diff options
553 files changed, 7843 insertions, 2932 deletions
@@ -316,6 +316,7 @@ Hans Verkuil <hverkuil@kernel.org> <hverkuil-cisco@xs4all.nl> Hans Verkuil <hverkuil@kernel.org> <hansverk@cisco.com> Hao Ge <hao.ge@linux.dev> <gehao@kylinos.cn> Harry Yoo <harry.yoo@oracle.com> <42.hyeyoo@gmail.com> +Harry Yoo <harry@kernel.org> <harry.yoo@oracle.com> Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com> Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com> Heiko Stuebner <heiko@sntech.de> <heiko.stuebner@bqreaders.com> @@ -587,6 +588,7 @@ Morten Welinder <terra@gnome.org> Morten Welinder <welinder@anemone.rentec.com> Morten Welinder <welinder@darter.rentec.com> Morten Welinder <welinder@troll.com> +Muhammad Usama Anjum <usama.anjum@arm.com> <usama.anjum@collabora.com> Mukesh Ojha <quic_mojha@quicinc.com> <mojha@codeaurora.org> Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org> Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org> diff --git a/Documentation/PCI/pcieaer-howto.rst b/Documentation/PCI/pcieaer-howto.rst index 3210c4792978..90fdfddd3ae5 100644 --- a/Documentation/PCI/pcieaer-howto.rst +++ b/Documentation/PCI/pcieaer-howto.rst @@ -85,6 +85,16 @@ In the example, 'Requester ID' means the ID of the device that sent the error message to the Root Port. Please refer to PCIe specs for other fields. +The 'TLP Header' is the prefix/header of the TLP that caused the error +in raw hex format. To decode the TLP Header into human-readable form +one may use tlp-tool: + +https://github.com/mmpg-x86/tlp-tool + +Example usage:: + + curl -L https://git.kernel.org/linus/2ca1c94ce0b6 | rtlp-tool --aer + AER Ratelimits -------------- diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst index 1d7bfad73b1c..123c8468d58f 100644 --- a/Documentation/core-api/dma-attributes.rst +++ b/Documentation/core-api/dma-attributes.rst @@ -149,11 +149,33 @@ For architectures that require cache flushing for DMA coherence DMA_ATTR_MMIO will not perform any cache flushing. The address provided must never be mapped cacheable into the CPU. -DMA_ATTR_CPU_CACHE_CLEAN ------------------------- - -This attribute indicates the CPU will not dirty any cacheline overlapping this -DMA_FROM_DEVICE/DMA_BIDIRECTIONAL buffer while it is mapped. This allows -multiple small buffers to safely share a cacheline without risk of data -corruption, suppressing DMA debug warnings about overlapping mappings. -All mappings sharing a cacheline should have this attribute. +DMA_ATTR_DEBUGGING_IGNORE_CACHELINES +------------------------------------ + +This attribute indicates that CPU cache lines may overlap for buffers mapped +with DMA_FROM_DEVICE or DMA_BIDIRECTIONAL. + +Such overlap may occur when callers map multiple small buffers that reside +within the same cache line. In this case, callers must guarantee that the CPU +will not dirty these cache lines after the mappings are established. When this +condition is met, multiple buffers can safely share a cache line without risking +data corruption. + +All mappings that share a cache line must set this attribute to suppress DMA +debug warnings about overlapping mappings. + +DMA_ATTR_REQUIRE_COHERENT +------------------------- + +DMA mapping requests with the DMA_ATTR_REQUIRE_COHERENT fail on any +system where SWIOTLB or cache management is required. This should only +be used to support uAPI designs that require continuous HW DMA +coherence with userspace processes, for example RDMA and DRM. At a +minimum the memory being mapped must be userspace memory from +pin_user_pages() or similar. + +Drivers should consider using dma_mmap_pages() instead of this +interface when building their uAPIs, when possible. + +It must never be used in an in-kernel driver that only works with +kernel memory. diff --git a/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml b/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml index b90eec2077b4..fe1272e86467 100644 --- a/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml +++ b/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml @@ -66,7 +66,7 @@ then: required: - refresh-rate-hz -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml index 56c755c22945..502907dd28b3 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml @@ -33,6 +33,7 @@ properties: - const: rockchip,rk3066-spdif - items: - enum: + - rockchip,rk3576-spdif - rockchip,rk3588-spdif - const: rockchip,rk3568-spdif diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml index 4a7129d0b157..551edf39e766 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml @@ -164,7 +164,7 @@ allOf: properties: compatible: contains: - const: st,stm32mph7-sai + const: st,stm32h7-sai then: properties: clocks: diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index af5a69f87da4..eb846518e6ac 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -783,6 +783,56 @@ controlled by the "uuid" mount option, which supports these values: mounted with "uuid=on". +Durability and copy up +---------------------- + +The fsync(2) system call ensures that the data and metadata of a file +are safely written to the backing storage, which is expected to +guarantee the existence of the information post system crash. + +Without an fsync(2) call, there is no guarantee that the observed +data after a system crash will be either the old or the new data, but +in practice, the observed data after crash is often the old or new data +or a mix of both. + +When an overlayfs file is modified for the first time, copy up will +create a copy of the lower file and its parent directories in the upper +layer. Since the Linux filesystem API does not enforce any particular +ordering on storing changes without explicit fsync(2) calls, in case +of a system crash, the upper file could end up with no data at all +(i.e. zeros), which would be an unusual outcome. To avoid this +experience, overlayfs calls fsync(2) on the upper file before completing +data copy up with rename(2) or link(2) to make the copy up "atomic". + +By default, overlayfs does not explicitly call fsync(2) on copied up +directories or on metadata-only copy up, so it provides no guarantee to +persist the user's modification unless the user calls fsync(2). +The fsync during copy up only guarantees that if a copy up is observed +after a crash, the observed data is not zeroes or intermediate values +from the copy up staging area. + +On traditional local filesystems with a single journal (e.g. ext4, xfs), +fsync on a file also persists the parent directory changes, because they +are usually modified in the same transaction, so metadata durability during +data copy up effectively comes for free. Overlayfs further limits risk by +disallowing network filesystems as upper layer. + +Overlayfs can be tuned to prefer performance or durability when storing +to the underlying upper layer. This is controlled by the "fsync" mount +option, which supports these values: + +- "auto": (default) + Call fsync(2) on upper file before completion of data copy up. + No explicit fsync(2) on directory or metadata-only copy up. +- "strict": + Call fsync(2) on upper file and directories before completion of any + copy up. +- "volatile": [*] + Prefer performance over durability (see `Volatile mount`_) + +[*] The mount option "volatile" is an alias to "fsync=volatile". + + Volatile mount -------------- diff --git a/Documentation/hwmon/adm1177.rst b/Documentation/hwmon/adm1177.rst index 1c85a2af92bf..375f6d6e03a7 100644 --- a/Documentation/hwmon/adm1177.rst +++ b/Documentation/hwmon/adm1177.rst @@ -27,10 +27,10 @@ for details. Sysfs entries ------------- -The following attributes are supported. Current maxim attribute +The following attributes are supported. Current maximum attribute is read-write, all other attributes are read-only. -in0_input Measured voltage in microvolts. +in0_input Measured voltage in millivolts. -curr1_input Measured current in microamperes. -curr1_max_alarm Overcurrent alarm in microamperes. +curr1_input Measured current in milliamperes. +curr1_max Overcurrent shutdown threshold in milliamperes. diff --git a/Documentation/hwmon/peci-cputemp.rst b/Documentation/hwmon/peci-cputemp.rst index fe0422248dc5..266b62a46f49 100644 --- a/Documentation/hwmon/peci-cputemp.rst +++ b/Documentation/hwmon/peci-cputemp.rst @@ -51,8 +51,9 @@ temp1_max Provides thermal control temperature of the CPU package temp1_crit Provides shutdown temperature of the CPU package which is also known as the maximum processor junction temperature, Tjmax or Tprochot. -temp1_crit_hyst Provides the hysteresis value from Tcontrol to Tjmax of - the CPU package. +temp1_crit_hyst Provides the hysteresis temperature of the CPU + package. Returns Tcontrol, the temperature at which + the critical condition clears. temp2_label "DTS" temp2_input Provides current temperature of the CPU package scaled @@ -62,8 +63,9 @@ temp2_max Provides thermal control temperature of the CPU package temp2_crit Provides shutdown temperature of the CPU package which is also known as the maximum processor junction temperature, Tjmax or Tprochot. -temp2_crit_hyst Provides the hysteresis value from Tcontrol to Tjmax of - the CPU package. +temp2_crit_hyst Provides the hysteresis temperature of the CPU + package. Returns Tcontrol, the temperature at which + the critical condition clears. temp3_label "Tcontrol" temp3_input Provides current Tcontrol temperature of the CPU diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst index 13134bccdd39..7f86d7a37dc2 100644 --- a/Documentation/userspace-api/landlock.rst +++ b/Documentation/userspace-api/landlock.rst @@ -8,7 +8,7 @@ Landlock: unprivileged access control ===================================== :Author: Mickaël Salaün -:Date: January 2026 +:Date: March 2026 The goal of Landlock is to enable restriction of ambient rights (e.g. global filesystem or network access) for a set of processes. Because Landlock @@ -197,12 +197,27 @@ similar backwards compatibility check is needed for the restrict flags .. code-block:: c - __u32 restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON; - if (abi < 7) { - /* Clear logging flags unsupported before ABI 7. */ + __u32 restrict_flags = + LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON | + LANDLOCK_RESTRICT_SELF_TSYNC; + switch (abi) { + case 1 ... 6: + /* Removes logging flags for ABI < 7 */ restrict_flags &= ~(LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF | LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON | LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF); + __attribute__((fallthrough)); + case 7: + /* + * Removes multithreaded enforcement flag for ABI < 8 + * + * WARNING: Without this flag, calling landlock_restrict_self(2) is + * only equivalent if the calling process is single-threaded. Below + * ABI v8 (and as of ABI v8, when not using this flag), a Landlock + * policy would only be enforced for the calling thread and its + * children (and not for all threads, including parents and siblings). + */ + restrict_flags &= ~LANDLOCK_RESTRICT_SELF_TSYNC; } The next step is to restrict the current thread from gaining more privileges diff --git a/MAINTAINERS b/MAINTAINERS index 980ba6ff3011..2f645897148c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3986,7 +3986,7 @@ F: drivers/hwmon/asus-ec-sensors.c ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS M: Corentin Chary <corentin.chary@gmail.com> M: Luke D. Jones <luke@ljones.dev> -M: Denis Benato <benato.denis96@gmail.com> +M: Denis Benato <denis.benato@linux.dev> L: platform-driver-x86@vger.kernel.org S: Maintained W: https://asus-linux.org/ @@ -8625,8 +8625,14 @@ F: drivers/gpu/drm/lima/ F: include/uapi/drm/lima_drm.h DRM DRIVERS FOR LOONGSON +M: Jianmin Lv <lvjianmin@loongson.cn> +M: Qianhai Wu <wuqianhai@loongson.cn> +R: Huacai Chen <chenhuacai@kernel.org> +R: Mingcong Bai <jeffbai@aosc.io> +R: Xi Ruoyao <xry111@xry111.site> +R: Icenowy Zheng <zhengxingda@iscas.ac.cn> L: dri-devel@lists.freedesktop.org -S: Orphan +S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/loongson/ @@ -9610,7 +9616,12 @@ F: include/linux/ext2* EXT4 FILE SYSTEM M: "Theodore Ts'o" <tytso@mit.edu> -M: Andreas Dilger <adilger.kernel@dilger.ca> +R: Andreas Dilger <adilger.kernel@dilger.ca> +R: Baokun Li <libaokun@linux.alibaba.com> +R: Jan Kara <jack@suse.cz> +R: Ojaswin Mujoo <ojaswin@linux.ibm.com> +R: Ritesh Harjani (IBM) <ritesh.list@gmail.com> +R: Zhang Yi <yi.zhang@huawei.com> L: linux-ext4@vger.kernel.org S: Maintained W: http://ext4.wiki.kernel.org @@ -12006,7 +12017,6 @@ I2C SUBSYSTEM M: Wolfram Sang <wsa+renesas@sang-engineering.com> L: linux-i2c@vger.kernel.org S: Maintained -W: https://i2c.wiki.kernel.org/ Q: https://patchwork.ozlabs.org/project/linux-i2c/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git F: Documentation/i2c/ @@ -12032,7 +12042,6 @@ I2C SUBSYSTEM HOST DRIVERS M: Andi Shyti <andi.shyti@kernel.org> L: linux-i2c@vger.kernel.org S: Maintained -W: https://i2c.wiki.kernel.org/ Q: https://patchwork.ozlabs.org/project/linux-i2c/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git F: Documentation/devicetree/bindings/i2c/ @@ -16874,7 +16883,7 @@ M: Lorenzo Stoakes <ljs@kernel.org> R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@kernel.org> -R: Harry Yoo <harry.yoo@oracle.com> +R: Harry Yoo <harry@kernel.org> R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org S: Maintained @@ -24340,7 +24349,7 @@ F: drivers/nvmem/layouts/sl28vpd.c SLAB ALLOCATOR M: Vlastimil Babka <vbabka@kernel.org> -M: Harry Yoo <harry.yoo@oracle.com> +M: Harry Yoo <harry@kernel.org> M: Andrew Morton <akpm@linux-foundation.org> R: Hao Li <hao.li@linux.dev> R: Christoph Lameter <cl@gentwo.org> @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1654,7 +1654,7 @@ CLEAN_FILES += vmlinux.symvers modules-only.symvers \ modules.builtin.ranges vmlinux.o.map vmlinux.unstripped \ compile_commands.json rust/test \ rust-project.json .vmlinux.objs .vmlinux.export.c \ - .builtin-dtbs-list .builtin-dtb.S + .builtin-dtbs-list .builtin-dtbs.S # Directories & files removed with 'make mrproper' MRPROPER_FILES += include/config include/generated \ diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index c5c5644b1878..a024d9a770dc 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -1753,7 +1753,7 @@ int __kvm_at_swap_desc(struct kvm *kvm, gpa_t ipa, u64 old, u64 new) if (!writable) return -EPERM; - ptep = (u64 __user *)hva + offset; + ptep = (void __user *)hva + offset; if (cpus_have_final_cap(ARM64_HAS_LSE_ATOMICS)) r = __lse_swap_desc(ptep, old, new); else diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 959532422d3a..b963fd975aac 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -247,6 +247,20 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) kvm_vcpu_set_be(vcpu); *vcpu_pc(vcpu) = target_pc; + + /* + * We may come from a state where either a PC update was + * pending (SMC call resulting in PC being increpented to + * skip the SMC) or a pending exception. Make sure we get + * rid of all that, as this cannot be valid out of reset. + * + * Note that clearing the exception mask also clears PC + * updates, but that's an implementation detail, and we + * really want to make it explicit. + */ + vcpu_clear_flag(vcpu, PENDING_EXCEPTION); + vcpu_clear_flag(vcpu, EXCEPT_MASK); + vcpu_clear_flag(vcpu, INCREMENT_PC); vcpu_set_reg(vcpu, 0, reset_state.r0); } diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h index e2eca1a25b4e..a1bd6a3ee03a 100644 --- a/arch/loongarch/include/asm/linkage.h +++ b/arch/loongarch/include/asm/linkage.h @@ -41,4 +41,40 @@ .cfi_endproc; \ SYM_END(name, SYM_T_NONE) +/* + * This is for the signal handler trampoline, which is used as the return + * address of the signal handlers in userspace instead of called normally. + * The long standing libgcc bug https://gcc.gnu.org/PR124050 requires a + * nop between .cfi_startproc and the actual address of the trampoline, so + * we cannot simply use SYM_FUNC_START. + * + * This wrapper also contains all the .cfi_* directives for recovering + * the content of the GPRs and the "return address" (where the rt_sigreturn + * syscall will jump to), assuming there is a struct rt_sigframe (where + * a struct sigcontext containing those information we need to recover) at + * $sp. The "DWARF for the LoongArch(TM) Architecture" manual states + * column 0 is for $zero, but it does not make too much sense to + * save/restore the hardware zero register. Repurpose this column here + * for the return address (here it's not the content of $ra we cannot use + * the default column 3). + */ +#define SYM_SIGFUNC_START(name) \ + .cfi_startproc; \ + .cfi_signal_frame; \ + .cfi_def_cfa 3, RT_SIGFRAME_SC; \ + .cfi_return_column 0; \ + .cfi_offset 0, SC_PC; \ + \ + .irp num, 1, 2, 3, 4, 5, 6, 7, 8, \ + 9, 10, 11, 12, 13, 14, 15, 16, \ + 17, 18, 19, 20, 21, 22, 23, 24, \ + 25, 26, 27, 28, 29, 30, 31; \ + .cfi_offset \num, SC_REGS + \num * SZREG; \ + .endr; \ + \ + nop; \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) + +#define SYM_SIGFUNC_END(name) SYM_FUNC_END(name) + #endif diff --git a/arch/loongarch/include/asm/sigframe.h b/arch/loongarch/include/asm/sigframe.h new file mode 100644 index 000000000000..109298b8d7e0 --- /dev/null +++ b/arch/loongarch/include/asm/sigframe.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#include <asm/siginfo.h> +#include <asm/ucontext.h> + +struct rt_sigframe { + struct siginfo rs_info; + struct ucontext rs_uctx; +}; diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 3017c7157600..2cc953f113ac 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -16,6 +16,7 @@ #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/ftrace.h> +#include <asm/sigframe.h> #include <vdso/datapage.h> static void __used output_ptreg_defines(void) @@ -220,6 +221,7 @@ static void __used output_sc_defines(void) COMMENT("Linux sigcontext offsets."); OFFSET(SC_REGS, sigcontext, sc_regs); OFFSET(SC_PC, sigcontext, sc_pc); + OFFSET(RT_SIGFRAME_SC, rt_sigframe, rs_uctx.uc_mcontext); BLANK(); } diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 841206fde3ab..652456768b55 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -42,16 +42,15 @@ static int __init init_cpu_fullname(void) int cpu, ret; char *cpuname; const char *model; - struct device_node *root; /* Parsing cpuname from DTS model property */ - root = of_find_node_by_path("/"); - ret = of_property_read_string(root, "model", &model); + ret = of_property_read_string(of_root, "model", &model); if (ret == 0) { cpuname = kstrdup(model, GFP_KERNEL); + if (!cpuname) + return -ENOMEM; loongson_sysconf.cpuname = strsep(&cpuname, " "); } - of_node_put(root); if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) { for (cpu = 0; cpu < NR_CPUS; cpu++) diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index c9f7ca778364..d4151d2fb82e 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -35,6 +35,7 @@ #include <asm/cpu-features.h> #include <asm/fpu.h> #include <asm/lbt.h> +#include <asm/sigframe.h> #include <asm/ucontext.h> #include <asm/vdso.h> @@ -51,11 +52,6 @@ #define lock_lbt_owner() ({ preempt_disable(); pagefault_disable(); }) #define unlock_lbt_owner() ({ pagefault_enable(); preempt_enable(); }) -struct rt_sigframe { - struct siginfo rs_info; - struct ucontext rs_uctx; -}; - struct _ctx_layout { struct sctx_info *addr; unsigned int size; diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index d2acb4d09e73..003bd773e11c 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -83,7 +83,7 @@ static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) { cpuid = ffs(cpuid) - 1; - cpuid = (cpuid >= 4) ? 0 : cpuid; + cpuid = ((cpuid < 0) || (cpuid >= 4)) ? 0 : cpuid; } vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); @@ -472,34 +472,34 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, switch (addr) { case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: offset = (addr - EIOINTC_NODETYPE_START) / 4; - p = s->nodetype + offset * 4; + p = (void *)s->nodetype + offset * 4; break; case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END: offset = (addr - EIOINTC_IPMAP_START) / 4; - p = &s->ipmap + offset * 4; + p = (void *)&s->ipmap + offset * 4; break; case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END: offset = (addr - EIOINTC_ENABLE_START) / 4; - p = s->enable + offset * 4; + p = (void *)s->enable + offset * 4; break; case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END: offset = (addr - EIOINTC_BOUNCE_START) / 4; - p = s->bounce + offset * 4; + p = (void *)s->bounce + offset * 4; break; case EIOINTC_ISR_START ... EIOINTC_ISR_END: offset = (addr - EIOINTC_ISR_START) / 4; - p = s->isr + offset * 4; + p = (void *)s->isr + offset * 4; break; case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: if (cpu >= s->num_cpu) return -EINVAL; offset = (addr - EIOINTC_COREISR_START) / 4; - p = s->coreisr[cpu] + offset * 4; + p = (void *)s->coreisr[cpu] + offset * 4; break; case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: offset = (addr - EIOINTC_COREMAP_START) / 4; - p = s->coremap + offset * 4; + p = (void *)s->coremap + offset * 4; break; default: kvm_err("%s: unknown eiointc register, addr = %d\n", __func__, addr); diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 8ffd50a470e6..831f381a8fd1 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -588,6 +588,9 @@ struct kvm_vcpu *kvm_get_vcpu_by_cpuid(struct kvm *kvm, int cpuid) { struct kvm_phyid_map *map; + if (cpuid < 0) + return NULL; + if (cpuid >= KVM_MAX_PHYID) return NULL; diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c index d923295ab8c6..d233ea2218fe 100644 --- a/arch/loongarch/pci/pci.c +++ b/arch/loongarch/pci/pci.c @@ -5,9 +5,11 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/acpi.h> +#include <linux/delay.h> #include <linux/types.h> #include <linux/pci.h> #include <linux/vgaarb.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <asm/cacheflush.h> #include <asm/loongson.h> @@ -15,6 +17,9 @@ #define PCI_DEVICE_ID_LOONGSON_DC1 0x7a06 #define PCI_DEVICE_ID_LOONGSON_DC2 0x7a36 #define PCI_DEVICE_ID_LOONGSON_DC3 0x7a46 +#define PCI_DEVICE_ID_LOONGSON_GPU1 0x7a15 +#define PCI_DEVICE_ID_LOONGSON_GPU2 0x7a25 +#define PCI_DEVICE_ID_LOONGSON_GPU3 0x7a35 int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) @@ -99,3 +104,78 @@ static void pci_fixup_vgadev(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC1, pci_fixup_vgadev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC2, pci_fixup_vgadev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC3, pci_fixup_vgadev); + +#define CRTC_NUM_MAX 2 +#define CRTC_OUTPUT_ENABLE 0x100 + +static void loongson_gpu_fixup_dma_hang(struct pci_dev *pdev, bool on) +{ + u32 i, val, count, crtc_offset, device; + void __iomem *crtc_reg, *base, *regbase; + static u32 crtc_status[CRTC_NUM_MAX] = { 0 }; + + base = pdev->bus->ops->map_bus(pdev->bus, pdev->devfn + 1, 0); + device = readw(base + PCI_DEVICE_ID); + + regbase = ioremap(readq(base + PCI_BASE_ADDRESS_0) & ~0xffull, SZ_64K); + if (!regbase) { + pci_err(pdev, "Failed to ioremap()\n"); + return; + } + + switch (device) { + case PCI_DEVICE_ID_LOONGSON_DC2: + crtc_reg = regbase + 0x1240; + crtc_offset = 0x10; + break; + case PCI_DEVICE_ID_LOONGSON_DC3: + crtc_reg = regbase; + crtc_offset = 0x400; + break; + } + + for (i = 0; i < CRTC_NUM_MAX; i++, crtc_reg += crtc_offset) { + val = readl(crtc_reg); + + if (!on) + crtc_status[i] = val; + + /* No need to fixup if the status is off at startup. */ + if (!(crtc_status[i] & CRTC_OUTPUT_ENABLE)) + continue; + + if (on) + val |= CRTC_OUTPUT_ENABLE; + else + val &= ~CRTC_OUTPUT_ENABLE; + + mb(); + writel(val, crtc_reg); + + for (count = 0; count < 40; count++) { + val = readl(crtc_reg) & CRTC_OUTPUT_ENABLE; + if ((on && val) || (!on && !val)) + break; + udelay(1000); + } + + pci_info(pdev, "DMA hang fixup at reg[0x%lx]: 0x%x\n", + (unsigned long)crtc_reg & 0xffff, readl(crtc_reg)); + } + + iounmap(regbase); +} + +static void pci_fixup_dma_hang_early(struct pci_dev *pdev) +{ + loongson_gpu_fixup_dma_hang(pdev, false); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_early); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_early); + +static void pci_fixup_dma_hang_final(struct pci_dev *pdev) +{ + loongson_gpu_fixup_dma_hang(pdev, true); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_final); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_final); diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index 520f1513f07d..294c16b9517f 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -26,7 +26,7 @@ cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -std=gnu11 -fms-extensions -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ - $(call cc-option, -fno-asynchronous-unwind-tables) \ + $(call cc-option, -fasynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) aflags-vdso := $(ccflags-vdso) \ -D__ASSEMBLY__ -Wa,-gdwarf-2 @@ -41,7 +41,7 @@ endif # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ - $(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id -T + $(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id --eh-frame-hdr -T # # Shared build commands. diff --git a/arch/loongarch/vdso/sigreturn.S b/arch/loongarch/vdso/sigreturn.S index 9cb3c58fad03..59f940d928de 100644 --- a/arch/loongarch/vdso/sigreturn.S +++ b/arch/loongarch/vdso/sigreturn.S @@ -12,13 +12,13 @@ #include <asm/regdef.h> #include <asm/asm.h> +#include <asm/asm-offsets.h> .section .text - .cfi_sections .debug_frame -SYM_FUNC_START(__vdso_rt_sigreturn) +SYM_SIGFUNC_START(__vdso_rt_sigreturn) li.w a7, __NR_rt_sigreturn syscall 0 -SYM_FUNC_END(__vdso_rt_sigreturn) +SYM_SIGFUNC_END(__vdso_rt_sigreturn) diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index f3184073e754..dad02f5b3c8d 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -62,8 +62,8 @@ do { \ * @size: number of elements in array */ #define array_index_mask_nospec array_index_mask_nospec -static inline unsigned long array_index_mask_nospec(unsigned long index, - unsigned long size) +static __always_inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) { unsigned long mask; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 64a50f0862aa..3039c88daa63 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -710,6 +710,9 @@ void kvm_arch_crypto_clear_masks(struct kvm *kvm); void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm, unsigned long *aqm, unsigned long *adm); +#define SIE64_RETURN_NORMAL 0 +#define SIE64_RETURN_MCCK 1 + int __sie64a(phys_addr_t sie_block_phys, struct kvm_s390_sie_block *sie_block, u64 *rsa, unsigned long gasce); diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index c9ae680a28af..ac3606c3babe 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -62,7 +62,7 @@ struct stack_frame { struct { unsigned long sie_control_block; unsigned long sie_savearea; - unsigned long sie_reason; + unsigned long sie_return; unsigned long sie_flags; unsigned long sie_control_block_phys; unsigned long sie_guest_asce; diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index e1a5b5b54e4f..fbd26f3e9f96 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -63,7 +63,7 @@ int main(void) OFFSET(__SF_EMPTY, stack_frame, empty[0]); OFFSET(__SF_SIE_CONTROL, stack_frame, sie_control_block); OFFSET(__SF_SIE_SAVEAREA, stack_frame, sie_savearea); - OFFSET(__SF_SIE_REASON, stack_frame, sie_reason); + OFFSET(__SF_SIE_RETURN, stack_frame, sie_return); OFFSET(__SF_SIE_FLAGS, stack_frame, sie_flags); OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys); OFFSET(__SF_SIE_GUEST_ASCE, stack_frame, sie_guest_asce); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 4873fe9d891b..bb806d1ddae0 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -200,7 +200,7 @@ SYM_FUNC_START(__sie64a) stg %r3,__SF_SIE_CONTROL(%r15) # ...and virtual addresses stg %r4,__SF_SIE_SAVEAREA(%r15) # save guest register save area stg %r5,__SF_SIE_GUEST_ASCE(%r15) # save guest asce - xc __SF_SIE_REASON(8,%r15),__SF_SIE_REASON(%r15) # reason code = 0 + xc __SF_SIE_RETURN(8,%r15),__SF_SIE_RETURN(%r15) # return code = 0 mvc __SF_SIE_FLAGS(8,%r15),__TI_flags(%r14) # copy thread flags lmg %r0,%r13,0(%r4) # load guest gprs 0-13 mvi __TI_sie(%r14),1 @@ -237,7 +237,7 @@ SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL) xgr %r4,%r4 xgr %r5,%r5 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers - lg %r2,__SF_SIE_REASON(%r15) # return exit reason code + lg %r2,__SF_SIE_RETURN(%r15) # return sie return code BR_EX %r14 SYM_FUNC_END(__sie64a) EXPORT_SYMBOL(__sie64a) @@ -271,6 +271,7 @@ SYM_CODE_START(system_call) xgr %r9,%r9 xgr %r10,%r10 xgr %r11,%r11 + xgr %r12,%r12 la %r2,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs mvc __PT_R8(64,%r2),__LC_SAVE_AREA(%r13) MBEAR %r2,%r13 @@ -407,6 +408,7 @@ SYM_CODE_START(\name) xgr %r6,%r6 xgr %r7,%r7 xgr %r10,%r10 + xgr %r12,%r12 xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA(%r13) MBEAR %r11,%r13 @@ -496,6 +498,7 @@ SYM_CODE_START(mcck_int_handler) xgr %r6,%r6 xgr %r7,%r7 xgr %r10,%r10 + xgr %r12,%r12 stmg %r8,%r9,__PT_PSW(%r11) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index a55abbf65333..94fbfad49f62 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -487,8 +487,8 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK); if (test_cpu_flag(CIF_MCCK_GUEST) && (mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) { - /* Set exit reason code for host's later handling */ - *((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR; + /* Set sie return code for host's later handling */ + ((struct stack_frame *)regs->gprs[15])->sie_return = SIE64_RETURN_MCCK; } clear_cpu_flag(CIF_MCCK_GUEST); diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c index 795b6cca74c9..d103c853e120 100644 --- a/arch/s390/kernel/syscall.c +++ b/arch/s390/kernel/syscall.c @@ -13,6 +13,7 @@ */ #include <linux/cpufeature.h> +#include <linux/nospec.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/mm.h> @@ -131,8 +132,10 @@ void noinstr __do_syscall(struct pt_regs *regs, int per_trap) if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET))) goto out; regs->gprs[2] = -ENOSYS; - if (likely(nr < NR_syscalls)) + if (likely(nr < NR_syscalls)) { + nr = array_index_nospec(nr, NR_syscalls); regs->gprs[2] = sys_call_table[nr](regs); + } out: syscall_exit_to_user_mode(regs); } diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 670404d4fa44..7b8d70fe406d 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -135,32 +135,6 @@ int dat_set_asce_limit(struct kvm_s390_mmu_cache *mc, union asce *asce, int newt } /** - * dat_crstep_xchg() - Exchange a gmap CRSTE with another. - * @crstep: Pointer to the CRST entry - * @new: Replacement entry. - * @gfn: The affected guest address. - * @asce: The ASCE of the address space. - * - * Context: This function is assumed to be called with kvm->mmu_lock held. - */ -void dat_crstep_xchg(union crste *crstep, union crste new, gfn_t gfn, union asce asce) -{ - if (crstep->h.i) { - WRITE_ONCE(*crstep, new); - return; - } else if (cpu_has_edat2()) { - crdte_crste(crstep, *crstep, new, gfn, asce); - return; - } - - if (machine_has_tlb_guest()) - idte_crste(crstep, gfn, IDTE_GUEST_ASCE, asce, IDTE_GLOBAL); - else - idte_crste(crstep, gfn, 0, NULL_ASCE, IDTE_GLOBAL); - WRITE_ONCE(*crstep, new); -} - -/** * dat_crstep_xchg_atomic() - Atomically exchange a gmap CRSTE with another. * @crstep: Pointer to the CRST entry. * @old: Expected old value. @@ -175,8 +149,8 @@ void dat_crstep_xchg(union crste *crstep, union crste new, gfn_t gfn, union asce * * Return: %true if the exchange was successful. */ -bool dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new, gfn_t gfn, - union asce asce) +bool __must_check dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new, + gfn_t gfn, union asce asce) { if (old.h.i) return arch_try_cmpxchg((long *)crstep, &old.val, new.val); @@ -292,6 +266,7 @@ static int dat_split_ste(struct kvm_s390_mmu_cache *mc, union pmd *pmdp, gfn_t g pt->ptes[i].val = init.val | i * PAGE_SIZE; /* No need to take locks as the page table is not installed yet. */ pgste_init.prefix_notif = old.s.fc1.prefix_notif; + pgste_init.vsie_notif = old.s.fc1.vsie_notif; pgste_init.pcl = uses_skeys && init.h.i; dat_init_pgstes(pt, pgste_init.val); } else { @@ -893,7 +868,8 @@ static long _dat_slot_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct d /* This table entry needs to be updated. */ if (walk->start <= gfn && walk->end >= next) { - dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce); + if (!dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce)) + return -EINVAL; /* A lower level table was present, needs to be freed. */ if (!crste.h.fc && !crste.h.i) { if (is_pmd(crste)) @@ -1021,67 +997,21 @@ bool dat_test_age_gfn(union asce asce, gfn_t start, gfn_t end) return _dat_walk_gfn_range(start, end, asce, &test_age_ops, 0, NULL) > 0; } -int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level, - bool uses_skeys, struct guest_fault *f) -{ - union crste oldval, newval; - union pte newpte, oldpte; - union pgste pgste; - int rc = 0; - - rc = dat_entry_walk(mc, f->gfn, asce, DAT_WALK_ALLOC_CONTINUE, level, &f->crstep, &f->ptep); - if (rc == -EINVAL || rc == -ENOMEM) - return rc; - if (rc) - return -EAGAIN; - - if (WARN_ON_ONCE(unlikely(get_level(f->crstep, f->ptep) > level))) - return -EINVAL; - - if (f->ptep) { - pgste = pgste_get_lock(f->ptep); - oldpte = *f->ptep; - newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page); - newpte.s.sd = oldpte.s.sd; - oldpte.s.sd = 0; - if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) { - pgste = __dat_ptep_xchg(f->ptep, pgste, newpte, f->gfn, asce, uses_skeys); - if (f->callback) - f->callback(f); - } else { - rc = -EAGAIN; - } - pgste_set_unlock(f->ptep, pgste); - } else { - oldval = READ_ONCE(*f->crstep); - newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable, - f->write_attempt | oldval.s.fc1.d); - newval.s.fc1.sd = oldval.s.fc1.sd; - if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val && - crste_origin_large(oldval) != crste_origin_large(newval)) - return -EAGAIN; - if (!dat_crstep_xchg_atomic(f->crstep, oldval, newval, f->gfn, asce)) - return -EAGAIN; - if (f->callback) - f->callback(f); - } - - return rc; -} - static long dat_set_pn_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *walk) { - union crste crste = READ_ONCE(*crstep); + union crste newcrste, oldcrste; int *n = walk->priv; - if (!crste.h.fc || crste.h.i || crste.h.p) - return 0; - + do { + oldcrste = READ_ONCE(*crstep); + if (!oldcrste.h.fc || oldcrste.h.i || oldcrste.h.p) + return 0; + if (oldcrste.s.fc1.prefix_notif) + break; + newcrste = oldcrste; + newcrste.s.fc1.prefix_notif = 1; + } while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, walk->asce)); *n = 2; - if (crste.s.fc1.prefix_notif) - return 0; - crste.s.fc1.prefix_notif = 1; - dat_crstep_xchg(crstep, crste, gfn, walk->asce); return 0; } diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index 123e11dcd70d..874cc962e196 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -160,14 +160,14 @@ union pmd { unsigned long :44; /* HW */ unsigned long : 3; /* Unused */ unsigned long : 1; /* HW */ + unsigned long s : 1; /* Special */ unsigned long w : 1; /* Writable soft-bit */ unsigned long r : 1; /* Readable soft-bit */ unsigned long d : 1; /* Dirty */ unsigned long y : 1; /* Young */ - unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long : 3; /* HW */ + unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long vsie_notif : 1; /* Referenced in a shadow table */ - unsigned long : 1; /* Unused */ unsigned long : 4; /* HW */ unsigned long sd : 1; /* Soft-Dirty */ unsigned long pr : 1; /* Present */ @@ -183,14 +183,14 @@ union pud { unsigned long :33; /* HW */ unsigned long :14; /* Unused */ unsigned long : 1; /* HW */ + unsigned long s : 1; /* Special */ unsigned long w : 1; /* Writable soft-bit */ unsigned long r : 1; /* Readable soft-bit */ unsigned long d : 1; /* Dirty */ unsigned long y : 1; /* Young */ - unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long : 3; /* HW */ + unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long vsie_notif : 1; /* Referenced in a shadow table */ - unsigned long : 1; /* Unused */ unsigned long : 4; /* HW */ unsigned long sd : 1; /* Soft-Dirty */ unsigned long pr : 1; /* Present */ @@ -254,14 +254,14 @@ union crste { struct { unsigned long :47; unsigned long : 1; /* HW (should be 0) */ + unsigned long s : 1; /* Special */ unsigned long w : 1; /* Writable */ unsigned long r : 1; /* Readable */ unsigned long d : 1; /* Dirty */ unsigned long y : 1; /* Young */ - unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long : 3; /* HW */ + unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long vsie_notif : 1; /* Referenced in a shadow table */ - unsigned long : 1; unsigned long : 4; /* HW */ unsigned long sd : 1; /* Soft-Dirty */ unsigned long pr : 1; /* Present */ @@ -540,8 +540,6 @@ int dat_set_slot(struct kvm_s390_mmu_cache *mc, union asce asce, gfn_t start, gf u16 type, u16 param); int dat_set_prefix_notif_bit(union asce asce, gfn_t gfn); bool dat_test_age_gfn(union asce asce, gfn_t start, gfn_t end); -int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level, - bool uses_skeys, struct guest_fault *f); int dat_perform_essa(union asce asce, gfn_t gfn, int orc, union essa_state *state, bool *dirty); long dat_reset_cmma(union asce asce, gfn_t start_gfn); @@ -938,11 +936,14 @@ static inline bool dat_pudp_xchg_atomic(union pud *pudp, union pud old, union pu return dat_crstep_xchg_atomic(_CRSTEP(pudp), _CRSTE(old), _CRSTE(new), gfn, asce); } -static inline void dat_crstep_clear(union crste *crstep, gfn_t gfn, union asce asce) +static inline union crste dat_crstep_clear_atomic(union crste *crstep, gfn_t gfn, union asce asce) { - union crste newcrste = _CRSTE_EMPTY(crstep->h.tt); + union crste oldcrste, empty = _CRSTE_EMPTY(crstep->h.tt); - dat_crstep_xchg(crstep, newcrste, gfn, asce); + do { + oldcrste = READ_ONCE(*crstep); + } while (!dat_crstep_xchg_atomic(crstep, oldcrste, empty, gfn, asce)); + return oldcrste; } static inline int get_level(union crste *crstep, union pte *ptep) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 4630b2a067ea..53a8550e7102 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1434,17 +1434,27 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union if (rc) return rc; - pgste = pgste_get_lock(ptep_h); - newpte = _pte(f->pfn, f->writable, !p, 0); - newpte.s.d |= ptep->s.d; - newpte.s.sd |= ptep->s.sd; - newpte.h.p &= ptep->h.p; - pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false); - pgste.vsie_notif = 1; + if (!pgste_get_trylock(ptep_h, &pgste)) + return -EAGAIN; + newpte = _pte(f->pfn, f->writable, !p, ptep_h->s.s); + newpte.s.d |= ptep_h->s.d; + newpte.s.sd |= ptep_h->s.sd; + newpte.h.p &= ptep_h->h.p; + if (!newpte.h.p && !f->writable) { + rc = -EOPNOTSUPP; + } else { + pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false); + pgste.vsie_notif = 1; + } pgste_set_unlock(ptep_h, pgste); + if (rc) + return rc; + if (!sg->parent) + return -EAGAIN; newpte = _pte(f->pfn, 0, !p, 0); - pgste = pgste_get_lock(ptep); + if (!pgste_get_trylock(ptep, &pgste)) + return -EAGAIN; pgste = __dat_ptep_xchg(ptep, pgste, newpte, gpa_to_gfn(raddr), sg->asce, uses_skeys(sg)); pgste_set_unlock(ptep, pgste); @@ -1454,7 +1464,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, union crste *table, struct guest_fault *f, bool p) { - union crste newcrste; + union crste newcrste, oldcrste; gfn_t gfn; int rc; @@ -1467,16 +1477,28 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni if (rc) return rc; - newcrste = _crste_fc1(f->pfn, host->h.tt, f->writable, !p); - newcrste.s.fc1.d |= host->s.fc1.d; - newcrste.s.fc1.sd |= host->s.fc1.sd; - newcrste.h.p &= host->h.p; - newcrste.s.fc1.vsie_notif = 1; - newcrste.s.fc1.prefix_notif = host->s.fc1.prefix_notif; - _gmap_crstep_xchg(sg->parent, host, newcrste, f->gfn, false); + do { + /* _gmap_crstep_xchg_atomic() could have unshadowed this shadow gmap */ + if (!sg->parent) + return -EAGAIN; + oldcrste = READ_ONCE(*host); + newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, f->writable, !p); + newcrste.s.fc1.d |= oldcrste.s.fc1.d; + newcrste.s.fc1.sd |= oldcrste.s.fc1.sd; + newcrste.h.p &= oldcrste.h.p; + newcrste.s.fc1.vsie_notif = 1; + newcrste.s.fc1.prefix_notif = oldcrste.s.fc1.prefix_notif; + newcrste.s.fc1.s = oldcrste.s.fc1.s; + if (!newcrste.h.p && !f->writable) + return -EOPNOTSUPP; + } while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false)); + if (!sg->parent) + return -EAGAIN; - newcrste = _crste_fc1(f->pfn, host->h.tt, 0, !p); - dat_crstep_xchg(table, newcrste, gpa_to_gfn(raddr), sg->asce); + newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p); + gfn = gpa_to_gfn(raddr); + while (!dat_crstep_xchg_atomic(table, READ_ONCE(*table), newcrste, gfn, sg->asce)) + ; return 0; } @@ -1500,21 +1522,31 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg, if (rc) return rc; - /* A race occourred. The shadow mapping is already valid, nothing to do */ - if ((ptep && !ptep->h.i) || (!ptep && crste_leaf(*table))) + /* A race occurred. The shadow mapping is already valid, nothing to do */ + if ((ptep && !ptep->h.i && ptep->h.p == w->p) || + (!ptep && crste_leaf(*table) && !table->h.i && table->h.p == w->p)) return 0; gl = get_level(table, ptep); + /* In case of a real address space */ + if (w->level <= LEVEL_MEM) { + l = TABLE_TYPE_PAGE_TABLE; + hl = TABLE_TYPE_REGION1; + goto real_address_space; + } + /* * Skip levels that are already protected. For each level, protect * only the page containing the entry, not the whole table. */ for (i = gl ; i >= w->level; i--) { - rc = gmap_protect_rmap(mc, sg, entries[i - 1].gfn, gpa_to_gfn(saddr), - entries[i - 1].pfn, i, entries[i - 1].writable); + rc = gmap_protect_rmap(mc, sg, entries[i].gfn, gpa_to_gfn(saddr), + entries[i].pfn, i + 1, entries[i].writable); if (rc) return rc; + if (!sg->parent) + return -EAGAIN; } rc = dat_entry_walk(NULL, entries[LEVEL_MEM].gfn, sg->parent->asce, DAT_WALK_LEAF, @@ -1526,6 +1558,7 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg, /* Get the smallest granularity */ l = min3(gl, hl, w->level); +real_address_space: flags = DAT_WALK_SPLIT_ALLOC | (uses_skeys(sg->parent) ? DAT_WALK_USES_SKEYS : 0); /* If necessary, create the shadow mapping */ if (l < gl) { diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index ef0c6ebfdde2..645c32c767d2 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -313,13 +313,16 @@ static long gmap_clear_young_crste(union crste *crstep, gfn_t gfn, gfn_t end, st struct clear_young_pte_priv *priv = walk->priv; union crste crste, new; - crste = READ_ONCE(*crstep); + do { + crste = READ_ONCE(*crstep); + + if (!crste.h.fc) + return 0; + if (!crste.s.fc1.y && crste.h.i) + return 0; + if (crste_prefix(crste) && !gmap_mkold_prefix(priv->gmap, gfn, end)) + break; - if (!crste.h.fc) - return 0; - if (!crste.s.fc1.y && crste.h.i) - return 0; - if (!crste_prefix(crste) || gmap_mkold_prefix(priv->gmap, gfn, end)) { new = crste; new.h.i = 1; new.s.fc1.y = 0; @@ -328,8 +331,8 @@ static long gmap_clear_young_crste(union crste *crstep, gfn_t gfn, gfn_t end, st folio_set_dirty(phys_to_folio(crste_origin_large(crste))); new.s.fc1.d = 0; new.h.p = 1; - dat_crstep_xchg(crstep, new, gfn, walk->asce); - } + } while (!dat_crstep_xchg_atomic(crstep, crste, new, gfn, walk->asce)); + priv->young = 1; return 0; } @@ -391,14 +394,18 @@ static long _gmap_unmap_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct { struct gmap_unmap_priv *priv = walk->priv; struct folio *folio = NULL; + union crste old = *crstep; - if (crstep->h.fc) { - if (crstep->s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags)) - folio = phys_to_folio(crste_origin_large(*crstep)); - gmap_crstep_xchg(priv->gmap, crstep, _CRSTE_EMPTY(crstep->h.tt), gfn); - if (folio) - uv_convert_from_secure_folio(folio); - } + if (!old.h.fc) + return 0; + + if (old.s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags)) + folio = phys_to_folio(crste_origin_large(old)); + /* No races should happen because kvm->mmu_lock is held in write mode */ + KVM_BUG_ON(!gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn), + priv->gmap->kvm); + if (folio) + uv_convert_from_secure_folio(folio); return 0; } @@ -474,23 +481,24 @@ static long _crste_test_and_clear_softdirty(union crste *table, gfn_t gfn, gfn_t if (fatal_signal_pending(current)) return 1; - crste = READ_ONCE(*table); - if (!crste.h.fc) - return 0; - if (crste.h.p && !crste.s.fc1.sd) - return 0; + do { + crste = READ_ONCE(*table); + if (!crste.h.fc) + return 0; + if (crste.h.p && !crste.s.fc1.sd) + return 0; - /* - * If this large page contains one or more prefixes of vCPUs that are - * currently running, do not reset the protection, leave it marked as - * dirty. - */ - if (!crste.s.fc1.prefix_notif || gmap_mkold_prefix(gmap, gfn, end)) { + /* + * If this large page contains one or more prefixes of vCPUs that are + * currently running, do not reset the protection, leave it marked as + * dirty. + */ + if (crste.s.fc1.prefix_notif && !gmap_mkold_prefix(gmap, gfn, end)) + break; new = crste; new.h.p = 1; new.s.fc1.sd = 0; - gmap_crstep_xchg(gmap, table, new, gfn); - } + } while (!gmap_crstep_xchg_atomic(gmap, table, crste, new, gfn)); for ( ; gfn < end; gfn++) mark_page_dirty(gmap->kvm, gfn); @@ -511,7 +519,7 @@ void gmap_sync_dirty_log(struct gmap *gmap, gfn_t start, gfn_t end) _dat_walk_gfn_range(start, end, gmap->asce, &walk_ops, 0, gmap); } -static int gmap_handle_minor_crste_fault(union asce asce, struct guest_fault *f) +static int gmap_handle_minor_crste_fault(struct gmap *gmap, struct guest_fault *f) { union crste newcrste, oldcrste = READ_ONCE(*f->crstep); @@ -536,10 +544,8 @@ static int gmap_handle_minor_crste_fault(union asce asce, struct guest_fault *f) newcrste.s.fc1.d = 1; newcrste.s.fc1.sd = 1; } - if (!oldcrste.s.fc1.d && newcrste.s.fc1.d) - SetPageDirty(phys_to_page(crste_origin_large(newcrste))); /* In case of races, let the slow path deal with it. */ - return !dat_crstep_xchg_atomic(f->crstep, oldcrste, newcrste, f->gfn, asce); + return !gmap_crstep_xchg_atomic(gmap, f->crstep, oldcrste, newcrste, f->gfn); } /* Trying to write on a read-only page, let the slow path deal with it. */ return 1; @@ -568,8 +574,6 @@ static int _gmap_handle_minor_pte_fault(struct gmap *gmap, union pgste *pgste, newpte.s.d = 1; newpte.s.sd = 1; } - if (!oldpte.s.d && newpte.s.d) - SetPageDirty(pfn_to_page(newpte.h.pfra)); *pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, *pgste, f->gfn); return 0; @@ -606,7 +610,7 @@ int gmap_try_fixup_minor(struct gmap *gmap, struct guest_fault *fault) fault->callback(fault); pgste_set_unlock(fault->ptep, pgste); } else { - rc = gmap_handle_minor_crste_fault(gmap->asce, fault); + rc = gmap_handle_minor_crste_fault(gmap, fault); if (!rc && fault->callback) fault->callback(fault); } @@ -623,10 +627,61 @@ static inline bool gmap_1m_allowed(struct gmap *gmap, gfn_t gfn) return test_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &gmap->flags); } +static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int level, + struct guest_fault *f) +{ + union crste oldval, newval; + union pte newpte, oldpte; + union pgste pgste; + int rc = 0; + + rc = dat_entry_walk(mc, f->gfn, gmap->asce, DAT_WALK_ALLOC_CONTINUE, level, + &f->crstep, &f->ptep); + if (rc == -ENOMEM) + return rc; + if (KVM_BUG_ON(rc == -EINVAL, gmap->kvm)) + return rc; + if (rc) + return -EAGAIN; + if (KVM_BUG_ON(get_level(f->crstep, f->ptep) > level, gmap->kvm)) + return -EINVAL; + + if (f->ptep) { + pgste = pgste_get_lock(f->ptep); + oldpte = *f->ptep; + newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page); + newpte.s.sd = oldpte.s.sd; + oldpte.s.sd = 0; + if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) { + pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, pgste, f->gfn); + if (f->callback) + f->callback(f); + } else { + rc = -EAGAIN; + } + pgste_set_unlock(f->ptep, pgste); + } else { + do { + oldval = READ_ONCE(*f->crstep); + newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable, + f->write_attempt | oldval.s.fc1.d); + newval.s.fc1.s = !f->page; + newval.s.fc1.sd = oldval.s.fc1.sd; + if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val && + crste_origin_large(oldval) != crste_origin_large(newval)) + return -EAGAIN; + } while (!gmap_crstep_xchg_atomic(gmap, f->crstep, oldval, newval, f->gfn)); + if (f->callback) + f->callback(f); + } + + return rc; +} + int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fault *f) { unsigned int order; - int rc, level; + int level; lockdep_assert_held(&gmap->kvm->mmu_lock); @@ -638,16 +693,14 @@ int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fau else if (order >= get_order(_SEGMENT_SIZE) && gmap_1m_allowed(gmap, f->gfn)) level = TABLE_TYPE_SEGMENT; } - rc = dat_link(mc, gmap->asce, level, uses_skeys(gmap), f); - KVM_BUG_ON(rc == -EINVAL, gmap->kvm); - return rc; + return _gmap_link(mc, gmap, level, f); } static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, gfn_t p_gfn, gfn_t c_gfn, bool force_alloc) { + union crste newcrste, oldcrste; struct page_table *pt; - union crste newcrste; union crste *crstep; union pte *ptep; int rc; @@ -673,7 +726,11 @@ static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, &crstep, &ptep); if (rc) return rc; - dat_crstep_xchg(crstep, newcrste, c_gfn, gmap->asce); + do { + oldcrste = READ_ONCE(*crstep); + if (oldcrste.val == newcrste.val) + break; + } while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, c_gfn, gmap->asce)); return 0; } @@ -777,8 +834,10 @@ static void gmap_ucas_unmap_one(struct gmap *gmap, gfn_t c_gfn) int rc; rc = dat_entry_walk(NULL, c_gfn, gmap->asce, 0, TABLE_TYPE_SEGMENT, &crstep, &ptep); - if (!rc) - dat_crstep_xchg(crstep, _PMD_EMPTY, c_gfn, gmap->asce); + if (rc) + return; + while (!dat_crstep_xchg_atomic(crstep, READ_ONCE(*crstep), _PMD_EMPTY, c_gfn, gmap->asce)) + ; } void gmap_ucas_unmap(struct gmap *gmap, gfn_t c_gfn, unsigned long count) @@ -1017,8 +1076,8 @@ static void gmap_unshadow_level(struct gmap *sg, gfn_t r_gfn, int level) dat_ptep_xchg(ptep, _PTE_EMPTY, r_gfn, sg->asce, uses_skeys(sg)); return; } - crste = READ_ONCE(*crstep); - dat_crstep_clear(crstep, r_gfn, sg->asce); + + crste = dat_crstep_clear_atomic(crstep, r_gfn, sg->asce); if (crste_leaf(crste) || crste.h.i) return; if (is_pmd(crste)) @@ -1101,6 +1160,7 @@ struct gmap_protect_asce_top_level { static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, struct gmap *sg, struct gmap_protect_asce_top_level *context) { + struct gmap *parent; int rc, i; guard(write_lock)(&sg->kvm->mmu_lock); @@ -1108,7 +1168,12 @@ static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, s if (kvm_s390_array_needs_retry_safe(sg->kvm, context->seq, context->f)) return -EAGAIN; - scoped_guard(spinlock, &sg->parent->children_lock) { + parent = READ_ONCE(sg->parent); + if (!parent) + return -EAGAIN; + scoped_guard(spinlock, &parent->children_lock) { + if (READ_ONCE(sg->parent) != parent) + return -EAGAIN; for (i = 0; i < CRST_TABLE_PAGES; i++) { if (!context->f[i].valid) continue; @@ -1191,6 +1256,9 @@ struct gmap *gmap_create_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *pare struct gmap *sg, *new; int rc; + if (WARN_ON(!parent)) + return ERR_PTR(-EINVAL); + scoped_guard(spinlock, &parent->children_lock) { sg = gmap_find_shadow(parent, asce, edat_level); if (sg) { diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h index ccb5cd751e31..579399ef5480 100644 --- a/arch/s390/kvm/gmap.h +++ b/arch/s390/kvm/gmap.h @@ -185,6 +185,8 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un else _gmap_handle_vsie_unshadow_event(gmap, gfn); } + if (!ptep->s.d && newpte.s.d && !newpte.s.s) + SetPageDirty(pfn_to_page(newpte.h.pfra)); return __dat_ptep_xchg(ptep, pgste, newpte, gfn, gmap->asce, uses_skeys(gmap)); } @@ -194,35 +196,42 @@ static inline union pgste gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, uni return _gmap_ptep_xchg(gmap, ptep, newpte, pgste, gfn, true); } -static inline void _gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne, - gfn_t gfn, bool needs_lock) +static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep, + union crste oldcrste, union crste newcrste, + gfn_t gfn, bool needs_lock) { - unsigned long align = 8 + (is_pmd(*crstep) ? 0 : 11); + unsigned long align = is_pmd(newcrste) ? _PAGE_ENTRIES : _PAGE_ENTRIES * _CRST_ENTRIES; + + if (KVM_BUG_ON(crstep->h.tt != oldcrste.h.tt || newcrste.h.tt != oldcrste.h.tt, gmap->kvm)) + return true; lockdep_assert_held(&gmap->kvm->mmu_lock); if (!needs_lock) lockdep_assert_held(&gmap->children_lock); gfn = ALIGN_DOWN(gfn, align); - if (crste_prefix(*crstep) && (ne.h.p || ne.h.i || !crste_prefix(ne))) { - ne.s.fc1.prefix_notif = 0; + if (crste_prefix(oldcrste) && (newcrste.h.p || newcrste.h.i || !crste_prefix(newcrste))) { + newcrste.s.fc1.prefix_notif = 0; gmap_unmap_prefix(gmap, gfn, gfn + align); } - if (crste_leaf(*crstep) && crstep->s.fc1.vsie_notif && - (ne.h.p || ne.h.i || !ne.s.fc1.vsie_notif)) { - ne.s.fc1.vsie_notif = 0; + if (crste_leaf(oldcrste) && oldcrste.s.fc1.vsie_notif && + (newcrste.h.p || newcrste.h.i || !newcrste.s.fc1.vsie_notif)) { + newcrste.s.fc1.vsie_notif = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); else _gmap_handle_vsie_unshadow_event(gmap, gfn); } - dat_crstep_xchg(crstep, ne, gfn, gmap->asce); + if (!oldcrste.s.fc1.d && newcrste.s.fc1.d && !newcrste.s.fc1.s) + SetPageDirty(phys_to_page(crste_origin_large(newcrste))); + return dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, gmap->asce); } -static inline void gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne, - gfn_t gfn) +static inline bool __must_check gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep, + union crste oldcrste, union crste newcrste, + gfn_t gfn) { - return _gmap_crstep_xchg(gmap, crstep, ne, gfn, true); + return _gmap_crstep_xchg_atomic(gmap, crstep, oldcrste, newcrste, gfn, true); } /** diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 18932a65ca68..7cb8ce833b62 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2724,6 +2724,9 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) bit = bit_nr + (addr % PAGE_SIZE) * 8; + /* kvm_set_routing_entry() should never allow this to happen */ + WARN_ON_ONCE(bit > (PAGE_SIZE * BITS_PER_BYTE - 1)); + return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit; } @@ -2824,6 +2827,12 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, int rc; mci.val = mcck_info->mcic; + + /* log machine checks being reinjected on all debugs */ + VCPU_EVENT(vcpu, 2, "guest machine check %lx", mci.val); + KVM_EVENT(2, "guest machine check %lx", mci.val); + pr_info("guest machine check pid %d: %lx", current->pid, mci.val); + if (mci.sr) cr14 |= CR14_RECOVERY_SUBMASK; if (mci.dg) @@ -2852,6 +2861,7 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { + const struct kvm_irq_routing_s390_adapter *adapter; u64 uaddr_s, uaddr_i; int idx; @@ -2862,6 +2872,14 @@ int kvm_set_routing_entry(struct kvm *kvm, return -EINVAL; e->set = set_adapter_int; + adapter = &ue->u.adapter; + if (adapter->summary_addr + (adapter->summary_offset / 8) >= + (adapter->summary_addr & PAGE_MASK) + PAGE_SIZE) + return -EINVAL; + if (adapter->ind_addr + (adapter->ind_offset / 8) >= + (adapter->ind_addr & PAGE_MASK) + PAGE_SIZE) + return -EINVAL; + idx = srcu_read_lock(&kvm->srcu); uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr); uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3eb60aa932ec..d7838334a338 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4617,7 +4617,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) return 0; } -static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) +static int vcpu_post_run(struct kvm_vcpu *vcpu, int sie_return) { struct mcck_volatile_info *mcck_info; struct sie_page *sie_page; @@ -4633,14 +4633,14 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14; vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15; - if (exit_reason == -EINTR) { - VCPU_EVENT(vcpu, 3, "%s", "machine check"); + if (sie_return == SIE64_RETURN_MCCK) { sie_page = container_of(vcpu->arch.sie_block, struct sie_page, sie_block); mcck_info = &sie_page->mcck_info; kvm_s390_reinject_machine_check(vcpu, mcck_info); return 0; } + WARN_ON_ONCE(sie_return != SIE64_RETURN_NORMAL); if (vcpu->arch.sie_block->icptcode > 0) { rc = kvm_handle_sie_intercept(vcpu); @@ -4679,7 +4679,7 @@ int noinstr kvm_s390_enter_exit_sie(struct kvm_s390_sie_block *scb, #define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK) static int __vcpu_run(struct kvm_vcpu *vcpu) { - int rc, exit_reason; + int rc, sie_return; struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block; /* @@ -4719,9 +4719,9 @@ xfer_to_guest_mode_check: guest_timing_enter_irqoff(); __disable_cpu_timer_accounting(vcpu); - exit_reason = kvm_s390_enter_exit_sie(vcpu->arch.sie_block, - vcpu->run->s.regs.gprs, - vcpu->arch.gmap->asce.val); + sie_return = kvm_s390_enter_exit_sie(vcpu->arch.sie_block, + vcpu->run->s.regs.gprs, + vcpu->arch.gmap->asce.val); __enable_cpu_timer_accounting(vcpu); guest_timing_exit_irqoff(); @@ -4744,7 +4744,7 @@ xfer_to_guest_mode_check: } kvm_vcpu_srcu_read_lock(vcpu); - rc = vcpu_post_run(vcpu, exit_reason); + rc = vcpu_post_run(vcpu, sie_return); if (rc || guestdbg_exit_pending(vcpu)) { kvm_vcpu_srcu_read_unlock(vcpu); break; @@ -5520,9 +5520,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_S390_VCPU_FAULT: { - idx = srcu_read_lock(&vcpu->kvm->srcu); - r = vcpu_dat_fault_handler(vcpu, arg, 0); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + gpa_t gaddr = arg; + + scoped_guard(srcu, &vcpu->kvm->srcu) { + r = vcpu_ucontrol_translate(vcpu, &gaddr); + if (r) + break; + + r = kvm_s390_faultin_gfn_simple(vcpu, NULL, gpa_to_gfn(gaddr), false); + if (r == PGM_ADDRESSING) + r = -EFAULT; + if (r <= 0) + break; + r = -EIO; + KVM_BUG_ON(r, vcpu->kvm); + } break; } case KVM_ENABLE_CAP: diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index d249b10044eb..72895dddc39a 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1122,6 +1122,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, struc { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + unsigned long sie_return = SIE64_RETURN_NORMAL; int guest_bp_isolation; int rc = 0; @@ -1163,7 +1164,7 @@ xfer_to_guest_mode_check: goto xfer_to_guest_mode_check; } guest_timing_enter_irqoff(); - rc = kvm_s390_enter_exit_sie(scb_s, vcpu->run->s.regs.gprs, sg->asce.val); + sie_return = kvm_s390_enter_exit_sie(scb_s, vcpu->run->s.regs.gprs, sg->asce.val); guest_timing_exit_irqoff(); local_irq_enable(); } @@ -1178,12 +1179,13 @@ skip_sie: kvm_vcpu_srcu_read_lock(vcpu); - if (rc == -EINTR) { - VCPU_EVENT(vcpu, 3, "%s", "machine check"); + if (sie_return == SIE64_RETURN_MCCK) { kvm_s390_reinject_machine_check(vcpu, &vsie_page->mcck_info); return 0; } + WARN_ON_ONCE(sie_return != SIE64_RETURN_NORMAL); + if (rc > 0) rc = 0; /* we could still have an icpt */ else if (current->thread.gmap_int_code) @@ -1326,7 +1328,7 @@ static void unregister_shadow_scb(struct kvm_vcpu *vcpu) static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; - struct gmap *sg; + struct gmap *sg = NULL; int rc = 0; while (1) { @@ -1366,6 +1368,8 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) sg = gmap_put(sg); cond_resched(); } + if (sg) + sg = gmap_put(sg); if (rc == -EFAULT) { /* diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index a52aa7a99b6b..191cc53caead 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -441,10 +441,17 @@ void do_secure_storage_access(struct pt_regs *regs) folio = phys_to_folio(addr); if (unlikely(!folio_try_get(folio))) return; - rc = arch_make_folio_accessible(folio); + rc = uv_convert_from_secure(folio_to_phys(folio)); + if (!rc) + clear_bit(PG_arch_1, &folio->flags.f); folio_put(folio); + /* + * There are some valid fixup types for kernel + * accesses to donated secure memory. zeropad is one + * of them. + */ if (rc) - BUG(); + return handle_fault_error_nolock(regs, 0); } else { if (faulthandler_disabled()) return handle_fault_error_nolock(regs, 0); diff --git a/arch/x86/coco/sev/noinstr.c b/arch/x86/coco/sev/noinstr.c index 9d94aca4a698..5afd663a1c21 100644 --- a/arch/x86/coco/sev/noinstr.c +++ b/arch/x86/coco/sev/noinstr.c @@ -121,6 +121,9 @@ noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state) WARN_ON(!irqs_disabled()); + if (!sev_cfg.ghcbs_initialized) + return boot_ghcb; + data = this_cpu_read(runtime_data); ghcb = &data->ghcb_page; @@ -164,6 +167,9 @@ noinstr void __sev_put_ghcb(struct ghcb_state *state) WARN_ON(!irqs_disabled()); + if (!sev_cfg.ghcbs_initialized) + return; + data = this_cpu_read(runtime_data); ghcb = &data->ghcb_page; diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index 88c757ac8ccd..fbe2d10dd737 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -177,6 +177,16 @@ static noinstr void fred_extint(struct pt_regs *regs) } } +#ifdef CONFIG_AMD_MEM_ENCRYPT +noinstr void exc_vmm_communication(struct pt_regs *regs, unsigned long error_code) +{ + if (user_mode(regs)) + return user_exc_vmm_communication(regs, error_code); + else + return kernel_exc_vmm_communication(regs, error_code); +} +#endif + static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code) { /* Optimize for #PF. That's the only exception which matters performance wise */ @@ -207,6 +217,10 @@ static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code) #ifdef CONFIG_X86_CET case X86_TRAP_CP: return exc_control_protection(regs, error_code); #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT + case X86_TRAP_VC: return exc_vmm_communication(regs, error_code); +#endif + default: return fred_bad_type(regs, error_code); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a8ff4376c286..ec0670114efa 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -433,7 +433,20 @@ static __always_inline void setup_lass(struct cpuinfo_x86 *c) /* These bits should not change their value after CPU init is finished. */ static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | - X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED; + X86_CR4_FSGSBASE | X86_CR4_CET; + +/* + * The CR pinning protects against ROP on the 'mov %reg, %CRn' instruction(s). + * Since you can ROP directly to these instructions (barring shadow stack), + * any protection must follow immediately and unconditionally after that. + * + * Specifically, the CR[04] write functions below will have the value + * validation controlled by the @cr_pinning static_branch which is + * __ro_after_init, just like the cr4_pinned_bits value. + * + * Once set, an attacker will have to defeat page-tables to get around these + * restrictions. Which is a much bigger ask than 'simple' ROP. + */ static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -2050,12 +2063,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_umip(c); setup_lass(c); - /* Enable FSGSBASE instructions if available. */ - if (cpu_has(c, X86_FEATURE_FSGSBASE)) { - cr4_set_bits(X86_CR4_FSGSBASE); - elf_hwcap2 |= HWCAP2_FSGSBASE; - } - /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -2416,6 +2423,18 @@ void cpu_init_exception_handling(bool boot_cpu) /* GHCB needs to be setup to handle #VC. */ setup_ghcb(); + /* + * On CPUs with FSGSBASE support, paranoid_entry() uses + * ALTERNATIVE-patched RDGSBASE/WRGSBASE instructions. Secondary CPUs + * boot after alternatives are patched globally, so early exceptions + * execute patched code that depends on FSGSBASE. Enable the feature + * before any exceptions occur. + */ + if (cpu_feature_enabled(X86_FEATURE_FSGSBASE)) { + cr4_set_bits(X86_CR4_FSGSBASE); + elf_hwcap2 |= HWCAP2_FSGSBASE; + } + if (cpu_feature_enabled(X86_FEATURE_FRED)) { /* The boot CPU has enabled FRED during early boot */ if (!boot_cpu) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index b922a8b00057..dd06453d5b72 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3044,12 +3044,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; - if (unlikely(is_noslot_pfn(pfn))) { - vcpu->stat.pf_mmio_spte_created++; - mark_mmio_spte(vcpu, sptep, gfn, pte_access); - return RET_PF_EMULATE; - } - if (is_shadow_present_pte(*sptep)) { if (prefetch && is_last_spte(*sptep, level) && pfn == spte_to_pfn(*sptep)) @@ -3066,13 +3060,22 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, child = spte_to_child_sp(pte); drop_parent_pte(vcpu->kvm, child, sptep); flush = true; - } else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) { + } else if (pfn != spte_to_pfn(*sptep)) { + WARN_ON_ONCE(vcpu->arch.mmu->root_role.direct); drop_spte(vcpu->kvm, sptep); flush = true; } else was_rmapped = 1; } + if (unlikely(is_noslot_pfn(pfn))) { + vcpu->stat.pf_mmio_spte_created++; + mark_mmio_spte(vcpu, sptep, gfn, pte_access); + if (flush) + kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); + return RET_PF_EMULATE; + } + wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, false, host_writable, &spte); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 35caa5746115..79f0818131e8 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -424,7 +424,7 @@ void __init efi_unmap_boot_services(void) if (efi_enabled(EFI_DBG)) return; - sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1; + sz = sizeof(*ranges_to_free) * (efi.memmap.nr_map + 1); ranges_to_free = kzalloc(sz, GFP_KERNEL); if (!ranges_to_free) { pr_err("Failed to allocate storage for freeable EFI regions\n"); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 0bb609fbec7d..8e0199394984 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -623,8 +623,10 @@ static int af_alg_alloc_tsgl(struct sock *sk) sg_init_table(sgl->sg, MAX_SGL_ENTS + 1); sgl->cur = 0; - if (sg) + if (sg) { + sg_unmark_end(sg + MAX_SGL_ENTS - 1); sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg); + } list_add_tail(&sgl->list, &ctx->tsgl_list); } @@ -635,15 +637,13 @@ static int af_alg_alloc_tsgl(struct sock *sk) /** * af_alg_count_tsgl - Count number of TX SG entries * - * The counting starts from the beginning of the SGL to @bytes. If - * an @offset is provided, the counting of the SG entries starts at the @offset. + * The counting starts from the beginning of the SGL to @bytes. * * @sk: socket of connection to user space * @bytes: Count the number of SG entries holding given number of bytes. - * @offset: Start the counting of SG entries from the given offset. * Return: Number of TX SG entries found given the constraints */ -unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) +unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes) { const struct alg_sock *ask = alg_sk(sk); const struct af_alg_ctx *ctx = ask->private; @@ -658,25 +658,11 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) const struct scatterlist *sg = sgl->sg; for (i = 0; i < sgl->cur; i++) { - size_t bytes_count; - - /* Skip offset */ - if (offset >= sg[i].length) { - offset -= sg[i].length; - bytes -= sg[i].length; - continue; - } - - bytes_count = sg[i].length - offset; - - offset = 0; sgl_count++; - - /* If we have seen requested number of bytes, stop */ - if (bytes_count >= bytes) + if (sg[i].length >= bytes) return sgl_count; - bytes -= bytes_count; + bytes -= sg[i].length; } } @@ -688,19 +674,14 @@ EXPORT_SYMBOL_GPL(af_alg_count_tsgl); * af_alg_pull_tsgl - Release the specified buffers from TX SGL * * If @dst is non-null, reassign the pages to @dst. The caller must release - * the pages. If @dst_offset is given only reassign the pages to @dst starting - * at the @dst_offset (byte). The caller must ensure that @dst is large - * enough (e.g. by using af_alg_count_tsgl with the same offset). + * the pages. * * @sk: socket of connection to user space * @used: Number of bytes to pull from TX SGL * @dst: If non-NULL, buffer is reassigned to dst SGL instead of releasing. The * caller must release the buffers in dst. - * @dst_offset: Reassign the TX SGL from given offset. All buffers before - * reaching the offset is released. */ -void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, - size_t dst_offset) +void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; @@ -725,18 +706,10 @@ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, * SG entries in dst. */ if (dst) { - if (dst_offset >= plen) { - /* discard page before offset */ - dst_offset -= plen; - } else { - /* reassign page to dst after offset */ - get_page(page); - sg_set_page(dst + j, page, - plen - dst_offset, - sg[i].offset + dst_offset); - dst_offset = 0; - j++; - } + /* reassign page to dst after offset */ + get_page(page); + sg_set_page(dst + j, page, plen, sg[i].offset); + j++; } sg[i].length -= plen; diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 79b016a899a1..dda15bb05e89 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -26,7 +26,6 @@ #include <crypto/internal/aead.h> #include <crypto/scatterwalk.h> #include <crypto/if_alg.h> -#include <crypto/skcipher.h> #include <linux/init.h> #include <linux/list.h> #include <linux/kernel.h> @@ -72,9 +71,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct crypto_aead *tfm = pask->private; - unsigned int i, as = crypto_aead_authsize(tfm); + unsigned int as = crypto_aead_authsize(tfm); struct af_alg_async_req *areq; - struct af_alg_tsgl *tsgl, *tmp; struct scatterlist *rsgl_src, *tsgl_src = NULL; int err = 0; size_t used = 0; /* [in] TX bufs to be en/decrypted */ @@ -154,23 +152,24 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, outlen -= less; } + /* + * Create a per request TX SGL for this request which tracks the + * SG entries from the global TX SGL. + */ processed = used + ctx->aead_assoclen; - list_for_each_entry_safe(tsgl, tmp, &ctx->tsgl_list, list) { - for (i = 0; i < tsgl->cur; i++) { - struct scatterlist *process_sg = tsgl->sg + i; - - if (!(process_sg->length) || !sg_page(process_sg)) - continue; - tsgl_src = process_sg; - break; - } - if (tsgl_src) - break; - } - if (processed && !tsgl_src) { - err = -EFAULT; + areq->tsgl_entries = af_alg_count_tsgl(sk, processed); + if (!areq->tsgl_entries) + areq->tsgl_entries = 1; + areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), + areq->tsgl_entries), + GFP_KERNEL); + if (!areq->tsgl) { + err = -ENOMEM; goto free; } + sg_init_table(areq->tsgl, areq->tsgl_entries); + af_alg_pull_tsgl(sk, processed, areq->tsgl); + tsgl_src = areq->tsgl; /* * Copy of AAD from source to destination @@ -179,76 +178,15 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, * when user space uses an in-place cipher operation, the kernel * will copy the data as it does not see whether such in-place operation * is initiated. - * - * To ensure efficiency, the following implementation ensure that the - * ciphers are invoked to perform a crypto operation in-place. This - * is achieved by memory management specified as follows. */ /* Use the RX SGL as source (and destination) for crypto op. */ rsgl_src = areq->first_rsgl.sgl.sgt.sgl; - if (ctx->enc) { - /* - * Encryption operation - The in-place cipher operation is - * achieved by the following operation: - * - * TX SGL: AAD || PT - * | | - * | copy | - * v v - * RX SGL: AAD || PT || Tag - */ - memcpy_sglist(areq->first_rsgl.sgl.sgt.sgl, tsgl_src, - processed); - af_alg_pull_tsgl(sk, processed, NULL, 0); - } else { - /* - * Decryption operation - To achieve an in-place cipher - * operation, the following SGL structure is used: - * - * TX SGL: AAD || CT || Tag - * | | ^ - * | copy | | Create SGL link. - * v v | - * RX SGL: AAD || CT ----+ - */ - - /* Copy AAD || CT to RX SGL buffer for in-place operation. */ - memcpy_sglist(areq->first_rsgl.sgl.sgt.sgl, tsgl_src, outlen); - - /* Create TX SGL for tag and chain it to RX SGL. */ - areq->tsgl_entries = af_alg_count_tsgl(sk, processed, - processed - as); - if (!areq->tsgl_entries) - areq->tsgl_entries = 1; - areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), - areq->tsgl_entries), - GFP_KERNEL); - if (!areq->tsgl) { - err = -ENOMEM; - goto free; - } - sg_init_table(areq->tsgl, areq->tsgl_entries); - - /* Release TX SGL, except for tag data and reassign tag data. */ - af_alg_pull_tsgl(sk, processed, areq->tsgl, processed - as); - - /* chain the areq TX SGL holding the tag with RX SGL */ - if (usedpages) { - /* RX SGL present */ - struct af_alg_sgl *sgl_prev = &areq->last_rsgl->sgl; - struct scatterlist *sg = sgl_prev->sgt.sgl; - - sg_unmark_end(sg + sgl_prev->sgt.nents - 1); - sg_chain(sg, sgl_prev->sgt.nents + 1, areq->tsgl); - } else - /* no RX SGL present (e.g. authentication only) */ - rsgl_src = areq->tsgl; - } + memcpy_sglist(rsgl_src, tsgl_src, ctx->aead_assoclen); /* Initialize the crypto operation */ - aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src, + aead_request_set_crypt(&areq->cra_u.aead_req, tsgl_src, areq->first_rsgl.sgl.sgt.sgl, used, ctx->iv); aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen); aead_request_set_tfm(&areq->cra_u.aead_req, tfm); @@ -450,7 +388,7 @@ static void aead_sock_destruct(struct sock *sk) struct crypto_aead *tfm = pask->private; unsigned int ivlen = crypto_aead_ivsize(tfm); - af_alg_pull_tsgl(sk, ctx->used, NULL, 0); + af_alg_pull_tsgl(sk, ctx->used, NULL); sock_kzfree_s(sk, ctx->iv, ivlen); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 125d395c5e00..82735e51be10 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -138,7 +138,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, * Create a per request TX SGL for this request which tracks the * SG entries from the global TX SGL. */ - areq->tsgl_entries = af_alg_count_tsgl(sk, len, 0); + areq->tsgl_entries = af_alg_count_tsgl(sk, len); if (!areq->tsgl_entries) areq->tsgl_entries = 1; areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), @@ -149,7 +149,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, goto free; } sg_init_table(areq->tsgl, areq->tsgl_entries); - af_alg_pull_tsgl(sk, len, areq->tsgl, 0); + af_alg_pull_tsgl(sk, len, areq->tsgl); /* Initialize the crypto operation */ skcipher_request_set_tfm(&areq->cra_u.skcipher_req, tfm); @@ -363,7 +363,7 @@ static void skcipher_sock_destruct(struct sock *sk) struct alg_sock *pask = alg_sk(psk); struct crypto_skcipher *tfm = pask->private; - af_alg_pull_tsgl(sk, ctx->used, NULL, 0); + af_alg_pull_tsgl(sk, ctx->used, NULL); sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); if (ctx->state) sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm)); diff --git a/crypto/authencesn.c b/crypto/authencesn.c index 542a978663b9..c0a01d738d9b 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -207,6 +207,7 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req, u8 *ohash = areq_ctx->tail; unsigned int cryptlen = req->cryptlen - authsize; unsigned int assoclen = req->assoclen; + struct scatterlist *src = req->src; struct scatterlist *dst = req->dst; u8 *ihash = ohash + crypto_ahash_digestsize(auth); u32 tmp[2]; @@ -214,23 +215,27 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req, if (!authsize) goto decrypt; - /* Move high-order bits of sequence number back. */ - scatterwalk_map_and_copy(tmp, dst, 4, 4, 0); - scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0); - scatterwalk_map_and_copy(tmp, dst, 0, 8, 1); + if (src == dst) { + /* Move high-order bits of sequence number back. */ + scatterwalk_map_and_copy(tmp, dst, 4, 4, 0); + scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0); + scatterwalk_map_and_copy(tmp, dst, 0, 8, 1); + } else + memcpy_sglist(dst, src, assoclen); if (crypto_memneq(ihash, ohash, authsize)) return -EBADMSG; decrypt: - sg_init_table(areq_ctx->dst, 2); + if (src != dst) + src = scatterwalk_ffwd(areq_ctx->src, src, assoclen); dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen); skcipher_request_set_tfm(skreq, ctx->enc); skcipher_request_set_callback(skreq, flags, req->base.complete, req->base.data); - skcipher_request_set_crypt(skreq, dst, dst, cryptlen, req->iv); + skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv); return crypto_skcipher_decrypt(skreq); } @@ -255,6 +260,7 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req) unsigned int assoclen = req->assoclen; unsigned int cryptlen = req->cryptlen; u8 *ihash = ohash + crypto_ahash_digestsize(auth); + struct scatterlist *src = req->src; struct scatterlist *dst = req->dst; u32 tmp[2]; int err; @@ -262,24 +268,28 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req) if (assoclen < 8) return -EINVAL; - cryptlen -= authsize; - - if (req->src != dst) - memcpy_sglist(dst, req->src, assoclen + cryptlen); + if (!authsize) + goto tail; + cryptlen -= authsize; scatterwalk_map_and_copy(ihash, req->src, assoclen + cryptlen, authsize, 0); - if (!authsize) - goto tail; - /* Move high-order bits of sequence number to the end. */ - scatterwalk_map_and_copy(tmp, dst, 0, 8, 0); - scatterwalk_map_and_copy(tmp, dst, 4, 4, 1); - scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1); - - sg_init_table(areq_ctx->dst, 2); - dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4); + scatterwalk_map_and_copy(tmp, src, 0, 8, 0); + if (src == dst) { + scatterwalk_map_and_copy(tmp, dst, 4, 4, 1); + scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1); + dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4); + } else { + scatterwalk_map_and_copy(tmp, dst, 0, 4, 1); + scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen - 4, 4, 1); + + src = scatterwalk_ffwd(areq_ctx->src, src, 8); + dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4); + memcpy_sglist(dst, src, assoclen + cryptlen - 8); + dst = req->dst; + } ahash_request_set_tfm(ahreq, auth); ahash_request_set_crypt(ahreq, dst, ohash, assoclen + cryptlen); diff --git a/crypto/deflate.c b/crypto/deflate.c index 46fc7def8d4c..710ebba7ce85 100644 --- a/crypto/deflate.c +++ b/crypto/deflate.c @@ -164,18 +164,21 @@ static int deflate_decompress_one(struct acomp_req *req, do { unsigned int dcur; + unsigned long avail_in; dcur = acomp_walk_next_dst(&walk); - if (!dcur) { - out_of_space = true; - break; - } stream->avail_out = dcur; stream->next_out = walk.dst.virt.addr; + avail_in = stream->avail_in; ret = zlib_inflate(stream, Z_NO_FLUSH); + if (!dcur && avail_in == stream->avail_in) { + out_of_space = true; + break; + } + dcur -= stream->avail_out; acomp_walk_done_dst(&walk, dcur); } while (ret == Z_OK && stream->avail_in); diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 5b34b6f50e69..f1b6155065ff 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -35,6 +35,7 @@ #define IVPU_HW_IP_60XX 60 #define IVPU_HW_IP_REV_LNL_B0 4 +#define IVPU_HW_IP_REV_NVL_A0 0 #define IVPU_HW_BTRS_MTL 1 #define IVPU_HW_BTRS_LNL 2 diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c index d69cd0d93569..d4a9bcda4100 100644 --- a/drivers/accel/ivpu/ivpu_hw.c +++ b/drivers/accel/ivpu/ivpu_hw.c @@ -70,8 +70,10 @@ static void wa_init(struct ivpu_device *vdev) if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL) vdev->wa.interrupt_clear_with_0 = ivpu_hw_btrs_irqs_clear_with_0_mtl(vdev); - if (ivpu_device_id(vdev) == PCI_DEVICE_ID_LNL && - ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0) + if ((ivpu_device_id(vdev) == PCI_DEVICE_ID_LNL && + ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0) || + (ivpu_device_id(vdev) == PCI_DEVICE_ID_NVL && + ivpu_revision(vdev) == IVPU_HW_IP_REV_NVL_A0)) vdev->wa.disable_clock_relinquish = true; if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_ENABLE) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 5f63ed120a2c..6f0065257a77 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1656,6 +1656,8 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca ret = ec_install_handlers(ec, device, call_reg); if (ret) { + ec_remove_handlers(ec); + if (ec == first_ec) first_ec = NULL; diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c index defb0573e43c..c7a962728752 100644 --- a/drivers/auxdisplay/lcd2s.c +++ b/drivers/auxdisplay/lcd2s.c @@ -99,8 +99,13 @@ static int lcd2s_print(struct charlcd *lcd, int c) { struct lcd2s_data *lcd2s = lcd->drvdata; u8 buf[2] = { LCD2S_CMD_WRITE, c }; + int ret; - lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf)); + ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf)); + if (ret < 0) + return ret; + if (ret != sizeof(buf)) + return -EIO; return 0; } @@ -108,9 +113,13 @@ static int lcd2s_gotoxy(struct charlcd *lcd, unsigned int x, unsigned int y) { struct lcd2s_data *lcd2s = lcd->drvdata; u8 buf[3] = { LCD2S_CMD_CUR_POS, y + 1, x + 1 }; + int ret; - lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf)); - + ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf)); + if (ret < 0) + return ret; + if (ret != sizeof(buf)) + return -EIO; return 0; } diff --git a/drivers/auxdisplay/line-display.c b/drivers/auxdisplay/line-display.c index 81b4aac65807..fb6d9294140d 100644 --- a/drivers/auxdisplay/line-display.c +++ b/drivers/auxdisplay/line-display.c @@ -365,7 +365,7 @@ static DEFINE_IDA(linedisp_id); static void linedisp_release(struct device *dev) { - struct linedisp *linedisp = to_linedisp(dev); + struct linedisp *linedisp = container_of(dev, struct linedisp, dev); kfree(linedisp->map); kfree(linedisp->message); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 607c1246d994..e388b19850e3 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1545,6 +1545,7 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg, unsigned int val_num) { void *orig_work_buf; + unsigned int selector_reg; unsigned int win_offset; unsigned int win_page; bool page_chg; @@ -1563,10 +1564,31 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg, return -EINVAL; } - /* It is possible to have selector register inside data window. - In that case, selector register is located on every page and - it needs no page switching, when accessed alone. */ + /* + * Calculate the address of the selector register in the corresponding + * data window if it is located on every page. + */ + page_chg = in_range(range->selector_reg, range->window_start, range->window_len); + if (page_chg) + selector_reg = range->range_min + win_page * range->window_len + + range->selector_reg - range->window_start; + + /* + * It is possible to have selector register inside data window. + * In that case, selector register is located on every page and it + * needs no page switching, when accessed alone. + * + * Nevertheless we should synchronize the cache values for it. + * This can't be properly achieved if the selector register is + * the first and the only one to be read inside the data window. + * That's why we update it in that case as well. + * + * However, we specifically avoid updating it for the default page, + * when it's overlapped with the real data window, to prevent from + * infinite looping. + */ if (val_num > 1 || + (page_chg && selector_reg != range->selector_reg) || range->window_start + win_offset != range->selector_reg) { /* Use separate work_buf during page switching */ orig_work_buf = map->work_buf; @@ -1575,7 +1597,7 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg, ret = _regmap_update_bits(map, range->selector_reg, range->selector_mask, win_page << range->selector_shift, - &page_chg, false); + NULL, false); map->work_buf = orig_work_buf; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index a324ede6206d..af679375b193 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -917,9 +917,8 @@ static void zram_account_writeback_submit(struct zram *zram) static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req) { - u32 size, index = req->pps->index; - int err, prio; - bool huge; + u32 index = req->pps->index; + int err; err = blk_status_to_errno(req->bio.bi_status); if (err) { @@ -946,28 +945,13 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req) goto out; } - if (zram->compressed_wb) { - /* - * ZRAM_WB slots get freed, we need to preserve data required - * for read decompression. - */ - size = get_slot_size(zram, index); - prio = get_slot_comp_priority(zram, index); - huge = test_slot_flag(zram, index, ZRAM_HUGE); - } - - slot_free(zram, index); - set_slot_flag(zram, index, ZRAM_WB); + clear_slot_flag(zram, index, ZRAM_IDLE); + if (test_slot_flag(zram, index, ZRAM_HUGE)) + atomic64_dec(&zram->stats.huge_pages); + atomic64_sub(get_slot_size(zram, index), &zram->stats.compr_data_size); + zs_free(zram->mem_pool, get_slot_handle(zram, index)); set_slot_handle(zram, index, req->blk_idx); - - if (zram->compressed_wb) { - if (huge) - set_slot_flag(zram, index, ZRAM_HUGE); - set_slot_size(zram, index, size); - set_slot_comp_priority(zram, index, prio); - } - - atomic64_inc(&zram->stats.pages_stored); + set_slot_flag(zram, index, ZRAM_WB); out: slot_unlock(zram, index); @@ -2010,8 +1994,13 @@ static void slot_free(struct zram *zram, u32 index) set_slot_comp_priority(zram, index, 0); if (test_slot_flag(zram, index, ZRAM_HUGE)) { + /* + * Writeback completion decrements ->huge_pages but keeps + * ZRAM_HUGE flag for deferred decompression path. + */ + if (!test_slot_flag(zram, index, ZRAM_WB)) + atomic64_dec(&zram->stats.huge_pages); clear_slot_flag(zram, index, ZRAM_HUGE); - atomic64_dec(&zram->stats.huge_pages); } if (test_slot_flag(zram, index, ZRAM_WB)) { diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 246b6205c5e0..ab146894ba4e 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -251,11 +251,13 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code) bt_dev_err(hdev, "Hardware error 0x%2.2x", code); + hci_req_sync_lock(hdev); + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { bt_dev_err(hdev, "Reset after hardware error failed (%ld)", PTR_ERR(skb)); - return; + goto unlock; } kfree_skb(skb); @@ -263,18 +265,21 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code) if (IS_ERR(skb)) { bt_dev_err(hdev, "Retrieving Intel exception info failed (%ld)", PTR_ERR(skb)); - return; + goto unlock; } if (skb->len != 13) { bt_dev_err(hdev, "Exception info size mismatch"); kfree_skb(skb); - return; + goto unlock; } bt_dev_err(hdev, "Exception info %s", (char *)(skb->data + 1)); kfree_skb(skb); + +unlock: + hci_req_sync_unlock(hdev); } EXPORT_SYMBOL_GPL(btintel_hw_error); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a1c5eb993e47..5c535f3ab722 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2376,8 +2376,11 @@ static void btusb_work(struct work_struct *work) if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_CVSD) { if (hdev->voice_setting & 0x0020) { static const int alts[3] = { 2, 4, 5 }; + unsigned int sco_idx; - new_alts = alts[data->sco_num - 1]; + sco_idx = min_t(unsigned int, data->sco_num - 1, + ARRAY_SIZE(alts) - 1); + new_alts = alts[sco_idx]; } else { new_alts = data->sco_num; } diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index 07cc2a79a77b..a889a66a326f 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -109,9 +109,6 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count) { struct h4_struct *h4 = hu->priv; - if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) - return -EUNATCH; - h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count, h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts)); if (IS_ERR(h4->rx_skb)) { diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 91acf24f1ef5..91c96ad12342 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -541,6 +541,8 @@ static int download_firmware(struct ll_device *lldev) if (err || !fw->data || !fw->size) { bt_dev_err(lldev->hu.hdev, "request_firmware failed(errno %d) for %s", err, bts_scr_name); + if (!err) + release_firmware(fw); return -EINVAL; } ptr = (void *)fw->data; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 277884d91913..1f794524a1d9 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1427,12 +1427,9 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy, * If there is a problem with its frequency table, take it * offline and drop it. */ - if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING && - policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) { - ret = cpufreq_table_validate_and_sort(policy); - if (ret) - goto out_offline_policy; - } + ret = cpufreq_table_validate_and_sort(policy); + if (ret) + goto out_offline_policy; /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index e0e847764511..df01d33993d8 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -313,6 +313,17 @@ static void cs_start(struct cpufreq_policy *policy) dbs_info->requested_freq = policy->cur; } +static void cs_limits(struct cpufreq_policy *policy) +{ + struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data); + + /* + * The limits have changed, so may have the current frequency. Reset + * requested_freq to avoid any unintended outcomes due to the mismatch. + */ + dbs_info->requested_freq = policy->cur; +} + static struct dbs_governor cs_governor = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"), .kobj_type = { .default_groups = cs_groups }, @@ -322,6 +333,7 @@ static struct dbs_governor cs_governor = { .init = cs_init, .exit = cs_exit, .start = cs_start, + .limits = cs_limits, }; #define CPU_FREQ_GOV_CONSERVATIVE (cs_governor.gov) diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 36eb7aee4bcd..acf101878733 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -563,6 +563,7 @@ EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop); void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy) { + struct dbs_governor *gov = dbs_governor_of(policy); struct policy_dbs_info *policy_dbs; /* Protect gov->gdbs_data against cpufreq_dbs_governor_exit() */ @@ -574,6 +575,8 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy) mutex_lock(&policy_dbs->update_mutex); cpufreq_policy_apply_limits(policy); gov_update_sample_delay(policy_dbs, 0); + if (gov->limits) + gov->limits(policy); mutex_unlock(&policy_dbs->update_mutex); out: diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index 168c23fd7fca..1462d59277bd 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -138,6 +138,7 @@ struct dbs_governor { int (*init)(struct dbs_data *dbs_data); void (*exit)(struct dbs_data *dbs_data); void (*start)(struct cpufreq_policy *policy); + void (*limits)(struct cpufreq_policy *policy); }; static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 7f251daf03ce..5b364d8da4f9 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -360,6 +360,10 @@ int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy) if (policy_has_boost_freq(policy)) policy->boost_supported = true; + if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING || + policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_DESCENDING) + return 0; + return set_freq_table_sorted(policy); } diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 167372936ca7..78964e1712e5 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -3326,9 +3326,10 @@ static int ahash_setkey(struct crypto_ahash *ahash, const u8 *key, if (aligned_len < keylen) return -EOVERFLOW; - hashed_key = kmemdup(key, aligned_len, GFP_KERNEL); + hashed_key = kmalloc(aligned_len, GFP_KERNEL); if (!hashed_key) return -ENOMEM; + memcpy(hashed_key, key, keylen); ret = hash_digest_key(ctx, &keylen, hashed_key, digestsize); if (ret) goto bad_free_key; diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 628c43a7efc4..44122208f70c 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -441,9 +441,10 @@ static int ahash_setkey(struct crypto_ahash *ahash, if (aligned_len < keylen) return -EOVERFLOW; - hashed_key = kmemdup(key, keylen, GFP_KERNEL); + hashed_key = kmalloc(aligned_len, GFP_KERNEL); if (!hashed_key) return -ENOMEM; + memcpy(hashed_key, key, keylen); ret = hash_digest_key(ctx, &keylen, hashed_key, digestsize); if (ret) goto bad_free_key; diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c index 0e07d0523291..9210cceb4b7b 100644 --- a/drivers/crypto/tegra/tegra-se-aes.c +++ b/drivers/crypto/tegra/tegra-se-aes.c @@ -529,7 +529,7 @@ static struct tegra_se_alg tegra_aes_algs[] = { .cra_name = "cbc(aes)", .cra_driver_name = "cbc-aes-tegra", .cra_priority = 500, - .