed. */ #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) /* Set up/modify memory layout */ diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 8549d4571257..c691ac210ce2 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LIST_USE 0x1 /* Admin command group type. */ +#define VIRTIO_ADMIN_GROUP_TYPE_SELF 0x0 #define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1 /* Transitional device admin command. */ diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h index 41ff44dfa1db..f52de5ed1b3b 100644 --- a/include/ufs/ufs_quirks.h +++ b/include/ufs/ufs_quirks.h @@ -107,4 +107,10 @@ struct ufs_dev_quirk { */ #define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM (1 << 11) +/* + * Some ufs devices may need more time to be in hibern8 before exiting. + * Enable this quirk to give it an additional 100us. + */ +#define UFS_DEVICE_QUIRK_PA_HIBER8TIME (1 << 12) + #endif /* UFS_QUIRKS_H_ */ diff --git a/init/Kconfig b/init/Kconfig index dd2ea3b9a799..63f5974b9fa6 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1555,6 +1555,16 @@ config SYSCTL_ARCH_UNALIGN_ALLOW the unaligned access emulation. see arch/parisc/kernel/unaligned.c for reference +config SYSFS_SYSCALL + bool "Sysfs syscall support" + default n + help + sys_sysfs is an obsolete system call no longer supported in libc. + Note that disabling this option is more secure but might break + compatibility with some systems. + + If unsure say N here. + config HAVE_PCSPKR_PLATFORM bool @@ -1599,16 +1609,6 @@ config SGETMASK_SYSCALL If unsure, leave the default option here. -config SYSFS_SYSCALL - bool "Sysfs syscall support" if EXPERT - default y - help - sys_sysfs is an obsolete system call no longer supported in libc. - Note that disabling this option is more secure but might break - compatibility with some systems. - - If unsure say Y here. - config FHANDLE bool "open by fhandle syscalls" if EXPERT select EXPORTFS diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index b36c8825550e..f80a77c4973f 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1032,10 +1032,33 @@ static int validate_fixed_range(u64 buf_addr, size_t len, return 0; } +static int io_import_kbuf(int ddir, struct iov_iter *iter, + struct io_mapped_ubuf *imu, size_t len, size_t offset) +{ + size_t count = len + offset; + + iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, count); + iov_iter_advance(iter, offset); + + if (count < imu->len) { + const struct bio_vec *bvec = iter->bvec; + + while (len > bvec->bv_len) { + len -= bvec->bv_len; + bvec++; + } + iter->nr_segs = 1 + bvec - iter->bvec; + } + return 0; +} + static int io_import_fixed(int ddir, struct iov_iter *iter, struct io_mapped_ubuf *imu, u64 buf_addr, size_t len) { + const struct bio_vec *bvec; + size_t folio_mask; + unsigned nr_segs; size_t offset; int ret; @@ -1047,56 +1070,35 @@ static int io_import_fixed(int ddir, struct iov_iter *iter, if (!(imu->dir & (1 << ddir))) return -EFAULT; - /* - * Might not be a start of buffer, set size appropriately - * and advance us to the beginning. - */ offset = buf_addr - imu->ubuf; - iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) { - /* - * Don't use iov_iter_advance() here, as it's really slow for - * using the latter parts of a big fixed buffer - it iterates - * over each segment manually. We can cheat a bit here for user - * registered nodes, because we know that: - * - * 1) it's a BVEC iter, we set it up - * 2) all bvecs are the same in size, except potentially the - * first and last bvec - * - * So just find our index, and adjust the iterator afterwards. - * If the offset is within the first bvec (or the whole first - * bvec, just use iov_iter_advance(). This makes it easier - * since we can just skip the first segment, which may not - * be folio_size aligned. - */ - const struct bio_vec *bvec = imu->bvec; - - /* - * Kernel buffer bvecs, on the other hand, don't necessarily - * have the size property of user registered ones, so we have - * to use the slow iter advance. - */ - if (offset < bvec->bv_len) { - iter->count -= offset; - iter->iov_offset = offset; - } else if (imu->is_kbuf) { - iov_iter_advance(iter, offset); - } else { - unsigned long seg_skip; + if (imu->is_kbuf) + return io_import_kbuf(ddir, iter, imu, len, offset); - /* skip first vec */ - offset -= bvec->bv_len; - seg_skip = 1 + (offset >> imu->folio_shift); + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here for user + * registered nodes, because we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are the same in size, except potentially the + * first and last bvec + */ + folio_mask = (1UL << imu->folio_shift) - 1; + bvec = imu->bvec; + if (offset >= bvec->bv_len) { + unsigned long seg_skip; - iter->bvec += seg_skip; - iter->nr_segs -= seg_skip; - iter->count -= bvec->bv_len + offset; - iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1); - } + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> imu->folio_shift); + bvec += seg_skip; + offset &= folio_mask; } - + nr_segs = (offset + len + bvec->bv_offset + folio_mask) >> imu->folio_shift; + iov_iter_bvec(iter, ddir, bvec, nr_segs, len); + iter->iov_offset = offset; return 0; } diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 0f46e0404c04..fe86606b9f30 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -26,6 +26,11 @@ #include "zcrx.h" #include "rsrc.h" +static inline struct io_zcrx_ifq *io_pp_to_ifq(struct page_pool *pp) +{ + return pp->mp_priv; +} + #define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, @@ -46,14 +51,21 @@ static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { + guard(mutex)(&ifq->dma_lock); + if (area->is_mapped) __io_zcrx_unmap_area(ifq, area, area->nia.num_niovs); + area->is_mapped = false; } static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { int i; + guard(mutex)(&ifq->dma_lock); + if (area->is_mapped) + return 0; + for (i = 0; i < area->nia.num_niovs; i++) { struct net_iov *niov = &area->nia.niovs[i]; dma_addr_t dma; @@ -275,6 +287,7 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx) ifq->ctx = ctx; spin_lock_init(&ifq->lock); spin_lock_init(&ifq->rq_lock); + mutex_init(&ifq->dma_lock); return ifq; } @@ -324,6 +337,7 @@ static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq) put_device(ifq->dev); io_free_rbuf_ring(ifq); + mutex_destroy(&ifq->dma_lock); kfree(ifq); } @@ -354,7 +368,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, return -EFAULT; if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd))) return -EFAULT; - if (memchr_inv(®.__resv, 0, sizeof(reg.__resv))) + if (memchr_inv(®.__resv, 0, sizeof(reg.__resv)) || + reg.__resv2 || reg.zcrx_id) return -EINVAL; if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags) return -EINVAL; @@ -394,10 +409,6 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, goto err; get_device(ifq->dev); - ret = io_zcrx_map_area(ifq, ifq->area); - if (ret) - goto err; - mp_param.mp_ops = &io_uring_pp_zc_ops; mp_param.mp_priv = ifq; ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param); @@ -585,7 +596,7 @@ static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq) static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) { - struct io_zcrx_ifq *ifq = pp->mp_priv; + struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); /* pp should already be ensuring that */ if (unlikely(pp->alloc.count)) @@ -617,7 +628,8 @@ static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem) static int io_pp_zc_init(struct page_pool *pp) { - struct io_zcrx_ifq *ifq = pp->mp_priv; + struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); + int ret; if (WARN_ON_ONCE(!ifq)) return -EINVAL; @@ -630,13 +642,17 @@ static int io_pp_zc_init(struct page_pool *pp) if (pp->p.dma_dir != DMA_FROM_DEVICE) return -EOPNOTSUPP; + ret = io_zcrx_map_area(ifq, ifq->area); + if (ret) + return ret; + percpu_ref_get(&ifq->ctx->refs); return 0; } static void io_pp_zc_destroy(struct page_pool *pp) { - struct io_zcrx_ifq *ifq = pp->mp_priv; + struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); struct io_zcrx_area *area = ifq->area; if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs)) @@ -665,6 +681,9 @@ static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq) struct io_zcrx_ifq *ifq = mp_priv; io_zcrx_drop_netdev(ifq); + if (ifq->area) + io_zcrx_unmap_area(ifq, ifq->area); + p->mp_ops = NULL; p->mp_priv = NULL; } @@ -791,7 +810,7 @@ static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, niov = netmem_to_net_iov(frag->netmem); if (niov->pp->mp_ops != &io_uring_pp_zc_ops || - niov->pp->mp_priv != ifq) + io_pp_to_ifq(niov->pp) != ifq) return -EFAULT; if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len)) diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index 47f1c0e8c197..f2bc811f022c 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -38,6 +38,7 @@ struct io_zcrx_ifq { struct net_device *netdev; netdevice_tracker netdev_tracker; spinlock_t lock; + struct mutex dma_lock; }; #if defined(CONFIG_IO_URING_ZCRX) diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 367eaf2c78b7..0ebbbe37a60f 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent) /* Get path information necessary for adding watches. */ static int audit_get_nd(struct audit_watch *watch, struct path *parent) { - struct dentry *d = kern_path_locked(watch->path, parent); + struct dentry *d; + + d = kern_path_locked_negative(watch->path, parent); if (IS_ERR(d)) return PTR_ERR(d); - /* update watch filter fields */ - watch->dev = d->d_sb->s_dev; - watch->ino = d_backing_inode(d)->i_ino; + + if (d_is_positive(d)) { + /* update watch filter fields */ + watch->dev = d->d_sb->s_dev; + watch->ino = d_backing_inode(d)->i_ino; + } inode_unlock(d_backing_inode(parent->dentry)); dput(d); @@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) /* caller expects mutex locked */ mutex_lock(&audit_filter_mutex); - if (ret && ret != -ENOENT) { + if (ret) { audit_put_watch(watch); return ret; } - ret = 0; /* either find an old parent or attach a new one */ parent = audit_find_parent(d_backing_inode(parent_path.dentry)); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 3caf2cd86e65..63e5b90da1f3 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -90,7 +90,7 @@ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); -#ifdef CONFIG_PROVE_RCU +#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP) EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif @@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = { }; #ifdef CONFIG_CPUSETS_V1 +enum cpuset_param { + Opt_cpuset_v2_mode, +}; + +static const struct fs_parameter_spec cpuset_fs_parameters[] = { + fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), + {} +}; + +static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, cpuset_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_cpuset_v2_mode: + ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; + return 0; + } + return -EINVAL; +} + static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, + .parse_param = cpuset_parse_param, }; /* @@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc) static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, + .parameters = cpuset_fs_parameters, .fs_flags = FS_USERNS_MOUNT, }; #endif diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 1a19d69b91ed..816f07f9d30f 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; - if (unlikely(sg_policy->limits_changed)) { - sg_policy->limits_changed = false; - sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + if (unlikely(READ_ONCE(sg_policy->limits_changed))) { + WRITE_ONCE(sg_policy->limits_changed, false); + sg_policy->need_freq_update = true; + + /* + * The above limits_changed update must occur before the reads + * of policy limits in cpufreq_driver_resolve_freq() or a policy + * limits update might be missed, so use a memory barrier to + * ensure it. + * + * This pairs with the write memory barrier in sugov_limits(). + */ + smp_mb(); + + return true; + } else if (sg_policy->need_freq_update) { + /* ignore_dl_rate_limit() wants a new frequency to be found. */ return true; } @@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { - if (sg_policy->need_freq_update) + if (sg_policy->need_freq_update) { sg_policy->need_freq_update = false; - else if (sg_policy->next_freq == next_freq) + /* + * The policy limits have changed, but if the return value of + * cpufreq_driver_resolve_freq() after applying the new limits + * is still equal to the previously selected frequency, the + * driver callback need not be invoked unless the driver + * specifically wants that to happen on every update of the + * policy limits. + */ + if (sg_policy->next_freq == next_freq && + !