From 1693c5db6ab8262e6f5263f9d211855959aa5acd Mon Sep 17 00:00:00 2001 From: Abhishek Chauhan Date: Thu, 9 May 2024 14:18:33 -0700 Subject: net: Add additional bit to support clockid_t timestamp type tstamp_type is now set based on actual clockid_t compressed into 2 bits. To make the design scalable for future needs this commit bring in the change to extend the tstamp_type:1 to tstamp_type:2 to support other clockid_t timestamp. We now support CLOCK_TAI as part of tstamp_type as part of this commit with existing support CLOCK_MONOTONIC and CLOCK_REALTIME. Signed-off-by: Abhishek Chauhan Reviewed-by: Willem de Bruijn Reviewed-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20240509211834.3235191-3-quic_abchauha@quicinc.com Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; -- cgit v1.2.3 From ed7ee6a69f9289337af4835a908aa782263d4852 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 29 May 2024 10:39:01 +0200 Subject: statx: Update offset commentary for struct statx In commit 2a82bb02941f ("statx: stx_subvol"), a new member was added to struct statx, but the offset comment was not correct. Update it. Signed-off-by: John Garry Link: https://lore.kernel.org/r/20240529081725.3769290-1-john.g.garry@oracle.com Signed-off-by: Christian Brauner --- include/uapi/linux/stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 67626d535316..95770941ee2c 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,8 +126,8 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ + __u64 stx_subvol; /* Subvolume identifier */ __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; -- cgit v1.2.3 From 1d8491d3e726984343dd8c3cdbe2f2b47cfdd928 Mon Sep 17 00:00:00 2001 From: Paolo Pisati Date: Sat, 1 Jun 2024 17:32:54 +0200 Subject: m68k: amiga: Turn off Warp1260 interrupts during boot On an Amiga 1200 equipped with a Warp1260 accelerator, an interrupt storm coming from the accelerator board causes the machine to crash in local_irq_enable() or auto_irq_enable(). Disabling interrupts for the Warp1260 in amiga_parse_bootinfo() fixes the problem. Link: https://lore.kernel.org/r/ZkjwzVwYeQtyAPrL@amaterasu.local Cc: stable Signed-off-by: Paolo Pisati Reviewed-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20240601153254.186225-1-p.pisati@gmail.com Signed-off-by: Geert Uytterhoeven --- arch/m68k/amiga/config.c | 9 +++++++++ include/uapi/linux/zorro_ids.h | 3 +++ 2 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index d4b170c861bf..0147130dc34e 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -180,6 +180,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record) dev->slotsize = be16_to_cpu(cd->cd_SlotSize); dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr); dev->boardsize = be32_to_cpu(cd->cd_BoardSize); + + /* CS-LAB Warp 1260 workaround */ + if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) && + dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) { + + /* turn off all interrupts */ + pr_info("Warp 1260 card detected: applying interrupt storm workaround\n"); + *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff; + } } else pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n"); #endif /* CONFIG_ZORRO */ diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h index 6e574d7b7d79..393f2ee9c042 100644 --- a/include/uapi/linux/zorro_ids.h +++ b/include/uapi/linux/zorro_ids.h @@ -449,6 +449,9 @@ #define ZORRO_PROD_VMC_ISDN_BLASTER_Z2 ZORRO_ID(VMC, 0x01, 0) #define ZORRO_PROD_VMC_HYPERCOM_4 ZORRO_ID(VMC, 0x02, 0) +#define ZORRO_MANUF_CSLAB 0x1400 +#define ZORRO_PROD_CSLAB_WARP_1260 ZORRO_ID(CSLAB, 0x65, 0) + #define ZORRO_MANUF_INFORMATION 0x157C #define ZORRO_PROD_INFORMATION_ISDN_ENGINE_I ZORRO_ID(INFORMATION, 0x64, 0) -- cgit v1.2.3 From 1d17568e74dedbcb54d36af0662a15128297d681 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 30 May 2024 19:08:35 +0200 Subject: net/sched: cls_flower: add support for matching tunnel control flags extend cls_flower to match TUNNEL_FLAGS_PRESENT bits in tunnel metadata. Suggested-by: Ilya Maximets Acked-by: Jamal Hadi Salim Signed-off-by: Davide Caratti Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_cls.h | 3 +++ net/sched/cls_flower.c | 56 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 58 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 229fc925ec3a..b6d38f5fd7c0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -554,6 +554,9 @@ enum { TCA_FLOWER_KEY_SPI, /* be32 */ TCA_FLOWER_KEY_SPI_MASK, /* be32 */ + TCA_FLOWER_KEY_ENC_FLAGS, /* u32 */ + TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* u32 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fd9a6f20b60b..eef570c577ac 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -41,6 +41,12 @@ #define TCA_FLOWER_KEY_CT_FLAGS_MASK \ (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) +#define TUNNEL_FLAGS_PRESENT (\ + _BITUL(IP_TUNNEL_CSUM_BIT) | \ + _BITUL(IP_TUNNEL_DONT_FRAGMENT_BIT) | \ + _BITUL(IP_TUNNEL_OAM_BIT) | \ + _BITUL(IP_TUNNEL_CRIT_OPT_BIT)) + struct fl_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; @@ -75,6 +81,7 @@ struct fl_flow_key { struct flow_dissector_key_l2tpv3 l2tpv3; struct flow_dissector_key_ipsec ipsec; struct flow_dissector_key_cfm cfm; + struct flow_dissector_key_enc_flags enc_flags; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -732,6 +739,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_U32, + TUNNEL_FLAGS_PRESENT), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_U32, + TUNNEL_FLAGS_PRESENT), }; static const struct nla_policy @@ -1825,6 +1836,21 @@ static int fl_set_key_cfm(struct nlattr **tb, return 0; } +static int fl_set_key_enc_flags(struct nlattr **tb, u32 *flags_key, + u32 *flags_mask, struct netlink_ext_ack *extack) +{ + /* mask is mandatory for flags */ + if (NL_REQ_ATTR_CHECK(extack, NULL, tb, TCA_FLOWER_KEY_ENC_FLAGS_MASK)) { + NL_SET_ERR_MSG(extack, "missing enc_flags mask"); + return -EINVAL; + } + + *flags_key = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS]); + *flags_mask = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS_MASK]); + + return 0; +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -2059,9 +2085,16 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (ret) return ret; - if (tb[TCA_FLOWER_KEY_FLAGS]) + if (tb[TCA_FLOWER_KEY_FLAGS]) { ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags, extack); + if (ret) + return ret; + } + + if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) + ret = fl_set_key_enc_flags(tb, &key->enc_flags.flags, + &mask->enc_flags.flags, extack); return ret; } @@ -2175,6 +2208,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPSEC, ipsec); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_CFM, cfm); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_FLAGS, enc_flags); skb_flow_dissector_init(dissector, keys, cnt); } @@ -3291,6 +3326,22 @@ err_cfm_opts: return err; } +static int fl_dump_key_enc_flags(struct sk_buff *skb, + struct flow_dissector_key_enc_flags *key, + struct flow_dissector_key_enc_flags *mask) +{ + if (!memchr_inv(mask, 0, sizeof(*mask))) + return 0; + + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS, key->flags)) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS_MASK, mask->flags)) + return -EMSGSIZE; + + return 0; +} + static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, struct flow_dissector_key_enc_opts *enc_opts) { @@ -3592,6 +3643,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; + if (fl_dump_key_enc_flags(skb, &key->enc_flags, &mask->enc_flags)) + goto nla_put_failure; + return 0; nla_put_failure: -- cgit v1.2.3 From 310ec03841a36e3f45fb528f0dfdfe5b9e84b037 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Wed, 5 Jun 2024 13:26:05 +1200 Subject: dma-buf: align fd_flags and heap_flags with dma_heap_allocation_data dma_heap_allocation_data defines the UAPI as follows: struct dma_heap_allocation_data { __u64 len; __u32 fd; __u32 fd_flags; __u64 heap_flags; }; However, dma_heap_buffer_alloc() casts both fd_flags and heap_flags into unsigned int. We're inconsistent with types in the non UAPI arguments. This patch fixes it. Signed-off-by: Barry Song Acked-by: John Stultz Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20240605012605.5341-1-21cnbao@gmail.com --- drivers/dma-buf/dma-heap.c | 4 ++-- include/uapi/linux/dma-heap.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 84ae708fafe7..2298ca5e112e 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -50,8 +50,8 @@ static struct class *dma_heap_class; static DEFINE_XARRAY_ALLOC(dma_heap_minors); static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, - unsigned int fd_flags, - unsigned int heap_flags) + u32 fd_flags, + u64 heap_flags) { struct dma_buf *dmabuf; int fd; diff --git a/include/uapi/linux/dma-heap.h b/include/uapi/linux/dma-heap.h index 6f84fa08e074..a4cf716a49fa 100644 --- a/include/uapi/linux/dma-heap.h +++ b/include/uapi/linux/dma-heap.h @@ -19,7 +19,7 @@ #define DMA_HEAP_VALID_FD_FLAGS (O_CLOEXEC | O_ACCMODE) /* Currently no heap flags */ -#define DMA_HEAP_VALID_HEAP_FLAGS (0) +#define DMA_HEAP_VALID_HEAP_FLAGS (0ULL) /** * struct dma_heap_allocation_data - metadata passed from userspace for -- cgit v1.2.3 From 6fef518594bcb7e374f809717281bd02894929f8 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 25 Apr 2024 15:07:01 -0700 Subject: KVM: x86: Add a capability to configure bus frequency for APIC timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add KVM_CAP_X86_APIC_BUS_CYCLES_NS capability to configure the APIC bus clock frequency for APIC timer emulation. Allow KVM_ENABLE_CAPABILITY(KVM_CAP_X86_APIC_BUS_CYCLES_NS) to set the frequency in nanoseconds. When using this capability, the user space VMM should configure CPUID leaf 0x15 to advertise the frequency. Vishal reported that the TDX guest kernel expects a 25MHz APIC bus frequency but ends up getting interrupts at a significantly higher rate. The TDX architecture hard-codes the core crystal clock frequency to 25MHz and mandates exposing it via CPUID leaf 0x15. The TDX architecture does not allow the VMM to override the value. In addition, per Intel SDM: "The APIC timer frequency will be the processor’s bus clock or core crystal clock frequency (when TSC/core crystal clock ratio is enumerated in CPUID leaf 0x15) divided by the value specified in the divide configuration register." The resulting 25MHz APIC bus frequency conflicts with the KVM hardcoded APIC bus frequency of 1GHz. The KVM doesn't enumerate CPUID leaf 0x15 to the guest unless the user space VMM sets it using KVM_SET_CPUID. If the CPUID leaf 0x15 is enumerated, the guest kernel uses it as the APIC bus frequency. If not, the guest kernel measures the frequency based on other known timers like the ACPI timer or the legacy PIT. As reported by Vishal the TDX guest kernel expects a 25MHz timer frequency but gets timer interrupt more frequently due to the 1GHz frequency used by KVM. To ensure that the guest doesn't have a conflicting view of the APIC bus frequency, allow the userspace to tell KVM to use the same frequency that TDX mandates instead of the default 1Ghz. Reported-by: Vishal Annapurve Closes: https://lore.kernel.org/lkml/20231006011255.4163884-1-vannapurve@google.com Signed-off-by: Isaku Yamahata Reviewed-by: Rick Edgecombe Co-developed-by: Reinette Chatre Signed-off-by: Reinette Chatre Reviewed-by: Xiaoyao Li Reviewed-by: Yuan Yao Link: https://lore.kernel.org/r/6748a4c12269e756f0c48680da8ccc5367c31ce7.1714081726.git.reinette.chatre@intel.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 17 +++++++++++++++++ arch/x86/kvm/x86.c | 27 +++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 3 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a71d91978d9e..cb31ae071cba 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8070,6 +8070,23 @@ error/annotated fault. See KVM_EXIT_MEMORY_FAULT for more information. +7.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS +----------------------------------- + +:Architectures: x86 +:Target: VM +:Parameters: args[0] is the desired APIC bus clock rate, in nanoseconds +:Returns: 0 on success, -EINVAL if args[0] contains an invalid value for the + frequency or if any vCPUs have been created, -ENXIO if a virtual + local APIC has not been created using KVM_CREATE_IRQCHIP. + +This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel +virtual APIC when emulating APIC timers. KVM's default value can be retrieved +by KVM_CHECK_EXTENSION. + +Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the +core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. + 8. Other capabilities. ====================== diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9bdc841d5928..09e3460bcbc5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4706,6 +4706,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: + r = APIC_BUS_CYCLE_NS_DEFAULT; + break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; @@ -6746,6 +6749,30 @@ split_irqchip_unlock: } mutex_unlock(&kvm->lock); break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: { + u64 bus_cycle_ns = cap->args[0]; + u64 unused; + + /* + * Guard against overflow in tmict_to_ns(). 128 is the highest + * divide value that can be programmed in APIC_TDCR. + */ + r = -EINVAL; + if (!bus_cycle_ns || + check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused)) + break; + + r = 0; + mutex_lock(&kvm->lock); + if (!irqchip_in_kernel(kvm)) + r = -ENXIO; + else if (kvm->created_vcpus) + r = -EINVAL; + else + kvm->arch.apic_bus_cycle_ns = bus_cycle_ns; + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..ec998e6b6555 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -917,6 +917,7 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 236 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 62096c48394b49e326056a62780fb67b60edde91 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Mon, 6 May 2024 17:49:16 +0900 Subject: media: v4l2-ctrls: Add average QP control Add a control V4L2_CID_MPEG_VIDEO_AVERAGE_QP to report the average QP value of the current encoded frame. The value applies to the last dequeued capture buffer. Signed-off-by: Ming Qian Reviewed-by: Hans Verkuil Signed-off-by: Sebastian Fricke Signed-off-by: Hans Verkuil --- Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 14 ++++++++++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 5 +++++ include/uapi/linux/v4l2-controls.h | 2 ++ 3 files changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 2a165ae063fb..4a379bd9e3fb 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1653,6 +1653,20 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - Quantization parameter for a P frame for FWHT. Valid range: from 1 to 31. +``V4L2_CID_MPEG_VIDEO_AVERAGE_QP (integer)`` + This read-only control returns the average QP value of the currently + encoded frame. The value applies to the last dequeued capture buffer + (VIDIOC_DQBUF). Its valid range depends on the encoding format and parameters. + For H264, its valid range is from 0 to 51. + For HEVC, its valid range is from 0 to 51 for 8 bit and + from 0 to 63 for 10 bit. + For H263 and MPEG4, its valid range is from 1 to 31. + For VP8, its valid range is from 0 to 127. + For VP9, its valid range is from 0 to 255. + If the codec's MIN_QP and MAX_QP are set, then the QP will meet both requirements. + Codecs need to always use the specified range, rather then a HW custom range. + Applicable to encoders + .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index 8696eb1cdd61..1ea52011247a 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -970,6 +970,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_LTR_COUNT: return "LTR Count"; case V4L2_CID_MPEG_VIDEO_FRAME_LTR_INDEX: return "Frame LTR Index"; case V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES: return "Use LTR Frames"; + case V4L2_CID_MPEG_VIDEO_AVERAGE_QP: return "Average QP Value"; case V4L2_CID_FWHT_I_FRAME_QP: return "FWHT I-Frame QP Value"; case V4L2_CID_FWHT_P_FRAME_QP: return "FWHT P-Frame QP Value"; @@ -1507,6 +1508,10 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, *max = 0xffffffffffffLL; *step = 1; break; + case V4L2_CID_MPEG_VIDEO_AVERAGE_QP: + *type = V4L2_CTRL_TYPE_INTEGER; + *flags |= V4L2_CTRL_FLAG_READ_ONLY; + break; case V4L2_CID_PIXEL_RATE: *type = V4L2_CTRL_TYPE_INTEGER64; *flags |= V4L2_CTRL_FLAG_READ_ONLY; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 99c3f5e99da7..974fd254e573 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -898,6 +898,8 @@ enum v4l2_mpeg_video_av1_level { V4L2_MPEG_VIDEO_AV1_LEVEL_7_3 = 23 }; +#define V4L2_CID_MPEG_VIDEO_AVERAGE_QP (V4L2_CID_CODEC_BASE + 657) + /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_CODEC_CX2341X_BASE (V4L2_CTRL_CLASS_CODEC | 0x1000) #define V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE (V4L2_CID_CODEC_CX2341X_BASE+0) -- cgit v1.2.3 From 85542adb65ecd7cc0e442e8befef74f2ed07f5f6 Mon Sep 17 00:00:00 2001 From: Thomas Prescher Date: Wed, 8 May 2024 15:25:01 +0200 Subject: KVM: x86: Add KVM_RUN_X86_GUEST_MODE kvm_run flag When a vCPU is interrupted by a signal while running a nested guest, KVM will exit to userspace with L2 state. However, userspace has no way to know whether it sees L1 or L2 state (besides calling KVM_GET_STATS_FD, which does not have a stable ABI). This causes multiple problems: The simplest one is L2 state corruption when userspace marks the sregs as dirty. See this mailing list thread [1] for a complete discussion. Another problem is that if userspace decides to continue by emulating instructions, it will unknowingly emulate with L2 state as if L1 doesn't exist, which can be considered a weird guest escape. Introduce a new flag, KVM_RUN_X86_GUEST_MODE, in the kvm_run data structure, which is set when the vCPU exited while running a nested guest. Also introduce a new capability, KVM_CAP_X86_GUEST_MODE, to advertise the functionality to userspace. [1] https://lore.kernel.org/kvm/20240416123558.212040-1-julian.stecklina@cyberus-technology.de/T/#m280aadcb2e10ae02c191a7dc4ed4b711a74b1f55 Signed-off-by: Thomas Prescher Signed-off-by: Julian Stecklina Link: https://lore.kernel.org/r/20240508132502.184428-1-julian.stecklina@cyberus-technology.de Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 17 +++++++++++++++++ arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/x86.c | 3 +++ include/uapi/linux/kvm.h | 1 + 4 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 67edb84317ef..42d1d9518bf2 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6419,6 +6419,9 @@ affect the device's behavior. Current defined flags:: #define KVM_RUN_X86_SMM (1 << 0) /* x86, set if bus lock detected in VM */ #define KVM_RUN_X86_BUS_LOCK (1 << 1) + /* x86, set if the VCPU is executing a nested (L2) guest */ + #define KVM_RUN_X86_GUEST_MODE (1 << 2) + /* arm64, set for KVM_EXIT_DEBUG */ #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) @@ -8089,6 +8092,20 @@ by KVM_CHECK_EXTENSION. Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. +7.36 KVM_CAP_X86_GUEST_MODE +------------------------------ + +:Architectures: x86 +:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP. + +The presence of this capability indicates that KVM_RUN will update the +KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the +vCPU was executing nested guest code when it exited. + +KVM exits with the register state of either the L1 or L2 guest +depending on which executed at the time of an exit. Userspace must +take care to differentiate between these cases. + 8. Other capabilities. ====================== diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 9fae1b73b529..b85671d9c8aa 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bfe3dba56e24..33e41103fcde 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4704,6 +4704,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_MEMORY_FAULT_INFO: + case KVM_CAP_X86_GUEST_MODE: r = 1; break; case KVM_CAP_X86_APIC_BUS_CYCLES_NS: @@ -10277,6 +10278,8 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; + if (is_guest_mode(vcpu)) + kvm_run->flags |= KVM_RUN_X86_GUEST_MODE; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ec998e6b6555..a6ac00ec77ad 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -918,6 +918,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 236 +#define KVM_CAP_X86_GUEST_MODE 237 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From f328a26eeb5380bc74e58cb9c3280a4908452df7 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 3 Jun 2024 17:55:55 -0400 Subject: dlm: introduce DLM_LSFL_SOFTIRQ_SAFE Introduce a new external lockspace flag DLM_LSFL_SOFTIRQ_SAFE. A lockspace user will set this flag if it can handle dlm running the callback functions from softirq context. When not set, dlm will continue to run callback functions from the dlm_callback workqueue. The new lockspace flag cannot be used for user space lockspaces, so a uapi placeholder definition is used for the new flag value. Signed-off-by: Alexander Aring Signed-off-by: David Teigland --- fs/dlm/lockspace.c | 3 +++ include/linux/dlm.h | 17 ++++++++++++++++- include/uapi/linux/dlm.h | 2 ++ 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 8a4351ee9a42..a7ac0fcb4ef3 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -629,6 +629,9 @@ int dlm_new_user_lockspace(const char *name, const char *cluster, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { + if (flags & DLM_LSFL_SOFTIRQ) + return -EINVAL; + return __dlm_new_lockspace(name, cluster, flags, lvblen, ops, ops_arg, ops_result, lockspace); } diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c58c4f790c04..bacda9898f2b 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -35,6 +35,9 @@ struct dlm_lockspace_ops { int num_slots, int our_slot, uint32_t generation); }; +/* only relevant for kernel lockspaces, will be removed in future */ +#define DLM_LSFL_SOFTIRQ __DLM_LSFL_RESERVED0 + /* * dlm_new_lockspace * @@ -55,6 +58,11 @@ struct dlm_lockspace_ops { * used to select the directory node. Must be the same on all nodes. * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. + * DLM_LSFL_SOFTIRQ + * dlm request callbacks (ast, bast) are softirq safe. Flag should be + * preferred by users. Will be default in some future. If set the + * strongest context for ast, bast callback is softirq as it avoids + * an additional context switch. * * lvblen: length of lvb in bytes. Must be multiple of 8. * dlm_new_lockspace() returns an error if this does not match @@ -121,7 +129,14 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); * call. * * AST routines should not block (at least not for long), but may make - * any locking calls they please. + * any locking calls they please. If DLM_LSFL_SOFTIRQ for kernel + * users of dlm_new_lockspace() is passed the ast and bast callbacks + * can be processed in softirq context. Also some of the callback + * contexts are in the same context as the DLM lock request API, users + * must not hold locks while calling dlm lock request API and trying + * to acquire this lock in the callback again, this will end in a + * lock recursion. For newer implementation the DLM_LSFL_SOFTIRQ + * should be used. */ int dlm_lock(dlm_lockspace_t *lockspace, diff --git a/include/uapi/linux/dlm.h b/include/uapi/linux/dlm.h index e7e905fb0bb2..4eaf835780b0 100644 --- a/include/uapi/linux/dlm.h +++ b/include/uapi/linux/dlm.h @@ -71,6 +71,8 @@ struct dlm_lksb { /* DLM_LSFL_TIMEWARN is deprecated and reserved. DO NOT USE! */ #define DLM_LSFL_TIMEWARN 0x00000002 #define DLM_LSFL_NEWEXCL 0x00000008 +/* currently reserved due in-kernel use */ +#define __DLM_LSFL_RESERVED0 0x00000010 #endif /* _UAPI__DLM_DOT_H__ */ -- cgit v1.2.3 From c1d8bd8d777d55f6708ca6e47c54dbe9f66f9bbb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 May 2024 12:09:49 +0200 Subject: wifi: cfg80211: add regulatory flag to allow VLP AP operation Add a regulatory flag to allow VLP AP operation even on channels otherwise marked NO_IR, which may be possible in some regulatory domains/countries. Note that this requires checking also when the beacon is changed, since that may change the regulatory power type. Reviewed-by: Miriam Rachel Korenblit Signed-off-by: Johannes Berg Link: https://msgid.link/20240523120945.63792ce19790.Ie2a02750d283b78fbf3c686b10565fb0388889e2@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 ++++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/chan.c | 37 ++++++++++++++++++++++++++----------- net/wireless/nl80211.c | 27 +++++++++++++++++++++++++-- net/wireless/reg.c | 2 ++ net/wireless/trace.h | 15 +++++++++------ 6 files changed, 74 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 45ffeb110d36..6f992aff74ae 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -125,6 +125,8 @@ struct wiphy; * @IEEE80211_CHAN_CAN_MONITOR: This channel can be used for monitor * mode even in the presence of other (regulatory) restrictions, * even if it is otherwise disabled. + * @IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP: Allow using this channel for AP operation + * with very low power (VLP), even if otherwise set to NO_IR. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = BIT(0), @@ -152,6 +154,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = BIT(22), IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = BIT(23), IEEE80211_CHAN_CAN_MONITOR = BIT(24), + IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP = BIT(25), }; #define IEEE80211_CHAN_NO_HT40 \ @@ -8806,9 +8809,12 @@ static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, * @relax: allow IR-relaxation conditions to apply (e.g. another * interface connected already on the same channel) * NOTE: If this is set, wiphy mutex must be held. + * @reg_power: &enum ieee80211_ap_reg_power value indicating the + * advertised/used 6 GHz regulatory power setting */ struct cfg80211_beaconing_check_config { enum nl80211_iftype iftype; + enum ieee80211_ap_reg_power reg_power; bool relax; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f917bc6c9b6f..6ae3997061b6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4277,6 +4277,8 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_CAN_MONITOR: This channel can be used in monitor * mode despite other (regulatory) restrictions, even if the channel is * otherwise completely disabled. + * @NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP: This channel can be used for a + * very low power (VLP) AP, despite being NO_IR. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4320,6 +4322,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT, NL80211_FREQUENCY_ATTR_CAN_MONITOR, + NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4529,6 +4532,8 @@ enum nl80211_sched_scan_match_attr { * Should be used together with %NL80211_RRF_DFS only. * @NL80211_RRF_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP not allowed * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed + * @NL80211_RRF_ALLOW_6GHZ_VLP_AP: Very low power (VLP) AP can be permitted + * despite NO_IR configuration. */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4553,6 +4558,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_DFS_CONCURRENT = 1<<21, NL80211_RRF_NO_6GHZ_VLP_CLIENT = 1<<22, NL80211_RRF_NO_6GHZ_AFC_CLIENT = 1<<23, + NL80211_RRF_ALLOW_6GHZ_VLP_AP = 1<<24, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 8b1796130b28..bf2fdcd42019 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -1523,28 +1523,38 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype, - bool check_no_ir) + u32 prohibited_flags, + u32 permitting_flags) { - bool res; - u32 prohibited_flags = IEEE80211_CHAN_DISABLED; + bool res, check_radar; int dfs_required; - trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir); + trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, + prohibited_flags, + permitting_flags); - if (check_no_ir) - prohibited_flags |= IEEE80211_CHAN_NO_IR; + if (!_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_DISABLED, 0)) + return false; dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype); - if (dfs_required != 0) - prohibited_flags |= IEEE80211_CHAN_RADAR; + check_radar = dfs_required != 0; if (dfs_required > 0 && cfg80211_chandef_dfs_available(wiphy, chandef)) { /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ - prohibited_flags = IEEE80211_CHAN_DISABLED; + prohibited_flags &= ~IEEE80211_CHAN_NO_IR; + check_radar = false; } - res = _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, 0); + if (check_radar && + !_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_RADAR, 0)) + return false; + + res = _cfg80211_chandef_usable(wiphy, chandef, + prohibited_flags, + permitting_flags); trace_cfg80211_return_bool(res); return res; @@ -1555,6 +1565,7 @@ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, struct cfg80211_beaconing_check_config *cfg) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + u32 permitting_flags = 0; bool check_no_ir = true; /* @@ -1569,8 +1580,12 @@ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, chandef->chan); } + if (cfg->reg_power == IEEE80211_REG_VLP_AP) + permitting_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; + return _cfg80211_reg_can_beacon(wiphy, chandef, cfg->iftype, - check_no_ir); + check_no_ir ? IEEE80211_CHAN_NO_IR : 0, + permitting_flags); } EXPORT_SYMBOL(cfg80211_reg_check_beaconing); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4628280abf1d..a94e73c133f7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1207,6 +1207,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_CAN_MONITOR) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_CAN_MONITOR)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -5954,6 +5957,7 @@ static int nl80211_validate_ap_phy_operation(struct cfg80211_ap_settings *params static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -6103,8 +6107,13 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, - wdev->iftype)) { + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, ¶ms->chandef, + &beacon_check)) { err = -EINVAL; goto out; } @@ -6261,6 +6270,7 @@ out: static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -6287,6 +6297,19 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + /* recheck beaconing is permitted with possibly changed power type */ + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, + &wdev->links[link_id].ap.chandef, + &beacon_check)) { + err = -EINVAL; + goto out; + } + attr = info->attrs[NL80211_ATTR_FILS_DISCOVERY]; if (attr) { err = nl80211_parse_fils_discovery(rdev, attr, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3cef0021a3db..4a27f3823e25 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1600,6 +1600,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; + if (rd_flags & NL80211_RRF_ALLOW_6GHZ_VLP_AP) + channel_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; return channel_flags; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 6ef9294747e3..5c26f065bd68 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3389,23 +3389,26 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify, TRACE_EVENT(cfg80211_reg_can_beacon, TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype, bool check_no_ir), - TP_ARGS(wiphy, chandef, iftype, check_no_ir), + enum nl80211_iftype iftype, u32 prohibited_flags, + u32 permitting_flags), + TP_ARGS(wiphy, chandef, iftype, prohibited_flags, permitting_flags), TP_STRUCT__entry( WIPHY_ENTRY CHAN_DEF_ENTRY __field(enum nl80211_iftype, iftype) - __field(bool, check_no_ir) + __field(u32, prohibited_flags) + __field(u32, permitting_flags) ), TP_fast_assign( WIPHY_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->iftype = iftype; - __entry->check_no_ir = check_no_ir; + __entry->prohibited_flags = prohibited_flags; + __entry->permitting_flags = permitting_flags; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d check_no_ir=%s", + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d prohibited_flags=0x%x permitting_flags=0x%x", WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype, - BOOL_TO_STR(__entry->check_no_ir)) + __entry->prohibited_flags, __entry->permitting_flags) ); TRACE_EVENT(cfg80211_chandef_dfs_required, -- cgit v1.2.3 From a3cfe84cca28f205761a0450016593b0d728165e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Thu, 6 Jun 2024 07:58:50 -0700 Subject: bpf: Add CHECKSUM_COMPLETE to bpf test progs Add special flag to validate that TC BPF program properly updates checksum information in skb. Signed-off-by: Vadim Fedorenko Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Kicinski Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240606145851.229116-1-vadfed@meta.com --- include/uapi/linux/bpf.h | 2 ++ net/bpf/test_run.c | 28 +++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 2 ++ 3 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 25ea393cf084..35bcf52dbc65 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1425,6 +1425,8 @@ enum { #define BPF_F_TEST_RUN_ON_CPU (1U << 0) /* If set, XDP frames will be transmitted after processing */ #define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 36ae54f57bf5..3c965e32fc33 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -983,7 +983,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; - if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) + if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) || + kattr->test.cpu || kattr->test.batch_size) return -EINVAL; data = bpf_test_init(kattr, kattr->test.data_size_in, @@ -1031,6 +1032,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); + if (ctx && ctx->ifindex > 1) { dev = dev_get_by_index(net, ctx->ifindex); if (!dev) { @@ -1066,9 +1068,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); + ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + + skb->csum = skb_checksum(skb, off, len, 0); + skb->ip_summed = CHECKSUM_COMPLETE; + } + ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; @@ -1083,6 +1095,20 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, } memset(__skb_push(skb, hh_len), 0, hh_len); } + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + __wsum csum; + + csum = skb_checksum(skb, off, len, 0); + + if (csum_fold(skb->csum) != csum_fold(csum)) { + ret = -EBADMSG; + goto out; + } + } + convert_skb_to___skb(skb, ctx); size = skb->len; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 25ea393cf084..35bcf52dbc65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1425,6 +1425,8 @@ enum { #define BPF_F_TEST_RUN_ON_CPU (1U << 0) /* If set, XDP frames will be transmitted after processing */ #define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { -- cgit v1.2.3 From d25a92ccae6bed02327b63d138e12e7806830f78 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Fri, 14 Jun 2024 02:00:30 +0800 Subject: net/smc: Introduce IPPROTO_SMC This patch allows to create smc socket via AF_INET, similar to the following code, /* create v4 smc sock */ v4 = socket(AF_INET, SOCK_STREAM, IPPROTO_SMC); /* create v6 smc sock */ v6 = socket(AF_INET6, SOCK_STREAM, IPPROTO_SMC); There are several reasons why we believe it is appropriate here: 1. For smc sockets, it actually use IPv4 (AF-INET) or IPv6 (AF-INET6) address. There is no AF_SMC address at all. 2. Create smc socket in the AF_INET(6) path, which allows us to reuse the infrastructure of AF_INET(6) path, such as common ebpf hooks. Otherwise, smc have to implement it again in AF_SMC path. Signed-off-by: D. Wythe Reviewed-by: Wenjia Zhang Reviewed-by: Dust Li Tested-by: Niklas Schnelle Tested-by: Wenjia Zhang Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 2 + net/smc/Makefile | 2 +- net/smc/af_smc.c | 16 ++++- net/smc/smc_inet.c | 159 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_inet.h | 22 +++++++ 5 files changed, 198 insertions(+), 3 deletions(-) create mode 100644 net/smc/smc_inet.c create mode 100644 net/smc/smc_inet.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/net/smc/Makefile b/net/smc/Makefile index 2c510d543058..60f1c87d5212 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o -smc-y += smc_tracepoint.o +smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 7ee6f37813d6..73a875573e7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -54,6 +54,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" +#include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -3575,10 +3576,15 @@ static int __init smc_init(void) pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } - + rc = smc_inet_init(); + if (rc) { + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); + goto out_ulp; + } static_branch_enable(&tcp_have_smc); return 0; - +out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: @@ -3615,6 +3621,7 @@ out_pernet_subsys: static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); @@ -3642,4 +3649,9 @@ MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); +#if IS_ENABLED(CONFIG_IPV6) +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); +#endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c new file mode 100644 index 000000000000..bece346dd8e9 --- /dev/null +++ b/net/smc/smc_inet.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + * + * Copyright IBM Corp. 2016, 2018 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe + */ + +#include +#include + +#include "smc_inet.h" +#include "smc.h" + +static int smc_inet_init_sock(struct sock *sk); + +static struct proto smc_inet_prot = { + .name = "INET_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet_prot, + .ops = &smc_inet_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct proto smc_inet6_prot = { + .name = "INET6_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet6_prot, + .ops = &smc_inet6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; +#endif /* CONFIG_IPV6 */ + +static int smc_inet_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + + /* init common smc sock */ + smc_sk_init(net, sk, IPPROTO_SMC); + /* create clcsock */ + return smc_create_clcsk(net, sk, sk->sk_family); +} + +int __init smc_inet_init(void) +{ + int rc; + + rc = proto_register(&smc_inet_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet_prot fails with %d\n", + __func__, rc); + return rc; + } + /* no return value */ + inet_register_protosw(&smc_inet_protosw); + +#if IS_ENABLED(CONFIG_IPV6) + rc = proto_register(&smc_inet6_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet6_prot fails with %d\n", + __func__, rc); + goto out_inet6_prot; + } + rc = inet6_register_protosw(&smc_inet6_protosw); + if (rc) { + pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", + __func__, rc); + goto out_inet6_protosw; + } + return rc; +out_inet6_protosw: + proto_unregister(&smc_inet6_prot); +out_inet6_prot: + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +#endif /* CONFIG_IPV6 */ + return rc; +} + +void smc_inet_exit(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + inet6_unregister_protosw(&smc_inet6_protosw); + proto_unregister(&smc_inet6_prot); +#endif /* CONFIG_IPV6 */ + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +} diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h new file mode 100644 index 000000000000..a489c8a2b8ef --- /dev/null +++ b/net/smc/smc_inet.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + + * Copyright IBM Corp. 2016 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe + */ +#ifndef __INET_SMC +#define __INET_SMC + +/* Initialize protocol registration on IPPROTO_SMC, + * @return 0 on success + */ +int smc_inet_init(void); + +void smc_inet_exit(void); + +#endif /* __INET_SMC */ -- cgit v1.2.3 From 4b23e0c199b20fa6fe9655b3d0e12d6c6f18c27f Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 3 May 2024 11:17:33 -0700 Subject: KVM: Ensure new code that references immediate_exit gets extra scrutiny Ensure that any new KVM code that references immediate_exit gets extra scrutiny by renaming it to immediate_exit__unsafe in kernel code. All fields in struct kvm_run are subject to TOCTOU races since they are mapped into userspace, which may be malicious or buggy. To protect KVM, introduces a new macro that appends __unsafe to select field names in struct kvm_run, hinting to developers and reviewers that accessing such fields must be done carefully. Apply the new macro to immediate_exit, since userspace can make immediate_exit inconsistent with vcpu->wants_to_run, i.e. accessing immediate_exit directly could lead to unexpected bugs in the future. Signed-off-by: David Matlack Link: https://lore.kernel.org/r/20240503181734.1467938-3-dmatlack@google.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- include/uapi/linux/kvm.h | 15 ++++++++++++++- virt/kvm/kvm_main.c | 2 +- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..795773f5db63 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from to __unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 66bfdfa11805..2fed9a9b8bd6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4435,7 +4435,7 @@ static long kvm_vcpu_ioctl(struct file *filp, synchronize_rcu(); put_pid(oldpid); } - vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit); + vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe); r = kvm_arch_vcpu_ioctl_run(vcpu); vcpu->wants_to_run = false; -- cgit v1.2.3 From 7481fd93fa0a851740e26026485f56a1305454ce Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 14 Jun 2024 12:30:46 -0400 Subject: io_uring: Introduce IORING_OP_BIND IORING_OP_BIND provides the semantic of bind(2) via io_uring. While this is an essentially synchronous system call, the main point is to enable a network path to execute fully with io_uring registered and descriptorless files. Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20240614163047.31581-3-krisman@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 36 ++++++++++++++++++++++++++++++++++++ io_uring/net.h | 3 +++ io_uring/opdef.c | 13 +++++++++++++ 4 files changed, 53 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 994bf7af0efe..4ef153d95c87 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -257,6 +257,7 @@ enum io_uring_op { IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, + IORING_OP_BIND, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index 7c98c4d50946..8cc4cfc2fef3 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -51,6 +51,11 @@ struct io_connect { bool seen_econnaborted; }; +struct io_bind { + struct file *file; + int addr_len; +}; + struct io_sr_msg { struct file *file; union { @@ -1715,6 +1720,37 @@ out: return IOU_OK; } +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct sockaddr __user *uaddr; + struct io_async_msghdr *io; + + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + bind->addr_len = READ_ONCE(sqe->addr2); + + io = io_msg_alloc_async(req); + if (unlikely(!io)) + return -ENOMEM; + return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); +} + +int io_bind(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct io_async_msghdr *io = req->async_data; + int ret; + + ret = __sys_bind_socket(sock_from_file(req->file), &io->addr, bind->addr_len); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return 0; +} + void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; diff --git a/io_uring/net.h b/io_uring/net.h index 0eb1c1920fc9..49f9a7bc1113 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -49,6 +49,9 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags); int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); void io_send_zc_cleanup(struct io_kiocb *req); +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_bind(struct io_kiocb *req, unsigned int issue_flags); + void io_netmsg_cache_free(const void *entry); #else static inline void io_netmsg_cache_free(const void *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 2e3b7b16effb..1424c2d9e9ef 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -495,6 +495,16 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_ftruncate_prep, .issue = io_ftruncate, }, + [IORING_OP_BIND] = { +#if defined(CONFIG_NET) + .needs_file = 1, + .prep = io_bind_prep, + .issue = io_bind, + .async_size = sizeof(struct io_async_msghdr), +#else + .prep = io_eopnotsupp_prep, +#endif + }, }; const struct io_cold_def io_cold_defs[] = { @@ -716,6 +726,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FTRUNCATE] = { .name = "FTRUNCATE", }, + [IORING_OP_BIND] = { + .name = "BIND", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3 From ff140cc8628abfb1755691d16cfa8788d8820ef7 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 14 Jun 2024 12:30:47 -0400 Subject: io_uring: Introduce IORING_OP_LISTEN IORING_OP_LISTEN provides the semantic of listen(2) via io_uring. While this is an essentially synchronous system call, the main point is to enable a network path to execute fully with io_uring registered and descriptorless files. Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20240614163047.31581-4-krisman@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 28 ++++++++++++++++++++++++++++ io_uring/net.h | 3 +++ io_uring/opdef.c | 13 +++++++++++++ 4 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4ef153d95c87..2aaf7ee256ac 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -258,6 +258,7 @@ enum io_uring_op { IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, IORING_OP_BIND, + IORING_OP_LISTEN, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index 8cc4cfc2fef3..db4a4a03ce3a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -56,6 +56,11 @@ struct io_bind { int addr_len; }; +struct io_listen { + struct file *file; + int backlog; +}; + struct io_sr_msg { struct file *file; union { @@ -1751,6 +1756,29 @@ int io_bind(struct io_kiocb *req, unsigned int issue_flags) return 0; } +int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen); + + if (sqe->addr || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in || sqe->addr2) + return -EINVAL; + + listen->backlog = READ_ONCE(sqe->len); + return 0; +} + +int io_listen(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen); + int ret; + + ret = __sys_listen_socket(sock_from_file(req->file), listen->backlog); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return 0; +} + void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; diff --git a/io_uring/net.h b/io_uring/net.h index 49f9a7bc1113..52bfee05f06a 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -52,6 +52,9 @@ void io_send_zc_cleanup(struct io_kiocb *req); int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_bind(struct io_kiocb *req, unsigned int issue_flags); +int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_listen(struct io_kiocb *req, unsigned int issue_flags); + void io_netmsg_cache_free(const void *entry); #else static inline void io_netmsg_cache_free(const void *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 1424c2d9e9ef..2dd49cf22f64 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -503,6 +503,16 @@ const struct io_issue_def io_issue_defs[] = { .async_size = sizeof(struct io_async_msghdr), #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_LISTEN] = { +#if defined(CONFIG_NET) + .needs_file = 1, + .prep = io_listen_prep, + .issue = io_listen, + .async_size = sizeof(struct io_async_msghdr), +#else + .prep = io_eopnotsupp_prep, #endif }, }; @@ -729,6 +739,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_BIND] = { .name = "BIND", }, + [IORING_OP_LISTEN] = { + .name = "LISTEN", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3 From ba63a7e08523be3496cc1b7e5f77d306144a3a40 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 20 Apr 2024 21:47:46 +0200 Subject: can: isotp: remove ISO 15675-2 specification version where possible With the new ISO 15765-2:2024 release the former documentation and comments have to be reworked. This patch removes the ISO specification version/date where possible. Signed-off-by: Oliver Hartkopp Acked-by: Vincent Mailhol Acked-by: Francesco Valla Link: https://lore.kernel.org/all/20240420194746.4885-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 2 +- net/can/Kconfig | 11 +++++------ net/can/isotp.c | 11 ++++++----- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 6cde62371b6f..bd990917f7c4 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -2,7 +2,7 @@ /* * linux/can/isotp.h * - * Definitions for isotp CAN sockets (ISO 15765-2:2016) + * Definitions for ISO 15765-2 CAN transport protocol sockets * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. diff --git a/net/can/Kconfig b/net/can/Kconfig index cb56be8e3862..af64a6f76458 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -56,18 +56,17 @@ config CAN_GW source "net/can/j1939/Kconfig" config CAN_ISOTP - tristate "ISO 15765-2:2016 CAN transport protocol" + tristate "ISO 15765-2 CAN transport protocol" help CAN Transport Protocols offer support for segmented Point-to-Point communication between CAN nodes via two defined CAN Identifiers. + This protocol driver implements segmented data transfers for CAN CC + (aka Classical CAN, CAN 2.0B) and CAN FD frame types which were + introduced with ISO 15765-2:2016. As CAN frames can only transport a small amount of data bytes - (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this + (max. 8 bytes for CAN CC and max. 64 bytes for CAN FD) this segmentation is needed to transport longer Protocol Data Units (PDU) as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. - This protocol driver implements data transfers according to - ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. - If you want to perform automotive vehicle diagnostic services (UDS), - say 'y'. endif diff --git a/net/can/isotp.c b/net/can/isotp.c index 25bac0fafc83..16046931542a 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -72,7 +72,7 @@ #include #include -MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); +MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp "); MODULE_ALIAS("can-proto-6"); @@ -83,10 +83,11 @@ MODULE_ALIAS("can-proto-6"); (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can - * take full 32 bit values (4 Gbyte). We would need some good concept to handle - * this between user space and kernel space. For now set the static buffer to - * something about 8 kbyte to be able to test this new functionality. +/* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 + * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). + * We would need some good concept to handle this between user space and + * kernel space. For now set the static buffer to something about 8 kbyte + * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 -- cgit v1.2.3 From c34fc6f26ab86d03a2d47446f42b6cd492dfdc56 Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:52 +0000 Subject: fs: Initial atomic write support An atomic write is a write issued with torn-write protection, meaning that for a power failure or any other hardware failure, all or none of the data from the write will be stored, but never a mix of old and new data. Userspace may add flag RWF_ATOMIC to pwritev2() to indicate that the write is to be issued with torn-write prevention, according to special alignment and length rules. For any syscall interface utilizing struct iocb, add IOCB_ATOMIC for iocb->ki_flags field to indicate the same. A call to statx will give the relevant atomic write info for a file: - atomic_write_unit_min - atomic_write_unit_max - atomic_write_segments_max Both min and max values must be a power-of-2. Applications can avail of atomic write feature by ensuring that the total length of a write is a power-of-2 in size and also sized between atomic_write_unit_min and atomic_write_unit_max, inclusive. Applications must ensure that the write is at a naturally-aligned offset in the file wrt the total write length. The value in atomic_write_segments_max indicates the upper limit for IOV_ITER iovcnt. Add file mode flag FMODE_CAN_ATOMIC_WRITE, so files which do not have the flag set will have RWF_ATOMIC rejected and not just ignored. Add a type argument to kiocb_set_rw_flags() to allows reads which have RWF_ATOMIC set to be rejected. Helper function generic_atomic_write_valid() can be used by FSes to verify compliant writes. There we check for iov_iter type is for ubuf, which implies iovcnt==1 for pwritev2(), which is an initial restriction for atomic_write_segments_max. Initially the only user will be bdev file operations write handler. We will rely on the block BIO submission path to ensure write sizes are compliant for the bdev, so we don't need to check atomic writes sizes yet. Signed-off-by: Prasad Singamsetty jpg: merge into single patch and much rewrite Acked-by: Darrick J. Wong Reviewed-by: Martin K. Petersen Signed-off-by: John Garry Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20240620125359.2684798-4-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- fs/aio.c | 8 ++++---- fs/btrfs/ioctl.c | 2 +- fs/read_write.c | 18 +++++++++++++++++- include/linux/fs.h | 17 +++++++++++++++-- include/uapi/linux/fs.h | 5 ++++- io_uring/rw.c | 9 ++++----- 6 files changed, 45 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/aio.c b/fs/aio.c index 57c9f7c077e6..93ef59d358b3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1516,7 +1516,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res) iocb_put(iocb); } -static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) +static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; @@ -1542,7 +1542,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) } else req->ki_ioprio = get_current_ioprio(); - ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; @@ -1594,7 +1594,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; @@ -1621,7 +1621,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret; - ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index efd5d6e9589e..6ad524b894fc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4627,7 +4627,7 @@ static int btrfs_ioctl_encoded_write(struct file *file, void __user *argp, bool goto out_iov; init_sync_kiocb(&kiocb, file); - ret = kiocb_set_rw_flags(&kiocb, 0); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); if (ret) goto out_iov; kiocb.ki_pos = pos; diff --git a/fs/read_write.c b/fs/read_write.c index ef6339391351..90e283b31ca1 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -730,7 +730,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ssize_t ret; init_sync_kiocb(&kiocb, filp); - ret = kiocb_set_rw_flags(&kiocb, flags); + ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); @@ -1736,3 +1736,19 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out) return 0; } + +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos) +{ + size_t len = iov_iter_count(iter); + + if (!iter_is_ubuf(iter)) + return false; + + if (!is_power_of_2(len)) + return false; + + if (!IS_ALIGNED(pos, len)) + return false; + + return true; +} diff --git a/include/linux/fs.h b/include/linux/fs.h index 0283cf366c2a..e049414bef7d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -125,8 +125,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) -/* FMODE_* bits 7 to 8 */ +/* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) @@ -317,6 +319,7 @@ struct readahead_control; #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -351,6 +354,7 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -3403,7 +3407,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3422,6 +3427,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3613,4 +3624,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); + #endif /* _LINUX_FS_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 45e4e64fd664..191a7e88a8ab 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -329,9 +329,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/io_uring/rw.c b/io_uring/rw.c index 1a2128459cb4..c004d21e2f12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -772,7 +772,7 @@ static bool need_complete_io(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } -static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct kiocb *kiocb = &rw->kiocb; @@ -787,7 +787,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) req->flags |= io_file_get_flags(file); kiocb->ki_flags = file->f_iocb_flags; - ret = kiocb_set_rw_flags(kiocb, rw->flags); + ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type); if (unlikely(ret)) return ret; kiocb->ki_flags |= IOCB_ALLOC_CACHE; @@ -832,8 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret < 0)) return ret; } - - ret = io_rw_init_file(req, FMODE_READ); + ret = io_rw_init_file(req, FMODE_READ, READ); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); @@ -1013,7 +1012,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) ssize_t ret, ret2; loff_t *ppos; - ret = io_rw_init_file(req, FMODE_WRITE); + ret = io_rw_init_file(req, FMODE_WRITE, WRITE); if (unlikely(ret)) return ret; req->cqe.res = iov_iter_count(&io->iter); -- cgit v1.2.3 From 0f9ca80fa4f9670ba09721e4e36b8baf086a500c Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:53 +0000 Subject: fs: Add initial atomic write support info to statx Extend statx system call to return additional info for atomic write support support for a file. Helper function generic_fill_statx_atomic_writes() can be used by FSes to fill in the relevant statx fields. For now atomic_write_segments_max will always be 1, otherwise some rules would need to be imposed on iovec length and alignment, which we don't want now. Signed-off-by: Prasad Singamsetty jpg: relocate bdev support to another patch Reviewed-by: Darrick J. Wong Reviewed-by: Martin K. Petersen Signed-off-by: John Garry Acked-by: Darrick J. Wong Link: https://lore.kernel.org/r/20240620125359.2684798-5-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- fs/stat.