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_aes_ctx), .cra_alignmask = 0xf, @@ -550,7 +550,7 @@ static struct tegra_se_alg tegra_aes_algs[] = { .cra_name = "ecb(aes)", .cra_driver_name = "ecb-aes-tegra", .cra_priority = 500, - .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_aes_ctx), .cra_alignmask = 0xf, @@ -572,7 +572,7 @@ static struct tegra_se_alg tegra_aes_algs[] = { .cra_name = "ctr(aes)", .cra_driver_name = "ctr-aes-tegra", .cra_priority = 500, - .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct tegra_aes_ctx), .cra_alignmask = 0xf, @@ -594,6 +594,7 @@ static struct tegra_se_alg tegra_aes_algs[] = { .cra_name = "xts(aes)", .cra_driver_name = "xts-aes-tegra", .cra_priority = 500, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_aes_ctx), .cra_alignmask = (__alignof__(u64) - 1), @@ -1922,6 +1923,7 @@ static struct tegra_se_alg tegra_aead_algs[] = { .cra_name = "gcm(aes)", .cra_driver_name = "gcm-aes-tegra", .cra_priority = 500, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct tegra_aead_ctx), .cra_alignmask = 0xf, @@ -1944,6 +1946,7 @@ static struct tegra_se_alg tegra_aead_algs[] = { .cra_name = "ccm(aes)", .cra_driver_name = "ccm-aes-tegra", .cra_priority = 500, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct tegra_aead_ctx), .cra_alignmask = 0xf, @@ -1971,7 +1974,7 @@ static struct tegra_se_alg tegra_cmac_algs[] = { .cra_name = "cmac(aes)", .cra_driver_name = "tegra-se-cmac", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_cmac_ctx), .cra_alignmask = 0, diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c index 4a298ace6e9f..06bb5bf0fa33 100644 --- a/drivers/crypto/tegra/tegra-se-hash.c +++ b/drivers/crypto/tegra/tegra-se-hash.c @@ -761,7 +761,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha1", .cra_driver_name = "tegra-se-sha1", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -786,7 +786,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha224", .cra_driver_name = "tegra-se-sha224", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -811,7 +811,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha256", .cra_driver_name = "tegra-se-sha256", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -836,7 +836,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha384", .cra_driver_name = "tegra-se-sha384", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -861,7 +861,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha512", .cra_driver_name = "tegra-se-sha512", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -886,7 +886,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha3-224", .cra_driver_name = "tegra-se-sha3-224", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA3_224_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -911,7 +911,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha3-256", .cra_driver_name = "tegra-se-sha3-256", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA3_256_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -936,7 +936,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha3-384", .cra_driver_name = "tegra-se-sha3-384", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA3_384_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -961,7 +961,7 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "sha3-512", .cra_driver_name = "tegra-se-sha3-512", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA3_512_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -988,7 +988,8 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "hmac(sha224)", .cra_driver_name = "tegra-se-hmac-sha224", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -1015,7 +1016,8 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "hmac(sha256)", .cra_driver_name = "tegra-se-hmac-sha256", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -1042,7 +1044,8 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "hmac(sha384)", .cra_driver_name = "tegra-se-hmac-sha384", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, @@ -1069,7 +1072,8 @@ static struct tegra_se_alg tegra_hash_algs[] = { .cra_name = "hmac(sha512)", .cra_driver_name = "tegra-se-hmac-sha512", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_ctxsize = sizeof(struct tegra_sha_ctx), .cra_alignmask = 0, diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 4589bf11d3fe..80aeb0d556bd 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -59,6 +59,7 @@ config CXL_ACPI tristate "CXL ACPI: Platform Support" depends on ACPI depends on ACPI_NUMA + depends on CXL_PMEM || !CXL_PMEM default CXL_BUS select ACPI_TABLE_LIB select ACPI_HMAT diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index c222e98ae736..cb5d5a047a9d 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -94,7 +94,6 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) struct cxl_hdm *cxlhdm; void __iomem *hdm; u32 ctrl; - int i; if (!info) return false; @@ -113,22 +112,16 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) return false; /* - * If any decoders are committed already, there should not be any - * emulated DVSEC decoders. + * If HDM decoders are globally enabled, do not fall back to DVSEC + * range emulation. Zeroed decoder registers after region teardown + * do not imply absence of HDM capability. + * + * Falling back to DVSEC here would treat the decoder as AUTO and + * may incorrectly latch default interleave settings. */ - for (i = 0; i < cxlhdm->decoder_count; i++) { - ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); - dev_dbg(&info->port->dev, - "decoder%d.%d: committed: %ld base: %#x_%.8x size: %#x_%.8x\n", - info->port->id, i, - FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl), - readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i)), - readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i)), - readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i)), - readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i))); - if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) - return false; - } + ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); + if (ctrl & CXL_HDM_DECODER_ENABLE) + return false; return true; } diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index e7a6452bf544..12386d912705 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1301,7 +1301,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) * Require an endpoint to be safe otherwise the driver can not * be sure that the device is unmapped. */ - if (endpoint && cxl_num_decoders_committed(endpoint) == 0) + if (cxlmd->dev.driver && cxl_num_decoders_committed(endpoint) == 0) return __cxl_mem_sanitize(mds, cmd); return -EBUSY; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 0c5957d1d329..c5aacd7054f1 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -552,10 +552,13 @@ static void cxl_port_release(struct device *dev) xa_destroy(&port->dports); xa_destroy(&port->regions); ida_free(&cxl_port_ida, port->id); - if (is_cxl_root(port)) + + if (is_cxl_root(port)) { kfree(to_cxl_root(port)); - else + } else { + put_device(dev->parent); kfree(port); + } } static ssize_t decoders_committed_show(struct device *dev, @@ -707,6 +710,7 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev, struct cxl_port *iter; dev->parent = &parent_port->dev; + get_device(dev->parent); port->depth = parent_port->depth + 1; port->parent_dport = parent_dport; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 42874948b589..c37ae0b28bbb 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -3854,8 +3854,10 @@ static int __construct_region(struct cxl_region *cxlr, } rc = sysfs_update_group(&cxlr->dev.kobj, &cxl_region_group); - if (rc) + if (rc) { + kfree(res); return rc; + } rc = insert_resource(cxlrd->res, res); if (rc) { diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 082ec0f1c3a0..261dff7ced9f 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -554,7 +554,7 @@ static __exit void cxl_pmem_exit(void) MODULE_DESCRIPTION("CXL PMEM: Persistent Memory Support"); MODULE_LICENSE("GPL v2"); -module_init(cxl_pmem_init); +subsys_initcall(cxl_pmem_init); module_exit(cxl_pmem_exit); MODULE_IMPORT_NS("CXL"); MODULE_ALIAS_CXL(CXL_DEVICE_NVDIMM_BRIDGE); diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index e7d698b352d3..5397dbda4f72 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -844,6 +844,7 @@ static int dw_edma_irq_request(struct dw_edma *dw, { struct dw_edma_chip *chip = dw->chip; struct device *dev = dw->chip->dev; + struct msi_desc *msi_desc; u32 wr_mask = 1; u32 rd_mask = 1; int i, err = 0; @@ -895,9 +896,12 @@ static int dw_edma_irq_request(struct dw_edma *dw, &dw->irq[i]); if (err) goto err_irq_free; - - if (irq_get_msi_desc(irq)) + msi_desc = irq_get_msi_desc(irq); + if (msi_desc) { get_cached_msi_msg(irq, &dw->irq[i].msi); + if (!msi_desc->pci.msi_attrib.is_msix) + dw->irq[i].msi.data = dw->irq[0].msi.data + i; + } } dw->nr_irqs = i; diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c index e3f8db4fe909..ce8f7254bab2 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-core.c +++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c @@ -252,10 +252,10 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) lower_32_bits(chunk->ll_region.paddr)); SET_CH_32(dw, chan->dir, chan->id, llp.msb, upper_32_bits(chunk->ll_region.paddr)); + /* Set consumer cycle */ + SET_CH_32(dw, chan->dir, chan->id, cycle_sync, + HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT); } - /* Set consumer cycle */ - SET_CH_32(dw, chan->dir, chan->id, cycle_sync, - HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT); dw_hdma_v0_sync_ll_data(chunk); diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index dbcdd1e68319..b596baa0a182 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -317,10 +317,8 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec, return NULL; i = fsl_chan - fsl_edma->chans; - fsl_chan->priority = dma_spec->args[1]; - fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX; - fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE; - fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO; + if (!b_chmux && i != dma_spec->args[0]) + continue; if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1)) continue; @@ -328,17 +326,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec, if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1)) continue; - if (!b_chmux && i == dma_spec->args[0]) { - chan = dma_get_slave_channel(chan); - chan->device->privatecnt++; - return chan; - } else if (b_chmux && !fsl_chan->srcid) { - /* if controller support channel mux, choose a free channel */ - chan = dma_get_slave_channel(chan); - chan->device->privatecnt++; - fsl_chan->srcid = dma_spec->args[0]; - return chan; - } + fsl_chan->srcid = dma_spec->args[0]; + fsl_chan->priority = dma_spec->args[1]; + fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX; + fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE; + fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO; + + chan = dma_get_slave_channel(chan); + chan->device->privatecnt++; + return chan; } return NULL; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index c37d233535f9..0366c7cf3502 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -158,11 +158,7 @@ static const struct device_type idxd_cdev_file_type = { static void idxd_cdev_dev_release(struct device *dev) { struct idxd_cdev *idxd_cdev = dev_to_cdev(dev); - struct idxd_cdev_context *cdev_ctx; - struct idxd_wq *wq = idxd_cdev->wq; - cdev_ctx = &ictx[wq->idxd->data->type]; - ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor); kfree(idxd_cdev); } @@ -582,11 +578,15 @@ int idxd_wq_add_cdev(struct idxd_wq *wq) void idxd_wq_del_cdev(struct idxd_wq *wq) { + struct idxd_cdev_context *cdev_ctx; struct idxd_cdev *idxd_cdev; idxd_cdev = wq->idxd_cdev; wq->idxd_cdev = NULL; cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev)); + + cdev_ctx = &ictx[wq->idxd->data->type]; + ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor); put_device(cdev_dev(idxd_cdev)); } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index c26128529ff4..131138483b87 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -175,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq) free_descs(wq); dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr); sbitmap_queue_free(&wq->sbq); + wq->type = IDXD_WQT_NONE; } EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, "IDXD"); @@ -382,7 +383,6 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq) lockdep_assert_held(&wq->wq_lock); wq->state = IDXD_WQ_DISABLED; memset(wq->wqcfg, 0, idxd->wqcfg_size); - wq->type = IDXD_WQT_NONE; wq->threshold = 0; wq->priority = 0; wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; @@ -831,8 +831,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) struct device *dev = &idxd->pdev->dev; struct idxd_evl *evl = idxd->evl; - gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); - if (!gencfg.evl_en) + if (!evl) return; mutex_lock(&evl->lock); @@ -1125,7 +1124,11 @@ int idxd_device_config(struct idxd_device *idxd) { int rc; - lockdep_assert_held(&idxd->dev_lock); + guard(spinlock)(&idxd->dev_lock); + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return 0; + rc = idxd_wqs_setup(idxd); if (rc < 0) return rc; @@ -1332,6 +1335,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq) free_irq(ie->vector, ie); idxd_flush_pending_descs(ie); + + /* The interrupt might have been already released by FLR */ + if (ie->int_handle == INVALID_INT_HANDLE) + return; + if (idxd->request_int_handles) idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); idxd_device_clear_perm_entry(idxd, ie); @@ -1340,6 +1348,23 @@ void idxd_wq_free_irq(struct idxd_wq *wq) ie->pasid = IOMMU_PASID_INVALID; } +void idxd_wq_flush_descs(struct idxd_wq *wq) +{ + struct idxd_irq_entry *ie = &wq->ie; + struct idxd_device *idxd = wq->idxd; + + guard(mutex)(&wq->wq_lock); + + if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL) + return; + + idxd_flush_pending_descs(ie); + if (idxd->request_int_handles) + idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); + idxd_device_clear_perm_entry(idxd, ie); + ie->int_handle = INVALID_INT_HANDLE; +} + int idxd_wq_request_irq(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; @@ -1454,11 +1479,7 @@ int idxd_drv_enable_wq(struct idxd_wq *wq) } } - rc = 0; - spin_lock(&idxd->dev_lock); - if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) - rc = idxd_device_config(idxd); - spin_unlock(&idxd->dev_lock); + rc = idxd_device_config(idxd); if (rc < 0) { dev_dbg(dev, "Writing wq %d config failed: %d\n", wq->id, rc); goto err; @@ -1533,7 +1554,6 @@ void idxd_drv_disable_wq(struct idxd_wq *wq) idxd_wq_reset(wq); idxd_wq_free_resources(wq); percpu_ref_exit(&wq->wq_active); - wq->type = IDXD_WQT_NONE; wq->client_count = 0; } EXPORT_SYMBOL_NS_GPL(idxd_drv_disable_wq, "IDXD"); @@ -1554,10 +1574,7 @@ int idxd_device_drv_probe(struct idxd_dev *idxd_dev) } /* Device configuration */ - spin_lock(&idxd->dev_lock); - if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) - rc = idxd_device_config(idxd); - spin_unlock(&idxd->dev_lock); + rc = idxd_device_config(idxd); if (rc < 0) return -ENXIO; diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index dbecd699237e..9937b671f637 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -194,6 +194,22 @@ static void idxd_dma_release(struct dma_device *device) kfree(idxd_dma); } +static int idxd_dma_terminate_all(struct dma_chan *c) +{ + struct idxd_wq *wq = to_idxd_wq(c); + + idxd_wq_flush_descs(wq); + + return 0; +} + +static void idxd_dma_synchronize(struct dma_chan *c) +{ + struct idxd_wq *wq = to_idxd_wq(c); + + idxd_wq_drain(wq); +} + int idxd_register_dma_device(struct idxd_device *idxd) { struct idxd_dma_dev *idxd_dma; @@ -224,6 +240,8 @@ int idxd_register_dma_device(struct idxd_device *idxd) dma->device_issue_pending = idxd_dma_issue_pending; dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources; dma->device_free_chan_resources = idxd_dma_free_chan_resources; + dma->device_terminate_all = idxd_dma_terminate_all; + dma->device_synchronize = idxd_dma_synchronize; rc = dma_async_device_register(dma); if (rc < 0) { diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index ea8c4daed38d..ce78b9a7c641 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -803,6 +803,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq); int idxd_wq_init_percpu_ref(struct idxd_wq *wq); void idxd_wq_free_irq(struct idxd_wq *wq); int idxd_wq_request_irq(struct idxd_wq *wq); +void idxd_wq_flush_descs(struct idxd_wq *wq); /* submission */ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index fb80803d5b57..f1cfc7790d95 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -973,7 +973,8 @@ static void idxd_device_config_restore(struct idxd_device *idxd, idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit; - idxd->evl->size = saved_evl->size; + if (idxd->evl) + idxd->evl->size = saved_evl->size; for (i = 0; i < idxd->max_groups; i++) { struct idxd_group *saved_group, *group; @@ -1104,12 +1105,10 @@ static void idxd_reset_done(struct pci_dev *pdev) idxd_device_config_restore(idxd, idxd->idxd_saved); /* Re-configure IDXD device if allowed. */ - if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) { - rc = idxd_device_config(idxd); - if (rc < 0) { - dev_err(dev, "HALT: %s config fails\n", idxd_name); - goto out; - } + rc = idxd_device_config(idxd); + if (rc < 0) { + dev_err(dev, "HALT: %s config fails\n", idxd_name); + goto out; } /* Bind IDXD device to driver. */ @@ -1147,6 +1146,7 @@ static void idxd_reset_done(struct pci_dev *pdev) } out: kfree(idxd->idxd_saved); + idxd->idxd_saved = NULL; } static const struct pci_error_handlers idxd_error_handler = { diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 7782f8c51c32..6a25e1fd0e62 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -397,6 +397,17 @@ static void idxd_device_flr(struct work_struct *work) dev_err(&idxd->pdev->dev, "FLR failed\n"); } +static void idxd_wqs_flush_descs(struct idxd_device *idxd) +{ + int i; + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *wq = idxd->wqs[i]; + + idxd_wq_flush_descs(wq); + } +} + static irqreturn_t idxd_halt(struct idxd_device *idxd) { union gensts_reg gensts; @@ -415,6 +426,11 @@ static irqreturn_t idxd_halt(struct idxd_device *idxd) } else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) { idxd->state = IDXD_DEV_HALTED; idxd_mask_error_interrupts(idxd); + /* Flush all pending descriptors, and disable + * interrupts, they will be re-enabled when FLR + * concludes. + */ + idxd_wqs_flush_descs(idxd); dev_dbg(&idxd->pdev->dev, "idxd halted, doing FLR. After FLR, configs are restored\n"); INIT_WORK(&idxd->work, idxd_device_flr); diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 6db1c5fcedc5..03217041b8b3 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -138,7 +138,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, */ list_for_each_entry_safe(d, t, &flist, list) { list_del_init(&d->list); - idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true, + idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true, NULL, NULL); } } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index cc2c83d7f710..6d251095c350 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1836,6 +1836,7 @@ static void idxd_conf_device_release(struct device *dev) { struct idxd_device *idxd = confdev_to_idxd(dev); + destroy_workqueue(idxd->wq); kfree(idxd->groups); bitmap_free(idxd->wq_enable_map); kfree(idxd->wqs); diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index d84ca551b2bf..f30bdf69c740 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -10,6 +10,7 @@ */ #include <linux/bitfield.h> +#include <linux/cleanup.h> #include <linux/dma-mapping.h> #include <linux/dmaengine.h> #include <linux/interrupt.h> @@ -296,13 +297,10 @@ static void rz_dmac_disable_hw(struct rz_dmac_chan *channel) { struct dma_chan *chan = &channel->vc.chan; struct rz_dmac *dmac = to_rz_dmac(chan->device); - unsigned long flags; dev_dbg(dmac->dev, "%s channel %d\n", __func__, channel->index); - local_irq_save(flags); rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1); - local_irq_restore(flags); } static void rz_dmac_set_dmars_register(struct rz_dmac *dmac, int nr, u32 dmars) @@ -447,6 +445,7 @@ static int rz_dmac_alloc_chan_resources(struct dma_chan *chan) if (!desc) break; + /* No need to lock. This is called only for the 1st client. */ list_add_tail(&desc->node, &channel->ld_free); channel->descs_allocated++; } @@ -502,18 +501,21 @@ rz_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, dev_dbg(dmac->dev, "%s channel: %d src=0x%pad dst=0x%pad len=%zu\n", __func__, channel->index, &src, &dest, len); - if (list_empty(&channel->ld_free)) - return NULL; + scoped_guard(spinlock_irqsave, &channel->vc.lock) { + if (list_empty(&channel->ld_free)) + return NULL; - desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node); + desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node); - desc->type = RZ_DMAC_DESC_MEMCPY; - desc->src = src; - desc->dest = dest; - desc->len = len; - desc->direction = DMA_MEM_TO_MEM; + desc->type = RZ_DMAC_DESC_MEMCPY; + desc->src = src; + desc->dest = dest; + desc->len = len; + desc->direction = DMA_MEM_TO_MEM; + + list_move_tail(channel->ld_free.next, &channel->ld_queue); + } - list_move_tail(channel->ld_free.next, &channel->ld_queue); return vchan_tx_prep(&channel->vc, &desc->vd, flags); } @@ -529,27 +531,29 @@ rz_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, int dma_length = 0; int i = 0; - if (list_empty(&channel->ld_free)) - return NULL; + scoped_guard(spinlock_irqsave, &channel->vc.lock) { + if (list_empty(&channel->ld_free)) + return NULL; - desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node); + desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node); - for_each_sg(sgl, sg, sg_len, i) { - dma_length += sg_dma_len(sg); - } + for_each_sg(sgl, sg, sg_len, i) + dma_length += sg_dma_len(sg); - desc->type = RZ_DMAC_DESC_SLAVE_SG; - desc->sg = sgl; - desc->sgcount = sg_len; - desc->len = dma_length; - desc->direction = direction; + desc->type = RZ_DMAC_DESC_SLAVE_SG; + desc->sg = sgl; + desc->sgcount = sg_len; + desc->len = dma_length; + desc->direction = direction; - if (direction == DMA_DEV_TO_MEM) - desc->src = channel->src_per_address; - else - desc->dest = channel->dst_per_address; + if (direction == DMA_DEV_TO_MEM) + desc->src = channel->src_per_address; + else + desc->dest = channel->dst_per_address; + + list_move_tail(channel->ld_free.next, &channel->ld_queue); + } - list_move_tail(channel->ld_free.next, &channel->ld_queue); return vchan_tx_prep(&channel->vc, &desc->vd, flags); } @@ -561,8 +565,8 @@ static int rz_dmac_terminate_all(struct dma_chan *chan) unsigned int i; LIST_HEAD(head); - rz_dmac_disable_hw(channel); spin_lock_irqsave(&channel->vc.lock, flags); + rz_dmac_disable_hw(channel); for (i = 0; i < DMAC_NR_LMDESC; i++) lmdesc[i].header = 0; @@ -699,7 +703,9 @@ static void rz_dmac_irq_handle_channel(struct rz_dmac_chan *channel) if (chstat & CHSTAT_ER) { dev_err(dmac->dev, "DMAC err CHSTAT_%d = %08X\n", channel->index, chstat); - rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1); + + scoped_guard(spinlock_irqsave, &channel->vc.lock) + rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1); goto done; } diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index d02a4dac2291..782a55edc55b 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -1234,8 +1234,8 @@ static int xdma_probe(struct platform_device *pdev) xdev->rmap = devm_regmap_init_mmio(&pdev->dev, reg_base, &xdma_regmap_config); - if (!xdev->rmap) { - xdma_err(xdev, "config regmap failed: %d", ret); + if (IS_ERR(xdev->rmap)) { + xdma_err(xdev, "config regmap failed: %pe", xdev->rmap); goto failed; } INIT_LIST_HEAD(&xdev->dma_dev.channels); diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index b53292e02448..e3a18ee42aa2 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -997,16 +997,16 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, struct xilinx_cdma_tx_segment, node); cdma_hw = &cdma_seg->hw; - residue += (cdma_hw->control - cdma_hw->status) & - chan->xdev->max_buffer_len; + residue += (cdma_hw->control & chan->xdev->max_buffer_len) - + (cdma_hw->status & chan->xdev->max_buffer_len); } else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { axidma_seg = list_entry(entry, struct xilinx_axidma_tx_segment, node); axidma_hw = &axidma_seg->hw; - residue += (axidma_hw->control - axidma_hw->status) & - chan->xdev->max_buffer_len; + residue += (axidma_hw->control & chan->xdev->max_buffer_len) - + (axidma_hw->status & chan->xdev->max_buffer_len); } else { aximcdma_seg = list_entry(entry, @@ -1014,8 +1014,8 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, node); aximcdma_hw = &aximcdma_seg->hw; residue += - (aximcdma_hw->control - aximcdma_hw->status) & - chan->xdev->max_buffer_len; + (aximcdma_hw->control & chan->xdev->max_buffer_len) - + (aximcdma_hw->status & chan->xdev->max_buffer_len); } } @@ -1235,14 +1235,6 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan) dma_cookie_init(dchan); - if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { - /* For AXI DMA resetting once channel will reset the - * other channel as well so enable the interrupts here. - */ - dma_ctrl_set(chan, XILINX_DMA_REG_DMACR, - XILINX_DMA_DMAXR_ALL_IRQ_MASK); - } - if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg) dma_ctrl_set(chan, XILINX_DMA_REG_DMACR, XILINX_CDMA_CR_SGMODE); @@ -1564,8 +1556,29 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) if (chan->err) return; - if (list_empty(&chan->pending_list)) + if (list_empty(&chan->pending_list)) { + if (chan->cyclic) { + struct xilinx_dma_tx_descriptor *desc; + struct list_head *entry; + + desc = list_last_entry(&chan->done_list, + struct xilinx_dma_tx_descriptor, node); + list_for_each(entry, &desc->segments) { + struct xilinx_axidma_tx_segment *axidma_seg; + struct xilinx_axidma_desc_hw *axidma_hw; + axidma_seg = list_entry(entry, + struct xilinx_axidma_tx_segment, + node); + axidma_hw = &axidma_seg->hw; + axidma_hw->status = 0; + } + + list_splice_tail_init(&chan->done_list, &chan->active_list); + chan->desc_pendingcount = 0; + chan->idle = false; + } return; + } if (!chan->idle) return; @@ -1591,6 +1604,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) head_desc->async_tx.phys); reg &= ~XILINX_DMA_CR_DELAY_MAX; reg |= chan->irq_delay << XILINX_DMA_CR_DELAY_SHIFT; + reg |= XILINX_DMA_DMAXR_ALL_IRQ_MASK; dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg); xilinx_dma_start(chan); @@ -3024,7 +3038,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev, return -EINVAL; } - xdev->common.directions |= chan->direction; + xdev->common.directions |= BIT(chan->direction); /* Request the interrupt */ chan->irq = of_irq_get(node, chan->tdest); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 40c22438b1d2..4f27c75abedb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -692,9 +692,9 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev, goto err_ib_sched; } - /* Drop the initial kref_init count (see drm_sched_main as example) */ - dma_fence_put(f); ret = dma_fence_wait(f, false); + /* Drop the returned fence reference after the wait completes */ + dma_fence_put(f); err_ib_sched: amdgpu_job_free(job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d8296dfc5e8a..6d8531f9b882 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4207,7 +4207,8 @@ fail: static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev) { - char *input = amdgpu_lockup_timeout; + char buf[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH]; + char *input = buf; char *timeout_setting = NULL; int index = 0; long timeout; @@ -4217,9 +4218,17 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev) adev->gfx_timeout = adev->compute_timeout = adev->sdma_timeout = adev->video_timeout = msecs_to_jiffies(2000); - if (!strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) + if (!strnlen(amdgpu_lockup_timeout, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) return 0; + /* + * strsep() destructively modifies its input by replacing delimiters + * with '\0'. Use a stack copy so the global module parameter buffer + * remains intact for multi-GPU systems where this function is called + * once per device. + */ + strscpy(buf, amdgpu_lockup_timeout, sizeof(buf)); + while ((timeout_setting = strsep(&input, ",")) && strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) { ret = kstrtol(timeout_setting, 0, &timeout); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 64c519cd7395..d88523568b62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -35,10 +35,13 @@ * PASIDs are global address space identifiers that can be shared * between the GPU, an IOMMU and the driver. VMs on different devices * may use the same PASID if they share the same address - * space. Therefore PASIDs are allocated using a global IDA. VMs are - * looked up from the PASID per amdgpu_device. + * space. Therefore PASIDs are allocated using IDR cyclic allocator + * (similar to kernel PID allocation) which naturally delays reuse. + * VMs are looked up from the PASID per amdgpu_device. */ -static DEFINE_IDA(amdgpu_pasid_ida); + +static DEFINE_IDR(amdgpu_pasid_idr); +static DEFINE_SPINLOCK(amdgpu_pasid_idr_lock); /* Helper to free pasid from a fence callback */ struct amdgpu_pasid_cb { @@ -50,8 +53,8 @@ struct amdgpu_pasid_cb { * amdgpu_pasid_alloc - Allocate a PASID * @bits: Maximum width of the PASID in bits, must be at least 1 * - * Allocates a PASID of the given width while keeping smaller PASIDs - * available if possible. + * Uses kernel's IDR cyclic allocator (same as PID allocation). + * Allocates sequentially with automatic wrap-around. * * Returns a positive integer on success. Returns %-EINVAL if bits==0. * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on @@ -59,14 +62,15 @@ struct amdgpu_pasid_cb { */ int amdgpu_pasid_alloc(unsigned int bits) { - int pasid = -EINVAL; + int pasid; - for (bits = min(bits, 31U); bits > 0; bits--) { - pasid = ida_alloc_range(&amdgpu_pasid_ida, 1U << (bits - 1), - (1U << bits) - 1, GFP_KERNEL); - if (pasid != -ENOSPC) - break; - } + if (bits == 0) + return -EINVAL; + + spin_lock(&amdgpu_pasid_idr_lock); + pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1, + 1U << bits, GFP_KERNEL); + spin_unlock(&amdgpu_pasid_idr_lock); if (pasid >= 0) trace_amdgpu_pasid_allocated(pasid); @@ -81,7 +85,10 @@ int amdgpu_pasid_alloc(unsigned int bits) void amdgpu_pasid_free(u32 pasid) { trace_amdgpu_pasid_freed(pasid); - ida_free(&amdgpu_pasid_ida, pasid); + + spin_lock(&amdgpu_pasid_idr_lock); + idr_remove(&amdgpu_pasid_idr, pasid); + spin_unlock(&amdgpu_pasid_idr_lock); } static void amdgpu_pasid_free_cb(struct dma_fence *fence, @@ -616,3 +623,15 @@ void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev) } } } + +/** + * amdgpu_pasid_mgr_cleanup - cleanup PASID manager + * + * Cleanup the IDR allocator. + */ +void amdgpu_pasid_mgr_cleanup(void) +{ + spin_lock(&amdgpu_pasid_idr_lock); + idr_destroy(&amdgpu_pasid_idr); + spin_unlock(&amdgpu_pasid_idr_lock); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h index b3649cd3af56..a57919478d3b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h @@ -74,6 +74,7 @@ int amdgpu_pasid_alloc(unsigned int bits); void amdgpu_pasid_free(u32 pasid); void amdgpu_pasid_free_delayed(struct dma_resv *resv, u32 pasid); +void amdgpu_pasid_mgr_cleanup(void); bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev, struct amdgpu_vmid *id); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c60cbce356cf..a677e38a493b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2898,6 +2898,7 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev) xa_destroy(&adev->vm_manager.pasids); amdgpu_vmid_mgr_fini(adev); + amdgpu_pasid_mgr_cleanup(); } /** @@ -2973,14 +2974,14 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, if (!root) return false; - addr /= AMDGPU_GPU_PAGE_SIZE; - if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid, - node_id, addr, ts, write_fault)) { + node_id, addr >> PAGE_SHIFT, ts, write_fault)) { amdgpu_bo_unref(&root); return true; } + addr /= AMDGPU_GPU_PAGE_SIZE; + r = amdgpu_bo_reserve(root, true); if (r) goto error_unref; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 09dabb3b3297..462a32abf720 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -3170,11 +3170,11 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v struct kfd_process *process; int ret; - /* Each FD owns only one kfd_process */ - if (p->context_id != KFD_CONTEXT_ID_PRIMARY) + if (!filep->private_data || !p) return -EINVAL; - if (!filep->private_data || !p) + /* Each FD owns only one kfd_process */ + if (p->context_id != KFD_CONTEXT_ID_PRIMARY) return -EINVAL; mutex_lock(&kfd_processes_mutex); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 085cc98bd875..2328c1aa0ead 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3909,8 +3909,9 @@ void amdgpu_dm_update_connector_after_detect( aconnector->dc_sink = sink; dc_sink_retain(aconnector->dc_sink); + drm_edid_free(aconnector->drm_edid); + aconnector->drm_edid = NULL; if (sink->dc_edid.length == 0) { - aconnector->drm_edid = NULL; hdmi_cec_unset_edid(aconnector); if (aconnector->dc_link->aux_mode) { drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); @@ -5422,7 +5423,7 @@ static void setup_backlight_device(struct amdgpu_display_manager *dm, caps = &dm->backlight_caps[aconnector->bl_idx]; /* Only offer ABM property when non-OLED and user didn't turn off by module parameter */ - if (!caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0) + if (caps->ext_caps && !caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0) drm_object_attach_property(&aconnector->base.base, dm->adev->mode_info.abm_level_property, ABM_SYSFS_CONTROL); @@ -12524,6 +12525,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, if (dc_resource_is_dsc_encoding_supported(dc)) { for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); + dm_new_crtc_state->mode_changed_independent_from_dsc = new_crtc_state->mode_changed; + } + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (drm_atomic_crtc_needs_modeset(new_crtc_state)) { ret = add_affected_mst_dsc_crtcs(state, crtc); if (ret) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 800813671748..d15812d51d72 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -984,6 +984,7 @@ struct dm_crtc_state { bool freesync_vrr_info_changed; + bool mode_changed_independent_from_dsc; bool dsc_force_changed; bool vrr_supported; struct mod_freesync_config freesync_config; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 7be50e8c0636..5d8c4c7020b1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1744,9 +1744,11 @@ int pre_validate_dsc(struct drm_atomic_state *state, int ind = find_crtc_index_in_state_by_stream(state, stream); if (ind >= 0) { + struct dm_crtc_state *dm_new_crtc_state = to_dm_crtc_state(state->crtcs[ind].new_state); + DRM_INFO_ONCE("%s:%d MST_DSC no mode changed for stream 0x%p\n", __func__, __LINE__, stream); - state->crtcs[ind].new_state->mode_changed = 0; + dm_new_crtc_state->base.mode_changed = dm_new_crtc_state->mode_changed_independent_from_dsc; } } } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c index 92c123aca0c9..fdcf8db6be50 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c @@ -650,9 +650,6 @@ static struct link_encoder *dce100_link_encoder_create( return &enc110->base; } - if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) - return NULL; - link_regs_id = map_transmitter_id_to_phy_instance(enc_init_data->transmitter); @@ -661,7 +658,8 @@ static struct link_encoder *dce100_link_encoder_create( &link_enc_feature, &link_enc_regs[link_regs_id], &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c index 95852d277c22..ab71f645c90e 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c @@ -671,7 +671,7 @@ static struct link_encoder *dce110_link_encoder_create( kzalloc_obj(struct dce110_link_encoder); int link_regs_id; - if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) + if (!enc110) return NULL; link_regs_id = @@ -682,7 +682,8 @@ static struct link_encoder *dce110_link_encoder_create( &link_enc_feature, &link_enc_regs[link_regs_id], &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c index 58c6a00397cf..b7051bfd4326 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c @@ -632,7 +632,7 @@ static struct link_encoder *dce112_link_encoder_create( kzalloc_obj(struct dce110_link_encoder); int link_regs_id; - if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) + if (!enc110) return NULL; link_regs_id = @@ -643,7 +643,8 @@ static struct link_encoder *dce112_link_encoder_create( &link_enc_feature, &link_enc_regs[link_regs_id], &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c index 71d76b021375..7ee70f7b3aa7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c @@ -716,7 +716,7 @@ static struct link_encoder *dce120_link_encoder_create( kzalloc_obj(struct dce110_link_encoder); int link_regs_id; - if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) + if (!enc110) return NULL; link_regs_id = @@ -727,7 +727,8 @@ static struct link_encoder *dce120_link_encoder_create( &link_enc_feature, &link_enc_regs[link_regs_id], &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index c27645708286..3d52973dd7f2 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -746,18 +746,16 @@ static struct link_encoder *dce60_link_encoder_create( return &enc110->base; } - if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) - return NULL; - link_regs_id = map_transmitter_id_to_phy_instance(enc_init_data->transmitter); dce60_link_encoder_construct(enc110, - enc_init_data, - &link_enc_feature, - &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data, + &link_enc_feature, + &link_enc_regs[link_regs_id], + &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c index d66d8ac6d897..89927727a0d9 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c @@ -752,9 +752,6 @@ static struct link_encoder *dce80_link_encoder_create( return &enc110->base; } - if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs)) - return NULL; - link_regs_id = map_transmitter_id_to_phy_instance(enc_init_data->transmitter); @@ -763,7 +760,8 @@ static struct link_encoder *dce80_link_encoder_create( &link_enc_feature, &link_enc_regs[link_regs_id], &link_enc_aux_regs[enc_init_data->channel - 1], - &link_enc_hpd_regs[enc_init_data->hpd_source]); + enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? + NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index a8d63d4d1f6e..554f616328c3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -59,6 +59,10 @@ #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c)) +static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu, + int od_feature_bit, + int32_t *min, int32_t *max); + static const struct smu_feature_bits smu_v13_0_0_dpm_features = { .bits = { SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT), @@ -1043,8 +1047,35 @@ static bool smu_v13_0_0_is_od_feature_supported(struct smu_context *smu, PPTable_t *pptable = smu->smu_table.driver_pptable; const OverDriveLimits_t * const overdrive_upperlimits = &pptable->SkuTable.OverDriveLimitsBasicMax; + int32_t min_value, max_value; + bool feature_enabled; - return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit); + switch (od_feature_bit) { + case PP_OD_FEATURE_FAN_CURVE_BIT: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + if (feature_enabled) { + smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + + smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + } + break; + default: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + break; + } + +out: + return feature_enabled; } static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 896b51c8a9a7..870bcc86fd79 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1391,7 +1391,7 @@ static int smu_v13_0_6_emit_clk_levels(struct smu_context *smu, break; case SMU_OD_MCLK: if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SET_UCLK_MAX))) - return 0; + return -EOPNOTSUPP; size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n", @@ -2122,6 +2122,7 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu, { struct smu_dpm_context *smu_dpm = &(smu->smu_dpm); struct smu_13_0_dpm_context *dpm_context = smu_dpm->dpm_context; + struct smu_dpm_table *uclk_table = &dpm_context->dpm_tables.uclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; uint32_t min_clk; uint32_t max_clk; @@ -2221,14 +2222,16 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu, if (ret) return ret; - min_clk = SMU_DPM_TABLE_MIN( - &dpm_context->dpm_tables.uclk_table); - max_clk = SMU_DPM_TABLE_MAX( - &dpm_context->dpm_tables.uclk_table); - ret = smu_v13_0_6_set_soft_freq_limited_range( - smu, SMU_UCLK, min_clk, max_clk, false); - if (ret) - return ret; + if (SMU_DPM_TABLE_MAX(uclk_table) != + pstate_table->uclk_pstate.curr.max) { + min_clk = SMU_DPM_TABLE_MIN(&dpm_context->dpm_tables.uclk_table); + max_clk = SMU_DPM_TABLE_MAX(&dpm_context->dpm_tables.uclk_table); + ret = smu_v13_0_6_set_soft_freq_limited_range(smu, + SMU_UCLK, min_clk, + max_clk, false); + if (ret) + return ret; + } smu_v13_0_reset_custom_level(smu); } break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 5500a0f12f0e..f331e87858c9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -59,6 +59,10 @@ #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c)) +static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu, + int od_feature_bit, + int32_t *min, int32_t *max); + static const struct smu_feature_bits smu_v13_0_7_dpm_features = { .bits = { SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT), @@ -1053,8 +1057,35 @@ static bool smu_v13_0_7_is_od_feature_supported(struct smu_context *smu, PPTable_t *pptable = smu->smu_table.driver_pptable; const OverDriveLimits_t * const overdrive_upperlimits = &pptable->SkuTable.OverDriveLimitsBasicMax; + int32_t min_value, max_value; + bool feature_enabled; - return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit); + switch (od_feature_bit) { + case PP_OD_FEATURE_FAN_CURVE_BIT: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + if (feature_enabled) { + smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + + smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + } + break; + default: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + break; + } + +out: + return feature_enabled; } static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 73762d9b5969..c3ebfac062a7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -56,6 +56,10 @@ #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c)) +static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu, + int od_feature_bit, + int32_t *min, int32_t *max); + static const struct smu_feature_bits smu_v14_0_2_dpm_features = { .bits = { SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT), SMU_FEATURE_BIT_INIT(FEATURE_DPM_UCLK_BIT), @@ -922,8 +926,35 @@ static bool smu_v14_0_2_is_od_feature_supported(struct smu_context *smu, PPTable_t *pptable = smu->smu_table.driver_pptable; const OverDriveLimits_t * const overdrive_upperlimits = &pptable->SkuTable.OverDriveLimitsBasicMax; + int32_t min_value, max_value; + bool feature_enabled; - return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit); + switch (od_feature_bit) { + case PP_OD_FEATURE_FAN_CURVE_BIT: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + if (feature_enabled) { + smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + + smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM, + &min_value, &max_value); + if (!min_value && !max_value) { + feature_enabled = false; + goto out; + } + } + break; + default: + feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit)); + break; + } + +out: + return feature_enabled; } static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu, diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 7b5a49935ae4..c549293b5bb6 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -550,27 +550,27 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev, } EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create); -static bool drm_gem_shmem_try_map_pmd(struct vm_fault *vmf, unsigned long addr, - struct page *page) +static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order, + unsigned long pfn) { + if (!order) { + return vmf_insert_pfn(vmf->vma, vmf->address, pfn); #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP - unsigned long pfn = page_to_pfn(page); - unsigned long paddr = pfn << PAGE_SHIFT; - bool aligned = (addr & ~PMD_MASK) == (paddr & ~PMD_MASK); - - if (aligned && - pmd_none(*vmf->pmd) && - folio_test_pmd_mappable(page_folio(page))) { - pfn &= PMD_MASK >> PAGE_SHIFT; - if (vmf_insert_pfn_pmd(vmf, pfn, false) == VM_FAULT_NOPAGE) - return true; - } + } else if (order == PMD_ORDER) { + unsigned long paddr = pfn << PAGE_SHIFT; + bool aligned = (vmf->address & ~PMD_MASK) == (paddr & ~PMD_MASK); + + if (aligned && + folio_test_pmd_mappable(page_folio(pfn_to_page(pfn)))) { + pfn &= PMD_MASK >> PAGE_SHIFT; + return vmf_insert_pfn_pmd(vmf, pfn, false); + } #endif - - return false; + } + return VM_FAULT_FALLBACK; } -static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) +static vm_fault_t drm_gem_shmem_any_fault(struct vm_fault *vmf, unsigned int order) { struct vm_area_struct *vma = vmf->vma; struct drm_gem_object *obj = vma->vm_private_data; @@ -581,6 +581,9 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) pgoff_t page_offset; unsigned long pfn; + if (order && order != PMD_ORDER) + return VM_FAULT_FALLBACK; + /* Offset to faulty address in the VMA. */ page_offset = vmf->pgoff - vma->vm_pgoff; @@ -593,13 +596,8 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) goto out; } - if (drm_gem_shmem_try_map_pmd(vmf, vmf->address, pages[page_offset])) { - ret = VM_FAULT_NOPAGE; - goto out; - } - pfn = page_to_pfn(pages[page_offset]); - ret = vmf_insert_pfn(vma, vmf->address, pfn); + ret = try_insert_pfn(vmf, order, pfn); out: dma_resv_unlock(shmem->base.resv); @@ -607,6 +605,11 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) return ret; } +static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) +{ + return drm_gem_shmem_any_fault(vmf, 0); +} + static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; @@ -643,6 +646,9 @@ static void drm_gem_shmem_vm_close(struct vm_area_struct *vma) const struct vm_operations_struct drm_gem_shmem_vm_ops = { .fault = drm_gem_shmem_fault, +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP + .huge_fault = drm_gem_shmem_any_fault, +#endif .open = drm_gem_shmem_vm_open, .close = drm_gem_shmem_vm_close, }; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 250734dee928..8d9fd1917c6e 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -602,7 +602,7 @@ int drm_syncobj_get_handle(struct drm_file *file_private, drm_syncobj_get(syncobj); ret = xa_alloc(&file_private->syncobj_xa, handle, syncobj, xa_limit_32b, - GFP_NOWAIT); + GFP_KERNEL); if (ret) drm_syncobj_put(syncobj); @@ -716,7 +716,7 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private, drm_syncobj_get(syncobj); ret = xa_alloc(&file_private->syncobj_xa, handle, syncobj, xa_limit_32b, - GFP_NOWAIT); + GFP_KERNEL); if (ret) drm_syncobj_put(syncobj); diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index c4246481fc2f..0f82bf771a92 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -4602,6 +4602,7 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_crtc_state *saved_state; + int err; saved_state = intel_crtc_state_alloc(crtc); if (!saved_state) @@ -4610,7 +4611,12 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state, /* free the old crtc_state->hw members */ intel_crtc_free_hw_state(crtc_state); - intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state); + err = intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state); + if (err) { + kfree(saved_state); + + return err; + } /* FIXME: before the switch to atomic started, a new pipe_config was * kzalloc'd. Code that depends on any field being zero should be diff --git a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c index 83865c02d477..55b423fd6b6f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c +++ b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c @@ -621,19 +621,27 @@ int intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state, * * Clear any DP tunnel stream BW requirement set by * intel_dp_tunnel_atomic_compute_stream_bw(). + * + * Returns 0 in case of success, a negative error code otherwise. */ -void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state, - struct intel_crtc_state *crtc_state) +int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state, + struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + int err; if (!crtc_state->dp_tunnel_ref.tunnel) - return; + return 0; + + err = drm_dp_tunnel_atomic_set_stream_bw(&state->base, + crtc_state->dp_tunnel_ref.tunnel, + crtc->pipe, 0); + if (err) + return err; - drm_dp_tunnel_atomic_set_stream_bw(&state->base, - crtc_state->dp_tunnel_ref.tunnel, - crtc->pipe, 0); drm_dp_tunnel_ref_put(&crtc_state->dp_tunnel_ref); + + return 0; } /** diff --git a/drivers/gpu/drm/i915/display/intel_dp_tunnel.h b/drivers/gpu/drm/i915/display/intel_dp_tunnel.h index 7f0f720e8dca..10ab9eebcef6 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_tunnel.h +++ b/drivers/gpu/drm/i915/display/intel_dp_tunnel.h @@ -40,8 +40,8 @@ int intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state, struct intel_dp *intel_dp, const struct intel_connector *connector, struct intel_crtc_state *crtc_state); -void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state, - struct intel_crtc_state *crtc_state); +int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state, + struct intel_crtc_state *crtc_state); int intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state, struct intel_crtc *crtc); @@ -88,9 +88,12 @@ intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state, return 0; } -static inline void +static inline int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state, - struct intel_crtc_state *crtc_state) {} + struct intel_crtc_state *crtc_state) +{ + return 0; +} static inline int intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state, diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index a7bce0c6a17e..264e6843bff1 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -496,8 +496,10 @@ gmbus_xfer_read_chunk(struct intel_display *display, val = intel_de_read_fw(display, GMBUS3(display)); do { - if (extra_byte_added && len == 1) + if (extra_byte_added && len == 1) { + len--; break; + } *buf++ = val & 0xff; val >>= 8; diff --git a/drivers/gpu/drm/i915/display/intel_plane.c b/drivers/gpu/drm/i915/display/intel_plane.c index e06a0618b4c6..076b9b356481 100644 --- a/drivers/gpu/drm/i915/display/intel_plane.c +++ b/drivers/gpu/drm/i915/display/intel_plane.c @@ -436,11 +436,16 @@ void intel_plane_copy_hw_state(struct intel_plane_state *plane_state, drm_framebuffer_get(plane_state->hw.fb); } +static void unlink_nv12_plane(struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state); + void intel_plane_set_invisible(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + unlink_nv12_plane(crtc_state, plane_state); + crtc_state->active_planes &= ~BIT(plane->id); crtc_state->scaled_planes &= ~BIT(plane->id); crtc_state->nv12_planes &= ~BIT(plane->id); @@ -1513,6 +1518,9 @@ static void unlink_nv12_plane(struct intel_crtc_state *crtc_state, struct intel_display *display = to_intel_display(plane_state); struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + if (!plane_state->planar_linked_plane) + return; + plane_state->planar_linked_plane = NULL; if (!plane_state->is_y_plane) @@ -1550,8 +1558,7 @@ static int icl_check_nv12_planes(struct intel_atomic_state *state, if (plane->pipe != crtc->pipe) continue; - if (plane_state->planar_linked_plane) - unlink_nv12_plane(crtc_state, plane_state); + unlink_nv12_plane(crtc_state, plane_state); } if (!crtc_state->nv12_planes) diff --git a/drivers/gpu/drm/i915/i915_wait_util.h b/drivers/gpu/drm/i915/i915_wait_util.h index 7376898e3bf8..e1ed7921ec70 100644 --- a/drivers/gpu/drm/i915/i915_wait_util.h +++ b/drivers/gpu/drm/i915/i915_wait_util.h @@ -25,9 +25,9 @@ might_sleep(); \ for (;;) { \ const bool expired__ = ktime_after(ktime_get_raw(), end__); \ - OP; \ /* Guarantee COND check prior to timeout */ \ barrier(); \ + OP; \ if (COND) { \ ret__ = 0; \ break; \ diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 17c67f02016b..aaf6c9ebd319 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1236,6 +1236,11 @@ static int mtk_dsi_probe(struct platform_device *pdev) dsi->host.ops = &mtk_dsi_ops; dsi->host.dev = dev; + + init_waitqueue_head(&dsi->irq_wait_queue); + + platform_set_drvdata(pdev, dsi); + ret = mipi_dsi_host_register(&dsi->host); if (ret < 0) return dev_err_probe(dev, ret, "Failed to register DSI host\n"); @@ -1247,10 +1252,6 @@ static int mtk_dsi_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, ret, "Failed to request DSI irq\n"); } - init_waitqueue_head(&dsi->irq_wait_queue); - - platform_set_drvdata(pdev, dsi); - dsi->bridge.of_node = dev->of_node; dsi->bridge.type = DRM_MODE_CONNECTOR_DSI; diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 24fc64fc832e..9d66f168ab8a 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -553,6 +553,7 @@ #define ENABLE_SMP_LD_RENDER_SURFACE_CONTROL REG_BIT(44 - 32) #define FORCE_SLM_FENCE_SCOPE_TO_TILE REG_BIT(42 - 32) #define FORCE_UGM_FENCE_SCOPE_TO_TILE REG_BIT(41 - 32) +#define L3_128B_256B_WRT_DIS REG_BIT(40 - 32) #define MAXREQS_PER_BANK REG_GENMASK(39 - 32, 37 - 32) #define DISABLE_128B_EVICTION_COMMAND_UDW REG_BIT(36 - 32) diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 2d9ce2c4cb4f..713a303c9053 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1442,9 +1442,9 @@ static int op_check_svm_userptr(struct xe_vm *vm, struct xe_vma_op *op, err = vma_check_userptr(vm, op->map.vma, pt_update); break; case DRM_GPUVA_OP_REMAP: - if (op->remap.prev) + if (op->remap.prev && !op->remap.skip_prev) err = vma_check_userptr(vm, op->remap.prev, pt_update); - if (!err && op->remap.next) + if (!err && op->remap.next && !op->remap.skip_next) err = vma_check_userptr(vm, op->remap.next, pt_update); break; case DRM_GPUVA_OP_UNMAP: @@ -2198,12 +2198,12 @@ static int op_prepare(struct xe_vm *vm, err = unbind_op_prepare(tile, pt_update_ops, old); - if (!err && op->remap.prev) { + if (!err && op->remap.prev && !op->remap.skip_prev) { err = bind_op_prepare(vm, tile, pt_update_ops, op->remap.prev, false); pt_update_ops->wait_vm_bookkeep = true; } - if (!err && op->remap.next) { + if (!err && op->remap.next && !op->remap.skip_next) { err = bind_op_prepare(vm, tile, pt_update_ops, op->remap.next, false); pt_update_ops->wait_vm_bookkeep = true; @@ -2428,10 +2428,10 @@ static void op_commit(struct xe_vm *vm, unbind_op_commit(vm, tile, pt_update_ops, old, fence, fence2); - if (op->remap.prev) + if (op->remap.prev && !op->remap.skip_prev) bind_op_commit(vm, tile, pt_update_ops, op->remap.prev, fence, fence2, false); - if (op->remap.next) + if (op->remap.next && !op->remap.skip_next) bind_op_commit(vm, tile, pt_update_ops, op->remap.next, fence, fence2, false); break; diff --git a/drivers/gpu/drm/xe/xe_sriov_packet.c b/drivers/gpu/drm/xe/xe_sriov_packet.c index 968f32496282..2ae9eff2a7c0 100644 --- a/drivers/gpu/drm/xe/xe_sriov_packet.c +++ b/drivers/gpu/drm/xe/xe_sriov_packet.c @@ -341,6 +341,8 @@ ssize_t xe_sriov_packet_write_single(struct xe_device *xe, unsigned int vfid, ret = xe_sriov_pf_migration_restore_produce(xe, vfid, *data); if (ret) { xe_sriov_packet_free(*data); + *data = NULL; + return ret; } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index a82e3a4fb389..ffdbab106a58 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2554,7 +2554,6 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op) if (!err && op->remap.skip_prev) { op->remap.prev->tile_present = tile_present; - op->remap.prev = NULL; } } if (op->remap.next) { @@ -2564,11 +2563,13 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op) if (!err && op->remap.skip_next) { op->remap.next->tile_present = tile_present; - op->remap.next = NULL; } } - /* Adjust for partial unbind after removing VMA from VM */ + /* + * Adjust for partial unbind after removing VMA from VM. In case + * of unwind we might need to undo this later. + */ if (!err) { op->base.remap.unmap->va->va.addr = op->remap.start; op->base.remap.unmap->va->va.range = op->remap.range; @@ -2687,6 +2688,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, op->remap.start = xe_vma_start(old); op->remap.range = xe_vma_size(old); + op->remap.old_start = op->remap.start; + op->remap.old_range = op->remap.range; flags |= op->base.remap.unmap->va->flags & XE_VMA_CREATE_MASK; if (op->base.remap.prev) { @@ -2835,8 +2838,19 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op, xe_svm_notifier_lock(vm); vma->gpuva.flags &= ~XE_VMA_DESTROYED; xe_svm_notifier_unlock(vm); - if (post_commit) + if (post_commit) { + /* + * Restore the old va range, in case of the + * prev/next skip optimisation. Otherwise what + * we re-insert here could be smaller than the + * original range. + */ + op->base.remap.unmap->va->va.addr = + op->remap.old_start; + op->base.remap.unmap->va->va.range = + op->remap.old_range; xe_vm_insert_vma(vm, vma); + } } break; } diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 437f64202f3b..e2946e311d7a 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -373,6 +373,10 @@ struct xe_vma_op_remap { u64 start; /** @range: range of the VMA unmap */ u64 range; + /** @old_start: Original start of the VMA we unmap */ + u64 old_start; + /** @old_range: Original range of the VMA we unmap */ + u64 old_range; /** @skip_prev: skip prev rebind */ bool skip_prev; /** @skip_next: skip next rebind */ diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 462c2fa712e0..d7e309ad9aba 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -247,7 +247,8 @@ static const struct xe_rtp_entry_sr gt_was[] = { LSN_DIM_Z_WGT_MASK, LSN_LNI_WGT(1) | LSN_LNE_WGT(1) | LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) | - LSN_DIM_Z_WGT(1))) + LSN_DIM_Z_WGT(1)), + SET(LSC_CHICKEN_BIT_0_UDW, L3_128B_256B_WRT_DIS)) }, /* Xe2_HPM */ diff --git a/drivers/hwmon/adm1177.c b/drivers/hwmon/adm1177.c index 8b2c965480e3..7888afe8dafd 100644 --- a/drivers/hwmon/adm1177.c +++ b/drivers/hwmon/adm1177.c @@ -10,6 +10,8 @@ #include <linux/hwmon.h> #include <linux/i2c.h> #include <linux/init.h> +#include <linux/math64.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/regulator/consumer.h> @@ -33,7 +35,7 @@ struct adm1177_state { struct i2c_client *client; u32 r_sense_uohm; - u32 alert_threshold_ua; + u64 alert_threshold_ua; bool vrange_high; }; @@ -48,7 +50,7 @@ static int adm1177_write_cmd(struct adm1177_state *st, u8 cmd) } static int adm1177_write_alert_thr(struct adm1177_state *st, - u32 alert_threshold_ua) + u64 alert_threshold_ua) { u64 val; int ret; @@ -91,8 +93,8 @@ static int adm1177_read(struct device *dev, enum hwmon_sensor_types type, *val = div_u64((105840000ull * dummy), 4096 * st->r_sense_uohm); return 0; - case hwmon_curr_max_alarm: - *val = st->alert_threshold_ua; + case hwmon_curr_max: + *val = div_u64(st->alert_threshold_ua, 1000); return 0; default: return -EOPNOTSUPP; @@ -126,9 +128,10 @@ static int adm1177_write(struct device *dev, enum hwmon_sensor_types type, switch (type) { case hwmon_curr: switch (attr) { - case hwmon_curr_max_alarm: - adm1177_write_alert_thr(st, val); - return 0; + case hwmon_curr_max: + val = clamp_val(val, 0, + div_u64(105840000ULL, st->r_sense_uohm)); + return adm1177_write_alert_thr(st, (u64)val * 1000); default: return -EOPNOTSUPP; } @@ -156,7 +159,7 @@ static umode_t adm1177_is_visible(const void *data, if (st->r_sense_uohm) return 0444; return 0; - case hwmon_curr_max_alarm: + case hwmon_curr_max: if (st->r_sense_uohm) return 0644; return 0; @@ -170,7 +173,7 @@ static umode_t adm1177_is_visible(const void *data, static const struct hwmon_channel_info * const adm1177_info[] = { HWMON_CHANNEL_INFO(curr, - HWMON_C_INPUT | HWMON_C_MAX_ALARM), + HWMON_C_INPUT | HWMON_C_MAX), HWMON_CHANNEL_INFO(in, HWMON_I_INPUT), NULL @@ -192,7 +195,8 @@ static int adm1177_probe(struct i2c_client *client) struct device *dev = &client->dev; struct device *hwmon_dev; struct adm1177_state *st; - u32 alert_threshold_ua; + u64 alert_threshold_ua; + u32 prop; int ret; st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL); @@ -208,22 +212,26 @@ static int adm1177_probe(struct i2c_client *client) if (device_property_read_u32(dev, "shunt-resistor-micro-ohms", &st->r_sense_uohm)) st->r_sense_uohm = 0; - if (device_property_read_u32(dev, "adi,shutdown-threshold-microamp", - &alert_threshold_ua)) { - if (st->r_sense_uohm) - /* - * set maximum default value from datasheet based on - * shunt-resistor - */ - alert_threshold_ua = div_u64(105840000000, - st->r_sense_uohm); - else - alert_threshold_ua = 0; + if (!device_property_read_u32(dev, "adi,shutdown-threshold-microamp", + &prop)) { + alert_threshold_ua = prop; + } else if (st->r_sense_uohm) { + /* + * set maximum default value from datasheet based on + * shunt-resistor + */ + alert_threshold_ua = div_u64(105840000000ULL, + st->r_sense_uohm); + } else { + alert_threshold_ua = 0; } st->vrange_high = device_property_read_bool(dev, "adi,vrange-high-enable"); - if (alert_threshold_ua && st->r_sense_uohm) - adm1177_write_alert_thr(st, alert_threshold_ua); + if (alert_threshold_ua && st->r_sense_uohm) { + ret = adm1177_write_alert_thr(st, alert_threshold_ua); + if (ret) + return ret; + } ret = adm1177_write_cmd(st, ADM1177_CMD_V_CONT | ADM1177_CMD_I_CONT | diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c index b2fc936851e1..457089c561b4 100644 --- a/drivers/hwmon/peci/cputemp.c +++ b/drivers/hwmon/peci/cputemp.c @@ -131,7 +131,7 @@ static int get_temp_target(struct peci_cputemp *priv, enum peci_temp_target_type *val = priv->temp.target.tjmax; break; case crit_hyst_type: - *val = priv->temp.target.tjmax - priv->temp.target.tcontrol; + *val = priv->temp.target.tcontrol; break; default: ret = -EOPNOTSUPP; @@ -319,7 +319,7 @@ static umode_t cputemp_is_visible(const void *data, enum hwmon_sensor_types type { const struct peci_cputemp *priv = data; - if (channel > CPUTEMP_CHANNEL_NUMS) + if (channel >= CPUTEMP_CHANNEL_NUMS) return 0; if (channel < channel_core) diff --git a/drivers/hwmon/pmbus/ina233.c b/drivers/hwmon/pmbus/ina233.c index 2d8b5a5347ed..7aebd854763a 100644 --- a/drivers/hwmon/pmbus/ina233.c +++ b/drivers/hwmon/pmbus/ina233.c @@ -72,7 +72,8 @@ static int ina233_read_word_data(struct i2c_client *client, int page, /* Adjust returned value to match VIN coefficients */ /* VIN: 1.25 mV VSHUNT: 2.5 uV LSB */ - ret = DIV_ROUND_CLOSEST(ret * 25, 12500); + ret = clamp_val(DIV_ROUND_CLOSEST((s16)ret * 25, 12500), + S16_MIN, S16_MAX) & 0xffff; break; default: ret = -ENODATA; diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index e7dac26b5be6..3e3a887aad05 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -96,7 +96,15 @@ static ssize_t isl68137_avs_enable_show_page(struct i2c_client *client, int page, char *buf) { - int val = pmbus_read_byte_data(client, page, PMBUS_OPERATION); + int val; + + val = pmbus_lock_interruptible(client); + if (val) + return val; + + val = pmbus_read_byte_data(client, page, PMBUS_OPERATION); + + pmbus_unlock(client); if (val < 0) return val; @@ -118,6 +126,10 @@ static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client, op_val = result ? ISL68137_VOUT_AVS : 0; + rc = pmbus_lock_interruptible(client); + if (rc) + return rc; + /* * Writes to VOUT setpoint over AVSBus will persist after the VRM is * switched to PMBus control. Switching back to AVSBus control @@ -129,17 +141,20 @@ static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client, rc = pmbus_read_word_data(client, page, 0xff, PMBUS_VOUT_COMMAND); if (rc < 0) - return rc; + goto unlock; rc = pmbus_write_word_data(client, page, PMBUS_VOUT_COMMAND, rc); if (rc < 0) - return rc; + goto unlock; } rc = pmbus_update_byte_data(client, page, PMBUS_OPERATION, ISL68137_VOUT_AVS, op_val); +unlock: + pmbus_unlock(client); + return (rc < 0) ? rc : count; } diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index be6d05def115..572be3ebc03d 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -6,6 +6,7 @@ * Copyright (c) 2012 Guenter Roeck */ +#include <linux/atomic.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/dcache.h> @@ -21,8 +22,8 @@ #include <linux/pmbus.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> -#include <linux/of.h> #include <linux/thermal.h> +#include <linux/workqueue.h> #include "pmbus.h" /* @@ -112,6 +113,11 @@ struct pmbus_data { struct mutex update_lock; +#if IS_ENABLED(CONFIG_REGULATOR) + atomic_t regulator_events[PMBUS_PAGES]; + struct work_struct regulator_notify_work; +#endif + bool has_status_word; /* device uses STATUS_WORD register */ int (*read_status)(struct i2c_client *client, int page); @@ -1209,6 +1215,12 @@ static ssize_t pmbus_show_boolean(struct device *dev, return sysfs_emit(buf, "%d\n", val); } +static ssize_t pmbus_show_zero(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + return sysfs_emit(buf, "0\n"); +} + static ssize_t pmbus_show_sensor(struct device *dev, struct device_attribute *devattr, char *buf) { @@ -1407,7 +1419,7 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, int reg, enum pmbus_sensor_classes class, bool update, bool readonly, - bool convert) + bool writeonly, bool convert) { struct pmbus_sensor *sensor; struct device_attribute *a; @@ -1436,7 +1448,8 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, sensor->data = -ENODATA; pmbus_dev_attr_init(a, sensor->name, readonly ? 0444 : 0644, - pmbus_show_sensor, pmbus_set_sensor); + writeonly ? pmbus_show_zero : pmbus_show_sensor, + pmbus_set_sensor); if (pmbus_add_attribute(data, &a->attr)) return NULL; @@ -1495,8 +1508,10 @@ static int pmbus_add_label(struct pmbus_data *data, struct pmbus_limit_attr { u16 reg; /* Limit register */ u16 sbit; /* Alarm attribute status bit */ - bool update; /* True if register needs updates */ - bool low; /* True if low limit; for limits with compare functions only */ + bool readonly:1; /* True if the attribute is read-only */ + bool writeonly:1; /* True if the attribute is write-only */ + bool update:1; /* True if register needs updates */ + bool low:1; /* True if low limit; for limits with compare functions only */ const char *attr; /* Attribute name */ const char *alarm; /* Alarm attribute name */ }; @@ -1511,9 +1526,9 @@ struct pmbus_sensor_attr { u8 nlimit; /* # of limit registers */ enum pmbus_sensor_classes class;/* sensor class */ const char *label; /* sensor label */ - bool paged; /* true if paged sensor */ - bool update; /* true if update needed */ - bool compare; /* true if compare function needed */ + bool paged:1; /* true if paged sensor */ + bool update:1; /* true if update needed */ + bool compare:1; /* true if compare function needed */ u32 func; /* sensor mask */ u32 sfunc; /* sensor status mask */ int sreg; /* status register */ @@ -1544,7 +1559,7 @@ static int pmbus_add_limit_attrs(struct i2c_client *client, curr = pmbus_add_sensor(data, name, l->attr, index, page, 0xff, l->reg, attr->class, attr->update || l->update, - false, true); + l->readonly, l->writeonly, true); if (!curr) return -ENOMEM; if (l->sbit && (info->func[page] & attr->sfunc)) { @@ -1584,7 +1599,7 @@ static int pmbus_add_sensor_attrs_one(struct i2c_client *client, return ret; } base = pmbus_add_sensor(data, name, "input", index, page, phase, - attr->reg, attr->class, true, true, true); + attr->reg, attr->class, true, true, false, true); if (!base) return -ENOMEM; /* No limit and alarm attributes for phase specific sensors */ @@ -1707,23 +1722,29 @@ static const struct pmbus_limit_attr vin_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_VIN_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_VIN_MIN, .update = true, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_VIN_MAX, .update = true, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_VIN_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_VIN_MIN, + .readonly = true, .attr = "rated_min", }, { .reg = PMBUS_MFR_VIN_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -1776,23 +1797,29 @@ static const struct pmbus_limit_attr vout_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_VOUT_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_VOUT_MIN, .update = true, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_VOUT_MAX, .update = true, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_VOUT_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_VOUT_MIN, + .readonly = true, .attr = "rated_min", }, { .reg = PMBUS_MFR_VOUT_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -1852,20 +1879,25 @@ static const struct pmbus_limit_attr iin_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_IIN_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_IIN_MIN, .update = true, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_IIN_MAX, .update = true, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_IIN_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_IIN_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -1889,20 +1921,25 @@ static const struct pmbus_limit_attr iout_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_IOUT_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_IOUT_MIN, .update = true, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_IOUT_MAX, .update = true, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_IOUT_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_IOUT_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -1943,20 +1980,25 @@ static const struct pmbus_limit_attr pin_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_PIN_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_PIN_MIN, .update = true, + .readonly = true, .attr = "input_lowest", }, { .reg = PMBUS_VIRT_READ_PIN_MAX, .update = true, + .readonly = true, .attr = "input_highest", }, { .reg = PMBUS_VIRT_RESET_PIN_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_PIN_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -1980,20 +2022,25 @@ static const struct pmbus_limit_attr pout_limit_attrs[] = { }, { .reg = PMBUS_VIRT_READ_POUT_AVG, .update = true, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_POUT_MIN, .update = true, + .readonly = true, .attr = "input_lowest", }, { .reg = PMBUS_VIRT_READ_POUT_MAX, .update = true, + .readonly = true, .attr = "input_highest", }, { .reg = PMBUS_VIRT_RESET_POUT_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_POUT_MAX, + .readonly = true, .attr = "rated_max", }, }; @@ -2049,18 +2096,23 @@ static const struct pmbus_limit_attr temp_limit_attrs[] = { .sbit = PB_TEMP_OT_FAULT, }, { .reg = PMBUS_VIRT_READ_TEMP_MIN, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_TEMP_AVG, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_TEMP_MAX, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_TEMP_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_MAX_TEMP_1, + .readonly = true, .attr = "rated_max", }, }; @@ -2090,18 +2142,23 @@ static const struct pmbus_limit_attr temp_limit_attrs2[] = { .sbit = PB_TEMP_OT_FAULT, }, { .reg = PMBUS_VIRT_READ_TEMP2_MIN, + .readonly = true, .attr = "lowest", }, { .reg = PMBUS_VIRT_READ_TEMP2_AVG, + .readonly = true, .attr = "average", }, { .reg = PMBUS_VIRT_READ_TEMP2_MAX, + .readonly = true, .attr = "highest", }, { .reg = PMBUS_VIRT_RESET_TEMP2_HISTORY, + .writeonly = true, .attr = "reset_history", }, { .reg = PMBUS_MFR_MAX_TEMP_2, + .readonly = true, .attr = "rated_max", }, }; @@ -2131,6 +2188,7 @@ static const struct pmbus_limit_attr temp_limit_attrs3[] = { .sbit = PB_TEMP_OT_FAULT, }, { .reg = PMBUS_MFR_MAX_TEMP_3, + .readonly = true, .attr = "rated_max", }, }; @@ -2214,7 +2272,7 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client, sensor = pmbus_add_sensor(data, "fan", "target", index, page, 0xff, PMBUS_VIRT_FAN_TARGET_1 + id, PSC_FAN, - false, false, true); + false, false, false, true); if (!sensor) return -ENOMEM; @@ -2225,14 +2283,14 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client, sensor = pmbus_add_sensor(data, "pwm", NULL, index, page, 0xff, PMBUS_VIRT_PWM_1 + id, PSC_PWM, - false, false, true); + false, false, false, true); if (!sensor) return -ENOMEM; sensor = pmbus_add_sensor(data, "pwm", "enable", index, page, 0xff, PMBUS_VIRT_PWM_ENABLE_1 + id, PSC_PWM, - true, false, false); + true, false, false, false); if (!sensor) return -ENOMEM; @@ -2274,7 +2332,7 @@ static int pmbus_add_fan_attributes(struct i2c_client *client, if (pmbus_add_sensor(data, "fan", "input", index, page, 0xff, pmbus_fan_registers[f], - PSC_FAN, true, true, true) == NULL) + PSC_FAN, true, true, false, true) == NULL) return -ENOMEM; /* Fan control */ @@ -3176,12 +3234,19 @@ static int pmbus_regulator_get_voltage(struct regulator_dev *rdev) .class = PSC_VOLTAGE_OUT, .convert = true, }; + int ret; + mutex_lock(&data->update_lock); s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_READ_VOUT); - if (s.data < 0) - return s.data; + if (s.data < 0) { + ret = s.data; + goto unlock; + } - return (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */ + ret = (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */ +unlock: + mutex_unlock(&data->update_lock); + return ret; } static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv, @@ -3198,16 +3263,22 @@ static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv, }; int val = DIV_ROUND_CLOSEST(min_uv, 1000); /* convert to mV */ int low, high; + int ret; *selector = 0; + mutex_lock(&data->update_lock); low = pmbus_regulator_get_low_margin(client, s.page); - if (low < 0) - return low; + if (low < 0) { + ret = low; + goto unlock; + } high = pmbus_regulator_get_high_margin(client, s.page); - if (high < 0) - return high; + if (high < 0) { + ret = high; + goto unlock; + } /* Make sure we are within margins */ if (low > val) @@ -3217,7 +3288,10 @@ static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv, val = pmbus_data2reg(data, &s, val); - return _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val); + ret = _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val); +unlock: + mutex_unlock(&data->update_lock); + return ret; } static int pmbus_regulator_list_voltage(struct regulator_dev *rdev, @@ -3227,6 +3301,7 @@ static int pmbus_regulator_list_voltage(struct regulator_dev *rdev, struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_data *data = i2c_get_clientdata(client); int val, low, high; + int ret; if (data->flags & PMBUS_VOUT_PROTECTED) return 0; @@ -3239,18 +3314,29 @@ static int pmbus_regulator_list_voltage(struct regulator_dev *rdev, val = DIV_ROUND_CLOSEST(rdev->desc->min_uV + (rdev->desc->uV_step * selector), 1000); /* convert to mV */ + mutex_lock(&data->update_lock); + low = pmbus_regulator_get_low_margin(client, rdev_get_id(rdev)); - if (low < 0) - return low; + if (low < 0) { + ret = low; + goto unlock; + } high = pmbus_regulator_get_high_margin(client, rdev_get_id(rdev)); - if (high < 0) - return high; + if (high < 0) { + ret = high; + goto unlock; + } - if (val >= low && val <= high) - return val * 1000; /* unit is uV */ + if (val >= low && val <= high) { + ret = val * 1000; /* unit is uV */ + goto unlock; + } - return 0; + ret = 0; +unlock: + mutex_unlock(&data->update_lock); + return ret; } const struct regulator_ops pmbus_regulator_ops = { @@ -3281,12 +3367,42 @@ int pmbus_regulator_init_cb(struct regulator_dev *rdev, } EXPORT_SYMBOL_NS_GPL(pmbus_regulator_init_cb, "PMBUS"); +static void pmbus_regulator_notify_work_cancel(void *data) +{ + struct pmbus_data *pdata = data; + + cancel_work_sync(&pdata->regulator_notify_work); +} + +static void pmbus_regulator_notify_worker(struct work_struct *work) +{ + struct pmbus_data *data = + container_of(work, struct pmbus_data, regulator_notify_work); + int i, j; + + for (i = 0; i < data->info->pages; i++) { + int event; + + event = atomic_xchg(&data->regulator_events[i], 0); + if (!event) + continue; + + for (j = 0; j < data->info->num_regulators; j++) { + if (i == rdev_get_id(data->rdevs[j])) { + regulator_notifier_call_chain(data->rdevs[j], + event, NULL); + break; + } + } + } +} + static int pmbus_regulator_register(struct pmbus_data *data) { struct device *dev = data->dev; const struct pmbus_driver_info *info = data->info; const struct pmbus_platform_data *pdata = dev_get_platdata(dev); - int i; + int i, ret; data->rdevs = devm_kzalloc(dev, sizeof(struct regulator_dev *) * info->num_regulators, GFP_KERNEL); @@ -3310,19 +3426,19 @@ static int pmbus_regulator_register(struct pmbus_data *data) info->reg_desc[i].name); } + INIT_WORK(&data->regulator_notify_work, pmbus_regulator_notify_worker); + + ret = devm_add_action_or_reset(dev, pmbus_regulator_notify_work_cancel, data); + if (ret) + return ret; + return 0; } static void pmbus_regulator_notify(struct pmbus_data *data, int page, int event) { - int j; - - for (j = 0; j < data->info->num_regulators; j++) { - if (page == rdev_get_id(data->rdevs[j])) { - regulator_notifier_call_chain(data->rdevs[j], event, NULL); - break; - } - } + atomic_or(event, &data->regulator_events[page]); + schedule_work(&data->regulator_notify_work); } #else static int pmbus_regulator_register(struct pmbus_data *data) diff --git a/drivers/i2c/busses/i2c-designware-amdisp.c b/drivers/i2c/busses/i2c-designware-amdisp.c index c48728ad9f6f..9f0ec0fae6f2 100644 --- a/drivers/i2c/busses/i2c-designware-amdisp.c +++ b/drivers/i2c/busses/i2c-designware-amdisp.c @@ -7,6 +7,7 @@ #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/soc/amd/isp4_misc.h> @@ -76,22 +77,20 @@ static int amd_isp_dw_i2c_plat_probe(struct platform_device *pdev) device_enable_async_suspend(&pdev->dev); - pm_runtime_enable(&pdev->dev); - pm_runtime_get_sync(&pdev->dev); - + dev_pm_genpd_resume(&pdev->dev); ret = i2c_dw_probe(isp_i2c_dev); if (ret) { dev_err_probe(&pdev->dev, ret, "i2c_dw_probe failed\n"); goto error_release_rpm; } - - pm_runtime_put_sync(&pdev->dev); + dev_pm_genpd_suspend(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_enable(&pdev->dev); return 0; error_release_rpm: amd_isp_dw_i2c_plat_pm_cleanup(isp_i2c_dev); - pm_runtime_put_sync(&pdev->dev); return ret; } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 85f554044cf1..452d120a210b 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1018,8 +1018,9 @@ static inline int i2c_imx_isr_read(struct imx_i2c_struct *i2c_imx) return 0; } -static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx) +static inline enum imx_i2c_state i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx) { + enum imx_i2c_state next_state = IMX_I2C_STATE_READ_CONTINUE; unsigned int temp; if ((i2c_imx->msg->len - 1) == i2c_imx->msg_buf_idx) { @@ -1033,18 +1034,20 @@ static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx) i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - } else { - /* - * For i2c master receiver repeat restart operation like: - * read -> repeat MSTA -> read/write - * The controller must set MTX before read the last byte in - * the first read operation, otherwise the first read cost - * one extra clock cycle. - */ - temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); - temp |= I2CR_MTX; - imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); + + return IMX_I2C_STATE_DONE; } + /* + * For i2c master receiver repeat restart operation like: + * read -> repeat MSTA -> read/write + * The controller must set MTX before read the last byte in + * the first read operation, otherwise the first read cost + * one extra clock cycle. + */ + temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + temp |= I2CR_MTX; + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); + next_state = IMX_I2C_STATE_DONE; } else if (i2c_imx->msg_buf_idx == (i2c_imx->msg->len - 2)) { temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); temp |= I2CR_TXAK; @@ -1052,6 +1055,7 @@ static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx) } i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); + return next_state; } static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_imx) @@ -1088,11 +1092,9 @@ static irqreturn_t i2c_imx_master_isr(struct imx_i2c_struct *i2c_imx, unsigned i break; case IMX_I2C_STATE_READ_CONTINUE: - i2c_imx_isr_read_continue(i2c_imx); - if (i2c_imx->msg_buf_idx == i2c_imx->msg->len) { - i2c_imx->state = IMX_I2C_STATE_DONE; + i2c_imx->state = i2c_imx_isr_read_continue(i2c_imx); + if (i2c_imx->state == IMX_I2C_STATE_DONE) wake_up(&i2c_imx->queue); - } break; case IMX_I2C_STATE_READ_BLOCK_DATA: @@ -1490,6 +1492,7 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, bool is_lastmsg) { int block_data = msgs->flags & I2C_M_RECV_LEN; + int ret = 0; dev_dbg(&i2c_imx->adapter.dev, "<%s> write slave address: addr=0x%x\n", @@ -1522,10 +1525,20 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, dev_err(&i2c_imx->adapter.dev, "<%s> read timedout\n", __func__); return -ETIMEDOUT; } - if (!i2c_imx->stopped) - return i2c_imx_bus_busy(i2c_imx, 0, false); + if (i2c_imx->is_lastmsg) { + if (!i2c_imx->stopped) + ret = i2c_imx_bus_busy(i2c_imx, 0, false); + /* + * Only read the last byte of the last message after the bus is + * not busy. Else the controller generates another clock which + * might confuse devices. + */ + if (!ret) + i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx, + IMX_I2C_I2DR); + } - return 0; + return ret; } static int i2c_imx_xfer_common(struct i2c_adapter *adapter, diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index fc45c384833f..4fafe393a48c 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -608,14 +608,29 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num, if (rdma_rw_io_needs_mr(qp->device, port_num, dir, sg_cnt)) { ret = rdma_rw_init_mr_wrs(ctx, qp, port_num, sg, sg_cnt, sg_offset, remote_addr, rkey, dir); - } else if (sg_cnt > 1) { + /* + * If MR init succeeded or failed for a reason other + * than pool exhaustion, that result is final. + * + * Pool exhaustion (-EAGAIN) from the max_sgl_rd + * optimization is recoverable: fall back to + * direct SGE posting. iWARP and force_mr require + * MRs unconditionally, so -EAGAIN is terminal. + */ + if (ret != -EAGAIN || + rdma_protocol_iwarp(qp->device, port_num) || + unlikely(rdma_rw_force_mr)) + goto out; + } + + if (sg_cnt > 1) ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset, remote_addr, rkey, dir); - } else { + else ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset, remote_addr, rkey, dir); - } +out: if (ret < 0) goto out_unmap_sg; return ret; @@ -686,14 +701,16 @@ int rdma_rw_ctx_init_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp, return ret; /* - * IOVA mapping not available. Check if MR registration provides - * better performance than multiple SGE entries. + * IOVA not available; fall back to the map_wrs path, which maps + * each bvec as a direct SGE. This is always correct: the MR path + * is a throughput optimization, not a correctness requirement. + * (iWARP, which does require MRs, is handled by the check above.) + * + * The rdma_rw_io_needs_mr() gate is not used here because nr_bvec + * is a raw page count that overstates DMA entry demand -- the bvec + * caller has no post-DMA-coalescing segment count, and feeding the + * inflated count into the MR path exhausts the pool on RDMA READs. */ - if (rdma_rw_io_needs_mr(dev, port_num, dir, nr_bvec)) - return rdma_rw_init_mr_wrs_bvec(ctx, qp, port_num, bvecs, - nr_bvec, &iter, remote_addr, - rkey, dir); - return rdma_rw_init_map_wrs_bvec(ctx, qp, bvecs, nr_bvec, &iter, remote_addr, rkey, dir); } diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index cff4fcca2c34..edc34c69f0f2 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -55,7 +55,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d if (dirty) ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt, - DMA_BIDIRECTIONAL, 0); + DMA_BIDIRECTIONAL, + DMA_ATTR_REQUIRE_COHERENT); for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) { unpin_user_page_range_dirty_lock(sg_page(sg), @@ -169,7 +170,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, unsigned long lock_limit; unsigned long new_pinned; unsigned long cur_base; - unsigned long dma_attr = 0; + unsigned long dma_attr = DMA_ATTR_REQUIRE_COHERENT; struct mm_struct *mm; unsigned long npages; int pinned, ret; diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c index d34b5f88cd40..71a7ca2196ad 100644 --- a/drivers/infiniband/hw/bng_re/bng_dev.c +++ b/drivers/infiniband/hw/bng_re/bng_dev.c @@ -210,7 +210,7 @@ static int bng_re_stats_ctx_alloc(struct bng_re_dev *rdev) return rc; } -static void bng_re_query_hwrm_version(struct bng_re_dev *rdev) +static int bng_re_query_hwrm_version(struct bng_re_dev *rdev) { struct bnge_auxr_dev *aux_dev = rdev->aux_dev; struct hwrm_ver_get_output ver_get_resp = {}; @@ -230,7 +230,7 @@ static void bng_re_query_hwrm_version(struct bng_re_dev *rdev) if (rc) { ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x", rc); - return; + return rc; } cctx = rdev->chip_ctx; @@ -244,6 +244,8 @@ static void bng_re_query_hwrm_version(struct bng_re_dev *rdev) if (!cctx->hwrm_cmd_max_timeout) cctx->hwrm_cmd_max_timeout = BNG_ROCE_FW_MAX_TIMEOUT; + + return 0; } static void bng_re_dev_uninit(struct bng_re_dev *rdev) @@ -306,13 +308,15 @@ static int bng_re_dev_init(struct bng_re_dev *rdev) goto msix_ctx_fail; } - bng_re_query_hwrm_version(rdev); + rc = bng_re_query_hwrm_version(rdev); + if (rc) + goto destroy_chip_ctx; rc = bng_re_alloc_fw_channel(&rdev->bng_res, &rdev->rcfw); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate RCFW Channel: %#x\n", rc); - goto alloc_fw_chl_fail; + goto destroy_chip_ctx; } /* Allocate nq record memory */ @@ -391,7 +395,7 @@ free_rcfw: kfree(rdev->nqr); nq_alloc_fail: bng_re_free_rcfw_channel(&rdev->rcfw); -alloc_fw_chl_fail: +destroy_chip_ctx: bng_re_destroy_chip_ctx(rdev); msix_ctx_fail: bnge_unregister_dev(rdev->aux_dev); diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c index 229b0ad3b0cb..e97b5f0d7003 100644 --- a/drivers/infiniband/hw/efa/efa_com.c +++ b/drivers/infiniband/hw/efa/efa_com.