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS)) + return false; + } else if (sg_policy->next_freq == next_freq) { return false; + } sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; @@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; } static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu) { if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min) - sg_cpu->sg_policy->limits_changed = true; + sg_cpu->sg_policy->need_freq_update = true; } static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, @@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy) mutex_unlock(&sg_policy->work_lock); } - sg_policy->limits_changed = true; + /* + * The limits_changed update below must take place before the updates + * of policy limits in cpufreq_set_policy() or a policy limits update + * might be missed, so use a memory barrier to ensure it. + * + * This pairs with the memory barrier in sugov_should_update_freq(). + */ + smp_wmb(); + + WRITE_ONCE(sg_policy->limits_changed, true); } struct cpufreq_governor schedutil_gov = { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 66bcd40a28ca..fdbf249d1c68 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -163,7 +163,7 @@ enum scx_ops_flags { /* * CPU cgroup support flags */ - SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ + SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */ SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | @@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq) DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem); static bool scx_cgroup_enabled; -static bool cgroup_warned_missing_weight; -static bool cgroup_warned_missing_idle; - -static void scx_cgroup_warn_missing_weight(struct task_group *tg) -{ - if (scx_ops_enable_state() == SCX_OPS_DISABLED || - cgroup_warned_missing_weight) - return; - - if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent) - return; - - pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n", - scx_ops.name); - cgroup_warned_missing_weight = true; -} - -static void scx_cgroup_warn_missing_idle(struct task_group *tg) -{ - if (!scx_cgroup_enabled || cgroup_warned_missing_idle) - return; - - if (!tg->idle) - return; - - pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n", - scx_ops.name); - cgroup_warned_missing_idle = true; -} int scx_tg_online(struct task_group *tg) { @@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg) percpu_down_read(&scx_cgroup_rwsem); - scx_cgroup_warn_missing_weight(tg); - if (scx_cgroup_enabled) { if (SCX_HAS_OP(cgroup_init)) { struct scx_cgroup_init_args args = @@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) void scx_group_set_idle(struct task_group *tg, bool idle) { - percpu_down_read(&scx_cgroup_rwsem); - scx_cgroup_warn_missing_idle(tg); - percpu_up_read(&scx_cgroup_rwsem); + /* TODO: Implement ops->cgroup_set_idle() */ } static void scx_cgroup_lock(void) @@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void) percpu_rwsem_assert_held(&scx_cgroup_rwsem); - cgroup_warned_missing_weight = false; - cgroup_warned_missing_idle = false; - /* * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk * cgroups and init, all online cgroups are initialized. @@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void) struct task_group *tg = css_tg(css); struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; - scx_cgroup_warn_missing_weight(tg); - scx_cgroup_warn_missing_idle(tg); - if ((tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE) continue; @@ -4623,7 +4584,7 @@ unlock: static void free_exit_info(struct scx_exit_info *ei) { - kfree(ei->dump); + kvfree(ei->dump); kfree(ei->msg); kfree(ei->bt); kfree(ei); @@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len) ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL); ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL); - ei->dump = kzalloc(exit_dump_len, GFP_KERNEL); + ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL); if (!ei->bt || !ei->msg || !ei->dump) { free_exit_info(ei); @@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops) return -EINVAL; } + if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT) + pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n"); + return 0; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a8a02868b435..61130bb34d6c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops) return; free_ftrace_hash(ops->func_hash->filter_hash); free_ftrace_hash(ops->func_hash->notrace_hash); + ops->func_hash->filter_hash = EMPTY_HASH; + ops->func_hash->notrace_hash = EMPTY_HASH; } EXPORT_SYMBOL_GPL(ftrace_free_filter); @@ -3443,6 +3445,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash ** size_bits); if (ret < 0) { free_ftrace_hash(*filter_hash); + *filter_hash = EMPTY_HASH; return ret; } } @@ -3472,6 +3475,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash ** subops_hash->notrace_hash); if (ret < 0) { free_ftrace_hash(*notrace_hash); + *notrace_hash = EMPTY_HASH; return ret; } } @@ -3490,8 +3494,8 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash ** */ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command) { - struct ftrace_hash *filter_hash; - struct ftrace_hash *notrace_hash; + struct ftrace_hash *filter_hash = EMPTY_HASH; + struct ftrace_hash *notrace_hash = EMPTY_HASH; struct ftrace_hash *save_filter_hash; struct ftrace_hash *save_notrace_hash; int ret; @@ -3605,6 +3609,9 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash * } } + free_ftrace_hash(temp_hash.filter_hash); + free_ftrace_hash(temp_hash.notrace_hash); + temp_hash.filter_hash = *filter_hash; temp_hash.notrace_hash = *notrace_hash; } @@ -3625,8 +3632,8 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash * */ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command) { - struct ftrace_hash *filter_hash; - struct ftrace_hash *notrace_hash; + struct ftrace_hash *filter_hash = EMPTY_HASH; + struct ftrace_hash *notrace_hash = EMPTY_HASH; int ret; if (unlikely(ftrace_disabled)) @@ -3699,8 +3706,11 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops, } ret = rebuild_hashes(&filter_hash, ¬race_hash, ops); - if (!ret) + if (!ret) { ret = ftrace_update_ops(ops, filter_hash, notrace_hash); + free_ftrace_hash(filter_hash); + free_ftrace_hash(notrace_hash); + } if (ret) { /* Put back the original hash */ @@ -5954,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) /* Make a copy hash to place the new and the old entries in */ size = hash->count + direct_functions->count; - if (size > 32) - size = 32; - new_hash = alloc_ftrace_hash(fls(size)); + size = fls(size); + if (size > FTRACE_HASH_MAX_BITS) + size = FTRACE_HASH_MAX_BITS; + new_hash = alloc_ftrace_hash(size); if (!new_hash) goto out_unlock; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index ee40d4e6ad1c..4ef4df6623a8 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, F_STRUCT( __field_struct( struct ftrace_graph_ent, graph_ent ) __field_packed( unsigned long, graph_ent, func ) - __field_packed( unsigned long, graph_ent, depth ) + __field_packed( unsigned int, graph_ent, depth ) __dynamic_array(unsigned long, args ) ), - F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth) + F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth) ); #ifdef CONFIG_FUNCTION_GRAPH_RETADDR diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 0993dfc1c5c1..2048560264bb 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str) kstr = ubuf->buffer; /* For safety, do not trust the string pointer */ - if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE)) + if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0) return NULL; return kstr; } @@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str) /* user space address? */ ustr = (char __user *)str; - if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE)) + if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0) return NULL; return kstr; diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index 2ef2e1b80091..2f844c279a3e 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop); * @arg: data to be passed to fn and handled_kill * @name: the thread's name * - * This returns a specialized task for use by the vhost layer or NULL on + * This returns a specialized task for use by the vhost layer or ERR_PTR() on * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9fe4d8dfe578..f9051ab610d5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3290,7 +3290,7 @@ config GCD_KUNIT_TEST config PRIME_NUMBERS_KUNIT_TEST tristate "Prime number generator test" if !KUNIT_ALL_TESTS depends on KUNIT - select PRIME_NUMBERS + depends on PRIME_NUMBERS default KUNIT_ALL_TESTS help This option enables the KUnit test suite for the {is,next}_prime_number diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 4216b3a4ff21..f6ea0c5b5da3 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -118,7 +118,6 @@ config UBSAN_UNREACHABLE config UBSAN_INTEGER_WRAP bool "Perform checking for integer arithmetic wrap-around" - default UBSAN depends on !COMPILE_TEST depends on $(cc-option,-fsanitize-undefined-ignore-overflow-pattern=all) depends on $(cc-option,-fsanitize=signed-integer-overflow) diff --git a/lib/string.c b/lib/string.c index eb4486ed40d2..b632c71df1a5 100644 --- a/lib/string.c +++ b/lib/string.c @@ -119,6 +119,7 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) if (count == 0 || WARN_ON_ONCE(count > INT_MAX)) return -E2BIG; +#ifndef CONFIG_DCACHE_WORD_ACCESS #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* * If src is unaligned, don't cross a page boundary, @@ -134,11 +135,13 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) if (((long) dest | (long) src) & (sizeof(long) - 1)) max = 0; #endif +#endif /* - * read_word_at_a_time() below may read uninitialized bytes after the - * trailing zero and use them in comparisons. Disable this optimization - * under KMSAN to prevent false positive reports. + * load_unaligned_zeropad() or read_word_at_a_time() below may read + * uninitialized bytes after the trailing zero and use them in + * comparisons. Disable this optimization under KMSAN to prevent + * false positive reports. */ if (IS_ENABLED(CONFIG_KMSAN)) max = 0; @@ -146,7 +149,11 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) while (max >= sizeof(unsigned long)) { unsigned long c, data; +#ifdef CONFIG_DCACHE_WORD_ACCESS + c = load_unaligned_zeropad(src+res); +#else c = read_word_at_a_time(src+res); +#endif if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index 8772e5edaa4f..a4b6f52b9c57 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -77,18 +77,22 @@ static void test_ubsan_shift_out_of_bounds(void) static void test_ubsan_out_of_bounds(void) { - volatile int i = 4, j = 5, k = -1; - volatile char above[4] = { }; /* Protect surrounding memory. */ - volatile int arr[4]; - volatile char below[4] = { }; /* Protect surrounding memory. */ + int i = 4, j = 4, k = -1; + volatile struct { + char above[4]; /* Protect surrounding memory. */ + int arr[4]; + char below[4]; /* Protect surrounding memory. */ + } data; - above[0] = below[0]; + OPTIMIZER_HIDE_VAR(i); + OPTIMIZER_HIDE_VAR(j); + OPTIMIZER_HIDE_VAR(k); UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "above"); - arr[j] = i; + data.arr[j] = i; UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "below"); - arr[k] = i; + data.arr[k] = i; } enum ubsan_test_enum { @@ -2207,8 +2207,8 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) } while (start != end); mmap_read_unlock(mm); - if (size > (unsigned long)uaddr - start) - return size - ((unsigned long)uaddr - start); + if (size > start - (unsigned long)uaddr) + return size - (start - (unsigned long)uaddr); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 9a99dfa3c495..27245e86df25 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -238,11 +238,11 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, * struct page, the special metadata (e.g. page->flags or page->mapping) * cannot copy to the tail struct page structs. The invalid value will be * checked in the free_tail_page_prepare(). In order to avoid the message - * of "corrupted mapping in tail page". We need to reset at least 3 (one - * head struct page struct and two tail struct page structs) struct page + * of "corrupted mapping in tail page". We need to reset at least 4 (one + * head struct page struct and three tail struct page structs) struct page * structs. */ -#define NR_RESET_STRUCT_PAGE 