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 +++ include/linux/stat.h | 3 +++ include/uapi/linux/stat.h | 12 ++++++++++-- 4 files changed, 50 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/stat.c b/fs/stat.c index 70bd3e888cfa..72d0e6357b91 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) } EXPORT_SYMBOL(generic_fill_statx_attr); +/** + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes + * @stat: Where to fill in the attribute flags + * @unit_min: Minimum supported atomic write length in bytes + * @unit_max: Maximum supported atomic write length in bytes + * + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from + * atomic write unit_min and unit_max values. + */ +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max) +{ + /* Confirm that the request type is known */ + stat->result_mask |= STATX_WRITE_ATOMIC; + + /* Confirm that the file attribute type is known */ + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC; + + if (unit_min) { + stat->atomic_write_unit_min = unit_min; + stat->atomic_write_unit_max = unit_max; + /* Initially only allow 1x segment */ + stat->atomic_write_segments_max = 1; + + /* Confirm atomic writes are actually supported */ + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; + } +} +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from @@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_subvol = stat->subvol; + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e049414bef7d..db26b4a70c62 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3235,6 +3235,9 @@ extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); diff --git a/include/linux/stat.h b/include/linux/stat.h index bf92441dbad2..3d900c86981c 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -54,6 +54,9 @@ struct kstat { u32 dio_offset_align; u64 change_cookie; u64 subvol; + u32 atomic_write_unit_min; + u32 atomic_write_unit_max; + u32 atomic_write_segments_max; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From ca567df74a28a9fb368c6b2d93e864113f73f5c2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 7 Jun 2020 22:47:08 +0200 Subject: nsfs: add pid translation ioctls Add ioctl()s to translate pids between pid namespaces. LXCFS is a tiny fuse filesystem used to virtualize various aspects of procfs. LXCFS is run on the host. The files and directories it creates can be bind-mounted by e.g. a container at startup and mounted over the various procfs files the container wishes to have virtualized. When e.g. a read request for uptime is received, LXCFS will receive the pid of the reader. In order to virtualize the corresponding read, LXCFS needs to know the pid of the init process of the reader's pid namespace. In order to do this, LXCFS first needs to fork() two helper processes. The first helper process setns() to the readers pid namespace. The second helper process is needed to create a process that is a proper member of the pid namespace. The second helper process then creates a ucred message with ucred.pid set to 1 and sends it back to LXCFS. The kernel will translate the ucred.pid field to the corresponding pid number in LXCFS's pid namespace. This way LXCFS can learn the init pid number of the reader's pid namespace and can go on to virtualize. Since these two forks() are costly LXCFS maintains an init pid cache that caches a given pid for a fixed amount of time. The cache is pruned during new read requests. However, even with the cache the hit of the two forks() is singificant when a very large number of containers are running. With this simple patch we add an ns ioctl that let's a caller retrieve the init pid nr of a pid namespace through its pid namespace fd. This significantly improves performance with a very simple change. Support translation of pids and tgids. Other concepts can be added but there are no obvious users for this right now. To protect against races pidfds can be used to check whether the process is still valid. If needed, this can also be extended to work on pidfds directly. Link: https://lore.kernel.org/r/20240619-work-ns_ioctl-v1-1-7c0097e6bb6b@kernel.org Reviewed-by: Alexander Mikhalitsyn Signed-off-by: Christian Brauner --- fs/nsfs.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/nsfs.h | 8 +++++++ 2 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 07e22a15ef02..a23c827a0299 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -123,9 +124,12 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct user_namespace *user_ns; + struct pid_namespace *pid_ns; + struct task_struct *tsk; struct ns_common *ns = get_proc_ns(file_inode(filp)); uid_t __user *argp; uid_t uid; + int ret; switch (ioctl) { case NS_GET_USERNS: @@ -143,9 +147,56 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, argp = (uid_t __user *) arg; uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); + case NS_GET_PID_FROM_PIDNS: + fallthrough; + case NS_GET_TGID_FROM_PIDNS: + fallthrough; + case NS_GET_PID_IN_PIDNS: + fallthrough; + case NS_GET_TGID_IN_PIDNS: + if (ns->ops->type != CLONE_NEWPID) + return -EINVAL; + + ret = -ESRCH; + pid_ns = container_of(ns, struct pid_namespace, ns); + + rcu_read_lock(); + + if (ioctl == NS_GET_PID_IN_PIDNS || + ioctl == NS_GET_TGID_IN_PIDNS) + tsk = find_task_by_vpid(arg); + else + tsk = find_task_by_pid_ns(arg, pid_ns); + if (!tsk) + break; + + switch (ioctl) { + case NS_GET_PID_FROM_PIDNS: + ret = task_pid_vnr(tsk); + break; + case NS_GET_TGID_FROM_PIDNS: + ret = task_tgid_vnr(tsk); + break; + case NS_GET_PID_IN_PIDNS: + ret = task_pid_nr_ns(tsk, pid_ns); + break; + case NS_GET_TGID_IN_PIDNS: + ret = task_tgid_nr_ns(tsk, pid_ns); + break; + default: + ret = 0; + break; + } + rcu_read_unlock(); + + if (!ret) + ret = -ESRCH; + break; default: - return -ENOTTY; + ret = -ENOTTY; } + + return ret; } int ns_get_name(char *buf, size_t size, struct task_struct *task, diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index a0c8552b64ee..faeb9195da08 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -15,5 +15,13 @@ #define NS_GET_NSTYPE _IO(NSIO, 0x3) /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Translate pid from target pid namespace into the caller's pid namespace. */ +#define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x5, int) +/* Return thread-group leader id of pid in the callers pid namespace. */ +#define NS_GET_TGID_FROM_PIDNS _IOR(NSIO, 0x7, int) +/* Translate pid from caller's pid namespace into a target pid namespace. */ +#define NS_GET_PID_IN_PIDNS _IOR(NSIO, 0x6, int) +/* Return thread-group leader id of pid in the target pid namespace. */ +#define NS_GET_TGID_IN_PIDNS _IOR(NSIO, 0x8, int) #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From e29630247be24c3987e2b048f8e152771b32d38b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 3 Jun 2024 20:16:59 +0200 Subject: netfilter: nf_tables: rise cap on SELinux secmark context secmark context is artificially limited 256 bytes, rise it to 4Kbytes. Fixes: fb961945457f ("netfilter: nf_tables: add SECMARK support") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index aa4094ca2444..639894ed1b97 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1376,7 +1376,7 @@ enum nft_secmark_attributes { #define NFTA_SECMARK_MAX (__NFTA_SECMARK_MAX - 1) /* Max security context length */ -#define NFT_SECMARK_CTX_MAXLEN 256 +#define NFT_SECMARK_CTX_MAXLEN 4096 /** * enum nft_reject_types - nf_tables reject expression reject types -- cgit v1.2.3 From f750dfe825b904164688adeb147950e0e0c4d262 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:51 +0800 Subject: ethtool: provide customized dim profile management The NetDIM library, currently leveraged by an array of NICs, delivers excellent acceleration benefits. Nevertheless, NICs vary significantly in their dim profile list prerequisites. Specifically, virtio-net backends may present diverse sw or hw device implementation, making a one-size-fits-all parameter list impractical. On Alibaba Cloud, the virtio DPU's performance under the default DIM profile falls short of expectations, partly due to a mismatch in parameter configuration. I also noticed that ice/idpf/ena and other NICs have customized profilelist or placed some restrictions on dim capabilities. Motivated by this, I tried adding new params for "ethtool -C" that provides a per-device control to modify and access a device's interrupt parameters. Usage ======== The target NIC is named ethx. Assume that ethx only declares support for rx profile setting (with DIM_PROFILE_RX flag set in profile_flags) and supports modification of usec and pkt fields. 1. Query the currently customized list of the device $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 256, .comps = n/a,}, {.usec = 8, .pkts = 256, .comps = n/a,}, {.usec = 64, .pkts = 256, .comps = n/a,}, {.usec = 128, .pkts = 256, .comps = n/a,}, {.usec = 256, .pkts = 256, .comps = n/a,} tx-profile: n/a 2. Tune $ ethtool -C ethx rx-profile 1,1,n_2,n,n_3,3,n_4,4,n_n,5,n "n" means do not modify this field. $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 1, .comps = n/a,}, {.usec = 2, .pkts = 256, .comps = n/a,}, {.usec = 3, .pkts = 3, .comps = n/a,}, {.usec = 4, .pkts = 4, .comps = n/a,}, {.usec = 256, .pkts = 5, .comps = n/a,} tx-profile: n/a 3. Hint If the device does not support some type of customized dim profiles, the corresponding "n/a" will display. If the "n/a" field is being modified, -EOPNOTSUPP will be reported. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-4-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 31 +++ Documentation/networking/ethtool-netlink.rst | 8 + Documentation/networking/net_dim.rst | 42 +++++ include/linux/dim.h | 58 ++++++ include/linux/ethtool.h | 4 +- include/linux/netdevice.h | 3 + include/uapi/linux/ethtool_netlink.h | 22 +++ lib/dim/net_dim.c | 70 +++++++ net/Kconfig | 1 + net/ethtool/coalesce.c | 273 ++++++++++++++++++++++++++- 10 files changed, 509 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 00dc61358be8..6c2ab3d1c22f 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -414,6 +414,26 @@ attribute-sets: name: combined-count type: u32 + - + name: irq-moderation + attributes: + - + name: usec + type: u32 + - + name: pkts + type: u32 + - + name: comps + type: u32 + - + name: profile + attributes: + - + name: irq-moderation + type: nest + multi-attr: true + nested-attributes: irq-moderation - name: coalesce attributes: @@ -502,6 +522,15 @@ attribute-sets: - name: tx-aggr-time-usecs type: u32 + - + name: rx-profile + type: nest + nested-attributes: profile + - + name: tx-profile + type: nest + nested-attributes: profile + - name: pause-stat attributes: @@ -1325,6 +1354,8 @@ operations: - tx-aggr-max-bytes - tx-aggr-max-frames - tx-aggr-time-usecs + - rx-profile + - tx-profile dump: *coalesce-get-op - name: coalesce-set diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 160bfb0ae8ba..7ec08e903bab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1033,6 +1033,8 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1062,6 +1064,10 @@ block should be sent. This feature is mainly of interest for specific USB devices which does not cope well with frequent small-sized URBs transmissions. +``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer +to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM) +`_. + COALESCE_SET ============ @@ -1098,6 +1104,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 3bed9fd95336..8908fd7b0a8d 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear. ... } + +Tuning DIM +========== + +Net DIM serves a range of network devices and delivers excellent acceleration +benefits. Yet, it has been observed that some preset configurations of DIM may +not align seamlessly with the varying specifications of network devices, and +this discrepancy has been identified as a factor to the suboptimal performance +outcomes of DIM-enabled network devices, related to a mismatch in profiles. + +To address this issue, Net DIM introduces a per-device control to modify and +access a device's ``rx-profile`` and ``tx-profile`` parameters: +Assume that the target network device is named ethx, and ethx only declares +support for RX profile setting and supports modification of ``usec`` field +and ``pkts`` field (See the data structure: +:c:type:`struct dim_cq_moder `). + +You can use ethtool to modify the current RX DIM profile where all +values are 64:: + + $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n + +``n`` means do not modify this field, and ``_`` separates structure +elements of the profile array. + +Querying the current profiles using:: + + $ ethtool -c ethx + ... + rx-profile: + {.usec = 1, .pkts = 1, .comps = n/a,}, + {.usec = 2, .pkts = 2, .comps = n/a,}, + {.usec = 3, .pkts = 64, .comps = n/a,}, + {.usec = 64, .pkts = 4, .comps = n/a,}, + {.usec = 64, .pkts = 64, .comps = n/a,} + tx-profile: n/a + +If the network device does not support specific fields of DIM profiles, +the corresponding ``n/a`` will display. If the ``n/a`` field is being +modified, error messages will be reported. + + Dynamic Interrupt Moderation (DIM) library API ============================================== diff --git a/include/linux/dim.h b/include/linux/dim.h index 43398f5eade2..e0f39bd85432 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,8 @@ #include #include +struct net_device; + /* Number of DIM profiles and period mode. */ #define NET_DIM_PARAMS_NUM_PROFILES 5 #define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 @@ -45,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -198,6 +233,29 @@ enum dim_step_result { DIM_ON_EDGE, }; +/** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6fd9107d3cc0..959196af7f5a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4e81660b4462..cc18acd3c58b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2402,6 +2402,9 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b49b804b9495..d15856c7e001 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -415,12 +415,34 @@ enum { ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_RX_PROFILE, + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_TX_PROFILE, /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) }; +enum { + ETHTOOL_A_PROFILE_UNSPEC, + /* nest, _A_IRQ_MODERATION_* */ + ETHTOOL_A_PROFILE_IRQ_MODERATION, + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + /* PAUSE */ enum { diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 67d5beb34dc3..0cd41277c7a3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include +#include /* * Net DIM profiles: @@ -95,6 +96,75 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) diff --git a/net/Kconfig b/net/Kconfig index 9fe65fa26e48..d27d0deac0bf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -508,6 +508,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..759b16e3d134 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; + struct dim_irq_moder *moder = req_base->dev->irq_moder; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!moder) + return 0; + + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +337,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +570,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); -- cgit v1.2.3 From f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Mon, 27 May 2024 20:29:14 -0700 Subject: xfrm: support sending NAT keepalives in ESP in UDP states Add the ability to send out RFC-3948 NAT keepalives from the xfrm stack. To use, Userspace sets an XFRM_NAT_KEEPALIVE_INTERVAL integer property when creating XFRM outbound states which denotes the number of seconds between keepalive messages. Keepalive messages are sent from a per net delayed work which iterates over the xfrm states. The logic is guarded by the xfrm state spinlock due to the xfrm state walk iterator. Possible future enhancements: - Adding counters to keep track of sent keepalives. - deduplicate NAT keepalives between states sharing the same nat keepalive parameters. - provisioning hardware offloads for devices capable of implementing this. - revise xfrm state list to use an rcu list in order to avoid running this under spinlock. Suggested-by: Paul Wouters Tested-by: Paul Wouters Tested-by: Antony Antony Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/ipv6_stubs.h | 3 + include/net/netns/xfrm.h | 1 + include/net/xfrm.h | 10 ++ include/uapi/linux/xfrm.h | 1 + net/ipv6/af_inet6.c | 1 + net/ipv6/xfrm6_policy.c | 7 + net/xfrm/Makefile | 3 +- net/xfrm/xfrm_compat.c | 6 +- net/xfrm/xfrm_nat_keepalive.c | 292 ++++++++++++++++++++++++++++++++++++++++++ net/xfrm/xfrm_policy.c | 8 ++ net/xfrm/xfrm_state.c | 17 +++ net/xfrm/xfrm_user.c | 15 +++ 12 files changed, 361 insertions(+), 3 deletions(-) create mode 100644 net/xfrm/xfrm_nat_keepalive.c (limited to 'include/uapi/linux') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 485c39a89866..11cefd50704d 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -9,6 +9,7 @@ #include #include #include +#include /* structs from net/ip6_fib.h */ struct fib6_info; @@ -72,6 +73,8 @@ struct ipv6_stub { int (*output)(struct net *, struct sock *, struct sk_buff *)); struct net_device *(*ipv6_dev_find)(struct net *net, const struct in6_addr *addr, struct net_device *dev); + int (*ip6_xmit)(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, + __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 423b52eca908..d489d9250bff 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -83,6 +83,7 @@ struct netns_xfrm { spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; + struct delayed_work nat_keepalive_work; }; #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 77ebf5bcf0b9..46a214a76081 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -229,6 +229,10 @@ struct xfrm_state { struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; + /* NAT keepalive */ + u32 nat_keepalive_interval; /* seconds */ + time64_t nat_keepalive_expiration; + /* Data for care-of address */ xfrm_address_t *coaddr; @@ -2203,4 +2207,10 @@ static inline int register_xfrm_state_bpf(void) } #endif +int xfrm_nat_keepalive_init(unsigned short family); +void xfrm_nat_keepalive_fini(unsigned short family); +int xfrm_nat_keepalive_net_init(struct net *net); +int xfrm_nat_keepalive_net_fini(struct net *net); +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x); + #endif /* _NET_XFRM_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index d950d02ab791..f28701500714 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -321,6 +321,7 @@ enum xfrm_attr_type_t { XFRMA_IF_ID, /* __u32 */ XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ XFRMA_SA_DIR, /* __u8 */ + XFRMA_NAT_KEEPALIVE_INTERVAL, /* __u32 in seconds for NAT keepalive */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8041dc181bd4..2b893858b9a9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1060,6 +1060,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .nd_tbl = &nd_tbl, .ipv6_fragment = ip6_fragment, .ipv6_dev_find = ipv6_dev_find, + .ip6_xmit = ip6_xmit, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cc885d3aa9e5..6837ff05f11a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -284,8 +284,14 @@ int __init xfrm6_init(void) ret = register_pernet_subsys(&xfrm6_net_ops); if (ret) goto out_protocol; + + ret = xfrm_nat_keepalive_init(AF_INET6); + if (ret) + goto out_nat_keepalive; out: return ret; +out_nat_keepalive: + unregister_pernet_subsys(&xfrm6_net_ops); out_protocol: xfrm6_protocol_fini(); out_state: @@ -297,6 +303,7 @@ out_policy: void xfrm6_fini(void) { + xfrm_nat_keepalive_fini(AF_INET6); unregister_pernet_subsys(&xfrm6_net_ops); xfrm6_protocol_fini(); xfrm6_policy_fini(); diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 547cec77ba03..512e0b2f8514 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -13,7 +13,8 @@ endif obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ - xfrm_sysctl.o xfrm_replay.o xfrm_device.o + xfrm_sysctl.o xfrm_replay.o xfrm_device.o \ + xfrm_nat_keepalive.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 703d4172c7d7..91357ccaf4af 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -131,6 +131,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -280,9 +281,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: + case XFRMA_NAT_KEEPALIVE_INTERVAL: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -437,7 +439,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c new file mode 100644 index 000000000000..82f0a301683f --- /dev/null +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * xfrm_nat_keepalive.c + * + * (c) 2024 Eyal Birger + */ + +#include +#include +#include + +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv4); +#if IS_ENABLED(CONFIG_IPV6) +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv6); +#endif + +struct nat_keepalive { + struct net *net; + u16 family; + xfrm_address_t saddr; + xfrm_address_t daddr; + __be16 encap_sport; + __be16 encap_dport; + __u32 smark; +}; + +static void nat_keepalive_init(struct nat_keepalive *ka, struct xfrm_state *x) +{ + ka->net = xs_net(x); + ka->family = x->props.family; + ka->saddr = x->props.saddr; + ka->daddr = x->id.daddr; + ka->encap_sport = x->encap->encap_sport; + ka->encap_dport = x->encap->encap_dport; + ka->smark = xfrm_smark_get(0, x); +} + +static int nat_keepalive_send_ipv4(struct sk_buff *skb, + struct nat_keepalive *ka) +{ + struct net *net = ka->net; + struct flowi4 fl4; + struct rtable *rt; + struct sock *sk; + __u8 tos = 0; + int err; + + flowi4_init_output(&fl4, 0 /* oif */, skb->mark, tos, + RT_SCOPE_UNIVERSE, IPPROTO_UDP, 0, + ka->daddr.a4, ka->saddr.a4, ka->encap_dport, + ka->encap_sport, sock_net_uid(net, NULL)); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + skb_dst_set(skb, &rt->dst); + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv4); + sock_net_set(sk, net); + err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos); + sock_net_set(sk, &init_net); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int nat_keepalive_send_ipv6(struct sk_buff *skb, + struct nat_keepalive *ka, + struct udphdr *uh) +{ + struct net *net = ka->net; + struct dst_entry *dst; + struct flowi6 fl6; + struct sock *sk; + __wsum csum; + int err; + + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = csum_ipv6_magic(&ka->saddr.in6, &ka->daddr.in6, + skb->len, IPPROTO_UDP, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.saddr = ka->saddr.in6; + fl6.daddr = ka->daddr.in6; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.fl6_sport = ka->encap_sport; + fl6.fl6_dport = ka->encap_dport; + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv6); + sock_net_set(sk, net); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, &fl6, NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_dst_set(skb, dst); + err = ipv6_stub->ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0); + sock_net_set(sk, &init_net); + return err; +} +#endif + +static void nat_keepalive_send(struct nat_keepalive *ka) +{ + const int nat_ka_hdrs_len = max(sizeof(struct iphdr), + sizeof(struct ipv6hdr)) + + sizeof(struct udphdr); + const u8 nat_ka_payload = 0xFF; + int err = -EAFNOSUPPORT; + struct sk_buff *skb; + struct udphdr *uh; + + skb = alloc_skb(nat_ka_hdrs_len + sizeof(nat_ka_payload), GFP_ATOMIC); + if (unlikely(!skb)) + return; + + skb_reserve(skb, nat_ka_hdrs_len); + + skb_put_u8(skb, nat_ka_payload); + + uh = skb_push(skb, sizeof(*uh)); + uh->source = ka->encap_sport; + uh->dest = ka->encap_dport; + uh->len = htons(skb->len); + uh->check = 0; + + skb->mark = ka->smark; + + switch (ka->family) { + case AF_INET: + err = nat_keepalive_send_ipv4(skb, ka); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_send_ipv6(skb, ka, uh); + break; +#endif + } + if (err) + kfree_skb(skb); +} + +struct nat_keepalive_work_ctx { + time64_t next_run; + time64_t now; +}; + +static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr) +{ + struct nat_keepalive_work_ctx *ctx = ptr; + bool send_keepalive = false; + struct nat_keepalive ka; + time64_t next_run; + u32 interval; + int delta; + + interval = x->nat_keepalive_interval; + if (!interval) + return 0; + + spin_lock(&x->lock); + + delta = (int)(ctx->now - x->lastused); + if (delta < interval) { + x->nat_keepalive_expiration = ctx->now + interval - delta; + next_run = x->nat_keepalive_expiration; + } else if (x->nat_keepalive_expiration > ctx->now) { + next_run = x->nat_keepalive_expiration; + } else { + next_run = ctx->now + interval; + nat_keepalive_init(&ka, x); + send_keepalive = true; + } + + spin_unlock(&x->lock); + + if (send_keepalive) + nat_keepalive_send(&ka); + + if (!ctx->next_run || next_run < ctx->next_run) + ctx->next_run = next_run; + return 0; +} + +static void nat_keepalive_work(struct work_struct *work) +{ + struct nat_keepalive_work_ctx ctx; + struct xfrm_state_walk walk; + struct net *net; + + ctx.next_run = 0; + ctx.now = ktime_get_real_seconds(); + + net = container_of(work, struct net, xfrm.nat_keepalive_work.work); + xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL); + xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx); + xfrm_state_walk_done(&walk, net); + if (ctx.next_run) + schedule_delayed_work(&net->xfrm.nat_keepalive_work, + (ctx.next_run - ctx.now) * HZ); +} + +static int nat_keepalive_sk_init(struct sock * __percpu *socks, + unsigned short family) +{ + struct sock *sk; + int err, i; + + for_each_possible_cpu(i) { + err = inet_ctl_sock_create(&sk, family, SOCK_RAW, IPPROTO_UDP, + &init_net); + if (err < 0) + goto err; + + *per_cpu_ptr(socks, i) = sk; + } + + return 0; +err: + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); + return err; +} + +static void nat_keepalive_sk_fini(struct sock * __percpu *socks) +{ + int i; + + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); +} + +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x) +{ + struct net *net; + + if (!x->nat_keepalive_interval) + return; + + net = xs_net(x); + schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0); +} + +int __net_init xfrm_nat_keepalive_net_init(struct net *net) +{ + INIT_DELAYED_WORK(&net->xfrm.nat_keepalive_work, nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_net_fini(struct net *net) +{ + cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_init(unsigned short family) +{ + int err = -EAFNOSUPPORT; + + switch (family) { + case AF_INET: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv4, PF_INET); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv6, PF_INET6); + break; +#endif + } + + if (err) + pr_err("xfrm nat keepalive init: failed to init err:%d\n", err); + return err; +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_init); + +void xfrm_nat_keepalive_fini(unsigned short family) +{ + switch (family) { + case AF_INET: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv4); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv6); + break; +#endif + } +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_fini); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 475b904fe68b..6603d3bd171f 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4289,8 +4289,14 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out_sysctl; + rv = xfrm_nat_keepalive_net_init(net); + if (rv < 0) + goto out_nat_keepalive; + return 0; +out_nat_keepalive: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -4303,6 +4309,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + xfrm_nat_keepalive_net_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); @@ -4364,6 +4371,7 @@ void __init xfrm_init(void) #endif register_xfrm_state_bpf(); + xfrm_nat_keepalive_init(AF_INET); } #ifdef CONFIG_AUDITSYSCALL diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 649bb739df0d..abadc857cd45 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -715,6 +715,7 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; + xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); if (x->encap_sk) @@ -1453,6 +1454,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); + xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ @@ -2871,6 +2873,21 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, goto error; } + if (x->nat_keepalive_interval) { + if (x->dir != XFRM_SA_DIR_OUT) { + NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); + err = -EINVAL; + goto error; + } + + if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { + NL_SET_ERR_MSG(extack, + "NAT keepalive is only supported for UDP encapsulation"); + err = -EINVAL; + goto error; + } + } + error: return err; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e83c687bd64e..a552cfa623ea 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -833,6 +833,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_DIR]) x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + if (attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]) + x->nat_keepalive_interval = + nla_get_u32(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack); if (err) goto error; @@ -1288,6 +1292,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, } if (x->dir) ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + + if (x->nat_keepalive_interval) { + ret = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, + x->nat_keepalive_interval); + if (ret) + goto out; + } out: return ret; } @@ -3165,6 +3176,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3474,6 +3486,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->dir) l += nla_total_size(sizeof(x->dir)); + if (x->nat_keepalive_interval) + l += nla_total_size(sizeof(x->nat_keepalive_interval)); + return l; } -- cgit v1.2.3 From d1741141d03f8f5535adaf5a2d5000da3be9fe90 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:32 +0200 Subject: media: uapi: Add a pixel format for BGR48 and RGB48 Add BGR48 and RGB48 16-bit per component image formats. Signed-off-by: Jacopo Mondi Reviewed-by: Kieran Bingham Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-rgb.rst | 54 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-common.c | 2 + drivers/media/v4l2-core/v4l2-ioctl.c | 2 + include/uapi/linux/videodev2.h | 2 + 4 files changed, 60 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst b/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst index b71b80d634d6..5ed4d62df909 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-rgb.rst @@ -996,6 +996,60 @@ arranged in little endian order. \normalsize +16 Bits Per Component +===================== + +These formats store an RGB triplet in six bytes, with 16 bits per component +stored in memory in little endian byte order. They are named based on the order +of the RGB components as stored in memory. For instance, RGB48 stores R\ +:sub:`7:0` and R\ :sub:`15:8` in bytes 0 and 1 respectively. This differs from +the DRM format nomenclature that instead uses the order of components as seen in +the 48-bits little endian word. + +.. raw:: latex + + \small + +.. flat-table:: RGB Formats With 16 Bits Per Component + :header-rows: 1 + + * - Identifier + - Code + - Byte 0 + - Byte 1 + - Byte 2 + - Byte 3 + - Byte 4 + - Byte 5 + + * .. _V4L2-PIX-FMT-BGR48: + + - ``V4L2_PIX_FMT_BGR48`` + - 'BGR6' + + - B\ :sub:`7-0` + - B\ :sub:`15-8` + - G\ :sub:`7-0` + - G\ :sub:`15-8` + - R\ :sub:`7-0` + - R\ :sub:`15-8` + + * .. _V4L2-PIX-FMT-RGB48: + + - ``V4L2_PIX_FMT_RGB48`` + - 'RGB6' + + - R\ :sub:`7-0` + - R\ :sub:`15-8` + - G\ :sub:`7-0` + - G\ :sub:`15-8` + - B\ :sub:`7-0` + - B\ :sub:`15-8` + +.. raw:: latex + + \normalsize + Deprecated RGB Formats ====================== diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 4165c815faef..0a2f4f0d0a07 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -253,6 +253,8 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) { .format = V4L2_PIX_FMT_RGB555, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_BGR666, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_BGR48_12, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_BGR48, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_RGB48, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 6, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_ABGR64_12, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 8, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_RGBA1010102, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_RGBX1010102, .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 4c76d17b4629..ee97643ff3a7 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1307,6 +1307,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_RGBX1010102: descr = "32-bit RGBX 10-10-10-2"; break; case V4L2_PIX_FMT_RGBA1010102: descr = "32-bit RGBA 10-10-10-2"; break; case V4L2_PIX_FMT_ARGB2101010: descr = "32-bit ARGB 2-10-10-10"; break; + case V4L2_PIX_FMT_BGR48: descr = "48-bit BGR 16-16-16"; break; + case V4L2_PIX_FMT_RGB48: descr = "48-bit RGB 16-16-16"; break; case V4L2_PIX_FMT_BGR48_12: descr = "12-bit Depth BGR"; break; case V4L2_PIX_FMT_ABGR64_12: descr = "12-bit Depth BGRA"; break; case V4L2_PIX_FMT_GREY: descr = "8-bit Greyscale"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index fe6b67e83751..dd6876380fe3 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -582,6 +582,8 @@ struct v4l2_pix_format { /* RGB formats (6 or 8 bytes per pixel) */ #define V4L2_PIX_FMT_BGR48_12 v4l2_fourcc('B', '3', '1', '2') /* 48 BGR 12-bit per component */ +#define V4L2_PIX_FMT_BGR48 v4l2_fourcc('B', 'G', 'R', '6') /* 48 BGR 16-bit per component */ +#define V4L2_PIX_FMT_RGB48 v4l2_fourcc('R', 'G', 'B', '6') /* 48 RGB 16-bit per component */ #define V4L2_PIX_FMT_ABGR64_12 v4l2_fourcc('B', '4', '1', '2') /* 64 BGRA 12-bit per component */ /* Grey formats */ -- cgit v1.2.3 From c6c49bac8770ef95518faf20083e8b3e6150f45f Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:33 +0200 Subject: media: uapi: Add Raspberry Pi PiSP Back End uAPI Add the Raspberry Pi PiSP Back End uAPI header. The header defines the data type used to configure the PiSP Back End ISP. The detailed description of the types and of the ISP configuration procedure is available at https://datasheets.raspberrypi.com/camera/raspberry-pi-image-signal-processor-specification.pdf Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- MAINTAINERS | 7 + .../uapi/linux/media/raspberrypi/pisp_be_config.h | 927 +++++++++++++++++++++ include/uapi/linux/media/raspberrypi/pisp_common.h | 199 +++++ 3 files changed, 1133 insertions(+) create mode 100644 include/uapi/linux/media/raspberrypi/pisp_be_config.h create mode 100644 include/uapi/linux/media/raspberrypi/pisp_common.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index ad1ecb2c4aed..861ee24cc1f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18805,6 +18805,13 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/ras/amd/fmpm.c +RASPBERRY PI PISP BACK END +M: Jacopo Mondi +L: Raspberry Pi Kernel Maintenance +L: linux-media@vger.kernel.org +S: Maintained +F: include/uapi/linux/media/raspberrypi/ + RC-CORE / LIRC FRAMEWORK M: Sean Young L: linux-media@vger.kernel.org diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h new file mode 100644 index 000000000000..1684ae068d4f --- /dev/null +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -0,0 +1,927 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * PiSP Back End configuration definitions. + * + * Copyright (C) 2021 - Raspberry Pi Ltd + * + */ +#ifndef _UAPI_PISP_BE_CONFIG_H_ +#define _UAPI_PISP_BE_CONFIG_H_ + +#include + +#include "pisp_common.h" + +/* byte alignment for inputs */ +#define PISP_BACK_END_INPUT_ALIGN 4u +/* alignment for compressed inputs */ +#define PISP_BACK_END_COMPRESSED_ALIGN 8u +/* minimum required byte alignment for outputs */ +#define PISP_BACK_END_OUTPUT_MIN_ALIGN 16u +/* preferred byte alignment for outputs */ +#define PISP_BACK_END_OUTPUT_MAX_ALIGN 64u + +/* minimum allowed tile width anywhere in the pipeline */ +#define PISP_BACK_END_MIN_TILE_WIDTH 16u +/* minimum allowed tile width anywhere in the pipeline */ +#define PISP_BACK_END_MIN_TILE_HEIGHT 16u + +#define PISP_BACK_END_NUM_OUTPUTS 2 +#define PISP_BACK_END_HOG_OUTPUT 1 + +#define PISP_BACK_END_NUM_TILES 64 + +enum pisp_be_bayer_enable { + PISP_BE_BAYER_ENABLE_INPUT = 0x000001, + PISP_BE_BAYER_ENABLE_DECOMPRESS = 0x000002, + PISP_BE_BAYER_ENABLE_DPC = 0x000004, + PISP_BE_BAYER_ENABLE_GEQ = 0x000008, + PISP_BE_BAYER_ENABLE_TDN_INPUT = 0x000010, + PISP_BE_BAYER_ENABLE_TDN_DECOMPRESS = 0x000020, + PISP_BE_BAYER_ENABLE_TDN = 0x000040, + PISP_BE_BAYER_ENABLE_TDN_COMPRESS = 0x000080, + PISP_BE_BAYER_ENABLE_TDN_OUTPUT = 0x000100, + PISP_BE_BAYER_ENABLE_SDN = 0x000200, + PISP_BE_BAYER_ENABLE_BLC = 0x000400, + PISP_BE_BAYER_ENABLE_STITCH_INPUT = 0x000800, + PISP_BE_BAYER_ENABLE_STITCH_DECOMPRESS = 0x001000, + PISP_BE_BAYER_ENABLE_STITCH = 0x002000, + PISP_BE_BAYER_ENABLE_STITCH_COMPRESS = 0x004000, + PISP_BE_BAYER_ENABLE_STITCH_OUTPUT = 0x008000, + PISP_BE_BAYER_ENABLE_WBG = 0x010000, + PISP_BE_BAYER_ENABLE_CDN = 0x020000, + PISP_BE_BAYER_ENABLE_LSC = 0x040000, + PISP_BE_BAYER_ENABLE_TONEMAP = 0x080000, + PISP_BE_BAYER_ENABLE_CAC = 0x100000, + PISP_BE_BAYER_ENABLE_DEBIN = 0x200000, + PISP_BE_BAYER_ENABLE_DEMOSAIC = 0x400000, +}; + +enum pisp_be_rgb_enable { + PISP_BE_RGB_ENABLE_INPUT = 0x000001, + PISP_BE_RGB_ENABLE_CCM = 0x000002, + PISP_BE_RGB_ENABLE_SAT_CONTROL = 0x000004, + PISP_BE_RGB_ENABLE_YCBCR = 0x000008, + PISP_BE_RGB_ENABLE_FALSE_COLOUR = 0x000010, + PISP_BE_RGB_ENABLE_SHARPEN = 0x000020, + /* Preferred colours would occupy 0x000040 */ + PISP_BE_RGB_ENABLE_YCBCR_INVERSE = 0x000080, + PISP_BE_RGB_ENABLE_GAMMA = 0x000100, + PISP_BE_RGB_ENABLE_CSC0 = 0x000200, + PISP_BE_RGB_ENABLE_CSC1 = 0x000400, + PISP_BE_RGB_ENABLE_DOWNSCALE0 = 0x001000, + PISP_BE_RGB_ENABLE_DOWNSCALE1 = 0x002000, + PISP_BE_RGB_ENABLE_RESAMPLE0 = 0x008000, + PISP_BE_RGB_ENABLE_RESAMPLE1 = 0x010000, + PISP_BE_RGB_ENABLE_OUTPUT0 = 0x040000, + PISP_BE_RGB_ENABLE_OUTPUT1 = 0x080000, + PISP_BE_RGB_ENABLE_HOG = 0x200000 +}; + +#define PISP_BE_RGB_ENABLE_CSC(i) (PISP_BE_RGB_ENABLE_CSC0 << (i)) +#define PISP_BE_RGB_ENABLE_DOWNSCALE(i) (PISP_BE_RGB_ENABLE_DOWNSCALE0 << (i)) +#define PISP_BE_RGB_ENABLE_RESAMPLE(i) (PISP_BE_RGB_ENABLE_RESAMPLE0 << (i)) +#define PISP_BE_RGB_ENABLE_OUTPUT(i) (PISP_BE_RGB_ENABLE_OUTPUT0 << (i)) + +/* + * We use the enable flags to show when blocks are "dirty", but we need some + * extra ones too. + */ +enum pisp_be_dirty { + PISP_BE_DIRTY_GLOBAL = 0x0001, + PISP_BE_DIRTY_SH_FC_COMBINE = 0x0002, + PISP_BE_DIRTY_CROP = 0x0004 +}; + +/** + * struct pisp_be_global_config - PiSP global enable bitmaps + * @bayer_enables: Bayer input enable flags + * @rgb_enables: RGB output enable flags + * @bayer_order: Bayer input format ordering + * @pad: Padding bytes + */ +struct pisp_be_global_config { + __u32 bayer_enables; + __u32 rgb_enables; + __u8 bayer_order; + __u8 pad[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_input_buffer_config - PiSP Back End input buffer + * @addr: Input buffer address + */ +struct pisp_be_input_buffer_config { + /* low 32 bits followed by high 32 bits (for each of up to 3 planes) */ + __u32 addr[3][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_dpc_config - PiSP Back End DPC config + * + * Defective Pixel Correction configuration + * + * @coeff_level: Coefficient for the darkest neighbouring pixel value + * @coeff_range: Coefficient for the range of pixels for this Bayer channel + * @pad: Padding byte + * @flags: DPC configuration flags + */ +struct pisp_be_dpc_config { + __u8 coeff_level; + __u8 coeff_range; + __u8 pad; +#define PISP_BE_DPC_FLAG_FOLDBACK 1 + __u8 flags; +} __attribute__((packed)); + +/** + * struct pisp_be_geq_config - PiSP Back End GEQ config + * + * Green Equalisation configuration + * + * @offset: Offset value for threshold calculation + * @slope_sharper: Slope/Sharper configuration + * @min: Minimum value the threshold may have + * @max: Maximum value the threshold may have + */ +struct pisp_be_geq_config { + __u16 offset; +#define PISP_BE_GEQ_SHARPER BIT(15) +#define PISP_BE_GEQ_SLOPE ((1 << 10) - 1) + /* top bit is the "sharper" flag, slope value is bottom 10 bits */ + __u16 slope_sharper; + __u16 min; + __u16 max; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_input_buffer_config - PiSP Back End TDN input buffer + * @addr: TDN input buffer address + */ +struct pisp_be_tdn_input_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_config - PiSP Back End TDN config + * + * Temporal Denoise configuration + * + * @black_level: Black level value subtracted from pixels + * @ratio: Multiplier for the LTA input frame + * @noise_constant: Constant offset value used in noise estimation + * @noise_slope: Noise estimation multiplier + * @threshold: Threshold for TDN operations + * @reset: Disable TDN operations + * @pad: Padding byte + */ +struct pisp_be_tdn_config { + __u16 black_level; + __u16 ratio; + __u16 noise_constant; + __u16 noise_slope; + __u16 threshold; + __u8 reset; + __u8 pad; +} __attribute__((packed)); + +/** + * struct pisp_be_tdn_output_buffer_config - PiSP Back End TDN output buffer + * @addr: TDN output buffer address + */ +struct pisp_be_tdn_output_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_sdn_config - PiSP Back End SDN config + * + * Spatial Denoise configuration + * + * @black_level: Black level subtracted from pixel for noise estimation + * @leakage: Proportion of the original undenoised value to mix in + * denoised output + * @pad: Padding byte + * @noise_constant: Noise constant used for noise estimation + * @noise_slope: Noise slope value used for noise estimation + * @noise_constant2: Second noise constant used for noise estimation + * @noise_slope2: Second slope value used for noise estimation + */ +struct pisp_be_sdn_config { + __u16 black_level; + __u8 leakage; + __u8 pad; + __u16 noise_constant; + __u16 noise_slope; + __u16 noise_constant2; + __u16 noise_slope2; +} __attribute__((packed)); + +/** + * struct pisp_be_stitch_input_buffer_config - PiSP Back End Stitch input + * @addr: Stitch input buffer address + */ +struct pisp_be_stitch_input_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +#define PISP_BE_STITCH_STREAMING_LONG 0x8000 +#define PISP_BE_STITCH_EXPOSURE_RATIO_MASK 0x7fff + +/** + * struct pisp_be_stitch_config - PiSP Back End Stitch config + * + * Stitch block configuration + * + * @threshold_lo: Low threshold value + * @threshold_diff_power: Low and high threshold difference + * @pad: Padding bytes + * @exposure_ratio: Multiplier to convert long exposure pixels into + * short exposure pixels + * @motion_threshold_256: Motion threshold above which short exposure + * pixels are used + * @motion_threshold_recip: Reciprocal of motion_threshold_256 value + */ +struct pisp_be_stitch_config { + __u16 threshold_lo; + __u8 threshold_diff_power; + __u8 pad; + + /* top bit indicates whether streaming input is the long exposure */ + __u16 exposure_ratio; + + __u8 motion_threshold_256; + __u8 motion_threshold_recip; +} __attribute__((packed)); + +/** + * struct pisp_be_stitch_output_buffer_config - PiSP Back End Stitch output + * @addr: Stitch input buffer address + */ +struct pisp_be_stitch_output_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_cdn_config - PiSP Back End CDN config + * + * Colour Denoise configuration + * + * @thresh: Constant for noise estimation + * @iir_strength: Relative strength of the IIR part of the filter + * @g_adjust: Proportion of the change assigned to the G channel + */ +struct pisp_be_cdn_config { + __u16 thresh; + __u8 iir_strength; + __u8 g_adjust; +} __attribute__((packed)); + +#define PISP_BE_LSC_LOG_GRID_SIZE 5 +#define PISP_BE_LSC_GRID_SIZE (1 << PISP_BE_LSC_LOG_GRID_SIZE) +#define PISP_BE_LSC_STEP_PRECISION 18 + +/** + * struct pisp_be_lsc_config - PiSP Back End LSC config + * + * Lens Shading Correction configuration + * + * @grid_step_x: Reciprocal of cell size width + * @grid_step_y: Reciprocal of cell size height + * @lut_packed: Jointly-coded RGB gains for each LSC grid + */ +struct pisp_be_lsc_config { + /* (1<<18) / grid_cell_width */ + __u16 grid_step_x; + /* (1<<18) / grid_cell_height */ + __u16 grid_step_y; + /* RGB gains jointly encoded in 32 bits */ +#define PISP_BE_LSC_LUT_SIZE (PISP_BE_LSC_GRID_SIZE + 1) + __u32 lut_packed[PISP_BE_LSC_LUT_SIZE][PISP_BE_LSC_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_lsc_extra - PiSP Back End LSC Extra config + * @offset_x: Horizontal offset into the LSC table of this tile + * @offset_y: Vertical offset into the LSC table of this tile + */ +struct pisp_be_lsc_extra { + __u16 offset_x; + __u16 offset_y; +} __attribute__((packed)); + +#define PISP_BE_CAC_LOG_GRID_SIZE 3 +#define PISP_BE_CAC_GRID_SIZE (1 << PISP_BE_CAC_LOG_GRID_SIZE) +#define PISP_BE_CAC_STEP_PRECISION 20 + +/** + * struct pisp_be_cac_config - PiSP Back End CAC config + * + * Chromatic Aberration Correction config + * + * @grid_step_x: Reciprocal of cell size width + * @grid_step_y: Reciprocal of cell size height + * @lut: Pixel shift for the CAC grid + */ +struct pisp_be_cac_config { + /* (1<<20) / grid_cell_width */ + __u16 grid_step_x; + /* (1<<20) / grid_cell_height */ + __u16 grid_step_y; + /* [gridy][gridx][rb][xy] */ +#define PISP_BE_CAC_LUT_SIZE (PISP_BE_CAC_GRID_SIZE + 1) + __s8 lut[PISP_BE_CAC_LUT_SIZE][PISP_BE_CAC_LUT_SIZE][2][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_cac_extra - PiSP Back End CAC extra config + * @offset_x: Horizontal offset into the CAC table of this tile + * @offset_y: Horizontal offset into the CAC table of this tile + */ +struct pisp_be_cac_extra { + __u16 offset_x; + __u16 offset_y; +} __attribute__((packed)); + +#define PISP_BE_DEBIN_NUM_COEFFS 4 + +/** + * struct pisp_be_debin_config - PiSP Back End Debin config + * + * Debinning configuration + * + * @coeffs: Filter coefficients for debinning + * @h_enable: Horizontal debinning enable + * @v_enable: Vertical debinning enable + * @pad: Padding bytes + */ +struct pisp_be_debin_config { + __s8 coeffs[PISP_BE_DEBIN_NUM_COEFFS]; + __s8 h_enable; + __s8 v_enable; + __s8 pad[2]; +} __attribute__((packed)); + +#define PISP_BE_TONEMAP_LUT_SIZE 64 + +/** + * struct pisp_be_tonemap_config - PiSP Back End Tonemap config + * + * Tonemapping configuration + * + * @detail_constant: Constant value for threshold calculation + * @detail_slope: Slope value for threshold calculation + * @iir_strength: Relative strength of the IIR fiter + * @strength: Strength factor + * @lut: Look-up table for tonemap curve + */ +struct pisp_be_tonemap_config { + __u16 detail_constant; + __u16 detail_slope; + __u16 iir_strength; + __u16 strength; + __u32 lut[PISP_BE_TONEMAP_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_demosaic_config - PiSP Back End Demosaic config + * + * Demosaic configuration + * + * @sharper: Use other Bayer channels to increase sharpness + * @fc_mode: Built-in false colour suppression mode + * @pad: Padding bytes + */ +struct pisp_be_demosaic_config { + __u8 sharper; + __u8 fc_mode; + __u8 pad[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_ccm_config - PiSP Back End CCM config + * + * Colour Correction Matrix configuration + * + * @coeffs: Matrix coefficients + * @pad: Padding bytes + * @offsets: Offsets triplet + */ +struct pisp_be_ccm_config { + __s16 coeffs[9]; + __u8 pad[2]; + __s32 offsets[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_sat_control_config - PiSP Back End SAT config + * + * Saturation Control configuration + * + * @shift_r: Left shift for Red colour channel + * @shift_g: Left shift for Green colour channel + * @shift_b: Left shift for Blue colour channel + * @pad: Padding byte + */ +struct pisp_be_sat_control_config { + __u8 shift_r; + __u8 shift_g; + __u8 shift_b; + __u8 pad; +} __attribute__((packed)); + +/** + * struct