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause /* - * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2026 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include <linux/log2.h> @@ -310,23 +310,19 @@ static inline struct efa_comp_ctx *efa_com_get_comp_ctx_by_cmd_id(struct efa_com return &aq->comp_ctx[ctx_id]; } -static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq, - struct efa_admin_aq_entry *cmd, - size_t cmd_size_in_bytes, - struct efa_admin_acq_entry *comp, - size_t comp_size_in_bytes) +static void __efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq, + struct efa_comp_ctx *comp_ctx, + struct efa_admin_aq_entry *cmd, + size_t cmd_size_in_bytes, + struct efa_admin_acq_entry *comp, + size_t comp_size_in_bytes) { struct efa_admin_aq_entry *aqe; - struct efa_comp_ctx *comp_ctx; u16 queue_size_mask; u16 cmd_id; u16 ctx_id; u16 pi; - comp_ctx = efa_com_alloc_comp_ctx(aq); - if (!comp_ctx) - return ERR_PTR(-EINVAL); - queue_size_mask = aq->depth - 1; pi = aq->sq.pc & queue_size_mask; ctx_id = efa_com_get_comp_ctx_id(aq, comp_ctx); @@ -360,8 +356,6 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu /* barrier not needed in case of writel */ writel(aq->sq.pc, aq->sq.db_addr); - - return comp_ctx; } static inline int efa_com_init_comp_ctxt(struct efa_com_admin_queue *aq) @@ -394,28 +388,25 @@ static inline int efa_com_init_comp_ctxt(struct efa_com_admin_queue *aq) return 0; } -static struct efa_comp_ctx *efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq, - struct efa_admin_aq_entry *cmd, - size_t cmd_size_in_bytes, - struct efa_admin_acq_entry *comp, - size_t comp_size_in_bytes) +static int efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq, + struct efa_comp_ctx *comp_ctx, + struct efa_admin_aq_entry *cmd, + size_t cmd_size_in_bytes, + struct efa_admin_acq_entry *comp, + size_t comp_size_in_bytes) { - struct efa_comp_ctx *comp_ctx; - spin_lock(&aq->sq.lock); if (!test_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state)) { ibdev_err_ratelimited(aq->efa_dev, "Admin queue is closed\n"); spin_unlock(&aq->sq.lock); - return ERR_PTR(-ENODEV); + return -ENODEV; } - comp_ctx = __efa_com_submit_admin_cmd(aq, cmd, cmd_size_in_bytes, comp, - comp_size_in_bytes); + __efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size_in_bytes, comp, + comp_size_in_bytes); spin_unlock(&aq->sq.lock); - if (IS_ERR(comp_ctx)) - clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state); - return comp_ctx; + return 0; } static int efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq, @@ -512,7 +503,6 @@ static int efa_com_wait_and_process_admin_cq_polling(struct efa_comp_ctx *comp_c { unsigned long timeout; unsigned long flags; - int err; timeout = jiffies + usecs_to_jiffies(aq->completion_timeout); @@ -532,24 +522,20 @@ static int efa_com_wait_and_process_admin_cq_polling(struct efa_comp_ctx *comp_c atomic64_inc(&aq->stats.no_completion); clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state); - err = -ETIME; - goto out; + return -ETIME; } msleep(aq->poll_interval); } - err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status); -out: - efa_com_dealloc_comp_ctx(aq, comp_ctx); - return err; + return efa_com_comp_status_to_errno( + comp_ctx->user_cqe->acq_common_descriptor.status); } static int efa_com_wait_and_process_admin_cq_interrupts(struct efa_comp_ctx *comp_ctx, struct efa_com_admin_queue *aq) { unsigned long flags; - int err; wait_for_completion_timeout(&comp_ctx->wait_event, usecs_to_jiffies(aq->completion_timeout)); @@ -585,14 +571,11 @@ static int efa_com_wait_and_process_admin_cq_interrupts(struct efa_comp_ctx *com aq->cq.cc); clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state); - err = -ETIME; - goto out; + return -ETIME; } - err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status); -out: - efa_com_dealloc_comp_ctx(aq, comp_ctx); - return err; + return efa_com_comp_status_to_errno( + comp_ctx->user_cqe->acq_common_descriptor.status); } /* @@ -642,30 +625,39 @@ int efa_com_cmd_exec(struct efa_com_admin_queue *aq, ibdev_dbg(aq->efa_dev, "%s (opcode %d)\n", efa_com_cmd_str(cmd->aq_common_descriptor.opcode), cmd->aq_common_descriptor.opcode); - comp_ctx = efa_com_submit_admin_cmd(aq, cmd, cmd_size, comp, comp_size); - if (IS_ERR(comp_ctx)) { + + comp_ctx = efa_com_alloc_comp_ctx(aq); + if (!comp_ctx) { + clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state); + up(&aq->avail_cmds); + return -EINVAL; + } + + err = efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size, comp, comp_size); + if (err) { ibdev_err_ratelimited( aq->efa_dev, - "Failed to submit command %s (opcode %u) err %pe\n", + "Failed to submit command %s (opcode %u) err %d\n", efa_com_cmd_str(cmd->aq_common_descriptor.opcode), - cmd->aq_common_descriptor.opcode, comp_ctx); + cmd->aq_common_descriptor.opcode, err); + efa_com_dealloc_comp_ctx(aq, comp_ctx); up(&aq->avail_cmds); atomic64_inc(&aq->stats.cmd_err); - return PTR_ERR(comp_ctx); + return err; } err = efa_com_wait_and_process_admin_cq(comp_ctx, aq); if (err) { ibdev_err_ratelimited( aq->efa_dev, - "Failed to process command %s (opcode %u) comp_status %d err %d\n", + "Failed to process command %s (opcode %u) err %d\n", efa_com_cmd_str(cmd->aq_common_descriptor.opcode), - cmd->aq_common_descriptor.opcode, - comp_ctx->user_cqe->acq_common_descriptor.status, err); + cmd->aq_common_descriptor.opcode, err); atomic64_inc(&aq->stats.cmd_err); } + efa_com_dealloc_comp_ctx(aq, comp_ctx); up(&aq->avail_cmds); return err; diff --git a/drivers/infiniband/hw/ionic/ionic_controlpath.c b/drivers/infiniband/hw/ionic/ionic_controlpath.c index 4842931f5316..a5671da3db64 100644 --- a/drivers/infiniband/hw/ionic/ionic_controlpath.c +++ b/drivers/infiniband/hw/ionic/ionic_controlpath.c @@ -508,6 +508,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev, { const struct ib_global_route *grh; enum rdma_network_type net; + u8 smac[ETH_ALEN]; u16 vlan; int rc; @@ -518,7 +519,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev, grh = rdma_ah_read_grh(attr); - rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, &hdr->eth.smac_h[0]); + rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, smac); if (rc) return rc; @@ -536,6 +537,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev, if (rc) return rc; + ether_addr_copy(hdr->eth.smac_h, smac); ether_addr_copy(hdr->eth.dmac_h, attr->roce.dmac); if (net == RDMA_NETWORK_IPV4) { diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 3d084d4ff577..91c0e7298283 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -2241,11 +2241,12 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev, int oldarpindex; int arpindex; struct net_device *netdev = iwdev->netdev; + int ret; /* create an hte and cm_node for this instance */ cm_node = kzalloc_obj(*cm_node, GFP_ATOMIC); if (!cm_node) - return NULL; + return ERR_PTR(-ENOMEM); /* set our node specific transport info */ cm_node->ipv4 = cm_info->ipv4; @@ -2348,8 +2349,10 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev, arpindex = -EINVAL; } - if (arpindex < 0) + if (arpindex < 0) { + ret = -EINVAL; goto err; + } ether_addr_copy(cm_node->rem_mac, iwdev->rf->arp_table[arpindex].mac_addr); @@ -2360,7 +2363,7 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev, err: kfree(cm_node); - return NULL; + return ERR_PTR(ret); } static void irdma_destroy_connection(struct irdma_cm_node *cm_node) @@ -3021,8 +3024,8 @@ static int irdma_create_cm_node(struct irdma_cm_core *cm_core, /* create a CM connection node */ cm_node = irdma_make_cm_node(cm_core, iwdev, cm_info, NULL); - if (!cm_node) - return -ENOMEM; + if (IS_ERR(cm_node)) + return PTR_ERR(cm_node); /* set our node side to client (active) side */ cm_node->tcp_cntxt.client = 1; @@ -3219,9 +3222,9 @@ void irdma_receive_ilq(struct irdma_sc_vsi *vsi, struct irdma_puda_buf *rbuf) cm_info.cm_id = listener->cm_id; cm_node = irdma_make_cm_node(cm_core, iwdev, &cm_info, listener); - if (!cm_node) { + if (IS_ERR(cm_node)) { ibdev_dbg(&cm_core->iwdev->ibdev, - "CM: allocate node failed\n"); + "CM: allocate node failed ret=%ld\n", PTR_ERR(cm_node)); refcount_dec(&listener->refcnt); return; } @@ -4239,21 +4242,21 @@ static void irdma_cm_event_handler(struct work_struct *work) irdma_cm_event_reset(event); break; case IRDMA_CM_EVENT_CONNECTED: - if (!event->cm_node->cm_id || - event->cm_node->state != IRDMA_CM_STATE_OFFLOADED) + if (!cm_node->cm_id || + cm_node->state != IRDMA_CM_STATE_OFFLOADED) break; irdma_cm_event_connected(event); break; case IRDMA_CM_EVENT_MPA_REJECT: - if (!event->cm_node->cm_id || + if (!cm_node->cm_id || cm_node->state == IRDMA_CM_STATE_OFFLOADED) break; irdma_send_cm_event(cm_node, cm_node->cm_id, IW_CM_EVENT_CONNECT_REPLY, -ECONNREFUSED); break; case IRDMA_CM_EVENT_ABORTED: - if (!event->cm_node->cm_id || - event->cm_node->state == IRDMA_CM_STATE_OFFLOADED) + if (!cm_node->cm_id || + cm_node->state == IRDMA_CM_STATE_OFFLOADED) break; irdma_event_connect_error(event); break; @@ -4263,7 +4266,7 @@ static void irdma_cm_event_handler(struct work_struct *work) break; } - irdma_rem_ref_cm_node(event->cm_node); + irdma_rem_ref_cm_node(cm_node); kfree(event); } diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index ac3721a5747a..4718acf6c6fd 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -1438,7 +1438,7 @@ exit: * irdma_round_up_wq - return round up qp wq depth * @wqdepth: wq depth in quanta to round up */ -static int irdma_round_up_wq(u32 wqdepth) +static u64 irdma_round_up_wq(u64 wqdepth) { int scount = 1; @@ -1491,15 +1491,16 @@ void irdma_get_wqe_shift(struct irdma_uk_attrs *uk_attrs, u32 sge, int irdma_get_sqdepth(struct irdma_uk_attrs *uk_attrs, u32 sq_size, u8 shift, u32 *sqdepth) { - u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift; + u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift; + u64 hw_quanta = + irdma_round_up_wq(((u64)sq_size << shift) + IRDMA_SQ_RSVD); - *sqdepth = irdma_round_up_wq((sq_size << shift) + IRDMA_SQ_RSVD); - - if (*sqdepth < min_size) - *sqdepth = min_size; - else if (*sqdepth > uk_attrs->max_hw_wq_quanta) + if (hw_quanta < min_hw_quanta) + hw_quanta = min_hw_quanta; + else if (hw_quanta > uk_attrs->max_hw_wq_quanta) return -EINVAL; + *sqdepth = hw_quanta; return 0; } @@ -1513,15 +1514,16 @@ int irdma_get_sqdepth(struct irdma_uk_attrs *uk_attrs, u32 sq_size, u8 shift, int irdma_get_rqdepth(struct irdma_uk_attrs *uk_attrs, u32 rq_size, u8 shift, u32 *rqdepth) { - u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift; - - *rqdepth = irdma_round_up_wq((rq_size << shift) + IRDMA_RQ_RSVD); + u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift; + u64 hw_quanta = + irdma_round_up_wq(((u64)rq_size << shift) + IRDMA_RQ_RSVD); - if (*rqdepth < min_size) - *rqdepth = min_size; - else if (*rqdepth > uk_attrs->max_hw_rq_quanta) + if (hw_quanta < min_hw_quanta) + hw_quanta = min_hw_quanta; + else if (hw_quanta > uk_attrs->max_hw_rq_quanta) return -EINVAL; + *rqdepth = hw_quanta; return 0; } @@ -1535,13 +1537,16 @@ int irdma_get_rqdepth(struct irdma_uk_attrs *uk_attrs, u32 rq_size, u8 shift, int irdma_get_srqdepth(struct irdma_uk_attrs *uk_attrs, u32 srq_size, u8 shift, u32 *srqdepth) { - *srqdepth = irdma_round_up_wq((srq_size << shift) + IRDMA_RQ_RSVD); + u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift; + u64 hw_quanta = + irdma_round_up_wq(((u64)srq_size << shift) + IRDMA_RQ_RSVD); - if (*srqdepth < ((u32)uk_attrs->min_hw_wq_size << shift)) - *srqdepth = uk_attrs->min_hw_wq_size << shift; - else if (*srqdepth > uk_attrs->max_hw_srq_quanta) + if (hw_quanta < min_hw_quanta) + hw_quanta = min_hw_quanta; + else if (hw_quanta > uk_attrs->max_hw_srq_quanta) return -EINVAL; + *srqdepth = hw_quanta; return 0; } diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index ab8c5284d4be..495e5daff4b4 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2322,8 +2322,6 @@ void irdma_modify_qp_to_err(struct irdma_sc_qp *sc_qp) struct irdma_qp *qp = sc_qp->qp_uk.back_qp; struct ib_qp_attr attr; - if (qp->iwdev->rf->reset) - return; attr.qp_state = IB_QPS_ERR; if (rdma_protocol_roce(qp->ibqp.device, 1)) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 7251cd7a2147..95f590c10c05 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -558,7 +558,8 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) } irdma_qp_rem_ref(&iwqp->ibqp); - wait_for_completion(&iwqp->free_qp); + if (!iwdev->rf->reset) + wait_for_completion(&iwqp->free_qp); irdma_free_lsmm_rsrc(iwqp); irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); @@ -1105,6 +1106,7 @@ static int irdma_create_qp(struct ib_qp *ibqp, spin_lock_init(&iwqp->sc_qp.pfpdu.lock); iwqp->sig_all = init_attr->sq_sig_type == IB_SIGNAL_ALL_WR; rf->qp_table[qp_num] = iwqp; + init_completion(&iwqp->free_qp); if (udata) { /* GEN_1 legacy support with libi40iw does not have expanded uresp struct */ @@ -1129,7 +1131,6 @@ static int irdma_create_qp(struct ib_qp *ibqp, } } - init_completion(&iwqp->free_qp); return 0; error: @@ -1462,8 +1463,6 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr, ctx_info->remote_atomics_en = true; } - wait_event(iwqp->mod_qp_waitq, !atomic_read(&iwqp->hw_mod_qp_pend)); - ibdev_dbg(&iwdev->ibdev, "VERBS: caller: %pS qp_id=%d to_ibqpstate=%d ibqpstate=%d irdma_qpstate=%d attr_mask=0x%x\n", __builtin_return_address(0), ibqp->qp_num, attr->qp_state, @@ -1540,6 +1539,7 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr, case IB_QPS_ERR: case IB_QPS_RESET: if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) { + iwqp->ibqp_state = attr->qp_state; spin_unlock_irqrestore(&iwqp->lock, flags); if (udata && udata->inlen) { if (ib_copy_from_udata(&ureq, udata, @@ -1745,6 +1745,7 @@ int irdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, case IB_QPS_ERR: case IB_QPS_RESET: if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) { + iwqp->ibqp_state = attr->qp_state; spin_unlock_irqrestore(&iwqp->lock, flags); if (udata && udata->inlen) { if (ib_copy_from_udata(&ureq, udata, @@ -3723,6 +3724,7 @@ static int irdma_rereg_mr_trans(struct irdma_mr *iwmr, u64 start, u64 len, err: ib_umem_release(region); + iwmr->region = NULL; return err; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 5dac64be61bb..94d514169642 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1211,7 +1211,7 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, */ if (dev_use_swiotlb(dev, size, dir) && iova_unaligned(iovad, phys, size)) { - if (attrs & DMA_ATTR_MMIO) + if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) return DMA_MAPPING_ERROR; phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs); @@ -1223,7 +1223,8 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, arch_sync_dma_for_device(phys, size, dir); iova = __iommu_dma_map(dev, phys, size, prot, dma_mask); - if (iova == DMA_MAPPING_ERROR && !(attrs & DMA_ATTR_MMIO)) + if (iova == DMA_MAPPING_ERROR && + !(attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))) swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); return iova; } @@ -1233,7 +1234,7 @@ void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle, { phys_addr_t phys; - if (attrs & DMA_ATTR_MMIO) { + if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) { __iommu_dma_unmap(dev, dma_handle, size); return; } @@ -1945,9 +1946,21 @@ int dma_iova_link(struct device *dev, struct dma_iova_state *state, if (WARN_ON_ONCE(iova_start_pad && offset > 0)) return -EIO; + /* + * DMA_IOVA_USE_SWIOTLB is set on state after some entry + * took SWIOTLB path, which we were supposed to prevent + * for DMA_ATTR_REQUIRE_COHERENT attribute. + */ + if (WARN_ON_ONCE((state->__size & DMA_IOVA_USE_SWIOTLB) && + (attrs & DMA_ATTR_REQUIRE_COHERENT))) + return -EOPNOTSUPP; + + if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT)) + return -EOPNOTSUPP; + if (dev_use_swiotlb(dev, size, dir) && iova_unaligned(iovad, phys, size)) { - if (attrs & DMA_ATTR_MMIO) + if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) return -EPERM; return iommu_dma_iova_link_swiotlb(dev, state, phys, offset, diff --git a/drivers/iommu/generic_pt/fmt/amdv1.h b/drivers/iommu/generic_pt/fmt/amdv1.h index 3b2c41d9654d..8d11b08291d7 100644 --- a/drivers/iommu/generic_pt/fmt/amdv1.h +++ b/drivers/iommu/generic_pt/fmt/amdv1.h @@ -191,7 +191,7 @@ static inline enum pt_entry_type amdv1pt_load_entry_raw(struct pt_state *pts) } #define pt_load_entry_raw amdv1pt_load_entry_raw -static inline void +static __always_inline void amdv1pt_install_leaf_entry(struct pt_state *pts, pt_oaddr_t oa, unsigned int oasz_lg2, const struct pt_write_attrs *attrs) diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h index 3e33fe64feab..7e7a6e7abdee 100644 --- a/drivers/iommu/generic_pt/iommu_pt.h +++ b/drivers/iommu/generic_pt/iommu_pt.h @@ -1057,7 +1057,7 @@ size_t DOMAIN_NS(unmap_pages)(struct iommu_domain *domain, unsigned long iova, pt_walk_range(&range, __unmap_range, &unmap); - gather_range_pages(iotlb_gather, iommu_table, iova, len, + gather_range_pages(iotlb_gather, iommu_table, iova, unmap.unmapped, &unmap.free_list); return unmap.unmapped; diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index 83f31ea657b7..181320528a47 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -306,6 +306,8 @@ static int mpm_pd_power_off(struct generic_pm_domain *genpd) if (ret < 0) return ret; + mbox_client_txdone(priv->mbox_chan, 0); + return 0; } @@ -434,6 +436,7 @@ static int qcom_mpm_probe(struct platform_device *pdev, struct device_node *pare } priv->mbox_client.dev = dev; + priv->mbox_client.knows_txdone = true; priv->mbox_chan = mbox_request_channel(&priv->mbox_client, 0); if (IS_ERR(priv->mbox_chan)) { ret = PTR_ERR(priv->mbox_chan); diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c index da2bc43a0e12..03e93b061edd 100644 --- a/drivers/irqchip/irq-renesas-rzv2h.c +++ b/drivers/irqchip/irq-renesas-rzv2h.c @@ -621,7 +621,7 @@ static int rzv2h_icu_probe_common(struct platform_device *pdev, struct device_no return 0; pm_put: - pm_runtime_put(&pdev->dev); + pm_runtime_put_sync(&pdev->dev); return ret; } diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c index aa4dd7e7cf5a..8e25f970fd12 100644 --- a/drivers/media/i2c/ccs/ccs-core.c +++ b/drivers/media/i2c/ccs/ccs-core.c @@ -3080,8 +3080,6 @@ static int ccs_init_state(struct v4l2_subdev *sd, struct v4l2_rect *crop = v4l2_subdev_state_get_crop(sd_state, pad); - guard(mutex)(&sensor->mutex); - ccs_get_native_size(ssd, crop); fmt->width = crop->width; diff --git a/drivers/media/mc/mc-request.c b/drivers/media/mc/mc-request.c index c7c7d4a86c6b..13e77648807c 100644 --- a/drivers/media/mc/mc-request.c +++ b/drivers/media/mc/mc-request.c @@ -192,6 +192,8 @@ static long media_request_ioctl_reinit(struct media_request *req) struct media_device *mdev = req->mdev; unsigned long flags; + mutex_lock(&mdev->req_queue_mutex); + spin_lock_irqsave(&req->lock, flags); if (req->state != MEDIA_REQUEST_STATE_IDLE && req->state != MEDIA_REQUEST_STATE_COMPLETE) { @@ -199,6 +201,7 @@ static long media_request_ioctl_reinit(struct media_request *req) "request: %s not in idle or complete state, cannot reinit\n", req->debug_str); spin_unlock_irqrestore(&req->lock, flags); + mutex_unlock(&mdev->req_queue_mutex); return -EBUSY; } if (req->access_count) { @@ -206,6 +209,7 @@ static long media_request_ioctl_reinit(struct media_request *req) "request: %s is being accessed, cannot reinit\n", req->debug_str); spin_unlock_irqrestore(&req->lock, flags); + mutex_unlock(&mdev->req_queue_mutex); return -EBUSY; } req->state = MEDIA_REQUEST_STATE_CLEANING; @@ -216,6 +220,7 @@ static long media_request_ioctl_reinit(struct media_request *req) spin_lock_irqsave(&req->lock, flags); req->state = MEDIA_REQUEST_STATE_IDLE; spin_unlock_irqrestore(&req->lock, flags); + mutex_unlock(&mdev->req_queue_mutex); return 0; } diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c index 28267ee30190..3119f3bc9f98 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c @@ -500,11 +500,15 @@ void rkvdec_hevc_run_preamble(struct rkvdec_ctx *ctx, ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, V4L2_CID_STATELESS_HEVC_EXT_SPS_ST_RPS); run->ext_sps_st_rps = ctrl ? ctrl->p_cur.p : NULL; + } else { + run->ext_sps_st_rps = NULL; } if (ctx->has_sps_lt_rps) { ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, V4L2_CID_STATELESS_HEVC_EXT_SPS_LT_RPS); run->ext_sps_lt_rps = ctrl ? ctrl->p_cur.p : NULL; + } else { + run->ext_sps_lt_rps = NULL; } rkvdec_run_preamble(ctx, &run->base); diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c index 97f1efde2e47..fb4f849d7366 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c @@ -130,7 +130,7 @@ struct rkvdec_h264_ctx { struct vdpu383_regs_h26x regs; }; -static void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_dpb_entry *dpb) +static noinline_for_stack void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_dpb_entry *dpb) { pps->top_field_order_cnt0 = dpb[0].top_field_order_cnt; pps->bot_field_order_cnt0 = dpb[0].bottom_field_order_cnt; @@ -166,6 +166,31 @@ static void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_d pps->bot_field_order_cnt15 = dpb[15].bottom_field_order_cnt; } +static noinline_for_stack void set_dec_params(struct rkvdec_pps *pps, const struct v4l2_ctrl_h264_decode_params *dec_params) +{ + const struct v4l2_h264_dpb_entry *dpb = dec_params->dpb; + + for (int i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) { + if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) + pps->is_longterm |= (1 << i); + pps->ref_field_flags |= + (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD)) << i; + pps->ref_colmv_use_flag |= + (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) << i; + pps->ref_topfield_used |= + (!!(dpb[i].fields & V4L2_H264_TOP_FIELD_REF)) << i; + pps->ref_botfield_used |= + (!!(dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)) << i; + } + pps->pic_field_flag = + !!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC); + pps->pic_associated_flag = + !!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD); + + pps->cur_top_field = dec_params->top_field_order_cnt; + pps->cur_bot_field = dec_params->bottom_field_order_cnt; +} + static void assemble_hw_pps(struct rkvdec_ctx *ctx, struct rkvdec_h264_run *run) { @@ -177,7 +202,6 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, struct rkvdec_h264_priv_tbl *priv_tbl = h264_ctx->priv_tbl.cpu; struct rkvdec_sps_pps *hw_ps; u32 pic_width, pic_height; - u32 i; /* * HW read the SPS/PPS information from PPS packet index by PPS id. @@ -261,28 +285,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, !!(pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT); set_field_order_cnt(&hw_ps->pps, dpb); + set_dec_params(&hw_ps->pps, dec_params); - for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) { - if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM) - hw_ps->pps.is_longterm |= (1 << i); - - hw_ps->pps.ref_field_flags |= - (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD)) << i; - hw_ps->pps.ref_colmv_use_flag |= - (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) << i; - hw_ps->pps.ref_topfield_used |= - (!!(dpb[i].fields & V4L2_H264_TOP_FIELD_REF)) << i; - hw_ps->pps.ref_botfield_used |= - (!!(dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)) << i; - } - - hw_ps->pps.pic_field_flag = - !!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC); - hw_ps->pps.pic_associated_flag = - !!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD); - - hw_ps->pps.cur_top_field = dec_params->top_field_order_cnt; - hw_ps->pps.cur_bot_field = dec_params->bottom_field_order_cnt; } static void rkvdec_write_regs(struct rkvdec_ctx *ctx) diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c index e4cdd2122873..2751f5396ee8 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c @@ -893,7 +893,8 @@ out_update_last: update_ctx_last_info(vp9_ctx); } -static void rkvdec_init_v4l2_vp9_count_tbl(struct rkvdec_ctx *ctx) +static noinline_for_stack void +rkvdec_init_v4l2_vp9_count_tbl(struct rkvdec_ctx *ctx) { struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv; struct rkvdec_vp9_intra_frame_symbol_counts *intra_cnts = vp9_ctx->count_tbl.cpu; diff --git a/drivers/media/platform/synopsys/Kconfig b/drivers/media/platform/synopsys/Kconfig index e798ec00b189..bf2ac092fbb3 100644 --- a/drivers/media/platform/synopsys/Kconfig +++ b/drivers/media/platform/synopsys/Kconfig @@ -7,6 +7,7 @@ config VIDEO_DW_MIPI_CSI2RX depends on VIDEO_DEV depends on V4L_PLATFORM_DRIVERS depends on PM && COMMON_CLK + select GENERIC_PHY_MIPI_DPHY select MEDIA_CONTROLLER select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API diff --git a/drivers/media/platform/synopsys/dw-mipi-csi2rx.c b/drivers/media/platform/synopsys/dw-mipi-csi2rx.c index 170346ae1a59..4d96171a650b 100644 --- a/drivers/media/platform/synopsys/dw-mipi-csi2rx.c +++ b/drivers/media/platform/synopsys/dw-mipi-csi2rx.c @@ -301,7 +301,7 @@ dw_mipi_csi2rx_enum_mbus_code(struct v4l2_subdev *sd, return 0; case DW_MIPI_CSI2RX_PAD_SINK: - if (code->index > csi2->formats_num) + if (code->index >= csi2->formats_num) return -EINVAL; code->code = csi2->formats[code->index].code; diff --git a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c index 6f8e43b7f157..fa4224de4b99 100644 --- a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c +++ b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c @@ -343,7 +343,7 @@ const struct hantro_variant imx8mq_vpu_variant = { .num_regs = ARRAY_SIZE(imx8mq_reg_names) }; -static const struct of_device_id imx8mq_vpu_shared_resources[] __initconst = { +static const struct of_device_id imx8mq_vpu_shared_resources[] = { { .compatible = "nxp,imx8mq-vpu-g1", }, { .compatible = "nxp,imx8mq-vpu-g2", }, { /* sentinel */ } diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 40c76c051da2..f6c8e3223796 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -1751,7 +1751,8 @@ static void uvc_video_complete(struct urb *urb) /* * Free transfer buffers. */ -static void uvc_free_urb_buffers(struct uvc_streaming *stream) +static void uvc_free_urb_buffers(struct uvc_streaming *stream, + unsigned int size) { struct usb_device *udev = stream->dev->udev; struct uvc_urb *uvc_urb; @@ -1760,7 +1761,7 @@ static void uvc_free_urb_buffers(struct uvc_streaming *stream) if (!uvc_urb->buffer) continue; - usb_free_noncoherent(udev, stream->urb_size, uvc_urb->buffer, + usb_free_noncoherent(udev, size, uvc_urb->buffer, uvc_stream_dir(stream), uvc_urb->sgt); uvc_urb->buffer = NULL; uvc_urb->sgt = NULL; @@ -1820,7 +1821,7 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream, if (!uvc_alloc_urb_buffer(stream, uvc_urb, urb_size, gfp_flags)) { - uvc_free_urb_buffers(stream); + uvc_free_urb_buffers(stream, urb_size); break; } @@ -1868,7 +1869,7 @@ static void uvc_video_stop_transfer(struct uvc_streaming *stream, } if (free_buffers) - uvc_free_urb_buffers(stream); + uvc_free_urb_buffers(stream, stream->urb_size); } /* diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 37d33d4a363d..a2b650f4ec3c 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -3082,13 +3082,14 @@ static long __video_do_ioctl(struct file *file, } /* - * We need to serialize streamon/off with queueing new requests. + * We need to serialize streamon/off/reqbufs with queueing new requests. * These ioctls may trigger the cancellation of a streaming * operation, and that should not be mixed with queueing a new * request at the same time. */ if (v4l2_device_supports_requests(vfd->v4l2_dev) && - (cmd == VIDIOC_STREAMON || cmd == VIDIOC_STREAMOFF)) { + (cmd == VIDIOC_STREAMON || cmd == VIDIOC_STREAMOFF || + cmd == VIDIOC_REQBUFS)) { req_queue_lock = &vfd->v4l2_dev->mdev->req_queue_mutex; if (mutex_lock_interruptible(req_queue_lock)) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 33f414d03ab9..a5484d11553d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5326,7 +5326,7 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)) continue; - if (bond_is_last_slave(bond, slave)) { + if (i + 1 == slaves_count) { skb2 = skb; skb_used = true; } else { diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 0498198a4696..766d455950f5 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -601,7 +601,9 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* We need synchronization with dev->stop() */ ASSERT_RTNL(); - can_ctrlmode_changelink(dev, data, extack); + err = can_ctrlmode_changelink(dev, data, extack); + if (err) + return err; if (data[IFLA_CAN_BITTIMING]) { struct can_bittiming bt; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index bb7782582f40..0d0190ae094a 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1225,7 +1225,11 @@ static int mcp251x_open(struct net_device *net) } mutex_lock(&priv->mcp_lock); - mcp251x_power_enable(priv->transceiver, 1); + ret = mcp251x_power_enable(priv->transceiver, 1); + if (ret) { + dev_err(&spi->dev, "failed to enable transceiver power: %pe\n", ERR_PTR(ret)); + goto out_close_candev; + } priv->force_quit = 0; priv->tx_skb = NULL; @@ -1272,6 +1276,7 @@ out_free_irq: mcp251x_hw_sleep(spi); out_close: mcp251x_power_enable(priv->transceiver, 0); +out_close_candev: close_candev(net); mutex_unlock(&priv->mcp_lock); if (release_irq) @@ -1516,11 +1521,25 @@ static int __maybe_unused mcp251x_can_resume(struct device *dev) { struct spi_device *spi = to_spi_device(dev); struct mcp251x_priv *priv = spi_get_drvdata(spi); + int ret = 0; - if (priv->after_suspend & AFTER_SUSPEND_POWER) - mcp251x_power_enable(priv->power, 1); - if (priv->after_suspend & AFTER_SUSPEND_UP) - mcp251x_power_enable(priv->transceiver, 1); + if (priv->after_suspend & AFTER_SUSPEND_POWER) { + ret = mcp251x_power_enable(priv->power, 1); + if (ret) { + dev_err(dev, "failed to restore power: %pe\n", ERR_PTR(ret)); + return ret; + } + } + + if (priv->after_suspend & AFTER_SUSPEND_UP) { + ret = mcp251x_power_enable(priv->transceiver, 1); + if (ret) { + dev_err(dev, "failed to restore transceiver power: %pe\n", ERR_PTR(ret)); + if (priv->after_suspend & AFTER_SUSPEND_POWER) + mcp251x_power_enable(priv->power, 0); + return ret; + } + } if (priv->after_suspend & (AFTER_SUSPEND_POWER | AFTER_SUSPEND_UP)) queue_work(priv->wq, &priv->restart_work); diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 56cf9a926a83..95ba99b89428 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -794,18 +794,34 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q, static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->qdma->eth; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0]; while (q->queued) { struct airoha_queue_entry *e = &q->entry[q->tail]; + struct airoha_qdma_desc *desc = &q->desc[q->tail]; struct page *page = virt_to_head_page(e->buf); dma_sync_single_for_cpu(eth->dev, e->dma_addr, e->dma_len, page_pool_get_dma_dir(q->page_pool)); page_pool_put_full_page(q->page_pool, page, false); + /* Reset DMA descriptor */ + WRITE_ONCE(desc->ctrl, 0); + WRITE_ONCE(desc->addr, 0); + WRITE_ONCE(desc->data, 0); + WRITE_ONCE(desc->msg0, 0); + WRITE_ONCE(desc->msg1, 0); + WRITE_ONCE(desc->msg2, 0); + WRITE_ONCE(desc->msg3, 0); + q->tail = (q->tail + 1) % q->ndesc; q->queued--; } + + q->head = q->tail; + airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, + FIELD_PREP(RX_RING_DMA_IDX_MASK, q->tail)); } static int airoha_qdma_init_rx(struct airoha_qdma *qdma) @@ -2946,6 +2962,8 @@ static int airoha_register_gdm_devices(struct airoha_eth *eth) return err; } + set_bit(DEV_STATE_REGISTERED, ð->state); + return 0; } diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 20e602d61e61..a97903569335 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -88,6 +88,7 @@ enum { enum { DEV_STATE_INITIALIZED, + DEV_STATE_REGISTERED, }; enum { diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 42dbe8f93231..c2c32b6833df 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -227,7 +227,9 @@ static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr, if (!dev) return -ENODEV; + rcu_read_lock(); err = dev_fill_forward_path(dev, addr, &stack); + rcu_read_unlock(); if (err) return err; @@ -1366,6 +1368,13 @@ int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data) struct airoha_eth *eth = ppe->eth; int err = 0; + /* Netfilter flowtable can try to offload flower rules while not all + * the net_devices are registered or initialized. Delay offloading + * until all net_devices are registered in the system. + */ + if (!test_bit(DEV_STATE_REGISTERED, ð->state)) + return -EBUSY; + mutex_lock(&flow_offload_mutex); if (!eth->npu) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index cd7dddeb91dd..9787c1857e13 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -25,7 +25,7 @@ config B44 select SSB select MII select PHYLIB - select FIXED_PHY if BCM47XX + select FIXED_PHY help If you have a network (Ethernet) controller of this type, say Y or M here. diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index aa6d8606849f..972474893a6b 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -1152,12 +1152,6 @@ void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en) } } -static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv) -{ - if (priv->wol_irq > 0) - free_irq(priv->wol_irq, priv); -} - static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en) { u32 reg, phy_lpi_overwrite; @@ -1255,7 +1249,7 @@ static int bcmasp_probe(struct platform_device *pdev) if (priv->irq <= 0) return -EINVAL; - priv->clk = devm_clk_get_optional_enabled(dev, "sw_asp"); + priv->clk = devm_clk_get_optional(dev, "sw_asp"); if (IS_ERR(priv->clk)) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to request clock\n"); @@ -1283,6 +1277,10 @@ static int bcmasp_probe(struct platform_device *pdev) bcmasp_set_pdata(priv, pdata); + ret = clk_prepare_enable(priv->clk); + if (ret) + return dev_err_probe(dev, ret, "failed to start clock\n"); + /* Enable all clocks to ensure successful probing */ bcmasp_core_clock_set(priv, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE, 0); @@ -1294,8 +1292,10 @@ static int bcmasp_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, priv->irq, bcmasp_isr, 0, pdev->name, priv); - if (ret) - return dev_err_probe(dev, ret, "failed to request ASP interrupt: %d", ret); + if (ret) { + dev_err(dev, "Failed to request ASP interrupt: %d", ret); + goto err_clock_disable; + } /* Register mdio child nodes */ of_platform_populate(dev->of_node, bcmasp_mdio_of_match, NULL, dev); @@ -1307,13 +1307,17 @@ static int bcmasp_probe(struct platform_device *pdev) priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters, sizeof(*priv->mda_filters), GFP_KERNEL); - if (!priv->mda_filters) - return -ENOMEM; + if (!priv->mda_filters) { + ret = -ENOMEM; + goto err_clock_disable; + } priv->net_filters = devm_kcalloc(dev, priv->num_net_filters, sizeof(*priv->net_filters), GFP_KERNEL); - if (!priv->net_filters) - return -ENOMEM; + if (!priv->net_filters) { + ret = -ENOMEM; + goto err_clock_disable; + } bcmasp_core_init_filters(priv); @@ -1322,7 +1326,8 @@ static int bcmasp_probe(struct platform_device *pdev) ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports"); if (!ports_node) { dev_warn(dev, "No ports found\n"); - return -EINVAL; + ret = -EINVAL; + goto err_clock_disable; } i = 0; @@ -1344,8 +1349,6 @@ static int bcmasp_probe(struct platform_device *pdev) */ bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE); - clk_disable_unprepare(priv->clk); - /* Now do the registration of the network ports which will take care * of managing the clock properly. */ @@ -1358,13 +1361,16 @@ static int bcmasp_probe(struct platform_device *pdev) count++; } + clk_disable_unprepare(priv->clk); + dev_info(dev, "Initialized %d port(s)\n", count); return ret; err_cleanup: - bcmasp_wol_irq_destroy(priv); bcmasp_remove_intfs(priv); +err_clock_disable: + clk_disable_unprepare(priv->clk); return ret; } @@ -1376,7 +1382,6 @@ static void bcmasp_remove(struct platform_device *pdev) if (!priv) return; - bcmasp_wol_irq_destroy(priv); bcmasp_remove_intfs(priv); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0751c0e4581a..3f775196ef81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8045,6 +8045,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp) ulp_msix = bnxt_get_avail_msix(bp, bp->ulp_num_msix_want); if (!ulp_msix) bnxt_set_ulp_stat_ctxs(bp, 0); + else + bnxt_set_dflt_ulp_stat_ctxs(bp); if (ulp_msix > bp->ulp_num_msix_want) ulp_msix = bp->ulp_num_msix_want; @@ -8671,7 +8673,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp) struct hwrm_func_backing_store_qcaps_v2_output *resp; struct hwrm_func_backing_store_qcaps_v2_input *req; struct bnxt_ctx_mem_info *ctx = bp->ctx; - u16 type; + u16 type, next_type = 0; int rc; rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2); @@ -8687,7 +8689,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp) resp = hwrm_req_hold(bp, req); - for (type = 0; type < BNXT_CTX_V2_MAX; ) { + for (type = 0; type < BNXT_CTX_V2_MAX; type = next_type) { struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type]; u8 init_val, init_off, i; u32 max_entries; @@ -8700,7 +8702,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp) if (rc) goto ctx_done; flags = le32_to_cpu(resp->flags); - type = le16_to_cpu(resp->next_valid_type); + next_type = le16_to_cpu(resp->next_valid_type); if (!(flags & BNXT_CTX_MEM_TYPE_VALID)) { bnxt_free_one_ctx_mem(bp, ctxm, true); continue; @@ -8715,7 +8717,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp) else continue; } - ctxm->type = le16_to_cpu(resp->type); + ctxm->type = type; ctxm->entry_size = entry_size; ctxm->flags = flags; ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map); @@ -12992,6 +12994,21 @@ static int bnxt_tx_nr_rings_per_tc(struct bnxt *bp) return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings; } +static void bnxt_set_xdp_tx_rings(struct bnxt *bp) +{ + bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc; + bp->tx_nr_rings += bp->tx_nr_rings_xdp; +} + +static void bnxt_adj_tx_rings(struct bnxt *bp) +{ + /* Make adjustments if reserved TX rings are less than requested */ + bp->tx_nr_rings -= bp->tx_nr_rings_xdp; + bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp); + if (bp->tx_nr_rings_xdp) + bnxt_set_xdp_tx_rings(bp); +} + static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { int rc = 0; @@ -13009,13 +13026,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (rc) return rc; - /* Make adjustments if reserved TX rings are less than requested */ - bp->tx_nr_rings -= bp->tx_nr_rings_xdp; - bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp); - if (bp->tx_nr_rings_xdp) { - bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc; - bp->tx_nr_rings += bp->tx_nr_rings_xdp; - } + bnxt_adj_tx_rings(bp); rc = bnxt_alloc_mem(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); @@ -15436,11 +15447,19 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) return 0; } +void bnxt_set_cp_rings(struct bnxt *bp, bool sh) +{ + int tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings); + + bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) : + tx_cp + bp->rx_nr_rings; +} + int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) { struct bnxt *bp = netdev_priv(dev); bool sh = false; - int rc, tx_cp; + int rc; if (tc > bp->max_tc) { netdev_err(dev, "Too many traffic classes requested: %d. Max supported is %d.\n", @@ -15473,9 +15492,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) bp->num_tc = 0; } bp->tx_nr_rings += bp->tx_nr_rings_xdp; - tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings); - bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) : - tx_cp + bp->rx_nr_rings; + bnxt_set_cp_rings(bp, sh); if (netif_running(bp->dev)) return bnxt_open_nic(bp, true, false); @@ -16525,6 +16542,19 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp) bp->tx_nr_rings = bnxt_tx_nr_rings(bp); } +static void bnxt_adj_dflt_rings(struct bnxt *bp, bool sh) +{ + if (sh) + bnxt_trim_dflt_sh_rings(bp); + else + bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings; + bp->tx_nr_rings = bnxt_tx_nr_rings(bp); + if (sh && READ_ONCE(bp->xdp_prog)) { + bnxt_set_xdp_tx_rings(bp); + bnxt_set_cp_rings(bp, true); + } +} + static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) { int dflt_rings, max_rx_rings, max_tx_rings, rc; @@ -16550,11 +16580,8 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) return rc; bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings); bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings); - if (sh) - bnxt_trim_dflt_sh_rings(bp); - else - bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings; - bp->tx_nr_rings = bnxt_tx_nr_rings(bp); + + bnxt_adj_dflt_rings(bp, sh); avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings; if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) { @@ -16567,16 +16594,17 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) rc = __bnxt_reserve_rings(bp); if (rc && rc != -ENODEV) netdev_warn(bp->dev, "Unable to reserve tx rings\n"); - bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp); + + bnxt_adj_tx_rings(bp); if (sh) - bnxt_trim_dflt_sh_rings(bp); + bnxt_adj_dflt_rings(bp, true); /* Rings may have been trimmed, re-reserve the trimmed rings. */ if (bnxt_need_reserve_rings(bp)) { rc = __bnxt_reserve_rings(bp); if (rc && rc != -ENODEV) netdev_warn(bp->dev, "2nd rings reservation failed.\n"); - bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp); + bnxt_adj_tx_rings(bp); } if (BNXT_CHIP_TYPE_NITRO_A0(bp)) { bp->rx_nr_rings++; @@ -16610,7 +16638,7 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp) if (rc) goto init_dflt_ring_err; - bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp); + bnxt_adj_tx_rings(bp); bnxt_set_dflt_rfs(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a97d651130df..4bc7f7aeaab3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2985,6 +2985,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, int tx_xdp); int bnxt_fw_init_one(struct bnxt *bp); bool bnxt_hwrm_reset_permitted(struct bnxt *bp); +void bnxt_set_cp_rings(struct bnxt *bp, bool sh); int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp, struct bnxt_ntuple_filter *fltr, u32 idx); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 28d0ece2e7b1..0407aa1b3190 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -945,7 +945,6 @@ static int bnxt_set_channels(struct net_device *dev, bool sh = false; int tx_xdp = 0; int rc = 0; - int tx_cp; if (channel->other_count) return -EINVAL; @@ -1013,9 +1012,7 @@ static int bnxt_set_channels(struct net_device *dev, if (tcs > 1) bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs + tx_xdp; - tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings); - bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) : - tx_cp + bp->rx_nr_rings; + bnxt_set_cp_rings(bp, sh); /* After changing number of rx channels, update NTUPLE feature. */ netdev_update_features(dev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 85cbeb35681c..bebe37e139c9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -384,7 +384,7 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) { struct net_device *dev = bp->dev; - int tx_xdp = 0, tx_cp, rc, tc; + int tx_xdp = 0, rc, tc; struct bpf_prog *old; netdev_assert_locked(dev); @@ -431,8 +431,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) } bp->tx_nr_rings_xdp = tx_xdp; bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp; - tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings); - bp->cp_nr_rings = max_t(int, tx_cp, bp->rx_nr_rings); + bnxt_set_cp_rings(bp, true); bnxt_set_tpa_flags(bp); bnxt_set_ring_params(bp); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 21a5dd342724..73a4b569b03e 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12299,7 +12299,7 @@ static int tg3_get_link_ksettings(struct net_device *dev, ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, advertising); - if (netif_running(dev) && tp->link_up) { + if (netif_running(dev) && netif_carrier_ok(dev)) { cmd->base.speed = tp->link_config.active_speed; cmd->base.duplex = tp->link_config.active_duplex; ethtool_convert_legacy_u32_to_link_mode( diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c16ac9c76aa3..99e7d5cf3786 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1071,7 +1071,7 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budge } if (tx_skb->skb) { - napi_consume_skb(tx_skb->skb, budget); + dev_consume_skb_any(tx_skb->skb); tx_skb->skb = NULL; } } @@ -3224,7 +3224,7 @@ static void gem_get_ethtool_stats(struct net_device *dev, spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); memcpy(data, &bp->ethtool_stats, sizeof(u64) - * (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES)); + * (GEM_STATS_LEN + QUEUE_STATS_LEN * bp->num_queues)); spin_unlock_irq(&bp->stats_lock); } @@ -5776,9 +5776,9 @@ static int __maybe_unused macb_suspend(struct device *dev) struct macb_queue *queue; struct in_device *idev; unsigned long flags; + u32 tmp, ifa_local; unsigned int q; int err; - u32 tmp; if (!device_may_wakeup(&bp->dev->dev)) phy_exit(bp->phy); @@ -5787,14 +5787,21 @@ static int __maybe_unused macb_suspend(struct device *dev) return 0; if (bp->wol & MACB_WOL_ENABLED) { - /* Check for IP address in WOL ARP mode */ - idev = __in_dev_get_rcu(bp->dev); - if (idev) - ifa = rcu_dereference(idev->ifa_list); - if ((bp->wolopts & WAKE_ARP) && !ifa) { - netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); - return -EOPNOTSUPP; + if (bp->wolopts & WAKE_ARP) { + /* Check for IP address in WOL ARP mode */ + rcu_read_lock(); + idev = __in_dev_get_rcu(bp->dev); + if (idev) + ifa = rcu_dereference(idev->ifa_list); + if (!ifa) { + rcu_read_unlock(); + netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); + return -EOPNOTSUPP; + } + ifa_local = be32_to_cpu(ifa->ifa_local); + rcu_read_unlock(); } + spin_lock_irqsave(&bp->lock, flags); /* Disable Tx and Rx engines before disabling the queues, @@ -5833,8 +5840,9 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wolopts & WAKE_ARP) { tmp |= MACB_BIT(ARP); /* write IP address into register */ - tmp |= MACB_BFEXT(IP, be32_to_cpu(ifa->ifa_local)); + tmp |= MACB_BFEXT(IP, ifa_local); } + spin_unlock_irqrestore(&bp->lock, flags); /* Change interrupt handler and * Enable WoL IRQ on queue 0 @@ -5847,11 +5855,12 @@ static int __maybe_unused macb_suspend(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } + spin_lock_irqsave(&bp->lock, flags); queue_writel(bp->queues, IER, GEM_BIT(WOL)); gem_writel(bp, WOL, tmp); + spin_unlock_irqrestore(&bp->lock, flags); } else { err = devm_request_irq(dev, bp->queues[0].irq, macb_wol_interrupt, IRQF_SHARED, netdev->name, bp->queues); @@ -5859,13 +5868,13 @@ static int __maybe_unused macb_suspend(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } + spin_lock_irqsave(&bp->lock, flags); queue_writel(bp->queues, IER, MACB_BIT(WOL)); macb_writel(bp, WOL, tmp); + spin_unlock_irqrestore(&bp->lock, flags); } - spin_unlock_irqrestore(&bp->lock, flags); enable_irq_wake(bp->queues[0].irq); } @@ -5932,6 +5941,8 @@ static int __maybe_unused macb_resume(struct device *dev) queue_readl(bp->queues, ISR); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(bp->queues, ISR, -1); + spin_unlock_irqrestore(&bp->lock, flags); + /* Replace interrupt handler on queue 0 */ devm_free_irq(dev, bp->queues[0].irq, bp->queues); err = devm_request_irq(dev, bp->queues[0].irq, macb_interrupt, @@ -5940,10 +5951,8 @@ static int __maybe_unused macb_resume(struct device *dev) dev_err(dev, "Unable to request IRQ %d (error %d)\n", bp->queues[0].irq, err); - spin_unlock_irqrestore(&bp->lock, flags); return err; } - spin_unlock_irqrestore(&bp->lock, flags); disable_irq_wake(bp->queues[0].irq); diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index fc4f5aee6ab3..b79dec17e6b0 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -96,10 +96,10 @@ static int macb_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; err_plat_dev_register: - clk_unregister(plat_data.hclk); + clk_unregister_fixed_rate(plat_data.hclk); err_hclk_register: - clk_unregister(plat_data.pclk); + clk_unregister_fixed_rate(plat_data.pclk); err_pclk_register: return err; @@ -109,10 +109,12 @@ static void macb_remove(struct pci_dev *pdev) { struct platform_device *plat_dev = pci_get_drvdata(pdev); struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev); + struct clk *pclk = plat_data->pclk; + struct clk *hclk = plat_data->hclk; - clk_unregister(plat_data->pclk); - clk_unregister(plat_data->hclk); platform_device_unregister(plat_dev); + clk_unregister_fixed_rate(pclk); + clk_unregister_fixed_rate(hclk); } static const struct pci_device_id dev_id_table[] = { diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 1e91e79c8134..6d2fe5c2f390 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -977,19 +977,19 @@ static int ftgmac100_alloc_rings(struct ftgmac100 *priv) priv->tx_skbs = kcalloc(MAX_TX_QUEUE_ENTRIES, sizeof(void *), GFP_KERNEL); if (!priv->tx_skbs) - return -ENOMEM; + goto err_free_rx_skbs; /* Allocate descriptors */ priv->rxdes = dma_alloc_coherent(priv->dev, MAX_RX_QUEUE_ENTRIES * sizeof(struct ftgmac100_rxdes), &priv->rxdes_dma, GFP_KERNEL); if (!priv->rxdes) - return -ENOMEM; + goto err_free_tx_skbs; priv->txdes = dma_alloc_coherent(priv->dev, MAX_TX_QUEUE_ENTRIES * sizeof(struct ftgmac100_txdes), &priv->txdes_dma, GFP_KERNEL); if (!priv->txdes) - return -ENOMEM; + goto err_free_rxdes; /* Allocate scratch packet buffer */ priv->rx_scratch = dma_alloc_coherent(priv->dev, @@ -997,9 +997,29 @@ static int ftgmac100_alloc_rings(struct ftgmac100 *priv) &priv->rx_scratch_dma, GFP_KERNEL); if (!priv->rx_scratch) - return -ENOMEM; + goto err_free_txdes; return 0; + +err_free_txdes: + dma_free_coherent(priv->dev, + MAX_TX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_txdes), + priv->txdes, priv->txdes_dma); + priv->txdes = NULL; +err_free_rxdes: + dma_free_coherent(priv->dev, + MAX_RX_QUEUE_ENTRIES * + sizeof(struct ftgmac100_rxdes), + priv->rxdes, priv->rxdes_dma); + priv->rxdes = NULL; +err_free_tx_skbs: + kfree(priv->tx_skbs); + priv->tx_skbs = NULL; +err_free_rx_skbs: + kfree(priv->rx_skbs); + priv->rx_skbs = NULL; + return -ENOMEM; } static void ftgmac100_init_rings(struct ftgmac100 *priv) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index a146ceaf2ed6..aa8a87124b10 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2578,6 +2578,7 @@ EXPORT_SYMBOL_GPL(enetc_free_si_resources); static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) { + struct enetc_si *si = container_of(hw, struct enetc_si, hw); int idx = tx_ring->index; u32 tbmr; @@ -2591,10 +2592,20 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) enetc_txbdr_wr(hw, idx, ENETC_TBLENR, ENETC_RTBLENR_LEN(tx_ring->bd_count)); - /* clearing PI/CI registers for Tx not supported, adjust sw indexes */ + /* For ENETC v1, clearing PI/CI registers for Tx not supported, + * adjust sw indexes + */ tx_ring->next_to_use = enetc_txbdr_rd(hw, idx, ENETC_TBPIR); tx_ring->next_to_clean = enetc_txbdr_rd(hw, idx, ENETC_TBCIR); + if (tx_ring->next_to_use != tx_ring->next_to_clean && + !is_enetc_rev1(si)) { + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + enetc_txbdr_wr(hw, idx, ENETC_TBPIR, 0); + enetc_txbdr_wr(hw, idx, ENETC_TBCIR, 0); + } + /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h index 3ed0f7a02767..719c88ceb801 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h @@ -134,6 +134,12 @@ /* Port operational register */ #define ENETC4_POR 0x4100 +#define POR_TXDIS BIT(0) +#define POR_RXDIS BIT(1) + +/* Port status register */ +#define ENETC4_PSR 0x4104 +#define PSR_RX_BUSY BIT(1) /* Port traffic class a transmit maximum SDU register */ #define ENETC4_PTCTMSDUR(a) ((a) * 0x20 + 0x4208) @@ -173,6 +179,11 @@ /* Port internal MDIO base address, use to access PCS */ #define ENETC4_PM_IMDIO_BASE 0x5030 +/* Port MAC 0/1 Interrupt Event Register */ +#define ENETC4_PM_IEVENT(mac) (0x5040 + (mac) * 0x400) +#define PM_IEVENT_TX_EMPTY BIT(5) +#define PM_IEVENT_RX_EMPTY BIT(6) + /* Port MAC 0/1 Pause Quanta Register */ #define ENETC4_PM_PAUSE_QUANTA(mac) (0x5054 + (mac) * 0x400) diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 689b9f13c5eb..56899f2254aa 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -444,20 +444,11 @@ static void enetc4_set_trx_frame_size(struct enetc_pf *pf) enetc4_pf_reset_tc_msdu(&si->hw); } -static void enetc4_enable_trx(struct enetc_pf *pf) -{ - struct enetc_hw *hw = &pf->si->hw; - - /* Enable port transmit/receive */ - enetc_port_wr(hw, ENETC4_POR, 0); -} - static void enetc4_configure_port(struct enetc_pf *pf) { enetc4_configure_port_si(pf); enetc4_set_trx_frame_size(pf); enetc_set_default_rss_key(pf); - enetc4_enable_trx(pf); } static int enetc4_init_ntmp_user(struct enetc_si *si) @@ -801,15 +792,112 @@ static void enetc4_set_tx_pause(struct enetc_pf *pf, int num_rxbdr, bool tx_paus enetc_port_wr(hw, ENETC4_PPAUOFFTR, pause_off_thresh); } -static void enetc4_enable_mac(struct enetc_pf *pf, bool en) +static void enetc4_mac_wait_tx_empty(struct enetc_si *si, int mac) +{ + u32 val; + + if (read_poll_timeout(enetc_port_rd, val, + val & PM_IEVENT_TX_EMPTY, + 100, 10000, false, &si->hw, + ENETC4_PM_IEVENT(mac))) + dev_warn(&si->pdev->dev, + "MAC %d TX is not empty\n", mac); +} + +static void enetc4_mac_tx_graceful_stop(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + struct enetc_si *si = pf->si; + u32 val; + + val = enetc_port_rd(hw, ENETC4_POR); + val |= POR_TXDIS; + enetc_port_wr(hw, ENETC4_POR, val); + + if (enetc_is_pseudo_mac(si)) + return; + + enetc4_mac_wait_tx_empty(si, 0); + if (si->hw_features & ENETC_SI_F_QBU) + enetc4_mac_wait_tx_empty(si, 1); + + val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); + val &= ~PM_CMD_CFG_TX_EN; + enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); +} + +static void enetc4_mac_tx_enable(struct enetc_pf *pf) { + struct enetc_hw *hw = &pf->si->hw; struct enetc_si *si = pf->si; u32 val; val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); - val &= ~(PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN); - val |= en ? (PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN) : 0; + val |= PM_CMD_CFG_TX_EN; + enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); + val = enetc_port_rd(hw, ENETC4_POR); + val &= ~POR_TXDIS; + enetc_port_wr(hw, ENETC4_POR, val); +} + +static void enetc4_mac_wait_rx_empty(struct enetc_si *si, int mac) +{ + u32 val; + + if (read_poll_timeout(enetc_port_rd, val, + val & PM_IEVENT_RX_EMPTY, + 100, 10000, false, &si->hw, + ENETC4_PM_IEVENT(mac))) + dev_warn(&si->pdev->dev, + "MAC %d RX is not empty\n", mac); +} + +static void enetc4_mac_rx_graceful_stop(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + struct enetc_si *si = pf->si; + u32 val; + + if (enetc_is_pseudo_mac(si)) + goto check_rx_busy; + + if (si->hw_features & ENETC_SI_F_QBU) { + val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(1)); + val &= ~PM_CMD_CFG_RX_EN; + enetc_port_wr(hw, ENETC4_PM_CMD_CFG(1), val); + enetc4_mac_wait_rx_empty(si, 1); + } + + val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(0)); + val &= ~PM_CMD_CFG_RX_EN; + enetc_port_wr(hw, ENETC4_PM_CMD_CFG(0), val); + enetc4_mac_wait_rx_empty(si, 0); + +check_rx_busy: + if (read_poll_timeout(enetc_port_rd, val, + !(val & PSR_RX_BUSY), + 100, 10000, false, hw, + ENETC4_PSR)) + dev_warn(&si->pdev->dev, "Port RX busy\n"); + + val = enetc_port_rd(hw, ENETC4_POR); + val |= POR_RXDIS; + enetc_port_wr(hw, ENETC4_POR, val); +} + +static void enetc4_mac_rx_enable(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + struct enetc_si *si = pf->si; + u32 val; + + val = enetc_port_rd(hw, ENETC4_POR); + val &= ~POR_RXDIS; + enetc_port_wr(hw, ENETC4_POR, val); + + val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); + val |= PM_CMD_CFG_RX_EN; enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); } @@ -853,7 +941,8 @@ static void enetc4_pl_mac_link_up(struct phylink_config *config, enetc4_set_hd_flow_control(pf, hd_fc); enetc4_set_tx_pause(pf, priv->num_rx_rings, tx_pause); enetc4_set_rx_pause(pf, rx_pause); - enetc4_enable_mac(pf, true); + enetc4_mac_tx_enable(pf); + enetc4_mac_rx_enable(pf); } static void enetc4_pl_mac_link_down(struct phylink_config *config, @@ -862,7 +951,8 @@ static void enetc4_pl_mac_link_down(struct phylink_config *config, { struct enetc_pf *pf = phylink_to_enetc_pf(config); - enetc4_enable_mac(pf, false); + enetc4_mac_rx_graceful_stop(pf); + enetc4_mac_tx_graceful_stop(pf); } static const struct phylink_mac_ops enetc_pl_mac_ops = { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index fed89d4f1e1d..7c17acaf7a38 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -795,9 +795,17 @@ static int enetc_set_rxfh(struct net_device *ndev, struct enetc_si *si = priv->si; int err = 0; + if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && + rxfh->hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + /* set hash key, if PF */ - if (rxfh->key && enetc_si_is_pf(si)) + if (rxfh->key) { + if (!enetc_si_is_pf(si)) + return -EOPNOTSUPP; + enetc_set_rss_key(si, rxfh->key); + } /* set RSS table */ if (rxfh->indir) @@ -813,6 +821,8 @@ static void enetc_get_ringparam(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); + ring->rx_max_pending = priv->rx_bd_count; + ring->tx_max_pending = priv->tx_bd_count; ring->rx_pending = priv->rx_bd_count; ring->tx_pending = priv->tx_bd_count; diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 4b7bad9a485d..56801c2009d5 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -545,9 +545,6 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, if (rq->perout.flags) return -EOPNOTSUPP; - if (rq->perout.index != fep->pps_channel) - return -EOPNOTSUPP; - period.tv_sec = rq->perout.period.sec; period.tv_nsec = rq->perout.period.nsec; period_ns = timespec64_to_ns(&period); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index ab67c709d5a0..1cd1f3f2930a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -313,14 +313,13 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset) { /* Report the maximum number queues, even if not every queue is * currently configured. Since allocation of queues is in pairs, - * use netdev->real_num_tx_queues * 2. The real_num_tx_queues is set - * at device creation and never changes. + * use netdev->num_tx_queues * 2. The num_tx_queues is set at + * device creation and never changes. */ if (sset == ETH_SS_STATS) return IAVF_STATS_LEN + - (IAVF_QUEUE_STATS_LEN * 2 * - netdev->real_num_tx_queues); + (IAVF_QUEUE_STATS_LEN * 2 * netdev->num_tx_queues); else return -EINVAL; } @@ -345,19 +344,19 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); - /* As num_active_queues describe both tx and rx queues, we can use - * it to iterate over rings' stats. + /* Use num_tx_queues to report stats for the maximum number of queues. + * Queues beyond num_active_queues will report zero. */ - for (i = 0; i < adapter->num_active_queues; i++) { - struct iavf_ring *ring; + for (i = 0; i < netdev->num_tx_queues; i++) { + struct iavf_ring *tx_ring = NULL, *rx_ring = NULL; - /* Tx rings stats */ - ring = &adapter->tx_rings[i]; - iavf_add_queue_stats(&data, ring); + if (i < adapter->num_active_queues) { + tx_ring = &adapter->tx_rings[i]; + rx_ring = &adapter->rx_rings[i]; + } - /* Rx rings stats */ - ring = &adapter->rx_rings[i]; - iavf_add_queue_stats(&data, ring); + iavf_add_queue_stats(&data, tx_ring); + iavf_add_queue_stats(&data, rx_ring); } rcu_read_unlock(); } @@ -376,9 +375,9 @@ static void iavf_get_stat_strings(struct net_device *netdev, u8 *data) iavf_add_stat_strings(&data, iavf_gstrings_stats); /* Queues are always allocated in pairs, so we just use - * real_num_tx_queues for both Tx and Rx queues. + * num_tx_queues for both Tx and Rx queues. */ - for (i = 0; i < netdev->real_num_tx_queues; i++) { + for (i = 0; i < netdev->num_tx_queues; i++) { iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, "tx", i); iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2b2b22af42be..eb3a48330cc1 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -840,6 +840,28 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) } /** + * ice_get_max_txq - return the maximum number of Tx queues for in a PF + * @pf: PF structure + * + * Return: maximum number of Tx queues + */ +static inline int ice_get_max_txq(struct ice_pf *pf) +{ + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); +} + +/** + * ice_get_max_rxq - return the maximum number of Rx queues for in a PF + * @pf: PF structure + * + * Return: maximum number of Rx queues + */ +static inline int ice_get_max_rxq(struct ice_pf *pf) +{ + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); +} + +/** * ice_get_main_vsi - Get the PF VSI * @pf: PF instance * diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 301947d53ede..e6a20af6f63d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1930,6 +1930,17 @@ __ice_get_ethtool_stats(struct net_device *netdev, int i = 0; char *p; + if (ice_is_port_repr_netdev(netdev)) { + ice_update_eth_stats(vsi); + + for (j = 0; j < ICE_VSI_STATS_LEN; j++) { + p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset; + data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + return; + } + ice_update_pf_stats(pf); ice_update_vsi_stats(vsi); @@ -1939,9 +1950,6 @@ __ice_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } - if (ice_is_port_repr_netdev(netdev)) - return; - /* populate per queue stats */ rcu_read_lock(); @@ -3774,24 +3782,6 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) } /** - * ice_get_max_txq - return the maximum number of Tx queues for in a PF - * @pf: PF structure - */ -static int ice_get_max_txq(struct ice_pf *pf) -{ - return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); -} - -/** - * ice_get_max_rxq - return the maximum number of Rx queues for in a PF - * @pf: PF structure - */ -static int ice_get_max_rxq(struct ice_pf *pf) -{ - return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); -} - -/** * ice_get_combined_cnt - return the current number of combined channels * @vsi: PF VSI pointer * diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index e7308e381e2f..3c36e3641b9e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4699,8 +4699,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) struct net_device *netdev; u8 mac_addr[ETH_ALEN]; - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); + netdev = alloc_etherdev_mqs(sizeof(*np), ice_get_max_txq(vsi->back), + ice_get_max_rxq(vsi->back)); if (!netdev) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 90f99443a922..096566c697f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -2,6 +2,7 @@ /* Copyright (C) 2019-2021, Intel Corporation. */ #include "ice.h" +#include "ice_lib.h" #include "ice_eswitch.h" #include "devlink/devlink.h" #include "devlink/port.h" @@ -67,7 +68,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) return; vsi = repr->src_vsi; - ice_update_vsi_stats(vsi); + ice_update_eth_stats(vsi); eth_stats = &vsi->eth_stats; stats->tx_packets = eth_stats->tx_unicast + eth_stats->tx_broadcast + @@ -315,7 +316,7 @@ ice_repr_reg_netdev(struct net_device *netdev, const struct net_device_ops *ops) static int ice_repr_ready_vf(struct ice_repr *repr) { - return !ice_check_vf_ready_for_cfg(repr->vf); + return ice_check_vf_ready_for_cfg(repr->vf); } static int ice_repr_ready_sf(struct ice_repr *repr) diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index b206fba092c8..ec1b75f039bb 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -1066,7 +1066,7 @@ bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val); int idpf_idc_init(struct idpf_adapter *adapter); int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter, enum iidc_function_type ftype); -void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info); +void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter); void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info); void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info); void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info, diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index bd4785fb8d3e..7e4f4ac92653 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -470,10 +470,11 @@ err_privd_alloc: /** * idpf_idc_deinit_core_aux_device - de-initialize Auxiliary Device(s) - * @cdev_info: IDC core device info pointer + * @adapter: driver private data structure */ -void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info) +void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter) { + struct iidc_rdma_core_dev_info *cdev_info = adapter->cdev_info; struct iidc_rdma_priv_dev_info *privd; if (!cdev_info) @@ -485,6 +486,7 @@ void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info) kfree(privd->mapped_mem_regions); kfree(privd); kfree(cdev_info); + adapter->cdev_info = NULL; } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 252259993022..f6b3b15364ff 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1860,13 +1860,13 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, idpf_queue_assign(HSPLIT_EN, q, hs); idpf_queue_assign(RSC_EN, q, rsc); - bufq_set->num_refillqs = num_rxq; bufq_set->refillqs = kcalloc(num_rxq, swq_size, GFP_KERNEL); if (!bufq_set->refillqs) { err = -ENOMEM; goto err_alloc; } + bufq_set->num_refillqs = num_rxq; for (unsigned int k = 0; k < bufq_set->num_refillqs; k++) { struct idpf_sw_queue *refillq = &bufq_set->refillqs[k]; diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d5a877e1fef8..113ecfc16dd7 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -3668,7 +3668,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter) idpf_ptp_release(adapter); idpf_deinit_task(adapter); - idpf_idc_deinit_core_aux_device(adapter->cdev_info); + idpf_idc_deinit_core_aux_device(adapter); idpf_rel_rx_pt_lkup(adapter); idpf_intr_rel(adapter); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index cb30108f2bf6..cc8c4ef8038f 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -244,6 +244,25 @@ out: return 0; } +static bool +mtk_flow_is_valid_idev(const struct mtk_eth *eth, const struct net_device *idev) +{ + size_t i; + + if (!idev) + return false; + + for (i = 0; i < ARRAY_SIZE(eth->netdev); i++) { + if (!eth->netdev[i]) + continue; + + if (idev->netdev_ops == eth->netdev[i]->netdev_ops) + return true; + } + + return false; +} + static int mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f, int ppe_index) @@ -270,7 +289,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f, flow_rule_match_meta(rule, &match); if (mtk_is_netsys_v2_or_greater(eth)) { idev = __dev_get_by_index(&init_net, match.key->ingress_ifindex); - if (idev && idev->netdev_ops == eth->netdev[0]->netdev_ops) { + if (mtk_flow_is_valid_idev(eth, idev)) { struct mtk_mac *mac = netdev_priv(idev); if (WARN_ON(mac->ppe_idx >= eth->soc->ppe_num)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 6698ac55a4bf..73cf0321bb86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -107,9 +107,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, if (err) return err; - err = mlx5_fw_version_query(dev, &running_fw, &stored_fw); - if (err) - return err; + mlx5_fw_version_query(dev, &running_fw, &stored_fw); snprintf(version_str, sizeof(version_str), "%d.%d.%04d", mlx5_fw_ver_major(running_fw), mlx5_fw_ver_minor(running_fw), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7a9ee36b8dca..01f6aecc4fcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3761,6 +3761,8 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) return 0; err_vports: + /* rollback to legacy, indicates don't unregister the uplink netdev */ + esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY; mlx5_esw_offloads_rep_unload(esw, MLX5_VPORT_UPLINK); err_uplink: esw_offloads_steering_cleanup(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index eeb4437975f2..c1f220e5fe18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -822,48 +822,63 @@ mlx5_fw_image_pending(struct mlx5_core_dev *dev, return 0; } -int mlx5_fw_version_query(struct mlx5_core_dev *dev, - u32 *running_ver, u32 *pending_ver) +void mlx5_fw_version_query(struct mlx5_core_dev *dev, + u32 *running_ver, u32 *pending_ver) { u32 reg_mcqi_version[MLX5_ST_SZ_DW(mcqi_version)] = {}; bool pending_version_exists; int component_index; int err; + *running_ver = 0; + *pending_ver = 0; + if (!MLX5_CAP_GEN(dev, mcam_reg) || !MLX5_CAP_MCAM_REG(dev, mcqi) || !MLX5_CAP_MCAM_REG(dev, mcqs)) { mlx5_core_warn(dev, "fw query isn't supported by the FW\n"); - return -EOPNOTSUPP; + return; } component_index = mlx5_get_boot_img_component_index(dev); - if (component_index < 0) - return component_index; + if (component_index < 0) { + mlx5_core_warn(dev, "fw query failed to find boot img component index, err %d\n", + component_index); + return; + } + *running_ver = U32_MAX; /* indicate failure */ err = mlx5_reg_mcqi_version_query(dev, component_index, MCQI_FW_RUNNING_VERSION, reg_mcqi_version); - if (err) - return err; - - *running_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version); - + if (!err) + *running_ver = MLX5_GET(mcqi_version, reg_mcqi_version, + version); + else + mlx5_core_warn(dev, "failed to query running version, err %d\n", + err); + + *pending_ver = U32_MAX; /* indicate failure */ err = mlx5_fw_image_pending(dev, component_index, &pending_version_exists); - if (err) - return err; + if (err) { + mlx5_core_warn(dev, "failed to query pending image, err %d\n", + err); + return; + } if (!pending_version_exists) { *pending_ver = 0; - return 0; + return; } err = mlx5_reg_mcqi_version_query(dev, component_index, MCQI_FW_STORED_VERSION, reg_mcqi_version); - if (err) - return err; - - *pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version); - - return 0; + if (!err) + *pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version, + version); + else + mlx5_core_warn(dev, "failed to query pending version, err %d\n", + err); + + return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c index 62b6faa4276a..b8d5f6a44d26 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c @@ -160,8 +160,11 @@ DEFINE_SHOW_ATTRIBUTE(members); void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev) { + struct mlx5_lag *ldev = mlx5_lag_dev(dev); struct dentry *dbg; + if (!ldev) + return; dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev)); dev->priv.dbg.lag_debugfs = dbg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b635b423d972..1507e881d962 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -393,8 +393,8 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw, struct netlink_ext_ack *extack); -int mlx5_fw_version_query(struct mlx5_core_dev *dev, - u32 *running_ver, u32 *stored_ver); +void mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver, + u32 *stored_ver); #ifdef CONFIG_MLX5_CORE_EN int mlx5e_init(void); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c index 08270db2dee8..3c4563c8f403 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c @@ -197,7 +197,7 @@ static int fbnic_dbg_bdq_desc_seq_show(struct seq_file *s, void *v) return 0; } - for (i = 0; i <= ring->size_mask; i++) { + for (i = 0; i < (ring->size_mask + 1) * FBNIC_BD_FRAG_COUNT; i++) { u64 bd = le64_to_cpu(ring->desc[i]); seq_printf(s, "%04x %#04llx %#014llx\n", i, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index 9fb91d4f3971..9cd85a0d0c3a 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -927,7 +927,7 @@ static void fbnic_fill_bdq(struct fbnic_ring *bdq) /* Force DMA writes to flush before writing to tail */ dma_wmb(); - writel(i, bdq->doorbell); + writel(i * FBNIC_BD_FRAG_COUNT, bdq->doorbell); } } @@ -2564,7 +2564,7 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq) hpq->tail = 0; hpq->head = 0; - log_size = fls(hpq->size_mask); + log_size = fls(hpq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT); /* Store descriptor ring address and size */ fbnic_ring_wr32(hpq, FBNIC_QUEUE_BDQ_HPQ_BAL, lower_32_bits(hpq->dma)); @@ -2576,7 +2576,7 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq) if (!ppq->size_mask) goto write_ctl; - log_size = fls(ppq->size_mask); + log_size = fls(ppq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT); /* Add enabling of PPQ to BDQ control */ bdq_ctl |= FBNIC_QUEUE_BDQ_CTL_PPQ_ENABLE; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index 980965274079..e03c9d2c38dc 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -38,7 +38,7 @@ struct fbnic_net; #define FBNIC_MAX_XDPQS 128u /* These apply to TWQs, TCQ, RCQ */ -#define FBNIC_QUEUE_SIZE_MIN 16u +#define FBNIC_QUEUE_SIZE_MIN 64u #define FBNIC_QUEUE_SIZE_MAX SZ_64K #define FBNIC_TXQ_SIZE_DEFAULT 1024 diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a3845edf0e48..f0b5dd752f08 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3053,6 +3053,11 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config, else if (speed == SPEED_100) mac_cr |= MAC_CR_CFG_L_; + if (duplex == DUPLEX_FULL) + mac_cr |= MAC_CR_DPX_; + else + mac_cr &= ~MAC_CR_DPX_; + lan743x_csr_write(adapter, MAC_CR, mac_cr); lan743x_ptp_update_latency(adapter, speed); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9017e806ecda..09a53c977545 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -766,6 +766,13 @@ static void mana_get_rxbuf_cfg(struct mana_port_context *apc, } *frag_count = 1; + + /* In the single-buffer path, napi_build_skb() must see the + * actual backing allocation size so skb->truesize reflects + * the full page (or higher-order page), not just the usable + * packet area. + */ + *alloc_size = PAGE_SIZE << get_order(*alloc_size); return; } @@ -3425,6 +3432,7 @@ static int add_adev(struct gdma_dev *gd, const char *name) struct auxiliary_device *adev; struct mana_adev *madev; int ret; + int id; madev = kzalloc_obj(*madev); if (!madev) @@ -3434,7 +3442,8 @@ static int add_adev(struct gdma_dev *gd, const char *name) ret = mana_adev_idx_alloc(); if (ret < 0) goto idx_fail; - adev->id = ret; + id = ret; + adev->id = id; adev->name = name; adev->dev.parent = gd->gdma_context->dev; @@ -3460,7 +3469,7 @@ add_fail: auxiliary_device_uninit(adev); init_fail: - mana_adev_idx_free(adev->id); + mana_adev_idx_free(id); idx_fail: kfree(madev); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 8d040e611d5a..637e635bbf03 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1719,13 +1719,18 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa) if (ether_addr_equal(netdev->dev_addr, mac)) return 0; - err = ionic_program_mac(lif, mac); - if (err < 0) - return err; + /* Only program macs for virtual functions to avoid losing the permanent + * Mac across warm reset/reboot. + */ + if (lif->ionic->pdev->is_virtfn) { + err = ionic_program_mac(lif, mac); + if (err < 0) + return err; - if (err > 0) - netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n", - __func__); + if (err > 0) + netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n", + __func__); + } err = eth_prepare_mac_addr_change(netdev, addr); if (err) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6827c99bde8c..13d3cac056be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -156,7 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue); static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue); static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan); -static int stmmac_vlan_restore(struct stmmac_priv *priv); +static void stmmac_vlan_restore(struct stmmac_priv *priv); #ifdef CONFIG_DEBUG_FS static const struct net_device_ops stmmac_netdev_ops; @@ -6859,21 +6859,15 @@ del_vlan_error: return ret; } -static int stmmac_vlan_restore(struct stmmac_priv *priv) +static void stmmac_vlan_restore(struct stmmac_priv *priv) { - int ret; - if (!(priv->dev->features & NETIF_F_VLAN_FEATURES)) - return 0; + return; if (priv->hw->num_vlan) stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw); - ret = stmmac_vlan_update(priv, priv->num_double_vlans); - if (ret) - netdev_err(priv->dev, "Failed to restore VLANs\n"); - - return ret; + stmmac_vlan_update(priv, priv->num_double_vlans); } static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf) diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 0a3cf2f848a5..a28a608f9bf4 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -902,6 +902,7 @@ static void emac_dispatch_skb_zc(struct prueth_emac *emac, struct xdp_buff *xdp, skb_reserve(skb, headroom); skb_put(skb, pkt_len); + skb_copy_to_linear_data(skb, xdp->data, pkt_len); skb->dev = ndev; /* RX HW timestamp */ @@ -912,7 +913,6 @@ static void emac_dispatch_skb_zc(struct prueth_emac *emac, struct xdp_buff *xdp, skb->offload_fwd_mark = emac->offload_fwd_mark; skb->protocol = eth_type_trans(skb, ndev); - skb_mark_for_recycle(skb); napi_gro_receive(&emac->napi_rx, skb); ndev->stats.rx_bytes += pkt_len; ndev->stats.rx_packets++; @@ -962,7 +962,6 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id, pkt_len -= 4; cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); psdata = cppi5_hdesc_get_psdata(desc_rx); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); count++; xsk_buff_set_size(xdp, pkt_len); xsk_buff_dma_sync_for_cpu(xdp); @@ -988,6 +987,7 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id, emac_dispatch_skb_zc(emac, xdp, psdata); xsk_buff_free(xdp); } + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); } if (xdp_status & ICSSG_XDP_REDIR) @@ -1057,7 +1057,6 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) /* firmware adds 4 CRC bytes, strip them */ pkt_len -= 4; cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); /* if allocation fails we drop the packet but push the * descriptor back to the ring with old page to prevent a stall @@ -1115,6 +1114,7 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) ndev->stats.rx_packets++; requeue: + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); /* queue another RX DMA */ ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page, PRUETH_MAX_PKT_SIZE); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 5ff742103beb..fcd3aaef27fc 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -105,7 +105,7 @@ #define XAXIDMA_BD_HAS_DRE_MASK 0xF00 /* Whether has DRE mask */ #define XAXIDMA_BD_WORDLEN_MASK 0xFF /* Whether has DRE mask */ -#define XAXIDMA_BD_CTRL_LENGTH_MASK 0x007FFFFF /* Requested len */ +#define XAXIDMA_BD_CTRL_LENGTH_MASK GENMASK(25, 0) /* Requested len */ #define XAXIDMA_BD_CTRL_TXSOF_MASK 0x08000000 /* First tx packet */ #define XAXIDMA_BD_CTRL_TXEOF_MASK 0x04000000 /* Last tx packet */ #define XAXIDMA_BD_CTRL_ALL_MASK 0x0C000000 /* All control bits */ @@ -130,7 +130,7 @@ #define XAXIDMA_BD_CTRL_TXEOF_MASK 0x04000000 /* Last tx packet */ #define XAXIDMA_BD_CTRL_ALL_MASK 0x0C000000 /* All control bits */ -#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK 0x007FFFFF /* Actual len */ +#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK GENMASK(25, 0) /* Actual len */ #define XAXIDMA_BD_STS_COMPLETE_MASK 0x80000000 /* Completed */ #define XAXIDMA_BD_STS_DEC_ERR_MASK 0x40000000 /* Decode error */ #define XAXIDMA_BD_STS_SLV_ERR_MASK 0x20000000 /* Slave error */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b06e4c37ff61..263c4b67fd5a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -770,8 +770,8 @@ static int axienet_device_reset(struct net_device *ndev) * @first_bd: Index of first descriptor to clean up * @nr_bds: Max number of descriptors to clean up * @force: Whether to clean descriptors even if not complete - * @sizep: Pointer to a u32 filled with the total sum of all bytes - * in all cleaned-up descriptors. Ignored if NULL. + * @sizep: Pointer to a u32 accumulating the total byte count of + * completed packets (using skb->len). Ignored if NULL. * @budget: NAPI budget (use 0 when not called from NAPI poll) * * Would either be called after a successful transmit operation, or after @@ -805,6 +805,8 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd, DMA_TO_DEVICE); if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) { + if (sizep) + *sizep += cur_p->skb->len; napi_consume_skb(cur_p->skb, budget); packets++; } @@ -818,9 +820,6 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd, wmb(); cur_p->cntrl = 0; cur_p->status = 0; - - if (sizep) - *sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK; } if (!force) { diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 5db841377199..ce8924613363 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -480,11 +480,16 @@ static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id, { /* Ubiquiti U-Fiber Instant module claims that support all transceiver * types including 10G Ethernet which is not truth. So clear all claimed - * modes and set only one mode which module supports: 1000baseX_Full. + * modes and set only one mode which module supports: 1000baseX_Full, + * along with the Autoneg and pause bits. */ linkmode_zero(caps->link_modes); linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, caps->link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, caps->link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, caps->link_modes); + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, caps->link_modes); + phy_interface_zero(caps->interfaces); __set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces); } diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index b7282f5c9632..120aeb539d9f 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2058,6 +2058,68 @@ static const struct ethtool_ops team_ethtool_ops = { * rt netlink interface ***********************/ +/* For tx path we need a linkup && enabled port and for parse any port + * suffices. + */ +static struct team_port *team_header_port_get_rcu(struct team *team, + bool txable) +{ + struct team_port *port; + + list_for_each_entry_rcu(port, &team->port_list, list) { + if (!txable || team_port_txable(port)) + return port; + } + + return NULL; +} + +static int team_header_create(struct sk_buff *skb, struct net_device *team_dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) +{ + struct team *team = netdev_priv(team_dev); + const struct header_ops *port_ops; + struct team_port *port; + int ret = 0; + + rcu_read_lock(); + port = team_header_port_get_rcu(team, true); + if (port) { + port_ops = READ_ONCE(port->dev->header_ops); + if (port_ops && port_ops->create) + ret = port_ops->create(skb, port->dev, + type, daddr, saddr, len); + } + rcu_read_unlock(); + return ret; +} + +static int team_header_parse(const struct sk_buff *skb, + const struct net_device *team_dev, + unsigned char *haddr) +{ + struct team *team = netdev_priv(team_dev); + const struct header_ops *port_ops; + struct team_port *port; + int ret = 0; + + rcu_read_lock(); + port = team_header_port_get_rcu(team, false); + if (port) { + port_ops = READ_ONCE(port->dev->header_ops); + if (port_ops && port_ops->parse) + ret = port_ops->parse(skb, port->dev, haddr); + } + rcu_read_unlock(); + return ret; +} + +static const struct header_ops team_header_ops = { + .create = team_header_create, + .parse = team_header_parse, +}; + static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { @@ -2066,7 +2128,8 @@ static void team_setup_by_port(struct net_device *dev, if (port_dev->type == ARPHRD_ETHER) dev->header_ops = team->header_ops_cache; else - dev->header_ops = port_dev->header_ops; + dev->header_ops = port_dev->header_ops ? + &team_header_ops : NULL; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h index a5f93b6c4482..fa5cab9d3e55 100644 --- a/drivers/net/tun_vnet.h +++ b/drivers/net/tun_vnet.h @@ -244,7 +244,7 @@ tun_vnet_hdr_tnl_from_skb(unsigned int flags, if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), - vlan_hlen, true)) { + vlan_hlen, true, false)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 72d6a9c6a5a2..c0b9bc5574e2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -381,8 +381,6 @@ struct receive_queue { struct xdp_buff **xsk_buffs; }; -#define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 - /* Control VQ buffers: protected by the rtnl lock */ struct control_buf { struct virtio_net_ctrl_hdr hdr; @@ -486,7 +484,7 @@ struct virtnet_info { /* Must be last as it ends in a flexible-array member. */ TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data, - u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; + u8 rss_hash_key_data[NETDEV_RSS_KEY_LEN]; ); }; static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) == @@ -3267,8 +3265,12 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) struct virtio_net_hdr_v1_hash_tunnel *hdr; int num_sg; unsigned hdr_len = vi->hdr_len; + bool feature_hdrlen; bool can_push; + feature_hdrlen = virtio_has_feature(vi->vdev, + VIRTIO_NET_F_GUEST_HDRLEN); + pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); /* Make sure it's safe to cast between formats */ @@ -3288,7 +3290,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl, virtio_is_little_endian(vi->vdev), 0, - false)) + false, feature_hdrlen)) return -EPROTO; if (vi->mergeable_rx_bufs) @@ -3351,6 +3353,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); + skb_dst_drop(skb); nf_reset_ct(skb); } @@ -6703,6 +6706,7 @@ static int virtnet_probe(struct virtio_device *vdev) struct virtnet_info *vi; u16 max_queue_pairs; int mtu = 0; + u16 key_sz; /* Find if host supports multiqueue/rss virtio_net device */ max_queue_pairs = 1; @@ -6837,14 +6841,13 @@ static int virtnet_probe(struct virtio_device *vdev) } if (vi->has_rss || vi->has_rss_hash_report) { - vi->rss_key_size = - virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); - if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) { - dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n", - vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE); - err = -EINVAL; - goto free; - } + key_sz = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); + + vi->rss_key_size = min_t(u16, key_sz, NETDEV_RSS_KEY_LEN); + if (key_sz > vi->rss_key_size) + dev_warn(&vdev->dev, + "rss_max_key_size=%u exceeds driver limit %u, clamping\n", + key_sz, vi->rss_key_size); vi->rss_hash_types_supported = virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types)); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 17c941aac32d..a94ac82a6136 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1965,12 +1965,14 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request, ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { - if (!ns->opt[i + 1]) { + if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { - daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + if ((ns->opt[i + 1] << 3) >= + sizeof(struct nd_opt_hdr) + ETH_ALEN) + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 49d959b2e148..85defe11750d 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include <linux/ieee80211.h> @@ -1110,9 +1110,8 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar, struct ath11k_base *ab = ar->ab; struct ath11k_peer *peer; struct ath11k_sta *arsta = ath11k_sta_to_arsta(params->sta); + struct dp_rx_tid *rx_tid; int vdev_id = arsta->arvif->vdev_id; - dma_addr_t paddr; - bool active; int ret; spin_lock_bh(&ab->base_lock); @@ -1124,15 +1123,14 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar, return -ENOENT; } - paddr = peer->rx_tid[params->tid].paddr; - active = peer->rx_tid[params->tid].active; + rx_tid = &peer->rx_tid[params->tid]; - if (!active) { + if (!rx_tid->active) { spin_unlock_bh(&ab->base_lock); return 0; } - ret = ath11k_peer_rx_tid_reo_update(ar, peer, peer->rx_tid, 1, 0, false); + ret = ath11k_peer_rx_tid_reo_update(ar, peer, rx_tid, 1, 0, false); spin_unlock_bh(&ab->base_lock); if (ret) { ath11k_warn(ab, "failed to update reo for rx tid %d: %d\n", @@ -1141,7 +1139,8 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar, } ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, - params->sta->addr, paddr, + params->sta->addr, + rx_tid->paddr, params->tid, 1, 1); if (ret) ath11k_warn(ab, "failed to send wmi to delete rx tid %d\n", diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 5a82ede65dd3..244d5230a5bd 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -735,6 +735,7 @@ int ath12k_dp_rx_ampdu_stop(struct ath12k *ar, struct ath12k_dp *dp = ath12k_ab_to_dp(ab); struct ath12k_dp_link_peer *peer; struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(params->sta); + struct ath12k_dp_rx_tid *rx_tid; struct ath12k_link_sta *arsta; int vdev_id; bool active; @@ -770,7 +771,8 @@ int ath12k_dp_rx_ampdu_stop(struct ath12k *ar, return 0; } - ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, peer->dp_peer->rx_tid, + rx_tid = &peer->dp_peer->rx_tid[params->tid]; + ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, rx_tid, 1, 0, false); spin_unlock_bh(&dp->dp_lock); if (ret) { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 8d64a271bb94..36159a769916 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -297,6 +297,11 @@ enum iwl_legacy_cmds { SCAN_OFFLOAD_UPDATE_PROFILES_CMD = 0x6E, /** + * @SCAN_START_NOTIFICATION_UMAC: uses &struct iwl_umac_scan_start + */ + SCAN_START_NOTIFICATION_UMAC = 0xb2, + + /** * @MATCH_FOUND_NOTIFICATION: scan match found */ MATCH_FOUND_NOTIFICATION = 0xd9, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h index 60f0a4924ddf..46fcc32608e3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h @@ -1157,6 +1157,16 @@ enum iwl_umac_scan_abort_status { }; /** + * struct iwl_umac_scan_start - scan start notification + * @uid: scan id, &enum iwl_umac_scan_uid_offsets + * @reserved: for future use + */ +struct iwl_umac_scan_start { + __le32 uid; + __le32 reserved; +} __packed; /* SCAN_START_UMAC_API_S_VER_1 */ + +/** * struct iwl_umac_scan_complete - scan complete notification * @uid: scan id, &enum iwl_umac_scan_uid_offsets * @last_schedule: last scheduling line diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c index 29df747c8938..9215fc7e2eca 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c @@ -111,14 +111,75 @@ static bool iwl_mld_is_nic_ack_enabled(struct iwl_mld *mld, IEEE80211_HE_MAC_CAP2_ACK_EN); } -static void iwl_mld_set_he_support(struct iwl_mld *mld, - struct ieee80211_vif *vif, - struct iwl_mac_config_cmd *cmd) +struct iwl_mld_mac_wifi_gen_sta_iter_data { + struct ieee80211_vif *vif; + struct iwl_mac_wifi_gen_support *support; +}; + +static void iwl_mld_mac_wifi_gen_sta_iter(void *_data, + struct ieee80211_sta *sta) { - if (vif->type == NL80211_IFTYPE_AP) - cmd->wifi_gen.he_ap_support = 1; - else - cmd->wifi_gen.he_support = 1; + struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta); + struct iwl_mld_mac_wifi_gen_sta_iter_data *data = _data; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; + + if (mld_sta->vif != data->vif) + return; + + for_each_sta_active_link(data->vif, sta, link_sta, link_id) { + if (link_sta->he_cap.has_he) + data->support->he_support = 1; + if (link_sta->eht_cap.has_eht) + data->support->eht_support = 1; + } +} + +static void iwl_mld_set_wifi_gen(struct iwl_mld *mld, + struct ieee80211_vif *vif, + struct iwl_mac_wifi_gen_support *support) +{ + struct iwl_mld_mac_wifi_gen_sta_iter_data sta_iter_data = { + .vif = vif, + .support = support, + }; + struct ieee80211_bss_conf *link_conf; + unsigned int link_id; + + switch (vif->type) { + case NL80211_IFTYPE_MONITOR: + /* for sniffer, set to HW capabilities */ + support->he_support = 1; + support->eht_support = mld->trans->cfg->eht_supported; + break; + case NL80211_IFTYPE_AP: + /* for AP set according to the link configs */ + for_each_vif_active_link(vif, link_conf, link_id) { + support->he_ap_support |= link_conf->he_support; + support->eht_support |= link_conf->eht_support; + } + break; + default: + /* + * If we have MLO enabled, then the firmware needs to enable + * address translation for the station(s) we add. That depends + * on having EHT enabled in firmware, which in turn depends on + * mac80211 in the iteration below. + * However, mac80211 doesn't enable capabilities on the AP STA + * until it has parsed the association response successfully, + * so set EHT (and HE as a pre-requisite for EHT) when the vif + * is an MLD. + */ + if (ieee80211_vif_is_mld(vif)) { + support->he_support = 1; + support->eht_support = 1; + } + + ieee80211_iterate_stations_mtx(mld->hw, + iwl_mld_mac_wifi_gen_sta_iter, + &sta_iter_data); + break; + } } /* fill the common part for all interface types */ @@ -128,8 +189,6 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld, u32 action) { struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif); - struct ieee80211_bss_conf *link_conf; - unsigned int link_id; lockdep_assert_wiphy(mld->wiphy); @@ -147,29 +206,7 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld, cmd->nic_not_ack_enabled = cpu_to_le32(!iwl_mld_is_nic_ack_enabled(mld, vif)); - /* If we have MLO enabled, then the firmware needs to enable - * address translation for the station(s) we add. That depends - * on having EHT enabled in firmware, which in turn depends on - * mac80211 in the code below. - * However, mac80211 doesn't enable HE/EHT until it has parsed - * the association response successfully, so just skip all that - * and enable both when we have MLO. - */ - if (ieee80211_vif_is_mld(vif)) { - iwl_mld_set_he_support(mld, vif, cmd); - cmd->wifi_gen.eht_support = 1; - return; - } - - for_each_vif_active_link(vif, link_conf, link_id) { - if (!link_conf->he_support) - continue; - - iwl_mld_set_he_support(mld, vif, cmd); - - /* EHT, if supported, was already set above */ - break; - } + iwl_mld_set_wifi_gen(mld, vif, &cmd->wifi_gen); } static void iwl_mld_fill_mac_cmd_sta(struct iwl_mld *mld, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 0c53d6bd9651..71a9a72c9ac0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1761,6 +1761,16 @@ static int iwl_mld_move_sta_state_up(struct iwl_mld *mld, if (vif->type == NL80211_IFTYPE_STATION) iwl_mld_link_set_2mhz_block(mld, vif, sta); + + if (sta->tdls) { + /* + * update MAC since wifi generation flags may change, + * we also update MAC on association to the AP via the + * vif assoc change + */ + iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY); + } + /* Now the link_sta's capabilities are set, update the FW */ iwl_mld_config_tlc(mld, vif, sta); @@ -1873,6 +1883,15 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld, /* just removed last TDLS STA, so enable PM */ iwl_mld_update_mac_power(mld, vif, false); } + + if (sta->tdls) { + /* + * update MAC since wifi generation flags may change, + * we also update MAC on disassociation to the AP via + * the vif assoc change + */ + iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY); + } } else { return -EINVAL; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c index 495e9d8f3af6..9af79297c3b6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c @@ -171,6 +171,7 @@ static const struct iwl_hcmd_names iwl_mld_legacy_names[] = { HCMD_NAME(MISSED_BEACONS_NOTIFICATION), HCMD_NAME(MAC_PM_POWER_TABLE), HCMD_NAME(MFUART_LOAD_NOTIFICATION), + HCMD_NAME(SCAN_START_NOTIFICATION_UMAC), HCMD_NAME(RSS_CONFIG_CMD), HCMD_NAME(SCAN_ITERATION_COMPLETE_UMAC), HCMD_NAME(REPLY_RX_MPDU_CMD), diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c index f842f5183223..fbff5915f7fd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c @@ -739,7 +739,7 @@ iwl_mld_set_link_sel_data(struct iwl_mld *mld, /* Ignore any BSS that was not seen in the last MLO scan */ if (ktime_before(link_conf->bss->ts_boottime, - mld->scan.last_mlo_scan_time)) + mld->scan.last_mlo_scan_start_time)) continue; data[n_data].link_id = link_id; @@ -945,7 +945,7 @@ static void _iwl_mld_select_links(struct iwl_mld *mld, if (!mld_vif->authorized || hweight16(usable_links) <= 1) return; - if (WARN(ktime_before(mld->scan.last_mlo_scan_time, + if (WARN(ktime_before(mld->scan.last_mlo_scan_start_time, ktime_sub_ns(ktime_get_boottime_ns(), 5ULL * NSEC_PER_SEC)), "Last MLO scan was too long ago, can't select links\n")) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c index 240526d8b632..9c88a8579a75 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/notif.