3 +#define NR_RESET_STRUCT_PAGE 4 static inline void reset_struct_pages(struct page *start) { diff --git a/mm/internal.h b/mm/internal.h index 50c2f590b2d0..e9695baa5922 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1595,6 +1595,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); +void unaccepted_cleanup_work(struct work_struct *work); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index f24e3bef72a4..5f922dd38ffa 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -1567,6 +1567,7 @@ static void kasan_memcmp(struct kunit *test) static void kasan_strings(struct kunit *test) { char *ptr; + char *src; size_t size = 24; /* @@ -1578,6 +1579,25 @@ static void kasan_strings(struct kunit *test) ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + src = kmalloc(KASAN_GRANULE_SIZE, GFP_KERNEL | __GFP_ZERO); + strscpy(src, "f0cacc1a0000000", KASAN_GRANULE_SIZE); + + /* + * Make sure that strscpy() does not trigger KASAN if it overreads into + * poisoned memory. + * + * The expected size does not include the terminator '\0' + * so it is (KASAN_GRANULE_SIZE - 2) == + * KASAN_GRANULE_SIZE - ("initial removed character" + "\0"). + */ + KUNIT_EXPECT_EQ(test, KASAN_GRANULE_SIZE - 2, + strscpy(ptr, src + 1, KASAN_GRANULE_SIZE)); + + /* strscpy should fail if the first byte is unreadable. */ + KUNIT_EXPECT_KASAN_FAIL(test, strscpy(ptr, src + KASAN_GRANULE_SIZE, + KASAN_GRANULE_SIZE)); + + kfree(src); kfree(ptr); /* diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 8660908850dc..4a9cf27a70af 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -620,7 +620,7 @@ void memcg1_swapout(struct folio *folio, swp_entry_t entry) mem_cgroup_id_get_many(swap_memcg, nr_entries - 1); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); - swap_cgroup_record(folio, mem_cgroup_id(memcg), entry); + swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry); folio_unqueue_deferred_split(folio); folio->memcg_data = 0; diff --git a/mm/memory.c b/mm/memory.c index 44481fe7c629..ba3ea0a82f7f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3734,8 +3734,6 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio, return false; VM_WARN_ON_ONCE(folio_test_ksm(folio)); - VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio)); - VM_WARN_ON_ONCE(folio_entire_mapcount(folio)); if (unlikely(folio_test_swapcache(folio))) { /* @@ -3760,6 +3758,8 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio, if (folio_large_mapcount(folio) != folio_ref_count(folio)) goto unlock; + VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio); VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id && folio_mm_id(folio, 1) != vma->vm_mm->mm_id); diff --git a/mm/mm_init.c b/mm/mm_init.c index 84f14fa12d0d..9659689b8ace 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1441,6 +1441,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) #ifdef CONFIG_UNACCEPTED_MEMORY INIT_LIST_HEAD(&zone->unaccepted_pages); + INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work); #endif } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1715e34b91af..5669baf2a6fe 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3470,18 +3470,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, return false; } -bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int highest_zoneidx) -{ - long free_pages = zone_page_state(z, NR_FREE_PAGES); - - if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) - free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); - - return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, - free_pages); -} - #ifdef CONFIG_NUMA int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; @@ -7191,6 +7179,11 @@ static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); static bool lazy_accept = true; +void unaccepted_cleanup_work(struct work_struct *work) +{ + static_branch_dec(&zones_with_unaccepted_pages); +} + static int __init accept_memory_parse(char *p) { if (!strcmp(p, "lazy")) { @@ -7229,8 +7222,27 @@ static void __accept_page(struct zone *zone, unsigned long *flags, __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); - if (last) - static_branch_dec(&zones_with_unaccepted_pages); + if (last) { + /* + * There are two corner cases: + * + * - If allocation occurs during the CPU bring up, + * static_branch_dec() cannot be used directly as + * it causes a deadlock on cpu_hotplug_lock. + * + * Instead, use schedule_work() to prevent deadlock. + * + * - If allocation occurs before workqueues are initialized, + * static_branch_dec() should be called directly. + * + * Workqueues are initialized before CPU bring up, so this + * will not conflict with the first scenario. + */ + if (system_wq) + schedule_work(&zone->unaccepted_cleanup); + else + unaccepted_cleanup_work(&zone->unaccepted_cleanup); + } } void accept_page(struct page *page) diff --git a/mm/vmscan.c b/mm/vmscan.c index b620d74b0f66..3783e45bfc92 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) * meet watermarks. */ for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { + enum zone_stat_item item; unsigned long free_pages; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) @@ -6746,11 +6747,33 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) /* * In defrag_mode, watermarks must be met in whole * blocks to avoid polluting allocator fallbacks. + * + * However, kswapd usually cannot accomplish this on + * its own and needs kcompactd support. Once it's + * reclaimed a compaction gap, and kswapd_shrink_node + * has dropped order, simply ensure there are enough + * base pages for compaction, wake kcompactd & sleep. */ - if (defrag_mode) - free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS); + if (defrag_mode && order) + item = NR_FREE_PAGES_BLOCKS; else - free_pages = zone_page_state(zone, NR_FREE_PAGES); + item = NR_FREE_PAGES; + + /* + * When there is a high number of CPUs in the system, + * the cumulative error from the vmstat per-cpu cache + * can blur the line between the watermarks. In that + * case, be safe and get an accurate snapshot. + * + * TODO: NR_FREE_PAGES_BLOCKS moves in steps of + * pageblock_nr_pages, while the vmstat pcp threshold + * is limited to 125. On many configurations that + * counter won't actually be per-cpu cached. But keep + * things simple for now; revisit when somebody cares. + */ + free_pages = zone_page_state(zone, item); + if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark) + free_pages = zone_page_state_snapshot(zone, item); if (__zone_watermark_ok(zone, order, mark, highest_zoneidx, 0, free_pages)) diff --git a/rust/Makefile b/rust/Makefile index fa0eea8a9eca..3aca903a7d08 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -368,7 +368,7 @@ $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ; $(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE $(call if_changed_dep,bindgen) -rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ && $$3!~/__odr_asan/ { printf $(2),$$3 }' +rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__(pfx|cfi|odr_asan)/ { printf $(2),$$3 }' quiet_cmd_exports = EXPORTS $@ cmd_exports = \ diff --git a/rust/helpers/dma.c b/rust/helpers/dma.c new file mode 100644 index 000000000000..df8b8a77355a --- /dev/null +++ b/rust/helpers/dma.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/dma-mapping.h> + +void *rust_helper_dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, + unsigned long attrs) +{ + return dma_alloc_attrs(dev, size, dma_handle, flag, attrs); +} + +void rust_helper_dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ + dma_free_attrs(dev, size, cpu_addr, dma_handle, attrs); +} diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index e1c21eba9b15..1e7c84df7252 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -14,6 +14,7 @@ #include "cpumask.c" #include "cred.c" #include "device.c" +#include "dma.c" #include "err.c" #include "fs.c" #include "io.c" diff --git a/rust/helpers/io.c b/rust/helpers/io.c index 4c2401ccd720..15ea187c5466 100644 --- a/rust/helpers/io.c +++ b/rust/helpers/io.c @@ -7,94 +7,94 @@ void __iomem *rust_helper_ioremap(phys_addr_t offset, size_t size) return ioremap(offset, size); } -void rust_helper_iounmap(volatile void __iomem *addr) +void rust_helper_iounmap(void __iomem *addr) { iounmap(addr); } -u8 rust_helper_readb(const volatile void __iomem *addr) +u8 rust_helper_readb(const void __iomem *addr) { return readb(addr); } -u16 rust_helper_readw(const volatile void __iomem *addr) +u16 rust_helper_readw(const void __iomem *addr) { return readw(addr); } -u32 rust_helper_readl(const volatile void __iomem *addr) +u32 rust_helper_readl(const void __iomem *addr) { return readl(addr); } #ifdef CONFIG_64BIT -u64 rust_helper_readq(const volatile void __iomem *addr) +u64 rust_helper_readq(const void __iomem *addr) { return readq(addr); } #endif -void rust_helper_writeb(u8 value, volatile void __iomem *addr) +void rust_helper_writeb(u8 value, void __iomem *addr) { writeb(value, addr); } -void rust_helper_writew(u16 value, volatile void __iomem *addr) +void rust_helper_writew(u16 value, void __iomem *addr) { writew(value, addr); } -void rust_helper_writel(u32 value, volatile void __iomem *addr) +void rust_helper_writel(u32 value, void __iomem *addr) { writel(value, addr); } #ifdef CONFIG_64BIT -void rust_helper_writeq(u64 value, volatile void __iomem *addr) +void rust_helper_writeq(u64 value, void __iomem *addr) { writeq(value, addr); } #endif -u8 rust_helper_readb_relaxed(const volatile void __iomem *addr) +u8 rust_helper_readb_relaxed(const void __iomem *addr) { return readb_relaxed(addr); } -u16 rust_helper_readw_relaxed(const volatile void __iomem *addr) +u16 rust_helper_readw_relaxed(const void __iomem *addr) { return readw_relaxed(addr); } -u32 rust_helper_readl_relaxed(const volatile void __iomem *addr) +u32 rust_helper_readl_relaxed(const void __iomem *addr) { return readl_relaxed(addr); } #ifdef CONFIG_64BIT -u64 rust_helper_readq_relaxed(const volatile void __iomem *addr) +u64 rust_helper_readq_relaxed(const void __iomem *addr) { return readq_relaxed(addr); } #endif -void rust_helper_writeb_relaxed(u8 value, volatile void __iomem *addr) +void rust_helper_writeb_relaxed(u8 value, void __iomem *addr) { writeb_relaxed(value, addr); } -void rust_helper_writew_relaxed(u16 value, volatile void __iomem *addr) +void rust_helper_writew_relaxed(u16 value, void __iomem *addr) { writew_relaxed(value, addr); } -void rust_helper_writel_relaxed(u32 value, volatile void __iomem *addr) +void rust_helper_writel_relaxed(u32 value, void __iomem *addr) { writel_relaxed(value, addr); } #ifdef CONFIG_64BIT -void rust_helper_writeq_relaxed(u64 value, volatile void __iomem *addr) +void rust_helper_writeq_relaxed(u64 value, void __iomem *addr) { writeq_relaxed(value, addr); } diff --git a/rust/pin-init/examples/pthread_mutex.rs b/rust/pin-init/examples/pthread_mutex.rs index 9164298c44c0..5ac22f1880d2 100644 --- a/rust/pin-init/examples/pthread_mutex.rs +++ b/rust/pin-init/examples/pthread_mutex.