From 35d02493dba1ae6386fac07072908717affc3ff8 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 17 May 2022 16:36:21 +0000 Subject: KVM: s390: pv: Add query interface Some of the query information is already available via sysfs but having a IOCTL makes the information easier to retrieve. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Reviewed-by: Steffen Eiden Link: https://lore.kernel.org/r/20220517163629.3443-4-frankja@linux.ibm.com Message-Id: <20220517163629.3443-4-frankja@linux.ibm.com> Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..5a5f66026dd3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1660,6 +1660,30 @@ struct kvm_s390_pv_unp { __u64 tweak; }; +enum pv_cmd_info_id { + KVM_PV_INFO_VM, +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + struct kvm_s390_pv_info_vm vm; +}; + enum pv_cmd_id { KVM_PV_ENABLE, KVM_PV_DISABLE, @@ -1668,6 +1692,7 @@ enum pv_cmd_id { KVM_PV_VERIFY, KVM_PV_PREP_RESET, KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, }; struct kvm_pv_cmd { -- cgit v1.2.3 From fe9a93e07ba4f29def2f8a4318b63e0c70a5c6c2 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 17 May 2022 16:36:23 +0000 Subject: KVM: s390: pv: Add query dump information The dump API requires userspace to provide buffers into which we will store data. The dump information added in this patch tells userspace how big those buffers need to be. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Reviewed-by: Steffen Eiden Link: https://lore.kernel.org/r/20220517163629.3443-6-frankja@linux.ibm.com Message-Id: <20220517163629.3443-6-frankja@linux.ibm.com> Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 11 +++++++++++ include/uapi/linux/kvm.h | 12 +++++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5859f243d287..de54f14e081e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2255,6 +2255,17 @@ static ssize_t kvm_s390_handle_pv_info(struct kvm_s390_pv_info *info) return len_min; } + case KVM_PV_INFO_DUMP: { + len_min = sizeof(info->header) + sizeof(info->dump); + + if (info->header.len_max < len_min) + return -EINVAL; + + info->dump.dump_cpu_buffer_len = uv_info.guest_cpu_stor_len; + info->dump.dump_config_mem_buffer_per_1m = uv_info.conf_dump_storage_state_len; + info->dump.dump_config_finalize_len = uv_info.conf_dump_finalize_len; + return len_min; + } default: return -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5a5f66026dd3..065a05ec06b6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1662,6 +1662,13 @@ struct kvm_s390_pv_unp { enum pv_cmd_info_id { KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; }; struct kvm_s390_pv_info_vm { @@ -1681,7 +1688,10 @@ struct kvm_s390_pv_info_header { struct kvm_s390_pv_info { struct kvm_s390_pv_info_header header; - struct kvm_s390_pv_info_vm vm; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; }; enum pv_cmd_id { -- cgit v1.2.3 From 0460eb35b443f73f8a8e3be1ea87bd690a852e20 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 17 May 2022 16:36:24 +0000 Subject: KVM: s390: Add configuration dump functionality Sometimes dumping inside of a VM fails, is unavailable or doesn't yield the required data. For these occasions we dump the VM from the outside, writing memory and cpu data to a file. Up to now PV guests only supported dumping from the inside of the guest through dumpers like KDUMP. A PV guest can be dumped from the hypervisor but the data will be stale and / or encrypted. To get the actual state of the PV VM we need the help of the Ultravisor who safeguards the VM state. New UV calls have been added to initialize the dump, dump storage state data, dump cpu data and complete the dump process. We expose these calls in this patch via a new UV ioctl command. The sensitive parts of the dump data are encrypted, the dump key is derived from the Customer Communication Key (CCK). This ensures that only the owner of the VM who has the CCK can decrypt the dump data. The memory is dumped / read via a normal export call and a re-import after the dump initialization is not needed (no re-encryption with a dump key). Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20220517163629.3443-7-frankja@linux.ibm.com Message-Id: <20220517163629.3443-7-frankja@linux.ibm.com> Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/kvm-s390.c | 93 ++++++++++++++++++++ arch/s390/kvm/kvm-s390.h | 4 + arch/s390/kvm/pv.c | 182 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 15 ++++ 5 files changed, 295 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 766028d54a3e..a0fbe4820e0a 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -923,6 +923,7 @@ struct kvm_s390_pv { u64 guest_len; unsigned long stor_base; void *stor_var; + bool dumping; }; struct kvm_arch{ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index de54f14e081e..1d00aead6bc5 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2271,6 +2271,68 @@ static ssize_t kvm_s390_handle_pv_info(struct kvm_s390_pv_info *info) } } +static int kvm_s390_pv_dmp(struct kvm *kvm, struct kvm_pv_cmd *cmd, + struct kvm_s390_pv_dmp dmp) +{ + int r = -EINVAL; + void __user *result_buff = (void __user *)dmp.buff_addr; + + switch (dmp.subcmd) { + case KVM_PV_DUMP_INIT: { + if (kvm->arch.pv.dumping) + break; + + /* + * Block SIE entry as concurrent dump UVCs could lead + * to validities. + */ + kvm_s390_vcpu_block_all(kvm); + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DUMP_INIT, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP INIT: rc %x rrc %x", + cmd->rc, cmd->rrc); + if (!r) { + kvm->arch.pv.dumping = true; + } else { + kvm_s390_vcpu_unblock_all(kvm); + r = -EINVAL; + } + break; + } + case KVM_PV_DUMP_CONFIG_STOR_STATE: { + if (!kvm->arch.pv.dumping) + break; + + /* + * gaddr is an output parameter since we might stop + * early. As dmp will be copied back in our caller, we + * don't need to do it ourselves. + */ + r = kvm_s390_pv_dump_stor_state(kvm, result_buff, &dmp.gaddr, dmp.buff_len, + &cmd->rc, &cmd->rrc); + break; + } + case KVM_PV_DUMP_COMPLETE: { + if (!kvm->arch.pv.dumping) + break; + + r = -EINVAL; + if (dmp.buff_len < uv_info.conf_dump_finalize_len) + break; + + r = kvm_s390_pv_dump_complete(kvm, result_buff, + &cmd->rc, &cmd->rrc); + break; + } + default: + r = -ENOTTY; + break; + } + + return r; +} + static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) { int r = 0; @@ -2447,6 +2509,28 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) r = 0; break; } + case KVM_PV_DUMP: { + struct kvm_s390_pv_dmp dmp; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&dmp, argp, sizeof(dmp))) + break; + + r = kvm_s390_pv_dmp(kvm, cmd, dmp); + if (r) + break; + + if (copy_to_user(argp, &dmp, sizeof(dmp))) { + r = -EFAULT; + break; + } + + break; + } default: r = -ENOTTY; } @@ -4564,6 +4648,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; int rc; + /* + * Running a VM while dumping always has the potential to + * produce inconsistent dump data. But for PV vcpus a SIE + * entry while dumping could also lead to a fatal validity + * intercept which we absolutely want to avoid. + */ + if (vcpu->kvm->arch.pv.dumping) + return -EINVAL; + if (kvm_run->immediate_exit) return -EINTR; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 497d52a83c78..2c11eb5ba3ef 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -250,6 +250,10 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, unsigned long tweak, u16 *rc, u16 *rrc); int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); +int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user, + u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc); +int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user, + u16 *rc, u16 *rrc); static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm) { diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index cc7c9599f43e..e9912113879c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include @@ -298,3 +299,184 @@ int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) return -EINVAL; return 0; } + +/* Size of the cache for the storage state dump data. 1MB for now */ +#define DUMP_BUFF_LEN HPAGE_SIZE + +/** + * kvm_s390_pv_dump_stor_state + * + * @kvm: pointer to the guest's KVM struct + * @buff_user: Userspace pointer where we will write the results to + * @gaddr: Starting absolute guest address for which the storage state + * is requested. + * @buff_user_len: Length of the buff_user buffer + * @rc: Pointer to where the uvcb return code is stored + * @rrc: Pointer to where the uvcb return reason code is stored + * + * Stores buff_len bytes of tweak component values to buff_user + * starting with the 1MB block specified by the absolute guest address + * (gaddr). The gaddr pointer will be updated with the last address + * for which data was written when returning to userspace. buff_user + * might be written to even if an error rc is returned. For instance + * if we encounter a fault after writing the first page of data. + * + * Context: kvm->lock needs to be held + * + * Return: + * 0 on success + * -ENOMEM if allocating the cache fails + * -EINVAL if gaddr is not aligned to 1MB + * -EINVAL if buff_user_len is not aligned to uv_info.conf_dump_storage_state_len + * -EINVAL if the UV call fails, rc and rrc will be set in this case + * -EFAULT if copying the result to buff_user failed + */ +int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user, + u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_stor_state uvcb = { + .header.cmd = UVC_CMD_DUMP_CONF_STOR_STATE, + .header.len = sizeof(uvcb), + .config_handle = kvm->arch.pv.handle, + .gaddr = *gaddr, + .dump_area_origin = 0, + }; + const u64 increment_len = uv_info.conf_dump_storage_state_len; + size_t buff_kvm_size; + size_t size_done = 0; + u8 *buff_kvm = NULL; + int cc, ret; + + ret = -EINVAL; + /* UV call processes 1MB guest storage chunks at a time */ + if (!IS_ALIGNED(*gaddr, HPAGE_SIZE)) + goto out; + + /* + * We provide the storage state for 1MB chunks of guest + * storage. The buffer will need to be aligned to + * conf_dump_storage_state_len so we don't end on a partial + * chunk. + */ + if (!buff_user_len || + !IS_ALIGNED(buff_user_len, increment_len)) + goto out; + + /* + * Allocate a buffer from which we will later copy to the user + * process. We don't want userspace to dictate our buffer size + * so we limit it to DUMP_BUFF_LEN. + */ + ret = -ENOMEM; + buff_kvm_size = min_t(u64, buff_user_len, DUMP_BUFF_LEN); + buff_kvm = vzalloc(buff_kvm_size); + if (!buff_kvm) + goto out; + + ret = 0; + uvcb.dump_area_origin = (u64)buff_kvm; + /* We will loop until the user buffer is filled or an error occurs */ + do { + /* Get 1MB worth of guest storage state data */ + cc = uv_call_sched(0, (u64)&uvcb); + + /* All or nothing */ + if (cc) { + ret = -EINVAL; + break; + } + + size_done += increment_len; + uvcb.dump_area_origin += increment_len; + buff_user_len -= increment_len; + uvcb.gaddr += HPAGE_SIZE; + + /* KVM Buffer full, time to copy to the process */ + if (!buff_user_len || size_done == DUMP_BUFF_LEN) { + if (copy_to_user(buff_user, buff_kvm, size_done)) { + ret = -EFAULT; + break; + } + + buff_user += size_done; + size_done = 0; + uvcb.dump_area_origin = (u64)buff_kvm; + } + } while (buff_user_len); + + /* Report back where we ended dumping */ + *gaddr = uvcb.gaddr; + + /* Lets only log errors, we don't want to spam */ +out: + if (ret) + KVM_UV_EVENT(kvm, 3, + "PROTVIRT DUMP STORAGE STATE: addr %llx ret %d, uvcb rc %x rrc %x", + uvcb.gaddr, ret, uvcb.header.rc, uvcb.header.rrc); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + vfree(buff_kvm); + + return ret; +} + +/** + * kvm_s390_pv_dump_complete + * + * @kvm: pointer to the guest's KVM struct + * @buff_user: Userspace pointer where we will write the results to + * @rc: Pointer to where the uvcb return code is stored + * @rrc: Pointer to where the uvcb return reason code is stored + * + * Completes the dumping operation and writes the completion data to + * user space. + * + * Context: kvm->lock needs to be held + * + * Return: + * 0 on success + * -ENOMEM if allocating the completion buffer fails + * -EINVAL if the UV call fails, rc and rrc will be set in this case + * -EFAULT if copying the result to buff_user failed + */ +int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user, + u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_complete complete = { + .header.len = sizeof(complete), + .header.cmd = UVC_CMD_DUMP_COMPLETE, + .config_handle = kvm_s390_pv_get_handle(kvm), + }; + u64 *compl_data; + int ret; + + /* Allocate dump area */ + compl_data = vzalloc(uv_info.conf_dump_finalize_len); + if (!compl_data) + return -ENOMEM; + complete.dump_area_origin = (u64)compl_data; + + ret = uv_call_sched(0, (u64)&complete); + *rc = complete.header.rc; + *rrc = complete.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP COMPLETE: rc %x rrc %x", + complete.header.rc, complete.header.rrc); + + if (!ret) { + /* + * kvm_s390_pv_dealloc_vm() will also (mem)set + * this to false on a reboot or other destroy + * operation for this vm. + */ + kvm->arch.pv.dumping = false; + kvm_s390_vcpu_unblock_all(kvm); + ret = copy_to_user(buff_user, compl_data, uv_info.conf_dump_finalize_len); + if (ret) + ret = -EFAULT; + } + vfree(compl_data); + /* If the UVC returned an error, translate it to -EINVAL */ + if (ret > 0) + ret = -EINVAL; + return ret; +} diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 065a05ec06b6..673be2061c6c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1660,6 +1660,20 @@ struct kvm_s390_pv_unp { __u64 tweak; }; +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + enum pv_cmd_info_id { KVM_PV_INFO_VM, KVM_PV_INFO_DUMP, @@ -1703,6 +1717,7 @@ enum pv_cmd_id { KVM_PV_PREP_RESET, KVM_PV_UNSHARE_ALL, KVM_PV_INFO, + KVM_PV_DUMP, }; struct kvm_pv_cmd { -- cgit v1.2.3 From 8aba09588d2af37c6cc1a781b87d1d91ebf389ae Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 17 May 2022 16:36:25 +0000 Subject: KVM: s390: Add CPU dump functionality The previous patch introduced the per-VM dump functions now let's focus on dumping the VCPU state via the newly introduced KVM_S390_PV_CPU_COMMAND ioctl which mirrors the VM UV ioctl and can be extended with new commands later. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20220517163629.3443-8-frankja@linux.ibm.com Message-Id: <20220517163629.3443-8-frankja@linux.ibm.com> Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.h | 1 + arch/s390/kvm/pv.c | 16 +++++++++++ include/uapi/linux/kvm.h | 4 +++ 4 files changed, 90 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1d00aead6bc5..37be2a33edb5 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5096,6 +5096,48 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp, return -ENOIOCTLCMD; } +static int kvm_s390_handle_pv_vcpu_dump(struct kvm_vcpu *vcpu, + struct kvm_pv_cmd *cmd) +{ + struct kvm_s390_pv_dmp dmp; + void *data; + int ret; + + /* Dump initialization is a prerequisite */ + if (!vcpu->kvm->arch.pv.dumping) + return -EINVAL; + + if (copy_from_user(&dmp, (__u8 __user *)cmd->data, sizeof(dmp))) + return -EFAULT; + + /* We only handle this subcmd right now */ + if (dmp.subcmd != KVM_PV_DUMP_CPU) + return -EINVAL; + + /* CPU dump length is the same as create cpu storage donation. */ + if (dmp.buff_len != uv_info.guest_cpu_stor_len) + return -EINVAL; + + data = kvzalloc(uv_info.guest_cpu_stor_len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + ret = kvm_s390_pv_dump_cpu(vcpu, data, &cmd->rc, &cmd->rrc); + + VCPU_EVENT(vcpu, 3, "PROTVIRT DUMP CPU %d rc %x rrc %x", + vcpu->vcpu_id, cmd->rc, cmd->rrc); + + if (ret) + ret = -EINVAL; + + /* On success copy over the dump data */ + if (!ret && copy_to_user((__u8 __user *)dmp.buff_addr, data, uv_info.guest_cpu_stor_len)) + ret = -EFAULT; + + kvfree(data); + return ret; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5260,6 +5302,33 @@ long kvm_arch_vcpu_ioctl(struct file *filp, irq_state.len); break; } + case KVM_S390_PV_CPU_COMMAND: { + struct kvm_pv_cmd cmd; + + r = -EINVAL; + if (!is_prot_virt_host()) + break; + + r = -EFAULT; + if (copy_from_user(&cmd, argp, sizeof(cmd))) + break; + + r = -EINVAL; + if (cmd.flags) + break; + + /* We only handle this cmd right now */ + if (cmd.cmd != KVM_PV_DUMP) + break; + + r = kvm_s390_handle_pv_vcpu_dump(vcpu, &cmd); + + /* Always copy over UV rc / rrc data */ + if (copy_to_user((__u8 __user *)argp, &cmd.rc, + sizeof(cmd.rc) + sizeof(cmd.rrc))) + r = -EFAULT; + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 2c11eb5ba3ef..dd01d989816f 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -250,6 +250,7 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, unsigned long tweak, u16 *rc, u16 *rrc); int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); +int kvm_s390_pv_dump_cpu(struct kvm_vcpu *vcpu, void *buff, u16 *rc, u16 *rrc); int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user, u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc); int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user, diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index e9912113879c..b4a499b10b67 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -300,6 +300,22 @@ int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) return 0; } +int kvm_s390_pv_dump_cpu(struct kvm_vcpu *vcpu, void *buff, u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_cpu uvcb = { + .header.cmd = UVC_CMD_DUMP_CPU, + .header.len = sizeof(uvcb), + .cpu_handle = vcpu->arch.pv.handle, + .dump_area_origin = (u64)buff, + }; + int cc; + + cc = uv_call_sched(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + return cc; +} + /* Size of the cache for the storage state dump data. 1MB for now */ #define DUMP_BUFF_LEN HPAGE_SIZE diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 673be2061c6c..af5d254f8061 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1664,6 +1664,7 @@ enum pv_cmd_dmp_id { KVM_PV_DUMP_INIT, KVM_PV_DUMP_CONFIG_STOR_STATE, KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, }; struct kvm_s390_pv_dmp { @@ -2168,4 +2169,7 @@ struct kvm_stats_desc { /* Available with KVM_CAP_XSAVE2 */ #define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) +/* Available with KVM_CAP_S390_PROTECTED_DUMP */ +#define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From e9bf3acb23f0a6e18438c35944d6cb618d16cf05 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 17 May 2022 16:36:26 +0000 Subject: KVM: s390: Add KVM_CAP_S390_PROTECTED_DUMP The capability indicates dump support for protected VMs. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20220517163629.3443-9-frankja@linux.ibm.com Message-Id: <20220517163629.3443-9-frankja@linux.ibm.com> Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 20 ++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 2 files changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 37be2a33edb5..d1a32eb3cf5d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -606,6 +606,26 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_PROTECTED: r = is_prot_virt_host(); break; + case KVM_CAP_S390_PROTECTED_DUMP: { + u64 pv_cmds_dump[] = { + BIT_UVC_CMD_DUMP_INIT, + BIT_UVC_CMD_DUMP_CONFIG_STOR_STATE, + BIT_UVC_CMD_DUMP_CPU, + BIT_UVC_CMD_DUMP_COMPLETE, + }; + int i; + + r = is_prot_virt_host(); + + for (i = 0; i < ARRAY_SIZE(pv_cmds_dump); i++) { + if (!test_bit_inv(pv_cmds_dump[i], + (unsigned long *)&uv_info.inst_calls_list)) { + r = 0; + break; + } + } + break; + } default: r = 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index af5d254f8061..c4a32910b88a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1157,6 +1157,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_PROTECTED_DUMP 217 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 6089fb325cf737eeb2c4d236c94697112ca860da Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 6 Jun 2022 23:26:00 -0700 Subject: bpf: Add btf enum64 support Currently, BTF only supports upto 32bit enum value with BTF_KIND_ENUM. But in kernel, some enum indeed has 64bit values, e.g., in uapi bpf.h, we have enum { BPF_F_INDEX_MASK = 0xffffffffULL, BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, BPF_F_CTXLEN_MASK = (0xfffffULL << 32), }; In this case, BTF_KIND_ENUM will encode the value of BPF_F_CTXLEN_MASK as 0, which certainly is incorrect. This patch added a new btf kind, BTF_KIND_ENUM64, which permits 64bit value to cover the above use case. The BTF_KIND_ENUM64 has the following three fields followed by the common type: struct bpf_enum64 { __u32 nume_off; __u32 val_lo32; __u32 val_hi32; }; Currently, btf type section has an alignment of 4 as all element types are u32. Representing the value with __u64 will introduce a pad for bpf_enum64 and may also introduce misalignment for the 64bit value. Hence, two members of val_hi32 and val_lo32 are chosen to avoid these issues. The kflag is also introduced for BTF_KIND_ENUM and BTF_KIND_ENUM64 to indicate whether the value is signed or unsigned. The kflag intends to provide consistent output of BTF C fortmat with the original source code. For example, the original BTF_KIND_ENUM bit value is 0xffffffff. The format C has two choices, printing out 0xffffffff or -1 and current libbpf prints out as unsigned value. But if the signedness is preserved in btf, the value can be printed the same as the original source code. The kflag value 0 means unsigned values, which is consistent to the default by libbpf and should also cover most cases as well. The new BTF_KIND_ENUM64 is intended to support the enum value represented as 64bit value. But it can represent all BTF_KIND_ENUM values as well. The compiler ([1]) and pahole will generate BTF_KIND_ENUM64 only if the value has to be represented with 64 bits. In addition, a static inline function btf_kind_core_compat() is introduced which will be used later when libbpf relo_core.c changed. Here the kernel shares the same relo_core.c with libbpf. [1] https://reviews.llvm.org/D124641 Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220607062600.3716578-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 28 ++++++++ include/uapi/linux/btf.h | 17 ++++- kernel/bpf/btf.c | 142 +++++++++++++++++++++++++++++++++++++---- kernel/bpf/verifier.c | 2 +- tools/include/uapi/linux/btf.h | 17 ++++- 5 files changed, 185 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 2611cea2c2b6..1bfed7fa0428 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -177,6 +177,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || + BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline bool str_is_empty(const char *s) { return !s || !s[0]; @@ -192,6 +205,16 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); @@ -332,6 +355,11 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index a9162a6c0284..ec1798b6d3ff 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -36,10 +36,10 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ BTF_KIND_TYPEDEF = 8, /* Typedef */ BTF_KIND_VOLATILE = 9, /* Volatile */ @@ -76,6 +76,7 @@ enum { BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -186,4 +187,14 @@ struct btf_decl_tag { __s32 component_idx; }; +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7bccaa4646e5..6c0d8480e15c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -309,6 +309,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", }; const char *btf_type_str(const struct btf_type *t) @@ -666,6 +667,7 @@ static bool btf_type_has_size(const struct btf_type *t) case BTF_KIND_ENUM: case BTF_KIND_DATASEC: case BTF_KIND_FLOAT: + case BTF_KIND_ENUM64: return true; } @@ -711,6 +713,11 @@ static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) return (const struct btf_decl_tag *)(t + 1); } +static const struct btf_enum64 *btf_type_enum64(const struct btf_type *t) +{ + return (const struct btf_enum64 *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -1019,6 +1026,7 @@ static const char *btf_show_name(struct btf_show *show) parens = "{"; break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: prefix = "enum"; break; default: @@ -1834,6 +1842,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type, case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_FLOAT: + case BTF_KIND_ENUM64: size = type->size; goto resolved; @@ -3670,6 +3679,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, { const struct btf_enum *enums = btf_type_enum(t); struct btf *btf = env->btf; + const char *fmt_str; u16 i, nr_enums; u32 meta_needed; @@ -3683,11 +3693,6 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_kflag(t)) { - btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); - return -EINVAL; - } - if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; @@ -3718,7 +3723,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, if (env->log.level == BPF_LOG_KERNEL) continue; - btf_verifier_log(env, "\t%s val=%d\n", + fmt_str = btf_type_kflag(t) ? "\t%s val=%d\n" : "\t%s val=%u\n"; + btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); } @@ -3759,7 +3765,10 @@ static void btf_enum_show(const struct btf *btf, const struct btf_type *t, return; } - btf_show_type_value(show, "%d", v); + if (btf_type_kflag(t)) + btf_show_type_value(show, "%d", v); + else + btf_show_type_value(show, "%u", v); btf_show_end_type(show); } @@ -3772,6 +3781,109 @@ static struct btf_kind_operations enum_ops = { .show = btf_enum_show, }; +static s32 btf_enum64_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_enum64 *enums = btf_type_enum64(t); + struct btf *btf = env->btf; + const char *fmt_str; + u16 i, nr_enums; + u32 meta_needed; + + nr_enums = btf_type_vlen(t); + meta_needed = nr_enums * sizeof(*enums); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->size > 8 || !is_power_of_2(t->size)) { + btf_verifier_log_type(env, t, "Unexpected size"); + return -EINVAL; + } + + /* enum type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for (i = 0; i < nr_enums; i++) { + if (!btf_name_offset_valid(btf, enums[i].name_off)) { + btf_verifier_log(env, "\tInvalid name_offset:%u", + enums[i].name_off); + return -EINVAL; + } + + /* enum member must have a valid name */ + if (!enums[i].name_off || + !btf_name_valid_identifier(btf, enums[i].name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + if (env->log.level == BPF_LOG_KERNEL) + continue; + + fmt_str = btf_type_kflag(t) ? "\t%s val=%lld\n" : "\t%s val=%llu\n"; + btf_verifier_log(env, fmt_str, + __btf_name_by_offset(btf, enums[i].name_off), + btf_enum64_value(enums + i)); + } + + return meta_needed; +} + +static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct btf_show *show) +{ + const struct btf_enum64 *enums = btf_type_enum64(t); + u32 i, nr_enums = btf_type_vlen(t); + void *safe_data; + s64 v; + + safe_data = btf_show_start_type(show, t, type_id, data); + if (!safe_data) + return; + + v = *(u64 *)safe_data; + + for (i = 0; i < nr_enums; i++) { + if (v != btf_enum64_value(enums + i)) + continue; + + btf_show_type_value(show, "%s", + __btf_name_by_offset(btf, + enums[i].name_off)); + + btf_show_end_type(show); + return; + } + + if (btf_type_kflag(t)) + btf_show_type_value(show, "%lld", v); + else + btf_show_type_value(show, "%llu", v); + btf_show_end_type(show); +} + +static struct btf_kind_operations enum64_ops = { + .check_meta = btf_enum64_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_enum_check_member, + .check_kflag_member = btf_enum_check_kflag_member, + .log_details = btf_enum_log, + .show = btf_enum64_show, +}; + static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) @@ -4438,6 +4550,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_FLOAT] = &float_ops, [BTF_KIND_DECL_TAG] = &decl_tag_ops, [BTF_KIND_TYPE_TAG] = &modifier_ops, + [BTF_KIND_ENUM64] = &enum64_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -5299,7 +5412,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_small_int(t) || btf_type_is_enum(t)) + if (btf_type_is_small_int(t) || btf_is_any_enum(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { @@ -5763,7 +5876,7 @@ static int __get_type_size(struct btf *btf, u32 btf_id, if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); - if (btf_type_is_int(t) || btf_type_is_enum(t)) + if (btf_type_is_int(t) || btf_is_any_enum(t)) return t->size; *bad_type = t; return -EINVAL; @@ -5911,7 +6024,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log, * to context only. And only global functions can be replaced. * Hence type check only those types. */ - if (btf_type_is_int(t1) || btf_type_is_enum(t1)) + if (btf_type_is_int(t1) || btf_is_any_enum(t1)) continue; if (!btf_type_is_ptr(t1)) { bpf_log(log, @@ -6408,7 +6521,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (!btf_type_is_int(t) && !btf_type_is_enum(t)) { + if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -6423,7 +6536,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_type_is_enum(t)) { + if (btf_type_is_int(t) || btf_is_any_enum(t)) { reg->type = SCALAR_VALUE; continue; } @@ -7335,6 +7448,7 @@ recur: case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_FWD: + case BTF_KIND_ENUM64: return 1; case BTF_KIND_INT: /* just reject deprecated bitfield-like integers; all other @@ -7387,10 +7501,10 @@ recur: * field-based relocations. This function assumes that root types were already * checked for name match. Beyond that initial root-level name check, names * are completely ignored. Compatibility rules are as follows: - * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs are considered compatible, but + * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs/ENUM64s are considered compatible, but * kind should match for local and target types (i.e., STRUCT is not * compatible with UNION); - * - for ENUMs, the size is ignored; + * - for ENUMs/ENUM64s, the size is ignored; * - for INT, size and signedness are ignored; * - for ARRAY, dimensionality is ignored, element types are checked for * compatibility recursively; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index aedac2ac02b9..2d2872682278 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10901,7 +10901,7 @@ static int check_btf_func(struct bpf_verifier_env *env, goto err_free; ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = - btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type); + btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); if (i && !scalar_return && env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n"); goto err_free; diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index a9162a6c0284..ec1798b6d3ff 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -36,10 +36,10 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ BTF_KIND_TYPEDEF = 8, /* Typedef */ BTF_KIND_VOLATILE = 9, /* Volatile */ @@ -76,6 +76,7 @@ enum { BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -186,4 +187,14 @@ struct btf_decl_tag { __s32 component_idx; }; +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ -- cgit v1.2.3 From ed2351174e38ad4febbbc0dba802803e6cff8ae0 Mon Sep 17 00:00:00 2001 From: Chenyi Qiang Date: Tue, 24 May 2022 21:56:21 +0800 Subject: KVM: x86: Extend KVM_{G,S}ET_VCPU_EVENTS to support pending triple fault For the triple fault sythesized by KVM, e.g. the RSM path or nested_vmx_abort(), if KVM exits to userspace before the request is serviced, userspace could migrate the VM and lose the triple fault. Extend KVM_{G,S}ET_VCPU_EVENTS to support pending triple fault with a new event KVM_VCPUEVENT_VALID_FAULT_FAULT so that userspace can save and restore the triple fault event. This extension is guarded by a new KVM capability KVM_CAP_TRIPLE_FAULT_EVENT. Note that in the set_vcpu_events path, userspace is able to set/clear the triple fault request through triple_fault.pending field. Signed-off-by: Chenyi Qiang Message-Id: <20220524135624.22988-2-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 8 ++++++++ arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/include/uapi/asm/kvm.h | 6 +++++- arch/x86/kvm/x86.c | 21 ++++++++++++++++++++- include/uapi/linux/kvm.h | 1 + 5 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 421479a67da5..f67e367c4059 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1150,6 +1150,10 @@ The following bits are defined in the flags field: fields contain a valid state. This bit will be set whenever KVM_CAP_EXCEPTION_PAYLOAD is enabled. +- KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the + triple_fault_pending field contains a valid state. This bit will + be set whenever KVM_CAP_TRIPLE_FAULT_EVENT is enabled. + ARM64: ^^^^^^ @@ -1245,6 +1249,10 @@ can be set in the flags field to signal that the exception_has_payload, exception_payload, and exception.pending fields contain a valid state and shall be written into the VCPU. +If KVM_CAP_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT +can be set in flags field to signal that the triple_fault field contains +a valid state and shall be written into the VCPU. + ARM64: ^^^^^^ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 032278f0ee6d..d6c62276e131 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1174,6 +1174,8 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled; + bool triple_fault_event; + bool bus_lock_detection_enabled; bool enable_pmu; /* diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 21614807a2cb..24c807c8d5f7 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -325,6 +325,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 #define KVM_VCPUEVENT_VALID_SMM 0x00000008 #define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010 +#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -359,7 +360,10 @@ struct kvm_vcpu_events { __u8 smm_inside_nmi; __u8 latched_init; } smi; - __u8 reserved[27]; + struct { + __u8 pending; + } triple_fault; + __u8 reserved[26]; __u8 exception_has_payload; __u64 exception_payload; }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8dfdef9e52f..422fbb0d7518 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4296,6 +4296,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_X86_TRIPLE_FAULT_EVENT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_LAST_CPU: case KVM_CAP_X86_USER_SPACE_MSR: @@ -4942,6 +4943,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SMM); if (vcpu->kvm->arch.exception_payload_enabled) events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD; + if (vcpu->kvm->arch.triple_fault_event) { + events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); + events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; + } memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -4955,7 +4960,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM - | KVM_VCPUEVENT_VALID_PAYLOAD)) + | KVM_VCPUEVENT_VALID_PAYLOAD + | KVM_VCPUEVENT_VALID_TRIPLE_FAULT)) return -EINVAL; if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) { @@ -5028,6 +5034,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, } } + if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) { + if (!vcpu->kvm->arch.triple_fault_event) + return -EINVAL; + if (events->triple_fault.pending) + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + else + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; @@ -6029,6 +6044,10 @@ split_irqchip_unlock: kvm->arch.exception_payload_enabled = cap->args[0]; r = 0; break; + case KVM_CAP_X86_TRIPLE_FAULT_EVENT: + kvm->arch.triple_fault_event = cap->args[0]; + r = 0; + break; case KVM_CAP_X86_USER_SPACE_MSR: kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c4a32910b88a..ca799319acfd 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1158,6 +1158,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SYSTEM_EVENT_DATA 215 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #define KVM_CAP_S390_PROTECTED_DUMP 217 +#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 2f4073e08f4cc5a41e35d777c240aaadd0257051 Mon Sep 17 00:00:00 2001 From: Tao Xu Date: Tue, 24 May 2022 21:56:24 +0800 Subject: KVM: VMX: Enable Notify VM exit There are cases that malicious virtual machines can cause CPU stuck (due to event windows don't open up), e.g., infinite loop in microcode when nested #AC (CVE-2015-5307). No event window means no event (NMI, SMI and IRQ) can be delivered. It leads the CPU to be unavailable to host or other VMs. VMM can enable notify VM exit that a VM exit generated if no event window occurs in VM non-root mode for a specified amount of time (notify window). Feature enabling: - The new vmcs field SECONDARY_EXEC_NOTIFY_VM_EXITING is introduced to enable this feature. VMM can set NOTIFY_WINDOW vmcs field to adjust the expected notify window. - Add a new KVM capability KVM_CAP_X86_NOTIFY_VMEXIT so that user space can query and enable this feature in per-VM scope. The argument is a 64bit value: bits 63:32 are used for notify window, and bits 31:0 are for flags. Current supported flags: - KVM_X86_NOTIFY_VMEXIT_ENABLED: enable the feature with the notify window provided. - KVM_X86_NOTIFY_VMEXIT_USER: exit to userspace once the exits happen. - It's safe to even set notify window to zero since an internal hardware threshold is added to vmcs.notify_window. VM exit handling: - Introduce a vcpu state notify_window_exits to records the count of notify VM exits and expose it through the debugfs. - Notify VM exit can happen incident to delivery of a vector event. Allow it in KVM. - Exit to userspace unconditionally for handling when VM_CONTEXT_INVALID bit is set. Nested handling - Nested notify VM exits are not supported yet. Keep the same notify window control in vmcs02 as vmcs01, so that L1 can't escape the restriction of notify VM exits through launching L2 VM. Notify VM exit is defined in latest Intel Architecture Instruction Set Extensions Programming Reference, chapter 9.2. Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Tao Xu Co-developed-by: Chenyi Qiang Signed-off-by: Chenyi Qiang Message-Id: <20220524135624.22988-5-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 49 ++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 7 ++++++ arch/x86/include/asm/vmx.h | 7 ++++++ arch/x86/include/asm/vmxfeatures.h | 1 + arch/x86/include/uapi/asm/vmx.h | 4 +++- arch/x86/kvm/vmx/capabilities.h | 6 +++++ arch/x86/kvm/vmx/nested.c | 8 +++++++ arch/x86/kvm/vmx/vmx.c | 40 +++++++++++++++++++++++++++++-- arch/x86/kvm/x86.c | 22 ++++++++++++++++- arch/x86/kvm/x86.h | 7 ++++++ include/uapi/linux/kvm.h | 11 +++++++++ 11 files changed, 158 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index f67e367c4059..30e31a886422 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6557,6 +6557,26 @@ array field represents return values. The userspace should update the return values of SBI call before resuming the VCPU. For more details on RISC-V SBI spec refer, https://github.com/riscv/riscv-sbi-doc. +:: + + /* KVM_EXIT_NOTIFY */ + struct { + #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) + __u32 flags; + } notify; + +Used on x86 systems. When the VM capability KVM_CAP_X86_NOTIFY_VMEXIT is +enabled, a VM exit generated if no event window occurs in VM non-root mode +for a specified amount of time. Once KVM_X86_NOTIFY_VMEXIT_USER is set when +enabling the cap, it would exit to userspace with the exit reason +KVM_EXIT_NOTIFY for further handling. The "flags" field contains more +detailed info. + +The valid value for 'flags' is: + + - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid + in VMCS. It would run into unknown result if resume the target VM. + :: /* Fix the size of the union. */ @@ -7523,6 +7543,35 @@ if the value was set to zero or KVM_ENABLE_CAP was not invoked, KVM uses the return value of KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPU_ID) as the maximum APIC ID. +7.33 KVM_CAP_X86_NOTIFY_VMEXIT +------------------------------ + +:Architectures: x86 +:Target: VM +:Parameters: args[0] is the value of notify window as well as some flags +:Returns: 0 on success, -EINVAL if args[0] contains invalid flags or notify + VM exit is unsupported. + +Bits 63:32 of args[0] are used for notify window. +Bits 31:0 of args[0] are for some flags. Valid bits are:: + + #define KVM_X86_NOTIFY_VMEXIT_ENABLED (1 << 0) + #define KVM_X86_NOTIFY_VMEXIT_USER (1 << 1) + +This capability allows userspace to configure the notify VM exit on/off +in per-VM scope during VM creation. Notify VM exit is disabled by default. +When userspace sets KVM_X86_NOTIFY_VMEXIT_ENABLED bit in args[0], VMM will +enable this feature with the notify window provided, which will generate +a VM exit if no event window occurs in VM non-root mode for a specified of +time (notify window). + +If KVM_X86_NOTIFY_VMEXIT_USER is set in args[0], upon notify VM exits happen, +KVM would exit to userspace for handling. + +This capability is aimed to mitigate the threat that malicious VMs can +cause CPU stuck (due to event windows don't open up) and make the CPU +unavailable to host or other VMs. + 8. Other capabilities. ====================== diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4e00bca08cfa..6cf5d77d7896 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -65,6 +65,9 @@ #define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ KVM_BUS_LOCK_DETECTION_EXIT) +#define KVM_X86_NOTIFY_VMEXIT_VALID_BITS (KVM_X86_NOTIFY_VMEXIT_ENABLED | \ + KVM_X86_NOTIFY_VMEXIT_USER) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) @@ -1178,6 +1181,9 @@ struct kvm_arch { bool bus_lock_detection_enabled; bool enable_pmu; + + u32 notify_window; + u32 notify_vmexit_flags; /* * If exit_on_emulation_error is set, and the in-kernel instruction * emulator fails to emulate an instruction, allow userspace @@ -1325,6 +1331,7 @@ struct kvm_vcpu_stat { u64 directed_yield_attempted; u64 directed_yield_successful; u64 guest_mode; + u64 notify_window_exits; }; struct x86_instruction_info; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 89d2172787c5..c371ef695fcc 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -75,6 +75,7 @@ #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) #define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION) +#define SECONDARY_EXEC_NOTIFY_VM_EXITING VMCS_CONTROL_BIT(NOTIFY_VM_EXITING) /* * Definitions of Tertiary Processor-Based VM-Execution Controls. @@ -280,6 +281,7 @@ enum vmcs_field { SECONDARY_VM_EXEC_CONTROL = 0x0000401e, PLE_GAP = 0x00004020, PLE_WINDOW = 0x00004022, + NOTIFY_WINDOW = 0x00004024, VM_INSTRUCTION_ERROR = 0x00004400, VM_EXIT_REASON = 0x00004402, VM_EXIT_INTR_INFO = 0x00004404, @@ -564,6 +566,11 @@ enum vm_entry_failure_code { #define EPT_VIOLATION_GVA_IS_VALID (1 << EPT_VIOLATION_GVA_IS_VALID_BIT) #define EPT_VIOLATION_GVA_TRANSLATED (1 << EPT_VIOLATION_GVA_TRANSLATED_BIT) +/* + * Exit Qualifications for NOTIFY VM EXIT + */ +#define NOTIFY_VM_CONTEXT_INVALID BIT(0) + /* * VM-instruction error numbers */ diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index 589608c157bf..c6a7eed03914 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -85,6 +85,7 @@ #define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */ +#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* VM-Exit when no event windows after notify window */ /* Tertiary Processor-Based VM-Execution Controls, word 3 */ #define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* Enable IPI virtualization */ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 946d761adbd3..a5faf6d88f1b 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -91,6 +91,7 @@ #define EXIT_REASON_UMWAIT 67 #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 +#define EXIT_REASON_NOTIFY 75 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -153,7 +154,8 @@ { EXIT_REASON_XRSTORS, "XRSTORS" }, \ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ { EXIT_REASON_TPAUSE, "TPAUSE" }, \ - { EXIT_REASON_BUS_LOCK, "BUS_LOCK" } + { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \ + { EXIT_REASON_NOTIFY, "NOTIFY" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index f14c4bef97e0..2d3f13b18714 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -436,4 +436,10 @@ static inline u64 vmx_supported_debugctl(void) return debugctl; } +static inline bool cpu_has_notify_vmexit(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_NOTIFY_VM_EXITING; +} + #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 5c5f4e3762f5..7d8cd0ebcc75 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2133,6 +2133,8 @@ static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) { + struct kvm *kvm = vmx->vcpu.kvm; + /* * If vmcs02 hasn't been initialized, set the constant vmcs02 state * according to L0's settings (vmcs12 is irrelevant here). Host @@ -2175,6 +2177,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) if (cpu_has_vmx_encls_vmexit()) vmcs_write64(ENCLS_EXITING_BITMAP, INVALID_GPA); + if (kvm_notify_vmexit_enabled(kvm)) + vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); + /* * Set the MSR load/store lists to match L0's settings. Only the * addresses are constant (for vmcs02), the counts can change based @@ -6112,6 +6117,9 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE); case EXIT_REASON_ENCLS: return nested_vmx_exit_handled_encls(vcpu, vmcs12); + case EXIT_REASON_NOTIFY: + /* Notify VM exit is not exposed to L1 */ + return false; default: return true; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6d631941ac1a..2e00890d752a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2499,7 +2499,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_BUS_LOCK_DETECTION; + SECONDARY_EXEC_BUS_LOCK_DETECTION | + SECONDARY_EXEC_NOTIFY_VM_EXITING; if (cpu_has_sgx()) opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, @@ -4417,6 +4418,9 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!vcpu->kvm->arch.bus_lock_detection_enabled) exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; + if (!kvm_notify_vmexit_enabled(vcpu->kvm)) + exec_control &= ~SECONDARY_EXEC_NOTIFY_VM_EXITING; + return exec_control; } @@ -4498,6 +4502,9 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->ple_window_dirty = true; } + if (kvm_notify_vmexit_enabled(kvm)) + vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ @@ -5784,6 +5791,32 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) return 1; } +static int handle_notify(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qual = vmx_get_exit_qual(vcpu); + bool context_invalid = exit_qual & NOTIFY_VM_CONTEXT_INVALID; + + ++vcpu->stat.notify_window_exits; + + /* + * Notify VM exit happened while executing iret from NMI, + * "blocked by NMI" bit has to be set before next VM entry. + */ + if (enable_vnmi && (exit_qual & INTR_INFO_UNBLOCK_NMI)) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + + if (vcpu->kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_USER || + context_invalid) { + vcpu->run->exit_reason = KVM_EXIT_NOTIFY; + vcpu->run->notify.flags = context_invalid ? + KVM_NOTIFY_CONTEXT_INVALID : 0; + return 0; + } + + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5841,6 +5874,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, + [EXIT_REASON_NOTIFY] = handle_notify, }; static const int kvm_vmx_max_exit_handlers = @@ -6214,7 +6248,8 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && - exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { + exit_reason.basic != EXIT_REASON_TASK_SWITCH && + exit_reason.basic != EXIT_REASON_NOTIFY)) { int ndata = 3; vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; @@ -8137,6 +8172,7 @@ static __init int hardware_setup(void) kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; kvm_caps.tsc_scaling_ratio_frac_bits = 48; kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + kvm_caps.has_notify_vmexit = cpu_has_notify_vmexit(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 53e5f2ad2422..a8014233fd57 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -284,7 +284,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), - STATS_DESC_ICOUNTER(VCPU, guest_mode) + STATS_DESC_ICOUNTER(VCPU, guest_mode), + STATS_DESC_COUNTER(VCPU, notify_window_exits), }; const struct kvm_stats_header kvm_vcpu_stats_header = { @@ -4402,6 +4403,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_DISABLE_QUIRKS2: r = KVM_X86_VALID_QUIRKS; break; + case KVM_CAP_X86_NOTIFY_VMEXIT: + r = kvm_caps.has_notify_vmexit; + break; default: break; } @@ -6125,6 +6129,22 @@ split_irqchip_unlock: } mutex_unlock(&kvm->lock); break; + case KVM_CAP_X86_NOTIFY_VMEXIT: + r = -EINVAL; + if ((u32)cap->args[0] & ~KVM_X86_NOTIFY_VMEXIT_VALID_BITS) + break; + if (!kvm_caps.has_notify_vmexit) + break; + if (!((u32)cap->args[0] & KVM_X86_NOTIFY_VMEXIT_ENABLED)) + break; + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + kvm->arch.notify_window = cap->args[0] >> 32; + kvm->arch.notify_vmexit_flags = (u32)cap->args[0]; + r = 0; + } + mutex_unlock(&kvm->lock); + break; default: r = -EINVAL; break; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 359d0454ad28..501b884b8cc4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -21,6 +21,8 @@ struct kvm_caps { u64 default_tsc_scaling_ratio; /* bus lock detection supported? */ bool has_bus_lock_exit; + /* notify VM exit supported? */ + bool has_notify_vmexit; u64 supported_mce_cap; u64 supported_xcr0; @@ -364,6 +366,11 @@ static inline bool kvm_cstate_in_guest(struct kvm *kvm) return kvm->arch.cstate_in_guest; } +static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm) +{ + return kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_ENABLED; +} + enum kvm_intr_type { /* Values are arbitrary, but must be non-zero. */ KVM_HANDLING_IRQ = 1, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ca799319acfd..7569b4ec199c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -270,6 +270,7 @@ struct kvm_xen_exit { #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 #define KVM_EXIT_RISCV_SBI 35 +#define KVM_EXIT_NOTIFY 36 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -496,6 +497,11 @@ struct kvm_run { unsigned long args[6]; unsigned long ret[2]; } riscv_sbi; + /* KVM_EXIT_NOTIFY */ + struct { +#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) + __u32 flags; + } notify; /* Fix the size of the union. */ char padding[256]; }; @@ -1159,6 +1165,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #define KVM_CAP_S390_PROTECTED_DUMP 217 #define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218 +#define KVM_CAP_X86_NOTIFY_VMEXIT 219 #ifdef KVM_CAP_IRQ_ROUTING @@ -2174,4 +2181,8 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_PROTECTED_DUMP */ #define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd) +/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */ +#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0) +#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From 20e10881a043af63f2962a9e6bca64661225b383 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 8 Jun 2022 10:21:41 -0500 Subject: dma-buf: Add an API for exporting sync files (v14) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Modern userspace APIs like Vulkan are built on an explicit synchronization model. This doesn't always play nicely with the implicit synchronization used in the kernel and assumed by X11 and Wayland. The client -> compositor half of the synchronization isn't too bad, at least on intel, because we can control whether or not i915 synchronizes on the buffer and whether or not it's considered written. The harder part is the compositor -> client synchronization when we get the buffer back from the compositor. We're required to be able to provide the client with a VkSemaphore and VkFence representing the point in time where the window system (compositor and/or display) finished using the buffer. With current APIs, it's very hard to do this in such a way that we don't get confused by the Vulkan driver's access of the buffer. In particular, once we tell the kernel that we're rendering to the buffer again, any CPU waits on the buffer or GPU dependencies will wait on some of the client rendering and not just the compositor. This new IOCTL solves this problem by allowing us to get a snapshot of the implicit synchronization state of a given dma-buf in the form of a sync file. It's effectively the same as a poll() or I915_GEM_WAIT only, instead of CPU waiting directly, it encapsulates the wait operation, at the current moment in time, in a sync_file so we can check/wait on it later. As long as the Vulkan driver does the sync_file export from the dma-buf before we re-introduce it for rendering, it will only contain fences from the compositor or display. This allows to accurately turn it into a VkFence or VkSemaphore without any over-synchronization. By making this an ioctl on the dma-buf itself, it allows this new functionality to be used in an entirely driver-agnostic way without having access to a DRM fd. This makes it ideal for use in driver-generic code in Mesa or in a client such as a compositor where the DRM fd may be hard to reach. v2 (Jason Ekstrand): - Use a wrapper dma_fence_array of all fences including the new one when importing an exclusive fence. v3 (Jason Ekstrand): - Lock around setting shared fences as well as exclusive - Mark SIGNAL_SYNC_FILE as a read-write ioctl. - Initialize ret to 0 in dma_buf_wait_sync_file v4 (Jason Ekstrand): - Use the new dma_resv_get_singleton helper v5 (Jason Ekstrand): - Rename the IOCTLs to import/export rather than wait/signal - Drop the WRITE flag and always get/set the exclusive fence v6 (Jason Ekstrand): - Drop the sync_file import as it was all-around sketchy and not nearly as useful as import. - Re-introduce READ/WRITE flag support for export - Rework the commit message v7 (Jason Ekstrand): - Require at least one sync flag - Fix a refcounting bug: dma_resv_get_excl() doesn't take a reference - Use _rcu helpers since we're accessing the dma_resv read-only v8 (Jason Ekstrand): - Return -ENOMEM if the sync_file_create fails - Predicate support on IS_ENABLED(CONFIG_SYNC_FILE) v9 (Jason Ekstrand): - Add documentation for the new ioctl v10 (Jason Ekstrand): - Go back to dma_buf_sync_file as the ioctl struct name v11 (Daniel Vetter): - Go back to dma_buf_export_sync_file as the ioctl struct name - Better kerneldoc describing what the read/write flags do v12 (Christian König): - Document why we chose to make it an ioctl on dma-buf v13 (Jason Ekstrand): - Rebase on Christian König's fence rework v14 (Daniel Vetter & Christian König): - Use dma_rev_usage_rw to get the properly inverted usage to pass to dma_resv_get_singleton() - Clean up the sync_file and fd if copy_to_user() fails Signed-off-by: Jason Ekstrand Signed-off-by: Jason Ekstrand Signed-off-by: Jason Ekstrand Acked-by: Simon Ser Reviewed-by: Christian König Reviewed-by: Daniel Vetter Cc: Sumit Semwal Cc: Maarten Lankhorst Signed-off-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20220608152142.14495-2-jason@jlekstrand.net --- drivers/dma-buf/dma-buf.c | 67 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/dma-buf.h | 35 +++++++++++++++++++++++ 2 files changed, 102 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index a2f9a1815e38..491797a5dfc8 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -192,6 +193,9 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) * Note that this only signals the completion of the respective fences, i.e. the * DMA transfers are complete. Cache flushing and any other necessary * preparations before CPU access can begin still need to happen. + * + * As an alternative to poll(), the set of fences on DMA buffer can be + * exported as a &sync_file using &dma_buf_sync_file_export. */ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) @@ -326,6 +330,64 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) return 0; } +#if IS_ENABLED(CONFIG_SYNC_FILE) +static long dma_buf_export_sync_file(struct dma_buf *dmabuf, + void __user *user_data) +{ + struct dma_buf_export_sync_file arg; + enum dma_resv_usage usage; + struct dma_fence *fence = NULL; + struct sync_file *sync_file; + int fd, ret; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + usage = dma_resv_usage_rw(arg.flags & DMA_BUF_SYNC_WRITE); + ret = dma_resv_get_singleton(dmabuf->resv, usage, &fence); + if (ret) + goto err_put_fd; + + if (!fence) + fence = dma_fence_get_stub(); + + sync_file = sync_file_create(fence); + + dma_fence_put(fence); + + if (!sync_file) { + ret = -ENOMEM; + goto err_put_fd; + } + + arg.fd = fd; + if (copy_to_user(user_data, &arg, sizeof(arg))) { + ret = -EFAULT; + goto err_put_file; + } + + fd_install(fd, sync_file->file); + + return 0; + +err_put_file: + fput(sync_file->file); +err_put_fd: + put_unused_fd(fd); + return ret; +} +#endif + static long dma_buf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -369,6 +431,11 @@ static long dma_buf_ioctl(struct file *file, case DMA_BUF_SET_NAME_B: return dma_buf_set_name(dmabuf, (const char __user *)arg); +#if IS_ENABLED(CONFIG_SYNC_FILE) + case DMA_BUF_IOCTL_EXPORT_SYNC_FILE: + return dma_buf_export_sync_file(dmabuf, (void __user *)arg); +#endif + default: return -ENOTTY; } diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..46f1e3e98b02 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -85,6 +85,40 @@ struct dma_buf_sync { #define DMA_BUF_NAME_LEN 32 +/** + * struct dma_buf_export_sync_file - Get a sync_file from a dma-buf + * + * Userspace can perform a DMA_BUF_IOCTL_EXPORT_SYNC_FILE to retrieve the + * current set of fences on a dma-buf file descriptor as a sync_file. CPU + * waits via poll() or other driver-specific mechanisms typically wait on + * whatever fences are on the dma-buf at the time the wait begins. This + * is similar except that it takes a snapshot of the current fences on the + * dma-buf for waiting later instead of waiting immediately. This is + * useful for modern graphics APIs such as Vulkan which assume an explicit + * synchronization model but still need to inter-operate with dma-buf. + */ +struct dma_buf_export_sync_file { + /** + * @flags: Read/write flags + * + * Must be DMA_BUF_SYNC_READ, DMA_BUF_SYNC_WRITE, or both. + * + * If DMA_BUF_SYNC_READ is set and DMA_BUF_SYNC_WRITE is not set, + * the returned sync file waits on any writers of the dma-buf to + * complete. Waiting on the returned sync file is equivalent to + * poll() with POLLIN. + * + * If DMA_BUF_SYNC_WRITE is set, the returned sync file waits on + * any users of the dma-buf (read or write) to complete. Waiting + * on the returned sync file is equivalent to poll() with POLLOUT. + * If both DMA_BUF_SYNC_WRITE and DMA_BUF_SYNC_READ are set, this + * is equivalent to just DMA_BUF_SYNC_WRITE. + */ + __u32 flags; + /** @fd: Returned sync file descriptor */ + __s32 fd; +}; + #define DMA_BUF_BASE 'b' #define DMA_BUF_IOCTL_SYNC _IOW(DMA_BUF_BASE, 0, struct dma_buf_sync) @@ -94,5 +128,6 @@ struct dma_buf_sync { #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) #define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) #define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_IOCTL_EXPORT_SYNC_FILE _IOWR(DMA_BUF_BASE, 2, struct dma_buf_export_sync_file) #endif -- cgit v1.2.3 From 594740497e998d30477ab26093bfb81c28cd3ff1 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Wed, 8 Jun 2022 10:21:42 -0500 Subject: dma-buf: Add an API for importing sync files (v10) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch is analogous to the previous sync file export patch in that it allows you to import a sync_file into a dma-buf. Unlike the previous patch, however, this does add genuinely new functionality to dma-buf. Without this, the only way to attach a sync_file to a dma-buf is to submit a batch to your driver of choice which waits on the sync_file and claims to write to the dma-buf. Even if said batch is a no-op, a submit is typically way more overhead than just attaching a fence. A submit may also imply extra synchronization with other work because it happens on a hardware queue. In the Vulkan world, this is useful for dealing with the out-fence from vkQueuePresent. Current Linux window-systems (X11, Wayland, etc.) all rely on dma-buf implicit sync. Since Vulkan is an explicit sync API, we get a set of fences (VkSemaphores) in vkQueuePresent and have to stash those as an exclusive (write) fence on the dma-buf. We handle it in Mesa today with the above mentioned dummy submit trick. This ioctl would allow us to set it directly without the dummy submit. This may also open up possibilities for GPU drivers to move away from implicit sync for their kernel driver uAPI and instead provide sync files and rely on dma-buf import/export for communicating with other implicit sync clients. We make the explicit choice here to only allow setting RW fences which translates to an exclusive fence on the dma_resv. There's no use for read-only fences for communicating with other implicit sync userspace and any such attempts are likely to be racy at best. When we got to insert the RW fence, the actual fence we set as the new exclusive fence is a combination of the sync_file provided by the user and all the other fences on the dma_resv. This ensures that the newly added exclusive fence will never signal before the old one would have and ensures that we don't break any dma_resv contracts. We require userspace to specify RW in the flags for symmetry with the export ioctl and in case we ever want to support read fences in the future. There is one downside here that's worth documenting: If two clients writing to the same dma-buf using this API race with each other, their actions on the dma-buf may happen in parallel or in an undefined order. Both with and without this API, the pattern is the same: Collect all the fences on dma-buf, submit work which depends on said fences, and then set a new exclusive (write) fence on the dma-buf which depends on said work. The difference is that, when it's all handled by the GPU driver's submit ioctl, the three operations happen atomically under the dma_resv lock. If two userspace submits race, one will happen before the other. You aren't guaranteed which but you are guaranteed that they're strictly ordered. If userspace manages the fences itself, then these three operations happen separately and the two render operations may happen genuinely in parallel or get interleaved. However, this is a case of userspace racing with itself. As long as we ensure userspace can't back the kernel into a corner, it should be fine. v2 (Jason Ekstrand): - Use a wrapper dma_fence_array of all fences including the new one when importing an exclusive fence. v3 (Jason Ekstrand): - Lock around setting shared fences as well as exclusive - Mark SIGNAL_SYNC_FILE as a read-write ioctl. - Initialize ret to 0 in dma_buf_wait_sync_file v4 (Jason Ekstrand): - Use the new dma_resv_get_singleton helper v5 (Jason Ekstrand): - Rename the IOCTLs to import/export rather than wait/signal - Drop the WRITE flag and always get/set the exclusive fence v6 (Jason Ekstrand): - Split import and export into separate patches - New commit message v7 (Daniel Vetter): - Fix the uapi header to use the right struct in the ioctl - Use a separate dma_buf_import_sync_file struct - Add kerneldoc for dma_buf_import_sync_file v8 (Jason Ekstrand): - Rebase on Christian König's fence rework v9 (Daniel Vetter): - Fix -EINVAL checks for the flags parameter - Add documentation about read/write fences - Add documentation about the expected usage of import/export and specifically call out the possible userspace race. v10 (Simon Ser): - Fix a typo in the docs Signed-off-by: Jason Ekstrand Signed-off-by: Jason Ekstrand Signed-off-by: Jason Ekstrand Reviewed-by: Christian König Reviewed-by: Daniel Vetter Cc: Sumit Semwal Cc: Maarten Lankhorst Signed-off-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20220608152142.14495-3-jason@jlekstrand.net --- drivers/dma-buf/dma-buf.c | 39 +++++++++++++++++++++++++++++++++++ include/uapi/linux/dma-buf.h | 49 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 491797a5dfc8..5e1b0534b3ce 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -386,6 +386,43 @@ err_put_fd: put_unused_fd(fd); return ret; } + +static long dma_buf_import_sync_file(struct dma_buf *dmabuf, + const void __user *user_data) +{ + struct dma_buf_import_sync_file arg; + struct dma_fence *fence; + enum dma_resv_usage usage; + int ret = 0; + + if (copy_from_user(&arg, user_data, sizeof(arg))) + return -EFAULT; + + if (arg.flags & ~DMA_BUF_SYNC_RW) + return -EINVAL; + + if ((arg.flags & DMA_BUF_SYNC_RW) == 0) + return -EINVAL; + + fence = sync_file_get_fence(arg.fd); + if (!fence) + return -EINVAL; + + usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE : + DMA_RESV_USAGE_READ; + + dma_resv_lock(dmabuf->resv, NULL); + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (!ret) + dma_resv_add_fence(dmabuf->resv, fence, usage); + + dma_resv_unlock(dmabuf->resv); + + dma_fence_put(fence); + + return ret; +} #endif static long dma_buf_ioctl(struct file *file, @@ -434,6 +471,8 @@ static long dma_buf_ioctl(struct file *file, #if IS_ENABLED(CONFIG_SYNC_FILE) case DMA_BUF_IOCTL_EXPORT_SYNC_FILE: return dma_buf_export_sync_file(dmabuf, (void __user *)arg); + case DMA_BUF_IOCTL_IMPORT_SYNC_FILE: + return dma_buf_import_sync_file(dmabuf, (const void __user *)arg); #endif default: diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 46f1e3e98b02..30fb8834aa3c 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -96,6 +96,24 @@ struct dma_buf_sync { * dma-buf for waiting later instead of waiting immediately. This is * useful for modern graphics APIs such as Vulkan which assume an explicit * synchronization model but still need to inter-operate with dma-buf. + * + * The intended usage pattern is the following: + * + * 1. Export a sync_file with flags corresponding to the expected GPU usage + * via DMA_BUF_IOCTL_EXPORT_SYNC_FILE. + * + * 2. Submit rendering work which uses the dma-buf. The work should wait on + * the exported sync file before rendering and produce another sync_file + * when complete. + * + * 3. Import the rendering-complete sync_file into the dma-buf with flags + * corresponding to the GPU usage via DMA_BUF_IOCTL_IMPORT_SYNC_FILE. + * + * Unlike doing implicit synchronization via a GPU kernel driver's exec ioctl, + * the above is not a single atomic operation. If userspace wants to ensure + * ordering via these fences, it is the respnosibility of userspace to use + * locks or other mechanisms to ensure that no other context adds fences or + * submits work between steps 1 and 3 above. */ struct dma_buf_export_sync_file { /** @@ -119,6 +137,36 @@ struct dma_buf_export_sync_file { __s32 fd; }; +/** + * struct dma_buf_import_sync_file - Insert a sync_file into a dma-buf + * + * Userspace can perform a DMA_BUF_IOCTL_IMPORT_SYNC_FILE to insert a + * sync_file into a dma-buf for the purposes of implicit synchronization + * with other dma-buf consumers. This allows clients using explicitly + * synchronized APIs such as Vulkan to inter-op with dma-buf consumers + * which expect implicit synchronization such as OpenGL or most media + * drivers/video. + */ +struct dma_buf_import_sync_file { + /** + * @flags: Read/write flags + * + * Must be DMA_BUF_SYNC_READ, DMA_BUF_SYNC_WRITE, or both. + * + * If DMA_BUF_SYNC_READ is set and DMA_BUF_SYNC_WRITE is not set, + * this inserts the sync_file as a read-only fence. Any subsequent + * implicitly synchronized writes to this dma-buf will wait on this + * fence but reads will not. + * + * If DMA_BUF_SYNC_WRITE is set, this inserts the sync_file as a + * write fence. All subsequent implicitly synchronized access to + * this dma-buf will wait on this fence. + */ + __u32 flags; + /** @fd: Sync file descriptor */ + __s32 fd; +}; + #define DMA_BUF_BASE 'b' #define DMA_BUF_IOCTL_SYNC _IOW(DMA_BUF_BASE, 0, struct dma_buf_sync) @@ -129,5 +177,6 @@ struct dma_buf_export_sync_file { #define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) #define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) #define DMA_BUF_IOCTL_EXPORT_SYNC_FILE _IOWR(DMA_BUF_BASE, 2, struct dma_buf_export_sync_file) +#define DMA_BUF_IOCTL_IMPORT_SYNC_FILE _IOW(DMA_BUF_BASE, 3, struct dma_buf_import_sync_file) #endif -- cgit v1.2.3 From 6b2a51ff03bf0c54cbc699ee85a9a49eb203ebfc Mon Sep 17 00:00:00 2001 From: Nathan Huckleberry Date: Fri, 20 May 2022 18:15:01 +0000 Subject: fscrypt: Add HCTR2 support for filename encryption HCTR2 is a tweakable, length-preserving encryption mode that is intended for use on CPUs with dedicated crypto instructions. HCTR2 has the property that a bitflip in the plaintext changes the entire ciphertext. This property fixes a known weakness with filename encryption: when two filenames in the same directory share a prefix of >= 16 bytes, with AES-CTS-CBC their encrypted filenames share a common substring, leaking information. HCTR2 does not have this problem. More information on HCTR2 can be found here: "Length-preserving encryption with HCTR2": https://eprint.iacr.org/2021/1441.pdf Signed-off-by: Nathan Huckleberry Reviewed-by: Ard Biesheuvel Acked-by: Eric Biggers Signed-off-by: Herbert Xu --- Documentation/filesystems/fscrypt.rst | 22 +++++++++++++++++----- fs/crypto/fscrypt_private.h | 2 +- fs/crypto/keysetup.c | 7 +++++++ fs/crypto/policy.c | 14 +++++++++++--- include/uapi/linux/fscrypt.h | 3 ++- 5 files changed, 38 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 2e9aaa295125..5ba5817c17c2 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -337,6 +337,7 @@ Currently, the following pairs of encryption modes are supported: - AES-256-XTS for contents and AES-256-CTS-CBC for filenames - AES-128-CBC for contents and AES-128-CTS-CBC for filenames - Adiantum for both contents and filenames +- AES-256-XTS for contents and AES-256-HCTR2 for filenames (v2 policies only) If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair. @@ -357,6 +358,17 @@ To use Adiantum, CONFIG_CRYPTO_ADIANTUM must be enabled. Also, fast implementations of ChaCha and NHPoly1305 should be enabled, e.g. CONFIG_CRYPTO_CHACHA20_NEON and CONFIG_CRYPTO_NHPOLY1305_NEON for ARM. +AES-256-HCTR2 is another true wide-block encryption mode that is intended for +use on CPUs with dedicated crypto instructions. AES-256-HCTR2 has the property +that a bitflip in the plaintext changes the entire ciphertext. This property +makes it desirable for filename encryption since initialization vectors are +reused within a directory. For more details on AES-256-HCTR2, see the paper +"Length-preserving encryption with HCTR2" +(https://eprint.iacr.org/2021/1441.pdf). To use AES-256-HCTR2, +CONFIG_CRYPTO_HCTR2 must be enabled. Also, fast implementations of XCTR and +POLYVAL should be enabled, e.g. CRYPTO_POLYVAL_ARM64_CE and +CRYPTO_AES_ARM64_CE_BLK for ARM64. + New encryption modes can be added relatively easily, without changes to individual filesystems. However, authenticated encryption (AE) modes are not currently supported because of the difficulty of dealing @@ -404,11 +416,11 @@ alternatively has the file's nonce (for `DIRECT_KEY policies`_) or inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs. Thus, IV reuse is limited to within a single directory. -With CTS-CBC, the IV reuse means that when the plaintext filenames -share a common prefix at least as long as the cipher block size (16 -bytes for AES), the corresponding encrypted filenames will also share -a common prefix. This is undesirable. Adiantum does not have this -weakness, as it is a wide-block encryption mode. +With CTS-CBC, the IV reuse means that when the plaintext filenames share a +common prefix at least as long as the cipher block size (16 bytes for AES), the +corresponding encrypted filenames will also share a common prefix. This is +undesirable. Adiantum and HCTR2 do not have this weakness, as they are +wide-block encryption modes. All supported filenames encryption modes accept any plaintext length >= 16 bytes; cipher block alignment is not required. However, diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 6b4c8094cc7b..f5be777d8279 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -31,7 +31,7 @@ #define FSCRYPT_CONTEXT_V2 2 /* Keep this in sync with include/uapi/linux/fscrypt.h */ -#define FSCRYPT_MODE_MAX FSCRYPT_MODE_ADIANTUM +#define FSCRYPT_MODE_MAX FSCRYPT_MODE_AES_256_HCTR2 struct fscrypt_context_v1 { u8 version; /* FSCRYPT_CONTEXT_V1 */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index c35711896bd4..fbc71abdabe3 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -53,6 +53,13 @@ struct fscrypt_mode fscrypt_modes[] = { .ivsize = 32, .blk_crypto_mode = BLK_ENCRYPTION_MODE_ADIANTUM, }, + [FSCRYPT_MODE_AES_256_HCTR2] = { + .friendly_name = "AES-256-HCTR2", + .cipher_str = "hctr2(aes)", + .keysize = 32, + .security_strength = 32, + .ivsize = 32, + }, }; static DEFINE_MUTEX(fscrypt_mode_key_setup_mutex); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 5f858cee1e3b..8a054e6d1e68 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -61,7 +61,7 @@ fscrypt_get_dummy_policy(struct super_block *sb) return sb->s_cop->get_dummy_policy(sb); } -static bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode) +static bool fscrypt_valid_enc_modes_v1(u32 contents_mode, u32 filenames_mode) { if (contents_mode == FSCRYPT_MODE_AES_256_XTS && filenames_mode == FSCRYPT_MODE_AES_256_CTS) @@ -78,6 +78,14 @@ static bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode) return false; } +static bool fscrypt_valid_enc_modes_v2(u32 contents_mode, u32 filenames_mode) +{ + if (contents_mode == FSCRYPT_MODE_AES_256_XTS && + filenames_mode == FSCRYPT_MODE_AES_256_HCTR2) + return true; + return fscrypt_valid_enc_modes_v1(contents_mode, filenames_mode); +} + static bool supported_direct_key_modes(const struct inode *inode, u32 contents_mode, u32 filenames_mode) { @@ -151,7 +159,7 @@ static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy, const struct inode *inode) { - if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, + if (!fscrypt_valid_enc_modes_v1(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, "Unsupported encryption modes (contents %d, filenames %d)", @@ -187,7 +195,7 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, { int count = 0; - if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, + if (!fscrypt_valid_enc_modes_v2(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, "Unsupported encryption modes (contents %d, filenames %d)", diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 9f4428be3e36..a756b29afcc2 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -27,7 +27,8 @@ #define FSCRYPT_MODE_AES_128_CBC 5 #define FSCRYPT_MODE_AES_128_CTS 6 #define FSCRYPT_MODE_ADIANTUM 9 -/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */ +#define FSCRYPT_MODE_AES_256_HCTR2 10 +/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */ /* * Legacy policy version; ad-hoc KDF and no key verification. -- cgit v1.2.3 From 924b290655c0f17ac84e752addfc9bc3ec361069 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 24 May 2022 13:47:40 -0700 Subject: xfrm: convert alg_key to flexible array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Iproute2 build generates a warning when built with gcc-12. This is because the alg_key in xfrm.h API has zero size array element instead of flexible array. CC xfrm_state.o In function ‘xfrm_algo_parse’, inlined from ‘xfrm_state_modify.constprop’ at xfrm_state.c:573:5: xfrm_state.c:162:32: warning: writing 1 byte into a region of size 0 [-Wstringop-overflow=] 162 | buf[j] = val; | ~~~~~~~^~~~~ This patch convert the alg_key into flexible array member. There are other zero size arrays here that should be converted as well. This patch is RFC only since it is only compile tested and passes trivial iproute2 tests. Signed-off-by: Stephen Hemminger Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 65e13a099b1a..3ed61df9cc91 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -102,21 +102,21 @@ struct xfrm_replay_state_esn { struct xfrm_algo { char alg_name[64]; unsigned int alg_key_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_algo_auth { char alg_name[64]; unsigned int alg_key_len; /* in bits */ unsigned int alg_trunc_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_algo_aead { char alg_name[64]; unsigned int alg_key_len; /* in bits */ unsigned int alg_icv_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_stats { -- cgit v1.2.3 From 20646f5b1e798bcc20044ae90ac3702f177bf254 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Jun 2022 17:23:45 +0200 Subject: netfilter: xtables: Bring SPDX identifier back Commit e2be04c7f995 ("License cleanup: add SPDX license identifier to uapi header files with a license") added the correct SPDX identifier to include/uapi/linux/netfilter/xt_IDLETIMER.h. A subsequent commit removed it for no reason and reintroduced the UAPI license incorrectness as the file is now missing the UAPI exception again. Add it back and remove the GPLv2 boilerplate while at it. Fixes: 68983a354a65 ("netfilter: xtables: Add snapshot of hardidletimer target") Cc: Manoj Basapathi Cc: Subash Abhinov Kasiviswanathan Cc: Pablo Neira Ayuso Cc: netfilter-devel@vger.kernel.org Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/netfilter/xt_IDLETIMER.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h index 49ddcdc61c09..7bfb31a66fc9 100644 --- a/include/uapi/linux/netfilter/xt_IDLETIMER.h +++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* - * linux/include/linux/netfilter/xt_IDLETIMER.h - * * Header file for Xtables timer target module. * * Copyright (C) 2004, 2010 Nokia Corporation @@ -10,20 +9,6 @@ * by Luciano Coelho * * Contact: Luciano Coelho - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA */ #ifndef _XT_IDLETIMER_H -- cgit v1.2.3 From 17472bc2c3d00e4ed72c3c7b9af0697edea02fff Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:11:27 +0200 Subject: wifi: nl80211: fix typo in comment Spelling mistake (triple letters) in comment. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall Link: https://lore.kernel.org/r/20220521111145.81697-77-Julia.Lawall@inria.fr Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d9490e3062a7..98f905f16411 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5874,7 +5874,7 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_INACTIVITY_TIMER: This driver takes care of freeing up * the connected inactive stations in AP mode. * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested - * to work properly to suppport receiving regulatory hints from + * to work properly to support receiving regulatory hints from * cellular base stations. * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only * here to reserve the value for API/ABI compatibility) -- cgit v1.2.3 From 9731dd4cadc53251ef80b3655c8d841fed52fa3d Mon Sep 17 00:00:00 2001 From: Daniel Phillips Date: Mon, 30 May 2022 11:21:22 -0400 Subject: drm/amdkfd: Add available memory ioctl Add a new KFD ioctl to return the largest possible memory size that can be allocated as a buffer object using kfd_ioctl_alloc_memory_of_gpu. It attempts to use exactly the same accept/reject criteria as that function so that allocating a new buffer object of the size returned by this new ioctl is guaranteed to succeed, barring races with other allocating tasks. This IOCTL will be used by libhsakmt: https://www.mail-archive.com/amd-gfx@lists.freedesktop.org/msg75743.html Signed-off-by: Daniel Phillips Signed-off-by: David Yat Sin Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 38 +++++++++++++++++++++--- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 34 +++++++++++++++++++++ include/uapi/linux/kfd_ioctl.h | 14 +++++++-- 4 files changed, 81 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index ffb2b7d9b9a5..648c031942e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -268,6 +268,7 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev, void *drm_priv); uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv); +size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev); int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct amdgpu_device *adev, uint64_t va, uint64_t size, void *drm_priv, struct kgd_mem **mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index f386b0d256d2..8805bd1eed37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -38,6 +38,12 @@ */ #define AMDGPU_USERPTR_RESTORE_DELAY_MS 1 +/* + * Align VRAM allocations to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB + * BO chunk + */ +#define VRAM_ALLOCATION_ALIGN (1 << 21) + /* Impose limit on how much memory KFD can use */ static struct { uint64_t max_system_mem_limit; @@ -108,7 +114,7 @@ void amdgpu_amdkfd_reserve_system_mem(uint64_t size) * compromise that should work in most cases without reserving too * much memory for page tables unnecessarily (factor 16K, >> 14). */ -#define ESTIMATE_PT_SIZE(mem_size) ((mem_size) >> 14) +#define ESTIMATE_PT_SIZE(mem_size) max(((mem_size) >> 14), AMDGPU_VM_RESERVED_VRAM) static size_t amdgpu_amdkfd_acc_size(uint64_t size) { @@ -148,7 +154,13 @@ static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { system_mem_needed = acc_size; ttm_mem_needed = acc_size; - vram_needed = size; + + /* + * Conservatively round up the allocation requirement to 2 MB + * to avoid fragmentation caused by 4K allocations in the tail + * 2M BO chunk. + */ + vram_needed = ALIGN(size, VRAM_ALLOCATION_ALIGN); } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { system_mem_needed = acc_size + size; ttm_mem_needed = acc_size; @@ -173,7 +185,9 @@ static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > kfd_mem_limit.max_ttm_mem_limit) || (adev->kfd.vram_used + vram_needed > - adev->gmc.real_vram_size - reserved_for_pt)) { + adev->gmc.real_vram_size - + atomic64_read(&adev->vram_pin_size) - + reserved_for_pt)) { ret = -ENOMEM; goto release; } @@ -205,7 +219,7 @@ static void unreserve_mem_limit(struct amdgpu_device *adev, } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { kfd_mem_limit.system_mem_used -= acc_size; kfd_mem_limit.ttm_mem_used -= acc_size; - adev->kfd.vram_used -= size; + adev->kfd.vram_used -= ALIGN(size, VRAM_ALLOCATION_ALIGN); } else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) { kfd_mem_limit.system_mem_used -= (acc_size + size); kfd_mem_limit.ttm_mem_used -= acc_size; @@ -1633,6 +1647,22 @@ out_unlock: return ret; } +size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev) +{ + uint64_t reserved_for_pt = + ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size); + size_t available; + + spin_lock(&kfd_mem_limit.mem_limit_lock); + available = adev->gmc.real_vram_size + - adev->kfd.vram_used + - atomic64_read(&adev->vram_pin_size) + - reserved_for_pt; + spin_unlock(&kfd_mem_limit.mem_limit_lock); + + return ALIGN_DOWN(available, VRAM_ALLOCATION_ALIGN); +} + int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct amdgpu_device *adev, uint64_t va, uint64_t size, void *drm_priv, struct kgd_mem **mem, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 1c7016958d6d..3bcf9bf29acb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -65,6 +65,25 @@ static int kfd_char_dev_major = -1; static struct class *kfd_class; struct device *kfd_device; +static inline struct kfd_process_device *kfd_lock_pdd_by_id(struct kfd_process *p, __u32 gpu_id) +{ + struct kfd_process_device *pdd; + + mutex_lock(&p->mutex); + pdd = kfd_process_device_data_by_id(p, gpu_id); + + if (pdd) + return pdd; + + mutex_unlock(&p->mutex); + return NULL; +} + +static inline void kfd_unlock_pdd(struct kfd_process_device *pdd) +{ + mutex_unlock(&pdd->process->mutex); +} + int kfd_chardev_init(void) { int err = 0; @@ -958,6 +977,19 @@ bool kfd_dev_is_large_bar(struct kfd_dev *dev) return false; } +static int kfd_ioctl_get_available_memory(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_get_available_memory_args *args = data; + struct kfd_process_device *pdd = kfd_lock_pdd_by_id(p, args->gpu_id); + + if (!pdd) + return -EINVAL; + args->available = amdgpu_amdkfd_get_available_memory(pdd->dev->adev); + kfd_unlock_pdd(pdd); + return 0; +} + static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, struct kfd_process *p, void *data) { @@ -2648,6 +2680,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_CRIU_OP, kfd_ioctl_criu, KFD_IOC_FLAG_CHECKPOINT_RESTORE), + AMDKFD_IOCTL_DEF(AMDKFD_IOC_AVAILABLE_MEMORY, + kfd_ioctl_get_available_memory, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 42975e940758..231eb010b823 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -34,9 +34,10 @@ * - 1.6 - Query clear flags in SVM get_attr API * - 1.7 - Checkpoint Restore (CRIU) API * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs + * - 1.9 - Add available memory ioctl */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 8 +#define KFD_IOCTL_MINOR_VERSION 9 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -100,6 +101,12 @@ struct kfd_ioctl_get_queue_wave_state_args { __u32 pad; }; +struct kfd_ioctl_get_available_memory_args { + __u64 available; /* from KFD */ + __u32 gpu_id; /* to KFD */ + __u32 pad; +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -826,7 +833,10 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_CRIU_OP \ AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args) +#define AMDKFD_IOC_AVAILABLE_MEMORY \ + AMDKFD_IOWR(0x23, struct kfd_ioctl_get_available_memory_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x23 +#define AMDKFD_COMMAND_END 0x24 #endif -- cgit v1.2.3 From d30dfd490f7dc4cb6a7c11a647bd1ff7a22139e7 Mon Sep 17 00:00:00 2001 From: Justin Stitt Date: Wed, 8 Jun 2022 15:35:39 -0700 Subject: include/uapi/linux/swab.h: move explicit cast outside ternary A cast inside __builtin_constant_p doesn't do anything since it should evaluate as constant at compile time irrespective of this cast. Instead, I moved this cast outside the ternary to ensure the return type is as expected. Additionally, if __HAVE_BUILTIN_BSWAP16__ was not defined then __swab16 is actually returning an `int` not a `u16` due to integer promotion. As Al Viro notes: You *can't* get smaller-than-int out of ? :, same as you can't get it out of addition, etc. This also fixes some clang -Wformat warnings involving default argument promotion. Link: https://github.com/ClangBuiltLinux/linux/issues/378 Link: https://lkml.kernel.org/r/20220608223539.470472-1-justinstitt@google.com Signed-off-by: Justin Stitt Suggested-by: Al Viro Suggested-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Suggested-by: Nick Desaulniers Signed-off-by: Andrew Morton --- include/uapi/linux/swab.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 7272f85d6d6a..0723a9cce747 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -102,7 +102,7 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) #define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) #else #define __swab16(x) \ - (__builtin_constant_p((__u16)(x)) ? \ + (__u16)(__builtin_constant_p(x) ? \ ___constant_swab16(x) : \ __fswab16(x)) #endif @@ -115,7 +115,7 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) #define __swab32(x) (__u32)__builtin_bswap32((__u32)(x)) #else #define __swab32(x) \ - (__builtin_constant_p((__u32)(x)) ? \ + (__u32)(__builtin_constant_p(x) ? \ ___constant_swab32(x) : \ __fswab32(x)) #endif @@ -128,7 +128,7 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) #define __swab64(x) (__u64)__builtin_bswap64((__u64)(x)) #else #define __swab64(x) \ - (__builtin_constant_p((__u64)(x)) ? \ + (__u64)(__builtin_constant_p(x) ? \ ___constant_swab64(x) : \ __fswab64(x)) #endif -- cgit v1.2.3 From ac80287a6af9fc3f3d189d6d1f523889a0a9e1bc Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:42 +0300 Subject: bpf: Fix documentation of th_len in bpf_tcp_{gen,check}_syncookie bpf_tcp_gen_syncookie expects the full length of the TCP header (with all options), and bpf_tcp_check_syncookie accepts lengths bigger than sizeof(struct tcphdr). Fix the documentation that says these lengths should be exactly sizeof(struct tcphdr). While at it, fix a typo in the name of struct ipv6hdr. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-2-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 10 ++++++---- tools/include/uapi/linux/bpf.h | 10 ++++++---- 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4009dbdf62d..f545e39df72a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3597,10 +3597,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3783,10 +3784,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..f545e39df72a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3597,10 +3597,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3783,10 +3784,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, -- cgit v1.2.3 From 33bf9885040c399cf6a95bd33216644126728e14 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:44 +0300 Subject: bpf: Add helpers to issue and check SYN cookies in XDP The new helpers bpf_tcp_raw_{gen,check}_syncookie_ipv{4,6} allow an XDP program to generate SYN cookies in response to TCP SYN packets and to check those cookies upon receiving the first ACK packet (the final packet of the TCP handshake). Unlike bpf_tcp_{gen,check}_syncookie these new helpers don't need a listening socket on the local machine, which allows to use them together with synproxy to accelerate SYN cookie generation. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-4-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- include/net/tcp.h | 1 + include/uapi/linux/bpf.h | 78 +++++++++++++++++++++++++++ net/core/filter.c | 118 +++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 3 +- scripts/bpf_doc.py | 4 ++ tools/include/uapi/linux/bpf.h | 78 +++++++++++++++++++++++++++ 6 files changed, 281 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..9a1efe23fab7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -432,6 +432,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); +u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f545e39df72a..e81362891596 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5251,6 +5251,80 @@ union bpf_attr { * Pointer to the underlying dynptr data, NULL if the dynptr is * read-only, if the dynptr is invalid, or if the offset and length * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5457,6 +5531,10 @@ union bpf_attr { FN(dynptr_read), \ FN(dynptr_write), \ FN(dynptr_data), \ + FN(tcp_raw_gen_syncookie_ipv4), \ + FN(tcp_raw_gen_syncookie_ipv6), \ + FN(tcp_raw_check_syncookie_ipv4), \ + FN(tcp_raw_check_syncookie_ipv6), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/net/core/filter.c b/net/core/filter.c index 5af58eb48587..b62d4126a561 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7444,6 +7444,114 @@ static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { .arg3_type = ARG_ANYTHING, }; +#ifdef CONFIG_SYN_COOKIES +BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, + struct tcphdr *, th, u32, th_len) +{ + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; + cookie = __cookie_v4_init_sequence(iph, th, &mss); + + return cookie | ((u64)mss << 32); +} + +static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { + .func = bpf_tcp_raw_gen_syncookie_ipv4, + .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct iphdr), + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, + struct tcphdr *, th, u32, th_len) +{ +#if IS_BUILTIN(CONFIG_IPV6) + const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - + sizeof(struct ipv6hdr); + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; + cookie = __cookie_v6_init_sequence(iph, th, &mss); + + return cookie | ((u64)mss << 32); +#else + return -EPROTONOSUPPORT; +#endif +} + +static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { + .func = bpf_tcp_raw_gen_syncookie_ipv6, + .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct ipv6hdr), + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, + struct tcphdr *, th) +{ + u32 cookie = ntohl(th->ack_seq) - 1; + + if (__cookie_v4_check(iph, th, cookie) > 0) + return 0; + + return -EACCES; +} + +static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { + .func = bpf_tcp_raw_check_syncookie_ipv4, + .gpl_only = true, /* __cookie_v4_check is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct iphdr), + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_size = sizeof(struct tcphdr), +}; + +BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, + struct tcphdr *, th) +{ +#if IS_BUILTIN(CONFIG_IPV6) + u32 cookie = ntohl(th->ack_seq) - 1; + + if (__cookie_v6_check(iph, th, cookie) > 0) + return 0; + + return -EACCES; +#else + return -EPROTONOSUPPORT; +#endif +} + +static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { + .func = bpf_tcp_raw_check_syncookie_ipv6, + .gpl_only = true, /* __cookie_v6_check is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct ipv6hdr), + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_size = sizeof(struct tcphdr), +}; +#endif /* CONFIG_SYN_COOKIES */ + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -7856,6 +7964,16 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; +#ifdef CONFIG_SYN_COOKIES + case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: + return &bpf_tcp_raw_gen_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: + return &bpf_tcp_raw_gen_syncookie_ipv6_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv4: + return &bpf_tcp_raw_check_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv6: + return &bpf_tcp_raw_check_syncookie_ipv6_proto; +#endif #endif default: return bpf_sk_base_func_proto(func_id); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2e2a9ece9af2..6426f6a2e744 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3967,7 +3967,7 @@ static bool smc_parse_options(const struct tcphdr *th, /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped * value on success. */ -static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) +u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) { const unsigned char *ptr = (const unsigned char *)(th + 1); int length = (th->doff * 4) - sizeof(struct tcphdr); @@ -4006,6 +4006,7 @@ static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) } return mss; } +EXPORT_SYMBOL_GPL(tcp_parse_mss_option); /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 855b937e7585..a0ec321469bd 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -635,6 +635,8 @@ class PrinterHelpers(Printer): 'struct bpf_timer', 'struct mptcp_sock', 'struct bpf_dynptr', + 'struct iphdr', + 'struct ipv6hdr', ] known_types = { '...', @@ -686,6 +688,8 @@ class PrinterHelpers(Printer): 'struct bpf_timer', 'struct mptcp_sock', 'struct bpf_dynptr', + 'struct iphdr', + 'struct ipv6hdr', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f545e39df72a..e81362891596 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5251,6 +5251,80 @@ union bpf_attr { * Pointer to the underlying dynptr data, NULL if the dynptr is * read-only, if the dynptr is invalid, or if the offset and length * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5457,6 +5531,10 @@ union bpf_attr { FN(dynptr_read), \ FN(dynptr_write), \ FN(dynptr_data), \ + FN(tcp_raw_gen_syncookie_ipv4), \ + FN(tcp_raw_gen_syncookie_ipv6), \ + FN(tcp_raw_check_syncookie_ipv4), \ + FN(tcp_raw_check_syncookie_ipv6), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 5374d8fb75f313294c7d97e85c22bead34d63f2b Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Thu, 19 May 2022 08:11:46 +0100 Subject: media: Add P010 video format P010 is a YUV format with 10-bits per component with interleaved UV. Signed-off-by: Benjamin Gaignard Acked-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 54 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-common.c | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 4 files changed, 57 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 8dff5906639b..a900ff66911a 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -109,6 +109,13 @@ All components are stored with the same number of bits per component. - Cb, Cr - No - 16x16 tiles + * - V4L2_PIX_FMT_P010 + - 'P010' + - 10 + - 4:2:0 + - Cb, Cr + - Yes + - Linear * - V4L2_PIX_FMT_NV16 - 'NV16' - 8 @@ -171,6 +178,7 @@ horizontally. .. _V4L2-PIX-FMT-NV21: .. _V4L2-PIX-FMT-NV12M: .. _V4L2-PIX-FMT-NV21M: +.. _V4L2-PIX-FMT-P010: NV12, NV21, NV12M and NV21M --------------------------- @@ -519,6 +527,52 @@ number of lines as the luma plane. - Cb\ :sub:`33` - Cr\ :sub:`33` +.. _V4L2_PIX_FMT_P010: + +P010 +---- + +Like NV12 with 10 bits per component, expanded to 16 bits. +Data in the 10 high bits, zeros in the 6 low bits, arranged in little endian order. + +.. flat-table:: Sample 4x4 P010 Image + :header-rows: 0 + :stub-columns: 0 + + * - start + 0: + - Y'\ :sub:`00` + - Y'\ :sub:`01` + - Y'\ :sub:`02` + - Y'\ :sub:`03` + * - start + 8: + - Y'\ :sub:`10` + - Y'\ :sub:`11` + - Y'\ :sub:`12` + - Y'\ :sub:`13` + * - start + 16: + - Y'\ :sub:`20` + - Y'\ :sub:`21` + - Y'\ :sub:`22` + - Y'\ :sub:`23` + * - start + 24: + - Y'\ :sub:`30` + - Y'\ :sub:`31` + - Y'\ :sub:`32` + - Y'\ :sub:`33` + * - start + 32: + - Cb\ :sub:`00` + - Cr\ :sub:`00` + - Cb\ :sub:`01` + - Cr\ :sub:`01` + * - start + 40: + - Cb\ :sub:`10` + - Cr\ :sub:`10` + - Cb\ :sub:`11` + - Cr\ :sub:`11` + +.. raw:: latex + + \endgroup Fully Planar YUV Formats ======================== diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index df34b2a283bc..1e38ad8906a2 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -266,6 +266,7 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) { .format = V4L2_PIX_FMT_NV61, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_NV24, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_NV42, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_P010, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 2, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_YUV410, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 }, { .format = V4L2_PIX_FMT_YVU410, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 21470de62d72..e2526701294e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1306,6 +1306,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_P010: descr = "10-bit Y/CrCb 4:2:0"; break; case V4L2_PIX_FMT_NV12_4L4: descr = "Y/CbCr 4:2:0 (4x4 Linear)"; break; case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 343b95107fce..5311ac4fde35 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -602,6 +602,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ #define V4L2_PIX_FMT_NV24 v4l2_fourcc('N', 'V', '2', '4') /* 24 Y/CbCr 4:4:4 */ #define V4L2_PIX_FMT_NV42 v4l2_fourcc('N', 'V', '4', '2') /* 24 Y/CrCb 4:4:4 */ +#define V4L2_PIX_FMT_P010 v4l2_fourcc('P', '0', '1', '0') /* 24 Y/CbCr 4:2:0 10-bit per component */ /* two non contiguous planes - one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12M v4l2_fourcc('N', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 */ -- cgit v1.2.3 From 7b0a0e3c3a88260b6fcb017e49f198463aa62ed1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 14 Apr 2022 16:50:57 +0200 Subject: wifi: cfg80211: do some rework towards MLO link APIs In order to support multi-link operation with multiple links, start adding some APIs. The notable addition here is to have the link ID in a new nl80211 attribute, that will be used to differentiate the links in many nl80211 operations. So far, this patch adds the netlink NL80211_ATTR_MLO_LINK_ID attribute (as well as the NL80211_ATTR_MLO_LINKS attribute) and plugs it through the system in some places, checking the validity etc. along with other infrastructure needed for it. For now, I've decided to include only the over-the-air link ID in the API. I know we discussed that we eventually need to have to have other ways of identifying a link, but for local AP mode and auth/assoc commands as well as set_key etc. we'll use the OTA ID. Also included in this patch is some refactoring of the data structures in struct wireless_dev, splitting for the first time the data into type dependent pieces, to make reasoning about these things easier. Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 6 +- drivers/net/wireless/ath/wil6210/cfg80211.c | 9 +- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 4 +- drivers/net/wireless/marvell/libertas/mesh.c | 10 +- drivers/net/wireless/marvell/mwifiex/11h.c | 2 +- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 18 +- drivers/net/wireless/microchip/wilc1000/cfg80211.c | 3 +- drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 14 +- drivers/net/wireless/quantenna/qtnfmac/commands.c | 2 +- drivers/net/wireless/quantenna/qtnfmac/event.c | 15 +- drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c | 4 +- include/linux/ieee80211.h | 3 + include/net/cfg80211.h | 99 +++- include/uapi/linux/nl80211.h | 28 + net/mac80211/cfg.c | 8 +- net/mac80211/mlme.c | 2 +- net/wireless/ap.c | 46 +- net/wireless/chan.c | 196 +++++-- net/wireless/core.c | 28 +- net/wireless/core.h | 13 +- net/wireless/ibss.c | 57 +- net/wireless/mesh.c | 31 +- net/wireless/mlme.c | 74 +-- net/wireless/nl80211.c | 623 +++++++++++++++------ net/wireless/ocb.c | 5 +- net/wireless/rdev-ops.h | 32 +- net/wireless/reg.c | 139 +++-- net/wireless/scan.c | 8 +- net/wireless/sme.c | 102 ++-- net/wireless/trace.h | 86 ++- net/wireless/util.c | 44 +- net/wireless/wext-compat.c | 48 +- net/wireless/wext-sme.c | 29 +- 33 files changed, 1255 insertions(+), 533 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index bd1183830e91..33ed54738d47 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -1119,7 +1119,7 @@ void ath6kl_cfg80211_ch_switch_notify(struct ath6kl_vif *vif, int freq, NL80211_CHAN_HT20 : NL80211_CHAN_NO_HT); mutex_lock(&vif->wdev.mtx); - cfg80211_ch_switch_notify(vif->ndev, &chandef); + cfg80211_ch_switch_notify(vif->ndev, &chandef, 0); mutex_unlock(&vif->wdev.mtx); } @@ -2967,7 +2967,8 @@ static int ath6kl_change_beacon(struct wiphy *wiphy, struct net_device *dev, return ath6kl_set_ies(vif, beacon); } -static int ath6kl_stop_ap(struct wiphy *wiphy, struct net_device *dev) +static int ath6kl_stop_ap(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id) { struct ath6kl *ar = ath6kl_priv(dev); struct ath6kl_vif *vif = netdev_priv(dev); @@ -3368,6 +3369,7 @@ static int ath6kl_cfg80211_sscan_stop(struct wiphy *wiphy, static int ath6kl_cfg80211_set_bitrate(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, const u8 *addr, const struct cfg80211_bitrate_mask *mask) { diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 8f2638f5b87b..f93bdffa4d1d 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -2098,8 +2098,8 @@ static int wil_cfg80211_change_beacon(struct wiphy *wiphy, bcon->tail_len)) privacy = 1; - memcpy(vif->ssid, wdev->ssid, wdev->ssid_len); - vif->ssid_len = wdev->ssid_len; + memcpy(vif->ssid, wdev->u.ap.ssid, wdev->u.ap.ssid_len); + vif->ssid_len = wdev->u.ap.ssid_len; /* in case privacy has changed, need to restart the AP */ if (vif->privacy != privacy) { @@ -2108,7 +2108,7 @@ static int wil_cfg80211_change_beacon(struct wiphy *wiphy, rc = _wil_cfg80211_start_ap(wiphy, ndev, vif->ssid, vif->ssid_len, privacy, - wdev->beacon_interval, + wdev->links[0].ap.beacon_interval, vif->channel, vif->wmi_edmg_channel, bcon, vif->hidden_ssid, @@ -2186,7 +2186,8 @@ static int wil_cfg80211_start_ap(struct wiphy *wiphy, } static int wil_cfg80211_stop_ap(struct wiphy *wiphy, - struct net_device *ndev) + struct net_device *ndev, + unsigned int link_id) { struct wil6210_priv *wil = wiphy_to_wil(wiphy); struct wil6210_vif *vif = ndev_to_vif(ndev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 605206abe424..11e1f07f83e0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4965,7 +4965,8 @@ exit: return err; } -static int brcmf_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *ndev) +static int brcmf_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *ndev, + unsigned int link_id) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_if *ifp = netdev_priv(ndev); @@ -5302,6 +5303,7 @@ exit: static int brcmf_cfg80211_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); diff --git a/drivers/net/wireless/marvell/libertas/mesh.c b/drivers/net/wireless/marvell/libertas/mesh.c index a58c1e141f2c..90ffe8d1e0e8 100644 --- a/drivers/net/wireless/marvell/libertas/mesh.c +++ b/drivers/net/wireless/marvell/libertas/mesh.c @@ -109,9 +109,9 @@ static int lbs_mesh_config(struct lbs_private *priv, uint16_t action, if (priv->mesh_dev) { mesh_wdev = priv->mesh_dev->ieee80211_ptr; - ie->val.mesh_id_len = mesh_wdev->mesh_id_up_len; - memcpy(ie->val.mesh_id, mesh_wdev->ssid, - mesh_wdev->mesh_id_up_len); + ie->val.mesh_id_len = mesh_wdev->u.mesh.id_up_len; + memcpy(ie->val.mesh_id, mesh_wdev->u.mesh.id, + mesh_wdev->u.mesh.id_up_len); } ie->len = sizeof(struct mrvl_meshie_val) - @@ -986,8 +986,8 @@ static int lbs_add_mesh(struct lbs_private *priv) mesh_wdev->wiphy = priv->wdev->wiphy; if (priv->mesh_tlv) { - sprintf(mesh_wdev->ssid, "mesh"); - mesh_wdev->mesh_id_up_len = 4; + sprintf(mesh_wdev->u.mesh.id, "mesh"); + mesh_wdev->u.mesh.id_up_len = 4; } mesh_wdev->netdev = mesh_dev; diff --git a/drivers/net/wireless/marvell/mwifiex/11h.c b/drivers/net/wireless/marvell/mwifiex/11h.c index 3fa25cd64cda..4ca8d0135708 100644 --- a/drivers/net/wireless/marvell/mwifiex/11h.c +++ b/drivers/net/wireless/marvell/mwifiex/11h.c @@ -304,6 +304,6 @@ void mwifiex_dfs_chan_sw_work_queue(struct work_struct *work) mwifiex_dbg(priv->adapter, MSG, "indicating channel switch completion to kernel\n"); mutex_lock(&priv->wdev.mtx); - cfg80211_ch_switch_notify(priv->netdev, &priv->dfs_chandef); + cfg80211_ch_switch_notify(priv->netdev, &priv->dfs_chandef, 0); mutex_unlock(&priv->wdev.mtx); } diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 6f23ec34e2e2..d68c40e0e122 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -1753,10 +1753,12 @@ mwifiex_mgmt_stypes[NUM_NL80211_IFTYPES] = { * Function configures data rates to firmware using bitrate mask * provided by cfg80211. */ -static int mwifiex_cfg80211_set_bitrate_mask(struct wiphy *wiphy, - struct net_device *dev, - const u8 *peer, - const struct cfg80211_bitrate_mask *mask) +static int +mwifiex_cfg80211_set_bitrate_mask(struct wiphy *wiphy, + struct net_device *dev, + unsigned int link_id, + const u8 *peer, + const struct cfg80211_bitrate_mask *mask) { struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev); u16 bitmap_rates[MAX_BITMAP_RATES_SIZE]; @@ -1998,7 +2000,8 @@ mwifiex_cfg80211_get_antenna(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant) /* cfg80211 operation handler for stop ap. * Function stops BSS running at uAP interface. */ -static int mwifiex_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) +static int mwifiex_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id) { struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev); @@ -2421,7 +2424,7 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } - if (priv->wdev.current_bss) { + if (priv->wdev.connected) { mwifiex_dbg(adapter, ERROR, "%s: already connected\n", dev->name); return -EALREADY; @@ -2649,7 +2652,7 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy, return -EBUSY; } - if (!priv->wdev.current_bss && priv->scan_block) + if (!priv->wdev.connected && priv->scan_block) priv->scan_block = false; if (!mwifiex_stop_bg_scan(priv)) @@ -4025,6 +4028,7 @@ mwifiex_cfg80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, static int mwifiex_cfg80211_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct mwifiex_private *priv = mwifiex_netdev_get_priv(wdev->netdev); diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index 1ac4684fab25..5c2c7f1dbffd 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1426,7 +1426,8 @@ static int change_beacon(struct wiphy *wiphy, struct net_device *dev, return wilc_add_beacon(vif, 0, 0, beacon); } -static int stop_ap(struct wiphy *wiphy, struct net_device *dev) +static int stop_ap(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id) { int ret; struct wilc_vif *vif = netdev_priv(dev); diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 84b15a655eab..1593e810b3ca 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -352,7 +352,8 @@ static int qtnf_start_ap(struct wiphy *wiphy, struct net_device *dev, return ret; } -static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev) +static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id) { struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); int ret; @@ -500,7 +501,7 @@ qtnf_dump_station(struct wiphy *wiphy, struct net_device *dev, switch (vif->wdev.iftype) { case NL80211_IFTYPE_STATION: - if (idx != 0 || !vif->wdev.current_bss) + if (idx != 0 || !vif->wdev.connected) return -ENOENT; ether_addr_copy(mac, vif->bssid); @@ -729,7 +730,7 @@ qtnf_disconnect(struct wiphy *wiphy, struct net_device *dev, pr_err("VIF%u.%u: failed to disconnect\n", mac->macid, vif->vifid); - if (vif->wdev.current_bss) { + if (vif->wdev.connected) { netif_carrier_off(vif->netdev); cfg80211_disconnected(vif->netdev, reason_code, NULL, 0, true, GFP_KERNEL); @@ -745,10 +746,11 @@ qtnf_dump_survey(struct wiphy *wiphy, struct net_device *dev, struct qtnf_wmac *mac = wiphy_priv(wiphy); struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_supported_band *sband; - const struct cfg80211_chan_def *chandef = &wdev->chandef; + const struct cfg80211_chan_def *chandef = wdev_chandef(wdev, 0); struct ieee80211_channel *chan; int ret; + sband = wiphy->bands[NL80211_BAND_2GHZ]; if (sband && idx >= sband->n_channels) { idx -= sband->n_channels; @@ -765,7 +767,7 @@ qtnf_dump_survey(struct wiphy *wiphy, struct net_device *dev, survey->channel = chan; survey->filled = 0x0; - if (chan == chandef->chan) + if (chandef && chan == chandef->chan) survey->filled = SURVEY_INFO_IN_USE; ret = qtnf_cmd_get_chan_stats(mac, chan->center_freq, survey); @@ -778,7 +780,7 @@ qtnf_dump_survey(struct wiphy *wiphy, struct net_device *dev, static int qtnf_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, - struct cfg80211_chan_def *chandef) + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct net_device *ndev = wdev->netdev; struct qtnf_vif *vif; diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index c68563c83098..3d734a7a5ba8 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -2005,7 +2005,7 @@ int qtnf_cmd_send_scan(struct qtnf_wmac *mac) dwell_active = scan_req->duration; dwell_passive = scan_req->duration; } else if (wdev->iftype == NL80211_IFTYPE_STATION && - wdev->current_bss) { + wdev->connected) { /* let device select dwell based on traffic conditions */ dwell_active = QTNF_SCAN_TIME_AUTO; dwell_passive = QTNF_SCAN_TIME_AUTO; diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index 8dc80574d08d..4fafe370101a 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -189,7 +189,7 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, vif->mac->macid, vif->vifid, join_info->bssid, chandef.chan->hw_value); - if (!vif->wdev.ssid_len) { + if (!vif->wdev.u.client.ssid_len) { pr_warn("VIF%u.%u: SSID unknown for BSS:%pM\n", vif->mac->macid, vif->vifid, join_info->bssid); @@ -197,7 +197,7 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, goto done; } - ie = kzalloc(2 + vif->wdev.ssid_len, GFP_KERNEL); + ie = kzalloc(2 + vif->wdev.u.client.ssid_len, GFP_KERNEL); if (!ie) { pr_warn("VIF%u.%u: IE alloc failed for BSS:%pM\n", vif->mac->macid, vif->vifid, @@ -207,14 +207,15 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, } ie[0] = WLAN_EID_SSID; - ie[1] = vif->wdev.ssid_len; - memcpy(ie + 2, vif->wdev.ssid, vif->wdev.ssid_len); + ie[1] = vif->wdev.u.client.ssid_len; + memcpy(ie + 2, vif->wdev.u.client.ssid, + vif->wdev.u.client.ssid_len); bss = cfg80211_inform_bss(wiphy, chandef.chan, CFG80211_BSS_FTYPE_UNKNOWN, join_info->bssid, 0, WLAN_CAPABILITY_ESS, 100, - ie, 2 + vif->wdev.ssid_len, + ie, 2 + vif->wdev.u.client.ssid_len, 0, GFP_KERNEL); if (!bss) { pr_warn("VIF%u.%u: can't connect to unknown BSS: %pM\n", @@ -470,14 +471,14 @@ qtnf_event_handle_freq_change(struct qtnf_wmac *mac, continue; if (vif->wdev.iftype == NL80211_IFTYPE_STATION && - !vif->wdev.current_bss) + !vif->wdev.connected) continue; if (!vif->netdev) continue; mutex_lock(&vif->wdev.mtx); - cfg80211_ch_switch_notify(vif->netdev, &chandef); + cfg80211_ch_switch_notify(vif->netdev, &chandef, 0); mutex_unlock(&vif->wdev.mtx); } diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index 43b5604c0bca..349aa3c4b668 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -2086,6 +2086,7 @@ static u8 rtw_get_chan_type(struct adapter *adapter) } static int cfg80211_rtw_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct adapter *adapter = wiphy_to_adapter(wiphy); @@ -2446,7 +2447,8 @@ static int cfg80211_rtw_change_beacon(struct wiphy *wiphy, struct net_device *nd return rtw_add_beacon(adapter, info->head, info->head_len, info->tail, info->tail_len); } -static int cfg80211_rtw_stop_ap(struct wiphy *wiphy, struct net_device *ndev) +static int cfg80211_rtw_stop_ap(struct wiphy *wiphy, struct net_device *ndev, + unsigned int link_id) { return 0; } diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 5c65ae6b8154..e15771965916 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4376,4 +4376,7 @@ enum ieee80211_range_params_max_total_ltf { IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED, }; +/* multi-link device */ +#define IEEE80211_MLD_MAX_NUM_LINKS 15 + #endif /* LINUX_IEEE80211_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6d02e12e4702..772e099fc932 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1158,6 +1158,7 @@ struct cfg80211_mbssid_elems { /** * struct cfg80211_beacon_data - beacon data + * @link_id: the link ID for the AP MLD link sending this beacon * @head: head portion of beacon (before TIM IE) * or %NULL if not changed * @tail: tail portion of beacon (after TIM IE) @@ -1188,6 +1189,8 @@ struct cfg80211_mbssid_elems { * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { + unsigned int link_id; + const u8 *head, *tail; const u8 *beacon_ies; const u8 *proberesp_ies; @@ -4201,7 +4204,8 @@ struct cfg80211_ops { struct cfg80211_ap_settings *settings); int (*change_beacon)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_beacon_data *info); - int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev); + int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id); int (*add_station)(struct wiphy *wiphy, struct net_device *dev, @@ -4309,6 +4313,7 @@ struct cfg80211_ops { int (*set_bitrate_mask)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask); @@ -4384,6 +4389,7 @@ struct cfg80211_ops { int (*get_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*start_p2p_device)(struct wiphy *wiphy, @@ -4420,6 +4426,7 @@ struct cfg80211_ops { struct cfg80211_qos_map *qos_map); int (*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev, @@ -4545,10 +4552,14 @@ struct cfg80211_ops { * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation * before connection. * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys + * @WIPHY_FLAG_SUPPORTS_MLO: This is a temporary flag gating the MLO APIs, + * in order to not have them reachable in normal drivers, until we have + * complete feature/interface combinations/etc. advertisement. No driver + * should set this flag for now. */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), - /* use hole at 1 */ + WIPHY_FLAG_SUPPORTS_MLO = BIT(1), WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), @@ -5505,6 +5516,8 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this * wireless device if it has no netdev + * @connected_addr: (private) BSSID or AP MLD address if connected + * @connected: indicates if connected or not (STA mode) * @current_bss: (private) Used by the internal configuration code * @chandef: (private) Used by the internal configuration code to track * the user-set channel definition. @@ -5585,8 +5598,6 @@ struct wireless_dev { u8 address[ETH_ALEN] __aligned(sizeof(u16)); /* currently used for IBSS and SME - might be rearranged later */ - u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; enum ieee80211_bss_type conn_bss_type; @@ -5598,20 +5609,17 @@ struct wireless_dev { struct list_head event_list; spinlock_t event_lock; - struct cfg80211_internal_bss *current_bss; /* associated / joined */ - struct cfg80211_chan_def preset_chandef; - struct cfg80211_chan_def chandef; + u8 connected:1; bool ps; int ps_timeout; - int beacon_interval; - u32 ap_unexpected_nlportid; u32 owner_nlportid; bool nl_owner_dead; + /* FIXME: need to rework radar detection for MLO */ bool cac_started; unsigned long cac_start_time; unsigned int cac_time_ms; @@ -5639,6 +5647,50 @@ struct wireless_dev { struct work_struct pmsr_free_wk; unsigned long unprot_beacon_reported; + + union { + struct { + u8 connected_addr[ETH_ALEN] __aligned(2); + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } client; + struct { + int beacon_interval; + struct cfg80211_chan_def preset_chandef; + struct cfg80211_chan_def chandef; + u8 id[IEEE80211_MAX_SSID_LEN]; + u8 id_len, id_up_len; + } mesh; + struct { + struct cfg80211_chan_def preset_chandef; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + struct cfg80211_chan_def chandef; + int beacon_interval; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ibss; + struct { + struct cfg80211_chan_def chandef; + } ocb; + } u; + + struct { + u8 addr[ETH_ALEN] __aligned(2); + union { + struct { + unsigned int beacon_interval; + struct cfg80211_chan_def chandef; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + } client; + }; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 valid_links; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) @@ -5667,6 +5719,31 @@ static inline void *wdev_priv(struct wireless_dev *wdev) return wiphy_priv(wdev->wiphy); } +/** + * wdev_chandef - return chandef pointer from wireless_dev + * @wdev: the wdev + * @link_id: the link ID for MLO + * + * Return: The chandef depending on the mode, or %NULL. + */ +struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, + unsigned int link_id); + +static inline void WARN_INVALID_LINK_ID(struct wireless_dev *wdev, + unsigned int link_id) +{ + WARN_ON(link_id && !wdev->valid_links); + WARN_ON(wdev->valid_links && + !(wdev->valid_links & BIT(link_id))); +} + +#define for_each_valid_link(wdev, link_id) \ + for (link_id = 0; \ + link_id < ((wdev)->valid_links ? ARRAY_SIZE((wdev)->links) : 1); \ + link_id++) \ + if (!(wdev)->valid_links || \ + ((wdev)->valid_links & BIT(link_id))) + /** * DOC: Utility functions * @@ -7882,12 +7959,14 @@ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition + * @link_id: the link ID for MLO, must be 0 for non-MLO * * Caller must acquire wdev_lock, therefore must only be called from sleepable * driver context! */ void cfg80211_ch_switch_notify(struct net_device *dev, - struct cfg80211_chan_def *chandef); + struct cfg80211_chan_def *chandef, + unsigned int link_id); /* * cfg80211_ch_switch_started_notify - notify channel switch start diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 98f905f16411..a9a2c9fef295 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -323,6 +323,17 @@ * Once the association is done, the driver cleans the FILS AAD data. */ +/** + * DOC: Multi-Link Operation + * + * In Multi-Link Operation, a connection between to MLDs utilizes multiple + * links. To use this in nl80211, various commands and responses now need + * to or will include the new %NL80211_ATTR_MLO_LINKS attribute. + * Additionally, various commands that need to operate on a specific link + * now need to be given the %NL80211_ATTR_MLO_LINK_ID attribute, e.g. to + * use %NL80211_CMD_START_AP or similar functions. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -1237,6 +1248,12 @@ * to describe the BSSID address of the AP and %NL80211_ATTR_TIMEOUT to * specify the timeout value. * + * @NL80211_CMD_ADD_LINK: Add a new link to an interface. The + * %NL80211_ATTR_MLO_LINK_ID attribute is used for the new link. + * @NL80211_CMD_REMOVE_LINK: Remove a link from an interface. This may come + * without %NL80211_ATTR_MLO_LINK_ID as an easy way to remove all links + * in preparation for e.g. roaming to a regular (non-MLO) AP. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1481,6 +1498,9 @@ enum nl80211_commands { NL80211_CMD_ASSOC_COMEBACK, + NL80211_CMD_ADD_LINK, + NL80211_CMD_REMOVE_LINK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2663,6 +2683,11 @@ enum nl80211_commands { * association request when used with NL80211_CMD_NEW_STATION). Can be set * only if %NL80211_STA_FLAG_WME is set. * + * @NL80211_ATTR_MLO_LINK_ID: A (u8) link ID for use with MLO, to be used with + * various commands that need a link ID to operate. + * @NL80211_ATTR_MLO_LINKS: A nested array of links, each containing some + * per-link information and a link ID. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3177,6 +3202,9 @@ enum nl80211_attrs { NL80211_ATTR_DISABLE_EHT, + NL80211_ATTR_MLO_LINKS, + NL80211_ATTR_MLO_LINK_ID, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 881efbfb96f6..362cac9e2135 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1342,7 +1342,8 @@ static void ieee80211_free_next_beacon(struct ieee80211_sub_if_data *sdata) sdata->u.ap.next_beacon = NULL; } -static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) +static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_sub_if_data *vlan; @@ -3049,6 +3050,7 @@ static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, const u8 *addr, const struct cfg80211_bitrate_mask *mask) { @@ -3390,7 +3392,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) if (err) return err; - cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); + cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef, 0); return 0; } @@ -3898,6 +3900,7 @@ unlock: static int ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); @@ -3958,6 +3961,7 @@ static int ieee80211_set_qos_map(struct wiphy *wiphy, static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 6d5ad71ef02c..e0a9b7d63071 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1314,7 +1314,7 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata) return; } - cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef); + cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef, 0); } void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success) diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 550ac9d827fe..e68923200018 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -1,4 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 +/* + * Parts of this file are + * Copyright (C) 2022 Intel Corporation + */ #include #include #include @@ -7,8 +11,9 @@ #include "rdev-ops.h" -int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool notify) +static int ___cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev, unsigned int link_id, + bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; @@ -22,15 +27,16 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; - if (!wdev->beacon_interval) + if (!wdev->links[link_id].ap.beacon_interval) return -ENOENT; - err = rdev_stop_ap(rdev, dev); + err = rdev_stop_ap(rdev, dev, link_id); if (!err) { wdev->conn_owner_nlportid = 0; - wdev->beacon_interval = 0; - memset(&wdev->chandef, 0, sizeof(wdev->chandef)); - wdev->ssid_len = 0; + wdev->links[link_id].ap.beacon_interval = 0; + memset(&wdev->links[link_id].ap.chandef, 0, + sizeof(wdev->links[link_id].ap.chandef)); + wdev->u.ap.ssid_len = 0; rdev_set_qos_map(rdev, dev, NULL); if (notify) nl80211_send_ap_stopped(wdev); @@ -46,14 +52,36 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, return err; } +int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev, int link_id, + bool notify) +{ + unsigned int link; + int ret = 0; + + if (link_id >= 0) + return ___cfg80211_stop_ap(rdev, dev, link_id, notify); + + for_each_valid_link(dev->ieee80211_ptr, link) { + int ret1 = ___cfg80211_stop_ap(rdev, dev, link, notify); + + if (ret1) + ret = ret1; + /* try the next one also if one errored */ + } + + return ret; +} + int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool notify) + struct net_device *dev, int link_id, + bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); - err = __cfg80211_stop_ap(rdev, dev, notify); + err = __cfg80211_stop_ap(rdev, dev, link_id, notify); wdev_unlock(wdev); return err; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index f74f176e0d9d..efc2de4bab57 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -672,14 +672,21 @@ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, * range of chandef. */ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, - struct ieee80211_channel *chan) + struct ieee80211_channel *chan, + bool primary_only) { int width; u32 freq; + if (!chandef->chan) + return false; + if (chandef->chan->center_freq == chan->center_freq) return true; + if (primary_only) + return false; + width = cfg80211_chandef_get_width(chandef); if (width <= 20) return false; @@ -704,23 +711,25 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev) { - bool active = false; + unsigned int link; ASSERT_WDEV_LOCK(wdev); - if (!wdev->chandef.chan) - return false; - switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - active = wdev->beacon_interval != 0; + for_each_valid_link(wdev, link) { + if (wdev->links[link].ap.beacon_interval) + return true; + } break; case NL80211_IFTYPE_ADHOC: - active = wdev->ssid_len != 0; + if (wdev->u.ibss.ssid_len) + return true; break; case NL80211_IFTYPE_MESH_POINT: - active = wdev->mesh_id_len != 0; + if (wdev->u.mesh.id_len) + return true; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_OCB: @@ -737,7 +746,35 @@ bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev) WARN_ON(1); } - return active; + return false; +} + +bool cfg80211_wdev_on_sub_chan(struct wireless_dev *wdev, + struct ieee80211_channel *chan, + bool primary_only) +{ + unsigned int link; + + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + for_each_valid_link(wdev, link) { + if (cfg80211_is_sub_chan(&wdev->links[link].ap.chandef, + chan, primary_only)) + return true; + } + break; + case NL80211_IFTYPE_ADHOC: + return cfg80211_is_sub_chan(&wdev->u.ibss.chandef, chan, + primary_only); + case NL80211_IFTYPE_MESH_POINT: + return cfg80211_is_sub_chan(&wdev->u.mesh.chandef, chan, + primary_only); + default: + break; + } + + return false; } static bool cfg80211_is_wiphy_oper_chan(struct wiphy *wiphy, @@ -752,7 +789,7 @@ static bool cfg80211_is_wiphy_oper_chan(struct wiphy *wiphy, continue; } - if (cfg80211_is_sub_chan(&wdev->chandef, chan)) { + if (cfg80211_wdev_on_sub_chan(wdev, chan, false)) { wdev_unlock(wdev); return true; } @@ -772,7 +809,8 @@ cfg80211_offchan_chain_is_active(struct cfg80211_registered_device *rdev, if (!cfg80211_chandef_valid(&rdev->background_radar_chandef)) return false; - return cfg80211_is_sub_chan(&rdev->background_radar_chandef, channel); + return cfg80211_is_sub_chan(&rdev->background_radar_chandef, channel, + false); } bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, @@ -1176,6 +1214,68 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_chandef_usable); +static bool cfg80211_ir_permissive_check_wdev(enum nl80211_iftype iftype, + struct wireless_dev *wdev, + struct ieee80211_channel *chan) +{ + struct ieee80211_channel *other_chan = NULL; + unsigned int link_id; + int r1, r2; + + for_each_valid_link(wdev, link_id) { + if (wdev->iftype == NL80211_IFTYPE_STATION && + wdev->links[link_id].client.current_bss) + other_chan = wdev->links[link_id].client.current_bss->pub.channel; + + /* + * If a GO already operates on the same GO_CONCURRENT channel, + * this one (maybe the same one) can beacon as well. We allow + * the operation even if the station we relied on with + * GO_CONCURRENT is disconnected now. But then we must make sure + * we're not outdoor on an indoor-only channel. + */ + if (iftype == NL80211_IFTYPE_P2P_GO && + wdev->iftype == NL80211_IFTYPE_P2P_GO && + wdev->links[link_id].ap.beacon_interval && + !(chan->flags & IEEE80211_CHAN_INDOOR_ONLY)) + other_chan = wdev->links[link_id].ap.chandef.chan; + + if (!other_chan) + continue; + + if (chan == other_chan) + return true; + + if (chan->band != NL80211_BAND_5GHZ && + chan->band != NL80211_BAND_6GHZ) + continue; + + r1 = cfg80211_get_unii(chan->center_freq); + r2 = cfg80211_get_unii(other_chan->center_freq); + + if (r1 != -EINVAL && r1 == r2) { + /* + * At some locations channels 149-165 are considered a + * bundle, but at other locations, e.g., Indonesia, + * channels 149-161 are considered a bundle while + * channel 165 is left out and considered to be in a + * different bundle. Thus, in case that there is a + * station interface connected to an AP on channel 165, + * it is assumed that channels 149-161 are allowed for + * GO operations. However, having a station interface + * connected to an AP on channels 149-161, does not + * allow GO operation on channel 165. + */ + if (chan->center_freq == 5825 && + other_chan->center_freq != 5825) + continue; + return true; + } + } + + return false; +} + /* * Check if the channel can be used under permissive conditions mandated by * some regulatory bodies, i.e., the channel is marked with @@ -1219,59 +1319,14 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, * the current registered device. */ list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { - struct ieee80211_channel *other_chan = NULL; - int r1, r2; + bool ret; wdev_lock(wdev); - if (wdev->iftype == NL80211_IFTYPE_STATION && - wdev->current_bss) - other_chan = wdev->current_bss->pub.channel; - - /* - * If a GO already operates on the same GO_CONCURRENT channel, - * this one (maybe the same one) can beacon as well. We allow - * the operation even if the station we relied on with - * GO_CONCURRENT is disconnected now. But then we must make sure - * we're not outdoor on an indoor-only channel. - */ - if (iftype == NL80211_IFTYPE_P2P_GO && - wdev->iftype == NL80211_IFTYPE_P2P_GO && - wdev->beacon_interval && - !(chan->flags & IEEE80211_CHAN_INDOOR_ONLY)) - other_chan = wdev->chandef.chan; + ret = cfg80211_ir_permissive_check_wdev(iftype, wdev, chan); wdev_unlock(wdev); - if (!other_chan) - continue; - - if (chan == other_chan) - return true; - - if (chan->band != NL80211_BAND_5GHZ && - chan->band != NL80211_BAND_6GHZ) - continue; - - r1 = cfg80211_get_unii(chan->center_freq); - r2 = cfg80211_get_unii(other_chan->center_freq); - - if (r1 != -EINVAL && r1 == r2) { - /* - * At some locations channels 149-165 are considered a - * bundle, but at other locations, e.g., Indonesia, - * channels 149-161 are considered a bundle while - * channel 165 is left out and considered to be in a - * different bundle. Thus, in case that there is a - * station interface connected to an AP on channel 165, - * it is assumed that channels 149-161 are allowed for - * GO operations. However, having a station interface - * connected to an AP on channels 149-161, does not - * allow GO operation on channel 165. - */ - if (chan->center_freq == 5825 && - other_chan->center_freq != 5825) - continue; - return true; - } + if (ret) + return ret; } return false; @@ -1374,3 +1429,24 @@ bool cfg80211_any_usable_channels(struct wiphy *wiphy, return false; } EXPORT_SYMBOL(cfg80211_any_usable_channels); + +struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, + unsigned int link_id) +{ + ASSERT_WDEV_LOCK(wdev); + + switch (wdev->iftype) { + case NL80211_IFTYPE_MESH_POINT: + return &wdev->u.mesh.chandef; + case NL80211_IFTYPE_ADHOC: + return &wdev->u.ibss.chandef; + case NL80211_IFTYPE_OCB: + return &wdev->u.ocb.chandef; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + return &wdev->links[link_id].ap.chandef; + default: + return NULL; + } +} +EXPORT_SYMBOL(wdev_chandef); diff --git a/net/wireless/core.c b/net/wireless/core.c index f08d4b3bb148..3e5d12040726 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1118,6 +1118,7 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + unsigned int link_id; ASSERT_RTNL(); lockdep_assert_held(&rdev->wiphy.mtx); @@ -1167,11 +1168,22 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, */ cfg80211_process_wdev_events(wdev); - if (WARN_ON(wdev->current_bss)) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - wdev->current_bss = NULL; + if (wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) { + for (link_id = 0; link_id < ARRAY_SIZE(wdev->links); link_id++) { + struct cfg80211_internal_bss *curbss; + + curbss = wdev->links[link_id].client.current_bss; + + if (WARN_ON(curbss)) { + cfg80211_unhold_bss(curbss); + cfg80211_put_bss(wdev->wiphy, &curbss->pub); + wdev->links[link_id].client.current_bss = NULL; + } + } } + + wdev->connected = false; } void cfg80211_unregister_wdev(struct wireless_dev *wdev) @@ -1233,7 +1245,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - __cfg80211_stop_ap(rdev, dev, true); + __cfg80211_stop_ap(rdev, dev, -1, true); break; case NL80211_IFTYPE_OCB: __cfg80211_leave_ocb(rdev, dev); @@ -1463,9 +1475,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, memcpy(&setup, &default_mesh_setup, sizeof(setup)); /* back compat only needed for mesh_id */ - setup.mesh_id = wdev->ssid; - setup.mesh_id_len = wdev->mesh_id_up_len; - if (wdev->mesh_id_up_len) + setup.mesh_id = wdev->u.mesh.id; + setup.mesh_id_len = wdev->u.mesh.id_up_len; + if (wdev->u.mesh.id_up_len) __cfg80211_join_mesh(rdev, dev, &setup, &default_mesh_config); diff --git a/net/wireless/core.h b/net/wireless/core.h index 5436ada91b1a..2c195067ddff 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -307,6 +307,7 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *rdev); void cfg80211_bss_age(struct cfg80211_registered_device *rdev, unsigned long age_secs); void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + unsigned int link, struct ieee80211_channel *channel); /* IBSS */ @@ -353,9 +354,11 @@ int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev, /* AP */ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool notify); + struct net_device *dev, int link, + bool notify); int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool notify); + struct net_device *dev, int link, + bool notify); /* MLME */ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, @@ -507,7 +510,11 @@ bool cfg80211_any_wiphy_oper_chan(struct wiphy *wiphy, bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev); bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, - struct ieee80211_channel *chan); + struct ieee80211_channel *chan, + bool primary_only); +bool cfg80211_wdev_on_sub_chan(struct wireless_dev *wdev, + struct ieee80211_channel *chan, + bool primary_only); static inline unsigned int elapsed_jiffies_msecs(unsigned long start) { diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 5d89eec2869a..4935f94d1acc 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -28,7 +28,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return; - if (!wdev->ssid_len) + if (!wdev->u.ibss.ssid_len) return; bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, NULL, 0, @@ -37,13 +37,13 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, if (WARN_ON(!bss)) return; - if (wdev->current_bss) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); + if (wdev->u.ibss.current_bss) { + cfg80211_unhold_bss(wdev->u.ibss.current_bss); + cfg80211_put_bss(wdev->wiphy, &wdev->u.ibss.current_bss->pub); } cfg80211_hold_bss(bss_from_pub(bss)); - wdev->current_bss = bss_from_pub(bss); + wdev->u.ibss.current_bss = bss_from_pub(bss); if (!(wdev->wiphy->flags & WIPHY_FLAG_HAS_STATIC_WEP)) cfg80211_upload_connect_keys(wdev); @@ -96,7 +96,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, lockdep_assert_held(&rdev->wiphy.mtx); ASSERT_WDEV_LOCK(wdev); - if (wdev->ssid_len) + if (wdev->u.ibss.ssid_len) return -EALREADY; if (!params->basic_rates) { @@ -131,7 +131,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, kfree_sensitive(wdev->connect_keys); wdev->connect_keys = connkeys; - wdev->chandef = params->chandef; + wdev->u.ibss.chandef = params->chandef; if (connkeys) { params->wep_keys = connkeys->params; params->wep_tx_key = connkeys->def; @@ -146,8 +146,8 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, return err; } - memcpy(wdev->ssid, params->ssid, params->ssid_len); - wdev->ssid_len = params->ssid_len; + memcpy(wdev->u.ibss.ssid, params->ssid, params->ssid_len); + wdev->u.ibss.ssid_len = params->ssid_len; return 0; } @@ -173,14 +173,14 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) for (i = 0; i < 6; i++) rdev_del_key(rdev, dev, i, false, NULL); - if (wdev->current_bss) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); + if (wdev->u.ibss.current_bss) { + cfg80211_unhold_bss(wdev->u.ibss.current_bss); + cfg80211_put_bss(wdev->wiphy, &wdev->u.ibss.current_bss->pub); } - wdev->current_bss = NULL; - wdev->ssid_len = 0; - memset(&wdev->chandef, 0, sizeof(wdev->chandef)); + wdev->u.ibss.current_bss = NULL; + wdev->u.ibss.ssid_len = 0; + memset(&wdev->u.ibss.chandef, 0, sizeof(wdev->u.ibss.chandef)); #ifdef CONFIG_CFG80211_WEXT if (!nowext) wdev->wext.ibss.ssid_len = 0; @@ -205,7 +205,7 @@ int __cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); - if (!wdev->ssid_len) + if (!wdev->u.ibss.ssid_len) return -ENOLINK; err = rdev_leave_ibss(rdev, dev); @@ -339,7 +339,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, wdev_lock(wdev); err = 0; - if (wdev->ssid_len) + if (wdev->u.ibss.ssid_len) err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); @@ -374,8 +374,8 @@ int cfg80211_ibss_wext_giwfreq(struct net_device *dev, return -EINVAL; wdev_lock(wdev); - if (wdev->current_bss) - chan = wdev->current_bss->pub.channel; + if (wdev->u.ibss.current_bss) + chan = wdev->u.ibss.current_bss->pub.channel; else if (wdev->wext.ibss.chandef.chan) chan = wdev->wext.ibss.chandef.chan; wdev_unlock(wdev); @@ -408,7 +408,7 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, wdev_lock(wdev); err = 0; - if (wdev->ssid_len) + if (wdev->u.ibss.ssid_len) err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); @@ -419,8 +419,8 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, if (len > 0 && ssid[len - 1] == '\0') len--; - memcpy(wdev->ssid, ssid, len); - wdev->wext.ibss.ssid = wdev->ssid; + memcpy(wdev->u.ibss.ssid, ssid, len); + wdev->wext.ibss.ssid = wdev->u.ibss.ssid; wdev->wext.ibss.ssid_len = len; wdev_lock(wdev); @@ -443,10 +443,10 @@ int cfg80211_ibss_wext_giwessid(struct net_device *dev, data->flags = 0; wdev_lock(wdev); - if (wdev->ssid_len) { + if (wdev->u.ibss.ssid_len) { data->flags = 1; - data->length = wdev->ssid_len; - memcpy(ssid, wdev->ssid, data->length); + data->length = wdev->u.ibss.ssid_len; + memcpy(ssid, wdev->u.ibss.ssid, data->length); } else if (wdev->wext.ibss.ssid && wdev->wext.ibss.ssid_len) { data->flags = 1; data->length = wdev->wext.ibss.ssid_len; @@ -494,7 +494,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, wdev_lock(wdev); err = 0; - if (wdev->ssid_len) + if (wdev->u.ibss.ssid_len) err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); @@ -527,8 +527,9 @@ int cfg80211_ibss_wext_giwap(struct net_device *dev, ap_addr->sa_family = ARPHRD_ETHER; wdev_lock(wdev); - if (wdev->current_bss) - memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); + if (wdev->u.ibss.current_bss) + memcpy(ap_addr->sa_data, wdev->u.ibss.current_bss->pub.bssid, + ETH_ALEN); else if (wdev->wext.ibss.bssid) memcpy(ap_addr->sa_data, wdev->wext.ibss.bssid, ETH_ALEN); else diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index e4e363138279..59a3c5c092b1 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -1,4 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 +/* + * Portions + * Copyright (C) 2022 Intel Corporation + */ #include #include #include @@ -114,7 +118,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, setup->is_secure) return -EOPNOTSUPP; - if (wdev->mesh_id_len) + if (wdev->u.mesh.id_len) return -EALREADY; if (!setup->mesh_id_len) @@ -125,7 +129,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!setup->chandef.chan) { /* if no channel explicitly given, use preset channel */ - setup->chandef = wdev->preset_chandef; + setup->chandef = wdev->u.mesh.preset_chandef; } if (!setup->chandef.chan) { @@ -209,10 +213,10 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, err = rdev_join_mesh(rdev, dev, conf, setup); if (!err) { - memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len); - wdev->mesh_id_len = setup->mesh_id_len; - wdev->chandef = setup->chandef; - wdev->beacon_interval = setup->beacon_interval; + memcpy(wdev->u.mesh.id, setup->mesh_id, setup->mesh_id_len); + wdev->u.mesh.id_len = setup->mesh_id_len; + wdev->u.mesh.chandef = setup->chandef; + wdev->u.mesh.beacon_interval = setup->beacon_interval; } return err; @@ -241,15 +245,15 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev, chandef->chan); if (!err) - wdev->chandef = *chandef; + wdev->u.mesh.chandef = *chandef; return err; } - if (wdev->mesh_id_len) + if (wdev->u.mesh.id_len) return -EBUSY; - wdev->preset_chandef = *chandef; + wdev->u.mesh.preset_chandef = *chandef; return 0; } @@ -267,15 +271,16 @@ int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, if (!rdev->ops->leave_mesh) return -EOPNOTSUPP; - if (!wdev->mesh_id_len) + if (!wdev->u.mesh.id_len) return -ENOTCONN; err = rdev_leave_mesh(rdev, dev); if (!err) { wdev->conn_owner_nlportid = 0; - wdev->mesh_id_len = 0; - wdev->beacon_interval = 0; - memset(&wdev->chandef, 0, sizeof(wdev->chandef)); + wdev->u.mesh.id_len = 0; + wdev->u.mesh.beacon_interval = 0; + memset(&wdev->u.mesh.chandef, 0, + sizeof(wdev->u.mesh.chandef)); rdev_set_qos_map(rdev, dev, NULL); cfg80211_sched_dfs_chan_update(rdev); } diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index c8155a483ec2..fab2d6206cdd 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -92,8 +92,7 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev, nl80211_send_deauth(rdev, wdev->netdev, buf, len, reconnect, GFP_KERNEL); - if (!wdev->current_bss || - !ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) + if (!wdev->connected || !ether_addr_equal(wdev->u.client.connected_addr, bssid)) return; __cfg80211_disconnected(wdev->netdev, NULL, 0, reason_code, from_ap); @@ -113,8 +112,8 @@ static void cfg80211_process_disassoc(struct wireless_dev *wdev, nl80211_send_disassoc(rdev, wdev->netdev, buf, len, reconnect, GFP_KERNEL); - if (WARN_ON(!wdev->current_bss || - !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + if (WARN_ON(!wdev->connected || + !ether_addr_equal(wdev->u.client.connected_addr, bssid))) return; __cfg80211_disconnected(wdev->netdev, NULL, 0, reason_code, from_ap); @@ -260,8 +259,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, if (!key || !key_len || key_idx < 0 || key_idx > 3) return -EINVAL; - if (wdev->current_bss && - ether_addr_equal(bssid, wdev->current_bss->pub.bssid)) + if (wdev->connected && + ether_addr_equal(bssid, wdev->u.client.connected_addr)) return -EALREADY; req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, @@ -322,9 +321,9 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); - if (wdev->current_bss && - (!req->prev_bssid || !ether_addr_equal(wdev->current_bss->pub.bssid, - req->prev_bssid))) + if (wdev->connected && + (!req->prev_bssid || + !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid))) return -EALREADY; cfg80211_oper_and_ht_capa(&req->ht_capa_mask, @@ -364,13 +363,13 @@ int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); if (local_state_change && - (!wdev->current_bss || - !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + (!wdev->connected || + !ether_addr_equal(wdev->u.client.connected_addr, bssid))) return 0; if (ether_addr_equal(wdev->disconnect_bssid, bssid) || - (wdev->current_bss && - ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + (wdev->connected && + ether_addr_equal(wdev->u.client.connected_addr, bssid))) wdev->conn_owner_nlportid = 0; return rdev_deauth(rdev, dev, &req); @@ -392,11 +391,12 @@ int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); - if (!wdev->current_bss) + if (!wdev->connected) return -ENOTCONN; - if (ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) - req.bss = &wdev->current_bss->pub; + if (ether_addr_equal(wdev->links[0].client.current_bss->pub.bssid, + bssid)) + req.bss = &wdev->links[0].client.current_bss->pub; else return -ENOTCONN; @@ -405,7 +405,7 @@ int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, return err; /* driver should have reported the disassoc */ - WARN_ON(wdev->current_bss); + WARN_ON(wdev->connected); return 0; } @@ -420,10 +420,10 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, if (!rdev->ops->deauth) return; - if (!wdev->current_bss) + if (!wdev->connected) return; - memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); + memcpy(bssid, wdev->u.client.connected_addr, ETH_ALEN); cfg80211_mlme_deauth(rdev, dev, bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); } @@ -676,28 +676,34 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: + /* + * check for IBSS DA must be done by driver as + * cfg80211 doesn't track the stations + */ + if (!wdev->u.ibss.current_bss || + !ether_addr_equal(wdev->u.ibss.current_bss->pub.bssid, + mgmt->bssid)) { + err = -ENOTCONN; + break; + } + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - if (!wdev->current_bss) { + if (!wdev->connected) { err = -ENOTCONN; break; } - if (!ether_addr_equal(wdev->current_bss->pub.bssid, + /* FIXME: MLD may address this differently */ + + if (!ether_addr_equal(wdev->u.client.connected_addr, mgmt->bssid)) { err = -ENOTCONN; break; } - /* - * check for IBSS DA must be done by driver as - * cfg80211 doesn't track the stations - */ - if (wdev->iftype == NL80211_IFTYPE_ADHOC) - break; - /* for station, check that DA is the AP */ - if (!ether_addr_equal(wdev->current_bss->pub.bssid, + if (!ether_addr_equal(wdev->u.client.connected_addr, mgmt->da)) { err = -ENOTCONN; break; @@ -743,12 +749,12 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, if (!ieee80211_is_action(mgmt->frame_control) || mgmt->u.action.category != WLAN_CATEGORY_PUBLIC) return -EINVAL; - if (!wdev->current_bss && + if (!wdev->connected && !wiphy_ext_feature_isset( &rdev->wiphy, NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA)) return -EINVAL; - if (wdev->current_bss && + if (wdev->connected && !wiphy_ext_feature_isset( &rdev->wiphy, NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED)) @@ -940,12 +946,16 @@ void cfg80211_cac_event(struct net_device *netdev, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); unsigned long timeout; + /* not yet supported */ + if (wdev->valid_links) + return; + trace_cfg80211_cac_event(netdev, event); if (WARN_ON(!wdev->cac_started && event != NL80211_RADAR_CAC_STARTED)) return; - if (WARN_ON(!wdev->chandef.chan)) + if (WARN_ON(!wdev->links[0].ap.chandef.chan)) return; switch (event) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 740b29481bc6..af31978fc9cc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -792,6 +792,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NL80211_EHT_MIN_CAPABILITY_LEN, NL80211_EHT_MAX_CAPABILITY_LEN), [NL80211_ATTR_DISABLE_EHT] = { .type = NLA_FLAG }, + [NL80211_ATTR_MLO_LINKS] = + NLA_POLICY_NESTED_ARRAY(nl80211_policy), + [NL80211_ATTR_MLO_LINK_ID] = + NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), }; /* policy for the key attributes */ @@ -1225,6 +1229,37 @@ static bool nl80211_put_txq_stats(struct sk_buff *msg, /* netlink command implementations */ +/** + * nl80211_link_id - return link ID + * @attrs: attributes to look at + * + * Returns: the link ID or 0 if not given + * + * Note this function doesn't do any validation of the link + * ID validity wrt. links that were actually added, so it must + * be called only from ops with %NL80211_FLAG_MLO_VALID_LINK_ID + * or if additional validation is done. + */ +static unsigned int nl80211_link_id(struct nlattr **attrs) +{ + struct nlattr *linkid = attrs[NL80211_ATTR_MLO_LINK_ID]; + + if (!linkid) + return 0; + + return nla_get_u8(linkid); +} + +static int nl80211_link_id_or_invalid(struct nlattr **attrs) +{ + struct nlattr *linkid = attrs[NL80211_ATTR_MLO_LINK_ID]; + + if (!linkid) + return -1; + + return nla_get_u8(linkid); +} + struct key_parse { struct key_params p; int idx; @@ -1496,11 +1531,15 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) case NL80211_IFTYPE_MESH_POINT: break; case NL80211_IFTYPE_ADHOC: + if (wdev->u.ibss.current_bss) + return 0; + return -ENOLINK; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - if (!wdev->current_bss) - return -ENOLINK; - break; + /* for MLO, require driver validation of the link ID */ + if (wdev->connected) + return 0; + return -ENOLINK; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_MONITOR: @@ -3232,12 +3271,14 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct genl_info *info) + struct genl_info *info, + int _link_id) { struct cfg80211_chan_def chandef; int result; enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR; struct wireless_dev *wdev = NULL; + int link_id = _link_id; if (dev) wdev = dev->ieee80211_ptr; @@ -3246,6 +3287,12 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, if (wdev) iftype = wdev->iftype; + if (link_id < 0) { + if (wdev && wdev->valid_links) + return -EINVAL; + link_id = 0; + } + result = nl80211_parse_chandef(rdev, info, &chandef); if (result) return result; @@ -3254,49 +3301,48 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, &chandef, - iftype)) { - result = -EINVAL; - break; - } - if (wdev->beacon_interval) { + iftype)) + return -EINVAL; + if (wdev->links[link_id].ap.beacon_interval) { + struct ieee80211_channel *cur_chan; + if (!dev || !rdev->ops->set_ap_chanwidth || !(rdev->wiphy.features & - NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE)) { - result = -EBUSY; - break; - } + NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE)) + return -EBUSY; /* Only allow dynamic channel width changes */ - if (chandef.chan != wdev->preset_chandef.chan) { - result = -EBUSY; - break; - } - result = rdev_set_ap_chanwidth(rdev, dev, &chandef); + cur_chan = wdev->links[link_id].ap.chandef.chan; + if (chandef.chan != cur_chan) + return -EBUSY; + + result = rdev_set_ap_chanwidth(rdev, dev, link_id, + &chandef); if (result) - break; + return result; + wdev->links[link_id].ap.chandef = chandef; + } else { + wdev->u.ap.preset_chandef = chandef; } - wdev->preset_chandef = chandef; - result = 0; - break; + return 0; case NL80211_IFTYPE_MESH_POINT: - result = cfg80211_set_mesh_channel(rdev, wdev, &chandef); - break; + return cfg80211_set_mesh_channel(rdev, wdev, &chandef); case NL80211_IFTYPE_MONITOR: - result = cfg80211_set_monitor_channel(rdev, &chandef); - break; + return cfg80211_set_monitor_channel(rdev, &chandef); default: - result = -EINVAL; + break; } - return result; + return -EINVAL; } static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + int link_id = nl80211_link_id_or_invalid(info->attrs); struct net_device *netdev = info->user_ptr[1]; - return __nl80211_set_channel(rdev, netdev, info); + return __nl80211_set_channel(rdev, netdev, info, link_id); } static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) @@ -3411,7 +3457,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = __nl80211_set_channel( rdev, nl80211_can_set_dev_channel(wdev) ? netdev : NULL, - info); + info, -1); if (result) goto out; } @@ -3696,15 +3742,13 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag nla_put_u8(msg, NL80211_ATTR_4ADDR, wdev->use_4addr)) goto nla_put_failure; - if (rdev->ops->get_channel) { - int ret; + if (rdev->ops->get_channel && !wdev->valid_links) { struct cfg80211_chan_def chandef = {}; + int ret; - ret = rdev_get_channel(rdev, wdev, &chandef); - if (ret == 0) { - if (nl80211_send_chandef(msg, &chandef)) - goto nla_put_failure; - } + ret = rdev_get_channel(rdev, wdev, 0, &chandef); + if (ret == 0 && nl80211_send_chandef(msg, &chandef)) + goto nla_put_failure; } if (rdev->ops->get_tx_power) { @@ -3721,27 +3765,24 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - if (wdev->ssid_len && - nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid)) + if (wdev->u.ap.ssid_len && + nla_put(msg, NL80211_ATTR_SSID, wdev->u.ap.ssid_len, + wdev->u.ap.ssid)) goto nla_put_failure_locked; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - case NL80211_IFTYPE_ADHOC: { - const struct element *ssid_elem; - - if (!wdev->current_bss) - break; - rcu_read_lock(); - ssid_elem = ieee80211_bss_get_elem(&wdev->current_bss->pub, - WLAN_EID_SSID); - if (ssid_elem && - nla_put(msg, NL80211_ATTR_SSID, ssid_elem->datalen, - ssid_elem->data)) - goto nla_put_failure_rcu_locked; - rcu_read_unlock(); + if (wdev->u.client.ssid_len && + nla_put(msg, NL80211_ATTR_SSID, wdev->u.client.ssid_len, + wdev->u.client.ssid)) + goto nla_put_failure_locked; + break; + case NL80211_IFTYPE_ADHOC: + if (wdev->u.ibss.ssid_len && + nla_put(msg, NL80211_ATTR_SSID, wdev->u.ibss.ssid_len, + wdev->u.ibss.ssid)) + goto nla_put_failure_locked; break; - } default: /* nothing */ break; @@ -3761,8 +3802,6 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag genlmsg_end(msg, hdr); return 0; - nla_put_failure_rcu_locked: - rcu_read_unlock(); nla_put_failure_locked: wdev_unlock(wdev); nla_put_failure: @@ -4014,10 +4053,11 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) wdev_lock(wdev); BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); - wdev->mesh_id_up_len = + wdev->u.mesh.id_up_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); - memcpy(wdev->ssid, nla_data(info->attrs[NL80211_ATTR_MESH_ID]), - wdev->mesh_id_up_len); + memcpy(wdev->u.mesh.id, + nla_data(info->attrs[NL80211_ATTR_MESH_ID]), + wdev->u.mesh.id_up_len); wdev_unlock(wdev); } @@ -4122,10 +4162,11 @@ static int _nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) wdev_lock(wdev); BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); - wdev->mesh_id_up_len = + wdev->u.mesh.id_up_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); - memcpy(wdev->ssid, nla_data(info->attrs[NL80211_ATTR_MESH_ID]), - wdev->mesh_id_up_len); + memcpy(wdev->u.mesh.id, + nla_data(info->attrs[NL80211_ATTR_MESH_ID]), + wdev->u.mesh.id_up_len); wdev_unlock(wdev); break; case NL80211_IFTYPE_NAN: @@ -4662,7 +4703,7 @@ static int nl80211_set_mac_acl(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; - if (!dev->ieee80211_ptr->beacon_interval) + if (!dev->ieee80211_ptr->links[0].ap.beacon_interval) return -EINVAL; acl = parse_acl_data(&rdev->wiphy, info); @@ -4818,14 +4859,24 @@ static void he_build_mcs_mask(u16 he_mcs_map, } } -static u16 he_get_txmcsmap(struct genl_info *info, +static u16 he_get_txmcsmap(struct genl_info *info, unsigned int link_id, const struct ieee80211_sta_he_cap *he_cap) { struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; - __le16 tx_mcs; + struct cfg80211_chan_def *chandef; + __le16 tx_mcs; - switch (wdev->chandef.width) { + chandef = wdev_chandef(wdev, link_id); + if (!chandef) { + /* + * This is probably broken, but we never maintained + * a chandef in these cases, so it always was. + */ + return le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_80); + } + + switch (chandef->width) { case NL80211_CHAN_WIDTH_80P80: tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80; break; @@ -4836,6 +4887,7 @@ static u16 he_get_txmcsmap(struct genl_info *info, tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80; break; } + return le16_to_cpu(tx_mcs); } @@ -4843,7 +4895,8 @@ static bool he_set_mcs_mask(struct genl_info *info, struct wireless_dev *wdev, struct ieee80211_supported_band *sband, struct nl80211_txrate_he *txrate, - u16 mcs[NL80211_HE_NSS_MAX]) + u16 mcs[NL80211_HE_NSS_MAX], + unsigned int link_id) { const struct ieee80211_sta_he_cap *he_cap; u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {}; @@ -4856,7 +4909,7 @@ static bool he_set_mcs_mask(struct genl_info *info, memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX); - tx_mcs_map = he_get_txmcsmap(info, he_cap); + tx_mcs_map = he_get_txmcsmap(info, link_id, he_cap); /* Build he_mcs_mask from HE capabilities */ he_build_mcs_mask(tx_mcs_map, tx_mcs_mask); @@ -4876,7 +4929,8 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, enum nl80211_attrs attr, struct cfg80211_bitrate_mask *mask, struct net_device *dev, - bool default_all_enabled) + bool default_all_enabled, + unsigned int link_id) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -4913,7 +4967,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (!he_cap) continue; - he_tx_mcs_map = he_get_txmcsmap(info, he_cap); + he_tx_mcs_map = he_get_txmcsmap(info, link_id, he_cap); he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs); mask->control[i].he_gi = 0xFF; @@ -4978,7 +5032,8 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (tb[NL80211_TXRATE_HE] && !he_set_mcs_mask(info, wdev, sband, nla_data(tb[NL80211_TXRATE_HE]), - mask->control[band].he_mcs)) + mask->control[band].he_mcs, + link_id)) return -EINVAL; if (tb[NL80211_TXRATE_HE_GI]) @@ -5215,6 +5270,8 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, memset(bcn, 0, sizeof(*bcn)); + bcn->link_id = nl80211_link_id(attrs); + if (attrs[NL80211_ATTR_BEACON_HEAD]) { bcn->head = nla_data(attrs[NL80211_ATTR_BEACON_HEAD]); bcn->head_len = nla_len(attrs[NL80211_ATTR_BEACON_HEAD]); @@ -5468,22 +5525,20 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, struct cfg80211_ap_settings *params) { struct wireless_dev *wdev; - bool ret = false; list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO) continue; - if (!wdev->preset_chandef.chan) + if (!wdev->u.ap.preset_chandef.chan) continue; - params->chandef = wdev->preset_chandef; - ret = true; - break; + params->chandef = wdev->u.ap.preset_chandef; + return true; } - return ret; + return false; } static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, @@ -5541,6 +5596,7 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_ap_settings *params; @@ -5553,7 +5609,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->start_ap) return -EOPNOTSUPP; - if (wdev->beacon_interval) + if (wdev->links[link_id].ap.beacon_interval) return -EALREADY; /* these are required for START_AP */ @@ -5595,6 +5651,18 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = -EINVAL; goto out; } + + if (wdev->u.ap.ssid_len && + (wdev->u.ap.ssid_len != params->ssid_len || + memcmp(wdev->u.ap.ssid, params->ssid, params->ssid_len))) { + /* require identical SSID for MLO */ + err = -EINVAL; + goto out; + } + } else if (wdev->valid_links) { + /* require SSID for MLO */ + err = -EINVAL; + goto out; } if (info->attrs[NL80211_ATTR_HIDDEN_SSID]) @@ -5662,8 +5730,12 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_chandef(rdev, info, ¶ms->chandef); if (err) goto out; - } else if (wdev->preset_chandef.chan) { - params->chandef = wdev->preset_chandef; + } else if (wdev->valid_links) { + /* with MLD need to specify the channel configuration */ + err = -EINVAL; + goto out; + } else if (wdev->u.ap.preset_chandef.chan) { + params->chandef = wdev->u.ap.preset_chandef; } else if (!nl80211_get_ap_channel(rdev, params)) { err = -EINVAL; goto out; @@ -5679,7 +5751,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, ¶ms->beacon_rate, - dev, false); + dev, false, link_id); if (err) goto out; @@ -5779,19 +5851,28 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params->flags |= NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; wdev_lock(wdev); + if (wdev->conn_owner_nlportid && + info->attrs[NL80211_ATTR_SOCKET_OWNER] && + wdev->conn_owner_nlportid != info->snd_portid) { + err = -EINVAL; + goto out_unlock; + } + + /* FIXME: validate MLO/link-id against driver capabilities */ + err = rdev_start_ap(rdev, dev, params); if (!err) { - wdev->preset_chandef = params->chandef; - wdev->beacon_interval = params->beacon_interval; - wdev->chandef = params->chandef; - wdev->ssid_len = params->ssid_len; - memcpy(wdev->ssid, params->ssid, wdev->ssid_len); + wdev->links[link_id].ap.beacon_interval = params->beacon_interval; + wdev->links[link_id].ap.chandef = params->chandef; + wdev->u.ap.ssid_len = params->ssid_len; + memcpy(wdev->u.ap.ssid, params->ssid, + params->ssid_len); if (info->attrs[NL80211_ATTR_SOCKET_OWNER]) wdev->conn_owner_nlportid = info->snd_portid; } +out_unlock: wdev_unlock(wdev); - out: kfree(params->acl); kfree(params->beacon.mbssid_ies); @@ -5807,6 +5888,7 @@ out: static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_beacon_data params; @@ -5819,7 +5901,7 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->change_beacon) return -EOPNOTSUPP; - if (!wdev->beacon_interval) + if (!wdev->links[link_id].ap.beacon_interval) return -EINVAL; err = nl80211_parse_beacon(rdev, info->attrs, ¶ms); @@ -5838,9 +5920,10 @@ out: static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; - return cfg80211_stop_ap(rdev, dev, false); + return cfg80211_stop_ap(rdev, dev, link_id, false); } static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { @@ -7590,7 +7673,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, wdev_lock(wdev); /* If not connected, get default parameters */ - if (!wdev->mesh_id_len) + if (!wdev->u.mesh.id_len) memcpy(&cur_params, &default_mesh_config, sizeof(cur_params)); else err = rdev_get_mesh_config(rdev, dev, &cur_params); @@ -7971,7 +8054,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, return err; wdev_lock(wdev); - if (!wdev->mesh_id_len) + if (!wdev->u.mesh.id_len) err = -ENOLINK; if (!err) @@ -8463,14 +8546,44 @@ int nl80211_parse_random_mac(struct nlattr **attrs, return 0; } -static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) +static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev, + struct ieee80211_channel *chan) { + unsigned int link_id; + bool all_ok = true; + ASSERT_WDEV_LOCK(wdev); if (!cfg80211_beaconing_iface_active(wdev)) return true; - if (!(wdev->chandef.chan->flags & IEEE80211_CHAN_RADAR)) + /* + * FIXME: check if we have a free HW resource/link for chan + * + * This, as well as the FIXME below, requires knowing the link + * capabilities of the hardware. + */ + + /* we cannot leave radar channels */ + for_each_valid_link(wdev, link_id) { + struct cfg80211_chan_def *chandef; + + chandef = wdev_chandef(wdev, link_id); + if (!chandef) + continue; + + /* + * FIXME: don't require all_ok, but rather check only the + * correct HW resource/link onto which 'chan' falls, + * as only that link leaves the channel for doing + * the off-channel operation. + */ + + if (chandef->chan->flags & IEEE80211_CHAN_RADAR) + all_ok = false; + } + + if (all_ok) return true; return regulatory_pre_cac_allowed(wdev->wiphy); @@ -8553,7 +8666,7 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, int err; if (!(wiphy->features & randomness_flag) || - (wdev && wdev->current_bss)) + (wdev && wdev->connected)) return -EOPNOTSUPP; err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask); @@ -8690,17 +8803,14 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->n_channels = i; wdev_lock(wdev); - if (!cfg80211_off_channel_oper_allowed(wdev)) { - struct ieee80211_channel *chan; + for (i = 0; i < request->n_channels; i++) { + struct ieee80211_channel *chan = request->channels[i]; - if (request->n_channels != 1) { - wdev_unlock(wdev); - err = -EBUSY; - goto out_free; - } + /* if we can go off-channel to the target channel we're good */ + if (cfg80211_off_channel_oper_allowed(wdev, chan)) + continue; - chan = request->channels[0]; - if (chan->center_freq != wdev->chandef.chan->center_freq) { + if (!cfg80211_wdev_on_sub_chan(wdev, chan, true)) { wdev_unlock(wdev); err = -EBUSY; goto out_free; @@ -9445,7 +9555,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms); if (!err) { - wdev->chandef = chandef; + wdev->links[0].ap.chandef = chandef; wdev->cac_started = true; wdev->cac_start_time = jiffies; wdev->cac_time_ms = cac_time_ms; @@ -9513,6 +9623,7 @@ static int nl80211_notify_radar_detection(struct sk_buff *skb, static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_csa_settings params; @@ -9539,15 +9650,15 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) need_handle_dfs_flag = false; /* useless if AP is not running */ - if (!wdev->beacon_interval) + if (!wdev->links[link_id].ap.beacon_interval) return -ENOTCONN; break; case NL80211_IFTYPE_ADHOC: - if (!wdev->ssid_len) + if (!wdev->u.ibss.ssid_len) return -ENOTCONN; break; case NL80211_IFTYPE_MESH_POINT: - if (!wdev->mesh_id_len) + if (!wdev->u.mesh.id_len) return -ENOTCONN; break; default: @@ -9718,6 +9829,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, { struct cfg80211_bss *res = &intbss->pub; const struct cfg80211_bss_ies *ies; + unsigned int link_id; void *hdr; struct nlattr *bss; @@ -9822,13 +9934,15 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, switch (wdev->iftype) { case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - if (intbss == wdev->current_bss && - nla_put_u32(msg, NL80211_BSS_STATUS, - NL80211_BSS_STATUS_ASSOCIATED)) - goto nla_put_failure; + for_each_valid_link(wdev, link_id) { + if (intbss == wdev->links[link_id].client.current_bss && + nla_put_u32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_ASSOCIATED)) + goto nla_put_failure; + } break; case NL80211_IFTYPE_ADHOC: - if (intbss == wdev->current_bss && + if (intbss == wdev->u.ibss.current_bss && nla_put_u32(msg, NL80211_BSS_STATUS, NL80211_BSS_STATUS_IBSS_JOINED)) goto nla_put_failure; @@ -11362,7 +11476,7 @@ static int nl80211_update_connect_params(struct sk_buff *skb, } wdev_lock(dev->ieee80211_ptr); - if (!wdev->current_bss) + if (!wdev->connected) ret = -ENOLINK; else ret = rdev_update_connect_params(rdev, dev, &connect, changed); @@ -11575,9 +11689,9 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + unsigned int link_id = nl80211_link_id(info->attrs); struct wireless_dev *wdev = info->user_ptr[1]; struct cfg80211_chan_def chandef; - const struct cfg80211_chan_def *compat_chandef; struct sk_buff *msg; void *hdr; u64 cookie; @@ -11607,10 +11721,22 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, return err; wdev_lock(wdev); - if (!cfg80211_off_channel_oper_allowed(wdev) && - !cfg80211_chandef_identical(&wdev->chandef, &chandef)) { - compat_chandef = cfg80211_chandef_compatible(&wdev->chandef, - &chandef); + if (!cfg80211_off_channel_oper_allowed(wdev, chandef.chan)) { + const struct cfg80211_chan_def *oper_chandef, *compat_chandef; + + oper_chandef = wdev_chandef(wdev, link_id); + + if (WARN_ON(!oper_chandef)) { + /* cannot happen since we must beacon to get here */ + WARN_ON(1); + wdev_unlock(wdev); + return -EBUSY; + } + + /* note: returns first one if identical chandefs */ + compat_chandef = cfg80211_chandef_compatible(&chandef, + oper_chandef); + if (compat_chandef != &chandef) { wdev_unlock(wdev); return -EBUSY; @@ -11672,6 +11798,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_bitrate_mask mask; + unsigned int link_id = nl80211_link_id(info->attrs); struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -11683,11 +11810,11 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, wdev_lock(wdev); err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, &mask, - dev, true); + dev, true, link_id); if (err) goto out; - err = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + err = rdev_set_bitrate_mask(rdev, dev, link_id, NULL, &mask); out: wdev_unlock(wdev); return err; @@ -11812,7 +11939,8 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) return -EINVAL; wdev_lock(wdev); - if (params.offchan && !cfg80211_off_channel_oper_allowed(wdev)) { + if (params.offchan && + !cfg80211_off_channel_oper_allowed(wdev, chandef.chan)) { wdev_unlock(wdev); return -EBUSY; } @@ -12030,12 +12158,13 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, * connection is established and enough beacons received to calculate * the average. */ - if (!wdev->cqm_config->last_rssi_event_value && wdev->current_bss && + if (!wdev->cqm_config->last_rssi_event_value && + wdev->links[0].client.current_bss && rdev->ops->get_station) { struct station_info sinfo = {}; u8 *mac_addr; - mac_addr = wdev->current_bss->pub.bssid; + mac_addr = wdev->links[0].client.current_bss->pub.bssid; err = rdev_get_station(rdev, dev, mac_addr, &sinfo); if (err) @@ -12298,7 +12427,7 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, &setup.beacon_rate, - dev, false); + dev, false, 0); if (err) return err; @@ -13268,7 +13397,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) rekey_data.akm = nla_get_u32(tb[NL80211_REKEY_DATA_AKM]); wdev_lock(wdev); - if (!wdev->current_bss) { + if (!wdev->connected) { err = -ENOTCONN; goto out; } @@ -14537,7 +14666,7 @@ static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info) switch (wdev->iftype) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - if (wdev->current_bss) + if (wdev->connected) break; err = -ENOTCONN; goto out; @@ -14710,13 +14839,13 @@ static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info) return -EINVAL; wdev_lock(wdev); - if (!wdev->current_bss) { + if (!wdev->connected) { ret = -ENOTCONN; goto out; } pmk_conf.aa = nla_data(info->attrs[NL80211_ATTR_MAC]); - if (memcmp(pmk_conf.aa, wdev->current_bss->pub.bssid, ETH_ALEN)) { + if (memcmp(pmk_conf.aa, wdev->u.client.connected_addr, ETH_ALEN)) { ret = -EINVAL; goto out; } @@ -14844,9 +14973,13 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_MESH_POINT: break; case NL80211_IFTYPE_ADHOC: + if (wdev->u.ibss.current_bss) + break; + err = -ENOTCONN; + goto out; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - if (wdev->current_bss) + if (wdev->connected) break; err = -ENOTCONN; goto out; @@ -14882,12 +15015,14 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb, struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_ftm_responder_stats ftm_stats = {}; + unsigned int link_id = nl80211_link_id(info->attrs); struct sk_buff *msg; void *hdr; struct nlattr *ftm_stats_attr; int err; - if (wdev->iftype != NL80211_IFTYPE_AP || !wdev->beacon_interval) + if (wdev->iftype != NL80211_IFTYPE_AP || + !wdev->links[link_id].ap.beacon_interval) return -EOPNOTSUPP; err = rdev_get_ftm_responder_stats(rdev, dev, &ftm_stats); @@ -15017,7 +15152,8 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info) static int parse_tid_conf(struct cfg80211_registered_device *rdev, struct nlattr *attrs[], struct net_device *dev, struct cfg80211_tid_cfg *tid_conf, - struct genl_info *info, const u8 *peer) + struct genl_info *info, const u8 *peer, + unsigned int link_id) { struct netlink_ext_ack *extack = info->extack; u64 mask; @@ -15092,7 +15228,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, attr = NL80211_TID_CONFIG_ATTR_TX_RATE; err = nl80211_parse_tx_bitrate_mask(info, attrs, attr, &tid_conf->txrate_mask, dev, - true); + true, link_id); if (err) return err; @@ -15119,6 +15255,7 @@ static int nl80211_set_tid_config(struct sk_buff *skb, { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct nlattr *attrs[NL80211_TID_CONFIG_ATTR_MAX + 1]; + unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct cfg80211_tid_config *tid_config; struct nlattr *tid; @@ -15156,7 +15293,7 @@ static int nl80211_set_tid_config(struct sk_buff *skb, ret = parse_tid_conf(rdev, attrs, dev, &tid_config->tid_conf[conf_idx], - info, tid_config->peer); + info, tid_config->peer, link_id); if (ret) goto bad_tid_conf; @@ -15295,6 +15432,62 @@ static int nl80211_set_fils_aad(struct sk_buff *skb, return rdev_set_fils_aad(rdev, dev, &fils_aad); } +static int nl80211_add_link(struct sk_buff *skb, struct genl_info *info) +{ + unsigned int link_id = nl80211_link_id(info->attrs); + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (!(wdev->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO)) + return -EINVAL; + + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + break; + default: + return -EINVAL; + } + + if (!info->attrs[NL80211_ATTR_MAC] || + !is_valid_ether_addr(nla_data(info->attrs[NL80211_ATTR_MAC]))) + return -EINVAL; + + wdev_lock(wdev); + wdev->valid_links |= BIT(link_id); + ether_addr_copy(wdev->links[link_id].addr, + nla_data(info->attrs[NL80211_ATTR_MAC])); + wdev_unlock(wdev); + + return 0; +} + +static int nl80211_remove_link(struct sk_buff *skb, struct genl_info *info) +{ + unsigned int link_id = nl80211_link_id(info->attrs); + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + + /* cannot remove if there's no link */ + if (!info->attrs[NL80211_ATTR_MLO_LINK_ID]) + return -EINVAL; + + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + break; + default: + return -EINVAL; + } + + /* FIXME: stop the link operations first */ + + wdev_lock(wdev); + wdev->valid_links &= ~BIT(link_id); + eth_zero_addr(wdev->links[link_id].addr); + wdev_unlock(wdev); + + return 0; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -15307,6 +15500,8 @@ static int nl80211_set_fils_aad(struct sk_buff *skb, NL80211_FLAG_CHECK_NETDEV_UP) #define NL80211_FLAG_CLEAR_SKB 0x20 #define NL80211_FLAG_NO_WIPHY_MTX 0x40 +#define NL80211_FLAG_MLO_VALID_LINK_ID 0x80 +#define NL80211_FLAG_MLO_UNSUPPORTED 0x100 #define INTERNAL_FLAG_SELECTORS(__sel) \ SELECTOR(__sel, NONE, 0) /* must be first */ \ @@ -15316,6 +15511,12 @@ static int nl80211_set_fils_aad(struct sk_buff *skb, NL80211_FLAG_NEED_WDEV) \ SELECTOR(__sel, NETDEV, \ NL80211_FLAG_NEED_NETDEV) \ + SELECTOR(__sel, NETDEV_LINK, \ + NL80211_FLAG_NEED_NETDEV | \ + NL80211_FLAG_MLO_VALID_LINK_ID) \ + SELECTOR(__sel, NETDEV_NO_MLO, \ + NL80211_FLAG_NEED_NETDEV | \ + NL80211_FLAG_MLO_UNSUPPORTED) \ SELECTOR(__sel, WIPHY_RTNL, \ NL80211_FLAG_NEED_WIPHY | \ NL80211_FLAG_NEED_RTNL) \ @@ -15331,14 +15532,31 @@ static int nl80211_set_fils_aad(struct sk_buff *skb, NL80211_FLAG_NEED_RTNL) \ SELECTOR(__sel, NETDEV_UP, \ NL80211_FLAG_NEED_NETDEV_UP) \ + SELECTOR(__sel, NETDEV_UP_LINK, \ + NL80211_FLAG_NEED_NETDEV_UP | \ + NL80211_FLAG_MLO_VALID_LINK_ID) \ + SELECTOR(__sel, NETDEV_UP_NO_MLO, \ + NL80211_FLAG_NEED_NETDEV_UP | \ + NL80211_FLAG_MLO_UNSUPPORTED) \ + SELECTOR(__sel, NETDEV_UP_NO_MLO_CLEAR, \ + NL80211_FLAG_NEED_NETDEV_UP | \ + NL80211_FLAG_CLEAR_SKB | \ + NL80211_FLAG_MLO_UNSUPPORTED) \ SELECTOR(__sel, NETDEV_UP_NOTMX, \ NL80211_FLAG_NEED_NETDEV_UP | \ NL80211_FLAG_NO_WIPHY_MTX) \ + SELECTOR(__sel, NETDEV_UP_NOTMX_NOMLO, \ + NL80211_FLAG_NEED_NETDEV_UP | \ + NL80211_FLAG_NO_WIPHY_MTX | \ + NL80211_FLAG_MLO_UNSUPPORTED) \ SELECTOR(__sel, NETDEV_UP_CLEAR, \ NL80211_FLAG_NEED_NETDEV_UP | \ NL80211_FLAG_CLEAR_SKB) \ SELECTOR(__sel, WDEV_UP, \ NL80211_FLAG_NEED_WDEV_UP) \ + SELECTOR(__sel, WDEV_UP_LINK, \ + NL80211_FLAG_NEED_WDEV_UP | \ + NL80211_FLAG_MLO_VALID_LINK_ID) \ SELECTOR(__sel, WDEV_UP_RTNL, \ NL80211_FLAG_NEED_WDEV_UP | \ NL80211_FLAG_NEED_RTNL) \ @@ -15362,9 +15580,10 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = NULL; - struct wireless_dev *wdev; - struct net_device *dev; + struct wireless_dev *wdev = NULL; + struct net_device *dev = NULL; u32 internal_flags; + int err; if (WARN_ON(ops->internal_flags >= ARRAY_SIZE(nl80211_internal_flags))) return -EINVAL; @@ -15375,8 +15594,8 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, if (internal_flags & NL80211_FLAG_NEED_WIPHY) { rdev = cfg80211_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { - rtnl_unlock(); - return PTR_ERR(rdev); + err = PTR_ERR(rdev); + goto out_unlock; } info->user_ptr[0] = rdev; } else if (internal_flags & NL80211_FLAG_NEED_NETDEV || @@ -15384,17 +15603,18 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, wdev = __cfg80211_wdev_from_attrs(NULL, genl_info_net(info), info->attrs); if (IS_ERR(wdev)) { - rtnl_unlock(); - return PTR_ERR(wdev); + err = PTR_ERR(wdev); + goto out_unlock; } dev = wdev->netdev; + dev_hold(dev); rdev = wiphy_to_rdev(wdev->wiphy); if (internal_flags & NL80211_FLAG_NEED_NETDEV) { if (!dev) { - rtnl_unlock(); - return -EINVAL; + err = -EINVAL; + goto out_unlock; } info->user_ptr[1] = dev; @@ -15404,14 +15624,44 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, if (internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && !wdev_running(wdev)) { - rtnl_unlock(); - return -ENETDOWN; + err = -ENETDOWN; + goto out_unlock; } - dev_hold(dev); info->user_ptr[0] = rdev; } + if (internal_flags & NL80211_FLAG_MLO_VALID_LINK_ID) { + struct nlattr *link_id = info->attrs[NL80211_ATTR_MLO_LINK_ID]; + + if (!wdev) { + err = -EINVAL; + goto out_unlock; + } + + /* MLO -> require valid link ID */ + if (wdev->valid_links && + (!link_id || + !(wdev->valid_links & BIT(nla_get_u16(link_id))))) { + err = -EINVAL; + goto out_unlock; + } + + /* non-MLO -> no link ID attribute accepted */ + if (!wdev->valid_links && link_id) { + err = -EINVAL; + goto out_unlock; + } + } + + if (internal_flags & NL80211_FLAG_MLO_UNSUPPORTED) { + if (info->attrs[NL80211_ATTR_MLO_LINK_ID] || + (wdev && wdev->valid_links)) { + err = -EINVAL; + goto out_unlock; + } + } + if (rdev && !(internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) { wiphy_lock(&rdev->wiphy); /* we keep the mutex locked until post_doit */ @@ -15421,6 +15671,10 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, rtnl_unlock(); return 0; +out_unlock: + rtnl_unlock(); + dev_put(dev); + return err; } static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, @@ -15636,6 +15890,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_key, .flags = GENL_UNS_ADMIN_PERM, + /* cannot use NL80211_FLAG_MLO_VALID_LINK_ID, depends on key */ .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_CLEAR_SKB), }, @@ -15659,21 +15914,24 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_set_beacon, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_START_AP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_start_ap, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_STOP_AP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_stop_ap, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_GET_STATION, @@ -15939,7 +16197,9 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_remain_on_channel, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_WDEV_UP), + /* FIXME: requiring a link ID here is probably not good */ + .internal_flags = IFLAGS(NL80211_FLAG_NEED_WDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, @@ -15953,7 +16213,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_tx_bitrate_mask, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_REGISTER_FRAME, @@ -16002,7 +16263,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_channel, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_JOIN_MESH, @@ -16163,7 +16425,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_mac_acl, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_MLO_UNSUPPORTED), }, { .cmd = NL80211_CMD_RADAR_DETECT, @@ -16171,7 +16434,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_start_radar_detection, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NO_WIPHY_MTX), + NL80211_FLAG_NO_WIPHY_MTX | + NL80211_FLAG_MLO_UNSUPPORTED), }, { .cmd = NL80211_CMD_GET_PROTOCOL_FEATURES, @@ -16217,7 +16481,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_channel_switch, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_VENDOR, @@ -16240,7 +16505,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_add_tx_ts, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_UNSUPPORTED), }, { .cmd = NL80211_CMD_DEL_TX_TS, @@ -16301,7 +16567,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .cmd = NL80211_CMD_GET_FTM_RESPONDER_STATS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_ftm_responder_stats, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_PEER_MEASUREMENT_START, @@ -16333,7 +16600,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .cmd = NL80211_CMD_SET_TID_CONFIG, .doit = nl80211_set_tid_config, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_SET_SAR_SPECS, @@ -16357,6 +16625,19 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, + { + .cmd = NL80211_CMD_ADD_LINK, + .doit = nl80211_add_link, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + }, + { + .cmd = NL80211_CMD_REMOVE_LINK, + .doit = nl80211_remove_link, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), + }, }; static struct genl_family nl80211_fam __ro_after_init = { @@ -17984,23 +18265,37 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, } void cfg80211_ch_switch_notify(struct net_device *dev, - struct cfg80211_chan_def *chandef) + struct cfg80211_chan_def *chandef, + unsigned int link_id) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); ASSERT_WDEV_LOCK(wdev); + WARN_INVALID_LINK_ID(wdev, link_id); - trace_cfg80211_ch_switch_notify(dev, chandef); - - wdev->chandef = *chandef; - wdev->preset_chandef = *chandef; + trace_cfg80211_ch_switch_notify(dev, chandef, link_id); - if ((wdev->iftype == NL80211_IFTYPE_STATION || - wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) && - !WARN_ON(!wdev->current_bss)) - cfg80211_update_assoc_bss_entry(wdev, chandef->chan); + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: + if (!WARN_ON(!wdev->links[link_id].client.current_bss)) + cfg80211_update_assoc_bss_entry(wdev, link_id, + chandef->chan); + break; + case NL80211_IFTYPE_MESH_POINT: + wdev->u.mesh.chandef = *chandef; + wdev->u.mesh.preset_chandef = *chandef; + break; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + wdev->links[link_id].ap.chandef = *chandef; + break; + default: + WARN_ON(1); + break; + } cfg80211_sched_dfs_chan_update(rdev); diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c index 2d26a6d980bf..27a1732264f9 100644 --- a/net/wireless/ocb.c +++ b/net/wireless/ocb.c @@ -4,6 +4,7 @@ * * Copyright: (c) 2014 Czech Technical University in Prague * (c) 2014 Volkswagen Group Research + * Copyright (C) 2022 Intel Corporation * Author: Rostislav Lisovy * Funded by: Volkswagen Group Research */ @@ -34,7 +35,7 @@ int __cfg80211_join_ocb(struct cfg80211_registered_device *rdev, err = rdev_join_ocb(rdev, dev, setup); if (!err) - wdev->chandef = setup->chandef; + wdev->u.ocb.chandef = setup->chandef; return err; } @@ -69,7 +70,7 @@ int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev, err = rdev_leave_ocb(rdev, dev); if (!err) - memset(&wdev->chandef, 0, sizeof(wdev->chandef)); + memset(&wdev->u.ocb.chandef, 0, sizeof(wdev->u.ocb.chandef)); return err; } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 439bcf52369c..d2300eff03ae 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions of this file + * Copyright(c) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2018, 2021-2022 Intel Corporation + */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS @@ -172,11 +177,11 @@ static inline int rdev_change_beacon(struct cfg80211_registered_device *rdev, } static inline int rdev_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, unsigned int link_id) { int ret; - trace_rdev_stop_ap(&rdev->wiphy, dev); - ret = rdev->ops->stop_ap(&rdev->wiphy, dev); + trace_rdev_stop_ap(&rdev->wiphy, dev, link_id); + ret = rdev->ops->stop_ap(&rdev->wiphy, dev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -651,12 +656,14 @@ static inline int rdev_testmode_dump(struct cfg80211_registered_device *rdev, static inline int rdev_set_bitrate_mask(struct cfg80211_registered_device *rdev, - struct net_device *dev, const u8 *peer, + struct net_device *dev, unsigned int link_id, + const u8 *peer, const struct cfg80211_bitrate_mask *mask) { int ret; - trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, peer, mask); - ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, peer, mask); + trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); + ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, link_id, + peer, mask); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -944,12 +951,13 @@ static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, static inline int rdev_get_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; - trace_rdev_get_channel(&rdev->wiphy, wdev); - ret = rdev->ops->get_channel(&rdev->wiphy, wdev, chandef); + trace_rdev_get_channel(&rdev->wiphy, wdev, link_id); + ret = rdev->ops->get_channel(&rdev->wiphy, wdev, link_id, chandef); trace_rdev_return_chandef(&rdev->wiphy, ret, chandef); return ret; @@ -1107,12 +1115,14 @@ static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev, static inline int rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev, - struct net_device *dev, struct cfg80211_chan_def *chandef) + struct net_device *dev, + unsigned int link_id, + struct cfg80211_chan_def *chandef) { int ret; - trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, chandef); - ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, chandef); + trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); + ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 58e83ce642ad..c7383ede794f 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -5,7 +5,7 @@ * Copyright 2008-2011 Luis R. Rodriguez * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -2370,6 +2370,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; bool ret; + int link; wdev_lock(wdev); iftype = wdev->iftype; @@ -2378,62 +2379,83 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) if (!wdev->netdev || !netif_running(wdev->netdev)) goto wdev_inactive_unlock; - switch (iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_P2P_GO: - case NL80211_IFTYPE_MESH_POINT: - if (!wdev->beacon_interval) - goto wdev_inactive_unlock; - chandef = wdev->chandef; - break; - case NL80211_IFTYPE_ADHOC: - if (!wdev->ssid_len) - goto wdev_inactive_unlock; - chandef = wdev->chandef; - break; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - if (!wdev->current_bss || - !wdev->current_bss->pub.channel) - goto wdev_inactive_unlock; - - if (!rdev->ops->get_channel || - rdev_get_channel(rdev, wdev, &chandef)) - cfg80211_chandef_create(&chandef, - wdev->current_bss->pub.channel, - NL80211_CHAN_NO_HT); - break; - case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_P2P_DEVICE: - /* no enforcement required */ - break; - default: - /* others not implemented for now */ - WARN_ON(1); - break; - } + for (link = 0; link < ARRAY_SIZE(wdev->links); link++) { + struct ieee80211_channel *chan; - wdev_unlock(wdev); + if (!wdev->valid_links && link > 0) + break; + if (!(wdev->valid_links & BIT(link))) + continue; + switch (iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_MESH_POINT: + if (!wdev->u.mesh.beacon_interval) + continue; + chandef = wdev->u.mesh.chandef; + break; + case NL80211_IFTYPE_ADHOC: + if (!wdev->u.ibss.ssid_len) + continue; + chandef = wdev->u.ibss.chandef; + break; + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: + /* Maybe we could consider disabling that link only? */ + if (!wdev->links[link].client.current_bss) + continue; - switch (iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_P2P_GO: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_MESH_POINT: - wiphy_lock(wiphy); - ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); - wiphy_unlock(wiphy); + chan = wdev->links[link].client.current_bss->pub.channel; + if (!chan) + continue; - return ret; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - return cfg80211_chandef_usable(wiphy, &chandef, - IEEE80211_CHAN_DISABLED); - default: - break; + if (!rdev->ops->get_channel || + rdev_get_channel(rdev, wdev, link, &chandef)) + cfg80211_chandef_create(&chandef, chan, + NL80211_CHAN_NO_HT); + break; + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_DEVICE: + /* no enforcement required */ + break; + default: + /* others not implemented for now */ + WARN_ON(1); + break; + } + + wdev_unlock(wdev); + + switch (iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + wiphy_lock(wiphy); + ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, + iftype); + wiphy_unlock(wiphy); + + if (!ret) + return ret; + break; + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: + ret = cfg80211_chandef_usable(wiphy, &chandef, + IEEE80211_CHAN_DISABLED); + if (!ret) + return ret; + break; + default: + break; + } + + wdev_lock(wdev); } + wdev_unlock(wdev); + return true; wdev_inactive_unlock: @@ -4215,8 +4237,17 @@ static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) * In both cases we should end the CAC on the wdev. */ list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { - if (wdev->cac_started && - !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef)) + struct cfg80211_chan_def *chandef; + + if (!wdev->cac_started) + continue; + + /* FIXME: radar detection is tied to link 0 for now */ + chandef = wdev_chandef(wdev, 0); + if (!chandef) + continue; + + if (!cfg80211_chandef_dfs_usable(&rdev->wiphy, chandef)) rdev_end_cac(rdev, wdev->netdev); } } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 6d82bd9eaf8c..0134e5d5c81a 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include #include @@ -2617,7 +2617,8 @@ void cfg80211_bss_iter(struct wiphy *wiphy, spin_lock_bh(&rdev->bss_lock); list_for_each_entry(bss, &rdev->bss_list, list) { - if (!chandef || cfg80211_is_sub_chan(chandef, bss->pub.channel)) + if (!chandef || cfg80211_is_sub_chan(chandef, bss->pub.channel, + false)) iter(wiphy, &bss->pub, iter_data); } @@ -2626,11 +2627,12 @@ void cfg80211_bss_iter(struct wiphy *wiphy, EXPORT_SYMBOL(cfg80211_bss_iter); void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + unsigned int link_id, struct ieee80211_channel *chan) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - struct cfg80211_internal_bss *cbss = wdev->current_bss; + struct cfg80211_internal_bss *cbss = wdev->links[link_id].client.current_bss; struct cfg80211_internal_bss *new = NULL; struct cfg80211_internal_bss *bss; struct cfg80211_bss *nontrans_bss; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index ff4d48fcbfb2..35602201057b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -5,7 +5,7 @@ * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg - * Copyright (C) 2009, 2020 Intel Corporation. All rights reserved. + * Copyright (C) 2009, 2020, 2022 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ @@ -454,6 +454,20 @@ void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev) schedule_work(&rdev->conn_work); } +static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev) +{ + unsigned int link; + + for_each_valid_link(wdev, link) { + if (!wdev->links[link].client.current_bss) + continue; + cfg80211_unhold_bss(wdev->links[link].client.current_bss); + cfg80211_put_bss(wdev->wiphy, + &wdev->links[link].client.current_bss->pub); + wdev->links[link].client.current_bss = NULL; + } +} + static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) @@ -521,12 +535,11 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; - if (wdev->current_bss) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - wdev->current_bss = NULL; + cfg80211_wdev_release_bsses(wdev); + if (wdev->connected) { cfg80211_sme_free(wdev); + wdev->connected = false; } if (wdev->conn) @@ -563,8 +576,8 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, wdev->conn->auto_auth = false; } - wdev->conn->params.ssid = wdev->ssid; - wdev->conn->params.ssid_len = wdev->ssid_len; + wdev->conn->params.ssid = wdev->u.client.ssid; + wdev->conn->params.ssid_len = wdev->u.client.ssid_len; /* see if we have the bss already */ bss = cfg80211_get_conn_bss(wdev); @@ -648,7 +661,7 @@ static bool cfg80211_is_all_idle(void) list_for_each_entry(rdev, &cfg80211_rdev_list, list) { list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { wdev_lock(wdev); - if (wdev->conn || wdev->current_bss || + if (wdev->conn || wdev->connected || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; wdev_unlock(wdev); @@ -668,7 +681,6 @@ static void disconnect_work(struct work_struct *work) DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); - /* * API calls for drivers implementing connect/disconnect and * SME event handling @@ -729,23 +741,19 @@ void __cfg80211_connect_result(struct net_device *dev, if (!cr->bss && (cr->status == WLAN_STATUS_SUCCESS)) { WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); cr->bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->bssid, - wdev->ssid, wdev->ssid_len, + wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (cr->bss) cfg80211_hold_bss(bss_from_pub(cr->bss)); } - if (wdev->current_bss) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - wdev->current_bss = NULL; - } + cfg80211_wdev_release_bsses(wdev); if (cr->status != WLAN_STATUS_SUCCESS) { kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; - wdev->ssid_len = 0; + wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; if (cr->bss) { cfg80211_unhold_bss(bss_from_pub(cr->bss)); @@ -758,7 +766,9 @@ void __cfg80211_connect_result(struct net_device *dev, if (WARN_ON(!cr->bss)) return; - wdev->current_bss = bss_from_pub(cr->bss); + wdev->links[0].client.current_bss = bss_from_pub(cr->bss); + wdev->connected = true; + ether_addr_copy(wdev->u.client.connected_addr, cr->bss->bssid); if (!(wdev->wiphy->flags & WIPHY_FLAG_HAS_STATIC_WEP)) cfg80211_upload_connect_keys(wdev); @@ -801,7 +811,7 @@ void cfg80211_connect_done(struct net_device *dev, found = cfg80211_get_bss(wdev->wiphy, NULL, params->bss->bssid, - wdev->ssid, wdev->ssid_len, + wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (found) { @@ -906,18 +916,17 @@ void __cfg80211_roamed(struct wireless_dev *wdev, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; - if (WARN_ON(!wdev->current_bss)) + if (WARN_ON(!wdev->connected)) goto out; - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - wdev->current_bss = NULL; + cfg80211_wdev_release_bsses(wdev); if (WARN_ON(!info->bss)) return; cfg80211_hold_bss(bss_from_pub(info->bss)); - wdev->current_bss = bss_from_pub(info->bss); + wdev->links[0].client.current_bss = bss_from_pub(info->bss); + ether_addr_copy(wdev->u.client.connected_addr, info->bss->bssid); wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), @@ -963,8 +972,8 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, if (!info->bss) { info->bss = cfg80211_get_bss(wdev->wiphy, info->channel, - info->bssid, wdev->ssid, - wdev->ssid_len, + info->bssid, wdev->u.client.ssid, + wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); } @@ -1034,8 +1043,8 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return; - if (WARN_ON(!wdev->current_bss) || - WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + if (WARN_ON(!wdev->connected) || + WARN_ON(!ether_addr_equal(wdev->u.client.connected_addr, bssid))) return; nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, @@ -1087,13 +1096,9 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; - if (wdev->current_bss) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - } - - wdev->current_bss = NULL; - wdev->ssid_len = 0; + cfg80211_wdev_release_bsses(wdev); + wdev->connected = false; + wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; @@ -1182,19 +1187,20 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, * already connected, so reject a new SSID unless it's the * same (which is the case for re-association.) */ - if (wdev->ssid_len && - (wdev->ssid_len != connect->ssid_len || - memcmp(wdev->ssid, connect->ssid, wdev->ssid_len))) + if (wdev->u.client.ssid_len && + (wdev->u.client.ssid_len != connect->ssid_len || + memcmp(wdev->u.client.ssid, connect->ssid, wdev->u.client.ssid_len))) return -EALREADY; /* * If connected, reject (re-)association unless prev_bssid * matches the current BSSID. */ - if (wdev->current_bss) { + if (wdev->connected) { if (!prev_bssid) return -EALREADY; - if (!ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid)) + if (!ether_addr_equal(prev_bssid, + wdev->u.client.connected_addr)) return -ENOTCONN; } @@ -1245,8 +1251,8 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, } wdev->connect_keys = connkeys; - memcpy(wdev->ssid, connect->ssid, connect->ssid_len); - wdev->ssid_len = connect->ssid_len; + memcpy(wdev->u.client.ssid, connect->ssid, connect->ssid_len); + wdev->u.client.ssid_len = connect->ssid_len; wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : IEEE80211_BSS_TYPE_ESS; @@ -1262,8 +1268,8 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, * This could be reassoc getting refused, don't clear * ssid_len in that case. */ - if (!wdev->current_bss) - wdev->ssid_len = 0; + if (!wdev->connected) + wdev->u.client.ssid_len = 0; return err; } @@ -1287,7 +1293,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) cfg80211_mlme_down(rdev, dev); - else if (wdev->ssid_len) + else if (wdev->u.client.ssid_len) err = rdev_disconnect(rdev, dev, reason); /* @@ -1295,8 +1301,8 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, * in which case cfg80211_disconnected() will take care of * this later. */ - if (!wdev->current_bss) - wdev->ssid_len = 0; + if (!wdev->connected) + wdev->u.client.ssid_len = 0; return err; } @@ -1320,7 +1326,7 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - __cfg80211_stop_ap(rdev, wdev->netdev, false); + __cfg80211_stop_ap(rdev, wdev->netdev, -1, false); break; case NL80211_IFTYPE_MESH_POINT: __cfg80211_leave_mesh(rdev, wdev->netdev); @@ -1332,7 +1338,7 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) * ops->disconnect not implemented. Otherwise we can * use cfg80211_disconnect. */ - if (rdev->ops->disconnect || wdev->current_bss) + if (rdev->ops->disconnect || wdev->connected) cfg80211_disconnect(rdev, wdev->netdev, WLAN_REASON_DEAUTH_LEAVING, true); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 228079d7690a..3b2c956b8d78 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -569,6 +569,7 @@ TRACE_EVENT(rdev_start_ap, __field(bool, privacy) __field(enum nl80211_auth_type, auth_type) __field(int, inactivity_timeout) + __field(unsigned int, link_id) ), TP_fast_assign( WIPHY_ASSIGN; @@ -583,16 +584,17 @@ TRACE_EVENT(rdev_start_ap, __entry->inactivity_timeout = settings->inactivity_timeout; memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); memcpy(__entry->ssid, settings->ssid, settings->ssid_len); + __entry->link_id = settings->beacon.link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", AP settings - ssid: %s, " CHAN_DEF_PR_FMT ", beacon interval: %d, dtim period: %d, " "hidden ssid: %d, wpa versions: %u, privacy: %s, " - "auth type: %d, inactivity timeout: %d", + "auth type: %d, inactivity timeout: %d, link_id: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->ssid, CHAN_DEF_PR_ARG, __entry->beacon_interval, __entry->dtim_period, __entry->hidden_ssid, __entry->wpa_ver, BOOL_TO_STR(__entry->privacy), __entry->auth_type, - __entry->inactivity_timeout) + __entry->inactivity_timeout, __entry->link_id) ); TRACE_EVENT(rdev_change_beacon, @@ -602,6 +604,7 @@ TRACE_EVENT(rdev_change_beacon, TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY + __field(int, link_id) __dynamic_array(u8, head, info ? info->head_len : 0) __dynamic_array(u8, tail, info ? info->tail_len : 0) __dynamic_array(u8, beacon_ies, info ? info->beacon_ies_len : 0) @@ -615,6 +618,7 @@ TRACE_EVENT(rdev_change_beacon, WIPHY_ASSIGN; NETDEV_ASSIGN; if (info) { + __entry->link_id = info->link_id; if (info->head) memcpy(__get_dynamic_array(head), info->head, info->head_len); @@ -635,9 +639,30 @@ TRACE_EVENT(rdev_change_beacon, if (info->probe_resp) memcpy(__get_dynamic_array(probe_resp), info->probe_resp, info->probe_resp_len); + } else { + __entry->link_id = -1; } ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG) + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", link_id:%d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->link_id) +); + +TRACE_EVENT(rdev_stop_ap, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + unsigned int link_id), + TP_ARGS(wiphy, netdev, link_id), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(unsigned int, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->link_id = link_id; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", link_id: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->link_id) ); DECLARE_EVENT_CLASS(wiphy_netdev_evt, @@ -654,11 +679,6 @@ DECLARE_EVENT_CLASS(wiphy_netdev_evt, TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG) ); -DEFINE_EVENT(wiphy_netdev_evt, rdev_stop_ap, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), - TP_ARGS(wiphy, netdev) -); - DEFINE_EVENT(wiphy_netdev_evt, rdev_set_rekey_data, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), TP_ARGS(wiphy, netdev) @@ -1619,20 +1639,24 @@ TRACE_EVENT(rdev_testmode_dump, TRACE_EVENT(rdev_set_bitrate_mask, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask), - TP_ARGS(wiphy, netdev, peer, mask), + TP_ARGS(wiphy, netdev, link_id, peer, mask), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY + __field(unsigned int, link_id) MAC_ENTRY(peer) ), TP_fast_assign( WIPHY_ASSIGN; NETDEV_ASSIGN; + __entry->link_id = link_id; MAC_ASSIGN(peer, peer); ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT, - WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", link_id: %d, peer: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->link_id, + MAC_PR_ARG(peer)) ); TRACE_EVENT(rdev_update_mgmt_frame_registrations, @@ -2040,9 +2064,22 @@ TRACE_EVENT(rdev_set_noack_map, WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->noack_map) ); -DEFINE_EVENT(wiphy_wdev_evt, rdev_get_channel, - TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), - TP_ARGS(wiphy, wdev) +TRACE_EVENT(rdev_get_channel, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id), + TP_ARGS(wiphy, wdev, link_id), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(unsigned int, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->link_id = link_id; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", link_id: %u", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->link_id) ); TRACE_EVENT(rdev_return_chandef, @@ -2296,20 +2333,24 @@ TRACE_EVENT(rdev_set_qos_map, TRACE_EVENT(rdev_set_ap_chanwidth, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + unsigned int link_id, struct cfg80211_chan_def *chandef), - TP_ARGS(wiphy, netdev, chandef), + TP_ARGS(wiphy, netdev, link_id, chandef), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY CHAN_DEF_ENTRY + __field(unsigned int, link_id) ), TP_fast_assign( WIPHY_ASSIGN; NETDEV_ASSIGN; CHAN_DEF_ASSIGN(chandef); + __entry->link_id = link_id; ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT, - WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG) + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d", + WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG, + __entry->link_id) ); TRACE_EVENT(rdev_add_tx_ts, @@ -3022,18 +3063,21 @@ TRACE_EVENT(cfg80211_chandef_dfs_required, TRACE_EVENT(cfg80211_ch_switch_notify, TP_PROTO(struct net_device *netdev, - struct cfg80211_chan_def *chandef), - TP_ARGS(netdev, chandef), + struct cfg80211_chan_def *chandef, + unsigned int link_id), + TP_ARGS(netdev, chandef, link_id), TP_STRUCT__entry( NETDEV_ENTRY CHAN_DEF_ENTRY + __field(unsigned int, link_id) ), TP_fast_assign( NETDEV_ASSIGN; CHAN_DEF_ASSIGN(chandef); + __entry->link_id = link_id; ), - TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT, - NETDEV_PR_ARG, CHAN_DEF_PR_ARG) + TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d", + NETDEV_PR_ARG, CHAN_DEF_PR_ARG, __entry->link_id) ); TRACE_EVENT(cfg80211_ch_switch_started_notify, diff --git a/net/wireless/util.c b/net/wireless/util.c index a60d7d638e72..b7257862e0fe 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include #include @@ -1041,7 +1041,6 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, return -EBUSY; dev->ieee80211_ptr->use_4addr = false; - dev->ieee80211_ptr->mesh_id_up_len = 0; wdev_lock(dev->ieee80211_ptr); rdev_set_qos_map(rdev, dev, NULL); wdev_unlock(dev->ieee80211_ptr); @@ -1049,7 +1048,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, switch (otype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - cfg80211_stop_ap(rdev, dev, true); + cfg80211_stop_ap(rdev, dev, -1, true); break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); @@ -1073,6 +1072,11 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, cfg80211_process_rdev_events(rdev); cfg80211_mlme_purge_registrations(dev->ieee80211_ptr); + + memset(&dev->ieee80211_ptr->u, 0, + sizeof(dev->ieee80211_ptr->u)); + memset(&dev->ieee80211_ptr->links, 0, + sizeof(dev->ieee80211_ptr->links)); } err = rdev_change_virtual_intf(rdev, dev, ntype, params); @@ -1930,6 +1934,24 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, } EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); +static int cfg80211_wdev_bi(struct wireless_dev *wdev) +{ + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + WARN_ON(wdev->valid_links); + return wdev->links[0].ap.beacon_interval; + case NL80211_IFTYPE_MESH_POINT: + return wdev->u.mesh.beacon_interval; + case NL80211_IFTYPE_ADHOC: + return wdev->u.ibss.beacon_interval; + default: + break; + } + + return 0; +} + static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, u32 *beacon_int_gcd, bool *beacon_int_different) @@ -1940,19 +1962,27 @@ static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, *beacon_int_different = false; list_for_each_entry(wdev, &wiphy->wdev_list, list) { - if (!wdev->beacon_interval) + int wdev_bi; + + /* this feature isn't supported with MLO */ + if (wdev->valid_links) + continue; + + wdev_bi = cfg80211_wdev_bi(wdev); + + if (!wdev_bi) continue; if (!*beacon_int_gcd) { - *beacon_int_gcd = wdev->beacon_interval; + *beacon_int_gcd = wdev_bi; continue; } - if (wdev->beacon_interval == *beacon_int_gcd) + if (wdev_bi == *beacon_int_gcd) continue; *beacon_int_different = true; - *beacon_int_gcd = gcd(*beacon_int_gcd, wdev->beacon_interval); + *beacon_int_gcd = gcd(*beacon_int_gcd, wdev_bi); } if (new_beacon_int && *beacon_int_gcd != new_beacon_int) { diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index a32065d600a1..a9767bfe7330 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -7,7 +7,7 @@ * we directly assign the wireless handlers of wireless interfaces. * * Copyright 2008-2009 Johannes Berg - * Copyright (C) 2019-2021 Intel Corporation + * Copyright (C) 2019-2022 Intel Corporation */ #include @@ -415,6 +415,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, int err, i; bool rejoin = false; + if (wdev->valid_links) + return -EINVAL; + if (pairwise && !addr) return -EINVAL; @@ -437,7 +440,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, return -EOPNOTSUPP; if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { - if (!wdev->current_bss) + if (!wdev->connected) return -ENOLINK; if (!rdev->ops->set_default_mgmt_key) @@ -450,7 +453,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (remove) { err = 0; - if (wdev->current_bss) { + if (wdev->connected || + (wdev->iftype == NL80211_IFTYPE_ADHOC && + wdev->u.ibss.current_bss)) { /* * If removing the current TX key, we will need to * join a new IBSS without the privacy bit clear. @@ -501,7 +506,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, return -EINVAL; err = 0; - if (wdev->current_bss) + if (wdev->connected || + (wdev->iftype == NL80211_IFTYPE_ADHOC && + wdev->u.ibss.current_bss)) err = rdev_add_key(rdev, dev, idx, pairwise, addr, params); else if (params->cipher != WLAN_CIPHER_SUITE_WEP40 && params->cipher != WLAN_CIPHER_SUITE_WEP104) @@ -526,7 +533,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if ((params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104) && (tx_key || (!addr && wdev->wext.default_key == -1))) { - if (wdev->current_bss) { + if (wdev->connected || + (wdev->iftype == NL80211_IFTYPE_ADHOC && + wdev->u.ibss.current_bss)) { /* * If we are getting a new TX key from not having * had one before we need to join a new IBSS with @@ -549,7 +558,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { - if (wdev->current_bss) + if (wdev->connected || + (wdev->iftype == NL80211_IFTYPE_ADHOC && + wdev->u.ibss.current_bss)) err = rdev_set_default_mgmt_key(rdev, dev, idx); if (!err) wdev->wext.default_mgmt_key = idx; @@ -595,6 +606,11 @@ static int cfg80211_wext_siwencode(struct net_device *dev, return -EOPNOTSUPP; wiphy_lock(&rdev->wiphy); + if (wdev->valid_links) { + err = -EOPNOTSUPP; + goto out; + } + idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; @@ -613,7 +629,9 @@ static int cfg80211_wext_siwencode(struct net_device *dev, /* No key data - just set the default TX key index */ err = 0; wdev_lock(wdev); - if (wdev->current_bss) + if (wdev->connected || + (wdev->iftype == NL80211_IFTYPE_ADHOC && + wdev->u.ibss.current_bss)) err = rdev_set_default_key(rdev, dev, idx, true, true); if (!err) @@ -865,7 +883,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, break; } - ret = rdev_get_channel(rdev, wdev, &chandef); + ret = rdev_get_channel(rdev, wdev, 0, &chandef); if (ret) break; freq->m = chandef.chan->center_freq; @@ -1270,7 +1288,10 @@ static int cfg80211_wext_siwrate(struct net_device *dev, return -EINVAL; wiphy_lock(&rdev->wiphy); - ret = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + if (dev->ieee80211_ptr->valid_links) + ret = -EOPNOTSUPP; + else + ret = rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); wiphy_unlock(&rdev->wiphy); return ret; @@ -1294,8 +1315,9 @@ static int cfg80211_wext_giwrate(struct net_device *dev, err = 0; wdev_lock(wdev); - if (wdev->current_bss) - memcpy(addr, wdev->current_bss->pub.bssid, ETH_ALEN); + if (!wdev->valid_links && wdev->links[0].client.current_bss) + memcpy(addr, wdev->links[0].client.current_bss->pub.bssid, + ETH_ALEN); else err = -EOPNOTSUPP; wdev_unlock(wdev); @@ -1339,11 +1361,11 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) /* Grab BSSID of current BSS, if any */ wdev_lock(wdev); - if (!wdev->current_bss) { + if (wdev->valid_links || !wdev->links[0].client.current_bss) { wdev_unlock(wdev); return NULL; } - memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); + memcpy(bssid, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); wdev_unlock(wdev); memset(&sinfo, 0, sizeof(sinfo)); diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index cd09a9042261..68f45afc352d 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -3,7 +3,7 @@ * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg - * Copyright (C) 2009, 2020-2021 Intel Corporation. + * Copyright (C) 2009, 2020-2022 Intel Corporation */ #include @@ -124,9 +124,12 @@ int cfg80211_mgd_wext_giwfreq(struct net_device *dev, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; + if (wdev->valid_links) + return -EOPNOTSUPP; + wdev_lock(wdev); - if (wdev->current_bss) - chan = wdev->current_bss->pub.channel; + if (wdev->links[0].client.current_bss) + chan = wdev->links[0].client.current_bss->pub.channel; else if (wdev->wext.connect.channel) chan = wdev->wext.connect.channel; wdev_unlock(wdev); @@ -208,15 +211,19 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; + if (wdev->valid_links) + return -EINVAL; + data->flags = 0; wdev_lock(wdev); - if (wdev->current_bss) { + if (wdev->links[0].client.current_bss) { const struct element *ssid_elem; rcu_read_lock(); - ssid_elem = ieee80211_bss_get_elem(&wdev->current_bss->pub, - WLAN_EID_SSID); + ssid_elem = ieee80211_bss_get_elem( + &wdev->links[0].client.current_bss->pub, + WLAN_EID_SSID); if (ssid_elem) { data->flags = 1; data->length = ssid_elem->datalen; @@ -300,8 +307,14 @@ int cfg80211_mgd_wext_giwap(struct net_device *dev, ap_addr->sa_family = ARPHRD_ETHER; wdev_lock(wdev); - if (wdev->current_bss) - memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); + if (wdev->valid_links) { + wdev_unlock(wdev); + return -EOPNOTSUPP; + } + if (wdev->links[0].client.current_bss) + memcpy(ap_addr->sa_data, + wdev->links[0].client.current_bss->pub.bssid, + ETH_ALEN); else eth_zero_addr(ap_addr->sa_data); wdev_unlock(wdev); -- cgit v1.2.3 From d648c23024bd01333acd2fd5e34bcde0ffb66b16 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 31 May 2022 19:48:33 +0200 Subject: wifi: nl80211: support MLO in auth/assoc For authentication, we need the BSS, the link_id and the AP MLD address to create the link and station, (for now) the driver assigns a link address and sends the frame, the MLD address needs to be the address of the interface. For association, pass the list of BSSes that were selected for the MLO connection, along with extra per-STA profile elements, the AP MLD address and the link ID on which the association request should be sent. Note that for now we don't have a proper way to pass the link address(es) and so the driver/mac80211 will select one, but depending on how that selection works it means that assoc w/o auth data still being around (mac80211 implementation detail) the association won't necessarily work - so this will need to be extended in the future to sort out the link addressing. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 31 +++++++++++++++ include/uapi/linux/nl80211.h | 3 ++ net/wireless/mlme.c | 30 +++++++++++++-- net/wireless/nl80211.c | 91 ++++++++++++++++++++++++++++++++++++++++++-- net/wireless/sme.c | 2 + 5 files changed, 151 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 772e099fc932..a4f9e6094118 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2718,6 +2718,12 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) * Authentication algorithm number, i.e., starting at the Authentication * transaction sequence number field. * @auth_data_len: Length of auth_data buffer in octets + * @link_id: if >= 0, indicates authentication should be done as an MLD, + * the interface address is included as the MLD address and the + * necessary link (with the given link_id) will be created (and + * given an MLD address) by the driver + * @ap_mld_addr: AP MLD address in case of authentication request with + * an AP MLD, valid iff @link_id >= 0 */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -2728,6 +2734,21 @@ struct cfg80211_auth_request { u8 key_len, key_idx; const u8 *auth_data; size_t auth_data_len; + s8 link_id; + const u8 *ap_mld_addr; +}; + +/** + * struct cfg80211_assoc_link - per-link information for MLO association + * @bss: the BSS pointer, see also &struct cfg80211_assoc_request::bss; + * if this is %NULL for a link, that link is not requested + * @elems: extra elements for the per-STA profile for this link + * @elems_len: length of the elements + */ +struct cfg80211_assoc_link { + struct cfg80211_bss *bss; + const u8 *elems; + size_t elems_len; }; /** @@ -2761,6 +2782,8 @@ enum cfg80211_assoc_req_flags { * given a reference that it must give back to cfg80211_send_rx_assoc() * or to cfg80211_assoc_timeout(). To ensure proper refcounting, new * association requests while already associating must be rejected. + * This also applies to the @links.bss parameter, which is used instead + * of this one (it is %NULL) for MLO associations. * @ie: Extra IEs to add to (Re)Association Request frame or %NULL * @ie_len: Length of ie buffer in octets * @use_mfp: Use management frame protection (IEEE 802.11w) in this association @@ -2785,6 +2808,11 @@ enum cfg80211_assoc_req_flags { * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. * @s1g_capa: S1G capability override * @s1g_capa_mask: S1G capability override mask + * @links: per-link information for MLO connections + * @link_id: >= 0 for MLO connections, where links are given, and indicates + * the link on which the association request should be sent + * @ap_mld_addr: AP MLD address in case of MLO association request, + * valid iff @link_id >= 0 */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -2800,6 +2828,9 @@ struct cfg80211_assoc_request { size_t fils_kek_len; const u8 *fils_nonces; struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; + struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS]; + const u8 *ap_mld_addr; + s8 link_id; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a9a2c9fef295..60ad9a9f153d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2687,6 +2687,8 @@ enum nl80211_commands { * various commands that need a link ID to operate. * @NL80211_ATTR_MLO_LINKS: A nested array of links, each containing some * per-link information and a link ID. + * @NL80211_ATTR_MLD_ADDR: An MLD address, used with various commands such as + * authenticate/associate. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -3204,6 +3206,7 @@ enum nl80211_attrs { NL80211_ATTR_MLO_LINKS, NL80211_ATTR_MLO_LINK_ID, + NL80211_ATTR_MLD_ADDR, /* add attributes here, update the policy in nl80211.c */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 532113937469..d92eed0e52cd 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -241,6 +241,10 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, if (!req->bss) return -ENOENT; + if (req->link_id >= 0 && + !(wdev->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO)) + return -EINVAL; + if (req->auth_type == NL80211_AUTHTYPE_SHARED_KEY) { if (!req->key || !req->key_len || req->key_idx < 0 || req->key_idx > 3) @@ -294,10 +298,19 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct cfg80211_assoc_request *req) { struct wireless_dev *wdev = dev->ieee80211_ptr; - int err; + int err, i, j; ASSERT_WDEV_LOCK(wdev); + for (i = 1; i < ARRAY_SIZE(req->links); i++) { + if (!req->links[i].bss) + continue; + for (j = 0; j < i; j++) { + if (req->links[i].bss == req->links[j].bss) + return -EINVAL; + } + } + if (wdev->connected && (!req->prev_bssid || !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid))) @@ -310,8 +323,19 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, err = rdev_assoc(rdev, dev, req); if (!err) { - cfg80211_ref_bss(&rdev->wiphy, req->bss); - cfg80211_hold_bss(bss_from_pub(req->bss)); + int link_id; + + if (req->bss) { + cfg80211_ref_bss(&rdev->wiphy, req->bss); + cfg80211_hold_bss(bss_from_pub(req->bss)); + } + + for (link_id = 0; link_id < ARRAY_SIZE(req->links); link_id++) { + if (!req->links[link_id].bss) + continue; + cfg80211_ref_bss(&rdev->wiphy, req->links[link_id].bss); + cfg80211_hold_bss(bss_from_pub(req->links[link_id].bss)); + } } return err; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5a4d3ddcdf80..9bc66a21ac3a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -796,6 +796,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_NESTED_ARRAY(nl80211_policy), [NL80211_ATTR_MLO_LINK_ID] = NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), + [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), }; /* policy for the key attributes */ @@ -10282,6 +10283,12 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) req.key = key.p.key; req.key_len = key.p.key_len; req.key_idx = key.idx; + req.link_id = nl80211_link_id_or_invalid(info->attrs); + if (req.link_id >= 0) { + if (!info->attrs[NL80211_ATTR_MLD_ADDR]) + return -EINVAL; + req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + } req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, IEEE80211_BSS_TYPE_ESS, @@ -10475,7 +10482,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct cfg80211_assoc_request req = {}; + struct nlattr **attrs = NULL; const u8 *bssid, *ssid; + unsigned int link_id; int err, ssid_len; if (dev->ieee80211_ptr->conn_owner_nlportid && @@ -10585,9 +10594,81 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) sizeof(req.s1g_capa)); } - req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, &bssid); - if (IS_ERR(req.bss)) - return PTR_ERR(req.bss); + req.link_id = nl80211_link_id_or_invalid(info->attrs); + + if (info->attrs[NL80211_ATTR_MLO_LINKS]) { + unsigned int attrsize = NUM_NL80211_ATTR * sizeof(*attrs); + struct nlattr *link; + int rem = 0; + + if (req.link_id < 0) + return -EINVAL; + + if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_MLO)) + return -EINVAL; + + if (info->attrs[NL80211_ATTR_MAC] || + info->attrs[NL80211_ATTR_WIPHY_FREQ] || + !info->attrs[NL80211_ATTR_MLD_ADDR]) + return -EINVAL; + + req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + + attrs = kzalloc(attrsize, GFP_KERNEL); + if (!attrs) + return -ENOMEM; + + nla_for_each_nested(link, + info->attrs[NL80211_ATTR_MLO_LINKS], + rem) { + memset(attrs, 0, attrsize); + + nla_parse_nested(attrs, NL80211_ATTR_MAX, + link, NULL, NULL); + + if (!attrs[NL80211_ATTR_MLO_LINK_ID]) { + err = -EINVAL; + goto free; + } + + link_id = nla_get_u8(attrs[NL80211_ATTR_MLO_LINK_ID]); + /* cannot use the same link ID again */ + if (req.links[link_id].bss) { + err = -EINVAL; + goto free; + } + req.links[link_id].bss = + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, + &bssid); + if (IS_ERR(req.links[link_id].bss)) { + err = PTR_ERR(req.links[link_id].bss); + goto free; + } + + if (attrs[NL80211_ATTR_IE]) { + req.links[link_id].elems = + nla_data(attrs[NL80211_ATTR_IE]); + req.links[link_id].elems_len = + nla_len(attrs[NL80211_ATTR_IE]); + } + } + + if (!req.links[req.link_id].bss) { + err = -EINVAL; + goto free; + } + + kfree(attrs); + attrs = NULL; + } else { + if (req.link_id >= 0) + return -EINVAL; + + req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, + &bssid); + if (IS_ERR(req.bss)) + return PTR_ERR(req.bss); + } err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); if (!err) { @@ -10605,7 +10686,11 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) wdev_unlock(dev->ieee80211_ptr); } +free: + for (link_id = 0; link_id < ARRAY_SIZE(req.links); link_id++) + cfg80211_put_bss(&rdev->wiphy, req.links[link_id].bss); cfg80211_put_bss(&rdev->wiphy, req.bss); + kfree(attrs); return err; } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index c8a99b90723b..b3c6ce4f85ee 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -177,6 +177,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); + auth_req.link_id = -1; err = cfg80211_mlme_auth(rdev, wdev->netdev, &auth_req); cfg80211_put_bss(&rdev->wiphy, auth_req.bss); return err; @@ -198,6 +199,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, req.ht_capa_mask = params->ht_capa_mask; req.vht_capa = params->vht_capa; req.vht_capa_mask = params->vht_capa_mask; + req.link_id = -1; req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, -- cgit v1.2.3 From efbabc11650040c64884ff3019b88c7bcc0ceb1d Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Wed, 8 Jun 2022 14:46:37 +0530 Subject: cfg80211: Indicate MLO connection info in connect and roam callbacks The MLO links used for connection with an MLD AP are decided by the driver in case of SME offloaded to driver. Add support for the drivers to indicate the information of links used for MLO connection in connect and roam callbacks, update the connected links information in wdev from connect/roam result sent by driver. Also, send the connected links information to userspace. Add a netlink flag attribute to indicate that userspace supports handling of MLO connection. Drivers must not do MLO connection when this flag is not set. This is to maintain backwards compatibility with older supplicant versions which doesn't have support for MLO connection. Signed-off-by: Veerendranath Jakkam Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +- drivers/net/wireless/ath/wil6210/wmi.c | 4 +- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 6 +- drivers/net/wireless/rndis_wlan.c | 5 +- drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c | 4 +- drivers/staging/wlan-ng/cfg80211.c | 2 +- include/net/cfg80211.h | 84 +++-- include/uapi/linux/nl80211.h | 6 + net/wireless/mlme.c | 4 +- net/wireless/nl80211.c | 120 ++++++- net/wireless/sme.c | 391 +++++++++++++++------ 11 files changed, 480 insertions(+), 148 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index 33ed54738d47..e11c7e9accc0 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -807,7 +807,7 @@ void ath6kl_cfg80211_connect_event(struct ath6kl_vif *vif, u16 channel, cfg80211_put_bss(ar->wiphy, bss); } else if (vif->sme_state == SME_CONNECTED) { struct cfg80211_roam_info roam_info = { - .bss = bss, + .links[0].bss = bss, .req_ie = assoc_req_ie, .req_ie_len = assoc_req_len, .resp_ie = assoc_resp_ie, diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c index 98b4c189eecc..ea7bd403e706 100644 --- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -1822,8 +1822,8 @@ wmi_evt_reassoc_status(struct wil6210_vif *vif, int id, void *d, int len) freq = ieee80211_channel_to_frequency(ch, NL80211_BAND_60GHZ); memset(&info, 0, sizeof(info)); - info.channel = ieee80211_get_channel(wiphy, freq); - info.bss = vif->bss; + info.links[0].channel = ieee80211_get_channel(wiphy, freq); + info.links[0].bss = vif->bss; info.req_ie = assoc_req_ie; info.req_ie_len = assoc_req_ie_len; info.resp_ie = assoc_resp_ie; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 11e1f07f83e0..3ae6779fe153 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -6017,8 +6017,8 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg, done: kfree(buf); - roam_info.channel = notify_channel; - roam_info.bssid = profile->bssid; + roam_info.links[0].channel = notify_channel; + roam_info.links[0].bssid = profile->bssid; roam_info.req_ie = conn_info->req_ie; roam_info.req_ie_len = conn_info->req_ie_len; roam_info.resp_ie = conn_info->resp_ie; @@ -6061,7 +6061,7 @@ brcmf_bss_connect_done(struct brcmf_cfg80211_info *cfg, } else { conn_params.status = WLAN_STATUS_AUTH_TIMEOUT; } - conn_params.bssid = profile->bssid; + conn_params.links[0].bssid = profile->bssid; conn_params.req_ie = conn_info->req_ie; conn_params.req_ie_len = conn_info->req_ie_len; conn_params.resp_ie = conn_info->resp_ie; diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index ff2448394a1e..05524291d60c 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -2813,8 +2813,9 @@ static void rndis_wlan_do_link_up_work(struct usbnet *usbdev) resp_ie_len, 0, GFP_KERNEL); } else { struct cfg80211_roam_info roam_info = { - .channel = get_current_channel(usbdev, NULL), - .bssid = bssid, + .links[0].channel = + get_current_channel(usbdev, NULL), + .links[0].bssid = bssid, .req_ie = req_ie, .req_ie_len = req_ie_len, .resp_ie = resp_ie, diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index 349aa3c4b668..cf35125b7891 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -450,8 +450,8 @@ check_bss: notify_channel = ieee80211_get_channel(wiphy, freq); - roam_info.channel = notify_channel; - roam_info.bssid = cur_network->network.mac_address; + roam_info.links[0].channel = notify_channel; + roam_info.links[0].bssid = cur_network->network.mac_address; roam_info.req_ie = pmlmepriv->assoc_req+sizeof(struct ieee80211_hdr_3addr)+2; roam_info.req_ie_len = diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c index 87379edce9a8..b7b56d8406d1 100644 --- a/drivers/staging/wlan-ng/cfg80211.c +++ b/drivers/staging/wlan-ng/cfg80211.c @@ -645,7 +645,7 @@ void prism2_disconnected(struct wlandevice *wlandev) void prism2_roamed(struct wlandevice *wlandev) { struct cfg80211_roam_info roam_info = { - .bssid = wlandev->bssid, + .links[0].bssid = wlandev->bssid, }; cfg80211_roamed(wlandev->netdev, &roam_info, GFP_KERNEL); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5706f96b819a..996782c44838 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2763,6 +2763,9 @@ struct cfg80211_assoc_link { * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE * @ASSOC_REQ_DISABLE_EHT: Disable EHT + * @CONNECT_REQ_MLO_SUPPORT: Userspace indicates support for handling MLD links. + * Drivers shall disable MLO features for the current association if this + * flag is not set. */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2771,6 +2774,7 @@ enum cfg80211_assoc_req_flags { CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), ASSOC_REQ_DISABLE_EHT = BIT(5), + CONNECT_REQ_MLO_SUPPORT = BIT(6), }; /** @@ -5780,12 +5784,13 @@ static inline void WARN_INVALID_LINK_ID(struct wireless_dev *wdev, !(wdev->valid_links & BIT(link_id))); } -#define for_each_valid_link(wdev, link_id) \ - for (link_id = 0; \ - link_id < ((wdev)->valid_links ? ARRAY_SIZE((wdev)->links) : 1); \ - link_id++) \ - if (!(wdev)->valid_links || \ - ((wdev)->valid_links & BIT(link_id))) +#define for_each_valid_link(link_info, link_id) \ + for (link_id = 0; \ + link_id < ((link_info)->valid_links ? \ + ARRAY_SIZE((link_info)->links) : 1); \ + link_id++) \ + if (!(link_info)->valid_links || \ + ((link_info)->valid_links & BIT(link_id))) /** * DOC: Utility functions @@ -7296,13 +7301,6 @@ struct cfg80211_fils_resp_params { * indicate that this is a failure, but without a status code. * @timeout_reason is used to report the reason for the timeout in that * case. - * @bssid: The BSSID of the AP (may be %NULL) - * @bss: Entry of bss to which STA got connected to, can be obtained through - * cfg80211_get_bss() (may be %NULL). But it is recommended to store the - * bss from the connect_request and hold a reference to it and return - * through this param to avoid a warning if the bss is expired during the - * connection, esp. for those drivers implementing connect op. - * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) @@ -7314,17 +7312,41 @@ struct cfg80211_fils_resp_params { * not known. This value is used only if @status < 0 to indicate that the * failure is due to a timeout and not due to explicit rejection by the AP. * This value is ignored in other cases (@status >= 0). + * @valid_links: For MLO connection, BIT mask of the valid link ids. Otherwise + * zero. + * @ap_mld_addr: For MLO connection, MLD address of the AP. Otherwise %NULL. + * @links : For MLO connection, contains link info for the valid links indicated + * using @valid_links. For non-MLO connection, links[0] contains the + * connected AP info. + * @links.addr: For MLO connection, MAC address of the STA link. Otherwise + * %NULL. + * @links.bssid: For MLO connection, MAC address of the AP link. For non-MLO + * connection, links[0].bssid points to the BSSID of the AP (may be %NULL). + * @links.bss: For MLO connection, entry of bss to which STA link is connected. + * For non-MLO connection, links[0].bss points to entry of bss to which STA + * is connected. It can be obtained through cfg80211_get_bss() (may be + * %NULL). It is recommended to store the bss from the connect_request and + * hold a reference to it and return through this param to avoid a warning + * if the bss is expired during the connection, esp. for those drivers + * implementing connect op. Only one parameter among @bssid and @bss needs + * to be specified. */ struct cfg80211_connect_resp_params { int status; - const u8 *bssid; - struct cfg80211_bss *bss; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** @@ -7394,8 +7416,8 @@ cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, memset(¶ms, 0, sizeof(params)); params.status = status; - params.bssid = bssid; - params.bss = bss; + params.links[0].bssid = bssid; + params.links[0].bss = bss; params.req_ie = req_ie; params.req_ie_len = req_ie_len; params.resp_ie = resp_ie; @@ -7466,24 +7488,40 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, /** * struct cfg80211_roam_info - driver initiated roaming information * - * @channel: the channel of the new AP - * @bss: entry of bss to which STA got roamed (may be %NULL if %bssid is set) - * @bssid: the BSSID of the new AP (may be %NULL if %bss is set) * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @fils: FILS related roaming information. + * @valid_links: For MLO roaming, BIT mask of the new valid links is set. + * Otherwise zero. + * @ap_mld_addr: For MLO roaming, MLD address of the new AP. Otherwise %NULL. + * @links : For MLO roaming, contains new link info for the valid links set in + * @valid_links. For non-MLO roaming, links[0] contains the new AP info. + * @links.addr: For MLO roaming, MAC address of the STA link. Otherwise %NULL. + * @links.bssid: For MLO roaming, MAC address of the new AP link. For non-MLO + * roaming, links[0].bssid points to the BSSID of the new AP. May be + * %NULL if %links.bss is set. + * @links.channel: the channel of the new AP. + * @links.bss: For MLO roaming, entry of new bss to which STA link got + * roamed. For non-MLO roaming, links[0].bss points to entry of bss to + * which STA got roamed (may be %NULL if %links.bssid is set) */ struct cfg80211_roam_info { - struct ieee80211_channel *channel; - struct cfg80211_bss *bss; - const u8 *bssid; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct ieee80211_channel *channel; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 60ad9a9f153d..89f64f46b98d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2690,6 +2690,10 @@ enum nl80211_commands { * @NL80211_ATTR_MLD_ADDR: An MLD address, used with various commands such as * authenticate/associate. * + * @NL80211_ATTR_MLO_SUPPORT: Flag attribute to indicate user space supports MLO + * connection. Used with %NL80211_CMD_CONNECT. If this attribute is not + * included in NL80211_CMD_CONNECT drivers must not perform MLO connection. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3208,6 +3212,8 @@ enum nl80211_attrs { NL80211_ATTR_MLO_LINK_ID, NL80211_ATTR_MLD_ADDR, + NL80211_ATTR_MLO_SUPPORT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index d92eed0e52cd..8a84cf77667c 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -42,8 +42,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss, memset(&cr, 0, sizeof(cr)); cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code); - cr.bssid = mgmt->bssid; - cr.bss = bss; + cr.links[0].bssid = mgmt->bssid; + cr.links[0].bss = bss; cr.req_ie = req_ies; cr.req_ie_len = req_ies_len; cr.resp_ie = resp_ie; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index aca799b9971e..6a45801c783c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -797,6 +797,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLO_LINK_ID] = NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), + [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -11529,6 +11530,9 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.flags |= CONNECT_REQ_EXTERNAL_AUTH_SUPPORT; } + if (nla_get_flag(info->attrs[NL80211_ATTR_MLO_SUPPORT])) + connect.flags |= CONNECT_REQ_MLO_SUPPORT; + wdev_lock(dev->ieee80211_ptr); err = cfg80211_connect(rdev, dev, &connect, connkeys, @@ -17304,10 +17308,29 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; void *hdr; + unsigned int link; + size_t link_info_size = 0; + const u8 *connected_addr = cr->valid_links ? + cr->ap_mld_addr : cr->links[0].bssid; + + if (cr->valid_links) { + for_each_valid_link(cr, link) { + /* Nested attribute header */ + link_info_size += NLA_HDRLEN; + /* Link ID */ + link_info_size += nla_total_size(sizeof(u8)); + link_info_size += cr->links[link].addr ? + nla_total_size(ETH_ALEN) : 0; + link_info_size += (cr->links[link].bssid || + cr->links[link].bss) ? + nla_total_size(ETH_ALEN) : 0; + } + } msg = nlmsg_new(100 + cr->req_ie_len + cr->resp_ie_len + cr->fils.kek_len + cr->fils.pmk_len + - (cr->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); + (cr->fils.pmkid ? WLAN_PMKID_LEN : 0) + link_info_size, + gfp); if (!msg) return; @@ -17319,8 +17342,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || - (cr->bssid && - nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, cr->bssid)) || + (connected_addr && + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, connected_addr)) || nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, cr->status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE : cr->status) || @@ -17346,6 +17369,38 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->fils.pmkid))))) goto nla_put_failure; + if (cr->valid_links) { + int i = 1; + struct nlattr *nested; + + nested = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); + if (!nested) + goto nla_put_failure; + + for_each_valid_link(cr, link) { + struct nlattr *nested_mlo_links; + const u8 *bssid = cr->links[link].bss ? + cr->links[link].bss->bssid : + cr->links[link].bssid; + + nested_mlo_links = nla_nest_start(msg, i); + if (!nested_mlo_links) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link) || + (bssid && + nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, bssid)) || + (cr->links[link].addr && + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, + cr->links[link].addr))) + goto nla_put_failure; + + nla_nest_end(msg, nested_mlo_links); + i++; + } + nla_nest_end(msg, nested); + } + genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, @@ -17362,11 +17417,32 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; void *hdr; - const u8 *bssid = info->bss ? info->bss->bssid : info->bssid; + size_t link_info_size = 0; + unsigned int link; + const u8 *connected_addr = info->ap_mld_addr ? + info->ap_mld_addr : + (info->links[0].bss ? + info->links[0].bss->bssid : + info->links[0].bssid); + + if (info->valid_links) { + for_each_valid_link(info, link) { + /* Nested attribute header */ + link_info_size += NLA_HDRLEN; + /* Link ID */ + link_info_size += nla_total_size(sizeof(u8)); + link_info_size += info->links[link].addr ? + nla_total_size(ETH_ALEN) : 0; + link_info_size += (info->links[link].bssid || + info->links[link].bss) ? + nla_total_size(ETH_ALEN) : 0; + } + } msg = nlmsg_new(100 + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + - (info->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); + (info->fils.pmkid ? WLAN_PMKID_LEN : 0) + + link_info_size, gfp); if (!msg) return; @@ -17378,7 +17454,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || - nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, connected_addr) || (info->req_ie && nla_put(msg, NL80211_ATTR_REQ_IE, info->req_ie_len, info->req_ie)) || @@ -17397,6 +17473,38 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, info->fils.pmkid))) goto nla_put_failure; + if (info->valid_links) { + int i = 1; + struct nlattr *nested; + + nested = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); + if (!nested) + goto nla_put_failure; + + for_each_valid_link(info, link) { + struct nlattr *nested_mlo_links; + const u8 *bssid = info->links[link].bss ? + info->links[link].bss->bssid : + info->links[link].bssid; + + nested_mlo_links = nla_nest_start(msg, i); + if (!nested_mlo_links) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link) || + (bssid && + nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, bssid)) || + (info->links[link].addr && + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, + info->links[link].addr))) + goto nla_put_failure; + + nla_nest_end(msg, nested_mlo_links); + i++; + } + nla_nest_end(msg, nested); + } + genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, diff --git a/net/wireless/sme.c b/net/wireless/sme.c index b3c6ce4f85ee..00be498aab2e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -275,7 +275,7 @@ void cfg80211_conn_work(struct work_struct *work) memset(&cr, 0, sizeof(cr)); cr.status = -1; - cr.bssid = bssid; + cr.links[0].bssid = bssid; cr.timeout_reason = treason; __cfg80211_connect_result(wdev->netdev, &cr, false); } @@ -384,7 +384,7 @@ void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) memset(&cr, 0, sizeof(cr)); cr.status = status_code; - cr.bssid = mgmt->bssid; + cr.links[0].bssid = mgmt->bssid; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; __cfg80211_connect_result(wdev->netdev, &cr, false); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { @@ -698,6 +698,20 @@ static void disconnect_work(struct work_struct *work) DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +static void +cfg80211_connect_result_release_bsses(struct wireless_dev *wdev, + struct cfg80211_connect_resp_params *cr) +{ + unsigned int link; + + for_each_valid_link(cr, link) { + if (!cr->links[link].bss) + continue; + cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); + cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); + } +} + /* * API calls for drivers implementing connect/disconnect and * SME event handling @@ -715,21 +729,33 @@ void __cfg80211_connect_result(struct net_device *dev, #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif + unsigned int link; + const u8 *connected_addr; + bool bss_not_found = false; ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && - wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) { - cfg80211_put_bss(wdev->wiphy, cr->bss); - return; + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) + goto out; + + if (cr->valid_links) { + if (WARN_ON(!cr->ap_mld_addr)) + goto out; + + for_each_valid_link(cr, link) { + if (WARN_ON(!cr->links[link].addr)) + goto out; + } } wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); + connected_addr = cr->valid_links ? cr->ap_mld_addr : cr->links[0].bssid; #ifdef CONFIG_CFG80211_WEXT - if (wextev) { + if (wextev && !cr->valid_links) { if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->req_ie_len; @@ -746,23 +772,38 @@ void __cfg80211_connect_result(struct net_device *dev, memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; - if (cr->bssid && cr->status == WLAN_STATUS_SUCCESS) { - memcpy(wrqu.ap_addr.sa_data, cr->bssid, ETH_ALEN); - memcpy(wdev->wext.prev_bssid, cr->bssid, ETH_ALEN); + if (connected_addr && cr->status == WLAN_STATUS_SUCCESS) { + memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); + memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif - if (!cr->bss && (cr->status == WLAN_STATUS_SUCCESS)) { - WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); - cr->bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->bssid, - wdev->u.client.ssid, wdev->u.client.ssid_len, - wdev->conn_bss_type, - IEEE80211_PRIVACY_ANY); - if (cr->bss) - cfg80211_hold_bss(bss_from_pub(cr->bss)); + if (cr->status == WLAN_STATUS_SUCCESS) { + for_each_valid_link(cr, link) { + if (WARN_ON_ONCE(!cr->links[link].bss)) + break; + } + + for_each_valid_link(cr, link) { + if (cr->links[link].bss) + continue; + + cr->links[link].bss = + cfg80211_get_bss(wdev->wiphy, NULL, + cr->links[link].bssid, + wdev->u.client.ssid, + wdev->u.client.ssid_len, + wdev->conn_bss_type, + IEEE80211_PRIVACY_ANY); + if (!cr->links[link].bss) { + bss_not_found = true; + break; + } + cfg80211_hold_bss(bss_from_pub(cr->links[link].bss)); + } } cfg80211_wdev_release_bsses(wdev); @@ -772,26 +813,40 @@ void __cfg80211_connect_result(struct net_device *dev, wdev->connect_keys = NULL; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; - if (cr->bss) { - cfg80211_unhold_bss(bss_from_pub(cr->bss)); - cfg80211_put_bss(wdev->wiphy, cr->bss); - } + cfg80211_connect_result_release_bsses(wdev, cr); cfg80211_sme_free(wdev); return; } - if (WARN_ON(!cr->bss)) + if (WARN_ON(bss_not_found)) { + cfg80211_connect_result_release_bsses(wdev, cr); return; + } - wdev->links[0].client.current_bss = bss_from_pub(cr->bss); + memset(wdev->links, 0, sizeof(wdev->links)); + wdev->valid_links = cr->valid_links; + for_each_valid_link(cr, link) + wdev->links[link].client.current_bss = + bss_from_pub(cr->links[link].bss); wdev->connected = true; - ether_addr_copy(wdev->u.client.connected_addr, cr->bss->bssid); + ether_addr_copy(wdev->u.client.connected_addr, connected_addr); + if (cr->valid_links) { + for_each_valid_link(cr, link) + memcpy(wdev->links[link].addr, cr->links[link].addr, + ETH_ALEN); + } if (!(wdev->wiphy->flags & WIPHY_FLAG_HAS_STATIC_WEP)) cfg80211_upload_connect_keys(wdev); rcu_read_lock(); - country_elem = ieee80211_bss_get_elem(cr->bss, WLAN_EID_COUNTRY); + for_each_valid_link(cr, link) { + country_elem = + ieee80211_bss_get_elem(cr->links[link].bss, + WLAN_EID_COUNTRY); + if (country_elem) + break; + } if (!country_elem) { rcu_read_unlock(); return; @@ -804,12 +859,60 @@ void __cfg80211_connect_result(struct net_device *dev, if (!country_data) return; - regulatory_hint_country_ie(wdev->wiphy, cr->bss->channel->band, + regulatory_hint_country_ie(wdev->wiphy, + cr->links[link].bss->channel->band, country_data, country_datalen); kfree(country_data); + + return; +out: + for_each_valid_link(cr, link) + cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } -/* Consumes bss object one way or another */ +static void cfg80211_update_link_bss(struct wireless_dev *wdev, + struct cfg80211_bss **bss) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_internal_bss *ibss; + + if (!*bss) + return; + + ibss = bss_from_pub(*bss); + if (list_empty(&ibss->list)) { + struct cfg80211_bss *found = NULL, *tmp = *bss; + + found = cfg80211_get_bss(wdev->wiphy, NULL, + (*bss)->bssid, + wdev->u.client.ssid, + wdev->u.client.ssid_len, + wdev->conn_bss_type, + IEEE80211_PRIVACY_ANY); + if (found) { + /* The same BSS is already updated so use it + * instead, as it has latest info. + */ + *bss = found; + } else { + /* Update with BSS provided by driver, it will + * be freshly added and ref cnted, we can free + * the old one. + * + * signal_valid can be false, as we are not + * expecting the BSS to be found. + * + * keep the old timestamp to avoid confusion + */ + cfg80211_bss_update(rdev, ibss, false, + ibss->ts); + } + + cfg80211_put_bss(wdev->wiphy, tmp); + } +} + +/* Consumes bss object(s) one way or another */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp) @@ -819,55 +922,34 @@ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_event *ev; unsigned long flags; u8 *next; + size_t link_info_size = 0; + unsigned int link; - if (params->bss) { - struct cfg80211_internal_bss *ibss = bss_from_pub(params->bss); - - if (list_empty(&ibss->list)) { - struct cfg80211_bss *found = NULL, *tmp = params->bss; - - found = cfg80211_get_bss(wdev->wiphy, NULL, - params->bss->bssid, - wdev->u.client.ssid, wdev->u.client.ssid_len, - wdev->conn_bss_type, - IEEE80211_PRIVACY_ANY); - if (found) { - /* The same BSS is already updated so use it - * instead, as it has latest info. - */ - params->bss = found; - } else { - /* Update with BSS provided by driver, it will - * be freshly added and ref cnted, we can free - * the old one. - * - * signal_valid can be false, as we are not - * expecting the BSS to be found. - * - * keep the old timestamp to avoid confusion - */ - cfg80211_bss_update(rdev, ibss, false, - ibss->ts); - } - - cfg80211_put_bss(wdev->wiphy, tmp); - } + for_each_valid_link(params, link) { + cfg80211_update_link_bss(wdev, ¶ms->links[link].bss); + link_info_size += params->links[link].bssid ? ETH_ALEN : 0; + link_info_size += params->links[link].addr ? ETH_ALEN : 0; } - ev = kzalloc(sizeof(*ev) + (params->bssid ? ETH_ALEN : 0) + + ev = kzalloc(sizeof(*ev) + (params->ap_mld_addr ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + params->fils.kek_len + params->fils.pmk_len + - (params->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); + (params->fils.pmkid ? WLAN_PMKID_LEN : 0) + link_info_size, + gfp); + if (!ev) { - cfg80211_put_bss(wdev->wiphy, params->bss); + for_each_valid_link(params, link) + cfg80211_put_bss(wdev->wiphy, + params->links[link].bss); return; } ev->type = EVENT_CONNECT_RESULT; next = ((u8 *)ev) + sizeof(*ev); - if (params->bssid) { - ev->cr.bssid = next; - memcpy((void *)ev->cr.bssid, params->bssid, ETH_ALEN); + if (params->ap_mld_addr) { + ev->cr.ap_mld_addr = next; + memcpy((void *)ev->cr.ap_mld_addr, params->ap_mld_addr, + ETH_ALEN); next += ETH_ALEN; } if (params->req_ie_len) { @@ -907,9 +989,28 @@ void cfg80211_connect_done(struct net_device *dev, ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; if (params->fils.update_erp_next_seq_num) ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; - if (params->bss) - cfg80211_hold_bss(bss_from_pub(params->bss)); - ev->cr.bss = params->bss; + ev->cr.valid_links = params->valid_links; + for_each_valid_link(params, link) { + if (params->links[link].bss) + cfg80211_hold_bss( + bss_from_pub(params->links[link].bss)); + ev->cr.links[link].bss = params->links[link].bss; + + if (params->links[link].addr) { + ev->cr.links[link].addr = next; + memcpy((void *)ev->cr.links[link].addr, + params->links[link].addr, + ETH_ALEN); + next += ETH_ALEN; + } + if (params->links[link].bssid) { + ev->cr.links[link].bssid = next; + memcpy((void *)ev->cr.links[link].bssid, + params->links[link].bssid, + ETH_ALEN); + next += ETH_ALEN; + } + } ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; @@ -927,6 +1028,9 @@ void __cfg80211_roamed(struct wireless_dev *wdev, #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif + unsigned int link; + const u8 *connected_addr; + ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && @@ -936,48 +1040,76 @@ void __cfg80211_roamed(struct wireless_dev *wdev, if (WARN_ON(!wdev->connected)) goto out; + if (info->valid_links) { + if (WARN_ON(!info->ap_mld_addr)) + goto out; + + for_each_valid_link(info, link) { + if (WARN_ON(!info->links[link].addr)) + goto out; + } + } + cfg80211_wdev_release_bsses(wdev); - if (WARN_ON(!info->bss)) - return; + for_each_valid_link(info, link) { + if (WARN_ON(!info->links[link].bss)) + goto out; + } - cfg80211_hold_bss(bss_from_pub(info->bss)); - wdev->links[0].client.current_bss = bss_from_pub(info->bss); - ether_addr_copy(wdev->u.client.connected_addr, info->bss->bssid); + memset(wdev->links, 0, sizeof(wdev->links)); + wdev->valid_links = info->valid_links; + for_each_valid_link(info, link) { + cfg80211_hold_bss(bss_from_pub(info->links[link].bss)); + wdev->links[link].client.current_bss = + bss_from_pub(info->links[link].bss); + } + connected_addr = info->valid_links ? + info->ap_mld_addr : + info->links[0].bss->bssid; + ether_addr_copy(wdev->u.client.connected_addr, connected_addr); + if (info->valid_links) { + for_each_valid_link(info, link) + memcpy(wdev->links[link].addr, info->links[link].addr, + ETH_ALEN); + } wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT - if (info->req_ie) { - memset(&wrqu, 0, sizeof(wrqu)); - wrqu.data.length = info->req_ie_len; - wireless_send_event(wdev->netdev, IWEVASSOCREQIE, - &wrqu, info->req_ie); - } + if (!info->valid_links) { + if (info->req_ie) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = info->req_ie_len; + wireless_send_event(wdev->netdev, IWEVASSOCREQIE, + &wrqu, info->req_ie); + } + + if (info->resp_ie) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = info->resp_ie_len; + wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, + &wrqu, info->resp_ie); + } - if (info->resp_ie) { memset(&wrqu, 0, sizeof(wrqu)); - wrqu.data.length = info->resp_ie_len; - wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, - &wrqu, info->resp_ie); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; + memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); + memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); + wdev->wext.prev_bssid_valid = true; + wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); } - - memset(&wrqu, 0, sizeof(wrqu)); - wrqu.ap_addr.sa_family = ARPHRD_ETHER; - memcpy(wrqu.ap_addr.sa_data, info->bss->bssid, ETH_ALEN); - memcpy(wdev->wext.prev_bssid, info->bss->bssid, ETH_ALEN); - wdev->wext.prev_bssid_valid = true; - wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); #endif return; out: - cfg80211_put_bss(wdev->wiphy, info->bss); + for_each_valid_link(info, link) + cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } -/* Consumes info->bss object one way or another */ +/* Consumes info->links.bss object(s) one way or another */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp) { @@ -986,25 +1118,41 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, struct cfg80211_event *ev; unsigned long flags; u8 *next; + unsigned int link; + size_t link_info_size = 0; + bool bss_not_found = false; + + for_each_valid_link(info, link) { + link_info_size += info->links[link].addr ? ETH_ALEN : 0; + link_info_size += info->links[link].bssid ? ETH_ALEN : 0; - if (!info->bss) { - info->bss = cfg80211_get_bss(wdev->wiphy, info->channel, - info->bssid, wdev->u.client.ssid, - wdev->u.client.ssid_len, - wdev->conn_bss_type, - IEEE80211_PRIVACY_ANY); + if (info->links[link].bss) + continue; + + info->links[link].bss = + cfg80211_get_bss(wdev->wiphy, + info->links[link].channel, + info->links[link].bssid, + wdev->u.client.ssid, + wdev->u.client.ssid_len, + wdev->conn_bss_type, + IEEE80211_PRIVACY_ANY); + + if (!info->links[link].bss) { + bss_not_found = true; + break; + } } - if (WARN_ON(!info->bss)) - return; + if (WARN_ON(bss_not_found)) + goto out; ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + - (info->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); - if (!ev) { - cfg80211_put_bss(wdev->wiphy, info->bss); - return; - } + (info->fils.pmkid ? WLAN_PMKID_LEN : 0) + + (info->ap_mld_addr ? ETH_ALEN : 0) + link_info_size, gfp); + if (!ev) + goto out; ev->type = EVENT_ROAMED; next = ((u8 *)ev) + sizeof(*ev); @@ -1044,12 +1192,43 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; if (info->fils.update_erp_next_seq_num) ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; - ev->rm.bss = info->bss; + if (info->ap_mld_addr) { + ev->rm.ap_mld_addr = next; + memcpy((void *)ev->rm.ap_mld_addr, info->ap_mld_addr, + ETH_ALEN); + next += ETH_ALEN; + } + ev->rm.valid_links = info->valid_links; + for_each_valid_link(info, link) { + ev->rm.links[link].bss = info->links[link].bss; + + if (info->links[link].addr) { + ev->rm.links[link].addr = next; + memcpy((void *)ev->rm.links[link].addr, + info->links[link].addr, + ETH_ALEN); + next += ETH_ALEN; + } + + if (info->links[link].bssid) { + ev->rm.links[link].bssid = next; + memcpy((void *)ev->rm.links[link].bssid, + info->links[link].bssid, + ETH_ALEN); + next += ETH_ALEN; + } + } spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); + + return; +out: + for_each_valid_link(info, link) + cfg80211_put_bss(wdev->wiphy, info->links[link].bss); + } EXPORT_SYMBOL(cfg80211_roamed); -- cgit v1.2.3 From e6445be4f549a0342cd9b8672b82e3b1d85d017f Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Sat, 11 Jun 2022 22:14:08 +0800 Subject: media: uapi: Add some RGB bus formats for i.MX8qm/qxp pixel combiner This patch adds RGB666_1X30_CPADLO, RGB888_1X30_CPADLO, RGB666_1X36_CPADLO and RGB888_1X36_CPADLO bus formats used by i.MX8qm/qxp pixel combiner. The RGB pixels with padding low per component are transmitted on a 30-bit input bus(10-bit per component) from a display controller or a 36-bit output bus(12-bit per component) to a pixel link. Reviewed-by: Robert Foss Reviewed-by: Laurent Pinchart Signed-off-by: Liu Ying Acked-by: Sakari Ailus Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20220611141421.718743-2-victor.liu@nxp.com --- include/uapi/linux/media-bus-format.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index 0dfc11ee243a..ec3323dbb927 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x101e */ +/* RGB - next is 0x1022 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -59,9 +59,13 @@ #define MEDIA_BUS_FMT_RGB888_3X8_DELTA 0x101d #define MEDIA_BUS_FMT_RGB888_1X7X4_SPWG 0x1011 #define MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA 0x1012 +#define MEDIA_BUS_FMT_RGB666_1X30_CPADLO 0x101e +#define MEDIA_BUS_FMT_RGB888_1X30_CPADLO 0x101f #define MEDIA_BUS_FMT_ARGB8888_1X32 0x100d #define MEDIA_BUS_FMT_RGB888_1X32_PADHI 0x100f #define MEDIA_BUS_FMT_RGB101010_1X30 0x1018 +#define MEDIA_BUS_FMT_RGB666_1X36_CPADLO 0x1020 +#define MEDIA_BUS_FMT_RGB888_1X36_CPADLO 0x1021 #define MEDIA_BUS_FMT_RGB121212_1X36 0x1019 #define MEDIA_BUS_FMT_RGB161616_1X48 0x101a -- cgit v1.2.3 From 084cc29f8bbb034cf30a7ee07a816c115e0c28df Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 13 Jun 2022 21:25:21 +0000 Subject: KVM: x86/MMU: Allow NX huge pages to be disabled on a per-vm basis In some cases, the NX hugepage mitigation for iTLB multihit is not needed for all guests on a host. Allow disabling the mitigation on a per-VM basis to avoid the performance hit of NX hugepages on trusted workloads. In order to disable NX hugepages on a VM, ensure that the userspace actor has permission to reboot the system. Since disabling NX hugepages would allow a guest to crash the system, it is similar to reboot permissions. Ideally, KVM would require userspace to prove it has access to KVM's nx_huge_pages module param, e.g. so that userspace can opt out without needing full reboot permissions. But getting access to the module param file info is difficult because it is buried in layers of sysfs and module glue. Requiring CAP_SYS_BOOT is sufficient for all known use cases. Suggested-by: Jim Mattson Reviewed-by: David Matlack Reviewed-by: Peter Xu Signed-off-by: Ben Gardon Message-Id: <20220613212523.3436117-9-bgardon@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 16 ++++++++++++++++ arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/mmu/mmu_internal.h | 7 ++++--- arch/x86/kvm/mmu/spte.c | 7 ++++--- arch/x86/kvm/mmu/spte.h | 3 ++- arch/x86/kvm/mmu/tdp_mmu.c | 2 +- arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 8 files changed, 60 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 320cb04f7bd9..bafaeedd455c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8206,6 +8206,22 @@ PV guests. The `KVM_PV_DUMP` command is available for the dump related UV data. Also the vcpu ioctl `KVM_S390_PV_CPU_COMMAND` is available and supports the `KVM_PV_DUMP_CPU` subcommand. +8.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES +--------------------------- + +:Capability KVM_CAP_VM_DISABLE_NX_HUGE_PAGES +:Architectures: x86 +:Type: vm +:Parameters: arg[0] must be 0. +:Returns 0 on success, -EPERM if the userspace process does not + have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been + created. + +This capability disables the NX huge pages mitigation for iTLB MULTIHIT. + +The capability has no effect if the nx_huge_pages module parameter is not set. + +This capability may only be set before any vCPUs are created. 9. Known KVM API problems ========================= diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e37727a74d0a..7e4c31b57a75 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1336,6 +1336,8 @@ struct kvm_arch { * the global KVM_MAX_VCPU_IDS may lead to significant memory waste. */ u32 max_vcpu_ids; + + bool disable_nx_huge_pages; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 5e1e3c8f8aaa..bb9d12ac0db3 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -155,9 +155,9 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); extern int nx_huge_pages; -static inline bool is_nx_huge_page_enabled(void) +static inline bool is_nx_huge_page_enabled(struct kvm *kvm) { - return READ_ONCE(nx_huge_pages); + return READ_ONCE(nx_huge_pages) && !kvm->arch.disable_nx_huge_pages; } struct kvm_page_fault { @@ -256,7 +256,8 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .user = err & PFERR_USER_MASK, .prefetch = prefetch, .is_tdp = likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault), - .nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(), + .nx_huge_page_workaround_enabled = + is_nx_huge_page_enabled(vcpu->kvm), .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 242e4828d7df..db294c1beea2 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -147,7 +147,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, spte |= spte_shadow_accessed_mask(spte); if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) && - is_nx_huge_page_enabled()) { + is_nx_huge_page_enabled(vcpu->kvm)) { pte_access &= ~ACC_EXEC_MASK; } @@ -246,7 +246,8 @@ static u64 make_spte_executable(u64 spte) * This is used during huge page splitting to build the SPTEs that make up the * new page table. */ -u64 make_huge_page_split_spte(u64 huge_spte, int huge_level, int index) +u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte, int huge_level, + int index) { u64 child_spte; int child_level; @@ -274,7 +275,7 @@ u64 make_huge_page_split_spte(u64 huge_spte, int huge_level, int index) * When splitting to a 4K page, mark the page executable as the * NX hugepage mitigation no longer applies. */ - if (is_nx_huge_page_enabled()) + if (is_nx_huge_page_enabled(kvm)) child_spte = make_spte_executable(child_spte); } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 121c5eaaec77..256f90587e8d 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -421,7 +421,8 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); -u64 make_huge_page_split_spte(u64 huge_spte, int huge_level, int index); +u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte, int huge_level, + int index); u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled); u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access); u64 mark_spte_for_access_track(u64 spte); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 1ea40809ef1f..522e2532343b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1478,7 +1478,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, * not been linked in yet and thus is not reachable from any other CPU. */ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) - sp->spt[i] = make_huge_page_split_spte(huge_spte, level, i); + sp->spt[i] = make_huge_page_split_spte(kvm, huge_spte, level, i); /* * Replace the huge spte with a pointer to the populated lower level diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c1b3b2ea8ee0..7ce0c6fe166d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4324,6 +4324,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SYS_ATTRIBUTES: case KVM_CAP_VAPIC: case KVM_CAP_ENABLE_CAP: + case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -6184,6 +6185,35 @@ split_irqchip_unlock: } mutex_unlock(&kvm->lock); break; + case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: + r = -EINVAL; + + /* + * Since the risk of disabling NX hugepages is a guest crashing + * the system, ensure the userspace process has permission to + * reboot the system. + * + * Note that unlike the reboot() syscall, the process must have + * this capability in the root namespace because exposing + * /dev/kvm into a container does not limit the scope of the + * iTLB multihit bug to that container. In other words, + * this must use capable(), not ns_capable(). + */ + if (!capable(CAP_SYS_BOOT)) { + r = -EPERM; + break; + } + + if (cap->args[0]) + break; + + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + kvm->arch.disable_nx_huge_pages = true; + r = 0; + } + mutex_unlock(&kvm->lock); + break; default: r = -EINVAL; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7569b4ec199c..a36e78710382 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1166,6 +1166,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_DUMP 217 #define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218 #define KVM_CAP_X86_NOTIFY_VMEXIT 219 +#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 0a2ff7cc8ad48a86939a91bd3457f38e59e741a1 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 21 Jun 2022 15:49:19 +0800 Subject: Bonding: add per-port priority for failover re-selection Add per port priority support for bonding active slave re-selection during failover. A higher number means higher priority in selection. The primary slave still has the highest priority. This option also follows the primary_reselect rules. This option could only be configured via netlink. Signed-off-by: Hangbin Liu Acked-by: Jonathan Toppins Signed-off-by: David S. Miller --- Documentation/networking/bonding.rst | 11 +++++++++++ drivers/net/bonding/bond_main.c | 27 +++++++++++++++++++++++++++ drivers/net/bonding/bond_netlink.c | 15 +++++++++++++++ drivers/net/bonding/bond_options.c | 33 +++++++++++++++++++++++++++++++++ include/net/bond_options.h | 1 + include/net/bonding.h | 1 + include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 8 files changed, 90 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 43be3782e5df..53a18ff7cf23 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -780,6 +780,17 @@ peer_notif_delay value is 0 which means to match the value of the link monitor interval. +prio + Slave priority. A higher number means higher priority. + The primary slave has the highest priority. This option also + follows the primary_reselect rules. + + This option could only be configured via netlink, and is only valid + for active-backup(1), balance-tlb (5) and balance-alb (6) mode. + The valid value range is a signed 32 bit integer. + + The default value is 0. + primary A string (eth0, eth2, etc) specifying which slave is the diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index dc3e9a06e1aa..e75acb14d066 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1026,12 +1026,38 @@ out: } +/** + * bond_choose_primary_or_current - select the primary or high priority slave + * @bond: our bonding struct + * + * - Check if there is a primary link. If the primary link was set and is up, + * go on and do link reselection. + * + * - If primary link is not set or down, find the highest priority link. + * If the highest priority link is not current slave, set it as primary + * link and do link reselection. + */ static struct slave *bond_choose_primary_or_current(struct bonding *bond) { struct slave *prim = rtnl_dereference(bond->primary_slave); struct slave *curr = rtnl_dereference(bond->curr_active_slave); + struct slave *slave, *hprio = NULL; + struct list_head *iter; if (!prim || prim->link != BOND_LINK_UP) { + bond_for_each_slave(bond, slave, iter) { + if (slave->link == BOND_LINK_UP) { + hprio = hprio ?: slave; + if (slave->prio > hprio->prio) + hprio = slave; + } + } + + if (hprio && hprio != curr) { + prim = hprio; + goto link_reselect; + } + if (!curr || curr->link != BOND_LINK_UP) return NULL; return curr; @@ -1042,6 +1068,7 @@ static struct slave *bond_choose_primary_or_current(struct bonding *bond) return prim; } +link_reselect: if (!curr || curr->link != BOND_LINK_UP) return prim; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 5a6f44455b95..c2d080fc4fc4 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -27,6 +27,7 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev, nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */ + nla_total_size(sizeof(s32)) + /* IFLA_BOND_SLAVE_PRIO */ 0; } @@ -53,6 +54,9 @@ static int bond_fill_slave_info(struct sk_buff *skb, if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id)) goto nla_put_failure; + if (nla_put_s32(skb, IFLA_BOND_SLAVE_PRIO, slave->prio)) + goto nla_put_failure; + if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { const struct aggregator *agg; const struct port *ad_port; @@ -117,6 +121,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { [IFLA_BOND_SLAVE_QUEUE_ID] = { .type = NLA_U16 }, + [IFLA_BOND_SLAVE_PRIO] = { .type = NLA_S32 }, }; static int bond_validate(struct nlattr *tb[], struct nlattr *data[], @@ -157,6 +162,16 @@ static int bond_slave_changelink(struct net_device *bond_dev, return err; } + if (data[IFLA_BOND_SLAVE_PRIO]) { + int prio = nla_get_s32(data[IFLA_BOND_SLAVE_PRIO]); + + bond_opt_slave_initval(&newval, &slave_dev, prio); + err = __bond_opt_set(bond, BOND_OPT_PRIO, &newval, + data[IFLA_BOND_SLAVE_PRIO], extack); + if (err) + return err; + } + return 0; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 96eef19cffc4..3498db1c1b3c 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -40,6 +40,8 @@ static int bond_option_arp_validate_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_arp_all_targets_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_prio_set(struct bonding *bond, + const struct bond_opt_value *newval); static int bond_option_primary_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_primary_reselect_set(struct bonding *bond, @@ -365,6 +367,16 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_intmax_tbl, .set = bond_option_miimon_set }, + [BOND_OPT_PRIO] = { + .id = BOND_OPT_PRIO, + .name = "prio", + .desc = "Link priority for failover re-selection", + .flags = BOND_OPTFLAG_RAWVAL, + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) | + BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB)), + .set = bond_option_prio_set + }, [BOND_OPT_PRIMARY] = { .id = BOND_OPT_PRIMARY, .name = "primary", @@ -1306,6 +1318,27 @@ static int bond_option_missed_max_set(struct bonding *bond, return 0; } +static int bond_option_prio_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + struct slave *slave; + + slave = bond_slave_get_rtnl(newval->slave_dev); + if (!slave) { + netdev_dbg(newval->slave_dev, "%s called on NULL slave\n", __func__); + return -ENODEV; + } + slave->prio = newval->value; + + if (rtnl_dereference(bond->primary_slave)) + slave_warn(bond->dev, slave->dev, + "prio updated, but will not affect failover re-selection as primary slave have been set\n"); + else + bond_select_active_slave(bond); + + return 0; +} + static int bond_option_primary_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/include/net/bond_options.h b/include/net/bond_options.h index eade8236a4df..d2aea5cf1e41 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -67,6 +67,7 @@ enum { BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, BOND_OPT_NS_TARGETS, + BOND_OPT_PRIO, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index cb904d356e31..6e78d657aa05 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -178,6 +178,7 @@ struct slave { u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; + int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5f58dcfe2787..e36d9d2c65a7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -963,6 +963,7 @@ enum { IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + IFLA_BOND_SLAVE_PRIO, __IFLA_BOND_SLAVE_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b339bf2196ca..0242f31e339c 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -890,6 +890,7 @@ enum { IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + IFLA_BOND_SLAVE_PRIO, __IFLA_BOND_SLAVE_MAX, }; -- cgit v1.2.3 From a08d6a6dc82036cbd889fe3d53f9c69dc13436eb Mon Sep 17 00:00:00 2001 From: Clément Léger Date: Fri, 24 Jun 2022 16:39:48 +0200 Subject: net: dsa: add Renesas RZ/N1 switch tag driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The switch that is present on the Renesas RZ/N1 SoC uses a specific VLAN value followed by 6 bytes which contains forwarding configuration. Signed-off-by: Clément Léger Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 2 + include/uapi/linux/if_ether.h | 1 + net/dsa/Kconfig | 7 +++ net/dsa/Makefile | 1 + net/dsa/tag_rzn1_a5psw.c | 113 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 124 insertions(+) create mode 100644 net/dsa/tag_rzn1_a5psw.c (limited to 'include/uapi/linux') diff --git a/include/net/dsa.h b/include/net/dsa.h index 64da5ed27fdc..33283eeda697 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -53,6 +53,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 +#define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -81,6 +82,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, + DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, }; struct dsa_switch; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 1d0bccc3fa54..d370165bc621 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -116,6 +116,7 @@ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_DSA_8021Q 0xDADB /* Fake VLAN Header for DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_DSA_A5PSW 0xE001 /* A5PSW Tag Value [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 8cb87b5067ee..63853fff4e2f 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -132,6 +132,13 @@ config NET_DSA_TAG_RTL8_4 Say Y or M if you want to enable support for tagging frames for Realtek switches with 8 byte protocol 4 tags, such as the Realtek RTL8365MB-VC. +config NET_DSA_TAG_RZN1_A5PSW + tristate "Tag driver for Renesas RZ/N1 A5PSW switch" + help + Say Y or M if you want to enable support for tagging frames for + Renesas RZ/N1 embedded switch that uses an 8 byte tag located after + destination MAC address. + config NET_DSA_TAG_LAN9303 tristate "Tag driver for SMSC/Microchip LAN9303 family of switches" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9f75820e7c98..af28c24ead18 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o +obj-$(CONFIG_NET_DSA_TAG_RZN1_A5PSW) += tag_rzn1_a5psw.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c new file mode 100644 index 000000000000..e2a5ee6ae688 --- /dev/null +++ b/net/dsa/tag_rzn1_a5psw.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 Schneider Electric + * + * Clément Léger + */ + +#include +#include +#include +#include + +#include "dsa_priv.h" + +/* To define the outgoing port and to discover the incoming port a TAG is + * inserted after Src MAC : + * + * Dest MAC Src MAC TAG Type + * ...| 1 2 3 4 5 6 | 1 2 3 4 5 6 | 1 2 3 4 5 6 7 8 | 1 2 |... + * |<--------------->| + * + * See struct a5psw_tag for layout + */ + +#define ETH_P_DSA_A5PSW 0xE001 +#define A5PSW_TAG_LEN 8 +#define A5PSW_CTRL_DATA_FORCE_FORWARD BIT(0) +/* This is both used for xmit tag and rcv tagging */ +#define A5PSW_CTRL_DATA_PORT GENMASK(3, 0) + +struct a5psw_tag { + __be16 ctrl_tag; + __be16 ctrl_data; + __be16 ctrl_data2_hi; + __be16 ctrl_data2_lo; +}; + +static struct sk_buff *a5psw_tag_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct a5psw_tag *ptag; + u32 data2_val; + + BUILD_BUG_ON(sizeof(*ptag) != A5PSW_TAG_LEN); + + /* The Ethernet switch we are interfaced with needs packets to be at + * least 60 bytes otherwise they will be discarded when they enter the + * switch port logic. + */ + if (__skb_put_padto(skb, ETH_ZLEN, false)) + return NULL; + + /* provide 'A5PSW_TAG_LEN' bytes additional space */ + skb_push(skb, A5PSW_TAG_LEN); + + /* make room between MACs and Ether-Type to insert tag */ + dsa_alloc_etype_header(skb, A5PSW_TAG_LEN); + + ptag = dsa_etype_header_pos_tx(skb); + + data2_val = FIELD_PREP(A5PSW_CTRL_DATA_PORT, BIT(dp->index)); + ptag->ctrl_tag = htons(ETH_P_DSA_A5PSW); + ptag->ctrl_data = htons(A5PSW_CTRL_DATA_FORCE_FORWARD); + ptag->ctrl_data2_lo = htons(data2_val); + ptag->ctrl_data2_hi = 0; + + return skb; +} + +static struct sk_buff *a5psw_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + struct a5psw_tag *tag; + int port; + + if (unlikely(!pskb_may_pull(skb, A5PSW_TAG_LEN))) { + dev_warn_ratelimited(&dev->dev, + "Dropping packet, cannot pull\n"); + return NULL; + } + + tag = dsa_etype_header_pos_rx(skb); + + if (tag->ctrl_tag != htons(ETH_P_DSA_A5PSW)) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid TAG marker\n"); + return NULL; + } + + port = FIELD_GET(A5PSW_CTRL_DATA_PORT, ntohs(tag->ctrl_data)); + + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; + + skb_pull_rcsum(skb, A5PSW_TAG_LEN); + dsa_strip_etype_header(skb, A5PSW_TAG_LEN); + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops a5psw_netdev_ops = { + .name = "a5psw", + .proto = DSA_TAG_PROTO_RZN1_A5PSW, + .xmit = a5psw_tag_xmit, + .rcv = a5psw_tag_rcv, + .needed_headroom = A5PSW_TAG_LEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_A5PSW); +module_dsa_tag_driver(a5psw_netdev_ops); -- cgit v1.2.3 From e23ee9d2c4ccb08fdfee3aea0a04a27bccd77433 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 24 Jun 2022 23:54:21 +0300 Subject: serial: Use bits for UART_LSR_BRK_ERROR_BITS/MSR_ANY_DELTA MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of listing the bits for UART_LSR_BRK_ERROR_BITS and UART_MSR_ANY_DELTA in comment, use them to define instead. Reviewed-by: Jiri Slaby Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220624205424.12686-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_reg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index f51bc8f36813..bab3b39266cc 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -139,7 +139,7 @@ #define UART_LSR_PE 0x04 /* Parity error indicator */ #define UART_LSR_OE 0x02 /* Overrun error indicator */ #define UART_LSR_DR 0x01 /* Receiver data ready */ -#define UART_LSR_BRK_ERROR_BITS 0x1E /* BI, FE, PE, OE bits */ +#define UART_LSR_BRK_ERROR_BITS (UART_LSR_BI|UART_LSR_FE|UART_LSR_PE|UART_LSR_OE) #define UART_MSR 6 /* In: Modem Status Register */ #define UART_MSR_DCD 0x80 /* Data Carrier Detect */ @@ -150,7 +150,7 @@ #define UART_MSR_TERI 0x04 /* Trailing edge ring indicator */ #define UART_MSR_DDSR 0x02 /* Delta DSR */ #define UART_MSR_DCTS 0x01 /* Delta CTS */ -#define UART_MSR_ANY_DELTA 0x0F /* Any of the delta bits! */ +#define UART_MSR_ANY_DELTA (UART_MSR_DDCD|UART_MSR_TERI|UART_MSR_DDSR|UART_MSR_DCTS) #define UART_SCR 7 /* I/O: Scratch Register */ -- cgit v1.2.3 From 4f768e94774c58c9f7f54ebd38dadf172970046a Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 24 Jun 2022 23:42:09 +0300 Subject: serial: Support for RS-485 multipoint addresses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for RS-485 multipoint addressing using 9th bit [*]. The addressing mode is configured through ->rs485_config(). ADDRB in termios indicates 9th bit addressing mode is enabled. In this mode, 9th bit is used to indicate an address (byte) within the communication line. ADDRB can only be enabled/disabled through ->rs485_config() that is also responsible for setting the destination and receiver (filter) addresses. Add traps to detect unwanted changes to struct serial_rs485 layout using static_assert(). [*] Technically, RS485 is just an electronic spec and does not itself specify the 9th bit addressing mode but 9th bit seems at least "semi-standard" way to do addressing with RS485. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220624204210.11112-6-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/driver.rst | 2 ++ Documentation/driver-api/serial/serial-rs485.rst | 26 +++++++++++++++++++++++- drivers/tty/serial/serial_core.c | 22 +++++++++++++++++++- drivers/tty/tty_ioctl.c | 4 ++++ include/uapi/asm-generic/termbits-common.h | 1 + include/uapi/linux/serial.h | 20 ++++++++++++++++-- 6 files changed, 71 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/driver-api/serial/driver.rst b/Documentation/driver-api/serial/driver.rst index 1e7ab4142d49..ee1679858aa2 100644 --- a/Documentation/driver-api/serial/driver.rst +++ b/Documentation/driver-api/serial/driver.rst @@ -261,6 +261,8 @@ hardware. - parity enable PARODD - odd parity (when PARENB is in force) + ADDRB + - address bit (changed through .rs485_config()). CREAD - enable reception of characters (if not set, still receive characters from the port, but diff --git a/Documentation/driver-api/serial/serial-rs485.rst b/Documentation/driver-api/serial/serial-rs485.rst index 00b5d333acba..6ebad75c74ed 100644 --- a/Documentation/driver-api/serial/serial-rs485.rst +++ b/Documentation/driver-api/serial/serial-rs485.rst @@ -99,7 +99,31 @@ RS485 Serial Communications /* Error handling. See errno. */ } -5. References +5. Multipoint Addressing +======================== + + The Linux kernel provides addressing mode for multipoint RS-485 serial + communications line. The addressing mode is enabled with SER_RS485_ADDRB + flag in serial_rs485. Struct serial_rs485 has two additional flags and + fields for enabling receive and destination addresses. + + Address mode flags: + - SER_RS485_ADDRB: Enabled addressing mode (sets also ADDRB in termios). + - SER_RS485_ADDR_RECV: Receive (filter) address enabled. + - SER_RS485_ADDR_DEST: Set destination address. + + Address fields (enabled with corresponding SER_RS485_ADDR_* flag): + - addr_recv: Receive address. + - addr_dest: Destination address. + + Once a receive address is set, the communication can occur only with the + particular device and other peers are filtered out. It is left up to the + receiver side to enforce the filtering. Receive address will be cleared + if SER_RS485_ADDR_RECV is not set. + + Note: not all devices supporting RS485 support multipoint addressing. + +6. References ============= [1] include/uapi/linux/serial.h diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 2529153c8979..85ef7ef00b82 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1288,6 +1288,17 @@ static int uart_check_rs485_flags(struct uart_port *port, struct serial_rs485 *r if (flags & ~port->rs485_supported->flags) return -EINVAL; + /* Asking for address w/o addressing mode? */ + if (!(rs485->flags & SER_RS485_ADDRB) && + (rs485->flags & (SER_RS485_ADDR_RECV|SER_RS485_ADDR_DEST))) + return -EINVAL; + + /* Address given but not enabled? */ + if (!(rs485->flags & SER_RS485_ADDR_RECV) && rs485->addr_recv) + return -EINVAL; + if (!(rs485->flags & SER_RS485_ADDR_DEST) && rs485->addr_dest) + return -EINVAL; + return 0; } @@ -1343,7 +1354,8 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4 rs485->flags &= supported_flags; /* Return clean padding area to userspace */ - memset(rs485->padding, 0, sizeof(rs485->padding)); + memset(rs485->padding0, 0, sizeof(rs485->padding0)); + memset(rs485->padding1, 0, sizeof(rs485->padding1)); } int uart_rs485_config(struct uart_port *port) @@ -3402,5 +3414,13 @@ int uart_get_rs485_mode(struct uart_port *port) } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); +/* Compile-time assertions for serial_rs485 layout */ +static_assert(offsetof(struct serial_rs485, padding) == + (offsetof(struct serial_rs485, delay_rts_after_send) + sizeof(__u32))); +static_assert(offsetof(struct serial_rs485, padding1) == + offsetof(struct serial_rs485, padding[1])); +static_assert((offsetof(struct serial_rs485, padding[4]) + sizeof(__u32)) == + sizeof(struct serial_rs485)); + MODULE_DESCRIPTION("Serial driver core"); MODULE_LICENSE("GPL"); diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index adae687f654b..2a76b330e108 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -319,6 +319,8 @@ unsigned char tty_get_frame_size(unsigned int cflag) bits++; if (cflag & PARENB) bits++; + if (cflag & ADDRB) + bits++; return bits; } @@ -353,6 +355,8 @@ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) old_termios = tty->termios; tty->termios = *new_termios; unset_locked_termios(tty, &old_termios); + /* Reset any ADDRB changes, ADDRB is changed through ->rs485_config() */ + tty->termios.c_cflag ^= (tty->termios.c_cflag ^ old_termios.c_cflag) & ADDRB; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); diff --git a/include/uapi/asm-generic/termbits-common.h b/include/uapi/asm-generic/termbits-common.h index 4d084fe8def5..4a6a79f28b21 100644 --- a/include/uapi/asm-generic/termbits-common.h +++ b/include/uapi/asm-generic/termbits-common.h @@ -46,6 +46,7 @@ typedef unsigned int speed_t; #define EXTA B19200 #define EXTB B38400 +#define ADDRB 0x20000000 /* address bit */ #define CMSPAR 0x40000000 /* mark or space (stick) parity */ #define CRTSCTS 0x80000000 /* flow control */ diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index fa6b16e5fdd8..cea06924b295 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -126,10 +126,26 @@ struct serial_rs485 { #define SER_RS485_TERMINATE_BUS (1 << 5) /* Enable bus termination (if supported) */ + +/* RS-485 addressing mode */ +#define SER_RS485_ADDRB (1 << 6) /* Enable addressing mode */ +#define SER_RS485_ADDR_RECV (1 << 7) /* Receive address filter */ +#define SER_RS485_ADDR_DEST (1 << 8) /* Destination address */ + __u32 delay_rts_before_send; /* Delay before send (milliseconds) */ __u32 delay_rts_after_send; /* Delay after send (milliseconds) */ - __u32 padding[5]; /* Memory is cheap, new structs - are a royal PITA .. */ + + /* The fields below are defined by flags */ + union { + __u32 padding[5]; /* Memory is cheap, new structs are a pain */ + + struct { + __u8 addr_recv; + __u8 addr_dest; + __u8 padding0[2]; + __u32 padding1[4]; + }; + }; }; /* -- cgit v1.2.3 From 9864bb4801331daa48514face9d0f4861e4d485b Mon Sep 17 00:00:00 2001 From: Li Li Date: Thu, 26 May 2022 15:00:18 -0700 Subject: Binder: add TF_UPDATE_TXN to replace outdated txn When the target process is busy, incoming oneway transactions are queued in the async_todo list. If the clients continue sending extra oneway transactions while the target process is frozen, this queue can become too large to accommodate new transactions. That's why binder driver introduced ONEWAY_SPAM_DETECTION to detect this situation. It's helpful to debug the async binder buffer exhausting issue, but the issue itself isn't solved directly. In real cases applications are designed to send oneway transactions repeatedly, delivering updated inforamtion to the target process. Typical examples are Wi-Fi signal strength and some real time sensor data. Even if the apps might only care about the lastet information, all outdated oneway transactions are still accumulated there until the frozen process is thawed later. For this kind of situations, there's no existing method to skip those outdated transactions and deliver the latest one only. This patch introduces a new transaction flag TF_UPDATE_TXN. To use it, use apps can set this new flag along with TF_ONE_WAY. When such an oneway transaction is to be queued into the async_todo list of a frozen process, binder driver will check if any previous pending transactions can be superseded by comparing their code, flags and target node. If such an outdated pending transaction is found, the latest transaction will supersede that outdated one. This effectively prevents the async binder buffer running out and saves unnecessary binder read workloads. Acked-by: Todd Kjos Signed-off-by: Li Li Link: https://lore.kernel.org/r/20220526220018.3334775-2-dualli@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 85 +++++++++++++++++++++++++++++++++++-- drivers/android/binder_trace.h | 4 ++ include/uapi/linux/android/binder.h | 1 + 3 files changed, 87 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 362c0deb65f1..d4f84f25c30b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2626,6 +2626,56 @@ static int binder_fixup_parent(struct list_head *pf_head, return binder_add_fixup(pf_head, buffer_offset, bp->buffer, 0); } +/** + * binder_can_update_transaction() - Can a txn be superseded by an updated one? + * @t1: the pending async txn in the frozen process + * @t2: the new async txn to supersede the outdated pending one + * + * Return: true if t2 can supersede t1 + * false if t2 can not supersede t1 + */ +static bool binder_can_update_transaction(struct binder_transaction *t1, + struct binder_transaction *t2) +{ + if ((t1->flags & t2->flags & (TF_ONE_WAY | TF_UPDATE_TXN)) != + (TF_ONE_WAY | TF_UPDATE_TXN) || !t1->to_proc || !t2->to_proc) + return false; + if (t1->to_proc->tsk == t2->to_proc->tsk && t1->code == t2->code && + t1->flags == t2->flags && t1->buffer->pid == t2->buffer->pid && + t1->buffer->target_node->ptr == t2->buffer->target_node->ptr && + t1->buffer->target_node->cookie == t2->buffer->target_node->cookie) + return true; + return false; +} + +/** + * binder_find_outdated_transaction_ilocked() - Find the outdated transaction + * @t: new async transaction + * @target_list: list to find outdated transaction + * + * Return: the outdated transaction if found + * NULL if no outdated transacton can be found + * + * Requires the proc->inner_lock to be held. + */ +static struct binder_transaction * +binder_find_outdated_transaction_ilocked(struct binder_transaction *t, + struct list_head *target_list) +{ + struct binder_work *w; + + list_for_each_entry(w, target_list, entry) { + struct binder_transaction *t_queued; + + if (w->type != BINDER_WORK_TRANSACTION) + continue; + t_queued = container_of(w, struct binder_transaction, work); + if (binder_can_update_transaction(t_queued, t)) + return t_queued; + } + return NULL; +} + /** * binder_proc_transaction() - sends a transaction to a process and wakes it up * @t: transaction to send @@ -2651,6 +2701,7 @@ static int binder_proc_transaction(struct binder_transaction *t, struct binder_node *node = t->buffer->target_node; bool oneway = !!(t->flags & TF_ONE_WAY); bool pending_async = false; + struct binder_transaction *t_outdated = NULL; BUG_ON(!node); binder_node_lock(node); @@ -2678,12 +2729,24 @@ static int binder_proc_transaction(struct binder_transaction *t, if (!thread && !pending_async) thread = binder_select_thread_ilocked(proc); - if (thread) + if (thread) { binder_enqueue_thread_work_ilocked(thread, &t->work); - else if (!pending_async) + } else if (!pending_async) { binder_enqueue_work_ilocked(&t->work, &proc->todo); - else + } else { + if ((t->flags & TF_UPDATE_TXN) && proc->is_frozen) { + t_outdated = binder_find_outdated_transaction_ilocked(t, + &node->async_todo); + if (t_outdated) { + binder_debug(BINDER_DEBUG_TRANSACTION, + "txn %d supersedes %d\n", + t->debug_id, t_outdated->debug_id); + list_del_init(&t_outdated->work.entry); + proc->outstanding_txns--; + } + } binder_enqueue_work_ilocked(&t->work, &node->async_todo); + } if (!pending_async) binder_wakeup_thread_ilocked(proc, thread, !oneway /* sync */); @@ -2692,6 +2755,22 @@ static int binder_proc_transaction(struct binder_transaction *t, binder_inner_proc_unlock(proc); binder_node_unlock(node); + /* + * To reduce potential contention, free the outdated transaction and + * buffer after releasing the locks. + */ + if (t_outdated) { + struct binder_buffer *buffer = t_outdated->buffer; + + t_outdated->buffer = NULL; + buffer->transaction = NULL; + trace_binder_transaction_update_buffer_release(buffer); + binder_transaction_buffer_release(proc, NULL, buffer, 0, 0); + binder_alloc_free_buf(&proc->alloc, buffer); + kfree(t_outdated); + binder_stats_deleted(BINDER_STAT_TRANSACTION); + } + return 0; } diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index 8eeccdc64724..8cc07e6a4273 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -311,6 +311,10 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release, TP_PROTO(struct binder_buffer *buffer), TP_ARGS(buffer)); +DEFINE_EVENT(binder_buffer_class, binder_transaction_update_buffer_release, + TP_PROTO(struct binder_buffer *buffer), + TP_ARGS(buffer)); + TRACE_EVENT(binder_update_page_range, TP_PROTO(struct binder_alloc *alloc, bool allocate, void __user *start, void __user *end), diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 986333cf5bbe..e72e4de8f452 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -287,6 +287,7 @@ enum transaction_flags { TF_STATUS_CODE = 0x08, /* contents are a 32-bit status code */ TF_ACCEPT_FDS = 0x10, /* allow replies with file descriptors */ TF_CLEAR_BUF = 0x20, /* clear buffer on txn complete */ + TF_UPDATE_TXN = 0x40, /* update the outdated pending async txn */ }; struct binder_transaction_data { -- cgit v1.2.3 From 713eb3c1261a1f89e35bdf233265aa5a2c46e9b2 Mon Sep 17 00:00:00 2001 From: Max Staudt Date: Sat, 18 Jun 2022 20:01:34 +0200 Subject: tty: Add N_CAN327 line discipline ID for ELM327 based CAN driver The actual driver will be added via the CAN tree. Link: https://lore.kernel.org/all/20220618180134.9890-1-max@enpas.org Link: https://lore.kernel.org/all/Yrm9Ezlw1dLmIxyS@kroah.com Signed-off-by: Max Staudt Acked-by: Marc Kleine-Budde Acked-by: Greg Kroah-Hartman Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/tty.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 9d0f06bfbac3..68aeae2addec 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,8 +38,9 @@ #define N_NULL 27 /* Null ldisc used for error handling */ #define N_MCTP 28 /* MCTP-over-serial */ #define N_DEVELOPMENT 29 /* Manual out-of-tree testing */ +#define N_CAN327 30 /* ELM327 based OBD-II interfaces */ /* Always the newest line discipline + 1 */ -#define NR_LDISCS 30 +#define NR_LDISCS 31 #endif /* _UAPI_LINUX_TTY_H */ -- cgit v1.2.3 From 94dfc73e7cf4a31da66b8843f0b9283ddd6b8381 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 6 Apr 2022 19:36:51 -0500 Subject: treewide: uapi: Replace zero-length arrays with flexible-array members MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. This code was transformed with the help of Coccinelle: (linux-5.19-rc2$ spatch --jobs $(getconf _NPROCESSORS_ONLN) --sp-file script.cocci --include-headers --dir . > output.patch) @@ identifier S, member, array; type T1, T2; @@ struct S { ... T1 member; T2 array[ - 0 ]; }; -fstrict-flex-arrays=3 is coming and we need to land these changes to prevent issues like these in the short future: ../fs/minix/dir.c:337:3: warning: 'strcpy' will always overflow; destination buffer has size 0, but the source string has length 2 (including NUL byte) [-Wfortify-source] strcpy(de3->name, "."); ^ Since these are all [0] to [] changes, the risk to UAPI is nearly zero. If this breaks anything, we can use a union with a new member name. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/78 Build-tested-by: kernel test robot Link: https://lore.kernel.org/lkml/62b675ec.wKX6AOZ6cbE71vtF%25lkp@intel.com/ Acked-by: Dan Williams # For ndctl.h Signed-off-by: Gustavo A. R. Silva --- arch/m68k/include/uapi/asm/bootinfo.h | 4 +- arch/mips/include/uapi/asm/ucontext.h | 2 +- arch/s390/include/uapi/asm/hwctrset.h | 6 +-- arch/x86/include/uapi/asm/bootparam.h | 2 +- arch/x86/include/uapi/asm/kvm.h | 12 ++--- include/uapi/drm/i915_drm.h | 6 +-- include/uapi/linux/blkzoned.h | 2 +- include/uapi/linux/bpf.h | 2 +- include/uapi/linux/btrfs.h | 10 ++-- include/uapi/linux/btrfs_tree.h | 2 +- include/uapi/linux/can/bcm.h | 2 +- include/uapi/linux/connector.h | 2 +- include/uapi/linux/cycx_cfm.h | 2 +- include/uapi/linux/dm-ioctl.h | 8 +-- include/uapi/linux/dm-log-userspace.h | 2 +- include/uapi/linux/ethtool.h | 28 +++++----- include/uapi/linux/fanotify.h | 2 +- include/uapi/linux/fiemap.h | 2 +- include/uapi/linux/firewire-cdev.h | 12 ++--- include/uapi/linux/fs.h | 2 +- include/uapi/linux/if_alg.h | 2 +- include/uapi/linux/if_arcnet.h | 6 +-- include/uapi/linux/if_pppox.h | 4 +- include/uapi/linux/if_tun.h | 2 +- include/uapi/linux/igmp.h | 6 +-- include/uapi/linux/inet_diag.h | 2 +- include/uapi/linux/inotify.h | 2 +- include/uapi/linux/ip.h | 4 +- include/uapi/linux/ip_vs.h | 4 +- include/uapi/linux/iso_fs.h | 4 +- include/uapi/linux/jffs2.h | 8 +-- include/uapi/linux/kcov.h | 2 +- include/uapi/linux/kvm.h | 8 +-- include/uapi/linux/minix_fs.h | 4 +- include/uapi/linux/mmc/ioctl.h | 2 +- include/uapi/linux/ndctl.h | 10 ++-- include/uapi/linux/net_dropmon.h | 4 +- include/uapi/linux/netfilter/x_tables.h | 4 +- include/uapi/linux/netfilter_arp/arp_tables.h | 6 +-- include/uapi/linux/netfilter_bridge/ebt_among.h | 2 +- include/uapi/linux/netfilter_ipv4/ip_tables.h | 6 +-- include/uapi/linux/netfilter_ipv6/ip6_tables.h | 4 +- include/uapi/linux/perf_event.h | 2 +- include/uapi/linux/pkt_cls.h | 4 +- include/uapi/linux/raid/md_p.h | 2 +- include/uapi/linux/random.h | 2 +- include/uapi/linux/romfs_fs.h | 4 +- include/uapi/linux/rtnetlink.h | 2 +- include/uapi/linux/sctp.h | 10 ++-- include/uapi/linux/seg6.h | 2 +- include/uapi/linux/seg6_iptunnel.h | 2 +- include/uapi/linux/stm.h | 2 +- include/uapi/linux/target_core_user.h | 2 +- include/uapi/linux/usb/audio.h | 2 +- include/uapi/linux/usb/cdc.h | 6 +-- include/uapi/linux/usb/ch9.h | 2 +- include/uapi/linux/usb/raw_gadget.h | 4 +- include/uapi/linux/usbdevice_fs.h | 4 +- include/uapi/linux/vhost_types.h | 4 +- include/uapi/linux/virtio_9p.h | 2 +- include/uapi/linux/xfrm.h | 10 ++-- include/uapi/rdma/hfi/hfi1_user.h | 2 +- include/uapi/rdma/ib_user_verbs.h | 72 ++++++++++++------------- include/uapi/rdma/rdma_user_cm.h | 2 +- include/uapi/rdma/rdma_user_ioctl_cmds.h | 2 +- include/uapi/scsi/fc/fc_els.h | 18 +++---- include/uapi/scsi/scsi_bsg_fc.h | 2 +- include/uapi/sound/asound.h | 2 +- include/uapi/sound/firewire.h | 6 +-- include/uapi/sound/skl-tplg-interface.h | 2 +- include/uapi/sound/sof/header.h | 2 +- include/uapi/sound/usb_stream.h | 2 +- tools/arch/x86/include/uapi/asm/kvm.h | 12 ++--- tools/include/uapi/drm/i915_drm.h | 6 +-- tools/include/uapi/linux/fs.h | 2 +- tools/include/uapi/linux/if_tun.h | 2 +- tools/include/uapi/linux/kvm.h | 8 +-- tools/include/uapi/linux/perf_event.h | 2 +- tools/include/uapi/linux/pkt_cls.h | 4 +- tools/include/uapi/linux/seg6.h | 4 +- tools/include/uapi/linux/usbdevice_fs.h | 4 +- tools/include/uapi/sound/asound.h | 2 +- 82 files changed, 216 insertions(+), 216 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h index 203d9cbf9630..95ecf3ae4c49 100644 --- a/arch/m68k/include/uapi/asm/bootinfo.h +++ b/arch/m68k/include/uapi/asm/bootinfo.h @@ -34,7 +34,7 @@ struct bi_record { __be16 tag; /* tag ID */ __be16 size; /* size of record (in bytes) */ - __be32 data[0]; /* data */ + __be32 data[]; /* data */ }; @@ -168,7 +168,7 @@ struct bootversion { struct { __be32 machtype; __be32 version; - } machversions[0]; + } machversions[]; } __packed; #endif /* __ASSEMBLY__ */ diff --git a/arch/mips/include/uapi/asm/ucontext.h b/arch/mips/include/uapi/asm/ucontext.h index 2d3bf8eebf1f..6122ef97c6ff 100644 --- a/arch/mips/include/uapi/asm/ucontext.h +++ b/arch/mips/include/uapi/asm/ucontext.h @@ -60,7 +60,7 @@ struct ucontext { sigset_t uc_sigmask; /* Extended context structures may follow ucontext */ - unsigned long long uc_extcontext[0]; + unsigned long long uc_extcontext[]; }; #endif /* __MIPS_UAPI_ASM_UCONTEXT_H */ diff --git a/arch/s390/include/uapi/asm/hwctrset.h b/arch/s390/include/uapi/asm/hwctrset.h index 3d8284b95f87..e56b9dd23a4b 100644 --- a/arch/s390/include/uapi/asm/hwctrset.h +++ b/arch/s390/include/uapi/asm/hwctrset.h @@ -30,18 +30,18 @@ struct s390_ctrset_start { /* Set CPUs to operate on */ struct s390_ctrset_setdata { /* Counter set data */ __u32 set; /* Counter set number */ __u32 no_cnts; /* # of counters stored in cv[] */ - __u64 cv[0]; /* Counter values (variable length) */ + __u64 cv[]; /* Counter values (variable length) */ }; struct s390_ctrset_cpudata { /* Counter set data per CPU */ __u32 cpu_nr; /* CPU number */ __u32 no_sets; /* # of counters sets in data[] */ - struct s390_ctrset_setdata data[0]; + struct s390_ctrset_setdata data[]; }; struct s390_ctrset_read { /* Structure to get all ctr sets */ __u64 no_cpus; /* Total # of CPUs data taken from */ - struct s390_ctrset_cpudata data[0]; + struct s390_ctrset_cpudata data[]; }; #define S390_HWCTR_MAGIC 'C' /* Random magic # for ioctls */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index bea5cdcdf532..cdd6c7f6cfa6 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -52,7 +52,7 @@ struct setup_data { __u64 next; __u32 type; __u32 len; - __u8 data[0]; + __u8 data[]; }; /* extensible setup indirect data node */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 21614807a2cb..ec53c9fa1da9 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -198,13 +198,13 @@ struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; - struct kvm_msr_entry entries[0]; + struct kvm_msr_entry entries[]; }; /* for KVM_GET_MSR_INDEX_LIST */ struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ - __u32 indices[0]; + __u32 indices[]; }; /* Maximum size of any access bitmap in bytes */ @@ -241,7 +241,7 @@ struct kvm_cpuid_entry { struct kvm_cpuid { __u32 nent; __u32 padding; - struct kvm_cpuid_entry entries[0]; + struct kvm_cpuid_entry entries[]; }; struct kvm_cpuid_entry2 { @@ -263,7 +263,7 @@ struct kvm_cpuid_entry2 { struct kvm_cpuid2 { __u32 nent; __u32 padding; - struct kvm_cpuid_entry2 entries[0]; + struct kvm_cpuid_entry2 entries[]; }; /* for KVM_GET_PIT and KVM_SET_PIT */ @@ -389,7 +389,7 @@ struct kvm_xsave { * the contents of CPUID leaf 0xD on the host. */ __u32 region[1024]; - __u32 extra[0]; + __u32 extra[]; }; #define KVM_MAX_XCRS 16 @@ -516,7 +516,7 @@ struct kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[0]; + __u64 events[]; }; #define KVM_PMU_EVENT_ALLOW 0 diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index a2def7b27009..b28ff5d88145 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2123,7 +2123,7 @@ struct i915_context_engines_load_balance { __u64 mbz64; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ @@ -2161,7 +2161,7 @@ struct i915_context_engines_bond { __u64 flags; /* all undefined flags must be zero */ __u64 mbz64[4]; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ @@ -2288,7 +2288,7 @@ struct i915_context_engines_parallel_submit { * length = width (i) * num_siblings (j) * index = j + i * num_siblings */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __packed; diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 656a326821a2..b80fcc9ea525 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -130,7 +130,7 @@ struct blk_zone_report { __u64 sector; __u32 nr_zones; __u32 flags; - struct blk_zone zones[0]; + struct blk_zone zones[]; }; /** diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f4009dbdf62d..e4b33ba06f00 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -79,7 +79,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[0]; /* Arbitrary size */ + __u8 data[]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index d956b2993970..3d0edbe3b991 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -93,7 +93,7 @@ struct btrfs_qgroup_inherit { __u64 num_ref_copies; __u64 num_excl_copies; struct btrfs_qgroup_limit lim; - __u64 qgroups[0]; + __u64 qgroups[]; }; struct btrfs_ioctl_qgroup_limit_args { @@ -561,7 +561,7 @@ struct btrfs_ioctl_search_args_v2 { __u64 buf_size; /* in - size of buffer * out - on EOVERFLOW: needed size * to store item */ - __u64 buf[0]; /* out - found items */ + __u64 buf[]; /* out - found items */ }; struct btrfs_ioctl_clone_range_args { @@ -632,7 +632,7 @@ struct btrfs_ioctl_same_args { __u16 dest_count; /* in - total elements in info array */ __u16 reserved1; __u32 reserved2; - struct btrfs_ioctl_same_extent_info info[0]; + struct btrfs_ioctl_same_extent_info info[]; }; struct btrfs_ioctl_space_info { @@ -644,7 +644,7 @@ struct btrfs_ioctl_space_info { struct btrfs_ioctl_space_args { __u64 space_slots; __u64 total_spaces; - struct btrfs_ioctl_space_info spaces[0]; + struct btrfs_ioctl_space_info spaces[]; }; struct btrfs_data_container { @@ -652,7 +652,7 @@ struct btrfs_data_container { __u32 bytes_missing; /* out -- additional bytes needed for result */ __u32 elem_cnt; /* out */ __u32 elem_missed; /* out */ - __u64 val[0]; /* out */ + __u64 val[]; /* out */ }; struct btrfs_ioctl_ino_path_args { diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index d4117152d907..5f32a2a495dc 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -575,7 +575,7 @@ struct btrfs_inode_extref { __le64 parent_objectid; __le64 index; __le16 name_len; - __u8 name[0]; + __u8 name[]; /* name goes here */ } __attribute__ ((__packed__)); diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index dd2b925b09ac..f1e45f533a72 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -71,7 +71,7 @@ struct bcm_msg_head { struct bcm_timeval ival1, ival2; canid_t can_id; __u32 nframes; - struct can_frame frames[0]; + struct can_frame frames[]; }; enum { diff --git a/include/uapi/linux/connector.h b/include/uapi/linux/connector.h index 3738936149a2..5ae131c3f145 100644 --- a/include/uapi/linux/connector.h +++ b/include/uapi/linux/connector.h @@ -75,7 +75,7 @@ struct cn_msg { __u16 len; /* Length of the following data */ __u16 flags; - __u8 data[0]; + __u8 data[]; }; #endif /* _UAPI__CONNECTOR_H */ diff --git a/include/uapi/linux/cycx_cfm.h b/include/uapi/linux/cycx_cfm.h index 51f541942ff9..91778c8024b1 100644 --- a/include/uapi/linux/cycx_cfm.h +++ b/include/uapi/linux/cycx_cfm.h @@ -91,7 +91,7 @@ struct cycx_firmware { unsigned short reserved[6]; char descr[CFM_DESCR_LEN]; struct cycx_fw_info info; - unsigned char image[0]; + unsigned char image[]; }; struct cycx_fw_header { diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 2e9550fef90f..8c97d75f3104 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -182,7 +182,7 @@ struct dm_target_spec { struct dm_target_deps { __u32 count; /* Array size */ __u32 padding; /* unused */ - __u64 dev[0]; /* out */ + __u64 dev[]; /* out */ }; /* @@ -192,7 +192,7 @@ struct dm_name_list { __u64 dev; __u32 next; /* offset to the next record from the _start_ of this */ - char name[0]; + char name[]; /* * The following members can be accessed by taking a pointer that @@ -216,7 +216,7 @@ struct dm_target_versions { __u32 next; __u32 version[3]; - char name[0]; + char name[]; }; /* @@ -225,7 +225,7 @@ struct dm_target_versions { struct dm_target_msg { __u64 sector; /* Device sector */ - char message[0]; + char message[]; }; /* diff --git a/include/uapi/linux/dm-log-userspace.h b/include/uapi/linux/dm-log-userspace.h index 5c47a8603376..23dad9565e46 100644 --- a/include/uapi/linux/dm-log-userspace.h +++ b/include/uapi/linux/dm-log-userspace.h @@ -426,7 +426,7 @@ struct dm_ulog_request { __u32 request_type; /* DM_ULOG_* defined above */ __u32 data_size; /* How much data (not including this struct) */ - char data[0]; + char data[]; }; #endif /* __DM_LOG_USERSPACE_H__ */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index e0f0ee9bc89e..2d5741fd44bb 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -257,7 +257,7 @@ struct ethtool_tunable { __u32 id; __u32 type_id; __u32 len; - void *data[0]; + void *data[]; }; #define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff @@ -322,7 +322,7 @@ struct ethtool_regs { __u32 cmd; __u32 version; __u32 len; - __u8 data[0]; + __u8 data[]; }; /** @@ -348,7 +348,7 @@ struct ethtool_eeprom { __u32 magic; __u32 offset; __u32 len; - __u8 data[0]; + __u8 data[]; }; /** @@ -752,7 +752,7 @@ struct ethtool_gstrings { __u32 cmd; __u32 string_set; __u32 len; - __u8 data[0]; + __u8 data[]; }; /** @@ -777,7 +777,7 @@ struct ethtool_sset_info { __u32 cmd; __u32 reserved; __u64 sset_mask; - __u32 data[0]; + __u32 data[]; }; /** @@ -817,7 +817,7 @@ struct ethtool_test { __u32 flags; __u32 reserved; __u32 len; - __u64 data[0]; + __u64 data[]; }; /** @@ -834,7 +834,7 @@ struct ethtool_test { struct ethtool_stats { __u32 cmd; __u32 n_stats; - __u64 data[0]; + __u64 data[]; }; /** @@ -851,7 +851,7 @@ struct ethtool_stats { struct ethtool_perm_addr { __u32 cmd; __u32 size; - __u8 data[0]; + __u8 data[]; }; /* boolean flags controlling per-interface behavior characteristics. @@ -1160,7 +1160,7 @@ struct ethtool_rxnfc { struct ethtool_rxfh_indir { __u32 cmd; __u32 size; - __u32 ring_index[0]; + __u32 ring_index[]; }; /** @@ -1201,7 +1201,7 @@ struct ethtool_rxfh { __u8 hfunc; __u8 rsvd8[3]; __u32 rsvd32; - __u32 rss_config[0]; + __u32 rss_config[]; }; #define ETH_RXFH_CONTEXT_ALLOC 0xffffffff #define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff @@ -1286,7 +1286,7 @@ struct ethtool_dump { __u32 version; __u32 flag; __u32 len; - __u8 data[0]; + __u8 data[]; }; #define ETH_FW_DUMP_DISABLE 0 @@ -1318,7 +1318,7 @@ struct ethtool_get_features_block { struct ethtool_gfeatures { __u32 cmd; __u32 size; - struct ethtool_get_features_block features[0]; + struct ethtool_get_features_block features[]; }; /** @@ -1340,7 +1340,7 @@ struct ethtool_set_features_block { struct ethtool_sfeatures { __u32 cmd; __u32 size; - struct ethtool_set_features_block features[0]; + struct ethtool_set_features_block features[]; }; /** @@ -2087,7 +2087,7 @@ struct ethtool_link_settings { __u8 master_slave_state; __u8 reserved1[1]; __u32 reserved[7]; - __u32 link_mode_masks[0]; + __u32 link_mode_masks[]; /* layout of link_mode_masks fields: * __u32 map_supported[link_mode_masks_nwords]; * __u32 map_advertising[link_mode_masks_nwords]; diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index f1f89132d60e..197df344307d 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -162,7 +162,7 @@ struct fanotify_event_info_fid { * Following is an opaque struct file_handle that can be passed as * an argument to open_by_handle_at(2). */ - unsigned char handle[0]; + unsigned char handle[]; }; /* diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 07c1cdcb715e..24ca0c00cae3 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 5effa9832802..92be3ea3c6e0 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -118,7 +118,7 @@ struct fw_cdev_event_response { __u32 type; __u32 rcode; __u32 length; - __u32 data[0]; + __u32 data[]; }; /** @@ -142,7 +142,7 @@ struct fw_cdev_event_request { __u64 offset; __u32 handle; __u32 length; - __u32 data[0]; + __u32 data[]; }; /** @@ -205,7 +205,7 @@ struct fw_cdev_event_request2 { __u32 generation; __u32 handle; __u32 length; - __u32 data[0]; + __u32 data[]; }; /** @@ -265,7 +265,7 @@ struct fw_cdev_event_iso_interrupt { __u32 type; __u32 cycle; __u32 header_length; - __u32 header[0]; + __u32 header[]; }; /** @@ -355,7 +355,7 @@ struct fw_cdev_event_phy_packet { __u32 type; __u32 rcode; __u32 length; - __u32 data[0]; + __u32 data[]; }; /** @@ -803,7 +803,7 @@ struct fw_cdev_set_iso_channels { */ struct fw_cdev_iso_packet { __u32 control; - __u32 header[0]; + __u32 header[]; }; /** diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index bdf7b404b3e7..b7b56871029c 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -90,7 +90,7 @@ struct file_dedupe_range { __u16 dest_count; /* in - total elements in info array */ __u16 reserved1; /* must be zero */ __u32 reserved2; /* must be zero */ - struct file_dedupe_range_info info[0]; + struct file_dedupe_range_info info[]; }; /* And dynamically-tunable limits and defaults: */ diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index dc52a11ba6d1..578b18aab821 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -42,7 +42,7 @@ struct sockaddr_alg_new { struct af_alg_iv { __u32 ivlen; - __u8 iv[0]; + __u8 iv[]; }; /* Socket options */ diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index 683878036d76..b122cfac7128 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -60,7 +60,7 @@ struct arc_rfc1201 { __u8 proto; /* protocol ID field - varies */ __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - __u8 payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 payload[]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -69,7 +69,7 @@ struct arc_rfc1201 { */ struct arc_rfc1051 { __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[0]; /* 507 bytes */ + __u8 payload[]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -80,7 +80,7 @@ struct arc_rfc1051 { struct arc_eth_encap { __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[0]; /* 493 bytes */ + __u8 payload[]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h index e7a693c28f16..9abd80dcc46f 100644 --- a/include/uapi/linux/if_pppox.h +++ b/include/uapi/linux/if_pppox.h @@ -122,7 +122,7 @@ struct sockaddr_pppol2tpv3in6 { struct pppoe_tag { __be16 tag_type; __be16 tag_len; - char tag_data[0]; + char tag_data[]; } __attribute__ ((packed)); /* Tag identifiers */ @@ -150,7 +150,7 @@ struct pppoe_hdr { __u8 code; __be16 sid; __be16 length; - struct pppoe_tag tag[0]; + struct pppoe_tag tag[]; } __packed; /* Length of entire PPPoE + PPP header */ diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 454ae31b93c7..2ec07de1d73b 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -108,7 +108,7 @@ struct tun_pi { struct tun_filter { __u16 flags; /* TUN_FLT_ flags see above */ __u16 count; /* Number of addresses */ - __u8 addr[0][ETH_ALEN]; + __u8 addr[][ETH_ALEN]; }; #endif /* _UAPI__IF_TUN_H */ diff --git a/include/uapi/linux/igmp.h b/include/uapi/linux/igmp.h index 90c28bc466c6..5930f2437cd1 100644 --- a/include/uapi/linux/igmp.h +++ b/include/uapi/linux/igmp.h @@ -48,7 +48,7 @@ struct igmpv3_grec { __u8 grec_auxwords; __be16 grec_nsrcs; __be32 grec_mca; - __be32 grec_src[0]; + __be32 grec_src[]; }; struct igmpv3_report { @@ -57,7 +57,7 @@ struct igmpv3_report { __sum16 csum; __be16 resv2; __be16 ngrec; - struct igmpv3_grec grec[0]; + struct igmpv3_grec grec[]; }; struct igmpv3_query { @@ -78,7 +78,7 @@ struct igmpv3_query { #endif __u8 qqic; __be16 nsrcs; - __be32 srcs[0]; + __be32 srcs[]; }; #define IGMP_HOST_MEMBERSHIP_QUERY 0x11 /* From RFC1112 */ diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 20ee93f0f876..50655de04c9b 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -104,7 +104,7 @@ struct inet_diag_hostcond { __u8 family; __u8 prefix_len; int port; - __be32 addr[0]; + __be32 addr[]; }; struct inet_diag_markcond { diff --git a/include/uapi/linux/inotify.h b/include/uapi/linux/inotify.h index 884b4846b630..b3e165853d5b 100644 --- a/include/uapi/linux/inotify.h +++ b/include/uapi/linux/inotify.h @@ -23,7 +23,7 @@ struct inotify_event { __u32 mask; /* watch mask */ __u32 cookie; /* cookie to synchronize two events */ __u32 len; /* length (including nulls) of name */ - char name[0]; /* stub for possible name */ + char name[]; /* stub for possible name */ }; /* the following are legal, implemented events that user-space can watch for */ diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index e00bbb9c47bb..961ec16a26b8 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -112,13 +112,13 @@ struct ip_auth_hdr { __be16 reserved; __be32 spi; __be32 seq_no; /* Sequence number */ - __u8 auth_data[0]; /* Variable len but >=4. Mind the 64 bit alignment! */ + __u8 auth_data[]; /* Variable len but >=4. Mind the 64 bit alignment! */ }; struct ip_esp_hdr { __be32 spi; __be32 seq_no; /* Sequence number */ - __u8 enc_data[0]; /* Variable len but >=8. Mind the 64 bit alignment! */ + __u8 enc_data[]; /* Variable len but >=8. Mind the 64 bit alignment! */ }; struct ip_comp_hdr { diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 4102ddcb4e14..1ed234e7f251 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -254,7 +254,7 @@ struct ip_vs_get_dests { unsigned int num_dests; /* the real servers */ - struct ip_vs_dest_entry entrytable[0]; + struct ip_vs_dest_entry entrytable[]; }; @@ -264,7 +264,7 @@ struct ip_vs_get_services { unsigned int num_services; /* service table */ - struct ip_vs_service_entry entrytable[0]; + struct ip_vs_service_entry entrytable[]; }; diff --git a/include/uapi/linux/iso_fs.h b/include/uapi/linux/iso_fs.h index a2555176f6d1..758178f5b52d 100644 --- a/include/uapi/linux/iso_fs.h +++ b/include/uapi/linux/iso_fs.h @@ -137,7 +137,7 @@ struct iso_path_table{ __u8 name_len[2]; /* 721 */ __u8 extent[4]; /* 731 */ __u8 parent[2]; /* 721 */ - char name[0]; + char name[]; } __attribute__((packed)); /* high sierra is identical to iso, except that the date is only 6 bytes, and @@ -154,7 +154,7 @@ struct iso_directory_record { __u8 interleave [ISODCL (28, 28)]; /* 711 */ __u8 volume_sequence_number [ISODCL (29, 32)]; /* 723 */ __u8 name_len [ISODCL (33, 33)]; /* 711 */ - char name [0]; + char name []; } __attribute__((packed)); #define ISOFS_BLOCK_BITS 11 diff --git a/include/uapi/linux/jffs2.h b/include/uapi/linux/jffs2.h index 784ba0b9690a..637ee4a793cf 100644 --- a/include/uapi/linux/jffs2.h +++ b/include/uapi/linux/jffs2.h @@ -123,7 +123,7 @@ struct jffs2_raw_dirent __u8 unused[2]; jint32_t node_crc; jint32_t name_crc; - __u8 name[0]; + __u8 name[]; }; /* The JFFS2 raw inode structure: Used for storage on physical media. */ @@ -155,7 +155,7 @@ struct jffs2_raw_inode jint16_t flags; /* See JFFS2_INO_FLAG_* */ jint32_t data_crc; /* CRC for the (compressed) data. */ jint32_t node_crc; /* CRC for the raw inode (excluding data) */ - __u8 data[0]; + __u8 data[]; }; struct jffs2_raw_xattr { @@ -170,7 +170,7 @@ struct jffs2_raw_xattr { jint16_t value_len; jint32_t data_crc; jint32_t node_crc; - __u8 data[0]; + __u8 data[]; } __attribute__((packed)); struct jffs2_raw_xref @@ -196,7 +196,7 @@ struct jffs2_raw_summary jint32_t padded; /* sum of the size of padding nodes */ jint32_t sum_crc; /* summary information crc */ jint32_t node_crc; /* node crc */ - jint32_t sum[0]; /* inode summary info */ + jint32_t sum[]; /* inode summary info */ }; union jffs2_node_union diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 1d0350e44ae3..ed95dba9fa37 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -13,7 +13,7 @@ struct kcov_remote_arg { __u32 area_size; /* Length of coverage buffer in words */ __u32 num_handles; /* Size of handles array */ __aligned_u64 common_handle; - __aligned_u64 handles[0]; + __aligned_u64 handles[]; }; #define KCOV_REMOTE_MAX_HANDLES 0x100 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..74dc8bafcb9e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -542,7 +542,7 @@ struct kvm_coalesced_mmio { struct kvm_coalesced_mmio_ring { __u32 first, last; - struct kvm_coalesced_mmio coalesced_mmio[0]; + struct kvm_coalesced_mmio coalesced_mmio[]; }; #define KVM_COALESCED_MMIO_MAX \ @@ -621,7 +621,7 @@ struct kvm_clear_dirty_log { /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; - __u8 sigset[0]; + __u8 sigset[]; }; /* for KVM_TPR_ACCESS_REPORTING */ @@ -1221,7 +1221,7 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing { __u32 nr; __u32 flags; - struct kvm_irq_routing_entry entries[0]; + struct kvm_irq_routing_entry entries[]; }; #endif @@ -1341,7 +1341,7 @@ struct kvm_dirty_tlb { struct kvm_reg_list { __u64 n; /* number of regs */ - __u64 reg[0]; + __u64 reg[]; }; struct kvm_one_reg { diff --git a/include/uapi/linux/minix_fs.h b/include/uapi/linux/minix_fs.h index 95dbcb17eacd..8d9ca8b2c357 100644 --- a/include/uapi/linux/minix_fs.h +++ b/include/uapi/linux/minix_fs.h @@ -97,11 +97,11 @@ struct minix3_super_block { struct minix_dir_entry { __u16 inode; - char name[0]; + char name[]; }; struct minix3_dir_entry { __u32 inode; - char name[0]; + char name[]; }; #endif diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 27a39847d55c..e7401ade6822 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -58,7 +58,7 @@ struct mmc_ioc_cmd { */ struct mmc_ioc_multi_cmd { __u64 num_of_cmds; - struct mmc_ioc_cmd cmds[0]; + struct mmc_ioc_cmd cmds[]; }; #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 17e02b64ea2e..73516e263627 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -30,25 +30,25 @@ struct nd_cmd_get_config_data_hdr { __u32 in_offset; __u32 in_length; __u32 status; - __u8 out_buf[0]; + __u8 out_buf[]; } __packed; struct nd_cmd_set_config_hdr { __u32 in_offset; __u32 in_length; - __u8 in_buf[0]; + __u8 in_buf[]; } __packed; struct nd_cmd_vendor_hdr { __u32 opcode; __u32 in_length; - __u8 in_buf[0]; + __u8 in_buf[]; } __packed; struct nd_cmd_vendor_tail { __u32 status; __u32 out_length; - __u8 out_buf[0]; + __u8 out_buf[]; } __packed; struct nd_cmd_ars_cap { @@ -86,7 +86,7 @@ struct nd_cmd_ars_status { __u32 reserved; __u64 err_address; __u64 length; - } __packed records[0]; + } __packed records[]; } __packed; struct nd_cmd_clear_error { diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 1bbea8f0681e..84f622a66a7a 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -29,12 +29,12 @@ struct net_dm_config_entry { struct net_dm_config_msg { __u32 entries; - struct net_dm_config_entry options[0]; + struct net_dm_config_entry options[]; }; struct net_dm_alert_msg { __u32 entries; - struct net_dm_drop_point points[0]; + struct net_dm_drop_point points[]; }; struct net_dm_user_msg { diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h index b8c6bb233ac1..796af83a963a 100644 --- a/include/uapi/linux/netfilter/x_tables.h +++ b/include/uapi/linux/netfilter/x_tables.h @@ -28,7 +28,7 @@ struct xt_entry_match { __u16 match_size; } u; - unsigned char data[0]; + unsigned char data[]; }; struct xt_entry_target { @@ -119,7 +119,7 @@ struct xt_counters_info { unsigned int num_counters; /* The counters (actually `number' of these). */ - struct xt_counters counters[0]; + struct xt_counters counters[]; }; #define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */ diff --git a/include/uapi/linux/netfilter_arp/arp_tables.h b/include/uapi/linux/netfilter_arp/arp_tables.h index bbf5af2b67a8..a6ac2463f787 100644 --- a/include/uapi/linux/netfilter_arp/arp_tables.h +++ b/include/uapi/linux/netfilter_arp/arp_tables.h @@ -109,7 +109,7 @@ struct arpt_entry struct xt_counters counters; /* The matches (if any), then the target. */ - unsigned char elems[0]; + unsigned char elems[]; }; /* @@ -181,7 +181,7 @@ struct arpt_replace { struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ - struct arpt_entry entries[0]; + struct arpt_entry entries[]; }; /* The argument to ARPT_SO_GET_ENTRIES. */ @@ -193,7 +193,7 @@ struct arpt_get_entries { unsigned int size; /* The entries. */ - struct arpt_entry entrytable[0]; + struct arpt_entry entrytable[]; }; /* Helper functions */ diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index 9acf757bc1f7..73b26a280c4f 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple { struct ebt_mac_wormhash { int table[257]; int poolsize; - struct ebt_mac_wormhash_tuple pool[0]; + struct ebt_mac_wormhash_tuple pool[]; }; #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \ diff --git a/include/uapi/linux/netfilter_ipv4/ip_tables.h b/include/uapi/linux/netfilter_ipv4/ip_tables.h index 50c7fee625ae..1485df28b239 100644 --- a/include/uapi/linux/netfilter_ipv4/ip_tables.h +++ b/include/uapi/linux/netfilter_ipv4/ip_tables.h @@ -121,7 +121,7 @@ struct ipt_entry { struct xt_counters counters; /* The matches (if any), then the target. */ - unsigned char elems[0]; + unsigned char elems[]; }; /* @@ -203,7 +203,7 @@ struct ipt_replace { struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ - struct ipt_entry entries[0]; + struct ipt_entry entries[]; }; /* The argument to IPT_SO_GET_ENTRIES. */ @@ -215,7 +215,7 @@ struct ipt_get_entries { unsigned int size; /* The entries. */ - struct ipt_entry entrytable[0]; + struct ipt_entry entrytable[]; }; /* Helper functions */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h index d9e364f96a5c..766e8e0bcc68 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6_tables.h +++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h @@ -243,7 +243,7 @@ struct ip6t_replace { struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ - struct ip6t_entry entries[0]; + struct ip6t_entry entries[]; }; /* The argument to IP6T_SO_GET_ENTRIES. */ @@ -255,7 +255,7 @@ struct ip6t_get_entries { unsigned int size; /* The entries. */ - struct ip6t_entry entrytable[0]; + struct ip6t_entry entrytable[]; }; /* Helper functions */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index d37629dbad72..4653834f078f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -491,7 +491,7 @@ struct perf_event_query_bpf { /* * User provided buffer to store program ids */ - __u32 ids[0]; + __u32 ids[]; }; /* diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9a2ee1e39fad..ffbe230ef90b 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -256,7 +256,7 @@ struct tc_u32_sel { short hoff; __be32 hmask; - struct tc_u32_key keys[0]; + struct tc_u32_key keys[]; }; struct tc_u32_mark { @@ -268,7 +268,7 @@ struct tc_u32_mark { struct tc_u32_pcnt { __u64 rcnt; __u64 rhit; - __u64 kcnts[0]; + __u64 kcnts[]; }; /* Flags */ diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index e5a98a16f9b0..6c0aa577730f 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -303,7 +303,7 @@ struct mdp_superblock_1 { * into the 'roles' value. If a device is spare or faulty, then it doesn't * have a meaningful role. */ - __le16 dev_roles[0]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ + __le16 dev_roles[]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ }; /* feature_map bits */ diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index dcc1b3e6106f..e744c23582eb 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -41,7 +41,7 @@ struct rand_pool_info { int entropy_count; int buf_size; - __u32 buf[0]; + __u32 buf[]; }; /* diff --git a/include/uapi/linux/romfs_fs.h b/include/uapi/linux/romfs_fs.h index a7f1585accef..6aa05e792454 100644 --- a/include/uapi/linux/romfs_fs.h +++ b/include/uapi/linux/romfs_fs.h @@ -27,7 +27,7 @@ struct romfs_super_block { __be32 word1; __be32 size; __be32 checksum; - char name[0]; /* volume name */ + char name[]; /* volume name */ }; /* On disk inode */ @@ -37,7 +37,7 @@ struct romfs_inode { __be32 spec; __be32 size; __be32 checksum; - char name[0]; + char name[]; }; #define ROMFH_TYPE 7 diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 83849a37db5b..eb2747d58a81 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -440,7 +440,7 @@ struct rtnexthop { /* RTA_VIA */ struct rtvia { __kernel_sa_family_t rtvia_family; - __u8 rtvia_addr[0]; + __u8 rtvia_addr[]; }; /* RTM_CACHEINFO */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index c4ff1ebd8bcc..ed7d4ecbf53d 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -365,7 +365,7 @@ struct sctp_assoc_change { __u16 sac_outbound_streams; __u16 sac_inbound_streams; sctp_assoc_t sac_assoc_id; - __u8 sac_info[0]; + __u8 sac_info[]; }; /* @@ -436,7 +436,7 @@ struct sctp_remote_error { __u32 sre_length; __be16 sre_error; sctp_assoc_t sre_assoc_id; - __u8 sre_data[0]; + __u8 sre_data[]; }; @@ -453,7 +453,7 @@ struct sctp_send_failed { __u32 ssf_error; struct sctp_sndrcvinfo ssf_info; sctp_assoc_t ssf_assoc_id; - __u8 ssf_data[0]; + __u8 ssf_data[]; }; struct sctp_send_failed_event { @@ -463,7 +463,7 @@ struct sctp_send_failed_event { __u32 ssf_error; struct sctp_sndinfo ssfe_info; sctp_assoc_t ssf_assoc_id; - __u8 ssf_data[0]; + __u8 ssf_data[]; }; /* @@ -1029,7 +1029,7 @@ struct sctp_getaddrs_old { struct sctp_getaddrs { sctp_assoc_t assoc_id; /*input*/ __u32 addr_num; /*output*/ - __u8 addrs[0]; /*output, variable size*/ + __u8 addrs[]; /*output, variable size*/ }; /* A socket user request obtained via SCTP_GET_ASSOC_STATS that retrieves diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index 286e8d6a8e98..13bcbc8bba32 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -30,7 +30,7 @@ struct ipv6_sr_hdr { __u8 flags; __u16 tag; - struct in6_addr segments[0]; + struct in6_addr segments[]; }; #define SR6_FLAG1_PROTECTED (1 << 6) diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index eb815e0d0ac3..a74294211290 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -26,7 +26,7 @@ enum { struct seg6_iptunnel_encap { int mode; - struct ipv6_sr_hdr srh[0]; + struct ipv6_sr_hdr srh[]; }; #define SEG6_IPTUN_ENCAP_SIZE(x) ((sizeof(*x)) + (((x)->srh->hdrlen + 1) << 3)) diff --git a/include/uapi/linux/stm.h b/include/uapi/linux/stm.h index 7bac318b4440..de3579c2cff0 100644 --- a/include/uapi/linux/stm.h +++ b/include/uapi/linux/stm.h @@ -36,7 +36,7 @@ struct stp_policy_id { /* padding */ __u16 __reserved_0; __u32 __reserved_1; - char id[0]; + char id[]; }; #define STP_POLICY_ID_SET _IOWR('%', 0, struct stp_policy_id) diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index 27ace512babd..fbd8ca67e107 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -152,7 +152,7 @@ struct tcmu_tmr_entry { __u32 cmd_cnt; __u64 __pad3; __u64 __pad4; - __u16 cmd_ids[0]; + __u16 cmd_ids[]; } __packed; #define TCMU_OP_ALIGN_SIZE sizeof(__u64) diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h index 76b7c3f6cd0d..c917c53070d5 100644 --- a/include/uapi/linux/usb/audio.h +++ b/include/uapi/linux/usb/audio.h @@ -341,7 +341,7 @@ struct uac_feature_unit_descriptor { __u8 bUnitID; __u8 bSourceID; __u8 bControlSize; - __u8 bmaControls[0]; /* variable length */ + __u8 bmaControls[]; /* variable length */ } __attribute__((packed)); static inline __u8 uac_feature_unit_iFeature(struct uac_feature_unit_descriptor *desc) diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index 6d61550959ef..acf3852bb676 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -171,7 +171,7 @@ struct usb_cdc_mdlm_detail_desc { /* type is associated with mdlm_desc.bGUID */ __u8 bGuidDescriptorType; - __u8 bDetailData[0]; + __u8 bDetailData[]; } __attribute__ ((packed)); /* "OBEX Control Model Functional Descriptor" */ @@ -379,7 +379,7 @@ struct usb_cdc_ncm_ndp16 { __le32 dwSignature; __le16 wLength; __le16 wNextNdpIndex; - struct usb_cdc_ncm_dpe16 dpe16[0]; + struct usb_cdc_ncm_dpe16 dpe16[]; } __attribute__ ((packed)); /* 32-bit NCM Datagram Pointer Entry */ @@ -395,7 +395,7 @@ struct usb_cdc_ncm_ndp32 { __le16 wReserved6; __le32 dwNextNdpIndex; __le32 dwReserved12; - struct usb_cdc_ncm_dpe32 dpe32[0]; + struct usb_cdc_ncm_dpe32 dpe32[]; } __attribute__ ((packed)); /* CDC NCM subclass 3.2.1 and 3.2.2 */ diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 17ce56198c9a..31fcfa084e63 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -818,7 +818,7 @@ struct usb_key_descriptor { __u8 tTKID[3]; __u8 bReserved; - __u8 bKeyData[0]; + __u8 bKeyData[]; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index 0be685272eb1..c7d2199134d7 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -60,7 +60,7 @@ enum usb_raw_event_type { struct usb_raw_event { __u32 type; __u32 length; - __u8 data[0]; + __u8 data[]; }; #define USB_RAW_IO_FLAGS_ZERO 0x0001 @@ -90,7 +90,7 @@ struct usb_raw_ep_io { __u16 ep; __u16 flags; __u32 length; - __u8 data[0]; + __u8 data[]; }; /* Maximum number of non-control endpoints in struct usb_raw_eps_info. */ diff --git a/include/uapi/linux/usbdevice_fs.h b/include/uapi/linux/usbdevice_fs.h index cf525cddeb94..74a84e02422a 100644 --- a/include/uapi/linux/usbdevice_fs.h +++ b/include/uapi/linux/usbdevice_fs.h @@ -131,7 +131,7 @@ struct usbdevfs_urb { unsigned int signr; /* signal to be sent on completion, or 0 if none should be sent. */ void __user *usercontext; - struct usbdevfs_iso_packet_desc iso_frame_desc[0]; + struct usbdevfs_iso_packet_desc iso_frame_desc[]; }; /* ioctls for talking directly to drivers */ @@ -176,7 +176,7 @@ struct usbdevfs_disconnect_claim { struct usbdevfs_streams { unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */ unsigned int num_eps; - unsigned char eps[0]; + unsigned char eps[]; }; /* diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 634cee485abb..391331a10879 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -107,7 +107,7 @@ struct vhost_memory_region { struct vhost_memory { __u32 nregions; __u32 padding; - struct vhost_memory_region regions[0]; + struct vhost_memory_region regions[]; }; /* VHOST_SCSI specific definitions */ @@ -135,7 +135,7 @@ struct vhost_scsi_target { struct vhost_vdpa_config { __u32 off; __u32 len; - __u8 buf[0]; + __u8 buf[]; }; /* vhost vdpa IOVA range diff --git a/include/uapi/linux/virtio_9p.h b/include/uapi/linux/virtio_9p.h index 441047432258..374b68f8ac6e 100644 --- a/include/uapi/linux/virtio_9p.h +++ b/include/uapi/linux/virtio_9p.h @@ -38,7 +38,7 @@ struct virtio_9p_config { /* length of the tag name */ __virtio16 tag_len; /* non-NULL terminated tag name */ - __u8 tag[0]; + __u8 tag[]; } __attribute__((packed)); #endif /* _LINUX_VIRTIO_9P_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 65e13a099b1a..e8191e0c3b56 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -33,7 +33,7 @@ struct xfrm_sec_ctx { __u8 ctx_alg; __u16 ctx_len; __u32 ctx_sid; - char ctx_str[0]; + char ctx_str[]; }; /* Security Context Domains of Interpretation */ @@ -96,27 +96,27 @@ struct xfrm_replay_state_esn { __u32 oseq_hi; __u32 seq_hi; __u32 replay_window; - __u32 bmp[0]; + __u32 bmp[]; }; struct xfrm_algo { char alg_name[64]; unsigned int alg_key_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_algo_auth { char alg_name[64]; unsigned int alg_key_len; /* in bits */ unsigned int alg_trunc_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_algo_aead { char alg_name[64]; unsigned int alg_key_len; /* in bits */ unsigned int alg_icv_len; /* in bits */ - char alg_key[0]; + char alg_key[]; }; struct xfrm_stats { diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h index d95ef9a2b032..1106a7c90b29 100644 --- a/include/uapi/rdma/hfi/hfi1_user.h +++ b/include/uapi/rdma/hfi/hfi1_user.h @@ -180,7 +180,7 @@ struct hfi1_sdma_comp_entry { struct hfi1_status { __aligned_u64 dev; /* device/hw status bits */ __aligned_u64 port; /* port state and status bits */ - char freezemsg[0]; + char freezemsg[]; }; enum sdma_req_opcode { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 7dd903d932e5..43672cb1fd57 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -158,18 +158,18 @@ struct ib_uverbs_ex_cmd_hdr { struct ib_uverbs_get_context { __aligned_u64 response; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_get_context_resp { __u32 async_fd; __u32 num_comp_vectors; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_device { __aligned_u64 response; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_device_resp { @@ -278,7 +278,7 @@ struct ib_uverbs_query_port { __aligned_u64 response; __u8 port_num; __u8 reserved[7]; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_port_resp { @@ -308,12 +308,12 @@ struct ib_uverbs_query_port_resp { struct ib_uverbs_alloc_pd { __aligned_u64 response; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_alloc_pd_resp { __u32 pd_handle; - __u32 driver_data[0]; + __u32 driver_data[]; }; struct ib_uverbs_dealloc_pd { @@ -324,12 +324,12 @@ struct ib_uverbs_open_xrcd { __aligned_u64 response; __u32 fd; __u32 oflags; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_open_xrcd_resp { __u32 xrcd_handle; - __u32 driver_data[0]; + __u32 driver_data[]; }; struct ib_uverbs_close_xrcd { @@ -343,14 +343,14 @@ struct ib_uverbs_reg_mr { __aligned_u64 hca_va; __u32 pd_handle; __u32 access_flags; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_reg_mr_resp { __u32 mr_handle; __u32 lkey; __u32 rkey; - __u32 driver_data[0]; + __u32 driver_data[]; }; struct ib_uverbs_rereg_mr { @@ -362,13 +362,13 @@ struct ib_uverbs_rereg_mr { __aligned_u64 hca_va; __u32 pd_handle; __u32 access_flags; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_rereg_mr_resp { __u32 lkey; __u32 rkey; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_dereg_mr { @@ -380,13 +380,13 @@ struct ib_uverbs_alloc_mw { __u32 pd_handle; __u8 mw_type; __u8 reserved[3]; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_alloc_mw_resp { __u32 mw_handle; __u32 rkey; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_dealloc_mw { @@ -408,7 +408,7 @@ struct ib_uverbs_create_cq { __u32 comp_vector; __s32 comp_channel; __u32 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; enum ib_uverbs_ex_create_cq_flags { @@ -442,13 +442,13 @@ struct ib_uverbs_resize_cq { __aligned_u64 response; __u32 cq_handle; __u32 cqe; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_resize_cq_resp { __u32 cqe; __u32 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_poll_cq { @@ -492,7 +492,7 @@ struct ib_uverbs_wc { struct ib_uverbs_poll_cq_resp { __u32 count; __u32 reserved; - struct ib_uverbs_wc wc[0]; + struct ib_uverbs_wc wc[]; }; struct ib_uverbs_req_notify_cq { @@ -585,7 +585,7 @@ struct ib_uverbs_create_qp { __u8 qp_type; __u8 is_srq; __u8 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; enum ib_uverbs_create_qp_mask { @@ -624,7 +624,7 @@ struct ib_uverbs_open_qp { __u32 qpn; __u8 qp_type; __u8 reserved[7]; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; /* also used for open response */ @@ -669,7 +669,7 @@ struct ib_uverbs_query_qp { __aligned_u64 response; __u32 qp_handle; __u32 attr_mask; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_qp_resp { @@ -703,7 +703,7 @@ struct ib_uverbs_query_qp_resp { __u8 alt_timeout; __u8 sq_sig_all; __u8 reserved[5]; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_modify_qp { @@ -824,7 +824,7 @@ struct ib_uverbs_post_send { __u32 wr_count; __u32 sge_count; __u32 wqe_size; - struct ib_uverbs_send_wr send_wr[0]; + struct ib_uverbs_send_wr send_wr[]; }; struct ib_uverbs_post_send_resp { @@ -843,7 +843,7 @@ struct ib_uverbs_post_recv { __u32 wr_count; __u32 sge_count; __u32 wqe_size; - struct ib_uverbs_recv_wr recv_wr[0]; + struct ib_uverbs_recv_wr recv_wr[]; }; struct ib_uverbs_post_recv_resp { @@ -856,7 +856,7 @@ struct ib_uverbs_post_srq_recv { __u32 wr_count; __u32 sge_count; __u32 wqe_size; - struct ib_uverbs_recv_wr recv[0]; + struct ib_uverbs_recv_wr recv[]; }; struct ib_uverbs_post_srq_recv_resp { @@ -869,12 +869,12 @@ struct ib_uverbs_create_ah { __u32 pd_handle; __u32 reserved; struct ib_uverbs_ah_attr attr; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_create_ah_resp { __u32 ah_handle; - __u32 driver_data[0]; + __u32 driver_data[]; }; struct ib_uverbs_destroy_ah { @@ -886,7 +886,7 @@ struct ib_uverbs_attach_mcast { __u32 qp_handle; __u16 mlid; __u16 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_detach_mcast { @@ -894,7 +894,7 @@ struct ib_uverbs_detach_mcast { __u32 qp_handle; __u16 mlid; __u16 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_flow_spec_hdr { @@ -1135,7 +1135,7 @@ struct ib_uverbs_flow_attr { * struct ib_flow_spec_xxx * struct ib_flow_spec_yyy */ - struct ib_uverbs_flow_spec_hdr flow_specs[0]; + struct ib_uverbs_flow_spec_hdr flow_specs[]; }; struct ib_uverbs_create_flow { @@ -1161,7 +1161,7 @@ struct ib_uverbs_create_srq { __u32 max_wr; __u32 max_sge; __u32 srq_limit; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_create_xsrq { @@ -1175,7 +1175,7 @@ struct ib_uverbs_create_xsrq { __u32 max_num_tags; __u32 xrcd_handle; __u32 cq_handle; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_create_srq_resp { @@ -1183,7 +1183,7 @@ struct ib_uverbs_create_srq_resp { __u32 max_wr; __u32 max_sge; __u32 srqn; - __u32 driver_data[0]; + __u32 driver_data[]; }; struct ib_uverbs_modify_srq { @@ -1191,14 +1191,14 @@ struct ib_uverbs_modify_srq { __u32 attr_mask; __u32 max_wr; __u32 srq_limit; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_srq { __aligned_u64 response; __u32 srq_handle; __u32 reserved; - __aligned_u64 driver_data[0]; + __aligned_u64 driver_data[]; }; struct ib_uverbs_query_srq_resp { @@ -1269,7 +1269,7 @@ struct ib_uverbs_ex_create_rwq_ind_table { * wq_handle1 * wq_handle2 */ - __u32 wq_handles[0]; + __u32 wq_handles[]; }; struct ib_uverbs_ex_create_rwq_ind_table_resp { diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index ed5a514305c1..7cea03581f79 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -184,7 +184,7 @@ struct rdma_ucm_query_addr_resp { struct rdma_ucm_query_path_resp { __u32 num_paths; __u32 reserved; - struct ib_path_rec_data path_data[0]; + struct ib_path_rec_data path_data[]; }; struct rdma_ucm_conn_param { diff --git a/include/uapi/rdma/rdma_user_ioctl_cmds.h b/include/uapi/rdma/rdma_user_ioctl_cmds.h index 38ab7accb7be..ab1aef17feb1 100644 --- a/include/uapi/rdma/rdma_user_ioctl_cmds.h +++ b/include/uapi/rdma/rdma_user_ioctl_cmds.h @@ -81,7 +81,7 @@ struct ib_uverbs_ioctl_hdr { __aligned_u64 reserved1; __u32 driver_id; __u32 reserved2; - struct ib_uverbs_attr attrs[0]; + struct ib_uverbs_attr attrs[]; }; #endif diff --git a/include/uapi/scsi/fc/fc_els.h b/include/uapi/scsi/fc/fc_els.h index c9812c5c2fc4..16782c360de3 100644 --- a/include/uapi/scsi/fc/fc_els.h +++ b/include/uapi/scsi/fc/fc_els.h @@ -264,7 +264,7 @@ struct fc_tlv_desc { * Size of descriptor excluding * desc_tag and desc_len fields. */ - __u8 desc_value[0]; /* Descriptor Value */ + __u8 desc_value[]; /* Descriptor Value */ }; /* Descriptor tag and len fields are considered the mandatory header @@ -1027,7 +1027,7 @@ struct fc_fn_li_desc { * threshold to caause the LI event */ __be32 pname_count; /* number of portname_list elements */ - __be64 pname_list[0]; /* list of N_Port_Names accessible + __be64 pname_list[]; /* list of N_Port_Names accessible * through the attached port */ }; @@ -1069,7 +1069,7 @@ struct fc_fn_peer_congn_desc { * congestion event */ __be32 pname_count; /* number of portname_list elements */ - __be64 pname_list[0]; /* list of N_Port_Names accessible + __be64 pname_list[]; /* list of N_Port_Names accessible * through the attached port */ }; @@ -1104,7 +1104,7 @@ struct fc_els_fpin { * Size of ELS excluding fpin_cmd, * fpin_zero and desc_len fields. */ - struct fc_tlv_desc fpin_desc[0]; /* Descriptor list */ + struct fc_tlv_desc fpin_desc[]; /* Descriptor list */ }; /* Diagnostic Function Descriptor - FPIN Registration */ @@ -1115,7 +1115,7 @@ struct fc_df_desc_fpin_reg { * desc_tag and desc_len fields. */ __be32 count; /* Number of desc_tags elements */ - __be32 desc_tags[0]; /* Array of Descriptor Tags. + __be32 desc_tags[]; /* Array of Descriptor Tags. * Each tag indicates a function * supported by the N_Port (request) * or by the N_Port and Fabric @@ -1135,7 +1135,7 @@ struct fc_els_rdf { * Size of ELS excluding fpin_cmd, * fpin_zero and desc_len fields. */ - struct fc_tlv_desc desc[0]; /* Descriptor list */ + struct fc_tlv_desc desc[]; /* Descriptor list */ }; /* @@ -1148,7 +1148,7 @@ struct fc_els_rdf_resp { * and desc_list_len fields. */ struct fc_els_lsri_desc lsri; - struct fc_tlv_desc desc[0]; /* Supported Descriptor list */ + struct fc_tlv_desc desc[]; /* Supported Descriptor list */ }; @@ -1231,7 +1231,7 @@ struct fc_els_edc { * Size of ELS excluding edc_cmd, * edc_zero and desc_len fields. */ - struct fc_tlv_desc desc[0]; + struct fc_tlv_desc desc[]; /* Diagnostic Descriptor list */ }; @@ -1245,7 +1245,7 @@ struct fc_els_edc_resp { * and desc_list_len fields. */ struct fc_els_lsri_desc lsri; - struct fc_tlv_desc desc[0]; + struct fc_tlv_desc desc[]; /* Supported Diagnostic Descriptor list */ }; diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 3ae65e93235c..7f5930801f72 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -209,7 +209,7 @@ struct fc_bsg_host_vendor { __u64 vendor_id; /* start of vendor command area */ - __u32 vendor_cmd[0]; + __u32 vendor_cmd[]; }; /* Response: diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 2d3e5df39a59..3974a2a911cc 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -1106,7 +1106,7 @@ struct snd_ctl_elem_value { struct snd_ctl_tlv { unsigned int numid; /* control element numeric identification */ unsigned int length; /* in bytes aligned to 4 */ - unsigned int tlv[0]; /* first TLV */ + unsigned int tlv[]; /* first TLV */ }; #define SNDRV_CTL_IOCTL_PVERSION _IOR('U', 0x00, int) diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 39cf6eb75940..3532ac7046d7 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -38,11 +38,11 @@ struct snd_efw_transaction { __be32 category; __be32 command; __be32 status; - __be32 params[0]; + __be32 params[]; }; struct snd_firewire_event_efw_response { unsigned int type; - __be32 response[0]; /* some responses */ + __be32 response[]; /* some responses */ }; struct snd_firewire_event_digi00x_message { @@ -63,7 +63,7 @@ struct snd_firewire_tascam_change { struct snd_firewire_event_tascam_control { unsigned int type; - struct snd_firewire_tascam_change changes[0]; + struct snd_firewire_tascam_change changes[]; }; struct snd_firewire_event_motu_register_dsp_change { diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index a93c0decfdd5..f29899b179a6 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -151,7 +151,7 @@ struct skl_dfw_algo_data { __u32 rsvd:30; __u32 param_id; __u32 max; - char params[0]; + char params[]; } __packed; enum skl_tkn_dir { diff --git a/include/uapi/sound/sof/header.h b/include/uapi/sound/sof/header.h index 5f4518e7a972..dbf137516522 100644 --- a/include/uapi/sound/sof/header.h +++ b/include/uapi/sound/sof/header.h @@ -23,7 +23,7 @@ struct sof_abi_hdr { __u32 size; /**< size in bytes of data excl. this struct */ __u32 abi; /**< SOF ABI version */ __u32 reserved[4]; /**< reserved for future use */ - __u32 data[0]; /**< Component data - opaque to core */ + __u32 data[]; /**< Component data - opaque to core */ } __packed; #endif diff --git a/include/uapi/sound/usb_stream.h b/include/uapi/sound/usb_stream.h index 95419d8bbc16..ffdd3ea1e31d 100644 --- a/include/uapi/sound/usb_stream.h +++ b/include/uapi/sound/usb_stream.h @@ -61,7 +61,7 @@ struct usb_stream { unsigned inpacket_split_at; unsigned next_inpacket_split; unsigned next_inpacket_split_at; - struct usb_stream_packet inpacket[0]; + struct usb_stream_packet inpacket[]; }; enum usb_stream_state { diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index bf6e96011dfe..e135f4dcb19d 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -198,13 +198,13 @@ struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; - struct kvm_msr_entry entries[0]; + struct kvm_msr_entry entries[]; }; /* for KVM_GET_MSR_INDEX_LIST */ struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ - __u32 indices[0]; + __u32 indices[]; }; /* Maximum size of any access bitmap in bytes */ @@ -241,7 +241,7 @@ struct kvm_cpuid_entry { struct kvm_cpuid { __u32 nent; __u32 padding; - struct kvm_cpuid_entry entries[0]; + struct kvm_cpuid_entry entries[]; }; struct kvm_cpuid_entry2 { @@ -263,7 +263,7 @@ struct kvm_cpuid_entry2 { struct kvm_cpuid2 { __u32 nent; __u32 padding; - struct kvm_cpuid_entry2 entries[0]; + struct kvm_cpuid_entry2 entries[]; }; /* for KVM_GET_PIT and KVM_SET_PIT */ @@ -389,7 +389,7 @@ struct kvm_xsave { * the contents of CPUID leaf 0xD on the host. */ __u32 region[1024]; - __u32 extra[0]; + __u32 extra[]; }; #define KVM_MAX_XCRS 16 @@ -515,7 +515,7 @@ struct kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[0]; + __u64 events[]; }; #define KVM_PMU_EVENT_ALLOW 0 diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 05c3642aaece..239b91b13c60 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2060,7 +2060,7 @@ struct i915_context_engines_load_balance { __u64 mbz64; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ @@ -2098,7 +2098,7 @@ struct i915_context_engines_bond { __u64 flags; /* all undefined flags must be zero */ __u64 mbz64[4]; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ @@ -2225,7 +2225,7 @@ struct i915_context_engines_parallel_submit { * length = width (i) * num_siblings (j) * index = j + i * num_siblings */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __packed; diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index bdf7b404b3e7..b7b56871029c 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -90,7 +90,7 @@ struct file_dedupe_range { __u16 dest_count; /* in - total elements in info array */ __u16 reserved1; /* must be zero */ __u32 reserved2; /* must be zero */ - struct file_dedupe_range_info info[0]; + struct file_dedupe_range_info info[]; }; /* And dynamically-tunable limits and defaults: */ diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h index 454ae31b93c7..2ec07de1d73b 100644 --- a/tools/include/uapi/linux/if_tun.h +++ b/tools/include/uapi/linux/if_tun.h @@ -108,7 +108,7 @@ struct tun_pi { struct tun_filter { __u16 flags; /* TUN_FLT_ flags see above */ __u16 count; /* Number of addresses */ - __u8 addr[0][ETH_ALEN]; + __u8 addr[][ETH_ALEN]; }; #endif /* _UAPI__IF_TUN_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6a184d260c7f..37ce8cbac322 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -539,7 +539,7 @@ struct kvm_coalesced_mmio { struct kvm_coalesced_mmio_ring { __u32 first, last; - struct kvm_coalesced_mmio coalesced_mmio[0]; + struct kvm_coalesced_mmio coalesced_mmio[]; }; #define KVM_COALESCED_MMIO_MAX \ @@ -618,7 +618,7 @@ struct kvm_clear_dirty_log { /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; - __u8 sigset[0]; + __u8 sigset[]; }; /* for KVM_TPR_ACCESS_REPORTING */ @@ -1216,7 +1216,7 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing { __u32 nr; __u32 flags; - struct kvm_irq_routing_entry entries[0]; + struct kvm_irq_routing_entry entries[]; }; #endif @@ -1335,7 +1335,7 @@ struct kvm_dirty_tlb { struct kvm_reg_list { __u64 n; /* number of regs */ - __u64 reg[0]; + __u64 reg[]; }; struct kvm_one_reg { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index d37629dbad72..4653834f078f 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -491,7 +491,7 @@ struct perf_event_query_bpf { /* * User provided buffer to store program ids */ - __u32 ids[0]; + __u32 ids[]; }; /* diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h index 12153771396a..3faee0199a9b 100644 --- a/tools/include/uapi/linux/pkt_cls.h +++ b/tools/include/uapi/linux/pkt_cls.h @@ -180,7 +180,7 @@ struct tc_u32_sel { short hoff; __be32 hmask; - struct tc_u32_key keys[0]; + struct tc_u32_key keys[]; }; struct tc_u32_mark { @@ -192,7 +192,7 @@ struct tc_u32_mark { struct tc_u32_pcnt { __u64 rcnt; __u64 rhit; - __u64 kcnts[0]; + __u64 kcnts[]; }; /* Flags */ diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h index 286e8d6a8e98..f94baf154c47 100644 --- a/tools/include/uapi/linux/seg6.h +++ b/tools/include/uapi/linux/seg6.h @@ -30,7 +30,7 @@ struct ipv6_sr_hdr { __u8 flags; __u16 tag; - struct in6_addr segments[0]; + struct in6_addr segments[]; }; #define SR6_FLAG1_PROTECTED (1 << 6) @@ -49,7 +49,7 @@ struct ipv6_sr_hdr { struct sr6_tlv { __u8 type; __u8 len; - __u8 data[0]; + __u8 data[]; }; #endif diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h index cf525cddeb94..74a84e02422a 100644 --- a/tools/include/uapi/linux/usbdevice_fs.h +++ b/tools/include/uapi/linux/usbdevice_fs.h @@ -131,7 +131,7 @@ struct usbdevfs_urb { unsigned int signr; /* signal to be sent on completion, or 0 if none should be sent. */ void __user *usercontext; - struct usbdevfs_iso_packet_desc iso_frame_desc[0]; + struct usbdevfs_iso_packet_desc iso_frame_desc[]; }; /* ioctls for talking directly to drivers */ @@ -176,7 +176,7 @@ struct usbdevfs_disconnect_claim { struct usbdevfs_streams { unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */ unsigned int num_eps; - unsigned char eps[0]; + unsigned char eps[]; }; /* diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 2d3e5df39a59..3974a2a911cc 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -1106,7 +1106,7 @@ struct snd_ctl_elem_value { struct snd_ctl_tlv { unsigned int numid; /* control element numeric identification */ unsigned int length; /* in bytes aligned to 4 */ - unsigned int tlv[0]; /* first TLV */ + unsigned int tlv[]; /* first TLV */ }; #define SNDRV_CTL_IOCTL_PVERSION _IOR('U', 0x00, int) -- cgit v1.2.3 From 69fd337a975c7e690dfe49d9cb4fe5ba1e6db44e Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 Jun 2022 10:43:06 -0700 Subject: bpf: per-cgroup lsm flavor Allow attaching to lsm hooks in the cgroup context. Attaching to per-cgroup LSM works exactly like attaching to other per-cgroup hooks. New BPF_LSM_CGROUP is added to trigger new mode; the actual lsm hook we attach to is signaled via existing attach_btf_id. For the hooks that have 'struct socket' or 'struct sock' as its first argument, we use the cgroup associated with that socket. For the rest, we use 'current' cgroup (this is all on default hierarchy == v2 only). Note that for some hooks that work on 'struct sock' we still take the cgroup from 'current' because some of them work on the socket that hasn't been properly initialized yet. Behind the scenes, we allocate a shim program that is attached to the trampoline and runs cgroup effective BPF programs array. This shim has some rudimentary ref counting and can be shared between several programs attaching to the same lsm hook from different cgroups. Note that this patch bloats cgroup size because we add 211 cgroup_bpf_attach_type(s) for simplicity sake. This will be addressed in the subsequent patch. Also note that we only add non-sleepable flavor for now. To enable sleepable use-cases, bpf_prog_run_array_cg has to grab trace rcu, shim programs have to be freed via trace rcu, cgroup_bpf.effective should be also trace-rcu-managed + maybe some other changes that I'm not aware of. Reviewed-by: Martin KaFai Lau Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20220628174314.1216643-4-sdf@google.com Signed-off-by: Alexei Starovoitov --- arch/x86/net/bpf_jit_comp.c | 24 +++-- include/linux/bpf-cgroup-defs.h | 8 ++ include/linux/bpf-cgroup.h | 7 ++ include/linux/bpf.h | 24 +++++ include/linux/bpf_lsm.h | 13 +++ include/linux/btf_ids.h | 3 +- include/uapi/linux/bpf.h | 1 + kernel/bpf/bpf_lsm.c | 48 ++++++++++ kernel/bpf/btf.c | 11 +++ kernel/bpf/cgroup.c | 136 ++++++++++++++++++++++++--- kernel/bpf/core.c | 2 + kernel/bpf/syscall.c | 10 ++ kernel/bpf/trampoline.c | 198 ++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 32 +++++++ tools/include/uapi/linux/bpf.h | 1 + 15 files changed, 498 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2c51ca9f7cec..2f460c67f9c7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1770,6 +1770,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, int run_ctx_off, bool save_ret) { + void (*exit)(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit; + u64 (*enter)(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter; u8 *prog = *pprog; u8 *jmp_insn; int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); @@ -1788,15 +1792,21 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off); + if (p->aux->sleepable) { + enter = __bpf_prog_enter_sleepable; + exit = __bpf_prog_exit_sleepable; + } else if (p->expected_attach_type == BPF_LSM_CGROUP) { + enter = __bpf_prog_enter_lsm_cgroup; + exit = __bpf_prog_exit_lsm_cgroup; + } + /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: lea rsi, [rbp - ctx_cookie_off] */ EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_call(&prog, - p->aux->sleepable ? __bpf_prog_enter_sleepable : - __bpf_prog_enter, prog)) - return -EINVAL; + if (emit_call(&prog, enter, prog)) + return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -1840,10 +1850,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_call(&prog, - p->aux->sleepable ? __bpf_prog_exit_sleepable : - __bpf_prog_exit, prog)) - return -EINVAL; + if (emit_call(&prog, exit, prog)) + return -EINVAL; *pprog = prog; return 0; diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 5d268e76d8e6..b99f8c3e37ea 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -10,6 +10,12 @@ struct bpf_prog_array; +#ifdef CONFIG_BPF_LSM +#define CGROUP_LSM_NUM 211 /* will be addressed in the next patch */ +#else +#define CGROUP_LSM_NUM 0 +#endif + enum cgroup_bpf_attach_type { CGROUP_BPF_ATTACH_TYPE_INVALID = -1, CGROUP_INET_INGRESS = 0, @@ -35,6 +41,8 @@ enum cgroup_bpf_attach_type { CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, + CGROUP_LSM_START, + CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, MAX_CGROUP_BPF_ATTACH_TYPE }; diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 6673acfbf2ef..2bd1b5f8de9b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,6 +23,13 @@ struct ctl_table; struct ctl_table_header; struct task_struct; +unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, + const struct bpf_insn *insn); + #ifdef CONFIG_CGROUP_BPF #define CGROUP_ATYPE(type) \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d547be9db75f..77cd613a00bd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -794,6 +794,10 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); @@ -1060,6 +1064,7 @@ struct bpf_prog_aux { struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; + int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY @@ -1167,6 +1172,11 @@ struct bpf_tramp_link { u64 cookie; }; +struct bpf_shim_tramp_link { + struct bpf_tramp_link link; + struct bpf_trampoline *trampoline; +}; + struct bpf_tracing_link { struct bpf_tramp_link link; enum bpf_attach_type attach_type; @@ -1245,6 +1255,9 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype); +void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { @@ -1268,6 +1281,14 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, { return -EINVAL; } +static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype) +{ + return -EOPNOTSUPP; +} +static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) +{ +} #endif struct bpf_array { @@ -2368,6 +2389,8 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; +extern const struct bpf_func_proto bpf_set_retval_proto; +extern const struct bpf_func_proto bpf_get_retval_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2485,6 +2508,7 @@ int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); +int btf_id_set_index(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 479c101546ad..61787a5f6af9 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -42,6 +42,9 @@ extern const struct bpf_func_proto bpf_inode_storage_get_proto; extern const struct bpf_func_proto bpf_inode_storage_delete_proto; void bpf_inode_storage_free(struct inode *inode); +int bpf_lsm_hook_idx(u32 btf_id); +void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); + #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -65,6 +68,16 @@ static inline void bpf_inode_storage_free(struct inode *inode) { } +static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, + bpf_func_t *bpf_func) +{ +} + +static inline int bpf_lsm_hook_idx(u32 btf_id) +{ + return -EINVAL; +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 335a19092368..252a4befeab1 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -179,7 +179,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e81362891596..b7479898c879 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -998,6 +998,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index c1351df9f7ee..0f72020bfdcf 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -16,6 +16,7 @@ #include #include #include +#include /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -35,6 +36,44 @@ BTF_SET_START(bpf_lsm_hooks) #undef LSM_HOOK BTF_SET_END(bpf_lsm_hooks) +/* List of LSM hooks that should operate on 'current' cgroup regardless + * of function signature. + */ +BTF_SET_START(bpf_lsm_current_hooks) +/* operate on freshly allocated sk without any cgroup association */ +BTF_ID(func, bpf_lsm_sk_alloc_security) +BTF_ID(func, bpf_lsm_sk_free_security) +BTF_SET_END(bpf_lsm_current_hooks) + +void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, + bpf_func_t *bpf_func) +{ + const struct btf_param *args; + + if (btf_type_vlen(prog->aux->attach_func_proto) < 1 || + btf_id_set_contains(&bpf_lsm_current_hooks, + prog->aux->attach_btf_id)) { + *bpf_func = __cgroup_bpf_run_lsm_current; + return; + } + + args = btf_params(prog->aux->attach_func_proto); + +#ifdef CONFIG_NET + if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCKET]) + *bpf_func = __cgroup_bpf_run_lsm_socket; + else if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCK]) + *bpf_func = __cgroup_bpf_run_lsm_sock; + else +#endif + *bpf_func = __cgroup_bpf_run_lsm_current; +} + +int bpf_lsm_hook_idx(u32 btf_id) +{ + return btf_id_set_index(&bpf_lsm_hooks, btf_id); +} + int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { @@ -158,6 +197,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL; case BPF_FUNC_get_attach_cookie: return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; + case BPF_FUNC_get_local_storage: + return prog->expected_attach_type == BPF_LSM_CGROUP ? + &bpf_get_local_storage_proto : NULL; + case BPF_FUNC_set_retval: + return prog->expected_attach_type == BPF_LSM_CGROUP ? + &bpf_set_retval_proto : NULL; + case BPF_FUNC_get_retval: + return prog->expected_attach_type == BPF_LSM_CGROUP ? + &bpf_get_retval_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2e2066d6af94..7c1fe422ed3f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5363,6 +5363,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (arg == nr_args) { switch (prog->expected_attach_type) { + case BPF_LSM_CGROUP: case BPF_LSM_MAC: case BPF_TRACE_FEXIT: /* When LSM programs are attached to void LSM hooks @@ -6842,6 +6843,16 @@ static int btf_id_cmp_func(const void *a, const void *b) return *pa - *pb; } +int btf_id_set_index(const struct btf_id_set *set, u32 id) +{ + const u32 *p; + + p = bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func); + if (!p) + return -1; + return p - set->ids; +} + bool btf_id_set_contains(const struct btf_id_set *set, u32 id) { return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4adb4f3ecb7f..9cf41dd4f96f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include @@ -61,6 +63,87 @@ bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, return run_ctx.retval; } +unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct sock *sk; + struct cgroup *cgrp; + int ret = 0; + u64 *args; + + args = (u64 *)ctx; + sk = (void *)(unsigned long)args[0]; + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct socket *sock; + struct cgroup *cgrp; + int ret = 0; + u64 *args; + + args = (u64 *)ctx; + sock = (void *)(unsigned long)args[0]; + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + cgrp = sock_cgroup_ptr(&sock->sk->sk_cgrp_data); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, + const struct bpf_insn *insn) +{ + const struct bpf_prog *shim_prog; + struct cgroup *cgrp; + int ret = 0; + + /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ + shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); + + /* We rely on trampoline's __bpf_prog_enter_lsm_cgroup to grab RCU read lock. */ + cgrp = task_dfl_cgroup(current); + if (likely(cgrp)) + ret = bpf_prog_run_array_cg(&cgrp->bpf, + shim_prog->aux->cgroup_atype, + ctx, bpf_prog_run, 0, NULL); + return ret; +} + +#ifdef CONFIG_BPF_LSM +static enum cgroup_bpf_attach_type +bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) +{ + if (attach_type != BPF_LSM_CGROUP) + return to_cgroup_bpf_attach_type(attach_type); + return CGROUP_LSM_START + bpf_lsm_hook_idx(attach_btf_id); +} +#else +static enum cgroup_bpf_attach_type +bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) +{ + if (attach_type != BPF_LSM_CGROUP) + return to_cgroup_bpf_attach_type(attach_type); + return -EOPNOTSUPP; +} +#endif /* CONFIG_BPF_LSM */ + void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); @@ -163,10 +246,16 @@ static void cgroup_bpf_release(struct work_struct *work) hlist_for_each_entry_safe(pl, pltmp, progs, node) { hlist_del(&pl->node); - if (pl->prog) + if (pl->prog) { + if (pl->prog->expected_attach_type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(pl->prog); bpf_prog_put(pl->prog); - if (pl->link) + } + if (pl->link) { + if (pl->link->link.prog->expected_attach_type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(pl->link->link.prog); bpf_cgroup_link_auto_detach(pl->link); + } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key[atype]); } @@ -479,6 +568,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; + struct bpf_prog *new_prog = prog ? : link->link.prog; enum cgroup_bpf_attach_type atype; struct bpf_prog_list *pl; struct hlist_head *progs; @@ -495,7 +585,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, /* replace_prog implies BPF_F_REPLACE, and vice versa */ return -EINVAL; - atype = to_cgroup_bpf_attach_type(type); + atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; @@ -549,17 +639,30 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; + if (type == BPF_LSM_CGROUP) { + err = bpf_trampoline_link_cgroup_shim(new_prog, atype); + if (err) + goto cleanup; + } + err = update_effective_progs(cgrp, atype); if (err) - goto cleanup; + goto cleanup_trampoline; - if (old_prog) + if (old_prog) { + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); - else + } else { static_branch_inc(&cgroup_bpf_enabled_key[atype]); + } bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; +cleanup_trampoline: + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(new_prog); + cleanup: if (old_prog) { pl->prog = old_prog; @@ -651,7 +754,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct hlist_head *progs; bool found = false; - atype = to_cgroup_bpf_attach_type(link->type); + atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; @@ -803,9 +906,15 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *old_prog; struct bpf_prog_list *pl; struct hlist_head *progs; + u32 attach_btf_id = 0; u32 flags; - atype = to_cgroup_bpf_attach_type(type); + if (prog) + attach_btf_id = prog->aux->attach_btf_id; + if (link) + attach_btf_id = link->link.prog->aux->attach_btf_id; + + atype = bpf_cgroup_atype_find(type, attach_btf_id); if (atype < 0) return -EINVAL; @@ -839,8 +948,11 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, if (hlist_empty(progs)) /* last program was detached, reset flags to zero */ cgrp->bpf.flags[atype] = 0; - if (old_prog) + if (old_prog) { + if (type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); + } static_branch_dec(&cgroup_bpf_enabled_key[atype]); return 0; } @@ -999,6 +1111,8 @@ static void bpf_cgroup_link_release(struct bpf_link *link) WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, cg_link->type)); + if (cg_link->type == BPF_LSM_CGROUP) + bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog); cg = cg_link->cgroup; cg_link->cgroup = NULL; @@ -1343,7 +1457,7 @@ BPF_CALL_0(bpf_get_retval) return ctx->retval; } -static const struct bpf_func_proto bpf_get_retval_proto = { +const struct bpf_func_proto bpf_get_retval_proto = { .func = bpf_get_retval, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1358,7 +1472,7 @@ BPF_CALL_1(bpf_set_retval, int, retval) return 0; } -static const struct bpf_func_proto bpf_set_retval_proto = { +const struct bpf_func_proto bpf_set_retval_proto = { .func = bpf_set_retval, .gpl_only = false, .ret_type = RET_INTEGER, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f023cb399e3f..4cc10b942a3c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2666,6 +2666,8 @@ const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; +const struct bpf_func_proto bpf_set_retval_proto __weak; +const struct bpf_func_proto bpf_get_retval_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7d5af5b99f0d..626b8f7d237b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3416,6 +3416,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; + case BPF_LSM_CGROUP: + return BPF_PROG_TYPE_LSM; default: return BPF_PROG_TYPE_UNSPEC; } @@ -3469,6 +3471,11 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_LSM: + if (ptype == BPF_PROG_TYPE_LSM && + prog->expected_attach_type != BPF_LSM_CGROUP) + return -EINVAL; + ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; default: @@ -3506,6 +3513,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_LSM: return cgroup_bpf_prog_detach(attr, ptype); default: return -EINVAL; @@ -4540,6 +4548,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_raw_tp_link_attach(prog, NULL); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); + else if (prog->expected_attach_type == BPF_LSM_CGROUP) + ret = cgroup_bpf_link_attach(attr, prog); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 5466e15be61f..d7c251d7fbcd 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -496,6 +498,177 @@ int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampolin return err; } +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +static void bpf_shim_tramp_link_release(struct bpf_link *link) +{ + struct bpf_shim_tramp_link *shim_link = + container_of(link, struct bpf_shim_tramp_link, link.link); + + /* paired with 'shim_link->trampoline = tr' in bpf_trampoline_link_cgroup_shim */ + if (!shim_link->trampoline) + return; + + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline)); + bpf_trampoline_put(shim_link->trampoline); +} + +static void bpf_shim_tramp_link_dealloc(struct bpf_link *link) +{ + struct bpf_shim_tramp_link *shim_link = + container_of(link, struct bpf_shim_tramp_link, link.link); + + kfree(shim_link); +} + +static const struct bpf_link_ops bpf_shim_tramp_link_lops = { + .release = bpf_shim_tramp_link_release, + .dealloc = bpf_shim_tramp_link_dealloc, +}; + +static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog, + bpf_func_t bpf_func, + int cgroup_atype) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_prog *p; + + shim_link = kzalloc(sizeof(*shim_link), GFP_USER); + if (!shim_link) + return NULL; + + p = bpf_prog_alloc(1, 0); + if (!p) { + kfree(shim_link); + return NULL; + } + + p->jited = false; + p->bpf_func = bpf_func; + + p->aux->cgroup_atype = cgroup_atype; + p->aux->attach_func_proto = prog->aux->attach_func_proto; + p->aux->attach_btf_id = prog->aux->attach_btf_id; + p->aux->attach_btf = prog->aux->attach_btf; + btf_get(p->aux->attach_btf); + p->type = BPF_PROG_TYPE_LSM; + p->expected_attach_type = BPF_LSM_MAC; + bpf_prog_inc(p); + bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC, + &bpf_shim_tramp_link_lops, p); + + return shim_link; +} + +static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr, + bpf_func_t bpf_func) +{ + struct bpf_tramp_link *link; + int kind; + + for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { + hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) { + struct bpf_prog *p = link->link.prog; + + if (p->bpf_func == bpf_func) + return container_of(link, struct bpf_shim_tramp_link, link); + } + } + + return NULL; +} + +int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_attach_target_info tgt_info = {}; + struct bpf_trampoline *tr; + bpf_func_t bpf_func; + u64 key; + int err; + + err = bpf_check_attach_target(NULL, prog, NULL, + prog->aux->attach_btf_id, + &tgt_info); + if (err) + return err; + + key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, + prog->aux->attach_btf_id); + + bpf_lsm_find_cgroup_shim(prog, &bpf_func); + tr = bpf_trampoline_get(key, &tgt_info); + if (!tr) + return -ENOMEM; + + mutex_lock(&tr->mutex); + + shim_link = cgroup_shim_find(tr, bpf_func); + if (shim_link) { + /* Reusing existing shim attached by the other program. */ + bpf_link_inc(&shim_link->link.link); + + mutex_unlock(&tr->mutex); + bpf_trampoline_put(tr); /* bpf_trampoline_get above */ + return 0; + } + + /* Allocate and install new shim. */ + + shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype); + if (!shim_link) { + err = -ENOMEM; + goto err; + } + + err = __bpf_trampoline_link_prog(&shim_link->link, tr); + if (err) + goto err; + + shim_link->trampoline = tr; + /* note, we're still holding tr refcnt from above */ + + mutex_unlock(&tr->mutex); + + return 0; +err: + mutex_unlock(&tr->mutex); + + if (shim_link) + bpf_link_put(&shim_link->link.link); + + /* have to release tr while _not_ holding its mutex */ + bpf_trampoline_put(tr); /* bpf_trampoline_get above */ + + return err; +} + +void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) +{ + struct bpf_shim_tramp_link *shim_link = NULL; + struct bpf_trampoline *tr; + bpf_func_t bpf_func; + u64 key; + + key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, + prog->aux->attach_btf_id); + + bpf_lsm_find_cgroup_shim(prog, &bpf_func); + tr = bpf_trampoline_lookup(key); + if (WARN_ON_ONCE(!tr)) + return; + + mutex_lock(&tr->mutex); + shim_link = cgroup_shim_find(tr, bpf_func); + mutex_unlock(&tr->mutex); + + if (shim_link) + bpf_link_put(&shim_link->link.link); + + bpf_trampoline_put(tr); /* bpf_trampoline_lookup above */ +} +#endif + struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { @@ -628,6 +801,31 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_ rcu_read_unlock(); } +u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) + __acquires(RCU) +{ + /* Runtime stats are exported via actual BPF_LSM_CGROUP + * programs, not the shims. + */ + rcu_read_lock(); + migrate_disable(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return NO_START_TIME; +} + +void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) + __releases(RCU) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + migrate_enable(); + rcu_read_unlock(); +} + u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) { rcu_read_lock_trace(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4938477912cd..df3ec6b05f05 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7322,6 +7322,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn reg_type_str(env, regs[BPF_REG_1].type)); return -EACCES; } + break; + case BPF_FUNC_set_retval: + if (env->prog->expected_attach_type == BPF_LSM_CGROUP) { + if (!env->prog->aux->attach_func_proto->type) { + /* Make sure programs that attach to void + * hooks don't try to modify return value. + */ + verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); + return -EINVAL; + } + } + break; } if (err) @@ -10527,6 +10539,22 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_SK_LOOKUP: range = tnum_range(SK_DROP, SK_PASS); break; + + case BPF_PROG_TYPE_LSM: + if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { + /* Regular BPF_PROG_TYPE_LSM programs can return + * any value. + */ + return 0; + } + if (!env->prog->aux->attach_func_proto->type) { + /* Make sure programs that attach to void + * hooks don't try to modify return value. + */ + range = tnum_range(1, 1); + } + break; + case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. @@ -10543,6 +10571,9 @@ static int check_return_code(struct bpf_verifier_env *env) if (!tnum_in(range, reg->var_off)) { verbose_invalid_scalar(env, reg, &range, "program exit", "R0"); + if (prog->expected_attach_type == BPF_LSM_CGROUP && + !prog->aux->attach_func_proto->type) + verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } @@ -14902,6 +14933,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: + case BPF_LSM_CGROUP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e81362891596..b7479898c879 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -998,6 +998,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From b79c9fc9551b45953a94abf550b7bd3b00e3a0f9 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 Jun 2022 10:43:08 -0700 Subject: bpf: implement BPF_PROG_QUERY for BPF_LSM_CGROUP We have two options: 1. Treat all BPF_LSM_CGROUP the same, regardless of attach_btf_id 2. Treat BPF_LSM_CGROUP+attach_btf_id as a separate hook point I was doing (2) in the original patch, but switching to (1) here: * bpf_prog_query returns all attached BPF_LSM_CGROUP programs regardless of attach_btf_id * attach_btf_id is exported via bpf_prog_info Reviewed-by: Martin KaFai Lau Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20220628174314.1216643-6-sdf@google.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 3 ++ kernel/bpf/cgroup.c | 95 ++++++++++++++++++++++++++++++++---------------- kernel/bpf/syscall.c | 8 +++- 3 files changed, 74 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b7479898c879..ad9e7311c4cf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1432,6 +1432,7 @@ union bpf_attr { __u32 attach_flags; __aligned_u64 prog_ids; __u32 prog_cnt; + __aligned_u64 prog_attach_flags; /* output: per-program attach_flags */ } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -6076,6 +6077,8 @@ struct bpf_prog_info { __u64 run_cnt; __u64 recursion_misses; __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 169cbd0de797..59b7eb60d5b4 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1017,57 +1017,90 @@ static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { + __u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags); __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; + enum cgroup_bpf_attach_type from_atype, to_atype; enum cgroup_bpf_attach_type atype; struct bpf_prog_array *effective; - struct hlist_head *progs; - struct bpf_prog *prog; int cnt, ret = 0, i; + int total_cnt = 0; u32 flags; - atype = to_cgroup_bpf_attach_type(type); - if (atype < 0) - return -EINVAL; - - progs = &cgrp->bpf.progs[atype]; - flags = cgrp->bpf.flags[atype]; + if (type == BPF_LSM_CGROUP) { + if (attr->query.prog_cnt && prog_ids && !prog_attach_flags) + return -EINVAL; - effective = rcu_dereference_protected(cgrp->bpf.effective[atype], - lockdep_is_held(&cgroup_mutex)); + from_atype = CGROUP_LSM_START; + to_atype = CGROUP_LSM_END; + flags = 0; + } else { + from_atype = to_cgroup_bpf_attach_type(type); + if (from_atype < 0) + return -EINVAL; + to_atype = from_atype; + flags = cgrp->bpf.flags[from_atype]; + } - if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) - cnt = bpf_prog_array_length(effective); - else - cnt = prog_list_length(progs); + for (atype = from_atype; atype <= to_atype; atype++) { + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + effective = rcu_dereference_protected(cgrp->bpf.effective[atype], + lockdep_is_held(&cgroup_mutex)); + total_cnt += bpf_prog_array_length(effective); + } else { + total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + } + } if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; - if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt))) return -EFAULT; - if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ return 0; - if (attr->query.prog_cnt < cnt) { - cnt = attr->query.prog_cnt; + + if (attr->query.prog_cnt < total_cnt) { + total_cnt = attr->query.prog_cnt; ret = -ENOSPC; } - if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { - return bpf_prog_array_copy_to_user(effective, prog_ids, cnt); - } else { - struct bpf_prog_list *pl; - u32 id; + for (atype = from_atype; atype <= to_atype && total_cnt; atype++) { + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + effective = rcu_dereference_protected(cgrp->bpf.effective[atype], + lockdep_is_held(&cgroup_mutex)); + cnt = min_t(int, bpf_prog_array_length(effective), total_cnt); + ret = bpf_prog_array_copy_to_user(effective, prog_ids, cnt); + } else { + struct hlist_head *progs; + struct bpf_prog_list *pl; + struct bpf_prog *prog; + u32 id; + + progs = &cgrp->bpf.progs[atype]; + cnt = min_t(int, prog_list_length(progs), total_cnt); + i = 0; + hlist_for_each_entry(pl, progs, node) { + prog = prog_list_prog(pl); + id = prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + } - i = 0; - hlist_for_each_entry(pl, progs, node) { - prog = prog_list_prog(pl); - id = prog->aux->id; - if (copy_to_user(prog_ids + i, &id, sizeof(id))) - return -EFAULT; - if (++i == cnt) - break; + if (prog_attach_flags) { + flags = cgrp->bpf.flags[atype]; + + for (i = 0; i < cnt; i++) + if (copy_to_user(prog_attach_flags + i, &flags, sizeof(flags))) + return -EFAULT; + prog_attach_flags += cnt; } + + prog_ids += cnt; + total_cnt -= cnt; } return ret; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 626b8f7d237b..ab688d85b2c6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3520,7 +3520,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) } } -#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt +#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -3556,6 +3556,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: + case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); @@ -4066,6 +4067,11 @@ static int bpf_prog_get_info_by_fd(struct file *file, if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); + info.attach_btf_id = prog->aux->attach_btf_id; + if (prog->aux->attach_btf) + info.attach_btf_obj_id = btf_obj_id(prog->aux->attach_btf); + else if (prog->aux->dst_prog) + info.attach_btf_obj_id = btf_obj_id(prog->aux->dst_prog->aux->attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; -- cgit v1.2.3 From 211da42eaa45db7b0edfde187dd88a85fbd466b5 Mon Sep 17 00:00:00 2001 From: Yuwei Wang Date: Wed, 29 Jun 2022 08:48:32 +0000 Subject: net, neigh: introduce interval_probe_time_ms for periodic probe commit ed6cd6a17896 ("net, neigh: Set lower cap for neigh_managed_work rearming") fixed a case when DELAY_PROBE_TIME is configured to 0, the processing of the system work queue hog CPU to 100%, and further more we should introduce a new option used by periodic probe Signed-off-by: Yuwei Wang Signed-off-by: Paolo Abeni --- Documentation/networking/ip-sysctl.rst | 6 ++++++ include/net/neighbour.h | 1 + include/uapi/linux/neighbour.h | 1 + include/uapi/linux/sysctl.h | 37 +++++++++++++++++----------------- net/core/neighbour.c | 32 +++++++++++++++++++++++++++-- net/decnet/dn_neigh.c | 1 + net/ipv4/arp.c | 1 + net/ipv6/ndisc.c | 1 + 8 files changed, 60 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 9f41961d11d5..4c8bbf5acfd1 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -202,6 +202,12 @@ neigh/default/unres_qlen - INTEGER Default: 101 +neigh/default/interval_probe_time_ms - INTEGER + The probe interval for neighbor entries with NTF_MANAGED flag, + the min value is 1. + + Default: 5000 + mtu_expires - INTEGER Time, in seconds, that cached PMTU information is kept. diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 87419f7f5421..9f0bab0589d9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -48,6 +48,7 @@ enum { NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, + NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 39c565e460c7..a998bf761635 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -154,6 +154,7 @@ enum { NDTPA_QUEUE_LENBYTES, /* u32 */ NDTPA_MCAST_REPROBES, /* u32 */ NDTPA_PAD, + NDTPA_INTERVAL_PROBE_TIME_MS, /* u64, msecs */ __NDTPA_MAX }; #define NDTPA_MAX (__NDTPA_MAX - 1) diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 6a3b194c50fe..8981f00204db 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -584,24 +584,25 @@ enum { /* /proc/sys/net//neigh/ */ enum { - NET_NEIGH_MCAST_SOLICIT=1, - NET_NEIGH_UCAST_SOLICIT=2, - NET_NEIGH_APP_SOLICIT=3, - NET_NEIGH_RETRANS_TIME=4, - NET_NEIGH_REACHABLE_TIME=5, - NET_NEIGH_DELAY_PROBE_TIME=6, - NET_NEIGH_GC_STALE_TIME=7, - NET_NEIGH_UNRES_QLEN=8, - NET_NEIGH_PROXY_QLEN=9, - NET_NEIGH_ANYCAST_DELAY=10, - NET_NEIGH_PROXY_DELAY=11, - NET_NEIGH_LOCKTIME=12, - NET_NEIGH_GC_INTERVAL=13, - NET_NEIGH_GC_THRESH1=14, - NET_NEIGH_GC_THRESH2=15, - NET_NEIGH_GC_THRESH3=16, - NET_NEIGH_RETRANS_TIME_MS=17, - NET_NEIGH_REACHABLE_TIME_MS=18, + NET_NEIGH_MCAST_SOLICIT = 1, + NET_NEIGH_UCAST_SOLICIT = 2, + NET_NEIGH_APP_SOLICIT = 3, + NET_NEIGH_RETRANS_TIME = 4, + NET_NEIGH_REACHABLE_TIME = 5, + NET_NEIGH_DELAY_PROBE_TIME = 6, + NET_NEIGH_GC_STALE_TIME = 7, + NET_NEIGH_UNRES_QLEN = 8, + NET_NEIGH_PROXY_QLEN = 9, + NET_NEIGH_ANYCAST_DELAY = 10, + NET_NEIGH_PROXY_DELAY = 11, + NET_NEIGH_LOCKTIME = 12, + NET_NEIGH_GC_INTERVAL = 13, + NET_NEIGH_GC_THRESH1 = 14, + NET_NEIGH_GC_THRESH2 = 15, + NET_NEIGH_GC_THRESH3 = 16, + NET_NEIGH_RETRANS_TIME_MS = 17, + NET_NEIGH_REACHABLE_TIME_MS = 18, + NET_NEIGH_INTERVAL_PROBE_TIME_MS = 19, }; /* /proc/sys/net/dccp */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d8ec70622ecb..6a8c2596ebab 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1579,7 +1579,7 @@ static void neigh_managed_work(struct work_struct *work) list_for_each_entry(neigh, &tbl->managed_list, managed_list) neigh_event_send_probe(neigh, NULL, false); queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, - max(NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME), HZ)); + NEIGH_VAR(&tbl->parms, INTERVAL_PROBE_TIME_MS)); write_unlock_bh(&tbl->lock); } @@ -2100,7 +2100,9 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) nla_put_msecs(skb, NDTPA_PROXY_DELAY, NEIGH_VAR(parms, PROXY_DELAY), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_LOCKTIME, - NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD)) + NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD) || + nla_put_msecs(skb, NDTPA_INTERVAL_PROBE_TIME_MS, + NEIGH_VAR(parms, INTERVAL_PROBE_TIME_MS), NDTPA_PAD)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -2255,6 +2257,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, [NDTPA_LOCKTIME] = { .type = NLA_U64 }, + [NDTPA_INTERVAL_PROBE_TIME_MS] = { .type = NLA_U64, .min = 1 }, }; static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2373,6 +2376,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, nla_get_msecs(tbp[i])); call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); break; + case NDTPA_INTERVAL_PROBE_TIME_MS: + NEIGH_VAR_SET(p, INTERVAL_PROBE_TIME_MS, + nla_get_msecs(tbp[i])); + break; case NDTPA_RETRANS_TIME: NEIGH_VAR_SET(p, RETRANS_TIME, nla_get_msecs(tbp[i])); @@ -3562,6 +3569,22 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, return ret; } +static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + int min = msecs_to_jiffies(1); + + tmp.extra1 = &min; + tmp.extra2 = NULL; + + ret = proc_dointvec_ms_jiffies_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3658,6 +3681,9 @@ static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, #define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) +#define NEIGH_SYSCTL_MS_JIFFIES_POSITIVE_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies_positive) + #define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) @@ -3676,6 +3702,8 @@ static struct neigh_sysctl_table { NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_MS_JIFFIES_POSITIVE_ENTRY(INTERVAL_PROBE_TIME_MS, + "interval_probe_time_ms"), NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index fbd98ac853ea..7c569bcc0aca 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -94,6 +94,7 @@ struct neigh_table dn_neigh_table = { [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 0, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index ab4a5601c82a..af2f12ffc9ca 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -168,6 +168,7 @@ struct neigh_table arp_tbl = { [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b0dfe97ea4ee..cd84cbdac0a2 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -128,6 +128,7 @@ struct neigh_table nd_tbl = { [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, -- cgit v1.2.3 From d7cfea332cca483ccd3970ed4de73ed892643e51 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Thu, 20 Jan 2022 15:06:30 -0500 Subject: drm/amdkfd: Add KFD SMI event IDs and triggers Define new system management interface event IDs for migration, GPU recoverable page fault, user queues eviction, restore and unmap from GPU events and corresponding event triggers, those will be implemented in the following patches. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 231eb010b823..280edda46faf 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -470,6 +470,43 @@ enum kfd_smi_event { KFD_SMI_EVENT_THERMAL_THROTTLE = 2, KFD_SMI_EVENT_GPU_PRE_RESET = 3, KFD_SMI_EVENT_GPU_POST_RESET = 4, + KFD_SMI_EVENT_MIGRATE_START = 5, + KFD_SMI_EVENT_MIGRATE_END = 6, + KFD_SMI_EVENT_PAGE_FAULT_START = 7, + KFD_SMI_EVENT_PAGE_FAULT_END = 8, + KFD_SMI_EVENT_QUEUE_EVICTION = 9, + KFD_SMI_EVENT_QUEUE_RESTORE = 10, + KFD_SMI_EVENT_UNMAP_FROM_GPU = 11, + + /* + * max event number, as a flag bit to get events from all processes, + * this requires super user permission, otherwise will not be able to + * receive event from any process. Without this flag to receive events + * from same process. + */ + KFD_SMI_EVENT_ALL_PROCESS = 64 +}; + +enum KFD_MIGRATE_TRIGGERS { + KFD_MIGRATE_TRIGGER_PREFETCH, + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + KFD_MIGRATE_TRIGGER_TTM_EVICTION +}; + +enum KFD_QUEUE_EVICTION_TRIGGERS { + KFD_QUEUE_EVICTION_TRIGGER_SVM, + KFD_QUEUE_EVICTION_TRIGGER_USERPTR, + KFD_QUEUE_EVICTION_TRIGGER_TTM, + KFD_QUEUE_EVICTION_TRIGGER_SUSPEND, + KFD_QUEUE_EVICTION_CRIU_CHECKPOINT, + KFD_QUEUE_EVICTION_CRIU_RESTORE +}; + +enum KFD_SVM_UNMAP_TRIGGERS { + KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY, + KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY_MIGRATE, + KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU }; #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) -- cgit v1.2.3 From 3db7f894549a54dd6f8dfb7fe213ede83249bb94 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Wed, 19 Jan 2022 12:57:26 -0500 Subject: drm/amdkfd: Bump KFD API version for SMI profiling event Indicate SMI profiling events available. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 280edda46faf..d993a0d50994 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -35,9 +35,10 @@ * - 1.7 - Checkpoint Restore (CRIU) API * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs * - 1.9 - Add available memory ioctl + * - 1.10 - Add SMI profiler event log */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 9 +#define KFD_IOCTL_MINOR_VERSION 10 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From ecad3b0b99bff7247a11f8c7cb19ac9b0cb28b09 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Mon, 23 May 2022 18:55:58 +0530 Subject: wifi: cfg80211: Increase akm_suites array size in cfg80211_crypto_settings Increase akm_suites array size in struct cfg80211_crypto_settings to 10 and advertise the capability to userspace. This allows userspace to send more than two AKMs to driver in netlink commands such as NL80211_CMD_CONNECT. This capability is needed for implementing WPA3-Personal transition mode correctly with any driver that handles roaming internally. Currently, the possible AKMs for multi-AKM connect can include PSK, PSK-SHA-256, SAE, FT-PSK and FT-SAE. Since the count is already 5, increasing the akm_suites array size to 10 should be reasonable for future usecases. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1653312358-12321-1-git-send-email-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- drivers/net/wireless/quantenna/qtnfmac/commands.c | 12 ++++++++---- include/net/cfg80211.h | 11 ++++++++++- include/uapi/linux/nl80211.h | 14 ++++++++++++++ net/wireless/core.c | 6 ++++++ net/wireless/nl80211.c | 7 ++++++- 5 files changed, 44 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index 3d734a7a5ba8..0fad53693292 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -241,6 +241,7 @@ int qtnf_cmd_send_start_ap(struct qtnf_vif *vif, struct qlink_auth_encr *aen; int ret; int i; + int n; if (!qtnf_cmd_start_ap_can_fit(vif, s)) return -E2BIG; @@ -280,8 +281,9 @@ int qtnf_cmd_send_start_ap(struct qtnf_vif *vif, for (i = 0; i < QLINK_MAX_NR_CIPHER_SUITES; i++) aen->ciphers_pairwise[i] = cpu_to_le32(s->crypto.ciphers_pairwise[i]); - aen->n_akm_suites = cpu_to_le32(s->crypto.n_akm_suites); - for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++) + n = min(QLINK_MAX_NR_AKM_SUITES, s->crypto.n_akm_suites); + aen->n_akm_suites = cpu_to_le32(n); + for (i = 0; i < n; i++) aen->akm_suites[i] = cpu_to_le32(s->crypto.akm_suites[i]); aen->control_port = s->crypto.control_port; aen->control_port_no_encrypt = s->crypto.control_port_no_encrypt; @@ -2076,6 +2078,7 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif, struct qlink_auth_encr *aen; int ret; int i; + int n; u32 connect_flags = 0; cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid, @@ -2132,9 +2135,10 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif, aen->ciphers_pairwise[i] = cpu_to_le32(sme->crypto.ciphers_pairwise[i]); - aen->n_akm_suites = cpu_to_le32(sme->crypto.n_akm_suites); + n = min(QLINK_MAX_NR_AKM_SUITES, sme->crypto.n_akm_suites); + aen->n_akm_suites = cpu_to_le32(n); - for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++) + for (i = 0; i < n; i++) aen->akm_suites[i] = cpu_to_le32(sme->crypto.akm_suites[i]); aen->control_port = sme->crypto.control_port; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 87ebed6a48bd..6bc161d653f3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1063,6 +1063,7 @@ struct survey_info { }; #define CFG80211_MAX_WEP_KEYS 4 +#define CFG80211_MAX_NUM_AKM_SUITES 10 /** * struct cfg80211_crypto_settings - Crypto settings @@ -1114,7 +1115,7 @@ struct cfg80211_crypto_settings { int n_ciphers_pairwise; u32 ciphers_pairwise[NL80211_MAX_NR_CIPHER_SUITES]; int n_akm_suites; - u32 akm_suites[NL80211_MAX_NR_AKM_SUITES]; + u32 akm_suites[CFG80211_MAX_NUM_AKM_SUITES]; bool control_port; __be16 control_port_ethertype; bool control_port_no_encrypt; @@ -5200,6 +5201,13 @@ struct wiphy_iftype_akm_suites { * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). + * @max_num_akm_suites: maximum number of AKM suites allowed for + * configuration through %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_START_AP. Set to NL80211_MAX_NR_AKM_SUITES if not set by + * driver. If set by driver minimum allowed value is + * NL80211_MAX_NR_AKM_SUITES in order to avoid compatibility issues with + * legacy userspace and maximum allowed value is + * CFG80211_MAX_NUM_AKM_SUITES. */ struct wiphy { struct mutex mtx; @@ -5346,6 +5354,7 @@ struct wiphy { u8 mbssid_max_interfaces; u8 ema_max_profile_periodicity; + u16 max_num_akm_suites; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 89f64f46b98d..279f9715919e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2694,6 +2694,13 @@ enum nl80211_commands { * connection. Used with %NL80211_CMD_CONNECT. If this attribute is not * included in NL80211_CMD_CONNECT drivers must not perform MLO connection. * + * @NL80211_ATTR_MAX_NUM_AKM_SUITES: U16 attribute. Indicates maximum number of + * AKM suites allowed for %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_START_AP in %NL80211_CMD_GET_WIPHY response. If this + * attribute is not present userspace shall consider maximum number of AKM + * suites allowed as %NL80211_MAX_NR_AKM_SUITES which is the legacy maximum + * number prior to the introduction of this attribute. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3214,6 +3221,8 @@ enum nl80211_attrs { NL80211_ATTR_MLO_SUPPORT, + NL80211_ATTR_MAX_NUM_AKM_SUITES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3268,6 +3277,11 @@ enum nl80211_attrs { #define NL80211_HE_MIN_CAPABILITY_LEN 16 #define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 + +/* + * NL80211_MAX_NR_AKM_SUITES is obsolete when %NL80211_ATTR_MAX_NUM_AKM_SUITES + * present in %NL80211_CMD_GET_WIPHY response. + */ #define NL80211_MAX_NR_AKM_SUITES 2 #define NL80211_EHT_MIN_CAPABILITY_LEN 13 #define NL80211_EHT_MAX_CAPABILITY_LEN 51 diff --git a/net/wireless/core.c b/net/wireless/core.c index 3e5d12040726..6b5321bb1176 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -913,6 +913,12 @@ int wiphy_register(struct wiphy *wiphy) return -EINVAL; #endif + if (!wiphy->max_num_akm_suites) + wiphy->max_num_akm_suites = NL80211_MAX_NR_AKM_SUITES; + else if (wiphy->max_num_akm_suites < NL80211_MAX_NR_AKM_SUITES || + wiphy->max_num_akm_suites > CFG80211_MAX_NUM_AKM_SUITES) + return -EINVAL; + /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b583a76ef492..e2b6740268a6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -798,6 +798,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, + [NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT }, }; /* policy for the key attributes */ @@ -2932,6 +2933,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_mbssid_support(&rdev->wiphy, msg)) goto nla_put_failure; + if (nla_put_u16(msg, NL80211_ATTR_MAX_NUM_AKM_SUITES, + rdev->wiphy.max_num_akm_suites)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -10431,7 +10436,7 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (len % sizeof(u32)) return -EINVAL; - if (settings->n_akm_suites > NL80211_MAX_NR_AKM_SUITES) + if (settings->n_akm_suites > rdev->wiphy.max_num_akm_suites) return -EINVAL; memcpy(settings->akm_suites, data, len); -- cgit v1.2.3 From 5e25c25aa2c08fb9a79476e029c0b1e3dcd70566 Mon Sep 17 00:00:00 2001 From: Petr Vaněk Date: Thu, 30 Jun 2022 16:27:20 +0200 Subject: xfrm: improve wording of comment above XFRM_OFFLOAD flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I have noticed a few minor wording issues in a comment recently added above XFRM_OFFLOAD flags in 7c76ecd9c99b ("xfrm: enforce validity of offload input flags"). Signed-off-by: Petr Vaněk Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 3ed61df9cc91..7929bf9cbee4 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -511,9 +511,9 @@ struct xfrm_user_offload { int ifindex; __u8 flags; }; -/* This flag was exposed without any kernel code that supporting it. - * Unfortunately, strongswan has the code that uses sets this flag, - * which makes impossible to reuse this bit. +/* This flag was exposed without any kernel code that supports it. + * Unfortunately, strongswan has the code that sets this flag, + * which makes it impossible to reuse this bit. * * So leave it here to make sure that it won't be reused by mistake. */ -- cgit v1.2.3 From 3c660a5d86f4c01cf641bfea004a49f5860a5bed Mon Sep 17 00:00:00 2001 From: Daniel Müller Date: Tue, 28 Jun 2022 16:01:18 +0000 Subject: bpf: Introduce TYPE_MATCH related constants/macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to provide type match support we require a new type of relocation which, in turn, requires toolchain support. Recent LLVM/Clang versions support a new value for the last argument to the __builtin_preserve_type_info builtin, for example. With this change we introduce the necessary constants into relevant header files, mirroring what the compiler may support. Signed-off-by: Daniel Müller Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220628160127.607834-2-deso@posteo.net --- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + tools/lib/bpf/bpf_core_read.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ad9e7311c4cf..379e68fb866f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6786,6 +6786,7 @@ enum bpf_core_relo_kind { BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ }; /* diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ad9e7311c4cf..379e68fb866f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6786,6 +6786,7 @@ enum bpf_core_relo_kind { BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ }; /* diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index fd48b1ff59ca..2308f4990e96 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -29,6 +29,7 @@ enum bpf_type_id_kind { enum bpf_type_info_kind { BPF_TYPE_EXISTS = 0, /* type existence in target kernel */ BPF_TYPE_SIZE = 1, /* type size in target kernel */ + BPF_TYPE_MATCHES = 2, /* type match in target kernel */ }; /* second argument to __builtin_preserve_enum_value() built-in */ -- cgit v1.2.3 From 88527790c079fb1ea41cbcfa4450ee37906a2fb0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 5 Jul 2022 16:59:24 -0700 Subject: tls: rx: add sockopt for enabling optimistic decrypt with TLS 1.3 Since optimisitic decrypt may add extra load in case of retries require socket owner to explicitly opt-in. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/tls.rst | 18 ++++++++++ include/linux/sockptr.h | 8 +++++ include/net/tls.h | 3 ++ include/uapi/linux/snmp.h | 1 + include/uapi/linux/tls.h | 2 ++ net/tls/tls_main.c | 75 ++++++++++++++++++++++++++++++++++++++++ net/tls/tls_proc.c | 1 + net/tls/tls_sw.c | 21 +++++++---- 8 files changed, 122 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index be8e10c14b05..7a6643836e42 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -239,6 +239,19 @@ for the original TCP transmission and TCP retransmissions. To the receiver this will look like TLS records had been tampered with and will result in record authentication failures. +TLS_RX_EXPECT_NO_PAD +~~~~~~~~~~~~~~~~~~~~ + +TLS 1.3 only. Expect the sender to not pad records. This allows the data +to be decrypted directly into user space buffers with TLS 1.3. + +This optimization is safe to enable only if the remote end is trusted, +otherwise it is an attack vector to doubling the TLS processing cost. + +If the record decrypted turns out to had been padded or is not a data +record it will be decrypted again into a kernel buffer without zero copy. +Such events are counted in the ``TlsDecryptRetry`` statistic. + Statistics ========== @@ -264,3 +277,8 @@ TLS implementation exposes the following per-namespace statistics - ``TlsDeviceRxResync`` - number of RX resyncs sent to NICs handling cryptography + +- ``TlsDecryptRetry`` - + number of RX records which had to be re-decrypted due to + ``TLS_RX_EXPECT_NO_PAD`` mis-prediction. Note that this counter will + also increment for non-data records. diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index ea193414298b..d45902fb4cad 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -102,4 +102,12 @@ static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) return strncpy_from_user(dst, src.user, count); } +static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, + size_t size) +{ + if (!sockptr_is_kernel(src)) + return check_zeroed_user(src.user + offset, size); + return memchr_inv(src.kernel + offset, 0, size) == NULL; +} + #endif /* _LINUX_SOCKPTR_H */ diff --git a/include/net/tls.h b/include/net/tls.h index 8017f1703447..4fc16ca5f469 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -149,6 +149,7 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 async_capable:1; + u8 zc_capable:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; @@ -239,6 +240,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; u8 zerocopy_sendfile:1; + u8 rx_no_pad:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); @@ -358,6 +360,7 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval, void tls_err_abort(struct sock *sk, int err); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); +void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 904909d020e2..1c9152add663 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -344,6 +344,7 @@ enum LINUX_MIB_TLSRXDEVICE, /* TlsRxDevice */ LINUX_MIB_TLSDECRYPTERROR, /* TlsDecryptError */ LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */ + LINUX_MIN_TLSDECRYPTRETRY, /* TlsDecryptRetry */ __LINUX_MIB_TLSMAX }; diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index bb8f80812b0b..f1157d8f4acd 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -40,6 +40,7 @@ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ #define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ +#define TLS_RX_EXPECT_NO_PAD 4 /* Attempt opportunistic zero-copy */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -162,6 +163,7 @@ enum { TLS_INFO_TXCONF, TLS_INFO_RXCONF, TLS_INFO_ZC_RO_TX, + TLS_INFO_RX_NO_PAD, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 2ffede463e4a..1b3efc96db0b 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -533,6 +533,37 @@ static int do_tls_getsockopt_tx_zc(struct sock *sk, char __user *optval, return 0; } +static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval, + int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + unsigned int value; + int err, len; + + if (ctx->prot_info.version != TLS_1_3_VERSION) + return -EINVAL; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < sizeof(value)) + return -EINVAL; + + lock_sock(sk); + err = -EINVAL; + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) + value = ctx->rx_no_pad; + release_sock(sk); + if (err) + return err; + + if (put_user(sizeof(value), optlen)) + return -EFAULT; + if (copy_to_user(optval, &value, sizeof(value))) + return -EFAULT; + + return 0; +} + static int do_tls_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { @@ -547,6 +578,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, case TLS_TX_ZEROCOPY_RO: rc = do_tls_getsockopt_tx_zc(sk, optval, optlen); break; + case TLS_RX_EXPECT_NO_PAD: + rc = do_tls_getsockopt_no_pad(sk, optval, optlen); + break; default: rc = -ENOPROTOOPT; break; @@ -718,6 +752,38 @@ static int do_tls_setsockopt_tx_zc(struct sock *sk, sockptr_t optval, return 0; } +static int do_tls_setsockopt_no_pad(struct sock *sk, sockptr_t optval, + unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + u32 val; + int rc; + + if (ctx->prot_info.version != TLS_1_3_VERSION || + sockptr_is_null(optval) || optlen < sizeof(val)) + return -EINVAL; + + rc = copy_from_sockptr(&val, optval, sizeof(val)); + if (rc) + return -EFAULT; + if (val > 1) + return -EINVAL; + rc = check_zeroed_sockptr(optval, sizeof(val), optlen - sizeof(val)); + if (rc < 1) + return rc == 0 ? -EINVAL : rc; + + lock_sock(sk); + rc = -EINVAL; + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) { + ctx->rx_no_pad = val; + tls_update_rx_zc_capable(ctx); + rc = 0; + } + release_sock(sk); + + return rc; +} + static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { @@ -736,6 +802,9 @@ static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, rc = do_tls_setsockopt_tx_zc(sk, optval, optlen); release_sock(sk); break; + case TLS_RX_EXPECT_NO_PAD: + rc = do_tls_setsockopt_no_pad(sk, optval, optlen); + break; default: rc = -ENOPROTOOPT; break; @@ -976,6 +1045,11 @@ static int tls_get_info(const struct sock *sk, struct sk_buff *skb) if (err) goto nla_failure; } + if (ctx->rx_no_pad) { + err = nla_put_flag(skb, TLS_INFO_RX_NO_PAD); + if (err) + goto nla_failure; + } rcu_read_unlock(); nla_nest_end(skb, start); @@ -997,6 +1071,7 @@ static size_t tls_get_info_size(const struct sock *sk) nla_total_size(sizeof(u16)) + /* TLS_INFO_RXCONF */ nla_total_size(sizeof(u16)) + /* TLS_INFO_TXCONF */ nla_total_size(0) + /* TLS_INFO_ZC_RO_TX */ + nla_total_size(0) + /* TLS_INFO_RX_NO_PAD */ 0; return size; diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c index feeceb0e4cb4..0c200000cc45 100644 --- a/net/tls/tls_proc.c +++ b/net/tls/tls_proc.c @@ -18,6 +18,7 @@ static const struct snmp_mib tls_mib_list[] = { SNMP_MIB_ITEM("TlsRxDevice", LINUX_MIB_TLSRXDEVICE), SNMP_MIB_ITEM("TlsDecryptError", LINUX_MIB_TLSDECRYPTERROR), SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC), + SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIN_TLSDECRYPTRETRY), SNMP_MIB_SENTINEL }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2bac57684429..7592b6519953 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1601,6 +1601,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { darg->zc = false; + TLS_INC_STATS(sock_net(sk), LINUX_MIN_TLSDECRYPTRETRY); return decrypt_skb_update(sk, skb, dest, darg); } @@ -1787,7 +1788,7 @@ int tls_sw_recvmsg(struct sock *sk, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); zc_capable = !bpf_strp_enabled && !is_kvec && !is_peek && - prot->version != TLS_1_3_VERSION; + ctx->zc_capable; decrypted = 0; while (len && (decrypted + copied < target || ctx->recv_pkt)) { struct tls_decrypt_arg darg = {}; @@ -2269,6 +2270,14 @@ void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) strp_check_rcv(&rx_ctx->strp); } +void tls_update_rx_zc_capable(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx); + + rx_ctx->zc_capable = tls_ctx->rx_no_pad || + tls_ctx->prot_info.version != TLS_1_3_VERSION; +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2504,12 +2513,10 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (sw_ctx_rx) { tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv); - if (crypto_info->version == TLS_1_3_VERSION) - sw_ctx_rx->async_capable = 0; - else - sw_ctx_rx->async_capable = - !!(tfm->__crt_alg->cra_flags & - CRYPTO_ALG_ASYNC); + tls_update_rx_zc_capable(ctx); + sw_ctx_rx->async_capable = + crypto_info->version != TLS_1_3_VERSION && + !!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC); /* Set up strparser */ memset(&cb, 0, sizeof(cb)); -- cgit v1.2.3 From fce7bf30d3309ea325a7ec452456f8f7c079f622 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 24 Jun 2022 11:03:37 -0400 Subject: drm/amdkfd: add new flag for svm It is to add new option for always keeping gpu mapping. Signed-off-by: Eric Huang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index d993a0d50994..d6bda40fbcf7 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -613,6 +613,8 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_EXEC 0x00000010 /* GPUs mostly read, may allow similar optimizations as RO, but writes fault */ #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 +/* Keep GPU memory mapping always valid as if XNACK is disable */ +#define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit v1.2.3 From 3f805f8cc23ba35679dd01446929292911c2b469 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Mon, 27 Jun 2022 08:35:25 -0700 Subject: LoadPin: Enable loading from trusted dm-verity devices Extend LoadPin to allow loading of kernel files from trusted dm-verity [1] devices. This change adds the concept of trusted verity devices to LoadPin. LoadPin maintains a list of root digests of verity devices it considers trusted. Userspace can populate this list through an ioctl on the new LoadPin securityfs entry 'dm-verity'. The ioctl receives a file descriptor of a file with verity digests as parameter. Verity reads the digests from this file after confirming that the file is located on the pinned root. The digest file must contain one digest per line. The list of trusted digests can only be set up once, which is typically done at boot time. When a kernel file is read LoadPin first checks (as usual) whether the file is located on the pinned root, if so the file can be loaded. Otherwise, if the verity extension is enabled, LoadPin determines whether the file is located on a verity backed device and whether the root digest of that device is in the list of trusted digests. The file can be loaded if the verity device has a trusted root digest. Background: As of now LoadPin restricts loading of kernel files to a single pinned filesystem, typically the rootfs. This works for many systems, however it can result in a bloated rootfs (and OTA updates) on platforms where multiple boards with different hardware configurations use the same rootfs image. Especially when 'optional' files are large it may be preferable to download/install them only when they are actually needed by a given board. Chrome OS uses Downloadable Content (DLC) [2] to deploy certain 'packages' at runtime. As an example a DLC package could contain firmware for a peripheral that is not present on all boards. DLCs use dm-verity to verify the integrity of the DLC content. [1] https://www.kernel.org/doc/html/latest/admin-guide/device-mapper/verity.html [2] https://chromium.googlesource.com/chromiumos/platform2/+/HEAD/dlcservice/docs/developer.md Signed-off-by: Matthias Kaehlcke Acked-by: Mike Snitzer Link: https://lore.kernel.org/lkml/20220627083512.v7.2.I01c67af41d2f6525c6d023101671d7339a9bc8b5@changeid Signed-off-by: Kees Cook --- include/uapi/linux/loadpin.h | 22 ++++++ security/loadpin/Kconfig | 16 +++++ security/loadpin/loadpin.c | 167 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 204 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/loadpin.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/loadpin.h b/include/uapi/linux/loadpin.h new file mode 100644 index 000000000000..daa6dbb8bb02 --- /dev/null +++ b/include/uapi/linux/loadpin.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2022, Google LLC + */ + +#ifndef _UAPI_LINUX_LOOP_LOADPIN_H +#define _UAPI_LINUX_LOOP_LOADPIN_H + +#define LOADPIN_IOC_MAGIC 'L' + +/** + * LOADPIN_IOC_SET_TRUSTED_VERITY_DIGESTS - Set up the root digests of verity devices + * that loadpin should trust. + * + * Takes a file descriptor from which to read the root digests of trusted verity devices. The file + * is expected to contain a list of digests in ASCII format, with one line per digest. The ioctl + * must be issued on the securityfs attribute 'loadpin/dm-verity' (which can be typically found + * under /sys/kernel/security/loadpin/dm-verity). + */ +#define LOADPIN_IOC_SET_TRUSTED_VERITY_DIGESTS _IOW(LOADPIN_IOC_MAGIC, 0x00, unsigned int) + +#endif /* _UAPI_LINUX_LOOP_LOADPIN_H */ diff --git a/security/loadpin/Kconfig b/security/loadpin/Kconfig index 91be65dec2ab..70e7985b2561 100644 --- a/security/loadpin/Kconfig +++ b/security/loadpin/Kconfig @@ -18,3 +18,19 @@ config SECURITY_LOADPIN_ENFORCE If selected, LoadPin will enforce pinning at boot. If not selected, it can be enabled at boot with the kernel parameter "loadpin.enforce=1". + +config SECURITY_LOADPIN_VERITY + bool "Allow reading files from certain other filesystems that use dm-verity" + depends on SECURITY_LOADPIN && DM_VERITY=y && SECURITYFS + help + If selected LoadPin can allow reading files from filesystems + that use dm-verity. LoadPin maintains a list of verity root + digests it considers trusted. A verity backed filesystem is + considered trusted if its root digest is found in the list + of trusted digests. + + The list of trusted verity can be populated through an ioctl + on the LoadPin securityfs entry 'dm-verity'. The ioctl + expects a file descriptor of a file with verity digests as + parameter. The file must be located on the pinned root and + contain a comma separated list of digests. diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index ad4e6756c038..6ab5f2bbf41f 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -18,6 +18,8 @@ #include #include /* current */ #include +#include +#include static void report_load(const char *origin, struct file *file, char *operation) { @@ -43,6 +45,9 @@ static char *exclude_read_files[READING_MAX_ID]; static int ignore_read_file_id[READING_MAX_ID] __ro_after_init; static struct super_block *pinned_root; static DEFINE_SPINLOCK(pinned_root_spinlock); +#ifdef CONFIG_SECURITY_LOADPIN_VERITY +static bool deny_reading_verity_digests; +#endif #ifdef CONFIG_SYSCTL @@ -171,7 +176,8 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id, spin_unlock(&pinned_root_spinlock); } - if (IS_ERR_OR_NULL(pinned_root) || load_root != pinned_root) { + if (IS_ERR_OR_NULL(pinned_root) || + ((load_root != pinned_root) && !dm_verity_loadpin_is_bdev_trusted(load_root->s_bdev))) { if (unlikely(!enforce)) { report_load(origin, file, "pinning-ignored"); return 0; @@ -237,6 +243,7 @@ static int __init loadpin_init(void) enforce ? "" : "not "); parse_exclude(); security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin"); + return 0; } @@ -245,6 +252,164 @@ DEFINE_LSM(loadpin) = { .init = loadpin_init, }; +#ifdef CONFIG_SECURITY_LOADPIN_VERITY + +enum loadpin_securityfs_interface_index { + LOADPIN_DM_VERITY, +}; + +static int read_trusted_verity_root_digests(unsigned int fd) +{ + struct fd f; + void *data; + int rc; + char *p, *d; + + if (deny_reading_verity_digests) + return -EPERM; + + /* The list of trusted root digests can only be set up once */ + if (!list_empty(&dm_verity_loadpin_trusted_root_digests)) + return -EPERM; + + f = fdget(fd); + if (!f.file) + return -EINVAL; + + data = kzalloc(SZ_4K, GFP_KERNEL); + if (!data) { + rc = -ENOMEM; + goto err; + } + + rc = kernel_read_file(f.file, 0, (void **)&data, SZ_4K - 1, NULL, READING_POLICY); + if (rc < 0) + goto err; + + p = data; + p[rc] = '\0'; + p = strim(p); + + p = strim(data); + while ((d = strsep(&p, "\n")) != NULL) { + int len = strlen(d); + struct dm_verity_loadpin_trusted_root_digest *trd; + + if (len % 2) { + rc = -EPROTO; + goto err; + } + + len /= 2; + + trd = kzalloc(struct_size(trd, data, len), GFP_KERNEL); + if (!trd) { + rc = -ENOMEM; + goto err; + } + + if (hex2bin(trd->data, d, len)) { + kfree(trd); + rc = -EPROTO; + goto err; + } + + trd->len = len; + + list_add_tail(&trd->node, &dm_verity_loadpin_trusted_root_digests); + } + + if (list_empty(&dm_verity_loadpin_trusted_root_digests)) { + rc = -EPROTO; + goto err; + } + + kfree(data); + fdput(f); + + return 0; + +err: + kfree(data); + + /* any failure in loading/parsing invalidates the entire list */ + { + struct dm_verity_loadpin_trusted_root_digest *trd, *tmp; + + list_for_each_entry_safe(trd, tmp, &dm_verity_loadpin_trusted_root_digests, node) { + list_del(&trd->node); + kfree(trd); + } + } + + /* disallow further attempts after reading a corrupt/invalid file */ + deny_reading_verity_digests = true; + + fdput(f); + + return rc; +} + +/******************************** securityfs ********************************/ + +static long dm_verity_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + void __user *uarg = (void __user *)arg; + unsigned int fd; + int rc; + + switch (cmd) { + case LOADPIN_IOC_SET_TRUSTED_VERITY_DIGESTS: + rc = copy_from_user(&fd, uarg, sizeof(fd)); + if (rc) + return rc; + + return read_trusted_verity_root_digests(fd); + + default: + return -EINVAL; + } +} + +static const struct file_operations loadpin_dm_verity_ops = { + .unlocked_ioctl = dm_verity_ioctl, + .compat_ioctl = compat_ptr_ioctl, +}; + +/** + * init_loadpin_securityfs - create the securityfs directory for LoadPin + * + * We can not put this method normally under the loadpin_init() code path since + * the security subsystem gets initialized before the vfs caches. + * + * Returns 0 if the securityfs directory creation was successful. + */ +static int __init init_loadpin_securityfs(void) +{ + struct dentry *loadpin_dir, *dentry; + + loadpin_dir = securityfs_create_dir("loadpin", NULL); + if (IS_ERR(loadpin_dir)) { + pr_err("LoadPin: could not create securityfs dir: %ld\n", + PTR_ERR(loadpin_dir)); + return PTR_ERR(loadpin_dir); + } + + dentry = securityfs_create_file("dm-verity", 0600, loadpin_dir, + (void *)LOADPIN_DM_VERITY, &loadpin_dm_verity_ops); + if (IS_ERR(dentry)) { + pr_err("LoadPin: could not create securityfs entry 'dm-verity': %ld\n", + PTR_ERR(dentry)); + return PTR_ERR(dentry); + } + + return 0; +} + +fs_initcall(init_loadpin_securityfs); + +#endif /* CONFIG_SECURITY_LOADPIN_VERITY */ + /* Should not be mutable after boot, so not listed in sysfs (perm == 0). */ module_param(enforce, int, 0); MODULE_PARM_DESC(enforce, "Enforce module/firmware pinning"); -- cgit v1.2.3 From faf3bfcb895037ae2a8b89d1048090c9e1291cae Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:22 -0400 Subject: vfio-pci/zdev: add function handle to clp base capability The function handle is a system-wide unique identifier for a zPCI device. With zPCI instruction interpretation, the host will no longer be executing the zPCI instructions on behalf of the guest. As a result, the guest needs to use the real function handle in order for firmware to associate the instruction with the proper PCI function. Let's provide that handle to the guest. Reviewed-by: Christian Borntraeger Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-19-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 5 +++-- include/uapi/linux/vfio_zdev.h | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 686f2e75e392..4f28cdd7ecd1 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -24,14 +24,15 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps) { struct vfio_device_info_cap_zpci_base cap = { .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE, - .header.version = 1, + .header.version = 2, .start_dma = zdev->start_dma, .end_dma = zdev->end_dma, .pchid = zdev->pchid, .vfn = zdev->vfn, .fmb_length = zdev->fmb_length, .pft = zdev->pft, - .gid = zdev->pfgid + .gid = zdev->pfgid, + .fh = zdev->fh }; return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index b4309397b6b2..78c022af3d29 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base { __u16 fmb_length; /* Measurement Block Length (in bytes) */ __u8 pft; /* PCI Function Type */ __u8 gid; /* PCI function group ID */ + /* End of version 1 */ + __u32 fh; /* PCI function handle */ + /* End of version 2 */ }; /** -- cgit v1.2.3 From ba6090ff8ae01b41288be87ed9f6bed3d8cf5961 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:23 -0400 Subject: vfio-pci/zdev: different maxstbl for interpreted devices When doing load/store interpretation, the maximum store block length is determined by the underlying firmware, not the host kernel API. Reflect that in the associated Query PCI Function Group clp capability and let userspace decide which is appropriate to present to the guest. Reviewed-by: Pierre Morel Signed-off-by: Matthew Rosato Acked-by: Alex Williamson Link: https://lore.kernel.org/r/20220606203325.110625-20-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- drivers/vfio/pci/vfio_pci_zdev.c | 6 ++++-- include/uapi/linux/vfio_zdev.h | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 4f28cdd7ecd1..e163aa9f6144 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -45,14 +45,16 @@ static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps) { struct vfio_device_info_cap_zpci_group cap = { .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP, - .header.version = 1, + .header.version = 2, .dasm = zdev->dma_mask, .msi_addr = zdev->msi_addr, .flags = VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH, .mui = zdev->fmb_update, .noi = zdev->max_msi, .maxstbl = ZPCI_MAX_WRITE_SIZE, - .version = zdev->version + .version = zdev->version, + .reserved = 0, + .imaxstbl = zdev->maxstbl }; return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h index 78c022af3d29..77f2aff1f27e 100644 --- a/include/uapi/linux/vfio_zdev.h +++ b/include/uapi/linux/vfio_zdev.h @@ -50,6 +50,10 @@ struct vfio_device_info_cap_zpci_group { __u16 noi; /* Maximum number of MSIs */ __u16 maxstbl; /* Maximum Store Block Length */ __u8 version; /* Supported PCI Version */ + /* End of version 1 */ + __u8 reserved; + __u16 imaxstbl; /* Maximum Interpreted Store Block Length */ + /* End of version 2 */ }; /** -- cgit v1.2.3 From db1c875e0539518e3d5fe9876ef50975cf4476bb Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Mon, 6 Jun 2022 16:33:24 -0400 Subject: KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices The KVM_S390_ZPCI_OP ioctl provides a mechanism for managing hardware-assisted virtualization features for s390x zPCI passthrough. Add the first 2 operations, which can be used to enable/disable the specified device for Adapter Event Notification interpretation. Signed-off-by: Matthew Rosato Acked-by: Pierre Morel Reviewed-by: Thomas Huth Link: https://lore.kernel.org/r/20220606203325.110625-21-mjrosato@linux.ibm.com Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/api.rst | 47 +++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 16 ++++++++ arch/s390/kvm/pci.c | 85 ++++++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/pci.h | 2 + include/uapi/linux/kvm.h | 31 +++++++++++++++ 5 files changed, 181 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 11e00a46c610..d58354e9af8f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5802,6 +5802,53 @@ of CPUID leaf 0xD on the host. This ioctl injects an event channel interrupt directly to the guest vCPU. +4.137 KVM_S390_ZPCI_OP +-------------------- + +:Capability: KVM_CAP_S390_ZPCI_OP +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_zpci_op (in) +:Returns: 0 on success, <0 on error + +Used to manage hardware-assisted virtualization features for zPCI devices. + +Parameters are specified via the following structure:: + + struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; + }; + +The type of operation is specified in the "op" field. +KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event +notification interpretation, which will allow firmware delivery of adapter +events directly to the vm, with KVM providing a backup delivery mechanism; +KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of +adapter event notifications. + +The target zPCI function must also be specified via the "fh" field. For the +KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware +delivery must be provided via the "reg_aen" struct. + +The "pad" and "reserved" fields may be used for future extensions and should be +set to 0s by userspace. + 5. The kvm_run structure ======================== diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4758bb731199..f214e0fc62ed 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -618,6 +618,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_PROTECTED: r = is_prot_virt_host(); break; + case KVM_CAP_S390_ZPCI_OP: + r = kvm_s390_pci_interp_allowed(); + break; default: r = 0; } @@ -2629,6 +2632,19 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_S390_ZPCI_OP: { + struct kvm_s390_zpci_op args; + + r = -EINVAL; + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + break; + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + r = kvm_s390_pci_zpci_op(kvm, &args); + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 24211741deb0..4946fb7757d6 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -585,6 +585,91 @@ void kvm_s390_pci_clear_list(struct kvm *kvm) spin_unlock(&kvm->arch.kzdev_list_lock); } +static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh) +{ + struct zpci_dev *zdev = NULL; + struct kvm_zdev *kzdev; + + spin_lock(&kvm->arch.kzdev_list_lock); + list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) { + if (kzdev->zdev->fh == fh) { + zdev = kzdev->zdev; + break; + } + } + spin_unlock(&kvm->arch.kzdev_list_lock); + + return zdev; +} + +static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev, + struct kvm_s390_zpci_op *args) +{ + struct zpci_fib fib = {}; + bool hostflag; + + fib.fmt0.aibv = args->u.reg_aen.ibv; + fib.fmt0.isc = args->u.reg_aen.isc; + fib.fmt0.noi = args->u.reg_aen.noi; + if (args->u.reg_aen.sb != 0) { + fib.fmt0.aisb = args->u.reg_aen.sb; + fib.fmt0.aisbo = args->u.reg_aen.sbo; + fib.fmt0.sum = 1; + } else { + fib.fmt0.aisb = 0; + fib.fmt0.aisbo = 0; + fib.fmt0.sum = 0; + } + + hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST); + return kvm_s390_pci_aif_enable(zdev, &fib, hostflag); +} + +int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args) +{ + struct kvm_zdev *kzdev; + struct zpci_dev *zdev; + int r; + + zdev = get_zdev_from_kvm_by_fh(kvm, args->fh); + if (!zdev) + return -ENODEV; + + mutex_lock(&zdev->kzdev_lock); + mutex_lock(&kvm->lock); + + kzdev = zdev->kzdev; + if (!kzdev) { + r = -ENODEV; + goto out; + } + if (kzdev->kvm != kvm) { + r = -EPERM; + goto out; + } + + switch (args->op) { + case KVM_S390_ZPCIOP_REG_AEN: + /* Fail on unknown flags */ + if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) { + r = -EINVAL; + break; + } + r = kvm_s390_pci_zpci_reg_aen(zdev, args); + break; + case KVM_S390_ZPCIOP_DEREG_AEN: + r = kvm_s390_pci_aif_disable(zdev, false); + break; + default: + r = -EINVAL; + } + +out: + mutex_unlock(&kvm->lock); + mutex_unlock(&zdev->kzdev_lock); + return r; +} + int kvm_s390_pci_init(void) { aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index fb2b91b76e0c..0351382e990f 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -59,6 +59,8 @@ void kvm_s390_pci_aen_exit(void); void kvm_s390_pci_init_list(struct kvm *kvm); void kvm_s390_pci_clear_list(struct kvm *kvm); +int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args); + int kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5088bd9f1922..2f302e2287d1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1157,6 +1157,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_ZPCI_OP 221 #ifdef KVM_CAP_IRQ_ROUTING @@ -2118,4 +2119,34 @@ struct kvm_stats_desc { /* Available with KVM_CAP_XSAVE2 */ #define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) +/* Available with KVM_CAP_S390_ZPCI_OP */ +#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From 3c512307de4097aaaab3f4741c7a98fe88afa469 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Fri, 8 Jul 2022 17:56:07 +0530 Subject: wifi: nl80211: fix sending link ID info of associated BSS commit dd374f84baec ("wifi: nl80211: expose link ID for associated BSSes") used a top-level attribute to send link ID of the associated BSS in the nested attribute NL80211_ATTR_BSS. But since NL80211_ATTR_BSS is a nested attribute of the attributes defined in enum nl80211_bss, define a new attribute in enum nl80211_bss and use it for sending the link ID of the BSS. Fixes: dd374f84baec ("wifi: nl80211: expose link ID for associated BSSes") Signed-off-by: Veerendranath Jakkam Reviewed-by: Jeff Johnson Link: https://lore.kernel.org/r/20220708122607.1836958-1-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ net/wireless/nl80211.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 279f9715919e..7bb1ae59f3a5 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4904,6 +4904,7 @@ enum nl80211_bss_scan_width { * Contains a nested array of signal strength attributes (u8, dBm), * using the nesting index as the antenna number. * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz + * @NL80211_BSS_MLO_LINK_ID: MLO link ID of the BSS (u8). * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -4929,6 +4930,7 @@ enum nl80211_bss { NL80211_BSS_PARENT_BSSID, NL80211_BSS_CHAIN_SIGNAL, NL80211_BSS_FREQUENCY_OFFSET, + NL80211_BSS_MLO_LINK_ID, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e20d0fc9678a..22c4cf6fbb57 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9991,7 +9991,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, (nla_put_u32(msg, NL80211_BSS_STATUS, NL80211_BSS_STATUS_ASSOCIATED) || (wdev->valid_links && - nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link_id)))) + nla_put_u8(msg, NL80211_BSS_MLO_LINK_ID, + link_id)))) goto nla_put_failure; } break; -- cgit v1.2.3 From 1090c1ea2208702a2fe0e3f71d262e3097d939f6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Jul 2022 19:52:52 -0700 Subject: tls: fix spelling of MIB MIN -> MIB Fixes: 88527790c079 ("tls: rx: add sockopt for enabling optimistic decrypt with TLS 1.3") Signed-off-by: Jakub Kicinski --- include/uapi/linux/snmp.h | 2 +- net/tls/tls_proc.c | 2 +- net/tls/tls_sw.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 1c9152add663..fd83fb9e525a 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -344,7 +344,7 @@ enum LINUX_MIB_TLSRXDEVICE, /* TlsRxDevice */ LINUX_MIB_TLSDECRYPTERROR, /* TlsDecryptError */ LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */ - LINUX_MIN_TLSDECRYPTRETRY, /* TlsDecryptRetry */ + LINUX_MIB_TLSDECRYPTRETRY, /* TlsDecryptRetry */ __LINUX_MIB_TLSMAX }; diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c index 1246e52b48f6..ede9df13c398 100644 --- a/net/tls/tls_proc.c +++ b/net/tls/tls_proc.c @@ -20,7 +20,7 @@ static const struct snmp_mib tls_mib_list[] = { SNMP_MIB_ITEM("TlsRxDevice", LINUX_MIB_TLSRXDEVICE), SNMP_MIB_ITEM("TlsDecryptError", LINUX_MIB_TLSDECRYPTERROR), SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC), - SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIN_TLSDECRYPTRETRY), + SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY), SNMP_MIB_SENTINEL }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 09370f853031..e12846d1871a 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1596,7 +1596,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { darg->zc = false; - TLS_INC_STATS(sock_net(sk), LINUX_MIN_TLSDECRYPTRETRY); + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTRETRY); return decrypt_skb_update(sk, skb, dest, darg); } -- cgit v1.2.3 From bb56cea9abd85c22175b31d8f7c44d6c615fe526 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Jul 2022 19:52:53 -0700 Subject: tls: rx: add counter for NoPad violations As discussed with Maxim add a counter for true NoPad violations. This should help deployments catch unexpected padded records vs just control records which always need re-encryption. https: //lore.kernel.org/all/b111828e6ac34baad9f4e783127eba8344ac252d.camel@nvidia.com/ Signed-off-by: Jakub Kicinski --- Documentation/networking/tls.rst | 4 ++++ include/uapi/linux/snmp.h | 1 + net/tls/tls_proc.c | 1 + net/tls/tls_sw.c | 2 ++ 4 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index 7a6643836e42..658ed3a71e1b 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -282,3 +282,7 @@ TLS implementation exposes the following per-namespace statistics number of RX records which had to be re-decrypted due to ``TLS_RX_EXPECT_NO_PAD`` mis-prediction. Note that this counter will also increment for non-data records. + +- ``TlsRxNoPadViolation`` - + number of data RX records which had to be re-decrypted due to + ``TLS_RX_EXPECT_NO_PAD`` mis-prediction. diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index fd83fb9e525a..4d7470036a8b 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -345,6 +345,7 @@ enum LINUX_MIB_TLSDECRYPTERROR, /* TlsDecryptError */ LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */ LINUX_MIB_TLSDECRYPTRETRY, /* TlsDecryptRetry */ + LINUX_MIB_TLSRXNOPADVIOL, /* TlsRxNoPadViolation */ __LINUX_MIB_TLSMAX }; diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c index ede9df13c398..68982728f620 100644 --- a/net/tls/tls_proc.c +++ b/net/tls/tls_proc.c @@ -21,6 +21,7 @@ static const struct snmp_mib tls_mib_list[] = { SNMP_MIB_ITEM("TlsDecryptError", LINUX_MIB_TLSDECRYPTERROR), SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC), SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY), + SNMP_MIB_ITEM("TlsRxNoPadViolation", LINUX_MIB_TLSRXNOPADVIOL), SNMP_MIB_SENTINEL }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index e12846d1871a..68d79ee48a56 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1596,6 +1596,8 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { darg->zc = false; + if (!darg->tail) + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTRETRY); return decrypt_skb_update(sk, skb, dest, darg); } -- cgit v1.2.3 From 50e8ca0b675add8eb0e95938448a4a0f9fb0b6dd Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Mon, 11 Jul 2022 14:10:55 -0400 Subject: drm/amdkfd: bump KFD version for unified ctx save/restore memory To expose unified memory for ctx save/resotre area feature availablity to libhsakmt. Proposed userspace: https://patchwork.freedesktop.org/series/106218/ Signed-off-by: Eric Huang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index d6bda40fbcf7..42b60198b6c5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -36,9 +36,10 @@ * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs * - 1.9 - Add available memory ioctl * - 1.10 - Add SMI profiler event log + * - 1.11 - Add unified memory for ctx save/restore area */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 10 +#define KFD_IOCTL_MINOR_VERSION 11 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From 71f28f3136aff5890cd56de78abc673f8393cad9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 13 Jul 2022 22:07:10 +0800 Subject: ublk_drv: add io_uring based userspace block driver This is the driver part of userspace block driver(ublk driver), the other part is userspace daemon part(ublksrv)[1]. The two parts communicate by io_uring's IORING_OP_URING_CMD with one shared cmd buffer for storing io command, and the buffer is read only for ublksrv, each io command is indexed by io request tag directly, and is written by ublk driver. For example, when one READ io request is submitted to ublk block driver, ublk driver stores the io command into cmd buffer first, then completes one IORING_OP_URING_CMD for notifying ublksrv, and the URING_CMD is issued to ublk driver beforehand by ublksrv for getting notification of any new io request, and each URING_CMD is associated with one io request by tag. After ublksrv gets the io command, it translates and handles the ublk io request, such as, for the ublk-loop target, ublksrv translates the request into same request on another file or disk, like the kernel loop block driver. In ublksrv's implementation, the io is still handled by io_uring, and share same ring with IORING_OP_URING_CMD command. When the target io request is done, the same IORING_OP_URING_CMD is issued to ublk driver for both committing io request result and getting future notification of new io request. Another thing done by ublk driver is to copy data between kernel io request and ublksrv's io buffer: 1) before ubsrv handles WRITE request, copy the request's data into ublksrv's userspace io buffer, so that ublksrv can handle the write request 2) after ubsrv handles READ request, copy ublksrv's userspace io buffer into this READ request, then ublk driver can complete the READ request Zero copy may be switched if mm is ready to support it. ublk driver doesn't handle any logic of the specific user space driver, so it is small/simple enough. [1] ublksrv https://github.com/ming1/ubdsrv Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220713140711.97356-2-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/Kconfig | 9 + drivers/block/Makefile | 2 + drivers/block/ublk_drv.c | 1530 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/ublk_cmd.h | 156 +++++ 4 files changed, 1697 insertions(+) create mode 100644 drivers/block/ublk_drv.c create mode 100644 include/uapi/linux/ublk_cmd.h (limited to 'include/uapi/linux') diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index fdb81f2794cd..e19fcab016ba 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -408,6 +408,15 @@ config BLK_DEV_RBD If unsure, say N. +config BLK_DEV_UBLK + tristate "Userspace block driver (Experimental)" + select IO_URING + help + io_uring based userspace block driver. Together with ublk server, ublk + has been working well, but interface with userspace or command data + definition isn't finalized yet, and might change according to future + requirement, so mark is as experimental now. + source "drivers/block/rnbd/Kconfig" endif # BLK_DEV diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 934a9c7c3a7c..be631352567e 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -39,4 +39,6 @@ obj-$(CONFIG_BLK_DEV_RNBD) += rnbd/ obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk/ +obj-$(CONFIG_BLK_DEV_UBLK) += ublk_drv.o + swim_mod-y := swim.o swim_asm.o diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c new file mode 100644 index 000000000000..922a84c86fc6 --- /dev/null +++ b/drivers/block/ublk_drv.c @@ -0,0 +1,1530 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Userspace block device - block device which IO is handled from userspace + * + * Take full use of io_uring passthrough command for communicating with + * ublk userspace daemon(ublksrvd) for handling basic IO request. + * + * Copyright 2022 Ming Lei + * + * (part of code stolen from loop.c) + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define UBLK_MINORS (1U << MINORBITS) + +struct ublk_uring_cmd_pdu { + struct request *req; +}; + +/* + * io command is active: sqe cmd is received, and its cqe isn't done + * + * If the flag is set, the io command is owned by ublk driver, and waited + * for incoming blk-mq request from the ublk block device. + * + * If the flag is cleared, the io command will be completed, and owned by + * ublk server. + */ +#define UBLK_IO_FLAG_ACTIVE 0x01 + +/* + * IO command is completed via cqe, and it is being handled by ublksrv, and + * not committed yet + * + * Basically exclusively with UBLK_IO_FLAG_ACTIVE, so can be served for + * cross verification + */ +#define UBLK_IO_FLAG_OWNED_BY_SRV 0x02 + +/* + * IO command is aborted, so this flag is set in case of + * !UBLK_IO_FLAG_ACTIVE. + * + * After this flag is observed, any pending or new incoming request + * associated with this io command will be failed immediately + */ +#define UBLK_IO_FLAG_ABORTED 0x04 + +struct ublk_io { + /* userspace buffer address from io cmd */ + __u64 addr; + unsigned int flags; + int res; + + struct io_uring_cmd *cmd; +}; + +struct ublk_queue { + int q_id; + int q_depth; + + struct task_struct *ubq_daemon; + char *io_cmd_buf; + + unsigned long io_addr; /* mapped vm address */ + unsigned int max_io_sz; + bool abort_work_pending; + unsigned short nr_io_ready; /* how many ios setup */ + struct ublk_device *dev; + struct ublk_io ios[0]; +}; + +#define UBLK_DAEMON_MONITOR_PERIOD (5 * HZ) + +struct ublk_device { + struct gendisk *ub_disk; + struct request_queue *ub_queue; + + char *__queues; + + unsigned short queue_size; + unsigned short bs_shift; + struct ublksrv_ctrl_dev_info dev_info; + + struct blk_mq_tag_set tag_set; + + struct cdev cdev; + struct device cdev_dev; + + atomic_t ch_open_cnt; + int ub_number; + + struct mutex mutex; + + struct mm_struct *mm; + + struct completion completion; + unsigned int nr_queues_ready; + atomic_t nr_aborted_queues; + + /* + * Our ubq->daemon may be killed without any notification, so + * monitor each queue's daemon periodically + */ + struct delayed_work monitor_work; + struct work_struct stop_work; +}; + +static dev_t ublk_chr_devt; +static struct class *ublk_chr_class; + +static DEFINE_IDR(ublk_index_idr); +static DEFINE_SPINLOCK(ublk_idr_lock); +static wait_queue_head_t ublk_idr_wq; /* wait until one idr is freed */ + +static DEFINE_MUTEX(ublk_ctl_mutex); + +static struct miscdevice ublk_misc; + +static struct ublk_device *ublk_get_device(struct ublk_device *ub) +{ + if (kobject_get_unless_zero(&ub->cdev_dev.kobj)) + return ub; + return NULL; +} + +static void ublk_put_device(struct ublk_device *ub) +{ + put_device(&ub->cdev_dev); +} + +static inline struct ublk_queue *ublk_get_queue(struct ublk_device *dev, + int qid) +{ + return (struct ublk_queue *)&(dev->__queues[qid * dev->queue_size]); +} + +static inline bool ublk_rq_has_data(const struct request *rq) +{ + return rq->bio && bio_has_data(rq->bio); +} + +static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq, + int tag) +{ + return (struct ublksrv_io_desc *) + &(ubq->io_cmd_buf[tag * sizeof(struct ublksrv_io_desc)]); +} + +static inline char *ublk_queue_cmd_buf(struct ublk_device *ub, int q_id) +{ + return ublk_get_queue(ub, q_id)->io_cmd_buf; +} + +static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id) +{ + struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + + return round_up(ubq->q_depth * sizeof(struct ublksrv_io_desc), + PAGE_SIZE); +} + +static int ublk_open(struct block_device *bdev, fmode_t mode) +{ + return 0; +} + +static void ublk_release(struct gendisk *disk, fmode_t mode) +{ +} + +static const struct block_device_operations ub_fops = { + .owner = THIS_MODULE, + .open = ublk_open, + .release = ublk_release, +}; + +#define UBLK_MAX_PIN_PAGES 32 + +struct ublk_map_data { + const struct ublk_queue *ubq; + const struct request *rq; + const struct ublk_io *io; + unsigned max_bytes; +}; + +struct ublk_io_iter { + struct page *pages[UBLK_MAX_PIN_PAGES]; + unsigned pg_off; /* offset in the 1st page in pages */ + int nr_pages; /* how many page pointers in pages */ + struct bio *bio; + struct bvec_iter iter; +}; + +static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data, + unsigned max_bytes, bool to_vm) +{ + const unsigned total = min_t(unsigned, max_bytes, + PAGE_SIZE - data->pg_off + + ((data->nr_pages - 1) << PAGE_SHIFT)); + unsigned done = 0; + unsigned pg_idx = 0; + + while (done < total) { + struct bio_vec bv = bio_iter_iovec(data->bio, data->iter); + const unsigned int bytes = min3(bv.bv_len, total - done, + (unsigned)(PAGE_SIZE - data->pg_off)); + void *bv_buf = bvec_kmap_local(&bv); + void *pg_buf = kmap_local_page(data->pages[pg_idx]); + + if (to_vm) + memcpy(pg_buf + data->pg_off, bv_buf, bytes); + else + memcpy(bv_buf, pg_buf + data->pg_off, bytes); + + kunmap_local(pg_buf); + kunmap_local(bv_buf); + + /* advance page array */ + data->pg_off += bytes; + if (data->pg_off == PAGE_SIZE) { + pg_idx += 1; + data->pg_off = 0; + } + + done += bytes; + + /* advance bio */ + bio_advance_iter_single(data->bio, &data->iter, bytes); + if (!data->iter.bi_size) { + data->bio = data->bio->bi_next; + if (data->bio == NULL) + break; + data->iter = data->bio->bi_iter; + } + } + + return done; +} + +static inline int ublk_copy_user_pages(struct ublk_map_data *data, + bool to_vm) +{ + const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0; + const unsigned long start_vm = data->io->addr; + unsigned int done = 0; + struct ublk_io_iter iter = { + .pg_off = start_vm & (PAGE_SIZE - 1), + .bio = data->rq->bio, + .iter = data->rq->bio->bi_iter, + }; + const unsigned int nr_pages = round_up(data->max_bytes + + (start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT; + + while (done < nr_pages) { + const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES, + nr_pages - done); + unsigned i, len; + + iter.nr_pages = get_user_pages_fast(start_vm + + (done << PAGE_SHIFT), to_pin, gup_flags, + iter.pages); + if (iter.nr_pages <= 0) + return done == 0 ? iter.nr_pages : done; + len = ublk_copy_io_pages(&iter, data->max_bytes, to_vm); + for (i = 0; i < iter.nr_pages; i++) { + if (to_vm) + set_page_dirty(iter.pages[i]); + put_page(iter.pages[i]); + } + data->max_bytes -= len; + done += iter.nr_pages; + } + + return done; +} + +static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, + struct ublk_io *io) +{ + const unsigned int rq_bytes = blk_rq_bytes(req); + /* + * no zero copy, we delay copy WRITE request data into ublksrv + * context and the big benefit is that pinning pages in current + * context is pretty fast, see ublk_pin_user_pages + */ + if (req_op(req) != REQ_OP_WRITE && req_op(req) != REQ_OP_FLUSH) + return rq_bytes; + + if (ublk_rq_has_data(req)) { + struct ublk_map_data data = { + .ubq = ubq, + .rq = req, + .io = io, + .max_bytes = rq_bytes, + }; + + ublk_copy_user_pages(&data, true); + + return rq_bytes - data.max_bytes; + } + return rq_bytes; +} + +static int ublk_unmap_io(const struct ublk_queue *ubq, + const struct request *req, + struct ublk_io *io) +{ + const unsigned int rq_bytes = blk_rq_bytes(req); + + if (req_op(req) == REQ_OP_READ && ublk_rq_has_data(req)) { + struct ublk_map_data data = { + .ubq = ubq, + .rq = req, + .io = io, + .max_bytes = io->res, + }; + + WARN_ON_ONCE(io->res > rq_bytes); + + ublk_copy_user_pages(&data, false); + + return io->res - data.max_bytes; + } + return rq_bytes; +} + +static inline unsigned int ublk_req_build_flags(struct request *req) +{ + unsigned flags = 0; + + if (req->cmd_flags & REQ_FAILFAST_DEV) + flags |= UBLK_IO_F_FAILFAST_DEV; + + if (req->cmd_flags & REQ_FAILFAST_TRANSPORT) + flags |= UBLK_IO_F_FAILFAST_TRANSPORT; + + if (req->cmd_flags & REQ_FAILFAST_DRIVER) + flags |= UBLK_IO_F_FAILFAST_DRIVER; + + if (req->cmd_flags & REQ_META) + flags |= UBLK_IO_F_META; + + if (req->cmd_flags & REQ_INTEGRITY) + flags |= UBLK_IO_F_INTEGRITY; + + if (req->cmd_flags & REQ_FUA) + flags |= UBLK_IO_F_FUA; + + if (req->cmd_flags & REQ_PREFLUSH) + flags |= UBLK_IO_F_PREFLUSH; + + if (req->cmd_flags & REQ_NOUNMAP) + flags |= UBLK_IO_F_NOUNMAP; + + if (req->cmd_flags & REQ_SWAP) + flags |= UBLK_IO_F_SWAP; + + return flags; +} + +static int ublk_setup_iod(struct ublk_queue *ubq, struct request *req) +{ + struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag); + struct ublk_io *io = &ubq->ios[req->tag]; + u32 ublk_op; + + switch (req_op(req)) { + case REQ_OP_READ: + ublk_op = UBLK_IO_OP_READ; + break; + case REQ_OP_WRITE: + ublk_op = UBLK_IO_OP_WRITE; + break; + case REQ_OP_FLUSH: + ublk_op = UBLK_IO_OP_FLUSH; + break; + case REQ_OP_DISCARD: + ublk_op = UBLK_IO_OP_DISCARD; + break; + case REQ_OP_WRITE_ZEROES: + ublk_op = UBLK_IO_OP_WRITE_ZEROES; + break; + default: + return BLK_STS_IOERR; + } + + /* need to translate since kernel may change */ + iod->op_flags = ublk_op | ublk_req_build_flags(req); + iod->nr_sectors = blk_rq_sectors(req); + iod->start_sector = blk_rq_pos(req); + iod->addr = io->addr; + + return BLK_STS_OK; +} + +static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( + struct io_uring_cmd *ioucmd) +{ + return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu; +} + +static bool ubq_daemon_is_dying(struct ublk_queue *ubq) +{ + return ubq->ubq_daemon->flags & PF_EXITING; +} + +/* todo: handle partial completion */ +static void ublk_complete_rq(struct request *req) +{ + struct ublk_queue *ubq = req->mq_hctx->driver_data; + struct ublk_io *io = &ubq->ios[req->tag]; + unsigned int unmapped_bytes; + + /* failed read IO if nothing is read */ + if (!io->res && req_op(req) == REQ_OP_READ) + io->res = -EIO; + + if (io->res < 0) { + blk_mq_end_request(req, errno_to_blk_status(io->res)); + return; + } + + /* + * FLUSH or DISCARD usually won't return bytes returned, so end them + * directly. + * + * Both the two needn't unmap. + */ + if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE) { + blk_mq_end_request(req, BLK_STS_OK); + return; + } + + /* for READ request, writing data in iod->addr to rq buffers */ + unmapped_bytes = ublk_unmap_io(ubq, req, io); + + /* + * Extremely impossible since we got data filled in just before + * + * Re-read simply for this unlikely case. + */ + if (unlikely(unmapped_bytes < io->res)) + io->res = unmapped_bytes; + + if (blk_update_request(req, BLK_STS_OK, io->res)) + blk_mq_requeue_request(req, true); + else + __blk_mq_end_request(req, BLK_STS_OK); +} + +/* + * __ublk_fail_req() may be called from abort context or ->ubq_daemon + * context during exiting, so lock is required. + * + * Also aborting may not be started yet, keep in mind that one failed + * request may be issued by block layer again. + */ +static void __ublk_fail_req(struct ublk_io *io, struct request *req) +{ + WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); + + if (!(io->flags & UBLK_IO_FLAG_ABORTED)) { + io->flags |= UBLK_IO_FLAG_ABORTED; + blk_mq_end_request(req, BLK_STS_IOERR); + } +} + +#define UBLK_REQUEUE_DELAY_MS 3 + +static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) +{ + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + struct ublk_device *ub = cmd->file->private_data; + struct request *req = pdu->req; + struct ublk_queue *ubq = req->mq_hctx->driver_data; + int tag = req->tag; + struct ublk_io *io = &ubq->ios[tag]; + bool task_exiting = current != ubq->ubq_daemon || + (current->flags & PF_EXITING); + unsigned int mapped_bytes; + + pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n", + __func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags, + ublk_get_iod(ubq, req->tag)->addr); + + if (unlikely(task_exiting)) { + blk_mq_end_request(req, BLK_STS_IOERR); + mod_delayed_work(system_wq, &ub->monitor_work, 0); + return; + } + + mapped_bytes = ublk_map_io(ubq, req, io); + + /* partially mapped, update io descriptor */ + if (unlikely(mapped_bytes != blk_rq_bytes(req))) { + /* + * Nothing mapped, retry until we succeed. + * + * We may never succeed in mapping any bytes here because + * of OOM. TODO: reserve one buffer with single page pinned + * for providing forward progress guarantee. + */ + if (unlikely(!mapped_bytes)) { + blk_mq_requeue_request(req, false); + blk_mq_delay_kick_requeue_list(req->q, + UBLK_REQUEUE_DELAY_MS); + return; + } + + ublk_get_iod(ubq, req->tag)->nr_sectors = + mapped_bytes >> 9; + } + + /* mark this cmd owned by ublksrv */ + io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV; + + /* + * clear ACTIVE since we are done with this sqe/cmd slot + * We can only accept io cmd in case of being not active. + */ + io->flags &= ~UBLK_IO_FLAG_ACTIVE; + + /* tell ublksrv one io request is coming */ + io_uring_cmd_done(io->cmd, UBLK_IO_RES_OK, 0); +} + +static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct ublk_queue *ubq = hctx->driver_data; + struct request *rq = bd->rq; + struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd; + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + blk_status_t res; + + /* fill iod to slot in io cmd buffer */ + res = ublk_setup_iod(ubq, rq); + if (unlikely(res != BLK_STS_OK)) + return BLK_STS_IOERR; + + blk_mq_start_request(bd->rq); + + if (unlikely(ubq_daemon_is_dying(ubq))) { + mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); + return BLK_STS_IOERR; + } + + pdu->req = rq; + io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + + return BLK_STS_OK; +} + + +static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, + unsigned int hctx_idx) +{ + struct ublk_device *ub = hctx->queue->queuedata; + struct ublk_queue *ubq = ublk_get_queue(ub, hctx->queue_num); + + hctx->driver_data = ubq; + return 0; +} + +static const struct blk_mq_ops ublk_mq_ops = { + .queue_rq = ublk_queue_rq, + .init_hctx = ublk_init_hctx, +}; + +static int ublk_ch_open(struct inode *inode, struct file *filp) +{ + struct ublk_device *ub = container_of(inode->i_cdev, + struct ublk_device, cdev); + + if (atomic_cmpxchg(&ub->ch_open_cnt, 0, 1) == 0) { + filp->private_data = ub; + return 0; + } + return -EBUSY; +} + +static int ublk_ch_release(struct inode *inode, struct file *filp) +{ + struct ublk_device *ub = filp->private_data; + + while (atomic_cmpxchg(&ub->ch_open_cnt, 1, 0) != 1) + cpu_relax(); + + filp->private_data = NULL; + return 0; +} + +/* map pre-allocated per-queue cmd buffer to ublksrv daemon */ +static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ublk_device *ub = filp->private_data; + size_t sz = vma->vm_end - vma->vm_start; + unsigned max_sz = UBLK_MAX_QUEUE_DEPTH * sizeof(struct ublksrv_io_desc); + unsigned long pfn, end, phys_off = vma->vm_pgoff << PAGE_SHIFT; + int q_id, ret = 0; + + mutex_lock(&ub->mutex); + if (!ub->mm) + ub->mm = current->mm; + if (current->mm != ub->mm) + ret = -EINVAL; + mutex_unlock(&ub->mutex); + + if (ret) + return ret; + + if (vma->vm_flags & VM_WRITE) + return -EPERM; + + end = UBLKSRV_CMD_BUF_OFFSET + ub->dev_info.nr_hw_queues * max_sz; + if (phys_off < UBLKSRV_CMD_BUF_OFFSET || phys_off >= end) + return -EINVAL; + + q_id = (phys_off - UBLKSRV_CMD_BUF_OFFSET) / max_sz; + pr_devel("%s: qid %d, pid %d, addr %lx pg_off %lx sz %lu\n", + __func__, q_id, current->pid, vma->vm_start, + phys_off, (unsigned long)sz); + + if (sz != ublk_queue_cmd_buf_size(ub, q_id)) + return -EINVAL; + + pfn = virt_to_phys(ublk_queue_cmd_buf(ub, q_id)) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); +} + +static void ublk_commit_completion(struct ublk_device *ub, + struct ublksrv_io_cmd *ub_cmd) +{ + u32 qid = ub_cmd->q_id, tag = ub_cmd->tag; + struct ublk_queue *ubq = ublk_get_queue(ub, qid); + struct ublk_io *io = &ubq->ios[tag]; + struct request *req; + + /* now this cmd slot is owned by nbd driver */ + io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV; + io->res = ub_cmd->result; + + /* find the io request and complete */ + req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag); + + if (req && likely(!blk_should_fake_timeout(req->q))) + ublk_complete_rq(req); +} + +/* + * When ->ubq_daemon is exiting, either new request is ended immediately, + * or any queued io command is drained, so it is safe to abort queue + * lockless + */ +static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) +{ + int i; + + if (!ublk_get_device(ub)) + return; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + if (!(io->flags & UBLK_IO_FLAG_ACTIVE)) { + struct request *rq; + + /* + * Either we fail the request or ublk_rq_task_work_fn + * will do it + */ + rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i); + if (rq) + __ublk_fail_req(io, rq); + } + } + ublk_put_device(ub); +} + +static void ublk_daemon_monitor_work(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, monitor_work.work); + int i; + + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + + if (ubq_daemon_is_dying(ubq)) { + schedule_work(&ub->stop_work); + + /* abort queue is for making forward progress */ + ublk_abort_queue(ub, ubq); + } + } + + /* + * We can't schedule monitor work after ublk_remove() is started. + * + * No need ub->mutex, monitor work are canceled after state is marked + * as DEAD, so DEAD state is observed reliably. + */ + if (ub->dev_info.state != UBLK_S_DEV_DEAD) + schedule_delayed_work(&ub->monitor_work, + UBLK_DAEMON_MONITOR_PERIOD); +} + +static void ublk_cancel_queue(struct ublk_queue *ubq) +{ + int i; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + if (io->flags & UBLK_IO_FLAG_ACTIVE) + io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0); + } +} + +/* Cancel all pending commands, must be called after del_gendisk() returns */ +static void ublk_cancel_dev(struct ublk_device *ub) +{ + int i; + + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_cancel_queue(ublk_get_queue(ub, i)); +} + +static void ublk_stop_dev(struct ublk_device *ub) +{ + mutex_lock(&ub->mutex); + if (!disk_live(ub->ub_disk)) + goto unlock; + + del_gendisk(ub->ub_disk); + ub->dev_info.state = UBLK_S_DEV_DEAD; + ub->dev_info.ublksrv_pid = -1; + ublk_cancel_dev(ub); + unlock: + mutex_unlock(&ub->mutex); + cancel_delayed_work_sync(&ub->monitor_work); +} + +static int ublk_ctrl_stop_dev(struct ublk_device *ub) +{ + ublk_stop_dev(ub); + cancel_work_sync(&ub->stop_work); + return 0; +} + +static inline bool ublk_queue_ready(struct ublk_queue *ubq) +{ + return ubq->nr_io_ready == ubq->q_depth; +} + +/* device can only be started after all IOs are ready */ +static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) +{ + mutex_lock(&ub->mutex); + ubq->nr_io_ready++; + if (ublk_queue_ready(ubq)) { + ubq->ubq_daemon = current; + get_task_struct(ubq->ubq_daemon); + ub->nr_queues_ready++; + } + if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) + complete_all(&ub->completion); + mutex_unlock(&ub->mutex); +} + +static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd; + struct ublk_device *ub = cmd->file->private_data; + struct ublk_queue *ubq; + struct ublk_io *io; + u32 cmd_op = cmd->cmd_op; + unsigned tag = ub_cmd->tag; + int ret = -EINVAL; + + pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n", + __func__, cmd->cmd_op, ub_cmd->q_id, tag, + ub_cmd->result); + + if (!(issue_flags & IO_URING_F_SQE128)) + goto out; + + if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues) + goto out; + + ubq = ublk_get_queue(ub, ub_cmd->q_id); + if (!ubq || ub_cmd->q_id != ubq->q_id) + goto out; + + if (ubq->ubq_daemon && ubq->ubq_daemon != current) + goto out; + + if (tag >= ubq->q_depth) + goto out; + + io = &ubq->ios[tag]; + + /* there is pending io cmd, something must be wrong */ + if (io->flags & UBLK_IO_FLAG_ACTIVE) { + ret = -EBUSY; + goto out; + } + + switch (cmd_op) { + case UBLK_IO_FETCH_REQ: + /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ + if (ublk_queue_ready(ubq)) { + ret = -EBUSY; + goto out; + } + /* + * The io is being handled by server, so COMMIT_RQ is expected + * instead of FETCH_REQ + */ + if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) + goto out; + /* FETCH_RQ has to provide IO buffer */ + if (!ub_cmd->addr) + goto out; + io->cmd = cmd; + io->flags |= UBLK_IO_FLAG_ACTIVE; + io->addr = ub_cmd->addr; + + ublk_mark_io_ready(ub, ubq); + break; + case UBLK_IO_COMMIT_AND_FETCH_REQ: + /* FETCH_RQ has to provide IO buffer */ + if (!ub_cmd->addr) + goto out; + if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) + goto out; + io->addr = ub_cmd->addr; + io->flags |= UBLK_IO_FLAG_ACTIVE; + io->cmd = cmd; + ublk_commit_completion(ub, ub_cmd); + break; + default: + goto out; + } + return -EIOCBQUEUED; + + out: + io->flags &= ~UBLK_IO_FLAG_ACTIVE; + io_uring_cmd_done(cmd, ret, 0); + pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n", + __func__, cmd_op, tag, ret, io->flags); + return -EIOCBQUEUED; +} + +static const struct file_operations ublk_ch_fops = { + .owner = THIS_MODULE, + .open = ublk_ch_open, + .release = ublk_ch_release, + .llseek = no_llseek, + .uring_cmd = ublk_ch_uring_cmd, + .mmap = ublk_ch_mmap, +}; + +static void ublk_deinit_queue(struct ublk_device *ub, int q_id) +{ + int size = ublk_queue_cmd_buf_size(ub, q_id); + struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + + if (ubq->ubq_daemon) + put_task_struct(ubq->ubq_daemon); + if (ubq->io_cmd_buf) + free_pages((unsigned long)ubq->io_cmd_buf, get_order(size)); +} + +static int ublk_init_queue(struct ublk_device *ub, int q_id) +{ + struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO; + void *ptr; + int size; + + ubq->q_id = q_id; + ubq->q_depth = ub->dev_info.queue_depth; + size = ublk_queue_cmd_buf_size(ub, q_id); + + ptr = (void *) __get_free_pages(gfp_flags, get_order(size)); + if (!ptr) + return -ENOMEM; + + ubq->io_cmd_buf = ptr; + ubq->dev = ub; + return 0; +} + +static void ublk_deinit_queues(struct ublk_device *ub) +{ + int nr_queues = ub->dev_info.nr_hw_queues; + int i; + + if (!ub->__queues) + return; + + for (i = 0; i < nr_queues; i++) + ublk_deinit_queue(ub, i); + kfree(ub->__queues); +} + +static int ublk_init_queues(struct ublk_device *ub) +{ + int nr_queues = ub->dev_info.nr_hw_queues; + int depth = ub->dev_info.queue_depth; + int ubq_size = sizeof(struct ublk_queue) + depth * sizeof(struct ublk_io); + int i, ret = -ENOMEM; + + ub->queue_size = ubq_size; + ub->__queues = kcalloc(nr_queues, ubq_size, GFP_KERNEL); + if (!ub->__queues) + return ret; + + for (i = 0; i < nr_queues; i++) { + if (ublk_init_queue(ub, i)) + goto fail; + } + + init_completion(&ub->completion); + return 0; + + fail: + ublk_deinit_queues(ub); + return ret; +} + +static int __ublk_alloc_dev_number(struct ublk_device *ub, int idx) +{ + int i = idx; + int err; + + spin_lock(&ublk_idr_lock); + /* allocate id, if @id >= 0, we're requesting that specific id */ + if (i >= 0) { + err = idr_alloc(&ublk_index_idr, ub, i, i + 1, GFP_NOWAIT); + if (err == -ENOSPC) + err = -EEXIST; + } else { + err = idr_alloc(&ublk_index_idr, ub, 0, 0, GFP_NOWAIT); + } + spin_unlock(&ublk_idr_lock); + + if (err >= 0) + ub->ub_number = err; + + return err; +} + +static struct ublk_device *__ublk_create_dev(int idx) +{ + struct ublk_device *ub = NULL; + int ret; + + ub = kzalloc(sizeof(*ub), GFP_KERNEL); + if (!ub) + return ERR_PTR(-ENOMEM); + + ret = __ublk_alloc_dev_number(ub, idx); + if (ret < 0) { + kfree(ub); + return ERR_PTR(ret); + } + return ub; +} + +static void __ublk_destroy_dev(struct ublk_device *ub) +{ + spin_lock(&ublk_idr_lock); + idr_remove(&ublk_index_idr, ub->ub_number); + wake_up_all(&ublk_idr_wq); + spin_unlock(&ublk_idr_lock); + + mutex_destroy(&ub->mutex); + + kfree(ub); +} + +static void ublk_cdev_rel(struct device *dev) +{ + struct ublk_device *ub = container_of(dev, struct ublk_device, cdev_dev); + + put_disk(ub->ub_disk); + + blk_mq_free_tag_set(&ub->tag_set); + + ublk_deinit_queues(ub); + + __ublk_destroy_dev(ub); +} + +static int ublk_add_chdev(struct ublk_device *ub) +{ + struct device *dev = &ub->cdev_dev; + int minor = ub->ub_number; + int ret; + + dev->parent = ublk_misc.this_device; + dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor); + dev->class = ublk_chr_class; + dev->release = ublk_cdev_rel; + device_initialize(dev); + + ret = dev_set_name(dev, "ublkc%d", minor); + if (ret) + goto fail; + + cdev_init(&ub->cdev, &ublk_ch_fops); + ret = cdev_device_add(&ub->cdev, dev); + if (ret) + goto fail; + return 0; + fail: + put_device(dev); + return ret; +} + +static void ublk_stop_work_fn(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, stop_work); + + ublk_stop_dev(ub); +} + +static void ublk_update_capacity(struct ublk_device *ub) +{ + unsigned int max_rq_bytes; + + /* make max request buffer size aligned with PAGE_SIZE */ + max_rq_bytes = round_down(ub->dev_info.rq_max_blocks << + ub->bs_shift, PAGE_SIZE); + ub->dev_info.rq_max_blocks = max_rq_bytes >> ub->bs_shift; + + set_capacity(ub->ub_disk, ub->dev_info.dev_blocks << (ub->bs_shift - 9)); +} + +/* add disk & cdev, cleanup everything in case of failure */ +static int ublk_add_dev(struct ublk_device *ub) +{ + struct gendisk *disk; + int err = -ENOMEM; + int bsize; + + /* We are not ready to support zero copy */ + ub->dev_info.flags[0] &= ~UBLK_F_SUPPORT_ZERO_COPY; + + bsize = ub->dev_info.block_size; + ub->bs_shift = ilog2(bsize); + + ub->dev_info.nr_hw_queues = min_t(unsigned int, + ub->dev_info.nr_hw_queues, nr_cpu_ids); + + INIT_WORK(&ub->stop_work, ublk_stop_work_fn); + INIT_DELAYED_WORK(&ub->monitor_work, ublk_daemon_monitor_work); + + if (ublk_init_queues(ub)) + goto out_destroy_dev; + + ub->tag_set.ops = &ublk_mq_ops; + ub->tag_set.nr_hw_queues = ub->dev_info.nr_hw_queues; + ub->tag_set.queue_depth = ub->dev_info.queue_depth; + ub->tag_set.numa_node = NUMA_NO_NODE; + ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + ub->tag_set.driver_data = ub; + + err = blk_mq_alloc_tag_set(&ub->tag_set); + if (err) + goto out_deinit_queues; + + disk = ub->ub_disk = blk_mq_alloc_disk(&ub->tag_set, ub); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); + goto out_cleanup_tags; + } + ub->ub_queue = ub->ub_disk->queue; + + ub->ub_queue->queuedata = ub; + + blk_queue_logical_block_size(ub->ub_queue, bsize); + blk_queue_physical_block_size(ub->ub_queue, bsize); + blk_queue_io_min(ub->ub_queue, bsize); + + blk_queue_max_hw_sectors(ub->ub_queue, ub->dev_info.rq_max_blocks << + (ub->bs_shift - 9)); + + ub->ub_queue->limits.discard_granularity = PAGE_SIZE; + + blk_queue_max_discard_sectors(ub->ub_queue, UINT_MAX >> 9); + blk_queue_max_write_zeroes_sectors(ub->ub_queue, UINT_MAX >> 9); + + ublk_update_capacity(ub); + + disk->fops = &ub_fops; + disk->private_data = ub; + disk->queue = ub->ub_queue; + sprintf(disk->disk_name, "ublkb%d", ub->ub_number); + + mutex_init(&ub->mutex); + + /* add char dev so that ublksrv daemon can be setup */ + err = ublk_add_chdev(ub); + if (err) + return err; + + /* don't expose disk now until we got start command from cdev */ + + return 0; + +out_cleanup_tags: + blk_mq_free_tag_set(&ub->tag_set); +out_deinit_queues: + ublk_deinit_queues(ub); +out_destroy_dev: + __ublk_destroy_dev(ub); + return err; +} + +static void ublk_remove(struct ublk_device *ub) +{ + ublk_ctrl_stop_dev(ub); + + cdev_device_del(&ub->cdev, &ub->cdev_dev); + put_device(&ub->cdev_dev); +} + +static struct ublk_device *ublk_get_device_from_id(int idx) +{ + struct ublk_device *ub = NULL; + + if (idx < 0) + return NULL; + + spin_lock(&ublk_idr_lock); + ub = idr_find(&ublk_index_idr, idx); + if (ub) + ub = ublk_get_device(ub); + spin_unlock(&ublk_idr_lock); + + return ub; +} + +static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + int ret = -EINVAL; + int ublksrv_pid = (int)header->data[0]; + unsigned long dev_blocks = header->data[1]; + + if (ublksrv_pid <= 0) + return ret; + + wait_for_completion_interruptible(&ub->completion); + + schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD); + + mutex_lock(&ub->mutex); + if (!disk_live(ub->ub_disk)) { + /* We may get disk size updated */ + if (dev_blocks) { + ub->dev_info.dev_blocks = dev_blocks; + ublk_update_capacity(ub); + } + ub->dev_info.ublksrv_pid = ublksrv_pid; + ret = add_disk(ub->ub_disk); + if (!ret) + ub->dev_info.state = UBLK_S_DEV_LIVE; + } else { + ret = -EEXIST; + } + mutex_unlock(&ub->mutex); + + return ret; +} + +static struct blk_mq_hw_ctx *ublk_get_hw_queue(struct ublk_device *ub, + unsigned int index) +{ + struct blk_mq_hw_ctx *hctx; + unsigned long i; + + queue_for_each_hw_ctx(ub->ub_queue, hctx, i) + if (hctx->queue_num == index) + return hctx; + return NULL; +} + +static int ublk_ctrl_get_queue_affinity(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct blk_mq_hw_ctx *hctx; + struct ublk_device *ub; + unsigned long queue; + unsigned int retlen; + int ret; + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + goto out; + + ret = -EINVAL; + queue = header->data[0]; + if (queue >= ub->dev_info.nr_hw_queues) + goto out; + hctx = ublk_get_hw_queue(ub, queue); + if (!hctx) + goto out; + + retlen = min_t(unsigned short, header->len, cpumask_size()); + if (copy_to_user(argp, hctx->cpumask, retlen)) { + ret = -EFAULT; + goto out; + } + if (retlen != header->len) { + if (clear_user(argp + retlen, header->len - retlen)) { + ret = -EFAULT; + goto out; + } + } + ret = 0; + out: + if (ub) + ublk_put_device(ub); + return ret; +} + +static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_dev_info *info, + void __user *argp, int idx) +{ + struct ublk_device *ub; + int ret; + + ret = mutex_lock_killable(&ublk_ctl_mutex); + if (ret) + return ret; + + ub = __ublk_create_dev(idx); + if (!IS_ERR_OR_NULL(ub)) { + memcpy(&ub->dev_info, info, sizeof(*info)); + + /* update device id */ + ub->dev_info.dev_id = ub->ub_number; + + ret = ublk_add_dev(ub); + if (!ret) { + if (copy_to_user(argp, &ub->dev_info, sizeof(*info))) { + ublk_remove(ub); + ret = -EFAULT; + } + } + } else { + if (IS_ERR(ub)) + ret = PTR_ERR(ub); + else + ret = -ENOMEM; + } + mutex_unlock(&ublk_ctl_mutex); + + return ret; +} + +static inline bool ublk_idr_freed(int id) +{ + void *ptr; + + spin_lock(&ublk_idr_lock); + ptr = idr_find(&ublk_index_idr, id); + spin_unlock(&ublk_idr_lock); + + return ptr == NULL; +} + +static int ublk_ctrl_del_dev(int idx) +{ + struct ublk_device *ub; + int ret; + + ret = mutex_lock_killable(&ublk_ctl_mutex); + if (ret) + return ret; + + ub = ublk_get_device_from_id(idx); + if (ub) { + ublk_remove(ub); + ublk_put_device(ub); + ret = 0; + } else { + ret = -ENODEV; + } + + /* + * Wait until the idr is removed, then it can be reused after + * DEL_DEV command is returned. + */ + if (!ret) + wait_event(ublk_idr_wq, ublk_idr_freed(idx)); + mutex_unlock(&ublk_ctl_mutex); + + return ret; +} + + +static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) +{ + pr_devel("%s: dev id %d flags %llx\n", __func__, + info->dev_id, info->flags[0]); + pr_devel("\t nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n", + info->nr_hw_queues, info->queue_depth, + info->block_size, info->dev_blocks); +} + +static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + + pr_devel("%s: cmd_op %x, dev id %d qid %d data %llx buf %llx len %u\n", + __func__, cmd->cmd_op, header->dev_id, header->queue_id, + header->data[0], header->addr, header->len); +} + +static int ublk_ctrl_cmd_validate(struct io_uring_cmd *cmd, + struct ublksrv_ctrl_dev_info *info) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + u32 cmd_op = cmd->cmd_op; + void __user *argp = (void __user *)(unsigned long)header->addr; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd_op) { + case UBLK_CMD_GET_DEV_INFO: + if (header->len < sizeof(*info) || !header->addr) + return -EINVAL; + break; + case UBLK_CMD_ADD_DEV: + if (header->len < sizeof(*info) || !header->addr) + return -EINVAL; + if (copy_from_user(info, argp, sizeof(*info)) != 0) + return -EFAULT; + ublk_dump_dev_info(info); + if (header->dev_id != info->dev_id) { + printk(KERN_WARNING "%s: cmd %x, dev id not match %u %u\n", + __func__, cmd_op, header->dev_id, + info->dev_id); + return -EINVAL; + } + if (header->queue_id != (u16)-1) { + printk(KERN_WARNING "%s: cmd %x queue_id is wrong %x\n", + __func__, cmd_op, header->queue_id); + return -EINVAL; + } + break; + case UBLK_CMD_GET_QUEUE_AFFINITY: + if ((header->len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (header->len & (sizeof(unsigned long)-1)) + return -EINVAL; + if (!header->addr) + return -EINVAL; + }; + + return 0; +} + +static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct ublksrv_ctrl_dev_info info; + u32 cmd_op = cmd->cmd_op; + struct ublk_device *ub; + int ret = -EINVAL; + + ublk_ctrl_cmd_dump(cmd); + + if (!(issue_flags & IO_URING_F_SQE128)) + goto out; + + ret = ublk_ctrl_cmd_validate(cmd, &info); + if (ret) + goto out; + + ret = -ENODEV; + switch (cmd_op) { + case UBLK_CMD_START_DEV: + ub = ublk_get_device_from_id(header->dev_id); + if (ub) { + ret = ublk_ctrl_start_dev(ub, cmd); + ublk_put_device(ub); + } + break; + case UBLK_CMD_STOP_DEV: + ub = ublk_get_device_from_id(header->dev_id); + if (ub) { + ret = ublk_ctrl_stop_dev(ub); + ublk_put_device(ub); + } + break; + case UBLK_CMD_GET_DEV_INFO: + ub = ublk_get_device_from_id(header->dev_id); + if (ub) { + if (copy_to_user(argp, &ub->dev_info, sizeof(info))) + ret = -EFAULT; + else + ret = 0; + ublk_put_device(ub); + } + break; + case UBLK_CMD_ADD_DEV: + ret = ublk_ctrl_add_dev(&info, argp, header->dev_id); + break; + case UBLK_CMD_DEL_DEV: + ret = ublk_ctrl_del_dev(header->dev_id); + break; + case UBLK_CMD_GET_QUEUE_AFFINITY: + ret = ublk_ctrl_get_queue_affinity(cmd); + break; + default: + break; + }; + out: + io_uring_cmd_done(cmd, ret, 0); + pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n", + __func__, ret, cmd->cmd_op, header->dev_id, header->queue_id); + return -EIOCBQUEUED; +} + +static const struct file_operations ublk_ctl_fops = { + .open = nonseekable_open, + .uring_cmd = ublk_ctrl_uring_cmd, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice ublk_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "ublk-control", + .fops = &ublk_ctl_fops, +}; + +static int __init ublk_init(void) +{ + int ret; + + init_waitqueue_head(&ublk_idr_wq); + + ret = misc_register(&ublk_misc); + if (ret) + return ret; + + ret = alloc_chrdev_region(&ublk_chr_devt, 0, UBLK_MINORS, "ublk-char"); + if (ret) + goto unregister_mis; + + ublk_chr_class = class_create(THIS_MODULE, "ublk-char"); + if (IS_ERR(ublk_chr_class)) { + ret = PTR_ERR(ublk_chr_class); + goto free_chrdev_region; + } + return 0; + +free_chrdev_region: + unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS); +unregister_mis: + misc_deregister(&ublk_misc); + return ret; +} + +static void __exit ublk_exit(void) +{ + struct ublk_device *ub; + int id; + + class_destroy(ublk_chr_class); + + misc_deregister(&ublk_misc); + + idr_for_each_entry(&ublk_index_idr, ub, id) + ublk_remove(ub); + + idr_destroy(&ublk_index_idr); + unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS); +} + +module_init(ublk_init); +module_exit(ublk_exit); + +MODULE_AUTHOR("Ming Lei "); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h new file mode 100644 index 000000000000..4f0c16ec875e --- /dev/null +++ b/include/uapi/linux/ublk_cmd.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef USER_BLK_DRV_CMD_INC_H +#define USER_BLK_DRV_CMD_INC_H + +#include + +/* ublk server command definition */ + +/* + * Admin commands, issued by ublk server, and handled by ublk driver. + */ +#define UBLK_CMD_GET_QUEUE_AFFINITY 0x01 +#define UBLK_CMD_GET_DEV_INFO 0x02 +#define UBLK_CMD_ADD_DEV 0x04 +#define UBLK_CMD_DEL_DEV 0x05 +#define UBLK_CMD_START_DEV 0x06 +#define UBLK_CMD_STOP_DEV 0x07 + +/* + * IO commands, issued by ublk server, and handled by ublk driver. + * + * FETCH_REQ: issued via sqe(URING_CMD) beforehand for fetching IO request + * from ublk driver, should be issued only when starting device. After + * the associated cqe is returned, request's tag can be retrieved via + * cqe->userdata. + * + * COMMIT_AND_FETCH_REQ: issued via sqe(URING_CMD) after ublkserver handled + * this IO request, request's handling result is committed to ublk + * driver, meantime FETCH_REQ is piggyback, and FETCH_REQ has to be + * handled before completing io request. + */ +#define UBLK_IO_FETCH_REQ 0x20 +#define UBLK_IO_COMMIT_AND_FETCH_REQ 0x21 + +/* only ABORT means that no re-fetch */ +#define UBLK_IO_RES_OK 0 +#define UBLK_IO_RES_ABORT (-ENODEV) + +#define UBLKSRV_CMD_BUF_OFFSET 0 +#define UBLKSRV_IO_BUF_OFFSET 0x80000000 + +/* tag bit is 12bit, so at most 4096 IOs for each queue */ +#define UBLK_MAX_QUEUE_DEPTH 4096 + +/* + * zero copy requires 4k block size, and can remap ublk driver's io + * request into ublksrv's vm space + */ +#define UBLK_F_SUPPORT_ZERO_COPY (1UL << 0) + +/* device state */ +#define UBLK_S_DEV_DEAD 0 +#define UBLK_S_DEV_LIVE 1 + +/* shipped via sqe->cmd of io_uring command */ +struct ublksrv_ctrl_cmd { + /* sent to which device, must be valid */ + __u32 dev_id; + + /* sent to which queue, must be -1 if the cmd isn't for queue */ + __u16 queue_id; + /* + * cmd specific buffer, can be IN or OUT. + */ + __u16 len; + __u64 addr; + + /* inline data */ + __u64 data[2]; +}; + +struct ublksrv_ctrl_dev_info { + __u16 nr_hw_queues; + __u16 queue_depth; + __u16 block_size; + __u16 state; + + __u32 rq_max_blocks; + __u32 dev_id; + + __u64 dev_blocks; + + __s32 ublksrv_pid; + __s32 reserved0; + __u64 flags[2]; + + /* For ublksrv internal use, invisible to ublk driver */ + __u64 ublksrv_flags; + __u64 reserved1[9]; +}; + +#define UBLK_IO_OP_READ 0 +#define UBLK_IO_OP_WRITE 1 +#define UBLK_IO_OP_FLUSH 2 +#define UBLK_IO_OP_DISCARD 3 +#define UBLK_IO_OP_WRITE_SAME 4 +#define UBLK_IO_OP_WRITE_ZEROES 5 + +#define UBLK_IO_F_FAILFAST_DEV (1U << 8) +#define UBLK_IO_F_FAILFAST_TRANSPORT (1U << 9) +#define UBLK_IO_F_FAILFAST_DRIVER (1U << 10) +#define UBLK_IO_F_META (1U << 11) +#define UBLK_IO_F_INTEGRITY (1U << 12) +#define UBLK_IO_F_FUA (1U << 13) +#define UBLK_IO_F_PREFLUSH (1U << 14) +#define UBLK_IO_F_NOUNMAP (1U << 15) +#define UBLK_IO_F_SWAP (1U << 16) + +/* + * io cmd is described by this structure, and stored in share memory, indexed + * by request tag. + * + * The data is stored by ublk driver, and read by ublksrv after one fetch command + * returns. + */ +struct ublksrv_io_desc { + /* op: bit 0-7, flags: bit 8-31 */ + __u32 op_flags; + + __u32 nr_sectors; + + /* start sector for this io */ + __u64 start_sector; + + /* buffer address in ublksrv daemon vm space, from ublk driver */ + __u64 addr; +}; + +static inline __u8 ublksrv_get_op(const struct ublksrv_io_desc *iod) +{ + return iod->op_flags & 0xff; +} + +static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod) +{ + return iod->op_flags >> 8; +} + +/* issued to ublk driver via /dev/ublkcN */ +struct ublksrv_io_cmd { + __u16 q_id; + + /* for fetch/commit which result */ + __u16 tag; + + /* io result, it is valid for COMMIT* command only */ + __s32 result; + + /* + * userspace buffer address in ublksrv daemon process, valid for + * FETCH* command only + */ + __u64 addr; +}; + +#endif -- cgit v1.2.3 From 0edb3696c1713c42f52acbd8355b545e58f782b1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 13 Jul 2022 22:07:11 +0800 Subject: ublk_drv: support to complete io command via task_work_add Use task_work_add if it is available, since task_work_add can bring up better performance, especially batching signaling ->ubq_daemon can be done. It is observed that task_work_add() can boost iops by +4% on random 4k io test. Also except for completing io command, all other code paths are same with completing io command via io_uring_cmd_complete_in_task. Meantime add one flag of UBLK_F_URING_CMD_COMP_IN_TASK for comparing the mode easily. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220713140711.97356-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 75 ++++++++++++++++++++++++++++++++++++++----- include/uapi/linux/ublk_cmd.h | 6 ++++ 2 files changed, 73 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 922a84c86fc6..35fa06ee70ff 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -41,10 +41,15 @@ #include #include #include +#include #include #define UBLK_MINORS (1U << MINORBITS) +struct ublk_rq_data { + struct callback_head work; +}; + struct ublk_uring_cmd_pdu { struct request *req; }; @@ -91,6 +96,7 @@ struct ublk_queue { int q_id; int q_depth; + unsigned long flags; struct task_struct *ubq_daemon; char *io_cmd_buf; @@ -149,6 +155,14 @@ static DEFINE_MUTEX(ublk_ctl_mutex); static struct miscdevice ublk_misc; +static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) +{ + if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) && + !(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK)) + return true; + return false; +} + static struct ublk_device *ublk_get_device(struct ublk_device *ub) { if (kobject_get_unless_zero(&ub->cdev_dev.kobj)) @@ -500,12 +514,10 @@ static void __ublk_fail_req(struct ublk_io *io, struct request *req) #define UBLK_REQUEUE_DELAY_MS 3 -static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) +static inline void __ublk_rq_task_work(struct request *req) { - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - struct ublk_device *ub = cmd->file->private_data; - struct request *req = pdu->req; struct ublk_queue *ubq = req->mq_hctx->driver_data; + struct ublk_device *ub = ubq->dev; int tag = req->tag; struct ublk_io *io = &ubq->ios[tag]; bool task_exiting = current != ubq->ubq_daemon || @@ -557,13 +569,27 @@ static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) io_uring_cmd_done(io->cmd, UBLK_IO_RES_OK, 0); } +static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) +{ + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + __ublk_rq_task_work(pdu->req); +} + +static void ublk_rq_task_work_fn(struct callback_head *work) +{ + struct ublk_rq_data *data = container_of(work, + struct ublk_rq_data, work); + struct request *req = blk_mq_rq_from_pdu(data); + + __ublk_rq_task_work(req); +} + static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct ublk_queue *ubq = hctx->driver_data; struct request *rq = bd->rq; - struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd; - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); blk_status_t res; /* fill iod to slot in io cmd buffer */ @@ -574,16 +600,36 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(bd->rq); if (unlikely(ubq_daemon_is_dying(ubq))) { + fail: mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); return BLK_STS_IOERR; } - pdu->req = rq; - io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + if (ublk_can_use_task_work(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); + enum task_work_notify_mode notify_mode = bd->last ? + TWA_SIGNAL_NO_IPI : TWA_NONE; + + if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) + goto fail; + } else { + struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd; + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + pdu->req = rq; + io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + } return BLK_STS_OK; } +static void ublk_commit_rqs(struct blk_mq_hw_ctx *hctx) +{ + struct ublk_queue *ubq = hctx->driver_data; + + if (ublk_can_use_task_work(ubq)) + __set_notify_signal(ubq->ubq_daemon); +} static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, unsigned int hctx_idx) @@ -595,9 +641,20 @@ static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, return 0; } +static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req, + unsigned int hctx_idx, unsigned int numa_node) +{ + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + init_task_work(&data->work, ublk_rq_task_work_fn); + return 0; +} + static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, + .commit_rqs = ublk_commit_rqs, .init_hctx = ublk_init_hctx, + .init_request = ublk_init_rq, }; static int ublk_ch_open(struct inode *inode, struct file *filp) @@ -912,6 +969,7 @@ static int ublk_init_queue(struct ublk_device *ub, int q_id) void *ptr; int size; + ubq->flags = ub->dev_info.flags[0]; ubq->q_id = q_id; ubq->q_depth = ub->dev_info.queue_depth; size = ublk_queue_cmd_buf_size(ub, q_id); @@ -1099,6 +1157,7 @@ static int ublk_add_dev(struct ublk_device *ub) ub->tag_set.nr_hw_queues = ub->dev_info.nr_hw_queues; ub->tag_set.queue_depth = ub->dev_info.queue_depth; ub->tag_set.numa_node = NUMA_NO_NODE; + ub->tag_set.cmd_size = sizeof(struct ublk_rq_data); ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ub->tag_set.driver_data = ub; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 4f0c16ec875e..a3f5e7c21807 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -48,6 +48,12 @@ */ #define UBLK_F_SUPPORT_ZERO_COPY (1UL << 0) +/* + * Force to complete io cmd via io_uring_cmd_complete_in_task so that + * performance comparison is done easily with using task_work_add + */ +#define UBLK_F_URING_CMD_COMP_IN_TASK (1UL << 1) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 577e5b8c3924539c7a09e3e00477534f39e61829 Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Wed, 8 Jun 2022 12:01:12 +0300 Subject: wifi: cfg80211: add API to add/modify/remove a link station Add an API for adding/modifying/removing a link of a station. Signed-off-by: Shaul Triebitz Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 64 +++++++++++++++++ include/uapi/linux/nl80211.h | 8 +++ net/wireless/nl80211.c | 168 ++++++++++++++++++++++++++++++++++++++++--- net/wireless/rdev-ops.h | 48 +++++++++++++ net/wireless/trace.h | 97 +++++++++++++++++++++++++ 5 files changed, 377 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3bcdd20ace66..422764881269 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1456,6 +1456,61 @@ struct sta_txpwr { enum nl80211_tx_power_setting type; }; +/** + * struct link_station_parameters - link station parameters + * + * Used to change and create a new link station. + * + * @mld_mac: MAC address of the station + * @link_id: the link id (-1 for non-MLD station) + * @link_mac: MAC address of the link + * @supported_rates: supported rates in IEEE 802.11 format + * (or NULL for no change) + * @supported_rates_len: number of supported rates + * @ht_capa: HT capabilities of station + * @vht_capa: VHT capabilities of station + * @opmode_notif: operating mode field from Operating Mode Notification + * @opmode_notif_used: information if operating mode field is used + * @he_capa: HE capabilities of station + * @he_capa_len: the length of the HE capabilities + * @txpwr: transmit power for an associated station + * @txpwr_set: txpwr field is set + * @he_6ghz_capa: HE 6 GHz Band capabilities of station + * @eht_capa: EHT capabilities of station + * @eht_capa_len: the length of the EHT capabilities + */ +struct link_station_parameters { + const u8 *mld_mac; + int link_id; + const u8 *link_mac; + const u8 *supported_rates; + u8 supported_rates_len; + const struct ieee80211_ht_cap *ht_capa; + const struct ieee80211_vht_cap *vht_capa; + u8 opmode_notif; + bool opmode_notif_used; + const struct ieee80211_he_cap_elem *he_capa; + u8 he_capa_len; + struct sta_txpwr txpwr; + bool txpwr_set; + const struct ieee80211_he_6ghz_capa *he_6ghz_capa; + const struct ieee80211_eht_cap_elem *eht_capa; + u8 eht_capa_len; +}; + +/** + * struct link_station_del_parameters - link station deletion parameters + * + * Used to delete a link station entry (or all stations). + * + * @mld_mac: MAC address of the station + * @link_id: the link id + */ +struct link_station_del_parameters { + const u8 *mld_mac; + u32 link_id; +}; + /** * struct station_parameters - station parameters * @@ -4215,6 +4270,9 @@ struct mgmt_frame_regs { * radar channel. * The caller is expected to set chandef pointer to NULL in order to * disable background CAC/radar detection. + * @add_link_station: Add a link to a station. + * @mod_link_station: Modify a link of a station. + * @del_link_station: Remove a link of a station. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4560,6 +4618,12 @@ struct cfg80211_ops { struct cfg80211_fils_aad *fils_aad); int (*set_radar_background)(struct wiphy *wiphy, struct cfg80211_chan_def *chandef); + int (*add_link_station)(struct wiphy *wiphy, struct net_device *dev, + struct link_station_parameters *params); + int (*mod_link_station)(struct wiphy *wiphy, struct net_device *dev, + struct link_station_parameters *params); + int (*del_link_station)(struct wiphy *wiphy, struct net_device *dev, + struct link_station_del_parameters *params); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 7bb1ae59f3a5..37bfc934325a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1254,6 +1254,10 @@ * without %NL80211_ATTR_MLO_LINK_ID as an easy way to remove all links * in preparation for e.g. roaming to a regular (non-MLO) AP. * + * @NL80211_CMD_ADD_LINK_STA: Add a link to an MLD station + * @NL80211_CMD_MODIFY_LINK_STA: Modify a link of an MLD station + * @NL80211_CMD_REMOVE_LINK_STA: Remove a link of an MLD station + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1501,6 +1505,10 @@ enum nl80211_commands { NL80211_CMD_ADD_LINK, NL80211_CMD_REMOVE_LINK, + NL80211_CMD_ADD_LINK_STA, + NL80211_CMD_MODIFY_LINK_STA, + NL80211_CMD_REMOVE_LINK_STA, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 22c4cf6fbb57..3cf8e01e3f7e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6801,7 +6801,8 @@ static int nl80211_set_station_tdls(struct genl_info *info, } static int nl80211_parse_sta_txpower_setting(struct genl_info *info, - struct station_parameters *params) + struct sta_txpwr *txpwr, + bool *txpwr_set) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; int idx; @@ -6813,18 +6814,20 @@ static int nl80211_parse_sta_txpower_setting(struct genl_info *info, return -EOPNOTSUPP; idx = NL80211_ATTR_STA_TX_POWER_SETTING; - params->txpwr.type = nla_get_u8(info->attrs[idx]); + txpwr->type = nla_get_u8(info->attrs[idx]); - if (params->txpwr.type == NL80211_TX_POWER_LIMITED) { + if (txpwr->type == NL80211_TX_POWER_LIMITED) { idx = NL80211_ATTR_STA_TX_POWER; if (info->attrs[idx]) - params->txpwr.power = - nla_get_s16(info->attrs[idx]); + txpwr->power = nla_get_s16(info->attrs[idx]); else return -EINVAL; } - params->sta_modify_mask |= STATION_PARAM_APPLY_STA_TXPOWER; + + *txpwr_set = true; + } else { + *txpwr_set = false; } return 0; @@ -6837,6 +6840,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) struct station_parameters params; u8 *mac_addr; int err; + bool txpwr_set; memset(¶ms, 0, sizeof(params)); @@ -6930,9 +6934,11 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) return -EOPNOTSUPP; - err = nl80211_parse_sta_txpower_setting(info, ¶ms); + err = nl80211_parse_sta_txpower_setting(info, ¶ms.txpwr, &txpwr_set); if (err) return err; + if (txpwr_set) + params.sta_modify_mask |= STATION_PARAM_APPLY_STA_TXPOWER; /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); @@ -6975,6 +6981,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) u8 *mac_addr = NULL; u32 auth_assoc = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); + bool txpwr_set; memset(¶ms, 0, sizeof(params)); @@ -7085,9 +7092,11 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) return -EOPNOTSUPP; - err = nl80211_parse_sta_txpower_setting(info, ¶ms); + err = nl80211_parse_sta_txpower_setting(info, ¶ms.txpwr, &txpwr_set); if (err) return err; + if (txpwr_set) + params.sta_modify_mask |= STATION_PARAM_APPLY_STA_TXPOWER; err = nl80211_parse_sta_channel_info(info, ¶ms); if (err) @@ -15682,6 +15691,128 @@ static int nl80211_remove_link(struct sk_buff *skb, struct genl_info *info) return 0; } +static int +nl80211_add_mod_link_station(struct sk_buff *skb, struct genl_info *info, + bool add) +{ + struct link_station_parameters params = {}; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + int err; + + if ((add && !rdev->ops->add_link_station) || + (!add && !rdev->ops->mod_link_station)) + return -EOPNOTSUPP; + + if (add && !info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + if (add && !info->attrs[NL80211_ATTR_MLD_ADDR]) + return -EINVAL; + + if (add && !info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]) + return -EINVAL; + + if (info->attrs[NL80211_ATTR_MLD_ADDR]) + params.mld_mac = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + + if (info->attrs[NL80211_ATTR_MAC]) { + params.link_mac = nla_data(info->attrs[NL80211_ATTR_MAC]); + if (!is_valid_ether_addr(params.link_mac)) + return -EINVAL; + } + + if (!info->attrs[NL80211_ATTR_MLO_LINK_ID]) + return -EINVAL; + + params.link_id = nla_get_u8(info->attrs[NL80211_ATTR_MLO_LINK_ID]); + + if (info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]) { + params.supported_rates = + nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]); + params.supported_rates_len = + nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]); + } + + if (info->attrs[NL80211_ATTR_HT_CAPABILITY]) + params.ht_capa = + nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY]) + params.vht_capa = + nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) { + params.he_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + params.he_capa_len = + nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_EHT_CAPABILITY]) { + params.eht_capa = + nla_data(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + params.eht_capa_len = + nla_len(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + + if (!ieee80211_eht_capa_size_ok((const u8 *)params.he_capa, + (const u8 *)params.eht_capa, + params.eht_capa_len)) + return -EINVAL; + } + } + + if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) + params.he_6ghz_capa = + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { + params.opmode_notif_used = true; + params.opmode_notif = + nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); + } + + err = nl80211_parse_sta_txpower_setting(info, ¶ms.txpwr, + ¶ms.txpwr_set); + if (err) + return err; + + if (add) + return rdev_add_link_station(rdev, dev, ¶ms); + return rdev_mod_link_station(rdev, dev, ¶ms); +} + +static int +nl80211_add_link_station(struct sk_buff *skb, struct genl_info *info) +{ + return nl80211_add_mod_link_station(skb, info, true); +} + +static int +nl80211_modify_link_station(struct sk_buff *skb, struct genl_info *info) +{ + return nl80211_add_mod_link_station(skb, info, false); +} + +static int +nl80211_remove_link_station(struct sk_buff *skb, struct genl_info *info) +{ + struct link_station_del_parameters params = {}; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + + if (!rdev->ops->del_link_station) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_MLD_ADDR] || + !info->attrs[NL80211_ATTR_MLO_LINK_ID]) + return -EINVAL; + + params.mld_mac = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + params.link_id = nla_get_u8(info->attrs[NL80211_ATTR_MLO_LINK_ID]); + + return rdev_del_link_station(rdev, dev, ¶ms); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -16832,6 +16963,27 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_MLO_VALID_LINK_ID), }, + { + .cmd = NL80211_CMD_ADD_LINK_STA, + .doit = nl80211_add_link_station, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), + }, + { + .cmd = NL80211_CMD_MODIFY_LINK_STA, + .doit = nl80211_modify_link_station, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), + }, + { + .cmd = NL80211_CMD_REMOVE_LINK_STA, + .doit = nl80211_remove_link_station, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index a329ba036989..6221a996c19f 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1448,4 +1448,52 @@ rdev_del_intf_link(struct cfg80211_registered_device *rdev, trace_rdev_return_void(&rdev->wiphy); } +static inline int +rdev_add_link_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct link_station_parameters *params) +{ + int ret; + + if (!rdev->ops->add_link_station) + return -EOPNOTSUPP; + + trace_rdev_add_link_station(&rdev->wiphy, dev, params); + ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_mod_link_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct link_station_parameters *params) +{ + int ret; + + if (!rdev->ops->mod_link_station) + return -EOPNOTSUPP; + + trace_rdev_mod_link_station(&rdev->wiphy, dev, params); + ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_del_link_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct link_station_del_parameters *params) +{ + int ret; + + if (!rdev->ops->del_link_station) + return -EOPNOTSUPP; + + trace_rdev_del_link_station(&rdev->wiphy, dev, params); + ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 65f8b814ecd0..16d0fe53fcf2 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3775,6 +3775,103 @@ TRACE_EVENT(cfg80211_assoc_comeback, WDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->timeout) ); +DECLARE_EVENT_CLASS(link_station_add_mod, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct link_station_parameters *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, mld_mac, 6) + __array(u8, link_mac, 6) + __field(u32, link_id) + __dynamic_array(u8, supported_rates, + params->supported_rates_len) + __array(u8, ht_capa, (int)sizeof(struct ieee80211_ht_cap)) + __array(u8, vht_capa, (int)sizeof(struct ieee80211_vht_cap)) + __field(u8, opmode_notif) + __field(bool, opmode_notif_used) + __dynamic_array(u8, he_capa, params->he_capa_len) + __array(u8, he_6ghz_capa, (int)sizeof(struct ieee80211_he_6ghz_capa)) + __dynamic_array(u8, eht_capa, params->eht_capa_len) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memset(__entry->mld_mac, 0, 6); + memset(__entry->link_mac, 0, 6); + if (params->mld_mac) + memcpy(__entry->mld_mac, params->mld_mac, 6); + if (params->link_mac) + memcpy(__entry->link_mac, params->link_mac, 6); + __entry->link_id = params->link_id; + if (params->supported_rates && params->supported_rates_len) + memcpy(__get_dynamic_array(supported_rates), + params->supported_rates, + params->supported_rates_len); + memset(__entry->ht_capa, 0, sizeof(struct ieee80211_ht_cap)); + if (params->ht_capa) + memcpy(__entry->ht_capa, params->ht_capa, + sizeof(struct ieee80211_ht_cap)); + memset(__entry->vht_capa, 0, sizeof(struct ieee80211_vht_cap)); + if (params->vht_capa) + memcpy(__entry->vht_capa, params->vht_capa, + sizeof(struct ieee80211_vht_cap)); + __entry->opmode_notif = params->opmode_notif; + __entry->opmode_notif_used = params->opmode_notif_used; + if (params->he_capa && params->he_capa_len) + memcpy(__get_dynamic_array(he_capa), params->he_capa, + params->he_capa_len); + memset(__entry->he_6ghz_capa, 0, sizeof(struct ieee80211_he_6ghz_capa)); + if (params->he_6ghz_capa) + memcpy(__entry->he_6ghz_capa, params->he_6ghz_capa, + sizeof(struct ieee80211_he_6ghz_capa)); + if (params->eht_capa && params->eht_capa_len) + memcpy(__get_dynamic_array(eht_capa), params->eht_capa, + params->eht_capa_len); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT + ", link mac: " MAC_PR_FMT ", link id: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(mld_mac), + MAC_PR_ARG(link_mac), __entry->link_id) +); + +DEFINE_EVENT(link_station_add_mod, rdev_add_link_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct link_station_parameters *params), + TP_ARGS(wiphy, netdev, params) +); + +DEFINE_EVENT(link_station_add_mod, rdev_mod_link_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct link_station_parameters *params), + TP_ARGS(wiphy, netdev, params) +); + +TRACE_EVENT(rdev_del_link_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct link_station_del_parameters *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, mld_mac, 6) + __field(u32, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memset(__entry->mld_mac, 0, 6); + if (params->mld_mac) + memcpy(__entry->mld_mac, params->mld_mac, 6); + __entry->link_id = params->link_id; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT + ", link id: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(mld_mac), + __entry->link_id) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit v1.2.3 From 4e9c3af398207d95957ae6c25290891574f2d7e8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 4 Jul 2022 15:02:33 +0200 Subject: wifi: nl80211: add EML/MLD capabilities to per-iftype capabilities We have the per-interface type capabilities, currently for extended capabilities, add the EML/MLD capabilities there to have this advertised by the driver. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 12 ++++++++++-- net/wireless/nl80211.c | 9 +++++++++ 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f9ea49e67164..bc960646973b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4993,12 +4993,16 @@ struct wiphy_vendor_command { * 802.11-2012 8.4.2.29 for the defined fields. * @extended_capabilities_mask: mask of the valid values * @extended_capabilities_len: length of the extended capabilities + * @eml_capabilities: EML capabilities (for MLO) + * @mld_capa_and_ops: MLD capabilities and operations (for MLO) */ struct wiphy_iftype_ext_capab { enum nl80211_iftype iftype; const u8 *extended_capabilities; const u8 *extended_capabilities_mask; u8 extended_capabilities_len; + u16 eml_capabilities; + u16 mld_capa_and_ops; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 37bfc934325a..3fa586e38f88 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2368,8 +2368,10 @@ enum nl80211_commands { * * @NL80211_ATTR_IFTYPE_EXT_CAPA: Nested attribute of the following attributes: * %NL80211_ATTR_IFTYPE, %NL80211_ATTR_EXT_CAPA, - * %NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities per - * interface type. + * %NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities and + * other interface-type specific capabilities per interface type. For MLO, + * %NL80211_ATTR_EML_CAPABILITY and %NL80211_ATTR_MLD_CAPA_AND_OPS are + * present. * * @NL80211_ATTR_MU_MIMO_GROUP_DATA: array of 24 bytes that defines a MU-MIMO * groupID for monitor mode. @@ -2709,6 +2711,9 @@ enum nl80211_commands { * suites allowed as %NL80211_MAX_NR_AKM_SUITES which is the legacy maximum * number prior to the introduction of this attribute. * + * @NL80211_ATTR_EML_CAPABILITY: EML Capability information (u16) + * @NL80211_ATTR_MLD_CAPA_AND_OPS: MLD Capabilities and Operations (u16) + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3231,6 +3236,9 @@ enum nl80211_attrs { NL80211_ATTR_MAX_NUM_AKM_SUITES, + NL80211_ATTR_EML_CAPABILITY, + NL80211_ATTR_MLD_CAPA_AND_OPS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 37ec8b3897b4..35fb2b0517d9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2867,6 +2867,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, capab->extended_capabilities_mask)) goto nla_put_failure; + if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_MLO && + (nla_put_u16(msg, + NL80211_ATTR_EML_CAPABILITY, + capab->eml_capabilities) || + nla_put_u16(msg, + NL80211_ATTR_MLD_CAPA_AND_OPS, + capab->mld_capa_and_ops))) + goto nla_put_failure; + nla_nest_end(msg, nested_ext_capab); if (state->split) break; -- cgit v1.2.3 From 00f6842ef41d90cc335ae4dbb00d71f4f642c712 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 7 Mar 2022 16:32:00 +0000 Subject: media: v4l: Add packed YUV 4:4:4 YUVA and YUVX pixel formats The new YUVA and YUVX are permutations of the existing AYUV and XYUV formats. They are use by the NXP i.MX8 ISI hardware. Signed-off-by: Laurent Pinchart Reviewed-by: Nicolas Dufresne Reviewed-by: Jacopo Mondi Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/pixfmt-packed-yuv.rst | 20 ++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 2 ++ include/uapi/linux/videodev2.h | 2 ++ 3 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst b/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst index 65520c3af7cf..bf283a1b5581 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-packed-yuv.rst @@ -220,6 +220,26 @@ the second byte and Y'\ :sub:`7-0` in the third byte. - Y'\ :sub:`7-0` - X\ :sub:`7-0` + * .. _V4L2-PIX-FMT-YUVA32: + + - ``V4L2_PIX_FMT_YUVA32`` + - 'YUVA' + + - Y'\ :sub:`7-0` + - Cb\ :sub:`7-0` + - Cr\ :sub:`7-0` + - A\ :sub:`7-0` + + * .. _V4L2-PIX-FMT-YUVX32: + + - ``V4L2_PIX_FMT_YUVX32`` + - 'YUVX' + + - Y'\ :sub:`7-0` + - Cb\ :sub:`7-0` + - Cr\ :sub:`7-0` + - X\ :sub:`7-0` + * .. _V4L2-PIX-FMT-YUV24: - ``V4L2_PIX_FMT_YUV24`` diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index e03362c8aef9..11f19099f33b 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1296,6 +1296,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_XYUV32: descr = "32-bit XYUV 8-8-8-8"; break; case V4L2_PIX_FMT_VUYA32: descr = "32-bit VUYA 8-8-8-8"; break; case V4L2_PIX_FMT_VUYX32: descr = "32-bit VUYX 8-8-8-8"; break; + case V4L2_PIX_FMT_YUVA32: descr = "32-bit YUVA 8-8-8-8"; break; + case V4L2_PIX_FMT_YUVX32: descr = "32-bit YUVX 8-8-8-8"; break; case V4L2_PIX_FMT_YUV410: descr = "Planar YUV 4:1:0"; break; case V4L2_PIX_FMT_YUV420: descr = "Planar YUV 4:2:0"; break; case V4L2_PIX_FMT_HI240: descr = "8-bit Dithered RGB (BTTV)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 5311ac4fde35..0028ab74ca7c 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -593,6 +593,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_XYUV32 v4l2_fourcc('X', 'Y', 'U', 'V') /* 32 XYUV-8-8-8-8 */ #define V4L2_PIX_FMT_VUYA32 v4l2_fourcc('V', 'U', 'Y', 'A') /* 32 VUYA-8-8-8-8 */ #define V4L2_PIX_FMT_VUYX32 v4l2_fourcc('V', 'U', 'Y', 'X') /* 32 VUYX-8-8-8-8 */ +#define V4L2_PIX_FMT_YUVA32 v4l2_fourcc('Y', 'U', 'V', 'A') /* 32 YUVA-8-8-8-8 */ +#define V4L2_PIX_FMT_YUVX32 v4l2_fourcc('Y', 'U', 'V', 'X') /* 32 YUVX-8-8-8-8 */ #define V4L2_PIX_FMT_M420 v4l2_fourcc('M', '4', '2', '0') /* 12 YUV 4:2:0 2 lines y, 1 line uv interleaved */ /* two planes -- one Y, one Cr + Cb interleaved */ -- cgit v1.2.3 From 718d2153ad0de0c7c0b6891eaa7f9918d68b6d5e Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 17 Mar 2022 12:37:12 +0000 Subject: media: v4l2: Make colorspace validity checks more future-proof The helper functions that test validity of colorspace-related fields use the last value of the corresponding enums. This isn't very future-proof, as there's a high chance someone adding a new value may forget to update the helpers. Add new "LAST" entries to the enumerations to improve this, and keep them private to the kernel. Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 6 +++--- include/uapi/linux/videodev2.h | 22 ++++++++++++++++++++++ 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 3eb202259e8c..b708d63995f4 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -563,19 +563,19 @@ static inline void v4l2_buffer_set_timestamp(struct v4l2_buffer *buf, static inline bool v4l2_is_colorspace_valid(__u32 colorspace) { return colorspace > V4L2_COLORSPACE_DEFAULT && - colorspace <= V4L2_COLORSPACE_DCI_P3; + colorspace < V4L2_COLORSPACE_LAST; } static inline bool v4l2_is_xfer_func_valid(__u32 xfer_func) { return xfer_func > V4L2_XFER_FUNC_DEFAULT && - xfer_func <= V4L2_XFER_FUNC_SMPTE2084; + xfer_func < V4L2_XFER_FUNC_LAST; } static inline bool v4l2_is_ycbcr_enc_valid(__u8 ycbcr_enc) { return ycbcr_enc > V4L2_YCBCR_ENC_DEFAULT && - ycbcr_enc <= V4L2_YCBCR_ENC_SMPTE240M; + ycbcr_enc < V4L2_YCBCR_ENC_LAST; } static inline bool v4l2_is_hsv_enc_valid(__u8 hsv_enc) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 0028ab74ca7c..e32b9e25258d 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -245,6 +245,14 @@ enum v4l2_colorspace { /* DCI-P3 colorspace, used by cinema projectors */ V4L2_COLORSPACE_DCI_P3 = 12, + +#ifdef __KERNEL__ + /* + * Largest supported colorspace value, assigned by the compiler, used + * by the framework to check for invalid values. + */ + V4L2_COLORSPACE_LAST, +#endif }; /* @@ -283,6 +291,13 @@ enum v4l2_xfer_func { V4L2_XFER_FUNC_NONE = 5, V4L2_XFER_FUNC_DCI_P3 = 6, V4L2_XFER_FUNC_SMPTE2084 = 7, +#ifdef __KERNEL__ + /* + * Largest supported transfer function value, assigned by the compiler, + * used by the framework to check for invalid values. + */ + V4L2_XFER_FUNC_LAST, +#endif }; /* @@ -343,6 +358,13 @@ enum v4l2_ycbcr_encoding { /* SMPTE 240M -- Obsolete HDTV */ V4L2_YCBCR_ENC_SMPTE240M = 8, +#ifdef __KERNEL__ + /* + * Largest supported encoding value, assigned by the compiler, used by + * the framework to check for invalid values. + */ + V4L2_YCBCR_ENC_LAST, +#endif }; /* -- cgit v1.2.3 From 64fe675e999c2c7d753ecaaa1349693c59ce6c11 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 8 Jul 2022 17:21:40 +0100 Subject: media: videodev2.h: add V4L2_CTRL_FLAG_DYNAMIC_ARRAY Add a new flag that indicates that this control is a dynamically sized array. Also document this flag. Currently dynamically sized arrays are limited to one dimensional arrays, but that might change in the future if there is a need for it. The initial use-case of dynamic arrays are stateless codecs. A frame can be divided in many slices, so you want to provide an array containing slice information for each slice. Typically the number of slices is small, but the standard allow for hundreds or thousands of slices. Dynamic arrays are a good solution since sizing the array for the worst case would waste substantial amounts of memory. Acked-by: Nicolas Dufresne Tested-by: Benjamin Gaignard Tested-by: Jernej Skrabec Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst | 8 ++++++++ Documentation/userspace-api/media/videodev2.h.rst.exceptions | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst index 88f630252d98..a20dfa2a933b 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-queryctrl.rst @@ -625,6 +625,14 @@ See also the examples in :ref:`control`. ``V4L2_CTRL_FLAG_GRABBED`` flag when buffers are allocated or streaming is in progress since most drivers do not support changing the format in that case. + * - ``V4L2_CTRL_FLAG_DYNAMIC_ARRAY`` + - 0x0800 + - This control is a dynamically sized 1-dimensional array. It + behaves the same as a regular array, except that the number + of elements as reported by the ``elems`` field is between 1 and + ``dims[0]``. So setting the control with a differently sized + array will change the ``elems`` field when the control is + queried afterwards. Return Value ============ diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 9cbb7a0c354a..0b91200776f8 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -379,6 +379,7 @@ replace define V4L2_CTRL_FLAG_VOLATILE control-flags replace define V4L2_CTRL_FLAG_HAS_PAYLOAD control-flags replace define V4L2_CTRL_FLAG_EXECUTE_ON_WRITE control-flags replace define V4L2_CTRL_FLAG_MODIFY_LAYOUT control-flags +replace define V4L2_CTRL_FLAG_DYNAMIC_ARRAY control-flags replace define V4L2_CTRL_FLAG_NEXT_CTRL control replace define V4L2_CTRL_FLAG_NEXT_COMPOUND control diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index e32b9e25258d..87ebc6baafb6 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1914,6 +1914,7 @@ struct v4l2_querymenu { #define V4L2_CTRL_FLAG_HAS_PAYLOAD 0x0100 #define V4L2_CTRL_FLAG_EXECUTE_ON_WRITE 0x0200 #define V4L2_CTRL_FLAG_MODIFY_LAYOUT 0x0400 +#define V4L2_CTRL_FLAG_DYNAMIC_ARRAY 0x0800 /* Query flags, to be ORed with the control ID */ #define V4L2_CTRL_FLAG_NEXT_CTRL 0x80000000 -- cgit v1.2.3 From 01dcfd53335cfb5c66a6c023ac0f789a5b87ace5 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Fri, 8 Jul 2022 17:21:49 +0100 Subject: media: uapi: Move parsed HEVC pixel format out of staging Move HEVC pixel format since we are ready to stabilize the uAPI Signed-off-by: Benjamin Gaignard Reviewed-by: Ezequiel Garcia Acked-by: Nicolas Dufresne Tested-by: Jernej Skrabec Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-compressed.rst | 5 ----- include/media/hevc-ctrls.h | 3 --- include/uapi/linux/videodev2.h | 1 + 3 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst index 967fc803ef94..c352d91a73d8 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst @@ -215,11 +215,6 @@ Compressed Formats See the :ref:`associated Codec Control IDs `. Buffers associated with this pixel format must contain the appropriate number of macroblocks to decode a full corresponding frame. - - .. note:: - - This format is not yet part of the public kernel API and it - is expected to change. * .. _V4L2-PIX-FMT-FWHT: - ``V4L2_PIX_FMT_FWHT`` diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h index e614cf20dfd3..3a6601a46ced 100644 --- a/include/media/hevc-ctrls.h +++ b/include/media/hevc-ctrls.h @@ -13,9 +13,6 @@ #include -/* The pixel format isn't stable at the moment and will likely be renamed. */ -#define V4L2_PIX_FMT_HEVC_SLICE v4l2_fourcc('S', '2', '6', '5') /* HEVC parsed slices */ - #define V4L2_CID_STATELESS_HEVC_SPS (V4L2_CID_CODEC_BASE + 1008) #define V4L2_CID_STATELESS_HEVC_PPS (V4L2_CID_CODEC_BASE + 1009) #define V4L2_CID_STATELESS_HEVC_SLICE_PARAMS (V4L2_CID_CODEC_BASE + 1010) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 87ebc6baafb6..06e3f81ad855 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -736,6 +736,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_FWHT v4l2_fourcc('F', 'W', 'H', 'T') /* Fast Walsh Hadamard Transform (vicodec) */ #define V4L2_PIX_FMT_FWHT_STATELESS v4l2_fourcc('S', 'F', 'W', 'H') /* Stateless FWHT (vicodec) */ #define V4L2_PIX_FMT_H264_SLICE v4l2_fourcc('S', '2', '6', '4') /* H264 parsed slices */ +#define V4L2_PIX_FMT_HEVC_SLICE v4l2_fourcc('S', '2', '6', '5') /* HEVC parsed slices */ /* Vendor-specific formats */ #define V4L2_PIX_FMT_CPIA1 v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */ -- cgit v1.2.3 From 16e2d220cdc64a1518878172dc7b50d4f60e5aac Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Fri, 8 Jul 2022 17:21:51 +0100 Subject: media: uapi: Move the HEVC stateless control type out of staging Move the HEVC stateless controls types out of staging, and re-number them. Signed-off-by: Benjamin Gaignard Reviewed-by: Ezequiel Garcia Acked-by: Nicolas Dufresne Tested-by: Jernej Skrabec Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/videodev2.h.rst.exceptions | 5 +++++ include/media/hevc-ctrls.h | 7 ------- include/uapi/linux/videodev2.h | 6 ++++++ 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 0b91200776f8..2feea4a5a008 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -153,6 +153,11 @@ replace symbol V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_VP9_FRAME :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_HDR10_CLL_INFO :c:type:`v4l2_ctrl_type` replace symbol V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_HEVC_SPS :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_HEVC_PPS :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX :c:type:`v4l2_ctrl_type` +replace symbol V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS :c:type:`v4l2_ctrl_type` # V4L2 capability defines replace define V4L2_CAP_VIDEO_CAPTURE device-capabilities diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h index 3a6601a46ced..42d16e8a1050 100644 --- a/include/media/hevc-ctrls.h +++ b/include/media/hevc-ctrls.h @@ -22,13 +22,6 @@ #define V4L2_CID_STATELESS_HEVC_START_CODE (V4L2_CID_CODEC_BASE + 1016) #define V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS (V4L2_CID_CODEC_BASE + 1017) -/* enum v4l2_ctrl_type type values */ -#define V4L2_CTRL_TYPE_HEVC_SPS 0x0120 -#define V4L2_CTRL_TYPE_HEVC_PPS 0x0121 -#define V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS 0x0122 -#define V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX 0x0123 -#define V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS 0x0124 - enum v4l2_stateless_hevc_decode_mode { V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED, V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED, diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 06e3f81ad855..cff2bb78b2cc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1860,6 +1860,12 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR = 0x0260, V4L2_CTRL_TYPE_VP9_FRAME = 0x0261, + + V4L2_CTRL_TYPE_HEVC_SPS = 0x0270, + V4L2_CTRL_TYPE_HEVC_PPS = 0x0271, + V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS = 0x0272, + V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX = 0x0273, + V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS = 0x0274, }; /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -- cgit v1.2.3 From ca24fef0f2c857b0533f21f9a8a756f9e73d60fb Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Fri, 8 Jul 2022 17:21:56 +0100 Subject: media: uapi: move HEVC stateless controls out of staging HEVC uAPI is used by 2 mainline drivers (Hantro, Cedrus) and at least 2 out-of-tree drivers (rkvdec, RPi). The uAPI has been reviewed so it is time to make it 'public' by un-staging it. Signed-off-by: Benjamin Gaignard Reviewed-by: Ezequiel Garcia Acked-by: Nicolas Dufresne Tested-by: Jernej Skrabec Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../media/v4l/ext-ctrls-codec-stateless.rst | 902 ++++++++++++++++++++ .../userspace-api/media/v4l/ext-ctrls-codec.rst | 906 --------------------- .../userspace-api/media/v4l/pixfmt-compressed.rst | 2 +- .../userspace-api/media/v4l/vidioc-g-ext-ctrls.rst | 20 + include/media/hevc-ctrls.h | 474 ----------- include/media/v4l2-ctrls.h | 6 - include/uapi/linux/v4l2-controls.h | 459 +++++++++++ include/uapi/linux/videodev2.h | 5 + 8 files changed, 1387 insertions(+), 1387 deletions(-) delete mode 100644 include/media/hevc-ctrls.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index bee73065e993..cd33857d947d 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -2048,3 +2048,905 @@ This structure contains all loop filter related parameters. See sections - 0x2 - When set, the bitstream contains additional syntax elements that specify which mode and reference frame deltas are to be updated. + +.. _v4l2-codec-stateless-hevc: + +``V4L2_CID_STATELESS_HEVC_SPS (struct)`` + Specifies the Sequence Parameter Set fields (as extracted from the + bitstream) for the associated HEVC slice data. + These bitstream parameters are defined according to :ref:`hevc`. + They are described in section 7.4.3.2 "Sequence parameter set RBSP + semantics" of the specification. + +.. c:type:: v4l2_ctrl_hevc_sps + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{1.2cm}|p{9.2cm}|p{6.9cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_sps + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``video_parameter_set_id`` + - Specifies the value of the vps_video_parameter_set_id of the active VPS + as described in section "7.4.3.2.1 General sequence parameter set RBSP semantics" + of H.265 specifications. + * - __u8 + - ``seq_parameter_set_id`` + - Provides an identifier for the SPS for reference by other syntax elements + as described in section "7.4.3.2.1 General sequence parameter set RBSP semantics" + of H.265 specifications. + * - __u16 + - ``pic_width_in_luma_samples`` + - Specifies the width of each decoded picture in units of luma samples. + * - __u16 + - ``pic_height_in_luma_samples`` + - Specifies the height of each decoded picture in units of luma samples. + * - __u8 + - ``bit_depth_luma_minus8`` + - This value plus 8 specifies the bit depth of the samples of the luma array. + * - __u8 + - ``bit_depth_chroma_minus8`` + - This value plus 8 specifies the bit depth of the samples of the chroma arrays. + * - __u8 + - ``log2_max_pic_order_cnt_lsb_minus4`` + - Specifies the value of the variable MaxPicOrderCntLsb. + * - __u8 + - ``sps_max_dec_pic_buffering_minus1`` + - This value plus 1 specifies the maximum required size of the decoded picture buffer for + the coded video sequence (CVS). + * - __u8 + - ``sps_max_num_reorder_pics`` + - Indicates the maximum allowed number of pictures. + * - __u8 + - ``sps_max_latency_increase_plus1`` + - Used to signal MaxLatencyPictures, which indicates the maximum number of + pictures that can precede any picture in output order and follow that + picture in decoding order. + * - __u8 + - ``log2_min_luma_coding_block_size_minus3`` + - This value plus 3 specifies the minimum luma coding block size. + * - __u8 + - ``log2_diff_max_min_luma_coding_block_size`` + - Specifies the difference between the maximum and minimum luma coding block size. + * - __u8 + - ``log2_min_luma_transform_block_size_minus2`` + - This value plus 2 specifies the minimum luma transform block size. + * - __u8 + - ``log2_diff_max_min_luma_transform_block_size`` + - Specifies the difference between the maximum and minimum luma transform block size. + * - __u8 + - ``max_transform_hierarchy_depth_inter`` + - Specifies the maximum hierarchy depth for transform units of coding units coded + in inter prediction mode. + * - __u8 + - ``max_transform_hierarchy_depth_intra`` + - Specifies the maximum hierarchy depth for transform units of coding units coded in + intra prediction mode. + * - __u8 + - ``pcm_sample_bit_depth_luma_minus1`` + - This value plus 1 specifies the number of bits used to represent each of PCM sample values of the + luma component. + * - __u8 + - ``pcm_sample_bit_depth_chroma_minus1`` + - Specifies the number of bits used to represent each of PCM sample values of + the chroma components. + * - __u8 + - ``log2_min_pcm_luma_coding_block_size_minus3`` + - Plus 3 specifies the minimum size of coding blocks. + * - __u8 + - ``log2_diff_max_min_pcm_luma_coding_block_size`` + - Specifies the difference between the maximum and minimum size of coding blocks. + * - __u8 + - ``num_short_term_ref_pic_sets`` + - Specifies the number of st_ref_pic_set() syntax structures included in the SPS. + * - __u8 + - ``num_long_term_ref_pics_sps`` + - Specifies the number of candidate long-term reference pictures that are + specified in the SPS. + * - __u8 + - ``chroma_format_idc`` + - Specifies the chroma sampling. + * - __u8 + - ``sps_max_sub_layers_minus1`` + - This value plus 1 specifies the maximum number of temporal sub-layers. + * - __u64 + - ``flags`` + - See :ref:`Sequence Parameter Set Flags ` + +.. raw:: latex + + \normalsize + +.. _hevc_sps_flags: + +``Sequence Parameter Set Flags`` + +.. raw:: latex + + \small + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE`` + - 0x00000001 + - + * - ``V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED`` + - 0x00000002 + - + * - ``V4L2_HEVC_SPS_FLAG_AMP_ENABLED`` + - 0x00000004 + - + * - ``V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET`` + - 0x00000008 + - + * - ``V4L2_HEVC_SPS_FLAG_PCM_ENABLED`` + - 0x00000010 + - + * - ``V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED`` + - 0x00000020 + - + * - ``V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT`` + - 0x00000040 + - + * - ``V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED`` + - 0x00000080 + - + * - ``V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED`` + - 0x00000100 + - + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_HEVC_PPS (struct)`` + Specifies the Picture Parameter Set fields (as extracted from the + bitstream) for the associated HEVC slice data. + These bitstream parameters are defined according to :ref:`hevc`. + They are described in section 7.4.3.3 "Picture parameter set RBSP + semantics" of the specification. + +.. c:type:: v4l2_ctrl_hevc_pps + +.. tabularcolumns:: |p{1.2cm}|p{8.6cm}|p{7.5cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_pps + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``pic_parameter_set_id`` + - Identifies the PPS for reference by other syntax elements. + * - __u8 + - ``num_extra_slice_header_bits`` + - Specifies the number of extra slice header bits that are present + in the slice header RBSP for coded pictures referring to the PPS. + * - __u8 + - ``num_ref_idx_l0_default_active_minus1`` + - This value plus 1 specifies the inferred value of num_ref_idx_l0_active_minus1. + * - __u8 + - ``num_ref_idx_l1_default_active_minus1`` + - This value plus 1 specifies the inferred value of num_ref_idx_l1_active_minus1. + * - __s8 + - ``init_qp_minus26`` + - This value plus 26 specifies the initial value of SliceQp Y for each slice + referring to the PPS. + * - __u8 + - ``diff_cu_qp_delta_depth`` + - Specifies the difference between the luma coding tree block size + and the minimum luma coding block size of coding units that + convey cu_qp_delta_abs and cu_qp_delta_sign_flag. + * - __s8 + - ``pps_cb_qp_offset`` + - Specifies the offsets to the luma quantization parameter Cb. + * - __s8 + - ``pps_cr_qp_offset`` + - Specifies the offsets to the luma quantization parameter Cr. + * - __u8 + - ``num_tile_columns_minus1`` + - This value plus 1 specifies the number of tile columns partitioning the picture. + * - __u8 + - ``num_tile_rows_minus1`` + - This value plus 1 specifies the number of tile rows partitioning the picture. + * - __u8 + - ``column_width_minus1[20]`` + - This value plus 1 specifies the width of the i-th tile column in units of + coding tree blocks. + * - __u8 + - ``row_height_minus1[22]`` + - This value plus 1 specifies the height of the i-th tile row in units of coding + tree blocks. + * - __s8 + - ``pps_beta_offset_div2`` + - Specifies the default deblocking parameter offsets for beta divided by 2. + * - __s8 + - ``pps_tc_offset_div2`` + - Specifies the default deblocking parameter offsets for tC divided by 2. + * - __u8 + - ``log2_parallel_merge_level_minus2`` + - This value plus 2 specifies the value of the variable Log2ParMrgLevel. + * - __u8 + - ``padding[4]`` + - Applications and drivers must set this to zero. + * - __u64 + - ``flags`` + - See :ref:`Picture Parameter Set Flags ` + +.. _hevc_pps_flags: + +``Picture Parameter Set Flags`` + +.. raw:: latex + + \small + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED`` + - 0x00000001 + - + * - ``V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT`` + - 0x00000002 + - + * - ``V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED`` + - 0x00000004 + - + * - ``V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT`` + - 0x00000008 + - + * - ``V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED`` + - 0x00000010 + - + * - ``V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED`` + - 0x00000020 + - + * - ``V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED`` + - 0x00000040 + - + * - ``V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT`` + - 0x00000080 + - + * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED`` + - 0x00000100 + - + * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED`` + - 0x00000200 + - + * - ``V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED`` + - 0x00000400 + - + * - ``V4L2_HEVC_PPS_FLAG_TILES_ENABLED`` + - 0x00000800 + - + * - ``V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED`` + - 0x00001000 + - + * - ``V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED`` + - 0x00002000 + - + * - ``V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED`` + - 0x00004000 + - + * - ``V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED`` + - 0x00008000 + - + * - ``V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER`` + - 0x00010000 + - + * - ``V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT`` + - 0x00020000 + - + * - ``V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT`` + - 0x00040000 + - + * - ``V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT`` + - 0x00080000 + - Specifies the presence of deblocking filter control syntax elements in + the PPS + * - ``V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING`` + - 0x00100000 + - Specifies that tile column boundaries and likewise tile row boundaries + are distributed uniformly across the picture + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_HEVC_SLICE_PARAMS (struct)`` + Specifies various slice-specific parameters, especially from the NAL unit + header, general slice segment header and weighted prediction parameter + parts of the bitstream. + These bitstream parameters are defined according to :ref:`hevc`. + They are described in section 7.4.7 "General slice segment header + semantics" of the specification. + This control is a dynamically sized 1-dimensional array, + V4L2_CTRL_FLAG_DYNAMIC_ARRAY flag must be set when using it. + +.. c:type:: v4l2_ctrl_hevc_slice_params + +.. raw:: latex + + \scriptsize + +.. tabularcolumns:: |p{5.4cm}|p{6.8cm}|p{5.1cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_slice_params + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u32 + - ``bit_size`` + - Size (in bits) of the current slice data. + * - __u32 + - ``data_byte_offset`` + - Offset (in byte) to the video data in the current slice data. + * - __u32 + - ``num_entry_point_offsets`` + - Specifies the number of entry point offset syntax elements in the slice header. + When the driver supports it, the ``V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS`` + must be set. + * - __u8 + - ``nal_unit_type`` + - Specifies the coding type of the slice (B, P or I). + * - __u8 + - ``nuh_temporal_id_plus1`` + - Minus 1 specifies a temporal identifier for the NAL unit. + * - __u8 + - ``slice_type`` + - + (V4L2_HEVC_SLICE_TYPE_I, V4L2_HEVC_SLICE_TYPE_P or + V4L2_HEVC_SLICE_TYPE_B). + * - __u8 + - ``colour_plane_id`` + - Specifies the colour plane associated with the current slice. + * - __s32 + - ``slice_pic_order_cnt`` + - Specifies the picture order count. + * - __u8 + - ``num_ref_idx_l0_active_minus1`` + - This value plus 1 specifies the maximum reference index for reference picture list 0 + that may be used to decode the slice. + * - __u8 + - ``num_ref_idx_l1_active_minus1`` + - This value plus 1 specifies the maximum reference index for reference picture list 1 + that may be used to decode the slice. + * - __u8 + - ``collocated_ref_idx`` + - Specifies the reference index of the collocated picture used for + temporal motion vector prediction. + * - __u8 + - ``five_minus_max_num_merge_cand`` + - Specifies the maximum number of merging motion vector prediction + candidates supported in the slice subtracted from 5. + * - __s8 + - ``slice_qp_delta`` + - Specifies the initial value of QpY to be used for the coding blocks in the slice. + * - __s8 + - ``slice_cb_qp_offset`` + - Specifies a difference to be added to the value of pps_cb_qp_offset. + * - __s8 + - ``slice_cr_qp_offset`` + - Specifies a difference to be added to the value of pps_cr_qp_offset. + * - __s8 + - ``slice_act_y_qp_offset`` + - Specifies the offset to the luma of quantization parameter qP derived in section 8.6.2 + * - __s8 + - ``slice_act_cb_qp_offset`` + - Specifies the offset to the cb of quantization parameter qP derived in section 8.6.2 + * - __s8 + - ``slice_act_cr_qp_offset`` + - Specifies the offset to the cr of quantization parameter qP derived in section 8.6.2 + * - __s8 + - ``slice_beta_offset_div2`` + - Specifies the deblocking parameter offsets for beta divided by 2. + * - __s8 + - ``slice_tc_offset_div2`` + - Specifies the deblocking parameter offsets for tC divided by 2. + * - __u8 + - ``pic_struct`` + - Indicates whether a picture should be displayed as a frame or as one or more fields. + * - __u32 + - ``slice_segment_addr`` + - Specifies the address of the first coding tree block in the slice segment. + * - __u8 + - ``ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The list of L0 reference elements as indices in the DPB. + * - __u8 + - ``ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The list of L1 reference elements as indices in the DPB. + * - __u16 + - ``short_term_ref_pic_set_size`` + - Specifies the size, in bits, of the short-term reference picture set, described as st_ref_pic_set() + in the specification, included in the slice header or SPS (section 7.3.6.1). + * - __u16 + - ``long_term_ref_pic_set_size`` + - Specifies the size, in bits, of the long-term reference picture set include in the slice header + or SPS. It is the number of bits in the conditional block if(long_term_ref_pics_present_flag) + in section 7.3.6.1 of the specification. + * - __u8 + - ``padding`` + - Applications and drivers must set this to zero. + * - struct :c:type:`v4l2_hevc_pred_weight_table` + - ``pred_weight_table`` + - The prediction weight coefficients for inter-picture prediction. + * - __u64 + - ``flags`` + - See :ref:`Slice Parameters Flags ` + +.. raw:: latex + + \normalsize + +.. _hevc_slice_params_flags: + +``Slice Parameters Flags`` + +.. raw:: latex + + \scriptsize + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA`` + - 0x00000001 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA`` + - 0x00000002 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED`` + - 0x00000004 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO`` + - 0x00000008 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT`` + - 0x00000010 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0`` + - 0x00000020 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV`` + - 0x00000040 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED`` + - 0x00000080 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED`` + - 0x00000100 + - + * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_DEPENDENT_SLICE_SEGMENT`` + - 0x00000200 + - + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS (integer)`` + Specifies entry point offsets in bytes. + This control is a dynamically sized array. The number of entry point + offsets is reported by the ``elems`` field. + This bitstream parameter is defined according to :ref:`hevc`. + They are described in section 7.4.7.1 "General slice segment header + semantics" of the specification. + When multiple slices are submitted in a request, the length of + this array must be the sum of num_entry_point_offsets of all the + slices in the request. + +``V4L2_CID_STATELESS_HEVC_SCALING_MATRIX (struct)`` + Specifies the HEVC scaling matrix parameters used for the scaling process + for transform coefficients. + These matrix and parameters are defined according to :ref:`hevc`. + They are described in section 7.4.5 "Scaling list data semantics" of + the specification. + +.. c:type:: v4l2_ctrl_hevc_scaling_matrix + +.. raw:: latex + + \scriptsize + +.. tabularcolumns:: |p{5.4cm}|p{6.8cm}|p{5.1cm}| + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_scaling_matrix + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``scaling_list_4x4[6][16]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + * - __u8 + - ``scaling_list_8x8[6][64]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + * - __u8 + - ``scaling_list_16x16[6][64]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + * - __u8 + - ``scaling_list_32x32[2][64]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + * - __u8 + - ``scaling_list_dc_coef_16x16[6]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + * - __u8 + - ``scaling_list_dc_coef_32x32[2]`` + - Scaling list is used for the scaling process for transform + coefficients. The values on each scaling list are expected + in raster scan order. + +.. raw:: latex + + \normalsize + +.. c:type:: v4l2_hevc_dpb_entry + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{1.0cm}|p{4.2cm}|p{12.1cm}| + +.. flat-table:: struct v4l2_hevc_dpb_entry + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u64 + - ``timestamp`` + - Timestamp of the V4L2 capture buffer to use as reference, used + with B-coded and P-coded frames. The timestamp refers to the + ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the + :c:func:`v4l2_timeval_to_ns()` function to convert the struct + :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64. + * - __u8 + - ``flags`` + - Long term flag for the reference frame + (V4L2_HEVC_DPB_ENTRY_LONG_TERM_REFERENCE). The flag is set as + described in the ITU HEVC specification chapter "8.3.2 Decoding + process for reference picture set". + * - __u8 + - ``field_pic`` + - Whether the reference is a field picture or a frame. + See :ref:`HEVC dpb field pic Flags ` + * - __s32 + - ``pic_order_cnt_val`` + - The picture order count of the current picture. + * - __u8 + - ``padding[2]`` + - Applications and drivers must set this to zero. + +.. raw:: latex + + \normalsize + +.. _hevc_dpb_field_pic_flags: + +``HEVC dpb field pic Flags`` + +.. raw:: latex + + \scriptsize + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME`` + - 0 + - (progressive) Frame + * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_FIELD`` + - 1 + - Top field + * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_FIELD`` + - 2 + - Bottom field + * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM`` + - 3 + - Top field, bottom field, in that order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP`` + - 4 + - Bottom field, top field, in that order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM_TOP`` + - 5 + - Top field, bottom field, top field repeated, in that order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP_BOTTOM`` + - 6 + - Bottom field, top field, bottom field repeated, in that order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME_DOUBLING`` + - 7 + - Frame doubling + * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME_TRIPLING`` + - 8 + - Frame tripling + * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_PREVIOUS_BOTTOM`` + - 9 + - Top field paired with previous bottom field in output order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_PREVIOUS_TOP`` + - 10 + - Bottom field paired with previous top field in output order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_NEXT_BOTTOM`` + - 11 + - Top field paired with next bottom field in output order + * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_NEXT_TOP`` + - 12 + - Bottom field paired with next top field in output order + +.. c:type:: v4l2_hevc_pred_weight_table + +.. raw:: latex + + \footnotesize + +.. tabularcolumns:: |p{0.8cm}|p{10.6cm}|p{5.9cm}| + +.. flat-table:: struct v4l2_hevc_pred_weight_table + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __s8 + - ``delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The difference of the weighting factor applied to the luma + prediction value for list 0. + * - __s8 + - ``luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The additive offset applied to the luma prediction value for list 0. + * - __s8 + - ``delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` + - The difference of the weighting factor applied to the chroma + prediction value for list 0. + * - __s8 + - ``chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` + - The difference of the additive offset applied to the chroma + prediction values for list 0. + * - __s8 + - ``delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The difference of the weighting factor applied to the luma + prediction value for list 1. + * - __s8 + - ``luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The additive offset applied to the luma prediction value for list 1. + * - __s8 + - ``delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` + - The difference of the weighting factor applied to the chroma + prediction value for list 1. + * - __s8 + - ``chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` + - The difference of the additive offset applied to the chroma + prediction values for list 1. + * - __u8 + - ``luma_log2_weight_denom`` + - The base 2 logarithm of the denominator for all luma weighting + factors. + * - __s8 + - ``delta_chroma_log2_weight_denom`` + - The difference of the base 2 logarithm of the denominator for + all chroma weighting factors. + * - __u8 + - ``padding[6]`` + - Applications and drivers must set this to zero. + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_HEVC_DECODE_MODE (enum)`` + Specifies the decoding mode to use. Currently exposes slice-based and + frame-based decoding but new modes might be added later on. + This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE + pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE + are required to set this control in order to specify the decoding mode + that is expected for the buffer. + Drivers may expose a single or multiple decoding modes, depending + on what they can support. + +.. c:type:: v4l2_stateless_hevc_decode_mode + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{9.4cm}|p{0.6cm}|p{7.3cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED`` + - 0 + - Decoding is done at the slice granularity. + The OUTPUT buffer must contain a single slice. + * - ``V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED`` + - 1 + - Decoding is done at the frame granularity. + The OUTPUT buffer must contain all slices needed to decode the + frame. + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_HEVC_START_CODE (enum)`` + Specifies the HEVC slice start code expected for each slice. + This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE + pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE + are required to set this control in order to specify the start code + that is expected for the buffer. + Drivers may expose a single or multiple start codes, depending + on what they can support. + +.. c:type:: v4l2_stateless_hevc_start_code + +.. tabularcolumns:: |p{9.2cm}|p{0.6cm}|p{7.5cm}| + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_STATELESS_HEVC_START_CODE_NONE`` + - 0 + - Selecting this value specifies that HEVC slices are passed + to the driver without any start code. The bitstream data should be + according to :ref:`hevc` 7.3.1.1 General NAL unit syntax, hence + contains emulation prevention bytes when required. + * - ``V4L2_STATELESS_HEVC_START_CODE_ANNEX_B`` + - 1 + - Selecting this value specifies that HEVC slices are expected + to be prefixed by Annex B start codes. According to :ref:`hevc` + valid start codes can be 3-bytes 0x000001 or 4-bytes 0x00000001. + +.. raw:: latex + + \normalsize + +``V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID (integer)`` + Specifies a priority identifier for the NAL unit, which will be applied to + the base layer. By default this value is set to 0 for the base layer, + and the next layer will have the priority ID assigned as 1, 2, 3 and so on. + The video encoder can't decide the priority id to be applied to a layer, + so this has to come from client. + This is applicable to H264 and valid Range is from 0 to 63. + Source Rec. ITU-T H.264 (06/2019); G.7.4.1.1, G.8.8.1. + +``V4L2_CID_MPEG_VIDEO_LTR_COUNT (integer)`` + Specifies the maximum number of Long Term Reference (LTR) frames at any + given time that the encoder can keep. + This is applicable to the H264 and HEVC encoders. + +``V4L2_CID_MPEG_VIDEO_FRAME_LTR_INDEX (integer)`` + After setting this control the frame that will be queued next + will be marked as a Long Term Reference (LTR) frame + and given this LTR index which ranges from 0 to LTR_COUNT-1. + This is applicable to the H264 and HEVC encoders. + Source Rec. ITU-T H.264 (06/2019); Table 7.9 + +``V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES (bitmask)`` + Specifies the Long Term Reference (LTR) frame(s) to be used for + encoding the next frame queued after setting this control. + This provides a bitmask which consists of bits [0, LTR_COUNT-1]. + This is applicable to the H264 and HEVC encoders. + +``V4L2_CID_STATELESS_HEVC_DECODE_PARAMS (struct)`` + Specifies various decode parameters, especially the references picture order + count (POC) for all the lists (short, long, before, current, after) and the + number of entries for each of them. + These parameters are defined according to :ref:`hevc`. + They are described in section 8.3 "Slice decoding process" of the + specification. + +.. c:type:: v4l2_ctrl_hevc_decode_params + +.. cssclass:: longtable + +.. flat-table:: struct v4l2_ctrl_hevc_decode_params + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __s32 + - ``pic_order_cnt_val`` + - PicOrderCntVal as described in section 8.3.1 "Decoding process + for picture order count" of the specification. + * - __u16 + - ``short_term_ref_pic_set_size`` + - Specifies the size, in bits, of the short-term reference picture set, of the first slice + described as st_ref_pic_set() in the specification, included in the slice header + or SPS (section 7.3.6.1). + * - __u16 + - ``long_term_ref_pic_set_size`` + - Specifies the size, in bits, of the long-term reference picture set, of the first slice + included in the slice header or SPS. It is the number of bits in the conditional block + if(long_term_ref_pics_present_flag) in section 7.3.6.1 of the specification. + * - __u8 + - ``num_active_dpb_entries`` + - The number of entries in ``dpb``. + * - __u8 + - ``num_poc_st_curr_before`` + - The number of reference pictures in the short-term set that come before + the current frame. + * - __u8 + - ``num_poc_st_curr_after`` + - The number of reference pictures in the short-term set that come after + the current frame. + * - __u8 + - ``num_poc_lt_curr`` + - The number of reference pictures in the long-term set. + * - __u8 + - ``poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocStCurrBefore as described in section 8.3.2 "Decoding process for reference + picture set": provides the index of the short term before references in DPB array. + * - __u8 + - ``poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocStCurrAfter as described in section 8.3.2 "Decoding process for reference + picture set": provides the index of the short term after references in DPB array. + * - __u8 + - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - PocLtCurr as described in section 8.3.2 "Decoding process for reference + picture set": provides the index of the long term references in DPB array. + * - struct :c:type:`v4l2_hevc_dpb_entry` + - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` + - The decoded picture buffer, for meta-data about reference frames. + * - __u64 + - ``flags`` + - See :ref:`Decode Parameters Flags ` + +.. _hevc_decode_params_flags: + +``Decode Parameters Flags`` + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC`` + - 0x00000001 + - + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC`` + - 0x00000002 + - + * - ``V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR`` + - 0x00000004 + - diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 6cf68588af1b..2a165ae063fb 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -2658,909 +2658,3 @@ enum v4l2_mpeg_video_hevc_size_of_length_field - Indicates whether to generate SPS and PPS at every IDR. Setting it to 0 disables generating SPS and PPS at every IDR. Setting it to one enables generating SPS and PPS at every IDR. - -.. _v4l2-mpeg-hevc: - -``V4L2_CID_STATELESS_HEVC_SPS (struct)`` - Specifies the Sequence Parameter Set fields (as extracted from the - bitstream) for the associated HEVC slice data. - These bitstream parameters are defined according to :ref:`hevc`. - They are described in section 7.4.3.2 "Sequence parameter set RBSP - semantics" of the specification. - -.. c:type:: v4l2_ctrl_hevc_sps - -.. raw:: latex - - \small - -.. tabularcolumns:: |p{1.2cm}|p{9.2cm}|p{6.9cm}| - -.. cssclass:: longtable - -.. flat-table:: struct v4l2_ctrl_hevc_sps - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u8 - - ``video_parameter_set_id`` - - Specifies the value of the vps_video_parameter_set_id of the active VPS - as described in section "7.4.3.2.1 General sequence parameter set RBSP semantics" - of H.265 specifications. - * - __u8 - - ``seq_parameter_set_id`` - - Provides an identifier for the SPS for reference by other syntax elements - as described in section "7.4.3.2.1 General sequence parameter set RBSP semantics" - of H.265 specifications. - * - __u16 - - ``pic_width_in_luma_samples`` - - Specifies the width of each decoded picture in units of luma samples. - * - __u16 - - ``pic_height_in_luma_samples`` - - Specifies the height of each decoded picture in units of luma samples. - * - __u8 - - ``bit_depth_luma_minus8`` - - This value plus 8 specifies the bit depth of the samples of the luma array. - * - __u8 - - ``bit_depth_chroma_minus8`` - - This value plus 8 specifies the bit depth of the samples of the chroma arrays. - * - __u8 - - ``log2_max_pic_order_cnt_lsb_minus4`` - - This value plus 4 specifies the value of the variable MaxPicOrderCntLsb. - * - __u8 - - ``sps_max_dec_pic_buffering_minus1`` - - This value plus 1 specifies the maximum required size of the decoded picture buffer for - the codec video sequence. - * - __u8 - - ``sps_max_num_reorder_pics`` - - Indicates the maximum allowed number of pictures. - * - __u8 - - ``sps_max_latency_increase_plus1`` - - Not equal to 0 is used to compute the value of SpsMaxLatencyPictures array. - * - __u8 - - ``log2_min_luma_coding_block_size_minus3`` - - This value plus 3 specifies the minimum luma coding block size. - * - __u8 - - ``log2_diff_max_min_luma_coding_block_size`` - - Specifies the difference between the maximum and minimum luma coding block size. - * - __u8 - - ``log2_min_luma_transform_block_size_minus2`` - - This value plus 2 specifies the minimum luma transform block size. - * - __u8 - - ``log2_diff_max_min_luma_transform_block_size`` - - Specifies the difference between the maximum and minimum luma transform block size. - * - __u8 - - ``max_transform_hierarchy_depth_inter`` - - Specifies the maximum hierarchy depth for transform units of coding units coded - in inter prediction mode. - * - __u8 - - ``max_transform_hierarchy_depth_intra`` - - Specifies the maximum hierarchy depth for transform units of coding units coded in - intra prediction mode. - * - __u8 - - ``pcm_sample_bit_depth_luma_minus1`` - - This value plus 1 specifies the number of bits used to represent each of PCM sample - values of the luma component. - * - __u8 - - ``pcm_sample_bit_depth_chroma_minus1`` - - This value plus 1 specifies the number of bits used to represent each of PCM sample - values of the chroma components. - * - __u8 - - ``log2_min_pcm_luma_coding_block_size_minus3`` - - This value plus 3 specifies the minimum size of coding blocks. - * - __u8 - - ``log2_diff_max_min_pcm_luma_coding_block_size`` - - Specifies the difference between the maximum and minimum size of coding blocks. - * - __u8 - - ``num_short_term_ref_pic_sets`` - - Specifies the number of st_ref_pic_set() syntax structures included in the SPS. - * - __u8 - - ``num_long_term_ref_pics_sps`` - - Specifies the number of candidate long-term reference pictures that are - specified in the SPS. - * - __u8 - - ``chroma_format_idc`` - - Specifies the chroma sampling. - * - __u8 - - ``sps_max_sub_layers_minus1`` - - This value plus 1 specifies the maximum number of temporal sub-layers. - * - __u64 - - ``flags`` - - See :ref:`Sequence Parameter Set Flags ` - -.. raw:: latex - - \normalsize - -.. _hevc_sps_flags: - -``Sequence Parameter Set Flags`` - -.. raw:: latex - - \small - -.. cssclass:: longtable - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE`` - - 0x00000001 - - - * - ``V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED`` - - 0x00000002 - - - * - ``V4L2_HEVC_SPS_FLAG_AMP_ENABLED`` - - 0x00000004 - - - * - ``V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET`` - - 0x00000008 - - - * - ``V4L2_HEVC_SPS_FLAG_PCM_ENABLED`` - - 0x00000010 - - - * - ``V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED`` - - 0x00000020 - - - * - ``V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT`` - - 0x00000040 - - - * - ``V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED`` - - 0x00000080 - - - * - ``V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED`` - - 0x00000100 - - - -.. raw:: latex - - \normalsize - -``V4L2_CID_STATELESS_HEVC_PPS (struct)`` - Specifies the Picture Parameter Set fields (as extracted from the - bitstream) for the associated HEVC slice data. - These bitstream parameters are defined according to :ref:`hevc`. - They are described in section 7.4.3.3 "Picture parameter set RBSP - semantics" of the specification. - -.. c:type:: v4l2_ctrl_hevc_pps - -.. tabularcolumns:: |p{1.2cm}|p{8.6cm}|p{7.5cm}| - -.. cssclass:: longtable - -.. flat-table:: struct v4l2_ctrl_hevc_pps - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u8 - - ``pic_parameter_set_id`` - - Identifies the PPS for reference by other syntax elements. - * - __u8 - - ``num_extra_slice_header_bits`` - - Specifies the number of extra slice header bits that are present - in the slice header RBSP for coded pictures referring to the PPS. - * - __u8 - - ``num_ref_idx_l0_default_active_minus1`` - - This value plus 1 specifies the inferred value of num_ref_idx_l0_active_minus1. - * - __u8 - - ``num_ref_idx_l1_default_active_minus1`` - - This value plus 1 specifies the inferred value of num_ref_idx_l1_active_minus1. - * - __s8 - - ``init_qp_minus26`` - - This value plus 26 specifies the initial value of SliceQp Y for each slice - referring to the PPS. - * - __u8 - - ``diff_cu_qp_delta_depth`` - - Specifies the difference between the luma coding tree block size - and the minimum luma coding block size of coding units that - convey cu_qp_delta_abs and cu_qp_delta_sign_flag. - * - __s8 - - ``pps_cb_qp_offset`` - - Specifies the offsets to the luma quantization parameter Cb. - * - __s8 - - ``pps_cr_qp_offset`` - - Specifies the offsets to the luma quantization parameter Cr. - * - __u8 - - ``num_tile_columns_minus1`` - - This value plus 1 specifies the number of tile columns partitioning the picture. - * - __u8 - - ``num_tile_rows_minus1`` - - This value plus 1 specifies the number of tile rows partitioning the picture. - * - __u8 - - ``column_width_minus1[20]`` - - Plus 1 specifies the width of each tile column in units of - coding tree blocks. - * - __u8 - - ``row_height_minus1[22]`` - - This value plus 1 specifies the height of each tile row in units of coding - tree blocks. - * - __s8 - - ``pps_beta_offset_div2`` - - Specifies the default deblocking parameter offsets for beta divided by 2. - * - __s8 - - ``pps_tc_offset_div2`` - - Specifies the default deblocking parameter offsets for tC divided by 2. - * - __u8 - - ``log2_parallel_merge_level_minus2`` - - Plus 2 specifies the value of the variable Log2ParMrgLevel. - * - __u8 - - ``padding[4]`` - - Applications and drivers must set this to zero. - * - __u64 - - ``flags`` - - See :ref:`Picture Parameter Set Flags ` - -.. _hevc_pps_flags: - -``Picture Parameter Set Flags`` - -.. raw:: latex - - \small - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED`` - - 0x00000001 - - - * - ``V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT`` - - 0x00000002 - - - * - ``V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED`` - - 0x00000004 - - - * - ``V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT`` - - 0x00000008 - - - * - ``V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED`` - - 0x00000010 - - - * - ``V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED`` - - 0x00000020 - - - * - ``V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED`` - - 0x00000040 - - - * - ``V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT`` - - 0x00000080 - - - * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED`` - - 0x00000100 - - - * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED`` - - 0x00000200 - - - * - ``V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED`` - - 0x00000400 - - - * - ``V4L2_HEVC_PPS_FLAG_TILES_ENABLED`` - - 0x00000800 - - - * - ``V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED`` - - 0x00001000 - - - * - ``V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED`` - - 0x00002000 - - - * - ``V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED`` - - 0x00004000 - - - * - ``V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED`` - - 0x00008000 - - - * - ``V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER`` - - 0x00010000 - - - * - ``V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT`` - - 0x00020000 - - - * - ``V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT`` - - 0x00040000 - - - * - ``V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT`` - - 0x00080000 - - Specifies the presence of deblocking filter control syntax elements in - the PPS - * - ``V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING`` - - 0x00100000 - - Specifies that tile column boundaries and likewise tile row boundaries - are distributed uniformly across the picture - -.. raw:: latex - - \normalsize - -``V4L2_CID_STATELESS_HEVC_SLICE_PARAMS (struct)`` - Specifies various slice-specific parameters, especially from the NAL unit - header, general slice segment header and weighted prediction parameter - parts of the bitstream. - These bitstream parameters are defined according to :ref:`hevc`. - They are described in section 7.4.7 "General slice segment header - semantics" of the specification. - This control is a dynamically sized 1-dimensional array, - V4L2_CTRL_FLAG_DYNAMIC_ARRAY flag must be set when using it. - -.. c:type:: v4l2_ctrl_hevc_slice_params - -.. raw:: latex - - \scriptsize - -.. tabularcolumns:: |p{5.4cm}|p{6.8cm}|p{5.1cm}| - -.. cssclass:: longtable - -.. flat-table:: struct v4l2_ctrl_hevc_slice_params - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u32 - - ``bit_size`` - - Size (in bits) of the current slice data. - * - __u32 - - ``data_byte_offset`` - - Offset (in bytes) to the video data in the current slice data. - * - __u32 - - ``num_entry_point_offsets`` - - Specifies the number of entry point offset syntax elements in the slice header. - When the driver supports it, the ``V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS`` - must be set. - * - __u8 - - ``nal_unit_type`` - - Specifies the coding type of the slice (B, P or I). - * - __u8 - - ``nuh_temporal_id_plus1`` - - This value minus 1 specifies a temporal identifier for the NAL unit. - * - __u8 - - ``slice_type`` - - - (V4L2_HEVC_SLICE_TYPE_I, V4L2_HEVC_SLICE_TYPE_P or - V4L2_HEVC_SLICE_TYPE_B). - * - __u8 - - ``colour_plane_id`` - - Specifies the colour plane associated with the current slice. - * - __s32 - - ``slice_pic_order_cnt`` - - Specifies the picture order count. - * - __u8 - - ``num_ref_idx_l0_active_minus1`` - - This value plus 1 specifies the maximum reference index for - reference picture list 0 that may be used to decode the slice. - * - __u8 - - ``num_ref_idx_l1_active_minus1`` - - This value plus 1 specifies the maximum reference index for - reference picture list 1 that may be used to decode the slice. - * - __u8 - - ``collocated_ref_idx`` - - Specifies the reference index of the collocated picture used for - temporal motion vector prediction. - * - __u8 - - ``five_minus_max_num_merge_cand`` - - Specifies the maximum number of merging motion vector prediction - candidates supported in the slice subtracted from 5. - * - __s8 - - ``slice_qp_delta`` - - Specifies the initial value of QpY to be used for the coding blocks in the slice. - * - __s8 - - ``slice_cb_qp_offset`` - - Specifies a difference to be added to the value of pps_cb_qp_offset. - * - __s8 - - ``slice_cr_qp_offset`` - - Specifies a difference to be added to the value of pps_cr_qp_offset. - * - __s8 - - ``slice_act_y_qp_offset`` - - Screen content extension parameters. - * - __s8 - - ``slice_act_cb_qp_offset`` - - Screen content extension parameters. - * - __s8 - - ``slice_act_cr_qp_offset`` - - Screen content extension parameters. - * - __s8 - - ``slice_beta_offset_div2`` - - Specifies the deblocking parameter offsets for beta divided by 2. - * - __s8 - - ``slice_tc_offset_div2`` - - Specifies the deblocking parameter offsets for tC divided by 2. - * - __u8 - - ``pic_struct`` - - Indicates whether a picture should be displayed as a frame or as one or more fields. - * - __u32 - - ``slice_segment_addr`` - - Specifies the address of the first coding tree block in the slice segment. - * - __u8 - - ``ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The list of L0 reference elements as indices in the DPB. - * - __u8 - - ``ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The list of L1 reference elements as indices in the DPB. - * - __u16 - - ``short_term_ref_pic_set_size`` - - Specifies the size, in bits, of the short-term reference picture set, described as st_ref_pic_set() - in the specification, included in the slice header or SPS (section 7.3.6.1). - * - __u16 - - ``long_term_ref_pic_set_size`` - - Specifies the size, in bits, of the long-term reference picture set include in the slice header - or SPS. It is the number of bits in the conditional block if(long_term_ref_pics_present_flag) - in section 7.3.6.1 of the specification. - * - __u8 - - ``padding`` - - Applications and drivers must set this to zero. - * - struct :c:type:`v4l2_hevc_pred_weight_table` - - ``pred_weight_table`` - - The prediction weight coefficients for inter-picture prediction. - * - __u64 - - ``flags`` - - See :ref:`Slice Parameters Flags ` - -.. raw:: latex - - \normalsize - -.. _hevc_slice_params_flags: - -``Slice Parameters Flags`` - -.. raw:: latex - - \scriptsize - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA`` - - 0x00000001 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA`` - - 0x00000002 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED`` - - 0x00000004 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO`` - - 0x00000008 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT`` - - 0x00000010 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0`` - - 0x00000020 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV`` - - 0x00000040 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED`` - - 0x00000080 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED`` - - 0x00000100 - - - * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_DEPENDENT_SLICE_SEGMENT`` - - 0x00000200 - - - -.. raw:: latex - - \normalsize - -``V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS (integer)`` - Specifies entry point offsets in bytes. - This control is a dynamically sized array. The number of entry point - offsets is reported by the ``elems`` field. - This bitstream parameter is defined according to :ref:`hevc`. - They are described in section 7.4.7.1 "General slice segment header - semantics" of the specification. - When multiple slices are submitted in a request, the length of - this array must be the sum of num_entry_point_offsets of all the - slices in the request. - -``V4L2_CID_STATELESS_HEVC_SCALING_MATRIX (struct)`` - Specifies the HEVC scaling matrix parameters used for the scaling process - for transform coefficients. - These matrix and parameters are defined according to :ref:`hevc`. - They are described in section 7.4.5 "Scaling list data semantics" of - the specification. - -.. c:type:: v4l2_ctrl_hevc_scaling_matrix - -.. raw:: latex - - \scriptsize - -.. tabularcolumns:: |p{5.4cm}|p{6.8cm}|p{5.1cm}| - -.. cssclass:: longtable - -.. flat-table:: struct v4l2_ctrl_hevc_scaling_matrix - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u8 - - ``scaling_list_4x4[6][16]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - * - __u8 - - ``scaling_list_8x8[6][64]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - * - __u8 - - ``scaling_list_16x16[6][64]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - * - __u8 - - ``scaling_list_32x32[2][64]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - * - __u8 - - ``scaling_list_dc_coef_16x16[6]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - * - __u8 - - ``scaling_list_dc_coef_32x32[2]`` - - Scaling list is used for the scaling process for transform - coefficients. The values on each scaling list are expected - in raster scan order. - -.. raw:: latex - - \normalsize - -.. c:type:: v4l2_hevc_dpb_entry - -.. raw:: latex - - \small - -.. tabularcolumns:: |p{1.0cm}|p{4.2cm}|p{12.1cm}| - -.. flat-table:: struct v4l2_hevc_dpb_entry - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u64 - - ``timestamp`` - - Timestamp of the V4L2 capture buffer to use as reference, used - with B-coded and P-coded frames. The timestamp refers to the - ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the - :c:func:`v4l2_timeval_to_ns()` function to convert the struct - :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64. - * - __u8 - - ``flags`` - - Long term flag for the reference frame - (V4L2_HEVC_DPB_ENTRY_LONG_TERM_REFERENCE). The flag is set as - described in the ITU HEVC specification chapter "8.3.2 Decoding - process for reference picture set". - * - __u8 - - ``field_pic`` - - Whether the reference is a field picture or a frame. - See :ref:`HEVC dpb field pic Flags ` - * - __s32 - - ``pic_order_cnt_val`` - - The picture order count of the current picture. - * - __u8 - - ``padding[2]`` - - Applications and drivers must set this to zero. - -.. raw:: latex - - \normalsize - -.. _hevc_dpb_field_pic_flags: - -``HEVC dpb field pic Flags`` - -.. raw:: latex - - \scriptsize - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME`` - - 0 - - (progressive) Frame - * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_FIELD`` - - 1 - - Top field - * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_FIELD`` - - 2 - - Bottom field - * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM`` - - 3 - - Top field, bottom field, in that order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP`` - - 4 - - Bottom field, top field, in that order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM_TOP`` - - 5 - - Top field, bottom field, top field repeated, in that order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP_BOTTOM`` - - 6 - - Bottom field, top field, bottom field repeated, in that order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME_DOUBLING`` - - 7 - - Frame doubling - * - ``V4L2_HEVC_SEI_PIC_STRUCT_FRAME_TRIPLING`` - - 8 - - Frame tripling - * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_PREVIOUS_BOTTOM`` - - 9 - - Top field paired with previous bottom field in output order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_PREVIOUS_TOP`` - - 10 - - Bottom field paired with previous top field in output order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_NEXT_BOTTOM`` - - 11 - - Top field paired with next bottom field in output order - * - ``V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_NEXT_TOP`` - - 12 - - Bottom field paired with next top field in output order - -.. c:type:: v4l2_hevc_pred_weight_table - -.. raw:: latex - - \footnotesize - -.. tabularcolumns:: |p{0.8cm}|p{10.6cm}|p{5.9cm}| - -.. flat-table:: struct v4l2_hevc_pred_weight_table - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __s8 - - ``delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The difference of the weighting factor applied to the luma - prediction value for list 0. - * - __s8 - - ``luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The additive offset applied to the luma prediction value for list 0. - * - __s8 - - ``delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` - - The difference of the weighting factor applied to the chroma - prediction value for list 0. - * - __s8 - - ``chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` - - The difference of the additive offset applied to the chroma - prediction values for list 0. - * - __s8 - - ``delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The difference of the weighting factor applied to the luma - prediction value for list 1. - * - __s8 - - ``luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The additive offset applied to the luma prediction value for list 1. - * - __s8 - - ``delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` - - The difference of the weighting factor applied to the chroma - prediction value for list 1. - * - __s8 - - ``chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]`` - - The difference of the additive offset applied to the chroma - prediction values for list 1. - * - __u8 - - ``luma_log2_weight_denom`` - - The base 2 logarithm of the denominator for all luma weighting - factors. - * - __s8 - - ``delta_chroma_log2_weight_denom`` - - The difference of the base 2 logarithm of the denominator for - all chroma weighting factors. - * - __u8 - - ``padding[6]`` - - Applications and drivers must set this to zero. - -.. raw:: latex - - \normalsize - -``V4L2_CID_STATELESS_HEVC_DECODE_MODE (enum)`` - Specifies the decoding mode to use. Currently exposes slice-based and - frame-based decoding but new modes might be added later on. - This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE - pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE - are required to set this control in order to specify the decoding mode - that is expected for the buffer. - Drivers may expose a single or multiple decoding modes, depending - on what they can support. - - .. note:: - - This menu control is not yet part of the public kernel API and - it is expected to change. - -.. c:type:: v4l2_stateless_hevc_decode_mode - -.. raw:: latex - - \small - -.. tabularcolumns:: |p{9.4cm}|p{0.6cm}|p{7.3cm}| - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED`` - - 0 - - Decoding is done at the slice granularity. - The OUTPUT buffer must contain a single slice. - * - ``V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED`` - - 1 - - Decoding is done at the frame granularity. - The OUTPUT buffer must contain all slices needed to decode the - frame. The OUTPUT buffer must also contain both fields. - -.. raw:: latex - - \normalsize - -``V4L2_CID_STATELESS_HEVC_START_CODE (enum)`` - Specifies the HEVC slice start code expected for each slice. - This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE - pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE - are required to set this control in order to specify the start code - that is expected for the buffer. - Drivers may expose a single or multiple start codes, depending - on what they can support. - - .. note:: - - This menu control is not yet part of the public kernel API and - it is expected to change. - -.. c:type:: v4l2_stateless_hevc_start_code - -.. tabularcolumns:: |p{9.2cm}|p{0.6cm}|p{7.5cm}| - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_STATELESS_HEVC_START_CODE_NONE`` - - 0 - - Selecting this value specifies that HEVC slices are passed - to the driver without any start code. The bitstream data should be - according to :ref:`hevc` 7.3.1.1 General NAL unit syntax, hence - contains emulation prevention bytes when required. - * - ``V4L2_STATELESS_HEVC_START_CODE_ANNEX_B`` - - 1 - - Selecting this value specifies that HEVC slices are expected - to be prefixed by Annex B start codes. According to :ref:`hevc` - valid start codes can be 3-bytes 0x000001 or 4-bytes 0x00000001. - -``V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID (integer)`` - Specifies a priority identifier for the NAL unit, which will be applied to - the base layer. By default this value is set to 0 for the base layer, - and the next layer will have the priority ID assigned as 1, 2, 3 and so on. - The video encoder can't decide the priority id to be applied to a layer, - so this has to come from client. - This is applicable to H264 and valid Range is from 0 to 63. - Source Rec. ITU-T H.264 (06/2019); G.7.4.1.1, G.8.8.1. - -``V4L2_CID_MPEG_VIDEO_LTR_COUNT (integer)`` - Specifies the maximum number of Long Term Reference (LTR) frames at any - given time that the encoder can keep. - This is applicable to the H264 and HEVC encoders. - -``V4L2_CID_MPEG_VIDEO_FRAME_LTR_INDEX (integer)`` - After setting this control the frame that will be queued next - will be marked as a Long Term Reference (LTR) frame - and given this LTR index which ranges from 0 to LTR_COUNT-1. - This is applicable to the H264 and HEVC encoders. - Source Rec. ITU-T H.264 (06/2019); Table 7.9 - -``V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES (bitmask)`` - Specifies the Long Term Reference (LTR) frame(s) to be used for - encoding the next frame queued after setting this control. - This provides a bitmask which consists of bits [0, LTR_COUNT-1]. - This is applicable to the H264 and HEVC encoders. - -``V4L2_CID_STATELESS_HEVC_DECODE_PARAMS (struct)`` - Specifies various decode parameters, especially the references picture order - count (POC) for all the lists (short, long, before, current, after) and the - number of entries for each of them. - These parameters are defined according to :ref:`hevc`. - They are described in section 8.3 "Slice decoding process" of the - specification. - -.. c:type:: v4l2_ctrl_hevc_decode_params - -.. cssclass:: longtable - -.. flat-table:: struct v4l2_ctrl_hevc_decode_params - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __s32 - - ``pic_order_cnt_val`` - - PicOrderCntVal as described in section 8.3.1 "Decoding process - for picture order count" of the specification. - * - __u16 - - ``short_term_ref_pic_set_size`` - - Specifies the size, in bits, of the short-term reference picture set, of the first slice - described as st_ref_pic_set() in the specification, included in the slice header - or SPS (section 7.3.6.1). - * - __u16 - - ``long_term_ref_pic_set_size`` - - Specifies the size, in bits, of the long-term reference picture set, of the first slice - included in the slice header or SPS. It is the number of bits in the conditional block - if(long_term_ref_pics_present_flag) in section 7.3.6.1 of the specification. - * - __u8 - - ``num_active_dpb_entries`` - - The number of entries in ``dpb``. - * - __u8 - - ``num_poc_st_curr_before`` - - The number of reference pictures in the short-term set that come before - the current frame. - * - __u8 - - ``num_poc_st_curr_after`` - - The number of reference pictures in the short-term set that come after - the current frame. - * - __u8 - - ``num_poc_lt_curr`` - - The number of reference pictures in the long-term set. - * - __u8 - - ``poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - PocStCurrBefore as described in section 8.3.2 "Decoding process for reference - picture set": provides the index of the short term before references in DPB array. - * - __u8 - - ``poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - PocStCurrAfter as described in section 8.3.2 "Decoding process for reference - picture set": provides the index of the short term after references in DPB array. - * - __u8 - - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - PocLtCurr as described in section 8.3.2 "Decoding process for reference - picture set": provides the index of the long term references in DPB array. - * - struct :c:type:`v4l2_hevc_dpb_entry` - - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - - The decoded picture buffer, for meta-data about reference frames. - * - __u64 - - ``flags`` - - See :ref:`Decode Parameters Flags ` - -.. _hevc_decode_params_flags: - -``Decode Parameters Flags`` - -.. cssclass:: longtable - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC`` - - 0x00000001 - - - * - ``V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC`` - - 0x00000002 - - - * - ``V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR`` - - 0x00000004 - - diff --git a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst index c352d91a73d8..506dd3c98884 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst @@ -212,7 +212,7 @@ Compressed Formats ``V4L2_CID_MPEG_VIDEO_HEVC_SPS``, ``V4L2_CID_MPEG_VIDEO_HEVC_PPS``, and ``V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS``. - See the :ref:`associated Codec Control IDs `. + See the :ref:`associated Codec Control IDs `. Buffers associated with this pixel format must contain the appropriate number of macroblocks to decode a full corresponding frame. * .. _V4L2-PIX-FMT-FWHT: diff --git a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst index 29971a45a2d4..892cfeb8b988 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst @@ -249,6 +249,26 @@ still cause this situation. - ``p_hdr10_mastering`` - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_mastering_display`. Valid if this control is of type ``V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY``. + * - struct :c:type:`v4l2_ctrl_hevc_sps` * + - ``p_hevc_sps`` + - A pointer to a struct :c:type:`v4l2_ctrl_hevc_sps`. Valid if this + control is of type ``V4L2_CTRL_TYPE_HEVC_SPS``. + * - struct :c:type:`v4l2_ctrl_hevc_pps` * + - ``p_hevc_pps`` + - A pointer to a struct :c:type:`v4l2_ctrl_hevc_pps`. Valid if this + control is of type ``V4L2_CTRL_TYPE_HEVC_PPS``. + * - struct :c:type:`v4l2_ctrl_hevc_slice_params` * + - ``p_hevc_slice_params`` + - A pointer to a struct :c:type:`v4l2_ctrl_hevc_slice_params`. Valid if this + control is of type ``V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS``. + * - struct :c:type:`v4l2_ctrl_hevc_scaling_matrix` * + - ``p_hevc_scaling_matrix`` + - A pointer to a struct :c:type:`v4l2_ctrl_hevc_scaling_matrix`. Valid if this + control is of type ``V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX``. + * - struct :c:type:`v4l2_ctrl_hevc_decode_params` * + - ``p_hevc_decode_params`` + - A pointer to a struct :c:type:`v4l2_ctrl_hevc_decode_params`. Valid if this + control is of type ``V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS``. * - void * - ``ptr`` - A pointer to a compound type which can be an N-dimensional array diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h deleted file mode 100644 index c89029b3c5da..000000000000 --- a/include/media/hevc-ctrls.h +++ /dev/null @@ -1,474 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * These are the HEVC state controls for use with stateless HEVC - * codec drivers. - * - * It turns out that these structs are not stable yet and will undergo - * more changes. So keep them private until they are stable and ready to - * become part of the official public API. - */ - -#ifndef _HEVC_CTRLS_H_ -#define _HEVC_CTRLS_H_ - -#include - -#define V4L2_CID_STATELESS_HEVC_SPS (V4L2_CID_CODEC_BASE + 1008) -#define V4L2_CID_STATELESS_HEVC_PPS (V4L2_CID_CODEC_BASE + 1009) -#define V4L2_CID_STATELESS_HEVC_SLICE_PARAMS (V4L2_CID_CODEC_BASE + 1010) -#define V4L2_CID_STATELESS_HEVC_SCALING_MATRIX (V4L2_CID_CODEC_BASE + 1011) -#define V4L2_CID_STATELESS_HEVC_DECODE_PARAMS (V4L2_CID_CODEC_BASE + 1012) -#define V4L2_CID_STATELESS_HEVC_DECODE_MODE (V4L2_CID_CODEC_BASE + 1015) -#define V4L2_CID_STATELESS_HEVC_START_CODE (V4L2_CID_CODEC_BASE + 1016) -#define V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS (V4L2_CID_CODEC_BASE + 1017) - -enum v4l2_stateless_hevc_decode_mode { - V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED, - V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED, -}; - -enum v4l2_stateless_hevc_start_code { - V4L2_STATELESS_HEVC_START_CODE_NONE, - V4L2_STATELESS_HEVC_START_CODE_ANNEX_B, -}; - -#define V4L2_HEVC_SLICE_TYPE_B 0 -#define V4L2_HEVC_SLICE_TYPE_P 1 -#define V4L2_HEVC_SLICE_TYPE_I 2 - -#define V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE (1ULL << 0) -#define V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED (1ULL << 1) -#define V4L2_HEVC_SPS_FLAG_AMP_ENABLED (1ULL << 2) -#define V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET (1ULL << 3) -#define V4L2_HEVC_SPS_FLAG_PCM_ENABLED (1ULL << 4) -#define V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED (1ULL << 5) -#define V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT (1ULL << 6) -#define V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED (1ULL << 7) -#define V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED (1ULL << 8) - -/** - * struct v4l2_ctrl_hevc_sps - ITU-T Rec. H.265: Sequence parameter set - * - * @video_parameter_set_id: specifies the value of the - * vps_video_parameter_set_id of the active VPS - * @seq_parameter_set_id: provides an identifier for the SPS for - * reference by other syntax elements - * @pic_width_in_luma_samples: specifies the width of each decoded picture - * in units of luma samples - * @pic_height_in_luma_samples: specifies the height of each decoded picture - * in units of luma samples - * @bit_depth_luma_minus8: this value plus 8 specifies the bit depth of the - * samples of the luma array - * @bit_depth_chroma_minus8: this value plus 8 specifies the bit depth of the - * samples of the chroma arrays - * @log2_max_pic_order_cnt_lsb_minus4: this value plus 4 specifies the value - * of the variable MaxPicOrderCntLsb - * @sps_max_dec_pic_buffering_minus1: this value plus 1 specifies the maximum - * required size of the decoded picture - * buffer for the codec video sequence - * @sps_max_num_reorder_pics: indicates the maximum allowed number of pictures - * @sps_max_latency_increase_plus1: not equal to 0 is used to compute the - * value of SpsMaxLatencyPictures array - * @log2_min_luma_coding_block_size_minus3: this value plus 3 specifies the - * minimum luma coding block size - * @log2_diff_max_min_luma_coding_block_size: specifies the difference between - * the maximum and minimum luma - * coding block size - * @log2_min_luma_transform_block_size_minus2: this value plus 2 specifies the - * minimum luma transform block size - * @log2_diff_max_min_luma_transform_block_size: specifies the difference between - * the maximum and minimum luma - * transform block size - * @max_transform_hierarchy_depth_inter: specifies the maximum hierarchy - * depth for transform units of - * coding units coded in inter - * prediction mode - * @max_transform_hierarchy_depth_intra: specifies the maximum hierarchy - * depth for transform units of - * coding units coded in intra - * prediction mode - * @pcm_sample_bit_depth_luma_minus1: this value plus 1 specifies the number of - * bits used to represent each of PCM sample - * values of the luma component - * @pcm_sample_bit_depth_chroma_minus1: this value plus 1 specifies the number - * of bits used to represent each of PCM - * sample values of the chroma components - * @log2_min_pcm_luma_coding_block_size_minus3: this value plus 3 specifies the - * minimum size of coding blocks - * @log2_diff_max_min_pcm_luma_coding_block_size: specifies the difference between - * the maximum and minimum size of - * coding blocks - * @num_short_term_ref_pic_sets: specifies the number of st_ref_pic_set() - * syntax structures included in the SPS - * @num_long_term_ref_pics_sps: specifies the number of candidate long-term - * reference pictures that are specified in the SPS - * @chroma_format_idc: specifies the chroma sampling - * @sps_max_sub_layers_minus1: this value plus 1 specifies the maximum number - * of temporal sub-layers - * @reserved: padding field. Should be zeroed by applications. - * @flags: see V4L2_HEVC_SPS_FLAG_{} - */ -struct v4l2_ctrl_hevc_sps { - __u8 video_parameter_set_id; - __u8 seq_parameter_set_id; - __u16 pic_width_in_luma_samples; - __u16 pic_height_in_luma_samples; - __u8 bit_depth_luma_minus8; - __u8 bit_depth_chroma_minus8; - __u8 log2_max_pic_order_cnt_lsb_minus4; - __u8 sps_max_dec_pic_buffering_minus1; - __u8 sps_max_num_reorder_pics; - __u8 sps_max_latency_increase_plus1; - __u8 log2_min_luma_coding_block_size_minus3; - __u8 log2_diff_max_min_luma_coding_block_size; - __u8 log2_min_luma_transform_block_size_minus2; - __u8 log2_diff_max_min_luma_transform_block_size; - __u8 max_transform_hierarchy_depth_inter; - __u8 max_transform_hierarchy_depth_intra; - __u8 pcm_sample_bit_depth_luma_minus1; - __u8 pcm_sample_bit_depth_chroma_minus1; - __u8 log2_min_pcm_luma_coding_block_size_minus3; - __u8 log2_diff_max_min_pcm_luma_coding_block_size; - __u8 num_short_term_ref_pic_sets; - __u8 num_long_term_ref_pics_sps; - __u8 chroma_format_idc; - __u8 sps_max_sub_layers_minus1; - - __u8 reserved[6]; - __u64 flags; -}; - -#define V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED (1ULL << 0) -#define V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT (1ULL << 1) -#define V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED (1ULL << 2) -#define V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT (1ULL << 3) -#define V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED (1ULL << 4) -#define V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED (1ULL << 5) -#define V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED (1ULL << 6) -#define V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT (1ULL << 7) -#define V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED (1ULL << 8) -#define V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED (1ULL << 9) -#define V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED (1ULL << 10) -#define V4L2_HEVC_PPS_FLAG_TILES_ENABLED (1ULL << 11) -#define V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED (1ULL << 12) -#define V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED (1ULL << 13) -#define V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 14) -#define V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED (1ULL << 15) -#define V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER (1ULL << 16) -#define V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT (1ULL << 17) -#define V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT (1ULL << 18) -#define V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT (1ULL << 19) -#define V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING (1ULL << 20) - -/** - * struct v4l2_ctrl_hevc_pps - ITU-T Rec. H.265: Picture parameter set - * - * @pic_parameter_set_id: identifies the PPS for reference by other - * syntax elements - * @num_extra_slice_header_bits: specifies the number of extra slice header - * bits that are present in the slice header RBSP - * for coded pictures referring to the PPS. - * @num_ref_idx_l0_default_active_minus1: this value plus 1 specifies the inferred - * value of num_ref_idx_l0_active_minus1 - * @num_ref_idx_l1_default_active_minus1: this value plus 1 specifies the inferred - * value of num_ref_idx_l1_active_minus1 - * @init_qp_minus26: this value plus 26 specifies the initial value of SliceQp Y - * for each slice referring to the PPS - * @diff_cu_qp_delta_depth: specifies the difference between the luma coding - * tree block size and the minimum luma coding block - * size of coding units that convey cu_qp_delta_abs - * and cu_qp_delta_sign_flag - * @pps_cb_qp_offset: specify the offsets to the luma quantization parameter Cb - * @pps_cr_qp_offset: specify the offsets to the luma quantization parameter Cr - * @num_tile_columns_minus1: this value plus 1 specifies the number of tile columns - * partitioning the picture - * @num_tile_rows_minus1: this value plus 1 specifies the number of tile rows - * partitioning the picture - * @column_width_minus1: this value plus 1 specifies the width of each tile column - * in units of coding tree blocks - * @row_height_minus1: this value plus 1 specifies the height of each tile row in - * units of coding tree blocks - * @pps_beta_offset_div2: specify the default deblocking parameter offsets for - * beta divided by 2 - * @pps_tc_offset_div2: specify the default deblocking parameter offsets for tC - * divided by 2 - * @log2_parallel_merge_level_minus2: this value plus 2 specifies the value of - * the variable Log2ParMrgLevel - * @reserved: padding field. Should be zeroed by applications. - * @flags: see V4L2_HEVC_PPS_FLAG_{} - */ -struct v4l2_ctrl_hevc_pps { - __u8 pic_parameter_set_id; - __u8 num_extra_slice_header_bits; - __u8 num_ref_idx_l0_default_active_minus1; - __u8 num_ref_idx_l1_default_active_minus1; - __s8 init_qp_minus26; - __u8 diff_cu_qp_delta_depth; - __s8 pps_cb_qp_offset; - __s8 pps_cr_qp_offset; - __u8 num_tile_columns_minus1; - __u8 num_tile_rows_minus1; - __u8 column_width_minus1[20]; - __u8 row_height_minus1[22]; - __s8 pps_beta_offset_div2; - __s8 pps_tc_offset_div2; - __u8 log2_parallel_merge_level_minus2; - __u8 reserved; - __u64 flags; -}; - -#define V4L2_HEVC_DPB_ENTRY_LONG_TERM_REFERENCE 0x01 - -#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME 0 -#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_FIELD 1 -#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_FIELD 2 -#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM 3 -#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP 4 -#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM_TOP 5 -#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP_BOTTOM 6 -#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME_DOUBLING 7 -#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME_TRIPLING 8 -#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_PREVIOUS_BOTTOM 9 -#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_PREVIOUS_TOP 10 -#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_NEXT_BOTTOM 11 -#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_NEXT_TOP 12 - -#define V4L2_HEVC_DPB_ENTRIES_NUM_MAX 16 - -/** - * struct v4l2_hevc_dpb_entry - HEVC decoded picture buffer entry - * - * @timestamp: timestamp of the V4L2 capture buffer to use as reference. - * @flags: long term flag for the reference frame - * @field_pic: whether the reference is a field picture or a frame. - * @reserved: padding field. Should be zeroed by applications. - * @pic_order_cnt_val: the picture order count of the reference. - */ -struct v4l2_hevc_dpb_entry { - __u64 timestamp; - __u8 flags; - __u8 field_pic; - __u16 reserved; - __s32 pic_order_cnt_val; -}; - -/** - * struct v4l2_hevc_pred_weight_table - HEVC weighted prediction parameters - * - * @delta_luma_weight_l0: the difference of the weighting factor applied - * to the luma prediction value for list 0 - * @luma_offset_l0: the additive offset applied to the luma prediction value - * for list 0 - * @delta_chroma_weight_l0: the difference of the weighting factor applied - * to the chroma prediction values for list 0 - * @chroma_offset_l0: the difference of the additive offset applied to - * the chroma prediction values for list 0 - * @delta_luma_weight_l1: the difference of the weighting factor applied - * to the luma prediction value for list 1 - * @luma_offset_l1: the additive offset applied to the luma prediction value - * for list 1 - * @delta_chroma_weight_l1: the difference of the weighting factor applied - * to the chroma prediction values for list 1 - * @chroma_offset_l1: the difference of the additive offset applied to - * the chroma prediction values for list 1 - * @luma_log2_weight_denom: the base 2 logarithm of the denominator for - * all luma weighting factors - * @delta_chroma_log2_weight_denom: the difference of the base 2 logarithm - * of the denominator for all chroma - * weighting factors - */ -struct v4l2_hevc_pred_weight_table { - __s8 delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __s8 luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __s8 delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; - __s8 chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; - - __s8 delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __s8 luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __s8 delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; - __s8 chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; - - __u8 luma_log2_weight_denom; - __s8 delta_chroma_log2_weight_denom; -}; - -#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA (1ULL << 0) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA (1ULL << 1) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED (1ULL << 2) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO (1ULL << 3) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT (1ULL << 4) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0 (1ULL << 5) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV (1ULL << 6) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED (1ULL << 7) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 8) -#define V4L2_HEVC_SLICE_PARAMS_FLAG_DEPENDENT_SLICE_SEGMENT (1ULL << 9) - -/** - * struct v4l2_ctrl_hevc_slice_params - HEVC slice parameters - * - * This control is a dynamically sized 1-dimensional array, - * V4L2_CTRL_FLAG_DYNAMIC_ARRAY flag must be set when using it. - * - * @bit_size: size (in bits) of the current slice data - * @data_byte_offset: offset (in bytes) to the video data in the current slice data - * @num_entry_point_offsets: specifies the number of entry point offset syntax - * elements in the slice header. - * @nal_unit_type: specifies the coding type of the slice (B, P or I) - * @nuh_temporal_id_plus1: minus 1 specifies a temporal identifier for the NAL unit - * @slice_type: see V4L2_HEVC_SLICE_TYPE_{} - * @colour_plane_id: specifies the colour plane associated with the current slice - * @slice_pic_order_cnt: specifies the picture order count - * @num_ref_idx_l0_active_minus1: this value plus 1 specifies the maximum reference - * index for reference picture list 0 that may be - * used to decode the slice - * @num_ref_idx_l1_active_minus1: this value plus 1 specifies the maximum reference - * index for reference picture list 1 that may be - * used to decode the slice - * @collocated_ref_idx: specifies the reference index of the collocated picture used - * for temporal motion vector prediction - * @five_minus_max_num_merge_cand: specifies the maximum number of merging - * motion vector prediction candidates supported in - * the slice subtracted from 5 - * @slice_qp_delta: specifies the initial value of QpY to be used for the coding - * blocks in the slice - * @slice_cb_qp_offset: specifies a difference to be added to the value of pps_cb_qp_offset - * @slice_cr_qp_offset: specifies a difference to be added to the value of pps_cr_qp_offset - * @slice_act_y_qp_offset: screen content extension parameters - * @slice_act_cb_qp_offset: screen content extension parameters - * @slice_act_cr_qp_offset: screen content extension parameters - * @slice_beta_offset_div2: specify the deblocking parameter offsets for beta divided by 2 - * @slice_tc_offset_div2: specify the deblocking parameter offsets for tC divided by 2 - * @pic_struct: indicates whether a picture should be displayed as a frame or as one or - * more fields - * @reserved0: padding field. Should be zeroed by applications. - * @slice_segment_addr: specifies the address of the first coding tree block in - * the slice segment - * @ref_idx_l0: the list of L0 reference elements as indices in the DPB - * @ref_idx_l1: the list of L1 reference elements as indices in the DPB - * @short_term_ref_pic_set_size: specifies the size of short-term reference - * pictures included in the SPS - * @long_term_ref_pic_set_size: specifies the size of long-term reference - * picture include in the SPS - * @pred_weight_table: the prediction weight coefficients for inter-picture - * prediction - * @reserved1: padding field. Should be zeroed by applications. - * @flags: see V4L2_HEVC_SLICE_PARAMS_FLAG_{} - */ -struct v4l2_ctrl_hevc_slice_params { - __u32 bit_size; - __u32 data_byte_offset; - __u32 num_entry_point_offsets; - /* ISO/IEC 23008-2, ITU-T Rec. H.265: NAL unit header */ - __u8 nal_unit_type; - __u8 nuh_temporal_id_plus1; - - /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ - __u8 slice_type; - __u8 colour_plane_id; - __s32 slice_pic_order_cnt; - __u8 num_ref_idx_l0_active_minus1; - __u8 num_ref_idx_l1_active_minus1; - __u8 collocated_ref_idx; - __u8 five_minus_max_num_merge_cand; - __s8 slice_qp_delta; - __s8 slice_cb_qp_offset; - __s8 slice_cr_qp_offset; - __s8 slice_act_y_qp_offset; - __s8 slice_act_cb_qp_offset; - __s8 slice_act_cr_qp_offset; - __s8 slice_beta_offset_div2; - __s8 slice_tc_offset_div2; - - /* ISO/IEC 23008-2, ITU-T Rec. H.265: Picture timing SEI message */ - __u8 pic_struct; - - __u8 reserved0[3]; - /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ - __u32 slice_segment_addr; - __u8 ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u16 short_term_ref_pic_set_size; - __u16 long_term_ref_pic_set_size; - - /* ISO/IEC 23008-2, ITU-T Rec. H.265: Weighted prediction parameter */ - struct v4l2_hevc_pred_weight_table pred_weight_table; - - __u8 reserved1[2]; - __u64 flags; -}; - -#define V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC 0x1 -#define V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC 0x2 -#define V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR 0x4 - -/** - * struct v4l2_ctrl_hevc_decode_params - HEVC decode parameters - * - * @pic_order_cnt_val: picture order count - * @short_term_ref_pic_set_size: specifies the size of short-term reference - * pictures set included in the SPS of the first slice - * @long_term_ref_pic_set_size: specifies the size of long-term reference - * pictures set include in the SPS of the first slice - * @num_active_dpb_entries: the number of entries in dpb - * @num_poc_st_curr_before: the number of reference pictures in the short-term - * set that come before the current frame - * @num_poc_st_curr_after: the number of reference pictures in the short-term - * set that come after the current frame - * @num_poc_lt_curr: the number of reference pictures in the long-term set - * @poc_st_curr_before: provides the index of the short term before references - * in DPB array - * @poc_st_curr_after: provides the index of the short term after references - * in DPB array - * @poc_lt_curr: provides the index of the long term references in DPB array - * @reserved: padding field. Should be zeroed by applications. - * @dpb: the decoded picture buffer, for meta-data about reference frames - * @flags: see V4L2_HEVC_DECODE_PARAM_FLAG_{} - */ -struct v4l2_ctrl_hevc_decode_params { - __s32 pic_order_cnt_val; - __u16 short_term_ref_pic_set_size; - __u16 long_term_ref_pic_set_size; - __u8 num_active_dpb_entries; - __u8 num_poc_st_curr_before; - __u8 num_poc_st_curr_after; - __u8 num_poc_lt_curr; - __u8 poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 reserved[4]; - struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u64 flags; -}; - -/** - * struct v4l2_ctrl_hevc_scaling_matrix - HEVC scaling lists parameters - * - * @scaling_list_4x4: scaling list is used for the scaling process for - * transform coefficients. The values on each scaling - * list are expected in raster scan order - * @scaling_list_8x8: scaling list is used for the scaling process for - * transform coefficients. The values on each scaling - * list are expected in raster scan order - * @scaling_list_16x16: scaling list is used for the scaling process for - * transform coefficients. The values on each scaling - * list are expected in raster scan order - * @scaling_list_32x32: scaling list is used for the scaling process for - * transform coefficients. The values on each scaling - * list are expected in raster scan order - * @scaling_list_dc_coef_16x16: scaling list is used for the scaling process - * for transform coefficients. The values on each - * scaling list are expected in raster scan order. - * @scaling_list_dc_coef_32x32: scaling list is used for the scaling process - * for transform coefficients. The values on each - * scaling list are expected in raster scan order. - */ -struct v4l2_ctrl_hevc_scaling_matrix { - __u8 scaling_list_4x4[6][16]; - __u8 scaling_list_8x8[6][64]; - __u8 scaling_list_16x16[6][64]; - __u8 scaling_list_32x32[2][64]; - __u8 scaling_list_dc_coef_16x16[6]; - __u8 scaling_list_dc_coef_32x32[2]; -}; - -#endif diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index f4105de8a8d2..00828a4f9404 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -13,12 +13,6 @@ #include #include -/* - * Include the stateless codec compound control definitions. - * This will move to the public headers once this API is fully stable. - */ -#include - /* forward references */ struct file; struct poll_table_struct; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index dfff69ed88f7..5f46bf4a570c 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1997,6 +1997,465 @@ struct v4l2_ctrl_mpeg2_quantisation { __u8 chroma_non_intra_quantiser_matrix[64]; }; +#define V4L2_CID_STATELESS_HEVC_SPS (V4L2_CID_CODEC_STATELESS_BASE + 400) +#define V4L2_CID_STATELESS_HEVC_PPS (V4L2_CID_CODEC_STATELESS_BASE + 401) +#define V4L2_CID_STATELESS_HEVC_SLICE_PARAMS (V4L2_CID_CODEC_STATELESS_BASE + 402) +#define V4L2_CID_STATELESS_HEVC_SCALING_MATRIX (V4L2_CID_CODEC_STATELESS_BASE + 403) +#define V4L2_CID_STATELESS_HEVC_DECODE_PARAMS (V4L2_CID_CODEC_STATELESS_BASE + 404) +#define V4L2_CID_STATELESS_HEVC_DECODE_MODE (V4L2_CID_CODEC_STATELESS_BASE + 405) +#define V4L2_CID_STATELESS_HEVC_START_CODE (V4L2_CID_CODEC_STATELESS_BASE + 406) +#define V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS (V4L2_CID_CODEC_STATELESS_BASE + 407) + +enum v4l2_stateless_hevc_decode_mode { + V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED, + V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED, +}; + +enum v4l2_stateless_hevc_start_code { + V4L2_STATELESS_HEVC_START_CODE_NONE, + V4L2_STATELESS_HEVC_START_CODE_ANNEX_B, +}; + +#define V4L2_HEVC_SLICE_TYPE_B 0 +#define V4L2_HEVC_SLICE_TYPE_P 1 +#define V4L2_HEVC_SLICE_TYPE_I 2 + +#define V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE (1ULL << 0) +#define V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED (1ULL << 1) +#define V4L2_HEVC_SPS_FLAG_AMP_ENABLED (1ULL << 2) +#define V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET (1ULL << 3) +#define V4L2_HEVC_SPS_FLAG_PCM_ENABLED (1ULL << 4) +#define V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED (1ULL << 5) +#define V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT (1ULL << 6) +#define V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED (1ULL << 7) +#define V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED (1ULL << 8) + +/** + * struct v4l2_ctrl_hevc_sps - ITU-T Rec. H.265: Sequence parameter set + * + * @video_parameter_set_id: specifies the value of the + * vps_video_parameter_set_id of the active VPS + * @seq_parameter_set_id: provides an identifier for the SPS for + * reference by other syntax elements + * @pic_width_in_luma_samples: specifies the width of each decoded picture + * in units of luma samples + * @pic_height_in_luma_samples: specifies the height of each decoded picture + * in units of luma samples + * @bit_depth_luma_minus8: this value plus 8specifies the bit depth of the + * samples of the luma array + * @bit_depth_chroma_minus8: this value plus 8 specifies the bit depth of the + * samples of the chroma arrays + * @log2_max_pic_order_cnt_lsb_minus4: this value plus 4 specifies the value of + * the variable MaxPicOrderCntLsb + * @sps_max_dec_pic_buffering_minus1: this value plus 1 specifies the maximum + * required size of the decoded picture + * buffer for the codec video sequence + * @sps_max_num_reorder_pics: indicates the maximum allowed number of pictures + * @sps_max_latency_increase_plus1: not equal to 0 is used to compute the + * value of SpsMaxLatencyPictures array + * @log2_min_luma_coding_block_size_minus3: plus 3 specifies the minimum + * luma coding block size + * @log2_diff_max_min_luma_coding_block_size: specifies the difference between + * the maximum and minimum luma + * coding block size + * @log2_min_luma_transform_block_size_minus2: plus 2 specifies