pisp_be_false_colour_config - PiSP Back End False Colour config + * + * False Colour configuration + * + * @distance: Distance of neighbouring pixels, either 1 or 2 + * @pad: Padding bytes + */ +struct pisp_be_false_colour_config { + __u8 distance; + __u8 pad[3]; +} __attribute__((packed)); + +#define PISP_BE_SHARPEN_SIZE 5 +#define PISP_BE_SHARPEN_FUNC_NUM_POINTS 9 + +/** + * struct pisp_be_sharpen_config - PiSP Back End Sharpening config + * + * Sharpening configuration + * + * @kernel0: Coefficient for filter 0 + * @pad0: Padding byte + * @kernel1: Coefficient for filter 1 + * @pad1: Padding byte + * @kernel2: Coefficient for filter 2 + * @pad2: Padding byte + * @kernel3: Coefficient for filter 3 + * @pad3: Padding byte + * @kernel4: Coefficient for filter 4 + * @pad4: Padding byte + * @threshold_offset0: Offset for filter 0 response calculation + * @threshold_slope0: Slope multiplier for the filter 0 response calculation + * @scale0: Scale factor for filter 0 response calculation + * @pad5: Padding byte + * @threshold_offset1: Offset for filter 0 response calculation + * @threshold_slope1: Slope multiplier for the filter 0 response calculation + * @scale1: Scale factor for filter 0 response calculation + * @pad6: Padding byte + * @threshold_offset2: Offset for filter 0 response calculation + * @threshold_slope2: Slope multiplier for the filter 0 response calculation + * @scale2: Scale factor for filter 0 response calculation + * @pad7: Padding byte + * @threshold_offset3: Offset for filter 0 response calculation + * @threshold_slope3: Slope multiplier for the filter 0 response calculation + * @scale3: Scale factor for filter 0 response calculation + * @pad8: Padding byte + * @threshold_offset4: Offset for filter 0 response calculation + * @threshold_slope4: Slope multiplier for the filter 0 response calculation + * @scale4: Scale factor for filter 0 response calculation + * @pad9: Padding byte + * @positive_strength: Factor to scale the positive sharpening strength + * @positive_pre_limit: Maximum allowed possible positive sharpening value + * @positive_func: Gain factor applied to positive sharpening response + * @positive_limit: Final gain factor applied to positive sharpening + * @negative_strength: Factor to scale the negative sharpening strength + * @negative_pre_limit: Maximum allowed possible negative sharpening value + * @negative_func: Gain factor applied to negative sharpening response + * @negative_limit: Final gain factor applied to negative sharpening + * @enables: Filter enable mask + * @white: White output pixel filter mask + * @black: Black output pixel filter mask + * @grey: Grey output pixel filter mask + */ +struct pisp_be_sharpen_config { + __s8 kernel0[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad0[3]; + __s8 kernel1[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad1[3]; + __s8 kernel2[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad2[3]; + __s8 kernel3[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad3[3]; + __s8 kernel4[PISP_BE_SHARPEN_SIZE * PISP_BE_SHARPEN_SIZE]; + __s8 pad4[3]; + __u16 threshold_offset0; + __u16 threshold_slope0; + __u16 scale0; + __u16 pad5; + __u16 threshold_offset1; + __u16 threshold_slope1; + __u16 scale1; + __u16 pad6; + __u16 threshold_offset2; + __u16 threshold_slope2; + __u16 scale2; + __u16 pad7; + __u16 threshold_offset3; + __u16 threshold_slope3; + __u16 scale3; + __u16 pad8; + __u16 threshold_offset4; + __u16 threshold_slope4; + __u16 scale4; + __u16 pad9; + __u16 positive_strength; + __u16 positive_pre_limit; + __u16 positive_func[PISP_BE_SHARPEN_FUNC_NUM_POINTS]; + __u16 positive_limit; + __u16 negative_strength; + __u16 negative_pre_limit; + __u16 negative_func[PISP_BE_SHARPEN_FUNC_NUM_POINTS]; + __u16 negative_limit; + __u8 enables; + __u8 white; + __u8 black; + __u8 grey; +} __attribute__((packed)); + +/** + * struct pisp_be_sh_fc_combine_config - PiSP Back End Sharpening and + * False Colour config + * + * Sharpening and False Colour configuration + * + * @y_factor: Control amount of desaturation of pixels being darkened + * @c1_factor: Control amount of brightening of a pixel for the Cb + * channel + * @c2_factor: Control amount of brightening of a pixel for the Cr + * channel + * @pad: Padding byte + */ +struct pisp_be_sh_fc_combine_config { + __u8 y_factor; + __u8 c1_factor; + __u8 c2_factor; + __u8 pad; +} __attribute__((packed)); + +#define PISP_BE_GAMMA_LUT_SIZE 64 + +/** + * struct pisp_be_gamma_config - PiSP Back End Gamma configuration + * @lut: Gamma curve look-up table + */ +struct pisp_be_gamma_config { + __u32 lut[PISP_BE_GAMMA_LUT_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_crop_config - PiSP Back End Crop config + * + * Crop configuration + * + * @offset_x: Number of pixels cropped from the left of the tile + * @offset_y: Number of pixels cropped from the top of the tile + * @width: Width of the cropped tile output + * @height: Height of the cropped tile output + */ +struct pisp_be_crop_config { + __u16 offset_x, offset_y; + __u16 width, height; +} __attribute__((packed)); + +#define PISP_BE_RESAMPLE_FILTER_SIZE 96 + +/** + * struct pisp_be_resample_config - PiSP Back End Resampling config + * + * Resample configuration + * + * @scale_factor_h: Horizontal scale factor + * @scale_factor_v: Vertical scale factor + * @coef: Resample coefficients + */ +struct pisp_be_resample_config { + __u16 scale_factor_h, scale_factor_v; + __s16 coef[PISP_BE_RESAMPLE_FILTER_SIZE]; +} __attribute__((packed)); + +/** + * struct pisp_be_resample_extra - PiSP Back End Resample config + * + * Resample configuration + * + * @scaled_width: Width in pixels of the scaled output + * @scaled_height: Height in pixels of the scaled output + * @initial_phase_h: Initial horizontal phase + * @initial_phase_v: Initial vertical phase + */ +struct pisp_be_resample_extra { + __u16 scaled_width; + __u16 scaled_height; + __s16 initial_phase_h[3]; + __s16 initial_phase_v[3]; +} __attribute__((packed)); + +/** + * struct pisp_be_downscale_config - PiSP Back End Downscale config + * + * Downscale configuration + * + * @scale_factor_h: Horizontal scale factor + * @scale_factor_v: Vertical scale factor + * @scale_recip_h: Horizontal reciprocal factor + * @scale_recip_v: Vertical reciprocal factor + */ +struct pisp_be_downscale_config { + __u16 scale_factor_h; + __u16 scale_factor_v; + __u16 scale_recip_h; + __u16 scale_recip_v; +} __attribute__((packed)); + +/** + * struct pisp_be_downscale_extra - PiSP Back End Downscale Extra config + * @scaled_width: Scaled image width + * @scaled_height: Scaled image height + */ +struct pisp_be_downscale_extra { + __u16 scaled_width; + __u16 scaled_height; +} __attribute__((packed)); + +/** + * struct pisp_be_hog_config - PiSP Back End HOG config + * + * Histogram of Oriented Gradients configuration + * + * @compute_signed: Set 0 for unsigned gradients, 1 for signed + * @channel_mix: Channels proportions to use + * @stride: Stride in bytes between blocks directly below + */ +struct pisp_be_hog_config { + __u8 compute_signed; + __u8 channel_mix[3]; + __u32 stride; +} __attribute__((packed)); + +struct pisp_be_axi_config { + __u8 r_qos; /* Read QoS */ + __u8 r_cache_prot; /* Read { prot[2:0], cache[3:0] } */ + __u8 w_qos; /* Write QoS */ + __u8 w_cache_prot; /* Write { prot[2:0], cache[3:0] } */ +} __attribute__((packed)); + +/** + * enum pisp_be_transform - PiSP Back End Transform flags + * @PISP_BE_TRANSFORM_NONE: No transform + * @PISP_BE_TRANSFORM_HFLIP: Horizontal flip + * @PISP_BE_TRANSFORM_VFLIP: Vertical flip + * @PISP_BE_TRANSFORM_ROT180: 180 degress rotation + */ +enum pisp_be_transform { + PISP_BE_TRANSFORM_NONE = 0x0, + PISP_BE_TRANSFORM_HFLIP = 0x1, + PISP_BE_TRANSFORM_VFLIP = 0x2, + PISP_BE_TRANSFORM_ROT180 = + (PISP_BE_TRANSFORM_HFLIP | PISP_BE_TRANSFORM_VFLIP) +}; + +struct pisp_be_output_format_config { + struct pisp_image_format_config image; + __u8 transform; + __u8 pad[3]; + __u16 lo; + __u16 hi; + __u16 lo2; + __u16 hi2; +} __attribute__((packed)); + +/** + * struct pisp_be_output_buffer_config - PiSP Back End Output buffer + * @addr: Output buffer address + */ +struct pisp_be_output_buffer_config { + /* low 32 bits followed by high 32 bits (for each of 3 planes) */ + __u32 addr[3][2]; +} __attribute__((packed)); + +/** + * struct pisp_be_hog_buffer_config - PiSP Back End HOG buffer + * @addr: HOG buffer address + */ +struct pisp_be_hog_buffer_config { + /* low 32 bits followed by high 32 bits */ + __u32 addr[2]; +} __attribute__((packed)); + +/** + * struct pisp_be_config - RaspberryPi PiSP Back End Processing configuration + * + * @global: Global PiSP configuration + * @input_format: Input image format + * @decompress: Decompress configuration + * @dpc: Defective Pixel Correction configuration + * @geq: Green Equalisation configuration + * @tdn_input_format: Temporal Denoise input format + * @tdn_decompress: Temporal Denoise decompress configuration + * @tdn: Temporal Denoise configuration + * @tdn_compress: Temporal Denoise compress configuration + * @tdn_output_format: Temporal Denoise output format + * @sdn: Spatial Denoise configuration + * @blc: Black Level Correction configuration + * @stitch_compress: Stitch compress configuration + * @stitch_output_format: Stitch output format + * @stitch_input_format: Stitch input format + * @stitch_decompress: Stitch decompress configuration + * @stitch: Stitch configuration + * @lsc: Lens Shading Correction configuration + * @wbg: White Balance Gain configuration + * @cdn: Colour Denoise configuration + * @cac: Colour Aberration Correction configuration + * @debin: Debinning configuration + * @tonemap: Tonemapping configuration + * @demosaic: Demosaicing configuration + * @ccm: Colour Correction Matrix configuration + * @sat_control: Saturation Control configuration + * @ycbcr: YCbCr colour correction configuration + * @sharpen: Sharpening configuration + * @false_colour: False colour correction + * @sh_fc_combine: Sharpening and False Colour correction + * @ycbcr_inverse: Inverse YCbCr colour correction + * @gamma: Gamma curve configuration + * @csc: Color Space Conversion configuration + * @downscale: Downscale configuration + * @resample: Resampling configuration + * @output_format: Output format configuration + * @hog: HOG configuration + */ +struct pisp_be_config { + struct pisp_be_global_config global; + struct pisp_image_format_config input_format; + struct pisp_decompress_config decompress; + struct pisp_be_dpc_config dpc; + struct pisp_be_geq_config geq; + struct pisp_image_format_config tdn_input_format; + struct pisp_decompress_config tdn_decompress; + struct pisp_be_tdn_config tdn; + struct pisp_compress_config tdn_compress; + struct pisp_image_format_config tdn_output_format; + struct pisp_be_sdn_config sdn; + struct pisp_bla_config blc; + struct pisp_compress_config stitch_compress; + struct pisp_image_format_config stitch_output_format; + struct pisp_image_format_config stitch_input_format; + struct pisp_decompress_config stitch_decompress; + struct pisp_be_stitch_config stitch; + struct pisp_be_lsc_config lsc; + struct pisp_wbg_config wbg; + struct pisp_be_cdn_config cdn; + struct pisp_be_cac_config cac; + struct pisp_be_debin_config debin; + struct pisp_be_tonemap_config tonemap; + struct pisp_be_demosaic_config demosaic; + struct pisp_be_ccm_config ccm; + struct pisp_be_sat_control_config sat_control; + struct pisp_be_ccm_config ycbcr; + struct pisp_be_sharpen_config sharpen; + struct pisp_be_false_colour_config false_colour; + struct pisp_be_sh_fc_combine_config sh_fc_combine; + struct pisp_be_ccm_config ycbcr_inverse; + struct pisp_be_gamma_config gamma; + struct pisp_be_ccm_config csc[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_downscale_config downscale[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_resample_config resample[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_output_format_config + output_format[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_hog_config hog; +} __attribute__((packed)); + +/** + * enum pisp_tile_edge - PiSP Back End Tile position + * @PISP_LEFT_EDGE: Left edge tile + * @PISP_RIGHT_EDGE: Right edge tile + * @PISP_TOP_EDGE: Top edge tile + * @PISP_BOTTOM_EDGE: Bottom edge tile + */ +enum pisp_tile_edge { + PISP_LEFT_EDGE = (1 << 0), + PISP_RIGHT_EDGE = (1 << 1), + PISP_TOP_EDGE = (1 << 2), + PISP_BOTTOM_EDGE = (1 << 3) +}; + +/** + * struct pisp_tile - Raspberry Pi PiSP Back End tile configuration + * + * Tile parameters: each set of tile parameters is a 160-bytes block of data + * which contains the tile processing parameters. + * + * @edge: Edge tile flag + * @pad0: Padding bytes + * @input_addr_offset: Top-left pixel offset, in bytes + * @input_addr_offset2: Top-left pixel offset, in bytes for the second/ + * third image planes + * @input_offset_x: Horizontal offset in pixels of this tile in the + * input image + * @input_offset_y: Vertical offset in pixels of this tile in the + * input image + * @input_width: Width in pixels of this tile + * @input_height: Height in pixels of the this tile + * @tdn_input_addr_offset: TDN input image offset, in bytes + * @tdn_output_addr_offset: TDN output image offset, in bytes + * @stitch_input_addr_offset: Stitch input image offset, in bytes + * @stitch_output_addr_offset: Stitch output image offset, in bytes + * @lsc_grid_offset_x: Horizontal offset in the LSC table for this tile + * @lsc_grid_offset_y: Vertical offset in the LSC table for this tile + * @cac_grid_offset_x: Horizontal offset in the CAC table for this tile + * @cac_grid_offset_y: Horizontal offset in the CAC table for this tile + * @crop_x_start: Number of pixels cropped from the left of the + * tile + * @crop_x_end: Number of pixels cropped from the right of the + * tile + * @crop_y_start: Number of pixels cropped from the top of the + * tile + * @crop_y_end: Number of pixels cropped from the bottom of the + * tile + * @downscale_phase_x: Initial horizontal phase in pixels + * @downscale_phase_y: Initial vertical phase in pixels + * @resample_in_width: Width in pixels of the tile entering the + * Resample block + * @resample_in_height: Height in pixels of the tile entering the + * Resample block + * @resample_phase_x: Initial horizontal phase for the Resample block + * @resample_phase_y: Initial vertical phase for the Resample block + * @output_offset_x: Horizontal offset in pixels where the tile will + * be written into the output image + * @output_offset_y: Vertical offset in pixels where the tile will be + * written into the output image + * @output_width: Width in pixels in the output image of this tile + * @output_height: Height in pixels in the output image of this tile + * @output_addr_offset: Offset in bytes into the output buffer + * @output_addr_offset2: Offset in bytes into the output buffer for the + * second and third plane + * @output_hog_addr_offset: Offset in bytes into the HOG buffer where + * results of this tile are to be written + */ +struct pisp_tile { + __u8 edge; /* enum pisp_tile_edge */ + __u8 pad0[3]; + /* 4 bytes */ + __u32 input_addr_offset; + __u32 input_addr_offset2; + __u16 input_offset_x; + __u16 input_offset_y; + __u16 input_width; + __u16 input_height; + /* 20 bytes */ + __u32 tdn_input_addr_offset; + __u32 tdn_output_addr_offset; + __u32 stitch_input_addr_offset; + __u32 stitch_output_addr_offset; + /* 36 bytes */ + __u32 lsc_grid_offset_x; + __u32 lsc_grid_offset_y; + /* 44 bytes */ + __u32 cac_grid_offset_x; + __u32 cac_grid_offset_y; + /* 52 bytes */ + __u16 crop_x_start[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_x_end[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_y_start[PISP_BACK_END_NUM_OUTPUTS]; + __u16 crop_y_end[PISP_BACK_END_NUM_OUTPUTS]; + /* 68 bytes */ + /* Ordering is planes then branches */ + __u16 downscale_phase_x[3 * PISP_BACK_END_NUM_OUTPUTS]; + __u16 downscale_phase_y[3 * PISP_BACK_END_NUM_OUTPUTS]; + /* 92 bytes */ + __u16 resample_in_width[PISP_BACK_END_NUM_OUTPUTS]; + __u16 resample_in_height[PISP_BACK_END_NUM_OUTPUTS]; + /* 100 bytes */ + /* Ordering is planes then branches */ + __u16 resample_phase_x[3 * PISP_BACK_END_NUM_OUTPUTS]; + __u16 resample_phase_y[3 * PISP_BACK_END_NUM_OUTPUTS]; + /* 124 bytes */ + __u16 output_offset_x[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_offset_y[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_width[PISP_BACK_END_NUM_OUTPUTS]; + __u16 output_height[PISP_BACK_END_NUM_OUTPUTS]; + /* 140 bytes */ + __u32 output_addr_offset[PISP_BACK_END_NUM_OUTPUTS]; + __u32 output_addr_offset2[PISP_BACK_END_NUM_OUTPUTS]; + /* 156 bytes */ + __u32 output_hog_addr_offset; + /* 160 bytes */ +} __attribute__((packed)); + +/** + * struct pisp_be_tiles_config - Raspberry Pi PiSP Back End configuration + * @tiles: Tile descriptors + * @num_tiles: Number of tiles + * @config: PiSP Back End configuration + */ +struct pisp_be_tiles_config { + struct pisp_tile tiles[PISP_BACK_END_NUM_TILES]; + __u32 num_tiles; + struct pisp_be_config config; +} __attribute__((packed)); + +#endif /* _UAPI_PISP_BE_CONFIG_H_ */ diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h new file mode 100644 index 000000000000..b2522e29c976 --- /dev/null +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * RP1 PiSP common definitions. + * + * Copyright (C) 2021 - Raspberry Pi Ltd. + * + */ +#ifndef _UAPI_PISP_COMMON_H_ +#define _UAPI_PISP_COMMON_H_ + +#include + +struct pisp_image_format_config { + /* size in pixels */ + __u16 width; + __u16 height; + /* must match struct pisp_image_format below */ + __u32 format; + __s32 stride; + /* some planar image formats will need a second stride */ + __s32 stride2; +} __attribute__((packed)); + +enum pisp_bayer_order { + /* + * Note how bayer_order&1 tells you if G is on the even pixels of the + * checkerboard or not, and bayer_order&2 tells you if R is on the even + * rows or is swapped with B. Note that if the top (of the 8) bits is + * set, this denotes a monochrome or greyscale image, and the lower bits + * should all be ignored. + */ + PISP_BAYER_ORDER_RGGB = 0, + PISP_BAYER_ORDER_GBRG = 1, + PISP_BAYER_ORDER_BGGR = 2, + PISP_BAYER_ORDER_GRBG = 3, + PISP_BAYER_ORDER_GREYSCALE = 128 +}; + +enum pisp_image_format { + /* + * Precise values are mostly tbd. Generally these will be portmanteau + * values comprising bit fields and flags. This format must be shared + * throughout the PiSP. + */ + PISP_IMAGE_FORMAT_BPS_8 = 0x00000000, + PISP_IMAGE_FORMAT_BPS_10 = 0x00000001, + PISP_IMAGE_FORMAT_BPS_12 = 0x00000002, + PISP_IMAGE_FORMAT_BPS_16 = 0x00000003, + PISP_IMAGE_FORMAT_BPS_MASK = 0x00000003, + + PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED = 0x00000000, + PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR = 0x00000010, + PISP_IMAGE_FORMAT_PLANARITY_PLANAR = 0x00000020, + PISP_IMAGE_FORMAT_PLANARITY_MASK = 0x00000030, + + PISP_IMAGE_FORMAT_SAMPLING_444 = 0x00000000, + PISP_IMAGE_FORMAT_SAMPLING_422 = 0x00000100, + PISP_IMAGE_FORMAT_SAMPLING_420 = 0x00000200, + PISP_IMAGE_FORMAT_SAMPLING_MASK = 0x00000300, + + PISP_IMAGE_FORMAT_ORDER_NORMAL = 0x00000000, + PISP_IMAGE_FORMAT_ORDER_SWAPPED = 0x00001000, + + PISP_IMAGE_FORMAT_SHIFT_0 = 0x00000000, + PISP_IMAGE_FORMAT_SHIFT_1 = 0x00010000, + PISP_IMAGE_FORMAT_SHIFT_2 = 0x00020000, + PISP_IMAGE_FORMAT_SHIFT_3 = 0x00030000, + PISP_IMAGE_FORMAT_SHIFT_4 = 0x00040000, + PISP_IMAGE_FORMAT_SHIFT_5 = 0x00050000, + PISP_IMAGE_FORMAT_SHIFT_6 = 0x00060000, + PISP_IMAGE_FORMAT_SHIFT_7 = 0x00070000, + PISP_IMAGE_FORMAT_SHIFT_8 = 0x00080000, + PISP_IMAGE_FORMAT_SHIFT_MASK = 0x000f0000, + + PISP_IMAGE_FORMAT_UNCOMPRESSED = 0x00000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_1 = 0x01000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_2 = 0x02000000, + PISP_IMAGE_FORMAT_COMPRESSION_MODE_3 = 0x03000000, + PISP_IMAGE_FORMAT_COMPRESSION_MASK = 0x03000000, + + PISP_IMAGE_FORMAT_HOG_SIGNED = 0x04000000, + PISP_IMAGE_FORMAT_HOG_UNSIGNED = 0x08000000, + PISP_IMAGE_FORMAT_INTEGRAL_IMAGE = 0x10000000, + PISP_IMAGE_FORMAT_WALLPAPER_ROLL = 0x20000000, + PISP_IMAGE_FORMAT_THREE_CHANNEL = 0x40000000, + + /* Lastly a few specific instantiations of the above. */ + PISP_IMAGE_FORMAT_SINGLE_16 = PISP_IMAGE_FORMAT_BPS_16, + PISP_IMAGE_FORMAT_THREE_16 = PISP_IMAGE_FORMAT_BPS_16 | + PISP_IMAGE_FORMAT_THREE_CHANNEL +}; + +#define PISP_IMAGE_FORMAT_bps_8(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_8) +#define PISP_IMAGE_FORMAT_bps_10(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_10) +#define PISP_IMAGE_FORMAT_bps_12(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_12) +#define PISP_IMAGE_FORMAT_bps_16(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_16) +#define PISP_IMAGE_FORMAT_bps(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) ? \ + 8 + (2 << (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) - 1)) : 8) +#define PISP_IMAGE_FORMAT_shift(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SHIFT_MASK) / PISP_IMAGE_FORMAT_SHIFT_1) +#define PISP_IMAGE_FORMAT_three_channel(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL) +#define PISP_IMAGE_FORMAT_single_channel(fmt) \ + (!((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL)) +#define PISP_IMAGE_FORMAT_compressed(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_COMPRESSION_MASK) != \ + PISP_IMAGE_FORMAT_UNCOMPRESSED) +#define PISP_IMAGE_FORMAT_sampling_444(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_444) +#define PISP_IMAGE_FORMAT_sampling_422(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_422) +#define PISP_IMAGE_FORMAT_sampling_420(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ + PISP_IMAGE_FORMAT_SAMPLING_420) +#define PISP_IMAGE_FORMAT_order_normal(fmt) \ + (!((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED)) +#define PISP_IMAGE_FORMAT_order_swapped(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED) +#define PISP_IMAGE_FORMAT_interleaved(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED) +#define PISP_IMAGE_FORMAT_semiplanar(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR) +#define PISP_IMAGE_FORMAT_planar(fmt) \ + (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ + PISP_IMAGE_FORMAT_PLANARITY_PLANAR) +#define PISP_IMAGE_FORMAT_wallpaper(fmt) \ + ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) +#define PISP_IMAGE_FORMAT_HOG(fmt) \ + ((fmt) & \ + (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) + +#define PISP_WALLPAPER_WIDTH 128 /* in bytes */ + +struct pisp_bla_config { + __u16 black_level_r; + __u16 black_level_gr; + __u16 black_level_gb; + __u16 black_level_b; + __u16 output_black_level; + __u8 pad[2]; +} __attribute__((packed)); + +struct pisp_wbg_config { + __u16 gain_r; + __u16 gain_g; + __u16 gain_b; + __u8 pad[2]; +} __attribute__((packed)); + +struct pisp_compress_config { + /* value subtracted from incoming data */ + __u16 offset; + __u8 pad; + /* 1 => Companding; 2 => Delta (recommended); 3 => Combined (for HDR) */ + __u8 mode; +} __attribute__((packed)); + +struct pisp_decompress_config { + /* value added to reconstructed data */ + __u16 offset; + __u8 pad; + /* 1 => Companding; 2 => Delta (recommended); 3 => Combined (for HDR) */ + __u8 mode; +} __attribute__((packed)); + +enum pisp_axi_flags { + /* + * round down bursts to end at a 32-byte boundary, to align following + * bursts + */ + PISP_AXI_FLAG_ALIGN = 128, + /* for FE writer: force WSTRB high, to pad output to 16-byte boundary */ + PISP_AXI_FLAG_PAD = 64, + /* for FE writer: Use Output FIFO level to trigger "panic" */ + PISP_AXI_FLAG_PANIC = 32, +}; + +struct pisp_axi_config { + /* + * burst length minus one, which must be in the range 0:15; OR'd with + * flags + */ + __u8 maxlen_flags; + /* { prot[2:0], cache[3:0] } fields, echoed on AXI bus */ + __u8 cache_prot; + /* QoS field(s) (4x4 bits for FE writer; 4 bits for other masters) */ + __u16 qos; +} __attribute__((packed)); + +#endif /* _UAPI_PISP_COMMON_H_ */ -- cgit v1.2.3 From 8f6c2202222faffa0959929d8cd9090254a60831 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:34 +0200 Subject: media: uapi: Add meta pixel format for PiSP BE config Add format description for the PiSP Back End configuration parameter buffer. Signed-off-by: Jacopo Mondi Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/meta-formats.rst | 1 + .../userspace-api/media/v4l/metafmt-pisp-be.rst | 56 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 3 ++ 4 files changed, 61 insertions(+) create mode 100644 Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/meta-formats.rst b/Documentation/userspace-api/media/v4l/meta-formats.rst index c23aac823d2c..c6e56b5888bc 100644 --- a/Documentation/userspace-api/media/v4l/meta-formats.rst +++ b/Documentation/userspace-api/media/v4l/meta-formats.rst @@ -15,6 +15,7 @@ These formats are used for the :ref:`metadata` interface only. metafmt-d4xx metafmt-generic metafmt-intel-ipu3 + metafmt-pisp-be metafmt-rkisp1 metafmt-uvc metafmt-vivid diff --git a/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst b/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst new file mode 100644 index 000000000000..3281fe366c86 --- /dev/null +++ b/Documentation/userspace-api/media/v4l/metafmt-pisp-be.rst @@ -0,0 +1,56 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _v4l2-meta-fmt-rpi-be-cfg: + +************************ +V4L2_META_FMT_RPI_BE_CFG +************************ + +Raspberry Pi PiSP Back End configuration format +=============================================== + +The Raspberry Pi PiSP Back End memory-to-memory image signal processor is +configured by userspace by providing a buffer of configuration parameters +to the `pispbe-config` output video device node using the +:c:type:`v4l2_meta_format` interface. + +The PiSP Back End processes images in tiles, and its configuration requires +specifying two different sets of parameters by populating the members of +:c:type:`pisp_be_tiles_config` defined in the ``pisp_be_config.h`` header file. + +The `Raspberry Pi PiSP technical specification +`_ +provide detailed description of the ISP back end configuration and programming +model. + +Global configuration data +------------------------- + +The global configuration data describe how the pixels in a particular image are +to be processed and is therefore shared across all the tiles of the image. So +for example, LSC (Lens Shading Correction) or Denoise parameters would be common +across all tiles from the same frame. + +Global configuration data are passed to the ISP by populating the member of +:c:type:`pisp_be_config`. + +Tile parameters +--------------- + +As the ISP processes images in tiles, each set of tiles parameters describe how +a single tile in an image is going to be processed. A single set of tile +parameters consist of 160 bytes of data and to process a batch of tiles several +sets of tiles parameters are required. + +Tiles parameters are passed to the ISP by populating the member of +``pisp_tile`` and the ``num_tiles`` fields of :c:type:`pisp_be_tiles_config`. + +Raspberry Pi PiSP Back End uAPI data types +========================================== + +This section describes the data types exposed to userspace by the Raspberry Pi +PiSP Back End. The section is informative only, for a detailed description of +each field refer to the `Raspberry Pi PiSP technical specification +`_. + +.. kernel-doc:: include/uapi/linux/media/raspberrypi/pisp_be_config.h diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ee97643ff3a7..7c684788997c 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1465,6 +1465,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y210: descr = "10-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y212: descr = "12-bit YUYV Packed"; break; case V4L2_PIX_FMT_Y216: descr = "16-bit YUYV Packed"; break; + case V4L2_META_FMT_RPI_BE_CFG: descr = "RPi PiSP BE Config format"; break; case V4L2_META_FMT_GENERIC_8: descr = "8-bit Generic Metadata"; break; case V4L2_META_FMT_GENERIC_CSI2_10: descr = "8-bit Generic Meta, 10b CSI-2"; break; case V4L2_META_FMT_GENERIC_CSI2_12: descr = "8-bit Generic Meta, 12b CSI-2"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index dd6876380fe3..96fc0456081e 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -843,6 +843,9 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_PARAMS v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 3A Parameters */ #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ +/* Vendor specific - used for RaspberryPi PiSP */ +#define V4L2_META_FMT_RPI_BE_CFG v4l2_fourcc('R', 'P', 'B', 'C') /* PiSP BE configuration */ + #ifdef __KERNEL__ /* * Line-based metadata formats. Remember to update v4l_fill_fmtdesc() when -- cgit v1.2.3 From d260c1224786c870edbae09ef6ecf5f35361821e Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 26 Jun 2024 20:14:35 +0200 Subject: media: uapi: Add PiSP Compressed RAW Bayer formats Add Raspberry Pi compressed RAW Bayer formats. The compression algorithm description is provided by Nick Hollinghurst from Raspberry Pi. Signed-off-by: Jacopo Mondi Reviewed-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-bayer.rst | 1 + .../media/v4l/pixfmt-srggb8-pisp-comp.rst | 74 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 10 +++ include/uapi/linux/videodev2.h | 12 ++++ 4 files changed, 97 insertions(+) create mode 100644 Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst b/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst index 2500413e5f43..ed3eb432967d 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-bayer.rst @@ -20,6 +20,7 @@ orders. See also `the Wikipedia article on Bayer filter :maxdepth: 1 pixfmt-srggb8 + pixfmt-srggb8-pisp-comp pixfmt-srggb10 pixfmt-srggb10p pixfmt-srggb10alaw8 diff --git a/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst b/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst new file mode 100644 index 000000000000..5a82a15559d6 --- /dev/null +++ b/Documentation/userspace-api/media/v4l/pixfmt-srggb8-pisp-comp.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later + +.. _v4l2-pix-fmt-pisp-comp1-rggb: +.. _v4l2-pix-fmt-pisp-comp1-grbg: +.. _v4l2-pix-fmt-pisp-comp1-gbrg: +.. _v4l2-pix-fmt-pisp-comp1-bggr: +.. _v4l2-pix-fmt-pisp-comp1-mono: +.. _v4l2-pix-fmt-pisp-comp2-rggb: +.. _v4l2-pix-fmt-pisp-comp2-grbg: +.. _v4l2-pix-fmt-pisp-comp2-gbrg: +.. _v4l2-pix-fmt-pisp-comp2-bggr: +.. _v4l2-pix-fmt-pisp-comp2-mono: + +************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************** +V4L2_PIX_FMT_PISP_COMP1_RGGB ('PC1R'), V4L2_PIX_FMT_PISP_COMP1_GRBG ('PC1G'), V4L2_PIX_FMT_PISP_COMP1_GBRG ('PC1g'), V4L2_PIX_FMT_PISP_COMP1_BGGR ('PC1B), V4L2_PIX_FMT_PISP_COMP1_MONO ('PC1M'), V4L2_PIX_FMT_PISP_COMP2_RGGB ('PC2R'), V4L2_PIX_FMT_PISP_COMP2_GRBG ('PC2G'), V4L2_PIX_FMT_PISP_COMP2_GBRG ('PC2g'), V4L2_PIX_FMT_PISP_COMP2_BGGR ('PC2B), V4L2_PIX_FMT_PISP_COMP2_MONO ('PC2M') +************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************** + +================================================ +Raspberry Pi PiSP compressed 8-bit Bayer formats +================================================ + +Description +=========== + +The Raspberry Pi ISP (PiSP) uses a family of three fixed-rate compressed Bayer +formats. A black-level offset may be subtracted to improve compression +efficiency; the nominal black level and amount of offset must be signalled out +of band. Each scanline is padded to a multiple of 8 pixels wide, and each block +of 8 horizontally-contiguous pixels is coded using 8 bytes. + +Mode 1 uses a quantization and delta-based coding scheme which preserves up to +12 significant bits. Mode 2 is a simple sqrt-like companding scheme with 6 PWL +chords, preserving up to 12 significant bits. Mode 3 combines both companding +(with 4 chords) and the delta scheme, preserving up to 14 significant bits. + +The remainder of this description applies to Modes 1 and 3. + +Each block of 8 pixels is separated into even and odd phases of 4 pixels, +coded independently by 32-bit words at successive locations in memory. +The two LS bits of each 32-bit word give its "quantization mode". + +In quantization mode 0, the lowest 321 quantization levels are multiples of +FSD/4096 and the remaining levels are successive multiples of FSD/2048. +Quantization modes 1 and 2 use linear quantization with step sizes of +FSD/1024 and FSD/512 respectively. Each of the four pixels is quantized +independently, with rounding to the nearest level. +In quantization mode 2 where the middle two samples have quantized values +(q1,q2) both in the range [384..511], they are coded using 9 bits for q1 +followed by 7 bits for (q2 & 127). Otherwise, for quantization modes +0, 1 and 2: a 9-bit field encodes MIN(q1,q2) which must be in the range +[0..511] and a 7-bit field encodes (q2-q1+64) which must be in [0..127]. + +Each of the outer samples (q0,q3) is encoded using a 7-bit field based +on its inner neighbour q1 or q2. In quantization mode 2 where the inner +sample has a quantized value in the range [448..511], the field value is +(q0-384). Otherwise for quantization modes 0, 1 and 2: The outer sample +is encoded as (q0-MAX(0,q1-64)). q3 is likewise coded based on q2. +Each of these values must be in the range [0..127]. All these fields +of 2, 9, 7, 7, 7 bits respectively are packed in little-endian order +to give a 32-bit word with LE byte order. + +Quantization mode 3 has a "7.5-bit" escape, used when none of the above +encodings will fit. Each pixel value is quantized to the nearest of 176 +levels, where the lowest 95 levels are multiples of FSD/256 and the +remaining levels are multiples of FSD/128 (level 175 represents values +very close to FSD and may require saturating arithmetic to decode). + +Each pair of quantized pixels (q0,q1) or (q2,q3) is jointly coded +by a 15-bit field: 2816*(q0>>4) + 16*q1 + (q0&15). +Three fields of 2, 15, 15 bits are packed in LE order {15,15,2}. + +An implementation of a software decoder of compressed formats is available +in `Raspberry Pi camera applications code base +`_. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 7c684788997c..5eb4d797d259 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1532,6 +1532,16 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_MT2110T: descr = "Mediatek 10bit Tile Mode"; break; case V4L2_PIX_FMT_MT2110R: descr = "Mediatek 10bit Raster Mode"; break; case V4L2_PIX_FMT_HEXTILE: descr = "Hextile Compressed Format"; break; + case V4L2_PIX_FMT_PISP_COMP1_RGGB: descr = "PiSP 8b RGRG/GBGB mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_GRBG: descr = "PiSP 8b GRGR/BGBG mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_GBRG: descr = "PiSP 8b GBGB/RGRG mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_BGGR: descr = "PiSP 8b BGBG/GRGR mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP1_MONO: descr = "PiSP 8b monochrome mode1 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_RGGB: descr = "PiSP 8b RGRG/GBGB mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_GRBG: descr = "PiSP 8b GRGR/BGBG mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_GBRG: descr = "PiSP 8b GBGB/RGRG mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_BGGR: descr = "PiSP 8b BGBG/GRGR mode2 compr"; break; + case V4L2_PIX_FMT_PISP_COMP2_MONO: descr = "PiSP 8b monochrome mode2 compr"; break; default: if (fmt->description[0]) return; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 96fc0456081e..4e91362da6da 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -816,6 +816,18 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_IPU3_SGRBG10 v4l2_fourcc('i', 'p', '3', 'G') /* IPU3 packed 10-bit GRBG bayer */ #define V4L2_PIX_FMT_IPU3_SRGGB10 v4l2_fourcc('i', 'p', '3', 'r') /* IPU3 packed 10-bit RGGB bayer */ +/* Raspberry Pi PiSP compressed formats. */ +#define V4L2_PIX_FMT_PISP_COMP1_RGGB v4l2_fourcc('P', 'C', '1', 'R') /* PiSP 8-bit mode 1 compressed RGGB bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_GRBG v4l2_fourcc('P', 'C', '1', 'G') /* PiSP 8-bit mode 1 compressed GRBG bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_GBRG v4l2_fourcc('P', 'C', '1', 'g') /* PiSP 8-bit mode 1 compressed GBRG bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_BGGR v4l2_fourcc('P', 'C', '1', 'B') /* PiSP 8-bit mode 1 compressed BGGR bayer */ +#define V4L2_PIX_FMT_PISP_COMP1_MONO v4l2_fourcc('P', 'C', '1', 'M') /* PiSP 8-bit mode 1 compressed monochrome */ +#define V4L2_PIX_FMT_PISP_COMP2_RGGB v4l2_fourcc('P', 'C', '2', 'R') /* PiSP 8-bit mode 2 compressed RGGB bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_GRBG v4l2_fourcc('P', 'C', '2', 'G') /* PiSP 8-bit mode 2 compressed GRBG bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_GBRG v4l2_fourcc('P', 'C', '2', 'g') /* PiSP 8-bit mode 2 compressed GBRG bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_BGGR v4l2_fourcc('P', 'C', '2', 'B') /* PiSP 8-bit mode 2 compressed BGGR bayer */ +#define V4L2_PIX_FMT_PISP_COMP2_MONO v4l2_fourcc('P', 'C', '2', 'M') /* PiSP 8-bit mode 2 compressed monochrome */ + /* SDR formats - used only for Software Defined Radio devices */ #define V4L2_SDR_FMT_CU8 v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */ #define V4L2_SDR_FMT_CU16LE v4l2_fourcc('C', 'U', '1', '6') /* IQ u16le */ -- cgit v1.2.3 From d04bccd8c19d601232ed3e3c9e248c0040167d47 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 7 Jun 2024 16:55:37 +0200 Subject: listmount: allow listing in reverse order util-linux is about to implement listmount() and statmount() support. Karel requested the ability to scan the mount table in backwards order because that's what libmount currently does in order to get the latest mount first. We currently don't support this in listmount(). Add a new LISTMOUNT_REVERSE flag to allow listing mounts in reverse order. For example, listing all child mounts of /sys without LISTMOUNT_REVERSE gives: /sys/kernel/security @ mnt_id: 4294968369 /sys/fs/cgroup @ mnt_id: 4294968370 /sys/firmware/efi/efivars @ mnt_id: 4294968371 /sys/fs/bpf @ mnt_id: 4294968372 /sys/kernel/tracing @ mnt_id: 4294968373 /sys/kernel/debug @ mnt_id: 4294968374 /sys/fs/fuse/connections @ mnt_id: 4294968375 /sys/kernel/config @ mnt_id: 4294968376 whereas with LISTMOUNT_REVERSE it gives: /sys/kernel/config @ mnt_id: 4294968376 /sys/fs/fuse/connections @ mnt_id: 4294968375 /sys/kernel/debug @ mnt_id: 4294968374 /sys/kernel/tracing @ mnt_id: 4294968373 /sys/fs/bpf @ mnt_id: 4294968372 /sys/firmware/efi/efivars @ mnt_id: 4294968371 /sys/fs/cgroup @ mnt_id: 4294968370 /sys/kernel/security @ mnt_id: 4294968369 Link: https://lore.kernel.org/r/20240607-vfs-listmount-reverse-v1-4-7877a2bfa5e5@kernel.org Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner --- fs/namespace.c | 59 ++++++++++++++++++++++++++++++++++++++-------- include/uapi/linux/mount.h | 1 + 2 files changed, 50 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 98671cd89511..02a697287da5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1448,6 +1448,30 @@ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) return ret; } +/* + * Returns the mount which either has the specified mnt_id, or has the next + * greater id before the specified one. + */ +static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id) +{ + struct rb_node *node = ns->mounts.rb_node; + struct mount *ret = NULL; + + while (node) { + struct mount *m = node_to_mount(node); + + if (mnt_id >= m->mnt_id_unique) { + ret = node_to_mount(node); + if (mnt_id == m->mnt_id_unique) + break; + node = node->rb_right; + } else { + node = node->rb_left; + } + } + return ret; +} + #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ @@ -5042,13 +5066,20 @@ retry: return ret; } -static struct mount *listmnt_next(struct mount *curr) +static struct mount *listmnt_next(struct mount *curr, bool reverse) { - return node_to_mount(rb_next(&curr->mnt_node)); + struct rb_node *node; + + if (reverse) + node = rb_prev(&curr->mnt_node); + else + node = rb_next(&curr->mnt_node); + + return node_to_mount(node); } static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, - size_t nr_mnt_ids) + size_t nr_mnt_ids, bool reverse) { struct path root __free(path_put) = {}; struct mnt_namespace *ns = current->nsproxy->mnt_ns; @@ -5080,12 +5111,19 @@ static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, if (ret) return ret; - if (!last_mnt_id) - first = node_to_mount(rb_first(&ns->mounts)); - else - first = mnt_find_id_at(ns, last_mnt_id + 1); + if (!last_mnt_id) { + if (reverse) + first = node_to_mount(rb_last(&ns->mounts)); + else + first = node_to_mount(rb_first(&ns->mounts)); + } else { + if (reverse) + first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); + else + first = mnt_find_id_at(ns, last_mnt_id + 1); + } - for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) { + for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, &orig)) @@ -5106,7 +5144,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, struct mnt_id_req kreq; ssize_t ret; - if (flags) + if (flags & ~LISTMOUNT_REVERSE) return -EINVAL; /* @@ -5130,7 +5168,8 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, return -ENOMEM; scoped_guard(rwsem_read, &namespace_sem) - ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, nr_mnt_ids); + ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, + nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) return -EFAULT; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index ad5478dbad00..88d78de1519f 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -207,5 +207,6 @@ struct mnt_id_req { * Special @mnt_id values that can be passed to listmount */ #define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ #endif /* _UAPI_LINUX_MOUNT_H */ -- cgit v1.2.3 From 09b31295f833031c88419550172703d45c5401e3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 11:49:47 -0400 Subject: fs: export the mount ns id via statmount In order to allow users to iterate through children mount namespaces via listmount we need a way for them to know what the ns id for the mount. Add a new field to statmount called mnt_ns_id which will carry the ns id for the given mount entry. Co-developed-by: Christian Brauner Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/6dabf437331fb7415d886f7c64b21cb2a50b1c66.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/namespace.c | 11 +++++++++++ include/uapi/linux/mount.h | 4 +++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index eebe9d912a71..ed2d9353e4be 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4974,6 +4974,14 @@ static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) return 0; } +static void statmount_mnt_ns_id(struct kstatmount *s) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + + s->sm.mask |= STATMOUNT_MNT_NS_ID; + s->sm.mnt_ns_id = ns->seq; +} + static int statmount_string(struct kstatmount *s, u64 flag) { int ret; @@ -5070,6 +5078,9 @@ static int do_statmount(struct kstatmount *s) if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); + if (!err && s->mask & STATMOUNT_MNT_NS_ID) + statmount_mnt_ns_id(s); + if (err) return err; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 88d78de1519f..a07508aee518 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -172,7 +172,8 @@ struct statmount { __u64 propagate_from; /* Propagation from in current namespace */ __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ - __u64 __spare2[50]; + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u64 __spare2[49]; char str[]; /* Variable size part containing strings */ }; @@ -202,6 +203,7 @@ struct mnt_id_req { #define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ /* * Special @mnt_id values that can be passed to listmount -- cgit v1.2.3 From 0a3deb11858ae8a0b3849b5fda45512ad383f0e1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 24 Jun 2024 11:49:48 -0400 Subject: fs: Allow listmount() in foreign mount namespace Expand struct mnt_id_req to add an optional mnt_ns_id field. When this field is populated, listmount() will be performed on the specified mount namespace, provided the currently application has CAP_SYS_ADMIN in its user namespace and the mount namespace is a child of the current namespace. Co-developed-by: Josef Bacik Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/49930bdce29a8367a213eb14c1e68e7e49284f86.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/namespace.c | 88 ++++++++++++++++++++++++++++++++++++---------- include/uapi/linux/mount.h | 2 ++ 2 files changed, 72 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index ed2d9353e4be..a54d68f822a8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5122,7 +5122,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, int ret; size_t usize; - BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0); + BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1); ret = get_user(usize, &req->size); if (ret) @@ -5140,6 +5140,58 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, return 0; } +static struct mount *listmnt_next(struct mount *curr, bool reverse) +{ + struct rb_node *node; + + if (reverse) + node = rb_prev(&curr->mnt_node); + else + node = rb_next(&curr->mnt_node); + + return node_to_mount(node); +} + +static int grab_requested_root(struct mnt_namespace *ns, struct path *root) +{ + struct mount *first; + + rwsem_assert_held(&namespace_sem); + + /* We're looking at our own ns, just use get_fs_root. */ + if (ns == current->nsproxy->mnt_ns) { + get_fs_root(current->fs, root); + return 0; + } + + /* + * We have to find the first mount in our ns and use that, however it + * may not exist, so handle that properly. + */ + if (RB_EMPTY_ROOT(&ns->mounts)) + return -ENOENT; + + first = listmnt_next(ns->root, false); + if (!first) + return -ENOENT; + root->mnt = mntget(&first->mnt); + root->dentry = dget(root->mnt->mnt_root); + return 0; +} + +/* + * If the user requested a specific mount namespace id, look that up and return + * that, or if not simply grab a passive reference on our mount namespace and + * return that. + */ +static struct mnt_namespace *grab_requested_mnt_ns(u64 mnt_ns_id) +{ + if (mnt_ns_id) + return lookup_mnt_ns(mnt_ns_id); + refcount_inc(¤t->nsproxy->mnt_ns->passive); + return current->nsproxy->mnt_ns; +} + SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) @@ -5185,30 +5237,21 @@ retry: return ret; } -static struct mount *listmnt_next(struct mount *curr, bool reverse) -{ - struct rb_node *node; - - if (reverse) - node = rb_prev(&curr->mnt_node); - else - node = rb_next(&curr->mnt_node); - - return node_to_mount(node); -} - -static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, - size_t nr_mnt_ids, bool reverse) +static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, + u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids, + bool reverse) { struct path root __free(path_put) = {}; - struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct path orig; struct mount *r, *first; ssize_t ret; rwsem_assert_held(&namespace_sem); - get_fs_root(current->fs, &root); + ret = grab_requested_root(ns, &root); + if (ret) + return ret; + if (mnt_parent_id == LSMT_ROOT) { orig = root; } else { @@ -5260,6 +5303,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, { u64 *kmnt_ids __free(kvfree) = NULL; const size_t maxcount = 1000000; + struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct mnt_id_req kreq; ssize_t ret; @@ -5286,8 +5330,16 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, if (!kmnt_ids) return -ENOMEM; + ns = grab_requested_mnt_ns(kreq.mnt_ns_id); + if (!ns) + return -ENOENT; + + if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && + !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) + return -ENOENT; + scoped_guard(rwsem_read, &namespace_sem) - ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, + ret = do_listmount(ns, kreq.mnt_id, kreq.param, kmnt_ids, nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index a07508aee518..ee1559cd6764 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -189,10 +189,12 @@ struct mnt_id_req { __u32 spare; __u64 mnt_id; __u64 param; + __u64 mnt_ns_id; }; /* List of all mnt_id_req versions. */ #define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ /* * @mask bits for statmount(2) -- cgit v1.2.3 From e8e43a1fcc5c07575f37e40f8a2cd78aee46f9a0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 11:49:50 -0400 Subject: fs: add an ioctl to get the mnt ns id from nsfs In order to utilize the listmount() and statmount() extensions that allow us to call them on different namespaces we need a way to get the mnt namespace id from user space. Add an ioctl to nsfs that will allow us to extract the mnt namespace id in order to make these new extensions usable. Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/180449959d5a756af7306d6bda55f41b9d53e3cb.1719243756.git.josef@toxicpanda.com Signed-off-by: Christian Brauner --- fs/nsfs.c | 14 ++++++++++++++ include/uapi/linux/nsfs.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/nsfs.c b/fs/nsfs.c index 07e22a15ef02..af352dadffe1 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -12,6 +12,7 @@ #include #include +#include "mount.h" #include "internal.h" static struct vfsmount *nsfs_mnt; @@ -143,6 +144,19 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, argp = (uid_t __user *) arg; uid = from_kuid_munged(current_user_ns(), user_ns->owner); return put_user(uid, argp); + case NS_GET_MNTNS_ID: { + struct mnt_namespace *mnt_ns; + __u64 __user *idp; + __u64 id; + + if (ns->ops->type != CLONE_NEWNS) + return -EINVAL; + + mnt_ns = container_of(ns, struct mnt_namespace, ns); + idp = (__u64 __user *)arg; + id = mnt_ns->seq; + return put_user(id, idp); + } default: return -ENOTTY; } diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index a0c8552b64ee..56e8b1639b98 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -15,5 +15,7 @@ #define NS_GET_NSTYPE _IO(NSIO, 0x3) /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Get the id for a mount namespace */ +#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From 5b08bd408534bfb3a7cf5778da5b27d4e4fffe12 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 27 Jun 2024 16:11:42 +0200 Subject: pidfs: allow retrieval of namespace file descriptors For users that hold a reference to a pidfd procfs might not even be available nor is it desirable to parse through procfs just for the sake of getting namespace file descriptors for a process. Make it possible to directly retrieve namespace file descriptors from a pidfd. Pidfds already can be used with setns() to change a set of namespaces atomically. Link: https://lore.kernel.org/r/20240627-work-pidfs-v1-4-7e9ab6cc3bb1@kernel.org Reviewed-by: Jeff Layton Reviewed-by: Josef Bacik Reviewed-by: Alexander Mikhalitsyn Signed-off-by: Christian Brauner --- fs/pidfs.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pidfd.h | 14 ++++++++ 2 files changed, 104 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/pidfs.c b/fs/pidfs.c index dbb9d854d1c5..c9cb14181def 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -11,10 +11,16 @@ #include #include #include +#include #include #include +#include +#include +#include +#include #include "internal.h" +#include "mount.h" #ifdef CONFIG_PROC_FS /** @@ -108,11 +114,95 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) return poll_flags; } +static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct task_struct *task __free(put_task) = NULL; + struct nsproxy *nsp __free(put_nsproxy) = NULL; + struct pid *pid = pidfd_pid(file); + struct ns_common *ns_common; + + if (arg) + return -EINVAL; + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return -ESRCH; + + scoped_guard(task_lock, task) { + nsp = task->nsproxy; + if (nsp) + get_nsproxy(nsp); + } + if (!nsp) + return -ESRCH; /* just pretend it didn't exist */ + + /* + * We're trying to open a file descriptor to the namespace so perform a + * filesystem cred ptrace check. Also, we mirror nsfs behavior. + */ + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + return -EACCES; + + switch (cmd) { + /* Namespaces that hang of nsproxy. */ + case PIDFD_GET_CGROUP_NAMESPACE: + get_cgroup_ns(nsp->cgroup_ns); + ns_common = to_ns_common(nsp->cgroup_ns); + break; + case PIDFD_GET_IPC_NAMESPACE: + get_ipc_ns(nsp->ipc_ns); + ns_common = to_ns_common(nsp->ipc_ns); + break; + case PIDFD_GET_MNT_NAMESPACE: + get_mnt_ns(nsp->mnt_ns); + ns_common = to_ns_common(nsp->mnt_ns); + break; + case PIDFD_GET_NET_NAMESPACE: + ns_common = to_ns_common(nsp->net_ns); + get_net_ns(ns_common); + break; + case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: + get_pid_ns(nsp->pid_ns_for_children); + ns_common = to_ns_common(nsp->pid_ns_for_children); + break; + case PIDFD_GET_TIME_NAMESPACE: + get_time_ns(nsp->time_ns); + ns_common = to_ns_common(nsp->time_ns); + break; + case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: + get_time_ns(nsp->time_ns_for_children); + ns_common = to_ns_common(nsp->time_ns_for_children); + break; + case PIDFD_GET_UTS_NAMESPACE: + get_uts_ns(nsp->uts_ns); + ns_common = to_ns_common(nsp->uts_ns); + break; + /* Namespaces that don't hang of nsproxy. */ + case PIDFD_GET_USER_NAMESPACE: + rcu_read_lock(); + ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns))); + rcu_read_unlock(); + break; + case PIDFD_GET_PID_NAMESPACE: + rcu_read_lock(); + ns_common = to_ns_common(get_pid_ns(task_active_pid_ns(task))); + rcu_read_unlock(); + break; + default: + return -ENOIOCTLCMD; + } + + /* open_namespace() unconditionally consumes the reference */ + return open_namespace(ns_common); +} + static const struct file_operations pidfs_file_operations = { .