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT -// inspired by https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs +// inspired by <https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs> #![allow(clippy::undocumented_unsafe_blocks)] #![cfg_attr(feature = "alloc", feature(allocator_api))] #[cfg(not(windows))] diff --git a/rust/pin-init/src/alloc.rs b/rust/pin-init/src/alloc.rs index e16baa3b434e..5017f57442d8 100644 --- a/rust/pin-init/src/alloc.rs +++ b/rust/pin-init/src/alloc.rs @@ -17,11 +17,9 @@ use crate::{ pub extern crate alloc; -// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee). -// -// In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant and there -// is no problem with a VTABLE pointer being null. -unsafe impl<T: ?Sized> ZeroableOption for Box<T> {} +// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee: +// <https://doc.rust-lang.org/stable/std/option/index.html#representation>). +unsafe impl<T> ZeroableOption for Box<T> {} /// Smart pointer that can initialize memory in-place. pub trait InPlaceInit<T>: Sized { diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs index 05c44514765e..0806c689f693 100644 --- a/rust/pin-init/src/lib.rs +++ b/rust/pin-init/src/lib.rs @@ -1447,7 +1447,7 @@ impl_zeroable! { {<T: ?Sized + Zeroable>} UnsafeCell<T>, // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee: - // https://doc.rust-lang.org/stable/std/option/index.html#representation). + // <https://doc.rust-lang.org/stable/std/option/index.html#representation>). Option<NonZeroU8>, Option<NonZeroU16>, Option<NonZeroU32>, Option<NonZeroU64>, Option<NonZeroU128>, Option<NonZeroUsize>, Option<NonZeroI8>, Option<NonZeroI16>, Option<NonZeroI32>, Option<NonZeroI64>, diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 8956587b8547..f4fcc1eaaeae 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -79,8 +79,8 @@ ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) # Usage: MY_RUSTFLAGS += $(call __rustc-option,$(RUSTC),$(MY_RUSTFLAGS),-Cinstrument-coverage,-Zinstrument-coverage) # TODO: remove RUSTC_BOOTSTRAP=1 when we raise the minimum GNU Make version to 4.4 __rustc-option = $(call try-run,\ - echo '#![allow(missing_docs)]#![feature(no_core)]#![no_core]' | RUSTC_BOOTSTRAP=1\ - $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null,$(2)) $(3)\ + echo '$(pound)![allow(missing_docs)]$(pound)![feature(no_core)]$(pound)![no_core]' | RUSTC_BOOTSTRAP=1\ + $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null --target=%,$(2)) $(3)\ --crate-type=rlib --out-dir=$(TMPOUT) --emit=obj=- - >/dev/null,$(3),$(4)) # rustc-option diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index d75897559d18..2d6e59561c9d 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -15,7 +15,7 @@ KBUILD_CFLAGS += -Werror=return-type KBUILD_CFLAGS += -Werror=strict-prototypes KBUILD_CFLAGS += -Wno-format-security KBUILD_CFLAGS += -Wno-trigraphs -KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,) +KBUILD_CFLAGS += $(call cc-disable-warning, frame-address) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += -Wmissing-declarations KBUILD_CFLAGS += -Wmissing-prototypes diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index cd41bc906fbd..fe663dd0c43b 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -112,6 +112,12 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): cfg=["kernel"], ) + append_crate( + "ffi", + srctree / "rust" / "ffi.rs", + ["core", "compiler_builtins"], + ) + def append_crate_with_generated( display_name, deps, @@ -131,9 +137,9 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): "exclude_dirs": [], } - append_crate_with_generated("bindings", ["core"]) - append_crate_with_generated("uapi", ["core"]) - append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "bindings", "uapi"]) + append_crate_with_generated("bindings", ["core", "ffi"]) + append_crate_with_generated("uapi", ["core", "ffi"]) + append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "ffi", "bindings", "uapi"]) def is_root_crate(build_file, target): try: diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c index b85e0979a00c..ee1499d27061 100644 --- a/scripts/genksyms/keywords.c +++ b/scripts/genksyms/keywords.c @@ -17,6 +17,8 @@ static struct resword { { "__signed__", SIGNED_KEYW }, { "__typeof", TYPEOF_KEYW }, { "__typeof__", TYPEOF_KEYW }, + { "__typeof_unqual", TYPEOF_KEYW }, + { "__typeof_unqual__", TYPEOF_KEYW }, { "__volatile", VOLATILE_KEYW }, { "__volatile__", VOLATILE_KEYW }, { "__builtin_va_list", VA_LIST_KEYW }, @@ -40,6 +42,10 @@ static struct resword { // KAO. }, // { "attribute", ATTRIBUTE_KEYW }, + // X86 named address space qualifiers + { "__seg_gs", X86_SEG_KEYW }, + { "__seg_fs", X86_SEG_KEYW }, + { "auto", AUTO_KEYW }, { "char", CHAR_KEYW }, { "const", CONST_KEYW }, @@ -57,6 +63,7 @@ static struct resword { { "struct", STRUCT_KEYW }, { "typedef", TYPEDEF_KEYW }, { "typeof", TYPEOF_KEYW }, + { "typeof_unqual", TYPEOF_KEYW }, { "union", UNION_KEYW }, { "unsigned", UNSIGNED_KEYW }, { "void", VOID_KEYW }, diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index ee600a804fa1..efdcf07c4eb6 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -91,6 +91,8 @@ static void record_compound(struct string_list **keyw, %token TYPEOF_KEYW %token VA_LIST_KEYW +%token X86_SEG_KEYW + %token EXPORT_SYMBOL_KEYW %token ASM_PHRASE @@ -292,7 +294,8 @@ type_qualifier_seq: ; type_qualifier: - CONST_KEYW | VOLATILE_KEYW + X86_SEG_KEYW + | CONST_KEYW | VOLATILE_KEYW | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ remove_node($1); diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index c17366ce8224..3fe9d7b945c4 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -344,7 +344,7 @@ config CC_HAS_RANDSTRUCT choice prompt "Randomize layout of sensitive kernel structures" - default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT) + default RANDSTRUCT_FULL if COMPILE_TEST && CC_HAS_RANDSTRUCT default RANDSTRUCT_NONE help If you enable this, the layouts of structures that are entirely diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index f3e7ac513db3..f99ab1a3b0f0 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -245,7 +245,9 @@ static int process_measurement(struct file *file, const struct cred *cred, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && - (ima_policy_flag & IMA_MEASURE)); + (ima_policy_flag & IMA_MEASURE) && + ((action & IMA_MEASURE) || + (file->f_mode & FMODE_WRITE))); if (!action && !violation_check) return 0; diff --git a/security/landlock/domain.c b/security/landlock/domain.c index bae2e9909013..a647b68e8d06 100644 --- a/security/landlock/domain.c +++ b/security/landlock/domain.c @@ -16,6 +16,7 @@ #include <linux/path.h> #include <linux/pid.h> #include <linux/sched.h> +#include <linux/signal.h> #include <linux/uidgid.h> #include "access.h" @@ -99,8 +100,7 @@ static struct landlock_details *get_current_details(void) return ERR_PTR(-ENOMEM); memcpy(details->exe_path, path_str, path_size); - WARN_ON_ONCE(current_cred() != current_real_cred()); - details->pid = get_pid(task_pid(current)); + details->pid = get_pid(task_tgid(current)); details->uid = from_kuid(&init_user_ns, current_uid()); get_task_comm(details->comm, current); return details; diff --git a/security/landlock/domain.h b/security/landlock/domain.h index ed0d348e214c..7fb70b25f85a 100644 --- a/security/landlock/domain.h +++ b/security/landlock/domain.h @@ -130,7 +130,7 @@ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy); static inline void landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy) { - if (WARN_ON_ONCE(!hierarchy || !hierarchy->details)) + if (!hierarchy || !hierarchy->details) return; put_pid(hierarchy->details->pid); diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 54a9f29e6ebb..b9561e3417ae 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -169,20 +169,16 @@ const int landlock_abi_version = 7; * the new ruleset. * @size: Size of the pointed &struct landlock_ruleset_attr (needed for * backward and forward compatibility). - * @flags: Supported value: + * @flags: Supported values: + * * - %LANDLOCK_CREATE_RULESET_VERSION * - %LANDLOCK_CREATE_RULESET_ERRATA * * This system call enables to create a new Landlock ruleset, and returns the * related file descriptor on success. * - * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is - * 0, then the returned value is the highest supported Landlock ABI version - * (starting at 1). - * - * If @flags is %LANDLOCK_CREATE_RULESET_ERRATA and @attr is NULL and @size is - * 0, then the returned value is a bitmask of fixed issues for the current - * Landlock ABI version. + * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is + * set, then @attr must be NULL and @size must be 0. * * Possible returned errors are: * @@ -191,6 +187,9 @@ const int landlock_abi_version = 7; * - %E2BIG: @attr or @size inconsistencies; * - %EFAULT: @attr or @size inconsistencies; * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs. + * + * .. kernel-doc:: include/uapi/linux/landlock.h + * :identifiers: landlock_create_ruleset_flags */ SYSCALL_DEFINE3(landlock_create_ruleset, const struct landlock_ruleset_attr __user *const, attr, @@ -452,18 +451,15 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, * @ruleset_fd: File descriptor tied to the ruleset to merge with the target. * @flags: Supported values: * - * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF - * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON - * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF + * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF + * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON + * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF * * This system call enables to enforce a Landlock ruleset on the current * thread. Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its * namespace or is running with no_new_privs. This avoids scenarios where * unprivileged tasks can affect the behavior of privileged children. * - * It is allowed to only pass the %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF - * flag with a @ruleset_fd value of -1. - * * Possible returned errors are: * * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; @@ -475,6 +471,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, * %CAP_SYS_ADMIN in its namespace. * - %E2BIG: The maximum number of stacked rulesets is reached for the current * thread. + * + * .. kernel-doc:: include/uapi/linux/landlock.h + * :identifiers: landlock_restrict_self_flags */ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, flags) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index b649049b6a11..3a411064fa34 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -225,6 +225,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking14panic_nounwind") || str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || + str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || strstr(func->name, "_4core9panicking13assert_failed") || strstr(func->name, "_4core9panicking11panic_const24panic_const_") || diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index 2c720e3ecad5..fdc7170639e6 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -950,5 +950,5 @@ SCX_OPS_DEFINE(flatcg_ops, .cgroup_move = (void *)fcg_cgroup_move, .init = (void *)fcg_init, .exit = (void *)fcg_exit, - .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING, + .flags = SCX_OPS_ENQ_EXITING, .name = "flatcg"); diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py index 78a474a5b95f..f00cb89fdef6 100644 --- a/tools/testing/kunit/qemu_configs/sh.py +++ b/tools/testing/kunit/qemu_configs/sh.py @@ -7,7 +7,9 @@ CONFIG_CPU_SUBTYPE_SH7751R=y CONFIG_MEMORY_START=0x0c000000 CONFIG_SH_RTS7751R2D=y CONFIG_RTS7751R2D_PLUS=y -CONFIG_SERIAL_SH_SCI=y''', +CONFIG_SERIAL_SH_SCI=y +CONFIG_CMDLINE_EXTEND=y +''', qemu_arch='sh4', kernel_path='arch/sh/boot/zImage', kernel_command_line='console=ttySC1', diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc index 6b94b678741a..f656bccb1a14 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc @@ -7,11 +7,32 @@ MAX_ARGS=128 EXCEED_ARGS=$((MAX_ARGS + 1)) +# bash and dash evaluate variables differently. +# dash will evaluate '\\' every time it is read whereas bash does not. +# +# TEST_STRING="$TEST_STRING \\$i" +# echo $TEST_STRING +# +# With i=123 +# On bash, that will print "\123" +# but on dash, that will print the escape sequence of \123 as the \ will +# be interpreted again in the echo. +# +# Set a variable "bs" to save a double backslash, then echo that +# to "ts" to see if $ts changed or not. If it changed, it's dash, +# if not, it's bash, and then bs can equal a single backslash. +bs='\\' +ts=`echo $bs` +if [ "$ts" = '\\' ]; then + # this is bash + bs='\' +fi + check_max_args() { # event_header TEST_STRING=$1 # Acceptable for i in `seq 1 $MAX_ARGS`; do - TEST_STRING="$TEST_STRING \\$i" + TEST_STRING="$TEST_STRING $bs$i" done echo "$TEST_STRING" >> dynamic_events echo > dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index 118247b8dd84..c62165fabd0c 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -80,6 +80,26 @@ if [ $misscnt -gt 0 ]; then exit_fail fi +# Check strings too +if [ -f events/syscalls/sys_enter_openat/filter ]; then + DIRNAME=`basename $TMPDIR` + echo "filename.ustring ~ \"*$DIRNAME*\"" > events/syscalls/sys_enter_openat/filter + echo 1 > events/syscalls/sys_enter_openat/enable + echo 1 > tracing_on + ls /bin/sh + nocnt=`grep openat trace | wc -l` + ls $TMPDIR + echo 0 > tracing_on + hitcnt=`grep openat trace | wc -l`; + echo 0 > events/syscalls/sys_enter_openat/enable + if [ $nocnt -gt 0 ]; then + exit_fail + fi + if [ $hitcnt -eq 0 ]; then + exit_fail + fi +fi + reset_events_filter exit 0 diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h index b9054086a0c9..18a6014920b5 100644 --- a/tools/testing/selftests/landlock/audit.h +++ b/tools/testing/selftests/landlock/audit.h @@ -300,15 +300,22 @@ out: return err; } -static int __maybe_unused matches_log_domain_allocated(int audit_fd, +static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid, __u64 *domain_id) { - return audit_match_record( - audit_fd, AUDIT_LANDLOCK_DOMAIN, - REGEX_LANDLOCK_PREFIX - " status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+" - " exe=\"[^\"]\\+\" comm=\".