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c @@ -287,6 +287,8 @@ static void iwl_mld_handle_beacon_notification(struct iwl_mld *mld, * at least enough bytes to cover the structure listed in the CMD_VER_ENTRY. */ +CMD_VERSIONS(scan_start_notif, + CMD_VER_ENTRY(1, iwl_umac_scan_start)) CMD_VERSIONS(scan_complete_notif, CMD_VER_ENTRY(1, iwl_umac_scan_complete)) CMD_VERSIONS(scan_iter_complete_notif, @@ -360,6 +362,7 @@ DEFINE_SIMPLE_CANCELLATION(datapath_monitor, iwl_datapath_monitor_notif, link_id) DEFINE_SIMPLE_CANCELLATION(roc, iwl_roc_notif, activity) DEFINE_SIMPLE_CANCELLATION(scan_complete, iwl_umac_scan_complete, uid) +DEFINE_SIMPLE_CANCELLATION(scan_start, iwl_umac_scan_start, uid) DEFINE_SIMPLE_CANCELLATION(probe_resp_data, iwl_probe_resp_data_notif, mac_id) DEFINE_SIMPLE_CANCELLATION(uapsd_misbehaving_ap, iwl_uapsd_misbehaving_ap_notif, @@ -402,6 +405,8 @@ const struct iwl_rx_handler iwl_mld_rx_handlers[] = { RX_HANDLER_SYNC) RX_HANDLER_NO_OBJECT(LEGACY_GROUP, BA_NOTIF, compressed_ba_notif, RX_HANDLER_SYNC) + RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_START_NOTIFICATION_UMAC, + scan_start_notif) RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_COMPLETE_UMAC, scan_complete_notif) RX_HANDLER_NO_OBJECT(LEGACY_GROUP, SCAN_ITERATION_COMPLETE_UMAC, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.c b/drivers/net/wireless/intel/iwlwifi/mld/scan.c index a1a4cf3ab3d3..abd4281b4b0e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.c @@ -473,6 +473,9 @@ iwl_mld_scan_get_cmd_gen_flags(struct iwl_mld *mld, params->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_TRIGGER_UHB_SCAN; + if (scan_status == IWL_MLD_SCAN_INT_MLO) + flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_NTF_START; + if (params->enable_6ghz_passive) flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_6GHZ_PASSIVE_SCAN; @@ -1817,9 +1820,6 @@ static void iwl_mld_int_mlo_scan_start(struct iwl_mld *mld, ret = _iwl_mld_single_scan_start(mld, vif, req, &ies, IWL_MLD_SCAN_INT_MLO); - if (!ret) - mld->scan.last_mlo_scan_time = ktime_get_boottime_ns(); - IWL_DEBUG_SCAN(mld, "Internal MLO scan: ret=%d\n", ret); } @@ -1904,6 +1904,30 @@ void iwl_mld_handle_match_found_notif(struct iwl_mld *mld, ieee80211_sched_scan_results(mld->hw); } +void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld, + struct iwl_rx_packet *pkt) +{ + struct iwl_umac_scan_complete *notif = (void *)pkt->data; + u32 uid = le32_to_cpu(notif->uid); + + if (IWL_FW_CHECK(mld, uid >= ARRAY_SIZE(mld->scan.uid_status), + "FW reports out-of-range scan UID %d\n", uid)) + return; + + if (IWL_FW_CHECK(mld, !(mld->scan.uid_status[uid] & mld->scan.status), + "FW reports scan UID %d we didn't trigger\n", uid)) + return; + + IWL_DEBUG_SCAN(mld, "Scan started: uid=%u type=%u\n", uid, + mld->scan.uid_status[uid]); + if (IWL_FW_CHECK(mld, mld->scan.uid_status[uid] != IWL_MLD_SCAN_INT_MLO, + "FW reports scan start notification %d we didn't trigger\n", + mld->scan.uid_status[uid])) + return; + + mld->scan.last_mlo_scan_start_time = ktime_get_boottime_ns(); +} + void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld, struct iwl_rx_packet *pkt) { diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.h b/drivers/net/wireless/intel/iwlwifi/mld/scan.h index 69110f0cfc8e..de5620e7f463 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/scan.h +++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.h @@ -27,6 +27,9 @@ int iwl_mld_sched_scan_start(struct iwl_mld *mld, void iwl_mld_handle_match_found_notif(struct iwl_mld *mld, struct iwl_rx_packet *pkt); +void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld, + struct iwl_rx_packet *pkt); + void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld, struct iwl_rx_packet *pkt); @@ -114,8 +117,8 @@ enum iwl_mld_traffic_load { * in jiffies. * @last_start_time_jiffies: stores the last start time in jiffies * (interface up/reset/resume). - * @last_mlo_scan_time: start time of the last MLO scan in nanoseconds since - * boot. + * @last_mlo_scan_start_time: start time of the last MLO scan in nanoseconds + * since boot. */ struct iwl_mld_scan { /* Add here fields that need clean up on restart */ @@ -136,7 +139,7 @@ struct iwl_mld_scan { void *cmd; unsigned long last_6ghz_passive_jiffies; unsigned long last_start_time_jiffies; - u64 last_mlo_scan_time; + u64 last_mlo_scan_start_time; }; /** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index a19f9d2e9346..9a74f60c9185 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2807,7 +2807,7 @@ static void iwl_mvm_nd_match_info_handler(struct iwl_mvm *mvm, if (IS_ERR_OR_NULL(vif)) return; - if (len < sizeof(struct iwl_scan_offload_match_info)) { + if (len < sizeof(struct iwl_scan_offload_match_info) + matches_len) { IWL_ERR(mvm, "Invalid scan match info notification\n"); return; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 43cf94c9a36b..6cc78661116e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -470,7 +470,8 @@ static void iwl_mvm_uats_init(struct iwl_mvm *mvm) .dataflags[0] = IWL_HCMD_DFL_NOCOPY, }; - if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) { + if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210 || + !mvm->trans->cfg->uhb_supported) { IWL_DEBUG_RADIO(mvm, "UATS feature is not supported\n"); return; } diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index f354b11cb919..944b2a812b63 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -163,7 +163,7 @@ int wilc_scan(struct wilc_vif *vif, u8 scan_source, u32 index = 0; u32 i, scan_timeout; u8 *buffer; - u8 valuesize = 0; + u32 valuesize = 0; u8 *search_ssid_vals = NULL; const u8 ch_list_len = request->n_channels; struct host_if_drv *hif_drv = vif->hif_drv; diff --git a/drivers/net/wireless/ti/wl1251/tx.c b/drivers/net/wireless/ti/wl1251/tx.c index 2da8c0d5105b..4489aa77bb0f 100644 --- a/drivers/net/wireless/ti/wl1251/tx.c +++ b/drivers/net/wireless/ti/wl1251/tx.c @@ -402,12 +402,14 @@ static void wl1251_tx_packet_cb(struct wl1251 *wl, int hdrlen; u8 *frame; - skb = wl->tx_frames[result->id]; - if (skb == NULL) { - wl1251_error("SKB for packet %d is NULL", result->id); + if (unlikely(result->id >= ARRAY_SIZE(wl->tx_frames) || + wl->tx_frames[result->id] == NULL)) { + wl1251_error("invalid packet id %u", result->id); return; } + skb = wl->tx_frames[result->id]; + info = IEEE80211_SKB_CB(skb); if (!(info->flags & IEEE80211_TX_CTL_NO_ACK) && diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c index 885dc7243e8d..97bd39d89e98 100644 --- a/drivers/net/wireless/virtual/virt_wifi.c +++ b/drivers/net/wireless/virtual/virt_wifi.c @@ -557,7 +557,6 @@ static int virt_wifi_newlink(struct net_device *dev, eth_hw_addr_inherit(dev, priv->lowerdev); netif_stacked_transfer_operstate(priv->lowerdev, dev); - SET_NETDEV_DEV(dev, &priv->lowerdev->dev); dev->ieee80211_ptr = kzalloc_obj(*dev->ieee80211_ptr); if (!dev->ieee80211_ptr) { diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c index 6d2f520a5bc8..1b82b7b2a5fa 100644 --- a/drivers/nfc/pn533/uart.c +++ b/drivers/nfc/pn533/uart.c @@ -211,6 +211,9 @@ static size_t pn532_receive_buf(struct serdev_device *serdev, timer_delete(&dev->cmd_timeout); for (i = 0; i < count; i++) { + if (unlikely(!skb_tailroom(dev->recv_skb))) + skb_trim(dev->recv_skb, 0); + skb_put_u8(dev->recv_skb, *data++); if (!pn532_uart_rx_is_frame(dev->recv_skb)) continue; diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c index 7754baed67f2..97cff5b8ca88 100644 --- a/drivers/pci/pwrctrl/core.c +++ b/drivers/pci/pwrctrl/core.c @@ -299,8 +299,10 @@ static bool pci_pwrctrl_is_required(struct device_node *np) struct device_node *remote __free(device_node) = of_graph_get_remote_port_parent(endpoint); if (remote) { - if (of_pci_supply_present(remote)) + if (of_pci_supply_present(remote)) { + of_node_put(endpoint); return true; + } } } } diff --git a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c index 0d0377283c37..c7e4beec160a 100644 --- a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c +++ b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c @@ -68,13 +68,6 @@ static int pwrseq_pwrctrl_power_off(struct pci_pwrctrl *pwrctrl) return pwrseq_power_off(pwrseq->pwrseq); } -static void devm_pwrseq_pwrctrl_power_off(void *data) -{ - struct pwrseq_pwrctrl *pwrseq = data; - - pwrseq_pwrctrl_power_off(&pwrseq->pwrctrl); -} - static int pwrseq_pwrctrl_probe(struct platform_device *pdev) { const struct pwrseq_pwrctrl_pdata *pdata; @@ -101,11 +94,6 @@ static int pwrseq_pwrctrl_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(pwrseq->pwrseq), "Failed to get the power sequencer\n"); - ret = devm_add_action_or_reset(dev, devm_pwrseq_pwrctrl_power_off, - pwrseq); - if (ret) - return ret; - pwrseq->pwrctrl.power_on = pwrseq_pwrctrl_power_on; pwrseq->pwrctrl.power_off = pwrseq_pwrctrl_power_off; diff --git a/drivers/pci/pwrctrl/slot.c b/drivers/pci/pwrctrl/slot.c index 082af81efe25..b87639253ae2 100644 --- a/drivers/pci/pwrctrl/slot.c +++ b/drivers/pci/pwrctrl/slot.c @@ -63,7 +63,6 @@ static void devm_slot_pwrctrl_release(void *data) { struct slot_pwrctrl *slot = data; - slot_pwrctrl_power_off(&slot->pwrctrl); regulator_bulk_free(slot->num_supplies, slot->supplies); } diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 02467dfd4fb0..1875d5b784f6 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -6,7 +6,7 @@ menu "PHY Subsystem" config PHY_COMMON_PROPS - bool + bool "PHY common properties" if KUNIT_ALL_TESTS help This parses properties common between generic PHYs and Ethernet PHYs. @@ -16,8 +16,7 @@ config PHY_COMMON_PROPS config PHY_COMMON_PROPS_TEST tristate "KUnit tests for PHY common props" if !KUNIT_ALL_TESTS - select PHY_COMMON_PROPS - depends on KUNIT + depends on KUNIT && PHY_COMMON_PROPS default KUNIT_ALL_TESTS help This builds KUnit tests for the PHY common property API. diff --git a/drivers/phy/freescale/phy-fsl-lynx-28g.c b/drivers/phy/freescale/phy-fsl-lynx-28g.c index 2b0fd95ba62f..63427fc34e26 100644 --- a/drivers/phy/freescale/phy-fsl-lynx-28g.c +++ b/drivers/phy/freescale/phy-fsl-lynx-28g.c @@ -1069,6 +1069,8 @@ static void lynx_28g_cdr_lock_check(struct work_struct *work) for (i = 0; i < LYNX_28G_NUM_LANE; i++) { lane = &priv->lane[i]; + if (!lane->phy) + continue; mutex_lock(&lane->phy->mutex); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index df138a5442eb..771bc7c2ab50 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -990,6 +990,7 @@ static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = { QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x68), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_POST_EMP_LVL_S4, 0x0e), @@ -999,13 +1000,11 @@ static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = { }; static const struct qmp_phy_init_tbl sm8650_ufsphy_g4_pcs[] = { - QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x13), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04), }; static const struct qmp_phy_init_tbl sm8650_ufsphy_g5_pcs[] = { - QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x05), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x05), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HS_G5_SYNC_LENGTH_CAPABILITY, 0x4d), diff --git a/drivers/phy/spacemit/phy-k1-usb2.c b/drivers/phy/spacemit/phy-k1-usb2.c index 342061380012..9215d0b223b2 100644 --- a/drivers/phy/spacemit/phy-k1-usb2.c +++ b/drivers/phy/spacemit/phy-k1-usb2.c @@ -48,6 +48,9 @@ #define PHY_CLK_HSTXP_EN BIT(3) /* clock hstxp enable */ #define PHY_HSTXP_MODE BIT(4) /* 0: force en_txp to be 1; 1: no force */ +#define PHY_K1_HS_HOST_DISC 0x40 +#define PHY_K1_HS_HOST_DISC_CLR BIT(0) + #define PHY_PLL_DIV_CFG 0x98 #define PHY_FDIV_FRACT_8_15 GENMASK(7, 0) #define PHY_FDIV_FRACT_16_19 GENMASK(11, 8) @@ -142,9 +145,20 @@ static int spacemit_usb2phy_exit(struct phy *phy) return 0; } +static int spacemit_usb2phy_disconnect(struct phy *phy, int port) +{ + struct spacemit_usb2phy *sphy = phy_get_drvdata(phy); + + regmap_update_bits(sphy->regmap_base, PHY_K1_HS_HOST_DISC, + PHY_K1_HS_HOST_DISC_CLR, PHY_K1_HS_HOST_DISC_CLR); + + return 0; +} + static const struct phy_ops spacemit_usb2phy_ops = { .init = spacemit_usb2phy_init, .exit = spacemit_usb2phy_exit, + .disconnect = spacemit_usb2phy_disconnect, .owner = THIS_MODULE, }; diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index 6e9ecb88dc8b..6b584706b913 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1425,6 +1425,7 @@ static int wiz_get_lane_phy_types(struct device *dev, struct wiz *wiz) dev_err(dev, "%s: Reading \"reg\" from \"%s\" failed: %d\n", __func__, subnode->name, ret); + of_node_put(serdes); return ret; } of_property_read_u32(subnode, "cdns,num-lanes", &num_lanes); @@ -1439,6 +1440,7 @@ static int wiz_get_lane_phy_types(struct device *dev, struct wiz *wiz) } } + of_node_put(serdes); return 0; } diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index d6a46fe0cda8..3f518dce6d23 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -1135,9 +1135,12 @@ int mtk_pctrl_init(struct platform_device *pdev, goto chip_error; } - ret = mtk_eint_init(pctl, pdev); - if (ret) - goto chip_error; + /* Only initialize EINT if we have EINT pins */ + if (data->eint_hw.ap_num > 0) { + ret = mtk_eint_init(pctl, pdev); + if (ret) + goto chip_error; + } return 0; diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 83f940fe30b2..d02d42513ebb 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -723,6 +723,21 @@ static const struct pinconf_ops pmic_gpio_pinconf_ops = { .pin_config_group_dbg_show = pmic_gpio_config_dbg_show, }; +static int pmic_gpio_get_direction(struct gpio_chip *chip, unsigned pin) +{ + struct pmic_gpio_state *state = gpiochip_get_data(chip); + struct pmic_gpio_pad *pad; + + pad = state->ctrl->desc->pins[pin].drv_data; + + if (!pad->is_enabled || pad->analog_pass || + (!pad->input_enabled && !pad->output_enabled)) + return -EINVAL; + + /* Make sure the state is aligned on what pmic_gpio_get() returns */ + return pad->input_enabled ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; +} + static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned pin) { struct pmic_gpio_state *state = gpiochip_get_data(chip); @@ -801,6 +816,7 @@ static void pmic_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) } static const struct gpio_chip pmic_gpio_gpio_template = { + .get_direction = pmic_gpio_get_direction, .direction_input = pmic_gpio_direction_input, .direction_output = pmic_gpio_direction_output, .get = pmic_gpio_get, diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c index bc8b9b9ad05b..d2949e4dbaf7 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza1.c +++ b/drivers/pinctrl/renesas/pinctrl-rza1.c @@ -589,7 +589,7 @@ static inline unsigned int rza1_get_bit(struct rza1_port *port, { void __iomem *mem = RZA1_ADDR(port->base, reg, port->id); - return ioread16(mem) & BIT(bit); + return !!(ioread16(mem) & BIT(bit)); } /** diff --git a/drivers/pinctrl/renesas/pinctrl-rzt2h.c b/drivers/pinctrl/renesas/pinctrl-rzt2h.c index 9949108a35bb..5927744c7a96 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzt2h.c +++ b/drivers/pinctrl/renesas/pinctrl-rzt2h.c @@ -85,7 +85,7 @@ struct rzt2h_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; DECLARE_BITMAP(used_irqs, RZT2H_INTERRUPTS_NUM); - spinlock_t lock; /* lock read/write registers */ + raw_spinlock_t lock; /* lock read/write registers */ struct mutex mutex; /* serialize adding groups and functions */ bool safety_port_enabled; atomic_t wakeup_path; @@ -145,7 +145,7 @@ static void rzt2h_pinctrl_set_pfc_mode(struct rzt2h_pinctrl *pctrl, u64 reg64; u16 reg16; - guard(spinlock_irqsave)(&pctrl->lock); + guard(raw_spinlock_irqsave)(&pctrl->lock); /* Set pin to 'Non-use (Hi-Z input protection)' */ reg16 = rzt2h_pinctrl_readw(pctrl, port, PM(port)); @@ -474,7 +474,7 @@ static int rzt2h_gpio_request(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - guard(spinlock_irqsave)(&pctrl->lock); + guard(raw_spinlock_irqsave)(&pctrl->lock); /* Select GPIO mode in PMC Register */ rzt2h_pinctrl_set_gpio_en(pctrl, port, bit, true); @@ -487,7 +487,7 @@ static void rzt2h_gpio_set_direction(struct rzt2h_pinctrl *pctrl, u32 port, { u16 reg; - guard(spinlock_irqsave)(&pctrl->lock); + guard(raw_spinlock_irqsave)(&pctrl->lock); reg = rzt2h_pinctrl_readw(pctrl, port, PM(port)); reg &= ~PM_PIN_MASK(bit); @@ -509,7 +509,7 @@ static int rzt2h_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - guard(spinlock_irqsave)(&pctrl->lock); + guard(raw_spinlock_irqsave)(&pctrl->lock); if (rzt2h_pinctrl_readb(pctrl, port, PMC(port)) & BIT(bit)) { /* @@ -547,7 +547,7 @@ static int rzt2h_gpio_set(struct gpio_chip *chip, unsigned int offset, u8 bit = RZT2H_PIN_ID_TO_PIN(offset); u8 reg; - guard(spinlock_irqsave)(&pctrl->lock); + guard(raw_spinlock_irqsave)(&pctrl->lock); reg = rzt2h_pinctrl_readb(pctrl, port, P(port)); if (value) @@ -833,6 +833,7 @@ static int rzt2h_gpio_register(struct rzt2h_pinctrl *pctrl) if (ret) return dev_err_probe(dev, ret, "Unable to parse gpio-ranges\n"); + of_node_put(of_args.np); if (of_args.args[0] != 0 || of_args.args[1] != 0 || of_args.args[2] != pctrl->data->n_port_pins) return dev_err_probe(dev, -EINVAL, @@ -964,7 +965,7 @@ static int rzt2h_pinctrl_probe(struct platform_device *pdev) if (ret) return ret; - spin_lock_init(&pctrl->lock); + raw_spin_lock_init(&pctrl->lock); mutex_init(&pctrl->mutex); platform_set_drvdata(pdev, pctrl); diff --git a/drivers/pinctrl/stm32/Kconfig b/drivers/pinctrl/stm32/Kconfig index 5f67e1ee66dd..d6a171523012 100644 --- a/drivers/pinctrl/stm32/Kconfig +++ b/drivers/pinctrl/stm32/Kconfig @@ -65,6 +65,7 @@ config PINCTRL_STM32_HDP select PINMUX select GENERIC_PINCONF select GPIOLIB + select GPIO_GENERIC help The Hardware Debug Port allows the observation of internal signals. It uses configurable multiplexer to route signals in a dedicated observation register. diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index c990b6118172..d3042e0c9712 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -157,6 +157,7 @@ sunxi_pinctrl_desc_find_function_by_name(struct sunxi_pinctrl *pctl, const char *pin_name, const char *func_name) { + unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK; int i; for (i = 0; i < pctl->desc->npins; i++) { @@ -168,7 +169,7 @@ sunxi_pinctrl_desc_find_function_by_name(struct sunxi_pinctrl *pctl, while (func->name) { if (!strcmp(func->name, func_name) && (!func->variant || - func->variant & pctl->variant)) + func->variant & variant)) return func; func++; @@ -209,6 +210,8 @@ sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl, const u16 pin_num, const u8 muxval) { + unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK; + for (unsigned int i = 0; i < pctl->desc->npins; i++) { const struct sunxi_desc_pin *pin = pctl->desc->pins + i; struct sunxi_desc_function *func = pin->functions; @@ -216,7 +219,7 @@ sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl, if (pin->pin.number != pin_num) continue; - if (pin->variant && !(pctl->variant & pin->variant)) + if (pin->variant && !(variant & pin->variant)) continue; while (func->name) { @@ -1089,6 +1092,9 @@ static int sunxi_pinctrl_irq_request_resources(struct irq_data *d) { struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d); struct sunxi_desc_function *func; + unsigned int offset; + u32 reg, shift, mask; + u8 disabled_mux, muxval; int ret; func = sunxi_pinctrl_desc_find_function_by_pin(pctl, @@ -1096,8 +1102,21 @@ static int sunxi_pinctrl_irq_request_resources(struct irq_data *d) if (!func) return -EINVAL; - ret = gpiochip_lock_as_irq(pctl->chip, - pctl->irq_array[d->hwirq] - pctl->desc->pin_base); + offset = pctl->irq_array[d->hwirq] - pctl->desc->pin_base; + sunxi_mux_reg(pctl, offset, ®, &shift, &mask); + muxval = (readl(pctl->membase + reg) & mask) >> shift; + + /* Change muxing to GPIO INPUT mode if at reset value */ + if (pctl->flags & SUNXI_PINCTRL_NEW_REG_LAYOUT) + disabled_mux = SUN4I_FUNC_DISABLED_NEW; + else + disabled_mux = SUN4I_FUNC_DISABLED_OLD; + + if (muxval == disabled_mux) + sunxi_pmx_set(pctl->pctl_dev, pctl->irq_array[d->hwirq], + SUN4I_FUNC_INPUT); + + ret = gpiochip_lock_as_irq(pctl->chip, offset); if (ret) { dev_err(pctl->dev, "unable to lock HW IRQ %lu for IRQ\n", irqd_to_hwirq(d)); @@ -1338,6 +1357,7 @@ static int sunxi_pinctrl_add_function(struct sunxi_pinctrl *pctl, static int sunxi_pinctrl_build_state(struct platform_device *pdev) { struct sunxi_pinctrl *pctl = platform_get_drvdata(pdev); + unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK; void *ptr; int i; @@ -1362,7 +1382,7 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) const struct sunxi_desc_pin *pin = pctl->desc->pins + i; struct sunxi_pinctrl_group *group = pctl->groups + pctl->ngroups; - if (pin->variant && !(pctl->variant & pin->variant)) + if (pin->variant && !(variant & pin->variant)) continue; group->name = pin->pin.name; @@ -1387,11 +1407,11 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) const struct sunxi_desc_pin *pin = pctl->desc->pins + i; struct sunxi_desc_function *func; - if (pin->variant && !(pctl->variant & pin->variant)) + if (pin->variant && !(variant & pin->variant)) continue; for (func = pin->functions; func->name; func++) { - if (func->variant && !(pctl->variant & func->variant)) + if (func->variant && !(variant & func->variant)) continue; /* Create interrupt mapping while we're at it */ @@ -1419,14 +1439,14 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) const struct sunxi_desc_pin *pin = pctl->desc->pins + i; struct sunxi_desc_function *func; - if (pin->variant && !(pctl->variant & pin->variant)) + if (pin->variant && !(variant & pin->variant)) continue; for (func = pin->functions; func->name; func++) { struct sunxi_pinctrl_function *func_item; const char **func_grp; - if (func->variant && !(pctl->variant & func->variant)) + if (func->variant && !(variant & func->variant)) continue; func_item = sunxi_pinctrl_find_function_by_name(pctl, @@ -1568,7 +1588,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev, pctl->dev = &pdev->dev; pctl->desc = desc; - pctl->variant = flags & SUNXI_PINCTRL_VARIANT_MASK; + pctl->flags = flags; if (flags & SUNXI_PINCTRL_NEW_REG_LAYOUT) { pctl->bank_mem_size = D1_BANK_MEM_SIZE; pctl->pull_regs_offset = D1_PULL_REGS_OFFSET; @@ -1604,8 +1624,9 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev, for (i = 0, pin_idx = 0; i < pctl->desc->npins; i++) { const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK; - if (pin->variant && !(pctl->variant & pin->variant)) + if (pin->variant && !(variant & pin->variant)) continue; pins[pin_idx++] = pin->pin; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index ad26e4de16a8..0daf7600e2fb 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -86,6 +86,8 @@ #define SUN4I_FUNC_INPUT 0 #define SUN4I_FUNC_IRQ 6 +#define SUN4I_FUNC_DISABLED_OLD 7 +#define SUN4I_FUNC_DISABLED_NEW 15 #define SUNXI_PINCTRL_VARIANT_MASK GENMASK(7, 0) #define SUNXI_PINCTRL_NEW_REG_LAYOUT BIT(8) @@ -174,7 +176,7 @@ struct sunxi_pinctrl { unsigned *irq_array; raw_spinlock_t lock; struct pinctrl_dev *pctl_dev; - unsigned long variant; + unsigned long flags; u32 bank_mem_size; u32 pull_regs_offset; u32 dlevel_field_width; diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c index fa7b3bda688a..bee271a4fda1 100644 --- a/drivers/platform/olpc/olpc-xo175-ec.c +++ b/drivers/platform/olpc/olpc-xo175-ec.c @@ -482,7 +482,7 @@ static int olpc_xo175_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *resp, dev_dbg(dev, "CMD %x, %zd bytes expected\n", cmd, resp_len); if (inlen > 5) { - dev_err(dev, "command len %zd too big!\n", resp_len); + dev_err(dev, "command len %zd too big!\n", inlen); return -EOVERFLOW; } diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c index 19f82c1d3090..631ffc0978d1 100644 --- a/drivers/platform/x86/amd/hsmp/hsmp.c +++ b/drivers/platform/x86/amd/hsmp/hsmp.c @@ -117,7 +117,7 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms } if (unlikely(mbox_status == HSMP_STATUS_NOT_READY)) { - dev_err(sock->dev, "Message ID 0x%X failure : SMU tmeout (status = 0x%X)\n", + dev_err(sock->dev, "Message ID 0x%X failure : SMU timeout (status = 0x%X)\n", msg->msg_id, mbox_status); return -ETIMEDOUT; } else if (unlikely(mbox_status == HSMP_ERR_INVALID_MSG)) { diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h index 208f6fe16168..569743746347 100644 --- a/drivers/platform/x86/asus-armoury.h +++ b/drivers/platform/x86/asus-armoury.h @@ -1082,6 +1082,20 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA503QM"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_def = 35, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 65, + .ppt_pl2_sppt_max = 80, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "GA503QR"), }, .driver_data = &(struct power_data) { @@ -1520,6 +1534,35 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GZ302EA"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 60, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 32, + .ppt_pl2_sppt_def = 75, + .ppt_pl2_sppt_max = 92, + .ppt_pl3_fppt_min = 45, + .ppt_pl3_fppt_def = 86, + .ppt_pl3_fppt_max = 93, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 45, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 32, + .ppt_pl2_sppt_def = 52, + .ppt_pl2_sppt_max = 92, + .ppt_pl3_fppt_min = 45, + .ppt_pl3_fppt_def = 71, + .ppt_pl3_fppt_max = 93, + }, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "G513I"), }, .driver_data = &(struct power_data) { @@ -1598,6 +1641,40 @@ static const struct dmi_system_id power_limits[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G614FP"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 30, + .ppt_pl1_spl_max = 120, + .ppt_pl2_sppt_min = 65, + .ppt_pl2_sppt_def = 140, + .ppt_pl2_sppt_max = 165, + .ppt_pl3_fppt_min = 65, + .ppt_pl3_fppt_def = 140, + .ppt_pl3_fppt_max = 165, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 15, + .nv_tgp_min = 50, + .nv_tgp_max = 100, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 65, + .ppt_pl2_sppt_min = 25, + .ppt_pl2_sppt_max = 65, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 75, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .requires_fan_curve = true, + }, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "G614J"), }, .driver_data = &(struct power_data) { diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index a38a65f5c550..b4677c5bba5b 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -548,7 +548,7 @@ static const struct dmi_system_id asus_quirks[] = { .callback = dmi_matched, .ident = "ASUS ROG Z13", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_SYS_VENDOR, "ASUS"), DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow Z13"), }, .driver_data = &quirk_asus_z13, diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 68ede7e5757a..988a0acc9622 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -120,6 +120,13 @@ static const struct thermal_profile_params omen_v1_thermal_params = { .ec_tp_offset = HP_VICTUS_S_EC_THERMAL_PROFILE_OFFSET, }; +static const struct thermal_profile_params omen_v1_legacy_thermal_params = { + .performance = HP_OMEN_V1_THERMAL_PROFILE_PERFORMANCE, + .balanced = HP_OMEN_V1_THERMAL_PROFILE_DEFAULT, + .low_power = HP_OMEN_V1_THERMAL_PROFILE_DEFAULT, + .ec_tp_offset = HP_OMEN_EC_THERMAL_PROFILE_OFFSET, +}; + /* * A generic pointer for the currently-active board's thermal profile * parameters. @@ -176,6 +183,10 @@ static const char * const victus_thermal_profile_boards[] = { /* DMI Board names of Victus 16-r and Victus 16-s laptops */ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = { { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8A4D") }, + .driver_data = (void *)&omen_v1_legacy_thermal_params, + }, + { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") }, .driver_data = (void *)&omen_v1_thermal_params, }, @@ -184,6 +195,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst .driver_data = (void *)&victus_s_thermal_params, }, { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCA") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, + { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") }, .driver_data = (void *)&omen_v1_thermal_params, }, @@ -196,6 +211,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst .driver_data = (void *)&victus_s_thermal_params, }, { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C76") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, + { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C78") }, .driver_data = (void *)&omen_v1_thermal_params, }, diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 95c405c8bac0..2ddd8af8c1ce 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -438,6 +438,14 @@ static int intel_hid_pl_suspend_handler(struct device *device) return 0; } +static int intel_hid_pl_freeze_handler(struct device *device) +{ + struct intel_hid_priv *priv = dev_get_drvdata(device); + + priv->wakeup_mode = false; + return intel_hid_pl_suspend_handler(device); +} + static int intel_hid_pl_resume_handler(struct device *device) { intel_hid_pm_complete(device); @@ -452,7 +460,7 @@ static int intel_hid_pl_resume_handler(struct device *device) static const struct dev_pm_ops intel_hid_pl_pm_ops = { .prepare = intel_hid_pm_prepare, .complete = intel_hid_pm_complete, - .freeze = intel_hid_pl_suspend_handler, + .freeze = intel_hid_pl_freeze_handler, .thaw = intel_hid_pl_resume_handler, .restore = intel_hid_pl_resume_handler, .suspend = intel_hid_pl_suspend_handler, diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index b8cdaa233ea9..e238c3105c78 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -558,6 +558,9 @@ static bool disable_dynamic_sst_features(void) { u64 value; + if (!static_cpu_has(X86_FEATURE_HWP)) + return true; + rdmsrq(MSR_PM_ENABLE, value); return !(value & 0x1); } @@ -869,7 +872,7 @@ static int isst_if_get_perf_level(void __user *argp) _read_pp_info("current_level", perf_level.current_level, SST_PP_STATUS_OFFSET, SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) _read_pp_info("locked", perf_level.locked, SST_PP_STATUS_OFFSET, - SST_PP_LOCK_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE) + SST_PP_LOCK_START, SST_PP_LOCK_WIDTH, SST_MUL_FACTOR_NONE) _read_pp_info("feature_state", perf_level.feature_state, SST_PP_STATUS_OFFSET, SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, SST_MUL_FACTOR_NONE) perf_level.enabled = !!(power_domain_info->sst_header.cap_mask & BIT(1)); diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.c b/drivers/platform/x86/lenovo/wmi-gamezone.c index 381836d29a96..c7fe7e3c9f17 100644 --- a/drivers/platform/x86/lenovo/wmi-gamezone.c +++ b/drivers/platform/x86/lenovo/wmi-gamezone.c @@ -31,8 +31,6 @@ #define LWMI_GZ_METHOD_ID_SMARTFAN_SET 44 #define LWMI_GZ_METHOD_ID_SMARTFAN_GET 45 -static BLOCKING_NOTIFIER_HEAD(gz_chain_head); - struct lwmi_gz_priv { enum thermal_mode current_mode; struct notifier_block event_nb; diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index a20fce04fe79..3dd2adda195e 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4966,7 +4966,8 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt) switch (mad_status) { case IBMVFC_MAD_SUCCESS: ibmvfc_dbg(vhost, "Discover Targets succeeded\n"); - vhost->num_targets = be32_to_cpu(rsp->num_written); + vhost->num_targets = min_t(u32, be32_to_cpu(rsp->num_written), + max_targets); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_ALLOC_TGTS); break; case IBMVFC_MAD_FAILED: diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 12124f9d5ccd..13412702188e 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -1734,7 +1734,7 @@ static int sas_user_scan(struct Scsi_Host *shost, uint channel, break; default: - if (channel < shost->max_channel) { + if (channel <= shost->max_channel) { res = scsi_scan_host_selected(shost, channel, id, lun, SCSI_SCAN_MANUAL); } else { diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 8e1686358e25..4c348645b04e 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -215,7 +215,7 @@ static unsigned char *ses_get_page2_descriptor(struct enclosure_device *edev, unsigned char *type_ptr = ses_dev->page1_types; unsigned char *desc_ptr = ses_dev->page2 + 8; - if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len) < 0) + if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len)) return NULL; for (i = 0; i < ses_dev->page1_num_types; i++, type_ptr += 4) { diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index b361c1bb3e43..45390e9b8cae 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -1009,7 +1009,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev) enable_irq(irq); } - ret = devm_spi_register_controller(&pdev->dev, controller); + ret = spi_register_controller(controller); if (ret < 0) { dev_err_probe(&pdev->dev, ret, "spi_register_controller error\n"); goto free_dma; @@ -1035,6 +1035,7 @@ static void fsl_lpspi_remove(struct platform_device *pdev) struct fsl_lpspi_data *fsl_lpspi = spi_controller_get_devdata(controller); + spi_unregister_controller(controller); fsl_lpspi_dma_exit(controller); pm_runtime_dont_use_autosuspend(fsl_lpspi->dev); diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index a7001b9e36e6..57768da3205d 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -1101,8 +1101,6 @@ static void meson_spicc_remove(struct platform_device *pdev) /* Disable SPI */ writel(0, spicc->base + SPICC_CONREG); - - spi_controller_put(spicc->host); } static const struct meson_spicc_data meson_spicc_gx_data = { diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c index bfcc140df810..3c61c799723b 100644 --- a/drivers/spi/spi-sn-f-ospi.c +++ b/drivers/spi/spi-sn-f-ospi.c @@ -612,7 +612,7 @@ static int f_ospi_probe(struct platform_device *pdev) u32 num_cs = OSPI_NUM_CS; int ret; - ctlr = spi_alloc_host(dev, sizeof(*ospi)); + ctlr = devm_spi_alloc_host(dev, sizeof(*ospi)); if (!ctlr) return -ENOMEM; @@ -635,43 +635,22 @@ static int f_ospi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ospi); ospi->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(ospi->base)) { - ret = PTR_ERR(ospi->base); - goto err_put_ctlr; - } + if (IS_ERR(ospi->base)) + return PTR_ERR(ospi->base); ospi->clk = devm_clk_get_enabled(dev, NULL); - if (IS_ERR(ospi->clk)) { - ret = PTR_ERR(ospi->clk); - goto err_put_ctlr; - } + if (IS_ERR(ospi->clk)) + return PTR_ERR(ospi->clk); - mutex_init(&ospi->mlock); - - ret = f_ospi_init(ospi); + ret = devm_mutex_init(dev, &ospi->mlock); if (ret) - goto err_destroy_mutex; + return ret; - ret = devm_spi_register_controller(dev, ctlr); + ret = f_ospi_init(ospi); if (ret) - goto err_destroy_mutex; - - return 0; - -err_destroy_mutex: - mutex_destroy(&ospi->mlock); - -err_put_ctlr: - spi_controller_put(ctlr); - - return ret; -} - -static void f_ospi_remove(struct platform_device *pdev) -{ - struct f_ospi *ospi = platform_get_drvdata(pdev); + return ret; - mutex_destroy(&ospi->mlock); + return devm_spi_register_controller(dev, ctlr); } static const struct of_device_id f_ospi_dt_ids[] = { @@ -686,7 +665,6 @@ static struct platform_driver f_ospi_driver = { .of_match_table = f_ospi_dt_ids, }, .probe = f_ospi_probe, - .remove = f_ospi_remove, }; module_platform_driver(f_ospi_driver); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 53dee314d76a..9b1125556d29 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -50,7 +50,6 @@ static void spidev_release(struct device *dev) struct spi_device *spi = to_spi_device(dev); spi_controller_put(spi->controller); - kfree(spi->driver_override); free_percpu(spi->pcpu_statistics); kfree(spi); } @@ -73,10 +72,9 @@ static ssize_t driver_override_store(struct device *dev, struct device_attribute *a, const char *buf, size_t count) { - struct spi_device *spi = to_spi_device(dev); int ret; - ret = driver_set_override(dev, &spi->driver_override, buf, count); + ret = __device_set_driver_override(dev, buf, count); if (ret) return ret; @@ -86,13 +84,8 @@ static ssize_t driver_override_store(struct device *dev, static ssize_t driver_override_show(struct device *dev, struct device_attribute *a, char *buf) { - const struct spi_device *spi = to_spi_device(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", spi->driver_override ? : ""); - device_unlock(dev); - return len; + guard(spinlock)(&dev->driver_override.lock); + return sysfs_emit(buf, "%s\n", dev->driver_override.name ?: ""); } static DEVICE_ATTR_RW(driver_override); @@ -376,10 +369,12 @@ static int spi_match_device(struct device *dev, const struct device_driver *drv) { const struct spi_device *spi = to_spi_device(dev); const struct spi_driver *sdrv = to_spi_driver(drv); + int ret; /* Check override first, and if set, only use the named driver */ - if (spi->driver_override) - return strcmp(spi->driver_override, drv->name) == 0; + ret = device_match_driver_override(dev, drv); + if (ret >= 0) + return ret; /* Attempt an OF style match */ if (of_driver_match_device(dev, drv)) @@ -3539,8 +3534,19 @@ int devm_spi_register_controller(struct device *dev, if (ret) return ret; - return devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr); + /* + * Prevent controller from being freed by spi_unregister_controller() + * if devm_add_action_or_reset() fails for a non-devres allocated + * controller. + */ + spi_controller_get(ctlr); + + ret = devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr); + if (ret == 0 || ctlr->devm_allocated) + spi_controller_put(ctlr); + + return ret; } EXPORT_SYMBOL_GPL(devm_spi_register_controller); diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index d668bd19fd4a..528883d989b8 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -26,6 +26,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/configfs.h> +#include <linux/blk-mq.h> #include <scsi/scsi.h> #include <scsi/scsi_tcq.h> #include <scsi/scsi_host.h> @@ -269,15 +270,27 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc) return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; } +static bool tcm_loop_flush_work_iter(struct request *rq, void *data) +{ + struct scsi_cmnd *sc = blk_mq_rq_to_pdu(rq); + struct tcm_loop_cmd *tl_cmd = scsi_cmd_priv(sc); + struct se_cmd *se_cmd = &tl_cmd->tl_se_cmd; + + flush_work(&se_cmd->work); + return true; +} + static int tcm_loop_target_reset(struct scsi_cmnd *sc) { struct tcm_loop_hba *tl_hba; struct tcm_loop_tpg *tl_tpg; + struct Scsi_Host *sh = sc->device->host; + int ret; /* * Locate the tcm_loop_hba_t pointer */ - tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); + tl_hba = *(struct tcm_loop_hba **)shost_priv(sh); if (!tl_hba) { pr_err("Unable to perform device reset without active I_T Nexus\n"); return FAILED; @@ -286,11 +299,38 @@ static int tcm_loop_target_reset(struct scsi_cmnd *sc) * Locate the tl_tpg pointer from TargetID in sc->device->id */ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id]; - if (tl_tpg) { - tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE; - return SUCCESS; - } - return FAILED; + if (!tl_tpg) + return FAILED; + + /* + * Issue a LUN_RESET to drain all commands that the target core + * knows about. This handles commands not yet marked CMD_T_COMPLETE. + */ + ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, 0, TMR_LUN_RESET); + if (ret != TMR_FUNCTION_COMPLETE) + return FAILED; + + /* + * Flush any deferred target core completion work that may still be + * queued. Commands that already had CMD_T_COMPLETE set before the TMR + * are skipped by the TMR drain, but their async completion work + * (transport_lun_remove_cmd → percpu_ref_put, release_cmd → scsi_done) + * may still be pending in target_completion_wq. + * + * The SCSI EH will reuse in-flight scsi_cmnd structures for recovery + * commands (e.g. TUR) immediately after this handler returns SUCCESS — + * if deferred work is still pending, the memset in queuecommand would + * zero the se_cmd while the work accesses it, leaking the LUN + * percpu_ref and hanging configfs unlink forever. + * + * Use blk_mq_tagset_busy_iter() to find all started requests and + * flush_work() on each — the same pattern used by mpi3mr, scsi_debug, + * and other SCSI drivers to drain outstanding commands during reset. + */ + blk_mq_tagset_busy_iter(&sh->tag_set, tcm_loop_flush_work_iter, NULL); + + tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE; + return SUCCESS; } static const struct scsi_host_template tcm_loop_driver_template = { diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 3ae1f7137d9d..3d593af30aa5 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -276,7 +276,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, ssize_t len = 0; int ret = 0, i; - aio_cmd = kmalloc_flex(*aio_cmd, bvecs, sgl_nents); + aio_cmd = kzalloc_flex(*aio_cmd, bvecs, sgl_nents); if (!aio_cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c index 49ff3bae7271..91f291627132 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c @@ -176,15 +176,21 @@ static inline void write_soc_slider(struct proc_thermal_device *proc_priv, u64 v static void set_soc_power_profile(struct proc_thermal_device *proc_priv, int slider) { + u8 offset; u64 val; val = read_soc_slider(proc_priv); val &= ~SLIDER_MASK; val |= FIELD_PREP(SLIDER_MASK, slider) | BIT(SLIDER_ENABLE_BIT); + if (slider == SOC_SLIDER_VALUE_MINIMUM || slider == SOC_SLIDER_VALUE_MAXIMUM) + offset = 0; + else + offset = slider_offset; + /* Set the slider offset from module params */ val &= ~SLIDER_OFFSET_MASK; - val |= FIELD_PREP(SLIDER_OFFSET_MASK, slider_offset); + val |= FIELD_PREP(SLIDER_OFFSET_MASK, offset); write_soc_slider(proc_priv, val); } diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c index 478beafc6ac3..b1d658b8f7b5 100644 --- a/drivers/vfio/pci/vfio_pci_dmabuf.c +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -301,11 +301,10 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags, */ ret = dma_buf_fd(priv->dmabuf, get_dma_buf.open_flags); if (ret < 0) - goto err_dma_buf; + dma_buf_put(priv->dmabuf); + return ret; -err_dma_buf: - dma_buf_put(priv->dmabuf); err_dev_put: vfio_device_put_registration(&vdev->vdev); err_free_phys: diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index 4252b147593a..7cee97559ba2 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -171,6 +171,8 @@ static void tdx_mr_deinit(const struct attribute_group *mr_grp) #define GET_QUOTE_SUCCESS 0 #define GET_QUOTE_IN_FLIGHT 0xffffffffffffffff +#define TDX_QUOTE_MAX_LEN (GET_QUOTE_BUF_SIZE - sizeof(struct tdx_quote_buf)) + /* struct tdx_quote_buf: Format of Quote request buffer. * @version: Quote format version, filled by TD. * @status: Status code of Quote request, filled by VMM. @@ -269,6 +271,7 @@ static int tdx_report_new_locked(struct tsm_report *report, void *data) u8 *buf; struct tdx_quote_buf *quote_buf = quote_data; struct tsm_report_desc *desc = &report->desc; + u32 out_len; int ret; u64 err; @@ -306,12 +309,17 @@ static int tdx_report_new_locked(struct tsm_report *report, void *data) return ret; } - buf = kvmemdup(quote_buf->data, quote_buf->out_len, GFP_KERNEL); + out_len = READ_ONCE(quote_buf->out_len); + + if (out_len > TDX_QUOTE_MAX_LEN) + return -EFBIG; + + buf = kvmemdup(quote_buf->data, out_len, GFP_KERNEL); if (!buf) return -ENOMEM; report->outblob = buf; - report->outblob_len = quote_buf->out_len; + report->outblob_len = out_len; /* * TODO: parse the PEM-formatted cert chain out of the quote buffer when diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 335692d41617..fbca7ce1c6bf 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2912,10 +2912,10 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf); * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * - * Same as virtqueue_add_inbuf but passes DMA_ATTR_CPU_CACHE_CLEAN to indicate - * that the CPU will not dirty any cacheline overlapping this buffer while it - * is available, and to suppress overlapping cacheline warnings in DMA debug - * builds. + * Same as virtqueue_add_inbuf but passes DMA_ATTR_DEBUGGING_IGNORE_CACHELINES + * to indicate that the CPU will not dirty any cacheline overlapping this buffer + * while it is available, and to suppress overlapping cacheline warnings in DMA + * debug builds. * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). @@ -2928,7 +2928,7 @@ int virtqueue_add_inbuf_cache_clean(struct virtqueue *vq, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, false, gfp, - DMA_ATTR_CPU_CACHE_CLEAN); + DMA_ATTR_DEBUGGING_IGNORE_CACHELINES); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_cache_clean); diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 1759cc18753f..15ba592236e8 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -12,6 +12,7 @@ #include <linux/eventfd.h> #include <linux/file.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/poll.h> @@ -30,7 +31,10 @@ #include <linux/seq_file.h> #include <linux/miscdevice.h> #include <linux/moduleparam.h> +#include <linux/notifier.h> +#include <linux/security.h> #include <linux/virtio_mmio.h> +#include <linux/wait.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -46,6 +50,7 @@ #include <xen/page.h> #include <xen/xen-ops.h> #include <xen/balloon.h> +#include <xen/xenbus.h> #ifdef CONFIG_XEN_ACPI #include <xen/acpi.h> #endif @@ -68,10 +73,20 @@ module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint, MODULE_PARM_DESC(dm_op_buf_max_size, "Maximum size of a dm_op hypercall buffer"); +static bool unrestricted; +module_param(unrestricted, bool, 0); +MODULE_PARM_DESC(unrestricted, + "Don't restrict hypercalls to target domain if running in a domU"); + struct privcmd_data { domid_t domid; }; +/* DOMID_INVALID implies no restriction */ +static domid_t target_domain = DOMID_INVALID; +static bool restrict_wait; +static DECLARE_WAIT_QUEUE_HEAD(restrict_wait_wq); + static int privcmd_vma_range_is_mapped( struct vm_area_struct *vma, unsigned long addr, @@ -1563,13 +1578,16 @@ static long privcmd_ioctl(struct file *file, static int privcmd_open(struct inode *ino, struct file *file) { - struct privcmd_data *data = kzalloc_obj(*data); + struct privcmd_data *data; + if (wait_event_interruptible(restrict_wait_wq, !restrict_wait) < 0) + return -EINTR; + + data = kzalloc_obj(*data); if (!data) return -ENOMEM; - /* DOMID_INVALID implies no restriction */ - data->domid = DOMID_INVALID; + data->domid = target_domain; file->private_data = data; return 0; @@ -1662,6 +1680,52 @@ static struct miscdevice privcmd_dev = { .fops = &xen_privcmd_fops, }; +static int init_restrict(struct notifier_block *notifier, + unsigned long event, + void *data) +{ + char *target; + unsigned int domid; + + /* Default to an guaranteed unused domain-id. */ + target_domain = DOMID_IDLE; + + target = xenbus_read(XBT_NIL, "target", "", NULL); + if (IS_ERR(target) || kstrtouint(target, 10, &domid)) { + pr_err("No target domain found, blocking all hypercalls\n"); + goto out; + } + + target_domain = domid; + + out: + if (!IS_ERR(target)) + kfree(target); + + restrict_wait = false; + wake_up_all(&restrict_wait_wq); + + return NOTIFY_DONE; +} + +static struct notifier_block xenstore_notifier = { + .notifier_call = init_restrict, +}; + +static void __init restrict_driver(void) +{ + if (unrestricted) { + if (security_locked_down(LOCKDOWN_XEN_USER_ACTIONS)) + pr_warn("Kernel is locked down, parameter \"unrestricted\" ignored\n"); + else + return; + } + + restrict_wait = true; + + register_xenstore_notifier(&xenstore_notifier); +} + static int __init privcmd_init(void) { int err; @@ -1669,6 +1733,9 @@ static int __init privcmd_init(void) if (!xen_domain()) return -ENODEV; + if (!xen_initial_domain()) + restrict_driver(); + err = misc_register(&privcmd_dev); if (err != 0) { pr_err("Could not register Xen privcmd device\n"); @@ -1698,6 +1765,9 @@ err_privcmdbuf: static void __exit privcmd_exit(void) { + if (!xen_initial_domain()) + unregister_xenstore_notifier(&xenstore_notifier); + privcmd_ioeventfd_exit(); privcmd_irqfd_exit(); misc_deregister(&privcmd_dev); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index ebf5079096af..c0d17a369bda 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -4583,7 +4583,7 @@ static void check_removing_space_info(struct btrfs_space_info *space_info) for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) { if (space_info->sub_group[i]) { check_removing_space_info(space_info->sub_group[i]); - kfree(space_info->sub_group[i]); + btrfs_sysfs_remove_space_info(space_info->sub_group[i]); space_info->sub_group[i] = NULL; } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 01f2dbb69832..1b0eb246b714 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2531,8 +2531,8 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info, if (mirror_num >= 0 && btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) { - btrfs_err(fs_info, "super offset mismatch %llu != %u", - btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET); + btrfs_err(fs_info, "super offset mismatch %llu != %llu", + btrfs_super_bytenr(sb), btrfs_sb_offset(mirror_num)); ret = -EINVAL; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 85ee5c79759d..098e64106d02 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -495,7 +495,7 @@ again: btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_DATA_REF_KEY) - return ret; + return -ENOENT; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ab0d460c7139..ac871efb9763 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4616,21 +4616,32 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, struct inode *inode, bool log_inode_only, u64 logged_isize) { + u64 gen = BTRFS_I(inode)->generation; u64 flags; if (log_inode_only) { - /* set the generation to zero so the recover code - * can tell the difference between an logging - * just to say 'this inode exists' and a logging - * to say 'update this inode with these values' + /* + * Set the generation to zero so the recover code can tell the + * difference between a logging just to say 'this inode exists' + * and a logging to say 'update this inode with these values'. + * But only if the inode was not already logged before. + * We access ->logged_trans directly since it was already set + * up in the call chain by btrfs_log_inode(), and data_race() + * to avoid false alerts from KCSAN and since it was set already + * and one can set it to 0 since that only happens on eviction + * and we are holding a ref on the inode. */ - btrfs_set_inode_generation(leaf, item, 0); + ASSERT(data_race(BTRFS_I(inode)->logged_trans) > 0); + if (data_race(BTRFS_I(inode)->logged_trans) < trans->transid) + gen = 0; + btrfs_set_inode_size(leaf, item, logged_isize); } else { - btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation); btrfs_set_inode_size(leaf, item, inode->i_size); } + btrfs_set_inode_generation(leaf, item, gen); + btrfs_set_inode_uid(leaf, item, i_uid_read(inode)); btrfs_set_inode_gid(leaf, item, i_gid_read(inode)); btrfs_set_inode_mode(leaf, item, inode->i_mode); @@ -5448,42 +5459,63 @@ process: return 0; } -static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, - struct btrfs_path *path, u64 *size_ret) +static int get_inode_size_to_log(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; + struct btrfs_inode_item *item; int ret; key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, log, &key, path, 0, 0); - if (ret < 0) { - return ret; - } else if (ret > 0) { - *size_ret = 0; - } else { - struct btrfs_inode_item *item; + /* + * Our caller called inode_logged(), so logged_trans is up to date. + * Use data_race() to silence any warning from KCSAN. Once logged_trans + * is set, it can only be reset to 0 after inode eviction. + */ + if (data_race(inode->logged_trans) == trans->transid) { + ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); + } else if (inode->generation < trans->transid) { + path->search_commit_root = true; + path->skip_locking = true; + ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0); + path->search_commit_root = false; + path->skip_locking = false; - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_item); - *size_ret = btrfs_inode_size(path->nodes[0], item); - /* - * If the in-memory inode's i_size is smaller then the inode - * size stored in the btree, return the inode's i_size, so - * that we get a correct inode size after replaying the log - * when before a power failure we had a shrinking truncate - * followed by addition of a new name (rename / new hard link). - * Otherwise return the inode size from the btree, to avoid - * data loss when replaying a log due to previously doing a - * write that expands the inode's size and logging a new name - * immediately after. - */ - if (*size_ret > inode->vfs_inode.i_size) - *size_ret = inode->vfs_inode.i_size; + } else { + *size_ret = 0; + return 0; } + /* + * If the inode was logged before or is from a past transaction, then + * its inode item must exist in the log root or in the commit root. + */ + ASSERT(ret <= 0); + if (WARN_ON_ONCE(ret > 0)) + ret = -ENOENT; + + if (ret < 0) + return ret; + + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_item); + *size_ret = btrfs_inode_size(path->nodes[0], item); + /* + * If the in-memory inode's i_size is smaller then the inode size stored + * in the btree, return the inode's i_size, so that we get a correct + * inode size after replaying the log when before a power failure we had + * a shrinking truncate followed by addition of a new name (rename / new + * hard link). Otherwise return the inode size from the btree, to avoid + * data loss when replaying a log due to previously doing a write that + * expands the inode's size and logging a new name immediately after. + */ + if (*size_ret > inode->vfs_inode.i_size) + *size_ret = inode->vfs_inode.i_size; + btrfs_release_path(path); return 0; } @@ -6996,7 +7028,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, ret = drop_inode_items(trans, log, path, inode, BTRFS_XATTR_ITEM_KEY); } else { - if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) { + if (inode_only == LOG_INODE_EXISTS) { /* * Make sure the new inode item we write to the log has * the same isize as the current one (if it exists). @@ -7010,7 +7042,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ - ret = logged_inode_size(log, inode, path, &logged_isize); + ret = get_inode_size_to_log(trans, inode, path, &logged_isize); if (ret) goto out_unlock; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ab51e6ecfdef..6b8e810a35ce 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -8099,8 +8099,9 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans) smp_rmb(); ret = update_dev_stat_item(trans, device); - if (!ret) - atomic_sub(stats_cnt, &device->dev_stats_ccnt); + if (ret) + break; + atomic_sub(stats_cnt, &device->dev_stats_ccnt); } mutex_unlock(&fs_devices->device_list_mutex); diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 1b7544aa88a2..c676e715b4f8 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -308,7 +308,9 @@ int zlib_compress_bio(struct list_head *ws, struct compressed_bio *cb) } /* Queue the remaining part of the folio. */ if (workspace->strm.total_out > bio->bi_iter.bi_size) { - u32 cur_len = offset_in_folio(out_folio, workspace->strm.total_out); + const u32 cur_len = workspace->strm.total_out - bio->bi_iter.bi_size; + + ASSERT(cur_len <= folio_size(out_folio)); if (!bio_add_folio(bio, out_folio, cur_len, 0)) { ret = -E2BIG; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index a9f645f57bb2..97c48ebe8458 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -16,22 +16,36 @@ config EROFS_FS select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD help - EROFS (Enhanced Read-Only File System) is a lightweight read-only - file system with modern designs (e.g. no buffer heads, inline - xattrs/data, chunk-based deduplication, multiple devices, etc.) for - scenarios which need high-performance read-only solutions, e.g. - smartphones with Android OS, LiveCDs and high-density hosts with - numerous containers; - - It also provides transparent compression and deduplication support to - improve storage density and maintain relatively high compression - ratios, and it implements in-place decompression to temporarily reuse - page cache for compressed data using proper strategies, which is - quite useful for ensuring guaranteed end-to-end runtime decompression + EROFS (Enhanced Read-Only File System) is a modern, lightweight, + secure read-only filesystem for various use cases, such as immutable + system images, container images, application sandboxes, and datasets. + + EROFS uses a flexible, hierarchical on-disk design so that features + can be enabled on demand: the core on-disk format is block-aligned in + order to perform optimally on all kinds of devices, including block + and memory-backed devices; the format is easy to parse and has zero + metadata redundancy, unlike generic filesystems, making it ideal for + filesystem auditing and remote access; inline data, random-access + friendly directory data, inline/shared extended attributes and + chunk-based deduplication ensure space efficiency while maintaining + high performance. + + Optionally, it supports multiple devices to reference external data, + enabling data sharing for container images. + + It also has advanced encoded on-disk layouts, particularly for data + compression and fine-grained deduplication. It utilizes fixed-size + output compression to improve storage density while keeping relatively + high compression ratios. Furthermore, it implements in-place + decompression to reuse file pages to keep compressed data temporarily + with proper strategies, which ensures guaranteed end-to-end runtime performance under extreme memory pressure without extra cost. - See the documentation at <file:Documentation/filesystems/erofs.rst> - and the web pages at <https://erofs.docs.kernel.org> for more details. + For more details, see the web pages at <https://erofs.docs.kernel.org> + and the documentation at <file:Documentation/filesystems/erofs.rst>. + + To compile EROFS filesystem support as a module, choose M here. The + module will be called erofs. If unsure, say N. @@ -105,7 +119,8 @@ config EROFS_FS_ZIP depends on EROFS_FS default y help - Enable transparent compression support for EROFS file systems. + Enable EROFS compression layouts so that filesystems containing + compressed files can be parsed by the kernel. If you don't want to enable compression feature, say N. diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index abe873f01297..98cdaa1cd1a7 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -25,10 +25,8 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret) container_of(iocb, struct erofs_fileio_rq, iocb); struct folio_iter fi; - if (ret >= 0 && ret != rq->bio.bi_iter.bi_size) { - bio_advance(&rq->bio, ret); - zero_fill_bio(&rq->bio); - } + if (ret >= 0 && ret != rq->bio.bi_iter.bi_size) + ret = -EIO; if (!rq->bio.bi_end_io) { bio_for_each_folio_all(fi, &rq->bio) { DBG_BUGON(folio_test_uptodate(fi.folio)); diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c index 829d50d5c717..ec433bacc592 100644 --- a/fs/erofs/ishare.c +++ b/fs/erofs/ishare.c @@ -200,8 +200,19 @@ struct inode *erofs_real_inode(struct inode *inode, bool *need_iput) int __init erofs_init_ishare(void) { - erofs_ishare_mnt = kern_mount(&erofs_anon_fs_type); - return PTR_ERR_OR_ZERO(erofs_ishare_mnt); + struct vfsmount *mnt; + int ret; + + mnt = kern_mount(&erofs_anon_fs_type); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + /* generic_fadvise() doesn't work if s_bdi == &noop_backing_dev_info */ + ret = super_setup_bdi(mnt->mnt_sb); + if (ret) + kern_unmount(mnt); + else + erofs_ishare_mnt = mnt; + return ret; } void erofs_exit_ishare(void) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 3977e42b9516..fe8121df9ef2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1445,6 +1445,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, int bios) { struct erofs_sb_info *const sbi = EROFS_SB(io->sb); + int gfp_flag; /* wake up the caller thread for sync decompression */ if (io->sync) { @@ -1477,7 +1478,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, sbi->sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON; return; } + gfp_flag = memalloc_noio_save(); z_erofs_decompressqueue_work(&io->u.work); + memalloc_noio_restore(gfp_flag); } static void z_erofs_fill_bio_vec(struct bio_vec *bvec, diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 72206a292676..3baee4e7c1cf 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -14,7 +14,8 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \ ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o -ext4-inode-test-objs += inode-test.o -obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-inode-test.o +ext4-test-objs += inode-test.o mballoc-test.o \ + extents-test.o +obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-test.o ext4-$(CONFIG_FS_VERITY) += verity.o ext4-$(CONFIG_FS_ENCRYPTION) += crypto.o diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index cf0a0970c095..f41f320f4437 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -163,10 +163,17 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, */ if (handle) { + /* + * Since the inode is new it is ok to pass the + * XATTR_CREATE flag. This is necessary to match the + * remaining journal credits check in the set_handle + * function with the credits allocated for the new + * inode. + */ res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); + ctx, len, XATTR_CREATE); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); ext4_clear_inode_state(inode, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 293f698b7042..7617e2d454ea 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1570,6 +1570,7 @@ struct ext4_sb_info { struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; + struct mutex s_error_notify_mutex; /* protects sysfs_notify vs kobject_del */ struct super_block *s_sb; struct buffer_head *s_mmp_bh; @@ -3944,6 +3945,11 @@ static inline bool ext4_inode_can_atomic_write(struct inode *inode) extern int ext4_block_write_begin(handle_t *handle, struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); + +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +#define EXPORT_SYMBOL_FOR_EXT4_TEST(sym) \ + EXPORT_SYMBOL_FOR_MODULES(sym, "ext4-test") +#endif #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index c484125d963f..ebaf7cc42430 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -264,5 +264,17 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } +extern int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path); +extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex); +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +extern int ext4_ext_space_root_idx_test(struct inode *inode, int check); +extern struct ext4_ext_path *ext4_split_convert_extents_test( + handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path, + int flags, unsigned int *allocated); +#endif #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c index 7c4690eb7dad..5496b2c8e2cd 100644 --- a/fs/ext4/extents-test.c +++ b/fs/ext4/extents-test.c @@ -142,8 +142,10 @@ static struct file_system_type ext_fs_type = { static void extents_kunit_exit(struct kunit *test) { - struct ext4_sb_info *sbi = k_ctx.k_ei->vfs_inode.i_sb->s_fs_info; + struct super_block *sb = k_ctx.k_ei->vfs_inode.i_sb; + struct ext4_sb_info *sbi = sb->s_fs_info; + ext4_es_unregister_shrinker(sbi); kfree(sbi); kfree(k_ctx.k_ei); kfree(k_ctx.k_data); @@ -280,8 +282,8 @@ static int extents_kunit_init(struct kunit *test) eh->eh_depth = 0; eh->eh_entries = cpu_to_le16(1); eh->eh_magic = EXT4_EXT_MAGIC; - eh->eh_max = - cpu_to_le16(ext4_ext_space_root_idx(&k_ctx.k_ei->vfs_inode, 0)); + eh->eh_max = cpu_to_le16(ext4_ext_space_root_idx_test( + &k_ctx.k_ei->vfs_inode, 0)); eh->eh_generation = 0; /* @@ -384,8 +386,8 @@ static void test_split_convert(struct kunit *test) switch (param->type) { case TEST_SPLIT_CONVERT: - path = ext4_split_convert_extents(NULL, inode, &map, path, - param->split_flags, NULL); + path = ext4_split_convert_extents_test(NULL, inode, &map, + path, param->split_flags, NULL); break; case TEST_CREATE_BLOCKS: ext4_map_create_blocks_helper(test, inode, &map, param->split_flags); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ae3804f36535..8cce1479be6d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -184,9 +184,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -static int __ext4_ext_dirty(const char *where, unsigned int line, - handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) +int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) { int err; @@ -1736,6 +1736,13 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; + if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { + EXT4_ERROR_INODE(inode, + "path[%d].p_idx %p > EXT_LAST_INDEX %p", + k, path[k].p_idx, + EXT_LAST_INDEX(path[k].p_hdr)); + return -EFSCORRUPTED; + } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) @@ -1748,6 +1755,14 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; + if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { + EXT4_ERROR_INODE(inode, + "path[%d].p_idx %p > EXT_LAST_INDEX %p", + k, path[k].p_idx, + EXT_LAST_INDEX(path[k].p_hdr)); + err = -EFSCORRUPTED; + goto clean; + } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) @@ -3144,7 +3159,7 @@ static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) } /* FIXME!! we need to try to merge to left or right after zero-out */ -static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) +int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; @@ -3239,6 +3254,9 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, insert_err = PTR_ERR(path); err = 0; + if (insert_err != -ENOSPC && insert_err != -EDQUOT && + insert_err != -ENOMEM) + goto out_path; /* * Get a new path to try to zeroout or fix the extent length. @@ -3255,13 +3273,20 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, goto out_path; } + depth = ext_depth(inode); + ex = path[depth].p_ext; + if (!ex) { + EXT4_ERROR_INODE(inode, + "bad extent address lblock: %lu, depth: %d pblock %llu", + (unsigned long)ee_block, depth, path[depth].p_block); + err = -EFSCORRUPTED; + goto out; + } + err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; - depth = ext_depth(inode); - ex = path[depth].p_ext; - fix_extent_len: ex->ee_len = orig_ex.ee_len; err = ext4_ext_dirty(handle, inode, path + path->p_depth); @@ -3363,7 +3388,7 @@ static int ext4_split_extent_zeroout(handle_t *handle, struct inode *inode, ext4_ext_mark_initialized(ex); - ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + depth); if (err) return err; @@ -4457,9 +4482,13 @@ got_allocated_blocks: path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (IS_ERR(path)) { err = PTR_ERR(path); - if (allocated_clusters) { + /* + * Gracefully handle out of space conditions. If the filesystem + * is inconsistent, we'll just leak allocated blocks to avoid + * causing even more damage. + */ + if (allocated_clusters && (err == -EDQUOT || err == -ENOSPC)) { int fb_flags = 0; - /* * free data blocks we just allocated. * not a good idea to call discard here directly, @@ -6238,6 +6267,33 @@ out: return 0; } -#ifdef CONFIG_EXT4_KUNIT_TESTS -#include "extents-test.c" +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +int ext4_ext_space_root_idx_test(struct inode *inode, int check) +{ + return ext4_ext_space_root_idx(inode, check); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_space_root_idx_test); + +struct ext4_ext_path *ext4_split_convert_extents_test(handle_t *handle, + struct inode *inode, struct ext4_map_blocks *map, + struct ext4_ext_path *path, int flags, + unsigned int *allocated) +{ + return ext4_split_convert_extents(handle, inode, map, path, + flags, allocated); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_split_convert_extents_test); + +EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_insert_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_insert_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_find_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_issue_zeroout); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_query_blocks); #endif diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index f575751f1cae..2f0057e04934 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -975,13 +975,13 @@ static int ext4_fc_flush_data(journal_t *journal) int ret = 0; list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_submit_inode_data(journal, ei->jinode); + ret = jbd2_submit_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_wait_inode_data(journal, ei->jinode); + ret = jbd2_wait_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } @@ -1613,19 +1613,21 @@ static int ext4_fc_replay_inode(struct super_block *sb, /* Immediately update the inode on disk. */ ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); if (ret) - goto out; + goto out_brelse; ret = sync_dirty_buffer(iloc.bh); if (ret) - goto out; + goto out_brelse; ret = ext4_mark_inode_used(sb, ino); if (ret) - goto out; + goto out_brelse; /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); - return -EFSCORRUPTED; + inode = NULL; + ret = -EFSCORRUPTED; + goto out_brelse; } /* @@ -1642,13 +1644,14 @@ static int ext4_fc_replay_inode(struct super_block *sb, ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode)); ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); sync_dirty_buffer(iloc.bh); +out_brelse: brelse(iloc.bh); out: iput(inode); if (!ret) blkdev_issue_flush(sb->s_bdev); - return 0; + return ret; } /* diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index e476c6de3074..bd8f230fa507 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -83,11 +83,23 @@ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end, int datasync, bool *needs_barrier) { struct inode *inode = file->f_inode; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + }; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); - if (!ret) - ret = ext4_sync_parent(inode); + if (ret) + return ret; + + /* Force writeout of inode table buffer to disk */ + ret = ext4_write_inode(inode, &wbc); + if (ret) + return ret; + + ret = ext4_sync_parent(inode); + if (test_opt(inode->i_sb, BARRIER)) *needs_barrier = true; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b20a1bf866ab..b1bc1950c9f0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -686,6 +686,12 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) if (unlikely(!gdp)) return 0; + /* Inode was never used in this filesystem? */ + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT) || + ino >= EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp))) + return 0; + bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) + (ino / inodes_per_block)); if (!bh || !buffer_uptodate(bh)) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 1f6bc05593df..408677fa8196 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -522,7 +522,15 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio) goto out; len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); - BUG_ON(len > PAGE_SIZE); + + if (len > PAGE_SIZE) { + ext4_error_inode(inode, __func__, __LINE__, 0, + "inline size %zu exceeds PAGE_SIZE", len); + ret = -EFSCORRUPTED; + brelse(iloc.bh); + goto out; + } + kaddr = kmap_local_folio(folio, 0); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); kaddr = folio_zero_tail(folio, len, kaddr + len); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 396dc3a5d16b..1123d995494b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -128,6 +128,8 @@ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { + struct jbd2_inode *jinode = READ_ONCE(EXT4_I(inode)->jinode); + trace_ext4_begin_ordered_truncate(inode, new_size); /* * If jinode is zero, then we never opened the file for @@ -135,10 +137,10 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, * jbd2_journal_begin_ordered_truncate() since there's no * outstanding writes we need to flush. */ - if (!EXT4_I(inode)->jinode) + if (!jinode) return 0; return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode), - EXT4_I(inode)->jinode, + jinode, new_size); } @@ -184,6 +186,14 @@ void ext4_evict_inode(struct inode *inode) if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) ext4_evict_ea_inode(inode); if (inode->i_nlink) { + /* + * If there's dirty page will lead to data loss, user + * could see stale data. + */ + if (unlikely(!ext4_emergency_state(inode->i_sb) && + mapping_tagged(&inode->i_data, PAGECACHE_TAG_DIRTY))) + ext4_warning_inode(inode, "data will be lost"); + truncate_inode_pages_final(&inode->i_data); goto no_delete; @@ -4451,8 +4461,13 @@ int ext4_inode_attach_jinode(struct inode *inode) spin_unlock(&inode->i_lock); return -ENOMEM; } - ei->jinode = jinode; - jbd2_journal_init_jbd_inode(ei->jinode, inode); + jbd2_journal_init_jbd_inode(jinode, inode); + /* + * Publish ->jinode only after it is fully initialized so that + * readers never observe a partially initialized jbd2_inode. + */ + smp_wmb(); + WRITE_ONCE(ei->jinode, jinode); jinode = NULL; } spin_unlock(&inode->i_lock); @@ -5401,18 +5416,36 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode->i_op = &ext4_encrypted_symlink_inode_operations; } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; - if (inode->i_size == 0 || - inode->i_size >= sizeof(ei->i_data) || - strnlen((char *)ei->i_data, inode->i_size + 1) != - inode->i_size) { - ext4_error_inode(inode, function, line, 0, - "invalid fast symlink length %llu", - (unsigned long long)inode->i_size); - ret = -EFSCORRUPTED; - goto bad_inode; + + /* + * Orphan cleanup can see inodes with i_size == 0 + * and i_data uninitialized. Skip size checks in + * that case. This is safe because the first thing + * ext4_evict_inode() does for fast symlinks is + * clearing of i_data and i_size. + */ + if ((EXT4_SB(sb)->s_mount_state & EXT4_ORPHAN_FS)) { + if (inode->i_nlink != 0) { + ext4_error_inode(inode, function, line, 0, + "invalid orphan symlink nlink %d", + inode->i_nlink); + ret = -EFSCORRUPTED; + goto bad_inode; + } + } else { + if (inode->i_size == 0 || + inode->i_size >= sizeof(ei->i_data) || + strnlen((char *)ei->i_data, inode->i_size + 1) != + inode->i_size) { + ext4_error_inode(inode, function, line, 0, + "invalid fast symlink length %llu", + (unsigned long long)inode->i_size); + ret = -EFSCORRUPTED; + goto bad_inode; + } + inode_set_cached_link(inode, (char *)ei->i_data, + inode->i_size); } - inode_set_cached_link(inode, (char *)ei->i_data, - inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; } @@ -5849,6 +5882,18 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_size == inode->i_size) inc_ivers = false; + /* + * If file has inline data but new size exceeds inline capacity, + * convert to extent-based storage first to prevent inconsistent + * state (inline flag set but size exceeds inline capacity). + */ + if (ext4_has_inline_data(inode) && + attr->ia_size > EXT4_I(inode)->i_inline_size) { + error = ext4_convert_inline_data(inode); + if (error) + goto err_out; + } + if (shrink) { if (ext4_should_order_data(inode)) { error = ext4_begin_ordered_truncate(inode, diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c index 9fbdf6a09489..6f5bfbb0e8a4 100644 --- a/fs/ext4/mballoc-test.c +++ b/fs/ext4/mballoc-test.c @@ -8,6 +8,7 @@ #include <linux/random.h> #include "ext4.h" +#include "mballoc.h" struct mbt_grp_ctx { struct buffer_head bitmap_bh; @@ -336,7 +337,7 @@ ext4_mb_mark_context_stub(handle_t *handle, struct super_block *sb, bool state, if (state) mb_set_bits(bitmap_bh->b_data, blkoff, len); else - mb_clear_bits(bitmap_bh->b_data, blkoff, len); + mb_clear_bits_test(bitmap_bh->b_data, blkoff, len); return 0; } @@ -413,14 +414,14 @@ static void test_new_blocks_simple(struct kunit *test) /* get block at goal */ ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ar.goal, found, "failed to alloc block at goal, expected %llu found %llu", ar.goal, found); /* get block after goal in goal group */ ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found, "failed to alloc block after goal in goal group, expected %llu found %llu", ar.goal + 1, found); @@ -428,7 +429,7 @@ static void test_new_blocks_simple(struct kunit *test) /* get block after goal group */ mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ext4_group_first_block_no(sb, goal_group + 1), found, "failed to alloc block after goal group, expected %llu found %llu", @@ -438,7 +439,7 @@ static void test_new_blocks_simple(struct kunit *test) for (i = goal_group; i < ext4_get_groups_count(sb); i++) mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found, "failed to alloc block before goal group, expected %llu found %llu", @@ -448,7 +449,7 @@ static void test_new_blocks_simple(struct kunit *test) for (i = 0; i < ext4_get_groups_count(sb); i++) mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_NE_MSG(test, err, 0, "unexpectedly get block when no block is available"); } @@ -492,16 +493,16 @@ validate_free_blocks_simple(struct kunit *test, struct super_block *sb, continue; bitmap = mbt_ctx_bitmap(sb, i); - bit = mb_find_next_zero_bit(bitmap, max, 0); + bit = mb_find_next_zero_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ_MSG(test, bit, max, "free block on unexpected group %d", i); } bitmap = mbt_ctx_bitmap(sb, goal_group); - bit = mb_find_next_zero_bit(bitmap, max, 0); + bit = mb_find_next_zero_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ(test, bit, start); - bit = mb_find_next_bit(bitmap, max, bit + 1); + bit = mb_find_next_bit_test(bitmap, max, bit + 1); KUNIT_ASSERT_EQ(test, bit, start + len); } @@ -524,7 +525,7 @@ test_free_blocks_simple_range(struct kunit *test, ext4_group_t goal_group, block = ext4_group_first_block_no(sb, goal_group) + EXT4_C2B(sbi, start); - ext4_free_blocks_simple(inode, block, len); + ext4_free_blocks_simple_test(inode, block, len); validate_free_blocks_simple(test, sb, goal_group, start, len); mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); } @@ -566,15 +567,15 @@ test_mark_diskspace_used_range(struct kunit *test, bitmap = mbt_ctx_bitmap(sb, TEST_GOAL_GROUP); memset(bitmap, 0, sb->s_blocksize); - ret = ext4_mb_mark_diskspace_used(ac, NULL); + ret = ext4_mb_mark_diskspace_used_test(ac, NULL); KUNIT_ASSERT_EQ(test, ret, 0); max = EXT4_CLUSTERS_PER_GROUP(sb); - i = mb_find_next_bit(bitmap, max, 0); + i = mb_find_next_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ(test, i, start); - i = mb_find_next_zero_bit(bitmap, max, i + 1); + i = mb_find_next_zero_bit_test(bitmap, max, i + 1); KUNIT_ASSERT_EQ(test, i, start + len); - i = mb_find_next_bit(bitmap, max, i + 1); + i = mb_find_next_bit_test(bitmap, max, i + 1); KUNIT_ASSERT_EQ(test, max, i); } @@ -617,54 +618,54 @@ static void mbt_generate_buddy(struct super_block *sb, void *buddy, max = EXT4_CLUSTERS_PER_GROUP(sb); bb_h = buddy + sbi->s_mb_offsets[1]; - off = mb_find_next_zero_bit(bb, max, 0); + off = mb_find_next_zero_bit_test(bb, max, 0); grp->bb_first_free = off; while (off < max) { grp->bb_counters[0]++; grp->bb_free++; - if (!(off & 1) && !mb_test_bit(off + 1, bb)) { + if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) { grp->bb_free++; grp->bb_counters[0]--; - mb_clear_bit(off >> 1, bb_h); + mb_clear_bit_test(off >> 1, bb_h); grp->bb_counters[1]++; grp->bb_largest_free_order = 1; off++; } - off = mb_find_next_zero_bit(bb, max, off + 1); + off = mb_find_next_zero_bit_test(bb, max, off + 1); } for (order = 1; order < MB_NUM_ORDERS(sb) - 1; order++) { bb = buddy + sbi->s_mb_offsets[order]; bb_h = buddy + sbi->s_mb_offsets[order + 1]; max = max >> 1; - off = mb_find_next_zero_bit(bb, max, 0); + off = mb_find_next_zero_bit_test(bb, max, 0); while (off < max) { - if (!(off & 1) && !mb_test_bit(off + 1, bb)) { + if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) { mb_set_bits(bb, off, 2); grp->bb_counters[order] -= 2; - mb_clear_bit(off >> 1, bb_h); + mb_clear_bit_test(off >> 1, bb_h); grp->bb_counters[order + 1]++; grp->bb_largest_free_order = order + 1; off++; } - off = mb_find_next_zero_bit(bb, max, off + 1); + off = mb_find_next_zero_bit_test(bb, max, off + 1); } } max = EXT4_CLUSTERS_PER_GROUP(sb); - off = mb_find_next_zero_bit(bitmap, max, 0); + off = mb_find_next_zero_bit_test(bitmap, max, 0); while (off < max) { grp->bb_fragments++; - off = mb_find_next_bit(bitmap, max, off + 1); + off = mb_find_next_bit_test(bitmap, max, off + 1); if (off + 1 >= max) break; - off = mb_find_next_zero_bit(bitmap, max, off + 1); + off = mb_find_next_zero_bit_test(bitmap, max, off + 1); } } @@ -706,7 +707,7 @@ do_test_generate_buddy(struct kunit *test, struct super_block *sb, void *bitmap, /* needed by validation in ext4_mb_generate_buddy */ ext4_grp->bb_free = mbt_grp->bb_free; memset(ext4_buddy, 0xff, sb->s_blocksize); - ext4_mb_generate_buddy(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP, + ext4_mb_generate_buddy_test(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP, ext4_grp); KUNIT_ASSERT_EQ(test, memcmp(mbt_buddy, ext4_buddy, sb->s_blocksize), @@ -760,7 +761,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b, ex.fe_group = TEST_GOAL_GROUP; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(e4b, &ex); + mb_mark_used_test(e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); mb_set_bits(bitmap, start, len); @@ -769,7 +770,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b, memset(buddy, 0xff, sb->s_blocksize); for (i = 0; i < MB_NUM_ORDERS(sb); i++) grp->bb_counters[i] = 0; - ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp); + ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp); KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize), 0); @@ -798,7 +799,7 @@ static void test_mb_mark_used(struct kunit *test) bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); grp->bb_free = EXT4_CLUSTERS_PER_GROUP(sb); @@ -809,7 +810,7 @@ static void test_mb_mark_used(struct kunit *test) test_mb_mark_used_range(test, &e4b, ranges[i].start, ranges[i].len, bitmap, buddy, grp); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } static void @@ -825,16 +826,16 @@ test_mb_free_blocks_range(struct kunit *test, struct ext4_buddy *e4b, return; ext4_lock_group(sb, e4b->bd_group); - mb_free_blocks(NULL, e4b, start, len); + mb_free_blocks_test(NULL, e4b, start, len); ext4_unlock_group(sb, e4b->bd_group); - mb_clear_bits(bitmap, start, len); + mb_clear_bits_test(bitmap, start, len); /* bypass bb_free validatoin in ext4_mb_generate_buddy */ grp->bb_free += len; memset(buddy, 0xff, sb->s_blocksize); for (i = 0; i < MB_NUM_ORDERS(sb); i++) grp->bb_counters[i] = 0; - ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp); + ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp); KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize), 0); @@ -865,7 +866,7 @@ static void test_mb_free_blocks(struct kunit *test) bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); ex.fe_start = 0; @@ -873,7 +874,7 @@ static void test_mb_free_blocks(struct kunit *test) ex.fe_group = TEST_GOAL_GROUP; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(&e4b, &ex); + mb_mark_used_test(&e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); grp->bb_free = 0; @@ -886,7 +887,7 @@ static void test_mb_free_blocks(struct kunit *test) test_mb_free_blocks_range(test, &e4b, ranges[i].start, ranges[i].len, bitmap, buddy, grp); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } #define COUNT_FOR_ESTIMATE 100000 @@ -904,7 +905,7 @@ static void test_mb_mark_used_cost(struct kunit *test) if (sb->s_blocksize > PAGE_SIZE) kunit_skip(test, "blocksize exceeds pagesize"); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); ex.fe_group = TEST_GOAL_GROUP; @@ -918,7 +919,7 @@ static void test_mb_mark_used_cost(struct kunit *test) ex.fe_start = ranges[i].start; ex.fe_len = ranges[i].len; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(&e4b, &ex); + mb_mark_used_test(&e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); } end = jiffies; @@ -929,14 +930,14 @@ static void test_mb_mark_used_cost(struct kunit *test) continue; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_free_blocks(NULL, &e4b, ranges[i].start, + mb_free_blocks_test(NULL, &e4b, ranges[i].start, ranges[i].len); ext4_unlock_group(sb, TEST_GOAL_GROUP); } } kunit_info(test, "costed jiffies %lu\n", all); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } static const struct mbt_ext4_block_layout mbt_test_layouts[] = { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 20e9fdaf4301..bb58eafb87bc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1199,6 +1199,8 @@ static int ext4_mb_scan_groups(struct ext4_allocation_context *ac) /* searching for the right group start from the goal value specified */ start = ac->ac_g_ex.fe_group; + if (start >= ngroups) + start = 0; ac->ac_prefetch_grp = start; ac->ac_prefetch_nr = 0; @@ -2443,8 +2445,12 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); - if (err) + if (err) { + if (EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info) && + !