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif + .unlocked_ioctl = pidfd_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; struct pid *pidfd_pid(const struct file *file) diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 72ec000a97cd..565fc0629fff 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -5,6 +5,7 @@ #include #include +#include /* Flags for pidfd_open(). */ #define PIDFD_NONBLOCK O_NONBLOCK @@ -15,4 +16,17 @@ #define PIDFD_SIGNAL_THREAD_GROUP (1UL << 1) #define PIDFD_SIGNAL_PROCESS_GROUP (1UL << 2) +#define PIDFS_IOCTL_MAGIC 0xFF + +#define PIDFD_GET_CGROUP_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 1) +#define PIDFD_GET_IPC_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 2) +#define PIDFD_GET_MNT_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 3) +#define PIDFD_GET_NET_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 4) +#define PIDFD_GET_PID_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 5) +#define PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 6) +#define PIDFD_GET_TIME_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 7) +#define PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 8) +#define PIDFD_GET_USER_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 9) +#define PIDFD_GET_UTS_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 10) + #endif /* _UAPI_LINUX_PIDFD_H */ -- cgit v1.2.3 From 46fb3ba95b93d1887e6dfa02a535e0526062de95 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 27 Jun 2024 17:08:50 +0300 Subject: ethtool: Add an interface for flashing transceiver modules' firmware CMIS compliant modules such as QSFP-DD might be running a firmware that can be updated in a vendor-neutral way by exchanging messages between the host and the module as described in section 7.3.1 of revision 5.2 of the CMIS standard. Add a pair of new ethtool messages that allow: * User space to trigger firmware update of transceiver modules * The kernel to notify user space about the progress of the process The user interface is designed to be asynchronous in order to avoid RTNL being held for too long and to allow several modules to be updated simultaneously. The interface is designed with CMIS compliant modules in mind, but kept generic enough to accommodate future use cases, if these arise. Signed-off-by: Danielle Ratson Reviewed-by: Petr Machata Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 55 ++++++++++++++++++++++ Documentation/networking/ethtool-netlink.rst | 70 ++++++++++++++++++++++++++++ include/uapi/linux/ethtool.h | 18 +++++++ include/uapi/linux/ethtool_netlink.h | 19 ++++++++ tools/net/ynl/Makefile.deps | 3 +- 5 files changed, 164 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 683f5c3f30ad..949e2722505d 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -20,6 +20,10 @@ definitions: name: header-flags type: flags entries: [ compact-bitsets, omit-reply, stats ] + - + name: module-fw-flash-status + type: enum + entries: [ started, in_progress, completed, error ] attribute-sets: - @@ -1004,6 +1008,32 @@ attribute-sets: - name: burst-tmr type: u32 + - + name: module-fw-flash + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: file-name + type: string + - + name: password + type: u32 + - + name: status + type: u32 + enum: module-fw-flash-status + - + name: status-msg + type: string + - + name: done + type: uint + - + name: total + type: uint operations: enum-model: directional @@ -1764,3 +1794,28 @@ operations: name: mm-ntf doc: Notification for change in MAC Merge configuration. notify: mm-get + - + name: module-fw-flash-act + doc: Flash transceiver module firmware. + + attribute-set: module-fw-flash + + do: + request: + attributes: + - header + - file-name + - password + - + name: module-fw-flash-ntf + doc: Notification for firmware flashing progress and status. + + attribute-set: module-fw-flash + + event: + attributes: + - header + - status + - status-msg + - done + - total diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7ec08e903bab..bfe2eda8580d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -228,6 +228,7 @@ Userspace to kernel: ``ETHTOOL_MSG_PLCA_GET_STATUS`` get PLCA RS status ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters + ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` flash transceiver module firmware ===================================== ================================= Kernel to userspace: @@ -274,6 +275,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PLCA_GET_STATUS_REPLY`` PLCA RS status ``ETHTOOL_MSG_PLCA_NTF`` PLCA RS parameters ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status + ``ETHTOOL_MSG_MODULE_FW_FLASH_NTF`` transceiver module flash updates ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -2041,6 +2043,73 @@ The attributes are propagated to the driver through the following structure: .. kernel-doc:: include/linux/ethtool.h :identifiers: ethtool_mm_cfg +MODULE_FW_FLASH_ACT +=================== + +Flashes transceiver module firmware. + +Request contents: + + ======================================= ====== =========================== + ``ETHTOOL_A_MODULE_FW_FLASH_HEADER`` nested request header + ``ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME`` string firmware image file name + ``ETHTOOL_A_MODULE_FW_FLASH_PASSWORD`` u32 transceiver module password + ======================================= ====== =========================== + +The firmware update process consists of three logical steps: + +1. Downloading a firmware image to the transceiver module and validating it. +2. Running the firmware image. +3. Committing the firmware image so that it is run upon reset. + +When flash command is given, those three steps are taken in that order. + +This message merely schedules the update process and returns immediately +without blocking. The process then runs asynchronously. +Since it can take several minutes to complete, during the update process +notifications are emitted from the kernel to user space updating it about +the status and progress. + +The ``ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME`` attribute encodes the firmware +image file name. The firmware image is downloaded to the transceiver module, +validated, run and committed. + +The optional ``ETHTOOL_A_MODULE_FW_FLASH_PASSWORD`` attribute encodes a password +that might be required as part of the transceiver module firmware update +process. + +The firmware update process can take several minutes to complete. Therefore, +during the update process notifications are emitted from the kernel to user +space updating it about the status and progress. + + + +Notification contents: + + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_HEADER`` | nested | reply header | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_STATUS`` | u32 | status | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG`` | string | status message | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` | uint | progress | + +---------------------------------------------------+--------+----------------+ + | ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` | uint | total | + +---------------------------------------------------+--------+----------------+ + +The ``ETHTOOL_A_MODULE_FW_FLASH_STATUS`` attribute encodes the current status +of the firmware update process. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_fw_flash_status + +The ``ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG`` attribute encodes a status message +string. + +The ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` and ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` +attributes encode the completed and total amount of work, respectively. + Request translation =================== @@ -2147,4 +2216,5 @@ are netlink only. n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` + n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8733a3117902..e011384c915c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -877,6 +877,24 @@ enum ethtool_mm_verify_status { ETHTOOL_MM_VERIFY_STATUS_DISABLED, }; +/** + * enum ethtool_module_fw_flash_status - plug-in module firmware flashing status + * @ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED: The firmware flashing process has + * started. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS: The firmware flashing process + * is in progress. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED: The firmware flashing process was + * completed successfully. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR: The firmware flashing process was + * stopped due to an error. + */ +enum ethtool_module_fw_flash_status { + ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED = 1, + ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS, + ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED, + ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index d15856c7e001..840dabdc9d88 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -57,6 +57,7 @@ enum { ETHTOOL_MSG_PLCA_GET_STATUS, ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, + ETHTOOL_MSG_MODULE_FW_FLASH_ACT, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -109,6 +110,7 @@ enum { ETHTOOL_MSG_PLCA_NTF, ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, + ETHTOOL_MSG_MODULE_FW_FLASH_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -1018,6 +1020,23 @@ enum { ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1) }; +/* MODULE_FW_FLASH */ + +enum { + ETHTOOL_A_MODULE_FW_FLASH_UNSPEC, + ETHTOOL_A_MODULE_FW_FLASH_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME, /* string */ + ETHTOOL_A_MODULE_FW_FLASH_PASSWORD, /* u32 */ + ETHTOOL_A_MODULE_FW_FLASH_STATUS, /* u32 */ + ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, /* string */ + ETHTOOL_A_MODULE_FW_FLASH_DONE, /* uint */ + ETHTOOL_A_MODULE_FW_FLASH_TOTAL, /* uint */ + + /* add new constants above here */ + __ETHTOOL_A_MODULE_FW_FLASH_CNT, + ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index f4e8eb79c1b8..dbdca32a1c61 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -16,7 +16,8 @@ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) -CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) -- cgit v1.2.3 From f9af549d1fd31487bbbc666b5b158cfc940ccc17 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 24 Jun 2024 15:40:52 -0400 Subject: fs: export mount options via statmount() statmount() can export arbitrary strings, so utilize the __spare1 slot for a mnt_opts string pointer, and then support asking for and setting the mount options during statmount(). This calls into the helper for showing mount options, which already uses a seq_file, so fits in nicely with our existing mechanism for exporting strings via statmount(). Signed-off-by: Josef Bacik Link: https://lore.kernel.org/r/3aa6bf8bd5d0a21df9ebd63813af8ab532c18276.1719257716.git.josef@toxicpanda.com Reviewed-by: Jeff Layton [brauner: only call sb->s_op->show_options()] Signed-off-by: Christian Brauner --- fs/namespace.c | 37 ++++++++++++++++++++++++++++++++++++- include/uapi/linux/mount.h | 3 ++- 2 files changed, 38 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index a989e89b0a10..c53a0ee748c6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4980,6 +4980,34 @@ static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns) s->sm.mnt_ns_id = ns->seq; } +static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) +{ + struct vfsmount *mnt = s->mnt; + struct super_block *sb = mnt->mnt_sb; + int err; + + if (sb->s_op->show_options) { + size_t start = seq->count; + + err = sb->s_op->show_options(seq, mnt->mnt_root); + if (err) + return err; + + if (unlikely(seq_has_overflowed(seq))) + return -EAGAIN; + + if (seq->count == start) + return 0; + + /* skip leading comma */ + memmove(seq->buf + start, seq->buf + start + 1, + seq->count - start - 1); + seq->count--; + } + + return 0; +} + static int statmount_string(struct kstatmount *s, u64 flag) { int ret; @@ -5000,6 +5028,10 @@ static int statmount_string(struct kstatmount *s, u64 flag) sm->mnt_point = seq->count; ret = statmount_mnt_point(s, seq); break; + case STATMOUNT_MNT_OPTS: + sm->mnt_opts = seq->count; + ret = statmount_mnt_opts(s, seq); + break; default: WARN_ON_ONCE(true); return -EINVAL; @@ -5130,6 +5162,9 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); + if (!err && s->mask & STATMOUNT_MNT_OPTS) + err = statmount_string(s, STATMOUNT_MNT_OPTS); + if (!err && s->mask & STATMOUNT_MNT_NS_ID) statmount_mnt_ns_id(s, ns); @@ -5151,7 +5186,7 @@ static inline bool retry_statmount(const long ret, size_t *seq_size) } #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \ - STATMOUNT_FS_TYPE) + STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS) static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index ee1559cd6764..225bc366ffcb 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 __spare1; + __u32 mnt_opts; /* [str] Mount options of the mount */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -206,6 +206,7 @@ struct mnt_id_req { #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ #define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ /* * Special @mnt_id values that can be passed to listmount -- cgit v1.2.3 From 3e26d9f08fbe0b73e951a5e810fdb7a332b7e37f Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 20 Jun 2024 14:27:22 +0200 Subject: iio: core: Add new DMABUF interface infrastructure Add the necessary infrastructure to the IIO core to support a new optional DMABUF based interface. With this new interface, DMABUF objects (externally created) can be attached to a IIO buffer, and subsequently used for data transfer. A userspace application can then use this interface to share DMABUF objects between several interfaces, allowing it to transfer data in a zero-copy fashion, for instance between IIO and the USB stack. The userspace application can also memory-map the DMABUF objects, and access the sample data directly. The advantage of doing this vs. the read() interface is that it avoids an extra copy of the data between the kernel and userspace. This is particularly userful for high-speed devices which produce several megabytes or even gigabytes of data per second. As part of the interface, 3 new IOCTLs have been added: IIO_BUFFER_DMABUF_ATTACH_IOCTL(int fd): Attach the DMABUF object identified by the given file descriptor to the buffer. IIO_BUFFER_DMABUF_DETACH_IOCTL(int fd): Detach the DMABUF object identified by the given file descriptor from the buffer. Note that closing the IIO buffer's file descriptor will automatically detach all previously attached DMABUF objects. IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *): Request a data transfer to/from the given DMABUF object. Its file descriptor, as well as the transfer size and flags are provided in the "iio_dmabuf" structure. These three IOCTLs have to be performed on the IIO buffer's file descriptor, obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl. Signed-off-by: Paul Cercueil Co-developed-by: Nuno Sa Signed-off-by: Nuno Sa Link: https://patch.msgid.link/20240620122726.41232-4-paul@crapouillou.net Signed-off-by: Jonathan Cameron --- drivers/iio/Kconfig | 1 + drivers/iio/industrialio-buffer.c | 459 ++++++++++++++++++++++++++++++++++++++ include/linux/iio/buffer_impl.h | 33 +++ include/uapi/linux/iio/buffer.h | 22 ++ 4 files changed, 515 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index 9c351ffc7bed..661127aed2f9 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -14,6 +14,7 @@ if IIO config IIO_BUFFER bool "Enable buffer support within IIO" + select DMA_SHARED_BUFFER help Provide core support for various buffer based data acquisition methods. diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 0138b21b244f..d6fe105d2f40 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -9,15 +9,20 @@ * - Better memory allocation techniques? * - Alternative access techniques? */ +#include #include #include #include #include #include +#include +#include +#include #include #include #include #include +#include #include #include @@ -29,6 +34,34 @@ #include #include +#define DMABUF_ENQUEUE_TIMEOUT_MS 5000 + +MODULE_IMPORT_NS(DMA_BUF); + +struct iio_dmabuf_priv { + struct list_head entry; + struct kref ref; + + struct iio_buffer *buffer; + struct iio_dma_buffer_block *block; + + u64 context; + + /* Spinlock used for locking the dma_fence */ + spinlock_t lock; + + struct dma_buf_attachment *attach; + struct sg_table *sgt; + enum dma_data_direction dir; + atomic_t seqno; +}; + +struct iio_dma_fence { + struct dma_fence base; + struct iio_dmabuf_priv *priv; + struct work_struct work; +}; + static const char * const iio_endian_prefix[] = { [IIO_BE] = "be", [IIO_LE] = "le", @@ -333,6 +366,8 @@ void iio_buffer_init(struct iio_buffer *buffer) { INIT_LIST_HEAD(&buffer->demux_list); INIT_LIST_HEAD(&buffer->buffer_list); + INIT_LIST_HEAD(&buffer->dmabufs); + mutex_init(&buffer->dmabufs_mutex); init_waitqueue_head(&buffer->pollq); kref_init(&buffer->ref); if (!buffer->watermark) @@ -1526,14 +1561,55 @@ static void iio_buffer_unregister_legacy_sysfs_groups(struct iio_dev *indio_dev) kfree(iio_dev_opaque->legacy_scan_el_group.attrs); } +static void iio_buffer_dmabuf_release(struct kref *ref) +{ + struct iio_dmabuf_priv *priv = container_of(ref, struct iio_dmabuf_priv, ref); + struct dma_buf_attachment *attach = priv->attach; + struct iio_buffer *buffer = priv->buffer; + struct dma_buf *dmabuf = attach->dmabuf; + + dma_resv_lock(dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); + dma_resv_unlock(dmabuf->resv); + + buffer->access->detach_dmabuf(buffer, priv->block); + + dma_buf_detach(attach->dmabuf, attach); + dma_buf_put(dmabuf); + kfree(priv); +} + +static void iio_buffer_dmabuf_get(struct dma_buf_attachment *attach) +{ + struct iio_dmabuf_priv *priv = attach->importer_priv; + + kref_get(&priv->ref); +} + +static void iio_buffer_dmabuf_put(struct dma_buf_attachment *attach) +{ + struct iio_dmabuf_priv *priv = attach->importer_priv; + + kref_put(&priv->ref, iio_buffer_dmabuf_release); +} + static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep) { struct iio_dev_buffer_pair *ib = filep->private_data; struct iio_dev *indio_dev = ib->indio_dev; struct iio_buffer *buffer = ib->buffer; + struct iio_dmabuf_priv *priv, *tmp; wake_up(&buffer->pollq); + guard(mutex)(&buffer->dmabufs_mutex); + + /* Close all attached DMABUFs */ + list_for_each_entry_safe(priv, tmp, &buffer->dmabufs, entry) { + list_del_init(&priv->entry); + iio_buffer_dmabuf_put(priv->attach); + } + kfree(ib); clear_bit(IIO_BUSY_BIT_POS, &buffer->flags); iio_device_put(indio_dev); @@ -1541,11 +1617,393 @@ static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep) return 0; } +static int iio_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock) +{ + if (!nonblock) + return dma_resv_lock_interruptible(dmabuf->resv, NULL); + + if (!dma_resv_trylock(dmabuf->resv)) + return -EBUSY; + + return 0; +} + +static struct dma_buf_attachment * +iio_buffer_find_attachment(struct iio_dev_buffer_pair *ib, + struct dma_buf *dmabuf, bool nonblock) +{ + struct device *dev = ib->indio_dev->dev.parent; + struct iio_buffer *buffer = ib->buffer; + struct dma_buf_attachment *attach = NULL; + struct iio_dmabuf_priv *priv; + + guard(mutex)(&buffer->dmabufs_mutex); + + list_for_each_entry(priv, &buffer->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + attach = priv->attach; + break; + } + } + + if (attach) + iio_buffer_dmabuf_get(attach); + + return attach ?: ERR_PTR(-EPERM); +} + +static int iio_buffer_attach_dmabuf(struct iio_dev_buffer_pair *ib, + int __user *user_fd, bool nonblock) +{ + struct iio_dev *indio_dev = ib->indio_dev; + struct iio_buffer *buffer = ib->buffer; + struct dma_buf_attachment *attach; + struct iio_dmabuf_priv *priv, *each; + struct dma_buf *dmabuf; + int err, fd; + + if (!buffer->access->attach_dmabuf + || !buffer->access->detach_dmabuf + || !buffer->access->enqueue_dmabuf) + return -EPERM; + + if (copy_from_user(&fd, user_fd, sizeof(fd))) + return -EFAULT; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->lock); + priv->context = dma_fence_context_alloc(1); + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) { + err = PTR_ERR(dmabuf); + goto err_free_priv; + } + + attach = dma_buf_attach(dmabuf, indio_dev->dev.parent); + if (IS_ERR(attach)) { + err = PTR_ERR(attach); + goto err_dmabuf_put; + } + + err = iio_dma_resv_lock(dmabuf, nonblock); + if (err) + goto err_dmabuf_detach; + + priv->dir = buffer->direction == IIO_BUFFER_DIRECTION_IN + ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + priv->sgt = dma_buf_map_attachment(attach, priv->dir); + if (IS_ERR(priv->sgt)) { + err = PTR_ERR(priv->sgt); + dev_err(&indio_dev->dev, "Unable to map attachment: %d\n", err); + goto err_resv_unlock; + } + + kref_init(&priv->ref); + priv->buffer = buffer; + priv->attach = attach; + attach->importer_priv = priv; + + priv->block = buffer->access->attach_dmabuf(buffer, attach); + if (IS_ERR(priv->block)) { + err = PTR_ERR(priv->block); + goto err_dmabuf_unmap_attachment; + } + + dma_resv_unlock(dmabuf->resv); + + mutex_lock(&buffer->dmabufs_mutex); + + /* + * Check whether we already have an attachment for this driver/DMABUF + * combo. If we do, refuse to attach. + */ + list_for_each_entry(each, &buffer->dmabufs, entry) { + if (each->attach->dev == indio_dev->dev.parent + && each->attach->dmabuf == dmabuf) { + /* + * We unlocked the reservation object, so going through + * the cleanup code would mean re-locking it first. + * At this stage it is simpler to free the attachment + * using iio_buffer_dma_put(). + */ + mutex_unlock(&buffer->dmabufs_mutex); + iio_buffer_dmabuf_put(attach); + return -EBUSY; + } + } + + /* Otherwise, add the new attachment to our dmabufs list. */ + list_add(&priv->entry, &buffer->dmabufs); + mutex_unlock(&buffer->dmabufs_mutex); + + return 0; + +err_dmabuf_unmap_attachment: + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_dmabuf_detach: + dma_buf_detach(dmabuf, attach); +err_dmabuf_put: + dma_buf_put(dmabuf); +err_free_priv: + kfree(priv); + + return err; +} + +static int iio_buffer_detach_dmabuf(struct iio_dev_buffer_pair *ib, + int __user *user_req, bool nonblock) +{ + struct iio_buffer *buffer = ib->buffer; + struct iio_dev *indio_dev = ib->indio_dev; + struct iio_dmabuf_priv *priv; + struct dma_buf *dmabuf; + int dmabuf_fd, ret = -EPERM; + + if (copy_from_user(&dmabuf_fd, user_req, sizeof(dmabuf_fd))) + return -EFAULT; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + guard(mutex)(&buffer->dmabufs_mutex); + + list_for_each_entry(priv, &buffer->dmabufs, entry) { + if (priv->attach->dev == indio_dev->dev.parent + && priv->attach->dmabuf == dmabuf) { + list_del(&priv->entry); + + /* Unref the reference from iio_buffer_attach_dmabuf() */ + iio_buffer_dmabuf_put(priv->attach); + ret = 0; + break; + } + } + + dma_buf_put(dmabuf); + + return ret; +} + +static const char * +iio_buffer_dma_fence_get_driver_name(struct dma_fence *fence) +{ + return "iio"; +} + +static void iio_buffer_dma_fence_release(struct dma_fence *fence) +{ + struct iio_dma_fence *iio_fence = + container_of(fence, struct iio_dma_fence, base); + + kfree(iio_fence); +} + +static const struct dma_fence_ops iio_buffer_dma_fence_ops = { + .get_driver_name = iio_buffer_dma_fence_get_driver_name, + .get_timeline_name = iio_buffer_dma_fence_get_driver_name, + .release = iio_buffer_dma_fence_release, +}; + +static int iio_buffer_enqueue_dmabuf(struct iio_dev_buffer_pair *ib, + struct iio_dmabuf __user *iio_dmabuf_req, + bool nonblock) +{ + struct iio_buffer *buffer = ib->buffer; + struct iio_dmabuf iio_dmabuf; + struct dma_buf_attachment *attach; + struct iio_dmabuf_priv *priv; + struct iio_dma_fence *fence; + struct dma_buf *dmabuf; + unsigned long timeout; + bool cookie, cyclic, dma_to_ram; + long retl; + u32 seqno; + int ret; + + if (copy_from_user(&iio_dmabuf, iio_dmabuf_req, sizeof(iio_dmabuf))) + return -EFAULT; + + if (iio_dmabuf.flags & ~IIO_BUFFER_DMABUF_SUPPORTED_FLAGS) + return -EINVAL; + + cyclic = iio_dmabuf.flags & IIO_BUFFER_DMABUF_CYCLIC; + + /* Cyclic flag is only supported on output buffers */ + if (cyclic && buffer->direction != IIO_BUFFER_DIRECTION_OUT) + return -EINVAL; + + dmabuf = dma_buf_get(iio_dmabuf.fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + if (!iio_dmabuf.bytes_used || iio_dmabuf.bytes_used > dmabuf->size) { + ret = -EINVAL; + goto err_dmabuf_put; + } + + attach = iio_buffer_find_attachment(ib, dmabuf, nonblock); + if (IS_ERR(attach)) { + ret = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = attach->importer_priv; + + fence = kmalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) { + ret = -ENOMEM; + goto err_attachment_put; + } + + fence->priv = priv; + + seqno = atomic_add_return(1, &priv->seqno); + + /* + * The transfers are guaranteed to be processed in the order they are + * enqueued, so we can use a simple incrementing sequence number for + * the dma_fence. + */ + dma_fence_init(&fence->base, &iio_buffer_dma_fence_ops, + &priv->lock, priv->context, seqno); + + ret = iio_dma_resv_lock(dmabuf, nonblock); + if (ret) + goto err_fence_put; + + timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS); + dma_to_ram = buffer->direction == IIO_BUFFER_DIRECTION_IN; + + /* Make sure we don't have writers */ + retl = dma_resv_wait_timeout(dmabuf->resv, + dma_resv_usage_rw(dma_to_ram), + true, timeout); + if (retl == 0) + retl = -EBUSY; + if (retl < 0) { + ret = (int)retl; + goto err_resv_unlock; + } + + if (buffer->access->lock_queue) + buffer->access->lock_queue(buffer); + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (ret) + goto err_queue_unlock; + + dma_resv_add_fence(dmabuf->resv, &fence->base, + dma_to_ram ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); + dma_resv_unlock(dmabuf->resv); + + cookie = dma_fence_begin_signalling(); + + ret = buffer->access->enqueue_dmabuf(buffer, priv->block, &fence->base, + priv->sgt, iio_dmabuf.bytes_used, + cyclic); + if (ret) { + /* + * DMABUF enqueue failed, but we already added the fence. + * Signal the error through the fence completion mechanism. + */ + iio_buffer_signal_dmabuf_done(&fence->base, ret); + } + + if (buffer->access->unlock_queue) + buffer->access->unlock_queue(buffer); + + dma_fence_end_signalling(cookie); + dma_buf_put(dmabuf); + + return ret; + +err_queue_unlock: + if (buffer->access->unlock_queue) + buffer->access->unlock_queue(buffer); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_fence_put: + dma_fence_put(&fence->base); +err_attachment_put: + iio_buffer_dmabuf_put(attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return ret; +} + +static void iio_buffer_cleanup(struct work_struct *work) +{ + struct iio_dma_fence *fence = + container_of(work, struct iio_dma_fence, work); + struct iio_dmabuf_priv *priv = fence->priv; + struct dma_buf_attachment *attach = priv->attach; + + dma_fence_put(&fence->base); + iio_buffer_dmabuf_put(attach); +} + +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret) +{ + struct iio_dma_fence *iio_fence = + container_of(fence, struct iio_dma_fence, base); + bool cookie = dma_fence_begin_signalling(); + + /* + * Get a reference to the fence, so that it's not freed as soon as + * it's signaled. + */ + dma_fence_get(fence); + + fence->error = ret; + dma_fence_signal(fence); + dma_fence_end_signalling(cookie); + + /* + * The fence will be unref'd in iio_buffer_cleanup. + * It can't be done here, as the unref functions might try to lock the + * resv object, which can deadlock. + */ + INIT_WORK(&iio_fence->work, iio_buffer_cleanup); + schedule_work(&iio_fence->work); +} +EXPORT_SYMBOL_GPL(iio_buffer_signal_dmabuf_done); + +static long iio_buffer_chrdev_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct iio_dev_buffer_pair *ib = filp->private_data; + void __user *_arg = (void __user *)arg; + bool nonblock = filp->f_flags & O_NONBLOCK; + + switch (cmd) { + case IIO_BUFFER_DMABUF_ATTACH_IOCTL: + return iio_buffer_attach_dmabuf(ib, _arg, nonblock); + case IIO_BUFFER_DMABUF_DETACH_IOCTL: + return iio_buffer_detach_dmabuf(ib, _arg, nonblock); + case IIO_BUFFER_DMABUF_ENQUEUE_IOCTL: + return iio_buffer_enqueue_dmabuf(ib, _arg, nonblock); + default: + return -EINVAL; + } +} + static const struct file_operations iio_buffer_chrdev_fileops = { .owner = THIS_MODULE, .llseek = noop_llseek, .read = iio_buffer_read, .write = iio_buffer_write, + .unlocked_ioctl = iio_buffer_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .poll = iio_buffer_poll, .release = iio_buffer_chrdev_release, }; @@ -1994,6 +2452,7 @@ static void iio_buffer_release(struct kref *ref) { struct iio_buffer *buffer = container_of(ref, struct iio_buffer, ref); + mutex_destroy(&buffer->dmabufs_mutex); buffer->access->release(buffer); } diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 89c3fd7c29ca..e72552e026f3 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -9,8 +9,12 @@ #include #include +struct dma_buf_attachment; +struct dma_fence; struct iio_dev; +struct iio_dma_buffer_block; struct iio_buffer; +struct sg_table; /** * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be @@ -39,6 +43,16 @@ struct iio_buffer; * device stops sampling. Calles are balanced with @enable. * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @attach_dmabuf: called from userspace via ioctl to attach one external + * DMABUF. + * @detach_dmabuf: called from userspace via ioctl to detach one previously + * attached DMABUF. + * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF + * object to this buffer. Requires a valid DMABUF fd, that + * was previouly attached to this buffer. + * @lock_queue: called when the core needs to lock the buffer queue; + * it is used when enqueueing DMABUF objects. + * @unlock_queue: used to unlock a previously locked buffer queue * @modes: Supported operating modes by this buffer type * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* * @@ -68,6 +82,17 @@ struct iio_buffer_access_funcs { void (*release)(struct iio_buffer *buffer); + struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); + void (*detach_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); + int (*enqueue_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, struct sg_table *sgt, + size_t size, bool cyclic); + void (*lock_queue)(struct iio_buffer *buffer); + void (*unlock_queue)(struct iio_buffer *buffer); + unsigned int modes; unsigned int flags; }; @@ -136,6 +161,12 @@ struct iio_buffer { /* @ref: Reference count of the buffer. */ struct kref ref; + + /* @dmabufs: List of DMABUF attachments */ + struct list_head dmabufs; /* P: dmabufs_mutex */ + + /* @dmabufs_mutex: Protects dmabufs */ + struct mutex dmabufs_mutex; }; /** @@ -159,6 +190,8 @@ void iio_buffer_init(struct iio_buffer *buffer); struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); void iio_buffer_put(struct iio_buffer *buffer); +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret); + #else /* CONFIG_IIO_BUFFER */ static inline void iio_buffer_get(struct iio_buffer *buffer) {} diff --git a/include/uapi/linux/iio/buffer.h b/include/uapi/linux/iio/buffer.h index 13939032b3f6..c666aa95e532 100644 --- a/include/uapi/linux/iio/buffer.h +++ b/include/uapi/linux/iio/buffer.h @@ -5,6 +5,28 @@ #ifndef _UAPI_IIO_BUFFER_H_ #define _UAPI_IIO_BUFFER_H_ +#include + +/* Flags for iio_dmabuf.flags */ +#define IIO_BUFFER_DMABUF_CYCLIC (1 << 0) +#define IIO_BUFFER_DMABUF_SUPPORTED_FLAGS 0x00000001 + +/** + * struct iio_dmabuf - Descriptor for a single IIO DMABUF object + * @fd: file descriptor of the DMABUF object + * @flags: one or more IIO_BUFFER_DMABUF_* flags + * @bytes_used: number of bytes used in this DMABUF for the data transfer. + * Should generally be set to the DMABUF's size. + */ +struct iio_dmabuf { + __u32 fd; + __u32 flags; + __u64 bytes_used; +}; + #define IIO_BUFFER_GET_FD_IOCTL _IOWR('i', 0x91, int) +#define IIO_BUFFER_DMABUF_ATTACH_IOCTL _IOW('i', 0x92, int) +#define IIO_BUFFER_DMABUF_DETACH_IOCTL _IOW('i', 0x93, int) +#define IIO_BUFFER_DMABUF_ENQUEUE_IOCTL _IOW('i', 0x94, struct iio_dmabuf) #endif /* _UAPI_IIO_BUFFER_H_ */ -- cgit v1.2.3 From 7c8110057b1bb9ab9f47ac0efc554d5c3a53b693 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jun 2024 14:35:50 -0700 Subject: tcp_metrics: add UAPI to the header guard tcp_metrics' header lacks the customary _UAPI in the header guard. This makes YNL build rules work less seamlessly. We can easily fix that on YNL side, but this could also be problematic if we ever needed to create a kernel-only tcp_metrics.h. Signed-off-by: Jakub Kicinski Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- include/uapi/linux/tcp_metrics.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index 7cb4a172feed..c48841076998 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* tcp_metrics.h - TCP Metrics Interface */ -#ifndef _LINUX_TCP_METRICS_H -#define _LINUX_TCP_METRICS_H +#ifndef _UAPI_LINUX_TCP_METRICS_H +#define _UAPI_LINUX_TCP_METRICS_H #include @@ -58,4 +58,4 @@ enum { #define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1) -#endif /* _LINUX_TCP_METRICS_H */ +#endif /* _UAPI_LINUX_TCP_METRICS_H */ -- cgit v1.2.3 From 85674625e0bc25be4dbaa165a556ef6037328379 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jun 2024 14:35:51 -0700 Subject: tcp_metrics: add netlink protocol spec in YAML Add a protocol spec for tcp_metrics, so that it's accessible via YNL. Useful at the very least for testing fixes. In this episode of "10,000 ways to complicate netlink" the metric nest has defines which are off by 1. iproute2 does: struct rtattr *m[TCP_METRIC_MAX + 1 + 1]; parse_rtattr_nested(m, TCP_METRIC_MAX + 1, a); for (i = 0; i < TCP_METRIC_MAX + 1; i++) { // ... attr = m[i + 1]; This is too weird to support in YNL, add a new set of defines with _correct_ values to the official kernel header. Signed-off-by: Jakub Kicinski Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- Documentation/netlink/specs/tcp_metrics.yaml | 169 +++++++++++++++++++++++++++ include/uapi/linux/tcp_metrics.h | 16 +++ tools/net/ynl/Makefile.deps | 1 + 3 files changed, 186 insertions(+) create mode 100644 Documentation/netlink/specs/tcp_metrics.yaml (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/tcp_metrics.yaml b/Documentation/netlink/specs/tcp_metrics.yaml new file mode 100644 index 000000000000..1bd94f43e526 --- /dev/null +++ b/Documentation/netlink/specs/tcp_metrics.yaml @@ -0,0 +1,169 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: tcp_metrics + +protocol: genetlink-legacy + +doc: | + Management interface for TCP metrics. + +c-family-name: tcp-metrics-genl-name +c-version-name: tcp-metrics-genl-version +max-by-define: true +kernel-policy: global + +definitions: + - + name: tcp-fastopen-cookie-max + type: const + value: 16 + +attribute-sets: + - + name: tcp-metrics + name-prefix: tcp-metrics-attr- + attributes: + - + name: addr-ipv4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: addr-ipv6 + type: binary + checks: + min-len: 16 + byte-order: big-endian + display-hint: ipv6 + - + name: age + type: u64 + - + name: tw-tsval + type: u32 + doc: unused + - + name: tw-ts-stamp + type: s32 + doc: unused + - + name: vals + type: nest + nested-attributes: metrics + - + name: fopen-mss + type: u16 + - + name: fopen-syn-drops + type: u16 + - + name: fopen-syn-drop-ts + type: u64 + - + name: fopen-cookie + type: binary + checks: + min-len: tcp-fastopen-cookie-max + - + name: saddr-ipv4 + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: saddr-ipv6 + type: binary + checks: + min-len: 16 + byte-order: big-endian + display-hint: ipv6 + - + name: pad + type: pad + + - + name: metrics + # Intentionally don't define the name-prefix, see below. + doc: | + Attributes with metrics. Note that the values here do not match + the TCP_METRIC_* defines in the kernel, because kernel defines + are off-by one (e.g. rtt is defined as enum 0, while netlink carries + attribute type 1). + attributes: + - + name: rtt + type: u32 + doc: | + Round Trip Time (RTT), in msecs with 3 bits fractional + (left-shift by 3 to get the msec value). + - + name: rttvar + type: u32 + doc: | + Round Trip Time VARiance (RTT), in msecs with 2 bits fractional + (left-shift by 2 to get the msec value). + - + name: ssthresh + type: u32 + doc: Slow Start THRESHold. + - + name: cwnd + type: u32 + doc: Congestion Window. + - + name: reodering + type: u32 + doc: Reodering metric. + - + name: rtt-us + type: u32 + doc: | + Round Trip Time (RTT), in usecs, with 3 bits fractional + (left-shift by 3 to get the msec value). + - + name: rttvar-us + type: u32 + doc: | + Round Trip Time (RTT), in usecs, with 2 bits fractional + (left-shift by 3 to get the msec value). + +operations: + list: + - + name: get + doc: Retrieve metrics. + attribute-set: tcp-metrics + + dont-validate: [ strict, dump ] + + do: + request: &sel_attrs + attributes: + - addr-ipv4 + - addr-ipv6 + - saddr-ipv4 + - saddr-ipv6 + reply: &all_attrs + attributes: + - addr-ipv4 + - addr-ipv6 + - saddr-ipv4 + - saddr-ipv6 + - age + - vals + - fopen-mss + - fopen-syn-drops + - fopen-syn-drop-ts + - fopen-cookie + dump: + reply: *all_attrs + + - + name: del + doc: Delete metrics. + attribute-set: tcp-metrics + + dont-validate: [ strict, dump ] + flags: [ admin-perm ] + + do: + request: *sel_attrs diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index c48841076998..927c735a5b0e 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -27,6 +27,22 @@ enum tcp_metric_index { #define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1) +/* Re-define enum tcp_metric_index, again, using the values carried + * as netlink attribute types. + */ +enum { + TCP_METRICS_A_METRICS_RTT = 1, + TCP_METRICS_A_METRICS_RTTVAR, + TCP_METRICS_A_METRICS_SSTHRESH, + TCP_METRICS_A_METRICS_CWND, + TCP_METRICS_A_METRICS_REODERING, + TCP_METRICS_A_METRICS_RTT_US, + TCP_METRICS_A_METRICS_RTTVAR_US, + + __TCP_METRICS_A_METRICS_MAX +}; +#define TCP_METRICS_A_METRICS_MAX (__TCP_METRICS_A_METRICS_MAX - 1) + enum { TCP_METRICS_ATTR_UNSPEC, TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */ diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index dbdca32a1c61..0712b5e82eb7 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -26,3 +26,4 @@ CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) CFLAGS_ovs_flow:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) CFLAGS_ovs_vport:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h) +CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h) -- cgit v1.2.3 From 6555acdefc758a4dae7038c3f2301f311e287218 Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Tue, 2 Jul 2024 19:21:18 +0200 Subject: um: time-travel: support time-travel protocol broadcast messages Add a message type to the time-travel protocol to broadcast a small (64-bit) value to all participants in a simulation. The main use case is to have an identical message come to all participants in a simulation, e.g. to separate out logs for different tests running in a single simulation. Down in the guts of time_travel_handle_message() we can't use printk() and not even printk_deferred(), so just store the message and print it at the start of the userspace() function. Unfortunately this means that other prints in the kernel can actually bypass the message, but in most cases where this is used, for example to separate test logs, userspace will be involved. Also, even if we could use printk_deferred(), we'd still need to flush it out in the userspace() function since otherwise userspace messages might cross it. As a result, this is a reasonable compromise, there's no need to have any core changes and it solves the main use case we have for it. Signed-off-by: Mordechay Goodstein Link: https://patch.msgid.link/20240702192118.c4093bc5b15e.I2ca8d006b67feeb866ac2017af7b741c9e06445a@changeid Signed-off-by: Johannes Berg --- arch/um/include/shared/timetravel.h | 9 ++++++ arch/um/kernel/time.c | 59 +++++++++++++++++++++++++++++++++++++ arch/um/os-Linux/skas/process.c | 3 ++ include/uapi/linux/um_timetravel.h | 11 +++++++ 4 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/um/include/shared/timetravel.h b/arch/um/include/shared/timetravel.h index e5c3d69f1b69..c8db2f213dba 100644 --- a/arch/um/include/shared/timetravel.h +++ b/arch/um/include/shared/timetravel.h @@ -15,8 +15,17 @@ enum time_travel_mode { #if defined(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT) || \ defined(CONFIG_UML_TIME_TRAVEL_SUPPORT) extern enum time_travel_mode time_travel_mode; +extern int time_travel_should_print_bc_msg; #else #define time_travel_mode TT_MODE_OFF +#define time_travel_should_print_bc_msg 0 #endif /* (UML_)CONFIG_UML_TIME_TRAVEL_SUPPORT */ +void _time_travel_print_bc_msg(void); +static inline void time_travel_print_bc_msg(void) +{ + if (time_travel_should_print_bc_msg) + _time_travel_print_bc_msg(); +} + #endif /* _UM_TIME_TRAVEL_H_ */ diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 5b5fd8f68d9c..2339edc22f7c 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -60,6 +60,15 @@ enum time_travel_message_handling { TTMH_READ, }; +static u64 bc_message; +int time_travel_should_print_bc_msg; + +void _time_travel_print_bc_msg(void) +{ + time_travel_should_print_bc_msg = 0; + printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message); +} + static void time_travel_handle_message(struct um_timetravel_msg *msg, enum time_travel_message_handling mode) { @@ -101,6 +110,10 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, time_travel_ext_free_until_valid = true; time_travel_ext_free_until = msg->time; break; + case UM_TIMETRAVEL_BROADCAST: + bc_message = msg->time; + time_travel_should_print_bc_msg = 1; + break; } resp.seq = msg->seq; @@ -880,4 +893,50 @@ __uml_help(setup_time_travel_start, "time-travel-start=\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); +static struct kobject *bc_time_kobject; + +static ssize_t bc_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "0x%llx", bc_message); +} + +static ssize_t bc_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret; + u64 user_bc_message; + + ret = kstrtou64(buf, 0, &user_bc_message); + if (ret) + return ret; + + bc_message = user_bc_message; + + time_travel_ext_req(UM_TIMETRAVEL_BROADCAST, bc_message); + pr_info("um: time: sent broadcast message: 0x%llx\n", bc_message); + return count; +} + +static struct kobj_attribute bc_attribute = __ATTR(bc-message, 0660, bc_show, bc_store); + +static int __init um_bc_start(void) +{ + if (time_travel_mode != TT_MODE_EXTERNAL) + return 0; + + bc_time_kobject = kobject_create_and_add("um-ext-time", kernel_kobj); + if (!bc_time_kobject) + return 0; + + if (sysfs_create_file(bc_time_kobject, &bc_attribute.attr)) + pr_debug("failed to create the bc file in /sys/kernel/um_time"); + + return 0; +} + +void __exit time_exit(void) +{ + kobject_put(bc_time_kobject); +} + +late_initcall(um_bc_start); #endif diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 41a288dcfc34..45885deb6cae 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "../internal.h" int is_skas_winch(int pid, int fd, void *data) @@ -345,6 +346,8 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) interrupt_end(); while (1) { + time_travel_print_bc_msg(); + if (kill_userspace_mm[0]) fatal_sigsegv(); diff --git a/include/uapi/linux/um_timetravel.h b/include/uapi/linux/um_timetravel.h index ca3238222b6d..078ea401aa2a 100644 --- a/include/uapi/linux/um_timetravel.h +++ b/include/uapi/linux/um_timetravel.h @@ -123,6 +123,17 @@ enum um_timetravel_ops { * the simulation. */ UM_TIMETRAVEL_GET_TOD = 8, + + /** + * @UM_TIMETRAVEL_BROADCAST: Send/Receive a broadcast message. + * This message can be used to sync all components in the system + * with a single message, if the calender gets the message, the + * calender broadcast the message to all components, and if a + * component receives it it should act based on it e.g print a + * message to it's log system. + * (calendar <-> host) + */ + UM_TIMETRAVEL_BROADCAST = 9, }; #endif /* _UAPI_LINUX_UM_TIMETRAVEL_H */ -- cgit v1.2.3 From bfb80d8bc92fa70f5b44a57ed2b24d57685fe188 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 2 Jul 2024 19:21:21 +0200 Subject: um: add shared memory optimisation for time-travel=ext With external time travel, a LOT of message can end up being exchanged on the socket, taking a significant amount of time just to do that. Add a new shared memory optimisation to that, where a number of changes are made: - the controller sends a client ID and a shared memory FD (and a logging FD we don't use) in the ACK message to the initial START - the shared memory holds the current time and the free_until value, so that there's no need to exchange messages for that - if the client that's running has shared memory support, any client (the running one included) can request the next time it wants to run inside the shared memory, rather than sending a message, by also updating the free_until value - when shared memory is enabled, RUN/WAIT messages no longer have an ACK, further cutting down on messages Together, this can reduce the number of messages very significantly, and reduce overall test/simulation run time. Co-developed-by: Mordechay Goodstein Signed-off-by: Mordechay Goodstein Link: https://patch.msgid.link/20240702192118.6ad0a083f574.Ie41206c8ce4507fe26b991937f47e86c24ca7a31@changeid Signed-off-by: Johannes Berg --- arch/um/kernel/time.c | 130 ++++++++++++++++++++++++--- include/uapi/linux/um_timetravel.h | 179 ++++++++++++++++++++++++++++++++++--- 2 files changed, 283 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 2339edc22f7c..d44eaad53d9d 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -31,6 +31,7 @@ EXPORT_SYMBOL_GPL(time_travel_mode); static bool time_travel_start_set; static unsigned long long time_travel_start; static unsigned long long time_travel_time; +static unsigned long long time_travel_shm_offset; static LIST_HEAD(time_travel_events); static LIST_HEAD(time_travel_irqs); static unsigned long long time_travel_timer_interval; @@ -40,8 +41,11 @@ static int time_travel_ext_fd = -1; static unsigned int time_travel_ext_waiting; static bool time_travel_ext_prev_request_valid; static unsigned long long time_travel_ext_prev_request; -static bool time_travel_ext_free_until_valid; -static unsigned long long time_travel_ext_free_until; +static unsigned long long *time_travel_ext_free_until; +static unsigned long long _time_travel_ext_free_until; +static u16 time_travel_shm_id; +static struct um_timetravel_schedshm *time_travel_shm; +static union um_timetravel_schedshm_client *time_travel_shm_client; static void time_travel_set_time(unsigned long long ns) { @@ -58,6 +62,7 @@ enum time_travel_message_handling { TTMH_IDLE, TTMH_POLL, TTMH_READ, + TTMH_READ_START_ACK, }; static u64 bc_message; @@ -69,6 +74,40 @@ void _time_travel_print_bc_msg(void) printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message); } +static void time_travel_setup_shm(int fd, u16 id) +{ + u32 len; + + time_travel_shm = os_mmap_rw_shared(fd, sizeof(*time_travel_shm)); + + if (!time_travel_shm) + goto out; + + len = time_travel_shm->len; + + if (time_travel_shm->version != UM_TIMETRAVEL_SCHEDSHM_VERSION || + len < struct_size(time_travel_shm, clients, id + 1)) { + os_unmap_memory(time_travel_shm, sizeof(*time_travel_shm)); + time_travel_shm = NULL; + goto out; + } + + time_travel_shm = os_mremap_rw_shared(time_travel_shm, + sizeof(*time_travel_shm), + len); + if (!time_travel_shm) + goto out; + + time_travel_shm_offset = time_travel_shm->current_time; + time_travel_shm_client = &time_travel_shm->clients[id]; + time_travel_shm_client->capa |= UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE; + time_travel_shm_id = id; + /* always look at that free_until from now on */ + time_travel_ext_free_until = &time_travel_shm->free_until; +out: + os_close_file(fd); +} + static void time_travel_handle_message(struct um_timetravel_msg *msg, enum time_travel_message_handling mode) { @@ -89,7 +128,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, } } - ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + if (unlikely(mode == TTMH_READ_START_ACK)) { + int fd[UM_TIMETRAVEL_SHARED_MAX_FDS]; + + ret = os_rcv_fd_msg(time_travel_ext_fd, fd, + ARRAY_SIZE(fd), msg, sizeof(*msg)); + if (ret == sizeof(*msg)) { + time_travel_setup_shm(fd[UM_TIMETRAVEL_SHARED_MEMFD], + msg->time & UM_TIMETRAVEL_START_ACK_ID); + /* we don't use the logging for now */ + os_close_file(fd[UM_TIMETRAVEL_SHARED_LOGFD]); + } + } else { + ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + } if (ret == 0) panic("time-travel external link is broken\n"); @@ -105,10 +157,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, return; case UM_TIMETRAVEL_RUN: time_travel_set_time(msg->time); + if (time_travel_shm) { + /* no request right now since we're running */ + time_travel_shm_client->flags &= + ~UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + /* no ack for shared memory RUN */ + return; + } break; case UM_TIMETRAVEL_FREE_UNTIL: - time_travel_ext_free_until_valid = true; - time_travel_ext_free_until = msg->time; + /* not supposed to get this with shm, but ignore it */ + if (time_travel_shm) + break; + time_travel_ext_free_until = &_time_travel_ext_free_until; + _time_travel_ext_free_until = msg->time; break; case UM_TIMETRAVEL_BROADCAST: bc_message = msg->time; @@ -149,8 +211,15 @@ static u64 time_travel_ext_req(u32 op, u64 time) block_signals_hard(); os_write_file(time_travel_ext_fd, &msg, sizeof(msg)); + /* no ACK expected for WAIT in shared memory mode */ + if (msg.op == UM_TIMETRAVEL_WAIT && time_travel_shm) + goto done; + while (msg.op != UM_TIMETRAVEL_ACK) - time_travel_handle_message(&msg, TTMH_READ); + time_travel_handle_message(&msg, + op == UM_TIMETRAVEL_START ? + TTMH_READ_START_ACK : + TTMH_READ); if (msg.seq != mseq) panic("time-travel: ACK message has different seqno! op=%d, seq=%d != %d time=%lld\n", @@ -158,6 +227,7 @@ static u64 time_travel_ext_req(u32 op, u64 time) if (op == UM_TIMETRAVEL_GET) time_travel_set_time(msg.time); +done: unblock_signals_hard(); return msg.time; @@ -193,13 +263,33 @@ static void time_travel_ext_update_request(unsigned long long time) /* * if we're running and are allowed to run past the request * then we don't need to update it either + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return; time_travel_ext_prev_request = time; time_travel_ext_prev_request_valid = true; + + if (time_travel_shm) { + union um_timetravel_schedshm_client *running; + + running = &time_travel_shm->clients[time_travel_shm->running_id]; + + if (running->capa & UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE) { + time_travel_shm_client->flags |= + UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + time += time_travel_shm_offset; + time_travel_shm_client->req_time = time; + if (time < time_travel_shm->free_until) + time_travel_shm->free_until = time; + return; + } + } + time_travel_ext_req(UM_TIMETRAVEL_REQUEST, time); } @@ -207,6 +297,14 @@ void __time_travel_propagate_time(void) { static unsigned long long last_propagated; + if (time_travel_shm) { + if (time_travel_shm->running_id != time_travel_shm_id) + panic("time-travel: setting time while not running\n"); + time_travel_shm->current_time = time_travel_time + + time_travel_shm_offset; + return; + } + if (last_propagated == time_travel_time) return; @@ -222,9 +320,12 @@ static bool time_travel_ext_request(unsigned long long time) * If we received an