*_test\"$", - domain_id); + static const char log_template[] = REGEX_LANDLOCK_PREFIX + " status=allocated mode=enforcing pid=%d uid=[0-9]\\+" + " exe=\"[^\"]\\+\" comm=\".*_test\"$"; + char log_match[sizeof(log_template) + 10]; + int log_match_len; + + log_match_len = + snprintf(log_match, sizeof(log_match), log_template, pid); + if (log_match_len > sizeof(log_match)) + return -E2BIG; + + return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match, + domain_id); } static int __maybe_unused matches_log_domain_deallocated( diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c index a0643070c403..cfc571afd0eb 100644 --- a/tools/testing/selftests/landlock/audit_test.c +++ b/tools/testing/selftests/landlock/audit_test.c @@ -9,6 +9,7 @@ #include <errno.h> #include <limits.h> #include <linux/landlock.h> +#include <pthread.h> #include <stdlib.h> #include <sys/mount.h> #include <sys/prctl.h> @@ -40,7 +41,6 @@ FIXTURE(audit) { struct audit_filter audit_filter; int audit_fd; - __u64(*domain_stack)[16]; }; FIXTURE_SETUP(audit) @@ -60,18 +60,10 @@ FIXTURE_SETUP(audit) TH_LOG("Failed to initialize audit: %s", error_msg); } clear_cap(_metadata, CAP_AUDIT_CONTROL); - - self->domain_stack = mmap(NULL, sizeof(*self->domain_stack), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, -1, 0); - ASSERT_NE(MAP_FAILED, self->domain_stack); - memset(self->domain_stack, 0, sizeof(*self->domain_stack)); } FIXTURE_TEARDOWN(audit) { - EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack))); - set_cap(_metadata, CAP_AUDIT_CONTROL); EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter)); clear_cap(_metadata, CAP_AUDIT_CONTROL); @@ -83,9 +75,15 @@ TEST_F(audit, layers) .scoped = LANDLOCK_SCOPE_SIGNAL, }; int status, ruleset_fd, i; + __u64(*domain_stack)[16]; __u64 prev_dom = 3; pid_t child; + domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, domain_stack); + memset(domain_stack, 0, sizeof(*domain_stack)); + ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); ASSERT_LE(0, ruleset_fd); @@ -94,7 +92,7 @@ TEST_F(audit, layers) child = fork(); ASSERT_LE(0, child); if (child == 0) { - for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) { + for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) { __u64 denial_dom = 1; __u64 allocated_dom = 2; @@ -107,7 +105,8 @@ TEST_F(audit, layers) matches_log_signal(_metadata, self->audit_fd, getppid(), &denial_dom)); EXPECT_EQ(0, matches_log_domain_allocated( - self->audit_fd, &allocated_dom)); + self->audit_fd, getpid(), + &allocated_dom)); EXPECT_NE(denial_dom, 1); EXPECT_NE(denial_dom, 0); EXPECT_EQ(denial_dom, allocated_dom); @@ -115,7 +114,7 @@ TEST_F(audit, layers) /* Checks that the new domain is younger than the previous one. */ EXPECT_GT(allocated_dom, prev_dom); prev_dom = allocated_dom; - (*self->domain_stack)[i] = allocated_dom; + (*domain_stack)[i] = allocated_dom; } /* Checks that we reached the maximum number of layers. */ @@ -142,23 +141,143 @@ TEST_F(audit, layers) /* Purges log from deallocated domains. */ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_dom_drop, sizeof(audit_tv_dom_drop))); - for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) { + for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) { __u64 deallocated_dom = 2; EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1, &deallocated_dom)); - EXPECT_EQ((*self->domain_stack)[i], deallocated_dom) + EXPECT_EQ((*domain_stack)[i], deallocated_dom) { TH_LOG("Failed to match domain %llx (#%d)", - (*self->domain_stack)[i], i); + (*domain_stack)[i], i); } } + EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack))); EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default, sizeof(audit_tv_default))); - EXPECT_EQ(0, close(ruleset_fd)); } +struct thread_data { + pid_t parent_pid; + int ruleset_fd, pipe_child, pipe_parent; +}; + +static void *thread_audit_test(void *arg) +{ + const struct thread_data *data = (struct thread_data *)arg; + uintptr_t err = 0; + char buffer; + + /* TGID and TID are different for a second thread. */ + if (getpid() == gettid()) { + err = 1; + goto out; + } + + if (landlock_restrict_self(data->ruleset_fd, 0)) { + err = 2; + goto out; + } + + if (close(data->ruleset_fd)) { + err = 3; + goto out; + } + + /* Creates a denial to get the domain ID. */ + if (kill(data->parent_pid, 0) != -1) { + err = 4; + goto out; + } + + if (EPERM != errno) { + err = 5; + goto out; + } + + /* Signals the parent to read denial logs. */ + if (write(data->pipe_child, ".", 1) != 1) { + err = 6; + goto out; + } + + /* Waits for the parent to update audit filters. */ + if (read(data->pipe_parent, &buffer, 1) != 1) { + err = 7; + goto out; + } + +out: + close(data->pipe_child); + close(data->pipe_parent); + return (void *)err; +} + +/* Checks that the PID tied to a domain is not a TID but the TGID. */ +TEST_F(audit, thread) +{ + const struct landlock_ruleset_attr ruleset_attr = { + .scoped = LANDLOCK_SCOPE_SIGNAL, + }; + __u64 denial_dom = 1; + __u64 allocated_dom = 2; + __u64 deallocated_dom = 3; + pthread_t thread; + int pipe_child[2], pipe_parent[2]; + char buffer; + struct thread_data child_data; + + child_data.parent_pid = getppid(); + ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC)); + child_data.pipe_child = pipe_child[1]; + ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC)); + child_data.pipe_parent = pipe_parent[0]; + child_data.ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, child_data.ruleset_fd); + + /* TGID and TID are the same for the initial thread . */ + EXPECT_EQ(getpid(), gettid()); + EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); + ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test, + &child_data)); + + /* Waits for the child to generate a denial. */ + ASSERT_EQ(1, read(pipe_child[0], &buffer, 1)); + EXPECT_EQ(0, close(pipe_child[0])); + + /* Matches the signal log to get the domain ID. */ + EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd, + child_data.parent_pid, &denial_dom)); + EXPECT_NE(denial_dom, 1); + EXPECT_NE(denial_dom, 0); + + EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(), + &allocated_dom)); + EXPECT_EQ(denial_dom, allocated_dom); + + /* Updates filter rules to match the drop record. */ + set_cap(_metadata, CAP_AUDIT_CONTROL); + EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE)); + EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter, + AUDIT_DEL_RULE)); + clear_cap(_metadata, CAP_AUDIT_CONTROL); + + /* Signals the thread to exit, which will generate a domain deallocation. */ + ASSERT_EQ(1, write(pipe_parent[1], ".", 1)); + EXPECT_EQ(0, close(pipe_parent[1])); + ASSERT_EQ(0, pthread_join(thread, NULL)); + + EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO, + &audit_tv_dom_drop, sizeof(audit_tv_dom_drop))); + EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1, + &deallocated_dom)); + EXPECT_EQ(denial_dom, deallocated_dom); + EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO, + &audit_tv_default, sizeof(audit_tv_default))); +} + FIXTURE(audit_flags) { struct audit_filter audit_filter; @@ -273,7 +392,8 @@ TEST_F(audit_flags, signal) /* Checks domain information records. */ EXPECT_EQ(0, matches_log_domain_allocated( - self->audit_fd, &allocated_dom)); + self->audit_fd, getpid(), + &allocated_dom)); EXPECT_NE(*self->domain_id, 1); EXPECT_NE(*self->domain_id, 0); EXPECT_EQ(*self->domain_id, allocated_dom); diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index f819011a8798..73729382d40f 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -5964,7 +5964,8 @@ TEST_F(audit_layout1, refer_handled) EXPECT_EQ(EXDEV, errno); EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer", dir_s1d1)); - EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL)); + EXPECT_EQ(0, + matches_log_domain_allocated(self->audit_fd, getpid(), NULL)); EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer", dir_s1d3)); diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config index 81a1f64a22e8..377b3699ff31 100644 --- a/tools/testing/selftests/lib/config +++ b/tools/testing/selftests/lib/config @@ -1,2 +1,3 @@ CONFIG_TEST_BITMAP=m +CONFIG_PRIME_NUMBERS=m CONFIG_TEST_BITOPS=m diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile index c7781efea0f3..ec4624a283bc 100644 --- a/tools/testing/selftests/ublk/Makefile +++ b/tools/testing/selftests/ublk/Makefile @@ -6,6 +6,9 @@ LDLIBS += -lpthread -lm -luring TEST_PROGS := test_generic_01.sh TEST_PROGS += test_generic_02.sh TEST_PROGS += test_generic_03.sh +TEST_PROGS += test_generic_04.sh +TEST_PROGS += test_generic_05.sh +TEST_PROGS += test_generic_06.sh TEST_PROGS += test_null_01.sh TEST_PROGS += test_null_02.sh @@ -21,12 +24,16 @@ TEST_PROGS += test_stripe_04.sh TEST_PROGS += test_stress_01.sh TEST_PROGS += test_stress_02.sh +TEST_PROGS += test_stress_03.sh +TEST_PROGS += test_stress_04.sh +TEST_PROGS += test_stress_05.sh TEST_GEN_PROGS_EXTENDED = kublk include ../lib.mk -$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c +$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \ + fault_inject.c check: shellcheck -x -f gcc *.sh diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c new file mode 100644 index 000000000000..94a8e729ba4c --- /dev/null +++ b/tools/testing/selftests/ublk/fault_inject.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Fault injection ublk target. Hack this up however you like for + * testing specific behaviors of ublk_drv. Currently is a null target + * with a configurable delay before completing each I/O. This delay can + * be used to test ublk_drv's handling of I/O outstanding to the ublk + * server when it dies. + */ + +#include "kublk.h" + +static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx, + struct ublk_dev *dev) +{ + const struct ublksrv_ctrl_dev_info *info = &dev->dev_info; + unsigned long dev_size = 250UL << 30; + + dev->tgt.dev_size = dev_size; + dev->tgt.params = (struct ublk_params) { + .types = UBLK_PARAM_TYPE_BASIC, + .basic = { + .logical_bs_shift = 9, + .physical_bs_shift = 12, + .io_opt_shift = 12, + .io_min_shift = 9, + .max_sectors = info->max_io_buf_bytes >> 9, + .dev_sectors = dev_size >> 9, + }, + }; + + dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000); + return 0; +} + +static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag) +{ + const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); + struct io_uring_sqe *sqe; + struct __kernel_timespec ts = { + .tv_nsec = (long long)q->dev->private_data, + }; + + ublk_queue_alloc_sqes(q, &sqe, 1); + io_uring_prep_timeout(sqe, &ts, 1, 0); + sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1); + + ublk_queued_tgt_io(q, tag, 1); + + return 0; +} + +static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag, + const struct io_uring_cqe *cqe) +{ + const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); + + if (cqe->res != -ETIME) + ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res); + + if (ublk_completed_tgt_io(q, tag)) + ublk_complete_io(q, tag, iod->nr_sectors << 9); + else + ublk_err("%s: io not complete after 1 cqe\n", __func__); +} + +static void ublk_fault_inject_cmd_line(struct dev_ctx *ctx, int argc, char *argv[]) +{ + static const struct option longopts[] = { + { "delay_us", 1, NULL, 0 }, + { 0, 0, 0, 0 } + }; + int option_idx, opt; + + ctx->fault_inject.delay_us = 0; + while ((opt = getopt_long(argc, argv, "", + longopts, &option_idx)) != -1) { + switch (opt) { + case 0: + if (!strcmp(longopts[option_idx].name, "delay_us")) + ctx->fault_inject.delay_us = strtoll(optarg, NULL, 10); + } + } +} + +static void ublk_fault_inject_usage(const struct ublk_tgt_ops *ops) +{ + printf("\tfault_inject: [--delay_us us (default 0)]\n"); +} + +const struct ublk_tgt_ops fault_inject_tgt_ops = { + .name = "fault_inject", + .init_tgt = ublk_fault_inject_tgt_init, + .queue_io = ublk_fault_inject_queue_io, + .tgt_io_done = ublk_fault_inject_tgt_io_done, + .parse_cmd_line = ublk_fault_inject_cmd_line, + .usage = ublk_fault_inject_usage, +}; diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 91c282bc7674..759f06637146 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -5,22 +5,24 @@ #include "kublk.h" +#define MAX_NR_TGT_ARG 64 + unsigned int ublk_dbg_mask = UBLK_LOG; static const struct ublk_tgt_ops *tgt_ops_list[] = { &null_tgt_ops, &loop_tgt_ops, &stripe_tgt_ops, + &fault_inject_tgt_ops, }; static