(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + return 0; return err; + } ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) @@ -3580,9 +3586,7 @@ err_freebuddy: rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - rcu_read_lock(); - kvfree(rcu_dereference(sbi->s_group_info)); - rcu_read_unlock(); + kvfree(rcu_access_pointer(sbi->s_group_info)); return -ENOMEM; } @@ -3889,15 +3893,14 @@ void ext4_mb_release(struct super_block *sb) struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; - if (test_opt(sb, DISCARD)) { - /* - * wait the discard work to drain all of ext4_free_data - */ - flush_work(&sbi->s_discard_work); - WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); - } + /* + * wait the discard work to drain all of ext4_free_data + */ + flush_work(&sbi->s_discard_work); + WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); - if (sbi->s_group_info) { + group_info = rcu_access_pointer(sbi->s_group_info); + if (group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); @@ -3915,12 +3918,9 @@ void ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); - rcu_read_lock(); - group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); - rcu_read_unlock(); } ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); @@ -4084,7 +4084,7 @@ void ext4_exit_mballoc(void) #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 #define EXT4_MB_SYNC_UPDATE 0x0002 -static int +int ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, ext4_group_t group, ext4_grpblk_t blkoff, ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) @@ -7188,6 +7188,102 @@ out_unload: return error; } -#ifdef CONFIG_EXT4_KUNIT_TESTS -#include "mballoc-test.c" +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +void mb_clear_bits_test(void *bm, int cur, int len) +{ + mb_clear_bits(bm, cur, len); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bits_test); + +ext4_fsblk_t +ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar, + int *errp) +{ + return ext4_mb_new_blocks_simple(ar, errp); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_new_blocks_simple_test); + +int mb_find_next_zero_bit_test(void *addr, int max, int start) +{ + return mb_find_next_zero_bit(addr, max, start); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_zero_bit_test); + +int mb_find_next_bit_test(void *addr, int max, int start) +{ + return mb_find_next_bit(addr, max, start); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_bit_test); + +void mb_clear_bit_test(int bit, void *addr) +{ + mb_clear_bit(bit, addr); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bit_test); + +int mb_test_bit_test(int bit, void *addr) +{ + return mb_test_bit(bit, addr); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_test_bit_test); + +int ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac, + handle_t *handle) +{ + return ext4_mb_mark_diskspace_used(ac, handle); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_diskspace_used_test); + +int mb_mark_used_test(struct ext4_buddy *e4b, struct ext4_free_extent *ex) +{ + return mb_mark_used(e4b, ex); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_mark_used_test); + +void ext4_mb_generate_buddy_test(struct super_block *sb, void *buddy, + void *bitmap, ext4_group_t group, + struct ext4_group_info *grp) +{ + ext4_mb_generate_buddy(sb, buddy, bitmap, group, grp); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_generate_buddy_test); + +int ext4_mb_load_buddy_test(struct super_block *sb, ext4_group_t group, + struct ext4_buddy *e4b) +{ + return ext4_mb_load_buddy(sb, group, e4b); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_load_buddy_test); + +void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b) +{ + ext4_mb_unload_buddy(e4b); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_unload_buddy_test); + +void mb_free_blocks_test(struct inode *inode, struct ext4_buddy *e4b, + int first, int count) +{ + mb_free_blocks(inode, e4b, first, count); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_free_blocks_test); + +void ext4_free_blocks_simple_test(struct inode *inode, ext4_fsblk_t block, + unsigned long count) +{ + return ext4_free_blocks_simple(inode, block, count); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_blocks_simple_test); + +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_wait_block_bitmap); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_init); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_desc); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_count_free_clusters); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_info); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_group_clusters_set); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_release); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_read_block_bitmap_nowait); +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_set_bits); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_fc_init_inode); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_context); #endif diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 15a049f05d04..39333ce72cbd 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -270,4 +270,34 @@ ext4_mballoc_query_range( ext4_mballoc_query_range_fn formatter, void *priv); +extern int ext4_mb_mark_context(handle_t *handle, + struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, + ext4_grpblk_t *ret_changed); +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +extern void mb_clear_bits_test(void *bm, int cur, int len); +extern ext4_fsblk_t +ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar, + int *errp); +extern int mb_find_next_zero_bit_test(void *addr, int max, int start); +extern int mb_find_next_bit_test(void *addr, int max, int start); +extern void mb_clear_bit_test(int bit, void *addr); +extern int mb_test_bit_test(int bit, void *addr); +extern int +ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac, + handle_t *handle); +extern int mb_mark_used_test(struct ext4_buddy *e4b, + struct ext4_free_extent *ex); +extern void ext4_mb_generate_buddy_test(struct super_block *sb, + void *buddy, void *bitmap, ext4_group_t group, + struct ext4_group_info *grp); +extern int ext4_mb_load_buddy_test(struct super_block *sb, + ext4_group_t group, struct ext4_buddy *e4b); +extern void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b); +extern void mb_free_blocks_test(struct inode *inode, + struct ext4_buddy *e4b, int first, int count); +extern void ext4_free_blocks_simple_test(struct inode *inode, + ext4_fsblk_t block, unsigned long count); +#endif #endif diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index a8c95eee91b7..39fe50b3c662 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -524,9 +524,15 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio, nr_to_submit++; } while ((bh = bh->b_this_page) != head); - /* Nothing to submit? Just unlock the folio... */ - if (!nr_to_submit) + if (!nr_to_submit) { + /* + * We have nothing to submit. Just cycle the folio through + * writeback state to properly update xarray tags. + */ + __folio_start_writeback(folio, keep_towrite); + folio_end_writeback(folio); return 0; + } bh = head = folio_buffers(folio); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 43f680c750ae..a34efb44e73d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1254,12 +1254,10 @@ static void ext4_group_desc_free(struct ext4_sb_info *sbi) struct buffer_head **group_desc; int i; - rcu_read_lock(); - group_desc = rcu_dereference(sbi->s_group_desc); + group_desc = rcu_access_pointer(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); - rcu_read_unlock(); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) @@ -1267,14 +1265,12 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi) struct flex_groups **flex_groups; int i; - rcu_read_lock(); - flex_groups = rcu_dereference(sbi->s_flex_groups); + flex_groups = rcu_access_pointer(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } - rcu_read_unlock(); } static void ext4_put_super(struct super_block *sb) @@ -1527,6 +1523,27 @@ void ext4_clear_inode(struct inode *inode) invalidate_inode_buffers(inode); clear_inode(inode); ext4_discard_preallocations(inode); + /* + * We must remove the inode from the hash before ext4_free_inode() + * clears the bit in inode bitmap as otherwise another process reusing + * the inode will block in insert_inode_hash() waiting for inode + * eviction to complete while holding transaction handle open, but + * ext4_evict_inode() still running for that inode could block waiting + * for transaction commit if the inode is marked as IS_SYNC => deadlock. + * + * Removing the inode from the hash here is safe. There are two cases + * to consider: + * 1) The inode still has references to it (i_nlink > 0). In that case + * we are keeping the inode and once we remove the inode from the hash, + * iget() can create the new inode structure for the same inode number + * and we are fine with that as all IO on behalf of the inode is + * finished. + * 2) We are deleting the inode (i_nlink == 0). In that case inode + * number cannot be reused until ext4_free_inode() clears the bit in + * the inode bitmap, at which point all IO is done and reuse is fine + * again. + */ + remove_inode_hash(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -3633,6 +3650,13 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) "extents feature\n"); return 0; } + if (ext4_has_feature_bigalloc(sb) && + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + ext4_msg(sb, KERN_WARNING, + "bad geometry: bigalloc file system with non-zero " + "first_data_block\n"); + return 0; + } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || @@ -5403,6 +5427,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); + mutex_init(&sbi->s_error_notify_mutex); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index b87d7bdab06a..923b375e017f 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -597,7 +597,10 @@ static const struct kobj_type ext4_feat_ktype = { void ext4_notify_error_sysfs(struct ext4_sb_info *sbi) { - sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); + mutex_lock(&sbi->s_error_notify_mutex); + if (sbi->s_kobj.state_in_sysfs) + sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); + mutex_unlock(&sbi->s_error_notify_mutex); } static struct kobject *ext4_root; @@ -610,8 +613,10 @@ int ext4_register_sysfs(struct super_block *sb) int err; init_completion(&sbi->s_kobj_unregister); + mutex_lock(&sbi->s_error_notify_mutex); err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root, "%s", sb->s_id); + mutex_unlock(&sbi->s_error_notify_mutex); if (err) { kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); @@ -644,7 +649,10 @@ void ext4_unregister_sysfs(struct super_block *sb) if (sbi->s_proc) remove_proc_subtree(sb->s_id, ext4_proc_root); + + mutex_lock(&sbi->s_error_notify_mutex); kobject_del(&sbi->s_kobj); + mutex_unlock(&sbi->s_error_notify_mutex); } int __init ext4_init_sysfs(void) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7c75ed7e8979..3c75ee025bda 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1711,6 +1711,19 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, } } +static bool __sync_lazytime(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (!(inode_state_read(inode) & I_DIRTY_TIME)) { + spin_unlock(&inode->i_lock); + return false; + } + inode_state_clear(inode, I_DIRTY_TIME); + spin_unlock(&inode->i_lock); + inode->i_op->sync_lazytime(inode); + return true; +} + bool sync_lazytime(struct inode *inode) { if (!(inode_state_read_once(inode) & I_DIRTY_TIME)) @@ -1718,9 +1731,8 @@ bool sync_lazytime(struct inode *inode) trace_writeback_lazytime(inode); if (inode->i_op->sync_lazytime) - inode->i_op->sync_lazytime(inode); - else - mark_inode_dirty_sync(inode); + return __sync_lazytime(inode); + mark_inode_dirty_sync(inode); return true; } @@ -2775,13 +2787,8 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. - * - * If the mapping does not have data integrity semantics, - * there's no need to wait for the writeout to complete, as the - * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || - mapping_no_data_integrity(mapping)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); @@ -2916,6 +2923,17 @@ void sync_inodes_sb(struct super_block *sb) */ if (bdi == &noop_backing_dev_info) return; + + /* + * If the superblock has SB_I_NO_DATA_INTEGRITY set, there's no need to + * wait for the writeout to complete, as the filesystem cannot guarantee + * data persistence on sync. Just kick off writeback and return. + */ + if (sb->s_iflags & SB_I_NO_DATA_INTEGRITY) { + wakeup_flusher_threads_bdi(bdi, WB_REASON_SYNC); + return; + } + WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b1bb7153cb78..676fd9856bfb 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3201,10 +3201,8 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) { + if (fc->writeback_cache) mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); - mapping_set_no_data_integrity(&inode->i_data); - } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e57b8af06be9..c795abe47a4f 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1709,6 +1709,7 @@ static void fuse_sb_defaults(struct super_block *sb) sb->s_export_op = &fuse_export_operations; sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE; sb->s_iflags |= SB_I_NOIDMAP; + sb->s_iflags |= SB_I_NO_DATA_INTEGRITY; if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c index fc045f2e4c45..edd908183058 100644 --- a/fs/iomap/bio.c +++ b/fs/iomap/bio.c @@ -8,7 +8,10 @@ #include "internal.h" #include "trace.h" -static void iomap_read_end_io(struct bio *bio) +static DEFINE_SPINLOCK(failed_read_lock); +static struct bio_list failed_read_list = BIO_EMPTY_LIST; + +static void __iomap_read_end_io(struct bio *bio) { int error = blk_status_to_errno(bio->bi_status); struct folio_iter fi; @@ -18,6 +21,52 @@ static void iomap_read_end_io(struct bio *bio) bio_put(bio); } +static void +iomap_fail_reads( + struct work_struct *work) +{ + struct bio *bio; + struct bio_list tmp = BIO_EMPTY_LIST; + unsigned long flags; + + spin_lock_irqsave(&failed_read_lock, flags); + bio_list_merge_init(&tmp, &failed_read_list); + spin_unlock_irqrestore(&failed_read_lock, flags); + + while ((bio = bio_list_pop(&tmp)) != NULL) { + __iomap_read_end_io(bio); + cond_resched(); + } +} + +static DECLARE_WORK(failed_read_work, iomap_fail_reads); + +static void iomap_fail_buffered_read(struct bio *bio) +{ + unsigned long flags; + + /* + * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions + * in the fserror code. The caller no longer owns the bio reference + * after the spinlock drops. + */ + spin_lock_irqsave(&failed_read_lock, flags); + if (bio_list_empty(&failed_read_list)) + WARN_ON_ONCE(!schedule_work(&failed_read_work)); + bio_list_add(&failed_read_list, bio); + spin_unlock_irqrestore(&failed_read_lock, flags); +} + +static void iomap_read_end_io(struct bio *bio) +{ + if (bio->bi_status) { + iomap_fail_buffered_read(bio); + return; + } + + __iomap_read_end_io(bio); +} + static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx) { struct bio *bio = ctx->read_ctx; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 00f0efaf12b2..92a831cf4bf1 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -514,6 +514,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, loff_t length = iomap_length(iter); struct folio *folio = ctx->cur_folio; size_t folio_len = folio_size(folio); + struct iomap_folio_state *ifs; size_t poff, plen; loff_t pos_diff; int ret; @@ -525,7 +526,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, return iomap_iter_advance(iter, length); } - ifs_alloc(iter->inode, folio, iter->flags); + ifs = ifs_alloc(iter->inode, folio, iter->flags); length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos)); while (length) { @@ -560,11 +561,15 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, *bytes_submitted += plen; /* - * If the entire folio has been read in by the IO - * helper, then the helper owns the folio and will end - * the read on it. + * Hand off folio ownership to the IO helper when: + * 1) The entire folio has been submitted for IO, or + * 2) There is no ifs attached to the folio + * + * Case (2) occurs when 1 << i_blkbits matches the folio + * size but the underlying filesystem or block device + * uses a smaller granularity for IO. */ - if (*bytes_submitted == folio_len) + if (*bytes_submitted == folio_len || !ifs) ctx->cur_folio = NULL; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index de89c5bef607..1508e2f54462 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -267,7 +267,15 @@ restart: */ BUFFER_TRACE(bh, "queue"); get_bh(bh); - J_ASSERT_BH(bh, !buffer_jwrite(bh)); + if (WARN_ON_ONCE(buffer_jwrite(bh))) { + put_bh(bh); /* drop the ref we just took */ + spin_unlock(&journal->j_list_lock); + /* Clean up any previously batched buffers */ + if (batch_count) + __flush_batch(journal, &batch_count); + jbd2_journal_abort(journal, -EFSCORRUPTED); + return -EFSCORRUPTED; + } journal->j_chkpt_bhs[batch_count++] = bh; transaction->t_chp_stats.cs_written++; transaction->t_checkpoint_list = jh->b_cpnext; @@ -325,7 +333,10 @@ int jbd2_cleanup_journal_tail(journal_t *journal) if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr)) return 1; - J_ASSERT(blocknr != 0); + if (WARN_ON_ONCE(blocknr == 0)) { + jbd2_journal_abort(journal, -EFSCORRUPTED); + return -EFSCORRUPTED; + } /* * We need to make sure that any blocks that were recently written out diff --git a/fs/mpage.c b/fs/mpage.c index 7dae5afc2b9e..b3d9f231a04a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -646,17 +646,24 @@ out: } /** - * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them + * __mpage_writepages - walk the list of dirty pages of the given address space + * & writepage() all of them * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @get_block: the filesystem's block mapper function. + * @write_folio: handler to call for each folio before calling + * mpage_write_folio() * * This is a library function, which implements the writepages() - * address_space_operation. + * address_space_operation. It calls @write_folio handler for each folio. If + * the handler returns value > 0, it calls mpage_write_folio() to do the + * folio writeback. */ int -mpage_writepages(struct address_space *mapping, - struct writeback_control *wbc, get_block_t get_block) +__mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block, + int (*write_folio)(struct folio *folio, + struct writeback_control *wbc)) { struct mpage_data mpd = { .get_block = get_block, @@ -666,11 +673,22 @@ mpage_writepages(struct address_space *mapping, int error; blk_start_plug(&plug); - while ((folio = writeback_iter(mapping, wbc, folio, &error))) + while ((folio = writeback_iter(mapping, wbc, folio, &error))) { + if (write_folio) { + error = write_folio(folio, wbc); + /* + * == 0 means folio is handled, < 0 means error. In + * both cases hand back control to writeback_iter() + */ + if (error <= 0) + continue; + /* Let mpage_write_folio() handle the folio. */ + } error = mpage_write_folio(wbc, folio, &mpd); + } if (mpd.bio) mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); return error; } -EXPORT_SYMBOL(mpage_writepages); +EXPORT_SYMBOL(__mpage_writepages); diff --git a/fs/namei.c b/fs/namei.c index 58f715f7657e..9e5500dad14f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2437,8 +2437,14 @@ inside: EXPORT_SYMBOL(hashlen_string); /* - * Calculate the length and hash of the path component, and - * return the length as the result. + * hash_name - Calculate the length and hash of the path component + * @nd: the path resolution state + * @name: the pathname to read the component from + * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT, + * LAST_WORD_IS_DOTDOT, or some other value depending on whether the + * component is '.', '..', or something else. Otherwise, @lastword is 0. + * + * Returns: a pointer to the terminating '/' or NUL character in @name. */ static inline const char *hash_name(struct nameidata *nd, const char *name, diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 88a0d801525f..a8c0d86118c5 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -171,9 +171,8 @@ static void netfs_queue_read(struct netfs_io_request *rreq, spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index a498ee8d6674..f72e6da88cca 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -71,9 +71,8 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index dd1451bf7543..f9ab69de3e29 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -111,7 +111,6 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; stream->construct = NULL; - stream->front = NULL; } /* Check if (re-)preparation failed. */ @@ -186,10 +185,18 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) stream->sreq_max_segs = INT_MAX; netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - stream->prepare_write(subreq); - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_stat(&netfs_n_wh_retry_write_subreq); + if (stream->prepare_write) { + stream->prepare_write(subreq); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); + } else { + struct iov_iter source; + + netfs_reset_iter(subreq); + source = subreq->io_iter; + netfs_reissue_write(stream, subreq, &source); + } } netfs_unbuffered_write_done(wreq); diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 72a435e5fc6d..154a14bb2d7f 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -143,6 +143,47 @@ static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset, } /* + * Select the span of a kvec iterator we're going to use. Limit it by both + * maximum size and maximum number of segments. Returns the size of the span + * in bytes. + */ +static size_t netfs_limit_kvec(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + const struct kvec *kvecs = iter->kvec; + unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0; + size_t len, span = 0, n = iter->count; + size_t skip = iter->iov_offset + start_offset; + + if (WARN_ON(!iov_iter_is_kvec(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + + while (n && ix < nkv && skip) { + len = kvecs[ix].iov_len; + if (skip < len) + break; + skip -= len; + n -= len; + ix++; + } + + while (n && ix < nkv) { + len = min3(n, kvecs[ix].iov_len - skip, max_size); + span += len; + nsegs++; + ix++; + if (span >= max_size || nsegs >= max_segs) + break; + skip = 0; + n -= len; + } + + return min(span, max_size); +} + +/* * Select the span of an xarray iterator we're going to use. Limit it by both * maximum size and maximum number of segments. It is assumed that segments * can be larger than a page in size, provided they're physically contiguous. @@ -245,6 +286,8 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, return netfs_limit_bvec(iter, start_offset, max_size, max_segs); if (iov_iter_is_xarray(iter)) return netfs_limit_xarray(iter, start_offset, max_size, max_segs); + if (iov_iter_is_kvec(iter)) + return netfs_limit_kvec(iter, start_offset, max_size, max_segs); BUG(); } EXPORT_SYMBOL(netfs_limit_iter); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 137f0e28a44c..e5f6665b3341 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -205,7 +205,8 @@ reassess: * in progress. The issuer thread may be adding stuff to the tail * whilst we're doing this. */ - front = READ_ONCE(stream->front); + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { size_t transferred; @@ -301,7 +302,6 @@ reassess: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&rreq->lock); netfs_put_subrequest(remove, notes & ABANDON_SREQ ? diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 7793ba5e3e8f..cca9ac43c077 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -93,8 +93,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) from->start, from->transferred, from->len); if (test_bit(NETFS_SREQ_FAILED, &from->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) { + subreq = from; goto abandon; + } list_for_each_continue(next, &stream->subrequests) { subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); @@ -178,6 +180,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) if (subreq == to) break; } + subreq = NULL; continue; } diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8e6264f62a8f..d0e23bc42445 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -107,7 +107,6 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); trace_netfs_sreq(subreq, netfs_sreq_trace_added); - stream->front = subreq; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); spin_unlock(&rreq->lock); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 83eb3dc1adf8..b194447f4b11 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -228,7 +228,8 @@ reassess_streams: if (!smp_load_acquire(&stream->active)) continue; - front = stream->front; + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { trace_netfs_collect_sreq(wreq, front); //_debug("sreq [%x] %llx %zx/%zx", @@ -279,7 +280,6 @@ reassess_streams: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&wreq->lock); netfs_put_subrequest(remove, notes & SAW_FAILURE ? diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 437268f65640..2db688f94125 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -206,9 +206,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, spin_lock(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Write list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 758611ee4475..13cb60b52bd6 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -1146,15 +1146,15 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, return -EOVERFLOW; /* - * With metacopy disabled, we fsync after final metadata copyup, for + * With "fsync=strict", we fsync after final metadata copyup, for * both regular files and directories to get atomic copyup semantics * on filesystems that do not use strict metadata ordering (e.g. ubifs). * - * With metacopy enabled we want to avoid fsync on all meta copyup + * By default, we want to avoid fsync on all meta copyup, because * that will hurt performance of workloads such as chown -R, so we * only fsync on data copyup as legacy behavior. */ - ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy && + ctx.metadata_fsync = ovl_should_sync_metadata(OVL_FS(dentry->d_sb)) && (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode)); ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index cad2055ebf18..63b299bf12f7 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -99,6 +99,12 @@ enum { OVL_VERITY_REQUIRE, }; +enum { + OVL_FSYNC_VOLATILE, + OVL_FSYNC_AUTO, + OVL_FSYNC_STRICT, +}; + /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: @@ -656,6 +662,21 @@ static inline bool ovl_xino_warn(struct ovl_fs *ofs) return ofs->config.xino == OVL_XINO_ON; } +static inline bool ovl_should_sync(struct ovl_fs *ofs) +{ + return ofs->config.fsync_mode != OVL_FSYNC_VOLATILE; +} + +static inline bool ovl_should_sync_metadata(struct ovl_fs *ofs) +{ + return ofs->config.fsync_mode == OVL_FSYNC_STRICT; +} + +static inline bool ovl_is_volatile(struct ovl_config *config) +{ + return config->fsync_mode == OVL_FSYNC_VOLATILE; +} + /* * To avoid regressions in existing setups with overlay lower offline changes, * we allow lower changes only if none of the new features are used. diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 1d4828dbcf7a..80cad4ea96a3 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -18,7 +18,7 @@ struct ovl_config { int xino; bool metacopy; bool userxattr; - bool ovl_volatile; + int fsync_mode; }; struct ovl_sb { @@ -120,11 +120,6 @@ static inline struct ovl_fs *OVL_FS(struct super_block *sb) return (struct ovl_fs *)sb->s_fs_info; } -static inline bool ovl_should_sync(struct ovl_fs *ofs) -{ - return !ofs->config.ovl_volatile; -} - static inline unsigned int ovl_numlower(struct ovl_entry *oe) { return oe ? oe->__numlower : 0; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 8111b437ae5d..c93fcaa45d4a 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -58,6 +58,7 @@ enum ovl_opt { Opt_xino, Opt_metacopy, Opt_verity, + Opt_fsync, Opt_volatile, Opt_override_creds, }; @@ -140,6 +141,23 @@ static int ovl_verity_mode_def(void) return OVL_VERITY_OFF; } +static const struct constant_table ovl_parameter_fsync[] = { + { "volatile", OVL_FSYNC_VOLATILE }, + { "auto", OVL_FSYNC_AUTO }, + { "strict", OVL_FSYNC_STRICT }, + {} +}; + +static const char *ovl_fsync_mode(struct ovl_config *config) +{ + return ovl_parameter_fsync[config->fsync_mode].name; +} + +static int ovl_fsync_mode_def(void) +{ + return OVL_FSYNC_AUTO; +} + const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_string_empty("lowerdir", Opt_lowerdir), fsparam_file_or_string("lowerdir+", Opt_lowerdir_add), @@ -155,6 +173,7 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_enum("xino", Opt_xino, ovl_parameter_xino), fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), fsparam_enum("verity", Opt_verity, ovl_parameter_verity), + fsparam_enum("fsync", Opt_fsync, ovl_parameter_fsync), fsparam_flag("volatile", Opt_volatile), fsparam_flag_no("override_creds", Opt_override_creds), {} @@ -665,8 +684,11 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_verity: config->verity_mode = result.uint_32; break; + case Opt_fsync: + config->fsync_mode = result.uint_32; + break; case Opt_volatile: - config->ovl_volatile = true; + config->fsync_mode = OVL_FSYNC_VOLATILE; break; case Opt_userxattr: config->userxattr = true; @@ -800,6 +822,7 @@ int ovl_init_fs_context(struct fs_context *fc) ofs->config.nfs_export = ovl_nfs_export_def; ofs->config.xino = ovl_xino_def(); ofs->config.metacopy = ovl_metacopy_def; + ofs->config.fsync_mode = ovl_fsync_mode_def(); fc->s_fs_info = ofs; fc->fs_private = ctx; @@ -870,9 +893,9 @@ int ovl_fs_params_verify(const struct ovl_fs_context *ctx, config->index = false; } - if (!config->upperdir && config->ovl_volatile) { + if (!config->upperdir && ovl_is_volatile(config)) { pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n"); - config->ovl_volatile = false; + config->fsync_mode = ovl_fsync_mode_def(); } if (!config->upperdir && config->uuid == OVL_UUID_ON) { @@ -1070,8 +1093,8 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config)); if (ofs->config.metacopy != ovl_metacopy_def) seq_printf(m, ",metacopy=%s", str_on_off(ofs->config.metacopy)); - if (ofs->config.ovl_volatile) - seq_puts(m, ",volatile"); + if (ofs->config.fsync_mode != ovl_fsync_mode_def()) + seq_printf(m, ",fsync=%s", ovl_fsync_mode(&ofs->config)); if (ofs->config.userxattr) seq_puts(m, ",userxattr"); if (ofs->config.verity_mode != ovl_verity_mode_def()) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index d4c12feec039..0822987cfb51 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -776,7 +776,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, * For volatile mount, create a incompat/volatile/dirty file to keep * track of it. */ - if (ofs->config.ovl_volatile) { + if (ovl_is_volatile(&ofs->config)) { err = ovl_create_volatile_dirty(ofs); if (err < 0) { pr_err("Failed to create volatile/dirty file.\n"); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 3f1b763a8bb4..2ea769f311c3 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -85,7 +85,10 @@ int ovl_can_decode_fh(struct super_block *sb) if (!exportfs_can_decode_fh(sb->s_export_op)) return 0; - return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN; + if (sb->s_export_op->encode_fh == generic_encode_ino32_fh) + return FILEID_INO32_GEN; + + return -1; } struct dentry *ovl_indexdir(struct super_block *sb) diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile index 26b6105f04d1..1a6e1e1c9764 100644 --- a/fs/smb/client/Makefile +++ b/fs/smb/client/Makefile @@ -48,8 +48,8 @@ cifs-$(CONFIG_CIFS_COMPRESSION) += compress.o compress/lz77.o # Build the SMB2 error mapping table from smb2status.h # $(obj)/smb2_mapping_table.c: $(src)/../common/smb2status.h \ - $(src)/gen_smb2_mapping - $(call cmd,gen_smb2_mapping) + $(src)/gen_smb2_mapping FORCE + $(call if_changed,gen_smb2_mapping) $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c @@ -58,4 +58,5 @@ quiet_cmd_gen_smb2_mapping = GEN $@ obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o -clean-files += smb2_mapping_table.c +# Let Kbuild handle tracking and cleaning +targets += smb2_mapping_table.c diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index a4a7c7eee038..a46764c24710 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -588,6 +588,10 @@ char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) while (IS_DELIM(*cursor1)) cursor1++; + /* exit in case of only delimiters */ + if (!*cursor1) + return NULL; + /* copy the first letter */ *cursor2 = *cursor1; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 393a4ae47cc1..9b2bb8764a80 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -82,11 +82,19 @@ static void lease_del_list(struct oplock_info *opinfo) spin_unlock(&lb->lb_lock); } -static void lb_add(struct lease_table *lb) +static struct lease_table *alloc_lease_table(struct oplock_info *opinfo) { - write_lock(&lease_list_lock); - list_add(&lb->l_entry, &lease_table_list); - write_unlock(&lease_list_lock); + struct lease_table *lb; + + lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP); + if (!lb) + return NULL; + + memcpy(lb->client_guid, opinfo->conn->ClientGUID, + SMB2_CLIENT_GUID_SIZE); + INIT_LIST_HEAD(&lb->lease_list); + spin_lock_init(&lb->lb_lock); + return lb; } static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) @@ -1042,34 +1050,27 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) lease2->version = lease1->version; } -static int add_lease_global_list(struct oplock_info *opinfo) +static void add_lease_global_list(struct oplock_info *opinfo, + struct lease_table *new_lb) { struct lease_table *lb; - read_lock(&lease_list_lock); + write_lock(&lease_list_lock); list_for_each_entry(lb, &lease_table_list, l_entry) { if (!memcmp(lb->client_guid, opinfo->conn->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { opinfo->o_lease->l_lb = lb; lease_add_list(opinfo); - read_unlock(&lease_list_lock); - return 0; + write_unlock(&lease_list_lock); + kfree(new_lb); + return; } } - read_unlock(&lease_list_lock); - lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP); - if (!lb) - return -ENOMEM; - - memcpy(lb->client_guid, opinfo->conn->ClientGUID, - SMB2_CLIENT_GUID_SIZE); - INIT_LIST_HEAD(&lb->lease_list); - spin_lock_init(&lb->lb_lock); - opinfo->o_lease->l_lb = lb; + opinfo->o_lease->l_lb = new_lb; lease_add_list(opinfo); - lb_add(lb); - return 0; + list_add(&new_lb->l_entry, &lease_table_list); + write_unlock(&lease_list_lock); } static void set_oplock_level(struct oplock_info *opinfo, int level, @@ -1189,6 +1190,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, int err = 0; struct oplock_info *opinfo = NULL, *prev_opinfo = NULL; struct ksmbd_inode *ci = fp->f_ci; + struct lease_table *new_lb = NULL; bool prev_op_has_lease; __le32 prev_op_state = 0; @@ -1291,21 +1293,37 @@ set_lev: set_oplock_level(opinfo, req_op_level, lctx); out: - opinfo_count_inc(fp); - opinfo_add(opinfo, fp); - + /* + * Set o_fp before any publication so that concurrent readers + * (e.g. find_same_lease_key() on the lease list) that + * dereference opinfo->o_fp don't hit a NULL pointer. + * + * Keep the original publication order so concurrent opens can + * still observe the in-flight grant via ci->m_op_list, but make + * everything after opinfo_add() no-fail by preallocating any new + * lease_table first. + */ + opinfo->o_fp = fp; if (opinfo->is_lease) { - err = add_lease_global_list(opinfo); - if (err) + new_lb = alloc_lease_table(opinfo); + if (!new_lb) { + err = -ENOMEM; goto err_out; + } } + opinfo_count_inc(fp); + opinfo_add(opinfo, fp); + + if (opinfo->is_lease) + add_lease_global_list(opinfo, new_lb); + rcu_assign_pointer(fp->f_opinfo, opinfo); - opinfo->o_fp = fp; return 0; err_out: - __free_opinfo(opinfo); + kfree(new_lb); + opinfo_put(opinfo); return err; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9c44e71e3c3b..8e4cfdc0ba02 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1939,8 +1939,14 @@ out_err: if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) try_delay = true; - sess->last_active = jiffies; - sess->state = SMB2_SESSION_EXPIRED; + /* + * For binding requests, session belongs to another + * connection. Do not expire it. + */ + if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { + sess->last_active = jiffies; + sess->state = SMB2_SESSION_EXPIRED; + } ksmbd_user_session_put(sess); work->sess = NULL; if (try_delay) { @@ -3396,20 +3402,24 @@ int smb2_open(struct ksmbd_work *work) KSMBD_SHARE_FLAG_ACL_XATTR)) { struct smb_fattr fattr; struct smb_ntsd *pntsd; - int pntsd_size, ace_num = 0; + int pntsd_size; + size_t scratch_len; ksmbd_acls_fattr(&fattr, idmap, inode); - if (fattr.cf_acls) - ace_num = fattr.cf_acls->a_count; - if (fattr.cf_dacls) - ace_num += fattr.cf_dacls->a_count; - - pntsd = kmalloc(sizeof(struct smb_ntsd) + - sizeof(struct smb_sid) * 3 + - sizeof(struct smb_acl) + - sizeof(struct smb_ace) * ace_num * 2, - KSMBD_DEFAULT_GFP); + scratch_len = smb_acl_sec_desc_scratch_len(&fattr, + NULL, 0, + OWNER_SECINFO | GROUP_SECINFO | + DACL_SECINFO); + if (!scratch_len || scratch_len == SIZE_MAX) { + rc = -EFBIG; + posix_acl_release(fattr.cf_acls); + posix_acl_release(fattr.cf_dacls); + goto err_out; + } + + pntsd = kvzalloc(scratch_len, KSMBD_DEFAULT_GFP); if (!pntsd) { + rc = -ENOMEM; posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); goto err_out; @@ -3424,7 +3434,7 @@ int smb2_open(struct ksmbd_work *work) posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); if (rc) { - kfree(pntsd); + kvfree(pntsd); goto err_out; } @@ -3434,7 +3444,7 @@ int smb2_open(struct ksmbd_work *work) pntsd, pntsd_size, false); - kfree(pntsd); + kvfree(pntsd); if (rc) pr_err("failed to store ntacl in xattr : %d\n", rc); @@ -4446,8 +4456,9 @@ int smb2_query_dir(struct ksmbd_work *work) d_info.wptr = (char *)rsp->Buffer; d_info.rptr = (char *)rsp->Buffer; d_info.out_buf_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_directory_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (d_info.out_buf_len < 0) { rc = -EINVAL; goto err_out; @@ -4714,8 +4725,9 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, } buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (buf_free_len < 0) return -EINVAL; @@ -4932,7 +4944,8 @@ static int get_file_all_info(struct ksmbd_work *work, int conv_len; char *filename; u64 time; - int ret; + int ret, buf_free_len, filename_len; + struct smb2_query_info_req *req = ksmbd_req_buf_next(work); if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n", @@ -4944,6 +4957,16 @@ static int get_file_all_info(struct ksmbd_work *work, if (IS_ERR(filename)) return PTR_ERR(filename); + filename_len = strlen(filename); + buf_free_len = smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer) + + offsetof(struct smb2_file_all_info, FileName), + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < (filename_len + 1) * 2) { + kfree(filename); + return -EINVAL; + } + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (ret) { @@ -4987,7 +5010,8 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Mode = fp->coption; file_info->AlignmentRequirement = 0; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename, - PATH_MAX, conn->local_nls, 0); + min(filename_len, PATH_MAX), + conn->local_nls, 0); conv_len *= 2; file_info->FileNameLength = cpu_to_le32(conv_len); rsp->OutputBufferLength = @@ -5041,8 +5065,9 @@ static int get_file_stream_info(struct ksmbd_work *work, file_info = (struct smb2_file_stream_info *)rsp->Buffer; buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (buf_free_len < 0) goto out; @@ -5351,8 +5376,9 @@ static int smb2_get_info_file(struct ksmbd_work *work, if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { /* smb2 info file called for pipe */ - return smb2_get_info_file_pipe(work->sess, req, rsp, + rc = smb2_get_info_file_pipe(work->sess, req, rsp, work->response_buf); + goto iov_pin_out; } if (work->next_smb2_rcv_hdr_off) { @@ -5452,6 +5478,12 @@ static int smb2_get_info_file(struct ksmbd_work *work, rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), rsp, work->response_buf); ksmbd_fd_put(work, fp); + +iov_pin_out: + if (!rc) + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_query_info_rsp, Buffer) + + le32_to_cpu(rsp->OutputBufferLength)); return rc; } @@ -5678,6 +5710,11 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), rsp, work->response_buf); path_put(&path); + + if (!rc) + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_query_info_rsp, Buffer) + + le32_to_cpu(rsp->OutputBufferLength)); return rc; } @@ -5687,13 +5724,14 @@ static int smb2_get_info_sec(struct ksmbd_work *work, { struct ksmbd_file *fp; struct mnt_idmap *idmap; - struct smb_ntsd *pntsd = (struct smb_ntsd *)rsp->Buffer, *ppntsd = NULL; + struct smb_ntsd *pntsd = NULL, *ppntsd = NULL; struct smb_fattr fattr = {{0}}; struct inode *inode; __u32 secdesclen = 0; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; int addition_info = le32_to_cpu(req->AdditionalInformation); - int rc = 0, ppntsd_size = 0; + int rc = 0, ppntsd_size = 0, max_len; + size_t scratch_len = 0; if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO | PROTECTED_DACL_SECINFO | @@ -5701,6 +5739,11 @@ static int smb2_get_info_sec(struct ksmbd_work *work, ksmbd_debug(SMB, "Unsupported addition info: 0x%x)\n", addition_info); + pntsd = kzalloc(ALIGN(sizeof(struct smb_ntsd), 8), + KSMBD_DEFAULT_GFP); + if (!pntsd) + return -ENOMEM; + pntsd->revision = cpu_to_le16(1); pntsd->type = cpu_to_le16(SELF_RELATIVE | DACL_PROTECTED); pntsd->osidoffset = 0; @@ -5709,9 +5752,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, pntsd->dacloffset = 0; secdesclen = sizeof(struct smb_ntsd); - rsp->OutputBufferLength = cpu_to_le32(secdesclen); - - return 0; + goto iov_pin; } if (work->next_smb2_rcv_hdr_off) { @@ -5743,18 +5784,58 @@ static int smb2_get_info_sec(struct ksmbd_work *work, &ppntsd); /* Check if sd buffer size exceeds response buffer size */ - if (smb2_resp_buf_len(work, 8) > ppntsd_size) - rc = build_sec_desc(idmap, pntsd, ppntsd, ppntsd_size, - addition_info, &secdesclen, &fattr); + max_len = smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); + if (max_len < 0) { + rc = -EINVAL; + goto release_acl; + } + + scratch_len = smb_acl_sec_desc_scratch_len(&fattr, ppntsd, + ppntsd_size, addition_info); + if (!scratch_len || scratch_len == SIZE_MAX) { + rc = -EFBIG; + goto release_acl; + } + + pntsd = kvzalloc(scratch_len, KSMBD_DEFAULT_GFP); + if (!pntsd) { + rc = -ENOMEM; + goto release_acl; + } + + rc = build_sec_desc(idmap, pntsd, ppntsd, ppntsd_size, + addition_info, &secdesclen, &fattr); + +release_acl: posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); kfree(ppntsd); ksmbd_fd_put(work, fp); + + if (!rc && ALIGN(secdesclen, 8) > scratch_len) + rc = -EFBIG; if (rc) - return rc; + goto err_out; +iov_pin: rsp->OutputBufferLength = cpu_to_le32(secdesclen); - return 0; + rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), + rsp, work->response_buf); + if (rc) + goto err_out; + + rc = ksmbd_iov_pin_rsp_read(work, (void *)rsp, + offsetof(struct smb2_query_info_rsp, Buffer), + pntsd, secdesclen); +err_out: + if (rc) { + rsp->OutputBufferLength = 0; + kvfree(pntsd); + } + + return rc; } /** @@ -5778,6 +5859,9 @@ int smb2_query_info(struct ksmbd_work *work) goto err_out; } + rsp->StructureSize = cpu_to_le16(9); + rsp->OutputBufferOffset = cpu_to_le16(72); + switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); @@ -5798,14 +5882,6 @@ int smb2_query_info(struct ksmbd_work *work) } ksmbd_revert_fsids(work); - if (!rc) { - rsp->StructureSize = cpu_to_le16(9); - rsp->OutputBufferOffset = cpu_to_le16(72); - rc = ksmbd_iov_pin_rsp(work, (void *)rsp, - offsetof(struct smb2_query_info_rsp, Buffer) + - le32_to_cpu(rsp->OutputBufferLength)); - } - err_out: if (rc < 0) { if (rc == -EACCES) @@ -5816,6 +5892,8 @@ err_out: rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; else if (rc == -ENOMEM) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + else if (rc == -EINVAL && rsp->hdr.Status == 0) + rsp->hdr.Status = STATUS_INVALID_PARAMETER; else if (rc == -EOPNOTSUPP || rsp->hdr.Status == 0) rsp->hdr.Status = STATUS_INVALID_INFO_CLASS; smb2_set_err_rsp(work); @@ -7586,14 +7664,15 @@ retry: rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL); skip: if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) { + locks_free_lock(flock); + kfree(smb_lock); if (!rc) { ksmbd_debug(SMB, "File unlocked\n"); } else if (rc == -ENOENT) { rsp->hdr.Status = STATUS_NOT_LOCKED; + err = rc; goto out; } - locks_free_lock(flock); - kfree(smb_lock); } else { if (rc == FILE_LOCK_DEFERRED) { void **argv; @@ -7662,6 +7741,9 @@ skip: spin_unlock(&work->conn->llist_lock); ksmbd_debug(SMB, "successful in taking lock\n"); } else { + locks_free_lock(flock); + kfree(smb_lock); + err = rc; goto out; } } @@ -7692,13 +7774,17 @@ out: struct file_lock *rlock = NULL; rlock = smb_flock_init(filp); - rlock->c.flc_type = F_UNLCK; - rlock->fl_start = smb_lock->start; - rlock->fl_end = smb_lock->end; + if (rlock) { + rlock->c.flc_type = F_UNLCK; + rlock->fl_start = smb_lock->start; + rlock->fl_end = smb_lock->end; - rc = vfs_lock_file(filp, F_SETLK, rlock, NULL); - if (rc) - pr_err("rollback unlock fail : %d\n", rc); + rc = vfs_lock_file(filp, F_SETLK, rlock, NULL); + if (rc) + pr_err("rollback unlock fail : %d\n", rc); + } else { + pr_err("rollback unlock alloc failed\n"); + } list_del(&smb_lock->llist); spin_lock(&work->conn->llist_lock); @@ -7708,7 +7794,8 @@ out: spin_unlock(&work->conn->llist_lock); locks_free_lock(smb_lock->fl); - locks_free_lock(rlock); + if (rlock) + locks_free_lock(rlock); kfree(smb_lock); } out2: @@ -8191,8 +8278,9 @@ int smb2_ioctl(struct ksmbd_work *work) buffer = (char *)req + le32_to_cpu(req->InputOffset); cnt_code = le32_to_cpu(req->CtlCode); - ret = smb2_calc_max_out_buf_len(work, 48, - le32_to_cpu(req->MaxOutputResponse)); + ret = smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_ioctl_rsp, Buffer), + le32_to_cpu(req->MaxOutputResponse)); if (ret < 0) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; goto out; diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 49c2abb29bf5..c30d01877c41 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -915,6 +915,49 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, return 0; } +size_t smb_acl_sec_desc_scratch_len(struct smb_fattr *fattr, + struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info) +{ + size_t len = sizeof(struct smb_ntsd); + size_t tmp; + + if (addition_info & OWNER_SECINFO) + len += sizeof(struct smb_sid); + if (addition_info & GROUP_SECINFO) + len += sizeof(struct smb_sid); + if (!(addition_info & DACL_SECINFO)) + return len; + + len += sizeof(struct smb_acl); + if (ppntsd && ppntsd_size > 0) { + unsigned int dacl_offset = le32_to_cpu(ppntsd->dacloffset); + + if (dacl_offset < ppntsd_size && + check_add_overflow(len, ppntsd_size - dacl_offset, &len)) + return 0; + } + + if (fattr->cf_acls) { + if (check_mul_overflow((size_t)fattr->cf_acls->a_count, + 2 * sizeof(struct smb_ace), &tmp) || + check_add_overflow(len, tmp, &len)) + return 0; + } else { + /* default/minimum DACL */ + if (check_add_overflow(len, 5 * sizeof(struct smb_ace), &len)) + return 0; + } + + if (fattr->cf_dacls) { + if (check_mul_overflow((size_t)fattr->cf_dacls->a_count, + sizeof(struct smb_ace), &tmp) || + check_add_overflow(len, tmp, &len)) + return 0; + } + + return len; +} + /* Convert permission bits from mode to equivalent CIFS ACL */ int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd, diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h index 355adaee39b8..ab21ba2cd4df 100644 --- a/fs/smb/server/smbacl.h +++ b/fs/smb/server/smbacl.h @@ -101,6 +101,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, bool type_check, bool get_write); void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid); void ksmbd_init_domain(u32 *sub_auth); +size_t smb_acl_sec_desc_scratch_len(struct smb_fattr *fattr, + struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info); static inline uid_t posix_acl_uid_translate(struct mnt_idmap *idmap, struct posix_acl_entry *pace) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7fae8002344a..23e894092dab 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -181,22 +181,23 @@ static void udf_write_failed(struct address_space *mapping, loff_t to) } } -static int udf_adinicb_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int udf_handle_page_wb(struct folio *folio, + struct writeback_control *wbc) { - struct inode *inode = mapping->host; + struct inode *inode = folio->mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); - struct folio *folio = NULL; - int error = 0; - while ((folio = writeback_iter(mapping, wbc, folio, &error))) { - BUG_ON(!folio_test_locked(folio)); - BUG_ON(folio->index != 0); - memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, - 0, i_size_read(inode)); - folio_unlock(folio); - } + /* + * Inodes in the normal format are handled by the generic code. This + * check is race-free as the folio lock protects us from inode type + * conversion. + */ + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) + return 1; + memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, + 0, i_size_read(inode)); + folio_unlock(folio); mark_inode_dirty(inode); return 0; } @@ -204,12 +205,8 @@ static int udf_adinicb_writepages(struct address_space *mapping, static int udf_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct inode *inode = mapping->host; - struct udf_inode_info *iinfo = UDF_I(inode); - - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - return udf_adinicb_writepages(mapping, wbc); - return mpage_writepages(mapping, wbc, udf_get_block_wb); + return __mpage_writepages(mapping, wbc, udf_get_block_wb, + udf_handle_page_wb); } static void udf_adinicb_read_folio(struct folio *folio) diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 8244305949de..67fd9c75ac3f 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -55,7 +55,8 @@ struct xfs_attr_list_context { struct xfs_trans *tp; struct xfs_inode *dp; /* inode */ struct xfs_attrlist_cursor_kern cursor; /* position in list */ - void *buffer; /* output buffer */ + /* output buffer */ + void *buffer __counted_by_ptr(bufsize); /* * Abort attribute list iteration if non-zero. Can be used to pass diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 47f48ae555c0..2b78041e8672 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -1416,6 +1416,28 @@ xfs_attr3_leaf_create( } /* + * Reinitialize an existing attr fork block as an empty leaf, and attach + * the buffer to tp. + */ +int +xfs_attr3_leaf_init( + struct xfs_trans *tp, + struct xfs_inode *dp, + xfs_dablk_t blkno) +{ + struct xfs_buf *bp = NULL; + struct xfs_da_args args = { + .trans = tp, + .dp = dp, + .owner = dp->i_ino, + .geo = dp->i_mount->m_attr_geo, + }; + + ASSERT(tp != NULL); + + return xfs_attr3_leaf_create(&args, blkno, &bp); +} +/* * Split the leaf node, rebalance, then add the new entry. * * Returns 0 if the entry was added, 1 if a further split is needed or a diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index aca46da2bc50..72639efe6ac3 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -87,6 +87,9 @@ int xfs_attr3_leaf_list_int(struct xfs_buf *bp, /* * Routines used for shrinking the Btree. */ + +int xfs_attr3_leaf_init(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_dablk_t blkno); int xfs_attr3_leaf_toosmall(struct xfs_da_state *state, int *retval); void xfs_attr3_leaf_unbalance(struct xfs_da_state *state, struct xfs_da_state_blk *drop_blk, diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 09d4c17b3e7b..ad801b7bd2dd 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -1506,21 +1506,20 @@ xfs_da3_fixhashpath( } /* - * Remove an entry from an intermediate node. + * Internal implementation to remove an entry from an intermediate node. */ STATIC void -xfs_da3_node_remove( - struct xfs_da_state *state, - struct xfs_da_state_blk *drop_blk) +__xfs_da3_node_remove( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_da_geometry *geo, + struct xfs_da_state_blk *drop_blk) { struct xfs_da_intnode *node; struct xfs_da3_icnode_hdr nodehdr; struct xfs_da_node_entry *btree; int index; int tmp; - struct xfs_inode *dp = state->args->dp; - - trace_xfs_da_node_remove(state->args); node = drop_blk->bp->b_addr; xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr, node); @@ -1536,17 +1535,17 @@ xfs_da3_node_remove( tmp = nodehdr.count - index - 1; tmp *= (uint)sizeof(xfs_da_node_entry_t); memmove(&btree[index], &btree[index + 1], tmp); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, + xfs_trans_log_buf(tp, drop_blk->bp, XFS_DA_LOGRANGE(node, &btree[index], tmp)); index = nodehdr.count - 1; } memset(&btree[index], 0, sizeof(xfs_da_node_entry_t)); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, + xfs_trans_log_buf(tp, drop_blk->bp, XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index]))); nodehdr.count -= 1; xfs_da3_node_hdr_to_disk(dp->i_mount, node, &nodehdr); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, - XFS_DA_LOGRANGE(node, &node->hdr, state->args->geo->node_hdr_size)); + xfs_trans_log_buf(tp, drop_blk->bp, + XFS_DA_LOGRANGE(node, &node->hdr, geo->node_hdr_size)); /* * Copy the last hash value from the block to propagate upwards. @@ -1555,6 +1554,38 @@ xfs_da3_node_remove( } /* + * Remove an entry from an intermediate node. + */ +STATIC void +xfs_da3_node_remove( + struct xfs_da_state *state, + struct xfs_da_state_blk *drop_blk) +{ + trace_xfs_da_node_remove(state->args); + + __xfs_da3_node_remove(state->args->trans, state->args->dp, + state->args->geo, drop_blk); +} + +/* + * Remove an entry from an intermediate attr node at the specified index. + */ +void +xfs_attr3_node_entry_remove( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_buf *bp, + int index) +{ + struct xfs_da_state_blk blk = { + .index = index, + .bp = bp, + }; + + __xfs_da3_node_remove(tp, dp, dp->i_mount->m_attr_geo, &blk); +} + +/* * Unbalance the elements between two intermediate nodes, * move all Btree elements from one node into another. */ diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index 354d5d65043e..afcf2d3c7a21 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -184,6 +184,8 @@ int xfs_da3_split(xfs_da_state_t *state); int xfs_da3_join(xfs_da_state_t *state); void xfs_da3_fixhashpath(struct xfs_da_state *state, struct xfs_da_state_path *path_to_to_fix); +void xfs_attr3_node_entry_remove(struct xfs_trans *tp, struct xfs_inode *dp, + struct xfs_buf *bp, int index); /* * Routines used for finding things in the Btree. diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 1d25bd5b892e..222812fe202c 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -171,8 +171,10 @@ xchk_quota_item( error = xchk_quota_item_bmap(sc, dq, offset); xchk_iunlock(sc, XFS_ILOCK_SHARED); - if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) + if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) { + mutex_unlock(&dq->q_qlock); return error; + } /* * Warn if the hard limits are larger than the fs. diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 39ea651cbb75..286c5f5e0544 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -972,20 +972,12 @@ TRACE_EVENT(xfile_create, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) - __array(char, pathname, MAXNAMELEN) ), TP_fast_assign( - char *path; - __entry->ino = file_inode(xf->file)->i_ino; - path = file_path(xf->file, __entry->pathname, MAXNAMELEN); - if (IS_ERR(path)) - strncpy(__entry->pathname, "(unknown)", - sizeof(__entry->pathname)); ), - TP_printk("xfino 0x%lx path '%s'", - __entry->ino, - __entry->pathname) + TP_printk("xfino 0x%lx", + __entry->ino) ); TRACE_EVENT(xfile_destroy, diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 92331991f9fd..a5b69c0fbfd0 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -140,7 +140,7 @@ xfs_attr3_node_inactive( xfs_daddr_t parent_blkno, child_blkno; struct xfs_buf *child_bp; struct xfs_da3_icnode_hdr ichdr; - int error, i; + int error; /* * Since this code is recursive (gasp!) we must protect ourselves. @@ -152,7 +152,7 @@ xfs_attr3_node_inactive( return -EFSCORRUPTED; } - xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr); + xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr); parent_blkno = xfs_buf_daddr(bp); if (!ichdr.count) { xfs_trans_brelse(*trans, bp); @@ -167,7 +167,7 @@ xfs_attr3_node_inactive( * over the leaves removing all of them. If this is higher up * in the tree, recurse downward. */ - for (i = 0; i < ichdr.count; i++) { + while (ichdr.count > 0) { /* * Read the subsidiary block to see what we have to work with. * Don't do this in a transaction. This is a depth-first @@ -218,29 +218,32 @@ xfs_attr3_node_inactive( xfs_trans_binval(*trans, child_bp); child_bp = NULL; + error = xfs_da3_node_read_mapped(*trans, dp, + parent_blkno, &bp, XFS_ATTR_FORK); + if (error) + return error; + /* - * If we're not done, re-read the parent to get the next - * child block number. + * Remove entry from parent node, prevents being indexed to. */ - if (i + 1 < ichdr.count) { - struct xfs_da3_icnode_hdr phdr; + xfs_attr3_node_entry_remove(*trans, dp, bp, 0); + + xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr); + bp = NULL; - error = xfs_da3_node_read_mapped(*trans, dp, - parent_blkno, &bp, XFS_ATTR_FORK); + if (ichdr.count > 0) { + /* + * If we're not done, get the next child block number. + */ + child_fsb = be32_to_cpu(ichdr.btree[0].before); + + /* + * Atomically commit the whole invalidate stuff. + */ + error = xfs_trans_roll_inode(trans, dp); if (error) return error; - xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr, - bp->b_addr); - child_fsb = be32_to_cpu(phdr.btree[i + 1].before); - xfs_trans_brelse(*trans, bp); - bp = NULL; } - /* - * Atomically commit the whole invalidate stuff. - */ - error = xfs_trans_roll_inode(trans, dp); - if (error) - return error; } return 0; @@ -257,10 +260,8 @@ xfs_attr3_root_inactive( struct xfs_trans **trans, struct xfs_inode *dp) { - struct xfs_mount *mp = dp->i_mount; struct xfs_da_blkinfo *info; struct xfs_buf *bp; - xfs_daddr_t blkno; int error; /* @@ -272,7 +273,6 @@ xfs_attr3_root_inactive( error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK); if (error) return error; - blkno = xfs_buf_daddr(bp); /* * Invalidate the tree, even if the "tree" is only a single leaf block. @@ -283,10 +283,26 @@ xfs_attr3_root_inactive( case cpu_to_be16(XFS_DA_NODE_MAGIC): case cpu_to_be16(XFS_DA3_NODE_MAGIC): error = xfs_attr3_node_inactive(trans, dp, bp, 1); + /* + * Empty root node block are not allowed, convert it to leaf. + */ + if (!error) + error = xfs_attr3_leaf_init(*trans, dp, 0); + if (!error) + error = xfs_trans_roll_inode(trans, dp); break; case cpu_to_be16(XFS_ATTR_LEAF_MAGIC): case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC): error = xfs_attr3_leaf_inactive(trans, dp, bp); + /* + * Reinit the leaf before truncating extents so that a crash + * mid-truncation leaves an empty leaf rather than one with + * entries that may reference freed remote value blocks. + */ + if (!error) + error = xfs_attr3_leaf_init(*trans, dp, 0); + if (!error) + error = xfs_trans_roll_inode(trans, dp); break; default: xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); @@ -295,21 +311,6 @@ xfs_attr3_root_inactive( xfs_trans_brelse(*trans, bp); break; } - if (error) - return error; - - /* - * Invalidate the incore copy of the root block. - */ - error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno, - XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp); - if (error) - return error; - xfs_trans_binval(*trans, bp); /* remove from cache */ - /* - * Commit the invalidate and start the next transaction. - */ - error = xfs_trans_roll_inode(trans, dp); return error; } @@ -328,6 +329,7 @@ xfs_attr_inactive( { struct xfs_trans *trans; struct xfs_mount *mp; + struct xfs_buf *bp; int lock_mode = XFS_ILOCK_SHARED; int error = 0; @@ -363,10 +365,27 @@ xfs_attr_inactive( * removal below. */ if (dp->i_af.if_nextents > 0) { + /* + * Invalidate and truncate all blocks but leave the root block. + */ error = xfs_attr3_root_inactive(&trans, dp); if (error) goto out_cancel; + error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, + XFS_FSB_TO_B(mp, mp->m_attr_geo->fsbcount)); + if (error) + goto out_cancel; + + /* + * Invalidate and truncate the root block and ensure that the + * operation is completed within a single transaction. + */ + error = xfs_da_get_buf(trans, dp, 0, &bp, XFS_ATTR_FORK); + if (error) + goto out_cancel; + + xfs_trans_binval(trans, bp); error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); if (error) goto out_cancel; diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index 354472bf45f1..deab14f31b38 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -653,7 +653,6 @@ xfs_attri_recover_work( break; } if (error) { - xfs_irele(ip); XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attrp, sizeof(*attrp)); return ERR_PTR(-EFSCORRUPTED); @@ -1047,8 +1046,8 @@ xlog_recover_attri_commit_pass2( break; case XFS_ATTRI_OP_FLAGS_SET: case XFS_ATTRI_OP_FLAGS_REPLACE: - /* Log item, attr name, attr value */ - if (item->ri_total != 3) { + /* Log item, attr name, optional attr value */ + if (item->ri_total != 2 + !!attri_formatp->alfi_value_len) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attri_formatp, len); return -EFSCORRUPTED; @@ -1132,52 +1131,6 @@ xlog_recover_attri_commit_pass2( return -EFSCORRUPTED; } - switch (op) { - case XFS_ATTRI_OP_FLAGS_REMOVE: - /* Regular remove operations operate only on names. */ - if (attr_value != NULL || value_len != 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - fallthrough; - case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE: - case XFS_ATTRI_OP_FLAGS_PPTR_SET: - case XFS_ATTRI_OP_FLAGS_SET: - case XFS_ATTRI_OP_FLAGS_REPLACE: - /* - * Regular xattr set/remove/replace operations require a name - * and do not take a newname. Values are optional for set and - * replace. - * - * Name-value set/remove operations must have a name, do not - * take a newname, and can take a value. - */ - if (attr_name == NULL || name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - break; - case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE: - /* - * Name-value replace operations require the caller to - * specify the old and new names and values explicitly. - * Values are optional. - */ - if (attr_name == NULL || name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - if (attr_new_name == NULL || new_name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - break; - } - /* * Memory alloc failure will cause replay to abort. We attach the * name/value buffer to the recovered incore log item and drop our diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 491e2a7053a3..65a0e69c3d08 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -125,6 +125,7 @@ xfs_qm_dquot_logitem_push( struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_buf *bp; + struct xfs_ail *ailp = lip->li_ailp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -153,7 +154,7 @@ xfs_qm_dquot_logitem_push( goto out_unlock; } - spin_unlock(&lip->li_ailp->ail_lock); + spin_unlock(&ailp->ail_lock); error = xfs_dquot_use_attached_buf(dqp, &bp); if (error == -EAGAIN) { @@ -172,9 +173,13 @@ xfs_qm_dquot_logitem_push( rval = XFS_ITEM_FLUSHING; } xfs_buf_relse(bp); + /* + * The buffer no longer protects the log item from reclaim, so + * do not reference lip after this point. + */ out_relock_ail: - spin_lock(&lip->li_ailp->ail_lock); + spin_lock(&ailp->ail_lock); out_unlock: mutex_unlock(&dqp->q_qlock); return rval; diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c index d1291ca15239..2b8617ae7ec2 100644 --- a/fs/xfs/xfs_handle.c +++ b/fs/xfs/xfs_handle.c @@ -443,8 +443,8 @@ xfs_ioc_attr_list( context.dp = dp; context.resynch = 1; context.attr_filter = xfs_attr_filter(flags); - context.buffer = buffer; context.bufsize = round_down(bufsize, sizeof(uint32_t)); + context.buffer = buffer; context.firstu = context.bufsize; context.put_listent = xfs_ioc_attr_put_listent; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 50c0404f9064..beaa26ec62da 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1048,7 +1048,8 @@ xfs_itruncate_extents_flags( xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (icount_read(VFS_I(ip))) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); - ASSERT(new_size <= XFS_ISIZE(ip)); + if (whichfork == XFS_DATA_FORK) + ASSERT(new_size <= XFS_ISIZE(ip)); ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(ip->i_itemp != NULL); ASSERT(ip->i_itemp->ili_lock_flags == 0); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 8913036b8024..4ae81eed0442 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -746,6 +746,7 @@ xfs_inode_item_push( struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; struct xfs_buf *bp = lip->li_buf; + struct xfs_ail *ailp = lip->li_ailp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -771,7 +772,7 @@ xfs_inode_item_push( if (!xfs_buf_trylock(bp)) return XFS_ITEM_LOCKED; - spin_unlock(&lip->li_ailp->ail_lock); + spin_unlock(&ailp->ail_lock); /* * We need to hold a reference for flushing the cluster buffer as it may @@ -795,7 +796,11 @@ xfs_inode_item_push( rval = XFS_ITEM_LOCKED; } - spin_lock(&lip->li_ailp->ail_lock); + /* + * The buffer no longer protects the log item from reclaim, so + * do not reference lip after this point. + */ + spin_lock(&ailp->ail_lock); return rval; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 9c295abd0a0a..ef1ea8a1238c 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -608,8 +608,9 @@ xfs_unmount_check( * have been retrying in the background. This will prevent never-ending * retries in AIL pushing from hanging the unmount. * - * Finally, we can push the AIL to clean all the remaining dirty objects, then - * reclaim the remaining inodes that are still in memory at this point in time. + * Stop inodegc and background reclaim before pushing the AIL so that they + * are not running while the AIL is being flushed. Then push the AIL to + * clean all the remaining dirty objects and reclaim the remaining inodes. */ static void xfs_unmount_flush_inodes( @@ -621,9 +622,9 @@ xfs_unmount_flush_inodes( xfs_set_unmounting(mp); - xfs_ail_push_all_sync(mp->m_ail); xfs_inodegc_stop(mp); cancel_delayed_work_sync(&mp->m_reclaim_work); + xfs_ail_push_all_sync(mp->m_ail); xfs_reclaim_inodes(mp); xfs_health_unmount(mp); xfs_healthmon_unmount(mp); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 813e5a9f57eb..5e8190fe2be9 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -56,6 +56,7 @@ #include <linux/tracepoint.h> struct xfs_agf; +struct xfs_ail; struct xfs_alloc_arg; struct xfs_attr_list_context; struct xfs_buf_log_item; @@ -1650,16 +1651,43 @@ TRACE_EVENT(xfs_log_force, DEFINE_EVENT(xfs_log_item_class, name, \ TP_PROTO(struct xfs_log_item *lip), \ TP_ARGS(lip)) -DEFINE_LOG_ITEM_EVENT(xfs_ail_push); -DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned); -DEFINE_LOG_ITEM_EVENT(xfs_ail_locked); -DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin); DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort); DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort); +DECLARE_EVENT_CLASS(xfs_ail_push_class, + TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), + TP_ARGS(ailp, type, flags, lsn), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(uint, type) + __field(unsigned long, flags) + __field(xfs_lsn_t, lsn) + ), + TP_fast_assign( + __entry->dev = ailp->ail_log->l_mp->m_super->s_dev; + __entry->type = type; + __entry->flags = flags; + __entry->lsn = lsn; + ), + TP_printk("dev %d:%d lsn %d/%d type %s flags %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn), + __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), + __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) +) + +#define DEFINE_AIL_PUSH_EVENT(name) \ +DEFINE_EVENT(xfs_ail_push_class, name, \ + TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), \ + TP_ARGS(ailp, type, flags, lsn)) +DEFINE_AIL_PUSH_EVENT(xfs_ail_push); +DEFINE_AIL_PUSH_EVENT(xfs_ail_pinned); +DEFINE_AIL_PUSH_EVENT(xfs_ail_locked); +DEFINE_AIL_PUSH_EVENT(xfs_ail_flushing); + DECLARE_EVENT_CLASS(xfs_ail_class, TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn), TP_ARGS(lip, old_lsn, new_lsn), @@ -5091,23 +5119,16 @@ TRACE_EVENT(xmbuf_create, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) - __array(char, pathname, MAXNAMELEN) ), TP_fast_assign( - char *path; struct file *file = btp->bt_file; __entry->dev = btp->bt_mount->m_super->s_dev; __entry->ino = file_inode(file)->i_ino; - path = file_path(file, __entry->pathname, MAXNAMELEN); - if (IS_ERR(path)) - strncpy(__entry->pathname, "(unknown)", - sizeof(__entry->pathname)); ), - TP_printk("dev %d:%d xmino 0x%lx path '%s'", + TP_printk("dev %d:%d xmino 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->pathname) + __entry->ino) ); TRACE_EVENT(xmbuf_free, diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 923729af4206..99a9bf3762b7 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -365,6 +365,12 @@ xfsaild_resubmit_item( return XFS_ITEM_SUCCESS; } +/* + * Push a single log item from the AIL. + * + * @lip may have been released and freed by the time this function returns, + * so callers must not dereference the log item afterwards. + */ static inline uint xfsaild_push_item( struct xfs_ail *ailp, @@ -458,6 +464,74 @@ xfs_ail_calc_push_target( return target_lsn; } +static void +xfsaild_process_logitem( + struct xfs_ail *ailp, + struct xfs_log_item *lip, + int *stuck, + int *flushing) +{ + struct xfs_mount *mp = ailp->ail_log->l_mp; + uint type = lip->li_type; + unsigned long flags = lip->li_flags; + xfs_lsn_t item_lsn = lip->li_lsn; + int lock_result; + + /* + * Note that iop_push may unlock and reacquire the AIL lock. We + * rely on the AIL cursor implementation to be able to deal with + * the dropped lock. + * + * The log item may have been freed by the push, so it must not + * be accessed or dereferenced below this line. + */ + lock_result = xfsaild_push_item(ailp, lip); + switch (lock_result) { + case XFS_ITEM_SUCCESS: + XFS_STATS_INC(mp, xs_push_ail_success); + trace_xfs_ail_push(ailp, type, flags, item_lsn); + + ailp->ail_last_pushed_lsn = item_lsn; + break; + + case XFS_ITEM_FLUSHING: + /* + * The item or its backing buffer is already being + * flushed. The typical reason for that is that an + * inode buffer is locked because we already pushed the + * updates to it as part of inode clustering. + * + * We do not want to stop flushing just because lots + * of items are already being flushed, but we need to + * re-try the flushing relatively soon if most of the + * AIL is being flushed. + */ + XFS_STATS_INC(mp, xs_push_ail_flushing); + trace_xfs_ail_flushing(ailp, type, flags, item_lsn); + + (*flushing)++; + ailp->ail_last_pushed_lsn = item_lsn; + break; + + case XFS_ITEM_PINNED: + XFS_STATS_INC(mp, xs_push_ail_pinned); + trace_xfs_ail_pinned(ailp, type, flags, item_lsn); + + (*stuck)++; + ailp->ail_log_flush++; + break; + case XFS_ITEM_LOCKED: + XFS_STATS_INC(mp, xs_push_ail_locked); + trace_xfs_ail_locked(ailp, type, flags, item_lsn); + + (*stuck)++; + break; + default: + ASSERT(0); + break; + } +} + static long xfsaild_push( struct xfs_ail *ailp) @@ -505,62 +579,11 @@ xfsaild_push( lsn = lip->li_lsn; while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) { - int lock_result; if (test_bit(XFS_LI_FLUSHING, &lip->li_flags)) goto next_item; - /* - * Note that iop_push may unlock and reacquire the AIL lock. We - * rely on the AIL cursor implementation to be able to deal with - * the dropped lock. - */ - lock_result = xfsaild_push_item(ailp, lip); - switch (lock_result) { - case XFS_ITEM_SUCCESS: - XFS_STATS_INC(mp, xs_push_ail_success); - trace_xfs_ail_push(lip); - - ailp->ail_last_pushed_lsn = lsn; - break; - - case XFS_ITEM_FLUSHING: - /* - * The item or its backing buffer is already being - * flushed. The typical reason for that is that an - * inode buffer is locked because we already pushed the - * updates to it as part of inode clustering. - * - * We do not want to stop flushing just because lots - * of items are already being flushed, but we need to - * re-try the flushing relatively soon if most of the - * AIL is being flushed. - */ - XFS_STATS_INC(mp, xs_push_ail_flushing); - trace_xfs_ail_flushing(lip); - - flushing++; - ailp->ail_last_pushed_lsn = lsn; - break; - - case XFS_ITEM_PINNED: - XFS_STATS_INC(mp, xs_push_ail_pinned); - trace_xfs_ail_pinned(lip); - - stuck++; - ailp->ail_log_flush++; - break; - case XFS_ITEM_LOCKED: - XFS_STATS_INC(mp, xs_push_ail_locked); - trace_xfs_ail_locked(lip); - - stuck++; - break; - default: - ASSERT(0); - break; - } - + xfsaild_process_logitem(ailp, lip, &stuck, &flushing); count++; /* diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 8bbd4ec567f8..5ead3976d511 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -183,10 +183,9 @@ xfs_verify_iosize( min_not_zero(SZ_1M, me->me_max_io_size); BUILD_BUG_ON(BBSHIFT != SECTOR_SHIFT); - ASSERT(BBTOB(bbcount) >= bdev_logical_block_size(btp->bt_bdev)); + ASSERT(BBTOB(bbcount) >= btp->bt_logical_sectorsize); - return clamp(iosize, bdev_logical_block_size(btp->bt_bdev), - BBTOB(bbcount)); + return clamp(iosize, btp->bt_logical_sectorsize, BBTOB(bbcount)); } /* Allocate as much memory as we can get for verification buffer. */ @@ -218,8 +217,8 @@ xfs_verify_media_error( unsigned int bio_bbcount, blk_status_t bio_status) { - trace_xfs_verify_media_error(mp, me, btp->bt_bdev->bd_dev, daddr, - bio_bbcount, bio_status); + trace_xfs_verify_media_error(mp, me, btp->bt_dev, daddr, bio_bbcount, + bio_status); /* * Pass any error, I/O or otherwise, up to the caller if we didn't @@ -280,7 +279,7 @@ xfs_verify_media( btp = mp->m_ddev_targp; break; case XFS_DEV_LOG: - if (mp->m_logdev_targp->bt_bdev != mp->m_ddev_targp->bt_bdev) + if (mp->m_logdev_targp != mp->m_ddev_targp) btp = mp->m_logdev_targp; break; case XFS_DEV_RT: @@ -299,7 +298,7 @@ xfs_verify_media( /* start and end have to be aligned to the lba size */ if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr), - bdev_logical_block_size(btp->bt_bdev))) + btp->bt_logical_sectorsize)) return -EINVAL; /* @@ -331,8 +330,7 @@ xfs_verify_media( if (!folio) return -ENOMEM; - trace_xfs_verify_media(mp, me, btp->bt_bdev->bd_dev, daddr, bbcount, - folio); + trace_xfs_verify_media(mp, me, btp->bt_dev, daddr, bbcount, folio); bio = bio_alloc(btp->bt_bdev, 1, REQ_OP_READ, GFP_KERNEL); if (!bio) { @@ -400,7 +398,7 @@ out_folio: * an operational error. */ me->me_start_daddr = daddr; - trace_xfs_verify_media_end(mp, me, btp->bt_bdev->bd_dev); + trace_xfs_verify_media_end(mp, me, btp->bt_dev); return 0; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index a735f16d9cd8..544213067d59 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -332,8 +332,8 @@ xfs_vn_listxattr( memset(&context, 0, sizeof(context)); context.dp = XFS_I(inode); context.resynch = 1; - context.buffer = size ? data : NULL; context.bufsize = size; + context.buffer = size ? data : NULL; context.firstu = context.bufsize; context.put_listent = xfs_xattr_put_listent; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 107b797c33ec..0cc8fa749f68 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -230,9 +230,8 @@ static inline bool af_alg_readable(struct sock *sk) return PAGE_SIZE <= af_alg_rcvbuf(sk); } -unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset); -void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, - size_t dst_offset); +unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes); +void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst); void af_alg_wmem_wakeup(struct sock *sk); int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min); int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05b34a6355b0..35b1e25bd104 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1854,6 +1854,10 @@ struct bpf_link_ops { * target hook is sleepable, we'll go through tasks trace RCU GP and * then "classic" RCU GP; this need for chaining tasks trace and * classic RCU GPs is designated by setting bpf_link->sleepable flag + * + * For non-sleepable tracepoint links we go through SRCU gp instead, + * since RCU is not used in that case. Sleepable tracepoints still + * follow the scheme above. */ void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index bb92f5c169ca..7f87399938fa 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -609,6 +609,9 @@ struct cgroup { /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; + /* used by cgroup_rmdir() to wait for dying tasks to leave */ + wait_queue_head_t dying_populated_waitq; + /* used to schedule release agent */ struct work_struct release_agent_work; diff --git a/include/linux/damon.h b/include/linux/damon.h index a4fea23da857..be3d198043ff 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -810,6 +810,12 @@ struct damon_ctx { struct damos_walk_control *walk_control; struct mutex walk_control_lock; + /* + * indicate if this may be corrupted. Currentonly this is set only for + * damon_commit_ctx() failure. + */ + bool maybe_corrupted; + /* Working thread of the given DAMON context */ struct task_struct *kdamond; /* Protects @kdamond field access */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 29973baa0581..99ef042ecdb4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -80,11 +80,18 @@ #define DMA_ATTR_MMIO (1UL << 10) /* - * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline - * overlapping this buffer while it is mapped for DMA. All mappings sharing - * a cacheline must have this attribute for this to be considered safe. + * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be + * overlapped. All mappings sharing a cacheline must have this attribute for + * this to be considered safe. */ -#define DMA_ATTR_CPU_CACHE_CLEAN (1UL << 11) +#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES (1UL << 11) + +/* + * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required. + * All mappings that carry this attribute can't work with SWIOTLB and cache + * flushing. + */ +#define DMA_ATTR_REQUIRE_COHERENT (1UL << 12) /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can @@ -248,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, { return NULL; } -static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, unsigned long attrs) +static inline void dma_free_attrs(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { } static inline void *dmam_alloc_attrs(struct device *dev, size_t size, diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index fa7638b81246..383050e7fdf5 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -338,5 +338,6 @@ struct super_block { #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ +#define SB_I_NO_DATA_INTEGRITY 0x00008000 /* fs cannot guarantee data persistence on sync */ #endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 54b8b48c762e..555597b54083 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -980,7 +980,8 @@ static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { - if (domain->ops->iotlb_sync) + if (domain->ops->iotlb_sync && + likely(iotlb_gather->start < iotlb_gather->end)) domain->ops->iotlb_sync(domain, iotlb_gather); iommu_iotlb_gather_init(iotlb_gather); diff --git a/include/linux/leafops.h b/include/linux/leafops.h index a9ff94b744f2..05673d3529e7 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +static inline void softleaf_migration_sync(softleaf_t entry, + struct folio *folio) +{ + /* + * Ensure we do not race with split, which might alter tail pages into new + * folios and thus result in observing an unlocked folio. + * This matches the write barrier in __split_folio_to_order(). + */ + smp_rmb(); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + VM_WARN_ON_ONCE(!folio_test_locked(folio)); +} + /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. @@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry) struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, page_folio(page)); return page; } @@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry) struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding folio is locked. - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && - !folio_test_locked(folio)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, folio); return folio; } diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0fe96f3ab3ef..65c732d440d2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -55,6 +55,7 @@ struct mempolicy { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; + struct rcu_head rcu; }; /* diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 1bdc39daac0a..358946990bfa 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -17,7 +17,14 @@ struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); int mpage_read_folio(struct folio *folio, get_block_t get_block); -int mpage_writepages(struct address_space *mapping, - struct writeback_control *wbc, get_block_t get_block); +int __mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block, + int (*write_folio)(struct folio *folio, + struct writeback_control *wbc)); +static inline int mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block) +{ + return __mpage_writepages(mapping, wbc, get_block, NULL); +} #endif diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e9f4f845d760..b98331572ad2 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -309,7 +309,7 @@ enum { /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(struct net *net, - const char *name, struct ip_set **set); + const struct nlattr *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 72ee7d210a74..ba17ac5bf356 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -140,7 +140,6 @@ struct netfs_io_stream { void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ struct list_head subrequests; /* Contributory I/O operations */ - struct netfs_io_subrequest *front; /* Op being collected */ unsigned long long collected_to; /* Position we've collected results to */ size_t transferred; /* The amount transferred from this stream */ unsigned short error; /* Aggregate error for the stream */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,7 +210,6 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ - AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline void mapping_set_no_data_integrity(struct address_space *mapping) -{ - set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - -static inline bool mapping_no_data_integrity(const struct address_space *mapping) -{ - return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/security.h b/include/linux/security.h index 83a646d72f6f..ee88dd2d2d1f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -145,6 +145,7 @@ enum lockdown_reason { LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_RTAS_ERROR_INJECTION, + LOCKDOWN_XEN_USER_ACTIONS, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index daa4e4944ce3..2f278ce376b7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5097,6 +5097,7 @@ static inline bool skb_has_extensions(struct sk_buff *skb) return unlikely(skb->active_extensions); } #else +static inline void __skb_ext_put(struct skb_ext *ext) {} static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af7cfee7b8f6..0dc671c07d3a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,10 +159,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @driver_override: If the name of a driver is written to this attribute, then - * the device will bind to the named driver and only the named driver. - * Do not set directly, because core frees it; use driver_set_override() to - * set or clear it. * @pcpu_statistics: statistics for the spi_device * @word_delay: delay to be inserted between consecutive * words of a transfer @@ -224,7 +220,6 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; - const char *driver_override; /* The statistics */ struct spi_statistics __percpu *pcpu_statistics; diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index dec7cbe015aa..905b629e8fa3 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SRCU_TINY_H #define _LINUX_SRCU_TINY_H +#include <linux/irq_work_types.h> #include <linux/swait.h> struct srcu_struct { @@ -24,18 +25,21 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ + struct irq_work srcu_irq_work; /* Defer schedule_work() to irq work. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; void srcu_drive_gp(struct work_struct *wp); +void srcu_tiny_irq_work(struct irq_work *irq_work); #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + .srcu_irq_work = { .func = srcu_tiny_irq_work }, \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 958cb7ef41cb..be76fa4fc170 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -34,7 +34,7 @@ struct srcu_data { /* Values: SRCU_READ_FLAVOR_.