external sync point ("free until") then we * don't have to request/wait for anything until then, unless * we're already waiting. + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return false; time_travel_ext_update_request(time); @@ -238,7 +339,8 @@ static void time_travel_ext_wait(bool idle) }; time_travel_ext_prev_request_valid = false; - time_travel_ext_free_until_valid = false; + if (!time_travel_shm) + time_travel_ext_free_until = NULL; time_travel_ext_waiting++; time_travel_ext_req(UM_TIMETRAVEL_WAIT, -1); @@ -261,7 +363,11 @@ static void time_travel_ext_wait(bool idle) static void time_travel_ext_get_time(void) { - time_travel_ext_req(UM_TIMETRAVEL_GET, -1); + if (time_travel_shm) + time_travel_set_time(time_travel_shm->current_time - + time_travel_shm_offset); + else + time_travel_ext_req(UM_TIMETRAVEL_GET, -1); } static void __time_travel_update_time(unsigned long long ns, bool idle) diff --git a/include/uapi/linux/um_timetravel.h b/include/uapi/linux/um_timetravel.h index 078ea401aa2a..546a690b0346 100644 --- a/include/uapi/linux/um_timetravel.h +++ b/include/uapi/linux/um_timetravel.h @@ -1,17 +1,6 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ /* - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - * - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019 - 2023 Intel Corporation */ #ifndef _UAPI_LINUX_UM_TIMETRAVEL_H #define _UAPI_LINUX_UM_TIMETRAVEL_H @@ -50,6 +39,36 @@ struct um_timetravel_msg { __u64 time; }; +/* max number of file descriptors that can be sent/received in a message */ +#define UM_TIMETRAVEL_MAX_FDS 2 + +/** + * enum um_timetravel_shared_mem_fds - fds sent in ACK message for START message + */ +enum um_timetravel_shared_mem_fds { + /** + * @UM_TIMETRAVEL_SHARED_MEMFD: Index of the shared memory file + * descriptor in the control message + */ + UM_TIMETRAVEL_SHARED_MEMFD, + /** + * @UM_TIMETRAVEL_SHARED_LOGFD: Index of the logging file descriptor + * in the control message + */ + UM_TIMETRAVEL_SHARED_LOGFD, + UM_TIMETRAVEL_SHARED_MAX_FDS, +}; + +/** + * enum um_timetravel_start_ack - ack-time mask for start message + */ +enum um_timetravel_start_ack { + /** + * @UM_TIMETRAVEL_START_ACK_ID: client ID that controller allocated. + */ + UM_TIMETRAVEL_START_ACK_ID = 0xffff, +}; + /** * enum um_timetravel_ops - Operation codes */ @@ -57,7 +76,9 @@ enum um_timetravel_ops { /** * @UM_TIMETRAVEL_ACK: response (ACK) to any previous message, * this usually doesn't carry any data in the 'time' field - * unless otherwise specified below + * unless otherwise specified below, note: while using shared + * memory no ACK for WAIT and RUN messages, for more info see + * &struct um_timetravel_schedshm. */ UM_TIMETRAVEL_ACK = 0, @@ -136,4 +157,134 @@ enum um_timetravel_ops { UM_TIMETRAVEL_BROADCAST = 9, }; +/* version of struct um_timetravel_schedshm */ +#define UM_TIMETRAVEL_SCHEDSHM_VERSION 2 + +/** + * enum um_timetravel_schedshm_cap - time travel capabilities of every client + * + * These flags must be set immediately after processing the ACK to + * the START message, before sending any message to the controller. + */ +enum um_timetravel_schedshm_cap { + /** + * @UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE: client can read current time + * update internal time request to shared memory and read + * free until and send no Ack on RUN and doesn't expect ACK on + * WAIT. + */ + UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE = 0x1, +}; + +/** + * enum um_timetravel_schedshm_flags - time travel flags of every client + */ +enum um_timetravel_schedshm_flags { + /** + * @UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN: client has a request to run. + * It's set by client when it has a request to run, if (and only + * if) the @running_id points to a client that is able to use + * shared memory, i.e. has %UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE + * (this includes the client itself). Otherwise, a message must + * be used. + */ + UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN = 0x1, +}; + +/** + * DOC: Time travel shared memory overview + * + * The main purpose of the shared memory is to avoid all time travel message + * that don't need any action, for example current time can be held in shared + * memory without the need of any client to send a message UM_TIMETRAVEL_GET + * in order to know what's the time. + * + * Since this is shared memory with all clients and controller and controller + * creates the shared memory space, all time values are absolute to controller + * time. So first time client connects to shared memory mode it should take the + * current_time value in shared memory and keep it internally as a diff to + * shared memory times, and once shared memory is initialized, any interaction + * with the controller must happen in the controller time domain, including any + * messages (for clients that are not using shared memory, the controller will + * handle an offset and make the clients think they start at time zero.) + * + * Along with the shared memory file descriptor is sent to the client a logging + * file descriptor, to have all logs related to shared memory, + * logged into one place. note: to have all logs synced into log file at write, + * file should be flushed (fflush) after writing to it. + * + * To avoid memory corruption, we define below for each field who can write to + * it at what time, defined in the structure fields. + * + * To avoid having to pack this struct, all fields in it must be naturally aligned + * (i.e. aligned to their size). + */ + +/** + * union um_timetravel_schedshm_client - UM time travel client struct + * + * Every entity using the shared memory including the controller has a place in + * the um_timetravel_schedshm clients array, that holds info related to the client + * using the shared memory, and can be set only by the client after it gets the + * fd memory. + * + * @capa: bit fields with client capabilities see + * &enum um_timetravel_schedshm_cap, set by client once after getting the + * shared memory file descriptor. + * @flags: bit fields for flags see &enum um_timetravel_schedshm_flags for doc. + * @req_time: request time to run, set by client on every request it needs. + * @name: unique id sent to the controller by client with START message. + */ +union um_timetravel_schedshm_client { + struct { + __u32 capa; + __u32 flags; + __u64 req_time; + __u64 name; + }; + char reserve[128]; /* reserved for future usage */ +}; + +/** + * struct um_timetravel_schedshm - UM time travel shared memory struct + * + * @hdr: header fields: + * @version: Current version struct UM_TIMETRAVEL_SCHEDSHM_VERSION, + * set by controller once at init, clients must check this after mapping + * and work without shared memory if they cannot handle the indicated + * version. + * @len: Length of all the memory including header (@hdr), clients should once + * per connection first mmap the header and take the length (@len) to remap the entire size. + * This is done in order to support dynamic struct size letting number of + * clients be dynamic based on controller support. + * @free_until: Stores the next request to run by any client, in order for the + * current client to know how long it can still run. A client needs to (at + * least) reload this value immediately after communicating with any other + * client, since the controller will update this field when a new request + * is made by any client. Clients also must update this value when they + * insert/update an own request into the shared memory while not running + * themselves, and the new request is before than the current value. + * current_time: Current time, can only be set by the client in running state + * (indicated by @running_id), though that client may only run until @free_until, + * so it must remain smaller than @free_until. + * @running_id: The current client in state running, set before a client is + * notified that it's now running. + * @max_clients: size of @clients array, set once at init by the controller. + * @clients: clients array see &union um_timetravel_schedshm_client for doc, + * set only by client. + */ +struct um_timetravel_schedshm { + union { + struct { + __u32 version; + __u32 len; + __u64 free_until; + __u64 current_time; + __u16 running_id; + __u16 max_clients; + }; + char hdr[4096]; /* align to 4K page size */ + }; + union um_timetravel_schedshm_client clients[]; +}; #endif /* _UAPI_LINUX_UM_TIMETRAVEL_H */ -- cgit v1.2.3 From 4ecaf7e98a3ae0c843d67c76649ecc694232834b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 2 Jul 2024 15:33:54 -0400 Subject: tracing: Have memmapped ring buffer use ioctl of "R" range 0x20-2F To prevent conflicts with other ioctl numbers to allow strace to have an idea of what is happening, add the range of ioctls for the trace buffer mapping from _IO("T", 0x1) to the range of "R" 0x20 - 0x2F. Link: https://lore.kernel.org/linux-trace-kernel/20240630105322.GA17573@altlinux.org/ Link: https://lore.kernel.org/linux-trace-kernel/20240630213626.GA23566@altlinux.org/ Cc: Jonathan Corbet Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer") Link: https://lore.kernel.org/20240702153354.367861db@rorschach.local.home Reported-by: "Dmitry V. Levin" Reviewed-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + include/uapi/linux/trace_mmap.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a141e8e65c5d..9a97030c6c8d 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -186,6 +186,7 @@ Code Seq# Include File Comments 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! +'R' 20-2F linux/trace_mmap.h 'R' C0-DF net/bluetooth/rfcomm.h 'R' E0 uapi/linux/fsl_mc.h 'S' all linux/cdrom.h conflict! diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h index bd1066754220..c102ef35d11e 100644 --- a/include/uapi/linux/trace_mmap.h +++ b/include/uapi/linux/trace_mmap.h @@ -43,6 +43,6 @@ struct trace_buffer_meta { __u64 Reserved2; }; -#define TRACE_MMAP_IOCTL_GET_READER _IO('T', 0x1) +#define TRACE_MMAP_IOCTL_GET_READER _IO('R', 0x20) #endif /* _TRACE_MMAP_H_ */ -- cgit v1.2.3 From 608f6976c309793ceea37292c54b057dab091944 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 26 Jun 2024 07:35:37 -0700 Subject: perf/x86/intel: Support new data source for Lunar Lake A new PEBS data source format is introduced for the p-core of Lunar Lake. The data source field is extended to 8 bits with new encodings. A new layout is introduced into the union intel_x86_pebs_dse. Introduce the lnl_latency_data() to parse the new format. Enlarge the pebs_data_source[] accordingly to include new encodings. Only the mem load and the mem store events can generate the data source. Introduce INTEL_HYBRID_LDLAT_CONSTRAINT and INTEL_HYBRID_STLAT_CONSTRAINT to mark them. Add two new bits for the new cache-related data src, L2_MHB and MSC. The L2_MHB is short for L2 Miss Handling Buffer, which is similar to LFB (Line Fill Buffer), but to track the L2 Cache misses. The MSC stands for the memory-side cache. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andi Kleen Reviewed-by: Ian Rogers Link: https://lkml.kernel.org/r/20240626143545.480761-6-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 2 + arch/x86/events/intel/ds.c | 94 ++++++++++++++++++++++++++++++++++++++++- arch/x86/events/perf_event.h | 16 ++++++- include/uapi/linux/perf_event.h | 6 ++- 4 files changed, 113 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 35f2d52281cc..6a6f1f4b9205 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6960,6 +6960,7 @@ __init int intel_pmu_init(void) case INTEL_ARROWLAKE: intel_pmu_init_hybrid(hybrid_big_small); + x86_pmu.pebs_latency_data = lnl_latency_data; x86_pmu.get_event_constraints = mtl_get_event_constraints; x86_pmu.hw_config = adl_hw_config; @@ -6977,6 +6978,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; intel_pmu_init_skt(&pmu->pmu); + intel_pmu_pebs_data_source_lnl(); pr_cont("Lunarlake Hybrid events, "); name = "lunarlake_hybrid"; break; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 3581c2715b21..b9cc520b2942 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -63,6 +63,15 @@ union intel_x86_pebs_dse { unsigned int mtl_fwd_blk:1; unsigned int ld_reserved4:24; }; + struct { + unsigned int lnc_dse:8; + unsigned int ld_reserved5:2; + unsigned int lnc_stlb_miss:1; + unsigned int lnc_locked:1; + unsigned int lnc_data_blk:1; + unsigned int lnc_addr_blk:1; + unsigned int ld_reserved6:18; + }; }; @@ -77,7 +86,7 @@ union intel_x86_pebs_dse { #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ -static u64 pebs_data_source[] = { +static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -173,6 +182,40 @@ void __init intel_pmu_pebs_data_source_cmt(void) __intel_pmu_pebs_data_source_cmt(pebs_data_source); } +/* Version for Lion Cove and later */ +static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* 0x00: ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 hit */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x02: L1 hit */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x03: LFB/L1 Miss Handling Buffer hit */ + 0, /* 0x04: Reserved */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x05: L2 Hit */ + OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE), /* 0x06: L2 Miss Handling Buffer Hit */ + 0, /* 0x07: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x08: L3 Hit */ + 0, /* 0x09: Reserved */ + 0, /* 0x0a: Reserved */ + 0, /* 0x0b: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* 0x0c: L3 Hit Snoop Fwd */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0d: L3 Hit Snoop HitM */ + 0, /* 0x0e: Reserved */ + P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0f: L3 Miss Snoop HitM */ + OP_LH | LEVEL(MSC) | P(SNOOP, NONE), /* 0x10: Memory-side Cache Hit */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */ +}; + +void __init intel_pmu_pebs_data_source_lnl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source)); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_cmt(data_source); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -264,7 +307,7 @@ static u64 __grt_latency_data(struct perf_event *event, u64 status, WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big); - dse &= PERF_PEBS_DATA_SOURCE_MASK; + dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; val = hybrid_var(event->pmu, pebs_data_source)[dse]; pebs_set_tlb_lock(&val, tlb, lock); @@ -300,6 +343,51 @@ u64 cmt_latency_data(struct perf_event *event, u64 status) dse.mtl_fwd_blk); } +static u64 lnc_latency_data(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + union perf_mem_data_src src; + u64 val; + + dse.val = status; + + /* LNC core latency data */ + val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK]; + if (!val) + val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA); + + if (dse.lnc_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + if (dse.lnc_locked) + val |= P(LOCK, LOCKED); + + if (dse.lnc_data_blk) + val |= P(BLK, DATA); + if (dse.lnc_addr_blk) + val |= P(BLK, ADDR); + if (!dse.lnc_data_blk && !dse.lnc_addr_blk) + val |= P(BLK, NA); + + src.val = val; + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + src.mem_op = P(OP, STORE); + + return src.val; +} + +u64 lnl_latency_data(struct perf_event *event, u64 status) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_small) + return cmt_latency_data(event, status); + + return lnc_latency_data(event, status); +} + static u64 load_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; @@ -1090,6 +1178,8 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), + INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff), + INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fc2561959fed..493bc9f70ffe 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -476,6 +476,14 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID) +#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW) + +#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW) + /* Event constraint, but match on all event flags too. */ #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS) @@ -655,8 +663,10 @@ enum { x86_lbr_exclusive_max, }; -#define PERF_PEBS_DATA_SOURCE_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_MAX 0x100 #define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1) +#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1) enum hybrid_cpu_type { HYBRID_INTEL_NONE, @@ -1552,6 +1562,8 @@ u64 grt_latency_data(struct perf_event *event, u64 status); u64 cmt_latency_data(struct perf_event *event, u64 status); +u64 lnl_latency_data(struct perf_event *event, u64 status); + extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; @@ -1673,6 +1685,8 @@ void intel_pmu_pebs_data_source_mtl(void); void intel_pmu_pebs_data_source_cmt(void); +void intel_pmu_pebs_data_source_lnl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ -- cgit v1.2.3 From 093b0f366567aa3fed85c316f832607069202b23 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:52 +0200 Subject: net: psample: add user cookie Add a user cookie to the sample metadata so that sample emitters can provide more contextual information to samples. If present, send the user cookie in a new attribute: PSAMPLE_ATTR_USER_COOKIE. Reviewed-by: Michal Kubiak Acked-by: Eelco Chaudron Reviewed-by: Simon Horman Reviewed-by: Ido Schimmel Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-2-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/net/psample.h | 2 ++ include/uapi/linux/psample.h | 1 + net/psample/psample.c | 9 ++++++++- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/psample.h b/include/net/psample.h index 0509d2d6be67..2ac71260a546 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -25,6 +25,8 @@ struct psample_metadata { out_tc_occ_valid:1, latency_valid:1, unused:5; + const u8 *user_cookie; + u32 user_cookie_len; }; struct psample_group *psample_group_get(struct net *net, u32 group_num); diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index e585db5bf2d2..e80637e1d97b 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -19,6 +19,7 @@ enum { PSAMPLE_ATTR_LATENCY, /* u64, nanoseconds */ PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */ PSAMPLE_ATTR_PROTO, /* u16 */ + PSAMPLE_ATTR_USER_COOKIE, /* binary, user provided data */ __PSAMPLE_ATTR_MAX }; diff --git a/net/psample/psample.c b/net/psample/psample.c index a5d9b8446f77..b37488f426bc 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -386,7 +386,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, nla_total_size(sizeof(u32)) + /* group_num */ nla_total_size(sizeof(u32)) + /* seq */ nla_total_size_64bit(sizeof(u64)) + /* timestamp */ - nla_total_size(sizeof(u16)); /* protocol */ + nla_total_size(sizeof(u16)) + /* protocol */ + (md->user_cookie_len ? + nla_total_size(md->user_cookie_len) : 0); /* user cookie */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -486,6 +488,11 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, } #endif + if (md->user_cookie && md->user_cookie_len && + nla_put(nl_skb, PSAMPLE_ATTR_USER_COOKIE, md->user_cookie_len, + md->user_cookie)) + goto error; + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); -- cgit v1.2.3 From 7b1b2b60c63f070e0dfbe072ccaae13168b38d01 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:55 +0200 Subject: net: psample: allow using rate as probability Although not explicitly documented in the psample module itself, the definition of PSAMPLE_ATTR_SAMPLE_RATE seems inherited from act_sample. Quoting tc-sample(8): "RATE of 100 will lead to an average of one sampled packet out of every 100 observed." With this semantics, the rates that we can express with an unsigned 32-bits number are very unevenly distributed and concentrated towards "sampling few packets". For example, we can express a probability of 2.32E-8% but we cannot express anything between 100% and 50%. For sampling applications that are capable of sampling a decent amount of packets, this sampling rate semantics is not very useful. Add a new flag to the uAPI that indicates that the sampling rate is expressed in scaled probability, this is: - 0 is 0% probability, no packets get sampled. - U32_MAX is 100% probability, all packets get sampled. Reviewed-by: Aaron Conole Acked-by: Eelco Chaudron Reviewed-by: Ido Schimmel Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-5-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/net/psample.h | 3 ++- include/uapi/linux/psample.h | 10 +++++++++- net/psample/psample.c | 3 +++ 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/psample.h b/include/net/psample.h index 2ac71260a546..c52e9ebd88dd 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -24,7 +24,8 @@ struct psample_metadata { u8 out_tc_valid:1, out_tc_occ_valid:1, latency_valid:1, - unused:5; + rate_as_probability:1, + unused:4; const u8 *user_cookie; u32 user_cookie_len; }; diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index e80637e1d97b..b765f0e81f20 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -8,7 +8,11 @@ enum { PSAMPLE_ATTR_ORIGSIZE, PSAMPLE_ATTR_SAMPLE_GROUP, PSAMPLE_ATTR_GROUP_SEQ, - PSAMPLE_ATTR_SAMPLE_RATE, + PSAMPLE_ATTR_SAMPLE_RATE, /* u32, ratio between observed and + * sampled packets or scaled probability + * if PSAMPLE_ATTR_SAMPLE_PROBABILITY + * is set. + */ PSAMPLE_ATTR_DATA, PSAMPLE_ATTR_GROUP_REFCOUNT, PSAMPLE_ATTR_TUNNEL, @@ -20,6 +24,10 @@ enum { PSAMPLE_ATTR_TIMESTAMP, /* u64, nanoseconds */ PSAMPLE_ATTR_PROTO, /* u16 */ PSAMPLE_ATTR_USER_COOKIE, /* binary, user provided data */ + PSAMPLE_ATTR_SAMPLE_PROBABILITY,/* no argument, interpret rate in + * PSAMPLE_ATTR_SAMPLE_RATE as a + * probability scaled 0 - U32_MAX. + */ __PSAMPLE_ATTR_MAX }; diff --git a/net/psample/psample.c b/net/psample/psample.c index 1c76f3e48dcd..f48b5b9cd409 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -497,6 +497,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, md->user_cookie)) goto error; + if (md->rate_as_probability) + nla_put_flag(skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); -- cgit v1.2.3 From aae0b82b46cb5004bdf82a000c004d69a0885c33 Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:56 +0200 Subject: net: openvswitch: add psample action Add support for a new action: psample. This action accepts a u32 group id and a variable-length cookie and uses the psample multicast group to make the packet available for observability. The maximum length of the user-defined cookie is set to 16, same as tc_cookie, to discourage using cookies that will not be offloadable. Reviewed-by: Michal Kubiak Reviewed-by: Aaron Conole Reviewed-by: Ilya Maximets Acked-by: Eelco Chaudron Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-6-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ovs_flow.yaml | 17 +++++++++++ include/uapi/linux/openvswitch.h | 28 ++++++++++++++++++ net/openvswitch/Kconfig | 1 + net/openvswitch/actions.c | 48 +++++++++++++++++++++++++++++++ net/openvswitch/flow_netlink.c | 32 ++++++++++++++++++++- 5 files changed, 125 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml index 4fdfc6b5cae9..46f5d1cd8a5f 100644 --- a/Documentation/netlink/specs/ovs_flow.yaml +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -727,6 +727,12 @@ attribute-sets: name: dec-ttl type: nest nested-attributes: dec-ttl-attrs + - + name: psample + type: nest + nested-attributes: psample-attrs + doc: | + Sends a packet sample to psample for external observation. - name: tunnel-key-attrs enum-name: ovs-tunnel-key-attr @@ -938,6 +944,17 @@ attribute-sets: - name: gbp type: u32 + - + name: psample-attrs + enum-name: ovs-psample-attr + name-prefix: ovs-psample-attr- + attributes: + - + name: group + type: u32 + - + name: cookie + type: binary operations: name-prefix: ovs-flow-cmd- diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efc82c318fa2..3dd653748725 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -914,6 +914,31 @@ struct check_pkt_len_arg { }; #endif +#define OVS_PSAMPLE_COOKIE_MAX_SIZE 16 +/** + * enum ovs_psample_attr - Attributes for %OVS_ACTION_ATTR_PSAMPLE + * action. + * + * @OVS_PSAMPLE_ATTR_GROUP: 32-bit number to identify the source of the + * sample. + * @OVS_PSAMPLE_ATTR_COOKIE: An optional variable-length binary cookie that + * contains user-defined metadata. The maximum length is + * OVS_PSAMPLE_COOKIE_MAX_SIZE bytes. + * + * Sends the packet to the psample multicast group with the specified group and + * cookie. It is possible to combine this action with the + * %OVS_ACTION_ATTR_TRUNC action to limit the size of the sample. + */ +enum ovs_psample_attr { + OVS_PSAMPLE_ATTR_GROUP = 1, /* u32 number. */ + OVS_PSAMPLE_ATTR_COOKIE, /* Optional, user specified cookie. */ + + /* private: */ + __OVS_PSAMPLE_ATTR_MAX +}; + +#define OVS_PSAMPLE_ATTR_MAX (__OVS_PSAMPLE_ATTR_MAX - 1) + /** * enum ovs_action_attr - Action types. * @@ -966,6 +991,8 @@ struct check_pkt_len_arg { * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS * argument. * @OVS_ACTION_ATTR_DROP: Explicit drop action. + * @OVS_ACTION_ATTR_PSAMPLE: Send a sample of the packet to external observers + * via psample. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -1004,6 +1031,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ OVS_ACTION_ATTR_DROP, /* u32 error code. */ + OVS_ACTION_ATTR_PSAMPLE, /* Nested OVS_PSAMPLE_ATTR_*. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 29a7081858cd..2535f3f9f462 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -10,6 +10,7 @@ config OPENVSWITCH (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) + depends on PSAMPLE || !PSAMPLE select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 964225580824..892d7e48fc5b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -24,6 +24,11 @@ #include #include #include + +#if IS_ENABLED(CONFIG_PSAMPLE) +#include +#endif + #include #include "datapath.h" @@ -1299,6 +1304,40 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +#if IS_ENABLED(CONFIG_PSAMPLE) +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{ + struct psample_group psample_group = {}; + struct psample_metadata md = {}; + const struct nlattr *a; + int rem; + + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_PSAMPLE_ATTR_GROUP: + psample_group.group_num = nla_get_u32(a); + break; + + case OVS_PSAMPLE_ATTR_COOKIE: + md.user_cookie = nla_data(a); + md.user_cookie_len = nla_len(a); + break; + } + } + + psample_group.net = ovs_dp_get_net(dp); + md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; + md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + + psample_sample_packet(&psample_group, skb, 0, &md); +} +#else +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{} +#endif + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1502,6 +1541,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, ovs_kfree_skb_reason(skb, reason); return 0; } + + case OVS_ACTION_ATTR_PSAMPLE: + execute_psample(dp, skb, a); + OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f224d9bcea5e..c92bdc4dfe19 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -64,6 +64,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: case OVS_ACTION_ATTR_DROP: + case OVS_ACTION_ATTR_PSAMPLE: break; case OVS_ACTION_ATTR_CT: @@ -2409,7 +2410,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25); if (!actions) return; @@ -3157,6 +3158,28 @@ static int validate_and_copy_check_pkt_len(struct net *net, return 0; } +static int validate_psample(const struct nlattr *attr) +{ + static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = { + [OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 }, + [OVS_PSAMPLE_ATTR_COOKIE] = { + .type = NLA_BINARY, + .len = OVS_PSAMPLE_COOKIE_MAX_SIZE, + }, + }; + struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1]; + int err; + + if (!IS_ENABLED(CONFIG_PSAMPLE)) + return -EOPNOTSUPP; + + err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL); + if (err) + return err; + + return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL; +} + static int copy_action(const struct nlattr *from, struct sw_flow_actions **sfa, bool log) { @@ -3212,6 +3235,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, [OVS_ACTION_ATTR_DROP] = sizeof(u32), + [OVS_ACTION_ATTR_PSAMPLE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3490,6 +3514,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_PSAMPLE: + err = validate_psample(a); + if (err) + return err; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; -- cgit v1.2.3 From 71763d8a8203c28178d7be7f18af73d4dddb36ba Mon Sep 17 00:00:00 2001 From: Adrian Moreno Date: Thu, 4 Jul 2024 10:56:57 +0200 Subject: net: openvswitch: store sampling probability in cb. When a packet sample is observed, the sampling rate that was used is important to estimate the real frequency of such event. Store the probability of the parent sample action in the skb's cb area and use it in psample action to pass it down to psample module. Reviewed-by: Aaron Conole Acked-by: Eelco Chaudron Reviewed-by: Ilya Maximets Signed-off-by: Adrian Moreno Link: https://patch.msgid.link/20240704085710.353845-7-amorenoz@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/openvswitch.h | 3 ++- net/openvswitch/actions.c | 20 +++++++++++++++++--- net/openvswitch/datapath.h | 3 +++ net/openvswitch/vport.c | 1 + 4 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 3dd653748725..3a701bd1f31b 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -649,7 +649,8 @@ enum ovs_flow_attr { * Actions are passed as nested attributes. * * Executes the specified actions with the given probability on a per-packet - * basis. + * basis. Nested actions will be able to access the probability value of the + * parent @OVS_ACTION_ATTR_SAMPLE. */ enum ovs_sample_attr { OVS_SAMPLE_ATTR_UNSPEC, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 892d7e48fc5b..101f9a23792c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1048,12 +1048,15 @@ static int sample(struct datapath *dp, struct sk_buff *skb, struct nlattr *sample_arg; int rem = nla_len(attr); const struct sample_arg *arg; + u32 init_probability; bool clone_flow_key; + int err; /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */ sample_arg = nla_data(attr); arg = nla_data(sample_arg); actions = nla_next(sample_arg, &rem); + init_probability = OVS_CB(skb)->probability; if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { @@ -1062,9 +1065,16 @@ static int sample(struct datapath *dp, struct sk_buff *skb, return 0; } + OVS_CB(skb)->probability = arg->probability; + clone_flow_key = !arg->exec; - return clone_execute(dp, skb, key, 0, actions, rem, last, - clone_flow_key); + err = clone_execute(dp, skb, key, 0, actions, rem, last, + clone_flow_key); + + if (!last) + OVS_CB(skb)->probability = init_probability; + + return err; } /* When 'last' is true, clone() should always consume the 'skb'. @@ -1311,6 +1321,7 @@ static void execute_psample(struct datapath *dp, struct sk_buff *skb, struct psample_group psample_group = {}; struct psample_metadata md = {}; const struct nlattr *a; + u32 rate; int rem; nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { @@ -1329,8 +1340,11 @@ static void execute_psample(struct datapath *dp, struct sk_buff *skb, psample_group.net = ovs_dp_get_net(dp); md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + md.rate_as_probability = 1; + + rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX; - psample_sample_packet(&psample_group, skb, 0, &md); + psample_sample_packet(&psample_group, skb, rate, &md); } #else static void execute_psample(struct datapath *dp, struct sk_buff *skb, diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 0cd29971a907..9ca6231ea647 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -115,12 +115,15 @@ struct datapath { * fragmented. * @acts_origlen: The netlink size of the flow actions applied to this skb. * @cutlen: The number of bytes from the packet end to be removed. + * @probability: The sampling probability that was applied to this skb; 0 means + * no sampling has occurred; U32_MAX means 100% probability. */ struct ovs_skb_cb { struct vport *input_vport; u16 mru; u16 acts_origlen; u32 cutlen; + u32 probability; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 972ae01a70f7..8732f6e51ae5 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -500,6 +500,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->probability = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { u32 mark; -- cgit v1.2.3 From e46296002113b4556baffd5dc68c4f9e22dae13a Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Thu, 4 Jul 2024 10:11:56 +0200 Subject: net: ethtool: pse-pd: Expand C33 PSE status with class, power and extended state This update expands the status information provided by ethtool for PSE c33. It includes details such as the detected class, current power delivered, and extended state information. Reviewed-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20240704-feature_poe_power_cap-v6-1-320003204264@bootlin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 37 ++++++ include/linux/ethtool.h | 15 +++ include/linux/pse-pd/pse.h | 8 ++ include/uapi/linux/ethtool.h | 191 +++++++++++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 4 + net/ethtool/pse-pd.c | 32 ++++- 6 files changed, 286 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index bfe2eda8580d..0656ad4be000 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1740,6 +1740,13 @@ Kernel response contents: PSE functions. ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. + ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of + the PoE PSE. ====================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies @@ -1772,6 +1779,36 @@ The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_PW_D_STATUS`` implementing .. kernel-doc:: include/uapi/linux/ethtool.h :identifiers: ethtool_c33_pse_pw_d_status +When set, the optional ``ETHTOOL_A_C33_PSE_PW_CLASS`` attribute identifies +the power class of the C33 PSE. It depends on the class negotiated between +the PSE and the PD. This option is corresponding to ``IEEE 802.3-2022`` +30.9.1.1.8 aPSEPowerClassification. + +When set, the optional ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` attribute identifies +This option is corresponding to ``IEEE 802.3-2022`` 30.9.1.1.23 aPSEActualPower. +Actual power is reported in mW. + +When set, the optional ``ETHTOOL_A_C33_PSE_EXT_STATE`` attribute identifies +the extended error state of the C33 PSE. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_c33_pse_ext_state + +When set, the optional ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` attribute identifies +the extended error state of the C33 PSE. Possible values are: +Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_c33_pse_ext_substate_class_num_events + ethtool_c33_pse_ext_substate_error_condition + ethtool_c33_pse_ext_substate_mr_pse_enable + ethtool_c33_pse_ext_substate_option_detect_ted + ethtool_c33_pse_ext_substate_option_vport_lim + ethtool_c33_pse_ext_substate_ovld_detected + ethtool_c33_pse_ext_substate_pd_dll_power_type + ethtool_c33_pse_ext_substate_power_not_available + ethtool_c33_pse_ext_substate_short_detected + PSE_SET ======= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 3a99238ef895..3e70f5d9e0bb 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1273,4 +1273,19 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 6eec24ffa866..38b9308e5e7a 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -36,12 +36,20 @@ struct pse_control_config { * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState * @c33_pw_status: power detection status of the PSE. * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + * @c33_pw_class: detected class of a powered PD + * IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification + * @c33_actual_pw: power currently delivered by the PSE in mW + * IEEE 802.3-2022 30.9.1.1.23 aPSEActualPower + * @c33_ext_state_info: extended state information of the PSE */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; enum ethtool_c33_pse_admin_state c33_admin_state; enum ethtool_c33_pse_pw_d_status c33_pw_status; + u32 c33_pw_class; + u32 c33_actual_pw; + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; }; /** diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index e011384c915c..230110b97029 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -752,6 +752,197 @@ enum ethtool_module_power_mode { ETHTOOL_MODULE_POWER_MODE_HIGH, }; +/** + * enum ethtool_c33_pse_ext_state - groups of PSE extended states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION: Group of error_condition states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID: Group of mr_mps_valid states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE: Group of mr_pse_enable states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED: Group of option_detect_ted + * states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM: Group of option_vport_lim states + * @ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED: Group of ovld_detected states + * @ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE: Group of pd_dll_power_type + * states + * @ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE: Group of power_not_available + * states + * @ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED: Group of short_detected states + */ +enum ethtool_c33_pse_ext_state { + ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION = 1, + ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID, + ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM, + ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED, + ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE, + ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE, + ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_mps_valid - mr_mps_valid states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD: Underload + * state + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN: Port is not + * connected + * + * The PSE monitors either the DC or AC Maintain Power Signature + * (MPS, see 33.2.9.1). This variable indicates the presence or absence of + * a valid MPS. + */ +enum ethtool_c33_pse_ext_substate_mr_mps_valid { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN, +}; + +/** + * enum ethtool_c33_pse_ext_substate_error_condition - error_condition states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT: Non-existing + * port number + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT: Undefined port + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT: Internal + * hardware fault + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON: + * Communication error after force on + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS: Unknown + * port status + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF: Host + * crash turn off + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN: + * Host crash force shutdown + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE: Configuration + * change + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP: Over + * temperature detected + * + * error_condition is a variable indicating the status of + * implementation-specific fault conditions or optionally other system faults + * that prevent the PSE from meeting the specifications in Table 33–11 and that + * require the PSE not to source power. These error conditions are different + * from those monitored by the state diagrams in Figure 33–10. + */ +enum ethtool_c33_pse_ext_substate_error_condition { + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_pse_enable - mr_pse_enable states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE: Disable + * pin active + * + * mr_pse_enable is control variable that selects PSE operation and test + * functions. + */ +enum ethtool_c33_pse_ext_substate_mr_pse_enable { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_detect_ted - option_detect_ted + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS: Detection + * in process + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR: + * Connection check error + * + * option_detect_ted is a variable indicating if detection can be performed + * by the PSE during the ted_timer interval. + */ +enum ethtool_c33_pse_ext_substate_option_detect_ted { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_vport_lim - option_vport_lim states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE: Main supply + * voltage is high + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE: Main supply + * voltage is low + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION: Voltage + * injection into the port + * + * option_vport_lim is an optional variable indicates if VPSE is out of the + * operating range during normal operating state. + */ +enum ethtool_c33_pse_ext_substate_option_vport_lim { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION, +}; + +/** + * enum ethtool_c33_pse_ext_substate_ovld_detected - ovld_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD: Overload state + * + * ovld_detected is a variable indicating if the PSE output current has been + * in an overload condition (see 33.2.7.6) for at least TCUT of a one-second + * sliding time. + */ +enum ethtool_c33_pse_ext_substate_ovld_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_power_not_available - power_not_available + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED: Power + * budget exceeded for the controller + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET: + * Configured port power limit exceeded controller power budget + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT: + * Power request from PD exceeds port limit + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT: Power + * denied due to Hardware power limit + * + * power_not_available is a variable that is asserted in an + * implementation-dependent manner when the PSE is no longer capable of + * sourcing sufficient power to support the attached PD. Sufficient power + * is defined by classification; see 33.2.6. + */ +enum ethtool_c33_pse_ext_substate_power_not_available { + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT, +}; + +/** + * enum ethtool_c33_pse_ext_substate_short_detected - short_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION: Short + * condition was detected + * + * short_detected is a variable indicating if the PSE output current has been + * in a short circuit condition for TLIM within a sliding window (see 33.2.7.7). + */ +enum ethtool_c33_pse_ext_substate_short_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION = 1, +}; + /** * enum ethtool_pse_types - Types of PSE controller. * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 840dabdc9d88..b8895da001bc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -939,6 +939,10 @@ enum { ETHTOOL_A_C33_PSE_ADMIN_STATE, /* u32 */ ETHTOOL_A_C33_PSE_ADMIN_CONTROL, /* u32 */ ETHTOOL_A_C33_PSE_PW_D_STATUS, /* u32 */ + ETHTOOL_A_C33_PSE_PW_CLASS, /* u32 */ + ETHTOOL_A_C33_PSE_ACTUAL_PW, /* u32 */ + ETHTOOL_A_C33_PSE_EXT_STATE, /* u32 */ + ETHTOOL_A_C33_PSE_EXT_SUBSTATE, /* u32 */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 2c981d443f27..d2a1c14d789f 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -86,7 +86,16 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ if (st->c33_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ - + if (st->c33_pw_class > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_CLASS */ + if (st->c33_actual_pw > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_ACTUAL_PW */ + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + len += nla_total_size(sizeof(u32)); /* _C33_PSE_EXT_STATE */ + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0) + /* _C33_PSE_EXT_SUBSTATE */ + len += nla_total_size(sizeof(u32)); + } return len; } @@ -117,6 +126,27 @@ static int pse_fill_reply(struct sk_buff *skb, st->c33_pw_status)) return -EMSGSIZE; + if (st->c33_pw_class > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_CLASS, + st->c33_pw_class)) + return -EMSGSIZE; + + if (st->c33_actual_pw > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_ACTUAL_PW, + st->c33_actual_pw)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_STATE, + st->c33_ext_state_info.c33_pse_ext_state)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_SUBSTATE, + st->c33_ext_state_info.__c33_pse_ext_substate)) + return -EMSGSIZE; + } + return 0; } -- cgit v1.2.3 From 30d7b6727724ce3729f2cb5b8be985d2d1931d2b Mon Sep 17 00:00:00 2001 From: "Kory Maincent (Dent Project)" Date: Thu, 4 Jul 2024 10:12:00 +0200 Subject: net: ethtool: Add new power limit get and set features This patch expands the status information provided by ethtool for PSE c33 with available power limit and available power limit ranges. It also adds a call to pse_ethtool_set_pw_limit() to configure the PSE control power limit. Reviewed-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20240704-feature_poe_power_cap-v6-5-320003204264@bootlin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 64 ++++++++++++++------ include/linux/ethtool.h | 5 ++ include/uapi/linux/ethtool_netlink.h | 8 +++ net/ethtool/pse-pd.c | 89 +++++++++++++++++++++++++--- 4 files changed, 141 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 0656ad4be000..3ab423b80e91 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1730,24 +1730,28 @@ Request contents: Kernel response contents: - ====================================== ====== ============================= - ``ETHTOOL_A_PSE_HEADER`` nested reply header - ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` u32 Operational state of the PoDL - PSE functions - ``ETHTOOL_A_PODL_PSE_PW_D_STATUS`` u32 power detection status of the - PoDL PSE. - ``ETHTOOL_A_C33_PSE_ADMIN_STATE`` u32 Operational state of the PoE - PSE functions. - ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the - PoE PSE. - ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. - ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the - PoE PSE. - ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the - PoE PSE. - ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of - the PoE PSE. - ====================================== ====== ============================= + ========================================== ====== ============================= + ``ETHTOOL_A_PSE_HEADER`` nested reply header + ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` u32 Operational state of the PoDL + PSE functions + ``ETHTOOL_A_PODL_PSE_PW_D_STATUS`` u32 power detection status of the + PoDL PSE. + ``ETHTOOL_A_C33_PSE_ADMIN_STATE`` u32 Operational state of the PoE + PSE functions. + ``ETHTOOL_A_C33_PSE_PW_D_STATUS`` u32 power detection status of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_CLASS`` u32 power class of the PoE PSE. + ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` u32 actual power drawn on the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_STATE`` u32 power extended state of the + PoE PSE. + ``ETHTOOL_A_C33_PSE_EXT_SUBSTATE`` u32 power extended substatus of + the PoE PSE. + ``ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT`` u32 currently configured power + limit of the PoE PSE. + ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES`` nested Supported power limit + configuration ranges. + ========================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies the operational state of the PoDL PSE functions. The operational state of the @@ -1809,6 +1813,16 @@ Possible values are: ethtool_c33_pse_ext_substate_power_not_available ethtool_c33_pse_ext_substate_short_detected +When set, the optional ``ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT`` attribute +identifies the C33 PSE power limit in mW. + +When set the optional ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES`` nested attribute +identifies the C33 PSE power limit ranges through +``ETHTOOL_A_C33_PSE_PWR_VAL_LIMIT_RANGE_MIN`` and +``ETHTOOL_A_C33_PSE_PWR_VAL_LIMIT_RANGE_MAX``. +If the controller works with fixed classes, the min and max values will be +equal. + PSE_SET ======= @@ -1820,6 +1834,8 @@ Request contents: ``ETHTOOL_A_PSE_HEADER`` nested request header ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` u32 Control PoDL PSE Admin state ``ETHTOOL_A_C33_PSE_ADMIN_CONTROL`` u32 Control PSE Admin state + ``ETHTOOL_A_C33_PSE_AVAIL_PWR_LIMIT`` u32 Control PoE PSE available + power limit ====================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` attribute is used @@ -1830,6 +1846,18 @@ to control PoDL PSE Admin functions. This option is implementing The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_CONTROL`` implementing ``IEEE 802.3-2022`` 30.9.1.2.1 acPSEAdminControl. +When set, the optional ``ETHTOOL_A_C33_PSE_AVAIL_PWR_LIMIT`` attribute is +used to control the available power value limit for C33 PSE in milliwatts. +This attribute corresponds to the `pse_available_power` variable described in +``IEEE 802.3-2022`` 33.2.4.4 Variables and `pse_avail_pwr` in 145.2.5.4 +Variables, which are described in power classes. + +It was decided to use milliwatts for this interface to unify it with other +power monitoring interfaces, which also use milliwatts, and to align with +various existing products that document power consumption in watts rather than +classes. If power limit configuration based on classes is needed, the +conversion can be done in user space, for example by ethtool. + RSS_GET ======= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 3e70f5d9e0bb..e213b5508da6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1288,4 +1288,9 @@ struct ethtool_c33_pse_ext_state_info { u32 __c33_pse_ext_substate; }; }; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b8895da001bc..6d5bdcc67631 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -930,6 +930,12 @@ enum { }; /* Power Sourcing Equipment */ +enum { + ETHTOOL_A_C33_PSE_PW_LIMIT_UNSPEC, + ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, /* u32 */ + ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, /* u32 */ +}; + enum { ETHTOOL_A_PSE_UNSPEC, ETHTOOL_A_PSE_HEADER, /* nest - _A_HEADER_* */ @@ -943,6 +949,8 @@ enum { ETHTOOL_A_C33_PSE_ACTUAL_PW, /* u32 */ ETHTOOL_A_C33_PSE_EXT_STATE, /* u32 */ ETHTOOL_A_C33_PSE_EXT_SUBSTATE, /* u32 */ + ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, /* u32 */ + ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES, /* nest - _C33_PSE_PW_LIMIT_* */ /* add new constants above here */ __ETHTOOL_A_PSE_CNT, diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index d2a1c14d789f..ba46c9c8b12d 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -96,9 +96,46 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, /* _C33_PSE_EXT_SUBSTATE */ len += nla_total_size(sizeof(u32)); } + if (st->c33_avail_pw_limit > 0) + /* _C33_AVAIL_PSE_PW_LIMIT */ + len += nla_total_size(sizeof(u32)); + if (st->c33_pw_limit_nb_ranges > 0) + /* _C33_PSE_PW_LIMIT_RANGES */ + len += st->c33_pw_limit_nb_ranges * + (nla_total_size(0) + + nla_total_size(sizeof(u32)) * 2); + return len; } +static int pse_put_pw_limit_ranges(struct sk_buff *skb, + const struct pse_control_status *st) +{ + const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; + int i; + + pw_limit_ranges = st->c33_pw_limit_ranges; + for (i = 0; i < st->c33_pw_limit_nb_ranges; i++) { + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, + pw_limit_ranges->min) || + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, + pw_limit_ranges->max)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + nla_nest_end(skb, nest); + pw_limit_ranges++; + } + + return 0; +} + static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -147,9 +184,25 @@ static int pse_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (st->c33_avail_pw_limit > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, + st->c33_avail_pw_limit)) + return -EMSGSIZE; + + if (st->c33_pw_limit_nb_ranges > 0 && + pse_put_pw_limit_ranges(skb, st)) + return -EMSGSIZE; + return 0; } +static void pse_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct pse_reply_data *data = PSE_REPDATA(reply_base); + + kfree(data->status.c33_pw_limit_ranges); +} + /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { @@ -160,6 +213,7 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), + [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, }; static int @@ -202,19 +256,39 @@ static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; - struct pse_control_config config = {}; struct nlattr **tb = info->attrs; struct phy_device *phydev; + int ret = 0; phydev = dev->phydev; + + if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { + unsigned int pw_limit; + + pw_limit = nla_get_u32(tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]); + ret = pse_ethtool_set_pw_limit(phydev->psec, info->extack, + pw_limit); + if (ret) + return ret; + } + /* These values are already validated by the ethnl_pse_set_policy */ - if (pse_has_podl(phydev->psec)) - config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); - if (pse_has_c33(phydev->psec)) - config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] || + tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) { + struct pse_control_config config = {}; + + if (pse_has_podl(phydev->psec)) + config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); + if (pse_has_c33(phydev->psec)) + config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + + ret = pse_ethtool_set_config(phydev->psec, info->extack, + &config); + if (ret) + return ret; + } - /* Return errno directly - PSE has no notification */ - return pse_ethtool_set_config(phydev->psec, info->extack, &config); + return ret; } const struct ethnl_request_ops ethnl_pse_request_ops = { @@ -227,6 +301,7 @@ const struct ethnl_request_ops ethnl_pse_request_ops = { .prepare_data = pse_prepare_data, .reply_size = pse_reply_size, .fill_reply = pse_fill_reply, + .cleanup_data = pse_cleanup_data, .set_validate = ethnl_set_pse_validate, .set = ethnl_set_pse, -- cgit v1.2.3 From 6a68aed602d7b770552c7f890d0c30c53725c7b8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Jun 2024 21:21:21 -0400 Subject: NFSv4: Add new attribute delegation definitions Add the attribute delegation XDR definitions from the spec. Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust Signed-off-by: Lance Shelton Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 2 +- include/linux/nfs4.h | 9 +++++++++ include/uapi/linux/nfs4.h | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7f294085e887..90df37f3866a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3852,7 +3852,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) -#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_XATTR_SUPPORT - 1UL) +#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_TIME_DELEG_MODIFY - 1UL) static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 0d896ce296ce..c074e0ac390f 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -367,6 +367,8 @@ enum open_delegation_type4 { NFS4_OPEN_DELEGATE_READ = 1, NFS4_OPEN_DELEGATE_WRITE = 2, NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */ + NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, }; enum why_no_delegation4 { /* new to v4.1 */ @@ -507,6 +509,11 @@ enum { FATTR4_XATTR_SUPPORT = 82, }; +enum { + FATTR4_TIME_DELEG_ACCESS = 84, + FATTR4_TIME_DELEG_MODIFY = 85, +}; + /* * The following internal definitions enable processing the above * attribute bits within 32-bit word boundaries. @@ -586,6 +593,8 @@ enum { #define FATTR4_WORD2_SECURITY_LABEL BIT(FATTR4_SEC_LABEL - 64) #define FATTR4_WORD2_MODE_UMASK BIT(FATTR4_MODE_UMASK - 64) #define FATTR4_WORD2_XATTR_SUPPORT BIT(FATTR4_XATTR_SUPPORT - 64) +#define FATTR4_WORD2_TIME_DELEG_ACCESS BIT(FATTR4_TIME_DELEG_ACCESS - 64) +#define FATTR4_WORD2_TIME_DELEG_MODIFY BIT(FATTR4_TIME_DELEG_MODIFY - 64) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 1d2043708bf1..afd7e32906c3 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -69,6 +69,8 @@ #define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000 #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 +#define NFS4_SHARE_WANT_DELEG_TIMESTAMPS 0x100000 + #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 #define NFS4_CDFC4_BOTH 0x3 -- cgit v1.2.3 From d2a00cceb93a4df2afaceb836297628d0aeec7ad Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Jun 2024 21:21:33 -0400 Subject: NFSv4: Detect support for OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION If the server supports the NFSv4.2 protocol extension to optimise away returning a stateid when it returns a delegation, then we cache that information in another capability flag. Signed-off-by: Trond Myklebust Signed-off-by: Lance Shelton Reviewed-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 4 ++++ include/linux/nfs_fs_sb.h | 1 + include/uapi/linux/nfs4.h | 2 ++ 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ae91492e9521..adf4fc8610f6 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3990,6 +3990,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f sizeof(server->attr_bitmask)); server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (res.open_caps.oa_share_access_want[0] & + NFS4_SHARE_WANT_OPEN_XOR_DELEGATION) + server->caps |= NFS_CAP_OPEN_XOR; + memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 5a76a87cd924..fe5b1a8bd723 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -278,6 +278,7 @@ struct nfs_server { #define NFS_CAP_LGOPEN (1U << 5) #define NFS_CAP_CASE_INSENSITIVE (1U << 6) #define NFS_CAP_CASE_PRESERVING (1U << 7) +#define NFS_CAP_OPEN_XOR (1U << 12) #define NFS_CAP_DELEGTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index afd7e32906c3..caf4db2fcbb9 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -46,6 +46,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 #define NFS4_OPEN_RESULT_PRESERVE_UNLINKED 0x0008 +#define NFS4_OPEN_RESULT_NO_OPEN_STATEID 0x0010 #define NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK 0x0020 #define NFS4_SHARE_ACCESS_MASK 0x000F @@ -70,6 +71,7 @@ #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 #define NFS4_SHARE_WANT_DELEG_TIMESTAMPS 0x100000 +#define NFS4_SHARE_WANT_OPEN_XOR_DELEGATION 0x200000 #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 -- cgit v1.2.3 From 00506072d70829196849e835ee4ef0b350b61fb9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 14 Jun 2024 08:59:10 -0400 Subject: nfsd: new netlink ops to get/set server pool_mode Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- Documentation/netlink/specs/nfsd.yaml | 27 +++++++++++++++++ fs/nfsd/netlink.c | 17 +++++++++++ fs/nfsd/netlink.h | 2 ++ fs/nfsd/nfsctl.c | 57 +++++++++++++++++++++++++++++++++++ include/uapi/linux/nfsd_netlink.h | 10 ++++++ 5 files changed, 113 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index 6bda7a467301..c87658114852 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -115,6 +115,15 @@ attribute-sets: type: nest nested-attributes: sock multi-attr: true + - + name: pool-mode + attributes: + - + name: mode + type: string + - + name: npools + type: u32 operations: list: @@ -195,3 +204,21 @@ operations: reply: attributes: - addr + - + name: pool-mode-set + doc: set the current server pool-mode + attribute-set: pool-mode + flags: [ admin-perm ] + do: + request: + attributes: + - mode + - + name: pool-mode-get + doc: get info about server pool-mode + attribute-set: pool-mode + do: + reply: + attributes: + - mode + - npools diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index 529a75ecf22e..ca54aa583530 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -40,6 +40,11 @@ static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_AD [NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy), }; +/* NFSD_CMD_POOL_MODE_SET - do */ +static const struct nla_policy nfsd_pool_mode_set_nl_policy[NFSD_A_POOL_MODE_MODE + 1] = { + [NFSD_A_POOL_MODE_MODE] = { .type = NLA_NUL_STRING, }, +}; + /* Ops table for nfsd */ static const struct genl_split_ops nfsd_nl_ops[] = { { @@ -83,6 +88,18 @@ static const struct genl_split_ops nfsd_nl_ops[] = { .doit = nfsd_nl_listener_get_doit, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = NFSD_CMD_POOL_MODE_SET, + .doit = nfsd_nl_pool_mode_set_doit, + .policy = nfsd_pool_mode_set_nl_policy, + .maxattr = NFSD_A_POOL_MODE_MODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = NFSD_CMD_POOL_MODE_GET, + .doit = nfsd_nl_pool_mode_get_doit, + .flags = GENL_CMD_CAP_DO, + }, }; struct genl_family nfsd_nl_family __ro_after_init = { diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 2e132ef328f8..8eb903f24c41 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -23,6 +23,8 @@ int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info); int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info); +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info); extern struct genl_family nfsd_nl_family; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3da7e4b3e2c3..9e0ea6fc2aa3 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -2156,6 +2156,63 @@ err_free_msg: return err; } +/** + * nfsd_nl_pool_mode_set_doit - set the number of running threads + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + const struct nlattr *attr; + + if (GENL_REQ_ATTR_CHECK(info, NFSD_A_POOL_MODE_MODE)) + return -EINVAL; + + attr = info->attrs[NFSD_A_POOL_MODE_MODE]; + return sunrpc_set_pool_mode(nla_data(attr)); +} + +/** + * nfsd_nl_pool_mode_get_doit - get info about pool_mode + * @skb: reply buffer + * @info: netlink metadata and command arguments + * + * Return 0 on success or a negative errno. + */ +int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + char buf[16]; + void *hdr; + int err; + + if (sunrpc_get_pool_mode(buf, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) + return -ERANGE; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_iput(skb, info); + if (!hdr) + goto err_free_msg; + + err = nla_put_string(skb, NFSD_A_POOL_MODE_MODE, buf) | + nla_put_u32(skb, NFSD_A_POOL_MODE_NPOOLS, nfsd_nrpools(net)); + if (err) + goto err_free_msg; + + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, info); + +err_free_msg: + nlmsg_free(skb); + return err; +} + /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 24c86dbc7ed5..887cbd12b695 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -70,6 +70,14 @@ enum { NFSD_A_SERVER_SOCK_MAX = (__NFSD_A_SERVER_SOCK_MAX - 1) }; +enum { + NFSD_A_POOL_MODE_MODE = 1, + NFSD_A_POOL_MODE_NPOOLS, + + __NFSD_A_POOL_MODE_MAX, + NFSD_A_POOL_MODE_MAX = (__NFSD_A_POOL_MODE_MAX - 1) +}; + enum { NFSD_CMD_RPC_STATUS_GET = 1, NFSD_CMD_THREADS_SET, @@ -78,6 +86,8 @@ enum { NFSD_CMD_VERSION_GET, NFSD_CMD_LISTENER_SET, NFSD_CMD_LISTENER_GET, + NFSD_CMD_POOL_MODE_SET, + NFSD_CMD_POOL_MODE_GET, __NFSD_CMD_MAX, NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1) -- cgit v1.2.3 From e6c06ca8f21d1cdb444c708e385d86a54bc5fc60 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 9 Jul 2024 10:38:30 +0200 Subject: wifi: cfg80211: add support for advertising multiple radios belonging to a wiphy The prerequisite for MLO support in cfg80211/mac80211 is that all the links participating in MLO must be from the same wiphy/ieee80211_hw. To meet this expectation, some drivers may need to group multiple discrete hardware each acting as a link in MLO under single wiphy. With this change, supported frequencies and interface combinations of each individual radio are reported to user space. This allows user space to figure out the limitations of what combination of channels can be used concurrently. Even for non-MLO devices, this improves support for devices capable of running on multiple channels at the same time. Signed-off-by: Felix Fietkau Link: https://patch.msgid.link/18a88f9ce82b1c9f7c12f1672430eaf2bb0be295.1720514221.git-series.nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 42 +++++++++++++++- include/uapi/linux/nl80211.h | 65 +++++++++++++++++++++++++ net/wireless/nl80211.c | 113 ++++++++++++++++++++++++++++++++++++++----- 3 files changed, 208 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6f992aff74ae..a00cf80e61dc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5046,7 +5046,9 @@ struct ieee80211_iface_limit { * struct ieee80211_iface_combination - possible interface combination * * With this structure the driver can describe which interface - * combinations it supports concurrently. + * combinations it supports concurrently. When set in a struct wiphy_radio, + * the combinations refer to combinations of interfaces currently active on + * that radio. * * Examples: * @@ -5406,6 +5408,38 @@ struct wiphy_iftype_akm_suites { int n_akm_suites; }; +/** + * struct wiphy_radio_freq_range - wiphy frequency range + * @start_freq: start range edge frequency (kHz) + * @end_freq: end range edge frequency (kHz) + */ +struct wiphy_radio_freq_range { + u32 start_freq; + u32 end_freq; +}; + + +/** + * struct wiphy_radio - physical radio of a wiphy + * This structure describes a physical radio belonging to a wiphy. + * It is used to describe concurrent-channel capabilities. Only one channel + * can be active on the radio described by struct wiphy_radio. + * + * @freq_range: frequency range that the radio can operate on. + * @n_freq_range: number of elements in @freq_range + * + * @iface_combinations: Valid interface combinations array, should not + * list single interface types. + * @n_iface_combinations: number of entries in @iface_combinations array. + */ +struct wiphy_radio { + const struct wiphy_radio_freq_range *freq_range; + int n_freq_range; + + const struct ieee80211_iface_combination *iface_combinations; + int n_iface_combinations; +}; + #define CFG80211_HW_TIMESTAMP_ALL_PEERS 0xffff /** @@ -5624,6 +5658,9 @@ struct wiphy_iftype_akm_suites { * A value of %CFG80211_HW_TIMESTAMP_ALL_PEERS indicates the driver * supports enabling HW timestamping for all peers (i.e. no need to * specify a mac address). + * + * @radio: radios belonging to this wiphy + * @n_radio: number of radios */ struct wiphy { struct mutex mtx; @@ -5774,6 +5811,9 @@ struct wiphy { u16 hw_timestamp_max_peers; + int n_radio; + const struct wiphy_radio *radio; + char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6ae3997061b6..f97f5adc8d51 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2052,6 +2052,10 @@ enum nl80211_commands { * @NL80211_ATTR_INTERFACE_COMBINATIONS: Nested attribute listing the supported * interface combinations. In each nested item, it contains attributes * defined in &enum nl80211_if_combination_attrs. + * If the wiphy uses multiple radios (@NL80211_ATTR_WIPHY_RADIOS is set), + * this attribute contains the interface combinations of the first radio. + * See @NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS for the global wiphy + * combinations for the sum of all radios. * @NL80211_ATTR_SOFTWARE_IFTYPES: Nested attribute (just like * %NL80211_ATTR_SUPPORTED_IFTYPES) containing the interface types that * are managed in software: interfaces of these types aren't subject to @@ -2856,6 +2860,14 @@ enum nl80211_commands { * %NL80211_CMD_ASSOCIATE indicating the SPP A-MSDUs * are used on this connection * + * @NL80211_ATTR_WIPHY_RADIOS: Nested attribute describing physical radios + * belonging to this wiphy. See &enum nl80211_wiphy_radio_attrs. + * + * @NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS: Nested attribute listing the + * supported interface combinations for all radios combined. In each + * nested item, it contains attributes defined in + * &enum nl80211_if_combination_attrs. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3401,6 +3413,9 @@ enum nl80211_attrs { NL80211_ATTR_ASSOC_SPP_AMSDU, + NL80211_ATTR_WIPHY_RADIOS, + NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -8005,4 +8020,54 @@ enum nl80211_ap_settings_flags { NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT = 1 << 1, }; +/** + * enum nl80211_wiphy_radio_attrs - wiphy radio attributes + * + * @__NL80211_WIPHY_RADIO_ATTR_INVALID: Invalid + * + * @NL80211_WIPHY_RADIO_ATTR_INDEX: Index of this radio (u32) + * @NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE: Frequency range supported by this + * radio. Attribute may be present multiple times. + * @NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION: Supported interface + * combination for this radio. Attribute may be present multiple times + * and contains attributes defined in &enum nl80211_if_combination_attrs. + * + * @__NL80211_WIPHY_RADIO_ATTR_LAST: Internal + * @NL80211_WIPHY_RADIO_ATTR_MAX: Highest attribute + */ +enum nl80211_wiphy_radio_attrs { + __NL80211_WIPHY_RADIO_ATTR_INVALID, + + NL80211_WIPHY_RADIO_ATTR_INDEX, + NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE, + NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION, + + /* keep last */ + __NL80211_WIPHY_RADIO_ATTR_LAST, + NL80211_WIPHY_RADIO_ATTR_MAX = __NL80211_WIPHY_RADIO_ATTR_LAST - 1, +}; + +/** + * enum nl80211_wiphy_radio_freq_range - wiphy radio frequency range + * + * @__NL80211_WIPHY_RADIO_FREQ_ATTR_INVALID: Invalid + * + * @NL80211_WIPHY_RADIO_FREQ_ATTR_START: Frequency range start (u32). + * The unit is kHz. + * @NL80211_WIPHY_RADIO_FREQ_ATTR_END: Frequency range end (u32). + * The unit is kHz. + * + * @__NL80211_WIPHY_RADIO_FREQ_ATTR_LAST: Internal + * @NL80211_WIPHY_RADIO_FREQ_ATTR_MAX: Highest attribute + */ +enum nl80211_wiphy_radio_freq_range { + __NL80211_WIPHY_RADIO_FREQ_ATTR_INVALID, + + NL80211_WIPHY_RADIO_FREQ_ATTR_START, + NL80211_WIPHY_RADIO_FREQ_ATTR_END, + + __NL80211_WIPHY_RADIO_FREQ_ATTR_LAST, + NL80211_WIPHY_RADIO_FREQ_ATTR_MAX = __NL80211_WIPHY_RADIO_FREQ_ATTR_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index deacd5f3f256..7397a372c78e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1632,16 +1632,18 @@ nla_put_failure: } static int nl80211_put_ifcomb_data(struct sk_buff *msg, bool large, int idx, - const struct ieee80211_iface_combination *c) + const struct ieee80211_iface_combination *c, + u16 nested) { struct nlattr *nl_combi, *nl_limits; int i; - nl_combi = nla_nest_start_noflag(msg, idx); + nl_combi = nla_nest_start_noflag(msg, idx | nested); if (!nl_combi) goto nla_put_failure; - nl_limits = nla_nest_start_noflag(msg, NL80211_IFACE_COMB_LIMITS); + nl_limits = nla_nest_start_noflag(msg, NL80211_IFACE_COMB_LIMITS | + nested); if (!nl_limits) goto nla_put_failure; @@ -1689,19 +1691,26 @@ nla_put_failure: static int nl80211_put_iface_combinations(struct wiphy *wiphy, struct sk_buff *msg, - bool large) + int attr, int radio, + bool large, u16 nested) { + const struct ieee80211_iface_combination *c; struct nlattr *nl_combis; - int i; + int i, n; - nl_combis = nla_nest_start_noflag(msg, - NL80211_ATTR_INTERFACE_COMBINATIONS); + nl_combis = nla_nest_start_noflag(msg, attr | nested); if (!nl_combis) goto nla_put_failure; - for (i = 0; i < wiphy->n_iface_combinations; i++) - if (nl80211_put_ifcomb_data(msg, large, i + 1, - &wiphy->iface_combinations[i])) + if (radio >= 0) { + c = wiphy->radio[0].iface_combinations; + n = wiphy->radio[0].n_iface_combinations; + } else { + c = wiphy->iface_combinations; + n = wiphy->n_iface_combinations; + } + for (i = 0; i < n; i++) + if (nl80211_put_ifcomb_data(msg, large, i + 1, &c[i], nested)) goto nla_put_failure; nla_nest_end(msg, nl_combis); @@ -2408,6 +2417,80 @@ fail: return -ENOBUFS; } +static int nl80211_put_radio(struct wiphy *wiphy, struct sk_buff *msg, int idx) +{ + const struct wiphy_radio *r = &wiphy->radio[idx]; + struct nlattr *radio, *freq; + int i; + + radio = nla_nest_start(msg, idx); + if (!radio) + return -ENOBUFS; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_ATTR_INDEX, idx)) + goto nla_put_failure; + + for (i = 0; i < r->n_freq_range; i++) { + const struct wiphy_radio_freq_range *range = &r->freq_range[i]; + + freq = nla_nest_start(msg, NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE); + if (!freq) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_START, + range->start_freq) || + nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_END, + range->end_freq)) + goto nla_put_failure; + + nla_nest_end(msg, freq); + } + + for (i = 0; i < r->n_iface_combinations; i++) + if (nl80211_put_ifcomb_data(msg, true, + NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION, + &r->iface_combinations[i], + NLA_F_NESTED)) + goto nla_put_failure; + + nla_nest_end(msg, radio); + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +static int nl80211_put_radios(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *radios; + int i; + + if (!wiphy->n_radio) + return 0; + + radios = nla_nest_start(msg, NL80211_ATTR_WIPHY_RADIOS); + if (!radios) + return -ENOBUFS; + + for (i = 0; i < wiphy->n_radio; i++) + if (nl80211_put_radio(wiphy, msg, i)) + goto fail; + + nla_nest_end(msg, radios); + + if (nl80211_put_iface_combinations(wiphy, msg, + NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS, + -1, true, NLA_F_NESTED)) + return -ENOBUFS; + + return 0; + +fail: + nla_nest_cancel(msg, radios); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2703,7 +2786,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; if (nl80211_put_iface_combinations(&rdev->wiphy, msg, - state->split)) + NL80211_ATTR_INTERFACE_COMBINATIONS, + rdev->wiphy.n_radio ? 0 : -1, + state->split, 0)) goto nla_put_failure; state->split_start++; @@ -3017,6 +3102,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.hw_timestamp_max_peers)) goto nla_put_failure; + state->split_start++; + break; + case 17: + if (nl80211_put_radios(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; -- cgit v1.2.3 From c714f15860fcca02fe0fd7c3f1f1fc35b1768ac1 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:39 +0800 Subject: iommufd: Add fault and response message definitions iommu_hwpt_pgfaults represent fault messages that the userspace can retrieve. Multiple iommu_hwpt_pgfaults might be put in an iopf group, with the IOMMU_PGFAULT_FLAGS_LAST_PAGE flag set only for the last iommu_hwpt_pgfault. An iommu_hwpt_page_response is a response message that the userspace should send to the kernel after finishing handling a group of fault messages. The @dev_id, @pasid, and @grpid fields in the message identify an outstanding iopf group for a device. The @cookie field, which matches the cookie field of the last fault in the group, will be used by the kernel to look up the pending message. Link: https://lore.kernel.org/r/20240702063444.105814-6-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 83 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 1dfeaa2e649e..4d89ed97b533 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -692,4 +692,87 @@ struct iommu_hwpt_invalidate { __u32 __reserved; }; #define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE) + +/** + * enum iommu_hwpt_pgfault_flags - flags for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_FLAGS_PASID_VALID: The pasid field of the fault data is + * valid. + * @IOMMU_PGFAULT_FLAGS_LAST_PAGE: It's the last fault of a fault group. + */ +enum iommu_hwpt_pgfault_flags { + IOMMU_PGFAULT_FLAGS_PASID_VALID = (1 << 0), + IOMMU_PGFAULT_FLAGS_LAST_PAGE = (1 << 1), +}; + +/** + * enum iommu_hwpt_pgfault_perm - perm bits for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_PERM_READ: request for read permission + * @IOMMU_PGFAULT_PERM_WRITE: request for write permission + * @IOMMU_PGFAULT_PERM_EXEC: (PCIE 10.4.1) request with a PASID that has the + * Execute Requested bit set in PASID TLP Prefix. + * @IOMMU_PGFAULT_PERM_PRIV: (PCIE 10.4.1) request with a PASID that has the + * Privileged Mode Requested bit set in PASID TLP + * Prefix. + */ +enum iommu_hwpt_pgfault_perm { + IOMMU_PGFAULT_PERM_READ = (1 << 0), + IOMMU_PGFAULT_PERM_WRITE = (1 << 1), + IOMMU_PGFAULT_PERM_EXEC = (1 << 2), + IOMMU_PGFAULT_PERM_PRIV = (1 << 3), +}; + +/** + * struct iommu_hwpt_pgfault - iommu page fault data + * @flags: Combination of enum iommu_hwpt_pgfault_flags + * @dev_id: id of the originated device + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @perm: Combination of enum iommu_hwpt_pgfault_perm + * @addr: Fault address + * @length: a hint of how much data the requestor is expecting to fetch. For + * example, if the PRI initiator knows it is going to do a 10MB + * transfer, it could fill in 10MB and the OS could pre-fault in + * 10MB of IOVA. It's default to 0 if there's no such hint. + * @cookie: kernel-managed cookie identifying a group of fault messages. The + * cookie number encoded in the last page fault of the group should + * be echoed back in the response message. + */ +struct iommu_hwpt_pgfault { + __u32 flags; + __u32 dev_id; + __u32 pasid; + __u32 grpid; + __u32 perm; + __u64 addr; + __u32 length; + __u32 cookie; +}; + +/** + * enum iommufd_page_response_code - Return status of fault handlers + * @IOMMUFD_PAGE_RESP_SUCCESS: Fault has been handled and the page tables + * populated, retry the access. This is the + * "Success" defined in PCI 10.4.2.1. + * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the + * access. This is the "Invalid Request" in PCI + * 10.4.2.1. + * @IOMMUFD_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from + * this device if possible. This is the "Response + * Failure" in PCI 10.4.2.1. + */ +enum iommufd_page_response_code { + IOMMUFD_PAGE_RESP_SUCCESS = 0, + IOMMUFD_PAGE_RESP_INVALID, + IOMMUFD_PAGE_RESP_FAILURE, +}; + +/** + * struct iommu_hwpt_page_response - IOMMU page fault response + * @cookie: The kernel-managed cookie reported in the fault message. + * @code: One of response code in enum iommufd_page_response_code. + */ +struct iommu_hwpt_page_response { + __u32 cookie; + __u32 code; +}; #endif -- cgit v1.2.3 From 07838f7fd529c8a6de44b601d4b7057e6c8d36ed Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:40 +0800 Subject: iommufd: Add iommufd fault object An iommufd fault object provides an interface for delivering I/O page faults to user space. These objects are created and destroyed by user space, and they can be associated with or dissociated from hardware page table objects during page table allocation or destruction. User space interacts with the fault object through a file interface. This interface offers a straightforward and efficient way for user space to handle page faults. It allows user space to read fault messages sequentially and respond to them by writing to the same file. The file interface supports reading messages in poll mode, so it's recommended that user space applications use io_uring to enhance read and write efficiency. A fault object can be associated with any iopf-capable iommufd_hw_pgtable during the pgtable's allocation. All I/O page faults triggered by devices when accessing the I/O addresses of an iommufd_hw_pgtable are routed through the fault object to user space. Similarly, user space's responses to these page faults are routed back to the iommu device driver through the same fault object. Link: https://lore.kernel.org/r/20240702063444.105814-7-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/io-pgfault.c | 2 + drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/fault.c | 226 ++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 30 +++++ drivers/iommu/iommufd/main.c | 6 + include/linux/iommu.h | 4 + include/uapi/linux/iommufd.h | 18 +++ 7 files changed, 287 insertions(+) create mode 100644 drivers/iommu/iommufd/fault.c (limited to 'include/uapi/linux') diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 7c9011992d3f..cd679c13752e 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -110,6 +110,8 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, list_add(&group->pending_node, &iopf_param->faults); mutex_unlock(&iopf_param->lock); + group->fault_count = list_count_nodes(&group->faults); + return group; } diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index 34b446146961..cf4605962bea 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ device.o \ + fault.o \ hw_pagetable.o \ io_pagetable.o \ ioas.o \ diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c new file mode 100644 index 000000000000..68ff94671d48 --- /dev/null +++ b/drivers/iommu/iommufd/fault.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024 Intel Corporation + */ +#define pr_fmt(fmt) "iommufd: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../iommu-priv.h" +#include "iommufd_private.h" + +void iommufd_fault_destroy(struct iommufd_object *obj) +{ + struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj); + struct iopf_group *group, *next; + + /* + * The iommufd object's reference count is zero at this point. + * We can be confident that no other threads are currently + * accessing this pointer. Therefore, acquiring the mutex here + * is unnecessary. + */ + list_for_each_entry_safe(group, next, &fault->deliver, node) { + list_del(&group->node); + iopf_group_response(group, IOMMU_PAGE_RESP_INVALID); + iopf_free_group(group); + } +} + +static void iommufd_compose_fault_message(struct iommu_fault *fault, + struct iommu_hwpt_pgfault *hwpt_fault, + struct iommufd_device *idev, + u32 cookie) +{ + hwpt_fault->flags = fault->prm.flags; + hwpt_fault->dev_id = idev->obj.id; + hwpt_fault->pasid = fault->prm.pasid; + hwpt_fault->grpid = fault->prm.grpid; + hwpt_fault->perm = fault->prm.perm; + hwpt_fault->addr = fault->prm.addr; + hwpt_fault->length = 0; + hwpt_fault->cookie = cookie; +} + +static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf, + size_t count, loff_t *ppos) +{ + size_t fault_size = sizeof(struct iommu_hwpt_pgfault); + struct iommufd_fault *fault = filep->private_data; + struct iommu_hwpt_pgfault data; + struct iommufd_device *idev; + struct iopf_group *group; + struct iopf_fault *iopf; + size_t done = 0; + int rc = 0; + + if (*ppos || count % fault_size) + return -ESPIPE; + + mutex_lock(&fault->mutex); + while (!list_empty(&fault->deliver) && count > done) { + group = list_first_entry(&fault->deliver, + struct iopf_group, node); + + if (group->fault_count * fault_size > count - done) + break; + + rc = xa_alloc(&fault->response, &group->cookie, group, + xa_limit_32b, GFP_KERNEL); + if (rc) + break; + + idev = to_iommufd_handle(group->attach_handle)->idev; + list_for_each_entry(iopf, &group->faults, list) { + iommufd_compose_fault_message(&iopf->fault, + &data, idev, + group->cookie); + if (copy_to_user(buf + done, &data, fault_size)) { + xa_erase(&fault->response, group->cookie); + rc = -EFAULT; + break; + } + done += fault_size; + } + + list_del(&group->node); + } + mutex_unlock(&fault->mutex); + + return done == 0 ? rc : done; +} + +static ssize_t iommufd_fault_fops_write(struct file *filep, const char __user *buf, + size_t count, loff_t *ppos) +{ + size_t response_size = sizeof(struct iommu_hwpt_page_response); + struct iommufd_fault *fault = filep->private_data; + struct iommu_hwpt_page_response response; + struct iopf_group *group; + size_t done = 0; + int rc = 0; + + if (*ppos || count % response_size) + return -ESPIPE; + + mutex_lock(&fault->mutex); + while (count > done) { + rc = copy_from_user(&response, buf + done, response_size); + if (rc) + break; + + group = xa_erase(&fault->response, response.cookie); + if (!group) { + rc = -EINVAL; + break; + } + + iopf_group_response(group, response.code); + iopf_free_group(group); + done += response_size; + } + mutex_unlock(&fault->mutex); + + return done == 0 ? rc : done; +} + +static __poll_t iommufd_fault_fops_poll(struct file *filep, + struct poll_table_struct *wait) +{ + struct iommufd_fault *fault = filep->private_data; + __poll_t pollflags = EPOLLOUT; + + poll_wait(filep, &fault->wait_queue, wait); + mutex_lock(&fault->mutex); + if (!list_empty(&fault->deliver)) + pollflags |= EPOLLIN | EPOLLRDNORM; + mutex_unlock(&fault->mutex); + + return pollflags; +} + +static int iommufd_fault_fops_release(struct inode *inode, struct file *filep) +{ + struct iommufd_fault *fault = filep->private_data; + + refcount_dec(&fault->obj.users); + iommufd_ctx_put(fault->ictx); + return 0; +} + +static const struct file_operations iommufd_fault_fops = { + .owner = THIS_MODULE, + .open = nonseekable_open, + .read = iommufd_fault_fops_read, + .write = iommufd_fault_fops_write, + .poll = iommufd_fault_fops_poll, + .release = iommufd_fault_fops_release, + .llseek = no_llseek, +}; + +int iommufd_fault_alloc(struct iommufd_ucmd *ucmd) +{ + struct iommu_fault_alloc *cmd = ucmd->cmd; + struct iommufd_fault *fault; + struct file *filep; + int fdno; + int rc; + + if (cmd->flags) + return -EOPNOTSUPP; + + fault = iommufd_object_alloc(ucmd->ictx, fault, IOMMUFD_OBJ_FAULT); + if (IS_ERR(fault)) + return PTR_ERR(fault); + + fault->ictx = ucmd->ictx; + INIT_LIST_HEAD(&fault->deliver); + xa_init_flags(&fault->response, XA_FLAGS_ALLOC1); + mutex_init(&fault->mutex); + init_waitqueue_head(&fault->wait_queue); + + filep = anon_inode_getfile("[iommufd-pgfault]", &iommufd_fault_fops, + fault, O_RDWR); + if (IS_ERR(filep)) { + rc = PTR_ERR(filep); + goto out_abort; + } + + refcount_inc(&fault->obj.users); + iommufd_ctx_get(fault->ictx); + fault->filep = filep; + + fdno = get_unused_fd_flags(O_CLOEXEC); + if (fdno < 0) { + rc = fdno; + goto out_fput; + } + + cmd->out_fault_id = fault->obj.id; + cmd->out_fault_fd = fdno; + + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_put_fdno; + iommufd_object_finalize(ucmd->ictx, &fault->obj); + + fd_install(fdno, fault->filep); + + return 0; +out_put_fdno: + put_unused_fd(fdno); +out_fput: + fput(filep); + refcount_dec(&fault->obj.users); + iommufd_ctx_put(fault->ictx); +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &fault->obj); + + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 991f864d1f9b..c8a4519f1405 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -128,6 +128,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_HWPT_NESTED, IOMMUFD_OBJ_IOAS, IOMMUFD_OBJ_ACCESS, + IOMMUFD_OBJ_FAULT, #ifdef CONFIG_IOMMUFD_TEST IOMMUFD_OBJ_SELFTEST, #endif @@ -426,6 +427,35 @@ void iopt_remove_access(struct io_pagetable *iopt, u32 iopt_access_list_id); void iommufd_access_destroy_object(struct iommufd_object *obj); +/* + * An iommufd_fault object represents an interface to deliver I/O page faults + * to the user space. These objects are created/destroyed by the user space and + * associated with hardware page table objects during page-table allocation. + */ +struct iommufd_fault { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct file *filep; + + /* The lists of outstanding faults protected by below mutex. */ + struct mutex mutex; + struct list_head deliver; + struct xarray response; + + struct wait_queue_head wait_queue; +}; + +struct iommufd_attach_handle { + struct iommu_attach_handle handle; + struct iommufd_device *idev; +}; + +/* Convert an iommu attach handle to iommufd handle. */ +#define to_iommufd_handle(hdl) container_of(hdl, struct iommufd_attach_handle, handle) + +int iommufd_fault_alloc(struct iommufd_ucmd *ucmd); +void iommufd_fault_destroy(struct iommufd_object *obj); + #ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); void iommufd_selftest_destroy(struct iommufd_object *obj); diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 39b32932c61e..83bbd7c5d160 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -319,6 +319,7 @@ static int iommufd_option(struct iommufd_ucmd *ucmd) union ucmd_buffer { struct iommu_destroy destroy; + struct iommu_fault_alloc fault; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; @@ -355,6 +356,8 @@ struct iommufd_ioctl_op { } static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), + IOCTL_OP(IOMMU_FAULT_QUEUE_ALLOC, iommufd_fault_alloc, struct iommu_fault_alloc, + out_fault_fd), IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info, __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, @@ -513,6 +516,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { .destroy = iommufd_hwpt_nested_destroy, .abort = iommufd_hwpt_nested_abort, }, + [IOMMUFD_OBJ_FAULT] = { + .destroy = iommufd_fault_destroy, + }, #ifdef CONFIG_IOMMUFD_TEST [IOMMUFD_OBJ_SELFTEST] = { .destroy = iommufd_selftest_destroy, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 910aec80886e..73bc3aee95a1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -124,12 +124,16 @@ struct iopf_fault { struct iopf_group { struct iopf_fault last_fault; struct list_head faults; + size_t fault_count; /* list node for iommu_fault_param::faults */ struct list_head pending_node; struct work_struct work; struct iommu_attach_handle *attach_handle; /* The device's fault data parameter. */ struct iommu_fault_param *fault_param; + /* Used by handler provider to hook the group on its own lists. */ + struct list_head node; + u32 cookie; }; /** diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4d89ed97b533..70b8a38fcd46 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -50,6 +50,7 @@ enum { IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, IOMMUFD_CMD_HWPT_INVALIDATE, + IOMMUFD_CMD_FAULT_QUEUE_ALLOC, }; /** @@ -775,4 +776,21 @@ struct iommu_hwpt_page_response { __u32 cookie; __u32 code; }; + +/** + * struct iommu_fault_alloc - ioctl(IOMMU_FAULT_QUEUE_ALLOC) + * @size: sizeof(struct iommu_fault_alloc) + * @flags: Must be 0 + * @out_fault_id: The ID of the new FAULT + * @out_fault_fd: The fd of the new FAULT + * + * Explicitly allocate a fault handling object. + */ +struct iommu_fault_alloc { + __u32 size; + __u32 flags; + __u32 out_fault_id; + __u32 out_fault_fd; +}; +#define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC) #endif -- cgit v1.2.3 From 34765cbc679c59ea5d952d738d2d16bf4aadc497 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 2 Jul 2024 14:34:42 +0800 Subject: iommufd: Associate fault object with iommufd_hw_pgtable When allocating a user iommufd_hw_pagetable, the user space is allowed to associate a fault object with the hw_pagetable by specifying the fault object ID in the page table allocation data and setting the IOMMU_HWPT_FAULT_ID_VALID flag bit. On a successful return of hwpt allocation, the user can retrieve and respond to page faults by reading and writing the file interface of the fault object. Once a fault object has been associated with a hwpt, the hwpt is iopf-capable, indicated by hwpt->fault is non NULL. Attaching, detaching, or replacing an iopf-capable hwpt to an RID or PASID will differ from those that are not iopf-capable. Link: https://lore.kernel.org/r/20240702063444.105814-9-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/fault.c | 17 +++++++++++++++ drivers/iommu/iommufd/hw_pagetable.c | 38 ++++++++++++++++++++++++++------- drivers/iommu/iommufd/iommufd_private.h | 9 ++++++++ include/uapi/linux/iommufd.h | 8 +++++++ 4 files changed, 64 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 4934ae572638..54d6cd20a673 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -414,3 +414,20 @@ out_abort: return rc; } + +int iommufd_fault_iopf_handler(struct iopf_group *group) +{ + struct iommufd_hw_pagetable *hwpt; + struct iommufd_fault *fault; + + hwpt = group->attach_handle->domain->fault_data; + fault = hwpt->fault; + + mutex_lock(&fault->mutex); + list_add_tail(&group->node, &fault->deliver); + mutex_unlock(&fault->mutex); + + wake_up_interruptible(&fault->wait_queue); + + return 0; +} diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 33d142f8057d..e63f80f087d1 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -8,6 +8,15 @@ #include "../iommu-priv.h" #include "iommufd_private.h" +static void __iommufd_hwpt_destroy(struct iommufd_hw_pagetable *hwpt) +{ + if (hwpt->domain) + iommu_domain_free(hwpt->domain); + + if (hwpt->fault) + refcount_dec(&hwpt->fault->obj.users); +} + void iommufd_hwpt_paging_destroy(struct iommufd_object *obj) { struct iommufd_hwpt_paging *hwpt_paging = @@ -22,9 +31,7 @@ void iommufd_hwpt_paging_destroy(struct iommufd_object *obj) hwpt_paging->common.domain); } - if (hwpt_paging->common.domain) - iommu_domain_free(hwpt_paging->common.domain); - + __iommufd_hwpt_destroy(&hwpt_paging->common); refcount_dec(&hwpt_paging->ioas->obj.users); } @@ -49,9 +56,7 @@ void iommufd_hwpt_nested_destroy(struct iommufd_object *obj) struct iommufd_hwpt_nested *hwpt_nested = container_of(obj, struct iommufd_hwpt_nested, common.obj); - if (hwpt_nested->common.domain) - iommu_domain_free(hwpt_nested->common.domain); - + __iommufd_hwpt_destroy(&hwpt_nested->common); refcount_dec(&hwpt_nested->parent->common.obj.users); } @@ -213,7 +218,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, struct iommufd_hw_pagetable *hwpt; int rc; - if (flags || !user_data->len || !ops->domain_alloc_user) + if ((flags & ~IOMMU_HWPT_FAULT_ID_VALID) || + !user_data->len || !ops->domain_alloc_user) return ERR_PTR(-EOPNOTSUPP); if (parent->auto_domain || !parent->nest_parent) return ERR_PTR(-EINVAL); @@ -227,7 +233,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, refcount_inc(&parent->common.obj.users); hwpt_nested->parent = parent; - hwpt->domain = ops->domain_alloc_user(idev->dev, flags, + hwpt->domain = ops->domain_alloc_user(idev->dev, + flags & ~IOMMU_HWPT_FAULT_ID_VALID, parent->common.domain, user_data); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); @@ -308,6 +315,21 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) goto out_put_pt; } + if (cmd->flags & IOMMU_HWPT_FAULT_ID_VALID) { + struct iommufd_fault *fault; + + fault = iommufd_get_fault(ucmd, cmd->fault_id); + if (IS_ERR(fault)) { + rc = PTR_ERR(fault); + goto out_hwpt; + } + hwpt->fault = fault; + hwpt->domain->iopf_handler = iommufd_fault_iopf_handler; + hwpt->domain->fault_data = hwpt; + refcount_inc(&fault->obj.users); + iommufd_put_object(ucmd->ictx, &fault->obj); + } + cmd->out_hwpt_id = hwpt->obj.id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index aa4c26c87cb9..92efe30a8f0d 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -458,8 +458,17 @@ struct iommufd_attach_handle { /* Convert an iommu attach handle to iommufd handle. */ #define to_iommufd_handle(hdl) container_of(hdl, struct iommufd_attach_handle, handle) +static inline struct iommufd_fault * +iommufd_get_fault(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_FAULT), + struct iommufd_fault, obj); +} + int iommufd_fault_alloc(struct iommufd_ucmd *ucmd); void iommufd_fault_destroy(struct iommufd_object *obj); +int iommufd_fault_iopf_handler(struct iopf_group *group); int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 70b8a38fcd46..ede2b464a761 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -357,10 +357,13 @@ struct iommu_vfio_ioas { * the parent HWPT in a nesting configuration. * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is * enforced on device attachment + * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is + * valid. */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, + IOMMU_HWPT_FAULT_ID_VALID = 1 << 2, }; /** @@ -412,6 +415,9 @@ enum iommu_hwpt_data_type { * @data_type: One of enum iommu_hwpt_data_type * @data_len: Length of the type specific data * @data_uptr: User pointer to the type specific data + * @fault_id: The ID of IOMMUFD_FAULT object. Valid only if flags field of + * IOMMU_HWPT_FAULT_ID_VALID is set. + * @__reserved2: Padding to 64-bit alignment. Must be 0. * * Explicitly allocate a hardware page table object. This is the same object * type that is returned by iommufd_device_attach() and represents the @@ -442,6 +448,8 @@ struct iommu_hwpt_alloc { __u32 data_type; __u32 data_len; __aligned_u64 data_uptr; + __u32 fault_id; + __u32 __reserved2; }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) -- cgit v1.2.3 From 87128f520a6b7573f8086f2c89b9381ee7e85e51 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 10 Jun 2024 06:22:56 +0930 Subject: btrfs: uapi: record temporary super flags used by btrfstune [BUG] There is a bug report that a canceled checksum conversion (still experimental feature) results in unexpected super block flags: csum_type 0 (crc32c) csum_size 4 csum 0x14973811 [match] bytenr 65536 flags 0x1000000001 ( WRITTEN | CHANGING_FSID_V2 ) magic _BHRfS_M [match] While for a filesystem with ongoing checksum conversion it should have either CHANGING_DATA_CSUM or CHANGING_META_CSUM. [CAUSE] It turns out that, due to btrfs-progs keeps its own extra flags inside its own ctree.h headers, not the shared uapi headers, we have conflicting super flags: kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_METADUMP_V2 (1ULL << 34) kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_CHANGING_FSID (1ULL << 35) kernel-shared/uapi/btrfs_tree.h:#define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36) kernel-shared/ctree.h:#define BTRFS_SUPER_FLAG_CHANGING_DATA_CSUM (1ULL << 36) kernel-shared/ctree.h:#define BTRFS_SUPER_FLAG_CHANGING_META_CSUM (1ULL << 37) Note that CHANGING_FSID_V2 is conflicting with CHANGING_DATA_CSUM. [FIX] The proper fix would be done inside btrfs-progs, but to keep everything properly recorded, we should have everything inside the same uapi header. Copy all the new flags into uapi header, and change the value for CHANGING_DATA_CSUM and CHANGING_META_CSUM, while keep the value of CHANGING_BG_TREE untouched. Thankfully checksum change is still only experimental and all those CHANGING_* flags are transient (only for btrfs-progs to resume the conversion, and kernel will reject them all), the damage is still minor. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index d24e8e121507..c7636331e566 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -777,6 +777,14 @@ struct btrfs_stripe_extent { #define BTRFS_SUPER_FLAG_CHANGING_FSID (1ULL << 35) #define BTRFS_SUPER_FLAG_CHANGING_FSID_V2 (1ULL << 36) +/* + * Those are temporaray flags utilized by btrfs-progs to do offline conversion. + * They are rejected by kernel. + * But still keep them all here to avoid conflicts. + */ +#define BTRFS_SUPER_FLAG_CHANGING_BG_TREE (1ULL << 38) +#define BTRFS_SUPER_FLAG_CHANGING_DATA_CSUM (1ULL << 39) +#define BTRFS_SUPER_FLAG_CHANGING_META_CSUM (1ULL << 40) /* * items in the extent btree are used to record the objectid of the -- cgit v1.2.3 From 2422547e99f99f952d1a37f26b63289f749d5fcd Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 13 May 2024 18:01:43 +0200 Subject: btrfs: remove raid-stripe-tree encoding field from stripe_extent Remove the encoding field from 'struct btrfs_stripe_extent'. It was originally intended to encode the RAID type as well as if we're a data or a parity stripe. But the RAID type can be inferred form the block-group and the data vs. parity differentiation can be done easier with adding a new key type for parity stripes in the RAID stripe tree. Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 3 --- fs/btrfs/print-tree.c | 5 ----- fs/btrfs/raid-stripe-tree.c | 13 ------------- fs/btrfs/raid-stripe-tree.h | 3 +-- fs/btrfs/tree-checker.c | 19 ------------------- include/uapi/linux/btrfs_tree.h | 14 +------------- 6 files changed, 2 insertions(+), 55 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index 6c3deaa3e878..b2eb9cde2c5d 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -315,11 +315,8 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32); BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64); BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32); -BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8); BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64); BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64); -BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding, - struct btrfs_stripe_extent, encoding, 8); BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64); BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 453cd8358760..32dcea662da3 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -208,11 +208,6 @@ static void print_raid_stripe_key(const struct extent_buffer *eb, u32 item_size, struct btrfs_stripe_extent *stripe) { const int num_stripes = btrfs_num_raid_stripes(item_size); - const u8 encoding = btrfs_stripe_extent_encoding(eb, stripe); - - pr_info("\t\t\tencoding: %s\n", - (encoding && encoding < BTRFS_NR_RAID_TYPES) ? - btrfs_raid_array[encoding].raid_name : "unknown"); for (int i = 0; i < num_stripes; i++) pr_info("\t\t\tstride %d devid %llu physical %llu\n", diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 6af6b4b9a32e..e6f7a234b8f6 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -80,7 +80,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_key stripe_key; struct btrfs_root *stripe_root = fs_info->stripe_root; const int num_stripes = btrfs_bg_type_to_factor(bioc->map_type); - u8 encoding = btrfs_bg_flags_to_raid_index(bioc->map_type); struct btrfs_stripe_extent *stripe_extent; const size_t item_size = struct_size(stripe_extent, strides, num_stripes); int ret; @@ -94,7 +93,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, trace_btrfs_insert_one_raid_extent(fs_info, bioc->logical, bioc->size, num_stripes); - btrfs_set_stack_stripe_extent_encoding(stripe_extent, encoding); for (int i = 0; i < num_stripes; i++) { u64 devid = bioc->stripes[i].dev->devid; u64 physical = bioc->stripes[i].physical; @@ -159,7 +157,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf; const u64 end = logical + *length; int num_stripes; - u8 encoding; u64 offset; u64 found_logical; u64 found_length; @@ -222,16 +219,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, num_stripes = btrfs_num_raid_stripes(btrfs_item_size(leaf, slot)); stripe_extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); - encoding = btrfs_stripe_extent_encoding(leaf, stripe_extent); - - if (encoding != btrfs_bg_flags_to_raid_index(map_type)) { - ret = -EUCLEAN; - btrfs_handle_fs_error(fs_info, ret, - "on-disk stripe encoding %d doesn't match RAID index %d", - encoding, - btrfs_bg_flags_to_raid_index(map_type)); - goto out; - } for (int i = 0; i < num_stripes; i++) { struct btrfs_raid_stride *stride = &stripe_extent->strides[i]; diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h index c9c258f84903..1ac1c21aac2f 100644 --- a/fs/btrfs/raid-stripe-tree.h +++ b/fs/btrfs/raid-stripe-tree.h @@ -48,8 +48,7 @@ static inline bool btrfs_need_stripe_tree_update(struct btrfs_fs_info *fs_info, static inline int btrfs_num_raid_stripes(u32 item_size) { - return (item_size - offsetof(struct btrfs_stripe_extent, strides)) / - sizeof(struct btrfs_raid_stride); + return item_size / sizeof(struct btrfs_raid_stride); } #endif diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a2c3651a3d8f..1e140f6dabc6 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1682,9 +1682,6 @@ static int check_inode_ref(struct extent_buffer *leaf, static int check_raid_stripe_extent(const struct extent_buffer *leaf, const struct btrfs_key *key, int slot) { - struct btrfs_stripe_extent *stripe_extent = - btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); - if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) { generic_err(leaf, slot, "invalid key objectid for raid stripe extent, have %llu expect aligned to %u", @@ -1698,22 +1695,6 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf, return -EUCLEAN; } - switch (btrfs_stripe_extent_encoding(leaf, stripe_extent)) { - case BTRFS_STRIPE_RAID0: - case BTRFS_STRIPE_RAID1: - case BTRFS_STRIPE_DUP: - case BTRFS_STRIPE_RAID10: - case BTRFS_STRIPE_RAID5: - case BTRFS_STRIPE_RAID6: - case BTRFS_STRIPE_RAID1C3: - case BTRFS_STRIPE_RAID1C4: - break; - default: - generic_err(leaf, slot, "invalid raid stripe encoding %u", - btrfs_stripe_extent_encoding(leaf, stripe_extent)); - return -EUCLEAN; - } - return 0; } diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index c7636331e566..fc29d273845d 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -747,21 +747,9 @@ struct btrfs_raid_stride { __le64 physical; } __attribute__ ((__packed__)); -/* The stripe_extent::encoding, 1:1 mapping of enum btrfs_raid_types. */ -#define BTRFS_STRIPE_RAID0 1 -#define BTRFS_STRIPE_RAID1 2 -#define BTRFS_STRIPE_DUP 3 -#define BTRFS_STRIPE_RAID10 4 -#define BTRFS_STRIPE_RAID5 5 -#define BTRFS_STRIPE_RAID6 6 -#define BTRFS_STRIPE_RAID1C3 7 -#define BTRFS_STRIPE_RAID1C4 8 - struct btrfs_stripe_extent { - __u8 encoding; - __u8 reserved[7]; /* An array of raid strides this stripe is composed of. */ - struct btrfs_raid_stride strides[]; + __DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides); } __attribute__ ((__packed__)); #define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) -- cgit v1.2.3 From 861f96a785149a0062cce6578e0fa7cb95435a7e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 10 Jul 2024 16:33:39 +0800 Subject: iommufd: Remove IOMMUFD_PAGE_RESP_FAILURE The response code of IOMMUFD_PAGE_RESP_FAILURE was defined to be equivalent to the "Response Failure" in PCI spec, section 10.4.2.1. This response code indicates that one or more pages within the associated request group have encountered or caused an unrecoverable error. Therefore, this response disables the PRI at the function. Modern I/O virtualization technologies, like SR-IOV, share PRI among the assignable device units. Therefore, a response failure on one unit might cause I/O failure on other units. Remove this response code so that user space can only respond with SUCCESS or INVALID. The VMM is recommended to emulate a failure response as a PRI reset, or PRI disable and changing to a non-PRI domain. Fixes: c714f15860fc ("iommufd: Add fault and response message definitions") Link: https://lore.kernel.org/r/20240710083341.44617-2-baolu.lu@linux.intel.