const struct ublk_tgt_ops *ublk_find_tgt(const char *name) { - const struct ublk_tgt_ops *ops; int i; if (name == NULL) return NULL; - for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++) + for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) if (strcmp(tgt_ops_list[i]->name, name) == 0) return tgt_ops_list[i]; return NULL; @@ -118,6 +120,27 @@ static int ublk_ctrl_start_dev(struct ublk_dev *dev, return __ublk_ctrl_cmd(dev, &data); } +static int ublk_ctrl_start_user_recovery(struct ublk_dev *dev) +{ + struct ublk_ctrl_cmd_data data = { + .cmd_op = UBLK_U_CMD_START_USER_RECOVERY, + }; + + return __ublk_ctrl_cmd(dev, &data); +} + +static int ublk_ctrl_end_user_recovery(struct ublk_dev *dev, int daemon_pid) +{ + struct ublk_ctrl_cmd_data data = { + .cmd_op = UBLK_U_CMD_END_USER_RECOVERY, + .flags = CTRL_CMD_HAS_DATA, + }; + + dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid; + + return __ublk_ctrl_cmd(dev, &data); +} + static int ublk_ctrl_add_dev(struct ublk_dev *dev) { struct ublk_ctrl_cmd_data data = { @@ -207,10 +230,73 @@ static const char *ublk_dev_state_desc(struct ublk_dev *dev) }; } +static void ublk_print_cpu_set(const cpu_set_t *set, char *buf, unsigned len) +{ + unsigned done = 0; + int i; + + for (i = 0; i < CPU_SETSIZE; i++) { + if (CPU_ISSET(i, set)) + done += snprintf(&buf[done], len - done, "%d ", i); + } +} + +static void ublk_adjust_affinity(cpu_set_t *set) +{ + int j, updated = 0; + + /* + * Just keep the 1st CPU now. + * + * In future, auto affinity selection can be tried. + */ + for (j = 0; j < CPU_SETSIZE; j++) { + if (CPU_ISSET(j, set)) { + if (!updated) { + updated = 1; + continue; + } + CPU_CLR(j, set); + } + } +} + +/* Caller must free the allocated buffer */ +static int ublk_ctrl_get_affinity(struct ublk_dev *ctrl_dev, cpu_set_t **ptr_buf) +{ + struct ublk_ctrl_cmd_data data = { + .cmd_op = UBLK_U_CMD_GET_QUEUE_AFFINITY, + .flags = CTRL_CMD_HAS_DATA | CTRL_CMD_HAS_BUF, + }; + cpu_set_t *buf; + int i, ret; + + buf = malloc(sizeof(cpu_set_t) * ctrl_dev->dev_info.nr_hw_queues); + if (!buf) + return -ENOMEM; + + for (i = 0; i < ctrl_dev->dev_info.nr_hw_queues; i++) { + data.data[0] = i; + data.len = sizeof(cpu_set_t); + data.addr = (__u64)&buf[i]; + + ret = __ublk_ctrl_cmd(ctrl_dev, &data); + if (ret < 0) { + free(buf); + return ret; + } + ublk_adjust_affinity(&buf[i]); + } + + *ptr_buf = buf; + return 0; +} + static void ublk_ctrl_dump(struct ublk_dev *dev) { struct ublksrv_ctrl_dev_info *info = &dev->dev_info; struct ublk_params p; + cpu_set_t *affinity; int ret; ret = ublk_ctrl_get_params(dev, &p); @@ -219,12 +305,31 @@ static void ublk_ctrl_dump(struct ublk_dev *dev) return; } + ret = ublk_ctrl_get_affinity(dev, &affinity); + if (ret < 0) { + ublk_err("failed to get affinity %m\n"); + return; + } + ublk_log("dev id %d: nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n", info->dev_id, info->nr_hw_queues, info->queue_depth, 1 << p.basic.logical_bs_shift, p.basic.dev_sectors); ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n", info->max_io_buf_bytes, info->ublksrv_pid, info->flags, ublk_dev_state_desc(dev)); + + if (affinity) { + char buf[512]; + int i; + + for (i = 0; i < info->nr_hw_queues; i++) { + ublk_print_cpu_set(&affinity[i], buf, sizeof(buf)); + printf("\tqueue %u: tid %d affinity(%s)\n", + i, dev->q[i].tid, buf); + } + free(affinity); + } + fflush(stdout); } @@ -347,7 +452,9 @@ static int ublk_queue_init(struct ublk_queue *q) } ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth, - IORING_SETUP_COOP_TASKRUN); + IORING_SETUP_COOP_TASKRUN | + IORING_SETUP_SINGLE_ISSUER | + IORING_SETUP_DEFER_TASKRUN); if (ret < 0) { ublk_err("ublk dev %d queue %d setup io_uring failed %d\n", q->dev->dev_info.dev_id, q->q_id, ret); @@ -602,9 +709,24 @@ static int ublk_process_io(struct ublk_queue *q) return reapped; } +static void ublk_queue_set_sched_affinity(const struct ublk_queue *q, + cpu_set_t *cpuset) +{ + if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0) + ublk_err("ublk dev %u queue %u set affinity failed", + q->dev->dev_info.dev_id, q->q_id); +} + +struct ublk_queue_info { + struct ublk_queue *q; + sem_t *queue_sem; + cpu_set_t *affinity; +}; + static void *ublk_io_handler_fn(void *data) { - struct ublk_queue *q = data; + struct ublk_queue_info *info = data; + struct ublk_queue *q = info->q; int dev_id = q->dev->dev_info.dev_id; int ret; @@ -614,6 +736,10 @@ static void *ublk_io_handler_fn(void *data) dev_id, q->q_id); return NULL; } + /* IO perf is sensitive with queue pthread affinity on NUMA machine*/ + ublk_queue_set_sched_affinity(q, info->affinity); + sem_post(info->queue_sem); + ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n", q->tid, dev_id, q->q_id); @@ -639,7 +765,7 @@ static void ublk_set_parameters(struct ublk_dev *dev) dev->dev_info.dev_id, ret); } -static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id) +static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev, int dev_id) { uint64_t id; int evtfd = ctx->_evtfd; @@ -652,36 +778,68 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id) else id = ERROR_EVTFD_DEVID; + if (dev && ctx->shadow_dev) + memcpy(&ctx->shadow_dev->q, &dev->q, sizeof(dev->q)); + if (write(evtfd, &id, sizeof(id)) != sizeof(id)) return -EINVAL; + close(evtfd); + shmdt(ctx->shadow_dev); + return 0; } static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) { - int ret, i; - void *thread_ret; const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info; + struct ublk_queue_info *qinfo; + cpu_set_t *affinity_buf; + void *thread_ret; + sem_t queue_sem; + int ret, i; ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__); + qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info), + dinfo->nr_hw_queues); + if (!qinfo) + return -ENOMEM; + + sem_init(&queue_sem, 0, 0); ret = ublk_dev_prep(ctx, dev); if (ret) return ret; + ret = ublk_ctrl_get_affinity(dev, &affinity_buf); + if (ret) + return ret; + for (i = 0; i < dinfo->nr_hw_queues; i++) { dev->q[i].dev = dev; dev->q[i].q_id = i; + + qinfo[i].q = &dev->q[i]; + qinfo[i].queue_sem = &queue_sem; + qinfo[i].affinity = &affinity_buf[i]; pthread_create(&dev->q[i].thread, NULL, ublk_io_handler_fn, - &dev->q[i]); + &qinfo[i]); } + for (i = 0; i < dinfo->nr_hw_queues; i++) + sem_wait(&queue_sem); + free(qinfo); + free(affinity_buf); + /* everything is fine now, start us */ - ublk_set_parameters(dev); - ret = ublk_ctrl_start_dev(dev, getpid()); + if (ctx->recovery) + ret = ublk_ctrl_end_user_recovery(dev, getpid()); + else { + ublk_set_parameters(dev); + ret = ublk_ctrl_start_dev(dev, getpid()); + } if (ret < 0) { ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret); goto fail; @@ -691,7 +849,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) if (ctx->fg) ublk_ctrl_dump(dev); else - ublk_send_dev_event(ctx, dev->dev_info.dev_id); + ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id); /* wait until we are terminated */ for (i = 0; i < dinfo->nr_hw_queues; i++) @@ -856,7 +1014,10 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) } } - ret = ublk_ctrl_add_dev(dev); + if (ctx->recovery) + ret = ublk_ctrl_start_user_recovery(dev); + else + ret = ublk_ctrl_add_dev(dev); if (ret < 0) { ublk_err("%s: can't add dev id %d, type %s ret %d\n", __func__, dev_id, tgt_type, ret); @@ -870,7 +1031,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) fail: if (ret < 0) - ublk_send_dev_event(ctx, -1); + ublk_send_dev_event(ctx, dev, -1); ublk_ctrl_deinit(dev); return ret; } @@ -884,30 +1045,58 @@ static int cmd_dev_add(struct dev_ctx *ctx) if (ctx->fg) goto run; + ctx->_shmid = shmget(IPC_PRIVATE, sizeof(struct ublk_dev), IPC_CREAT | 0666); + if (ctx->_shmid < 0) { + ublk_err("%s: failed to shmget %s\n", __func__, strerror(errno)); + exit(-1); + } + ctx->shadow_dev = (struct ublk_dev *)shmat(ctx->_shmid, NULL, 0); + if (ctx->shadow_dev == (struct ublk_dev *)-1) { + ublk_err("%s: failed to shmat %s\n", __func__, strerror(errno)); + exit(-1); + } ctx->_evtfd = eventfd(0, 0); if (ctx->_evtfd < 0) { ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno)); exit(-1); } - setsid(); res = fork(); if (res == 0) { + int res2; + + setsid(); + res2 = fork(); + if (res2 == 0) { + /* prepare for detaching */ + close(STDIN_FILENO); + close(STDOUT_FILENO); + close(STDERR_FILENO); run: - res = __cmd_dev_add(ctx); - return res; + res = __cmd_dev_add(ctx); + return res; + } else { + /* detached from the foreground task */ + exit(EXIT_SUCCESS); + } } else if (res > 0) { uint64_t id; + int exit_code = EXIT_FAILURE; res = read(ctx->_evtfd, &id, sizeof(id)); close(ctx->_evtfd); if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) { ctx->dev_id = id - 1; - return __cmd_dev_list(ctx); + if (__cmd_dev_list(ctx) >= 0) + exit_code = EXIT_SUCCESS; } - exit(EXIT_FAILURE); + shmdt(ctx->shadow_dev); + shmctl(ctx->_shmid, IPC_RMID, NULL); + /* wait for child and detach from it */ + wait(NULL); + exit(exit_code); } else { - return res; + exit(EXIT_FAILURE); } } @@ -969,6 +1158,9 @@ static int __cmd_dev_list(struct dev_ctx *ctx) ublk_err("%s: can't get dev info from %d: %d\n", __func__, ctx->dev_id, ret); } else { + if (ctx->shadow_dev) + memcpy(&dev->q, ctx->shadow_dev->q, sizeof(dev->q)); + ublk_ctrl_dump(dev); } @@ -1039,14 +1231,47 @@ static int cmd_dev_get_features(void) return ret; } +static void __cmd_create_help(char *exe, bool recovery) +{ + int i; + + printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n", + exe, recovery ? "recover" : "add"); + printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g 0|1]\n"); + printf("\t[-e 0|1 ] [-i 0|1]\n"); + printf("\t[target options] [backfile1] [backfile2] ...\n"); + printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n"); + + for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) { + const struct ublk_tgt_ops *ops = tgt_ops_list[i]; + + if (ops->usage) + ops->usage(ops); + } +} + +static void cmd_add_help(char *exe) +{ + __cmd_create_help(exe, false); + printf("\n"); +} + +static void cmd_recover_help(char *exe) +{ + __cmd_create_help(exe, true); + printf("\tPlease provide exact command line for creating this device with real dev_id\n"); + printf("\n"); +} + static int cmd_dev_help(char *exe) { - printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe); - printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n"); + cmd_add_help(exe); + cmd_recover_help(exe); + printf("%s del [-n dev_id] -a \n", exe); - printf("\t -a delete all devices -n delete specified device\n"); + printf("\t -a delete all devices -n delete specified device\n\n"); printf("%s list [-n dev_id] -a \n", exe); - printf("\t -a list all devices, -n list specified device, default -a \n"); + printf("\t -a list all devices, -n list specified device, default -a \n\n"); printf("%s features\n", exe); return 0; } @@ -1063,9 +1288,13 @@ int main(int argc, char *argv[]) { "quiet", 0, NULL, 0 }, { "zero_copy", 0, NULL, 'z' }, { "foreground", 0, NULL, 0 }, - { "chunk_size", 1, NULL, 0 }, + { "recovery", 1, NULL, 'r' }, + { "recovery_fail_io", 1, NULL, 'e'}, + { "recovery_reissue", 1, NULL, 'i'}, + { "get_data", 1, NULL, 'g'}, { 0, 0, 0, 0 } }; + const struct ublk_tgt_ops *ops = NULL; int option_idx, opt; const char *cmd = argv[1]; struct dev_ctx ctx = { @@ -1073,15 +1302,18 @@ int main(int argc, char *argv[]) .nr_hw_queues = 2, .dev_id = -1, .tgt_type = "unknown", - .chunk_size = 65536, /* def chunk size is 64K */ }; int ret = -EINVAL, i; + int tgt_argc = 1; + char *tgt_argv[MAX_NR_TGT_ARG] = { NULL }; + int value; if (argc == 1) return ret; + opterr = 0; optind = 2; - while ((opt = getopt_long(argc, argv, "t:n:d:q:az", + while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:az", longopts, &option_idx)) != -1) { switch (opt) { case 'a': @@ -1103,6 +1335,25 @@ int main(int argc, char *argv[]) case 'z': ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY; break; + case 'r': + value = strtol(optarg, NULL, 10); + if (value) + ctx.flags |= UBLK_F_USER_RECOVERY; + break; + case 'e': + value = strtol(optarg, NULL, 10); + if (value) + ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO; + break; + case 'i': + value = strtol(optarg, NULL, 10); + if (value) + ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE; + break; + case 'g': + value = strtol(optarg, NULL, 10); + if (value) + ctx.flags |= UBLK_F_NEED_GET_DATA; case 0: if (!strcmp(longopts[option_idx].name, "debug_mask")) ublk_dbg_mask = strtol(optarg, NULL, 16); @@ -1110,8 +1361,26 @@ int main(int argc, char *argv[]) ublk_dbg_mask = 0; if (!strcmp(longopts[option_idx].name, "foreground")) ctx.fg = 1; - if (!strcmp(longopts[option_idx].name, "chunk_size")) - ctx.chunk_size = strtol(optarg, NULL, 10); + break; + case '?': + /* + * target requires every option must have argument + */ + if (argv[optind][0] == '-' || argv[optind - 1][0] != '-') { + fprintf(stderr, "every target option requires argument: %s %s\n", + argv[optind - 1], argv[optind]); + exit(EXIT_FAILURE); + } + + if (tgt_argc < (MAX_NR_TGT_ARG - 1) / 2) { + tgt_argv[tgt_argc++] = argv[optind - 1]; + tgt_argv[tgt_argc++] = argv[optind]; + } else { + fprintf(stderr, "too many target options\n"); + exit(EXIT_FAILURE); + } + optind += 1; + break; } } @@ -1120,9 +1389,25 @@ int main(int argc, char *argv[]) ctx.files[ctx.nr_files++] = argv[i++]; } + ops = ublk_find_tgt(ctx.tgt_type); + if (ops && ops->parse_cmd_line) { + optind = 0; + + tgt_argv[0] = ctx.tgt_type; + ops->parse_cmd_line(&ctx, tgt_argc, tgt_argv); + } + if (!strcmp(cmd, "add")) ret = cmd_dev_add(&ctx); - else if (!strcmp(cmd, "del")) + else if (!strcmp(cmd, "recover")) { + if (ctx.dev_id < 0) { + fprintf(stderr, "device id isn't provided for recovering\n"); + ret = -EINVAL; + } else { + ctx.recovery = 1; + ret = cmd_dev_add(&ctx); + } + } else if (!strcmp(cmd, "del")) ret = cmd_dev_del(&ctx); else if (!strcmp(cmd, "list")) { ctx.all = 1; diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 760ff8ffb810..29571eb296f1 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -20,9 +20,15 @@ #include <sys/wait.h> #include <sys/eventfd.h> #include <sys/uio.h> +#include <sys/ipc.h> +#include <sys/shm.h> +#include <linux/io_uring.h> #include <liburing.h> -#include <linux/ublk_cmd.h> +#include <semaphore.h> + +/* allow ublk_dep.h to override ublk_cmd.h */ #include "ublk_dep.h" +#include <linux/ublk_cmd.h> #define __maybe_unused __attribute__((unused)) #define MAX_BACK_FILES 4 @@ -30,6 +36,8 @@ #define min(a, b) ((a) < (b) ? (a) : (b)) #endif +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + /****************** part 1: libublk ********************/ #define CTRL_DEV "/dev/ublk-control" @@ -42,8 +50,8 @@ #define UBLKSRV_IO_IDLE_SECS 20 #define UBLK_IO_MAX_BYTES (1 << 20) -#define UBLK_MAX_QUEUES 4 -#define UBLK_QUEUE_DEPTH 128 +#define UBLK_MAX_QUEUES 32 +#define UBLK_QUEUE_DEPTH 1024 #define UBLK_DBG_DEV (1U << 0) #define UBLK_DBG_QUEUE (1U << 1) @@ -55,6 +63,16 @@ struct ublk_dev; struct ublk_queue; +struct stripe_ctx { + /* stripe */ + unsigned int chunk_size; +}; + +struct fault_inject_ctx { + /* fault_inject */ + unsigned long delay_us; +}; + struct dev_ctx { char tgt_type[16]; unsigned long flags; @@ -66,11 +84,21 @@ struct dev_ctx { unsigned int logging:1; unsigned int all:1; unsigned int fg:1; + unsigned int recovery:1; - /* stripe */ - unsigned int chunk_size; + /* fault_inject */ + long long delay_us; int _evtfd; + int _shmid; + + /* built from shmem, only for ublk_dump_dev() */ + struct ublk_dev *shadow_dev; + + union { + struct stripe_ctx stripe; + struct fault_inject_ctx fault_inject; + }; }; struct ublk_ctrl_cmd_data { @@ -107,6 +135,14 @@ struct ublk_tgt_ops { int (*queue_io)(struct ublk_queue *, int tag); void (*tgt_io_done)(struct ublk_queue *, int tag, const struct io_uring_cqe *); + + /* + * Target specific command line handling + * + * each option requires argument for target command line + */ + void (*parse_cmd_line)(struct dev_ctx *ctx, int argc, char *argv[]); + void (*usage)(const struct ublk_tgt_ops *ops); }; struct ublk_tgt { @@ -357,6 +393,7 @@ static inline int ublk_queue_use_zc(const struct ublk_queue *q) extern const struct ublk_tgt_ops null_tgt_ops; extern const struct ublk_tgt_ops loop_tgt_ops; extern const struct ublk_tgt_ops stripe_tgt_ops; +extern const struct ublk_tgt_ops fault_inject_tgt_ops; void backing_file_tgt_deinit(struct ublk_dev *dev); int backing_file_tgt_init(struct ublk_dev *dev); diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c index 179731c3dd6f..5dbd6392d83d 100644 --- a/tools/testing/selftests/ublk/stripe.c +++ b/tools/testing/selftests/ublk/stripe.c @@ -281,7 +281,7 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev) .max_sectors = dev->dev_info.max_io_buf_bytes >> 9, }, }; - unsigned chunk_size = ctx->chunk_size; + unsigned chunk_size = ctx->stripe.chunk_size; struct stripe_conf *conf; unsigned chunk_shift; loff_t bytes = 0; @@ -344,10 +344,36 @@ static void ublk_stripe_tgt_deinit(struct ublk_dev *dev) backing_file_tgt_deinit(dev); } +static void ublk_stripe_cmd_line(struct dev_ctx *ctx, int argc, char *argv[]) +{ + static const struct option longopts[] = { + { "chunk_size", 1, NULL, 0 }, + { 0, 0, 0, 0 } + }; + int option_idx, opt; + + ctx->stripe.chunk_size = 65536; + while ((opt = getopt_long(argc, argv, "", + longopts, &option_idx)) != -1) { + switch (opt) { + case 0: + if (!strcmp(longopts[option_idx].name, "chunk_size")) + ctx->stripe.chunk_size = strtol(optarg, NULL, 10); + } + } +} + +static void ublk_stripe_usage(const struct ublk_tgt_ops *ops) +{ + printf("\tstripe: [--chunk_size chunk_size (default 65536)]\n"); +} + const struct ublk_tgt_ops stripe_tgt_ops = { .name = "stripe", .init_tgt = ublk_stripe_tgt_init, .deinit_tgt = ublk_stripe_tgt_deinit, .queue_io = ublk_stripe_queue_io, .tgt_io_done = ublk_stripe_io_done, + .parse_cmd_line = ublk_stripe_cmd_line, + .usage = ublk_stripe_usage, }; diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh index a88b35943227..9fc111f64576 100755 --- a/tools/testing/selftests/ublk/test_common.sh +++ b/tools/testing/selftests/ublk/test_common.sh @@ -30,18 +30,26 @@ _run_fio_verify_io() { } _create_backfile() { - local my_size=$1 - local my_file + local index=$1 + local new_size=$2 + local old_file + local new_file - my_file=$(mktemp ublk_file_"${my_size}"_XXXXX) - truncate -s "${my_size}" "${my_file}" - echo "$my_file" + old_file="${UBLK_BACKFILES[$index]}" + [ -f "$old_file" ] && rm -f "$old_file" + + new_file=$(mktemp ublk_file_"${new_size}"_XXXXX) + truncate -s "${new_size}" "${new_file}" + UBLK_BACKFILES["$index"]="$new_file" } -_remove_backfile() { - local file=$1 +_remove_files() { + local file - [ -f "$file" ] && rm -f "$file" + for file in "${UBLK_BACKFILES[@]}"; do + [ -f "$file" ] && rm -f "$file" + done + [ -f "$UBLK_TMP" ] && rm -f "$UBLK_TMP" } _create_tmp_dir() { @@ -106,6 +114,7 @@ _prep_test() { local type=$1 shift 1 modprobe ublk_drv > /dev/null 2>&1 + UBLK_TMP=$(mktemp ublk_test_XXXXX) [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*" } @@ -129,7 +138,10 @@ _show_result() echo "$1 : [FAIL]" fi fi - [ "$2" -ne 0 ] && exit "$2" + if [ "$2" -ne 0 ]; then + _remove_files + exit "$2" + fi return 0 } @@ -138,16 +150,16 @@ _check_add_dev() { local tid=$1 local code=$2 - shift 2 + if [ "${code}" -ne 0 ]; then - _remove_test_files "$@" _show_result "${tid}" "${code}" fi } _cleanup_test() { "${UBLK_PROG}" del -a - rm -f "$UBLK_TMP" + + _remove_files } _have_feature() @@ -158,9 +170,11 @@ _have_feature() return 1 } -_add_ublk_dev() { - local kublk_temp; +_create_ublk_dev() { local dev_id; + local cmd=$1 + + shift 1 if [ ! -c /dev/ublk-control ]; then return ${UBLK_SKIP_CODE} @@ -171,17 +185,34 @@ _add_ublk_dev() { fi fi - kublk_temp=$(mktemp /tmp/kublk-XXXXXX) - if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then + if ! dev_id=$("${UBLK_PROG}" "$cmd" "$@" | grep "dev id" | awk -F '[ :]' '{print $3}'); then echo "fail to add ublk dev $*" - rm -f "${kublk_temp}" return 255 fi - - dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}') udevadm settle - rm -f "${kublk_temp}" - echo "${dev_id}" + + if [[ "$dev_id" =~ ^[0-9]+$ ]]; then + echo "${dev_id}" + else + return 255 + fi +} + +_add_ublk_dev() { + _create_ublk_dev "add" "$@" +} + +_recover_ublk_dev() { + local dev_id + local state + + dev_id=$(_create_ublk_dev "recover" "$@") + for ((j=0;j<20;j++)); do + state=$(_get_ublk_dev_state "${dev_id}") + [ "$state" == "LIVE" ] && break + sleep 1 + done + echo "$state" } # kill the ublk daemon and return ublk device state @@ -220,7 +251,7 @@ __run_io_and_remove() local kill_server=$3 fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \ - --rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \ + --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \ --runtime=20 --time_based > /dev/null 2>&1 & sleep 2 if [ "${kill_server}" = "yes" ]; then @@ -238,15 +269,80 @@ __run_io_and_remove() wait } +run_io_and_remove() +{ + local size=$1 + local dev_id + shift 1 + + dev_id=$(_add_ublk_dev "$@") + _check_add_dev "$TID" $? + + [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)" + if ! __run_io_and_remove "$dev_id" "${size}" "no"; then + echo "/dev/ublkc$dev_id isn't removed" + exit 255 + fi +} + +run_io_and_kill_daemon() +{ + local size=$1 + local dev_id + shift 1 + + dev_id=$(_add_ublk_dev "$@") + _check_add_dev "$TID" $? + + [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)" + if ! __run_io_and_remove "$dev_id" "${size}" "yes"; then + echo "/dev/ublkc$dev_id isn't removed res ${res}" + exit 255 + fi +} + +run_io_and_recover() +{ + local state + local dev_id + + dev_id=$(_add_ublk_dev "$@") + _check_add_dev "$TID" $? + + fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \ + --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \ + --runtime=20 --time_based > /dev/null 2>&1 & + sleep 4 + + state=$(__ublk_kill_daemon "${dev_id}" "QUIESCED") + if [ "$state" != "QUIESCED" ]; then + echo "device isn't quiesced($state) after killing daemon" + return 255 + fi + + state=$(_recover_ublk_dev -n "$dev_id" "$@") + if [ "$state" != "LIVE" ]; then + echo "faile to recover to LIVE($state)" + return 255 + fi + + if ! __remove_ublk_dev_return "${dev_id}"; then + echo "delete dev ${dev_id} failed" + return 255 + fi + wait +} + + _ublk_test_top_dir() { cd "$(dirname "$0")" && pwd } -UBLK_TMP=$(mktemp ublk_test_XXXXX) UBLK_PROG=$(_ublk_test_top_dir)/kublk UBLK_TEST_QUIET=1 UBLK_TEST_SHOW_RESULT=1 +UBLK_BACKFILES=() export UBLK_PROG export UBLK_TEST_QUIET export UBLK_TEST_SHOW_RESULT diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh new file mode 100755 index 000000000000..8a3bc080c577 --- /dev/null +++ b/tools/testing/selftests/ublk/test_generic_04.sh @@ -0,0 +1,40 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="generic_04" +ERR_CODE=0 + +ublk_run_recover_test() +{ + run_io_and_recover "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "recover" "basic recover function verification" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_run_recover_test -t null -q 2 -r 1 & +ublk_run_recover_test -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +ublk_run_recover_test -t null -q 2 -r 1 -i 1 & +ublk_run_recover_test -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "recover" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh new file mode 100755 index 000000000000..714630b4b329 --- /dev/null +++ b/tools/testing/selftests/ublk/test_generic_05.sh @@ -0,0 +1,44 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="generic_04" +ERR_CODE=0 + +ublk_run_recover_test() +{ + run_io_and_recover "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +if ! _have_feature "ZERO_COPY"; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "recover" "basic recover function verification (zero copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_run_recover_test -t null -q 2 -r 1 -z & +ublk_run_recover_test -t loop -q 2 -r 1 -z "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +ublk_run_recover_test -t null -q 2 -r 1 -z -i 1 & +ublk_run_recover_test -t loop -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "recover" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_generic_06.sh b/tools/testing/selftests/ublk/test_generic_06.sh new file mode 100755 index 000000000000..b67230c42c84 --- /dev/null +++ b/tools/testing/selftests/ublk/test_generic_06.