* */ /* Update-side state. */ - spinlock_t __private lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -55,7 +55,7 @@ struct srcu_data { * Node in SRCU combining tree, similar in function to rcu_data. */ struct srcu_node { - spinlock_t __private lock; + raw_spinlock_t __private lock; unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ /* if greater than ->srcu_gp_seq. */ unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ @@ -74,7 +74,7 @@ struct srcu_usage { /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters and size state. */ + raw_spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ @@ -95,6 +95,7 @@ struct srcu_usage { unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; + struct irq_work irq_work; struct srcu_struct *srcu_ssp; }; @@ -156,7 +157,7 @@ struct srcu_struct { #define __SRCU_USAGE_INIT(name) \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL, \ .srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE, \ .srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL, \ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 22ca1c8b54f3..1d7f29f5e901 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -122,6 +122,22 @@ static inline bool tracepoint_is_faultable(struct tracepoint *tp) { return tp->ext && tp->ext->faultable; } +/* + * Run RCU callback with the appropriate grace period wait for non-faultable + * tracepoints, e.g., those used in atomic context. + */ +static inline void call_tracepoint_unregister_atomic(struct rcu_head *rcu, rcu_callback_t func) +{ + call_srcu(&tracepoint_srcu, rcu, func); +} +/* + * Run RCU callback with the appropriate grace period wait for faultable + * tracepoints, e.g., those used in syscall context. + */ +static inline void call_tracepoint_unregister_syscall(struct rcu_head *rcu, rcu_callback_t func) +{ + call_rcu_tasks_trace(rcu, func); +} #else static inline void tracepoint_synchronize_unregister(void) { } @@ -129,6 +145,10 @@ static inline bool tracepoint_is_faultable(struct tracepoint *tp) { return false; } +static inline void call_tracepoint_unregister_atomic(struct rcu_head *rcu, rcu_callback_t func) +{ } +static inline void call_tracepoint_unregister_syscall(struct rcu_head *rcu, rcu_callback_t func) +{ } #endif #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 75dabb763c65..f36d21b5bc19 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -207,6 +207,39 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr, + bool little_endian) +{ + u16 hdr_len; + + hdr_len = skb_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); +} + +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr) +{ + u16 hdr_len; + + hdr_len = skb_inner_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += inner_tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); +} + static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, @@ -385,7 +418,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, - bool has_data_valid) + bool has_data_valid, + bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,9 +428,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); - if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, - has_data_valid, vlan_hlen); + if (!tnl_gso_type) { + ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); + if (ret) + return ret; + + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_hdrlen(skb, hdr, little_endian); + + return ret; + } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) @@ -414,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (ret) return ret; + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_tnl_hdrlen(skb, hdr); + if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 010f1a8fd15f..5172afee5494 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -658,6 +658,7 @@ struct l2cap_conn { struct sk_buff *rx_skb; __u32 rx_len; struct ida tx_ida; + __u8 tx_ident; struct sk_buff_head pending_rx; struct work_struct pending_rx_work; diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 78a27ac73070..b2c359c6dd1b 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -158,6 +158,7 @@ static struct sk_buff *codel_dequeue(void *ctx, bool drop; if (!skb) { + vars->first_above_time = 0; vars->dropping = false; return skb; } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5a979dcab538..6d936e9f2fd3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk, return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } +static inline bool inet_use_hash2_on_bind(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + return false; + + if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return true; + } +#endif + return sk->sk_rcv_saddr != htonl(INADDR_ANY); +} + struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 88b0dd4d8e09..9f8b6814a96a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -507,12 +507,14 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); +void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now); void fib6_run_gc(unsigned long expires, struct net *net, bool force); - void fib6_gc_cleanup(void); int fib6_init(void); +#if IS_ENABLED(CONFIG_IPV6) /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. @@ -545,6 +547,23 @@ static inline void fib6_remove_gc_list(struct fib6_info *f6i) hlist_del_init(&f6i->gc_link); } +static inline void fib6_may_remove_gc_list(struct net *net, + struct fib6_info *f6i) +{ + struct fib6_gc_args gc_args; + + if (hlist_unhashed(&f6i->gc_link)) + return; + + gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval); + gc_args.more = 0; + + rcu_read_lock(); + fib6_age_exceptions(f6i, &gc_args, jiffies); + rcu_read_unlock(); +} +#endif + struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3384859a8921..8883575adcc1 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -83,6 +83,11 @@ void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; +static inline void lockdep_nfct_expect_lock_held(void) +{ + lockdep_assert_held(&nf_conntrack_expect_lock); +} + /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 165e7a03b8e9..e9a8350e7ccf 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -22,10 +22,16 @@ struct nf_conntrack_expect { /* Hash member */ struct hlist_node hnode; + /* Network namespace */ + possible_net_t net; + /* We expect this tuple, with the following mask */ struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_mask mask; +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone zone; +#endif /* Usage count. */ refcount_t use; @@ -40,7 +46,7 @@ struct nf_conntrack_expect { struct nf_conntrack_expect *this); /* Helper to assign to new connection */ - struct nf_conntrack_helper *helper; + struct nf_conntrack_helper __rcu *helper; /* The conntrack of the master connection */ struct nf_conn *master; @@ -62,7 +68,17 @@ struct nf_conntrack_expect { static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { - return nf_ct_net(exp->master); + return read_pnet(&exp->net); +} + +static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a, + const struct nf_conntrack_zone *b) +{ +#ifdef CONFIG_NF_CONNTRACK_ZONES + return a->zone.id == b->id; +#else + return true; +#endif } #define NF_CT_EXP_POLICY_NAME_LEN 16 diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index 6682e51513ef..2073cbac2afb 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -17,6 +17,7 @@ struct netns_mpls { size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; struct mutex platform_mutex; + seqcount_mutex_t platform_label_seq; struct ctl_table_header *ctl; }; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 23dd647fe024..b73983a17e08 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -59,7 +59,7 @@ struct netns_xfrm { struct list_head inexact_bins; - struct sock *nlsk; + struct sock __rcu *nlsk; struct sock *nlsk_stash; u32 sysctl_aevent_etime; diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index 79bd5a7a0f88..0e871c786513 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -27,11 +27,6 @@ struct sdca_function_desc; #define SDCA_MAX_ENTITY_COUNT 128 /* - * Sanity check on number of initialization writes, can be expanded if needed. - */ -#define SDCA_MAX_INIT_COUNT 2048 - -/* * The Cluster IDs are 16-bit, so a maximum of 65535 Clusters per * function can be represented, however limit this to a slightly * more reasonable value. Can be expanded if needed. diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 125bdc166bfe..0864700f76e0 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -769,12 +769,15 @@ TRACE_EVENT(btrfs_sync_file, ), TP_fast_assign( - const struct dentry *dentry = file->f_path.dentry; - const struct inode *inode = d_inode(dentry); + struct dentry *dentry = file_dentry(file); + struct inode *inode = file_inode(file); + struct dentry *parent = dget_parent(dentry); + struct inode *parent_inode = d_inode(parent); - TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); + dput(parent); + TP_fast_assign_fsid(btrfs_sb(inode->i_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); - __entry->parent = btrfs_ino(BTRFS_I(d_inode(dentry->d_parent))); + __entry->parent = btrfs_ino(BTRFS_I(parent_inode)); __entry->datasync = datasync; __entry->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); ), diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 33e99e792f1a..63597b004424 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -32,7 +32,9 @@ TRACE_DEFINE_ENUM(DMA_NONE); { DMA_ATTR_ALLOC_SINGLE_PAGES, "ALLOC_SINGLE_PAGES" }, \ { DMA_ATTR_NO_WARN, "NO_WARN" }, \ { DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \ - { DMA_ATTR_MMIO, "MMIO" }) + { DMA_ATTR_MMIO, "MMIO" }, \ + { DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \ + { DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" }) DECLARE_EVENT_CLASS(dma_map, TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 2d366be46a1c..cbe28211106c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -740,19 +740,19 @@ TRACE_EVENT(netfs_collect_stream, __field(unsigned int, wreq) __field(unsigned char, stream) __field(unsigned long long, collected_to) - __field(unsigned long long, front) + __field(unsigned long long, issued_to) ), TP_fast_assign( __entry->wreq = wreq->debug_id; __entry->stream = stream->stream_nr; __entry->collected_to = stream->collected_to; - __entry->front = stream->front ? stream->front->start : UINT_MAX; + __entry->issued_to = atomic64_read(&wreq->issued_to); ), - TP_printk("R=%08x[%x:] cto=%llx frn=%llx", + TP_printk("R=%08x[%x:] cto=%llx ito=%llx", __entry->wreq, __entry->stream, - __entry->collected_to, __entry->front) + __entry->collected_to, __entry->issued_to) ); TRACE_EVENT(netfs_folioq, diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 26071021e986..56b6b60a814f 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -159,5 +159,9 @@ enum ip_conntrack_expect_events { #define NF_CT_EXPECT_INACTIVE 0x2 #define NF_CT_EXPECT_USERSPACE 0x4 +#ifdef __KERNEL__ +#define NF_CT_EXPECT_MASK (NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \ + NF_CT_EXPECT_USERSPACE) +#endif #endif /* _UAPI_NF_CONNTRACK_COMMON_H */ diff --git a/init/Kconfig b/init/Kconfig index 444ce811ea67..7484cd703bc1 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -146,7 +146,7 @@ config CC_HAS_COUNTED_BY config CC_HAS_COUNTED_BY_PTR bool # supported since clang 22 - default y if CC_IS_CLANG && CLANG_VERSION >= 220000 + default y if CC_IS_CLANG && CLANG_VERSION >= 220100 # supported since gcc 16.0.0 default y if CC_IS_GCC && GCC_VERSION >= 160000 diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 80178b69e05a..c2d3e45544bb 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -119,12 +119,14 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) sq_idx); break; } - if ((++sq_head & sq_mask) == 0) { + if (sq_idx == sq_mask) { seq_printf(m, "%5u: corrupted sqe, wrapping 128B entry\n", sq_idx); break; } + sq_head++; + i++; sqe128 = true; } seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, " diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e1505c9cd09e..810991709da7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3261,6 +3261,18 @@ static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) bpf_link_dealloc(link); } +static bool bpf_link_is_tracepoint(struct bpf_link *link) +{ + /* + * Only these combinations support a tracepoint bpf_link. + * BPF_LINK_TYPE_TRACING raw_tp progs are hardcoded to use + * bpf_raw_tp_link_lops and thus dealloc_deferred(), see + * bpf_raw_tp_link_attach(). + */ + return link->type == BPF_LINK_TYPE_RAW_TRACEPOINT || + (link->type == BPF_LINK_TYPE_TRACING && link->attach_type == BPF_TRACE_RAW_TP); +} + static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) @@ -3279,16 +3291,25 @@ static void bpf_link_free(struct bpf_link *link) if (link->prog) ops->release(link); if (ops->dealloc_deferred) { - /* Schedule BPF link deallocation, which will only then + /* + * Schedule BPF link deallocation, which will only then * trigger putting BPF program refcount. * If underlying BPF program is sleepable or BPF link's target * attach hookpoint is sleepable or otherwise requires RCU GPs * to ensure link and its underlying BPF program is not * reachable anymore, we need to first wait for RCU tasks - * trace sync, and then go through "classic" RCU grace period + * trace sync, and then go through "classic" RCU grace period. + * + * For tracepoint BPF links, we need to go through SRCU grace + * period wait instead when non-faultable tracepoint is used. We + * don't need to chain SRCU grace period waits, however, for the + * faultable case, since it exclusively uses RCU Tasks Trace. */ if (link->sleepable || (link->prog && link->prog->sleepable)) call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + /* We need to do a SRCU grace period wait for non-faultable tracepoint BPF links. */ + else if (bpf_link_is_tracepoint(link)) + call_tracepoint_unregister_atomic(&link->rcu, bpf_link_defer_dealloc_rcu_gp); else call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); } else if (ops->dealloc) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a431b7d50e1b..5434b162c930 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -642,6 +642,13 @@ static bool is_atomic_load_insn(const struct bpf_insn *insn) insn->imm == BPF_LOAD_ACQ; } +static bool is_atomic_fetch_insn(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + (insn->imm & BPF_FETCH); +} + static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; @@ -4499,10 +4506,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * dreg still needs precision before this insn */ } - } else if (class == BPF_LDX || is_atomic_load_insn(insn)) { - if (!bt_is_reg_set(bt, dreg)) + } else if (class == BPF_LDX || + is_atomic_load_insn(insn) || + is_atomic_fetch_insn(insn)) { + u32 load_reg = dreg; + + /* + * Atomic fetch operation writes the old value into + * a register (sreg or r0) and if it was tracked for + * precision, propagate to the stack slot like we do + * in regular ldx. + */ + if (is_atomic_fetch_insn(insn)) + load_reg = insn->imm == BPF_CMPXCHG ? + BPF_REG_0 : sreg; + + if (!bt_is_reg_set(bt, load_reg)) return 0; - bt_clear_reg(bt, dreg); + bt_clear_reg(bt, load_reg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. @@ -7996,7 +8017,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); - } else if (base_type(reg->type) == PTR_TO_BUF) { + } else if (base_type(reg->type) == PTR_TO_BUF && + !type_may_be_null(reg->type)) { bool rdonly_mem = type_is_rdonly_mem(reg->type); u32 *max_access; @@ -20094,8 +20116,13 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * since someone could have accessed through (ptr - k), or * even done ptr -= k in a register, to get a safe access. */ - if (rold->range > rcur->range) + if (rold->range < 0 || rcur->range < 0) { + /* special case for [BEYOND|AT]_PKT_END */ + if (rold->range != rcur->range) + return false; + } else if (rold->range > rcur->range) { return false; + } /* id relations must be preserved */ if (!check_ids(rold->id, rcur->id, idmap)) return false; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 01fc2a93f3ef..4ca3cb993da2 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2126,6 +2126,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) #endif init_waitqueue_head(&cgrp->offline_waitq); + init_waitqueue_head(&cgrp->dying_populated_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } @@ -6224,6 +6225,78 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return 0; }; +/** + * cgroup_drain_dying - wait for dying tasks to leave before rmdir + * @cgrp: the cgroup being removed + * + * cgroup.procs and cgroup.threads use css_task_iter which filters out + * PF_EXITING tasks so that userspace doesn't see tasks that have already been + * reaped via waitpid(). However, cgroup_has_tasks() - which tests whether the + * cgroup has non-empty css_sets - is only updated when dying tasks pass through + * cgroup_task_dead() in finish_task_switch(). This creates a window where + * cgroup.procs reads empty but cgroup_has_tasks() is still true, making rmdir + * fail with -EBUSY from cgroup_destroy_locked() even though userspace sees no + * tasks. + * + * This function aligns cgroup_has_tasks() with what userspace can observe. If + * cgroup_has_tasks() but the task iterator sees nothing (all remaining tasks are + * PF_EXITING), we wait for cgroup_task_dead() to finish processing them. As the + * window between PF_EXITING and cgroup_task_dead() is short, the wait is brief. + * + * This function only concerns itself with this cgroup's own dying tasks. + * Whether the cgroup has children is cgroup_destroy_locked()'s problem. + * + * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we + * retry the full check from scratch. + * + * Must be called with cgroup_mutex held. + */ +static int cgroup_drain_dying(struct cgroup *cgrp) + __releases(&cgroup_mutex) __acquires(&cgroup_mutex) +{ + struct css_task_iter it; + struct task_struct *task; + DEFINE_WAIT(wait); + + lockdep_assert_held(&cgroup_mutex); +retry: + if (!cgroup_has_tasks(cgrp)) + return 0; + + /* Same iterator as cgroup.threads - if any task is visible, it's busy */ + css_task_iter_start(&cgrp->self, 0, &it); + task = css_task_iter_next(&it); + css_task_iter_end(&it); + + if (task) + return -EBUSY; + + /* + * All remaining tasks are PF_EXITING and will pass through + * cgroup_task_dead() shortly. Wait for a kick and retry. + * + * cgroup_has_tasks() can't transition from false to true while we're + * holding cgroup_mutex, but the true to false transition happens + * under css_set_lock (via cgroup_task_dead()). We must retest and + * prepare_to_wait() under css_set_lock. Otherwise, the transition + * can happen between our first test and prepare_to_wait(), and we + * sleep with no one to wake us. + */ + spin_lock_irq(&css_set_lock); + if (!cgroup_has_tasks(cgrp)) { + spin_unlock_irq(&css_set_lock); + return 0; + } + prepare_to_wait(&cgrp->dying_populated_waitq, &wait, + TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&css_set_lock); + mutex_unlock(&cgroup_mutex); + schedule(); + finish_wait(&cgrp->dying_populated_waitq, &wait); + mutex_lock(&cgroup_mutex); + goto retry; +} + int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; @@ -6233,9 +6306,12 @@ int cgroup_rmdir(struct kernfs_node *kn) if (!cgrp) return 0; - ret = cgroup_destroy_locked(cgrp); - if (!ret) - TRACE_CGROUP_PATH(rmdir, cgrp); + ret = cgroup_drain_dying(cgrp); + if (!ret) { + ret = cgroup_destroy_locked(cgrp); + if (!ret) + TRACE_CGROUP_PATH(rmdir, cgrp); + } cgroup_kn_unlock(kn); return ret; @@ -6995,6 +7071,7 @@ void cgroup_task_exit(struct task_struct *tsk) static void do_cgroup_task_dead(struct task_struct *tsk) { + struct cgrp_cset_link *link; struct css_set *cset; unsigned long flags; @@ -7008,6 +7085,11 @@ static void do_cgroup_task_dead(struct task_struct *tsk) if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); + /* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */ + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) + if (waitqueue_active(&link->cgrp->dying_populated_waitq)) + wake_up(&link->cgrp->dying_populated_waitq); + if (dl_task(tsk)) dec_dl_tasks_cs(tsk); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d21868455341..1335e437098e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2988,7 +2988,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; - bool cpus_updated, mems_updated; + bool setsched_check; int ret; /* used later by cpuset_attach() */ @@ -3003,20 +3003,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) if (ret) goto out_unlock; - cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); - mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); + /* + * Skip rights over task setsched check in v2 when nothing changes, + * migration permission derives from hierarchy ownership in + * cgroup_procs_write_permission()). + */ + setsched_check = !cpuset_v2() || + !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus) || + !nodes_equal(cs->effective_mems, oldcs->effective_mems); + + /* + * A v1 cpuset with tasks will have no CPU left only when CPU hotplug + * brings the last online CPU offline as users are not allowed to empty + * cpuset.cpus when there are active tasks inside. When that happens, + * we should allow tasks to migrate out without security check to make + * sure they will be able to run after migration. + */ + if (!is_in_v2_mode() && cpumask_empty(oldcs->effective_cpus)) + setsched_check = false; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; - /* - * Skip rights over task check in v2 when nothing changes, - * migration permission derives from hierarchy ownership in - * cgroup_procs_write_permission()). - */ - if (!cpuset_v2() || (cpus_updated || mems_updated)) { + if (setsched_check) { ret = security_task_setscheduler(task); if (ret) goto out_unlock; diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 86f87e43438c..0677918f06a8 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -453,7 +453,7 @@ static int active_cacheline_set_overlap(phys_addr_t cln, int overlap) return overlap; } -static void active_cacheline_inc_overlap(phys_addr_t cln) +static void active_cacheline_inc_overlap(phys_addr_t cln, bool is_cache_clean) { int overlap = active_cacheline_read_overlap(cln); @@ -462,7 +462,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln) /* If we overflowed the overlap counter then we're potentially * leaking dma-mappings. */ - WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, + WARN_ONCE(!is_cache_clean && overlap > ACTIVE_CACHELINE_MAX_OVERLAP, pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"), ACTIVE_CACHELINE_MAX_OVERLAP, &cln); } @@ -495,7 +495,7 @@ static int active_cacheline_insert(struct dma_debug_entry *entry, if (rc == -EEXIST) { struct dma_debug_entry *existing; - active_cacheline_inc_overlap(cln); + active_cacheline_inc_overlap(cln, entry->is_cache_clean); existing = radix_tree_lookup(&dma_active_cacheline, cln); /* A lookup failure here after we got -EEXIST is unexpected. */ WARN_ON(!existing); @@ -601,7 +601,8 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs) unsigned long flags; int rc; - entry->is_cache_clean = !!(attrs & DMA_ATTR_CPU_CACHE_CLEAN); + entry->is_cache_clean = attrs & (DMA_ATTR_DEBUGGING_IGNORE_CACHELINES | + DMA_ATTR_REQUIRE_COHERENT); bucket = get_hash_bucket(entry, &flags); hash_bucket_add(bucket, entry); diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index e89f175e9c2d..6184ff303f08 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -84,7 +84,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev, dma_addr_t dma_addr; if (is_swiotlb_force_bounce(dev)) { - if (attrs & DMA_ATTR_MMIO) + if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) return DMA_MAPPING_ERROR; return swiotlb_map(dev, phys, size, dir, attrs); @@ -98,7 +98,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev, dma_addr = phys_to_dma(dev, phys); if (unlikely(!dma_capable(dev, dma_addr, size, true)) || dma_kmalloc_needs_bounce(dev, size, dir)) { - if (is_swiotlb_active(dev)) + if (is_swiotlb_active(dev) && + !(attrs & DMA_ATTR_REQUIRE_COHERENT)) return swiotlb_map(dev, phys, size, dir, attrs); goto err_overflow; @@ -123,7 +124,7 @@ static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr, { phys_addr_t phys; - if (attrs & DMA_ATTR_MMIO) + if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) /* nothing to do: uncached and no swiotlb */ return; diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 3928a509c44c..6d3dd0bd3a88 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -164,6 +164,9 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, if (WARN_ON_ONCE(!dev->dma_mask)) return DMA_MAPPING_ERROR; + if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT)) + return DMA_MAPPING_ERROR; + if (dma_map_direct(dev, ops) || (!is_mmio && arch_dma_map_phys_direct(dev, phys + size))) addr = dma_direct_map_phys(dev, phys, size, dir, attrs); @@ -235,6 +238,9 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, BUG_ON(!valid_dma_direction(dir)); + if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT)) + return -EOPNOTSUPP; + if (WARN_ON_ONCE(!dev->dma_mask)) return 0; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index d8e6f1d889d5..9fd73700ddcf 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -30,6 +30,7 @@ #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/io.h> +#include <linux/kmsan-checks.h> #include <linux/iommu-helper.h> #include <linux/init.h> #include <linux/memblock.h> @@ -901,10 +902,19 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size local_irq_save(flags); page = pfn_to_page(pfn); - if (dir == DMA_TO_DEVICE) + if (dir == DMA_TO_DEVICE) { + /* + * Ideally, kmsan_check_highmem_page() + * could be used here to detect infoleaks, + * but callers may map uninitialized buffers + * that will be written by the device, + * causing false positives. + */ memcpy_from_page(vaddr, page, offset, sz); - else + } else { + kmsan_unpoison_memory(vaddr, sz); memcpy_to_page(page, offset, vaddr, sz); + } local_irq_restore(flags); size -= sz; @@ -913,8 +923,15 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size offset = 0; } } else if (dir == DMA_TO_DEVICE) { + /* + * Ideally, kmsan_check_memory() could be used here to detect + * infoleaks (uninitialized data being sent to device), but + * callers may map uninitialized buffers that will be written + * by the device, causing false positives. + */ memcpy(vaddr, phys_to_virt(orig_addr), size); } else { + kmsan_unpoison_memory(vaddr, size); memcpy(phys_to_virt(orig_addr), vaddr, size); } } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index cf7e610eac42..31e83a09789e 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -342,7 +342,7 @@ static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr) if (!vma) return FUTEX_NO_NODE; - mpol = vma_policy(vma); + mpol = READ_ONCE(vma->vm_policy); if (!mpol) return FUTEX_NO_NODE; diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index bc1f7e83a37e..7808068fa59e 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -918,7 +918,7 @@ int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked) int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to; - struct task_struct *exiting = NULL; + struct task_struct *exiting; struct rt_mutex_waiter rt_waiter; struct futex_q q = futex_q_init; DEFINE_WAKE_Q(wake_q); @@ -933,6 +933,7 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl to = futex_setup_timer(time, &timeout, flags, 0); retry: + exiting = NULL; ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 743c7a728237..77ad9691f6a6 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -459,6 +459,14 @@ SYSCALL_DEFINE4(futex_requeue, if (ret) return ret; + /* + * For now mandate both flags are identical, like the sys_futex() + * interface has. If/when we merge the variable sized futex support, + * that patch can modify this test to allow a difference in size. + */ + if (futexes[0].w.flags != futexes[1].w.flags) + return -EINVAL; + cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, diff --git a/kernel/power/main.c b/kernel/power/main.c index 5f8c9e12eaec..5429e9f19b65 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -40,7 +40,7 @@ void pm_restore_gfp_mask(void) { WARN_ON(!mutex_is_locked(&system_transition_mutex)); - if (WARN_ON(!saved_gfp_count) || --saved_gfp_count) + if (!saved_gfp_count || --saved_gfp_count) return; gfp_allowed_mask = saved_gfp_mask; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 6e1321837c66..a564650734dc 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -2855,6 +2855,17 @@ int snapshot_write_finalize(struct snapshot_handle *handle) { int error; + /* + * Call snapshot_write_next() to drain any trailing zero pages, + * but make sure we're in the data page region first. + * This function can return PAGE_SIZE if the kernel was expecting + * another copy page. Return -ENODATA in that situation. + */ + if (handle->cur > nr_meta_pages + 1) { + error = snapshot_write_next(handle); + if (error) + return error > 0 ? -ENODATA : error; + } copy_last_highmem_page(); error = hibernate_restore_protect_page(handle->buffer); /* Do that only if we have loaded the image entirely */ diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index dc5d614b372c..9b10b57b79ad 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -502,6 +502,15 @@ do { \ ___locked; \ }) +#define raw_spin_trylock_irqsave_rcu_node(p, flags) \ +({ \ + bool ___locked = raw_spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + \ + if (___locked) \ + smp_mb__after_unlock_lock(); \ + ___locked; \ +}) + #define raw_lockdep_assert_held_rcu_node(p) \ lockdep_assert_held(&ACCESS_PRIVATE(p, lock)) diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 3450c3751ef7..a2e2d516e51b 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -9,6 +9,7 @@ */ #include <linux/export.h> +#include <linux/irq_work.h> #include <linux/mutex.h> #include <linux/preempt.h> #include <linux/rcupdate_wait.h> @@ -41,6 +42,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp) ssp->srcu_idx_max = 0; INIT_WORK(&ssp->srcu_work, srcu_drive_gp); INIT_LIST_HEAD(&ssp->srcu_work.entry); + init_irq_work(&ssp->srcu_irq_work, srcu_tiny_irq_work); return 0; } @@ -84,6 +86,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); void cleanup_srcu_struct(struct srcu_struct *ssp) { WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]); + irq_work_sync(&ssp->srcu_irq_work); flush_work(&ssp->srcu_work); WARN_ON(ssp->srcu_gp_running); WARN_ON(ssp->srcu_gp_waiting); @@ -177,6 +180,20 @@ void srcu_drive_gp(struct work_struct *wp) } EXPORT_SYMBOL_GPL(srcu_drive_gp); +/* + * Use an irq_work to defer schedule_work() to avoid acquiring the workqueue + * pool->lock while the caller might hold scheduler locks, causing lockdep + * splats due to workqueue_init() doing a wakeup. + */ +void srcu_tiny_irq_work(struct irq_work *irq_work) +{ + struct srcu_struct *ssp; + + ssp = container_of(irq_work, struct srcu_struct, srcu_irq_work); + schedule_work(&ssp->srcu_work); +} +EXPORT_SYMBOL_GPL(srcu_tiny_irq_work); + static void srcu_gp_start_if_needed(struct srcu_struct *ssp) { unsigned long cookie; @@ -189,7 +206,7 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp) WRITE_ONCE(ssp->srcu_idx_max, cookie); if (!READ_ONCE(ssp->srcu_gp_running)) { if (likely(srcu_init_done)) - schedule_work(&ssp->srcu_work); + irq_work_queue(&ssp->srcu_irq_work); else if (list_empty(&ssp->srcu_work.entry)) list_add(&ssp->srcu_work.entry, &srcu_boot_list); } diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index aef8e91ad33e..0d01cd8c4b4a 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -19,6 +19,7 @@ #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/preempt.h> +#include <linux/irq_work.h> #include <linux/rcupdate_wait.h> #include <linux/sched.h> #include <linux/smp.h> @@ -75,44 +76,9 @@ static bool __read_mostly srcu_init_done; static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay); static void process_srcu(struct work_struct *work); +static void srcu_irq_work(struct irq_work *work); static void srcu_delay_timer(struct timer_list *t); -/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */ -#define spin_lock_rcu_node(p) \ -do { \ - spin_lock(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ -} while (0) - -#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock)) - -#define spin_lock_irq_rcu_node(p) \ -do { \ - spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ -} while (0) - -#define spin_unlock_irq_rcu_node(p) \ - spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) - -#define spin_lock_irqsave_rcu_node(p, flags) \ -do { \ - spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ - smp_mb__after_unlock_lock(); \ -} while (0) - -#define spin_trylock_irqsave_rcu_node(p, flags) \ -({ \ - bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ - \ - if (___locked) \ - smp_mb__after_unlock_lock(); \ - ___locked; \ -}) - -#define spin_unlock_irqrestore_rcu_node(p, flags) \ - spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ - /* * Initialize SRCU per-CPU data. Note that statically allocated * srcu_struct structures might already have srcu_read_lock() and @@ -131,7 +97,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp) */ for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); + raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); rcu_segcblist_init(&sdp->srcu_cblist); sdp->srcu_cblist_invoking = false; sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq; @@ -186,7 +152,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags) /* Each pass through this loop initializes one srcu_node structure. */ srcu_for_each_node_breadth_first(ssp, snp) { - spin_lock_init(&ACCESS_PRIVATE(snp, lock)); + raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock)); BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) { @@ -242,7 +208,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) if (!ssp->srcu_sup) return -ENOMEM; if (!is_static) - spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock)); + raw_spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock)); ssp->srcu_sup->srcu_size_state = SRCU_SIZE_SMALL; ssp->srcu_sup->node = NULL; mutex_init(&ssp->srcu_sup->srcu_cb_mutex); @@ -252,6 +218,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) mutex_init(&ssp->srcu_sup->srcu_barrier_mutex); atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0); INIT_DELAYED_WORK(&ssp->srcu_sup->work, process_srcu); + init_irq_work(&ssp->srcu_sup->irq_work, srcu_irq_work); ssp->srcu_sup->sda_is_static = is_static; if (!is_static) { ssp->sda = alloc_percpu(struct srcu_data); @@ -263,9 +230,12 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL; ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns(); if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { - if (!init_srcu_struct_nodes(ssp, is_static ? GFP_ATOMIC : GFP_KERNEL)) + if (!preemptible()) + WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_ALLOC); + else if (init_srcu_struct_nodes(ssp, GFP_KERNEL)) + WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); + else goto err_free_sda; - WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); } ssp->srcu_sup->srcu_ssp = ssp; smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, @@ -394,20 +364,20 @@ static void srcu_transition_to_big(struct srcu_struct *ssp) /* Double-checked locking on ->srcu_size-state. */ if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL) return; - spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags); + raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags); if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL) { - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); return; } __srcu_transition_to_big(ssp); - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); } /* * Check to see if the just-encountered contention event justifies * a transition to SRCU_SIZE_BIG. */ -static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp) +static void raw_spin_lock_irqsave_check_contention(struct srcu_struct *ssp) { unsigned long j; @@ -429,16 +399,16 @@ static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp) * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module * parameter permits this. */ -static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags) +static void raw_spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags) { struct srcu_struct *ssp = sdp->ssp; - if (spin_trylock_irqsave_rcu_node(sdp, *flags)) + if (raw_spin_trylock_irqsave_rcu_node(sdp, *flags)) return; - spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags); - spin_lock_irqsave_check_contention(ssp); - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, *flags); - spin_lock_irqsave_rcu_node(sdp, *flags); + raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags); + raw_spin_lock_irqsave_check_contention(ssp); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, *flags); + raw_spin_lock_irqsave_rcu_node(sdp, *flags); } /* @@ -447,12 +417,12 @@ static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned lon * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module * parameter permits this. */ -static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags) +static void raw_spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags) { - if (spin_trylock_irqsave_rcu_node(ssp->srcu_sup, *flags)) + if (raw_spin_trylock_irqsave_rcu_node(ssp->srcu_sup, *flags)) return; - spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags); - spin_lock_irqsave_check_contention(ssp); + raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags); + raw_spin_lock_irqsave_check_contention(ssp); } /* @@ -470,13 +440,13 @@ static void check_init_srcu_struct(struct srcu_struct *ssp) /* The smp_load_acquire() pairs with the smp_store_release(). */ if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq_needed))) /*^^^*/ return; /* Already initialized. */ - spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags); + raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags); if (!rcu_seq_state(ssp->srcu_sup->srcu_gp_seq_needed)) { - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); return; } init_srcu_struct_fields(ssp, true); - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); } /* @@ -742,13 +712,15 @@ void cleanup_srcu_struct(struct srcu_struct *ssp) unsigned long delay; struct srcu_usage *sup = ssp->srcu_sup; - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); delay = srcu_get_delay(ssp); - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); if (WARN_ON(!delay)) return; /* Just leak it! */ if (WARN_ON(srcu_readers_active(ssp))) return; /* Just leak it! */ + /* Wait for irq_work to finish first as it may queue a new work. */ + irq_work_sync(&sup->irq_work); flush_delayed_work(&sup->work); for_each_possible_cpu(cpu) { struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu); @@ -960,7 +932,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) mutex_lock(&sup->srcu_cb_mutex); /* End the current grace period. */ - spin_lock_irq_rcu_node(sup); + raw_spin_lock_irq_rcu_node(sup); idx = rcu_seq_state(sup->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); if (srcu_gp_is_expedited(ssp)) @@ -971,7 +943,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) gpseq = rcu_seq_current(&sup->srcu_gp_seq); if (ULONG_CMP_LT(sup->srcu_gp_seq_needed_exp, gpseq)) WRITE_ONCE(sup->srcu_gp_seq_needed_exp, gpseq); - spin_unlock_irq_rcu_node(sup); + raw_spin_unlock_irq_rcu_node(sup); mutex_unlock(&sup->srcu_gp_mutex); /* A new grace period can start at this point. But only one. */ @@ -983,7 +955,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) } else { idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); srcu_for_each_node_breadth_first(ssp, snp) { - spin_lock_irq_rcu_node(snp); + raw_spin_lock_irq_rcu_node(snp); cbs = false; last_lvl = snp >= sup->level[rcu_num_lvls - 1]; if (last_lvl) @@ -998,7 +970,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) else mask = snp->srcu_data_have_cbs[idx]; snp->srcu_data_have_cbs[idx] = 0; - spin_unlock_irq_rcu_node(snp); + raw_spin_unlock_irq_rcu_node(snp); if (cbs) srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay); } @@ -1008,27 +980,27 @@ static void srcu_gp_end(struct srcu_struct *ssp) if (!(gpseq & counter_wrap_check)) for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_irq_rcu_node(sdp); + raw_spin_lock_irq_rcu_node(sdp); if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100)) sdp->srcu_gp_seq_needed = gpseq; if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100)) sdp->srcu_gp_seq_needed_exp = gpseq; - spin_unlock_irq_rcu_node(sdp); + raw_spin_unlock_irq_rcu_node(sdp); } /* Callback initiation done, allow grace periods after next. */ mutex_unlock(&sup->srcu_cb_mutex); /* Start a new grace period if needed. */ - spin_lock_irq_rcu_node(sup); + raw_spin_lock_irq_rcu_node(sup); gpseq = rcu_seq_current(&sup->srcu_gp_seq); if (!rcu_seq_state(gpseq) && ULONG_CMP_LT(gpseq, sup->srcu_gp_seq_needed)) { srcu_gp_start(ssp); - spin_unlock_irq_rcu_node(sup); + raw_spin_unlock_irq_rcu_node(sup); srcu_reschedule(ssp, 0); } else { - spin_unlock_irq_rcu_node(sup); + raw_spin_unlock_irq_rcu_node(sup); } /* Transition to big if needed. */ @@ -1059,19 +1031,19 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_sup->srcu_gp_seq, s)) || (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s))) return; - spin_lock_irqsave_rcu_node(snp, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); sgsne = snp->srcu_gp_seq_needed_exp; if (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)) { - spin_unlock_irqrestore_rcu_node(snp, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); return; } WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } - spin_lock_irqsave_ssp_contention(ssp, &flags); + raw_spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(ssp->srcu_sup->srcu_gp_seq_needed_exp, s)) WRITE_ONCE(ssp->srcu_sup->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); } /* @@ -1109,12 +1081,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) { if (WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) && snp != snp_leaf) return; /* GP already done and CBs recorded. */ - spin_lock_irqsave_rcu_node(snp, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); snp_seq = snp->srcu_have_cbs[idx]; if (!srcu_invl_snp_seq(snp_seq) && ULONG_CMP_GE(snp_seq, s)) { if (snp == snp_leaf && snp_seq == s) snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - spin_unlock_irqrestore_rcu_node(snp, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); if (snp == snp_leaf && snp_seq != s) { srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0); return; @@ -1129,11 +1101,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, sgsne = snp->srcu_gp_seq_needed_exp; if (!do_norm && (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, s))) WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } /* Top of tree, must ensure the grace period will be started. */ - spin_lock_irqsave_ssp_contention(ssp, &flags); + raw_spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(sup->srcu_gp_seq_needed, s)) { /* * Record need for grace period s. Pair with load @@ -1154,13 +1126,17 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, // it isn't. And it does not have to be. After all, it // can only be executed during early boot when there is only // the one boot CPU running with interrupts still disabled. + // + // Use an irq_work here to avoid acquiring runqueue lock with + // srcu rcu_node::lock held. BPF instrument could introduce the + // opposite dependency, hence we need to break the possible + // locking dependency here. if (likely(srcu_init_done)) - queue_delayed_work(rcu_gp_wq, &sup->work, - !!srcu_get_delay(ssp)); + irq_work_queue(&sup->irq_work); else if (list_empty(&sup->work.work.entry)) list_add(&sup->work.work.entry, &srcu_boot_list); } - spin_unlock_irqrestore_rcu_node(sup, flags); + raw_spin_unlock_irqrestore_rcu_node(sup, flags); } /* @@ -1172,9 +1148,9 @@ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount) { unsigned long curdelay; - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); curdelay = !srcu_get_delay(ssp); - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); for (;;) { if (srcu_readers_active_idx_check(ssp, idx)) @@ -1285,12 +1261,12 @@ static bool srcu_should_expedite(struct srcu_struct *ssp) return false; /* If the local srcu_data structure has callbacks, not idle. */ sdp = raw_cpu_ptr(ssp->sda); - spin_lock_irqsave_rcu_node(sdp, flags); + raw_spin_lock_irqsave_rcu_node(sdp, flags); if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { - spin_unlock_irqrestore_rcu_node(sdp, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); return false; /* Callbacks already present, so not idle. */ } - spin_unlock_irqrestore_rcu_node(sdp, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); /* * No local callbacks, so probabilistically probe global state. @@ -1350,7 +1326,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id()); else sdp = raw_cpu_ptr(ssp->sda); - spin_lock_irqsave_sdp_contention(sdp, &flags); + raw_spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); /* @@ -1410,7 +1386,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, sdp->srcu_gp_seq_needed_exp = s; needexp = true; } - spin_unlock_irqrestore_rcu_node(sdp, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); /* Ensure that snp node tree is fully initialized before traversing it */ if (ss_state < SRCU_SIZE_WAIT_BARRIER) @@ -1522,7 +1498,7 @@ static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm) /* * Make sure that later code is ordered after the SRCU grace - * period. This pairs with the spin_lock_irq_rcu_node() + * period. This pairs with the raw_spin_lock_irq_rcu_node() * in srcu_invoke_callbacks(). Unlike Tree RCU, this is needed * because the current CPU might have been totally uninvolved with * (and thus unordered against) that grace period. @@ -1701,7 +1677,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp) */ static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp) { - spin_lock_irq_rcu_node(sdp); + raw_spin_lock_irq_rcu_node(sdp); atomic_inc(&ssp->srcu_sup->srcu_barrier_cpu_cnt); sdp->srcu_barrier_head.func = srcu_barrier_cb; debug_rcu_head_queue(&sdp->srcu_barrier_head); @@ -1710,7 +1686,7 @@ static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp) debug_rcu_head_unqueue(&sdp->srcu_barrier_head); atomic_dec(&ssp->srcu_sup->srcu_barrier_cpu_cnt); } - spin_unlock_irq_rcu_node(sdp); + raw_spin_unlock_irq_rcu_node(sdp); } /** @@ -1761,7 +1737,7 @@ static void srcu_expedite_current_cb(struct rcu_head *rhp) bool needcb = false; struct srcu_data *sdp = container_of(rhp, struct srcu_data, srcu_ec_head); - spin_lock_irqsave_sdp_contention(sdp, &flags); + raw_spin_lock_irqsave_sdp_contention(sdp, &flags); if (sdp->srcu_ec_state == SRCU_EC_IDLE) { WARN_ON_ONCE(1); } else if (sdp->srcu_ec_state == SRCU_EC_PENDING) { @@ -1771,7 +1747,7 @@ static void srcu_expedite_current_cb(struct rcu_head *rhp) sdp->srcu_ec_state = SRCU_EC_PENDING; needcb = true; } - spin_unlock_irqrestore_rcu_node(sdp, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); // If needed, requeue ourselves as an expedited SRCU callback. if (needcb) __call_srcu(sdp->ssp, &sdp->srcu_ec_head, srcu_expedite_current_cb, false); @@ -1795,7 +1771,7 @@ void srcu_expedite_current(struct srcu_struct *ssp) migrate_disable(); sdp = this_cpu_ptr(ssp->sda); - spin_lock_irqsave_sdp_contention(sdp, &flags); + raw_spin_lock_irqsave_sdp_contention(sdp, &flags); if (sdp->srcu_ec_state == SRCU_EC_IDLE) { sdp->srcu_ec_state = SRCU_EC_PENDING; needcb = true; @@ -1804,7 +1780,7 @@ void srcu_expedite_current(struct srcu_struct *ssp) } else { WARN_ON_ONCE(sdp->srcu_ec_state != SRCU_EC_REPOST); } - spin_unlock_irqrestore_rcu_node(sdp, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); // If needed, queue an expedited SRCU callback. if (needcb) __call_srcu(ssp, &sdp->srcu_ec_head, srcu_expedite_current_cb, false); @@ -1848,17 +1824,17 @@ static void srcu_advance_state(struct srcu_struct *ssp) */ idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq)); /* ^^^ */ if (idx == SRCU_STATE_IDLE) { - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) { WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq)); - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex); return; } idx = rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq)); if (idx == SRCU_STATE_IDLE) srcu_gp_start(ssp); - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); if (idx != SRCU_STATE_IDLE) { mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex); return; /* Someone else started the grace period. */ @@ -1872,10 +1848,10 @@ static void srcu_advance_state(struct srcu_struct *ssp) return; /* readers present, retry later. */ } srcu_flip(ssp); - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); rcu_seq_set_state(&ssp->srcu_sup->srcu_gp_seq, SRCU_STATE_SCAN2); ssp->srcu_sup->srcu_n_exp_nodelay = 0; - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); } if (rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq)) == SRCU_STATE_SCAN2) { @@ -1913,7 +1889,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) ssp = sdp->ssp; rcu_cblist_init(&ready_cbs); - spin_lock_irq_rcu_node(sdp); + raw_spin_lock_irq_rcu_node(sdp); WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); @@ -1924,7 +1900,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) */ if (sdp->srcu_cblist_invoking || !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) { - spin_unlock_irq_rcu_node(sdp); + raw_spin_unlock_irq_rcu_node(sdp); return; /* Someone else on the job or nothing to do. */ } @@ -1932,7 +1908,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) sdp->srcu_cblist_invoking = true; rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs); len = ready_cbs.len; - spin_unlock_irq_rcu_node(sdp); + raw_spin_unlock_irq_rcu_node(sdp); rhp = rcu_cblist_dequeue(&ready_cbs); for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { debug_rcu_head_unqueue(rhp); @@ -1947,11 +1923,11 @@ static void srcu_invoke_callbacks(struct work_struct *work) * Update counts, accelerate new callbacks, and if needed, * schedule another round of callback invocation. */ - spin_lock_irq_rcu_node(sdp); + raw_spin_lock_irq_rcu_node(sdp); rcu_segcblist_add_len(&sdp->srcu_cblist, -len); sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); - spin_unlock_irq_rcu_node(sdp); + raw_spin_unlock_irq_rcu_node(sdp); /* An SRCU barrier or callbacks from previous nesting work pending */ if (more) srcu_schedule_cbs_sdp(sdp, 0); @@ -1965,7 +1941,7 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay) { bool pushgp = true; - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) { if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq))) { /* All requests fulfilled, time to go idle. */ @@ -1975,7 +1951,7 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay) /* Outstanding request and no GP. Start one. */ srcu_gp_start(ssp); } - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); if (pushgp) queue_delayed_work(rcu_gp_wq, &ssp->srcu_sup->work, delay); @@ -1995,9 +1971,9 @@ static void process_srcu(struct work_struct *work) ssp = sup->srcu_ssp; srcu_advance_state(ssp); - spin_lock_irq_rcu_node(ssp->srcu_sup); + raw_spin_lock_irq_rcu_node(ssp->srcu_sup); curdelay = srcu_get_delay(ssp); - spin_unlock_irq_rcu_node(ssp->srcu_sup); + raw_spin_unlock_irq_rcu_node(ssp->srcu_sup); if (curdelay) { WRITE_ONCE(sup->reschedule_count, 0); } else { @@ -2015,6 +1991,23 @@ static void process_srcu(struct work_struct *work) srcu_reschedule(ssp, curdelay); } +static void srcu_irq_work(struct irq_work *work) +{ + struct srcu_struct *ssp; + struct srcu_usage *sup; + unsigned long delay; + unsigned long flags; + + sup = container_of(work, struct srcu_usage, irq_work); + ssp = sup->srcu_ssp; + + raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags); + delay = srcu_get_delay(ssp); + raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags); + + queue_delayed_work(rcu_gp_wq, &sup->work, !!delay); +} + void srcutorture_get_gp_data(struct srcu_struct *ssp, int *flags, unsigned long *gp_seq) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 26a6ac2f8826..d5bdcdb3f700 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2404,7 +2404,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, { struct scx_sched *sch = scx_root; - /* see kick_cpus_irq_workfn() */ + /* see kick_sync_wait_bal_cb() */ smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1); update_curr_scx(rq); @@ -2447,6 +2447,48 @@ switch_class: switch_class(rq, next); } +static void kick_sync_wait_bal_cb(struct rq *rq) +{ + struct scx_kick_syncs __rcu *ks = __this_cpu_read(scx_kick_syncs); + unsigned long *ksyncs = rcu_dereference_sched(ks)->syncs; + bool waited; + s32 cpu; + + /* + * Drop rq lock and enable IRQs while waiting. IRQs must be enabled + * — a target CPU may be waiting for us to process an IPI (e.g. TLB + * flush) while we wait for its kick_sync to advance. + * + * Also, keep advancing our own kick_sync so that new kick_sync waits + * targeting us, which can start after we drop the lock, cannot form + * cyclic dependencies. + */ +retry: + waited = false; + for_each_cpu(cpu, rq->scx.cpus_to_sync) { + /* + * smp_load_acquire() pairs with smp_store_release() on + * kick_sync updates on the target CPUs. + */ + if (cpu == cpu_of(rq) || + smp_load_acquire(&cpu_rq(cpu)->scx.kick_sync) != ksyncs[cpu]) { + cpumask_clear_cpu(cpu, rq->scx.cpus_to_sync); + continue; + } + + raw_spin_rq_unlock_irq(rq); + while (READ_ONCE(cpu_rq(cpu)->scx.kick_sync) == ksyncs[cpu]) { + smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1); + cpu_relax(); + } + raw_spin_rq_lock_irq(rq); + waited = true; + } + + if (waited) + goto retry; +} + static struct task_struct *first_local_task(struct rq *rq) { return list_first_entry_or_null(&rq->scx.local_dsq.list, @@ -2460,7 +2502,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) bool keep_prev; struct task_struct *p; - /* see kick_cpus_irq_workfn() */ + /* see kick_sync_wait_bal_cb() */ smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1); rq_modified_begin(rq, &ext_sched_class); @@ -2471,6 +2513,17 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) maybe_queue_balance_callback(rq); /* + * Defer to a balance callback which can drop rq lock and enable + * IRQs. Waiting directly in the pick path would deadlock against + * CPUs sending us IPIs (e.g. TLB flushes) while we wait for them. + */ + if (unlikely(rq->scx.kick_sync_pending)) { + rq->scx.kick_sync_pending = false; + queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb, + kick_sync_wait_bal_cb); + } + + /* * If any higher-priority sched class enqueued a runnable task on * this rq during balance_one(), abort and return RETRY_TASK, so * that the scheduler loop can restart. @@ -4713,6 +4766,9 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) if (!cpumask_empty(rq->scx.cpus_to_wait)) dump_line(&ns, " cpus_to_wait : %*pb", cpumask_pr_args(rq->scx.cpus_to_wait)); + if (!cpumask_empty(rq->scx.cpus_to_sync)) + dump_line(&ns, " cpus_to_sync : %*pb", + cpumask_pr_args(rq->scx.cpus_to_sync)); used = seq_buf_used(&ns); if (SCX_HAS_OP(sch, dump_cpu)) { @@ -5610,11 +5666,11 @@ static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *ksyncs) if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) { if (cur_class == &ext_sched_class) { + cpumask_set_cpu(cpu, this_scx->cpus_to_sync); ksyncs[cpu] = rq->scx.kick_sync; should_wait = true; - } else { - cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); } + cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); } resched_curr(rq); @@ -5669,27 +5725,15 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work) cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle); } - if (!should_wait) - return; - - for_each_cpu(cpu, this_scx->cpus_to_wait) { - unsigned long *wait_kick_sync = &cpu_rq(cpu)->scx.kick_sync; - - /* - * Busy-wait until the task running at the time of kicking is no - * longer running. This can be used to implement e.g. core - * scheduling. - * - * smp_cond_load_acquire() pairs with store_releases in - * pick_task_scx() and put_prev_task_scx(). The former breaks - * the wait if SCX's scheduling path is entered even if the same - * task is picked subsequently. The latter is necessary to break - * the wait when $cpu is taken by a higher sched class. - */ - if (cpu != cpu_of(this_rq)) - smp_cond_load_acquire(wait_kick_sync, VAL != ksyncs[cpu]); - - cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); + /* + * Can't wait in hardirq — kick_sync can't advance, deadlocking if + * CPUs wait for each other. Defer to kick_sync_wait_bal_cb(). + */ + if (should_wait) { + raw_spin_rq_lock(this_rq); + this_scx->kick_sync_pending = true; + resched_curr(this_rq); + raw_spin_rq_unlock(this_rq); } } @@ -5794,6 +5838,7 @@ void __init init_sched_ext_class(void) BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL, n)); BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_preempt, GFP_KERNEL, n)); BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_wait, GFP_KERNEL, n)); + BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_sync, GFP_KERNEL, n)); rq->scx.deferred_irq_work = IRQ_WORK_INIT_HARD(deferred_irq_workfn); rq->scx.kick_cpus_irq_work = IRQ_WORK_INIT_HARD(kick_cpus_irq_workfn); diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index ba298ac3ce6c..0ae93cd64004 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -543,7 +543,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, * piled up on it even if there is an idle core elsewhere on * the system. */ - waker_node = cpu_to_node(cpu); + waker_node = scx_cpu_node_if_enabled(cpu); if (!(current->flags & PF_EXITING) && cpu_rq(cpu)->scx.local_dsq.nr == 0 && (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) && diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 43bbf0693cca..1ef9ba480f51 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -805,9 +805,12 @@ struct scx_rq { cpumask_var_t cpus_to_kick_if_idle; cpumask_var_t cpus_to_preempt; cpumask_var_t cpus_to_wait; + cpumask_var_t cpus_to_sync; + bool kick_sync_pending; unsigned long kick_sync; local_t reenq_local_deferred; struct balance_callback deferred_bal_cb; + struct balance_callback kick_sync_bal_cb; struct irq_work deferred_irq_work; struct irq_work kick_cpus_irq_work; struct scx_dispatch_q bypass_dsq; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9d3a666ffde1..c9efb17cc255 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1118,7 +1118,7 @@ int proc_do_large_bitmap(const struct ctl_table *table, int dir, unsigned long bitmap_len = table->maxlen; unsigned long *bitmap = *(unsigned long **) table->data; unsigned long *tmp_bitmap = NULL; - char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c; + char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c = 0; if (!bitmap || !bitmap_len || !left || (*ppos && SYSCTL_KERN_TO_USER(dir))) { *lenp = 0; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 069d93bfb0c7..b64db405ba5c 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -540,7 +540,7 @@ static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return alarm_forward(alarm, timr->it_interval, now); + return alarm_forward(alarm, now, timr->it_interval); } /** diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0b040a417442..af7079aa0f36 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2752,6 +2752,10 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (!is_kprobe_multi(prog)) return -EINVAL; + /* kprobe_multi is not allowed to be sleepable. */ + if (prog->sleepable) + return -EINVAL; + /* Writing to context is not allowed for kprobes. */ if (prog->aux->kprobe_write_ctx) return -EINVAL; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d5230b759a2d..655db2e82513 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -22,6 +22,39 @@ static struct task_struct *trigger_kthread; static struct llist_head trigger_data_free_list; static DEFINE_MUTEX(trigger_data_kthread_mutex); +static int trigger_kthread_fn(void *ignore); + +static void trigger_create_kthread_locked(void) +{ + lockdep_assert_held(&trigger_data_kthread_mutex); + + if (!trigger_kthread) { + struct task_struct *kthread; + + kthread = kthread_create(trigger_kthread_fn, NULL, + "trigger_data_free"); + if (!IS_ERR(kthread)) + WRITE_ONCE(trigger_kthread, kthread); + } +} + +static void trigger_data_free_queued_locked(void) +{ + struct event_trigger_data *data, *tmp; + struct llist_node *llnodes; + + lockdep_assert_held(&trigger_data_kthread_mutex); + + llnodes = llist_del_all(&trigger_data_free_list); + if (!llnodes) + return; + + tracepoint_synchronize_unregister(); + + llist_for_each_entry_safe(data, tmp, llnodes, llist) + kfree(data); +} + /* Bulk garbage collection of event_trigger_data elements */ static int trigger_kthread_fn(void *ignore) { @@ -56,30 +89,50 @@ void trigger_data_free(struct event_trigger_data *data) if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); + /* + * Boot-time trigger registration can fail before kthread creation + * works. Keep the deferred-free semantics during boot and let late + * init start the kthread to drain the list. + */ + if (system_state == SYSTEM_BOOTING && !trigger_kthread) { + llist_add(&data->llist, &trigger_data_free_list); + return; + } + if (unlikely(!trigger_kthread)) { guard(mutex)(&trigger_data_kthread_mutex); + + trigger_create_kthread_locked(); /* Check again after taking mutex */ if (!trigger_kthread) { - struct task_struct *kthread; - - kthread = kthread_create(trigger_kthread_fn, NULL, - "trigger_data_free"); - if (!IS_ERR(kthread)) - WRITE_ONCE(trigger_kthread, kthread); + llist_add(&data->llist, &trigger_data_free_list); + /* Drain the queued frees synchronously if creation failed. */ + trigger_data_free_queued_locked(); + return; } } - if (!trigger_kthread) { - /* Do it the slow way */ - tracepoint_synchronize_unregister(); - kfree(data); - return; - } - llist_add(&data->llist, &trigger_data_free_list); wake_up_process(trigger_kthread); } +static int __init trigger_data_free_init(void) +{ + guard(mutex)(&trigger_data_kthread_mutex); + + if (llist_empty(&trigger_data_free_list)) + return 0; + + trigger_create_kthread_locked(); + if (trigger_kthread) + wake_up_process(trigger_kthread); + else + trigger_data_free_queued_locked(); + + return 0; +} +late_initcall(trigger_data_free_init); + static inline void data_ops_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index dee610e465b9..be6cf0bb3c03 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2073,8 +2073,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy) if (!osnoise_has_registered_instances()) return; - guard(mutex)(&interface_lock); guard(cpus_read_lock)(); + guard(mutex)(&interface_lock); if (!cpu_online(cpu)) return; @@ -2237,11 +2237,11 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf, if (running) stop_per_cpu_kthreads(); - mutex_lock(&interface_lock); /* * avoid CPU hotplug operations that might read options. */ cpus_read_lock(); + mutex_lock(&interface_lock); retval = cnt; @@ -2257,8 +2257,8 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf, clear_bit(option, &osnoise_options); } - cpus_read_unlock(); mutex_unlock(&interface_lock); + cpus_read_unlock(); if (running) start_per_cpu_kthreads(); @@ -2345,16 +2345,16 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count, if (running) stop_per_cpu_kthreads(); - mutex_lock(&interface_lock); /* * osnoise_cpumask is read by CPU hotplug operations. */ cpus_read_lock(); + mutex_lock(&interface_lock); cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new); - cpus_read_unlock(); mutex_unlock(&interface_lock); + cpus_read_unlock(); if (running) start_per_cpu_kthreads(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b77119d71641..eda756556341 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7699,8 +7699,29 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) else ts = touched; - /* did we stall? */ + /* + * Did we stall? + * + * Do a lockless check first to do not disturb the system. + * + * Prevent false positives by double checking the timestamp + * under pool->lock. The lock makes sure that the check reads + * an updated pool->last_progress_ts when this CPU saw + * an already updated pool->worklist above. It seems better + * than adding another barrier into __queue_work() which + * is a hotter path. + */ if (time_after(now, ts + thresh)) { + scoped_guard(raw_spinlock_irqsave, &pool->lock) { + pool_ts = pool->last_progress_ts; + if (time_after(pool_ts, touched)) + ts = pool_ts; + else + ts = touched; + } + if (!time_after(now, ts + thresh)) + continue; + lockup_detected = true; stall_time = jiffies_to_msecs(now - pool_ts) / 1000; max_stall_time = max(max_stall_time, stall_time); @@ -7712,8 +7733,6 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", stall_time); } - - } if (lockup_detected) diff --git a/lib/bug.c b/lib/bug.c index 623c467a8b76..aab9e6a40c5f 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -173,10 +173,8 @@ struct bug_entry *find_bug(unsigned long bugaddr) return module_find_bug(bugaddr); } -__diag_push(); -__diag_ignore(GCC, all, "-Wsuggest-attribute=format", - "Not a valid __printf() conversion candidate."); -static void __warn_printf(const char *fmt, struct pt_regs *regs) +static __printf(1, 0) +void __warn_printf(const char *fmt, struct pt_regs *regs) { if (!fmt) return; @@ -195,7 +193,6 @@ static void __warn_printf(const char *fmt, struct pt_regs *regs) printk("%s", fmt); } -__diag_pop(); static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long bugaddr, struct pt_regs *regs) { diff --git a/lib/crypto/chacha-block-generic.c b/lib/crypto/chacha-block-generic.c index 77f68de71066..4a6d627580cb 100644 --- a/lib/crypto/chacha-block-generic.c +++ b/lib/crypto/chacha-block-generic.c @@ -87,6 +87,8 @@ void chacha_block_generic(struct chacha_state *state, &out[i * sizeof(u32)]); state->x[12]++; + + chacha_zeroize_state(&permuted_state); } EXPORT_SYMBOL(chacha_block_generic); @@ -110,5 +112,7 @@ void hchacha_block_generic(const struct chacha_state *state, memcpy(&out[0], &permuted_state.x[0], 16); memcpy(&out[4], &permuted_state.x[12], 16); + + chacha_zeroize_state(&permuted_state); } EXPORT_SYMBOL(hchacha_block_generic); diff --git a/mm/damon/core.c b/mm/damon/core.c index c1d1091d307e..3e1890d64d06 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1252,6 +1252,7 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src) { int err; + dst->maybe_corrupted = true; if (!is_power_of_2(src->min_region_sz)) return -EINVAL; @@ -1277,6 +1278,7 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src) dst->addr_unit = src->addr_unit; dst->min_region_sz = src->min_region_sz; + dst->maybe_corrupted = false; return 0; } @@ -2678,6 +2680,8 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel) complete(&control->completion); else if (control->canceled && control->dealloc_on_cancel) kfree(control); + if (!cancel && ctx->maybe_corrupted) + break; } mutex_lock(&ctx->call_controls_lock); @@ -2707,6 +2711,8 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) kdamond_usleep(min_wait_time); kdamond_call(ctx, false); + if (ctx->maybe_corrupted) + return -EINVAL; damos_walk_cancel(ctx); } return -EBUSY; @@ -2790,6 +2796,8 @@ static int kdamond_fn(void *data) * kdamond_merge_regions() if possible, to reduce overhead */ kdamond_call(ctx, false); + if (ctx->maybe_corrupted) + break; if (!list_empty(&ctx->schemes)) kdamond_apply_schemes(ctx); else diff --git a/mm/damon/stat.c b/mm/damon/stat.c index 25fb44ccf99d..cf2c5a541eee 100644 --- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -145,12 +145,59 @@ static int damon_stat_damon_call_fn(void *data) return 0; } +struct damon_stat_system_ram_range_walk_arg { + bool walked; + struct resource res; +}; + +static int damon_stat_system_ram_walk_fn(struct resource *res, void *arg) +{ + struct damon_stat_system_ram_range_walk_arg *a = arg; + + if (!a->walked) { + a->walked = true; + a->res.start = res->start; + } + a->res.end = res->end; + return 0; +} + +static unsigned long damon_stat_res_to_core_addr(resource_size_t ra, + unsigned long addr_unit) +{ + /* + * Use div_u64() for avoiding linking errors related with __udivdi3, + * __aeabi_uldivmod, or similar problems. This should also improve the + * performance optimization (read div_u64() comment for the detail). + */ + if (sizeof(ra) == 8 && sizeof(addr_unit) == 4) + return div_u64(ra, addr_unit); + return ra / addr_unit; +} + +static int damon_stat_set_monitoring_region(struct damon_target *t, + unsigned long addr_unit, unsigned long min_region_sz) +{ + struct damon_addr_range addr_range; + struct damon_stat_system_ram_range_walk_arg arg = {}; + + walk_system_ram_res(0, -1, &arg, damon_stat_system_ram_walk_fn); + if (!arg.walked) + return -EINVAL; + addr_range.start = damon_stat_res_to_core_addr( + arg.res.start, addr_unit); + addr_range.end = damon_stat_res_to_core_addr( + arg.res.end + 1, addr_unit); + if (addr_range.end <= addr_range.start) + return -EINVAL; + return damon_set_regions(t, &addr_range, 1, min_region_sz); +} + static struct damon_ctx *damon_stat_build_ctx(void) { struct damon_ctx *ctx; struct damon_attrs attrs; struct damon_target *target; - unsigned long start = 0, end = 0; ctx = damon_new_ctx(); if (!ctx) @@ -180,8 +227,8 @@ static struct damon_ctx *damon_stat_build_ctx(void) if (!target) goto free_out; damon_add_target(ctx, target); - if (damon_set_region_biggest_system_ram_default(target, &start, &end, - ctx->min_region_sz)) + if (damon_stat_set_monitoring_region(target, ctx->addr_unit, + ctx->min_region_sz)) goto free_out; return ctx; free_out: diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 576d1ddd736b..6a44a2f3d8fc 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1524,8 +1524,10 @@ static int damon_sysfs_commit_input(void *data) if (IS_ERR(param_ctx)) return PTR_ERR(param_ctx); test_ctx = damon_sysfs_new_test_ctx(kdamond->damon_ctx); - if (!test_ctx) + if (!test_ctx) { + damon_destroy_ctx(param_ctx); return -ENOMEM; + } err = damon_commit_ctx(test_ctx, param_ctx); if (err) goto out; @@ -1618,9 +1620,12 @@ static int damon_sysfs_repeat_call_fn(void *data) if (!mutex_trylock(&damon_sysfs_lock)) return 0; + if (sysfs_kdamond->contexts->nr != 1) + goto out; damon_sysfs_upd_tuned_intervals(sysfs_kdamond); damon_sysfs_upd_schemes_stats(sysfs_kdamond); damon_sysfs_upd_schemes_effective_quotas(sysfs_kdamond); +out: mutex_unlock(&damon_sysfs_lock); return 0; } @@ -1747,6 +1752,9 @@ static int damon_sysfs_update_schemes_tried_regions( static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd, struct damon_sysfs_kdamond *kdamond) { + if (cmd != DAMON_SYSFS_CMD_OFF && kdamond->contexts->nr != 1) + return -EINVAL; + switch (cmd) { case DAMON_SYSFS_CMD_ON: return damon_sysfs_turn_damon_on(kdamond); @@ -778,7 +778,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map, struct page *page = hmm_pfn_to_page(pfns[idx]); phys_addr_t paddr = hmm_pfn_to_phys(pfns[idx]); size_t offset = idx * map->dma_entry_size; - unsigned long attrs = 0; + unsigned long attrs = DMA_ATTR_REQUIRE_COHERENT; dma_addr_t dma_addr; int ret; @@ -871,7 +871,7 @@ bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx) struct dma_iova_state *state = &map->state; dma_addr_t *dma_addrs = map->dma_list; unsigned long *pfns = map->pfn_list; - unsigned long attrs = 0; + unsigned long attrs = DMA_ATTR_REQUIRE_COHERENT; if ((pfns[idx] & valid_dma) != valid_dma) return false; diff --git a/mm/memory.c b/mm/memory.c index 2f815a34d924..c65e82c86fed 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6815,11 +6815,16 @@ retry: pudp = pud_offset(p4dp, address); pud = pudp_get(pudp); - if (pud_none(pud)) + if (!pud_present(pud)) goto out; if (pud_leaf(pud)) { lock = pud_lock(mm, pudp); - if (!unlikely(pud_leaf(pud))) { + pud = pudp_get(pudp); + + if (unlikely(!pud_present(pud))) { + spin_unlock(lock); + goto out; + } else if (unlikely(!pud_leaf(pud))) { spin_unlock(lock); goto retry; } @@ -6831,9 +6836,16 @@ retry: pmdp = pmd_offset(pudp, address); pmd = pmdp_get_lockless(pmdp); + if (!pmd_present(pmd)) + goto out; if (pmd_leaf(pmd)) { lock = pmd_lock(mm, pmdp); - if (!unlikely(pmd_leaf(pmd))) { + pmd = pmdp_get(pmdp); + + if (unlikely(!pmd_present(pmd))) { + spin_unlock(lock); + goto out; + } else if (unlikely(!pmd_leaf(pmd))) { spin_unlock(lock); goto retry; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e5175f1c767..cf92bd6a8226 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -487,7 +487,13 @@ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; - kmem_cache_free(policy_cache, pol); + /* + * Required to allow mmap_lock_speculative*() access, see for example + * futex_key_to_node_opt(). All accesses are serialized by mmap_lock, + * however the speculative lock section unbound by the normal lock + * boundaries, requiring RCU freeing. + */ + kfree_rcu(pol, rcu); } EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm"); @@ -1020,7 +1026,7 @@ static int vma_replace_policy(struct vm_area_struct *vma, } old = vma->vm_policy; - vma->vm_policy = new; /* protected by mmap_lock */ + WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */ mpol_put(old); return 0; diff --git a/mm/mseal.c b/mm/mseal.c index 316b5e1dec78..ac58643181f7 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -56,7 +56,6 @@ static int mseal_apply(struct mm_struct *mm, unsigned long start, unsigned long end) { struct vm_area_struct *vma, *prev; - unsigned long curr_start = start; VMA_ITERATOR(vmi, mm, start); /* We know there are no gaps so this will be non-NULL. */ @@ -66,6 +65,7 @@ static int mseal_apply(struct mm_struct *mm, prev = vma; for_each_vma_range(vmi, vma, end) { + const unsigned long curr_start = MAX(vma->vm_start, start); const unsigned long curr_end = MIN(vma->vm_end, end); if (!(vma->vm_flags & VM_SEALED)) { @@ -79,7 +79,6 @@ static int mseal_apply(struct mm_struct *mm, } prev = vma; - curr_start = curr_end; } return 0; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index a94c401ab2cf..4e7bcd975c54 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -97,6 +97,7 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pud_t pudval = pudp_get(pud); pmd_t *pmd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; @@ -105,6 +106,24 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, int err = 0; int depth = real_depth(3); + /* + * For PTE handling, pte_offset_map_lock() takes care of checking + * whether there actually is a page table. But it also has to be + * very careful about concurrent page table reclaim. + * + * Similarly, we have to be careful here - a PUD entry that points + * to a PMD table cannot go away, so we can just walk it. But if + * it's something else, we need to ensure we didn't race something, + * so need to retry. + * + * A pertinent example of this is a PUD refault after PUD split - + * we will need to split again or risk accessing invalid memory. + */ + if (!pud_present(pudval) || pud_leaf(pudval)) { + walk->action = ACTION_AGAIN; + return 0; + } + pmd = pmd_offset(pud, addr); do { again: @@ -218,12 +237,12 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, else if (pud_leaf(*pud) || !pud_present(*pud)) continue; /* Nothing to do. */ - if (pud_none(*pud)) - goto again; - err = walk_pmd_range(pud, addr, next, walk); if (err) break; + + if (walk->action == ACTION_AGAIN) + goto again; } while (pud++, addr = next, addr != end); return err; diff --git a/mm/rmap.c b/mm/rmap.c index 391337282e3f..8f08090d7eb9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -457,6 +457,13 @@ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma) list_del(&avc->same_vma); anon_vma_chain_free(avc); } + + /* + * The anon_vma assigned to this VMA is no longer valid, as we were not + * able to correctly clone AVC state. Avoid inconsistent anon_vma tree + * state by resetting. + */ + vma->anon_vma = NULL; } /** diff --git a/mm/swap_state.c b/mm/swap_state.c index 6d0eef7470be..48aff2c917c0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -494,6 +494,10 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry, __folio_set_locked(folio); __folio_set_swapbacked(folio); + + if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) + goto failed; + for (;;) { ret = swap_cache_add_folio(folio, entry, &shadow); if (!ret) @@ -514,11 +518,6 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry, goto failed; } - if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) { - swap_cache_del_folio(folio); - goto failed; - } - memcg1_swapin(entry, folio_nr_pages(folio)); if (shadow) workingset_refault(folio, shadow); diff --git a/mm/zswap.c b/mm/zswap.c index e6ec3295bdb0..16b2ef7223e1 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -942,9 +942,15 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio) /* zswap entries of length PAGE_SIZE are not compressed. */ if (entry->length == PAGE_SIZE) { + void *dst; + WARN_ON_ONCE(input->length != PAGE_SIZE); - memcpy_from_sglist(kmap_local_folio(folio, 0), input, 0, PAGE_SIZE); + + dst = kmap_local_folio(folio, 0); + memcpy_from_sglist(dst, input, 0, PAGE_SIZE); dlen = PAGE_SIZE; + kunmap_local(dst); + flush_dcache_folio(folio); } else { sg_init_table(&output, 1); sg_set_folio(&output, folio, PAGE_SIZE, 0); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6eb59e9f2aa8..11d3ad8d2551 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1843,9 +1843,13 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data) u8 aux_num_cis = 0; u8 cis_id; + hci_dev_lock(hdev); + conn = hci_conn_hash_lookup_cig(hdev, cig_id); - if (!conn) + if (!conn) { + hci_dev_unlock(hdev); return 0; + } qos = &conn->iso_qos; pdu->cig_id = cig_id; @@ -1884,6 +1888,8 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data) } pdu->num_cis = aux_num_cis; + hci_dev_unlock(hdev); + if (!pdu->num_cis) return 0; @@ -3095,7 +3101,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) * hci_connect_le serializes the connection attempts so only one * connection can be in BT_CONNECT at time. */ - if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { + if (conn->state == BT_CONNECT && READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 31308c1de4ec..01f8ceeb1c0c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4126,7 +4126,7 @@ static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb); } - if (hdev->req_status == HCI_REQ_PEND && + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 286529d2e554..3ebc5e6d45d9 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -80,6 +80,10 @@ static void *hci_le_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, return data; } +static void hci_store_wake_reason(struct hci_dev *hdev, + const bdaddr_t *bdaddr, u8 addr_type) + __must_hold(&hdev->lock); + static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -3111,6 +3115,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); + hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); /* Check for existing connection: * @@ -3274,6 +3279,10 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type); + hci_dev_lock(hdev); + hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); + hci_dev_unlock(hdev); + /* Reject incoming connection from device with same BD ADDR against * CVE-2020-26555 */ @@ -5021,6 +5030,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); + hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { @@ -5713,6 +5723,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, int err; hci_dev_lock(hdev); + hci_store_wake_reason(hdev, bdaddr, bdaddr_type); /* All controllers implicitly stop advertising in the event of a * connection, so ensure that the state bit is cleared. @@ -6005,6 +6016,7 @@ static void hci_le_past_received_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); + hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type); hci_dev_clear_flag(hdev, HCI_PA_SYNC); @@ -6403,6 +6415,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, info->length + 1)) break; + hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); + if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, @@ -6491,6 +6505,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, info->length)) break; + hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); + evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); @@ -6536,6 +6552,7 @@ static void hci_le_pa_sync_established_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); + hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type); hci_dev_clear_flag(hdev, HCI_PA_SYNC); @@ -6767,25 +6784,31 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, latency = le16_to_cpu(ev->latency); timeout = le16_to_cpu(ev->timeout); + hci_dev_lock(hdev); + hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon || hcon->state != BT_CONNECTED) - return send_conn_param_neg_reply(hdev, handle, - HCI_ERROR_UNKNOWN_CONN_ID); + if (!hcon || hcon->state != BT_CONNECTED) { + send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_UNKNOWN_CONN_ID); + goto unlock; + } - if (max > hcon->le_conn_max_interval) - return send_conn_param_neg_reply(hdev, handle, - HCI_ERROR_INVALID_LL_PARAMS); + if (max > hcon->le_conn_max_interval) { + send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + goto unlock; + } - if (hci_check_conn_params(min, max, latency, timeout)) - return send_conn_param_neg_reply(hdev, handle, - HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) { + send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + goto unlock; + } if (hcon->role == HCI_ROLE_MASTER) { struct hci_conn_params *params; u8 store_hint; - hci_dev_lock(hdev); - params = hci_conn_params_lookup(hdev, &hcon->dst, hcon->dst_type); if (params) { @@ -6798,8 +6821,6 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, store_hint = 0x00; } - hci_dev_unlock(hdev); - mgmt_new_conn_param(hdev, &hcon->dst, hcon->dst_type, store_hint, min, max, latency, timeout); } @@ -6813,6 +6834,9 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, cp.max_ce_len = 0; hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp); + +unlock: + hci_dev_unlock(hdev); } static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, @@ -6834,6 +6858,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, for (i = 0; i < ev->num; i++) { struct hci_ev_le_direct_adv_info *info = &ev->info[i]; + hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); + process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, info->direct_addr_type, HCI_ADV_PHY_1M, 0, @@ -7517,73 +7543,29 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return true; } -static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, - struct sk_buff *skb) +static void hci_store_wake_reason(struct hci_dev *hdev, + const bdaddr_t *bdaddr, u8 addr_type) + __must_hold(&hdev->lock) { - struct hci_ev_le_advertising_info *adv; - struct hci_ev_le_direct_adv_info *direct_adv; - struct hci_ev_le_ext_adv_info *ext_adv; - const struct hci_ev_conn_complete *conn_complete = (void *)skb->data; - const struct hci_ev_conn_request *conn_request = (void *)skb->data; - - hci_dev_lock(hdev); + lockdep_assert_held(&hdev->lock); /* If we are currently suspended and this is the first BT event seen, * save the wake reason associated with the event. */ if (!hdev->suspended || hdev->wake_reason) - goto unlock; + return; + + if (!bdaddr) { + hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED; + return; + } /* Default to remote wake. Values for wake_reason are documented in the * Bluez mgmt api docs. */ hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE; - - /* Once configured for remote wakeup, we should only wake up for - * reconnections. It's useful to see which device is waking us up so - * keep track of the bdaddr of the connection event that woke us up. - */ - if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); - hdev->wake_addr_type = BDADDR_BREDR; - } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); - hdev->wake_addr_type = BDADDR_BREDR; - } else if (event == HCI_EV_LE_META) { - struct hci_ev_le_meta *le_ev = (void *)skb->data; - u8 subevent = le_ev->subevent; - u8 *ptr = &skb->data[sizeof(*le_ev)]; - u8 num_reports = *ptr; - - if ((subevent == HCI_EV_LE_ADVERTISING_REPORT || - subevent == HCI_EV_LE_DIRECT_ADV_REPORT || - subevent == HCI_EV_LE_EXT_ADV_REPORT) && - num_reports) { - adv = (void *)(ptr + 1); - direct_adv = (void *)(ptr + 1); - ext_adv = (void *)(ptr + 1); - - switch (subevent) { - case HCI_EV_LE_ADVERTISING_REPORT: - bacpy(&hdev->wake_addr, &adv->bdaddr); - hdev->wake_addr_type = adv->bdaddr_type; - break; - case HCI_EV_LE_DIRECT_ADV_REPORT: - bacpy(&hdev->wake_addr, &direct_adv->bdaddr); - hdev->wake_addr_type = direct_adv->bdaddr_type; - break; - case HCI_EV_LE_EXT_ADV_REPORT: - bacpy(&hdev->wake_addr, &ext_adv->bdaddr); - hdev->wake_addr_type = ext_adv->bdaddr_type; - break; - } - } - } else { - hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED; - } - -unlock: - hci_dev_unlock(hdev); + bacpy(&hdev->wake_addr, bdaddr); + hdev->wake_addr_type = addr_type; } #define HCI_EV_VL(_op, _func, _min_len, _max_len) \ @@ -7830,14 +7812,15 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) skb_pull(skb, HCI_EVENT_HDR_SIZE); - /* Store wake reason if we're suspended */ - hci_store_wake_reason(hdev, event, skb); - bt_dev_dbg(hdev, "event 0x%2.2x", event); hci_event_func(hdev, event, skb, &opcode, &status, &req_complete, &req_complete_skb); + hci_dev_lock(hdev); + hci_store_wake_reason(hdev, NULL, 0); + hci_dev_unlock(hdev); + if (req_complete) { req_complete(hdev, status, opcode); } else if (req_complete_skb) { diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 3166914b0d6c..919ec275dd23 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -25,11 +25,11 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, { bt_dev_dbg(hdev, "result 0x%2.2x", result); - if (hdev->req_status != HCI_REQ_PEND) + if (READ_ONCE(hdev->req_status) != HCI_REQ_PEND) return; hdev->req_result = result; - hdev->req_status = HCI_REQ_DONE; + WRITE_ONCE(hdev->req_status, HCI_REQ_DONE); /* Free the request command so it is not used as response */ kfree_skb(hdev->req_skb); @@ -167,20 +167,20 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hci_cmd_sync_add(&req, opcode, plen, param, event, sk); - hdev->req_status = HCI_REQ_PEND; + WRITE_ONCE(hdev->req_status, HCI_REQ_PEND); err = hci_req_sync_run(&req); if (err < 0) return ERR_PTR(err); err = wait_event_interruptible_timeout(hdev->req_wait_q, - hdev->req_status != HCI_REQ_PEND, + READ_ONCE(hdev->req_status) != HCI_REQ_PEND, timeout); if (err == -ERESTARTSYS) return ERR_PTR(-EINTR); - switch (hdev->req_status) { + switch (READ_ONCE(hdev->req_status)) { case HCI_REQ_DONE: err = -bt_to_errno(hdev->req_result); break; @@ -194,7 +194,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, break; } - hdev->req_status = 0; + WRITE_ONCE(hdev->req_status, 0); hdev->req_result = 0; skb = hdev->req_rsp; hdev->req_rsp = NULL; @@ -665,9 +665,9 @@ void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); - if (hdev->req_status == HCI_REQ_PEND) { + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { hdev->req_result = err; - hdev->req_status = HCI_REQ_CANCELED; + WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED); queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } @@ -683,12 +683,12 @@ void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); - if (hdev->req_status == HCI_REQ_PEND) { + if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { /* req_result is __u32 so error must be positive to be properly * propagated. */ hdev->req_result = err < 0 ? -err : err; - hdev->req_status = HCI_REQ_CANCELED; + WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED); wake_up_interruptible(&hdev->req_wait_q); } @@ -780,7 +780,7 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy) { if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) - return 0; + return -EEXIST; return hci_cmd_sync_queue(hdev, func, data, destroy); } @@ -801,8 +801,15 @@ int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, return -ENETDOWN; /* If on cmd_sync_work then run immediately otherwise queue */ - if (current_work() == &hdev->cmd_sync_work) - return func(hdev, data); + if (current_work() == &hdev->cmd_sync_work) { + int err; + + err = func(hdev, data); + if (destroy) + destroy(hdev, data, err); + + return 0; + } return hci_cmd_sync_submit(hdev, func, data, destroy); } @@ -3255,6 +3262,8 @@ static int update_passive_scan_sync(struct hci_dev *hdev, void *data) int hci_update_passive_scan(struct hci_dev *hdev) { + int err; + /* Only queue if it would have any effect */ if (!test_bit(HCI_UP, &hdev->flags) || test_bit(HCI_INIT, &hdev->flags) || @@ -3264,8 +3273,9 @@ int hci_update_passive_scan(struct hci_dev *hdev) hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; - return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL, - NULL); + err = hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL, + NULL); + return (err == -EEXIST) ? 0 : err; } int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val) @@ -6958,8 +6968,11 @@ static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) { - return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn, - NULL); + int err; + + err = hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn, + NULL); + return (err == -EEXIST) ? 0 : err; } static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) @@ -6995,8 +7008,11 @@ done: int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) { - return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn, - create_le_conn_complete); + int err; + + err = hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); + return (err == -EEXIST) ? 0 : err; } int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -7203,8 +7219,11 @@ done: int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn) { - return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn, - create_pa_complete); + int err; + + err = hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn, + create_pa_complete); + return (err == -EEXIST) ? 0 : err; } static void create_big_complete(struct hci_dev *hdev, void *data, int err) @@ -7222,7 +7241,8 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err) static int hci_le_big_create_sync(struct hci_dev *hdev, void *data) { - DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11); + DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, + HCI_MAX_ISO_BIS); struct hci_conn *conn = data; struct bt_iso_qos *qos = &conn->iso_qos; int err; @@ -7266,8 +7286,11 @@ static int hci_le_big_create_sync(struct hci_dev *hdev, void *data) int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn) { - return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn, - create_big_complete); + int err; + + err = hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn, + create_big_complete); + return (err == -EEXIST) ? 0 : err; } struct past_data { @@ -7359,7 +7382,7 @@ int hci_past_sync(struct hci_conn *conn, struct hci_conn *le) if (err) kfree(data); - return err; + return (err == -EEXIST) ? 0 : err; } static void le_read_features_complete(struct hci_dev *hdev, void *data, int err) @@ -7368,10 +7391,8 @@ static void le_read_features_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - if (err == -ECANCELED) - return; - hci_conn_drop(conn); + hci_conn_put(conn); } static int hci_le_read_all_remote_features_sync(struct hci_dev *hdev, @@ -7438,15 +7459,20 @@ int hci_le_read_remote_features(struct hci_conn *conn) * role is possible. Otherwise just transition into the * connected state without requesting the remote features. */ - if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) + if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) { err = hci_cmd_sync_queue_once(hdev, hci_le_read_remote_features_sync, - hci_conn_hold(conn), + hci_conn_hold(hci_conn_get(conn)), le_read_features_complete); - else + if (err) { + hci_conn_drop(conn); + hci_conn_put(conn); + } + } else { err = -EOPNOTSUPP; + } - return err; + return (err == -EEXIST) ? 0 : err; } static void pkt_type_changed(struct hci_dev *hdev, void *data, int err) @@ -7472,6 +7498,7 @@ int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type) { struct hci_dev *hdev = conn->hdev; struct hci_cp_change_conn_ptype *cp; + int err; cp = kmalloc_obj(*cp); if (!cp) @@ -7480,8 +7507,12 @@ int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type) cp->handle = cpu_to_le16(conn->handle); cp->pkt_type = cpu_to_le16(pkt_type); - return hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp, - pkt_type_changed); + err = hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp, + pkt_type_changed); + if (err) + kfree(cp); + + return (err == -EEXIST) ? 0 : err; } static void le_phy_update_complete(struct hci_dev *hdev, void *data, int err) @@ -7507,6 +7538,7 @@ int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_set_phy *cp; + int err; cp = kmalloc_obj(*cp); if (!cp) @@ -7517,6 +7549,10 @@ int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys) cp->tx_phys = tx_phys; cp->rx_phys = rx_phys; - return hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp, - le_phy_update_complete); + err = hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp, + le_phy_update_complete); + if (err) + kfree(cp); + + return (err == -EEXIST) ? 0 : err; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 5deb6c4f1e41..95c65fece39b 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -926,16 +926,39 @@ int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator) static int l2cap_get_ident(struct l2cap_conn *conn) { + u8 max; + int ident; + /* LE link does not support tools like l2ping so use the full range */ if (conn->hcon->type == LE_LINK) - return ida_alloc_range(&conn->tx_ida, 1, 255, GFP_ATOMIC); - + max = 255; /* Get next available identificator. * 1 - 128 are used by kernel. * 129 - 199 are reserved. * 200 - 254 are used by utilities like l2ping, etc. */ - return ida_alloc_range(&conn->tx_ida, 1, 128, GFP_ATOMIC); + else + max = 128; + + /* Allocate ident using min as last used + 1 (cyclic) */ + ident = ida_alloc_range(&conn->tx_ida, READ_ONCE(conn->tx_ident) + 1, + max, GFP_ATOMIC); + /* Force min 1 to start over */ + if (ident <= 0) { + ident = ida_alloc_range(&conn->tx_ida, 1, max, GFP_ATOMIC); + if (ident <= 0) { + /* If all idents are in use, log an error, this is + * extremely unlikely to happen and would indicate a bug + * in the code that idents are not being freed properly. + */ + BT_ERR("Unable to allocate ident: %d", ident); + return 0; + } + } + + WRITE_ONCE(conn->tx_ident, ident); + + return ident; } static void l2cap_send_acl(struct l2cap_conn *conn, struct sk_buff *skb, @@ -1748,6 +1771,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); + disable_delayed_work_sync(&conn->info_timer); + disable_delayed_work_sync(&conn->id_addr_timer); + mutex_lock(&conn->lock); kfree_skb(conn->rx_skb); @@ -1763,8 +1789,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) ida_destroy(&conn->tx_ida); - cancel_delayed_work_sync(&conn->id_addr_timer); - l2cap_unregister_all_users(conn); /* Force the connection to be immediately dropped */ @@ -1783,9 +1807,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_put(chan); } - if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) - cancel_delayed_work_sync(&conn->info_timer); - hci_chan_del(conn->hchan); conn->hchan = NULL; @@ -2377,6 +2398,9 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, /* Remote device may have requested smaller PDUs */ pdu_len = min_t(size_t, pdu_len, chan->remote_mps); + if (!pdu_len) + return -EINVAL; + if (len <= pdu_len) { sar = L2CAP_SAR_UNSEGMENTED; sdu_len = 0; @@ -4312,14 +4336,16 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - if (chan->mode == L2CAP_MODE_ERTM || - chan->mode == L2CAP_MODE_STREAMING) - err = l2cap_ertm_init(chan); + if (chan->state != BT_CONNECTED) { + if (chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) + err = l2cap_ertm_init(chan); - if (err < 0) - l2cap_send_disconn_req(chan, -err); - else - l2cap_chan_ready(chan); + if (err < 0) + l2cap_send_disconn_req(chan, -err); + else + l2cap_chan_ready(chan); + } goto unlock; } @@ -5081,14 +5107,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, cmd_len -= sizeof(*req); num_scid = cmd_len / sizeof(u16); - /* Always respond with the same number of scids as in the request */ - rsp_len = cmd_len; - if (num_scid > L2CAP_ECRED_MAX_CID) { result = L2CAP_CR_LE_INVALID_PARAMS; goto response; } + /* Always respond with the same number of scids as in the request */ + rsp_len = cmd_len; + mtu = __le16_to_cpu(req->mtu); mps = __le16_to_cpu(req->mps); @@ -6607,6 +6633,10 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) struct l2cap_le_credits pkt; u16 return_credits = l2cap_le_rx_credits(chan); + if (chan->mode != L2CAP_MODE_LE_FLOWCTL && + chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + if (chan->rx_credits >= return_credits) return; @@ -6690,6 +6720,11 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) if (!chan->sdu) { u16 sdu_len; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) { + err = -EINVAL; + goto failed; + } + sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 597686790371..71e8c1b45bce 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1698,6 +1698,9 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + lock_sock(sk); parent = bt_sk(sk)->parent; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d52238ce6a9a..b05bb380e5f8 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2478,6 +2478,7 @@ static int mesh_send(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) struct mgmt_mesh_tx *mesh_tx; struct mgmt_cp_mesh_send *send = data; struct mgmt_rp_mesh_read_features rp; + u16 expected_len; bool sending; int err = 0; @@ -2485,12 +2486,19 @@ static int mesh_send(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) !hci_dev_test_flag(hdev, HCI_MESH_EXPERIMENTAL)) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND, MGMT_STATUS_NOT_SUPPORTED); - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) || - len <= MGMT_MESH_SEND_SIZE || - len > (MGMT_MESH_SEND_SIZE + 31)) + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND, MGMT_STATUS_REJECTED); + if (!send->adv_data_len || send->adv_data_len > 31) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND, + MGMT_STATUS_REJECTED); + + expected_len = struct_size(send, adv_data, send->adv_data_len); + if (expected_len != len) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND, + MGMT_STATUS_INVALID_PARAMS); + hci_dev_lock(hdev); memset(&rp, 0, sizeof(rp)); @@ -5355,7 +5363,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, * hci_adv_monitors_clear is about to be called which will take care of * freeing the adv_monitor instances. */ - if (status == -ECANCELED && !mgmt_pending_valid(hdev, cmd)) + if (status == -ECANCELED || !mgmt_pending_valid(hdev, cmd)) return; monitor = cmd->user_data; @@ -7248,6 +7256,9 @@ static bool ltk_is_valid(struct mgmt_ltk_info *key) if (key->initiator != 0x00 && key->initiator != 0x01) return false; + if (key->enc_size > sizeof(key->val)) + return false; + switch (key->addr.type) { case BDADDR_LE_PUBLIC: return true; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e7db50165879..b84587811ef4 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -298,7 +298,7 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, int err = 0; sco_conn_lock(conn); - if (conn->sk) + if (conn->sk || sco_pi(sk)->conn) err = -EBUSY; else __sco_chan_add(conn, sk, parent); @@ -353,9 +353,20 @@ static int sco_connect(struct sock *sk) lock_sock(sk); + /* Recheck state after reacquiring the socket lock, as another + * thread may have changed it (e.g., closed the socket). + */ + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { + release_sock(sk); + hci_conn_drop(hcon); + err = -EBADFD; + goto unlock; + } + err = sco_chan_add(conn, sk, NULL); if (err) { release_sock(sk); + hci_conn_drop(hcon); goto unlock; } @@ -401,7 +412,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) struct sock *sk; sco_conn_lock(conn); - sk = conn->sk; + sk = sco_sock_hold(conn); sco_conn_unlock(conn); if (!sk) @@ -410,11 +421,15 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) - goto drop; + goto drop_put; - if (!sock_queue_rcv_skb(sk, skb)) + if (!sock_queue_rcv_skb(sk, skb)) { + sock_put(sk); return; + } +drop_put: + sock_put(sk); drop: kfree_skb(skb); } @@ -652,13 +667,18 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, addr->sa_family != AF_BLUETOOTH) return -EINVAL; - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + lock_sock(sk); + + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { + release_sock(sk); return -EBADFD; + } - if (sk->sk_type != SOCK_SEQPACKET) - err = -EINVAL; + if (sk->sk_type != SOCK_SEQPACKET) { + release_sock(sk); + return -EINVAL; + } - lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); release_sock(sk); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 485e3468bd26..98f1da4f5f55 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1018,10 +1018,7 @@ static u8 smp_random(struct smp_chan *smp) smp_s1(smp->tk, smp->prnd, smp->rrnd, stk); - if (hcon->pending_sec_level == BT_SECURITY_HIGH) - auth = 1; - else - auth = 0; + auth = test_bit(SMP_FLAG_MITM_AUTH, &smp->flags) ? 