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index ede2b464a761..e31385b75d0b 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -765,14 +765,10 @@ struct iommu_hwpt_pgfault { * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the * access. This is the "Invalid Request" in PCI * 10.4.2.1. - * @IOMMUFD_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from - * this device if possible. This is the "Response - * Failure" in PCI 10.4.2.1. */ enum iommufd_page_response_code { IOMMUFD_PAGE_RESP_SUCCESS = 0, IOMMUFD_PAGE_RESP_INVALID, - IOMMUFD_PAGE_RESP_FAILURE, }; /** -- cgit v1.2.3 From 79cf9c6ee44e0af7e1383365d29c64eece6665bb Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:42 +0200 Subject: media: uapi: pisp_be_config: Drop BIT() from uAPI The pisp_be_config.h uAPI header file contains a bit-field definition that uses the BIT() helper macro. As the BIT() identifier is not defined in userspace, drop it from the uAPI header. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Reviewed-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_be_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index 1684ae068d4f..27d0cc417d6b 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -146,7 +146,7 @@ struct pisp_be_dpc_config { */ struct pisp_be_geq_config { __u16 offset; -#define PISP_BE_GEQ_SHARPER BIT(15) +#define PISP_BE_GEQ_SHARPER (1U << 15) #define PISP_BE_GEQ_SLOPE ((1 << 10) - 1) /* top bit is the "sharper" flag, slope value is bottom 10 bits */ __u16 slope_sharper; -- cgit v1.2.3 From 1991a09e6d7c1dff5efea65b5b31082332f2e64e Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:43 +0200 Subject: media: uapi: pisp_common: Add 32 bpp format test Add definition and test for 32-bits image formats to the pisp_common.h uAPI header. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Acked-by: David Plowman Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_common.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h index b2522e29c976..74d096188233 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_common.h +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -72,6 +72,8 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_SHIFT_8 = 0x00080000, PISP_IMAGE_FORMAT_SHIFT_MASK = 0x000f0000, + PISP_IMAGE_FORMAT_BPP_32 = 0x00100000, + PISP_IMAGE_FORMAT_UNCOMPRESSED = 0x00000000, PISP_IMAGE_FORMAT_COMPRESSION_MODE_1 = 0x01000000, PISP_IMAGE_FORMAT_COMPRESSION_MODE_2 = 0x02000000, @@ -134,6 +136,7 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_PLANARITY_PLANAR) #define PISP_IMAGE_FORMAT_wallpaper(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) +#define PISP_IMAGE_FORMAT_bpp_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) #define PISP_IMAGE_FORMAT_HOG(fmt) \ ((fmt) & \ (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) -- cgit v1.2.3 From f5cee94f2dfe5b7625452b831f7629369ce68a7b Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:44 +0200 Subject: media: uapi: pisp_common: Capitalize all macros The macro used to inspect an image format characteristic use a mixture of capitalized and non-capitalized letters, which is rather unusual for the Linux kernel style. Capitalize all identifiers. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_common.h | 38 +++++++++++----------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_common.h b/include/uapi/linux/media/raspberrypi/pisp_common.h index 74d096188233..cbdccfed1261 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_common.h +++ b/include/uapi/linux/media/raspberrypi/pisp_common.h @@ -92,51 +92,51 @@ enum pisp_image_format { PISP_IMAGE_FORMAT_THREE_CHANNEL }; -#define PISP_IMAGE_FORMAT_bps_8(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_8(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_8) -#define PISP_IMAGE_FORMAT_bps_10(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_10(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_10) -#define PISP_IMAGE_FORMAT_bps_12(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_12(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_12) -#define PISP_IMAGE_FORMAT_bps_16(fmt) \ +#define PISP_IMAGE_FORMAT_BPS_16(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) == PISP_IMAGE_FORMAT_BPS_16) -#define PISP_IMAGE_FORMAT_bps(fmt) \ +#define PISP_IMAGE_FORMAT_BPS(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) ? \ 8 + (2 << (((fmt) & PISP_IMAGE_FORMAT_BPS_MASK) - 1)) : 8) -#define PISP_IMAGE_FORMAT_shift(fmt) \ +#define PISP_IMAGE_FORMAT_SHIFT(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SHIFT_MASK) / PISP_IMAGE_FORMAT_SHIFT_1) -#define PISP_IMAGE_FORMAT_three_channel(fmt) \ +#define PISP_IMAGE_FORMAT_THREE_CHANNEL(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL) -#define PISP_IMAGE_FORMAT_single_channel(fmt) \ +#define PISP_IMAGE_FORMAT_SINGLE_CHANNEL(fmt) \ (!((fmt) & PISP_IMAGE_FORMAT_THREE_CHANNEL)) -#define PISP_IMAGE_FORMAT_compressed(fmt) \ +#define PISP_IMAGE_FORMAT_COMPRESSED(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_COMPRESSION_MASK) != \ PISP_IMAGE_FORMAT_UNCOMPRESSED) -#define PISP_IMAGE_FORMAT_sampling_444(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_444(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_444) -#define PISP_IMAGE_FORMAT_sampling_422(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_422(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_422) -#define PISP_IMAGE_FORMAT_sampling_420(fmt) \ +#define PISP_IMAGE_FORMAT_SAMPLING_420(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_SAMPLING_MASK) == \ PISP_IMAGE_FORMAT_SAMPLING_420) -#define PISP_IMAGE_FORMAT_order_normal(fmt) \ +#define PISP_IMAGE_FORMAT_ORDER_NORMAL(fmt) \ (!((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED)) -#define PISP_IMAGE_FORMAT_order_swapped(fmt) \ +#define PISP_IMAGE_FORMAT_ORDER_SWAPPED(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_ORDER_SWAPPED) -#define PISP_IMAGE_FORMAT_interleaved(fmt) \ +#define PISP_IMAGE_FORMAT_INTERLEAVED(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_INTERLEAVED) -#define PISP_IMAGE_FORMAT_semiplanar(fmt) \ +#define PISP_IMAGE_FORMAT_SEMIPLANAR(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_SEMI_PLANAR) -#define PISP_IMAGE_FORMAT_planar(fmt) \ +#define PISP_IMAGE_FORMAT_PLANAR(fmt) \ (((fmt) & PISP_IMAGE_FORMAT_PLANARITY_MASK) == \ PISP_IMAGE_FORMAT_PLANARITY_PLANAR) -#define PISP_IMAGE_FORMAT_wallpaper(fmt) \ +#define PISP_IMAGE_FORMAT_WALLPAPER(fmt) \ ((fmt) & PISP_IMAGE_FORMAT_WALLPAPER_ROLL) -#define PISP_IMAGE_FORMAT_bpp_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) +#define PISP_IMAGE_FORMAT_BPP_32(fmt) ((fmt) & PISP_IMAGE_FORMAT_BPP_32) #define PISP_IMAGE_FORMAT_HOG(fmt) \ ((fmt) & \ (PISP_IMAGE_FORMAT_HOG_SIGNED | PISP_IMAGE_FORMAT_HOG_UNSIGNED)) -- cgit v1.2.3 From 639065c621df9bad9d94373084e1c568f81d34e0 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:45 +0200 Subject: media: uapi: pisp_be_config: Re-sort pisp_be_tiles_config The order of the members of pisp_be_tiles_config is relevant as the driver logic assumes 'config' to be at offset 0. Re-sort the member to match the driver's expectations. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Acked-by: Naushir Patuck Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/media/raspberrypi/pisp_be_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index 27d0cc417d6b..f8650ca92bf8 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -919,9 +919,9 @@ struct pisp_tile { * @config: PiSP Back End configuration */ struct pisp_be_tiles_config { + struct pisp_be_config config; struct pisp_tile tiles[PISP_BACK_END_NUM_TILES]; __u32 num_tiles; - struct pisp_be_config config; } __attribute__((packed)); #endif /* _UAPI_PISP_BE_CONFIG_H_ */ -- cgit v1.2.3 From 1c2c57bd439ecaffc728139a0a00701bee886d0a Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 28 Jun 2024 15:29:46 +0200 Subject: media: uapi: pisp_be_config: Add extra config fields Complete the pisp_be_config strcture by adding fields that even if not written to the HW are relevant to complete the uAPI and put it in par with the BSP driver. Fixes: c6c49bac8770 ("media: uapi: Add Raspberry Pi PiSP Back End uAPI") Signed-off-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- .../uapi/linux/media/raspberrypi/pisp_be_config.h | 41 ++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/raspberrypi/pisp_be_config.h b/include/uapi/linux/media/raspberrypi/pisp_be_config.h index f8650ca92bf8..cbeb714f4d61 100644 --- a/include/uapi/linux/media/raspberrypi/pisp_be_config.h +++ b/include/uapi/linux/media/raspberrypi/pisp_be_config.h @@ -716,6 +716,13 @@ struct pisp_be_hog_buffer_config { /** * struct pisp_be_config - RaspberryPi PiSP Back End Processing configuration * + * @input_buffer: Input buffer addresses + * @tdn_input_buffer: TDN input buffer addresses + * @stitch_input_buffer: Stitch input buffer addresses + * @tdn_output_buffer: TDN output buffer addresses + * @stitch_output_buffer: Stitch output buffer addresses + * @output_buffer: Output buffers addresses + * @hog_buffer: HOG buffer addresses * @global: Global PiSP configuration * @input_format: Input image format * @decompress: Decompress configuration @@ -753,8 +760,30 @@ struct pisp_be_hog_buffer_config { * @resample: Resampling configuration * @output_format: Output format configuration * @hog: HOG configuration + * @axi: AXI bus configuration + * @lsc_extra: LSC extra info + * @cac_extra: CAC extra info + * @downscale_extra: Downscaler extra info + * @resample_extra: Resample extra info + * @crop: Crop configuration + * @hog_format: HOG format info + * @dirty_flags_bayer: Bayer enable dirty flags + * (:c:type:`pisp_be_bayer_enable`) + * @dirty_flags_rgb: RGB enable dirty flags + * (:c:type:`pisp_be_rgb_enable`) + * @dirty_flags_extra: Extra dirty flags */ struct pisp_be_config { + /* I/O configuration: */ + struct pisp_be_input_buffer_config input_buffer; + struct pisp_be_tdn_input_buffer_config tdn_input_buffer; + struct pisp_be_stitch_input_buffer_config stitch_input_buffer; + struct pisp_be_tdn_output_buffer_config tdn_output_buffer; + struct pisp_be_stitch_output_buffer_config stitch_output_buffer; + struct pisp_be_output_buffer_config + output_buffer[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_hog_buffer_config hog_buffer; + /* Processing configuration: */ struct pisp_be_global_config global; struct pisp_image_format_config input_format; struct pisp_decompress_config decompress; @@ -793,6 +822,18 @@ struct pisp_be_config { struct pisp_be_output_format_config output_format[PISP_BACK_END_NUM_OUTPUTS]; struct pisp_be_hog_config hog; + struct pisp_be_axi_config axi; + /* Non-register fields: */ + struct pisp_be_lsc_extra lsc_extra; + struct pisp_be_cac_extra cac_extra; + struct pisp_be_downscale_extra + downscale_extra[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_resample_extra resample_extra[PISP_BACK_END_NUM_OUTPUTS]; + struct pisp_be_crop_config crop; + struct pisp_image_format_config hog_format; + __u32 dirty_flags_bayer; /* these use pisp_be_bayer_enable */ + __u32 dirty_flags_rgb; /* use pisp_be_rgb_enable */ + __u32 dirty_flags_extra; /* these use pisp_be_dirty_t */ } __attribute__((packed)); /** -- cgit v1.2.3 From bc1a5cd002116552db4c3541e91f8a5b1b0cf65d Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Wed, 10 Apr 2024 15:07:28 -0700 Subject: KVM: Add KVM_PRE_FAULT_MEMORY vcpu ioctl to pre-populate guest memory Add a new ioctl KVM_PRE_FAULT_MEMORY in the KVM common code. It iterates on the memory range and calls the arch-specific function. The implementation is optional and enabled by a Kconfig symbol. Suggested-by: Sean Christopherson Signed-off-by: Isaku Yamahata Reviewed-by: Rick Edgecombe Message-ID: <819322b8f25971f2b9933bfa4506e618508ad782.1712785629.git.isaku.yamahata@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 ++++ include/uapi/linux/kvm.h | 10 ++++++++ virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 78 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7b57878c8c18..c3c922bf077f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2477,4 +2477,9 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d03842abae57..e5af8c692dc0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -917,6 +917,7 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1548,4 +1549,13 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 754c6c923427..b14e14cdbfb9 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -67,6 +67,9 @@ config HAVE_KVM_INVALID_WAKEUPS config KVM_GENERIC_DIRTYLOG_READ_PROTECT bool +config KVM_GENERIC_PRE_FAULT_MEMORY + bool + config KVM_COMPAT def_bool y depends on KVM && COMPAT && !(S390 || ARM64 || RISCV) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8e422c2c9450..f817ec66c85f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4373,6 +4373,52 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) return fd; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + int idx; + long r; + u64 full_size; + + if (range->flags) + return -EINVAL; + + if (!PAGE_ALIGNED(range->gpa) || + !PAGE_ALIGNED(range->size) || + range->gpa + range->size <= range->gpa) + return -EINVAL; + + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + full_size = range->size; + do { + if (signal_pending(current)) { + r = -EINTR; + break; + } + + r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); + if (WARN_ON_ONCE(r == 0 || r == -EIO)) + break; + + if (r < 0) + break; + + range->size -= r; + range->gpa += r; + cond_resched(); + } while (range->size); + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + vcpu_put(vcpu); + + /* Return success if at least one page was mapped successfully. */ + return full_size == range->size ? r : 0; +} +#endif + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4573,6 +4619,20 @@ out_free1: r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY + case KVM_PRE_FAULT_MEMORY: { + struct kvm_pre_fault_memory range; + + r = -EFAULT; + if (copy_from_user(&range, argp, sizeof(range))) + break; + r = kvm_vcpu_pre_fault_memory(vcpu, &range); + /* Pass back leftover range. */ + if (copy_to_user(argp, &range, sizeof(range))) + r = -EFAULT; + break; + } +#endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } -- cgit v1.2.3 From ed5d583a88a9207b866c14ba834984c6f3c51d23 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 27 Jun 2024 10:08:54 -0700 Subject: fs/procfs: implement efficient VMA querying API for /proc//maps /proc//maps file is extremely useful in practice for various tasks involving figuring out process memory layout, what files are backing any given memory range, etc. One important class of applications that absolutely rely on this are profilers/stack symbolizers (perf tool being one of them). Patterns of use differ, but they generally would fall into two categories. In on-demand pattern, a profiler/symbolizer would normally capture stack trace containing absolute memory addresses of some functions, and would then use /proc//maps file to find corresponding backing ELF files (normally, only executable VMAs are of interest), file offsets within them, and then continue from there to get yet more information (ELF symbols, DWARF information) to get human-readable symbolic information. This pattern is used by Meta's fleet-wide profiler, as one example. In preprocessing pattern, application doesn't know the set of addresses of interest, so it has to fetch all relevant VMAs (again, probably only executable ones), store or cache them, then proceed with profiling and stack trace capture. Once done, it would do symbolization based on stored VMA information. This can happen at much later point in time. This patterns is used by perf tool, as an example. In either case, there are both performance and correctness requirement involved. This address to VMA information translation has to be done as efficiently as possible, but also not miss any VMA (especially in the case of loading/unloading shared libraries). In practice, correctness can't be guaranteed (due to process dying before VMA data can be captured, or shared library being unloaded, etc), but any effort to maximize the chance of finding the VMA is appreciated. Unfortunately, for all the /proc//maps file universality and usefulness, it doesn't fit the above use cases 100%. First, it's main purpose is to emit all VMAs sequentially, but in practice captured addresses would fall only into a smaller subset of all process' VMAs, mainly containing executable text. Yet, library would need to parse most or all of the contents to find needed VMAs, as there is no way to skip VMAs that are of no use. Efficient library can do the linear pass and it is still relatively efficient, but it's definitely an overhead that can be avoided, if there was a way to do more targeted querying of the relevant VMA information. Second, it's a text based interface, which makes its programmatic use from applications and libraries more cumbersome and inefficient due to the need to handle text parsing to get necessary pieces of information. The overhead is actually payed both by kernel, formatting originally binary VMA data into text, and then by user space application, parsing it back into binary data for further use. For the on-demand pattern of usage, described above, another problem when writing generic stack trace symbolization library is an unfortunate performance-vs-correctness tradeoff that needs to be made. Library has to make a decision to either cache parsed contents of /proc//maps (after initial processing) to service future requests (if application requests to symbolize another set of addresses (for the same process), captured at some later time, which is typical for periodic/continuous profiling cases) to avoid higher costs of re-parsing this file. Or it has to choose to cache the contents in memory to speed up future requests. In the former case, more memory is used for the cache and there is a risk of getting stale data if application loads or unloads shared libraries, or otherwise changed its set of VMAs somehow, e.g., through additional mmap() calls. In the latter case, it's the performance hit that comes from re-opening the file and re-parsing its contents all over again. This patch aims to solve this problem by providing a new API built on top of /proc//maps. It's meant to address both non-selectiveness and text nature of /proc//maps, by giving user more control of what sort of VMA(s) needs to be queried, and being binary-based interface eliminates the overhead of text formatting (on kernel side) and parsing (on user space side). It's also designed to be extensible and forward/backward compatible by including required struct size field, which user has to provide. We use established copy_struct_from_user() approach to handle extensibility. User has a choice to pick either getting VMA that covers provided address or -ENOENT if none is found (exact, least surprising, case). Or, with an extra query flag (PROCMAP_QUERY_COVERING_OR_NEXT_VMA), they can get either VMA that covers the address (if there is one), or the closest next VMA (i.e., VMA with the smallest vm_start > addr). The latter allows more efficient use, but, given it could be a surprising behavior, requires an explicit opt-in. There is another query flag that is useful for some use cases. PROCMAP_QUERY_FILE_BACKED_VMA instructs this API to only return file-backed VMAs. Combining this with PROCMAP_QUERY_COVERING_OR_NEXT_VMA makes it possible to efficiently iterate only file-backed VMAs of the process, which is what profilers/symbolizers are normally interested in. All the above querying flags can be combined with (also optional) set of desired VMA permissions flags. This allows to, for example, iterate only an executable subset of VMAs, which is what preprocessing pattern, used by perf tool, would benefit from, as the assumption is that captured stack traces would have addresses of executable code. This saves time by skipping non-executable VMAs altogether efficienty. All these querying flags (modifiers) are orthogonal and can be combined in a semantically meaningful and natural way. Basing this ioctl()-based API on top of /proc//maps's FD makes sense given it's querying the same set of VMA data. It's also benefitial because permission checks for /proc//maps is performed at open time once, and the actual data read of text contents of /proc//maps is done without further permission checks. We piggyback on this pattern with ioctl()-based API as well, as that's a desired property. Both for performance reasons, but also for security and flexibility reasons. Allowing application to open an FD for /proc/self/maps without any extra capabilities, and then passing it to some sort of profiling agent through Unix-domain socket, would allow such profiling agent to not require some of the capabilities that are otherwise expected when opening /proc//maps file for *another* process. This is a desirable property for some more restricted setups. This new ioctl-based implementation doesn't interfere with seq_file-based implementation of /proc//maps textual interface, and so could be used together or independently without paying any price for that. Note also, that fetching VMA name (e.g., backing file path, or special hard-coded or user-provided names) is optional just like build ID. If user sets vma_name_size to zero, kernel code won't attempt to retrieve it, saving resources. Earlier versions of this patch set were adding per-VMA locking, which is why we have a code structure that is ready for abstracting mmap_lock vs vm_lock differences (query_vma_setup(), query_vma_teardown(), and query_vma_find_by_addr()), but given anon_vma_name() is not yet compatible with per-VMA locking, initial implementation sticks to using only mmap_lock for now. It will be easy to add back per-VMA locking once all the pieces are ready later on. Which is why we keep existing code structure with setup/teardown/query helper functions. [andrii@kernel.org: improve PROCMAP_QUERY's compat mode handling] Link: https://lkml.kernel.org/r/20240701174805.1897344-2-andrii@kernel.org Link: https://lkml.kernel.org/r/20240627170900.1672542-3-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Liam R. Howlett Cc: Alexey Dobriyan Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Mike Rapoport (IBM) Cc: Suren Baghdasaryan Cc: Andi Kleen Cc: Arnd Bergmann Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 235 ++++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fs.h | 130 ++++++++++++++++++++++++++- 2 files changed, 364 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 507b7dc7c4c8..75679b5de549 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -375,11 +375,246 @@ static int pid_maps_open(struct inode *inode, struct file *file) return do_maps_open(inode, file, &proc_pid_maps_op); } +#define PROCMAP_QUERY_VMA_FLAGS ( \ + PROCMAP_QUERY_VMA_READABLE | \ + PROCMAP_QUERY_VMA_WRITABLE | \ + PROCMAP_QUERY_VMA_EXECUTABLE | \ + PROCMAP_QUERY_VMA_SHARED \ +) + +#define PROCMAP_QUERY_VALID_FLAGS_MASK ( \ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA | \ + PROCMAP_QUERY_FILE_BACKED_VMA | \ + PROCMAP_QUERY_VMA_FLAGS \ +) + +static int query_vma_setup(struct mm_struct *mm) +{ + return mmap_read_lock_killable(mm); +} + +static void query_vma_teardown(struct mm_struct *mm, struct vm_area_struct *vma) +{ + mmap_read_unlock(mm); +} + +static struct vm_area_struct *query_vma_find_by_addr(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +static struct vm_area_struct *query_matching_vma(struct mm_struct *mm, + unsigned long addr, u32 flags) +{ + struct vm_area_struct *vma; + +next_vma: + vma = query_vma_find_by_addr(mm, addr); + if (!vma) + goto no_vma; + + /* user requested only file-backed VMA, keep iterating */ + if ((flags & PROCMAP_QUERY_FILE_BACKED_VMA) && !vma->vm_file) + goto skip_vma; + + /* VMA permissions should satisfy query flags */ + if (flags & PROCMAP_QUERY_VMA_FLAGS) { + u32 perm = 0; + + if (flags & PROCMAP_QUERY_VMA_READABLE) + perm |= VM_READ; + if (flags & PROCMAP_QUERY_VMA_WRITABLE) + perm |= VM_WRITE; + if (flags & PROCMAP_QUERY_VMA_EXECUTABLE) + perm |= VM_EXEC; + if (flags & PROCMAP_QUERY_VMA_SHARED) + perm |= VM_MAYSHARE; + + if ((vma->vm_flags & perm) != perm) + goto skip_vma; + } + + /* found covering VMA or user is OK with the matching next VMA */ + if ((flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) || vma->vm_start <= addr) + return vma; + +skip_vma: + /* + * If the user needs closest matching VMA, keep iterating. + */ + addr = vma->vm_end; + if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) + goto next_vma; +no_vma: + return ERR_PTR(-ENOENT); +} + +static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) +{ + struct procmap_query karg; + struct vm_area_struct *vma; + struct mm_struct *mm; + const char *name = NULL; + char *name_buf = NULL; + __u64 usize; + int err; + + if (copy_from_user(&usize, (void __user *)uarg, sizeof(usize))) + return -EFAULT; + /* argument struct can never be that large, reject abuse */ + if (usize > PAGE_SIZE) + return -E2BIG; + /* argument struct should have at least query_flags and query_addr fields */ + if (usize < offsetofend(struct procmap_query, query_addr)) + return -EINVAL; + err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + if (err) + return err; + + /* reject unknown flags */ + if (karg.query_flags & ~PROCMAP_QUERY_VALID_FLAGS_MASK) + return -EINVAL; + /* either both buffer address and size are set, or both should be zero */ + if (!!karg.vma_name_size != !!karg.vma_name_addr) + return -EINVAL; + + mm = priv->mm; + if (!mm || !mmget_not_zero(mm)) + return -ESRCH; + + err = query_vma_setup(mm); + if (err) { + mmput(mm); + return err; + } + + vma = query_matching_vma(mm, karg.query_addr, karg.query_flags); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + vma = NULL; + goto out; + } + + karg.vma_start = vma->vm_start; + karg.vma_end = vma->vm_end; + + karg.vma_flags = 0; + if (vma->vm_flags & VM_READ) + karg.vma_flags |= PROCMAP_QUERY_VMA_READABLE; + if (vma->vm_flags & VM_WRITE) + karg.vma_flags |= PROCMAP_QUERY_VMA_WRITABLE; + if (vma->vm_flags & VM_EXEC) + karg.vma_flags |= PROCMAP_QUERY_VMA_EXECUTABLE; + if (vma->vm_flags & VM_MAYSHARE) + karg.vma_flags |= PROCMAP_QUERY_VMA_SHARED; + + karg.vma_page_size = vma_kernel_pagesize(vma); + + if (vma->vm_file) { + const struct inode *inode = file_user_inode(vma->vm_file); + + karg.vma_offset = ((__u64)vma->vm_pgoff) << PAGE_SHIFT; + karg.dev_major = MAJOR(inode->i_sb->s_dev); + karg.dev_minor = MINOR(inode->i_sb->s_dev); + karg.inode = inode->i_ino; + } else { + karg.vma_offset = 0; + karg.dev_major = 0; + karg.dev_minor = 0; + karg.inode = 0; + } + + if (karg.build_id_size) { + __u32 build_id_sz; + + err = build_id_parse(vma, build_id_buf, &build_id_sz); + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + + if (karg.vma_name_size) { + size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); + const struct path *path; + const char *name_fmt; + size_t name_sz = 0; + + get_vma_name(vma, &path, &name, &name_fmt); + + if (path || name_fmt || name) { + name_buf = kmalloc(name_buf_sz, GFP_KERNEL); + if (!name_buf) { + err = -ENOMEM; + goto out; + } + } + if (path) { + name = d_path(path, name_buf, name_buf_sz); + if (IS_ERR(name)) { + err = PTR_ERR(name); + goto out; + } + name_sz = name_buf + name_buf_sz - name; + } else if (name || name_fmt) { + name_sz = 1 + snprintf(name_buf, name_buf_sz, name_fmt ?: "%s", name); + name = name_buf; + } + if (name_sz > name_buf_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.vma_name_size = name_sz; + } + + /* unlock vma or mmap_lock, and put mm_struct before copying data to user */ + query_vma_teardown(mm, vma); + mmput(mm); + + if (karg.vma_name_size && copy_to_user((void __user *)karg.vma_name_addr, + name, karg.vma_name_size)) { + kfree(name_buf); + return -EFAULT; + } + kfree(name_buf); + + if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize))) + return -EFAULT; + + return 0; + +out: + query_vma_teardown(mm, vma); + mmput(mm); + kfree(name_buf); + return err; +} + +static long procfs_procmap_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + switch (cmd) { + case PROCMAP_QUERY: + return do_procmap_query(priv, (void __user *)arg); + default: + return -ENOIOCTLCMD; + } +} + const struct file_operations proc_pid_maps_operations = { .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, .release = proc_map_release, + .unlocked_ioctl = procfs_procmap_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; /* diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 45e4e64fd664..5d440f9b5d92 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -333,8 +333,10 @@ typedef int __bitwise __kernel_rwf_t; #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND) +#define PROCFS_IOCTL_MAGIC 'f' + /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -393,4 +395,130 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc//maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc//maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3 From bfc69fd05ef9b6416f4811aafafb7f2b34daa000 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 27 Jun 2024 10:08:55 -0700 Subject: fs/procfs: add build ID fetching to PROCMAP_QUERY API The need to get ELF build ID reliably is an important aspect when dealing with profiling and stack trace symbolization, and /proc//maps textual representation doesn't help with this. To get backing file's ELF build ID, application has to first resolve VMA, then use it's start/end address range to follow a special /proc//map_files/- symlink to open the ELF file (this is necessary because backing file might have been removed from the disk or was already replaced with another binary in the same file path. Such approach, beyond just adding complexity of having to do a bunch of extra work, has extra security implications. Because application opens underlying ELF file and needs read access to its entire contents (as far as kernel is concerned), kernel puts additional capable() checks on following /proc//map_files/- symlink. And that makes sense in general. But in the case of build ID, profiler/symbolizer doesn't need the contents of ELF file, per se. It's only build ID that is of interest, and ELF build ID itself doesn't provide any sensitive information. So this patch adds a way to request backing file's ELF build ID along the rest of VMA information in the same API. User has control over whether this piece of information is requested or not by either setting build_id_size field to zero or non-zero maximum buffer size they provided through build_id_addr field (which encodes user pointer as __u64 field). This is a completely optional piece of information, and so has no performance implications for user cases that don't care about build ID, while improving performance and simplifying the setup for those application that do need it. Kernel already implements build ID fetching, which is used from BPF subsystem. We are reusing this code here, but plan a follow up changes to make it work better under more relaxed assumption (compared to what existing code assumes) of being called from user process context, in which page faults are allowed. BPF-specific implementation currently bails out if necessary part of ELF file is not paged in, all due to extra BPF-specific restrictions (like the need to fetch build ID in restrictive contexts such as NMI handler). [andrii@kernel.org: fix integer to pointer cast warning in do_procmap_query()] Link: https://lkml.kernel.org/r/20240701174805.1897344-1-andrii@kernel.org Link: https://lkml.kernel.org/r/20240627170900.1672542-4-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Liam R. Howlett Cc: Alexey Dobriyan Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Mike Rapoport (IBM) Cc: Suren Baghdasaryan Cc: Andi Kleen Cc: Arnd Bergmann Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 27 +++++++++++++++++++++++++-- include/uapi/linux/fs.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 75679b5de549..728693ed00e6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -445,6 +446,7 @@ skip_vma: addr = vma->vm_end; if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) goto next_vma; + no_vma: return ERR_PTR(-ENOENT); } @@ -455,7 +457,7 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) struct vm_area_struct *vma; struct mm_struct *mm; const char *name = NULL; - char *name_buf = NULL; + char build_id_buf[BUILD_ID_SIZE_MAX], *name_buf = NULL; __u64 usize; int err; @@ -477,6 +479,8 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) /* either both buffer address and size are set, or both should be zero */ if (!!karg.vma_name_size != !!karg.vma_name_addr) return -EINVAL; + if (!!karg.build_id_size != !!karg.build_id_addr) + return -EINVAL; mm = priv->mm; if (!mm || !mmget_not_zero(mm)) @@ -539,6 +543,21 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) } } + if (karg.build_id_size) { + __u32 build_id_sz; + + err = build_id_parse(vma, build_id_buf, &build_id_sz); + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + if (karg.vma_name_size) { size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); const struct path *path; @@ -576,13 +595,17 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg) query_vma_teardown(mm, vma); mmput(mm); - if (karg.vma_name_size && copy_to_user((void __user *)karg.vma_name_addr, + if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr), name, karg.vma_name_size)) { kfree(name_buf); return -EFAULT; } kfree(name_buf); + if (karg.build_id_size && copy_to_user(u64_to_user_ptr(karg.build_id_addr), + build_id_buf, karg.build_id_size)) + return -EFAULT; + if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize))) return -EFAULT; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 5d440f9b5d92..2a4a5f50c98e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -511,6 +511,26 @@ struct procmap_query { * If set to zero, vma_name_addr should be set to zero as well */ __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ /* * User-supplied address of a buffer of at least vma_name_size bytes * for kernel to fill with matched VMA's name (see vma_name_size field @@ -519,6 +539,14 @@ struct procmap_query { * Should be set to zero if VMA name should not be returned. */ __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ }; #endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3 From 2c1583290b08c5aa9005178a573be8f329de2976 Mon Sep 17 00:00:00 2001 From: "Kamil Horák (2N)" Date: Fri, 12 Jul 2024 17:07:06 +0200 Subject: net: phy: bcm54811: New link mode for BroadR-Reach MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new link mode necessary for 10 MBit single-pair connection in BroadR-Reach mode on bcm5481x PHY by Broadcom. This new link mode, 10baseT1BRR, is known as 1BR10 in the Broadcom terminology. Another link mode to be used is 1BR100 and it is already present as 100baseT1, because Broadcom's 1BR100 became 100baseT1 (IEEE 802.3bw). Signed-off-by: Kamil Horák (2N) Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240712150709.3134474-2-kamilh@axis.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy-core.c | 3 ++- include/uapi/linux/ethtool.h | 1 + net/ethtool/common.c | 3 +++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index a235ea2264a7..1f98b6a96c15 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -13,7 +13,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 102, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 103, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -266,6 +266,7 @@ static const struct phy_setting settings[] = { PHY_SETTING( 10, FULL, 10baseT1S_Full ), PHY_SETTING( 10, HALF, 10baseT1S_Half ), PHY_SETTING( 10, HALF, 10baseT1S_P2MP_Half ), + PHY_SETTING( 10, FULL, 10baseT1BRR_Full ), }; #undef PHY_SETTING diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 230110b97029..4a0a6e703483 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2054,6 +2054,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, + ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT = 102, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 67d06cd002a5..5f99a32e4fe5 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -211,6 +211,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(10, T1S, Full), __DEFINE_LINK_MODE_NAME(10, T1S, Half), __DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_NAME(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -251,6 +252,7 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_T1S_P2MP 1 #define __LINK_MODE_LANES_VR8 8 #define __LINK_MODE_LANES_DR8_2 8 +#define __LINK_MODE_LANES_T1BRR 1 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -374,6 +376,7 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); -- cgit v1.2.3 From 136a8066676e593cd29627219467fc222c8f3b04 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 11 Jul 2024 21:11:03 -0300 Subject: iommufd: Put constants for all the uAPI enums Relying on position in the enum makes it subtly harder when doing merge resolutions or backporting as it is easy to grab a patch and not notice it is a uAPI change with a differently ordered enum. This may become a bigger problem in next cycles when iommu_hwpt_invalidate_data_type and other per-driver enums have patches flowing through different trees. So lets start including constants for all the uAPI enums to make this safer. No functional change. Link: https://lore.kernel.org/r/0-v1-2c06ec044924+133-iommufd_uapi_const_jgg@nvidia.com Reviewed-by: Kevin Tian Reviewed-by: Yi Liu Tested-by: Yi Liu Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index e31385b75d0b..4dde745cfb7e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -37,20 +37,20 @@ enum { IOMMUFD_CMD_BASE = 0x80, IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, - IOMMUFD_CMD_IOAS_ALLOC, - IOMMUFD_CMD_IOAS_ALLOW_IOVAS, - IOMMUFD_CMD_IOAS_COPY, - IOMMUFD_CMD_IOAS_IOVA_RANGES, - IOMMUFD_CMD_IOAS_MAP, - IOMMUFD_CMD_IOAS_UNMAP, - IOMMUFD_CMD_OPTION, - IOMMUFD_CMD_VFIO_IOAS, - IOMMUFD_CMD_HWPT_ALLOC, - IOMMUFD_CMD_GET_HW_INFO, - IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, - IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, - IOMMUFD_CMD_HWPT_INVALIDATE, - IOMMUFD_CMD_FAULT_QUEUE_ALLOC, + IOMMUFD_CMD_IOAS_ALLOC = 0x81, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS = 0x82, + IOMMUFD_CMD_IOAS_COPY = 0x83, + IOMMUFD_CMD_IOAS_IOVA_RANGES = 0x84, + IOMMUFD_CMD_IOAS_MAP = 0x85, + IOMMUFD_CMD_IOAS_UNMAP = 0x86, + IOMMUFD_CMD_OPTION = 0x87, + IOMMUFD_CMD_VFIO_IOAS = 0x88, + IOMMUFD_CMD_HWPT_ALLOC = 0x89, + IOMMUFD_CMD_GET_HW_INFO = 0x8a, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING = 0x8b, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c, + IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d, + IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e, }; /** @@ -400,8 +400,8 @@ struct iommu_hwpt_vtd_s1 { * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table */ enum iommu_hwpt_data_type { - IOMMU_HWPT_DATA_NONE, - IOMMU_HWPT_DATA_VTD_S1, + IOMMU_HWPT_DATA_NONE = 0, + IOMMU_HWPT_DATA_VTD_S1 = 1, }; /** @@ -491,8 +491,8 @@ struct iommu_hw_info_vtd { * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type */ enum iommu_hw_info_type { - IOMMU_HW_INFO_TYPE_NONE, - IOMMU_HW_INFO_TYPE_INTEL_VTD, + IOMMU_HW_INFO_TYPE_NONE = 0, + IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, }; /** @@ -629,7 +629,7 @@ struct iommu_hwpt_get_dirty_bitmap { * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 */ enum iommu_hwpt_invalidate_data_type { - IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1 = 0, }; /** @@ -768,7 +768,7 @@ struct iommu_hwpt_pgfault { */ enum iommufd_page_response_code { IOMMUFD_PAGE_RESP_SUCCESS = 0, - IOMMUFD_PAGE_RESP_INVALID, + IOMMUFD_PAGE_RESP_INVALID = 1, }; /** -- cgit v1.2.3 From 6e5c85c003e47fd49b72ca052b9181644e04a520 Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:18:58 +0000 Subject: net/sched: flower: refactor control flag definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Redefine the flower control flags as an enum, so they are included in BTF info. Make the kernel-side enum a more explicit superset of TCA_FLOWER_KEY_FLAGS_*, new flags still need to be added to both enums, but at least the bit position only has to be defined once. FLOW_DIS_ENCAPSULATION is never set for mask, so it can't be exposed to userspace in an unsupported flags mask error message, so it will be placed one bit position above the last uAPI flag. Suggested-by: Alexander Lobakin Suggested-by: Jakub Kicinski Signed-off-by: Asbjørn Sloth Tønnesen Reviewed-by: Davide Caratti Link: https://patch.msgid.link/20240713021911.1631517-2-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/net/flow_dissector.h | 14 +++++++++++--- include/uapi/linux/pkt_cls.h | 3 +++ 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 3e47e123934d..c3fce070b912 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -7,6 +7,7 @@ #include #include #include +#include struct bpf_prog; struct net; @@ -24,9 +25,16 @@ struct flow_dissector_key_control { u32 flags; }; -#define FLOW_DIS_IS_FRAGMENT BIT(0) -#define FLOW_DIS_FIRST_FRAG BIT(1) -#define FLOW_DIS_ENCAPSULATION BIT(2) +/* The control flags are kept in sync with TCA_FLOWER_KEY_FLAGS_*, as those + * flags are exposed to userspace in some error paths, ie. unsupported flags. + */ +enum flow_dissector_ctrl_flags { + FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, + FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + + /* These flags are internal to the kernel */ + FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), +}; enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index b6d38f5fd7c0..12db276f0c11 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -677,8 +677,11 @@ enum { enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), + __TCA_FLOWER_KEY_FLAGS_MAX, }; +#define TCA_FLOWER_KEY_FLAGS_MAX (__TCA_FLOWER_KEY_FLAGS_MAX - 1) + enum { TCA_FLOWER_KEY_CFM_OPT_UNSPEC, TCA_FLOWER_KEY_CFM_MD_LEVEL, -- cgit v1.2.3 From bfda5a63137bc83c344c4d995f404c8e701ff0fa Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:19:00 +0000 Subject: net/sched: flower: define new tunnel flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define new TCA_FLOWER_KEY_FLAGS_* flags for use in struct flow_dissector_key_control, covering the same flags as currently exposed through TCA_FLOWER_KEY_ENC_FLAGS. Put the new flags under FLOW_DIS_F_*. The idea is that we can later, move the existing flags under FLOW_DIS_F_* as well. The ynl flag names have been taken from the RFC iproute2 patch. Signed-off-by: Asbjørn Sloth Tønnesen Reviewed-by: Donald Hunter Link: https://patch.msgid.link/20240713021911.1631517-4-ast@fiberby.net Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/tc.yaml | 4 ++++ include/net/flow_dissector.h | 7 ++++++- include/uapi/linux/pkt_cls.h | 4 ++++ 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index fbbc928647fa..aa574e3827ab 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -47,6 +47,10 @@ definitions: entries: - frag - firstfrag + - tuncsum + - tundf + - tunoam + - tuncrit - name: tc-stats type: struct diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index c3fce070b912..460ea65b9e59 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -17,7 +17,8 @@ struct sk_buff; * struct flow_dissector_key_control: * @thoff: Transport header offset * @addr_type: Type of key. One of FLOW_DISSECTOR_KEY_* - * @flags: Key flags. Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAGENCAPSULATION) + * @flags: Key flags. + * Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAG|ENCAPSULATION|F_*) */ struct flow_dissector_key_control { u16 thoff; @@ -31,6 +32,10 @@ struct flow_dissector_key_control { enum flow_dissector_ctrl_flags { FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, + FLOW_DIS_F_TUNNEL_CSUM = TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT = TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_OAM = TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, + FLOW_DIS_F_TUNNEL_CRIT_OPT = TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, /* These flags are internal to the kernel */ FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 12db276f0c11..3dc4388e944c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -677,6 +677,10 @@ enum { enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM = (1 << 2), + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT = (1 << 3), + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM = (1 << 4), + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT = (1 << 5), __TCA_FLOWER_KEY_FLAGS_MAX, }; -- cgit v1.2.3 From 11036bd7a0b3b05c5e1f43d107ddb02abf83adb9 Mon Sep 17 00:00:00 2001 From: Asbjørn Sloth Tønnesen Date: Sat, 13 Jul 2024 02:19:06 +0000 Subject: net/sched: cls_flower: rework TCA_FLOWER_KEY_ENC_FLAGS usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch changes how TCA_FLOWER_KEY_ENC_FLAGS is used, so that it is used with TCA_FLOWER_KEY_FLAGS_* flags, in the same way as TCA_FLOWER_KEY_FLAGS is currently used. Where TCA_FLOWER_KEY_FLAGS uses {key,mask}->control.flags, then TCA_FLOWER_KEY_ENC_FLAGS now uses {key,mask}->enc_control.flags, therefore {key,mask}->enc_flags is now unused. As the generic fl_set_key_flags/fl_dump_key_flags() is used with encap set to true, then fl_{set,dump}_key_enc_flags() is removed. This breaks unreleased userspace API (net-next since 2024-06-04). Signed-off-by: Asbjørn Sloth Tønnesen Tested-by: Davide Caratti Reviewed-by: Davide Caratti Link: https://patch.msgid.link/20240713021911.1631517-10-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 4 ++-- net/sched/cls_flower.c | 56 ++++++++++---------------------------------- 2 files changed, 15 insertions(+), 45 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 3dc4388e944c..d36d9cdf0c00 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -554,8 +554,8 @@ enum { TCA_FLOWER_KEY_SPI, /* be32 */ TCA_FLOWER_KEY_SPI_MASK, /* be32 */ - TCA_FLOWER_KEY_ENC_FLAGS, /* u32 */ - TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* u32 */ + TCA_FLOWER_KEY_ENC_FLAGS, /* be32 */ + TCA_FLOWER_KEY_ENC_FLAGS_MASK, /* be32 */ __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2a440f11fe1f..e2239ab01355 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -45,11 +45,11 @@ (TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT | \ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST) -#define TUNNEL_FLAGS_PRESENT (\ - _BITUL(IP_TUNNEL_CSUM_BIT) | \ - _BITUL(IP_TUNNEL_DONT_FRAGMENT_BIT) | \ - _BITUL(IP_TUNNEL_OAM_BIT) | \ - _BITUL(IP_TUNNEL_CRIT_OPT_BIT)) +#define TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT) struct fl_flow_key { struct flow_dissector_key_meta meta; @@ -745,10 +745,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, - [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_U32, - TUNNEL_FLAGS_PRESENT), - [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_U32, - TUNNEL_FLAGS_PRESENT), + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), }; static const struct nla_policy @@ -1866,21 +1866,6 @@ static int fl_set_key_cfm(struct nlattr **tb, return 0; } -static int fl_set_key_enc_flags(struct nlattr **tb, u32 *flags_key, - u32 *flags_mask, struct netlink_ext_ack *extack) -{ - /* mask is mandatory for flags */ - if (NL_REQ_ATTR_CHECK(extack, NULL, tb, TCA_FLOWER_KEY_ENC_FLAGS_MASK)) { - NL_SET_ERR_MSG(extack, "missing enc_flags mask"); - return -EINVAL; - } - - *flags_key = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS]); - *flags_mask = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_FLAGS_MASK]); - - return 0; -} - static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -2123,8 +2108,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb, } if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) - ret = fl_set_key_enc_flags(tb, &key->enc_flags.flags, - &mask->enc_flags.flags, extack); + ret = fl_set_key_flags(tb, true, &key->enc_control.flags, + &mask->enc_control.flags, extack); return ret; } @@ -3381,22 +3366,6 @@ err_cfm_opts: return err; } -static int fl_dump_key_enc_flags(struct sk_buff *skb, - struct flow_dissector_key_enc_flags *key, - struct flow_dissector_key_enc_flags *mask) -{ - if (!memchr_inv(mask, 0, sizeof(*mask))) - return 0; - - if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS, key->flags)) - return -EMSGSIZE; - - if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_FLAGS_MASK, mask->flags)) - return -EMSGSIZE; - - return 0; -} - static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, struct flow_dissector_key_enc_opts *enc_opts) { @@ -3699,7 +3668,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; - if (fl_dump_key_enc_flags(skb, &key->enc_flags, &mask->enc_flags)) + if (fl_dump_key_flags(skb, true, key->enc_control.flags, + mask->enc_control.flags)) goto nla_put_failure; return 0; -- cgit v1.2.3 From 33c97e7c0338d921c2ae0c2e54bf17121007fb94 Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Thu, 11 Jul 2024 16:54:57 +0000 Subject: landlock: Clarify documentation for struct landlock_ruleset_attr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The explanation for @handled_access_fs and @handled_access_net has significant overlap and is better explained together. * Explain the commonalities in structure-level documentation. * Clarify some wording and break up longer sentences. * Put emphasis on the word "handled" to make it clearer that "handled" is a term with special meaning in the context of Landlock. I'd like to transfer this wording into the man pages as well. Signed-off-by: Günther Noack Cc: Alejandro Colomar Cc: Konstantin Meskhidze Cc: linux-security-module@vger.kernel.org Link: https://lore.kernel.org/r/20240711165456.2148590-2-gnoack@google.com [mic: Format commit message] Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 39 +++++++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 68625e728f43..e76186da3260 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -12,29 +12,36 @@ #include /** - * struct landlock_ruleset_attr - Ruleset definition + * struct landlock_ruleset_attr - Ruleset definition. * - * Argument of sys_landlock_create_ruleset(). This structure can grow in - * future versions. + * Argument of sys_landlock_create_ruleset(). + * + * This structure defines a set of *handled access rights*, a set of actions on + * different object types, which should be denied by default when the ruleset is + * enacted. Vice versa, access rights that are not specifically listed here are + * not going to be denied by this ruleset when it is enacted. + * + * For historical reasons, the %LANDLOCK_ACCESS_FS_REFER right is always denied + * by default, even when its bit is not set in @handled_access_fs. In order to + * add new rules with this access right, the bit must still be set explicitly + * (cf. `Filesystem flags`_). + * + * The explicit listing of *handled access rights* is required for backwards + * compatibility reasons. In most use cases, processes that use Landlock will + * *handle* a wide range or all access rights that they know about at build time + * (and that they have tested with a kernel that supported them all). + * + * This structure can grow in future Landlock versions. */ struct landlock_ruleset_attr { /** - * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) - * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them: it is a deny-by-default list that should - * contain as much Landlock access rights as possible. Indeed, all - * Landlock filesystem access rights that are not part of - * handled_access_fs are allowed. This is needed for backward - * compatibility reasons. One exception is the - * %LANDLOCK_ACCESS_FS_REFER access right, which is always implicitly - * handled, but must still be explicitly handled to add new rules with - * this access right. + * @handled_access_fs: Bitmask of handled filesystem actions + * (cf. `Filesystem flags`_). */ __u64 handled_access_fs; /** - * @handled_access_net: Bitmask of actions (cf. `Network flags`_) - * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them. + * @handled_access_net: Bitmask of handled network actions (cf. `Network + * flags`_). */ __u64 handled_access_net; }; -- cgit v1.2.3 From 88caf544c9305313e1c48ac1a437faa5df8fff06 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 1 Jul 2024 17:31:46 -0500 Subject: KVM: SEV: Provide support for SNP_GUEST_REQUEST NAE event