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="generic_06" +ERR_CODE=0 + +_prep_test "fault_inject" "fast cleanup when all I/Os of one hctx are in server" + +# configure ublk server to sleep 2s before completing each I/O +dev_id=$(_add_ublk_dev -t fault_inject -q 2 -d 1 --delay_us 2000000) +_check_add_dev $TID $? + +STARTTIME=${SECONDS} + +dd if=/dev/urandom of=/dev/ublkb${dev_id} oflag=direct bs=4k count=1 status=none > /dev/null 2>&1 & +dd_pid=$! + +__ublk_kill_daemon ${dev_id} "DEAD" + +wait $dd_pid +dd_exitcode=$? + +ENDTIME=${SECONDS} +ELAPSED=$(($ENDTIME - $STARTTIME)) + +# assert that dd sees an error and exits quickly after ublk server is +# killed. previously this relied on seeing an I/O timeout and so would +# take ~30s +if [ $dd_exitcode -eq 0 ]; then + echo "dd unexpectedly exited successfully!" + ERR_CODE=255 +fi +if [ $ELAPSED -ge 5 ]; then + echo "dd took $ELAPSED seconds to exit (>= 5s tolerance)!" + ERR_CODE=255 +fi + +_cleanup_test "fault_inject" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh index 1ef8b6044777..833fa0dbc700 100755 --- a/tools/testing/selftests/ublk/test_loop_01.sh +++ b/tools/testing/selftests/ublk/test_loop_01.sh @@ -12,10 +12,10 @@ fi _prep_test "loop" "write and verify test" -backfile_0=$(_create_backfile 256M) +_create_backfile 0 256M -dev_id=$(_add_ublk_dev -t loop "$backfile_0") -_check_add_dev $TID $? "${backfile_0}" +dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? # run fio over the ublk disk _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M @@ -23,6 +23,4 @@ ERR_CODE=$? _cleanup_test "loop" -_remove_backfile "$backfile_0" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh index 03863d825e07..874568b3646b 100755 --- a/tools/testing/selftests/ublk/test_loop_02.sh +++ b/tools/testing/selftests/ublk/test_loop_02.sh @@ -8,15 +8,13 @@ ERR_CODE=0 _prep_test "loop" "mkfs & mount & umount" -backfile_0=$(_create_backfile 256M) -dev_id=$(_add_ublk_dev -t loop "$backfile_0") -_check_add_dev $TID $? "$backfile_0" +_create_backfile 0 256M +dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? _mkfs_mount_test /dev/ublkb"${dev_id}" ERR_CODE=$? _cleanup_test "loop" -_remove_backfile "$backfile_0" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh index e9ca744de8b1..c30f797c6429 100755 --- a/tools/testing/selftests/ublk/test_loop_03.sh +++ b/tools/testing/selftests/ublk/test_loop_03.sh @@ -12,9 +12,9 @@ fi _prep_test "loop" "write and verify over zero copy" -backfile_0=$(_create_backfile 256M) -dev_id=$(_add_ublk_dev -t loop -z "$backfile_0") -_check_add_dev $TID $? "$backfile_0" +_create_backfile 0 256M +dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? # run fio over the ublk disk _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M @@ -22,6 +22,4 @@ ERR_CODE=$? _cleanup_test "loop" -_remove_backfile "$backfile_0" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh index 1435422c38ec..b01d75b3214d 100755 --- a/tools/testing/selftests/ublk/test_loop_04.sh +++ b/tools/testing/selftests/ublk/test_loop_04.sh @@ -8,15 +8,14 @@ ERR_CODE=0 _prep_test "loop" "mkfs & mount & umount with zero copy" -backfile_0=$(_create_backfile 256M) -dev_id=$(_add_ublk_dev -t loop -z "$backfile_0") -_check_add_dev $TID $? "$backfile_0" +_create_backfile 0 256M + +dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? _mkfs_mount_test /dev/ublkb"${dev_id}" ERR_CODE=$? _cleanup_test "loop" -_remove_backfile "$backfile_0" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_05.sh b/tools/testing/selftests/ublk/test_loop_05.sh index 2e6e2e6978fc..de2141533074 100755 --- a/tools/testing/selftests/ublk/test_loop_05.sh +++ b/tools/testing/selftests/ublk/test_loop_05.sh @@ -12,10 +12,10 @@ fi _prep_test "loop" "write and verify test" -backfile_0=$(_create_backfile 256M) +_create_backfile 0 256M -dev_id=$(_add_ublk_dev -q 2 -t loop "$backfile_0") -_check_add_dev $TID $? "${backfile_0}" +dev_id=$(_add_ublk_dev -q 2 -t loop "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? # run fio over the ublk disk _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M @@ -23,6 +23,4 @@ ERR_CODE=$? _cleanup_test "loop" -_remove_backfile "$backfile_0" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh index a8be24532b24..7d3150f057d4 100755 --- a/tools/testing/selftests/ublk/test_stress_01.sh +++ b/tools/testing/selftests/ublk/test_stress_01.sh @@ -4,44 +4,31 @@ . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh TID="stress_01" ERR_CODE=0 -DEV_ID=-1 ublk_io_and_remove() { - local size=$1 - shift 1 - local backfile="" - if echo "$@" | grep -q "loop"; then - backfile=${*: -1} - fi - DEV_ID=$(_add_ublk_dev "$@") - _check_add_dev $TID $? "${backfile}" - - [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)" - if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then - echo "/dev/ublkc${DEV_ID} isn't removed" - _remove_backfile "${backfile}" - exit 255 + run_io_and_remove "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE fi } +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "stress" "run IO and remove device" -ublk_io_and_remove 8G -t null -q 4 -ERR_CODE=$? -if [ ${ERR_CODE} -ne 0 ]; then - _show_result $TID $ERR_CODE -fi +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M -BACK_FILE=$(_create_backfile 256M) -ublk_io_and_remove 256M -t loop -q 4 "${BACK_FILE}" -ERR_CODE=$? -if [ ${ERR_CODE} -ne 0 ]; then - _show_result $TID $ERR_CODE -fi +ublk_io_and_remove 8G -t null -q 4 & +ublk_io_and_remove 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" & +ublk_io_and_remove 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait -ublk_io_and_remove 256M -t loop -q 4 -z "${BACK_FILE}" -ERR_CODE=$? _cleanup_test "stress" -_remove_backfile "${BACK_FILE}" _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh index 2159e4cc8140..1a9065125ae1 100755 --- a/tools/testing/selftests/ublk/test_stress_02.sh +++ b/tools/testing/selftests/ublk/test_stress_02.sh @@ -4,44 +4,31 @@ . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh TID="stress_02" ERR_CODE=0 -DEV_ID=-1 + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi ublk_io_and_kill_daemon() { - local size=$1 - shift 1 - local backfile="" - if echo "$@" | grep -q "loop"; then - backfile=${*: -1} - fi - DEV_ID=$(_add_ublk_dev "$@") - _check_add_dev $TID $? "${backfile}" - - [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)" - if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then - echo "/dev/ublkc${DEV_ID} isn't removed res ${res}" - _remove_backfile "${backfile}" - exit 255 + run_io_and_kill_daemon "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE fi } _prep_test "stress" "run IO and kill ublk server" -ublk_io_and_kill_daemon 8G -t null -q 4 -ERR_CODE=$? -if [ ${ERR_CODE} -ne 0 ]; then - _show_result $TID $ERR_CODE -fi +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M -BACK_FILE=$(_create_backfile 256M) -ublk_io_and_kill_daemon 256M -t loop -q 4 "${BACK_FILE}" -ERR_CODE=$? -if [ ${ERR_CODE} -ne 0 ]; then - _show_result $TID $ERR_CODE -fi +ublk_io_and_kill_daemon 8G -t null -q 4 & +ublk_io_and_kill_daemon 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait -ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${BACK_FILE}" -ERR_CODE=$? _cleanup_test "stress" -_remove_backfile "${BACK_FILE}" _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh new file mode 100755 index 000000000000..e0854f71d35b --- /dev/null +++ b/tools/testing/selftests/ublk/test_stress_03.sh @@ -0,0 +1,38 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh +TID="stress_03" +ERR_CODE=0 + +ublk_io_and_remove() +{ + run_io_and_remove "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +if ! _have_feature "ZERO_COPY"; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "stress" "run IO and remove device(zero copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_io_and_remove 8G -t null -q 4 -z & +ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & +ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "stress" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh new file mode 100755 index 000000000000..1798a98387e8 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stress_04.sh @@ -0,0 +1,37 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh +TID="stress_04" +ERR_CODE=0 + +ublk_io_and_kill_daemon() +{ + run_io_and_kill_daemon "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi +if ! _have_feature "ZERO_COPY"; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "stress" "run IO and kill ublk server(zero copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_io_and_kill_daemon 8G -t null -q 4 -z & +ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "stress" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh new file mode 100755 index 000000000000..a7071b10224d --- /dev/null +++ b/tools/testing/selftests/ublk/test_stress_05.sh @@ -0,0 +1,64 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh +TID="stress_05" +ERR_CODE=0 + +run_io_and_remove() +{ + local size=$1 + local dev_id + local dev_pid + shift 1 + + dev_id=$(_add_ublk_dev "$@") + _check_add_dev $TID $? + + [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)" + + fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \ + --rw=readwrite --iodepth=128 --size="${size}" --numjobs=4 \ + --runtime=40 --time_based > /dev/null 2>&1 & + sleep 4 + + dev_pid=$(_get_ublk_daemon_pid "$dev_id") + kill -9 "$dev_pid" + + if ! __remove_ublk_dev_return "${dev_id}"; then + echo "delete dev ${dev_id} failed" + return 255 + fi +} + +ublk_io_and_remove() +{ + run_io_and_remove "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +_prep_test "stress" "run IO and remove device with recovery enabled" + +_create_backfile 0 256M +_create_backfile 1 256M + +for reissue in $(seq 0 1); do + ublk_io_and_remove 8G -t null -q 4 -g 1 -r 1 -i "$reissue" & + ublk_io_and_remove 256M -t loop -q 4 -g 1 -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" & + wait +done + +if _have_feature "ZERO_COPY"; then + for reissue in $(seq 0 1); do + ublk_io_and_remove 8G -t null -q 4 -g 1 -z -r 1 -i "$reissue" & + ublk_io_and_remove 256M -t loop -q 4 -g 1 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" & + wait + done +fi + +_cleanup_test "stress" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh index 7e387ef656ea..4e4f0fdf3c9b 100755 --- a/tools/testing/selftests/ublk/test_stripe_01.sh +++ b/tools/testing/selftests/ublk/test_stripe_01.sh @@ -12,19 +12,15 @@ fi _prep_test "stripe" "write and verify test" -backfile_0=$(_create_backfile 256M) -backfile_1=$(_create_backfile 256M) +_create_backfile 0 256M +_create_backfile 1 256M -dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1") -_check_add_dev $TID $? "${backfile_0}" +dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? # run fio over the ublk disk _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M ERR_CODE=$? _cleanup_test "stripe" - -_remove_backfile "$backfile_0" -_remove_backfile "$backfile_1" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh index e8a45fa82dde..5820ab2efba4 100755 --- a/tools/testing/selftests/ublk/test_stripe_02.sh +++ b/tools/testing/selftests/ublk/test_stripe_02.sh @@ -8,17 +8,14 @@ ERR_CODE=0 _prep_test "stripe" "mkfs & mount & umount" -backfile_0=$(_create_backfile 256M) -backfile_1=$(_create_backfile 256M) -dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1") -_check_add_dev $TID $? "$backfile_0" "$backfile_1" +_create_backfile 0 256M +_create_backfile 1 256M + +dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? _mkfs_mount_test /dev/ublkb"${dev_id}" ERR_CODE=$? _cleanup_test "stripe" - -_remove_backfile "$backfile_0" -_remove_backfile "$backfile_1" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_03.sh b/tools/testing/selftests/ublk/test_stripe_03.sh index c1b34af36145..20b977e27814 100755 --- a/tools/testing/selftests/ublk/test_stripe_03.sh +++ b/tools/testing/selftests/ublk/test_stripe_03.sh @@ -12,19 +12,15 @@ fi _prep_test "stripe" "write and verify test" -backfile_0=$(_create_backfile 256M) -backfile_1=$(_create_backfile 256M) +_create_backfile 0 256M +_create_backfile 1 256M -dev_id=$(_add_ublk_dev -q 2 -t stripe "$backfile_0" "$backfile_1") -_check_add_dev $TID $? "${backfile_0}" +dev_id=$(_add_ublk_dev -q 2 -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? # run fio over the ublk disk _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M ERR_CODE=$? _cleanup_test "stripe" - -_remove_backfile "$backfile_0" -_remove_backfile "$backfile_1" - _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh index 1f2b642381d1..1b51ed2f1d84 100755 --- a/tools/testing/selftests/ublk/test_stripe_04.sh +++ b/tools/testing/selftests/ublk/test_stripe_04.sh @@ -8,17 +8,14 @@ ERR_CODE=0 _prep_test "stripe" "mkfs & mount & umount on zero copy" -backfile_0=$(_create_backfile 256M) -backfile_1=$(_create_backfile 256M) -dev_id=$(_add_ublk_dev -t stripe -z -q 2 "$backfile_0" "$backfile_1") -_check_add_dev $TID $? "$backfile_0" "$backfile_1" +_create_backfile 0 256M +_create_backfile 1 256M + +dev_id=$(_add_ublk_dev -t stripe -z -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? _mkfs_mount_test /dev/ublkb"${dev_id}" ERR_CODE=$? _cleanup_test "stripe" - -_remove_backfile "$backfile_0" -_remove_backfile "$backfile_1" - _show_result $TID $ERR_CODE |