1 : 0; /* Even though there's no _RESPONDER suffix this is the * responder STK we're adding for later lookup (the initiator @@ -1826,7 +1823,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (sec_level > conn->hcon->pending_sec_level) conn->hcon->pending_sec_level = sec_level; - /* If we need MITM check that it can be achieved */ + /* If we need MITM check that it can be achieved. */ if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) { u8 method; @@ -1834,6 +1831,10 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) req->io_capability); if (method == JUST_WORKS || method == JUST_CFM) return SMP_AUTH_REQUIREMENTS; + + /* Force MITM bit if it isn't set by the initiator. */ + auth |= SMP_AUTH_MITM; + rsp.auth_req |= SMP_AUTH_MITM; } key_size = min(req->max_key_size, rsp.max_key_size); diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index 1e2b51769eec..6b5595868a39 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -251,12 +251,12 @@ struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *msg) static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, struct sk_buff *request, struct neighbour *n, - __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns) + __be16 vlan_proto, u16 vlan_tci) { struct net_device *dev = request->dev; struct net_bridge_vlan_group *vg; + struct nd_msg *na, *ns; struct sk_buff *reply; - struct nd_msg *na; struct ipv6hdr *pip6; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; @@ -264,7 +264,7 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, u8 *daddr; u16 pvid; - if (!dev) + if (!dev || skb_linearize(request)) return; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + @@ -281,17 +281,21 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, skb_set_mac_header(reply, 0); daddr = eth_hdr(request)->h_source; + ns = (struct nd_msg *)(skb_network_header(request) + + sizeof(struct ipv6hdr)); /* Do we need option processing ? */ ns_olen = request->len - (skb_network_offset(request) + sizeof(struct ipv6hdr)) - sizeof(*ns); for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { - if (!ns->opt[i + 1]) { + if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) { kfree_skb(reply); return; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { - daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + if ((ns->opt[i + 1] << 3) >= + sizeof(struct nd_opt_hdr) + ETH_ALEN) + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } @@ -472,9 +476,9 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, if (vid != 0) br_nd_send(br, p, skb, n, skb->vlan_proto, - skb_vlan_tag_get(skb), msg); + skb_vlan_tag_get(skb)); else - br_nd_send(br, p, skb, n, 0, 0, msg); + br_nd_send(br, p, skb, n, 0, 0); replied = true; } diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c index ce6f63c77cc0..86f0e75d6e34 100644 --- a/net/bridge/br_mrp_netlink.c +++ b/net/bridge/br_mrp_netlink.c @@ -196,7 +196,7 @@ static const struct nla_policy br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = { [IFLA_BRIDGE_MRP_START_TEST_UNSPEC] = { .type = NLA_REJECT }, [IFLA_BRIDGE_MRP_START_TEST_RING_ID] = { .type = NLA_U32 }, - [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = NLA_POLICY_MIN(NLA_U32, 1), [IFLA_BRIDGE_MRP_START_TEST_MAX_MISS] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_PERIOD] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_MONITOR] = { .type = NLA_U32 }, @@ -316,7 +316,7 @@ static const struct nla_policy br_mrp_start_in_test_policy[IFLA_BRIDGE_MRP_START_IN_TEST_MAX + 1] = { [IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC] = { .type = NLA_REJECT }, [IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID] = { .type = NLA_U32 }, - [IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL] = NLA_POLICY_MIN(NLA_U32, 1), [IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD] = { .type = NLA_U32 }, }; diff --git a/net/can/af_can.c b/net/can/af_can.c index f70e2ba0aadc..7bc86b176b4d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -469,7 +469,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, rcv->can_id = can_id; rcv->mask = mask; - rcv->matches = 0; + atomic_long_set(&rcv->matches, 0); rcv->func = func; rcv->data = data; rcv->ident = ident; @@ -573,7 +573,7 @@ EXPORT_SYMBOL(can_rx_unregister); static inline void deliver(struct sk_buff *skb, struct receiver *rcv) { rcv->func(skb, rcv->data); - rcv->matches++; + atomic_long_inc(&rcv->matches); } static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buff *skb) diff --git a/net/can/af_can.h b/net/can/af_can.h index 22f3352c77fe..87887014f562 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -52,7 +52,7 @@ struct receiver { struct hlist_node list; canid_t can_id; canid_t mask; - unsigned long matches; + atomic_long_t matches; void (*func)(struct sk_buff *skb, void *data); void *data; char *ident; diff --git a/net/can/gw.c b/net/can/gw.c index 8ee4d67a07d3..0ec99f68aa45 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -375,10 +375,10 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, return; if (from <= to) { - for (i = crc8->from_idx; i <= crc8->to_idx; i++) + for (i = from; i <= to; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { - for (i = crc8->from_idx; i >= crc8->to_idx; i--) + for (i = from; i >= to; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } @@ -397,7 +397,7 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf, break; } - cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; + cf->data[res] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, diff --git a/net/can/isotp.c b/net/can/isotp.c index da3b72e7afcc..2770f43f4951 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1248,12 +1248,6 @@ static int isotp_release(struct socket *sock) so->ifindex = 0; so->bound = 0; - if (so->rx.buf != so->rx.sbuf) - kfree(so->rx.buf); - - if (so->tx.buf != so->tx.sbuf) - kfree(so->tx.buf); - sock_orphan(sk); sock->sk = NULL; @@ -1622,6 +1616,21 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; } +static void isotp_sock_destruct(struct sock *sk) +{ + struct isotp_sock *so = isotp_sk(sk); + + /* do the standard CAN sock destruct work */ + can_sock_destruct(sk); + + /* free potential extended PDU buffers */ + if (so->rx.buf != so->rx.sbuf) + kfree(so->rx.buf); + + if (so->tx.buf != so->tx.sbuf) + kfree(so->tx.buf); +} + static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); @@ -1666,6 +1675,9 @@ static int isotp_init(struct sock *sk) list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); + /* re-assign default can_sock_destruct() reference */ + sk->sk_destruct = isotp_sock_destruct; + return 0; } diff --git a/net/can/proc.c b/net/can/proc.c index 0938bf7dd646..de4d05ae3459 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -196,7 +196,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, - r->func, r->data, r->matches, r->ident); + r->func, r->data, atomic_long_read(&r->matches), + r->ident); } } diff --git a/net/core/dev.c b/net/core/dev.c index 14a83f2035b9..831129f2a69b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3769,6 +3769,22 @@ static netdev_features_t dflt_features_check(struct sk_buff *skb, return vlan_features_check(skb, features); } +static bool skb_gso_has_extension_hdr(const struct sk_buff *skb) +{ + if (!skb->encapsulation) + return ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr)); + else + return (!skb_inner_network_header_was_set(skb) || + ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + inner_ip_hdr(skb)->version == 6)) && + skb_inner_network_header_len(skb) != sizeof(struct ipv6hdr))); +} + static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) @@ -3805,10 +3821,15 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, * segmentation-offloads.rst). */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - struct iphdr *iph = skb->encapsulation ? - inner_ip_hdr(skb) : ip_hdr(skb); + const struct iphdr *iph; + struct iphdr _iph; + int nhoff = skb->encapsulation ? + skb_inner_network_offset(skb) : + skb_network_offset(skb); + + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (!(iph->frag_off & htons(IP_DF))) + if (!iph || !(iph->frag_off & htons(IP_DF))) features &= ~dev->mangleid_features; } @@ -3816,11 +3837,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, * so neither does TSO that depends on it. */ if (features & NETIF_F_IPV6_CSUM && - (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || - (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && - skb_transport_header_was_set(skb) && - skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + skb_gso_has_extension_hdr(skb)) features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); return features; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dad4b1054955..fae8034efbff 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -629,6 +629,9 @@ int rtnl_link_register(struct rtnl_link_ops *ops) unlock: mutex_unlock(&link_ops_mutex); + if (err) + cleanup_srcu_struct(&ops->srcu); + return err; } EXPORT_SYMBOL_GPL(rtnl_link_register); @@ -707,11 +710,14 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) goto out; ops = master_dev->rtnl_link_ops; - if (!ops || !ops->get_slave_size) + if (!ops) + goto out; + size += nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_SLAVE_KIND */ + if (!ops->get_slave_size) goto out; /* IFLA_INFO_SLAVE_DATA + nested data */ - size = nla_total_size(sizeof(struct nlattr)) + - ops->get_slave_size(master_dev, dev); + size += nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); out: rcu_read_unlock(); @@ -1267,6 +1273,21 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) return size; } +static size_t rtnl_dev_parent_size(const struct net_device *dev) +{ + size_t size = 0; + + /* IFLA_PARENT_DEV_NAME */ + if (dev->dev.parent) + size += nla_total_size(strlen(dev_name(dev->dev.parent)) + 1); + + /* IFLA_PARENT_DEV_BUS_NAME */ + if (dev->dev.parent && dev->dev.parent->bus) + size += nla_total_size(strlen(dev->dev.parent->bus->name) + 1); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1328,6 +1349,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(8) /* IFLA_MAX_PACING_OFFLOAD_HORIZON */ + nla_total_size(2) /* IFLA_HEADROOM */ + nla_total_size(2) /* IFLA_TAILROOM */ + + rtnl_dev_parent_size(dev) + 0; if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3261793abe83..6187a83bd741 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1267,17 +1267,20 @@ out: static void sk_psock_verdict_data_ready(struct sock *sk) { - struct socket *sock = sk->sk_socket; - const struct proto_ops *ops; + const struct proto_ops *ops = NULL; + struct socket *sock; int copied; trace_sk_data_ready(sk); - if (unlikely(!sock)) - return; - ops = READ_ONCE(sock->ops); + rcu_read_lock(); + sock = READ_ONCE(sk->sk_socket); + if (likely(sock)) + ops = READ_ONCE(sock->ops); + rcu_read_unlock(); if (!ops || !ops->read_skb) return; + copied = ops->read_skb(sk, sk_psock_verdict_recv); if (copied >= 0) { struct sk_psock *psock; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index d1bfc49b5f01..fd2fea25eff0 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -532,8 +532,8 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { - bool is_slave_a_added = false; - bool is_slave_b_added = false; + struct net_device *slave_a_dev = NULL; + struct net_device *slave_b_dev = NULL; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; @@ -549,33 +549,35 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { - /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); - if (is_slave_b_added) - vlan_vid_del(port->dev, proto, vid); - return ret; + goto unwind; } - - is_slave_a_added = true; + slave_a_dev = port->dev; break; - case HSR_PT_SLAVE_B: if (ret) { - /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); - if (is_slave_a_added) - vlan_vid_del(port->dev, proto, vid); - return ret; + goto unwind; } - - is_slave_b_added = true; + slave_b_dev = port->dev; break; default: + if (ret) + goto unwind; break; } } return 0; + +unwind: + if (slave_a_dev) + vlan_vid_del(slave_a_dev, proto, vid); + + if (slave_b_dev) + vlan_vid_del(slave_b_dev, proto, vid); + + return ret; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 50996f4de7f9..d41863593674 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -123,6 +123,40 @@ static void hsr_free_node_rcu(struct rcu_head *rn) hsr_free_node(node); } +static void hsr_lock_seq_out_pair(struct hsr_node *node_a, + struct hsr_node *node_b) +{ + if (node_a == node_b) { + spin_lock_bh(&node_a->seq_out_lock); + return; + } + + if (node_a < node_b) { + spin_lock_bh(&node_a->seq_out_lock); + spin_lock_nested(&node_b->seq_out_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock_bh(&node_b->seq_out_lock); + spin_lock_nested(&node_a->seq_out_lock, SINGLE_DEPTH_NESTING); + } +} + +static void hsr_unlock_seq_out_pair(struct hsr_node *node_a, + struct hsr_node *node_b) +{ + if (node_a == node_b) { + spin_unlock_bh(&node_a->seq_out_lock); + return; + } + + if (node_a < node_b) { + spin_unlock(&node_b->seq_out_lock); + spin_unlock_bh(&node_a->seq_out_lock); + } else { + spin_unlock(&node_a->seq_out_lock); + spin_unlock_bh(&node_b->seq_out_lock); + } +} + void hsr_del_nodes(struct list_head *node_db) { struct hsr_node *node; @@ -432,7 +466,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) } ether_addr_copy(node_real->macaddress_B, ethhdr->h_source); - spin_lock_bh(&node_real->seq_out_lock); + hsr_lock_seq_out_pair(node_real, node_curr); for (i = 0; i < HSR_PT_PORTS; i++) { if (!node_curr->time_in_stale[i] && time_after(node_curr->time_in[i], node_real->time_in[i])) { @@ -455,7 +489,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) src_blk->seq_nrs[i], HSR_SEQ_BLOCK_SIZE); } } - spin_unlock_bh(&node_real->seq_out_lock); + hsr_unlock_seq_out_pair(node_real, node_curr); node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2c922afadb8f..6dfc0bcdef65 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -235,10 +235,13 @@ static void esp_output_done(void *data, int err) xfrm_dev_resume(skb); } else { if (!err && - x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) - esp_output_tail_tcp(x, skb); - else + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) { + err = esp_output_tail_tcp(x, skb); + if (err != -EINPROGRESS) + kfree_skb(skb); + } else { xfrm_output_resume(skb_to_full_sk(skb), skb, err); + } } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5dfac6ce1110..e961936b6be7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -154,20 +154,6 @@ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) } EXPORT_SYMBOL(inet_sk_get_local_port_range); -static bool inet_use_bhash2_on_bind(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) - return false; - - if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) - return true; - } -#endif - return sk->sk_rcv_saddr != htonl(INADDR_ANY); -} - static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, kuid_t uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) @@ -259,7 +245,7 @@ static int inet_csk_bind_conflict(const struct sock *sk, * checks separately because their spinlocks have to be acquired/released * independently of each other, to prevent possible deadlocks */ - if (inet_use_bhash2_on_bind(sk)) + if (inet_use_hash2_on_bind(sk)) return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok); @@ -376,7 +362,7 @@ other_parity_scan: head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); - if (inet_use_bhash2_on_bind(sk)) { + if (inet_use_hash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false)) goto next_port; } @@ -562,7 +548,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) check_bind_conflict = false; } - if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) { + if (check_bind_conflict && inet_use_hash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true)) goto fail_unlock; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b60fad393e18..cb99a3c27053 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -287,7 +287,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, } else { hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); - if (hslot->count > 10) { + if (inet_use_hash2_on_bind(sk) && hslot->count > 10) { int exist; unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 04c1e856bf7f..22c5cdffeae7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2863,7 +2863,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) fib6_add_gc_list(rt); } else { fib6_clean_expires(rt); - fib6_remove_gc_list(rt); + fib6_may_remove_gc_list(net, rt); } spin_unlock_bh(&table->tb6_lock); @@ -3626,12 +3626,12 @@ static void addrconf_permanent_addr(struct net *net, struct net_device *dev) if ((ifp->flags & IFA_F_PERMANENT) && fixup_permanent_addr(net, idev, ifp) < 0) { write_unlock_bh(&idev->lock); - in6_ifa_hold(ifp); - ipv6_del_addr(ifp); - write_lock_bh(&idev->lock); net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", idev->dev->name, &ifp->addr); + in6_ifa_hold(ifp); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); } } @@ -4841,7 +4841,7 @@ static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp, if (!(flags & RTF_EXPIRES)) { fib6_clean_expires(f6i); - fib6_remove_gc_list(f6i); + fib6_may_remove_gc_list(net, f6i); } else { fib6_set_expires(f6i, expires); fib6_add_gc_list(f6i); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c564b68a0562..993e2d76fc1f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -763,6 +763,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; + struct ipv6_rt_hdr *orthdr; struct ipv6_rt_hdr *rthdr; struct ipv6_opt_hdr *hdr; struct ipv6_txoptions *opt = ipc6->opt; @@ -924,9 +925,13 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, goto exit_f; } if (cmsg->cmsg_type == IPV6_DSTOPTS) { + if (opt->dst1opt) + opt->opt_flen -= ipv6_optlen(opt->dst1opt); opt->opt_flen += len; opt->dst1opt = hdr; } else { + if (opt->dst0opt) + opt->opt_nflen -= ipv6_optlen(opt->dst0opt); opt->opt_nflen += len; opt->dst0opt = hdr; } @@ -969,12 +974,17 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, goto exit_f; } + orthdr = opt->srcrt; + if (orthdr) + opt->opt_nflen -= ((orthdr->hdrlen + 1) << 3); opt->opt_nflen += len; opt->srcrt = rthdr; if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) { int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3); + if (opt->dst0opt) + opt->opt_nflen -= ipv6_optlen(opt->dst0opt); opt->opt_nflen += dsthdrlen; opt->dst0opt = opt->dst1opt; opt->dst1opt = NULL; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index e75da98f5283..9f75313734f8 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -271,10 +271,13 @@ static void esp_output_done(void *data, int err) xfrm_dev_resume(skb); } else { if (!err && - x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) - esp_output_tail_tcp(x, skb); - else + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) { + err = esp_output_tail_tcp(x, skb); + if (err != -EINPROGRESS) + kfree_skb(skb); + } else { xfrm_output_resume(skb_to_full_sk(skb), skb, err); + } } } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 813d2e9edb8b..d5d23a9296ea 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -875,6 +875,9 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, if (!skb2) return 1; + /* Remove debris left by IPv4 stack. */ + memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); + skb_dst_drop(skb2); skb_pull(skb2, nhs); skb_reset_network_header(skb2); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index b76f89d92e7b..3978773bec42 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -708,7 +708,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, struct ioam6_namespace *ns, struct ioam6_trace_hdr *trace, struct ioam6_schema *sc, - u8 sclen, bool is_input) + unsigned int sclen, bool is_input) { struct net_device *dev = skb_dst_dev(skb); struct timespec64 ts; @@ -939,7 +939,7 @@ void ioam6_fill_trace_data(struct sk_buff *skb, bool is_input) { struct ioam6_schema *sc; - u8 sclen = 0; + unsigned int sclen = 0; /* Skip if Overflow flag is set */ diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 9058e71241dc..45ef4d65dcbc 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -727,20 +727,28 @@ unlock: void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { + struct dst_metrics *m; + if (!f6i) return; - if (f6i->fib6_metrics == &dst_default_metrics) { + if (READ_ONCE(f6i->fib6_metrics) == &dst_default_metrics) { + struct dst_metrics *dflt = (struct dst_metrics *)&dst_default_metrics; struct dst_metrics *p = kzalloc_obj(*p, GFP_ATOMIC); if (!p) return; + p->metrics[metric - 1] = val; refcount_set(&p->refcnt, 1); - f6i->fib6_metrics = p; + if (cmpxchg(&f6i->fib6_metrics, dflt, p) != dflt) + kfree(p); + else + return; } - f6i->fib6_metrics->metrics[metric - 1] = val; + m = READ_ONCE(f6i->fib6_metrics); + WRITE_ONCE(m->metrics[metric - 1], val); } /* @@ -1133,7 +1141,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); - fib6_remove_gc_list(iter); + fib6_may_remove_gc_list(info->nl_net, iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); @@ -2348,6 +2356,17 @@ static void fib6_flush_trees(struct net *net) /* * Garbage collection */ +void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now) +{ + bool may_expire = rt->fib6_flags & RTF_EXPIRES && rt->expires; + int old_more = gc_args->more; + + rt6_age_exceptions(rt, gc_args, now); + + if (!may_expire && old_more == gc_args->more) + fib6_remove_gc_list(rt); +} static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { @@ -2370,7 +2389,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) * Note, that clones are aged out * only if they are not in use now. */ - rt6_age_exceptions(rt, gc_args, now); + fib6_age_exceptions(rt, gc_args, now); return 0; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 7c12bf75beed..c92f98c6f6ec 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -133,11 +133,6 @@ static void fl_release(struct ip6_flowlabel *fl) if (time_after(ttd, fl->expires)) fl->expires = ttd; ttd = fl->expires; - if (fl->opt && fl->share == IPV6_FL_S_EXCL) { - struct ipv6_txoptions *opt = fl->opt; - fl->opt = NULL; - kfree(opt); - } if (!timer_pending(&ip6_fl_gc_timer) || time_after(ip6_fl_gc_timer.expires, ttd)) mod_timer(&ip6_fl_gc_timer, ttd); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4c29aa94e86e..0b53488a9229 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -601,11 +601,16 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; + /* Remove debris left by IPv6 stack. */ + memset(IPCB(skb2), 0, sizeof(*IPCB(skb2))); + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); + if (eiph->version != 4 || eiph->ihl < 5) + goto out; /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f6a5d8c73af9..186e60c79214 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1209,6 +1209,9 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; + ndmsg->nduseropt_pad1 = 0; + ndmsg->nduseropt_pad2 = 0; + ndmsg->nduseropt_pad3 = 0; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 4ad8b2032f1f..5561bd9cea81 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -157,6 +157,10 @@ static int rt_mt6_check(const struct xt_mtchk_param *par) pr_debug("unknown flags %X\n", rtinfo->invflags); return -EINVAL; } + if (rtinfo->addrnr > IP6T_RT_HOPS) { + pr_debug("too many addresses specified\n"); + return -EINVAL; + } if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) && (!(rtinfo->flags & IP6T_RT_TYP) || (rtinfo->rt_type != 0) || diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 08cd86f49bf9..cb521700cee7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1033,7 +1033,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); - fib6_remove_gc_list(rt); + fib6_may_remove_gc_list(net, rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); diff --git a/net/key/af_key.c b/net/key/af_key.c index 0756bac62f7c..72ac2ace419d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3518,7 +3518,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress * static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, - uint32_t reqid, uint8_t family, + uint32_t reqid, sa_family_t family, const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; @@ -3583,12 +3583,17 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* ipsecrequests */ for (i = 0, mp = m; i < num_bundles; i++, mp++) { - /* old locator pair */ - size_pol += sizeof(struct sadb_x_ipsecrequest) + - pfkey_sockaddr_pair_size(mp->old_family); - /* new locator pair */ - size_pol += sizeof(struct sadb_x_ipsecrequest) + - pfkey_sockaddr_pair_size(mp->new_family); + int pair_size; + + pair_size = pfkey_sockaddr_pair_size(mp->old_family); + if (!pair_size) + return -EINVAL; + size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size; + + pair_size = pfkey_sockaddr_pair_size(mp->new_family); + if (!pair_size) + return -EINVAL; + size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size; } size += sizeof(struct sadb_msg) + size_pol; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index d5417688f69e..18d3da8ab384 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -83,14 +83,30 @@ static struct mpls_route *mpls_route_input(struct net *net, unsigned int index) return mpls_dereference(net, platform_label[index]); } +static struct mpls_route __rcu **mpls_platform_label_rcu(struct net *net, size_t *platform_labels) +{ + struct mpls_route __rcu **platform_label; + unsigned int sequence; + + do { + sequence = read_seqcount_begin(&net->mpls.platform_label_seq); + platform_label = rcu_dereference(net->mpls.platform_label); + *platform_labels = net->mpls.platform_labels; + } while (read_seqcount_retry(&net->mpls.platform_label_seq, sequence)); + + return platform_label; +} + static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned int index) { struct mpls_route __rcu **platform_label; + size_t platform_labels; + + platform_label = mpls_platform_label_rcu(net, &platform_labels); - if (index >= net->mpls.platform_labels) + if (index >= platform_labels) return NULL; - platform_label = rcu_dereference(net->mpls.platform_label); return rcu_dereference(platform_label[index]); } @@ -2240,8 +2256,7 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; - platform_label = rcu_dereference(net->mpls.platform_label); - platform_labels = net->mpls.platform_labels; + platform_label = mpls_platform_label_rcu(net, &platform_labels); if (filter.filter_set) flags |= NLM_F_DUMP_FILTERED; @@ -2645,8 +2660,12 @@ static int resize_platform_label_table(struct net *net, size_t limit) } /* Update the global pointers */ + local_bh_disable(); + write_seqcount_begin(&net->mpls.platform_label_seq); net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); + write_seqcount_end(&net->mpls.platform_label_seq); + local_bh_enable(); mutex_unlock(&net->mpls.platform_mutex); @@ -2728,6 +2747,8 @@ static __net_init int mpls_net_init(struct net *net) int i; mutex_init(&net->mpls.platform_mutex); + seqcount_mutex_init(&net->mpls.platform_label_seq, &net->mpls.platform_mutex); + net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cf1852b99963..65c3bb8016f4 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2006,7 +2006,7 @@ static void mptcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, size_t len, int flags, int copied_total, struct scm_timestamping_internal *tss, - int *cmsg_flags) + int *cmsg_flags, struct sk_buff **last) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; @@ -2023,6 +2023,7 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, /* skip already peeked skbs */ if (total_data_len + data_len <= copied_total) { total_data_len += data_len; + *last = skb; continue; } @@ -2058,6 +2059,8 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, } mptcp_eat_recv_skb(sk, skb); + } else { + *last = skb; } if (copied >= len) @@ -2288,10 +2291,12 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, cmsg_flags = MPTCP_CMSG_INQ; while (copied < len) { + struct sk_buff *last = NULL; int err, bytes_read; bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, - copied, &tss, &cmsg_flags); + copied, &tss, &cmsg_flags, + &last); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2343,7 +2348,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, pr_debug("block timeout %ld\n", timeo); mptcp_cleanup_rbuf(msk, copied); - err = sk_wait_data(sk, &timeo, NULL); + err = sk_wait_data(sk, &timeo, last); if (err < 0) { err = copied ? : err; goto out_err; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index a2fe711cb5e3..d0c9fe59c67d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -821,7 +821,7 @@ EXPORT_SYMBOL_GPL(ip_set_del); * */ ip_set_id_t -ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) +ip_set_get_byname(struct net *net, const struct nlattr *name, struct ip_set **set) { ip_set_id_t i, index = IPSET_INVALID_ID; struct ip_set *s; @@ -830,7 +830,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) rcu_read_lock(); for (i = 0; i < inst->ip_set_max; i++) { s = rcu_dereference(inst->ip_set_list)[i]; - if (s && STRNCMP(s->name, name)) { + if (s && nla_strcmp(name, s->name) == 0) { __ip_set_get(s); index = i; *set = s; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 181daa9c2019..b79e5dd2af03 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1098,7 +1098,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (!test_bit(i, n->used)) k++; } - if (n->pos == 0 && k == 0) { + if (k == n->pos) { t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 98b91b34c314..1cef84f15e8c 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -367,7 +367,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s); + e.id = ip_set_get_byname(map->net, tb[IPSET_ATTR_NAME], &s); if (e.id == IPSET_INVALID_ID) return -IPSET_ERR_NAME; /* "Loop detection" */ @@ -389,7 +389,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_NAMEREF]) { e.refid = ip_set_get_byname(map->net, - nla_data(tb[IPSET_ATTR_NAMEREF]), + tb[IPSET_ATTR_NAMEREF], &s); if (e.refid == IPSET_INVALID_ID) { ret = -IPSET_ERR_NAMEREF; diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index a7552a46d6ac..4f39bf7c843f 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -21,6 +21,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, unsigned int timeout) { const struct nf_conntrack_helper *helper; + struct net *net = read_pnet(&ct->ct_net); struct nf_conntrack_expect *exp; struct iphdr *iph = ip_hdr(skb); struct rtable *rt = skb_rtable(skb); @@ -70,8 +71,11 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->expectfn = NULL; exp->flags = NF_CT_EXPECT_PERMANENT; exp->class = NF_CT_EXPECT_CLASS_DEFAULT; - exp->helper = NULL; - + rcu_assign_pointer(exp->helper, helper); + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 81baf2082604..9df159448b89 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -247,6 +247,8 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; + lockdep_nfct_expect_lock_held(); + rcu_read_lock(); notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (!notify) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index cfc2daa3fc7f..24d0576d84b7 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -51,6 +51,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, struct net *net = nf_ct_exp_net(exp); struct nf_conntrack_net *cnet; + lockdep_nfct_expect_lock_held(); WARN_ON(!master_help); WARN_ON(timer_pending(&exp->timeout)); @@ -112,12 +113,14 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple, const struct net *net) { return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && - net_eq(net, nf_ct_net(i->master)) && - nf_ct_zone_equal_any(i->master, zone); + net_eq(net, read_pnet(&i->net)) && + nf_ct_exp_zone_equal_any(i, zone); } bool nf_ct_remove_expect(struct nf_conntrack_expect *exp) { + lockdep_nfct_expect_lock_held(); + if (timer_delete(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -177,6 +180,8 @@ nf_ct_find_expectation(struct net *net, struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; + lockdep_nfct_expect_lock_held(); + if (!cnet->expect_count) return NULL; @@ -309,12 +314,20 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); +/* This function can only be used from packet path, where accessing + * master's helper is safe, because the packet holds a reference on + * the conntrack object. Never use it from control plane. + */ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, u_int8_t family, const union nf_inet_addr *saddr, const union nf_inet_addr *daddr, u_int8_t proto, const __be16 *src, const __be16 *dst) { + struct nf_conntrack_helper *helper = NULL; + struct nf_conn *ct = exp->master; + struct net *net = read_pnet(&ct->ct_net); + struct nf_conn_help *help; int len; if (family == AF_INET) @@ -325,7 +338,16 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, exp->flags = 0; exp->class = class; exp->expectfn = NULL; - exp->helper = NULL; + + help = nfct_help(ct); + if (help) + helper = rcu_dereference(help->helper); + + rcu_assign_pointer(exp->helper, helper); + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif exp->tuple.src.l3num = family; exp->tuple.dst.protonum = proto; @@ -442,6 +464,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, unsigned int h; int ret = 0; + lockdep_nfct_expect_lock_held(); + if (!master_help) { ret = -ESHUTDOWN; goto out; @@ -498,8 +522,9 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, nf_ct_expect_insert(expect); - spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); + spin_unlock_bh(&nf_conntrack_expect_lock); + return 0; out: spin_unlock_bh(&nf_conntrack_expect_lock); @@ -627,11 +652,15 @@ static int exp_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_expect *expect; struct nf_conntrack_helper *helper; + struct net *net = seq_file_net(s); struct hlist_node *n = v; char *delim = ""; expect = hlist_entry(n, struct nf_conntrack_expect, hnode); + if (!net_eq(nf_ct_exp_net(expect), net)) + return 0; + if (expect->timeout.function) seq_printf(s, "%ld ", timer_pending(&expect->timeout) ? (long)(expect->timeout.expires - jiffies)/HZ : 0); @@ -654,7 +683,7 @@ static int exp_seq_show(struct seq_file *s, void *v) if (expect->flags & NF_CT_EXPECT_USERSPACE) seq_printf(s, "%sUSERSPACE", delim); - helper = rcu_dereference(nfct_help(expect->master)->helper); + helper = rcu_dereference(expect->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); if (helper->expect_policy[expect->class].name[0]) diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index a2a0e22ccee1..3f5c50455b71 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - exp->helper = &nf_conntrack_helper_h245; + rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nathook = rcu_dereference(nfct_h323_nat_hook); @@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_UDP, NULL, &port); - exp->helper = nf_conntrack_helper_ras; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); @@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - exp->helper = nf_conntrack_helper_q931; + rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ceb48c3ca0a4..a715304a53d8 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -395,14 +395,10 @@ EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) { - struct nf_conn_help *help = nfct_help(exp->master); const struct nf_conntrack_helper *me = data; const struct nf_conntrack_helper *this; - if (exp->helper == me) - return true; - - this = rcu_dereference_protected(help->helper, + this = rcu_dereference_protected(exp->helper, lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } @@ -419,8 +415,13 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) */ synchronize_rcu(); - nf_ct_expect_iterate_destroy(expect_iter_me, NULL); + nf_ct_expect_iterate_destroy(expect_iter_me, me); nf_ct_iterate_destroy(unhelp, me); + + /* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as + * last step, this ensures rcu readers of exp->helper are done. + * No need for another synchronize_rcu() here. + */ } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c156574e1273..a20cd82446c5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -910,8 +910,8 @@ struct ctnetlink_filter { }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { - [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, - [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, + [CTA_FILTER_ORIG_FLAGS] = NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL), + [CTA_FILTER_REPLY_FLAGS] = NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL), }; static int ctnetlink_parse_filter(const struct nlattr *attr, @@ -925,17 +925,11 @@ static int ctnetlink_parse_filter(const struct nlattr *attr, if (ret) return ret; - if (tb[CTA_FILTER_ORIG_FLAGS]) { + if (tb[CTA_FILTER_ORIG_FLAGS]) filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); - if (filter->orig_flags & ~CTA_FILTER_F_ALL) - return -EOPNOTSUPP; - } - if (tb[CTA_FILTER_REPLY_FLAGS]) { + if (tb[CTA_FILTER_REPLY_FLAGS]) filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); - if (filter->reply_flags & ~CTA_FILTER_F_ALL) - return -EOPNOTSUPP; - } return 0; } @@ -2634,7 +2628,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, - [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, + [CTA_EXPECT_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NF_CT_EXPECT_MASK), [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, @@ -2642,7 +2636,6 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, - struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); @@ -2871,7 +2864,6 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; - struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; @@ -2885,17 +2877,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (err < 0) return err; - if (cda[CTA_EXPECT_HELP_NAME]) { - const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); - - helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), - nf_ct_protonum(ct)); - if (helper == NULL) - return -EOPNOTSUPP; - } - exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, - helper, &tuple, &mask); + &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); @@ -3012,7 +2995,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; - struct nf_conn_help *help; + struct nf_conntrack_helper *helper; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; @@ -3057,15 +3040,12 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; - help = nfct_help(master); - if (help) { - struct nf_conntrack_helper *helper; - helper = rcu_dereference(help->helper); - if (helper && - nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) - goto nla_put_failure; - } + helper = rcu_dereference(exp->helper); + if (helper && + nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) + goto nla_put_failure; + expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) @@ -3358,31 +3338,37 @@ static int ctnetlink_get_expect(struct sk_buff *skb, if (err < 0) return err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb2) + return -ENOMEM; + + spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_expect_find_get(info->net, &zone, &tuple); - if (!exp) + if (!exp) { + spin_unlock_bh(&nf_conntrack_expect_lock); + kfree_skb(skb2); return -ENOENT; + } if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); + kfree_skb(skb2); return -ENOENT; } } - skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb2) { - nf_ct_expect_put(exp); - return -ENOMEM; - } - rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); + if (err <= 0) { kfree_skb(skb2); return -ENOMEM; @@ -3394,12 +3380,9 @@ static int ctnetlink_get_expect(struct sk_buff *skb, static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { struct nf_conntrack_helper *helper; - const struct nf_conn_help *m_help; const char *name = data; - m_help = nfct_help(exp->master); - - helper = rcu_dereference(m_help->helper); + helper = rcu_dereference(exp->helper); if (!helper) return false; @@ -3432,22 +3415,26 @@ static int ctnetlink_del_expect(struct sk_buff *skb, if (err < 0) return err; + spin_lock_bh(&nf_conntrack_expect_lock); + /* bump usage count to 2 */ exp = nf_ct_expect_find_get(info->net, &zone, &tuple); - if (!exp) + if (!exp) { + spin_unlock_bh(&nf_conntrack_expect_lock); return -ENOENT; + } if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); + spin_unlock_bh(&nf_conntrack_expect_lock); return -ENOENT; } } /* after list removal, usage count == 1 */ - spin_lock_bh(&nf_conntrack_expect_lock); if (timer_delete(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); @@ -3530,20 +3517,25 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, - struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { - u_int32_t class = 0; + struct net *net = read_pnet(&ct->ct_net); + struct nf_conntrack_helper *helper; struct nf_conntrack_expect *exp; struct nf_conn_help *help; + u32 class = 0; int err; help = nfct_help(ct); if (!help) return ERR_PTR(-EOPNOTSUPP); - if (cda[CTA_EXPECT_CLASS] && helper) { + helper = rcu_dereference(help->helper); + if (!helper) + return ERR_PTR(-EOPNOTSUPP); + + if (cda[CTA_EXPECT_CLASS]) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); if (class > helper->expect_class_max) return ERR_PTR(-EINVAL); @@ -3573,7 +3565,11 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp->class = class; exp->master = ct; - exp->helper = helper; + write_pnet(&exp->net, net); +#ifdef CONFIG_NF_CONNTRACK_ZONES + exp->zone = ct->zone; +#endif + rcu_assign_pointer(exp->helper, helper); exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; @@ -3583,6 +3579,12 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; +#if IS_ENABLED(CONFIG_NF_NAT) + } else { + memset(&exp->saved_addr, 0, sizeof(exp->saved_addr)); + memset(&exp->saved_proto, 0, sizeof(exp->saved_proto)); + exp->dir = 0; +#endif } return exp; err_out: @@ -3598,7 +3600,6 @@ ctnetlink_create_expect(struct net *net, { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; - struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; int err; @@ -3624,33 +3625,7 @@ ctnetlink_create_expect(struct net *net, ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); - if (cda[CTA_EXPECT_HELP_NAME]) { - const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); - - helper = __nf_conntrack_helper_find(helpname, u3, - nf_ct_protonum(ct)); - if (helper == NULL) { - rcu_read_unlock(); -#ifdef CONFIG_MODULES - if (request_module("nfct-helper-%s", helpname) < 0) { - err = -EOPNOTSUPP; - goto err_ct; - } - rcu_read_lock(); - helper = __nf_conntrack_helper_find(helpname, u3, - nf_ct_protonum(ct)); - if (helper) { - err = -EAGAIN; - goto err_rcu; - } - rcu_read_unlock(); -#endif - err = -EOPNOTSUPP; - goto err_ct; - } - } - - exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); + exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; @@ -3660,8 +3635,8 @@ ctnetlink_create_expect(struct net *net, nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); -err_ct: nf_ct_put(ct); + return err; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 0c1d086e96cb..b67426c2189b 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1385,9 +1385,9 @@ nla_put_failure: } static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { - [CTA_PROTOINFO_TCP_STATE] = { .type = NLA_U8 }, - [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 }, - [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 }, + [CTA_PROTOINFO_TCP_STATE] = NLA_POLICY_MAX(NLA_U8, TCP_CONNTRACK_SYN_SENT2), + [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE), + [CTA_PROTOINFO_TCP_WSCALE_REPLY] = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE), [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) }, [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, }; @@ -1414,10 +1414,6 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) if (err < 0) return err; - if (tb[CTA_PROTOINFO_TCP_STATE] && - nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) - return -EINVAL; - spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4ab5ef71d96d..939502ff7c87 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -924,7 +924,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); if (!exp || exp->master == ct || - nfct_help(exp->master)->helper != nfct_help(ct)->helper || + exp->helper != nfct_help(ct)->helper || exp->class != class) break; #if IS_ENABLED(CONFIG_NF_NAT) @@ -1040,6 +1040,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, unsigned int port; const struct sdp_media_type *t; int ret = NF_ACCEPT; + bool have_rtp_addr = false; hooks = rcu_dereference(nf_nat_sip_hooks); @@ -1056,8 +1057,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, caddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, sdpoff, *datalen, SDP_HDR_CONNECTION, SDP_HDR_MEDIA, - &matchoff, &matchlen, &caddr) > 0) + &matchoff, &matchlen, &caddr) > 0) { caddr_len = matchlen; + memcpy(&rtp_addr, &caddr, sizeof(rtp_addr)); + have_rtp_addr = true; + } mediaoff = sdpoff; for (i = 0; i < ARRAY_SIZE(sdp_media_types); ) { @@ -1091,9 +1095,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen, &maddr) > 0) { maddr_len = matchlen; memcpy(&rtp_addr, &maddr, sizeof(rtp_addr)); - } else if (caddr_len) + have_rtp_addr = true; + } else if (caddr_len) { memcpy(&rtp_addr, &caddr, sizeof(rtp_addr)); - else { + have_rtp_addr = true; + } else { nf_ct_helper_log(skb, ct, "cannot parse SDP message"); return NF_DROP; } @@ -1125,7 +1131,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, /* Update session connection and owner addresses */ hooks = rcu_dereference(nf_nat_sip_hooks); - if (hooks && ct->status & IPS_NAT_MASK) + if (hooks && ct->status & IPS_NAT_MASK && have_rtp_addr) ret = hooks->sdp_session(skb, protoff, dataoff, dptr, datalen, sdpoff, &rtp_addr); @@ -1297,7 +1303,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; - exp->helper = helper; + rcu_assign_pointer(exp->helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; hooks = rcu_dereference(nf_nat_sip_hooks); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 9b677e116487..93d0aa7f8fcc 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -14,6 +14,8 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_tuple.h> +#define NF_FLOW_RULE_ACTION_MAX 24 + static struct workqueue_struct *nf_flow_offload_add_wq; static struct workqueue_struct *nf_flow_offload_del_wq; static struct workqueue_struct *nf_flow_offload_stats_wq; @@ -216,7 +218,12 @@ static void flow_offload_mangle(struct flow_action_entry *entry, static inline struct flow_action_entry * flow_action_entry_next(struct nf_flow_rule *flow_rule) { - int i = flow_rule->rule->action.num_entries++; + int i; + + if (unlikely(flow_rule->rule->action.num_entries >= NF_FLOW_RULE_ACTION_MAX)) + return NULL; + + i = flow_rule->rule->action.num_entries++; return &flow_rule->rule->action.entries[i]; } @@ -234,6 +241,9 @@ static int flow_offload_eth_src(struct net *net, u32 mask, val; u16 val16; + if (!entry0 || !entry1) + return -E2BIG; + this_tuple = &flow->tuplehash[dir].tuple; switch (this_tuple->xmit_type) { @@ -284,6 +294,9 @@ static int flow_offload_eth_dst(struct net *net, u8 nud_state; u16 val16; + if (!entry0 || !entry1) + return -E2BIG; + this_tuple = &flow->tuplehash[dir].tuple; switch (this_tuple->xmit_type) { @@ -325,16 +338,19 @@ static int flow_offload_eth_dst(struct net *net, return 0; } -static void flow_offload_ipv4_snat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_ipv4_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); u32 mask = ~htonl(0xffffffff); __be32 addr; u32 offset; + if (!entry) + return -E2BIG; + switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; @@ -345,23 +361,27 @@ static void flow_offload_ipv4_snat(struct net *net, offset = offsetof(struct iphdr, daddr); break; default: - return; + return -EOPNOTSUPP; } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, &addr, &mask); + return 0; } -static void flow_offload_ipv4_dnat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_ipv4_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); u32 mask = ~htonl(0xffffffff); __be32 addr; u32 offset; + if (!entry) + return -E2BIG; + switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; @@ -372,14 +392,15 @@ static void flow_offload_ipv4_dnat(struct net *net, offset = offsetof(struct iphdr, saddr); break; default: - return; + return -EOPNOTSUPP; } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, &addr, &mask); + return 0; } -static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, +static int flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, unsigned int offset, const __be32 *addr, const __be32 *mask) { @@ -388,15 +409,20 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) { entry = flow_action_entry_next(flow_rule); + if (!entry) + return -E2BIG; + flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, offset + i * sizeof(u32), &addr[i], mask); } + + return 0; } -static void flow_offload_ipv6_snat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_ipv6_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); const __be32 *addr; @@ -412,16 +438,16 @@ static void flow_offload_ipv6_snat(struct net *net, offset = offsetof(struct ipv6hdr, daddr); break; default: - return; + return -EOPNOTSUPP; } - flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); + return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } -static void flow_offload_ipv6_dnat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_ipv6_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); const __be32 *addr; @@ -437,10 +463,10 @@ static void flow_offload_ipv6_dnat(struct net *net, offset = offsetof(struct ipv6hdr, saddr); break; default: - return; + return -EOPNOTSUPP; } - flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); + return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static int flow_offload_l4proto(const struct flow_offload *flow) @@ -462,15 +488,18 @@ static int flow_offload_l4proto(const struct flow_offload *flow) return type; } -static void flow_offload_port_snat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_port_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); u32 mask, port; u32 offset; + if (!entry) + return -E2BIG; + switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); @@ -485,22 +514,26 @@ static void flow_offload_port_snat(struct net *net, mask = ~htonl(0xffff); break; default: - return; + return -EOPNOTSUPP; } flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, &port, &mask); + return 0; } -static void flow_offload_port_dnat(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_port_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); u32 mask, port; u32 offset; + if (!entry) + return -E2BIG; + switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port); @@ -515,20 +548,24 @@ static void flow_offload_port_dnat(struct net *net, mask = ~htonl(0xffff0000); break; default: - return; + return -EOPNOTSUPP; } flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, &port, &mask); + return 0; } -static void flow_offload_ipv4_checksum(struct net *net, - const struct flow_offload *flow, - struct nf_flow_rule *flow_rule) +static int flow_offload_ipv4_checksum(struct net *net, + const struct flow_offload *flow, + struct nf_flow_rule *flow_rule) { u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto; struct flow_action_entry *entry = flow_action_entry_next(flow_rule); + if (!entry) + return -E2BIG; + entry->id = FLOW_ACTION_CSUM; entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR; @@ -540,12 +577,14 @@ static void flow_offload_ipv4_checksum(struct net *net, entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP; break; } + + return 0; } -static void flow_offload_redirect(struct net *net, - const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_redirect(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { const struct flow_offload_tuple *this_tuple, *other_tuple; struct flow_action_entry *entry; @@ -563,21 +602,28 @@ static void flow_offload_redirect(struct net *net, ifindex = other_tuple->iifidx; break; default: - return; + return -EOPNOTSUPP; } dev = dev_get_by_index(net, ifindex); if (!dev) - return; + return -ENODEV; entry = flow_action_entry_next(flow_rule); + if (!entry) { + dev_put(dev); + return -E2BIG; + } + entry->id = FLOW_ACTION_REDIRECT; entry->dev = dev; + + return 0; } -static void flow_offload_encap_tunnel(const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_encap_tunnel(const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { const struct flow_offload_tuple *this_tuple; struct flow_action_entry *entry; @@ -585,7 +631,7 @@ static void flow_offload_encap_tunnel(const struct flow_offload *flow, this_tuple = &flow->tuplehash[dir].tuple; if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) - return; + return 0; dst = this_tuple->dst_cache; if (dst && dst->lwtstate) { @@ -594,15 +640,19 @@ static void flow_offload_encap_tunnel(const struct flow_offload *flow, tun_info = lwt_tun_info(dst->lwtstate); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) { entry = flow_action_entry_next(flow_rule); + if (!entry) + return -E2BIG; entry->id = FLOW_ACTION_TUNNEL_ENCAP; entry->tunnel = tun_info; } } + + return 0; } -static void flow_offload_decap_tunnel(const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int flow_offload_decap_tunnel(const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { const struct flow_offload_tuple *other_tuple; struct flow_action_entry *entry; @@ -610,7 +660,7 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, other_tuple = &flow->tuplehash[!dir].tuple; if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) - return; + return 0; dst = other_tuple->dst_cache; if (dst && dst->lwtstate) { @@ -619,9 +669,13 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, tun_info = lwt_tun_info(dst->lwtstate); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) { entry = flow_action_entry_next(flow_rule); + if (!entry) + return -E2BIG; entry->id = FLOW_ACTION_TUNNEL_DECAP; } } + + return 0; } static int @@ -633,8 +687,9 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, const struct flow_offload_tuple *tuple; int i; - flow_offload_decap_tunnel(flow, dir, flow_rule); - flow_offload_encap_tunnel(flow, dir, flow_rule); + if (flow_offload_decap_tunnel(flow, dir, flow_rule) < 0 || + flow_offload_encap_tunnel(flow, dir, flow_rule) < 0) + return -1; if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 || flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) @@ -650,6 +705,8 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, if (tuple->encap[i].proto == htons(ETH_P_8021Q)) { entry = flow_action_entry_next(flow_rule); + if (!entry) + return -1; entry->id = FLOW_ACTION_VLAN_POP; } } @@ -663,6 +720,8 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, continue; entry = flow_action_entry_next(flow_rule); + if (!entry) + return -1; switch (other_tuple->encap[i].proto) { case htons(ETH_P_PPP_SES): @@ -688,18 +747,22 @@ int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, return -1; if (test_bit(NF_FLOW_SNAT, &flow->flags)) { - flow_offload_ipv4_snat(net, flow, dir, flow_rule); - flow_offload_port_snat(net, flow, dir, flow_rule); + if (flow_offload_ipv4_snat(net, flow, dir, flow_rule) < 0 || + flow_offload_port_snat(net, flow, dir, flow_rule) < 0) + return -1; } if (test_bit(NF_FLOW_DNAT, &flow->flags)) { - flow_offload_ipv4_dnat(net, flow, dir, flow_rule); - flow_offload_port_dnat(net, flow, dir, flow_rule); + if (flow_offload_ipv4_dnat(net, flow, dir, flow_rule) < 0 || + flow_offload_port_dnat(net, flow, dir, flow_rule) < 0) + return -1; } if (test_bit(NF_FLOW_SNAT, &flow->flags) || test_bit(NF_FLOW_DNAT, &flow->flags)) - flow_offload_ipv4_checksum(net, flow, flow_rule); + if (flow_offload_ipv4_checksum(net, flow, flow_rule) < 0) + return -1; - flow_offload_redirect(net, flow, dir, flow_rule); + if (flow_offload_redirect(net, flow, dir, flow_rule) < 0) + return -1; return 0; } @@ -713,22 +776,23 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, return -1; if (test_bit(NF_FLOW_SNAT, &flow->flags)) { - flow_offload_ipv6_snat(net, flow, dir, flow_rule); - flow_offload_port_snat(net, flow, dir, flow_rule); + if (flow_offload_ipv6_snat(net, flow, dir, flow_rule) < 0 || + flow_offload_port_snat(net, flow, dir, flow_rule) < 0) + return -1; } if (test_bit(NF_FLOW_DNAT, &flow->flags)) { - flow_offload_ipv6_dnat(net, flow, dir, flow_rule); - flow_offload_port_dnat(net, flow, dir, flow_rule); + if (flow_offload_ipv6_dnat(net, flow, dir, flow_rule) < 0 || + flow_offload_port_dnat(net, flow, dir, flow_rule) < 0) + return -1; } - flow_offload_redirect(net, flow, dir, flow_rule); + if (flow_offload_redirect(net, flow, dir, flow_rule) < 0) + return -1; return 0; } EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv6); -#define NF_FLOW_RULE_ACTION_MAX 16 - static struct nf_flow_rule * nf_flow_offload_rule_alloc(struct net *net, const struct flow_offload_work *offload, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3922cff1bb3d..8c42247a176c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -11667,8 +11667,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, switch (data->verdict.code) { case NF_ACCEPT: case NF_DROP: - case NF_QUEUE: - break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -11703,6 +11701,11 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.chain = chain; break; + case NF_QUEUE: + /* The nft_queue expression is used for this purpose, an + * immediate NF_QUEUE verdict should not ever be seen here. + */ + fallthrough; default: return -EINVAL; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b35a90955e2e..f80978c06fa0 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -647,15 +647,11 @@ __build_packet_message(struct nfnl_log_net *log, if (data_len) { struct nlattr *nla; - int size = nla_attr_size(data_len); - if (skb_tailroom(inst->skb) < nla_total_size(data_len)) + nla = nla_reserve(inst->skb, NFULA_PAYLOAD, data_len); + if (!nla) goto nla_put_failure; - nla = skb_put(inst->skb, nla_total_size(data_len)); - nla->nla_type = NFULA_PAYLOAD; - nla->nla_len = size; - if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) BUG(); } @@ -730,7 +726,7 @@ nfulnl_log_packet(struct net *net, + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) - + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ + + nlmsg_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 7ff90325c97f..6395982e4d95 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -242,7 +242,7 @@ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -319,7 +319,7 @@ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -414,7 +414,7 @@ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -505,7 +505,7 @@ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -641,7 +641,7 @@ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -699,7 +699,7 @@ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -764,7 +764,7 @@ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -839,7 +839,7 @@ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -925,7 +925,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; @@ -1019,7 +1019,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) - return b; + ret = b; if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fe8bd497d74a..737c339decd0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -572,14 +572,12 @@ static struct nft_array *nft_array_alloc(u32 max_intervals) return array; } -#define NFT_ARRAY_EXTRA_SIZE 10240 - /* Similar to nft_rbtree_{u,k}size to hide details to userspace, but consider * packed representation coming from userspace for anonymous sets too. */ static u32 nft_array_elems(const struct nft_set *set) { - u32 nelems = atomic_read(&set->nelems); + u32 nelems = atomic_read(&set->nelems) - set->ndeact; /* Adjacent intervals are represented with a single start element in * anonymous sets, use the current element counter as is. @@ -595,27 +593,87 @@ static u32 nft_array_elems(const struct nft_set *set) return (nelems / 2) + 2; } -static int nft_array_may_resize(const struct nft_set *set) +#define NFT_ARRAY_INITIAL_SIZE 1024 +#define NFT_ARRAY_INITIAL_ANON_SIZE 16 +#define NFT_ARRAY_INITIAL_ANON_THRESH (8192U / sizeof(struct nft_array_interval)) + +static int nft_array_may_resize(const struct nft_set *set, bool flush) { - u32 nelems = nft_array_elems(set), new_max_intervals; + u32 initial_intervals, max_intervals, new_max_intervals, delta; + u32 shrinked_max_intervals, nelems = nft_array_elems(set); struct nft_rbtree *priv = nft_set_priv(set); struct nft_array *array; - if (!priv->array_next) { - array = nft_array_alloc(nelems + NFT_ARRAY_EXTRA_SIZE); - if (!array) - return -ENOMEM; + if (nft_set_is_anonymous(set)) + initial_intervals = NFT_ARRAY_INITIAL_ANON_SIZE; + else + initial_intervals = NFT_ARRAY_INITIAL_SIZE; + + if (priv->array_next) { + max_intervals = priv->array_next->max_intervals; + new_max_intervals = priv->array_next->max_intervals; + } else { + if (priv->array) { + max_intervals = priv->array->max_intervals; + new_max_intervals = priv->array->max_intervals; + } else { + max_intervals = 0; + new_max_intervals = initial_intervals; + } + } - priv->array_next = array; + if (nft_set_is_anonymous(set)) + goto maybe_grow; + + if (flush) { + /* Set flush just started, nelems still report elements.*/ + nelems = 0; + new_max_intervals = NFT_ARRAY_INITIAL_SIZE; + goto realloc_array; } - if (nelems < priv->array_next->max_intervals) - return 0; + if (check_add_overflow(new_max_intervals, new_max_intervals, + &shrinked_max_intervals)) + return -EOVERFLOW; + + shrinked_max_intervals = DIV_ROUND_UP(shrinked_max_intervals, 3); - new_max_intervals = priv->array_next->max_intervals + NFT_ARRAY_EXTRA_SIZE; - if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0) + if (shrinked_max_intervals > NFT_ARRAY_INITIAL_SIZE && + nelems < shrinked_max_intervals) { + new_max_intervals = shrinked_max_intervals; + goto realloc_array; + } +maybe_grow: + if (nelems > new_max_intervals) { + if (nft_set_is_anonymous(set) && + new_max_intervals < NFT_ARRAY_INITIAL_ANON_THRESH) { + new_max_intervals <<= 1; + } else { + delta = new_max_intervals >> 1; + if (check_add_overflow(new_max_intervals, delta, + &new_max_intervals)) + return -EOVERFLOW; + } + } + +realloc_array: + if (WARN_ON_ONCE(nelems > new_max_intervals)) return -ENOMEM; + if (priv->array_next) { + if (max_intervals == new_max_intervals) + return 0; + + if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0) + return -ENOMEM; + } else { + array = nft_array_alloc(new_max_intervals); + if (!array) + return -ENOMEM; + + priv->array_next = array; + } + return 0; } @@ -630,7 +688,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_maybe_reset_start_cookie(priv, tstamp); - if (nft_array_may_resize(set) < 0) + if (nft_array_may_resize(set, false) < 0) return -ENOMEM; do { @@ -741,7 +799,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, nft_rbtree_interval_null(set, this)) priv->start_rbe_cookie = 0; - if (nft_array_may_resize(set) < 0) + if (nft_array_may_resize(set, false) < 0) return NULL; while (parent != NULL) { @@ -811,7 +869,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, switch (iter->type) { case NFT_ITER_UPDATE_CLONE: - if (nft_array_may_resize(set) < 0) { + if (nft_array_may_resize(set, true) < 0) { iter->err = -ENOMEM; break; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e594b3b7ad82..b39017c80548 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -501,6 +501,17 @@ int xt_check_match(struct xt_mtchk_param *par, par->match->table, par->table); return -EINVAL; } + + /* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with + * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP + * support. + */ + if (par->family == NFPROTO_ARP && + par->match->family != NFPROTO_ARP) { + pr_info_ratelimited("%s_tables: %s match: not valid for this family\n", + xt_prefix[par->family], par->match->name); + return -EINVAL; + } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; @@ -1016,6 +1027,18 @@ int xt_check_target(struct xt_tgchk_param *par, par->target->table, par->table); return -EINVAL; } + + /* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with + * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP + * support. + */ + if (par->family == NFPROTO_ARP && + par->target->family != NFPROTO_ARP) { + pr_info_ratelimited("%s_tables: %s target: not valid for this family\n", + xt_prefix[par->family], par->target->name); + return -EINVAL; + } + if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index c437fbd59ec1..43d2ae2be628 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -65,6 +65,9 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) info->priv = NULL; if (info->has_path) { + if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path)) + return -ENAMETOOLONG; + cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", @@ -102,6 +105,9 @@ static int cgroup_mt_check_v2(const struct xt_mtchk_param *par) info->priv = NULL; if (info->has_path) { + if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path)) + return -ENAMETOOLONG; + cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index 72324bd976af..b1d736c15fcb 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -91,6 +91,11 @@ static int xt_rateest_mt_checkentry(const struct xt_mtchk_param *par) goto err1; } + if (strnlen(info->name1, sizeof(info->name1)) >= sizeof(info->name1)) + return -ENAMETOOLONG; + if (strnlen(info->name2, sizeof(info->name2)) >= sizeof(info->name2)) + return -ENAMETOOLONG; + ret = -ENOENT; est1 = xt_rateest_lookup(par->net, info->name1); if (!est1) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 43d871525dbc..5f46c4b5720f 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -579,8 +579,7 @@ static int nci_close_device(struct nci_dev *ndev) skb_queue_purge(&ndev->rx_q); skb_queue_purge(&ndev->tx_q); - /* Flush RX and TX wq */ - flush_workqueue(ndev->rx_wq); + /* Flush TX wq, RX wq flush can't be under the lock */ flush_workqueue(ndev->tx_wq); /* Reset device */ @@ -592,13 +591,13 @@ static int nci_close_device(struct nci_dev *ndev) msecs_to_jiffies(NCI_RESET_TIMEOUT)); /* After this point our queues are empty - * and no works are scheduled. + * rx work may be running but will see that NCI_UP was cleared */ ndev->ops->close(ndev); clear_bit(NCI_INIT, &ndev->flags); - /* Flush cmd wq */ + /* Flush cmd and tx wq */ flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); @@ -613,6 +612,9 @@ static int nci_close_device(struct nci_dev *ndev) mutex_unlock(&ndev->req_lock); + /* rx_work may take req_lock via nci_deactivate_target */ + flush_workqueue(ndev->rx_wq); + return 0; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 67fbf6e48a30..13052408a132 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2953,6 +2953,8 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_MPLS: if (!eth_p_mpls(eth_type)) return -EINVAL; + if (key_len != sizeof(struct ovs_key_mpls)) + return -EINVAL; break; case OVS_KEY_ATTR_SCTP: diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 6574f9bcdc02..12055af832dc 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -151,11 +151,15 @@ static void vport_netdev_free(struct rcu_head *rcu) void ovs_netdev_detach_dev(struct vport *vport) { ASSERT_RTNL(); - vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(vport->dev); netdev_upper_dev_unlink(vport->dev, netdev_master_upper_dev_get(vport->dev)); dev_set_promiscuity(vport->dev, -1); + + /* paired with smp_mb() in netdev_destroy() */ + smp_wmb(); + + vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; } static void netdev_destroy(struct vport *vport) @@ -174,6 +178,9 @@ static void netdev_destroy(struct vport *vport) rtnl_unlock(); } + /* paired with smp_wmb() in ovs_netdev_detach_dev() */ + smp_mb(); + call_rcu(&vport->rcu, vport_netdev_free); } @@ -189,8 +196,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) */ if (vport->dev->reg_state == NETREG_REGISTERED) rtnl_delete_link(vport->dev, 0, NULL); - netdev_put(vport->dev, &vport->dev_tracker); - vport->dev = NULL; rtnl_unlock(); call_rcu(&vport->rcu, vport_netdev_free); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 72d0935139f0..bb2d88205e5a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3135,6 +3135,7 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + WRITE_ONCE(po->num, 0); packet_cached_dev_reset(po); if (po->prot_hook.dev) { diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 55fd2dd37588..d77e9c8212da 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -118,7 +118,7 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports); * @ep: endpoint * @ref: reference count for node * @nid: node id - * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port + * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port * @qrtr_tx_lock: lock for qrtr_tx_flow inserts * @rx_queue: receive queue * @item: list item for broadcast list @@ -129,7 +129,7 @@ struct qrtr_node { struct kref ref; unsigned int nid; - struct radix_tree_root qrtr_tx_flow; + struct xarray qrtr_tx_flow; struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ struct sk_buff_head rx_queue; @@ -172,6 +172,7 @@ static void __qrtr_node_release(struct kref *kref) struct qrtr_tx_flow *flow; unsigned long flags; void __rcu **slot; + unsigned long index; spin_lock_irqsave(&qrtr_nodes_lock, flags); /* If the node is a bridge for other nodes, there are possibly @@ -189,11 +190,9 @@ static void __qrtr_node_release(struct kref *kref) skb_queue_purge(&node->rx_queue); /* Free tx flow counters */ - radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { - flow = *slot; - radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); + xa_for_each(&node->qrtr_tx_flow, index, flow) kfree(flow); - } + xa_destroy(&node->qrtr_tx_flow); kfree(node); } @@ -228,9 +227,7 @@ static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb) key = remote_node << 32 | remote_port; - rcu_read_lock(); - flow = radix_tree_lookup(&node->qrtr_tx_flow, key); - rcu_read_unlock(); + flow = xa_load(&node->qrtr_tx_flow, key); if (flow) { spin_lock(&flow->resume_tx.lock); flow->pending = 0; @@ -269,12 +266,13 @@ static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port, return 0; mutex_lock(&node->qrtr_tx_lock); - flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + flow = xa_load(&node->qrtr_tx_flow, key); if (!flow) { flow = kzalloc_obj(*flow); if (flow) { init_waitqueue_head(&flow->resume_tx); - if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) { + if (xa_err(xa_store(&node->qrtr_tx_flow, key, flow, + GFP_KERNEL))) { kfree(flow); flow = NULL; } @@ -326,9 +324,7 @@ static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node, unsigned long key = (u64)dest_node << 32 | dest_port; struct qrtr_tx_flow *flow; - rcu_read_lock(); - flow = radix_tree_lookup(&node->qrtr_tx_flow, key); - rcu_read_unlock(); + flow = xa_load(&node->qrtr_tx_flow, key); if (flow) { spin_lock_irq(&flow->resume_tx.lock); flow->tx_failed = 1; @@ -599,7 +595,7 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) node->nid = QRTR_EP_NID_AUTO; node->ep = ep; - INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL); + xa_init(&node->qrtr_tx_flow); mutex_init(&node->qrtr_tx_lock); qrtr_node_assign(node, nid); @@ -627,6 +623,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) struct qrtr_tx_flow *flow; struct sk_buff *skb; unsigned long flags; + unsigned long index; void __rcu **slot; mutex_lock(&node->ep_lock); @@ -649,10 +646,8 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) /* Wake up any transmitters waiting for resume-tx from the node */ mutex_lock(&node->qrtr_tx_lock); - radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { - flow = *slot; + xa_for_each(&node->qrtr_tx_flow, index, flow) wake_up_interruptible_all(&flow->resume_tx); - } mutex_unlock(&node->qrtr_tx_lock); qrtr_node_release(node); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 077f7041df15..2cfec252eeac 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -604,8 +604,13 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, return ibmr; } - if (conn) + if (conn) { ic = conn->c_transport_data; + if (!ic || !ic->i_cm_id || !ic->i_cm_id->qp) { + ret = -ENODEV; + goto out; + } + } if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 4829c27446e3..20f7f9ee0b35 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2969,6 +2969,7 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_handle = 0; + tcm->tcm_info = 0; if (block->q) { tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex; tcm->tcm_parent = block->q->handle; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 339c664beff6..ab364e4e4686 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -503,8 +503,16 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, } if (TC_H_MAJ(baseclass) == 0) { - struct Qdisc *q = tcf_block_q(tp->chain->block); + struct tcf_block *block = tp->chain->block; + struct Qdisc *q; + if (tcf_block_shared(block)) { + NL_SET_ERR_MSG(extack, + "Must specify baseclass when attaching flow filter to block"); + goto err2; + } + + q = tcf_block_q(block); baseclass = TC_H_MAKE(q->handle, baseclass); } if (TC_H_MIN(baseclass) == 0) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index be81c108179d..23884ef8b80c 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -247,8 +247,18 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_FW_MAX + 1]; int err; - if (!opt) - return handle ? -EINVAL : 0; /* Succeed if it is old method. */ + if (!opt) { + if (handle) + return -EINVAL; + + if (tcf_block_shared(tp->chain->block)) { + NL_SET_ERR_MSG(extack, + "Must specify mark when attaching fw filter to block"); + return -EINVAL; + } + + return 0; /* Succeed if it is old method. */ + } err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy, NULL); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b5657ffbbf84..83b2ca2e37fc 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -555,7 +555,7 @@ static void rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) { u64 y1, y2, dx, dy; - u32 dsm; + u64 dsm; if (isc->sm1 <= isc->sm2) { /* service curve is convex */ @@ -598,7 +598,7 @@ rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) */ dx = (y1 - y) << SM_SHIFT; dsm = isc->sm1 - isc->sm2; - do_div(dx, dsm); + dx = div64_u64(dx, dsm); /* * check if (x, y1) belongs to the 1st segment of rtsc. * if so, add the offset. diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5de1c932944a..20df1c08b1e9 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -519,8 +519,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto finish_segs; } - skb->data[get_random_u32_below(skb_headlen(skb))] ^= - 1<<get_random_u32_below(8); + if (skb_headlen(skb)) + skb->data[get_random_u32_below(skb_headlen(skb))] ^= + 1 << get_random_u32_below(8); } if (unlikely(q->t_len >= sch->limit)) { diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index d833e36f7fd4..c1d9b923938d 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -135,9 +135,16 @@ out: sock_put(sk); } +static bool smc_rx_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + /* smc_spd_priv in buf->private is not shareable; disallow cloning. */ + return false; +} + static const struct pipe_buf_operations smc_pipe_ops = { .release = smc_rx_pipe_buf_release, - .get = generic_pipe_buf_get + .get = smc_rx_pipe_buf_get, }; static void smc_rx_spd_release(struct splice_pipe_desc *spd, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5fe07f110fe8..dd9dda759bbb 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -246,6 +246,7 @@ static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); atomic_inc(&ctx->decrypt_pending); + __skb_queue_purge(&ctx->async_hold); return ctx->async_wait.err; } @@ -2225,7 +2226,6 @@ recv_end: /* Wait for all previously submitted records to be decrypted */ ret = tls_decrypt_async_wait(ctx); - __skb_queue_purge(&ctx->async_hold); if (ret) { if (err >= 0 || err == -EINPROGRESS) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2f7d94d682cb..d912ed2f012a 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -2928,6 +2928,7 @@ static void vsock_net_init(struct net *net) net->vsock.mode = vsock_net_child_mode(current->nsproxy->net_ns); net->vsock.child_ns_mode = net->vsock.mode; + net->vsock.child_ns_mode_locked = 0; } static __net_init int vsock_sysctl_init_net(struct net *net) diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index b981a4828d08..e47ebd8acd21 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -34,6 +34,10 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more) struct sk_buff *skbo, *skbn = skb; struct x25_sock *x25 = x25_sk(sk); + /* make sure we don't overflow */ + if (x25->fraglen + skb->len > USHRT_MAX) + return 1; + if (more) { x25->fraglen += skb->len; skb_queue_tail(&x25->fragment_queue, skb); @@ -44,10 +48,9 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more) if (x25->fraglen > 0) { /* End of fragment */ int len = x25->fraglen + skb->len; - if ((skbn = alloc_skb(len, GFP_ATOMIC)) == NULL){ - kfree_skb(skb); + skbn = alloc_skb(len, GFP_ATOMIC); + if (!skbn) return 1; - } skb_queue_tail(&x25->fragment_queue, skb); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 0285aaa1e93c..159708d9ad20 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -40,6 +40,7 @@ void x25_clear_queues(struct sock *sk) skb_queue_purge(&x25->interrupt_in_queue); skb_queue_purge(&x25->interrupt_out_queue); skb_queue_purge(&x25->fragment_queue); + x25->fraglen = 0; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 4ed346e682c7..dc1312ed5a09 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -75,7 +75,10 @@ int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) spin_lock_bh(&xfrm_input_afinfo_lock); if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) { - if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo)) + const struct xfrm_input_afinfo *cur; + + cur = rcu_access_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family]); + if (unlikely(cur != afinfo)) err = -EINVAL; else RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL); diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c index 050a82101ca5..97bc979e55ba 100644 --- a/net/xfrm/xfrm_iptfs.c +++ b/net/xfrm/xfrm_iptfs.c @@ -901,6 +901,12 @@ static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq, iptfs_skb_can_add_frags(newskb, fragwalk, data, copylen)) { iptfs_skb_add_frags(newskb, fragwalk, data, copylen); } else { + if (skb_linearize(newskb)) { + XFRM_INC_STATS(xs_net(xtfs->x), + LINUX_MIB_XFRMINBUFFERERROR); + goto abandon; + } + /* copy fragment data into newskb */ if (skb_copy_seq_read(st, data, skb_put(newskb, copylen), copylen)) { @@ -991,6 +997,11 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data, iplen = be16_to_cpu(iph->tot_len); iphlen = iph->ihl << 2; + if (iplen < iphlen || iphlen < sizeof(*iph)) { + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINHDRERROR); + goto done; + } protocol = cpu_to_be16(ETH_P_IP); XFRM_MODE_SKB_CB(skbseq->root_skb)->tos = iph->tos; } else if (iph->version == 0x6) { @@ -2653,9 +2664,6 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) if (!xtfs) return -ENOMEM; - x->mode_data = xtfs; - xtfs->x = x; - xtfs->ra_newskb = NULL; if (xtfs->cfg.reorder_win_size) { xtfs->w_saved = kzalloc_objs(*xtfs->w_saved, @@ -2666,6 +2674,9 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) } } + x->mode_data = xtfs; + xtfs->x = x; + return 0; } diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c index ebf95d48e86c..1856beee0149 100644 --- a/net/xfrm/xfrm_nat_keepalive.c +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -261,7 +261,7 @@ int __net_init xfrm_nat_keepalive_net_init(struct net *net) int xfrm_nat_keepalive_net_fini(struct net *net) { - cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work); + disable_delayed_work_sync(&net->xfrm.nat_keepalive_work); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9e1a522ab1c5..362939aa56cf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4156,7 +4156,7 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { - if (xfrm_policy_afinfo[i] != afinfo) + if (rcu_access_pointer(xfrm_policy_afinfo[i]) != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; @@ -4242,7 +4242,7 @@ static int __net_init xfrm_policy_init(struct net *net) net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; htab = &net->xfrm.policy_bydst[dir]; - htab->table = xfrm_hash_alloc(sz); + rcu_assign_pointer(htab->table, xfrm_hash_alloc(sz)); if (!htab->table) goto out_bydst; htab->hmask = hmask; @@ -4269,7 +4269,7 @@ out_bydst: struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; - xfrm_hash_free(htab->table, sz); + xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: @@ -4282,6 +4282,8 @@ static void xfrm_policy_fini(struct net *net) unsigned int sz; int dir; + disable_work_sync(&net->xfrm.policy_hthresh.work); + flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); @@ -4295,8 +4297,8 @@ static void xfrm_policy_fini(struct net *net) htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); - WARN_ON(!hlist_empty(htab->table)); - xfrm_hash_free(htab->table, sz); + WARN_ON(!hlist_empty(rcu_dereference_protected(htab->table, true))); + xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 98b362d51836..1748d374abca 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -53,7 +53,7 @@ static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static HLIST_HEAD(xfrm_state_dev_gc_list); -static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) +static inline bool xfrm_state_hold_rcu(struct xfrm_state *x) { return refcount_inc_not_zero(&x->refcnt); } @@ -870,7 +870,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); @@ -891,7 +891,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool struct xfrm_state *x; struct xfrm_dev_offload *xso; - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (xso->dev == dev && @@ -931,7 +931,7 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); @@ -973,7 +973,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { restart: - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { @@ -1563,23 +1563,23 @@ found: list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); XFRM_STATE_INSERT(bydst, &x->bydst, - net->xfrm.state_bydst + h, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); XFRM_STATE_INSERT(bysrc, &x->bysrc, - net->xfrm.state_bysrc + h, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); INIT_HLIST_NODE(&x->state_cache); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); XFRM_STATE_INSERT(byspi, &x->byspi, - net->xfrm.state_byspi + h, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, - net->xfrm.state_byseq + h, + xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; @@ -1652,7 +1652,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -1703,18 +1703,12 @@ static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 sp struct xfrm_state *x; unsigned int i; - rcu_read_lock(); for (i = 0; i <= net->xfrm.state_hmask; i++) { - hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) { - if (x->id.spi == spi && x->id.proto == proto) { - if (!xfrm_state_hold_rcu(x)) - continue; - rcu_read_unlock(); + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + i, byspi) { + if (x->id.spi == spi && x->id.proto == proto) return x; - } } } - rcu_read_unlock(); return NULL; } @@ -1730,25 +1724,29 @@ static void __xfrm_state_insert(struct xfrm_state *x) h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); - XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + XFRM_STATE_INSERT(bydst, &x->bydst, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); - XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + XFRM_STATE_INSERT(bysrc, &x->bysrc, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, + XFRM_STATE_INSERT(byspi, &x->byspi, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); - XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, + XFRM_STATE_INSERT(byseq, &x->byseq, + xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } @@ -1775,7 +1773,7 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) u32 cpu_id = xnew->pcpu_num; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && @@ -1811,7 +1809,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_state *x; u32 mark = m->v & m->m; - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || @@ -1868,10 +1866,12 @@ static struct xfrm_state *__find_acq_core(struct net *net, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); - XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + XFRM_STATE_INSERT(bydst, &x->bydst, + xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); - XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + XFRM_STATE_INSERT(bysrc, &x->bysrc, + xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); net->xfrm.state_num++; @@ -2091,7 +2091,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -2110,7 +2110,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -2264,6 +2264,7 @@ out: err = 0; x->km.state = XFRM_STATE_DEAD; + xfrm_dev_state_delete(x); __xfrm_state_put(x); } @@ -2312,7 +2313,7 @@ void xfrm_state_update_stats(struct net *net) spin_lock_bh(&net->xfrm.xfrm_state_lock); for (i = 0; i <= net->xfrm.state_hmask; i++) { - hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst) + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) xfrm_dev_state_update_stats(x); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); @@ -2503,7 +2504,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { + hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->pcpu_num == pcpu_num && @@ -2602,12 +2603,13 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, if (!x0) { x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family); - XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); + XFRM_STATE_INSERT(byspi, &x->byspi, + xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, + x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; goto unlock; } - xfrm_state_put(x0); spin_unlock_bh(&net->xfrm.xfrm_state_lock); next: @@ -3258,6 +3260,7 @@ EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { + struct hlist_head *ndst, *nsrc, *nspi, *nseq; unsigned int sz; if (net_eq(net, &init_net)) @@ -3268,18 +3271,25 @@ int __net_init xfrm_state_init(struct net *net) sz = sizeof(struct hlist_head) * 8; - net->xfrm.state_bydst = xfrm_hash_alloc(sz); - if (!net->xfrm.state_bydst) + ndst = xfrm_hash_alloc(sz); + if (!ndst) goto out_bydst; - net->xfrm.state_bysrc = xfrm_hash_alloc(sz); - if (!net->xfrm.state_bysrc) + rcu_assign_pointer(net->xfrm.state_bydst, ndst); + + nsrc = xfrm_hash_alloc(sz); + if (!nsrc) goto out_bysrc; - net->xfrm.state_byspi = xfrm_hash_alloc(sz); - if (!net->xfrm.state_byspi) + rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); + + nspi = xfrm_hash_alloc(sz); + if (!nspi) goto out_byspi; - net->xfrm.state_byseq = xfrm_hash_alloc(sz); - if (!net->xfrm.state_byseq) + rcu_assign_pointer(net->xfrm.state_byspi, nspi); + + nseq = xfrm_hash_alloc(sz); + if (!nseq) goto out_byseq; + rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_cache_input = alloc_percpu(struct hlist_head); if (!net->xfrm.state_cache_input) @@ -3295,17 +3305,19 @@ int __net_init xfrm_state_init(struct net *net) return 0; out_state_cache_input: - xfrm_hash_free(net->xfrm.state_byseq, sz); + xfrm_hash_free(nseq, sz); out_byseq: - xfrm_hash_free(net->xfrm.state_byspi, sz); + xfrm_hash_free(nspi, sz); out_byspi: - xfrm_hash_free(net->xfrm.state_bysrc, sz); + xfrm_hash_free(nsrc, sz); out_bysrc: - xfrm_hash_free(net->xfrm.state_bydst, sz); + xfrm_hash_free(ndst, sz); out_bydst: return -ENOMEM; } +#define xfrm_state_deref_netexit(table) \ + rcu_dereference_protected((table), true /* netns is going away */) void xfrm_state_fini(struct net *net) { unsigned int sz; @@ -3318,17 +3330,17 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); for (i = 0; i <= net->xfrm.state_hmask; i++) { - WARN_ON(!hlist_empty(net->xfrm.state_byseq + i)); - WARN_ON(!hlist_empty(net->xfrm.state_byspi + i)); - WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i)); - WARN_ON(!hlist_empty(net->xfrm.state_bydst + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byseq) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byspi) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bysrc) + i)); + WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bydst) + i)); } sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); - xfrm_hash_free(net->xfrm.state_byseq, sz); - xfrm_hash_free(net->xfrm.state_byspi, sz); - xfrm_hash_free(net->xfrm.state_bysrc, sz); - xfrm_hash_free(net->xfrm.state_bydst, sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byseq), sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byspi), sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bysrc), sz); + xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bydst), sz); free_percpu(net->xfrm.state_cache_input); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 403b5ecac2c5..1656b487f833 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -35,6 +35,15 @@ #endif #include <linux/unaligned.h> +static struct sock *xfrm_net_nlsk(const struct net *net, const struct sk_buff *skb) +{ + /* get the source of this request, see netlink_unicast_kernel */ + const struct sock *sk = NETLINK_CB(skb).sk; + + /* sk is refcounted, the netns stays alive and nlsk with it */ + return rcu_dereference_protected(net->xfrm.nlsk, sk->sk_net_refcnt); +} + static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type, struct netlink_ext_ack *extack) { @@ -1727,7 +1736,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_spdinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static inline unsigned int xfrm_sadinfo_msgsize(void) @@ -1787,7 +1796,7 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_sadinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1807,7 +1816,7 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } xfrm_state_put(x); out_noput: @@ -1850,6 +1859,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); if (pcpu_num >= num_possible_cpus()) { err = -EINVAL; + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto out_noput; } } @@ -1897,7 +1907,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, } } - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); out: xfrm_state_put(x); @@ -2542,7 +2552,7 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT]; nlmsg_end(r_skb, r_nlh); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); + return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid); } static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2608,7 +2618,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } } else { @@ -2781,7 +2791,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, err = build_aevent(r_skb, x, &c); BUG_ON(err < 0); - err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid); + err = nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, NETLINK_CB(skb).portid); spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; @@ -3001,8 +3011,10 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); err = -EINVAL; - if (x->pcpu_num >= num_possible_cpus()) + if (x->pcpu_num >= num_possible_cpus()) { + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto free_state; + } } err = verify_newpolicy_info(&ua->policy, extack); @@ -3483,7 +3495,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, goto err; } - err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c); + err = netlink_dump_start(xfrm_net_nlsk(net, skb), skb, nlh, &c); goto err; } @@ -3673,7 +3685,7 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) } if (x->if_id) l += nla_total_size(sizeof(x->if_id)); - if (x->pcpu_num) + if (x->pcpu_num != UINT_MAX) l += nla_total_size(sizeof(x->pcpu_num)); /* Must count x->lastused as it may become non-zero behind our back. */ diff --git a/rust/kernel/regulator.rs b/rust/kernel/regulator.rs index 4f7837c7e53a..41e730cedc81 100644 --- a/rust/kernel/regulator.rs +++ b/rust/kernel/regulator.rs @@ -23,7 +23,10 @@ use crate::{ prelude::*, }; -use core::{marker::PhantomData, mem::ManuallyDrop, ptr::NonNull}; +use core::{ + marker::PhantomData, + mem::ManuallyDrop, // +}; mod private { pub trait Sealed {} @@ -229,15 +232,17 @@ pub fn devm_enable_optional(dev: &Device<Bound>, name: &CStr) -> Result { /// /// # Invariants /// -/// - `inner` is a non-null wrapper over a pointer to a `struct -/// regulator` obtained from [`regulator_get()`]. +/// - `inner` is a pointer obtained from a successful call to +/// [`regulator_get()`]. It is treated as an opaque token that may only be +/// accessed using C API methods (e.g., it may be `NULL` if the C API returns +/// `NULL`). /// /// [`regulator_get()`]: https://docs.kernel.org/driver-api/regulator.html#c.regulator_get pub struct Regulator<State> where State: RegulatorState, { - inner: NonNull<bindings::regulator>, + inner: *mut bindings::regulator, _phantom: PhantomData<State>, } @@ -249,7 +254,7 @@ impl<T: RegulatorState> Regulator<T> { // SAFETY: Safe as per the type invariants of `Regulator`. to_result(unsafe { bindings::regulator_set_voltage( - self.inner.as_ptr(), + self.inner, min_voltage.as_microvolts(), max_voltage.as_microvolts(), ) @@ -259,7 +264,7 @@ impl<T: RegulatorState> Regulator<T> { /// Gets the current voltage of the regulator. pub fn get_voltage(&self) -> Result<Voltage> { // SAFETY: Safe as per the type invariants of `Regulator`. - let voltage = unsafe { bindings::regulator_get_voltage(self.inner.as_ptr()) }; + let voltage = unsafe { bindings::regulator_get_voltage(self.inner) }; to_result(voltage).map(|()| Voltage::from_microvolts(voltage)) } @@ -270,10 +275,8 @@ impl<T: RegulatorState> Regulator<T> { // received from the C code. from_err_ptr(unsafe { bindings::regulator_get(dev.as_raw(), name.as_char_ptr()) })?; - // SAFETY: We can safely trust `inner` to be a pointer to a valid - // regulator if `ERR_PTR` was not returned. - let inner = unsafe { NonNull::new_unchecked(inner) }; - + // INVARIANT: `inner` is a pointer obtained from `regulator_get()`, and + // the call was successful. Ok(Self { inner, _phantom: PhantomData, @@ -282,12 +285,12 @@ impl<T: RegulatorState> Regulator<T> { fn enable_internal(&self) -> Result { // SAFETY: Safe as per the type invariants of `Regulator`. - to_result(unsafe { bindings::regulator_enable(self.inner.as_ptr()) }) + to_result(unsafe { bindings::regulator_enable(self.inner) }) } fn disable_internal(&self) -> Result { // SAFETY: Safe as per the type invariants of `Regulator`. - to_result(unsafe { bindings::regulator_disable(self.inner.as_ptr()) }) + to_result(unsafe { bindings::regulator_disable(self.inner) }) } } @@ -349,7 +352,7 @@ impl<T: IsEnabled> Regulator<T> { /// Checks if the regulator is enabled. pub fn is_enabled(&self) -> bool { // SAFETY: Safe as per the type invariants of `Regulator`. - unsafe { bindings::regulator_is_enabled(self.inner.as_ptr()) != 0 } + unsafe { bindings::regulator_is_enabled(self.inner) != 0 } } } @@ -359,11 +362,11 @@ impl<T: RegulatorState> Drop for Regulator<T> { // SAFETY: By the type invariants, we know that `self` owns a // reference on the enabled refcount, so it is safe to relinquish it // now. - unsafe { bindings::regulator_disable(self.inner.as_ptr()) }; + unsafe { bindings::regulator_disable(self.inner) }; } // SAFETY: By the type invariants, we know that `self` owns a reference, // so it is safe to relinquish it now. - unsafe { bindings::regulator_put(self.inner.as_ptr()) }; + unsafe { bindings::regulator_put(self.inner) }; } } diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c index e7af02f98208..9f21088c0855 100644 --- a/samples/landlock/sandboxer.c +++ b/samples/landlock/sandboxer.c @@ -299,7 +299,7 @@ out_unset: /* clang-format on */ -#define LANDLOCK_ABI_LAST 7 +#define LANDLOCK_ABI_LAST 8 #define XSTR(s) #s #define STR(s) XSTR(s) @@ -436,7 +436,8 @@ int main(const int argc, char *const argv[], char *const *const envp) /* Removes LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON for ABI < 7 */ supported_restrict_flags &= ~LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON; - + __attribute__((fallthrough)); + case 7: /* Must be printed for any ABI < LANDLOCK_ABI_LAST. */ fprintf(stderr, "Hint: You should update the running kernel " diff --git a/scripts/coccinelle/api/kmalloc_objs.cocci b/scripts/coccinelle/api/kmalloc_objs.cocci index db12b7be7247..e9a415b7b6f4 100644 --- a/scripts/coccinelle/api/kmalloc_objs.cocci +++ b/scripts/coccinelle/api/kmalloc_objs.cocci @@ -122,3 +122,14 @@ fresh identifier ALLOC_OBJS = script:python(ALLOC_ARRAY) { alloc_array(ALLOC_ARR - ALLOC(struct_size_t(TYPE, FLEX, COUNT), GFP) + ALLOC_FLEX(TYPE, FLEX, COUNT, GFP) ) + +@drop_gfp_kernel depends on patch && !(file in "tools") && !(file in "samples")@ +identifier ALLOC = {kmalloc_obj,kmalloc_objs,kmalloc_flex, + kzalloc_obj,kzalloc_objs,kzalloc_flex, + kvmalloc_obj,kvmalloc_objs,kvmalloc_flex, + kvzalloc_obj,kvzalloc_objs,kvzalloc_flex}; +@@ + + ALLOC(... +- , GFP_KERNEL + ) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 735e1de450c6..f08e0863b712 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -151,6 +151,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do if ! "$AWK" -v prefix="$CONFIG_PREFIX" \ -v warnoverride="$WARNOVERRIDE" \ -v strict="$STRICT" \ + -v outfile="$TMP_FILE.new" \ -v builtin="$BUILTIN" \ -v warnredun="$WARNREDUN" ' BEGIN { @@ -195,7 +196,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do # First pass: read merge file, store all lines and index FILENAME == ARGV[1] { - mergefile = FILENAME + mergefile = FILENAME merge_lines[FNR] = $0 merge_total = FNR cfg = get_cfg($0) @@ -212,17 +213,17 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do # Not a config or not in merge file - keep it if (cfg == "" || !(cfg in merge_cfg)) { - print $0 >> ARGV[3] + print $0 >> outfile next } - prev_val = $0 + prev_val = $0 new_val = merge_cfg[cfg] # BUILTIN: do not demote y to m if (builtin == "true" && new_val ~ /=m$/ && prev_val ~ /=y$/) { warn_builtin(cfg, prev_val, new_val) - print $0 >> ARGV[3] + print $0 >> outfile skip_merge[merge_cfg_line[cfg]] = 1 next } @@ -235,7 +236,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do # "=n" is the same as "is not set" if (prev_val ~ /=n$/ && new_val ~ / is not set$/) { - print $0 >> ARGV[3] + print $0 >> outfile next } @@ -246,25 +247,20 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do } } - # output file, skip all lines - FILENAME == ARGV[3] { - nextfile - } - END { # Newline in case base file lacks trailing newline - print "" >> ARGV[3] + print "" >> outfile # Append merge file, skipping lines marked for builtin preservation for (i = 1; i <= merge_total; i++) { if (!(i in skip_merge)) { - print merge_lines[i] >> ARGV[3] + print merge_lines[i] >> outfile } } if (strict_violated) { exit 1 } }' \ - "$ORIG_MERGE_FILE" "$TMP_FILE" "$TMP_FILE.new"; then + "$ORIG_MERGE_FILE" "$TMP_FILE"; then # awk exited non-zero, strict mode was violated STRICT_MODE_VIOLATED=true fi @@ -381,7 +377,7 @@ END { STRICT_MODE_VIOLATED=true fi -if [ "$STRICT" == "true" ] && [ "$STRICT_MODE_VIOLATED" == "true" ]; then +if [ "$STRICT" = "true" ] && [ "$STRICT_MODE_VIOLATED" = "true" ]; then echo "Requested and effective config differ" exit 1 fi diff --git a/security/landlock/domain.c b/security/landlock/domain.c index f5b78d4766cd..f0d83f43afa1 100644 --- a/security/landlock/domain.c +++ b/security/landlock/domain.c @@ -94,8 +94,7 @@ static struct landlock_details *get_current_details(void) * allocate with GFP_KERNEL_ACCOUNT because it is independent from the * caller. */ - details = - kzalloc_flex(*details, exe_path, path_size); + details = kzalloc_flex(*details, exe_path, path_size); if (!details) return ERR_PTR(-ENOMEM); diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index 319873586385..73018dc8d6c7 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -32,9 +32,8 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers) { struct landlock_ruleset *new_ruleset; - new_ruleset = - kzalloc_flex(*new_ruleset, access_masks, num_layers, - GFP_KERNEL_ACCOUNT); + new_ruleset = kzalloc_flex(*new_ruleset, access_masks, num_layers, + GFP_KERNEL_ACCOUNT); if (!new_ruleset) return ERR_PTR(-ENOMEM); refcount_set(&new_ruleset->usage, 1); @@ -559,8 +558,8 @@ landlock_merge_ruleset(struct landlock_ruleset *const parent, if (IS_ERR(new_dom)) return new_dom; - new_dom->hierarchy = kzalloc_obj(*new_dom->hierarchy, - GFP_KERNEL_ACCOUNT); + new_dom->hierarchy = + kzalloc_obj(*new_dom->hierarchy, GFP_KERNEL_ACCOUNT); if (!new_dom->hierarchy) return ERR_PTR(-ENOMEM); diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c index de01aa899751..4d4427ba8d93 100644 --- a/security/landlock/tsync.c +++ b/security/landlock/tsync.c @@ -203,6 +203,40 @@ static struct tsync_work *tsync_works_provide(struct tsync_works *s, return ctx; } +/** + * tsync_works_trim - Put the last tsync_work element + * + * @s: TSYNC works to trim. + * + * Put the last task and decrement the size of @s. + * + * This helper does not cancel a running task, but just reset the last element + * to zero. + */ +static void tsync_works_trim(struct tsync_works *s) +{ + struct tsync_work *ctx; + + if (WARN_ON_ONCE(s->size <= 0)) + return; + + ctx = s->works[s->size - 1]; + + /* + * For consistency, remove the task from ctx so that it does not look like + * we handed it a task_work. + */ + put_task_struct(ctx->task); + *ctx = (typeof(*ctx)){}; + + /* + * Cancel the tsync_works_provide() change to recycle the reserved memory + * for the next thread, if any. This also ensures that cancel_tsync_works() + * and tsync_works_release() do not see any NULL task pointers. + */ + s->size--; +} + /* * tsync_works_grow_by - preallocates space for n more contexts in s * @@ -256,13 +290,14 @@ static int tsync_works_grow_by(struct tsync_works *s, size_t n, gfp_t flags) * tsync_works_contains - checks for presence of task in s */ static bool tsync_works_contains_task(const struct tsync_works *s, - struct task_struct *task) + const struct task_struct *task) { size_t i; for (i = 0; i < s->size; i++) if (s->works[i]->task == task) return true; + return false; } @@ -276,7 +311,7 @@ static void tsync_works_release(struct tsync_works *s) size_t i; for (i = 0; i < s->size; i++) { - if (!s->works[i]->task) + if (WARN_ON_ONCE(!s->works[i]->task)) continue; put_task_struct(s->works[i]->task); @@ -284,6 +319,7 @@ static void tsync_works_release(struct tsync_works *s) for (i = 0; i < s->capacity; i++) kfree(s->works[i]); + kfree(s->works); s->works = NULL; s->size = 0; @@ -295,7 +331,7 @@ static void tsync_works_release(struct tsync_works *s) */ static size_t count_additional_threads(const struct tsync_works *works) { - struct task_struct *thread, *caller; + const struct task_struct *caller, *thread; size_t n = 0; caller = current; @@ -334,7 +370,8 @@ static bool schedule_task_work(struct tsync_works *works, struct tsync_shared_context *shared_ctx) { int err; - struct task_struct *thread, *caller; + const struct task_struct *caller; + struct task_struct *thread; struct tsync_work *ctx; bool found_more_threads = false; @@ -379,16 +416,14 @@ static bool schedule_task_work(struct tsync_works *works, init_task_work(&ctx->work, restrict_one_thread_callback); err = task_work_add(thread, &ctx->work, TWA_SIGNAL); - if (err) { + if (unlikely(err)) { /* * task_work_add() only fails if the task is about to exit. We * checked that earlier, but it can happen as a race. Resume * without setting an error, as the task is probably gone in the - * next loop iteration. For consistency, remove the task from ctx - * so that it does not look like we handed it a task_work. + * next loop iteration. */ - put_task_struct(ctx->task); - ctx->task = NULL; + tsync_works_trim(works); atomic_dec(&shared_ctx->num_preparing); atomic_dec(&shared_ctx->num_unfinished); @@ -406,12 +441,15 @@ static bool schedule_task_work(struct tsync_works *works, * shared_ctx->num_preparing and shared_ctx->num_unfished and mark the two * completions if needed, as if the task was never scheduled. */ -static void cancel_tsync_works(struct tsync_works *works, +static void cancel_tsync_works(const struct tsync_works *works, struct tsync_shared_context *shared_ctx) { - int i; + size_t i; for (i = 0; i < works->size; i++) { + if (WARN_ON_ONCE(!works->works[i]->task)) + continue; + if (!task_work_cancel(works->works[i]->task, &works->works[i]->work)) continue; @@ -448,6 +486,16 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred, shared_ctx.set_no_new_privs = task_no_new_privs(current); /* + * Serialize concurrent TSYNC operations to prevent deadlocks when + * multiple threads call landlock_restrict_self() simultaneously. + * If the lock is already held, we gracefully yield by restarting the + * syscall. This allows the current thread to process pending + * task_works before retrying. + */ + if (!down_write_trylock(¤t->signal->exec_update_lock)) + return restart_syscall(); + + /* * We schedule a pseudo-signal task_work for each of the calling task's * sibling threads. In the task work, each thread: * @@ -527,24 +575,30 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred, -ERESTARTNOINTR); /* - * Cancel task works for tasks that did not start running yet, - * and decrement all_prepared and num_unfinished accordingly. + * Opportunistic improvement: try to cancel task + * works for tasks that did not start running + * yet. We do not have a guarantee that it + * cancels any of the enqueued task works + * because task_work_run() might already have + * dequeued them. */ cancel_tsync_works(&works, &shared_ctx); /* - * The remaining task works have started running, so waiting for - * their completion will finish. + * Break the loop with error. The cleanup code + * after the loop unblocks the remaining + * task_works. */ - wait_for_completion(&shared_ctx.all_prepared); + break; } } } while (found_more_threads && !atomic_read(&shared_ctx.preparation_error)); /* - * We now have all sibling threads blocking and in "prepared" state in the - * task work. Ask all threads to commit. + * We now have either (a) all sibling threads blocking and in "prepared" + * state in the task work, or (b) the preparation error is set. Ask all + * threads to commit (or abort). */ complete_all(&shared_ctx.ready_to_commit); @@ -556,6 +610,6 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred, wait_for_completion(&shared_ctx.all_finished); tsync_works_release(&works); - + up_write(¤t->signal->exec_update_lock); return atomic_read(&shared_ctx.preparation_error); } diff --git a/security/security.c b/security/security.c index 67af9228c4e9..a26c1474e2e4 100644 --- a/security/security.c +++ b/security/security.c @@ -61,6 +61,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", + [LOCKDOWN_XEN_USER_ACTIONS] = "Xen guest user action", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index e97721f80f65..8e70da850fac 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -1164,7 +1164,7 @@ static void process_rx_packets(struct fw_iso_context *context, u32 tstamp, size_ struct pkt_desc *desc = s->packet_descs_cursor; unsigned int pkt_header_length; unsigned int packets; - u32 curr_cycle_time; + u32 curr_cycle_time = 0; bool need_hw_irq; int i; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index ab4b22fcb72e..6db23ce8a5fe 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -1017,12 +1017,30 @@ static int alc269_resume(struct hda_codec *codec) return 0; } -#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS 30 +#define ALC233_STARFIGHTER_SPK_PIN 0x1b +#define ALC233_STARFIGHTER_GPIO2 0x04 -static void starlabs_starfighter_shutup(struct hda_codec *codec) +static void alc233_starfighter_update_amp(struct hda_codec *codec, bool on) { - if (snd_hda_gen_shutup_speakers(codec)) - msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS); + snd_hda_codec_write(codec, ALC233_STARFIGHTER_SPK_PIN, 0, + AC_VERB_SET_EAPD_BTLENABLE, + on ? AC_EAPDBTL_EAPD : 0); + alc_update_gpio_data(codec, ALC233_STARFIGHTER_GPIO2, on); +} + +static void alc233_starfighter_pcm_hook(struct hda_pcm_stream *hinfo, + struct hda_codec *codec, + struct snd_pcm_substream *substream, + int action) +{ + switch (action) { + case HDA_GEN_PCM_ACT_PREPARE: + alc233_starfighter_update_amp(codec, true); + break; + case HDA_GEN_PCM_ACT_CLEANUP: + alc233_starfighter_update_amp(codec, false); + break; + } } static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec, @@ -1031,8 +1049,16 @@ static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec, { struct alc_spec *spec = codec->spec; - if (action == HDA_FIXUP_ACT_PRE_PROBE) - spec->shutup = starlabs_starfighter_shutup; + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->gpio_mask |= ALC233_STARFIGHTER_GPIO2; + spec->gpio_dir |= ALC233_STARFIGHTER_GPIO2; + spec->gpio_data &= ~ALC233_STARFIGHTER_GPIO2; + break; + case HDA_FIXUP_ACT_PROBE: + spec->gen.pcm_playback_hook = alc233_starfighter_pcm_hook; + break; + } } static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec, @@ -3699,22 +3725,42 @@ static void alc245_tas2781_spi_hp_fixup_muteled(struct hda_codec *codec, alc_fixup_hp_gpio_led(codec, action, 0x04, 0x0); alc285_fixup_hp_coef_micmute_led(codec, fix, action); } + +static void alc245_hp_spk_mute_led_update(void *private_data, int enabled) +{ + struct hda_codec *codec = private_data; + unsigned int val; + + val = enabled ? 0x08 : 0x04; /* 0x08 led on, 0x04 led off */ + alc_update_coef_idx(codec, 0x0b, 0x0c, val); +} + /* JD2: mute led GPIO3: micmute led */ static void alc245_tas2781_i2c_hp_fixup_muteled(struct hda_codec *codec, const struct hda_fixup *fix, int action) { struct alc_spec *spec = codec->spec; + hda_nid_t hp_pin = alc_get_hp_pin(spec); static const hda_nid_t conn[] = { 0x02 }; switch (action) { case HDA_FIXUP_ACT_PRE_PROBE: + if (!hp_pin) { + spec->gen.vmaster_mute.hook = alc245_hp_spk_mute_led_update; + spec->gen.vmaster_mute_led = 1; + } spec->gen.auto_mute_via_amp = 1; snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); break; + case HDA_FIXUP_ACT_INIT: + if (!hp_pin) + alc245_hp_spk_mute_led_update(codec, !spec->gen.master_mute); + break; } tas2781_fixup_txnw_i2c(codec, fix, action); - alc245_fixup_hp_mute_led_coefbit(codec, fix, action); + if (hp_pin) + alc245_fixup_hp_mute_led_coefbit(codec, fix, action); alc285_fixup_hp_coef_micmute_led(codec, fix, action); } /* @@ -4076,6 +4122,8 @@ enum { ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY, ALC245_FIXUP_BASS_HP_DAC, ALC245_FIXUP_ACER_MICMUTE_LED, + ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED, + ALC236_FIXUP_HP_DMIC, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -6605,6 +6653,19 @@ static const struct hda_fixup alc269_fixups[] = { .v.func = alc285_fixup_hp_coef_micmute_led, .chained = true, .chain_id = ALC2XX_FIXUP_HEADSET_MIC, + }, + [ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc245_fixup_hp_mute_led_coefbit, + .chained = true, + .chain_id = ALC287_FIXUP_CS35L41_I2C_2, + }, + [ALC236_FIXUP_HP_DMIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x12, 0x90a60160 }, /* use as internal mic */ + { } + }, } }; @@ -6659,6 +6720,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED), + SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), @@ -6854,6 +6916,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x8756, "HP ENVY Laptop 13-ba0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x8760, "HP EliteBook 8{4,5}5 G7", ALC285_FIXUP_HP_BEEP_MICMUTE_LED), SND_PCI_QUIRK(0x103c, 0x876e, "HP ENVY x360 Convertible 13-ay0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), @@ -6867,6 +6930,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87cb, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87cc, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87df, "HP ProBook 430 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -6954,6 +7018,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), + SND_PCI_QUIRK(0x103c, 0x8a3d, "HP Victus 15-fb0xxx (MB 8A3D)", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -7097,7 +7162,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8dc9, "HP Laptop 15-fc0xxx", ALC236_FIXUP_HP_DMIC), SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS), + SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2), SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED), @@ -7128,7 +7195,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8e60, "HP OmniBook 7 Laptop 16-bh0xxx", ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e8a, "HP NexusX", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), @@ -7177,6 +7244,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1194, "ASUS UM3406KA", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), + HDA_CODEC_QUIRK(0x1043, 0x1204, "ASUS Strix G16 G615JMR", ALC287_FIXUP_TXNW2781_I2C_ASUS), SND_PCI_QUIRK(0x1043, 0x1204, "ASUS Strix G615JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x1214, "ASUS Strix G615LH_LM_LP", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), @@ -7206,10 +7274,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x14f2, "ASUS VivoBook X515JA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1514, "ASUS ROG Flow Z13 GZ302EAC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1584, "ASUS UM3406GA ", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1602, "ASUS ROG Strix SCAR 15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -7349,6 +7419,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc1ac, "Samsung Galaxy Book2 Pro 360 (NP950QED)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS), SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP), @@ -7544,6 +7615,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I), + /* Yoga Pro 7 14IMH9 shares PCI SSID 17aa:3847 with Legion 7 16ACHG6; + * use codec SSID to distinguish them + */ + HDA_CODEC_QUIRK(0x17aa, 0x38cf, "Lenovo Yoga Pro 7 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3847, "Legion 7 16ACHG6", ALC287_FIXUP_LEGION_16ACHG6), SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -7575,6 +7650,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), HDA_CODEC_QUIRK(0x17aa, 0x391c, "Lenovo Yoga 7 2-in-1 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), + HDA_CODEC_QUIRK(0x17aa, 0x391d, "Lenovo Yoga 7 2-in-1 16AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b7, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2), @@ -7605,6 +7681,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), + SND_PCI_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3929, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), @@ -7698,6 +7775,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000f, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c index 3f434994c18d..8a7bd49e411f 100644 --- a/sound/hda/controllers/intel.c +++ b/sound/hda/controllers/intel.c @@ -2077,7 +2077,6 @@ static const struct pci_device_id driver_denylist[] = { { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */ - { PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */ {} }; @@ -2086,6 +2085,11 @@ static struct pci_device_id driver_denylist_ideapad_z570[] = { {} }; +static struct pci_device_id driver_denylist_msi_x870e[] = { + { PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */ + {} +}; + /* DMI-based denylist, to be used when: * - PCI subsystem IDs are zero, impossible to distinguish from valid sound cards. * - Different modifications of the same laptop use different GPU models. @@ -2099,6 +2103,14 @@ static const struct dmi_system_id driver_denylist_dmi[] = { }, .driver_data = &driver_denylist_ideapad_z570, }, + { + /* PCI device matching alone incorrectly matches some laptops */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "MAG X870E TOMAHAWK WIFI (MS-7E59)"), + }, + .driver_data = &driver_denylist_msi_x870e, + }, {} }; diff --git a/sound/pci/asihpi/hpimsgx.c b/sound/pci/asihpi/hpimsgx.c index b68e6bfbbfba..ed1c7b774436 100644 --- a/sound/pci/asihpi/hpimsgx.c +++ b/sound/pci/asihpi/hpimsgx.c @@ -581,8 +581,10 @@ static u16 adapter_prepare(u16 adapter) HPI_ADAPTER_OPEN); hm.adapter_index = adapter; hw_entry_point(&hm, &hr); - memcpy(&rESP_HPI_ADAPTER_OPEN[adapter], &hr, - sizeof(rESP_HPI_ADAPTER_OPEN[0])); + memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].h, &hr, + sizeof(rESP_HPI_ADAPTER_OPEN[adapter].h)); + memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].a, &hr.u.ax.info, + sizeof(rESP_HPI_ADAPTER_OPEN[adapter].a)); if (hr.error) return hr.error; diff --git a/sound/pci/ctxfi/ctatc.c b/sound/pci/ctxfi/ctatc.c index f122e396bc55..da2667cb2489 100644 --- a/sound/pci/ctxfi/ctatc.c +++ b/sound/pci/ctxfi/ctatc.c @@ -1427,10 +1427,14 @@ static int atc_get_resources(struct ct_atc *atc) daio_mgr = (struct daio_mgr *)atc->rsc_mgrs[DAIO]; da_desc.msr = atc->msr; for (i = 0; i < NUM_DAIOTYP; i++) { - if (((i == MIC) && !cap.dedicated_mic) || ((i == RCA) && !cap.dedicated_rca)) + if (((i == MIC) && !cap.dedicated_mic) || + ((i == RCA) && !cap.dedicated_rca) || + i == SPDIFI1) continue; - da_desc.type = (atc->model != CTSB073X) ? i : - ((i == SPDIFIO) ? SPDIFI1 : i); + if (atc->model == CTSB073X && i == SPDIFIO) + da_desc.type = SPDIFI1; + else + da_desc.type = i; da_desc.output = (i < LINEIM) || (i == RCA); err = daio_mgr->get_daio(daio_mgr, &da_desc, (struct daio **)&atc->daios[i]); diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c index b8bde27f3a1d..4dbb1dd7af32 100644 --- a/sound/pci/ctxfi/ctdaio.c +++ b/sound/pci/ctxfi/ctdaio.c @@ -99,7 +99,7 @@ static const struct rsc_ops daio_in_rsc_ops_20k2 = { .output_slot = daio_index, }; -static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw) +static int daio_device_index(enum DAIOTYP type, struct hw *hw) { switch (hw->chip_type) { case ATC20K1: @@ -112,12 +112,15 @@ static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw) case LINEO3: return 5; case LINEO4: return 6; case LINEIM: return 7; - default: return -EINVAL; + default: + pr_err("ctxfi: Invalid type %d for hw20k1\n", type); + return -EINVAL; } case ATC20K2: switch (type) { case SPDIFOO: return 0; case SPDIFIO: return 0; + case SPDIFI1: return 1; case LINEO1: return 4; case LINEO2: return 7; case LINEO3: return 5; @@ -125,9 +128,12 @@ static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw) case LINEIM: return 4; case MIC: return 5; case RCA: return 3; - default: return -EINVAL; + default: + pr_err("ctxfi: Invalid type %d for hw20k2\n", type); + return -EINVAL; } default: + pr_err("ctxfi: Invalid chip type %d\n", hw->chip_type); return -EINVAL; } } @@ -148,8 +154,11 @@ static int dao_spdif_set_spos(struct dao *dao, unsigned int spos) static int dao_commit_write(struct dao *dao) { - dao->hw->dao_commit_write(dao->hw, - daio_device_index(dao->daio.type, dao->hw), dao->ctrl_blk); + int idx = daio_device_index(dao->daio.type, dao->hw); + + if (idx < 0) + return idx; + dao->hw->dao_commit_write(dao->hw, idx, dao->ctrl_blk); return 0; } @@ -287,8 +296,11 @@ static int dai_set_enb_srt(struct dai *dai, unsigned int enb) static int dai_commit_write(struct dai *dai) { - dai->hw->dai_commit_write(dai->hw, - daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk); + int idx = daio_device_index(dai->daio.type, dai->hw); + + if (idx < 0) + return idx; + dai->hw->dai_commit_write(dai->hw, idx, dai->ctrl_blk); return 0; } @@ -367,7 +379,7 @@ static int dao_rsc_init(struct dao *dao, { struct hw *hw = mgr->mgr.hw; unsigned int conf; - int err; + int idx, err; err = daio_rsc_init(&dao->daio, desc, mgr->mgr.hw); if (err) @@ -386,15 +398,18 @@ static int dao_rsc_init(struct dao *dao, if (err) goto error2; - hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, - daio_device_index(dao->daio.type, hw)); + idx = daio_device_index(dao->daio.type, hw); + if (idx < 0) { + err = idx; + goto error2; + } + + hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx); hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk); conf = (desc->msr & 0x7) | (desc->passthru << 3); - hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk, - daio_device_index(dao->daio.type, hw), conf); - hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, - daio_device_index(dao->daio.type, hw)); + hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk, idx, conf); + hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx); hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk); return 0; @@ -443,7 +458,7 @@ static int dai_rsc_init(struct dai *dai, const struct daio_desc *desc, struct daio_mgr *mgr) { - int err; + int idx, err; struct hw *hw = mgr->mgr.hw; unsigned int rsr, msr; @@ -457,6 +472,12 @@ static int dai_rsc_init(struct dai *dai, if (err) goto error1; + idx = daio_device_index(dai->daio.type, dai->hw); + if (idx < 0) { + err = idx; + goto error1; + } + for (rsr = 0, msr = desc->msr; msr > 1; msr >>= 1) rsr++; @@ -465,8 +486,7 @@ static int dai_rsc_init(struct dai *dai, /* default to disabling control of a SRC */ hw->dai_srt_set_ec(dai->ctrl_blk, 0); hw->dai_srt_set_et(dai->ctrl_blk, 0); /* default to disabling SRT */ - hw->dai_commit_write(hw, - daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk); + hw->dai_commit_write(hw, idx, dai->ctrl_blk); return 0; @@ -581,28 +601,28 @@ static int put_daio_rsc(struct daio_mgr *mgr, struct daio *daio) static int daio_mgr_enb_daio(struct daio_mgr *mgr, struct daio *daio) { struct hw *hw = mgr->mgr.hw; - - if (daio->output) { - hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, - daio_device_index(daio->type, hw)); - } else { - hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk, - daio_device_index(daio->type, hw)); - } + int idx = daio_device_index(daio->type, hw); + + if (idx < 0) + return idx; + if (daio->output) + hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx); + else + hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk, idx); return 0; } static int daio_mgr_dsb_daio(struct daio_mgr *mgr, struct daio *daio) { struct hw *hw = mgr->mgr.hw; - - if (daio->output) { - hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, - daio_device_index(daio->type, hw)); - } else { - hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk, - daio_device_index(daio->type, hw)); - } + int idx = daio_device_index(daio->type, hw); + + if (idx < 0) + return idx; + if (daio->output) + hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx); + else + hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk, idx); return 0; } diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c index 365209ea53f3..1604ed679224 100644 --- a/sound/soc/amd/acp-config.c +++ b/sound/soc/amd/acp-config.c @@ -23,6 +23,16 @@ static int acp_quirk_data; +static const struct dmi_system_id acp70_acpi_flag_override_table[] = { + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"), + }, + }, + {} +}; + static const struct config_entry config_table[] = { { .flags = FLAG_AMD_SOF, @@ -186,8 +196,11 @@ int snd_amd_acp_find_config(struct pci_dev *pci) */ if (!pci->revision) return 0; - else if (pci->revision >= ACP_7_0_REV) + else if (pci->revision >= ACP_7_0_REV) { + if (dmi_check_system(acp70_acpi_flag_override_table)) + return 0; return snd_amd_acp_acpi_find_config(pci); + } for (i = 0; i < ARRAY_SIZE(config_table); i++, table++) { if (table->device != device) diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index c30ccf23005a..6388cd7cb28e 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -111,6 +111,14 @@ static const struct dmi_system_id soc_sdw_quirk_table[] = { }, .driver_data = (void *)(ASOC_SDW_CODEC_SPKR), }, + { + .callback = soc_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"), + }, + .driver_data = (void *)(ASOC_SDW_ACP_DMIC), + }, {} }; diff --git a/sound/soc/amd/acp/amd-acp70-acpi-match.c b/sound/soc/amd/acp/amd-acp70-acpi-match.c index 7a567ba02292..1ae43df5da6c 100644 --- a/sound/soc/amd/acp/amd-acp70-acpi-match.c +++ b/sound/soc/amd/acp/amd-acp70-acpi-match.c @@ -69,6 +69,28 @@ static const struct snd_soc_acpi_endpoint jack_amp_g1_dmic_endpoints[] = { }, }; +static const struct snd_soc_acpi_endpoint jack_dmic_endpoints[] = { + /* Jack Endpoint */ + { + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + /* DMIC Endpoint */ + { + /* + * rt721 endpoint #2 maps to AIF3 (internal DMIC capture). + * Endpoint #1 is AIF2 amp path and is handled by external amps + * on this platform. + */ + .num = 2, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, +}; + static const struct snd_soc_acpi_adr_device rt712_vb_1_group1_adr[] = { { .adr = 0x000130025D071201ull, @@ -563,6 +585,40 @@ static const struct snd_soc_acpi_link_adr acp70_rt1320_l0_rt722_l1[] = { {} }; +static const struct snd_soc_acpi_adr_device rt721_l1u0_tas2783x2_l1u8b_adr[] = { + { + .adr = 0x000130025D072101ull, + /* + * On this platform speakers are provided by two TAS2783 amps. + * Keep rt721 as UAJ + DMIC only. + */ + .num_endpoints = ARRAY_SIZE(jack_dmic_endpoints), + .endpoints = jack_dmic_endpoints, + .name_prefix = "rt721", + }, + { + .adr = 0x0001380102000001ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "tas2783-1", + }, + { + .adr = 0x00013B0102000001ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "tas2783-2", + }, +}; + +static const struct snd_soc_acpi_link_adr acp70_rt721_l1u0_tas2783x2_l1u8b[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt721_l1u0_tas2783x2_l1u8b_adr), + .adr_d = rt721_l1u0_tas2783x2_l1u8b_adr, + }, + {} +}; + struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = { { .link_mask = BIT(0) | BIT(1), @@ -650,6 +706,11 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = { .machine_check = snd_soc_acpi_amd_sdca_is_device_rt712_vb, .drv_name = "amd_sdw", }, + { + .link_mask = BIT(1), + .links = acp70_rt721_l1u0_tas2783x2_l1u8b, + .drv_name = "amd_sdw", + }, {}, }; EXPORT_SYMBOL(snd_soc_acpi_amd_acp70_sdw_machines); diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c index 3a20cc10d61f..9751cf0784a6 100644 --- a/sound/soc/amd/ps/pci-ps.c +++ b/sound/soc/amd/ps/pci-ps.c @@ -339,7 +339,7 @@ static struct snd_soc_acpi_mach *acp63_sdw_machine_select(struct device *dev) mach->mach_params.subsystem_device = acp_data->subsystem_device; mach->mach_params.subsystem_id_set = true; - dev_dbg(dev, "SSID %x%x\n", mach->mach_params.subsystem_vendor, + dev_dbg(dev, "SSID %x%04x\n", mach->mach_params.subsystem_vendor, mach->mach_params.subsystem_device); return mach; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 1324543b42d7..aa6200933182 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -48,6 +48,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15-fc0xxx"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5525"), } @@ -717,6 +724,27 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "BM1403CDA"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M7601RM"), + } + }, {} }; diff --git a/sound/soc/cirrus/ep93xx-i2s.c b/sound/soc/cirrus/ep93xx-i2s.c index cca01c03f048..5dba741594fa 100644 --- a/sound/soc/cirrus/ep93xx-i2s.c +++ b/sound/soc/cirrus/ep93xx-i2s.c @@ -91,16 +91,28 @@ static inline unsigned ep93xx_i2s_read_reg(struct ep93xx_i2s_info *info, return __raw_readl(info->regs + reg); } -static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream) +static int ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream) { unsigned base_reg; + int err; if ((ep93xx_i2s_read_reg(info, EP93XX_I2S_TX0EN) & 0x1) == 0 && (ep93xx_i2s_read_reg(info, EP93XX_I2S_RX0EN) & 0x1) == 0) { /* Enable clocks */ - clk_prepare_enable(info->mclk); - clk_prepare_enable(info->sclk); - clk_prepare_enable(info->lrclk); + err = clk_prepare_enable(info->mclk); + if (err) + return err; + err = clk_prepare_enable(info->sclk); + if (err) { + clk_disable_unprepare(info->mclk); + return err; + } + err = clk_prepare_enable(info->lrclk); + if (err) { + clk_disable_unprepare(info->sclk); + clk_disable_unprepare(info->mclk); + return err; + } /* Enable i2s */ ep93xx_i2s_write_reg(info, EP93XX_I2S_GLCTRL, 1); @@ -119,6 +131,8 @@ static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream) ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCTRL, EP93XX_I2S_TXCTRL_TXEMPTY_LVL | EP93XX_I2S_TXCTRL_TXUFIE); + + return 0; } static void ep93xx_i2s_disable(struct ep93xx_i2s_info *info, int stream) @@ -195,9 +209,7 @@ static int ep93xx_i2s_startup(struct snd_pcm_substream *substream, { struct ep93xx_i2s_info *info = snd_soc_dai_get_drvdata(dai); - ep93xx_i2s_enable(info, substream->stream); - - return 0; + return ep93xx_i2s_enable(info, substream->stream); } static void ep93xx_i2s_shutdown(struct snd_pcm_substream *substream, @@ -373,14 +385,16 @@ static int ep93xx_i2s_suspend(struct snd_soc_component *component) static int ep93xx_i2s_resume(struct snd_soc_component *component) { struct ep93xx_i2s_info *info = snd_soc_component_get_drvdata(component); + int err; if (!snd_soc_component_active(component)) return 0; - ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK); - ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE); + err = ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK); + if (err) + return err; - return 0; + return ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE); } #else #define ep93xx_i2s_suspend NULL diff --git a/sound/soc/codecs/adau1372.c b/sound/soc/codecs/adau1372.c index fdee689cae53..d7363f9d53bb 100644 --- a/sound/soc/codecs/adau1372.c +++ b/sound/soc/codecs/adau1372.c @@ -762,7 +762,7 @@ static int adau1372_startup(struct snd_pcm_substream *substream, struct snd_soc_ return 0; } -static void adau1372_enable_pll(struct adau1372 *adau1372) +static int adau1372_enable_pll(struct adau1372 *adau1372) { unsigned int val, timeout = 0; int ret; @@ -778,19 +778,26 @@ static void adau1372_enable_pll(struct adau1372 *adau1372) timeout++; } while (!(val & 1) && timeout < 3); - if (ret < 0 || !(val & 1)) + if (ret < 0 || !(val & 1)) { dev_err(adau1372->dev, "Failed to lock PLL\n"); + return ret < 0 ? ret : -ETIMEDOUT; + } + + return 0; } -static void adau1372_set_power(struct adau1372 *adau1372, bool enable) +static int adau1372_set_power(struct adau1372 *adau1372, bool enable) { if (adau1372->enabled == enable) - return; + return 0; if (enable) { unsigned int clk_ctrl = ADAU1372_CLK_CTRL_MCLK_EN; + int ret; - clk_prepare_enable(adau1372->mclk); + ret = clk_prepare_enable(adau1372->mclk); + if (ret) + return ret; if (adau1372->pd_gpio) gpiod_set_value(adau1372->pd_gpio, 0); @@ -804,7 +811,14 @@ static void adau1372_set_power(struct adau1372 *adau1372, bool enable) * accessed. */ if (adau1372->use_pll) { - adau1372_enable_pll(adau1372); + ret = adau1372_enable_pll(adau1372); + if (ret) { + regcache_cache_only(adau1372->regmap, true); + if (adau1372->pd_gpio) + gpiod_set_value(adau1372->pd_gpio, 1); + clk_disable_unprepare(adau1372->mclk); + return ret; + } clk_ctrl |= ADAU1372_CLK_CTRL_CLKSRC; } @@ -829,6 +843,8 @@ static void adau1372_set_power(struct adau1372 *adau1372, bool enable) } adau1372->enabled = enable; + + return 0; } static int adau1372_set_bias_level(struct snd_soc_component *component, @@ -842,11 +858,9 @@ static int adau1372_set_bias_level(struct snd_soc_component *component, case SND_SOC_BIAS_PREPARE: break; case SND_SOC_BIAS_STANDBY: - adau1372_set_power(adau1372, true); - break; + return adau1372_set_power(adau1372, true); case SND_SOC_BIAS_OFF: - adau1372_set_power(adau1372, false); - break; + return adau1372_set_power(adau1372, false); } return 0; diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c index 4bb59e5c0891..5850bf6e71ca 100644 --- a/sound/soc/codecs/sma1307.c +++ b/sound/soc/codecs/sma1307.c @@ -1759,8 +1759,10 @@ static void sma1307_setting_loaded(struct sma1307_priv *sma1307, const char *fil sma1307->set.mode_size * 2 * sizeof(int), GFP_KERNEL); if (!sma1307->set.mode_set[i]) { - for (int j = 0; j < i; j++) - kfree(sma1307->set.mode_set[j]); + for (int j = 0; j < i; j++) { + devm_kfree(sma1307->dev, sma1307->set.mode_set[j]); + sma1307->set.mode_set[j] = NULL; + } sma1307->set.status = false; return; } diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index 5798d518d94c..a1d86bd309f4 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -2550,6 +2550,9 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i) int k = i * (cali_data->cali_dat_sz_per_dev + 1); int rc; + if (!data || !cali_data->total_sz) + return; + if (data[k] != i) { dev_err(priv->dev, "%s: no cal-data for dev %d from usr-spc\n", __func__, i); diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index c8db33f78a1b..bc41a1466c70 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -2172,7 +2172,7 @@ static int wcd934x_init_dmic(struct snd_soc_component *comp) u32 def_dmic_rate, dmic_clk_drv; int ret; - ret = wcd_dt_parse_mbhc_data(comp->dev, &wcd->mbhc_cfg); + ret = wcd_dt_parse_micbias_info(&wcd->common); if (ret) return ret; diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 05b4e971a366..a4518fefad69 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -710,6 +710,8 @@ static int imx_card_parse_of(struct imx_card_data *data) link->ops = &imx_aif_ops; } + playback_only = false; + capture_only = false; graph_util_parse_link_direction(np, &playback_only, &capture_only); link->playback_only = playback_only; link->capture_only = capture_only; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 9e5be0eaa77f..89d694c2cbdd 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1183,9 +1183,9 @@ void graph_util_parse_link_direction(struct device_node *np, bool is_playback_only = of_property_read_bool(np, "playback-only"); bool is_capture_only = of_property_read_bool(np, "capture-only"); - if (np && playback_only) + if (playback_only && is_playback_only) *playback_only = is_playback_only; - if (np && capture_only) + if (capture_only && is_capture_only) *capture_only = is_capture_only; } EXPORT_SYMBOL_GPL(graph_util_parse_link_direction); diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index c5942b5655d3..d53af8f7e55b 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -530,8 +530,6 @@ config SND_SOC_INTEL_SOUNDWIRE_SOF_MACH select SND_SOC_CS42L43_SDW select MFD_CS42L43 select MFD_CS42L43_SDW - select PINCTRL_CS42L43 - select SPI_CS42L43 select SND_SOC_CS35L56_SPI select SND_SOC_CS35L56_SDW select SND_SOC_DMIC diff --git a/sound/soc/intel/boards/ehl_rt5660.c b/sound/soc/intel/boards/ehl_rt5660.c index 5c7b218f22b7..c40cd9fb1a26 100644 --- a/sound/soc/intel/boards/ehl_rt5660.c +++ b/sound/soc/intel/boards/ehl_rt5660.c @@ -127,7 +127,7 @@ static int rt5660_hw_params(struct snd_pcm_substream *substream, params_rate(params) * 50, params_rate(params) * 512); if (ret < 0) - dev_err(codec_dai->dev, "can't set codec pll: %d\n", ret); + dev_err(rtd->dev, "can't set codec pll: %d\n", ret); return ret; } diff --git a/sound/soc/intel/catpt/device.c b/sound/soc/intel/catpt/device.c index 0638aecba40d..0b3f20e384c7 100644 --- a/sound/soc/intel/catpt/device.c +++ b/sound/soc/intel/catpt/device.c @@ -281,7 +281,15 @@ static int catpt_acpi_probe(struct platform_device *pdev) if (IS_ERR(cdev->pci_ba)) return PTR_ERR(cdev->pci_ba); - /* alloc buffer for storing DRAM context during dx transitions */ + /* + * As per design HOST is responsible for preserving firmware's runtime + * context during D0 -> D3 -> D0 transitions. Addresses used for DMA + * to/from HOST memory shall be outside the reserved range of 0xFFFxxxxx. + */ + ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31)); + if (ret) + return ret; + cdev->dxbuf_vaddr = dmam_alloc_coherent(dev, catpt_dram_size(cdev), &cdev->dxbuf_paddr, GFP_KERNEL); if (!cdev->dxbuf_vaddr) diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c index 008a20a2acbd..677f348909c8 100644 --- a/sound/soc/intel/catpt/dsp.c +++ b/sound/soc/intel/catpt/dsp.c @@ -125,9 +125,6 @@ int catpt_dmac_probe(struct catpt_dev *cdev) dmac->dev = cdev->dev; dmac->irq = cdev->irq; - ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31)); - if (ret) - return ret; /* * Caller is responsible for putting device in D0 to allow * for I/O and memory access before probing DW. diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index e0ed593697ba..dca60ee8e62c 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -216,9 +216,6 @@ static int find_sdca_init_table(struct device *dev, } else if (num_init_writes % sizeof(*raw) != 0) { dev_err(dev, "%pfwP: init table size invalid\n", function_node); return -EINVAL; - } else if ((num_init_writes / sizeof(*raw)) > SDCA_MAX_INIT_COUNT) { - dev_err(dev, "%pfwP: maximum init table size exceeded\n", function_node); - return -EINVAL; } raw = kzalloc(num_init_writes, GFP_KERNEL); @@ -1604,10 +1601,19 @@ static int find_sdca_entities(struct device *dev, struct sdw_slave *sdw, static struct sdca_entity *find_sdca_entity_by_label(struct sdca_function_data *function, const char *entity_label) { + struct sdca_entity *entity = NULL; int i; for (i = 0; i < function->num_entities; i++) { - struct sdca_entity *entity = &function->entities[i]; + entity = &function->entities[i]; + + /* check whole string first*/ + if (!strcmp(entity->label, entity_label)) + return entity; + } + + for (i = 0; i < function->num_entities; i++) { + entity = &function->entities[i]; if (!strncmp(entity->label, entity_label, strlen(entity_label))) return entity; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 573693e21780..ff6eb6bfc63b 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2859,6 +2859,7 @@ int snd_soc_component_initialize(struct snd_soc_component *component, INIT_LIST_HEAD(&component->dobj_list); INIT_LIST_HEAD(&component->card_list); INIT_LIST_HEAD(&component->list); + INIT_LIST_HEAD(&component->card_aux_list); mutex_init(&component->io_mutex); if (!component->name) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index db077e9d5644..c12ffdcfe4e3 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -2950,7 +2950,7 @@ static int sof_ipc4_control_load_bytes(struct snd_sof_dev *sdev, struct snd_sof_ return -EINVAL; } - if (scontrol->priv_size < sizeof(struct sof_abi_hdr)) { + if (scontrol->priv_size && scontrol->priv_size < sizeof(struct sof_abi_hdr)) { dev_err(sdev->dev, "bytes control %s initial data size %zu is insufficient.\n", scontrol->name, scontrol->priv_size); diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 18e2401152c8..35200d801fb7 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -736,7 +736,7 @@ static int sof_parse_token_sets(struct snd_soc_component *scomp, asize = le32_to_cpu(array->size); /* validate asize */ - if (asize < 0) { /* FIXME: A zero-size array makes no sense */ + if (asize < sizeof(*array)) { dev_err(scomp->dev, "error: invalid array size 0x%x\n", asize); return -EINVAL; diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig index 9b890abd96d3..b4588915efa1 100644 --- a/sound/usb/Kconfig +++ b/sound/usb/Kconfig @@ -192,6 +192,7 @@ config SND_USB_AUDIO_QMI tristate "Qualcomm Audio Offload driver" depends on QCOM_QMI_HELPERS && SND_USB_AUDIO && SND_SOC_USB depends on USB_XHCI_HCD && USB_XHCI_SIDEBAND + select AUXILIARY_BUS help Say Y here to enable the Qualcomm USB audio offloading feature. diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index dfd820483849..3a71bab8a477 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -488,7 +488,7 @@ static int init_card(struct snd_usb_caiaqdev *cdev) memset(id, 0, sizeof(id)); for (c = card->shortname, len = 0; - *c && len < sizeof(card->id); c++) + *c && len < sizeof(card->id) - 1; c++) if (*c != ' ') id[len++] = *c; diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 510b68cced33..f161eb29f911 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include <linux/auxiliary_bus.h> diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 049a94079f9e..4cfa24c06fcd 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2148,6 +2148,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { /* Device matches */ DEVICE_FLG(0x001f, 0x0b21, /* AB13X USB Audio */ QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), + DEVICE_FLG(0x001f, 0x0b23, /* AB17X USB Audio */ + QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x0020, 0x0b21, /* GHW-123P */ QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x03f0, 0x654a, /* HP 320 FHD Webcam */ @@ -2303,6 +2305,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x13e5, 0x0001, /* Serato Phono */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x152a, 0x880a, /* NeuralDSP Quad Cortex */ + 0), /* Doesn't have the vendor quirk which would otherwise apply */ DEVICE_FLG(0x154e, 0x1002, /* Denon DCD-1500RE */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x154e, 0x1003, /* Denon DA-300USB */ @@ -2429,6 +2433,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY), VENDOR_FLG(0x07fd, /* MOTU */ QUIRK_FLAG_VALIDATE_RATES), + DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */ + DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */ + DEVICE_FLG(0x1235, 0x8016, 0), /* Focusrite Scarlett 2i2 1st Gen */ + DEVICE_FLG(0x1235, 0x801c, 0), /* Focusrite Scarlett Solo 1st Gen */ VENDOR_FLG(0x1235, /* Focusrite Novation */ QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_SKIP_IFACE_SETUP), diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index da5275d8eda6..6673601246b3 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -740,7 +740,10 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_SECURE_AVIC_BIT 18 #define MSR_AMD64_SNP_SECURE_AVIC BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT) -#define MSR_AMD64_SNP_RESV_BIT 19 +#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19) +#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT 23 +#define MSR_AMD64_SNP_IBPB_ON_ENTRY BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT) +#define MSR_AMD64_SNP_RESV_BIT 24 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_SAVIC_CONTROL 0xc0010138 #define MSR_AMD64_SAVIC_EN_BIT 0 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 846a63215ce1..0d4538fa6c31 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -476,6 +476,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9) +#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h index ab2aa97bd8ce..406923bd4846 100644 --- a/tools/include/linux/build_bug.h +++ b/tools/include/linux/build_bug.h @@ -32,7 +32,8 @@ /** * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied * error message. - * @condition: the condition which the compiler should know is false. + * @cond: the condition which the compiler should know is false. + * @msg: build-time error message * * See BUILD_BUG_ON for description. */ @@ -60,6 +61,7 @@ /** * static_assert - check integer constant expression at build time + * @expr: expression to be checked * * static_assert() is a wrapper for the C11 _Static_assert, with a * little macro magic to make the message optional (defaulting to the diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 65500f5db379..80364d4dbebb 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include <linux/ioctl.h> #include <asm/kvm.h> +#ifdef __KERNEL__ +#include <linux/kvm_types.h> +#endif + #define KVM_API_VERSION 12 /* @@ -1601,7 +1605,11 @@ struct kvm_stats_desc { __u16 size; __u32 offset; __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else char name[]; +#endif }; #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index da3aca87457f..31826621eebd 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -187,7 +187,6 @@ done check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check arch/x86/include/asm/amd/ibs.h '-I "^#include .*/msr-index.h"' -check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c index 43275d25b6cb..0f626db3a439 100644 --- a/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c @@ -4,9 +4,9 @@ #include "../kvm-stat.h" #include "../evsel.h" #include "../env.h" -#include "../../arch/x86/include/uapi/asm/svm.h" -#include "../../arch/x86/include/uapi/asm/vmx.h" -#include "../../arch/x86/include/uapi/asm/kvm.h" +#include "../../../arch/x86/include/uapi/asm/svm.h" +#include "../../../arch/x86/include/uapi/asm/vmx.h" +#include "../../../arch/x86/include/uapi/asm/kvm.h" #include <subcmd/parse-options.h> define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 46bf4dfeebc8..7e39d469111b 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1605,9 +1605,9 @@ bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_gr .metric_or_groups = metric_or_groups, }; - return pmu_metrics_table__for_each_metric(table, - metricgroup__has_metric_or_groups_callback, - &data) + return metricgroup__for_each_metric(table, + metricgroup__has_metric_or_groups_callback, + &data) ? true : false; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index b9efb296bba5..7b4629625b1e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1117,7 +1117,7 @@ static int config_attr(struct perf_event_attr *attr, static struct evsel_config_term *add_config_term(enum evsel_term_type type, struct list_head *head_terms, - bool weak) + bool weak, char *str, u64 val) { struct evsel_config_term *t; @@ -1128,8 +1128,62 @@ static struct evsel_config_term *add_config_term(enum evsel_term_type type, INIT_LIST_HEAD(&t->list); t->type = type; t->weak = weak; - list_add_tail(&t->list, head_terms); + switch (type) { + case EVSEL__CONFIG_TERM_PERIOD: + case EVSEL__CONFIG_TERM_FREQ: + case EVSEL__CONFIG_TERM_STACK_USER: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG1: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG2: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG3: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG4: + t->val.val = val; + break; + case EVSEL__CONFIG_TERM_TIME: + t->val.time = val; + break; + case EVSEL__CONFIG_TERM_INHERIT: + t->val.inherit = val; + break; + case EVSEL__CONFIG_TERM_OVERWRITE: + t->val.overwrite = val; + break; + case EVSEL__CONFIG_TERM_MAX_STACK: + t->val.max_stack = val; + break; + case EVSEL__CONFIG_TERM_MAX_EVENTS: + t->val.max_events = val; + break; + case EVSEL__CONFIG_TERM_PERCORE: + t->val.percore = val; + break; + case EVSEL__CONFIG_TERM_AUX_OUTPUT: + t->val.aux_output = val; + break; + case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: + t->val.aux_sample_size = val; + break; + case EVSEL__CONFIG_TERM_CALLGRAPH: + case EVSEL__CONFIG_TERM_BRANCH: + case EVSEL__CONFIG_TERM_DRV_CFG: + case EVSEL__CONFIG_TERM_RATIO_TO_PREV: + case EVSEL__CONFIG_TERM_AUX_ACTION: + if (str) { + t->val.str = strdup(str); + if (!t->val.str) { + zfree(&t); + return NULL; + } + t->free_str = true; + } + break; + default: + t->val.val = val; + break; + } + + list_add_tail(&t->list, head_terms); return t; } @@ -1142,7 +1196,7 @@ static int get_config_terms(const struct parse_events_terms *head_config, struct evsel_config_term *new_term; enum evsel_term_type new_type; bool str_type = false; - u64 val; + u64 val = 0; switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: @@ -1234,20 +1288,15 @@ static int get_config_terms(const struct parse_events_terms *head_config, continue; } - new_term = add_config_term(new_type, head_terms, term->weak); + /* + * Note: Members evsel_config_term::val and + * parse_events_term::val are unions and endianness needs + * to be taken into account when changing such union members. + */ + new_term = add_config_term(new_type, head_terms, term->weak, + str_type ? term->val.str : NULL, val); if (!new_term) return -ENOMEM; - - if (str_type) { - new_term->val.str = strdup(term->val.str); - if (!new_term->val.str) { - zfree(&new_term); - return -ENOMEM; - } - new_term->free_str = true; - } else { - new_term->val.val = val; - } } return 0; } @@ -1277,10 +1326,9 @@ static int add_cfg_chg(const struct perf_pmu *pmu, if (bits) { struct evsel_config_term *new_term; - new_term = add_config_term(new_term_type, head_terms, false); + new_term = add_config_term(new_term_type, head_terms, false, NULL, bits); if (!new_term) return -ENOMEM; - new_term->val.cfg_chg = bits; } return 0; diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 1fe090cd6744..4794903aec8e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -5,6 +5,13 @@ #include "../../../include/linux/filter.h" #include "bpf_misc.h" +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} precision_map SEC(".maps"); + SEC("?raw_tp") __success __log_level(2) __msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10") @@ -301,4 +308,338 @@ __naked int bpf_neg_5(void) ::: __clobber_all); } +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_fetch_add_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[fetch_add_insn];" /* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(fetch_add_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_xchg((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_xchg_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[xchg_insn];" /* r2 = atomic_xchg(*(u64 *)(r10 - 8), r2) */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(xchg_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_or((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_fetch_or_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[fetch_or_insn];" /* r2 = atomic_fetch_or(*(u64 *)(r10 - 8), r2) */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(fetch_or_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_OR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_and((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_fetch_and_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[fetch_and_insn];" /* r2 = atomic_fetch_and(*(u64 *)(r10 - 8), r2) */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(fetch_and_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_xor((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_fetch_xor_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[fetch_xor_insn];" /* r2 = atomic_fetch_xor(*(u64 *)(r10 - 8), r2) */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(fetch_xor_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_XOR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_cmpxchg_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r0 = 0;" + "r2 = 0;" + ".8byte %[cmpxchg_insn];" /* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */ + "r3 = r10;" + "r3 += r0;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(cmpxchg_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +/* Regression test for dual precision: Both the fetched value (r2) and + * a reread of the same stack slot (r3) are tracked for precision. After + * the atomic operation, the stack slot is STACK_MISC. Thus, the ldx at + * insn 4 does NOT set INSN_F_STACK_ACCESS. Precision for the stack slot + * propagates solely through the atomic fetch's load side (insn 3). + */ +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2,r3 stack= before 4: (79) r3 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_fetch_add_dual_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = 0;" + ".8byte %[fetch_add_insn];" /* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */ + "r3 = *(u64 *)(r10 - 8);" + "r4 = r2;" + "r4 += r3;" + "r4 &= 7;" + "r5 = r10;" + "r5 += r4;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(fetch_add_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r0,r3 stack= before 5: (79) r3 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 8") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_atomic_cmpxchg_dual_precision(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + "r0 = 8;" + "r2 = 0;" + ".8byte %[cmpxchg_insn];" /* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */ + "r3 = *(u64 *)(r10 - 8);" + "r4 = r0;" + "r4 += r3;" + "r4 &= 7;" + "r5 = r10;" + "r5 += r4;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(cmpxchg_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7") +__msg("mark_precise: frame0: regs=r1 stack= before 9: (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)") +__not_msg("falling back to forcing all scalars precise") +__naked int bpf_atomic_fetch_add_map_precision(void) +{ + asm volatile ( + "r1 = 0;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = r10;" + "r2 += -8;" + "r1 = %[precision_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto 1f;" + "r1 = 0;" + ".8byte %[fetch_add_insn];" /* r1 = atomic_fetch_add(*(u64 *)(r0 + 0), r1) */ + "r1 &= 7;" + "r2 = r10;" + "r2 += r1;" /* mark_precise */ + "1: r0 = 0;" + "exit;" + : + : __imm_addr(precision_map), + __imm(bpf_map_lookup_elem), + __imm_insn(fetch_add_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (db) r0 = atomic64_cmpxchg((u64 *)(r6 +0), r0, r1)") +__not_msg("falling back to forcing all scalars precise") +__naked int bpf_atomic_cmpxchg_map_precision(void) +{ + asm volatile ( + "r1 = 0;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = r10;" + "r2 += -8;" + "r1 = %[precision_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto 1f;" + "r6 = r0;" + "r0 = 0;" + "r1 = 0;" + ".8byte %[cmpxchg_insn];" /* r0 = atomic_cmpxchg(*(u64 *)(r6 + 0), r0, r1) */ + "r0 &= 7;" + "r2 = r10;" + "r2 += r0;" /* mark_precise */ + "1: r0 = 0;" + "exit;" + : + : __imm_addr(precision_map), + __imm(bpf_map_lookup_elem), + __imm_insn(cmpxchg_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7") +__msg("mark_precise: frame0: regs=r1 stack= before 9: (c3) r1 = atomic_fetch_add((u32 *)(r0 +0), r1)") +__not_msg("falling back to forcing all scalars precise") +__naked int bpf_atomic_fetch_add_32bit_precision(void) +{ + asm volatile ( + "r1 = 0;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = r10;" + "r2 += -8;" + "r1 = %[precision_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto 1f;" + "r1 = 0;" + ".8byte %[fetch_add_insn];" /* r1 = atomic_fetch_add(*(u32 *)(r0 + 0), r1) */ + "r1 &= 7;" + "r2 = r10;" + "r2 += r1;" /* mark_precise */ + "1: r0 = 0;" + "exit;" + : + : __imm_addr(precision_map), + __imm(bpf_map_lookup_elem), + __imm_insn(fetch_add_insn, + BPF_ATOMIC_OP(BPF_W, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (c3) r0 = atomic_cmpxchg((u32 *)(r6 +0), r0, r1)") +__not_msg("falling back to forcing all scalars precise") +__naked int bpf_atomic_cmpxchg_32bit_precision(void) +{ + asm volatile ( + "r1 = 0;" + "*(u64 *)(r10 - 8) = r1;" + "r2 = r10;" + "r2 += -8;" + "r1 = %[precision_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto 1f;" + "r6 = r0;" + "r0 = 0;" + "r1 = 0;" + ".8byte %[cmpxchg_insn];" /* r0 = atomic_cmpxchg(*(u32 *)(r6 + 0), r0, r1) */ + "r0 &= 7;" + "r2 = r10;" + "r2 += r0;" /* mark_precise */ + "1: r0 = 0;" + "exit;" + : + : __imm_addr(precision_map), + __imm(bpf_map_lookup_elem), + __imm_insn(cmpxchg_insn, + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c index ce6c2642fd9b..6a7295347e90 100644 --- a/tools/testing/selftests/cgroup/lib/cgroup_util.c +++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c @@ -123,6 +123,21 @@ int cg_read_strcmp(const char *cgroup, const char *control, return ret; } +int cg_read_strcmp_wait(const char *cgroup, const char *control, + const char *expected) +{ + int i, ret; + + for (i = 0; i < 100; i++) { + ret = cg_read_strcmp(cgroup, control, expected); + if (!ret) + return ret; + usleep(10000); + } + + return ret; +} + int cg_read_strstr(const char *cgroup, const char *control, const char *needle) { char buf[PAGE_SIZE]; diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h index 77f386dab5e8..567b1082974c 100644 --- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h +++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h @@ -61,6 +61,8 @@ extern int cg_read(const char *cgroup, const char *control, char *buf, size_t len); extern int cg_read_strcmp(const char *cgroup, const char *control, const char *expected); +extern int cg_read_strcmp_wait(const char *cgroup, const char *control, + const char *expected); extern int cg_read_strstr(const char *cgroup, const char *control, const char *needle); extern long cg_read_long(const char *cgroup, const char *control); diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 102262555a59..7b83c7e7c9d4 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -233,7 +233,8 @@ static int test_cgcore_populated(const char *root) if (err) goto cleanup; - if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n")) + if (cg_read_strcmp_wait(cg_test_d, "cgroup.events", + "populated 0\n")) goto cleanup; /* Remove cgroup. */ diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index c8c9d306925b..f6cd23a8ecc7 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -86,7 +86,7 @@ cleanup: wait_for_pid(pids[i]); if (ret == KSFT_PASS && - cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n")) + cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n")) ret = KSFT_FAIL; if (cgroup) @@ -190,7 +190,8 @@ cleanup: wait_for_pid(pids[i]); if (ret == KSFT_PASS && - cg_read_strcmp(cgroup[0], "cgroup.events", "populated 0\n")) + cg_read_strcmp_wait(cgroup[0], "cgroup.events", + "populated 0\n")) ret = KSFT_FAIL; for (i = 9; i >= 0 && cgroup[i]; i--) { @@ -251,7 +252,7 @@ cleanup: wait_for_pid(pid); if (ret == KSFT_PASS && - cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n")) + cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n")) ret = KSFT_FAIL; if (cgroup) diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 45a3e7ad3dcb..02d6f51d5a06 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -3,6 +3,7 @@ TEST_PROGS := \ dev_addr_lists.sh \ + non_ether_header_ops.sh \ options.sh \ propagation.sh \ refleak.sh \ diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 558e1d0cf565..5d36a22ef080 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,7 +1,9 @@ +CONFIG_BONDING=y CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y CONFIG_NETDEVSIM=m +CONFIG_NET_IPGRE=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y diff --git a/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh new file mode 100755 index 000000000000..948a43576bdc --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2154 +# +# Reproduce the non-Ethernet header_ops confusion scenario with: +# g0 (gre) -> b0 (bond) -> t0 (team) +# +# Before the fix, direct header_ops inheritance in this stack could call +# callbacks with the wrong net_device context and crash. + +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/lib.sh + +trap cleanup_all_ns EXIT + +setup_ns ns1 + +ip -n "$ns1" link add d0 type dummy +ip -n "$ns1" addr add 10.10.10.1/24 dev d0 +ip -n "$ns1" link set d0 up + +ip -n "$ns1" link add g0 type gre local 10.10.10.1 +ip -n "$ns1" link add b0 type bond mode active-backup +ip -n "$ns1" link add t0 type team + +ip -n "$ns1" link set g0 master b0 +ip -n "$ns1" link set b0 master t0 + +ip -n "$ns1" link set g0 up +ip -n "$ns1" link set b0 up +ip -n "$ns1" link set t0 up + +# IPv6 address assignment triggers MLD join reports that call +# dev_hard_header() on t0, exercising the inherited header_ops path. +ip -n "$ns1" -6 addr add 2001:db8:1::1/64 dev t0 nodad +for i in $(seq 1 20); do + ip netns exec "$ns1" ping -6 -I t0 ff02::1 -c1 -W1 &>/dev/null || true +done + +echo "PASS: non-Ethernet header_ops stacking did not crash" +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index dc68371f76a3..6471fa214a9f 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -206,6 +206,7 @@ TEST_GEN_PROGS_s390 += s390/ucontrol_test TEST_GEN_PROGS_s390 += s390/user_operexec TEST_GEN_PROGS_s390 += s390/keyop TEST_GEN_PROGS_s390 += rseq_test +TEST_GEN_PROGS_s390 += s390/irq_routing TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test diff --git a/tools/testing/selftests/kvm/s390/irq_routing.c b/tools/testing/selftests/kvm/s390/irq_routing.c new file mode 100644 index 000000000000..7819a0af19a8 --- /dev/null +++ b/tools/testing/selftests/kvm/s390/irq_routing.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * IRQ routing offset tests. + * + * Copyright IBM Corp. 2026 + * + * Authors: + * Janosch Frank <frankja@linux.ibm.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "kselftest.h" +#include "ucall_common.h" + +extern char guest_code[]; +asm("guest_code:\n" + "diag %r0,%r0,0\n" + "j .\n"); + +static void test(void) +{ + struct kvm_irq_routing *routing; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + vm_paddr_t mem; + int ret; + + struct kvm_irq_routing_entry ue = { + .type = KVM_IRQ_ROUTING_S390_ADAPTER, + .gsi = 1, + }; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + mem = vm_phy_pages_alloc(vm, 2, 4096 * 42, 0); + + routing = kvm_gsi_routing_create(); + routing->nr = 1; + routing->entries[0] = ue; + routing->entries[0].u.adapter.summary_addr = (uintptr_t)mem; + routing->entries[0].u.adapter.ind_addr = (uintptr_t)mem; + + routing->entries[0].u.adapter.summary_offset = 4096 * 8; + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); + ksft_test_result(ret == -1 && errno == EINVAL, "summary offset outside of page\n"); + + routing->entries[0].u.adapter.summary_offset -= 4; + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); + ksft_test_result(ret == 0, "summary offset inside of page\n"); + + routing->entries[0].u.adapter.ind_offset = 4096 * 8; + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); + ksft_test_result(ret == -1 && errno == EINVAL, "ind offset outside of page\n"); + + routing->entries[0].u.adapter.ind_offset -= 4; + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); + ksft_test_result(ret == 0, "ind offset inside of page\n"); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_IRQ_ROUTING)); + + ksft_print_header(); + ksft_set_plan(4); + test(); + + ksft_finished(); /* Print results and exit() accordingly */ +} diff --git a/tools/testing/selftests/landlock/tsync_test.c b/tools/testing/selftests/landlock/tsync_test.c index 37ef0d2270db..2b9ad4f154f4 100644 --- a/tools/testing/selftests/landlock/tsync_test.c +++ b/tools/testing/selftests/landlock/tsync_test.c @@ -6,9 +6,10 @@ */ #define _GNU_SOURCE +#include <linux/landlock.h> #include <pthread.h> +#include <signal.h> #include <sys/prctl.h> -#include <linux/landlock.h> #include "common.h" @@ -158,4 +159,92 @@ TEST(competing_enablement) EXPECT_EQ(0, close(ruleset_fd)); } +static void signal_nop_handler(int sig) +{ +} + +struct signaler_data { + pthread_t target; + volatile bool stop; +}; + +static void *signaler_thread(void *data) +{ + struct signaler_data *sd = data; + + while (!sd->stop) + pthread_kill(sd->target, SIGUSR1); + + return NULL; +} + +/* + * Number of idle sibling threads. This must be large enough that even on + * machines with many cores, the sibling threads cannot all complete their + * credential preparation in a single parallel wave, otherwise the signaler + * thread has no window to interrupt wait_for_completion_interruptible(). + * 200 threads on a 64-core machine yields ~3 serialized waves, giving the + * tight signal loop enough time to land an interruption. + */ +#define NUM_IDLE_THREADS 200 + +/* + * Exercises the tsync interruption and cancellation paths in tsync.c. + * + * When a signal interrupts the calling thread while it waits for sibling + * threads to finish their credential preparation + * (wait_for_completion_interruptible in landlock_restrict_sibling_threads), + * the kernel sets ERESTARTNOINTR, cancels queued task works that have not + * started yet (cancel_tsync_works), then waits for the remaining works to + * finish. On the error return, syscalls.c aborts the prepared credentials. + * The kernel automatically restarts the syscall, so userspace sees success. + */ +TEST(tsync_interrupt) +{ + size_t i; + pthread_t threads[NUM_IDLE_THREADS]; + pthread_t signaler; + struct signaler_data sd; + struct sigaction sa = {}; + const int ruleset_fd = create_ruleset(_metadata); + + disable_caps(_metadata); + + /* Install a no-op SIGUSR1 handler so the signal does not kill us. */ + sa.sa_handler = signal_nop_handler; + sigemptyset(&sa.sa_mask); + ASSERT_EQ(0, sigaction(SIGUSR1, &sa, NULL)); + + ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); + + for (i = 0; i < NUM_IDLE_THREADS; i++) + ASSERT_EQ(0, pthread_create(&threads[i], NULL, idle, NULL)); + + /* + * Start a signaler thread that continuously sends SIGUSR1 to the + * calling thread. This maximizes the chance of interrupting + * wait_for_completion_interruptible() in the kernel's tsync path. + */ + sd.target = pthread_self(); + sd.stop = false; + ASSERT_EQ(0, pthread_create(&signaler, NULL, signaler_thread, &sd)); + + /* + * The syscall may be interrupted and transparently restarted by the + * kernel (ERESTARTNOINTR). From userspace, it should always succeed. + */ + EXPECT_EQ(0, landlock_restrict_self(ruleset_fd, + LANDLOCK_RESTRICT_SELF_TSYNC)); + + sd.stop = true; + ASSERT_EQ(0, pthread_join(signaler, NULL)); + + for (i = 0; i < NUM_IDLE_THREADS; i++) { + ASSERT_EQ(0, pthread_cancel(threads[i])); + ASSERT_EQ(0, pthread_join(threads[i], NULL)); + } + + EXPECT_EQ(0, close(ruleset_fd)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 7aec3ae82a44..c6dafb3cc116 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1020,7 +1020,7 @@ FIXTURE_SETUP(mount_setattr_idmapped) "size=100000,mode=700"), 0); ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, - "size=2m,mode=700"), 0); + "size=256m,mode=700"), 0); ASSERT_EQ(mkdir("/mnt/A", 0777), 0); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index c5694cc4ddd2..829f72c8ee07 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -868,6 +868,64 @@ fib6_gc_test() check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with permanent)" + # Delete dummy_10 and remove all routes + $IP link del dev dummy_10 + + # rd6 is required for the next test. (ipv6toolkit) + if [ ! -x "$(command -v rd6)" ]; then + echo "SKIP: rd6 not found." + set +e + cleanup &> /dev/null + return + fi + + setup_ns ns2 + $IP link add veth1 type veth peer veth2 netns $ns2 + $IP link set veth1 up + ip -netns $ns2 link set veth2 up + $IP addr add fe80:dead::1/64 dev veth1 + ip -netns $ns2 addr add fe80:dead::2/64 dev veth2 + + # Add NTF_ROUTER neighbour to prevent rt6_age_examine_exception() + # from removing not-yet-expired exceptions. + ip -netns $ns2 link set veth2 address 00:11:22:33:44:55 + $IP neigh add fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router + + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_redirects=1 + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.forwarding=0 + + # Temporary routes + for i in $(seq 1 5); do + # Expire route after $EXPIRE seconds + $IP -6 route add 2001:10::$i \ + via fe80:dead::2 dev veth1 expires $EXPIRE + + ip netns exec $ns2 rd6 -i veth2 \ + -s fe80:dead::2 -d fe80:dead::1 \ + -r 2001:10::$i -t fe80:dead::3 -p ICMP6 + done + + check_rt_num 5 $($IP -6 route list | grep expires | grep 2001:10:: | wc -l) + + # Promote to permanent routes by "prepend" (w/o NLM_F_EXCL and NLM_F_REPLACE) + for i in $(seq 1 5); do + # -EEXIST, but the temporary route becomes the permanent route. + $IP -6 route append 2001:10::$i \ + via fe80:dead::2 dev veth1 2>/dev/null || true + done + + check_rt_num 5 $($IP -6 route list | grep -v expires | grep 2001:10:: | wc -l) + check_rt_num 5 $($IP -6 route list cache | grep 2001:10:: | wc -l) + + # Trigger GC instead of waiting $GC_WAIT_TIME. + # rt6_nh_dump_exceptions() just skips expired exceptions. + $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + check_rt_num 0 $($IP -6 route list cache | grep 2001:10:: | wc -l) + log_test $ret 0 "ipv6 route garbage collection (promote to permanent routes)" + + $IP neigh del fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router + $IP link del veth1 + # ra6 is required for the next test. (ipv6toolkit) if [ ! -x "$(command -v ra6)" ]; then echo "SKIP: ra6 not found." @@ -876,9 +934,6 @@ fib6_gc_test() return fi - # Delete dummy_10 and remove all routes - $IP link del dev dummy_10 - # Create a pair of veth devices to send a RA message from one # device to another. $IP link add veth1 type veth peer name veth2 diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh index 394166f224a4..ffdc6ccc6511 100755 --- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh @@ -29,7 +29,8 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate insert_overlap" +BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate + insert_overlap load_flush_load4 load_flush_load8" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -432,6 +433,30 @@ race_repeat 0 perf_duration 0 " +TYPE_load_flush_load4=" +display reload with flush, 4bit groups +type_spec ipv4_addr . ipv4_addr +chain_spec ip saddr . ip daddr +dst addr4 +proto icmp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_load_flush_load8=" +display reload with flush, 8bit groups +type_spec ipv4_addr . ipv4_addr +chain_spec ip saddr . ip daddr +dst addr4 +proto icmp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1997,6 +2022,49 @@ test_bug_insert_overlap() return 0 } +test_bug_load_flush_load4() +{ + local i + + setup veth send_"${proto}" set || return ${ksft_skip} + + for i in $(seq 0 255); do + local addelem="add element inet filter test" + local j + + for j in $(seq 0 20); do + echo "$addelem { 10.$j.0.$i . 10.$j.1.$i }" + echo "$addelem { 10.$j.0.$i . 10.$j.2.$i }" + done + done > "$tmp" + + nft -f "$tmp" || return 1 + + ( echo "flush set inet filter test";cat "$tmp") | nft -f - + [ $? -eq 0 ] || return 1 + + return 0 +} + +test_bug_load_flush_load8() +{ + local i + + setup veth send_"${proto}" set || return ${ksft_skip} + + for i in $(seq 1 100); do + echo "add element inet filter test { 10.0.0.$i . 10.0.1.$i }" + echo "add element inet filter test { 10.0.0.$i . 10.0.2.$i }" + done > "$tmp" + + nft -f "$tmp" || return 1 + + ( echo "flush set inet filter test";cat "$tmp") | nft -f - + [ $? -eq 0 ] || return 1 + + return 0 +} + test_reported_issues() { eval test_bug_"${subtest}" } diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 006300ac6dff..1c9ca328cca1 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -188,6 +188,7 @@ auto-test-targets := \ rt_stall \ test_example \ total_bw \ + cyclic_kick_wait \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c new file mode 100644 index 000000000000..cb34d3335917 --- /dev/null +++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock. + * + * Three CPUs are designated from userspace. Every enqueue from one of the + * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a + * persistent A -> B -> C -> A wait cycle pressure. + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +const volatile s32 test_cpu_a; +const volatile s32 test_cpu_b; +const volatile s32 test_cpu_c; + +u64 nr_enqueues; +u64 nr_wait_kicks; + +UEI_DEFINE(uei); + +static s32 target_cpu(s32 cpu) +{ + if (cpu == test_cpu_a) + return test_cpu_b; + if (cpu == test_cpu_b) + return test_cpu_c; + if (cpu == test_cpu_c) + return test_cpu_a; + return -1; +} + +void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p, + u64 enq_flags) +{ + s32 this_cpu = bpf_get_smp_processor_id(); + s32 tgt; + + __sync_fetch_and_add(&nr_enqueues, 1); + + if (p->flags & PF_KTHREAD) { + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF, + enq_flags | SCX_ENQ_PREEMPT); + return; + } + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + + tgt = target_cpu(this_cpu); + if (tgt < 0 || tgt == this_cpu) + return; + + __sync_fetch_and_add(&nr_wait_kicks, 1); + scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT); +} + +void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops cyclic_kick_wait_ops = { + .enqueue = cyclic_kick_wait_enqueue, + .exit = cyclic_kick_wait_exit, + .name = "cyclic_kick_wait", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c new file mode 100644 index 000000000000..c2e5aa9de715 --- /dev/null +++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Test SCX_KICK_WAIT forward progress under cyclic wait pressure. + * + * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path. + * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits + * for A), all CPUs deadlock unless the implementation breaks the cycle. + * + * This test creates that scenario: three CPUs are arranged in a ring. The BPF + * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT + * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling + * sched_yield(), generating a steady stream of enqueues and thus sustained + * A->B->C->A kick_wait cycle pressure. The test passes if the system remains + * responsive for 5 seconds without the scheduler being killed by the watchdog. + */ +#define _GNU_SOURCE + +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <sched.h> +#include <scx/common.h> +#include <stdint.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +#include "scx_test.h" +#include "cyclic_kick_wait.bpf.skel.h" + +#define WORKERS_PER_CPU 4 +#define NR_TEST_CPUS 3 +#define NR_WORKERS (NR_TEST_CPUS * WORKERS_PER_CPU) + +struct worker_ctx { + pthread_t tid; + int cpu; + volatile bool stop; + volatile __u64 iters; + bool started; +}; + +static void *worker_fn(void *arg) +{ + struct worker_ctx *worker = arg; + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(worker->cpu, &mask); + + if (sched_setaffinity(0, sizeof(mask), &mask)) + return (void *)(uintptr_t)errno; + + while (!worker->stop) { + sched_yield(); + worker->iters++; + } + + return NULL; +} + +static int join_worker(struct worker_ctx *worker) +{ + void *ret; + struct timespec ts; + int err; + + if (!worker->started) + return 0; + + if (clock_gettime(CLOCK_REALTIME, &ts)) + return -errno; + + ts.tv_sec += 2; + err = pthread_timedjoin_np(worker->tid, &ret, &ts); + if (err == ETIMEDOUT) + pthread_detach(worker->tid); + if (err) + return -err; + + if ((uintptr_t)ret) + return -(int)(uintptr_t)ret; + + return 0; +} + +static enum scx_test_status setup(void **ctx) +{ + struct cyclic_kick_wait *skel; + + skel = cyclic_kick_wait__open(); + SCX_FAIL_IF(!skel, "Failed to open skel"); + SCX_ENUM_INIT(skel); + + *ctx = skel; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct cyclic_kick_wait *skel = ctx; + struct worker_ctx workers[NR_WORKERS] = {}; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_PASS; + int test_cpus[NR_TEST_CPUS]; + int nr_cpus = 0; + cpu_set_t mask; + int ret, i; + + if (sched_getaffinity(0, sizeof(mask), &mask)) { + SCX_ERR("Failed to get affinity (%d)", errno); + return SCX_TEST_FAIL; + } + + for (i = 0; i < CPU_SETSIZE; i++) { + if (CPU_ISSET(i, &mask)) + test_cpus[nr_cpus++] = i; + if (nr_cpus == NR_TEST_CPUS) + break; + } + + if (nr_cpus < NR_TEST_CPUS) + return SCX_TEST_SKIP; + + skel->rodata->test_cpu_a = test_cpus[0]; + skel->rodata->test_cpu_b = test_cpus[1]; + skel->rodata->test_cpu_c = test_cpus[2]; + + if (cyclic_kick_wait__load(skel)) { + SCX_ERR("Failed to load skel"); + return SCX_TEST_FAIL; + } + + link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + for (i = 0; i < NR_WORKERS; i++) + workers[i].cpu = test_cpus[i / WORKERS_PER_CPU]; + + for (i = 0; i < NR_WORKERS; i++) { + ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]); + if (ret) { + SCX_ERR("Failed to create worker thread %d (%d)", i, ret); + status = SCX_TEST_FAIL; + goto out; + } + workers[i].started = true; + } + + sleep(5); + + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) { + SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)", + (unsigned long long)skel->data->uei.kind, + (long long)skel->data->uei.exit_code); + status = SCX_TEST_FAIL; + } + +out: + for (i = 0; i < NR_WORKERS; i++) + workers[i].stop = true; + + for (i = 0; i < NR_WORKERS; i++) { + ret = join_worker(&workers[i]); + if (ret && status == SCX_TEST_PASS) { + SCX_ERR("Failed to join worker thread %d (%d)", i, ret); + status = SCX_TEST_FAIL; + } + } + + if (link) + bpf_link__destroy(link); + + return status; +} + +static void cleanup(void *ctx) +{ + struct cyclic_kick_wait *skel = ctx; + + cyclic_kick_wait__destroy(skel); +} + +struct scx_test cyclic_kick_wait = { + .name = "cyclic_kick_wait", + .description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&cyclic_kick_wait) diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json index 8d10042b489b..dbce6436ed26 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json @@ -22,5 +22,49 @@ "teardown": [ "$TC qdisc del dev $DUMMY root handle 1: htb default 1" ] + }, + { + "id": "b7e3", + "name": "Empty fw filter on shared block - rejected at config time", + "category": [ + "filter", + "fw" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 egress_block 1 clsact" + ], + "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 fw", + "expExitCode": "2", + "verifyCmd": "$TC filter show block 1", + "matchPattern": "fw", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "c8f4", + "name": "Flow filter on shared block without baseclass - rejected at config time", + "category": [ + "filter", + "flow" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress_block 1 clsact" + ], + "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 handle 1 flow map key dst", + "expExitCode": "2", + "verifyCmd": "$TC filter show block 1", + "matchPattern": "flow", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 6a39640aa2a8..1e5efb2a31eb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1111,5 +1111,30 @@ "teardown": [ "$TC qdisc del dev $DUMMY root handle 1:" ] + }, + { + "id": "a3d7", + "name": "HFSC with large m1 - no divide-by-zero on class reactivation", + "category": [ + "qdisc", + "hfsc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc replace dev $DUMMY root handle 1: hfsc default 1", + "$TC class replace dev $DUMMY parent 1: classid 1:1 hfsc rt m1 32gbit d 1ms m2 0bit ls m1 32gbit d 1ms m2 0bit", + "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true", + "sleep 1" + ], + "cmdUnderTest": "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc hfsc 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h index 169abeaf4363..f7c5675737fe 100644 --- a/tools/tracing/rtla/src/timerlat_bpf.h +++ b/tools/tracing/rtla/src/timerlat_bpf.h @@ -12,7 +12,6 @@ enum summary_field { }; #ifndef __bpf__ -#include <bpf/libbpf.h> #ifdef HAVE_BPF_SKEL int timerlat_bpf_init(struct timerlat_params *params); int timerlat_bpf_attach(void); |