Version 2 of GHCB specification added support for the SNP Guest Request Message NAE event. The event allows for an SEV-SNP guest to make requests to the SEV-SNP firmware through the hypervisor using the SNP_GUEST_REQUEST API defined in the SEV-SNP firmware specification. This is used by guests primarily to request attestation reports from firmware. There are other request types are available as well, but the specifics of what guest requests are being made generally does not affect how they are handled by the hypervisor, which only serves as a proxy for the guest requests and firmware responses. Implement handling for these events. When an SNP Guest Request is issued, the guest will provide its own request/response pages, which could in theory be passed along directly to firmware. However, these pages would need special care: - Both pages are from shared guest memory, so they need to be protected from migration/etc. occurring while firmware reads/writes to them. At a minimum, this requires elevating the ref counts and potentially needing an explicit pinning of the memory. This places additional restrictions on what type of memory backends userspace can use for shared guest memory since there would be some reliance on using refcounted pages. - The response page needs to be switched to Firmware-owned state before the firmware can write to it, which can lead to potential host RMP #PFs if the guest is misbehaved and hands the host a guest page that KVM is writing to for other reasons (e.g. virtio buffers). Both of these issues can be avoided completely by using separately-allocated bounce pages for both the request/response pages and passing those to firmware instead. So that's the approach taken here. Signed-off-by: Brijesh Singh Co-developed-by: Alexey Kardashevskiy Signed-off-by: Alexey Kardashevskiy Co-developed-by: Ashish Kalra Signed-off-by: Ashish Kalra Reviewed-by: Tom Lendacky Reviewed-by: Liam Merwick [mdr: ensure FW command failures are indicated to guest, drop extended request handling to be re-written as separate patch, massage commit] Signed-off-by: Michael Roth Message-ID: <20240701223148.3798365-2-michael.roth@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 134 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.h | 3 + include/uapi/linux/sev-guest.h | 3 + 3 files changed, 140 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 20b92f4b0906..fdf3ba7dda07 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -326,6 +327,78 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_decommission(handle); } +/* + * This sets up bounce buffers/firmware pages to handle SNP Guest Request + * messages (e.g. attestation requests). See "SNP Guest Request" in the GHCB + * 2.0 specification for more details. + * + * Technically, when an SNP Guest Request is issued, the guest will provide its + * own request/response pages, which could in theory be passed along directly + * to firmware rather than using bounce pages. However, these pages would need + * special care: + * + * - Both pages are from shared guest memory, so they need to be protected + * from migration/etc. occurring while firmware reads/writes to them. At a + * minimum, this requires elevating the ref counts and potentially needing + * an explicit pinning of the memory. This places additional restrictions + * on what type of memory backends userspace can use for shared guest + * memory since there is some reliance on using refcounted pages. + * + * - The response page needs to be switched to Firmware-owned[1] state + * before the firmware can write to it, which can lead to potential + * host RMP #PFs if the guest is misbehaved and hands the host a + * guest page that KVM might write to for other reasons (e.g. virtio + * buffers/etc.). + * + * Both of these issues can be avoided completely by using separately-allocated + * bounce pages for both the request/response pages and passing those to + * firmware instead. So that's what is being set up here. + * + * Guest requests rely on message sequence numbers to ensure requests are + * issued to firmware in the order the guest issues them, so concurrent guest + * requests generally shouldn't happen. But a misbehaved guest could issue + * concurrent guest requests in theory, so a mutex is used to serialize + * access to the bounce buffers. + * + * [1] See the "Page States" section of the SEV-SNP Firmware ABI for more + * details on Firmware-owned pages, along with "RMP and VMPL Access Checks" + * in the APM for details on the related RMP restrictions. + */ +static int snp_guest_req_init(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + struct page *req_page; + + req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!req_page) + return -ENOMEM; + + sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!sev->guest_resp_buf) { + __free_page(req_page); + return -EIO; + } + + sev->guest_req_buf = page_address(req_page); + mutex_init(&sev->guest_req_mutex); + + return 0; +} + +static void snp_guest_req_cleanup(struct kvm *kvm) +{ + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + + if (sev->guest_resp_buf) + snp_free_firmware_page(sev->guest_resp_buf); + + if (sev->guest_req_buf) + __free_page(virt_to_page(sev->guest_req_buf)); + + sev->guest_req_buf = NULL; + sev->guest_resp_buf = NULL; +} + static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, struct kvm_sev_init *data, unsigned long vm_type) @@ -376,6 +449,10 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, if (ret) goto e_free; + /* This needs to happen after SEV/SNP firmware initialization. */ + if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm)) + goto e_free; + INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); sev->need_init = false; @@ -2834,6 +2911,8 @@ void sev_vm_destroy(struct kvm *kvm) } if (sev_snp_guest(kvm)) { + snp_guest_req_cleanup(kvm); + /* * Decomission handles unbinding of the ASID. If it fails for * some unexpected reason, just leak the ASID. @@ -3299,6 +3378,13 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; + case SVM_VMGEXIT_GUEST_REQUEST: + if (!sev_snp_guest(vcpu->kvm) || + !PAGE_ALIGNED(control->exit_info_1) || + !PAGE_ALIGNED(control->exit_info_2) || + control->exit_info_1 == control->exit_info_2) + goto vmgexit_err; + break; default: reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; @@ -3917,6 +4003,51 @@ out: return ret; } +static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa) +{ + struct sev_data_snp_guest_request data = {0}; + struct kvm *kvm = svm->vcpu.kvm; + struct kvm_sev_info *sev = to_kvm_sev_info(kvm); + sev_ret_code fw_err = 0; + int ret; + + if (!sev_snp_guest(kvm)) + return -EINVAL; + + mutex_lock(&sev->guest_req_mutex); + + if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + data.gctx_paddr = __psp_pa(sev->snp_context); + data.req_paddr = __psp_pa(sev->guest_req_buf); + data.res_paddr = __psp_pa(sev->guest_resp_buf); + + /* + * Firmware failures are propagated on to guest, but any other failure + * condition along the way should be reported to userspace. E.g. if + * the PSP is dead and commands are timing out. + */ + ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err); + if (ret && !fw_err) + goto out_unlock; + + if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) { + ret = -EIO; + goto out_unlock; + } + + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err)); + + ret = 1; /* resume guest */ + +out_unlock: + mutex_unlock(&sev->guest_req_mutex); + return ret; +} + static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -4191,6 +4322,9 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = 1; break; + case SVM_VMGEXIT_GUEST_REQUEST: + ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2); + break; case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f0ab0d93cd20..8528f40efffc 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -94,6 +94,9 @@ struct kvm_sev_info { struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; void *snp_context; /* SNP guest context page */ + void *guest_req_buf; /* Bounce buffer for SNP Guest Request input */ + void *guest_resp_buf; /* Bounce buffer for SNP Guest Request output */ + struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */ }; struct kvm_svm { diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 154a87a1eca9..fcdfea767fca 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -89,6 +89,9 @@ struct snp_ext_report_req { #define SNP_GUEST_FW_ERR_MASK GENMASK_ULL(31, 0) #define SNP_GUEST_VMM_ERR_SHIFT 32 #define SNP_GUEST_VMM_ERR(x) (((u64)x) << SNP_GUEST_VMM_ERR_SHIFT) +#define SNP_GUEST_FW_ERR(x) ((x) & SNP_GUEST_FW_ERR_MASK) +#define SNP_GUEST_ERR(vmm_err, fw_err) (SNP_GUEST_VMM_ERR(vmm_err) | \ + SNP_GUEST_FW_ERR(fw_err)) #define SNP_GUEST_VMM_ERR_INVALID_LEN 1 #define SNP_GUEST_VMM_ERR_BUSY 2 -- cgit v1.2.3 From 332d2c1d713e232e163386c35a3ba0c1b90df83f Mon Sep 17 00:00:00 2001 From: Michael Roth Date: Wed, 1 May 2024 03:52:10 -0500 Subject: crypto: ccp: Add the SNP_VLEK_LOAD command When requesting an attestation report a guest is able to specify whether it wants SNP firmware to sign the report using either a Versioned Chip Endorsement Key (VCEK), which is derived from chip-unique secrets, or a Versioned Loaded Endorsement Key (VLEK) which is obtained from an AMD Key Derivation Service (KDS) and derived from seeds allocated to enrolled cloud service providers (CSPs). For VLEK keys, an SNP_VLEK_LOAD SNP firmware command is used to load them into the system after obtaining them from the KDS. Add a corresponding userspace interface so to allow the loading of VLEK keys into the system. See SEV-SNP Firmware ABI 1.54, SNP_VLEK_LOAD for more details. Reviewed-by: Tom Lendacky Signed-off-by: Michael Roth Message-ID: <20240501085210.2213060-21-michael.roth@amd.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/coco/sev-guest.rst | 19 ++++++++++++++++++ drivers/crypto/ccp/sev-dev.c | 36 +++++++++++++++++++++++++++++++++++ include/uapi/linux/psp-sev.h | 27 ++++++++++++++++++++++++++ 3 files changed, 82 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index e1eaf6a830ce..de68d3a4b540 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -176,6 +176,25 @@ to SNP_CONFIG command defined in the SEV-SNP spec. The current values of the firmware parameters affected by this command can be queried via SNP_PLATFORM_STATUS. +2.7 SNP_VLEK_LOAD +----------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_vlek_load +:Returns (out): 0 on success, -negative on error + +When requesting an attestation report a guest is able to specify whether +it wants SNP firmware to sign the report using either a Versioned Chip +Endorsement Key (VCEK), which is derived from chip-unique secrets, or a +Versioned Loaded Endorsement Key (VLEK) which is obtained from an AMD +Key Derivation Service (KDS) and derived from seeds allocated to +enrolled cloud service providers. + +In the case of VLEK keys, the SNP_VLEK_LOAD SNP command is used to load +them into the system after obtaining them from the KDS, and corresponds +closely to the SNP_VLEK_LOAD firmware command specified in the SEV-SNP +spec. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 2102377f727b..97a7959406ee 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -2027,6 +2027,39 @@ static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); } +static int sev_ioctl_do_snp_vlek_load(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_vlek_load input; + void *blob; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&input, u64_to_user_ptr(argp->data), sizeof(input))) + return -EFAULT; + + if (input.len != sizeof(input) || input.vlek_wrapped_version != 0) + return -EINVAL; + + blob = psp_copy_user_blob(input.vlek_wrapped_address, + sizeof(struct sev_user_data_snp_wrapped_vlek_hashstick)); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + input.vlek_wrapped_address = __psp_pa(blob); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_VLEK_LOAD, &input, &argp->error); + + kfree(blob); + + return ret; +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -2087,6 +2120,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SNP_SET_CONFIG: ret = sev_ioctl_do_snp_set_config(&input, writable); break; + case SNP_VLEK_LOAD: + ret = sev_ioctl_do_snp_vlek_load(&input, writable); + break; default: ret = -EINVAL; goto out; diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index b7a2c2ee35b7..2289b7c76c59 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -31,6 +31,7 @@ enum { SNP_PLATFORM_STATUS, SNP_COMMIT, SNP_SET_CONFIG, + SNP_VLEK_LOAD, SEV_MAX, }; @@ -214,6 +215,32 @@ struct sev_user_data_snp_config { __u8 rsvd1[52]; } __packed; +/** + * struct sev_data_snp_vlek_load - SNP_VLEK_LOAD structure + * + * @len: length of the command buffer read by the PSP + * @vlek_wrapped_version: version of wrapped VLEK hashstick (Must be 0h) + * @rsvd: reserved + * @vlek_wrapped_address: address of a wrapped VLEK hashstick + * (struct sev_user_data_snp_wrapped_vlek_hashstick) + */ +struct sev_user_data_snp_vlek_load { + __u32 len; /* In */ + __u8 vlek_wrapped_version; /* In */ + __u8 rsvd[3]; /* In */ + __u64 vlek_wrapped_address; /* In */ +} __packed; + +/** + * struct sev_user_data_snp_vlek_wrapped_vlek_hashstick - Wrapped VLEK data + * + * @data: Opaque data provided by AMD KDS (as described in SEV-SNP Firmware ABI + * 1.54, SNP_VLEK_LOAD) + */ +struct sev_user_data_snp_wrapped_vlek_hashstick { + __u8 data[432]; /* In */ +} __packed; + /** * struct sev_issue_cmd - SEV ioctl parameters * -- cgit v1.2.3 From f4b89d8ce5a835afa51404977ee7e3889c2b9722 Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Mon, 15 Jul 2024 16:03:29 +0000 Subject: landlock: Various documentation improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Fix some typos, incomplete or confusing phrases. * Split paragraphs where appropriate. * List the same error code multiple times, if it has multiple possible causes. * Bring wording closer to the man page wording, which has undergone more thorough review (esp. for LANDLOCK_ACCESS_FS_WRITE_FILE). * Small semantic clarifications * Call the ephemeral port range "ephemeral" * Clarify reasons for EFAULT in landlock_add_rule() * Clarify @rule_type doc for landlock_add_rule() This is a collection of small fixes which I collected when preparing the corresponding man pages [1]. Cc: Alejandro Colomar Cc: Konstantin Meskhidze Link: https://lore.kernel.org/r/20240715155554.2791018-1-gnoack@google.com [1] Signed-off-by: Günther Noack Link: https://lore.kernel.org/r/20240715160328.2792835-2-gnoack@google.com [mic: Add label to link, fix formatting spotted by make htmldocs, synchronize userspace-api documentation's date] Signed-off-by: Mickaël Salaün --- Documentation/userspace-api/landlock.rst | 2 +- include/uapi/linux/landlock.h | 27 ++++++++++++++------------- security/landlock/syscalls.c | 17 +++++++++-------- 3 files changed, 24 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst index 07b63aec56fa..37dafce8038b 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: April 2024 +:Date: July 2024 The goal of Landlock is to enable to restrict ambient rights (e.g. global filesystem or network access) for a set of processes. Because Landlock diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index e76186da3260..2c8dbc74b955 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -104,20 +104,21 @@ struct landlock_path_beneath_attr { */ struct landlock_net_port_attr { /** - * @allowed_access: Bitmask of allowed access network for a port + * @allowed_access: Bitmask of allowed network actions for a port * (cf. `Network flags`_). */ __u64 allowed_access; /** * @port: Network port in host endianness. * - * It should be noted that port 0 passed to :manpage:`bind(2)` will - * bind to an available port from a specific port range. This can be - * configured thanks to the ``/proc/sys/net/ipv4/ip_local_port_range`` - * sysctl (also used for IPv6). A Landlock rule with port 0 and the - * ``LANDLOCK_ACCESS_NET_BIND_TCP`` right means that requesting to bind - * on port 0 is allowed and it will automatically translate to binding - * on the related port range. + * It should be noted that port 0 passed to :manpage:`bind(2)` will bind + * to an available port from the ephemeral port range. This can be + * configured with the ``/proc/sys/net/ipv4/ip_local_port_range`` sysctl + * (also used for IPv6). + * + * A Landlock rule with port 0 and the ``LANDLOCK_ACCESS_NET_BIND_TCP`` + * right means that requesting to bind on port 0 is allowed and it will + * automatically translate to binding on the related port range. */ __u64 port; }; @@ -138,10 +139,10 @@ struct landlock_net_port_attr { * The following access rights apply only to files: * * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file. - * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. Note that - * you might additionally need the %LANDLOCK_ACCESS_FS_TRUNCATE right in order - * to overwrite files with :manpage:`open(2)` using ``O_TRUNC`` or - * :manpage:`creat(2)`. + * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. When + * opening files for writing, you will often additionally need the + * %LANDLOCK_ACCESS_FS_TRUNCATE right. In many cases, these system calls + * truncate existing files when overwriting them (e.g., :manpage:`creat(2)`). * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access. * - %LANDLOCK_ACCESS_FS_TRUNCATE: Truncate a file with :manpage:`truncate(2)`, * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with @@ -263,7 +264,7 @@ struct landlock_net_port_attr { * These flags enable to restrict a sandboxed process to a set of network * actions. This is supported since the Landlock ABI version 4. * - * TCP sockets with allowed actions: + * The following access rights apply to TCP port numbers: * * - %LANDLOCK_ACCESS_NET_BIND_TCP: Bind a TCP socket to a local port. * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect an active TCP socket to diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 03b470f5a85a..ccc8bc6c1584 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -378,8 +378,7 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * with the new rule. * @rule_type: Identify the structure type pointed to by @rule_attr: * %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT. - * @rule_attr: Pointer to a rule (only of type &struct - * landlock_path_beneath_attr for now). + * @rule_attr: Pointer to a rule (matching the @rule_type). * @flags: Must be 0. * * This system call enables to define a new rule and add it to an existing @@ -390,18 +389,20 @@ static int add_rule_net_port(struct landlock_ruleset *ruleset, * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not * supported by the running kernel; - * - %EINVAL: @flags is not 0, or inconsistent access in the rule (i.e. + * - %EINVAL: @flags is not 0; + * - %EINVAL: The rule accesses are inconsistent (i.e. * &landlock_path_beneath_attr.allowed_access or - * &landlock_net_port_attr.allowed_access is not a subset of the - * ruleset handled accesses), or &landlock_net_port_attr.port is - * greater than 65535; - * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access); + * &landlock_net_port_attr.allowed_access is not a subset of the ruleset + * handled accesses) + * - %EINVAL: &landlock_net_port_attr.port is greater than 65535; + * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access is + * 0); * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; * - %EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of * @rule_attr is not the expected file descriptor type; * - %EPERM: @ruleset_fd has no write access to the underlying ruleset; - * - %EFAULT: @rule_attr inconsistency. + * - %EFAULT: @rule_attr was not a valid address. */ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, const enum landlock_rule_type, rule_type, -- cgit v1.2.3 From 9651fcedf7b92d3f7f1ab179e8ab55b85ee10fc1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 8 Dec 2022 17:55:04 +0100 Subject: mm: add MAP_DROPPABLE for designating always lazily freeable mappings The vDSO getrandom() implementation works with a buffer allocated with a new system call that has certain requirements: - It shouldn't be written to core dumps. * Easy: VM_DONTDUMP. - It should be zeroed on fork. * Easy: VM_WIPEONFORK. - It shouldn't be written to swap. * Uh-oh: mlock is rlimited. * Uh-oh: mlock isn't inherited by forks. - It shouldn't reserve actual memory, but it also shouldn't crash when page faulting in memory if none is available * Uh-oh: VM_NORESERVE means segfaults. It turns out that the vDSO getrandom() function has three really nice characteristics that we can exploit to solve this problem: 1) Due to being wiped during fork(), the vDSO code is already robust to having the contents of the pages it reads zeroed out midway through the function's execution. 2) In the absolute worst case of whatever contingency we're coding for, we have the option to fallback to the getrandom() syscall, and everything is fine. 3) The buffers the function uses are only ever useful for a maximum of 60 seconds -- a sort of cache, rather than a long term allocation. These characteristics mean that we can introduce VM_DROPPABLE, which has the following semantics: a) It never is written out to swap. b) Under memory pressure, mm can just drop the pages (so that they're zero when read back again). c) It is inherited by fork. d) It doesn't count against the mlock budget, since nothing is locked. e) If there's not enough memory to service a page fault, it's not fatal, and no signal is sent. This way, allocations used by vDSO getrandom() can use: VM_DROPPABLE | VM_DONTDUMP | VM_WIPEONFORK | VM_NORESERVE And there will be no problem with OOMing, crashing on overcommitment, using memory when not in use, not wiping on fork(), coredumps, or writing out to swap. In order to let vDSO getrandom() use this, expose these via mmap(2) as MAP_DROPPABLE. Note that this involves removing the MADV_FREE special case from sort_folio(), which according to Yu Zhao is unnecessary and will simply result in an extra call to shrink_folio_list() in the worst case. The chunk removed reenables the swapbacked flag, which we don't want for VM_DROPPABLE, and we can't conditionalize it here because there isn't a vma reference available. Finally, the provided self test ensures that this is working as desired. Cc: linux-mm@kvack.org Acked-by: David Hildenbrand Signed-off-by: Jason A. Donenfeld --- fs/proc/task_mmu.c | 1 + include/linux/mm.h | 7 +++++ include/linux/userfaultfd_k.h | 3 ++ include/trace/events/mmflags.h | 7 +++++ include/uapi/linux/mman.h | 1 + mm/ksm.c | 2 +- mm/madvise.c | 5 +++- mm/memory.c | 13 +++++++++ mm/mempolicy.c | 3 ++ mm/mlock.c | 2 +- mm/mmap.c | 30 +++++++++++++++++++ mm/rmap.c | 22 ++++++++++++-- mm/vmscan.c | 9 ------ tools/include/uapi/linux/mman.h | 1 + tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/droppable.c | 53 ++++++++++++++++++++++++++++++++++ 17 files changed, 146 insertions(+), 15 deletions(-) create mode 100644 tools/testing/selftests/mm/droppable.c (limited to 'include/uapi/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 71e5039d940d..46f0b0fe9ee3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -708,6 +708,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_SHADOW_STACK)] = "ss", #endif #ifdef CONFIG_64BIT + [ilog2(VM_DROPPABLE)] = "dp", [ilog2(VM_SEALED)] = "sl", #endif }; diff --git a/include/linux/mm.h b/include/linux/mm.h index eb7c96d24ac0..e078c2890bf8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -406,6 +406,13 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +#define VM_DROPPABLE_BIT 40 +#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#else +#define VM_DROPPABLE VM_NONE +#endif + #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 05d59f74fc88..a12bcf042551 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; + if (vm_flags & VM_DROPPABLE) + return false; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index e46d6e82765e..b63d211bd141 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3) # define IF_HAVE_UFFD_MINOR(flag, name) #endif +#ifdef CONFIG_64BIT +# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name}, +#else +# define IF_HAVE_VM_DROPPABLE(flag, name) +#endif + #define __def_vmaflag_names \ {VM_READ, "read" }, \ {VM_WRITE, "write" }, \ @@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \ {VM_MIXEDMAP, "mixedmap" }, \ {VM_HUGEPAGE, "hugepage" }, \ {VM_NOHUGEPAGE, "nohugepage" }, \ +IF_HAVE_VM_DROPPABLE(VM_DROPPABLE, "droppable" ) \ {VM_MERGEABLE, "mergeable" } \ #define show_vma_flags(flags) \ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/mm/ksm.c b/mm/ksm.c index 34c4820e0d3d..8778eb7c40f8 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -717,7 +717,7 @@ static bool vma_ksm_compatible(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_HUGETLB | - VM_MIXEDMAP)) + VM_MIXEDMAP| VM_DROPPABLE)) return false; /* just ignore the advice */ if (vma_is_dax(vma)) diff --git a/mm/madvise.c b/mm/madvise.c index a77893462b92..cba5bc652fc4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1068,13 +1068,16 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: + if (vma->vm_flags & VM_DROPPABLE) + return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: - if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) + if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) || + (vma->vm_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; diff --git a/mm/memory.c b/mm/memory.c index d10e616d7389..98d9a4485d24 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5660,6 +5660,7 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, /* If the fault handler drops the mmap_lock, vma may be freed */ struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; + bool is_droppable; __set_current_state(TASK_RUNNING); @@ -5674,6 +5675,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, goto out; } + is_droppable = !!(vma->vm_flags & VM_DROPPABLE); + /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. @@ -5688,8 +5691,18 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, else ret = __handle_mm_fault(vma, address, flags); + /* + * Warning: It is no longer safe to dereference vma-> after this point, + * because mmap_lock might have been dropped by __handle_mm_fault(), so + * vma might be destroyed from underneath us. + */ + lru_gen_exit_fault(); + /* If the mapping is droppable, then errors due to OOM aren't fatal. */ + if (is_droppable) + ret &= ~VM_FAULT_OOM; + if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* diff --git a/mm/mempolicy.c b/mm/mempolicy.c index aec756ae5637..32291ab25960 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2300,6 +2300,9 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct pgoff_t ilx; struct page *page; + if (vma->vm_flags & VM_DROPPABLE) + gfp |= __GFP_NOWARN; + pol = get_vma_policy(vma, addr, order, &ilx); page = alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, numa_node_id()); diff --git a/mm/mlock.c b/mm/mlock.c index 30b51cdea89d..b87b3d8cc9cc 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -485,7 +485,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || - vma_is_dax(vma) || vma_is_secretmem(vma)) + vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; diff --git a/mm/mmap.c b/mm/mmap.c index 83b4682ec85c..8aeedeb784c2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1369,6 +1369,36 @@ unsigned long do_mmap(struct file *file, unsigned long addr, pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; + case MAP_DROPPABLE: + if (VM_DROPPABLE == VM_NONE) + return -ENOTSUPP; + /* + * A locked or stack area makes no sense to be droppable. + * + * Also, since droppable pages can just go away at any time + * it makes no sense to copy them on fork or dump them. + * + * And don't attempt to combine with hugetlb for now. + */ + if (flags & (MAP_LOCKED | MAP_HUGETLB)) + return -EINVAL; + if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP)) + return -EINVAL; + + vm_flags |= VM_DROPPABLE; + + /* + * If the pages can be dropped, then it doesn't make + * sense to reserve them. + */ + vm_flags |= VM_NORESERVE; + + /* + * Likewise, they're volatile enough that they + * shouldn't survive forks or coredumps. + */ + vm_flags |= VM_WIPEONFORK | VM_DONTDUMP; + fallthrough; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. diff --git a/mm/rmap.c b/mm/rmap.c index e8fc5ecb59b2..1f9b5a9cb121 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1397,7 +1397,12 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); - __folio_set_swapbacked(folio); + /* + * VM_DROPPABLE mappings don't swap; instead they're just dropped when + * under memory pressure. + */ + if (!(vma->vm_flags & VM_DROPPABLE)) + __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, true); if (likely(!folio_test_large(folio))) { @@ -1841,7 +1846,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && - !folio_test_dirty(folio)) { + (!folio_test_dirty(folio) || + /* + * Unlike MADV_FREE mappings, VM_DROPPABLE + * ones can be dropped even if they've + * been dirtied. + */ + (vma->vm_flags & VM_DROPPABLE))) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } @@ -1851,7 +1862,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); - folio_set_swapbacked(folio); + /* + * Unlike MADV_FREE mappings, VM_DROPPABLE ones + * never get swap backed on failure to drop. + */ + if (!(vma->vm_flags & VM_DROPPABLE)) + folio_set_swapbacked(folio); ret = false; page_vma_mapped_walk_done(&pvmw); break; diff --git a/mm/vmscan.c b/mm/vmscan.c index 2e34de9cd0d4..5ef0ee4610d6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4265,15 +4265,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c return true; } - /* dirty lazyfree */ - if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) { - success = lru_gen_del_folio(lruvec, folio, true); - VM_WARN_ON_ONCE_FOLIO(!success, folio); - folio_set_swapbacked(folio); - lruvec_add_folio_tail(lruvec, folio); - return true; - } - /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index a246e11988d5..e89d00528f2f 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 0b9ab987601c..a8beeb43c2b5 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -49,3 +49,4 @@ hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test seal_elf +droppable diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 3b49bc3d0a3b..e3e5740e13e1 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -73,6 +73,7 @@ TEST_GEN_FILES += ksm_functional_tests TEST_GEN_FILES += mdwe_test TEST_GEN_FILES += hugetlb_fault_after_madv TEST_GEN_FILES += hugetlb_madv_vs_map +TEST_GEN_FILES += droppable ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c new file mode 100644 index 000000000000..f3d9ecf96890 --- /dev/null +++ b/tools/testing/selftests/mm/droppable.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +int main(int argc, char *argv[]) +{ + size_t alloc_size = 134217728; + size_t page_size = getpagesize(); + void *alloc; + pid_t child; + + ksft_print_header(); + ksft_set_plan(1); + + alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0); + assert(alloc != MAP_FAILED); + memset(alloc, 'A', alloc_size); + for (size_t i = 0; i < alloc_size; i += page_size) + assert(*(uint8_t *)(alloc + i)); + + child = fork(); + assert(child >= 0); + if (!child) { + for (;;) + *(char *)malloc(page_size) = 'B'; + } + + for (bool done = false; !done;) { + for (size_t i = 0; i < alloc_size; i += page_size) { + if (!*(uint8_t *)(alloc + i)) { + done = true; + break; + } + } + } + kill(child, SIGTERM); + + ksft_test_result_pass("MAP_DROPPABLE: PASS\n"); + exit(KSFT_PASS); +} -- cgit v1.2.3 From 4ad10a5f5f78a5b3e525a63bd075a4eb1139dde1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 18 Nov 2022 17:23:34 +0100 Subject: random: introduce generic vDSO getrandom() implementation Provide a generic C vDSO getrandom() implementation, which operates on an opaque state returned by vgetrandom_alloc() and produces random bytes the same way as getrandom(). This has the following API signature: ssize_t vgetrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); The return value and the first three arguments are the same as ordinary getrandom(), while the last two arguments are a pointer to the opaque allocated state and its size. Were all five arguments passed to the getrandom() syscall, nothing different would happen, and the functions would have the exact same behavior. The actual vDSO RNG algorithm implemented is the same one implemented by drivers/char/random.c, using the same fast-erasure techniques as that. Should the in-kernel implementation change, so too will the vDSO one. It requires an implementation of ChaCha20 that does not use any stack, in order to maintain forward secrecy if a multi-threaded program forks (though this does not account for a similar issue with SA_SIGINFO copying registers to the stack), so this is left as an architecture-specific fill-in. Stack-less ChaCha20 is an easy algorithm to implement on a variety of architectures, so this shouldn't be too onerous. Initially, the state is keyless, and so the first call makes a getrandom() syscall to generate that key, and then uses it for subsequent calls. By keeping track of a generation counter, it knows when its key is invalidated and it should fetch a new one using the syscall. Later, more than just a generation counter might be used. Since MADV_WIPEONFORK is set on the opaque state, the key and related state is wiped during a fork(), so secrets don't roll over into new processes, and the same state doesn't accidentally generate the same random stream. The generation counter, as well, is always >0, so that the 0 counter is a useful indication of a fork() or otherwise uninitialized state. If the kernel RNG is not yet initialized, then the vDSO always calls the syscall, because that behavior cannot be emulated in userspace, but fortunately that state is short lived and only during early boot. If it has been initialized, then there is no need to inspect the `flags` argument, because the behavior does not change post-initialization regardless of the `flags` value. Since the opaque state passed to it is mutated, vDSO getrandom() is not reentrant, when used with the same opaque state, which libc should be mindful of. The function works over an opaque per-thread state of a particular size, which must be marked VM_WIPEONFORK, VM_DONTDUMP, VM_NORESERVE, and VM_DROPPABLE for proper operation. Over time, the nuances of these allocations may change or grow or even differ based on architectural features. The opaque state passed to vDSO getrandom() must be allocated using the mmap_flags and mmap_prot parameters provided by the vgetrandom_opaque_params struct, which also contains the size of each state. That struct can be obtained with a call to vgetrandom(NULL, 0, 0, ¶ms, ~0UL). Then, libc can call mmap(2) and slice up the returned array into a state per each thread, while ensuring that no single state straddles a page boundary. Libc is expected to allocate a chunk of these on first use, and then dole them out to threads as they're created, allocating more when needed. vDSO getrandom() provides the ability for userspace to generate random bytes quickly and safely, and is intended to be integrated into libc's thread management. As an illustrative example, the introduced code in the vdso_test_getrandom self test later in this series might be used to do the same outside of libc. In a libc the various pthread-isms are expected to be elided into libc internals. Reviewed-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld --- MAINTAINERS | 2 + drivers/char/random.c | 18 +++- include/uapi/linux/random.h | 15 +++ include/vdso/datapage.h | 11 ++ include/vdso/getrandom.h | 46 ++++++++ lib/vdso/Kconfig | 5 + lib/vdso/getrandom.c | 251 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 347 insertions(+), 1 deletion(-) create mode 100644 include/vdso/getrandom.h create mode 100644 lib/vdso/getrandom.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 2a4d4b3a9b40..7edb30b4abf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18745,6 +18745,8 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git F: Documentation/devicetree/bindings/rng/microsoft,vmgenid.yaml F: drivers/char/random.c F: drivers/virt/vmgenid.c +F: include/vdso/getrandom.h +F: lib/vdso/getrandom.c RAPIDIO SUBSYSTEM M: Matt Porter diff --git a/drivers/char/random.c b/drivers/char/random.c index 2597cb43f438..b02a12436750 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* - * Copyright (C) 2017-2022 Jason A. Donenfeld . All Rights Reserved. + * Copyright (C) 2017-2024 Jason A. Donenfeld . All Rights Reserved. * Copyright Matt Mackall , 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * @@ -56,6 +56,10 @@ #include #include #include +#ifdef CONFIG_VDSO_GETRANDOM +#include +#include +#endif #include #include #include @@ -271,6 +275,15 @@ static void crng_reseed(struct work_struct *work) if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); +#ifdef CONFIG_VDSO_GETRANDOM + /* base_crng.generation's invalid value is ULONG_MAX, while + * _vdso_rng_data.generation's invalid value is 0, so add one to the + * former to arrive at the latter. Use smp_store_release so that this + * is ordered with the write above to base_crng.generation. Pairs with + * the smp_rmb() before the syscall in the vDSO code. + */ + smp_store_release(&_vdso_rng_data.generation, next_gen + 1); +#endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); @@ -721,6 +734,9 @@ static void __cold _credit_init_bits(size_t bits) if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); +#ifdef CONFIG_VDSO_GETRANDOM + WRITE_ONCE(_vdso_rng_data.is_ready, true); +#endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index e744c23582eb..2a3fe4c2cdc9 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -55,4 +55,19 @@ struct rand_pool_info { #define GRND_RANDOM 0x0002 #define GRND_INSECURE 0x0004 +/** + * struct vgetrandom_opaque_params - arguments for allocating memory for vgetrandom + * + * @size_per_opaque_state: Size of each state that is to be passed to vgetrandom(). + * @mmap_prot: Value of the prot argument in mmap(2). + * @mmap_flags: Value of the flags argument in mmap(2). + * @reserved: Reserved for future use. + */ +struct vgetrandom_opaque_params { + __u32 size_of_opaque_state; + __u32 mmap_prot; + __u32 mmap_flags; + __u32 reserved[13]; +}; + #endif /* _UAPI_LINUX_RANDOM_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index d04d394db064..05e5787beb73 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -113,6 +113,16 @@ struct vdso_data { struct arch_vdso_data arch_data; }; +/** + * struct vdso_rng_data - vdso RNG state information + * @generation: counter representing the number of RNG reseeds + * @is_ready: boolean signaling whether the RNG is initialized + */ +struct vdso_rng_data { + u64 generation; + u8 is_ready; +}; + /* * We use the hidden visibility to prevent the compiler from generating a GOT * relocation. Not only is going through a GOT useless (the entry couldn't and @@ -124,6 +134,7 @@ struct vdso_data { */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); +extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden"))); /** * union vdso_data_store - Generic vDSO data page diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h new file mode 100644 index 000000000000..a8b7c14b0ae0 --- /dev/null +++ b/include/vdso/getrandom.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#ifndef _VDSO_GETRANDOM_H +#define _VDSO_GETRANDOM_H + +#include + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 + +/** + * struct vgetrandom_state - State used by vDSO getrandom(). + * + * @batch: One and a half ChaCha20 blocks of buffered RNG output. + * + * @key: Key to be used for generating next batch. + * + * @batch_key: Union of the prior two members, which is exactly two full + * ChaCha20 blocks in size, so that @batch and @key can be filled + * together. + * + * @generation: Snapshot of @rng_info->generation in the vDSO data page at + * the time @key was generated. + * + * @pos: Offset into @batch of the next available random byte. + * + * @in_use: Reentrancy guard for reusing a state within the same thread + * due to signal handlers. + */ +struct vgetrandom_state { + union { + struct { + u8 batch[CHACHA_BLOCK_SIZE * 3 / 2]; + u32 key[CHACHA_KEY_SIZE / sizeof(u32)]; + }; + u8 batch_key[CHACHA_BLOCK_SIZE * 2]; + }; + u64 generation; + u8 pos; + bool in_use; +}; + +#endif /* _VDSO_GETRANDOM_H */ diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index c46c2300517c..82fe827af542 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT in the hotpath. endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..b230f0b10832 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >= sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } \ +} while (0) + +static void memcpy_and_zero_src(void *dst, void *src, size_t len) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + if (IS_ENABLED(CONFIG_64BIT)) + MEMCPY_AND_ZERO_SRC(u64, dst, src, len); + MEMCPY_AND_ZERO_SRC(u32, dst, src, len); + MEMCPY_AND_ZERO_SRC(u16, dst, src, len); + } + MEMCPY_AND_ZERO_SRC(u8, dst, src, len); +} + +/** + * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall. + * @rng_info: Describes state of kernel RNG, memory shared with kernel. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * @opaque_state: Pointer to an opaque state area. + * @opaque_len: Length of opaque state area. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same + * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always + * calls into the syscall. + * + * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated + * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0, + * this function should not be used. + * + * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields + * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external + * locking is used, one state must be allocated per thread, as it is not safe to call this function + * concurrently with the same @opaque_state. However, it is safe to call this using the same + * @opaque_state that is shared between main code and signal handling code, within the same thread. + * + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t +__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len, + unsigned int flags, void *opaque_state, size_t opaque_len) +{ + ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len); + struct vgetrandom_state *state = opaque_state; + size_t batch_len, nblocks, orig_len = len; + bool in_use, have_retried = false; + unsigned long current_generation; + void *orig_buffer = buffer; + u32 counter[2] = { 0 }; + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) { + *(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) { + .size_of_opaque_state = sizeof(*state), + .mmap_prot = PROT_READ | PROT_WRITE, + .mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS + }; + return 0; + } + + /* The state must not straddle a page, since pages can be zeroed at any time. */ + if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE)) + return -EFAULT; + + /* If the caller passes the wrong size, which might happen due to CRIU, fallback. */ + if (unlikely(opaque_len != sizeof(*state))) + goto fallback_syscall; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from + * userspace, because A) the various @flags require this to block, or not, depending on + * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is + * ready is to reseed from the entropy pool at every invocation. + */ + if (unlikely(!READ_ONCE(rng_info->is_ready))) + goto fallback_syscall; + + /* + * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is + * initialized, the @flags parameter may require this to block or return an error, even when + * len is zero. + */ + if (unlikely(!len)) + return 0; + + /* + * @state->in_use is basic reentrancy protection against this running in a signal handler + * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one + * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before + * writing @state->in_use, there is still no race, because the signal handler will run to + * its completion before returning execution. + */ + in_use = READ_ONCE(state->in_use); + if (unlikely(in_use)) + /* The syscall simply fills the buffer and does not touch @state, so fallback. */ + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @state->key with the + * kernel's RNG reseeding schedule. + */ + current_generation = READ_ONCE(rng_info->generation); + + /* + * If @state->generation doesn't match the kernel RNG's generation, then it means the + * kernel's RNG has reseeded, and so @state->key is reseeded as well. + */ + if (unlikely(state->generation != current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If there is a fork + * just after this line, the parent and child will get different random bytes from + * the syscall, which is good. However, were this line to occur after the getrandom + * syscall, then both child and parent could have the same bytes and the same + * generation counter, so the fork would not be detected. Therefore, write + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* + * Prevent the syscall from being reordered wrt current_generation. Pairs with the + * smp_store_release(&_vdso_rng_data.generation) in random.c. + */ + smp_rmb(); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) { + /* + * If the syscall failed to refresh the key, then @state->key is now + * invalid, so invalidate the generation so that it is not used again, and + * fallback to using the syscall entirely. + */ + WRITE_ONCE(state->generation, 0); + + /* + * Set @state->in_use to false only after the last write to @state in the + * line above. + */ + WRITE_ONCE(state->in_use, false); + + goto fallback_syscall; + } + + /* + * Set @state->pos to beyond the end of the batch, so that the batch is refilled + * using the new key. + */ + state->pos = sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to read, ret. */ + len = ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by the last call to this + * function. + */ + batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len); + if (batch_len) { + /* Zeroing at the same time as memcpying helps preserve forward secrecy. */ + memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len); + state->pos += batch_len; + buffer += batch_len; + len -= batch_len; + } + + if (!len) { + /* Prevent the loop from being reordered wrt ->generation. */ + barrier(); + + /* + * Since @rng_info->generation will never be 0, re-read @state->generation, rather + * than using the local current_generation variable, to learn whether a fork + * occurred or if @state was zeroed due to memory pressure. Primarily, though, this + * indicates whether the kernel's RNG has reseeded, in which case generate a new key + * and start over. + */ + if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) { + /* + * Prevent this from looping forever in case of low memory or racing with a + * user force-reseeding the kernel's RNG using the ioctl. + */ + if (have_retried) { + WRITE_ONCE(state->in_use, false); + goto fallback_syscall; + } + + have_retried = true; + buffer = orig_buffer; + goto retry_generation; + } + + /* + * Set @state->in_use to false only when there will be no more reads or writes of + * @state. + */ + WRITE_ONCE(state->in_use, false); + return ret; + } + + /* Generate blocks of RNG output directly into @buffer while there's enough room left. */ + nblocks = len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer += nblocks * CHACHA_BLOCK_SIZE; + len -= nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0); + + /* Refill the batch and overwrite the key, in order to preserve forward secrecy. */ + __arch_chacha20_blocks_nostack(state->batch_key, state->key, counter, + sizeof(state->batch_key) / CHACHA_BLOCK_SIZE); + + /* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */ + state->pos = 0; + goto more_batch; + +fallback_syscall: + return getrandom_syscall(orig_buffer, orig_len, flags); +} + +static __always_inline ssize_t +__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); +} -- cgit v1.2.3 From 13f75d9ecf3d8efcf597dfcd8f7be7460cdaa11a Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 15 Jul 2024 04:50:07 +0200 Subject: random: note that RNDGETPOOL was removed in 2.6.9-rc2 RNDGETPOOL was thankfully removed twenty years ago, but it's stuck around in headers. Probably removing it from uapi headers isn't great in case there are some weird users out there, but we should at least mark this as having been removed, to save future readers the same goose chase I just went on. Link: https://lore.kernel.org/all/E1By1St-0001TS-Qj@thunk.org/ Link: https://lore.kernel.org/all/Pine.LNX.4.58.0409130937050.4094@ppc970.osdl.org/ Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index 2a3fe4c2cdc9..1dd047ec98a1 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -20,7 +20,7 @@ /* Add to (or subtract from) the entropy count. (Superuser only.) */ #define RNDADDTOENTCNT _IOW( 'R', 0x01, int ) -/* Get the contents of the entropy pool. (Superuser only.) */ +/* Get the contents of the entropy pool. (Superuser only.) (Removed in 2.6.9-rc2.) */ #define RNDGETPOOL _IOR( 'R', 0x02, int [2] ) /* -- cgit v1.2.3 From d5e726d9143c5624135f5dc9e4069799adeef734 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 12 Jul 2024 18:52:51 -0700 Subject: xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len Julian reports that commit 341ac980eab9 ("xsk: Support tx_metadata_len") can break existing use cases which don't zero-initialize xdp_umem_reg padding. Introduce new XDP_UMEM_TX_METADATA_LEN to make sure we interpret the padding as tx_metadata_len only when being explicitly asked. Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len") Reported-by: Julian Schindel Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Reviewed-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20240713015253.121248-2-sdf@fomichev.me --- Documentation/networking/xsk-tx-metadata.rst | 16 ++++++++++------ include/uapi/linux/if_xdp.h | 4 ++++ net/xdp/xdp_umem.c | 9 ++++++--- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst index bd033fe95cca..e76b0cfc32f7 100644 --- a/Documentation/networking/xsk-tx-metadata.rst +++ b/Documentation/networking/xsk-tx-metadata.rst @@ -11,12 +11,16 @@ metadata on the receive side. General Design ============== -The headroom for the metadata is reserved via ``tx_metadata_len`` in -``struct xdp_umem_reg``. The metadata length is therefore the same for -every socket that shares the same umem. The metadata layout is a fixed UAPI, -refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``. -Thus, generally, the ``tx_metadata_len`` field above should contain -``sizeof(union xsk_tx_metadata)``. +The headroom for the metadata is reserved via ``tx_metadata_len`` and +``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata +length is therefore the same for every socket that shares the same umem. +The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in +``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len`` +field above should contain ``sizeof(union xsk_tx_metadata)``. + +Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN`` +flag was not required. Applications might attempt to create a umem +with a flag first and if it fails, do another attempt without a flag. The headroom and the metadata itself should be located right before ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index d31698410410..42ec5ddaab8d 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -41,6 +41,10 @@ */ #define XDP_UMEM_TX_SW_CSUM (1 << 1) +/* Request to reserve tx_metadata_len bytes of per-chunk metadata. + */ +#define XDP_UMEM_TX_METADATA_LEN (1 << 2) + struct sockaddr_xdp { __u16 sxdp_family; __u16 sxdp_flags; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index caa340134b0e..9f76ca591d54 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) #define XDP_UMEM_FLAGS_VALID ( \ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ XDP_UMEM_TX_SW_CSUM | \ + XDP_UMEM_TX_METADATA_LEN | \ 0) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) @@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; - if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) - return -EINVAL; + if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->tx_metadata_len = mr->tx_metadata_len; + } umem->size = size; umem->headroom = headroom; @@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); -- cgit v1.2.3