the minimum luma + * transform block size + * @log2_diff_max_min_luma_transform_block_size: specifies the difference between + * the maximum and minimum luma + * transform block size + * @max_transform_hierarchy_depth_inter: specifies the maximum hierarchy + * depth for transform units of + * coding units coded in inter + * prediction mode + * @max_transform_hierarchy_depth_intra: specifies the maximum hierarchy + * depth for transform units of + * coding units coded in intra + * prediction mode + * @pcm_sample_bit_depth_luma_minus1: this value plus 1 specifies the number of + * bits used to represent each of PCM sample + * values of the luma component + * @pcm_sample_bit_depth_chroma_minus1: this value plus 1 specifies the number + * of bits used to represent each of PCM + * sample values of the chroma components + * @log2_min_pcm_luma_coding_block_size_minus3: this value plus 3 specifies the + * minimum size of coding blocks + * @log2_diff_max_min_pcm_luma_coding_block_size: specifies the difference between + * the maximum and minimum size of + * coding blocks + * @num_short_term_ref_pic_sets: specifies the number of st_ref_pic_set() + * syntax structures included in the SPS + * @num_long_term_ref_pics_sps: specifies the number of candidate long-term + * reference pictures that are specified in the SPS + * @chroma_format_idc: specifies the chroma sampling + * @sps_max_sub_layers_minus1: this value plus 1 specifies the maximum number + * of temporal sub-layers + * @reserved: padding field. Should be zeroed by applications. + * @flags: see V4L2_HEVC_SPS_FLAG_{} + */ +struct v4l2_ctrl_hevc_sps { + __u8 video_parameter_set_id; + __u8 seq_parameter_set_id; + __u16 pic_width_in_luma_samples; + __u16 pic_height_in_luma_samples; + __u8 bit_depth_luma_minus8; + __u8 bit_depth_chroma_minus8; + __u8 log2_max_pic_order_cnt_lsb_minus4; + __u8 sps_max_dec_pic_buffering_minus1; + __u8 sps_max_num_reorder_pics; + __u8 sps_max_latency_increase_plus1; + __u8 log2_min_luma_coding_block_size_minus3; + __u8 log2_diff_max_min_luma_coding_block_size; + __u8 log2_min_luma_transform_block_size_minus2; + __u8 log2_diff_max_min_luma_transform_block_size; + __u8 max_transform_hierarchy_depth_inter; + __u8 max_transform_hierarchy_depth_intra; + __u8 pcm_sample_bit_depth_luma_minus1; + __u8 pcm_sample_bit_depth_chroma_minus1; + __u8 log2_min_pcm_luma_coding_block_size_minus3; + __u8 log2_diff_max_min_pcm_luma_coding_block_size; + __u8 num_short_term_ref_pic_sets; + __u8 num_long_term_ref_pics_sps; + __u8 chroma_format_idc; + __u8 sps_max_sub_layers_minus1; + + __u8 reserved[6]; + __u64 flags; +}; + +#define V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED (1ULL << 0) +#define V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT (1ULL << 1) +#define V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED (1ULL << 2) +#define V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT (1ULL << 3) +#define V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED (1ULL << 4) +#define V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED (1ULL << 5) +#define V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED (1ULL << 6) +#define V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT (1ULL << 7) +#define V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED (1ULL << 8) +#define V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED (1ULL << 9) +#define V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED (1ULL << 10) +#define V4L2_HEVC_PPS_FLAG_TILES_ENABLED (1ULL << 11) +#define V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED (1ULL << 12) +#define V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED (1ULL << 13) +#define V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 14) +#define V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED (1ULL << 15) +#define V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER (1ULL << 16) +#define V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT (1ULL << 17) +#define V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT (1ULL << 18) +#define V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT (1ULL << 19) +#define V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING (1ULL << 20) + +/** + * struct v4l2_ctrl_hevc_pps - ITU-T Rec. H.265: Picture parameter set + * + * @pic_parameter_set_id: identifies the PPS for reference by other + * syntax elements + * @num_extra_slice_header_bits: specifies the number of extra slice header + * bits that are present in the slice header RBSP + * for coded pictures referring to the PPS. + * @num_ref_idx_l0_default_active_minus1: this value plus 1 specifies the + * inferred value of num_ref_idx_l0_active_minus1 + * @num_ref_idx_l1_default_active_minus1: this value plus 1 specifies the + * inferred value of num_ref_idx_l1_active_minus1 + * @init_qp_minus26: this value plus 26 specifies the initial value of SliceQp Y for + * each slice referring to the PPS + * @diff_cu_qp_delta_depth: specifies the difference between the luma coding + * tree block size and the minimum luma coding block + * size of coding units that convey cu_qp_delta_abs + * and cu_qp_delta_sign_flag + * @pps_cb_qp_offset: specify the offsets to the luma quantization parameter Cb + * @pps_cr_qp_offset: specify the offsets to the luma quantization parameter Cr + * @num_tile_columns_minus1: this value plus 1 specifies the number of tile columns + * partitioning the picture + * @num_tile_rows_minus1: this value plus 1 specifies the number of tile rows partitioning + * the picture + * @column_width_minus1: this value plus 1 specifies the width of the each tile column in + * units of coding tree blocks + * @row_height_minus1: this value plus 1 specifies the height of the each tile row in + * units of coding tree blocks + * @pps_beta_offset_div2: specify the default deblocking parameter offsets for + * beta divided by 2 + * @pps_tc_offset_div2: specify the default deblocking parameter offsets for tC + * divided by 2 + * @log2_parallel_merge_level_minus2: this value plus 2 specifies the value of + * the variable Log2ParMrgLevel + * @reserved: padding field. Should be zeroed by applications. + * @flags: see V4L2_HEVC_PPS_FLAG_{} + */ +struct v4l2_ctrl_hevc_pps { + __u8 pic_parameter_set_id; + __u8 num_extra_slice_header_bits; + __u8 num_ref_idx_l0_default_active_minus1; + __u8 num_ref_idx_l1_default_active_minus1; + __s8 init_qp_minus26; + __u8 diff_cu_qp_delta_depth; + __s8 pps_cb_qp_offset; + __s8 pps_cr_qp_offset; + __u8 num_tile_columns_minus1; + __u8 num_tile_rows_minus1; + __u8 column_width_minus1[20]; + __u8 row_height_minus1[22]; + __s8 pps_beta_offset_div2; + __s8 pps_tc_offset_div2; + __u8 log2_parallel_merge_level_minus2; + __u8 reserved; + __u64 flags; +}; + +#define V4L2_HEVC_DPB_ENTRY_LONG_TERM_REFERENCE 0x01 + +#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME 0 +#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_FIELD 1 +#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_FIELD 2 +#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM 3 +#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP 4 +#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_BOTTOM_TOP 5 +#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_TOP_BOTTOM 6 +#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME_DOUBLING 7 +#define V4L2_HEVC_SEI_PIC_STRUCT_FRAME_TRIPLING 8 +#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_PREVIOUS_BOTTOM 9 +#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_PREVIOUS_TOP 10 +#define V4L2_HEVC_SEI_PIC_STRUCT_TOP_PAIRED_NEXT_BOTTOM 11 +#define V4L2_HEVC_SEI_PIC_STRUCT_BOTTOM_PAIRED_NEXT_TOP 12 + +#define V4L2_HEVC_DPB_ENTRIES_NUM_MAX 16 + +/** + * struct v4l2_hevc_dpb_entry - HEVC decoded picture buffer entry + * + * @timestamp: timestamp of the V4L2 capture buffer to use as reference. + * @flags: long term flag for the reference frame + * @field_pic: whether the reference is a field picture or a frame. + * @reserved: padding field. Should be zeroed by applications. + * @pic_order_cnt_val: the picture order count of the current picture. + */ +struct v4l2_hevc_dpb_entry { + __u64 timestamp; + __u8 flags; + __u8 field_pic; + __u16 reserved; + __s32 pic_order_cnt_val; +}; + +/** + * struct v4l2_hevc_pred_weight_table - HEVC weighted prediction parameters + * + * @delta_luma_weight_l0: the difference of the weighting factor applied + * to the luma prediction value for list 0 + * @luma_offset_l0: the additive offset applied to the luma prediction value + * for list 0 + * @delta_chroma_weight_l0: the difference of the weighting factor applied + * to the chroma prediction values for list 0 + * @chroma_offset_l0: the difference of the additive offset applied to + * the chroma prediction values for list 0 + * @delta_luma_weight_l1: the difference of the weighting factor applied + * to the luma prediction value for list 1 + * @luma_offset_l1: the additive offset applied to the luma prediction value + * for list 1 + * @delta_chroma_weight_l1: the difference of the weighting factor applied + * to the chroma prediction values for list 1 + * @chroma_offset_l1: the difference of the additive offset applied to + * the chroma prediction values for list 1 + * @luma_log2_weight_denom: the base 2 logarithm of the denominator for + * all luma weighting factors + * @delta_chroma_log2_weight_denom: the difference of the base 2 logarithm + * of the denominator for all chroma + * weighting factors + */ +struct v4l2_hevc_pred_weight_table { + __s8 delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __s8 luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __s8 delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; + __s8 chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; + + __s8 delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __s8 luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __s8 delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; + __s8 chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]; + + __u8 luma_log2_weight_denom; + __s8 delta_chroma_log2_weight_denom; +}; + +#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA (1ULL << 0) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA (1ULL << 1) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED (1ULL << 2) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO (1ULL << 3) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT (1ULL << 4) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0 (1ULL << 5) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV (1ULL << 6) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED (1ULL << 7) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 8) +#define V4L2_HEVC_SLICE_PARAMS_FLAG_DEPENDENT_SLICE_SEGMENT (1ULL << 9) + +/** + * struct v4l2_ctrl_hevc_slice_params - HEVC slice parameters + * + * This control is a dynamically sized 1-dimensional array, + * V4L2_CTRL_FLAG_DYNAMIC_ARRAY flag must be set when using it. + * + * @bit_size: size (in bits) of the current slice data + * @data_byte_offset: offset (in bytes) to the video data in the current slice data + * @num_entry_point_offsets: specifies the number of entry point offset syntax + * elements in the slice header. + * @nal_unit_type: specifies the coding type of the slice (B, P or I) + * @nuh_temporal_id_plus1: minus 1 specifies a temporal identifier for the NAL unit + * @slice_type: see V4L2_HEVC_SLICE_TYPE_{} + * @colour_plane_id: specifies the colour plane associated with the current slice + * @slice_pic_order_cnt: specifies the picture order count + * @num_ref_idx_l0_active_minus1: this value plus 1 specifies the maximum + * reference index for reference picture list 0 + * that may be used to decode the slice + * @num_ref_idx_l1_active_minus1: this value plus 1 specifies the maximum + * reference index for reference picture list 1 + * that may be used to decode the slice + * @collocated_ref_idx: specifies the reference index of the collocated picture used + * for temporal motion vector prediction + * @five_minus_max_num_merge_cand: specifies the maximum number of merging + * motion vector prediction candidates supported in + * the slice subtracted from 5 + * @slice_qp_delta: specifies the initial value of QpY to be used for the coding + * blocks in the slice + * @slice_cb_qp_offset: specifies a difference to be added to the value of pps_cb_qp_offset + * @slice_cr_qp_offset: specifies a difference to be added to the value of pps_cr_qp_offset + * @slice_act_y_qp_offset: screen content extension parameters + * @slice_act_cb_qp_offset: screen content extension parameters + * @slice_act_cr_qp_offset: screen content extension parameters + * @slice_beta_offset_div2: specify the deblocking parameter offsets for beta divided by 2 + * @slice_tc_offset_div2: specify the deblocking parameter offsets for tC divided by 2 + * @pic_struct: indicates whether a picture should be displayed as a frame or as one or + * more fields + * @reserved0: padding field. Should be zeroed by applications. + * @slice_segment_addr: specifies the address of the first coding tree block in + * the slice segment + * @ref_idx_l0: the list of L0 reference elements as indices in the DPB + * @ref_idx_l1: the list of L1 reference elements as indices in the DPB + * @short_term_ref_pic_set_size: specifies the size of short-term reference + * pictures set included in the SPS + * @long_term_ref_pic_set_size: specifies the size of long-term reference + * pictures set include in the SPS + * @pred_weight_table: the prediction weight coefficients for inter-picture + * prediction + * @reserved1: padding field. Should be zeroed by applications. + * @flags: see V4L2_HEVC_SLICE_PARAMS_FLAG_{} + */ +struct v4l2_ctrl_hevc_slice_params { + __u32 bit_size; + __u32 data_byte_offset; + __u32 num_entry_point_offsets; + + /* ISO/IEC 23008-2, ITU-T Rec. H.265: NAL unit header */ + __u8 nal_unit_type; + __u8 nuh_temporal_id_plus1; + + /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ + __u8 slice_type; + __u8 colour_plane_id; + __s32 slice_pic_order_cnt; + __u8 num_ref_idx_l0_active_minus1; + __u8 num_ref_idx_l1_active_minus1; + __u8 collocated_ref_idx; + __u8 five_minus_max_num_merge_cand; + __s8 slice_qp_delta; + __s8 slice_cb_qp_offset; + __s8 slice_cr_qp_offset; + __s8 slice_act_y_qp_offset; + __s8 slice_act_cb_qp_offset; + __s8 slice_act_cr_qp_offset; + __s8 slice_beta_offset_div2; + __s8 slice_tc_offset_div2; + + /* ISO/IEC 23008-2, ITU-T Rec. H.265: Picture timing SEI message */ + __u8 pic_struct; + + __u8 reserved0[3]; + /* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */ + __u32 slice_segment_addr; + __u8 ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u16 short_term_ref_pic_set_size; + __u16 long_term_ref_pic_set_size; + + /* ISO/IEC 23008-2, ITU-T Rec. H.265: Weighted prediction parameter */ + struct v4l2_hevc_pred_weight_table pred_weight_table; + + __u8 reserved1[2]; + __u64 flags; +}; + +#define V4L2_HEVC_DECODE_PARAM_FLAG_IRAP_PIC 0x1 +#define V4L2_HEVC_DECODE_PARAM_FLAG_IDR_PIC 0x2 +#define V4L2_HEVC_DECODE_PARAM_FLAG_NO_OUTPUT_OF_PRIOR 0x4 + +/** + * struct v4l2_ctrl_hevc_decode_params - HEVC decode parameters + * + * @pic_order_cnt_val: picture order count + * @short_term_ref_pic_set_size: specifies the size of short-term reference + * pictures set included in the SPS of the first slice + * @long_term_ref_pic_set_size: specifies the size of long-term reference + * pictures set include in the SPS of the first slice + * @num_active_dpb_entries: the number of entries in dpb + * @num_poc_st_curr_before: the number of reference pictures in the short-term + * set that come before the current frame + * @num_poc_st_curr_after: the number of reference pictures in the short-term + * set that come after the current frame + * @num_poc_lt_curr: the number of reference pictures in the long-term set + * @poc_st_curr_before: provides the index of the short term before references + * in DPB array + * @poc_st_curr_after: provides the index of the short term after references + * in DPB array + * @poc_lt_curr: provides the index of the long term references in DPB array + * @reserved: padding field. Should be zeroed by applications. + * @dpb: the decoded picture buffer, for meta-data about reference frames + * @flags: see V4L2_HEVC_DECODE_PARAM_FLAG_{} + */ +struct v4l2_ctrl_hevc_decode_params { + __s32 pic_order_cnt_val; + __u16 short_term_ref_pic_set_size; + __u16 long_term_ref_pic_set_size; + __u8 num_active_dpb_entries; + __u8 num_poc_st_curr_before; + __u8 num_poc_st_curr_after; + __u8 num_poc_lt_curr; + __u8 poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u8 reserved[4]; + struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; + __u64 flags; +}; + +/** + * struct v4l2_ctrl_hevc_scaling_matrix - HEVC scaling lists parameters + * + * @scaling_list_4x4: scaling list is used for the scaling process for + * transform coefficients. The values on each scaling + * list are expected in raster scan order + * @scaling_list_8x8: scaling list is used for the scaling process for + * transform coefficients. The values on each scaling + * list are expected in raster scan order + * @scaling_list_16x16: scaling list is used for the scaling process for + * transform coefficients. The values on each scaling + * list are expected in raster scan order + * @scaling_list_32x32: scaling list is used for the scaling process for + * transform coefficients. The values on each scaling + * list are expected in raster scan order + * @scaling_list_dc_coef_16x16: scaling list is used for the scaling process + * for transform coefficients. The values on each + * scaling list are expected in raster scan order. + * @scaling_list_dc_coef_32x32: scaling list is used for the scaling process + * for transform coefficients. The values on each + * scaling list are expected in raster scan order. + */ +struct v4l2_ctrl_hevc_scaling_matrix { + __u8 scaling_list_4x4[6][16]; + __u8 scaling_list_8x8[6][64]; + __u8 scaling_list_16x16[6][64]; + __u8 scaling_list_32x32[2][64]; + __u8 scaling_list_dc_coef_16x16[6]; + __u8 scaling_list_dc_coef_32x32[2]; +}; + #define V4L2_CID_COLORIMETRY_CLASS_BASE (V4L2_CTRL_CLASS_COLORIMETRY | 0x900) #define V4L2_CID_COLORIMETRY_CLASS (V4L2_CTRL_CLASS_COLORIMETRY | 1) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index cff2bb78b2cc..d6fac2344033 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1793,6 +1793,11 @@ struct v4l2_ext_control { struct v4l2_ctrl_mpeg2_quantisation __user *p_mpeg2_quantisation; struct v4l2_ctrl_vp9_compressed_hdr __user *p_vp9_compressed_hdr_probs; struct v4l2_ctrl_vp9_frame __user *p_vp9_frame; + struct v4l2_ctrl_hevc_sps __user *p_hevc_sps; + struct v4l2_ctrl_hevc_pps __user *p_hevc_pps; + struct v4l2_ctrl_hevc_slice_params __user *p_hevc_slice_params; + struct v4l2_ctrl_hevc_scaling_matrix __user *p_hevc_scaling_matrix; + struct v4l2_ctrl_hevc_decode_params __user *p_hevc_decode_params; void __user *ptr; }; } __attribute__ ((packed)); -- cgit v1.2.3 From ceefa81e6e69b020997205e5c30a42d43aa5ae63 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 15 Jul 2022 16:03:22 +0200 Subject: serial: remove VR41XX serial driver Commit d3164e2f3b0a ("MIPS: Remove VR41xx support") removed support for MIPS VR41xx platform, so remove exclusive drivers for this platform, too. Signed-off-by: Thomas Bogendoerfer Link: https://lore.kernel.org/r/20220715140322.135825-1-tsbogend@alpha.franken.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 17 - drivers/tty/serial/Makefile | 1 - drivers/tty/serial/vr41xx_siu.c | 932 --------------------------------------- include/uapi/linux/serial_core.h | 4 - 4 files changed, 954 deletions(-) delete mode 100644 drivers/tty/serial/vr41xx_siu.c (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 8a3ee1525d80..f92963a2226b 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -890,23 +890,6 @@ config SERIAL_TXX9_STDSERIAL bool "TX39XX/49XX SIO act as standard serial" depends on !SERIAL_8250 && SERIAL_TXX9 -config SERIAL_VR41XX - tristate "NEC VR4100 series Serial Interface Unit support" - depends on CPU_VR41XX - select SERIAL_CORE - help - If you have a NEC VR4100 series processor and you want to use - Serial Interface Unit(SIU) or Debug Serial Interface Unit(DSIU) - (not include VR4111/VR4121 DSIU), say Y. Otherwise, say N. - -config SERIAL_VR41XX_CONSOLE - bool "Enable NEC VR4100 series Serial Interface Unit console" - depends on SERIAL_VR41XX=y - select SERIAL_CORE_CONSOLE - help - If you have a NEC VR4100 series processor and you want to use - a console on a serial port, say Y. Otherwise, say N. - config SERIAL_JSM tristate "Digi International NEO and Classic PCI Support" depends on PCI diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 61cc8de95571..238a9557b487 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -51,7 +51,6 @@ obj-$(CONFIG_SERIAL_SCCNXP) += sccnxp.o obj-$(CONFIG_SERIAL_SC16IS7XX_CORE) += sc16is7xx.o obj-$(CONFIG_SERIAL_JSM) += jsm/ obj-$(CONFIG_SERIAL_TXX9) += serial_txx9.o -obj-$(CONFIG_SERIAL_VR41XX) += vr41xx_siu.o obj-$(CONFIG_SERIAL_ATMEL) += atmel_serial.o obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o obj-$(CONFIG_SERIAL_MSM) += msm_serial.o diff --git a/drivers/tty/serial/vr41xx_siu.c b/drivers/tty/serial/vr41xx_siu.c deleted file mode 100644 index 1ba689a81abd..000000000000 --- a/drivers/tty/serial/vr41xx_siu.c +++ /dev/null @@ -1,932 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Driver for NEC VR4100 series Serial Interface Unit. - * - * Copyright (C) 2004-2008 Yoichi Yuasa - * - * Based on drivers/serial/8250.c, by Russell King. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#define SIU_BAUD_BASE 1152000 -#define SIU_MAJOR 204 -#define SIU_MINOR_BASE 82 - -#define RX_MAX_COUNT 256 -#define TX_MAX_COUNT 15 - -#define SIUIRSEL 0x08 - #define TMICMODE 0x20 - #define TMICTX 0x10 - #define IRMSEL 0x0c - #define IRMSEL_HP 0x08 - #define IRMSEL_TEMIC 0x04 - #define IRMSEL_SHARP 0x00 - #define IRUSESEL 0x02 - #define SIRSEL 0x01 - -static struct uart_port siu_uart_ports[SIU_PORTS_MAX] = { - [0 ... SIU_PORTS_MAX-1] = { - .lock = __SPIN_LOCK_UNLOCKED(siu_uart_ports->lock), - .irq = 0, - }, -}; - -#ifdef CONFIG_SERIAL_VR41XX_CONSOLE -static uint8_t lsr_break_flag[SIU_PORTS_MAX]; -#endif - -#define siu_read(port, offset) readb((port)->membase + (offset)) -#define siu_write(port, offset, value) writeb((value), (port)->membase + (offset)) - -void vr41xx_select_siu_interface(siu_interface_t interface) -{ - struct uart_port *port; - unsigned long flags; - uint8_t irsel; - - port = &siu_uart_ports[0]; - - spin_lock_irqsave(&port->lock, flags); - - irsel = siu_read(port, SIUIRSEL); - if (interface == SIU_INTERFACE_IRDA) - irsel |= SIRSEL; - else - irsel &= ~SIRSEL; - siu_write(port, SIUIRSEL, irsel); - - spin_unlock_irqrestore(&port->lock, flags); -} -EXPORT_SYMBOL_GPL(vr41xx_select_siu_interface); - -void vr41xx_use_irda(irda_use_t use) -{ - struct uart_port *port; - unsigned long flags; - uint8_t irsel; - - port = &siu_uart_ports[0]; - - spin_lock_irqsave(&port->lock, flags); - - irsel = siu_read(port, SIUIRSEL); - if (use == FIR_USE_IRDA) - irsel |= IRUSESEL; - else - irsel &= ~IRUSESEL; - siu_write(port, SIUIRSEL, irsel); - - spin_unlock_irqrestore(&port->lock, flags); -} -EXPORT_SYMBOL_GPL(vr41xx_use_irda); - -void vr41xx_select_irda_module(irda_module_t module, irda_speed_t speed) -{ - struct uart_port *port; - unsigned long flags; - uint8_t irsel; - - port = &siu_uart_ports[0]; - - spin_lock_irqsave(&port->lock, flags); - - irsel = siu_read(port, SIUIRSEL); - irsel &= ~(IRMSEL | TMICTX | TMICMODE); - switch (module) { - case SHARP_IRDA: - irsel |= IRMSEL_SHARP; - break; - case TEMIC_IRDA: - irsel |= IRMSEL_TEMIC | TMICMODE; - if (speed == IRDA_TX_4MBPS) - irsel |= TMICTX; - break; - case HP_IRDA: - irsel |= IRMSEL_HP; - break; - default: - break; - } - siu_write(port, SIUIRSEL, irsel); - - spin_unlock_irqrestore(&port->lock, flags); -} -EXPORT_SYMBOL_GPL(vr41xx_select_irda_module); - -static inline void siu_clear_fifo(struct uart_port *port) -{ - siu_write(port, UART_FCR, UART_FCR_ENABLE_FIFO); - siu_write(port, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | - UART_FCR_CLEAR_XMIT); - siu_write(port, UART_FCR, 0); -} - -static inline unsigned long siu_port_size(struct uart_port *port) -{ - switch (port->type) { - case PORT_VR41XX_SIU: - return 11UL; - case PORT_VR41XX_DSIU: - return 8UL; - } - - return 0; -} - -static inline unsigned int siu_check_type(struct uart_port *port) -{ - if (port->line == 0) - return PORT_VR41XX_SIU; - if (port->line == 1 && port->irq) - return PORT_VR41XX_DSIU; - - return PORT_UNKNOWN; -} - -static inline const char *siu_type_name(struct uart_port *port) -{ - switch (port->type) { - case PORT_VR41XX_SIU: - return "SIU"; - case PORT_VR41XX_DSIU: - return "DSIU"; - } - - return NULL; -} - -static unsigned int siu_tx_empty(struct uart_port *port) -{ - uint8_t lsr; - - lsr = siu_read(port, UART_LSR); - if (lsr & UART_LSR_TEMT) - return TIOCSER_TEMT; - - return 0; -} - -static void siu_set_mctrl(struct uart_port *port, unsigned int mctrl) -{ - uint8_t mcr = 0; - - if (mctrl & TIOCM_DTR) - mcr |= UART_MCR_DTR; - if (mctrl & TIOCM_RTS) - mcr |= UART_MCR_RTS; - if (mctrl & TIOCM_OUT1) - mcr |= UART_MCR_OUT1; - if (mctrl & TIOCM_OUT2) - mcr |= UART_MCR_OUT2; - if (mctrl & TIOCM_LOOP) - mcr |= UART_MCR_LOOP; - - siu_write(port, UART_MCR, mcr); -} - -static unsigned int siu_get_mctrl(struct uart_port *port) -{ - uint8_t msr; - unsigned int mctrl = 0; - - msr = siu_read(port, UART_MSR); - if (msr & UART_MSR_DCD) - mctrl |= TIOCM_CAR; - if (msr & UART_MSR_RI) - mctrl |= TIOCM_RNG; - if (msr & UART_MSR_DSR) - mctrl |= TIOCM_DSR; - if (msr & UART_MSR_CTS) - mctrl |= TIOCM_CTS; - - return mctrl; -} - -static void siu_stop_tx(struct uart_port *port) -{ - unsigned long flags; - uint8_t ier; - - spin_lock_irqsave(&port->lock, flags); - - ier = siu_read(port, UART_IER); - ier &= ~UART_IER_THRI; - siu_write(port, UART_IER, ier); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static void siu_start_tx(struct uart_port *port) -{ - unsigned long flags; - uint8_t ier; - - spin_lock_irqsave(&port->lock, flags); - - ier = siu_read(port, UART_IER); - ier |= UART_IER_THRI; - siu_write(port, UART_IER, ier); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static void siu_stop_rx(struct uart_port *port) -{ - unsigned long flags; - uint8_t ier; - - spin_lock_irqsave(&port->lock, flags); - - ier = siu_read(port, UART_IER); - ier &= ~UART_IER_RLSI; - siu_write(port, UART_IER, ier); - - port->read_status_mask &= ~UART_LSR_DR; - - spin_unlock_irqrestore(&port->lock, flags); -} - -static void siu_enable_ms(struct uart_port *port) -{ - unsigned long flags; - uint8_t ier; - - spin_lock_irqsave(&port->lock, flags); - - ier = siu_read(port, UART_IER); - ier |= UART_IER_MSI; - siu_write(port, UART_IER, ier); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static void siu_break_ctl(struct uart_port *port, int ctl) -{ - unsigned long flags; - uint8_t lcr; - - spin_lock_irqsave(&port->lock, flags); - - lcr = siu_read(port, UART_LCR); - if (ctl == -1) - lcr |= UART_LCR_SBC; - else - lcr &= ~UART_LCR_SBC; - siu_write(port, UART_LCR, lcr); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static inline void receive_chars(struct uart_port *port, uint8_t *status) -{ - uint8_t lsr, ch; - char flag; - int max_count = RX_MAX_COUNT; - - lsr = *status; - - do { - ch = siu_read(port, UART_RX); - port->icount.rx++; - flag = TTY_NORMAL; - -#ifdef CONFIG_SERIAL_VR41XX_CONSOLE - lsr |= lsr_break_flag[port->line]; - lsr_break_flag[port->line] = 0; -#endif - if (unlikely(lsr & (UART_LSR_BI | UART_LSR_FE | - UART_LSR_PE | UART_LSR_OE))) { - if (lsr & UART_LSR_BI) { - lsr &= ~(UART_LSR_FE | UART_LSR_PE); - port->icount.brk++; - - if (uart_handle_break(port)) - goto ignore_char; - } - - if (lsr & UART_LSR_FE) - port->icount.frame++; - if (lsr & UART_LSR_PE) - port->icount.parity++; - if (lsr & UART_LSR_OE) - port->icount.overrun++; - - lsr &= port->read_status_mask; - if (lsr & UART_LSR_BI) - flag = TTY_BREAK; - if (lsr & UART_LSR_FE) - flag = TTY_FRAME; - if (lsr & UART_LSR_PE) - flag = TTY_PARITY; - } - - if (uart_handle_sysrq_char(port, ch)) - goto ignore_char; - - uart_insert_char(port, lsr, UART_LSR_OE, ch, flag); - - ignore_char: - lsr = siu_read(port, UART_LSR); - } while ((lsr & UART_LSR_DR) && (max_count-- > 0)); - - tty_flip_buffer_push(&port->state->port); - - *status = lsr; -} - -static inline void check_modem_status(struct uart_port *port) -{ - uint8_t msr; - - msr = siu_read(port, UART_MSR); - if ((msr & UART_MSR_ANY_DELTA) == 0) - return; - if (msr & UART_MSR_DDCD) - uart_handle_dcd_change(port, msr & UART_MSR_DCD); - if (msr & UART_MSR_TERI) - port->icount.rng++; - if (msr & UART_MSR_DDSR) - port->icount.dsr++; - if (msr & UART_MSR_DCTS) - uart_handle_cts_change(port, msr & UART_MSR_CTS); - - wake_up_interruptible(&port->state->port.delta_msr_wait); -} - -static inline void transmit_chars(struct uart_port *port) -{ - struct circ_buf *xmit; - int max_count = TX_MAX_COUNT; - - xmit = &port->state->xmit; - - if (port->x_char) { - siu_write(port, UART_TX, port->x_char); - port->icount.tx++; - port->x_char = 0; - return; - } - - if (uart_circ_empty(xmit) || uart_tx_stopped(port)) { - siu_stop_tx(port); - return; - } - - do { - siu_write(port, UART_TX, xmit->buf[xmit->tail]); - xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); - port->icount.tx++; - if (uart_circ_empty(xmit)) - break; - } while (max_count-- > 0); - - if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) - uart_write_wakeup(port); - - if (uart_circ_empty(xmit)) - siu_stop_tx(port); -} - -static irqreturn_t siu_interrupt(int irq, void *dev_id) -{ - struct uart_port *port; - uint8_t iir, lsr; - - port = (struct uart_port *)dev_id; - - iir = siu_read(port, UART_IIR); - if (iir & UART_IIR_NO_INT) - return IRQ_NONE; - - lsr = siu_read(port, UART_LSR); - if (lsr & UART_LSR_DR) - receive_chars(port, &lsr); - - check_modem_status(port); - - if (lsr & UART_LSR_THRE) - transmit_chars(port); - - return IRQ_HANDLED; -} - -static int siu_startup(struct uart_port *port) -{ - int retval; - - if (port->membase == NULL) - return -ENODEV; - - siu_clear_fifo(port); - - (void)siu_read(port, UART_LSR); - (void)siu_read(port, UART_RX); - (void)siu_read(port, UART_IIR); - (void)siu_read(port, UART_MSR); - - if (siu_read(port, UART_LSR) == 0xff) - return -ENODEV; - - retval = request_irq(port->irq, siu_interrupt, 0, siu_type_name(port), port); - if (retval) - return retval; - - if (port->type == PORT_VR41XX_DSIU) - vr41xx_enable_dsiuint(DSIUINT_ALL); - - siu_write(port, UART_LCR, UART_LCR_WLEN8); - - spin_lock_irq(&port->lock); - siu_set_mctrl(port, port->mctrl); - spin_unlock_irq(&port->lock); - - siu_write(port, UART_IER, UART_IER_RLSI | UART_IER_RDI); - - (void)siu_read(port, UART_LSR); - (void)siu_read(port, UART_RX); - (void)siu_read(port, UART_IIR); - (void)siu_read(port, UART_MSR); - - return 0; -} - -static void siu_shutdown(struct uart_port *port) -{ - unsigned long flags; - uint8_t lcr; - - siu_write(port, UART_IER, 0); - - spin_lock_irqsave(&port->lock, flags); - - port->mctrl &= ~TIOCM_OUT2; - siu_set_mctrl(port, port->mctrl); - - spin_unlock_irqrestore(&port->lock, flags); - - lcr = siu_read(port, UART_LCR); - lcr &= ~UART_LCR_SBC; - siu_write(port, UART_LCR, lcr); - - siu_clear_fifo(port); - - (void)siu_read(port, UART_RX); - - if (port->type == PORT_VR41XX_DSIU) - vr41xx_disable_dsiuint(DSIUINT_ALL); - - free_irq(port->irq, port); -} - -static void siu_set_termios(struct uart_port *port, struct ktermios *new, - struct ktermios *old) -{ - tcflag_t c_cflag, c_iflag; - uint8_t lcr, fcr, ier; - unsigned int baud, quot; - unsigned long flags; - - c_cflag = new->c_cflag; - lcr = UART_LCR_WLEN(tty_get_char_size(c_cflag)); - - if (c_cflag & CSTOPB) - lcr |= UART_LCR_STOP; - if (c_cflag & PARENB) - lcr |= UART_LCR_PARITY; - if ((c_cflag & PARODD) != PARODD) - lcr |= UART_LCR_EPAR; - if (c_cflag & CMSPAR) - lcr |= UART_LCR_SPAR; - - baud = uart_get_baud_rate(port, new, old, 0, port->uartclk/16); - quot = uart_get_divisor(port, baud); - - fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10; - - spin_lock_irqsave(&port->lock, flags); - - uart_update_timeout(port, c_cflag, baud); - - c_iflag = new->c_iflag; - - port->read_status_mask = UART_LSR_THRE | UART_LSR_OE | UART_LSR_DR; - if (c_iflag & INPCK) - port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (c_iflag & (IGNBRK | BRKINT | PARMRK)) - port->read_status_mask |= UART_LSR_BI; - - port->ignore_status_mask = 0; - if (c_iflag & IGNPAR) - port->ignore_status_mask |= UART_LSR_FE | UART_LSR_PE; - if (c_iflag & IGNBRK) { - port->ignore_status_mask |= UART_LSR_BI; - if (c_iflag & IGNPAR) - port->ignore_status_mask |= UART_LSR_OE; - } - - if ((c_cflag & CREAD) == 0) - port->ignore_status_mask |= UART_LSR_DR; - - ier = siu_read(port, UART_IER); - ier &= ~UART_IER_MSI; - if (UART_ENABLE_MS(port, c_cflag)) - ier |= UART_IER_MSI; - siu_write(port, UART_IER, ier); - - siu_write(port, UART_LCR, lcr | UART_LCR_DLAB); - - siu_write(port, UART_DLL, (uint8_t)quot); - siu_write(port, UART_DLM, (uint8_t)(quot >> 8)); - - siu_write(port, UART_LCR, lcr); - - siu_write(port, UART_FCR, fcr); - - siu_set_mctrl(port, port->mctrl); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static void siu_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) -{ - switch (state) { - case 0: - switch (port->type) { - case PORT_VR41XX_SIU: - vr41xx_supply_clock(SIU_CLOCK); - break; - case PORT_VR41XX_DSIU: - vr41xx_supply_clock(DSIU_CLOCK); - break; - } - break; - case 3: - switch (port->type) { - case PORT_VR41XX_SIU: - vr41xx_mask_clock(SIU_CLOCK); - break; - case PORT_VR41XX_DSIU: - vr41xx_mask_clock(DSIU_CLOCK); - break; - } - break; - } -} - -static const char *siu_type(struct uart_port *port) -{ - return siu_type_name(port); -} - -static void siu_release_port(struct uart_port *port) -{ - unsigned long size; - - if (port->flags & UPF_IOREMAP) { - iounmap(port->membase); - port->membase = NULL; - } - - size = siu_port_size(port); - release_mem_region(port->mapbase, size); -} - -static int siu_request_port(struct uart_port *port) -{ - unsigned long size; - struct resource *res; - - size = siu_port_size(port); - res = request_mem_region(port->mapbase, size, siu_type_name(port)); - if (res == NULL) - return -EBUSY; - - if (port->flags & UPF_IOREMAP) { - port->membase = ioremap(port->mapbase, size); - if (port->membase == NULL) { - release_resource(res); - return -ENOMEM; - } - } - - return 0; -} - -static void siu_config_port(struct uart_port *port, int flags) -{ - if (flags & UART_CONFIG_TYPE) { - port->type = siu_check_type(port); - (void)siu_request_port(port); - } -} - -static int siu_verify_port(struct uart_port *port, struct serial_struct *serial) -{ - if (port->type != PORT_VR41XX_SIU && port->type != PORT_VR41XX_DSIU) - return -EINVAL; - if (port->irq != serial->irq) - return -EINVAL; - if (port->iotype != serial->io_type) - return -EINVAL; - if (port->mapbase != (unsigned long)serial->iomem_base) - return -EINVAL; - - return 0; -} - -static const struct uart_ops siu_uart_ops = { - .tx_empty = siu_tx_empty, - .set_mctrl = siu_set_mctrl, - .get_mctrl = siu_get_mctrl, - .stop_tx = siu_stop_tx, - .start_tx = siu_start_tx, - .stop_rx = siu_stop_rx, - .enable_ms = siu_enable_ms, - .break_ctl = siu_break_ctl, - .startup = siu_startup, - .shutdown = siu_shutdown, - .set_termios = siu_set_termios, - .pm = siu_pm, - .type = siu_type, - .release_port = siu_release_port, - .request_port = siu_request_port, - .config_port = siu_config_port, - .verify_port = siu_verify_port, -}; - -static int siu_init_ports(struct platform_device *pdev) -{ - struct uart_port *port; - struct resource *res; - int *type = dev_get_platdata(&pdev->dev); - int i; - - if (!type) - return 0; - - port = siu_uart_ports; - for (i = 0; i < SIU_PORTS_MAX; i++) { - port->type = type[i]; - if (port->type == PORT_UNKNOWN) - continue; - port->irq = platform_get_irq(pdev, i); - port->uartclk = SIU_BAUD_BASE * 16; - port->fifosize = 16; - port->regshift = 0; - port->iotype = UPIO_MEM; - port->flags = UPF_IOREMAP | UPF_BOOT_AUTOCONF; - port->line = i; - res = platform_get_resource(pdev, IORESOURCE_MEM, i); - port->mapbase = res->start; - port++; - } - - return i; -} - -#ifdef CONFIG_SERIAL_VR41XX_CONSOLE - -static void wait_for_xmitr(struct uart_port *port) -{ - int timeout = 10000; - uint8_t lsr, msr; - - do { - lsr = siu_read(port, UART_LSR); - if (lsr & UART_LSR_BI) - lsr_break_flag[port->line] = UART_LSR_BI; - - if (uart_lsr_tx_empty(lsr)) - break; - } while (timeout-- > 0); - - if (port->flags & UPF_CONS_FLOW) { - timeout = 1000000; - - do { - msr = siu_read(port, UART_MSR); - if ((msr & UART_MSR_CTS) != 0) - break; - } while (timeout-- > 0); - } -} - -static void siu_console_putchar(struct uart_port *port, unsigned char ch) -{ - wait_for_xmitr(port); - siu_write(port, UART_TX, ch); -} - -static void siu_console_write(struct console *con, const char *s, unsigned count) -{ - struct uart_port *port; - uint8_t ier; - - port = &siu_uart_ports[con->index]; - - ier = siu_read(port, UART_IER); - siu_write(port, UART_IER, 0); - - uart_console_write(port, s, count, siu_console_putchar); - - wait_for_xmitr(port); - siu_write(port, UART_IER, ier); -} - -static int __init siu_console_setup(struct console *con, char *options) -{ - struct uart_port *port; - int baud = 9600; - int parity = 'n'; - int bits = 8; - int flow = 'n'; - - if (con->index >= SIU_PORTS_MAX) - con->index = 0; - - port = &siu_uart_ports[con->index]; - if (port->membase == NULL) { - if (port->mapbase == 0) - return -ENODEV; - port->membase = ioremap(port->mapbase, siu_port_size(port)); - } - - if (port->type == PORT_VR41XX_SIU) - vr41xx_select_siu_interface(SIU_INTERFACE_RS232C); - - if (options != NULL) - uart_parse_options(options, &baud, &parity, &bits, &flow); - - return uart_set_options(port, con, baud, parity, bits, flow); -} - -static struct uart_driver siu_uart_driver; - -static struct console siu_console = { - .name = "ttyVR", - .write = siu_console_write, - .device = uart_console_device, - .setup = siu_console_setup, - .flags = CON_PRINTBUFFER, - .index = -1, - .data = &siu_uart_driver, -}; - -static int siu_console_init(void) -{ - struct uart_port *port; - int i; - - for (i = 0; i < SIU_PORTS_MAX; i++) { - port = &siu_uart_ports[i]; - port->ops = &siu_uart_ops; - } - - register_console(&siu_console); - - return 0; -} - -console_initcall(siu_console_init); - -void __init vr41xx_siu_early_setup(struct uart_port *port) -{ - if (port->type == PORT_UNKNOWN) - return; - - siu_uart_ports[port->line].line = port->line; - siu_uart_ports[port->line].type = port->type; - siu_uart_ports[port->line].uartclk = SIU_BAUD_BASE * 16; - siu_uart_ports[port->line].mapbase = port->mapbase; - siu_uart_ports[port->line].ops = &siu_uart_ops; -} - -#define SERIAL_VR41XX_CONSOLE &siu_console -#else -#define SERIAL_VR41XX_CONSOLE NULL -#endif - -static struct uart_driver siu_uart_driver = { - .owner = THIS_MODULE, - .driver_name = "SIU", - .dev_name = "ttyVR", - .major = SIU_MAJOR, - .minor = SIU_MINOR_BASE, - .cons = SERIAL_VR41XX_CONSOLE, -}; - -static int siu_probe(struct platform_device *dev) -{ - struct uart_port *port; - int num, i, retval; - - num = siu_init_ports(dev); - if (num <= 0) - return -ENODEV; - - siu_uart_driver.nr = num; - retval = uart_register_driver(&siu_uart_driver); - if (retval) - return retval; - - for (i = 0; i < num; i++) { - port = &siu_uart_ports[i]; - port->ops = &siu_uart_ops; - port->dev = &dev->dev; - port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_VR41XX_CONSOLE); - - retval = uart_add_one_port(&siu_uart_driver, port); - if (retval < 0) { - port->dev = NULL; - break; - } - } - - if (i == 0 && retval < 0) { - uart_unregister_driver(&siu_uart_driver); - return retval; - } - - return 0; -} - -static int siu_remove(struct platform_device *dev) -{ - struct uart_port *port; - int i; - - for (i = 0; i < siu_uart_driver.nr; i++) { - port = &siu_uart_ports[i]; - if (port->dev == &dev->dev) { - uart_remove_one_port(&siu_uart_driver, port); - port->dev = NULL; - } - } - - uart_unregister_driver(&siu_uart_driver); - - return 0; -} - -static int siu_suspend(struct platform_device *dev, pm_message_t state) -{ - struct uart_port *port; - int i; - - for (i = 0; i < siu_uart_driver.nr; i++) { - port = &siu_uart_ports[i]; - if ((port->type == PORT_VR41XX_SIU || - port->type == PORT_VR41XX_DSIU) && port->dev == &dev->dev) - uart_suspend_port(&siu_uart_driver, port); - - } - - return 0; -} - -static int siu_resume(struct platform_device *dev) -{ - struct uart_port *port; - int i; - - for (i = 0; i < siu_uart_driver.nr; i++) { - port = &siu_uart_ports[i]; - if ((port->type == PORT_VR41XX_SIU || - port->type == PORT_VR41XX_DSIU) && port->dev == &dev->dev) - uart_resume_port(&siu_uart_driver, port); - } - - return 0; -} - -static struct platform_driver siu_device_driver = { - .probe = siu_probe, - .remove = siu_remove, - .suspend = siu_suspend, - .resume = siu_resume, - .driver = { - .name = "SIU", - }, -}; - -module_platform_driver(siu_device_driver); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:SIU"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 6faf502b7860..3ba34d8378bd 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -124,10 +124,6 @@ /* TXX9 type number */ #define PORT_TXX9 64 -/* NEC VR4100 series SIU/DSIU */ -#define PORT_VR41XX_SIU 65 -#define PORT_VR41XX_DSIU 66 - /* Samsung S3C2400 SoC */ #define PORT_S3C2400 67 -- cgit v1.2.3 From 3c8e19d3d3f9a20cde987fa73fd83b13dcc8604f Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Wed, 6 Jul 2022 19:28:55 +0100 Subject: media: Add P010 tiled format Add P010 tiled format [rebased, updated pixel format name and added description] Tested-by: Benjamin Gaignard Signed-off-by: Ezequiel Garcia Signed-off-by: Jernej Skrabec Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 18 +++++++++++++++--- drivers/media/v4l2-core/v4l2-common.c | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 4 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 997ce2d094fc..10b1feeb0b57 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -116,6 +116,13 @@ All components are stored with the same number of bits per component. - Cb, Cr - Yes - Linear + * - V4L2_PIX_FMT_P010_4L4 + - 'T010' + - 10 + - 4:2:0 + - Cb, Cr + - Yes + - 4x4 tiles * - V4L2_PIX_FMT_NV16 - 'NV16' - 8 @@ -528,11 +535,12 @@ number of lines as the luma plane. - Cr\ :sub:`33` .. _V4L2_PIX_FMT_P010: +.. _V4L2-PIX-FMT-P010-4L4: -P010 ----- +P010 and tiled P010 +------------------- -Like NV12 with 10 bits per component, expanded to 16 bits. +P010 is like NV12 with 10 bits per component, expanded to 16 bits. Data in the 10 high bits, zeros in the 6 low bits, arranged in little endian order. .. flat-table:: Sample 4x4 P010 Image @@ -589,6 +597,10 @@ relationship between the luma and chroma line padding and stride. All components are stored with the same number of bits per component. +``V4L2_PIX_FMT_P010_4L4`` stores pixels in 4x4 tiles, and stores tiles linearly +in memory. The line stride must be aligned to multiple of 8 and image height to +a multiple of 4. The layouts of the luma and chroma planes are identical. + .. raw:: latex \small diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 1e38ad8906a2..e0fbe6ba4b6c 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -278,6 +278,7 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) /* Tiled YUV formats */ { .format = V4L2_PIX_FMT_NV12_4L4, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 }, + { .format = V4L2_PIX_FMT_P010_4L4, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 2, 4, 0, 0 }, .hdiv = 2, .vdiv = 2 }, /* YUV planar formats, non contiguous variant */ { .format = V4L2_PIX_FMT_YUV420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index d9b6b8a678bc..c314025d977e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1357,6 +1357,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV12_4L4: descr = "Y/CbCr 4:2:0 (4x4 Linear)"; break; case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; + case V4L2_PIX_FMT_P010_4L4: descr = "10-bit Y/CbCr 4:2:0 (4x4 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV21M: descr = "Y/CrCb 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV16M: descr = "Y/CbCr 4:2:2 (N-C)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d6fac2344033..01e630f2ec78 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -654,6 +654,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV12_4L4 v4l2_fourcc('V', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 4x4 tiles */ #define V4L2_PIX_FMT_NV12_16L16 v4l2_fourcc('H', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ #define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ +#define V4L2_PIX_FMT_P010_4L4 v4l2_fourcc('T', '0', '1', '0') /* 12 Y/CbCr 4:2:0 10-bit 4x4 macroblocks */ /* Tiled YUV formats, non contiguous planes */ #define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 tiles */ -- cgit v1.2.3 From ddefb2d205539418f3c3851a3e06fac9624f257d Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Thu, 14 Jul 2022 17:44:05 +0800 Subject: net/smc: Extend SMC-R link group netlink attribute Extend SMC-R link group netlink attribute SMC_GEN_LGR_SMCR. Introduce SMC_NLA_LGR_R_BUF_TYPE to show the buffer type of SMC-R link group. Signed-off-by: Wen Gu Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 1 + net/smc/smc_core.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 693f549f6966..bb4dacca31e7 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -124,6 +124,7 @@ enum { SMC_NLA_LGR_R_V2, /* nest */ SMC_NLA_LGR_R_NET_COOKIE, /* u64 */ SMC_NLA_LGR_R_PAD, /* flag */ + SMC_NLA_LGR_R_BUF_TYPE, /* u8 */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f26770c29d78..ff49a11f57b8 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -347,6 +347,8 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_BUF_TYPE, lgr->buf_type)) + goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE, -- cgit v1.2.3 From d276a22314c2bad9136c5e0b09eb3c8a560e1161 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Jul 2022 08:30:13 +0200 Subject: ublk: remove UBLK_IO_F_INTEGRITY The ublk protocol has no mechanism to actually transfer the integrity metadata, so don't define this flag, which requires that an integrity payload is attached to a bio. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220718063013.335531-1-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 3 --- include/uapi/linux/ublk_cmd.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 42afab25864f..796d8230fb60 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -389,9 +389,6 @@ static inline unsigned int ublk_req_build_flags(struct request *req) if (req->cmd_flags & REQ_META) flags |= UBLK_IO_F_META; - if (req->cmd_flags & REQ_INTEGRITY) - flags |= UBLK_IO_F_INTEGRITY; - if (req->cmd_flags & REQ_FUA) flags |= UBLK_IO_F_FUA; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index a3f5e7c21807..d6879eea2fde 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -106,7 +106,6 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_F_FAILFAST_TRANSPORT (1U << 9) #define UBLK_IO_F_FAILFAST_DRIVER (1U << 10) #define UBLK_IO_F_META (1U << 11) -#define UBLK_IO_F_INTEGRITY (1U << 12) #define UBLK_IO_F_FUA (1U << 13) #define UBLK_IO_F_PREFLUSH (1U << 14) #define UBLK_IO_F_NOUNMAP (1U << 15) -- cgit v1.2.3 From bdb2bc7599298ebb677e40fc92b1fa9e69e05098 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Fri, 15 Jul 2022 12:38:00 -0700 Subject: bpf: fix bpf_skb_pull_data documentation Fix documentation for bpf_skb_pull_data() helper for when len == 0. Fixes: fa15601ab31e ("bpf: add documentation for eBPF helpers (33-41)") Signed-off-by: Joanne Koong Acked-by: Quentin Monnet Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220715193800.3940070-1-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 3 ++- tools/include/uapi/linux/bpf.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 379e68fb866f..ffcbf79a556b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2361,7 +2361,8 @@ union bpf_attr { * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes * from *skb* readable and writable. If a zero value is passed for - * *len*, then the whole length of the *skb* is pulled. + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. * * This helper is only needed for reading and writing with direct * packet access. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 379e68fb866f..ffcbf79a556b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2361,7 +2361,8 @@ union bpf_attr { * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes * from *skb* readable and writable. If a zero value is passed for - * *len*, then the whole length of the *skb* is pulled. + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. * * This helper is only needed for reading and writing with direct * packet access. -- cgit v1.2.3 From 9d24322e887b6a3d3f9f9c3e76937a646102c8c1 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 19 Jul 2022 13:52:46 -0700 Subject: PCI/DOE: Add DOE mailbox support functions Introduced in a PCIe r6.0, sec 6.30, DOE provides a config space based mailbox with standard protocol discovery. Each mailbox is accessed through a DOE Extended Capability. Each DOE mailbox must support the DOE discovery protocol in addition to any number of additional protocols. Define core PCIe functionality to manage a single PCIe DOE mailbox at a defined config space offset. Functionality includes iterating, creating, query of supported protocol, and task submission. Destruction of the mailboxes is device managed. Cc: "Li, Ming" Cc: Bjorn Helgaas Cc: Matthew Wilcox Acked-by: Bjorn Helgaas Signed-off-by: Jonathan Cameron Co-developed-by: Ira Weiny Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20220719205249.566684-4-ira.weiny@intel.com Signed-off-by: Dan Williams --- .clang-format | 1 + drivers/pci/Kconfig | 3 + drivers/pci/Makefile | 1 + drivers/pci/doe.c | 536 ++++++++++++++++++++++++++++++++++++++++++ include/linux/pci-doe.h | 77 ++++++ include/uapi/linux/pci_regs.h | 29 ++- 6 files changed, 646 insertions(+), 1 deletion(-) create mode 100644 drivers/pci/doe.c create mode 100644 include/linux/pci-doe.h (limited to 'include/uapi/linux') diff --git a/.clang-format b/.clang-format index 9b87ea1fc16e..1247d54f9e49 100644 --- a/.clang-format +++ b/.clang-format @@ -516,6 +516,7 @@ ForEachMacros: - 'of_property_for_each_string' - 'of_property_for_each_u32' - 'pci_bus_for_each_resource' + - 'pci_doe_for_each_off' - 'pcl_for_each_chunk' - 'pcl_for_each_segment' - 'pcm_for_each_format' diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 133c73207782..b2f2e588a817 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -121,6 +121,9 @@ config XEN_PCIDEV_FRONTEND config PCI_ATS bool +config PCI_DOE + bool + config PCI_ECAM bool diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 0da6b1ebc694..2680e4c92f0a 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_PCI_ECAM) += ecam.o obj-$(CONFIG_PCI_P2PDMA) += p2pdma.o obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o obj-$(CONFIG_VGA_ARB) += vgaarb.o +obj-$(CONFIG_PCI_DOE) += doe.o # Endpoint library must be initialized before its users obj-$(CONFIG_PCI_ENDPOINT) += endpoint/ diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c new file mode 100644 index 000000000000..e402f05068a5 --- /dev/null +++ b/drivers/pci/doe.c @@ -0,0 +1,536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Data Object Exchange + * PCIe r6.0, sec 6.30 DOE + * + * Copyright (C) 2021 Huawei + * Jonathan Cameron + * + * Copyright (C) 2022 Intel Corporation + * Ira Weiny + */ + +#define dev_fmt(fmt) "DOE: " fmt + +#include +#include +#include +#include +#include +#include +#include + +#define PCI_DOE_PROTOCOL_DISCOVERY 0 + +/* Timeout of 1 second from 6.30.2 Operation, PCI Spec r6.0 */ +#define PCI_DOE_TIMEOUT HZ +#define PCI_DOE_POLL_INTERVAL (PCI_DOE_TIMEOUT / 128) + +#define PCI_DOE_FLAG_CANCEL 0 +#define PCI_DOE_FLAG_DEAD 1 + +/** + * struct pci_doe_mb - State for a single DOE mailbox + * + * This state is used to manage a single DOE mailbox capability. All fields + * should be considered opaque to the consumers and the structure passed into + * the helpers below after being created by devm_pci_doe_create() + * + * @pdev: PCI device this mailbox belongs to + * @cap_offset: Capability offset + * @prots: Array of protocols supported (encoded as long values) + * @wq: Wait queue for work item + * @work_queue: Queue of pci_doe_work items + * @flags: Bit array of PCI_DOE_FLAG_* flags + */ +struct pci_doe_mb { + struct pci_dev *pdev; + u16 cap_offset; + struct xarray prots; + + wait_queue_head_t wq; + struct workqueue_struct *work_queue; + unsigned long flags; +}; + +static int pci_doe_wait(struct pci_doe_mb *doe_mb, unsigned long timeout) +{ + if (wait_event_timeout(doe_mb->wq, + test_bit(PCI_DOE_FLAG_CANCEL, &doe_mb->flags), + timeout)) + return -EIO; + return 0; +} + +static void pci_doe_write_ctrl(struct pci_doe_mb *doe_mb, u32 val) +{ + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + + pci_write_config_dword(pdev, offset + PCI_DOE_CTRL, val); +} + +static int pci_doe_abort(struct pci_doe_mb *doe_mb) +{ + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + unsigned long timeout_jiffies; + + pci_dbg(pdev, "[%x] Issuing Abort\n", offset); + + timeout_jiffies = jiffies + PCI_DOE_TIMEOUT; + pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_ABORT); + + do { + int rc; + u32 val; + + rc = pci_doe_wait(doe_mb, PCI_DOE_POLL_INTERVAL); + if (rc) + return rc; + pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val); + + /* Abort success! */ + if (!FIELD_GET(PCI_DOE_STATUS_ERROR, val) && + !FIELD_GET(PCI_DOE_STATUS_BUSY, val)) + return 0; + + } while (!time_after(jiffies, timeout_jiffies)); + + /* Abort has timed out and the MB is dead */ + pci_err(pdev, "[%x] ABORT timed out\n", offset); + return -EIO; +} + +static int pci_doe_send_req(struct pci_doe_mb *doe_mb, + struct pci_doe_task *task) +{ + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + u32 val; + int i; + + /* + * Check the DOE busy bit is not set. If it is set, this could indicate + * someone other than Linux (e.g. firmware) is using the mailbox. Note + * it is expected that firmware and OS will negotiate access rights via + * an, as yet to be defined, method. + */ + pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val); + if (FIELD_GET(PCI_DOE_STATUS_BUSY, val)) + return -EBUSY; + + if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) + return -EIO; + + /* Write DOE Header */ + val = FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_1_VID, task->prot.vid) | + FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_1_TYPE, task->prot.type); + pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, val); + /* Length is 2 DW of header + length of payload in DW */ + pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, + FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, + 2 + task->request_pl_sz / + sizeof(u32))); + for (i = 0; i < task->request_pl_sz / sizeof(u32); i++) + pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, + task->request_pl[i]); + + pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); + + return 0; +} + +static bool pci_doe_data_obj_ready(struct pci_doe_mb *doe_mb) +{ + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + u32 val; + + pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val); + if (FIELD_GET(PCI_DOE_STATUS_DATA_OBJECT_READY, val)) + return true; + return false; +} + +static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) +{ + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + size_t length, payload_length; + u32 val; + int i; + + /* Read the first dword to get the protocol */ + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + if ((FIELD_GET(PCI_DOE_DATA_OBJECT_HEADER_1_VID, val) != task->prot.vid) || + (FIELD_GET(PCI_DOE_DATA_OBJECT_HEADER_1_TYPE, val) != task->prot.type)) { + dev_err_ratelimited(&pdev->dev, "[%x] expected [VID, Protocol] = [%04x, %02x], got [%04x, %02x]\n", + doe_mb->cap_offset, task->prot.vid, task->prot.type, + FIELD_GET(PCI_DOE_DATA_OBJECT_HEADER_1_VID, val), + FIELD_GET(PCI_DOE_DATA_OBJECT_HEADER_1_TYPE, val)); + return -EIO; + } + + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + /* Read the second dword to get the length */ + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + + length = FIELD_GET(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, val); + if (length > SZ_1M || length < 2) + return -EIO; + + /* First 2 dwords have already been read */ + length -= 2; + payload_length = min(length, task->response_pl_sz / sizeof(u32)); + /* Read the rest of the response payload */ + for (i = 0; i < payload_length; i++) { + pci_read_config_dword(pdev, offset + PCI_DOE_READ, + &task->response_pl[i]); + /* Prior to the last ack, ensure Data Object Ready */ + if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) + return -EIO; + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + } + + /* Flush excess length */ + for (; i < length; i++) { + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + } + + /* Final error check to pick up on any since Data Object Ready */ + pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val); + if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) + return -EIO; + + return min(length, task->response_pl_sz / sizeof(u32)) * sizeof(u32); +} + +static void signal_task_complete(struct pci_doe_task *task, int rv) +{ + task->rv = rv; + task->complete(task); +} + +static void signal_task_abort(struct pci_doe_task *task, int rv) +{ + struct pci_doe_mb *doe_mb = task->doe_mb; + struct pci_dev *pdev = doe_mb->pdev; + + if (pci_doe_abort(doe_mb)) { + /* + * If the device can't process an abort; set the mailbox dead + * - no more submissions + */ + pci_err(pdev, "[%x] Abort failed marking mailbox dead\n", + doe_mb->cap_offset); + set_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags); + } + signal_task_complete(task, rv); +} + +static void doe_statemachine_work(struct work_struct *work) +{ + struct pci_doe_task *task = container_of(work, struct pci_doe_task, + work); + struct pci_doe_mb *doe_mb = task->doe_mb; + struct pci_dev *pdev = doe_mb->pdev; + int offset = doe_mb->cap_offset; + unsigned long timeout_jiffies; + u32 val; + int rc; + + if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) { + signal_task_complete(task, -EIO); + return; + } + + /* Send request */ + rc = pci_doe_send_req(doe_mb, task); + if (rc) { + /* + * The specification does not provide any guidance on how to + * resolve conflicting requests from other entities. + * Furthermore, it is likely that busy will not be detected + * most of the time. Flag any detection of status busy with an + * error. + */ + if (rc == -EBUSY) + dev_err_ratelimited(&pdev->dev, "[%x] busy detected; another entity is sending conflicting requests\n", + offset); + signal_task_abort(task, rc); + return; + } + + timeout_jiffies = jiffies + PCI_DOE_TIMEOUT; + /* Poll for response */ +retry_resp: + pci_read_config_dword(pdev, offset + PCI_DOE_STATUS, &val); + if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) { + signal_task_abort(task, -EIO); + return; + } + + if (!FIELD_GET(PCI_DOE_STATUS_DATA_OBJECT_READY, val)) { + if (time_after(jiffies, timeout_jiffies)) { + signal_task_abort(task, -EIO); + return; + } + rc = pci_doe_wait(doe_mb, PCI_DOE_POLL_INTERVAL); + if (rc) { + signal_task_abort(task, rc); + return; + } + goto retry_resp; + } + + rc = pci_doe_recv_resp(doe_mb, task); + if (rc < 0) { + signal_task_abort(task, rc); + return; + } + + signal_task_complete(task, rc); +} + +static void pci_doe_task_complete(struct pci_doe_task *task) +{ + complete(task->private); +} + +static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, + u8 *protocol) +{ + u32 request_pl = FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX, + *index); + u32 response_pl; + DECLARE_COMPLETION_ONSTACK(c); + struct pci_doe_task task = { + .prot.vid = PCI_VENDOR_ID_PCI_SIG, + .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, + .request_pl = &request_pl, + .request_pl_sz = sizeof(request_pl), + .response_pl = &response_pl, + .response_pl_sz = sizeof(response_pl), + .complete = pci_doe_task_complete, + .private = &c, + }; + int rc; + + rc = pci_doe_submit_task(doe_mb, &task); + if (rc < 0) + return rc; + + wait_for_completion(&c); + + if (task.rv != sizeof(response_pl)) + return -EIO; + + *vid = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID, response_pl); + *protocol = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL, + response_pl); + *index = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX, + response_pl); + + return 0; +} + +static void *pci_doe_xa_prot_entry(u16 vid, u8 prot) +{ + return xa_mk_value((vid << 8) | prot); +} + +static int pci_doe_cache_protocols(struct pci_doe_mb *doe_mb) +{ + u8 index = 0; + u8 xa_idx = 0; + + do { + int rc; + u16 vid; + u8 prot; + + rc = pci_doe_discovery(doe_mb, &index, &vid, &prot); + if (rc) + return rc; + + pci_dbg(doe_mb->pdev, + "[%x] Found protocol %d vid: %x prot: %x\n", + doe_mb->cap_offset, xa_idx, vid, prot); + + rc = xa_insert(&doe_mb->prots, xa_idx++, + pci_doe_xa_prot_entry(vid, prot), GFP_KERNEL); + if (rc) + return rc; + } while (index); + + return 0; +} + +static void pci_doe_xa_destroy(void *mb) +{ + struct pci_doe_mb *doe_mb = mb; + + xa_destroy(&doe_mb->prots); +} + +static void pci_doe_destroy_workqueue(void *mb) +{ + struct pci_doe_mb *doe_mb = mb; + + destroy_workqueue(doe_mb->work_queue); +} + +static void pci_doe_flush_mb(void *mb) +{ + struct pci_doe_mb *doe_mb = mb; + + /* Stop all pending work items from starting */ + set_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags); + + /* Cancel an in progress work item, if necessary */ + set_bit(PCI_DOE_FLAG_CANCEL, &doe_mb->flags); + wake_up(&doe_mb->wq); + + /* Flush all work items */ + flush_workqueue(doe_mb->work_queue); +} + +/** + * pcim_doe_create_mb() - Create a DOE mailbox object + * + * @pdev: PCI device to create the DOE mailbox for + * @cap_offset: Offset of the DOE mailbox + * + * Create a single mailbox object to manage the mailbox protocol at the + * cap_offset specified. + * + * RETURNS: created mailbox object on success + * ERR_PTR(-errno) on failure + */ +struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) +{ + struct pci_doe_mb *doe_mb; + struct device *dev = &pdev->dev; + int rc; + + doe_mb = devm_kzalloc(dev, sizeof(*doe_mb), GFP_KERNEL); + if (!doe_mb) + return ERR_PTR(-ENOMEM); + + doe_mb->pdev = pdev; + doe_mb->cap_offset = cap_offset; + init_waitqueue_head(&doe_mb->wq); + + xa_init(&doe_mb->prots); + rc = devm_add_action(dev, pci_doe_xa_destroy, doe_mb); + if (rc) + return ERR_PTR(rc); + + doe_mb->work_queue = alloc_ordered_workqueue("%s %s DOE [%x]", 0, + dev_driver_string(&pdev->dev), + pci_name(pdev), + doe_mb->cap_offset); + if (!doe_mb->work_queue) { + pci_err(pdev, "[%x] failed to allocate work queue\n", + doe_mb->cap_offset); + return ERR_PTR(-ENOMEM); + } + rc = devm_add_action_or_reset(dev, pci_doe_destroy_workqueue, doe_mb); + if (rc) + return ERR_PTR(rc); + + /* Reset the mailbox by issuing an abort */ + rc = pci_doe_abort(doe_mb); + if (rc) { + pci_err(pdev, "[%x] failed to reset mailbox with abort command : %d\n", + doe_mb->cap_offset, rc); + return ERR_PTR(rc); + } + + /* + * The state machine and the mailbox should be in sync now; + * Set up mailbox flush prior to using the mailbox to query protocols. + */ + rc = devm_add_action_or_reset(dev, pci_doe_flush_mb, doe_mb); + if (rc) + return ERR_PTR(rc); + + rc = pci_doe_cache_protocols(doe_mb); + if (rc) { + pci_err(pdev, "[%x] failed to cache protocols : %d\n", + doe_mb->cap_offset, rc); + return ERR_PTR(rc); + } + + return doe_mb; +} +EXPORT_SYMBOL_GPL(pcim_doe_create_mb); + +/** + * pci_doe_supports_prot() - Return if the DOE instance supports the given + * protocol + * @doe_mb: DOE mailbox capability to query + * @vid: Protocol Vendor ID + * @type: Protocol type + * + * RETURNS: True if the DOE mailbox supports the protocol specified + */ +bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) +{ + unsigned long index; + void *entry; + + /* The discovery protocol must always be supported */ + if (vid == PCI_VENDOR_ID_PCI_SIG && type == PCI_DOE_PROTOCOL_DISCOVERY) + return true; + + xa_for_each(&doe_mb->prots, index, entry) + if (entry == pci_doe_xa_prot_entry(vid, type)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(pci_doe_supports_prot); + +/** + * pci_doe_submit_task() - Submit a task to be processed by the state machine + * + * @doe_mb: DOE mailbox capability to submit to + * @task: task to be queued + * + * Submit a DOE task (request/response) to the DOE mailbox to be processed. + * Returns upon queueing the task object. If the queue is full this function + * will sleep until there is room in the queue. + * + * task->complete will be called when the state machine is done processing this + * task. + * + * Excess data will be discarded. + * + * RETURNS: 0 when task has been successfully queued, -ERRNO on error + */ +int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) +{ + if (!pci_doe_supports_prot(doe_mb, task->prot.vid, task->prot.type)) + return -EINVAL; + + /* + * DOE requests must be a whole number of DW and the response needs to + * be big enough for at least 1 DW + */ + if (task->request_pl_sz % sizeof(u32) || + task->response_pl_sz < sizeof(u32)) + return -EINVAL; + + if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) + return -EIO; + + task->doe_mb = doe_mb; + INIT_WORK(&task->work, doe_statemachine_work); + queue_work(doe_mb->work_queue, &task->work); + return 0; +} +EXPORT_SYMBOL_GPL(pci_doe_submit_task); diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h new file mode 100644 index 000000000000..ed9b4df792b8 --- /dev/null +++ b/include/linux/pci-doe.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data Object Exchange + * PCIe r6.0, sec 6.30 DOE + * + * Copyright (C) 2021 Huawei + * Jonathan Cameron + * + * Copyright (C) 2022 Intel Corporation + * Ira Weiny + */ + +#ifndef LINUX_PCI_DOE_H +#define LINUX_PCI_DOE_H + +struct pci_doe_protocol { + u16 vid; + u8 type; +}; + +struct pci_doe_mb; + +/** + * struct pci_doe_task - represents a single query/response + * + * @prot: DOE Protocol + * @request_pl: The request payload + * @request_pl_sz: Size of the request payload (bytes) + * @response_pl: The response payload + * @response_pl_sz: Size of the response payload (bytes) + * @rv: Return value. Length of received response or error (bytes) + * @complete: Called when task is complete + * @private: Private data for the consumer + * @work: Used internally by the mailbox + * @doe_mb: Used internally by the mailbox + * + * The payload sizes and rv are specified in bytes with the following + * restrictions concerning the protocol. + * + * 1) The request_pl_sz must be a multiple of double words (4 bytes) + * 2) The response_pl_sz must be >= a single double word (4 bytes) + * 3) rv is returned as bytes but it will be a multiple of double words + * + * NOTE there is no need for the caller to initialize work or doe_mb. + */ +struct pci_doe_task { + struct pci_doe_protocol prot; + u32 *request_pl; + size_t request_pl_sz; + u32 *response_pl; + size_t response_pl_sz; + int rv; + void (*complete)(struct pci_doe_task *task); + void *private; + + /* No need for the user to initialize these fields */ + struct work_struct work; + struct pci_doe_mb *doe_mb; +}; + +/** + * pci_doe_for_each_off - Iterate each DOE capability + * @pdev: struct pci_dev to iterate + * @off: u16 of config space offset of each mailbox capability found + */ +#define pci_doe_for_each_off(pdev, off) \ + for (off = pci_find_next_ext_capability(pdev, off, \ + PCI_EXT_CAP_ID_DOE); \ + off > 0; \ + off = pci_find_next_ext_capability(pdev, off, \ + PCI_EXT_CAP_ID_DOE)) + +struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); +bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); +int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); + +#endif diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 108f8523fa04..57b8e2ffb1dd 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -737,7 +737,8 @@ #define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */ #define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */ #define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_16GT +#define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -1103,4 +1104,30 @@ #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Data Object Exchange */ +#define PCI_DOE_CAP 0x04 /* DOE Capabilities Register */ +#define PCI_DOE_CAP_INT_SUP 0x00000001 /* Interrupt Support */ +#define PCI_DOE_CAP_INT_MSG_NUM 0x00000ffe /* Interrupt Message Number */ +#define PCI_DOE_CTRL 0x08 /* DOE Control Register */ +#define PCI_DOE_CTRL_ABORT 0x00000001 /* DOE Abort */ +#define PCI_DOE_CTRL_INT_EN 0x00000002 /* DOE Interrupt Enable */ +#define PCI_DOE_CTRL_GO 0x80000000 /* DOE Go */ +#define PCI_DOE_STATUS 0x0c /* DOE Status Register */ +#define PCI_DOE_STATUS_BUSY 0x00000001 /* DOE Busy */ +#define PCI_DOE_STATUS_INT_STATUS 0x00000002 /* DOE Interrupt Status */ +#define PCI_DOE_STATUS_ERROR 0x00000004 /* DOE Error */ +#define PCI_DOE_STATUS_DATA_OBJECT_READY 0x80000000 /* Data Object Ready */ +#define PCI_DOE_WRITE 0x10 /* DOE Write Data Mailbox Register */ +#define PCI_DOE_READ 0x14 /* DOE Read Data Mailbox Register */ + +/* DOE Data Object - note not actually registers */ +#define PCI_DOE_DATA_OBJECT_HEADER_1_VID 0x0000ffff +#define PCI_DOE_DATA_OBJECT_HEADER_1_TYPE 0x00ff0000 +#define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH 0x0003ffff + +#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000 +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000 + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From e70a3263a7eed768d5f947b8f2aff8d2a79c9d97 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 19 Jul 2022 23:35:48 +0900 Subject: can: error: specify the values of data[5..7] of CAN error frames Currently, data[5..7] of struct can_frame, when used as a CAN error frame, are defined as being "controller specific". Device specific behaviours are problematic because it prevents someone from writing code which is portable between devices. As a matter of fact, data[5] is never used, data[6] is always used to report TX error counter and data[7] is always used to report RX error counter. can-utils also relies on this. This patch updates the comment in the uapi header to specify that data[5] is reserved (and thus should not be used) and that data[6..7] are used for error counters. Fixes: 0d66548a10cb ("[CAN]: Add PF_CAN core module") Link: https://lore.kernel.org/all/20220719143550.3681-11-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/error.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index 34633283de64..a1000cb63063 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -120,6 +120,9 @@ #define CAN_ERR_TRX_CANL_SHORT_TO_GND 0x70 /* 0111 0000 */ #define CAN_ERR_TRX_CANL_SHORT_TO_CANH 0x80 /* 1000 0000 */ -/* controller specific additional information / data[5..7] */ +/* data[5] is reserved (do not use) */ + +/* TX error counter / data[6] */ +/* RX error counter / data[7] */ #endif /* _UAPI_CAN_ERROR_H */ -- cgit v1.2.3 From 3e5c291c7942d0909a48bc5ec1b9bba136465166 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 19 Jul 2022 23:35:49 +0900 Subject: can: add CAN_ERR_CNT flag to notify availability of error counter Add a dedicated flag in uapi/linux/can/error.h to notify the userland that fields data[6] and data[7] of the CAN error frame were respectively populated with the tx and rx error counters. For all driver tree-wide, set up this flags whenever needed. Link: https://lore.kernel.org/all/20220719143550.3681-12-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/c_can/c_can_main.c | 6 +++--- drivers/net/can/cc770/cc770.c | 1 + drivers/net/can/ctucanfd/ctucanfd_base.c | 5 +++-- drivers/net/can/grcan.c | 1 + drivers/net/can/ifi_canfd/ifi_canfd.c | 4 ++-- drivers/net/can/janz-ican3.c | 4 ++-- drivers/net/can/kvaser_pciefd.c | 2 +- drivers/net/can/m_can/m_can.c | 4 ++-- drivers/net/can/pch_can.c | 1 + drivers/net/can/peak_canfd/peak_canfd.c | 6 +++--- drivers/net/can/rcar/rcar_can.c | 1 + drivers/net/can/rcar/rcar_canfd.c | 4 ++-- drivers/net/can/sja1000/sja1000.c | 1 + drivers/net/can/slcan/slcan-core.c | 1 + drivers/net/can/spi/hi311x.c | 1 + drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 1 + drivers/net/can/sun4i_can.c | 1 + drivers/net/can/ti_hecc.c | 1 + drivers/net/can/usb/esd_usb.c | 3 ++- drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 ++ drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 1 + drivers/net/can/usb/peak_usb/pcan_usb.c | 1 + drivers/net/can/usb/usb_8dev.c | 1 + drivers/net/can/xilinx_can.c | 1 + include/uapi/linux/can/error.h | 2 ++ 25 files changed, 38 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index ed4db4cf8716..de38d8f7b5f7 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -952,14 +952,14 @@ static int c_can_handle_state_change(struct net_device *dev, switch (error_type) { case C_CAN_NO_ERROR: - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = CAN_ERR_CRTL_ACTIVE; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; break; case C_CAN_ERROR_WARNING: /* error warning state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (bec.txerr > bec.rxerr) ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; @@ -969,7 +969,7 @@ static int c_can_handle_state_change(struct net_device *dev, break; case C_CAN_ERROR_PASSIVE: /* error passive state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; if (rx_err_passive) cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; if (bec.txerr > 127) diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index bb7224cfc6ab..797a954bb1a0 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -512,6 +512,7 @@ static int cc770_err(struct net_device *dev, u8 status) /* Use extended functions of the CC770 */ if (priv->control_normal_mode & CTRL_EAF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = cc770_read_reg(priv, tx_error_counter); cf->data[7] = cc770_read_reg(priv, rx_error_counter); } diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 14ac7c0ee04c..6b281f6eb9b4 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -847,7 +847,7 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) case CAN_STATE_ERROR_PASSIVE: priv->can.can_stats.error_passive++; if (skb) { - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (bec.rxerr > 127) ? CAN_ERR_CRTL_RX_PASSIVE : CAN_ERR_CRTL_TX_PASSIVE; @@ -858,7 +858,7 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) case CAN_STATE_ERROR_WARNING: priv->can.can_stats.error_warning++; if (skb) { - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] |= (bec.txerr > bec.rxerr) ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; @@ -867,6 +867,7 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) } break; case CAN_STATE_ERROR_ACTIVE: + cf->can_id |= CAN_ERR_CNT; cf->data[1] = CAN_ERR_CRTL_ACTIVE; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 4c47c1055eff..24035a6187c9 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -671,6 +671,7 @@ static void grcan_err(struct net_device *dev, u32 sources, u32 status) /* There are no others at this point */ break; } + cf.can_id |= CAN_ERR_CNT; cf.data[6] = txerr; cf.data[7] = rxerr; priv->can.state = state; diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 968ed6d7316b..64e3be8b73af 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -492,7 +492,7 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev, switch (new_state) { case CAN_STATE_ERROR_WARNING: /* error warning state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (bec.txerr > bec.rxerr) ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; @@ -501,7 +501,7 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev, break; case CAN_STATE_ERROR_PASSIVE: /* error passive state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; if (bec.txerr > 127) cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE; diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 35bfb82d6929..ccb5c5405224 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1127,7 +1127,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) /* bus error interrupt */ if (isrc == CEVTIND_BEI) { mod->can.can_stats.bus_error++; - cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR; + cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | CAN_ERR_CNT; switch (ecc & ECC_MASK) { case ECC_BIT: @@ -1153,7 +1153,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) if (state != mod->can.state && (state == CAN_STATE_ERROR_WARNING || state == CAN_STATE_ERROR_PASSIVE)) { - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; if (state == CAN_STATE_ERROR_WARNING) { mod->can.can_stats.error_warning++; cf->data[1] = (txerr > rxerr) ? diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 017f2d36ffc3..dcd2c9d50d5e 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1306,7 +1306,7 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, shhwtstamps->hwtstamp = ns_to_ktime(div_u64(p->timestamp * 1000, can->kv_pcie->freq_to_ticks_div)); - cf->can_id |= CAN_ERR_BUSERROR; + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index afaaeb610c00..713a4b0edf86 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -741,7 +741,7 @@ static int m_can_handle_state_change(struct net_device *dev, switch (new_state) { case CAN_STATE_ERROR_WARNING: /* error warning state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (bec.txerr > bec.rxerr) ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; @@ -750,7 +750,7 @@ static int m_can_handle_state_change(struct net_device *dev, break; case CAN_STATE_ERROR_PASSIVE: /* error passive state */ - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; ecr = m_can_read(cdev, M_CAN_ECR); if (ecr & ECR_RP) cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index 497ef77340ea..50f6719b3aa4 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -497,6 +497,7 @@ static void pch_can_error(struct net_device *ndev, u32 status) priv->can.can_stats.bus_off++; can_bus_off(ndev); } else { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = errc & PCH_TEC; cf->data[7] = (errc & PCH_REC) >> 8; } diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index b2dea360813d..afb9adb3d5c2 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -373,7 +373,7 @@ static int pucan_handle_status(struct peak_canfd_priv *priv, priv->can.state = CAN_STATE_ERROR_PASSIVE; priv->can.can_stats.error_passive++; if (skb) { - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (priv->bec.txerr > priv->bec.rxerr) ? CAN_ERR_CRTL_TX_PASSIVE : CAN_ERR_CRTL_RX_PASSIVE; @@ -386,7 +386,7 @@ static int pucan_handle_status(struct peak_canfd_priv *priv, priv->can.state = CAN_STATE_ERROR_WARNING; priv->can.can_stats.error_warning++; if (skb) { - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = (priv->bec.txerr > priv->bec.rxerr) ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; @@ -430,7 +430,7 @@ static int pucan_handle_cache_critical(struct peak_canfd_priv *priv) return -ENOMEM; } - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; cf->data[6] = priv->bec.txerr; diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 24d7a71def6a..d11db2112a4a 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -334,6 +334,7 @@ static void rcar_can_error(struct net_device *ndev) if (skb) cf->can_id |= CAN_ERR_BUSOFF; } else if (skb) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index ba42cef10a53..e3382284e172 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1052,7 +1052,7 @@ static void rcar_canfd_error(struct net_device *ndev, u32 cerfl, netdev_dbg(ndev, "Error warning interrupt\n"); priv->can.state = CAN_STATE_ERROR_WARNING; priv->can.can_stats.error_warning++; - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_WARNING : CAN_ERR_CRTL_RX_WARNING; cf->data[6] = txerr; @@ -1062,7 +1062,7 @@ static void rcar_canfd_error(struct net_device *ndev, u32 cerfl, netdev_dbg(ndev, "Error passive interrupt\n"); priv->can.state = CAN_STATE_ERROR_PASSIVE; priv->can.can_stats.error_passive++; - cf->can_id |= CAN_ERR_CRTL; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_PASSIVE : CAN_ERR_CRTL_RX_PASSIVE; cf->data[6] = txerr; diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 74bff5092b47..75a2f9bf8c16 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -426,6 +426,7 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status) state = CAN_STATE_ERROR_ACTIVE; } if (state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index dfd1baba4130..dc28e715bbe1 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -314,6 +314,7 @@ static void slc_bump_state(struct slcan *sl) if (state == CAN_STATE_BUS_OFF) { can_bus_off(dev); } else if (skb) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index bfb7c4bb5bc3..167114aae6dd 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -680,6 +680,7 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) break; } } else { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 9b47b07162fe..f4e174cadd4e 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -1099,6 +1099,7 @@ static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv) err = mcp251xfd_get_berr_counter(priv->ndev, &bec); if (err) return err; + cf->can_id |= CAN_ERR_CNT; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; } diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index afe9b541f037..b90dfb429ccd 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -566,6 +566,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) state = CAN_STATE_ERROR_ACTIVE; } if (skb && state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index debe17bfd0f0..afa38771520e 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -662,6 +662,7 @@ static void ti_hecc_change_state(struct net_device *ndev, can_change_state(priv->ndev, cf, tx_state, rx_state); if (max(tx_state, rx_state) != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = hecc_read(priv, HECC_CANTEC); cf->data[7] = hecc_read(priv, HECC_CANREC); } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 8a4bf2961f3d..177ed33e08d9 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -265,7 +265,8 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, priv->can.can_stats.bus_error++; stats->rx_errors++; - cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR; + cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | + CAN_ERR_CNT; switch (ecc & SJA1000_ECC_MASK) { case SJA1000_ECC_BIT: diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 404093468b2f..dd65c101bfb8 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -918,6 +918,7 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, priv->can.can_stats.restarts++; if (new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = bec->txerr; cf->data[7] = bec->rxerr; } @@ -1072,6 +1073,7 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, cf->can_id |= CAN_ERR_BUSERROR; if (new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index f551fde16a70..07f687f29b34 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -854,6 +854,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, } if (new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = es->txerr; cf->data[7] = es->rxerr; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 091c631ebe23..d07b7ee79e3e 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -506,6 +506,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, /* Supply TX/RX error counters in case of * controller error. */ + cf->can_id = CAN_ERR_CNT; cf->data[6] = mc->pdev->bec.txerr; cf->data[7] = mc->pdev->bec.rxerr; } diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 4d38dc90472a..8b7cd69e20b0 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -439,6 +439,7 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv, if (rx_errors) stats->rx_errors++; if (priv->can.state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 0de2f97d9f62..caa6b4cee63f 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -965,6 +965,7 @@ static void xcan_set_error_state(struct net_device *ndev, can_change_state(ndev, cf, tx_state, rx_state); if (cf) { + cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; } diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index a1000cb63063..b7c3efd9ff99 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -57,6 +57,8 @@ #define CAN_ERR_BUSOFF 0x00000040U /* bus off */ #define CAN_ERR_BUSERROR 0x00000080U /* bus error (may flood!) */ #define CAN_ERR_RESTARTED 0x00000100U /* controller restarted */ +#define CAN_ERR_CNT 0x00000200U /* TX error counter / data[6] */ + /* RX error counter / data[7] */ /* arbitration lost in bit ... / data[0] */ #define CAN_ERR_LOSTARB_UNSPEC 0x00 /* unspecified */ -- cgit v1.2.3 From 3f9c26210cf80ea8cb5dd901aba5feb77200b085 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 19 Jul 2022 23:35:50 +0900 Subject: can: error: add definitions for the different CAN error thresholds Currently, drivers are using magic numbers to derive the CAN error states from the error counter. Add three macro declarations to remediate this. For reference, the error-active, error-passive and bus-off are defined in ISO 11898, section 12.1.4.2 "Error counting". Although ISO 11898 does not define error-warning state, this extra value is also commonly used and is thus also added. Link: https://lore.kernel.org/all/20220719143550.3681-13-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/error.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index b7c3efd9ff99..acc1ac393d2a 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -127,4 +127,17 @@ /* TX error counter / data[6] */ /* RX error counter / data[7] */ +/* CAN state thresholds + * + * Error counter Error state + * ----------------------------------- + * 0 - 95 Error-active + * 96 - 127 Error-warning + * 128 - 255 Error-passive + * 256 and greater Bus-off + */ +#define CAN_ERROR_WARNING_THRESHOLD 96 +#define CAN_ERROR_PASSIVE_THRESHOLD 128 +#define CAN_BUS_OFF_THRESHOLD 256 + #endif /* _UAPI_CAN_ERROR_H */ -- cgit v1.2.3 From f5ecfee94493475783074e86ded10a0499d779fc Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 14 Jul 2022 21:43:34 +0200 Subject: KVM: s390: resetting the Topology-Change-Report During a subsystem reset the Topology-Change-Report is cleared. Let's give userland the possibility to clear the MTCR in the case of a subsystem reset. To migrate the MTCR, we give userland the possibility to query the MTCR state. We indicate KVM support for the CPU topology facility with a new KVM capability: KVM_CAP_S390_CPU_TOPOLOGY. Signed-off-by: Pierre Morel Reviewed-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Message-Id: <20220714194334.127812-1-pmorel@linux.ibm.com> Link: https://lore.kernel.org/all/20220714194334.127812-1-pmorel@linux.ibm.com/ [frankja@linux.ibm.com: Simple conflict resolution in Documentation/virt/kvm/api.rst] Signed-off-by: Janosch Frank --- Documentation/virt/kvm/api.rst | 25 ++++++++++++++++++++ arch/s390/include/uapi/asm/kvm.h | 1 + arch/s390/kvm/kvm-s390.c | 51 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 4 files changed, 78 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5be5cc59869d..3c4551a2f6d0 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8269,6 +8269,31 @@ The capability has no effect if the nx_huge_pages module parameter is not set. This capability may only be set before any vCPUs are created. +8.39 KVM_CAP_S390_CPU_TOPOLOGY +------------------------------ + +:Capability: KVM_CAP_S390_CPU_TOPOLOGY +:Architectures: s390 +:Type: vm + +This capability indicates that KVM will provide the S390 CPU Topology +facility which consist of the interpretation of the PTF instruction for +the function code 2 along with interception and forwarding of both the +PTF instruction with function codes 0 or 1 and the STSI(15,1,x) +instruction to the userland hypervisor. + +The stfle facility 11, CPU Topology facility, should not be indicated +to the guest without this capability. + +When this capability is present, KVM provides a new attribute group +on vm fd, KVM_S390_VM_CPU_TOPOLOGY. +This new attribute allows to get, set or clear the Modified Change +Topology Report (MTCR) bit of the SCA through the kvm_device_attr +structure. + +When getting the Modified Change Topology Report value, the attr->addr +must point to a byte where the value will be stored or retrieved from. + 9. Known KVM API problems ========================= diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 7a6b14874d65..a73cf01a1606 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 #define KVM_S390_VM_MIGRATION 4 +#define KVM_S390_VM_CPU_TOPOLOGY 5 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5d18b66a08c9..edfd4bbd0cba 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -642,6 +642,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_ZPCI_OP: r = kvm_s390_pci_interp_allowed(); break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = test_facility(11); + break; default: r = 0; } @@ -853,6 +856,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) icpt_operexc_on_all_vcpus(kvm); r = 0; break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = -EINVAL; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + r = -EBUSY; + } else if (test_facility(11)) { + set_kvm_facility(kvm->arch.model.fac_mask, 11); + set_kvm_facility(kvm->arch.model.fac_list, 11); + r = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_CPU_TOPOLOGY %s", + r ? "(not available)" : "(success)"); + break; default: r = -EINVAL; break; @@ -1789,6 +1806,31 @@ static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val) read_unlock(&kvm->arch.sca_lock); } +static int kvm_s390_set_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + kvm_s390_update_topology_change_report(kvm, !!attr->attr); + return 0; +} + +static int kvm_s390_get_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + u8 topo; + + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + read_lock(&kvm->arch.sca_lock); + topo = ((struct bsca_block *)kvm->arch.sca)->utility.mtcr; + read_unlock(&kvm->arch.sca_lock); + + return put_user(topo, (u8 __user *)attr->addr); +} + static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { int ret; @@ -1809,6 +1851,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_set_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_set_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1834,6 +1879,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_get_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_get_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1907,6 +1955,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = 0; break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = test_kvm_facility(kvm, 11) ? 0 : -ENXIO; + break; default: ret = -ENXIO; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 20817dd7f2f1..7e06194129e3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1168,6 +1168,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_NOTIFY_VMEXIT 219 #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #define KVM_CAP_S390_ZPCI_OP 221 +#define KVM_CAP_S390_CPU_TOPOLOGY 222 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From d0b55afa47694f6f61b40f578ede7bde1648fe48 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Wed, 6 Jul 2022 17:20:52 -0700 Subject: dmaengine: idxd: Correct IAX operation code names Some IAX operation code nomenclatures are misleading or don't match with others: 1. Operation code 0x4c is Zero Compress 32. IAX_OPCODE_DECOMP_32 is a misleading name. Change it to IAX_OPCODE_ZERO_COMP_32. 2. Operation code 0x4d is Zero Compress 16. IAX_OPCODE_DECOMP_16 is a misleading name. Change it to IAX_OPCODE_ZERO_COMP_16. 3. IAX_OPCDE_FIND_UNIQUE is corrected to match with other nomenclatures. Co-developed-by: Li Zhang Signed-off-by: Li Zhang Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20220707002052.1546361-1-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index bce7c43657d5..095299c75828 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -89,14 +89,14 @@ enum iax_opcode { IAX_OPCODE_CRC64, IAX_OPCODE_ZERO_DECOMP_32 = 0x48, IAX_OPCODE_ZERO_DECOMP_16, - IAX_OPCODE_DECOMP_32 = 0x4c, - IAX_OPCODE_DECOMP_16, + IAX_OPCODE_ZERO_COMP_32 = 0x4c, + IAX_OPCODE_ZERO_COMP_16, IAX_OPCODE_SCAN = 0x50, IAX_OPCODE_SET_MEMBER, IAX_OPCODE_EXTRACT, IAX_OPCODE_SELECT, IAX_OPCODE_RLE_BURST, - IAX_OPCDE_FIND_UNIQUE, + IAX_OPCODE_FIND_UNIQUE, IAX_OPCODE_EXPAND, }; -- cgit v1.2.3 From 5f8bcc837a9640ba4bf5e7b1d7f9b254ea029f47 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Jul 2022 15:09:10 +0200 Subject: ublk: remove UBLK_IO_F_PREFLUSH REQ_PREFLUSH is turned into REQ_OP_FLUSH by the flush state machine and thus never seen by a blk-mq based driver. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220721130916.1869719-3-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 3 --- include/uapi/linux/ublk_cmd.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index b90481b295a7..07913b5bccd9 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -392,9 +392,6 @@ static inline unsigned int ublk_req_build_flags(struct request *req) if (req->cmd_flags & REQ_FUA) flags |= UBLK_IO_F_FUA; - if (req->cmd_flags & REQ_PREFLUSH) - flags |= UBLK_IO_F_PREFLUSH; - if (req->cmd_flags & REQ_NOUNMAP) flags |= UBLK_IO_F_NOUNMAP; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index d6879eea2fde..917580b34198 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -107,7 +107,6 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_F_FAILFAST_DRIVER (1U << 10) #define UBLK_IO_F_META (1U << 11) #define UBLK_IO_F_FUA (1U << 13) -#define UBLK_IO_F_PREFLUSH (1U << 14) #define UBLK_IO_F_NOUNMAP (1U << 15) #define UBLK_IO_F_SWAP (1U << 16) -- cgit v1.2.3 From 9dd1953846c7cd58100a5c6bd90db54e2c60668a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 19 Jul 2022 10:26:50 +0200 Subject: wifi: nl80211/mac80211: clarify link ID in control port TX Clarify the link ID behaviour in control port TX, we need it to select the link to transmit on for both MLD and non-MLD receivers, but select the link address as the SA only if the receiver is not an MLD. Fixes: 67207bab9341 ("wifi: cfg80211/mac80211: Support control port TX from specific link") Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 6 ++++++ net/mac80211/tx.c | 43 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 47 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3fa586e38f88..d4d6ba585b41 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1119,6 +1119,12 @@ * has been received. %NL80211_ATTR_FRAME is used to specify the * frame contents. The frame is the raw EAPoL data, without ethernet or * 802.11 headers. + * For an MLD transmitter, the %NL80211_ATTR_MLO_LINK_ID may be given and + * its effect will depend on the destination: If the destination is known + * to be an MLD, this will be used as a hint to select the link to transmit + * the frame on. If the destination is not an MLD, this will select both + * the link to transmit on and the source address will be set to the link + * address of that link. * When used as an event indication %NL80211_ATTR_CONTROL_PORT_ETHERTYPE, * %NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT and %NL80211_ATTR_MAC are added * indicating the protocol type of the received frame; whether the frame diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 772108c2cc6b..06ec152e8188 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2896,9 +2896,35 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, info->flags = info_flags; info->ack_frame_id = info_id; info->band = band; - info->control.flags = ctrl_flags | - u32_encode_bits(link_id, + + if (likely(!cookie)) { + ctrl_flags |= u32_encode_bits(link_id, IEEE80211_TX_CTRL_MLO_LINK); + } else { + unsigned int pre_conf_link_id; + + /* + * ctrl_flags already have been set by + * ieee80211_tx_control_port(), here + * we just sanity check that + */ + + pre_conf_link_id = u32_get_bits(ctrl_flags, + IEEE80211_TX_CTRL_MLO_LINK); + + if (pre_conf_link_id != link_id && + link_id != IEEE80211_LINK_UNSPECIFIED) { +#ifdef CPTCFG_MAC80211_VERBOSE_DEBUG + net_info_ratelimited("%s: dropped frame to %pM with bad link ID request (%d vs. %d)\n", + sdata->name, hdr.addr1, + pre_conf_link_id, link_id); +#endif + ret = -EINVAL; + goto free; + } + } + + info->control.flags = ctrl_flags; return skb; free: @@ -5745,11 +5771,17 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr->h_dest, dest, ETH_ALEN); + /* we may override the SA for MLO STA later */ if (link_id < 0) { + ctrl_flags |= u32_encode_bits(IEEE80211_LINK_UNSPECIFIED, + IEEE80211_TX_CTRL_MLO_LINK); memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN); } else { struct ieee80211_bss_conf *link_conf; + ctrl_flags |= u32_encode_bits(link_id, + IEEE80211_TX_CTRL_MLO_LINK); + rcu_read_lock(); link_conf = rcu_dereference(sdata->vif.link_conf[link_id]); if (!link_conf) { @@ -5784,6 +5816,13 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_set_queue_mapping(skb, queue); skb_get_hash(skb); + + /* + * for MLO STA, the SA should be the AP MLD address, but + * the link ID has been selected already + */ + if (sta->sta.mlo) + memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN); } rcu_read_unlock(); -- cgit v1.2.3 From 80b0ed70a271d375feb2286696ca8af147a035cf Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Wed, 26 Jan 2022 16:06:35 +0200 Subject: wifi: nl80211: add RX and TX timestamp attributes Add attributes for reporting hardware timestamps for management frames RX and TX. These attributes will be used for reporting hardware timestamps for Timing measurement and Fine Timing Measurement action frames, which will allow userspace applications to measure the path delay between devices and sync clocks. For TX, these attributes are used for reporting the frame RX time and the ack TX time. For TX, they are used for reporting the frame TX time and the ack RX time. Signed-off-by: Avraham Stern Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d4d6ba585b41..5275dcbc5ee8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -764,6 +764,9 @@ * %NL80211_ATTR_CSA_C_OFFSETS_TX is an array of offsets to CSA * counters which will be updated to the current value. This attribute * is used during CSA period. + * For RX notification, %NL80211_ATTR_RX_HW_TIMESTAMP may be included to + * indicate the frame RX timestamp and %NL80211_ATTR_TX_HW_TIMESTAMP may + * be included to indicate the ack TX timestamp. * @NL80211_CMD_FRAME_WAIT_CANCEL: When an off-channel TX was requested, this * command may be used with the corresponding cookie to cancel the wait * time if it is known that it is no longer necessary. This command is @@ -774,7 +777,9 @@ * transmitted with %NL80211_CMD_FRAME. %NL80211_ATTR_COOKIE identifies * the TX command and %NL80211_ATTR_FRAME includes the contents of the * frame. %NL80211_ATTR_ACK flag is included if the recipient acknowledged - * the frame. + * the frame. %NL80211_ATTR_TX_HW_TIMESTAMP may be included to indicate the + * tx timestamp and %NL80211_ATTR_RX_HW_TIMESTAMP may be included to + * indicate the ack RX timestamp. * @NL80211_CMD_ACTION_TX_STATUS: Alias for @NL80211_CMD_FRAME_TX_STATUS for * backward compatibility. * @@ -2720,6 +2725,18 @@ enum nl80211_commands { * @NL80211_ATTR_EML_CAPABILITY: EML Capability information (u16) * @NL80211_ATTR_MLD_CAPA_AND_OPS: MLD Capabilities and Operations (u16) * + * @NL80211_ATTR_TX_HW_TIMESTAMP: Hardware timestamp for TX operation in + * nanoseconds (u64). This is the device clock timestamp so it will + * probably reset when the device is stopped or the firmware is reset. + * When used with %NL80211_CMD_FRAME_TX_STATUS, indicates the frame TX + * timestamp. When used with %NL80211_CMD_FRAME RX notification, indicates + * the ack TX timestamp. + * @NL80211_ATTR_RX_HW_TIMESTAMP: Hardware timestamp for RX operation in + * nanoseconds (u64). This is the device clock timestamp so it will + * probably reset when the device is stopped or the firmware is reset. + * When used with %NL80211_CMD_FRAME_TX_STATUS, indicates the ack RX + * timestamp. When used with %NL80211_CMD_FRAME RX notification, indicates + * the incoming frame RX timestamp. * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3245,6 +3262,9 @@ enum nl80211_attrs { NL80211_ATTR_EML_CAPABILITY, NL80211_ATTR_MLD_CAPA_AND_OPS, + NL80211_ATTR_TX_HW_TIMESTAMP, + NL80211_ATTR_RX_HW_TIMESTAMP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 95f498bb49f7030c1f40236107e5241e50f79ade Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 18 Jul 2022 12:13:46 +0200 Subject: wifi: nl80211: add MLO link ID to the NL80211_CMD_FRAME TX API Allow optionally specifying the link ID to transmit on, which can be done instead of the link frequency, on an MLD addressed frame. Both can also be omitted in which case the frame must be MLD addressed and link selection (and address translation) will be done on lower layers. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 4 ++++ net/wireless/nl80211.c | 12 ++++++++++++ 3 files changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8545ed098d90..908d58393484 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3411,6 +3411,9 @@ struct cfg80211_update_ft_ies_params { * @dont_wait_for_ack: tells the low level not to wait for an ack * @n_csa_offsets: length of csa_offsets array * @csa_offsets: array of all the csa offsets in the frame + * @link_id: for MLO, the link ID to transmit on, -1 if not given; note + * that the link ID isn't validated (much), it's in range but the + * link might not exist (or be used by the receiver STA) */ struct cfg80211_mgmt_tx_params { struct ieee80211_channel *chan; @@ -3422,6 +3425,7 @@ struct cfg80211_mgmt_tx_params { bool dont_wait_for_ack; int n_csa_offsets; const u16 *csa_offsets; + int link_id; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5275dcbc5ee8..ffb7c573e299 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -764,6 +764,10 @@ * %NL80211_ATTR_CSA_C_OFFSETS_TX is an array of offsets to CSA * counters which will be updated to the current value. This attribute * is used during CSA period. + * For TX on an MLD, the frequency can be omitted and the link ID be + * specified, or if transmitting to a known peer MLD (with MLD addresses + * in the frame) both can be omitted and the link will be selected by + * lower layers. * For RX notification, %NL80211_ATTR_RX_HW_TIMESTAMP may be included to * indicate the frame RX timestamp and %NL80211_ATTR_TX_HW_TIMESTAMP may * be included to indicate the ack TX timestamp. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 60b8406b8d7e..2705e3ee8fc4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12256,6 +12256,18 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); return -EBUSY; } + + params.link_id = nl80211_link_id_or_invalid(info->attrs); + /* + * This now races due to the unlock, but we cannot check + * the valid links for the _station_ anyway, so that's up + * to the driver. + */ + if (params.link_id >= 0 && + !(wdev->valid_links & BIT(params.link_id))) { + wdev_unlock(wdev); + return -EINVAL; + } wdev_unlock(wdev); params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); -- cgit v1.2.3 From 6d8c5afc9ab14595707ff25d971dde45728eba3e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jul 2022 18:38:17 +0800 Subject: ublk_drv: make sure that correct flags(features) returned to userspace Userspace may support more features or new added flags, but the driver side can be old, so make sure correct flags(features) returned to userpsace, then userspace can work as expected. Also mark the 2nd flags as reversed, just use the 1st one. When we run out of flags, the reserved one can be handled at that time. Reviewed-by: Christoph Hellwig Reviewed-by: ZiyangZhang Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220722103817.631258-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 17 ++++++++++++++--- include/uapi/linux/ublk_cmd.h | 7 ++++--- 2 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 67f91a80a7ab..255b2de46a24 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -46,6 +46,9 @@ #define UBLK_MINORS (1U << MINORBITS) +/* All UBLK_F_* have to be included into UBLK_F_ALL */ +#define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_URING_CMD_COMP_IN_TASK) + struct ublk_rq_data { struct callback_head work; }; @@ -953,7 +956,7 @@ static int ublk_init_queue(struct ublk_device *ub, int q_id) void *ptr; int size; - ubq->flags = ub->dev_info.flags[0]; + ubq->flags = ub->dev_info.flags; ubq->q_id = q_id; ubq->q_depth = ub->dev_info.queue_depth; size = ublk_queue_cmd_buf_size(ub, q_id); @@ -1246,7 +1249,7 @@ out_put_device: static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) { pr_devel("%s: dev id %d flags %llx\n", __func__, - info->dev_id, info->flags[0]); + info->dev_id, info->flags); pr_devel("\t nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n", info->nr_hw_queues, info->queue_depth, info->block_size, info->dev_blocks); @@ -1298,8 +1301,16 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) /* update device id */ ub->dev_info.dev_id = ub->ub_number; + /* + * 64bit flags will be copied back to userspace as feature + * negotiation result, so have to clear flags which driver + * doesn't support yet, then userspace can get correct flags + * (features) to handle. + */ + ub->dev_info.flags &= UBLK_F_ALL; + /* We are not ready to support zero copy */ - ub->dev_info.flags[0] &= ~UBLK_F_SUPPORT_ZERO_COPY; + ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; ub->bs_shift = ilog2(ub->dev_info.block_size); ub->dev_info.nr_hw_queues = min_t(unsigned int, diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 917580b34198..ca33092354ab 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -46,13 +46,13 @@ * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space */ -#define UBLK_F_SUPPORT_ZERO_COPY (1UL << 0) +#define UBLK_F_SUPPORT_ZERO_COPY (1ULL << 0) /* * Force to complete io cmd via io_uring_cmd_complete_in_task so that * performance comparison is done easily with using task_work_add */ -#define UBLK_F_URING_CMD_COMP_IN_TASK (1UL << 1) +#define UBLK_F_URING_CMD_COMP_IN_TASK (1ULL << 1) /* device state */ #define UBLK_S_DEV_DEAD 0 @@ -88,7 +88,8 @@ struct ublksrv_ctrl_dev_info { __s32 ublksrv_pid; __s32 reserved0; - __u64 flags[2]; + __u64 flags; + __u64 flags_reserved; /* For ublksrv internal use, invisible to ublk driver */ __u64 ublksrv_flags; -- cgit v1.2.3 From b9ba8a4463cd78d0aee520c4bf2569820ac29929 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 27 May 2022 10:55:07 -0600 Subject: io_uring: add support for level triggered poll By default, the POLL_ADD command does edge triggered poll - if we get a non-zero mask on the initial poll attempt, we complete the request successfully. Support level triggered by always waiting for a notification, regardless of whether or not the initial mask matches the file state. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ io_uring/poll.c | 15 ++++++++++----- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0ad3da28d2fc..4927bb69387a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -229,10 +229,13 @@ enum io_uring_op { * * IORING_POLL_UPDATE Update existing poll request, matching * sqe->addr as the old user_data field. + * + * IORING_POLL_LEVEL Level triggered poll. */ #define IORING_POLL_ADD_MULTI (1U << 0) #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +#define IORING_POLL_ADD_LEVEL (1U << 3) /* * ASYNC_CANCEL flags. diff --git a/io_uring/poll.c b/io_uring/poll.c index b80f7fa26123..558dc170468a 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -423,11 +423,13 @@ static int __io_arm_poll_handler(struct io_kiocb *req, atomic_set(&req->poll_refs, 1); mask = vfs_poll(req->file, &ipt->pt) & poll->events; - if (mask && (poll->events & EPOLLONESHOT)) { + if (mask && + ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) { io_poll_remove_entries(req); /* no one else has access to the req, forget about the ref */ return mask; } + if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { io_poll_remove_entries(req); if (!ipt->error) @@ -439,7 +441,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, io_poll_req_insert(req); spin_unlock(&ctx->completion_lock); - if (mask) { + if (mask && (poll->events & EPOLLET)) { /* can't multishot if failed, just queue the event we've got */ if (unlikely(ipt->error || !ipt->nr_entries)) { poll->events |= EPOLLONESHOT; @@ -475,7 +477,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask = POLLPRI | POLLERR; + __poll_t mask = POLLPRI | POLLERR | EPOLLET; int ret; if (!def->pollin && !def->pollout) @@ -638,7 +640,10 @@ static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, #endif if (!(flags & IORING_POLL_ADD_MULTI)) events |= EPOLLONESHOT; - return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); + if (!(flags & IORING_POLL_ADD_LEVEL)) + events |= EPOLLET; + return demangle_poll(events) | + (events & (EPOLLEXCLUSIVE|EPOLLONESHOT|EPOLLET)); } int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -679,7 +684,7 @@ int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); - if (flags & ~IORING_POLL_ADD_MULTI) + if (flags & ~(IORING_POLL_ADD_MULTI|IORING_POLL_ADD_LEVEL)) return -EINVAL; if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) return -EINVAL; -- cgit v1.2.3 From 97bbdc06a4446bc69d8ba71d722abae542a6b70c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 16 Jun 2022 10:22:08 +0100 Subject: io_uring: add IORING_SETUP_SINGLE_ISSUER Add a new IORING_SETUP_SINGLE_ISSUER flag and the userspace visible part of it, i.e. put limitations of submitters. Also, don't allow it together with IOPOLL as we're not going to put it to good use. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4bcc41ee467fdf04c8aab8baf6ce3ba21858c3d4.1655371007.git.asml.silence@gmail.com Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 ++++- io_uring/io_uring.c | 7 +++++-- io_uring/io_uring_types.h | 1 + io_uring/tctx.c | 27 ++++++++++++++++++++++++--- io_uring/tctx.h | 4 ++-- 5 files changed, 36 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4927bb69387a..d7ae81b10893 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -140,9 +140,12 @@ enum { * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) - #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ #define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ +/* + * Only one task is allowed to submit requests + */ +#define IORING_SETUP_SINGLE_ISSUER (1U << 12) enum io_uring_op { IORING_OP_NOP, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 85a479594b05..06772139b7da 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2457,6 +2457,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_destroy_buffers(ctx); if (ctx->sq_creds) put_cred(ctx->sq_creds); + if (ctx->submitter_task) + put_task_struct(ctx->submitter_task); /* there are no registered resources left, nobody uses it */ if (ctx->rsrc_node) @@ -3189,7 +3191,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = io_uring_add_tctx_node(ctx); + ret = __io_uring_add_tctx_node(ctx, false); if (ret) { put_unused_fd(fd); return ret; @@ -3409,7 +3411,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | - IORING_SETUP_SQE128 | IORING_SETUP_CQE32)) + IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | + IORING_SETUP_SINGLE_ISSUER)) return -EINVAL; return io_uring_create(entries, &p, params); diff --git a/io_uring/io_uring_types.h b/io_uring/io_uring_types.h index 1f8db2dd7af7..8b00243abf65 100644 --- a/io_uring/io_uring_types.h +++ b/io_uring/io_uring_types.h @@ -243,6 +243,7 @@ struct io_ring_ctx { /* Keep this last, we don't need it for the fast path */ struct io_restriction restrictions; + struct task_struct *submitter_task; /* slow path rsrc auxilary data, used by update/register */ struct io_rsrc_node *rsrc_backup_node; diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 5a5d4f908529..a819da8fc85c 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -94,12 +94,32 @@ __cold int io_uring_alloc_task_context(struct task_struct *task, return 0; } -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) +static int io_register_submitter(struct io_ring_ctx *ctx) +{ + int ret = 0; + + mutex_lock(&ctx->uring_lock); + if (!ctx->submitter_task) + ctx->submitter_task = get_task_struct(current); + else if (ctx->submitter_task != current) + ret = -EEXIST; + mutex_unlock(&ctx->uring_lock); + + return ret; +} + +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; int ret; + if ((ctx->flags & IORING_SETUP_SINGLE_ISSUER) && submitter) { + ret = io_register_submitter(ctx); + if (ret) + return ret; + } + if (unlikely(!tctx)) { ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) @@ -133,7 +153,8 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) list_add(&node->ctx_node, &ctx->tctx_list); mutex_unlock(&ctx->uring_lock); } - tctx->last = ctx; + if (submitter) + tctx->last = ctx; return 0; } @@ -241,7 +262,7 @@ int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, return -EINVAL; mutex_unlock(&ctx->uring_lock); - ret = io_uring_add_tctx_node(ctx); + ret = __io_uring_add_tctx_node(ctx, false); mutex_lock(&ctx->uring_lock); if (ret) return ret; diff --git a/io_uring/tctx.h b/io_uring/tctx.h index 7684713e950f..dde82ce4d8e2 100644 --- a/io_uring/tctx.h +++ b/io_uring/tctx.h @@ -34,7 +34,7 @@ struct io_tctx_node { int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); void io_uring_del_tctx_node(unsigned long index); -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx); +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter); void io_uring_clean_tctx(struct io_uring_task *tctx); void io_uring_unreg_ringfd(void); @@ -52,5 +52,5 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) if (likely(tctx && tctx->last == ctx)) return 0; - return __io_uring_add_tctx_node(ctx); + return __io_uring_add_tctx_node(ctx, true); } -- cgit v1.2.3 From 7d8ca7250197096bfa9f432c1d99b0555504bbba Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 18 Jun 2022 09:47:04 -0600 Subject: io_uring: add IORING_ASYNC_CANCEL_FD_FIXED cancel flag In preparation for not having a request to pass in that carries this state, add a separate cancelation flag that allows the caller to ask for a fixed file for cancelation. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ io_uring/cancel.c | 9 ++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d7ae81b10893..a09a78bd7556 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -247,10 +247,12 @@ enum io_uring_op { * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' * IORING_ASYNC_CANCEL_ANY Match any request + * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) #define IORING_ASYNC_CANCEL_ANY (1U << 2) +#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3) /* * send/sendmsg and recv/recvmsg flags (sqe->ioprio) diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 500ee5f5fd23..da486de07029 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -24,7 +24,7 @@ struct io_cancel { }; #define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ - IORING_ASYNC_CANCEL_ANY) + IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED) static bool io_cancel_cb(struct io_wq_work *work, void *data) { @@ -174,11 +174,14 @@ int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) int ret; if (cd.flags & IORING_ASYNC_CANCEL_FD) { - if (req->flags & REQ_F_FIXED_FILE) + if (req->flags & REQ_F_FIXED_FILE || + cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { + req->flags |= REQ_F_FIXED_FILE; req->file = io_file_get_fixed(req, cancel->fd, issue_flags); - else + } else { req->file = io_file_get_normal(req, cancel->fd); + } if (!req->file) { ret = -EBADF; goto done; -- cgit v1.2.3 From 78a861b9495920f8609dee5b670dacbff09d359f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 18 Jun 2022 10:00:50 -0600 Subject: io_uring: add sync cancelation API through io_uring_register() The io_uring cancelation API is async, like any other API that we expose there. For the case of finding a request to cancel, or not finding one, it is fully sync in that when submission returns, the CQE for both the cancelation request and the targeted request have been posted to the CQ ring. However, if the targeted work is being executed by io-wq, the API can only start the act of canceling it. This makes it difficult to use in some circumstances, as the caller then has to wait for the CQEs to come in and match on the same cancelation data there. Provide a IORING_REGISTER_SYNC_CANCEL command for io_uring_register() that does sync cancelations, always. For the io-wq case, it'll wait for the cancelation to come in before returning. The only expected returns from this API is: 0 Request found and canceled fine. > 0 Requests found and canceled. Only happens if asked to cancel multiple requests, and if the work wasn't in progress. -ENOENT Request not found. -ETIME A timeout on the operation was requested, but the timeout expired before we could cancel. and we won't get -EALREADY via this API. If the timeout value passed in is -1 (tv_sec and tv_nsec), then that means that no timeout is requested. Otherwise, the timespec passed in is the amount of time the sync cancel will wait for a successful cancelation. Link: https://github.com/axboe/liburing/discussions/608 Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 15 ++++++ io_uring/cancel.c | 107 ++++++++++++++++++++++++++++++++++++++++++ io_uring/cancel.h | 2 + io_uring/io_uring.c | 6 +++ 4 files changed, 130 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a09a78bd7556..094f706c93e0 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -10,6 +10,7 @@ #include #include +#include /* * IO submission data structure (Submission Queue Entry) @@ -428,6 +429,9 @@ enum { IORING_REGISTER_PBUF_RING = 22, IORING_UNREGISTER_PBUF_RING = 23, + /* sync cancelation API */ + IORING_REGISTER_SYNC_CANCEL = 24, + /* this goes last */ IORING_REGISTER_LAST }; @@ -563,4 +567,15 @@ struct io_uring_getevents_arg { __u64 ts; }; +/* + * Argument for IORING_REGISTER_SYNC_CANCEL + */ +struct io_uring_sync_cancel_reg { + __u64 addr; + __s32 fd; + __u32 flags; + struct __kernel_timespec timeout; + __u64 pad[4]; +}; + #endif diff --git a/io_uring/cancel.c b/io_uring/cancel.c index da486de07029..8435a1eba59a 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -206,3 +207,109 @@ void init_hash_table(struct io_hash_table *table, unsigned size) INIT_HLIST_HEAD(&table->hbs[i].list); } } + +static int __io_sync_cancel(struct io_uring_task *tctx, + struct io_cancel_data *cd, int fd) +{ + struct io_ring_ctx *ctx = cd->ctx; + + /* fixed must be grabbed every time since we drop the uring_lock */ + if ((cd->flags & IORING_ASYNC_CANCEL_FD) && + (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + unsigned long file_ptr; + + if (unlikely(fd > ctx->nr_user_files)) + return -EBADF; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + cd->file = (struct file *) (file_ptr & FFS_MASK); + if (!cd->file) + return -EBADF; + } + + return __io_async_cancel(cd, tctx, 0); +} + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_cancel_data cd = { + .ctx = ctx, + .seq = atomic_inc_return(&ctx->cancel_seq), + }; + ktime_t timeout = KTIME_MAX; + struct io_uring_sync_cancel_reg sc; + struct fd f = { }; + DEFINE_WAIT(wait); + int ret; + + if (copy_from_user(&sc, arg, sizeof(sc))) + return -EFAULT; + if (sc.flags & ~CANCEL_FLAGS) + return -EINVAL; + if (sc.pad[0] || sc.pad[1] || sc.pad[2] || sc.pad[3]) + return -EINVAL; + + cd.data = sc.addr; + cd.flags = sc.flags; + + /* we can grab a normal file descriptor upfront */ + if ((cd.flags & IORING_ASYNC_CANCEL_FD) && + !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { + f = fdget(sc.fd); + if (!f.file) + return -EBADF; + cd.file = f.file; + } + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + /* found something, done! */ + if (ret != -EALREADY) + goto out; + + if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { + struct timespec64 ts = { + .tv_sec = sc.timeout.tv_sec, + .tv_nsec = sc.timeout.tv_nsec + }; + + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + + /* + * Keep looking until we get -ENOENT. we'll get woken everytime + * every time a request completes and will retry the cancelation. + */ + do { + cd.seq = atomic_inc_return(&ctx->cancel_seq); + + prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); + + ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + + if (ret != -EALREADY) + break; + + mutex_unlock(&ctx->uring_lock); + ret = io_run_task_work_sig(); + if (ret < 0) { + mutex_lock(&ctx->uring_lock); + break; + } + ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); + mutex_lock(&ctx->uring_lock); + if (!ret) { + ret = -ETIME; + break; + } + } while (1); + + finish_wait(&ctx->cq_wait, &wait); + + if (ret == -ENOENT || ret > 0) + ret = 0; +out: + fdput(f); + return ret; +} diff --git a/io_uring/cancel.h b/io_uring/cancel.h index 1bc7e917ce94..6a59ee484d0c 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -19,3 +19,5 @@ int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags); int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned int issue_flags); void init_hash_table(struct io_hash_table *table, unsigned size); + +int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 997b915a1ff7..45538b3c3a76 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3871,6 +3871,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_unregister_pbuf_ring(ctx, arg); break; + case IORING_REGISTER_SYNC_CANCEL: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_sync_cancel(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit v1.2.3 From 8fcf4c48f44bd7b1b75db139f56ff1ad6477379e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 28 Jun 2022 21:33:20 +0200 Subject: io_uring: replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/78 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 094f706c93e0..8fe0275cdaf3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -495,7 +495,7 @@ struct io_uring_probe { __u8 ops_len; /* length of ops[] array below */ __u16 resv; __u32 resv2[3]; - struct io_uring_probe_op ops[0]; + struct io_uring_probe_op ops[]; }; struct io_uring_restriction { -- cgit v1.2.3 From e6130eba8a848a7a6ba6c534bd8f6d60749ae1a9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 13 Jun 2022 04:47:02 -0600 Subject: io_uring: add support for passing fixed file descriptors With IORING_OP_MSG_RING, one ring can send a message to another ring. Extend that support to also allow sending a fixed file descriptor to that ring, enabling one ring to pass a registered descriptor to another one. Arguments are extended to pass in: sqe->addr3 fixed file slot in source ring sqe->file_index fixed file slot in destination ring IORING_OP_MSG_RING is extended to take a command argument in sqe->addr. If set to zero (or IORING_MSG_DATA), it sends just a message like before. If set to IORING_MSG_SEND_FD, a fixed file descriptor is sent according to the above arguments. Two common use cases for this are: 1) Server needs to be shutdown or restarted, pass file descriptors to another onei 2) Backend is split, and one accepts connections, while others then get the fd passed and handle the actual connection. Both of those are classic SCM_RIGHTS use cases, and it's not possible to support them with direct descriptors today. By default, this will post a CQE to the target ring, similarly to how IORING_MSG_DATA does it. If IORING_MSG_RING_CQE_SKIP is set, no message is posted to the target ring. The issuer is expected to notify the receiver side separately. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 17 ++++++ io_uring/msg_ring.c | 130 +++++++++++++++++++++++++++++++++++++++--- 2 files changed, 140 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8fe0275cdaf3..f378eabbff21 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -51,6 +51,7 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; + __u32 msg_ring_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -270,6 +271,22 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +/* + * IORING_OP_MSG_RING command types, stored in sqe->addr + */ +enum { + IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ + IORING_MSG_SEND_FD, /* send a registered fd to another ring */ +}; + +/* + * IORING_OP_MSG_RING flags (sqe->msg_ring_flags) + * + * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not + * applicable for IORING_MSG_DATA, obviously. + */ +#define IORING_MSG_RING_CQE_SKIP (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index b02be2349652..939205b30c8b 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -3,46 +3,162 @@ #include #include #include +#include #include #include #include "io_uring.h" +#include "rsrc.h" +#include "filetable.h" #include "msg_ring.h" struct io_msg { struct file *file; u64 user_data; u32 len; + u32 cmd; + u32 src_fd; + u32 dst_fd; + u32 flags; }; +static int io_msg_ring_data(struct io_kiocb *req) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + + if (msg->src_fd || msg->dst_fd || msg->flags) + return -EINVAL; + + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + return 0; + + return -EOVERFLOW; +} + +static void io_double_unlock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); + mutex_unlock(&octx->uring_lock); +} + +static int io_double_lock_ctx(struct io_ring_ctx *ctx, + struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + /* + * To ensure proper ordering between the two ctxs, we can only + * attempt a trylock on the target. If that fails and we already have + * the source ctx lock, punt to io-wq. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + if (!mutex_trylock(&octx->uring_lock)) + return -EAGAIN; + return 0; + } + + /* Always grab smallest value ctx first. We know ctx != octx. */ + if (ctx < octx) { + mutex_lock(&ctx->uring_lock); + mutex_lock(&octx->uring_lock); + } else { + mutex_lock(&octx->uring_lock); + mutex_lock(&ctx->uring_lock); + } + + return 0; +} + +static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned long file_ptr; + struct file *src_file; + int ret; + + if (target_ctx == ctx) + return -EINVAL; + + ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); + if (unlikely(ret)) + return ret; + + ret = -EBADF; + if (unlikely(msg->src_fd >= ctx->nr_user_files)) + goto out_unlock; + + msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; + src_file = (struct file *) (file_ptr & FFS_MASK); + get_file(src_file); + + ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); + if (ret < 0) { + fput(src_file); + goto out_unlock; + } + + if (msg->flags & IORING_MSG_RING_CQE_SKIP) + goto out_unlock; + + /* + * If this fails, the target still received the file descriptor but + * wasn't notified of the fact. This means that if this request + * completes with -EOVERFLOW, then the sender must ensure that a + * later IORING_OP_MSG_RING delivers the message. + */ + if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + ret = -EOVERFLOW; +out_unlock: + io_double_unlock_ctx(ctx, target_ctx, issue_flags); + return ret; +} + int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_msg *msg = io_kiocb_to_cmd(req); - if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in || - sqe->buf_index || sqe->personality)) + if (unlikely(sqe->buf_index || sqe->personality)) return -EINVAL; msg->user_data = READ_ONCE(sqe->off); msg->len = READ_ONCE(sqe->len); + msg->cmd = READ_ONCE(sqe->addr); + msg->src_fd = READ_ONCE(sqe->addr3); + msg->dst_fd = READ_ONCE(sqe->file_index); + msg->flags = READ_ONCE(sqe->msg_ring_flags); + if (msg->flags & ~IORING_MSG_RING_CQE_SKIP) + return -EINVAL; + return 0; } int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) { struct io_msg *msg = io_kiocb_to_cmd(req); - struct io_ring_ctx *target_ctx; int ret; ret = -EBADFD; if (!io_is_uring_fops(req->file)) goto done; - ret = -EOVERFLOW; - target_ctx = req->file->private_data; - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) - ret = 0; + switch (msg->cmd) { + case IORING_MSG_DATA: + ret = io_msg_ring_data(req); + break; + case IORING_MSG_SEND_FD: + ret = io_msg_send_fd(req, issue_flags); + break; + default: + ret = -EINVAL; + break; + } done: if (ret < 0) -- cgit v1.2.3 From 6e73dffbb93cb8797cd4e42e98d837edf0f1a967 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 25 Jun 2022 11:55:38 +0100 Subject: io_uring: let to set a range for file slot allocation From recently io_uring provides an option to allocate a file index for operation registering fixed files. However, it's utterly unusable with mixed approaches when for a part of files the userspace knows better where to place it, as it may race and users don't have any sane way to pick a slot and hoping it will not be taken. Let the userspace to register a range of fixed file slots in which the auto-allocation happens. The use case is splittting the fixed table in two parts, where on of them is used for auto-allocation and another for slot-specified operations. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/66ab0394e436f38437cf7c44676e1920d09687ad.1656154403.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 +++ include/uapi/linux/io_uring.h | 13 +++++++++++++ io_uring/filetable.c | 24 ++++++++++++++++++++---- io_uring/filetable.h | 20 +++++++++++++++++--- io_uring/io_uring.c | 6 ++++++ io_uring/rsrc.c | 2 ++ 6 files changed, 61 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3ca8f363f504..26ef11e978d4 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -233,6 +233,9 @@ struct io_ring_ctx { unsigned long check_cq; + unsigned int file_alloc_start; + unsigned int file_alloc_end; + struct { /* * We cache a range of free CQEs we can use, once exhausted it diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f378eabbff21..cf95354198a3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -449,6 +449,9 @@ enum { /* sync cancelation API */ IORING_REGISTER_SYNC_CANCEL = 24, + /* register a range of fixed file slots for automatic slot allocation */ + IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* this goes last */ IORING_REGISTER_LAST }; @@ -595,4 +598,14 @@ struct io_uring_sync_cancel_reg { __u64 pad[4]; }; +/* + * Argument for IORING_REGISTER_FILE_ALLOC_RANGE + * The range is specified as [off, off + len) + */ +struct io_uring_file_index_range { + __u32 off; + __u32 len; + __u64 resv; +}; + #endif diff --git a/io_uring/filetable.c b/io_uring/filetable.c index abaa5ba7f655..7b473259f3f4 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -16,7 +16,7 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) { struct io_file_table *table = &ctx->file_table; - unsigned long nr = ctx->nr_user_files; + unsigned long nr = ctx->file_alloc_end; int ret; do { @@ -24,11 +24,10 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) if (ret != nr) return ret; - if (!table->alloc_hint) + if (table->alloc_hint == ctx->file_alloc_start) break; - nr = table->alloc_hint; - table->alloc_hint = 0; + table->alloc_hint = ctx->file_alloc_start; } while (1); return -ENFILE; @@ -175,3 +174,20 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) io_rsrc_node_switch(ctx, ctx->file_data); return 0; } + +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg) +{ + struct io_uring_file_index_range range; + u32 end; + + if (copy_from_user(&range, arg, sizeof(range))) + return -EFAULT; + if (check_add_overflow(range.off, range.len, &end)) + return -EOVERFLOW; + if (range.resv || end > ctx->nr_user_files) + return -EINVAL; + + io_file_table_set_alloc_range(ctx, range.off, range.len); + return 0; +} diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 79eb50c1980e..ff3a712e11bf 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -3,9 +3,7 @@ #define IOU_FILE_TABLE_H #include - -struct io_ring_ctx; -struct io_kiocb; +#include /* * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 @@ -33,6 +31,9 @@ int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, unsigned int file_slot); int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset); +int io_register_file_alloc_range(struct io_ring_ctx *ctx, + struct io_uring_file_index_range __user *arg); + unsigned int io_file_get_flags(struct file *file); static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) @@ -71,4 +72,17 @@ static inline void io_fixed_file_set(struct io_fixed_file *file_slot, file_slot->file_ptr = file_ptr; } +static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx) +{ + ctx->file_table.alloc_hint = ctx->file_alloc_start; +} + +static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx, + unsigned off, unsigned len) +{ + ctx->file_alloc_start = off; + ctx->file_alloc_end = off + len; + io_reset_alloc_hint(ctx); +} + #endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 070ee9ec9ee7..745264938a48 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3866,6 +3866,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sync_cancel(ctx, arg); break; + case IORING_REGISTER_FILE_ALLOC_RANGE: + ret = -EINVAL; + if (!arg || nr_args) + break; + ret = io_register_file_alloc_range(ctx, arg); + break; default: ret = -EINVAL; break; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 706fa020505b..d2e589c703d0 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1012,6 +1012,8 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, io_file_bitmap_set(&ctx->file_table, i); } + /* default it to the whole table */ + io_file_table_set_alloc_range(ctx, 0, ctx->nr_user_files); io_rsrc_node_switch(ctx, NULL); return 0; fail: -- cgit v1.2.3 From b3fdea6ecb55c3ceea866ff66486927e51a982b3 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 30 Jun 2022 02:12:29 -0700 Subject: io_uring: multishot recv Support multishot receive for io_uring. Typical server applications will run a loop where for each recv CQE it requeues another recv/recvmsg. This can be simplified by using the existing multishot functionality combined with io_uring's provided buffers. The API is to add the IORING_RECV_MULTISHOT flag to the SQE. CQEs will then be posted (with IORING_CQE_F_MORE flag set) when data is available and is read. Once an error occurs or the socket ends, the multishot will be removed and a completion without IORING_CQE_F_MORE will be posted. The benefit to this is that the recv is much more performant. * Subsequent receives are queued up straight away without requiring the application to finish a processing loop. * If there are more data in the socket (sat the provided buffer size is smaller than the socket buffer) then the data is immediately returned, improving batching. * Poll is only armed once and reused, saving CPU cycles Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220630091231.1456789-11-dylany@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 +++ io_uring/net.c | 102 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 94 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cf95354198a3..499679134961 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -263,8 +263,13 @@ enum io_uring_op { * or receive and arm poll if that yields an * -EAGAIN result, arm poll upfront and skip * the initial transfer attempt. + * + * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if + * the handler will continue to report + * CQEs on behalf of the same SQE. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) +#define IORING_RECV_MULTISHOT (1U << 1) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/net.c b/io_uring/net.c index e1eaf902f3b2..cb08a4b62840 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -389,6 +389,8 @@ int io_recvmsg_prep_async(struct io_kiocb *req) return ret; } +#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT) + int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -399,13 +401,22 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); - if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + if (sr->flags & ~(RECVMSG_FLAGS)) return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; if (sr->msg_flags & MSG_ERRQUEUE) req->flags |= REQ_F_CLEAR_POLLIN; + if (sr->flags & IORING_RECV_MULTISHOT) { + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + if (sr->msg_flags & MSG_WAITALL) + return -EINVAL; + if (req->opcode == IORING_OP_RECV && sr->len) + return -EINVAL; + req->flags |= REQ_F_APOLL_MULTISHOT; + } #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -415,6 +426,48 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static inline void io_recv_prep_retry(struct io_kiocb *req) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req); + + sr->done_io = 0; + sr->len = 0; /* get from the provided buffer */ +} + +/* + * Finishes io_recv and io_recvmsg. + * + * Returns true if it is actually finished, or false if it should run + * again (for multishot). + */ +static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int cflags) +{ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + io_req_set_res(req, *ret, cflags); + *ret = IOU_OK; + return true; + } + + if (*ret > 0) { + if (io_post_aux_cqe(req->ctx, req->cqe.user_data, *ret, + cflags | IORING_CQE_F_MORE, false)) { + io_recv_prep_retry(req); + return false; + } + /* + * Otherwise stop multishot but use the current result. + * Probably will end up going into overflow, but this means + * we cannot trust the ordering anymore + */ + } + + io_req_set_res(req, *ret, cflags); + + if (req->flags & REQ_F_POLLED) + *ret = IOU_STOP_MULTISHOT; + return true; +} + int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -424,6 +477,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + size_t len = sr->len; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -442,16 +496,17 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return io_setup_async_msg(req, kmsg); +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; kmsg->fast_iov[0].iov_base = buf; - kmsg->fast_iov[0].iov_len = sr->len; + kmsg->fast_iov[0].iov_len = len; iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, - sr->len); + len); } flags = sr->msg_flags; @@ -463,8 +518,15 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg->msg.msg_get_inq = 1; ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return io_setup_async_msg(req, kmsg); + if (ret == -EAGAIN && force_nonblock) { + ret = io_setup_async_msg(req, kmsg); + if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -491,8 +553,11 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) cflags = io_put_kbuf(req, issue_flags); if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + + if (!io_recv_finish(req, &ret, cflags)) + goto retry_multishot; + + return ret; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) @@ -505,6 +570,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + size_t len = sr->len; if (!(req->flags & REQ_F_POLLED) && (sr->flags & IORING_RECVSEND_POLL_FIRST)) @@ -514,16 +580,17 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; sr->buf = buf; } - ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter); + ret = import_single_range(READ, sr->buf, len, &iov, &msg.msg_iter); if (unlikely(ret)) goto out_free; @@ -543,8 +610,14 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) ret = sock_recvmsg(sock, &msg, flags); if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) + if (ret == -EAGAIN && force_nonblock) { + if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return -EAGAIN; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -570,8 +643,11 @@ out_free: cflags = io_put_kbuf(req, issue_flags); if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + + if (!io_recv_finish(req, &ret, cflags)) + goto retry_multishot; + + return ret; } int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -- cgit v1.2.3 From 9bb66906f23e50d6db1e11f7498b72dfca1982a2 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 14 Jul 2022 04:02:58 -0700 Subject: io_uring: support multishot in recvmsg Similar to multishot recv, this will require provided buffers to be used. However recvmsg is much more complex than recv as it has multiple outputs. Specifically flags, name, and control messages. Support this by introducing a new struct io_uring_recvmsg_out with 4 fields. namelen, controllen and flags match the similar out fields in msghdr from standard recvmsg(2), payloadlen is the length of the payload following the header. This struct is placed at the start of the returned buffer. Based on what the user specifies in struct msghdr, the next bytes of the buffer will be name (the next msg_namelen bytes), and then control (the next msg_controllen bytes). The payload will come at the end. The return value in the CQE is the total used size of the provided buffer. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220714110258.1336200-4-dylany@fb.com [axboe: style fixups, see link] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 ++ io_uring/net.c | 180 +++++++++++++++++++++++++++++++++++++----- io_uring/net.h | 6 ++ 3 files changed, 174 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 499679134961..4c9b11e2e991 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -613,4 +613,11 @@ struct io_uring_file_index_range { __u64 resv; }; +struct io_uring_recvmsg_out { + __u32 namelen; + __u32 controllen; + __u32 payloadlen; + __u32 flags; +}; + #endif diff --git a/io_uring/net.c b/io_uring/net.c index 5bc3440a8290..616d5f04cc74 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -325,6 +325,21 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg) +{ + unsigned long hdr; + + if (check_add_overflow(sizeof(struct io_uring_recvmsg_out), + (unsigned long)iomsg->namelen, &hdr)) + return true; + if (check_add_overflow(hdr, iomsg->controllen, &hdr)) + return true; + if (hdr > INT_MAX) + return true; + + return false; +} + static int __io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { @@ -352,6 +367,13 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, sr->len = iomsg->fast_iov[0].iov_len; iomsg->free_iov = NULL; } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, @@ -399,6 +421,13 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, sr->len = clen; iomsg->free_iov = NULL; } + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + iomsg->namelen = msg.msg_namelen; + iomsg->controllen = msg.msg_controllen; + if (io_recvmsg_multishot_overflow(iomsg)) + return -EOVERFLOW; + } } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, msg.msg_iovlen, @@ -455,8 +484,6 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sr->msg_flags & MSG_ERRQUEUE) req->flags |= REQ_F_CLEAR_POLLIN; if (sr->flags & IORING_RECV_MULTISHOT) { - if (req->opcode == IORING_OP_RECVMSG) - return -EINVAL; if (!(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sr->msg_flags & MSG_WAITALL) @@ -483,12 +510,13 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) } /* - * Finishes io_recv + * Finishes io_recv and io_recvmsg. * * Returns true if it is actually finished, or false if it should run * again (for multishot). */ -static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int cflags) +static inline bool io_recv_finish(struct io_kiocb *req, int *ret, + unsigned int cflags, bool mshot_finished) { if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { io_req_set_res(req, *ret, cflags); @@ -496,7 +524,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int c return true; } - if (*ret > 0) { + if (!mshot_finished) { if (io_post_aux_cqe(req->ctx, req->cqe.user_data, *ret, cflags | IORING_CQE_F_MORE, false)) { io_recv_prep_retry(req); @@ -518,6 +546,90 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, unsigned int c return true; } +static int io_recvmsg_prep_multishot(struct io_async_msghdr *kmsg, + struct io_sr_msg *sr, void __user **buf, + size_t *len) +{ + unsigned long ubuf = (unsigned long) *buf; + unsigned long hdr; + + hdr = sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen; + if (*len < hdr) + return -EFAULT; + + if (kmsg->controllen) { + unsigned long control = ubuf + hdr - kmsg->controllen; + + kmsg->msg.msg_control_user = (void *) control; + kmsg->msg.msg_controllen = kmsg->controllen; + } + + sr->buf = *buf; /* stash for later copy */ + *buf = (void *) (ubuf + hdr); + kmsg->payloadlen = *len = *len - hdr; + return 0; +} + +struct io_recvmsg_multishot_hdr { + struct io_uring_recvmsg_out msg; + struct sockaddr_storage addr; +}; + +static int io_recvmsg_multishot(struct socket *sock, struct io_sr_msg *io, + struct io_async_msghdr *kmsg, + unsigned int flags, bool *finished) +{ + int err; + int copy_len; + struct io_recvmsg_multishot_hdr hdr; + + if (kmsg->namelen) + kmsg->msg.msg_name = &hdr.addr; + kmsg->msg.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + kmsg->msg.msg_namelen = 0; + + if (sock->file->f_flags & O_NONBLOCK) + flags |= MSG_DONTWAIT; + + err = sock_recvmsg(sock, &kmsg->msg, flags); + *finished = err <= 0; + if (err < 0) + return err; + + hdr.msg = (struct io_uring_recvmsg_out) { + .controllen = kmsg->controllen - kmsg->msg.msg_controllen, + .flags = kmsg->msg.msg_flags & ~MSG_CMSG_COMPAT + }; + + hdr.msg.payloadlen = err; + if (err > kmsg->payloadlen) + err = kmsg->payloadlen; + + copy_len = sizeof(struct io_uring_recvmsg_out); + if (kmsg->msg.msg_namelen > kmsg->namelen) + copy_len += kmsg->namelen; + else + copy_len += kmsg->msg.msg_namelen; + + /* + * "fromlen shall refer to the value before truncation.." + * 1003.1g + */ + hdr.msg.namelen = kmsg->msg.msg_namelen; + + /* ensure that there is no gap between hdr and sockaddr_storage */ + BUILD_BUG_ON(offsetof(struct io_recvmsg_multishot_hdr, addr) != + sizeof(struct io_uring_recvmsg_out)); + if (copy_to_user(io->buf, &hdr, copy_len)) { + *finished = true; + return -EFAULT; + } + + return sizeof(struct io_uring_recvmsg_out) + kmsg->namelen + + kmsg->controllen + err; +} + int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req); @@ -527,6 +639,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool mshot_finished = true; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -545,16 +658,27 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return io_setup_async_msg(req, kmsg, issue_flags); +retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; + size_t len = sr->len; - buf = io_buffer_select(req, &sr->len, issue_flags); + buf = io_buffer_select(req, &len, issue_flags); if (!buf) return -ENOBUFS; + + if (req->flags & REQ_F_APOLL_MULTISHOT) { + ret = io_recvmsg_prep_multishot(kmsg, sr, &buf, &len); + if (ret) { + io_kbuf_recycle(req, issue_flags); + return ret; + } + } + kmsg->fast_iov[0].iov_base = buf; - kmsg->fast_iov[0].iov_len = sr->len; + kmsg->fast_iov[0].iov_len = len; iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, - sr->len); + len); } flags = sr->msg_flags; @@ -564,10 +688,23 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&kmsg->msg.msg_iter); kmsg->msg.msg_get_inq = 1; - ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + if (req->flags & REQ_F_APOLL_MULTISHOT) + ret = io_recvmsg_multishot(sock, sr, kmsg, flags, + &mshot_finished); + else + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, + kmsg->uaddr, flags); + if (ret < min_ret) { - if (ret == -EAGAIN && force_nonblock) - return io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -EAGAIN && force_nonblock) { + ret = io_setup_async_msg(req, kmsg, issue_flags); + if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) { + io_kbuf_recycle(req, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { @@ -580,11 +717,6 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); } - /* fast path, check for non-NULL to avoid function call */ - if (kmsg->free_iov) - kfree(kmsg->free_iov); - io_netmsg_recycle(req, issue_flags); - req->flags &= ~REQ_F_NEED_CLEANUP; if (ret > 0) ret += sr->done_io; else if (sr->done_io) @@ -596,8 +728,18 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - io_req_set_res(req, ret, cflags); - return IOU_OK; + if (!io_recv_finish(req, &ret, cflags, mshot_finished)) + goto retry_multishot; + + if (mshot_finished) { + io_netmsg_recycle(req, issue_flags); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + } + + return ret; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) @@ -684,7 +826,7 @@ out_free: if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags)) + if (!io_recv_finish(req, &ret, cflags, ret <= 0)) goto retry_multishot; return ret; diff --git a/io_uring/net.h b/io_uring/net.h index 178a6d8b76e0..db20ce9d6546 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -9,6 +9,12 @@ struct io_async_msghdr { union { struct iovec fast_iov[UIO_FASTIOV]; + struct { + struct iovec fast_iov_one; + __kernel_size_t controllen; + int namelen; + __kernel_size_t payloadlen; + }; struct io_cache_entry cache; }; /* points to an allocated iov, if NULL we use fast_iov instead */ -- cgit v1.2.3 From bc24d6bd32df0be19df3d30e74be4ba56493c0e2 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:42 +0100 Subject: io_uring: add notification slot registration Let the userspace to register and unregister notification slots. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a0aa8161fe3ebb2a4cc6e5dbd0cffb96e6881cf5.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 17 +++++++++++++++++ io_uring/io_uring.c | 9 +++++++++ io_uring/notif.c | 43 +++++++++++++++++++++++++++++++++++++++++++ io_uring/notif.h | 3 +++ 4 files changed, 72 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4c9b11e2e991..dcfc7a0bda0c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -457,6 +457,10 @@ enum { /* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* zerocopy notification API */ + IORING_REGISTER_NOTIFIERS = 26, + IORING_UNREGISTER_NOTIFIERS = 27, + /* this goes last */ IORING_REGISTER_LAST }; @@ -503,6 +507,19 @@ struct io_uring_rsrc_update2 { __u32 resv2; }; +struct io_uring_notification_slot { + __u64 tag; + __u64 resv[3]; +}; + +struct io_uring_notification_register { + __u32 nr_slots; + __u32 resv; + __u64 resv2; + __u64 data; + __u64 resv3; +}; + /* Skip updating fd indexes set to this value in the fd table */ #define IORING_REGISTER_FILES_SKIP (-2) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 20e65d45ca1c..cae11374456e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3870,6 +3870,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_file_alloc_range(ctx, arg); break; + case IORING_REGISTER_NOTIFIERS: + ret = io_notif_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_NOTIFIERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_notif_unregister(ctx); + break; default: ret = -EINVAL; break; diff --git a/io_uring/notif.c b/io_uring/notif.c index 0a2e98bd74f6..e6d98dc208c7 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -162,5 +162,48 @@ __cold int io_notif_unregister(struct io_ring_ctx *ctx) kvfree(ctx->notif_slots); ctx->notif_slots = NULL; ctx->nr_notif_slots = 0; + io_notif_cache_purge(ctx); + return 0; +} + +__cold int io_notif_register(struct io_ring_ctx *ctx, + void __user *arg, unsigned int size) + __must_hold(&ctx->uring_lock) +{ + struct io_uring_notification_slot __user *slots; + struct io_uring_notification_slot slot; + struct io_uring_notification_register reg; + unsigned i; + + if (ctx->nr_notif_slots) + return -EBUSY; + if (size != sizeof(reg)) + return -EINVAL; + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS) + return -EINVAL; + if (reg.resv || reg.resv2 || reg.resv3) + return -EINVAL; + + slots = u64_to_user_ptr(reg.data); + ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]), + GFP_KERNEL_ACCOUNT); + if (!ctx->notif_slots) + return -ENOMEM; + + for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) { + struct io_notif_slot *notif_slot = &ctx->notif_slots[i]; + + if (copy_from_user(&slot, &slots[i], sizeof(slot))) { + io_notif_unregister(ctx); + return -EFAULT; + } + if (slot.resv[0] | slot.resv[1] | slot.resv[2]) { + io_notif_unregister(ctx); + return -EINVAL; + } + notif_slot->tag = slot.tag; + } return 0; } diff --git a/io_uring/notif.h b/io_uring/notif.h index 1dd48efb7744..00efe164bdc4 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -6,6 +6,7 @@ #include #define IO_NOTIF_SPLICE_BATCH 32 +#define IORING_MAX_NOTIF_SLOTS (1U << 10) struct io_notif { struct ubuf_info uarg; @@ -48,6 +49,8 @@ struct io_notif_slot { u32 seq; }; +int io_notif_register(struct io_ring_ctx *ctx, + void __user *arg, unsigned int size); int io_notif_unregister(struct io_ring_ctx *ctx); void io_notif_cache_purge(struct io_ring_ctx *ctx); -- cgit v1.2.3 From 06a5464be84e4ae48394d34441baf34bf9706827 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:43 +0100 Subject: io_uring: wire send zc request type Add a new io_uring opcode IORING_OP_SENDZC. The main distinction from IORING_OP_SEND is that the user should specify a notification slot index in sqe::notification_idx and the buffers are safe to reuse only when the used notification is flushed and completes. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a80387c6a68ce9cf99b3b6ef6f71068468761fb7.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 +++ io_uring/net.c | 94 +++++++++++++++++++++++++++++++++++++++++++ io_uring/net.h | 3 ++ io_uring/opdef.c | 15 +++++++ 4 files changed, 117 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index dcfc7a0bda0c..82bf2991e9bd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -66,6 +66,10 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + struct { + __u16 notification_idx; + __u16 __pad; + }; }; union { struct { @@ -197,6 +201,7 @@ enum io_uring_op { IORING_OP_GETXATTR, IORING_OP_SOCKET, IORING_OP_URING_CMD, + IORING_OP_SENDZC_NOTIF, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index bbc9c603641a..89a8678ce69b 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -14,6 +14,7 @@ #include "kbuf.h" #include "alloc_cache.h" #include "net.h" +#include "notif.h" #if defined(CONFIG_NET) struct io_shutdown { @@ -59,6 +60,15 @@ struct io_sr_msg { unsigned int flags; }; +struct io_sendzc { + struct file *file; + void __user *buf; + size_t len; + u16 slot_idx; + unsigned msg_flags; + unsigned flags; +}; + #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -834,6 +844,90 @@ out_free: return ret; } +int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sendzc *zc = io_kiocb_to_cmd(req); + + if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) || + READ_ONCE(sqe->addr3)) + return -EINVAL; + + zc->flags = READ_ONCE(sqe->ioprio); + if (zc->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; + + zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + zc->len = READ_ONCE(sqe->len); + zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + zc->slot_idx = READ_ONCE(sqe->notification_idx); + if (zc->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + zc->msg_flags |= MSG_CMSG_COMPAT; +#endif + return 0; +} + +int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_sendzc *zc = io_kiocb_to_cmd(req); + struct io_notif_slot *notif_slot; + struct io_notif *notif; + struct msghdr msg; + struct iovec iov; + struct socket *sock; + unsigned msg_flags; + int ret, min_ret = 0; + + if (!(req->flags & REQ_F_POLLED) && + (zc->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + + if (issue_flags & IO_URING_F_UNLOCKED) + return -EAGAIN; + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + notif_slot = io_get_notif_slot(ctx, zc->slot_idx); + if (!notif_slot) + return -EINVAL; + notif = io_get_notif(ctx, notif_slot); + if (!notif) + return -ENOMEM; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + + ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); + if (unlikely(ret)) + return ret; + + msg_flags = zc->msg_flags | MSG_ZEROCOPY; + if (issue_flags & IO_URING_F_NONBLOCK) + msg_flags |= MSG_DONTWAIT; + if (msg_flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + msg.msg_flags = msg_flags; + msg.msg_ubuf = ¬if->uarg; + msg.sg_from_iter = NULL; + ret = sock_sendmsg(sock, &msg); + + if (unlikely(ret < min_ret)) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + return ret == -ERESTARTSYS ? -EINTR : ret; + } + + io_req_set_res(req, ret, 0); + return IOU_OK; +} + int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = io_kiocb_to_cmd(req); diff --git a/io_uring/net.h b/io_uring/net.h index db20ce9d6546..7c438d39c089 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -52,6 +52,9 @@ int io_connect_prep_async(struct io_kiocb *req); int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_connect(struct io_kiocb *req, unsigned int issue_flags); +int io_sendzc(struct io_kiocb *req, unsigned int issue_flags); +int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); + void io_netmsg_cache_free(struct io_cache_entry *entry); #else static inline void io_netmsg_cache_free(struct io_cache_entry *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index a7b84b43e6c2..7ab19bbf3126 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -470,6 +470,21 @@ const struct io_op_def io_op_defs[] = { .issue = io_uring_cmd, .prep_async = io_uring_cmd_prep_async, }, + [IORING_OP_SENDZC_NOTIF] = { + .name = "SENDZC_NOTIF", + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .audit_skip = 1, + .ioprio = 1, +#if defined(CONFIG_NET) + .prep = io_sendzc_prep, + .issue = io_sendzc, +#else + .prep = io_eopnotsupp_prep, +#endif + + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3 From 092aeedb750a9fad0f0252d6067fc91d76ca44bd Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:45 +0100 Subject: io_uring: allow to pass addr into sendzc Allow to specify an address to zerocopy sends making it more like sendto(2). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/70417a8f7c5b51ab454690bae08adc0c187f89e8.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- io_uring/net.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 82bf2991e9bd..0736e2773a5d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -68,7 +68,7 @@ struct io_uring_sqe { __u32 file_index; struct { __u16 notification_idx; - __u16 __pad; + __u16 addr_len; }; }; union { diff --git a/io_uring/net.c b/io_uring/net.c index 2d04a70b0632..61414d865cd7 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -67,6 +67,8 @@ struct io_sendzc { u16 slot_idx; unsigned msg_flags; unsigned flags; + unsigned addr_len; + void __user *addr; }; #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) @@ -848,8 +850,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sendzc *zc = io_kiocb_to_cmd(req); - if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) || - READ_ONCE(sqe->addr3)) + if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); @@ -862,6 +863,10 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) zc->slot_idx = READ_ONCE(sqe->notification_idx); if (zc->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; + + zc->addr = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + zc->addr_len = READ_ONCE(sqe->addr_len); + #ifdef CONFIG_COMPAT if (req->ctx->compat) zc->msg_flags |= MSG_CMSG_COMPAT; @@ -871,6 +876,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) { + struct sockaddr_storage address; struct io_ring_ctx *ctx = req->ctx; struct io_sendzc *zc = io_kiocb_to_cmd(req); struct io_notif_slot *notif_slot; @@ -908,6 +914,14 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) return ret; mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + if (zc->addr) { + ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address); + if (unlikely(ret < 0)) + return ret; + msg.msg_name = (struct sockaddr *)&address; + msg.msg_namelen = zc->addr_len; + } + msg_flags = zc->msg_flags | MSG_ZEROCOPY; if (issue_flags & IO_URING_F_NONBLOCK) msg_flags |= MSG_DONTWAIT; -- cgit v1.2.3 From 10c7d33ecd51619e453cf6aeee8e326f8ba5cfea Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:46 +0100 Subject: io_uring: sendzc with fixed buffers Allow zerocopy sends to use fixed buffers. There is an optimisation for this case, the network layer don't need to reference the pages, see SKBFL_MANAGED_FRAG_REFS, so io_uring have to ensure validity of fixed buffers until the notifier is released. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e1d8bd1b5934e541d90c1824eb4020ae3f5f43f3.1657643355.git.asml.silence@gmail.com [axboe: fold in 32-bit pointer cast warning fix] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +++++- io_uring/net.c | 29 ++++++++++++++++++++++++----- 2 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0736e2773a5d..f1a9ff9b9ea7 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -272,9 +272,13 @@ enum io_uring_op { * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if * the handler will continue to report * CQEs on behalf of the same SQE. + * + * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in + * the buf_index field. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) -#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECVSEND_FIXED_BUF (1U << 2) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/net.c b/io_uring/net.c index 61414d865cd7..ab443c52dcfd 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -15,6 +15,7 @@ #include "alloc_cache.h" #include "net.h" #include "notif.h" +#include "rsrc.h" #if defined(CONFIG_NET) struct io_shutdown { @@ -849,13 +850,23 @@ out_free: int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sendzc *zc = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); - if (zc->flags & ~IORING_RECVSEND_POLL_FIRST) + if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)) return -EINVAL; + if (zc->flags & IORING_RECVSEND_FIXED_BUF) { + unsigned idx = READ_ONCE(sqe->buf_index); + + if (unlikely(idx >= ctx->nr_user_bufs)) + return -EFAULT; + idx = array_index_nospec(idx, ctx->nr_user_bufs); + req->imu = READ_ONCE(ctx->user_bufs[idx]); + io_req_set_rsrc_node(req, ctx, 0); + } zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); zc->len = READ_ONCE(sqe->len); @@ -909,10 +920,18 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) msg.msg_controllen = 0; msg.msg_namelen = 0; - ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); - if (unlikely(ret)) - return ret; - mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + if (zc->flags & IORING_RECVSEND_FIXED_BUF) { + ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu, + (u64)(uintptr_t)zc->buf, zc->len); + if (unlikely(ret)) + return ret; + } else { + ret = import_single_range(WRITE, zc->buf, zc->len, &iov, + &msg.msg_iter); + if (unlikely(ret)) + return ret; + mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + } if (zc->addr) { ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address); -- cgit v1.2.3 From 63809137ebb58f0aa2ce359117422686e3304f45 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:47 +0100 Subject: io_uring: flush notifiers after sendzc Allow to flush notifiers as a part of sendzc request by setting IORING_SENDZC_FLUSH flag. When the sendzc request succeedes it will flush the used [active] notifier. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e0b4d9a6797e2fd6092824fe42953db7a519bbc8.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 ++++ io_uring/io_uring.c | 11 +---------- io_uring/io_uring.h | 10 ++++++++++ io_uring/net.c | 5 ++++- io_uring/notif.c | 2 +- io_uring/notif.h | 11 +++++++++++ 6 files changed, 31 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f1a9ff9b9ea7..45272eb37d10 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -275,10 +275,14 @@ enum io_uring_op { * * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in * the buf_index field. + * + * IORING_RECVSEND_NOTIF_FLUSH Flush a notification after a successful + * successful. Only for zerocopy sends. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) +#define IORING_RECVSEND_NOTIF_FLUSH (1U << 3) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cae11374456e..1d600a63643b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -621,7 +621,7 @@ void __io_put_task(struct task_struct *task, int nr) put_task_struct_many(task, nr); } -static void io_task_refs_refill(struct io_uring_task *tctx) +void io_task_refs_refill(struct io_uring_task *tctx) { unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; @@ -630,15 +630,6 @@ static void io_task_refs_refill(struct io_uring_task *tctx) tctx->cached_refs += refill; } -static inline void io_get_task_refs(int nr) -{ - struct io_uring_task *tctx = current->io_uring; - - tctx->cached_refs -= nr; - if (unlikely(tctx->cached_refs < 0)) - io_task_refs_refill(tctx); -} - static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 66bfd880d07f..cc81a9d1fd4d 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -74,6 +74,7 @@ void io_wq_submit_work(struct io_wq_work *work); void io_free_req(struct io_kiocb *req); void io_queue_next(struct io_kiocb *req); void __io_put_task(struct task_struct *task, int nr); +void io_task_refs_refill(struct io_uring_task *tctx); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); @@ -270,4 +271,13 @@ static inline void io_put_task(struct task_struct *task, int nr) __io_put_task(task, nr); } +static inline void io_get_task_refs(int nr) +{ + struct io_uring_task *tctx = current->io_uring; + + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); +} + #endif diff --git a/io_uring/net.c b/io_uring/net.c index ab443c52dcfd..9ac2ce37c522 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -856,7 +856,8 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); - if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)) + if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | + IORING_RECVSEND_FIXED_BUF | IORING_RECVSEND_NOTIF_FLUSH)) return -EINVAL; if (zc->flags & IORING_RECVSEND_FIXED_BUF) { unsigned idx = READ_ONCE(sqe->buf_index); @@ -958,6 +959,8 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) return ret == -ERESTARTSYS ? -EINTR : ret; } + if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH) + io_notif_slot_flush_submit(notif_slot, 0); io_req_set_res(req, ret, 0); return IOU_OK; } diff --git a/io_uring/notif.c b/io_uring/notif.c index c5179e5c1cd6..a93887451bbb 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -133,7 +133,7 @@ struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, return notif; } -static void io_notif_slot_flush(struct io_notif_slot *slot) +void io_notif_slot_flush(struct io_notif_slot *slot) __must_hold(&ctx->uring_lock) { struct io_notif *notif = slot->notif; diff --git a/io_uring/notif.h b/io_uring/notif.h index 00efe164bdc4..6cd73d7b965b 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -54,6 +54,7 @@ int io_notif_register(struct io_ring_ctx *ctx, int io_notif_unregister(struct io_ring_ctx *ctx); void io_notif_cache_purge(struct io_ring_ctx *ctx); +void io_notif_slot_flush(struct io_notif_slot *slot); struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, struct io_notif_slot *slot); @@ -74,3 +75,13 @@ static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx, idx = array_index_nospec(idx, ctx->nr_notif_slots); return &ctx->notif_slots[idx]; } + +static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot, + unsigned int issue_flags) +{ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + slot->notif->task = current; + io_get_task_refs(1); + } + io_notif_slot_flush(slot); +} -- cgit v1.2.3 From 4379d5f15b3fd4224c37841029178aa8082a242e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:48 +0100 Subject: io_uring: rename IORING_OP_FILES_UPDATE IORING_OP_FILES_UPDATE will be a more generic opcode serving different resource types, rename it into IORING_OP_RSRC_UPDATE and add subtype handling. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0a907133907d9af3415a8a7aa1802c6aa97c03c6.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 +++++++++++- io_uring/opdef.c | 9 +++++---- io_uring/rsrc.c | 17 +++++++++++++++-- io_uring/rsrc.h | 4 ++-- 4 files changed, 33 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 45272eb37d10..210a00ab6301 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -174,7 +174,8 @@ enum io_uring_op { IORING_OP_FALLOCATE, IORING_OP_OPENAT, IORING_OP_CLOSE, - IORING_OP_FILES_UPDATE, + IORING_OP_RSRC_UPDATE, + IORING_OP_FILES_UPDATE = IORING_OP_RSRC_UPDATE, IORING_OP_STATX, IORING_OP_READ, IORING_OP_WRITE, @@ -223,6 +224,7 @@ enum io_uring_op { #define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) + /* * sqe->splice_flags * extends splice(2) flags @@ -289,6 +291,14 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* + * IORING_OP_RSRC_UPDATE flags + */ +enum { + IORING_RSRC_UPDATE_FILES, +}; + /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 7ab19bbf3126..72dd2b2d8a9d 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -246,12 +246,13 @@ const struct io_op_def io_op_defs[] = { .prep = io_close_prep, .issue = io_close, }, - [IORING_OP_FILES_UPDATE] = { + [IORING_OP_RSRC_UPDATE] = { .audit_skip = 1, .iopoll = 1, - .name = "FILES_UPDATE", - .prep = io_files_update_prep, - .issue = io_files_update, + .name = "RSRC_UPDATE", + .prep = io_rsrc_update_prep, + .issue = io_rsrc_update, + .ioprio = 1, }, [IORING_OP_STATX] = { .audit_skip = 1, diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 7f66b0e25674..fc2b337e6c25 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -21,6 +21,7 @@ struct io_rsrc_update { u64 arg; u32 nr_args; u32 offset; + int type; }; static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, @@ -657,7 +658,7 @@ __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; } -int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); @@ -671,6 +672,7 @@ int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!up->nr_args) return -EINVAL; up->arg = READ_ONCE(sqe->addr); + up->type = READ_ONCE(sqe->ioprio); return 0; } @@ -713,7 +715,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req, return ret; } -int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); struct io_ring_ctx *ctx = req->ctx; @@ -742,6 +744,17 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + + switch (up->type) { + case IORING_RSRC_UPDATE_FILES: + return io_files_update(req, issue_flags); + } + return -EINVAL; +} + int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index af342fd239d0..21813a23215f 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -167,6 +167,6 @@ static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) return &data->tags[table_idx][off]; } -int io_files_update(struct io_kiocb *req, unsigned int issue_flags); -int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags); +int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); #endif -- cgit v1.2.3 From 492dddb4f6e3a5839c27d41ff1fecdbe6c3ab851 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:49 +0100 Subject: io_uring: add zc notification flush requests Overlay notification control onto IORING_OP_RSRC_UPDATE (former IORING_OP_FILES_UPDATE). It allows to flush a range of zc notifications from slots with indexes [sqe->off, sqe->off+sqe->len). If sqe->arg is not zero, it also copies sqe->arg as a new tag for all flushed notifications. Note, it doesn't flush a notification of a slot if there was no requests attached to it (since last flush or registration). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/df13e2363400682a73dd9e71c3b990b8d1ff0333.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/rsrc.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 210a00ab6301..1463cfecb56b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -297,6 +297,7 @@ enum io_uring_op { */ enum { IORING_RSRC_UPDATE_FILES, + IORING_RSRC_UPDATE_NOTIF, }; /* diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index fc2b337e6c25..9165fdf64269 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -15,6 +15,7 @@ #include "io_uring.h" #include "openclose.h" #include "rsrc.h" +#include "notif.h" struct io_rsrc_update { struct file *file; @@ -744,6 +745,41 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned len = up->nr_args; + unsigned idx_end, idx = up->offset; + int ret = 0; + + io_ring_submit_lock(ctx, issue_flags); + if (unlikely(check_add_overflow(idx, len, &idx_end))) { + ret = -EOVERFLOW; + goto out; + } + if (unlikely(idx_end > ctx->nr_notif_slots)) { + ret = -EINVAL; + goto out; + } + + for (; idx < idx_end; idx++) { + struct io_notif_slot *slot = &ctx->notif_slots[idx]; + + if (!slot->notif) + continue; + if (up->arg) + slot->tag = up->arg; + io_notif_slot_flush_submit(slot, issue_flags); + } +out: + io_ring_submit_unlock(ctx, issue_flags); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); @@ -751,6 +787,8 @@ int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) switch (up->type) { case IORING_RSRC_UPDATE_FILES: return io_files_update(req, issue_flags); + case IORING_RSRC_UPDATE_NOTIF: + return io_notif_update(req, issue_flags); } return -EINVAL; } -- cgit v1.2.3 From b4023554b1fb49f73a09e5f346a5facbf27d7383 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 25 Jul 2022 09:58:35 +0200 Subject: USB: cdc: add control-signal defines Add defines for the Control Signal Bitmap Values from section 6.2.14 SetControlLineState of the CDC specification version 1.1. Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20220725075841.1187-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/cdc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index 6d61550959ef..372c81425cae 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -271,6 +271,10 @@ struct usb_cdc_line_coding { __u8 bDataBits; } __attribute__ ((packed)); +/* Control Signal Bitmap Values from 6.2.14 SetControlLineState */ +#define USB_CDC_CTRL_DTR (1 << 0) +#define USB_CDC_CTRL_RTS (1 << 1) + /* table 62; bits in multicast filter */ #define USB_CDC_PACKET_TYPE_PROMISCUOUS (1 << 0) #define USB_CDC_PACKET_TYPE_ALL_MULTICAST (1 << 1) /* no filter */ -- cgit v1.2.3 From a0a3202b44a9fdf2a1f6330a0d176aee76c8631d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 25 Jul 2022 09:58:36 +0200 Subject: USB: cdc: add serial-state defines Add defines for the serial-state bitmap values from section 6.3.5 SerialState of the CDC specification version 1.1. Note that the bTxCarrier and bRxCarrier bits have been named after their RS-232 signal equivalents DSR and DCD. Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20220725075841.1187-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/cdc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index 372c81425cae..78caa9bdc4ae 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -306,6 +306,15 @@ struct usb_cdc_notification { __le16 wLength; } __attribute__ ((packed)); +/* UART State Bitmap Values from 6.3.5 SerialState */ +#define USB_CDC_SERIAL_STATE_DCD (1 << 0) +#define USB_CDC_SERIAL_STATE_DSR (1 << 1) +#define USB_CDC_SERIAL_STATE_BREAK (1 << 2) +#define USB_CDC_SERIAL_STATE_RING_SIGNAL (1 << 3) +#define USB_CDC_SERIAL_STATE_FRAMING (1 << 4) +#define USB_CDC_SERIAL_STATE_PARITY (1 << 5) +#define USB_CDC_SERIAL_STATE_OVERRUN (1 << 6) + struct usb_cdc_speed_change { __le32 DLBitRRate; /* contains the downlink bit rate (IN pipe) */ __le32 ULBitRate; /* contains the uplink bit rate (OUT pipe) */ -- cgit v1.2.3 From b7c14f23fb604fc66edae7514ed9b4b93930b5ba Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 17 Mar 2022 10:25:39 -0700 Subject: btrfs: send: add stream v2 definitions This adds the definitions of the new commands for send stream version 2 and their respective attributes: fallocate, FS_IOC_SETFLAGS (a.k.a. chattr), and encoded writes. It also documents two changes to the send stream format in v2: the receiver shouldn't assume a maximum command size, and the DATA attribute is encoded differently to allow for writes larger than 64k. These will be implemented in subsequent changes, and then the ioctl will accept the new version and flag. Reviewed-by: Josef Bacik Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- fs/btrfs/send.h | 40 ++++++++++++++++++++++++++++++++++++---- include/uapi/linux/btrfs.h | 7 +++++++ 3 files changed, 44 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 237753860758..6ec31736c522 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7552,7 +7552,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) sctx->clone_roots_cnt = arg->clone_sources_count; - sctx->send_max_size = BTRFS_SEND_BUF_SIZE; + sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1; sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL); if (!sctx->send_buf) { ret = -ENOMEM; diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index c47a2984aa5b..858ce8132614 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -12,7 +12,11 @@ #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream" #define BTRFS_SEND_STREAM_VERSION 1 -#define BTRFS_SEND_BUF_SIZE SZ_64K +/* + * In send stream v1, no command is larger than 64K. In send stream v2, no limit + * should be assumed. + */ +#define BTRFS_SEND_BUF_SIZE_V1 SZ_64K enum btrfs_tlv_type { BTRFS_TLV_U8, @@ -80,16 +84,20 @@ enum btrfs_send_cmd { BTRFS_SEND_C_MAX_V1 = 22, /* Version 2 */ - BTRFS_SEND_C_MAX_V2 = 22, + BTRFS_SEND_C_FALLOCATE = 23, + BTRFS_SEND_C_SETFLAGS = 24, + BTRFS_SEND_C_ENCODED_WRITE = 25, + BTRFS_SEND_C_MAX_V2 = 25, /* End */ - BTRFS_SEND_C_MAX = 22, + BTRFS_SEND_C_MAX = 25, }; /* attributes in send stream */ enum { BTRFS_SEND_A_UNSPEC = 0, + /* Version 1 */ BTRFS_SEND_A_UUID = 1, BTRFS_SEND_A_CTRANSID = 2, @@ -112,6 +120,11 @@ enum { BTRFS_SEND_A_PATH_LINK = 17, BTRFS_SEND_A_FILE_OFFSET = 18, + /* + * As of send stream v2, this attribute is special: it must be the last + * attribute in a command, its header contains only the type, and its + * length is implicitly the remaining length of the command. + */ BTRFS_SEND_A_DATA = 19, BTRFS_SEND_A_CLONE_UUID = 20, @@ -120,7 +133,26 @@ enum { BTRFS_SEND_A_CLONE_OFFSET = 23, BTRFS_SEND_A_CLONE_LEN = 24, - BTRFS_SEND_A_MAX = 24, + BTRFS_SEND_A_MAX_V1 = 24, + + /* Version 2 */ + BTRFS_SEND_A_FALLOCATE_MODE = 25, + + BTRFS_SEND_A_SETFLAGS_FLAGS = 26, + + BTRFS_SEND_A_UNENCODED_FILE_LEN = 27, + BTRFS_SEND_A_UNENCODED_LEN = 28, + BTRFS_SEND_A_UNENCODED_OFFSET = 29, + /* + * COMPRESSION and ENCRYPTION default to NONE (0) if omitted from + * BTRFS_SEND_C_ENCODED_WRITE. + */ + BTRFS_SEND_A_COMPRESSION = 30, + BTRFS_SEND_A_ENCRYPTION = 31, + BTRFS_SEND_A_MAX_V2 = 31, + + /* End */ + BTRFS_SEND_A_MAX = 31, }; #ifdef __KERNEL__ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index d956b2993970..b6f26a434b10 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -777,6 +777,13 @@ struct btrfs_ioctl_received_subvol_args { */ #define BTRFS_SEND_FLAG_VERSION 0x8 +/* + * Send compressed data using the ENCODED_WRITE command instead of decompressing + * the data and sending it with the WRITE command. This requires protocol + * version >= 2. + */ +#define BTRFS_SEND_FLAG_COMPRESSED 0x10 + #define BTRFS_SEND_FLAG_MASK \ (BTRFS_SEND_FLAG_NO_FILE_DATA | \ BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \ -- cgit v1.2.3 From d6815592806f481244d0e3435ca1f5383d90a14c Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 17 Mar 2022 10:25:43 -0700 Subject: btrfs: send: enable support for stream v2 and compressed writes Now that the new support is implemented, allow the ioctl to accept v2 and the compressed flag, and update the version in sysfs. Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/send.c | 7 +++++-- fs/btrfs/send.h | 2 +- include/uapi/linux/btrfs.h | 3 ++- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index bc00393c1233..6d01dc26d408 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -701,8 +701,7 @@ static int send_header(struct send_ctx *sctx) struct btrfs_stream_header hdr; strcpy(hdr.magic, BTRFS_SEND_STREAM_MAGIC); - hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION); - + hdr.version = cpu_to_le32(sctx->proto); return write_buf(sctx->send_filp, &hdr, sizeof(hdr), &sctx->send_off); } @@ -7755,6 +7754,10 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } else { sctx->proto = 1; } + if ((arg->flags & BTRFS_SEND_FLAG_COMPRESSED) && sctx->proto < 2) { + ret = -EINVAL; + goto out; + } sctx->send_filp = fget(arg->send_fd); if (!sctx->send_filp) { diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index 858ce8132614..b0dc07567d09 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -10,7 +10,7 @@ #include "ctree.h" #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream" -#define BTRFS_SEND_STREAM_VERSION 1 +#define BTRFS_SEND_STREAM_VERSION 2 /* * In send stream v1, no command is larger than 64K. In send stream v2, no limit diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index b6f26a434b10..f54dc91e4025 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -788,7 +788,8 @@ struct btrfs_ioctl_received_subvol_args { (BTRFS_SEND_FLAG_NO_FILE_DATA | \ BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \ BTRFS_SEND_FLAG_OMIT_END_CMD | \ - BTRFS_SEND_FLAG_VERSION) + BTRFS_SEND_FLAG_VERSION | \ + BTRFS_SEND_FLAG_COMPRESSED) struct btrfs_ioctl_send_args { __s64 send_fd; /* in */ -- cgit v1.2.3 From 5008750eff5d4af8a3aed4a7567c4cfb2b3cb156 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Mon, 18 Jul 2022 14:18:11 +0200 Subject: net/sched: flower: Add PPPoE filter Add support for PPPoE specific fields for tc-flower. Those fields can be provided only when protocol was set to ETH_P_PPP_SES. Defines, dump, load and set are being done here. Overwrite basic.n_proto only in case of PPP_IP and PPP_IPV6, otherwise leave it as ETH_P_PPP_SES. Signed-off-by: Wojciech Drewek Acked-by: Guillaume Nault Signed-off-by: Tony Nguyen --- include/uapi/linux/pkt_cls.h | 3 +++ net/sched/cls_flower.c | 64 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9a2ee1e39fad..c142c0f8ed8a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -589,6 +589,9 @@ enum { TCA_FLOWER_KEY_NUM_OF_VLANS, /* u8 */ + TCA_FLOWER_KEY_PPPOE_SID, /* be16 */ + TCA_FLOWER_KEY_PPP_PROTO, /* be16 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1a1e34480b7e..041d63ff809a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -67,6 +68,7 @@ struct fl_flow_key { struct flow_dissector_key_ct ct; struct flow_dissector_key_hash hash; struct flow_dissector_key_num_of_vlans num_of_vlans; + struct flow_dissector_key_pppoe pppoe; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -708,6 +710,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_HASH] = { .type = NLA_U32 }, [TCA_FLOWER_KEY_HASH_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_KEY_NUM_OF_VLANS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, }; @@ -1035,6 +1039,50 @@ static void fl_set_key_vlan(struct nlattr **tb, } } +static void fl_set_key_pppoe(struct nlattr **tb, + struct flow_dissector_key_pppoe *key_val, + struct flow_dissector_key_pppoe *key_mask, + struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + /* key_val::type must be set to ETH_P_PPP_SES + * because ETH_P_PPP_SES was stored in basic.n_proto + * which might get overwritten by ppp_proto + * or might be set to 0, the role of key_val::type + * is simmilar to vlan_key::tpid + */ + key_val->type = htons(ETH_P_PPP_SES); + key_mask->type = cpu_to_be16(~0); + + if (tb[TCA_FLOWER_KEY_PPPOE_SID]) { + key_val->session_id = + nla_get_be16(tb[TCA_FLOWER_KEY_PPPOE_SID]); + key_mask->session_id = cpu_to_be16(~0); + } + if (tb[TCA_FLOWER_KEY_PPP_PROTO]) { + key_val->ppp_proto = + nla_get_be16(tb[TCA_FLOWER_KEY_PPP_PROTO]); + key_mask->ppp_proto = cpu_to_be16(~0); + + if (key_val->ppp_proto == htons(PPP_IP)) { + key->basic.n_proto = htons(ETH_P_IP); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_IPV6)) { + key->basic.n_proto = htons(ETH_P_IPV6); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_UC)) { + key->basic.n_proto = htons(ETH_P_MPLS_UC); + mask->basic.n_proto = cpu_to_be16(~0); + } else if (key_val->ppp_proto == htons(PPP_MPLS_MC)) { + key->basic.n_proto = htons(ETH_P_MPLS_MC); + mask->basic.n_proto = cpu_to_be16(~0); + } + } else { + key->basic.n_proto = 0; + mask->basic.n_proto = cpu_to_be16(0); + } +} + static void fl_set_key_flag(u32 flower_key, u32 flower_mask, u32 *dissector_key, u32 *dissector_mask, u32 flower_flag_bit, u32 dissector_flag_bit) @@ -1645,6 +1693,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, } } + if (key->basic.n_proto == htons(ETH_P_PPP_SES)) + fl_set_key_pppoe(tb, &key->pppoe, &mask->pppoe, key, mask); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, @@ -1917,6 +1968,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_HASH, hash); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PPPOE, pppoe); skb_flow_dissector_init(dissector, keys, cnt); } @@ -3045,6 +3098,17 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, fl_dump_key_ip(skb, false, &key->ip, &mask->ip))) goto nla_put_failure; + if (mask->pppoe.session_id) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPPOE_SID, + key->pppoe.session_id)) + goto nla_put_failure; + } + if (mask->basic.n_proto && mask->pppoe.ppp_proto) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_PPP_PROTO, + key->pppoe.ppp_proto)) + goto nla_put_failure; + } + if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, -- cgit v1.2.3 From 7b2d9a1a50ec3bedf067fe234a4a71196c89e826 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Jul 2022 10:29:16 +0200 Subject: net: devlink: introduce nested devlink entity for line card For the purpose of exposing device info and allow flash update which is going to be implemented in follow-up patches, introduce a possibility for a line card to expose relation to nested devlink entity. The nested devlink entity represents the line card. Example: $ devlink lc show pci/0000:01:00.0 lc 1 pci/0000:01:00.0: lc 1 state active type 16x100G nested_devlink auxiliary/mlxsw_core.lc.0 supported_types: 16x100G $ devlink dev show auxiliary/mlxsw_core.lc.0 auxiliary/mlxsw_core.lc.0 Signed-off-by: Jiri Pirko Acked-by: Jakub Kicinski Reviewed-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 2 ++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 46 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 780744b550b8..5bd3fac12e9e 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1580,6 +1580,8 @@ void devlink_linecard_provision_clear(struct devlink_linecard *linecard); void devlink_linecard_provision_fail(struct devlink_linecard *linecard); void devlink_linecard_activate(struct devlink_linecard *linecard); void devlink_linecard_deactivate(struct devlink_linecard *linecard); +void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, + struct devlink *nested_devlink); int devl_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b3d40a5d72ff..541321695f52 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -576,6 +576,8 @@ enum devlink_attr { DEVLINK_ATTR_LINECARD_TYPE, /* string */ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ + DEVLINK_ATTR_NESTED_DEVLINK, /* nested */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 865232a1455f..698b2d6e0ec7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -89,6 +89,7 @@ struct devlink_linecard { const char *type; struct devlink_linecard_type *types; unsigned int types_count; + struct devlink *nested_devlink; }; /** @@ -856,6 +857,24 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) return 0; } +static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) +{ + struct nlattr *nested_attr; + + nested_attr = nla_nest_start(msg, DEVLINK_ATTR_NESTED_DEVLINK); + if (!nested_attr) + return -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + nla_nest_end(msg, nested_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, nested_attr); + return -EMSGSIZE; +} + struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; @@ -2135,6 +2154,10 @@ static int devlink_nl_linecard_fill(struct sk_buff *msg, nla_nest_end(msg, attr); } + if (linecard->nested_devlink && + devlink_nl_put_nested_handle(msg, linecard->nested_devlink)) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0; @@ -10255,6 +10278,7 @@ EXPORT_SYMBOL_GPL(devlink_linecard_provision_set); void devlink_linecard_provision_clear(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); + WARN_ON(linecard->nested_devlink); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); @@ -10273,6 +10297,7 @@ EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear); void devlink_linecard_provision_fail(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); + WARN_ON(linecard->nested_devlink); linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); @@ -10320,6 +10345,23 @@ void devlink_linecard_deactivate(struct devlink_linecard *linecard) } EXPORT_SYMBOL_GPL(devlink_linecard_deactivate); +/** + * devlink_linecard_nested_dl_set - Attach/detach nested devlink + * instance to linecard. + * + * @linecard: devlink linecard + * @nested_devlink: devlink instance to attach or NULL to detach + */ +void devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, + struct devlink *nested_devlink) +{ + mutex_lock(&linecard->state_lock); + linecard->nested_devlink = nested_devlink; + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); + mutex_unlock(&linecard->state_lock); +} +EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set); + int devl_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, -- cgit v1.2.3 From a0c0c44e9aa2b5da876467083c359b368f3ce95e Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 20 Jul 2022 12:43:28 +0000 Subject: s390: add ELF note type for encrypted CPU state of a PV VCPU The type NT_S390_PV_CPU_DATA note contains the encrypted CPU state of a PV VCPU. It's only relevant in dumps of s390 PV VMs and can't be decrypted without a second block of encrypted data which provides key parts. Therefore we only reserve the note type here. The zgetdump tool from the s390-tools package can, together with a Customer Communication Key, be used to convert a PV VM dump into a normal VM dump. zgetdump will decrypt the CPU data and overwrite the other respective notes to make the data accessible for crash and other debugging tools. Signed-off-by: Janosch Frank Acked-by: Heiko Carstens [agordeev@linux.ibm.com changed desctiption] Signed-off-by: Alexander Gordeev --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 2b9f5e9985e5..c7b056af9ef0 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -420,6 +420,7 @@ typedef struct elf64_shdr { #define NT_S390_GS_CB 0x30b /* s390 guarded storage registers */ #define NT_S390_GS_BC 0x30c /* s390 guarded storage broadcast control block */ #define NT_S390_RI_CB 0x30d /* s390 runtime instrumentation */ +#define NT_S390_PV_CPU_DATA 0x30e /* s390 protvirt cpu dump data */ #define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ #define NT_ARM_TLS 0x401 /* ARM TLS register */ #define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ -- cgit v1.2.3 From 9dd1cd3220eca534f2d47afad7ce85f4c40118d8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 20 Jul 2022 13:58:04 -0400 Subject: dm: fix dm-raid crash if md_handle_request() splits bio Commit ca522482e3eaf ("dm: pass NULL bdev to bio_alloc_clone") introduced the optimization to _not_ perform bio_associate_blkg()'s relatively costly work when DM core clones its bio. But in doing so it exposed the possibility for DM's cloned bio to alter DM target behavior (e.g. crash) if a target were to issue IO without first calling bio_set_dev(). The DM raid target can trigger an MD crash due to its need to split the DM bio that is passed to md_handle_request(). The split will recurse to submit_bio_noacct() using a bio with an uninitialized ->bi_blkg. This NULL bio->bi_blkg causes blk_throtl_bio() to dereference a NULL blkg_to_tg(bio->bi_blkg). Fix this in DM core by adding a new 'needs_bio_set_dev' target flag that will make alloc_tio() call bio_set_dev() on behalf of the target. dm-raid is the only target that requires this flag. bio_set_dev() initializes the DM cloned bio's ->bi_blkg, using bio_associate_blkg, before passing the bio to md_handle_request(). Long-term fix would be to audit and refactor MD code to rely on DM to split its bio, using dm_accept_partial_bio(), but there are MD raid personalities (e.g. raid1 and raid10) whose implementation are tightly coupled to handling the bio splitting inline. Fixes: ca522482e3eaf ("dm: pass NULL bdev to bio_alloc_clone") Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm-raid.c | 1 + drivers/md/dm.c | 13 ++++++------- include/linux/device-mapper.h | 6 ++++++ include/uapi/linux/dm-ioctl.h | 4 ++-- 4 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index e6a9b8cb22d3..3203aecd6961 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3095,6 +3095,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_WORK(&rs->md.event_work, do_table_event); ti->private = rs; ti->num_flush_bios = 1; + ti->needs_bio_set_dev = true; /* Restore any requested new layout for conversion decision */ rs_config_restore(rs, &rs_layout); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 47bcc5081b2b..f6a6437d0a7c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -574,9 +574,6 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio) struct bio *clone; clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->mempools->io_bs); - /* Set default bdev, but target must bio_set_dev() before issuing IO */ - clone->bi_bdev = md->disk->part0; - tio = clone_to_tio(clone); tio->flags = 0; dm_tio_set_flag(tio, DM_TIO_INSIDE_DM_IO); @@ -609,6 +606,7 @@ static void free_io(struct dm_io *io) static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti, unsigned target_bio_nr, unsigned *len, gfp_t gfp_mask) { + struct mapped_device *md = ci->io->md; struct dm_target_io *tio; struct bio *clone; @@ -618,14 +616,10 @@ static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti, /* alloc_io() already initialized embedded clone */ clone = &tio->clone; } else { - struct mapped_device *md = ci->io->md; - clone = bio_alloc_clone(NULL, ci->bio, gfp_mask, &md->mempools->bs); if (!clone) return NULL; - /* Set default bdev, but target must bio_set_dev() before issuing IO */ - clone->bi_bdev = md->disk->part0; /* REQ_DM_POLL_LIST shouldn't be inherited */ clone->bi_opf &= ~REQ_DM_POLL_LIST; @@ -641,6 +635,11 @@ static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti, tio->len_ptr = len; tio->old_sector = 0; + /* Set default bdev, but target must bio_set_dev() before issuing IO */ + clone->bi_bdev = md->disk->part0; + if (unlikely(ti->needs_bio_set_dev)) + bio_set_dev(clone, md->disk->part0); + if (len) { clone->bi_iter.bi_size = to_bytes(*len); if (bio_integrity(clone)) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 920085dd7f3b..04c6acf7faaa 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -373,6 +373,12 @@ struct dm_target { * after returning DM_MAPIO_SUBMITTED from its map function. */ bool accounts_remapped_io:1; + + /* + * Set if the target will submit the DM bio without first calling + * bio_set_dev(). NOTE: ideally a target should _not_ need this. + */ + bool needs_bio_set_dev:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 2e9550fef90f..27ad9671f2df 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -286,9 +286,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 46 +#define DM_VERSION_MINOR 47 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2022-02-22)" +#define DM_VERSION_EXTRA "-ioctl (2022-07-28)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 08f588fa301bef264576fc915da6bf31b585a824 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Wed, 27 Jul 2022 22:27:20 +0530 Subject: devlink: introduce framework for selftests Add a framework for running selftests. Framework exposes devlink commands and test suite(s) to the user to execute and query the supported tests by the driver. Below are new entries in devlink_nl_ops devlink_nl_cmd_selftests_show_doit/dumpit: To query the supported selftests by the drivers. devlink_nl_cmd_selftests_run: To execute selftests. Users can provide a test mask for executing group tests or standalone tests. Documentation/networking/devlink/ path is already part of MAINTAINERS & the new files come under this path. Hence no update needed to the MAINTAINERS Signed-off-by: Vikas Gupta Reviewed-by: Andy Gospodarek Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- .../networking/devlink/devlink-selftests.rst | 38 ++++ include/net/devlink.h | 21 ++ include/uapi/linux/devlink.h | 29 +++ net/core/devlink.c | 216 +++++++++++++++++++++ 4 files changed, 304 insertions(+) create mode 100644 Documentation/networking/devlink/devlink-selftests.rst (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-selftests.rst b/Documentation/networking/devlink/devlink-selftests.rst new file mode 100644 index 000000000000..c0aa1f3aef0d --- /dev/null +++ b/Documentation/networking/devlink/devlink-selftests.rst @@ -0,0 +1,38 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +================= +Devlink Selftests +================= + +The ``devlink-selftests`` API allows executing selftests on the device. + +Tests Mask +========== +The ``devlink-selftests`` command should be run with a mask indicating +the tests to be executed. + +Tests Description +================= +The following is a list of tests that drivers may execute. + +.. list-table:: List of tests + :widths: 5 90 + + * - Name + - Description + * - ``DEVLINK_SELFTEST_FLASH`` + - Devices may have the firmware on non-volatile memory on the board, e.g. + flash. This particular test helps to run a flash selftest on the device. + Implementation of the test is left to the driver/firmware. + +example usage +------------- + +.. code:: shell + + # Query selftests supported on the devlink device + $ devlink dev selftests show DEV + # Query selftests supported on all devlink devices + $ devlink dev selftests show + # Executes selftests on the device + $ devlink dev selftests run DEV id flash diff --git a/include/net/devlink.h b/include/net/devlink.h index 5bd3fac12e9e..119ed1ffb988 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1509,6 +1509,27 @@ struct devlink_ops { struct devlink_rate *parent, void *priv_child, void *priv_parent, struct netlink_ext_ack *extack); + /** + * selftests_check() - queries if selftest is supported + * @devlink: devlink instance + * @id: test index + * @extack: extack for reporting error messages + * + * Return: true if test is supported by the driver + */ + bool (*selftest_check)(struct devlink *devlink, unsigned int id, + struct netlink_ext_ack *extack); + /** + * selftest_run() - Runs a selftest + * @devlink: devlink instance + * @id: test index + * @extack: extack for reporting error messages + * + * Return: status of the test + */ + enum devlink_selftest_status + (*selftest_run)(struct devlink *devlink, unsigned int id, + struct netlink_ext_ack *extack); }; void *devlink_priv(struct devlink *devlink); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 541321695f52..2f24b53a87a5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -136,6 +136,9 @@ enum devlink_command { DEVLINK_CMD_LINECARD_NEW, DEVLINK_CMD_LINECARD_DEL, + DEVLINK_CMD_SELFTESTS_GET, /* can dump */ + DEVLINK_CMD_SELFTESTS_RUN, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -276,6 +279,30 @@ enum { #define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \ (_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1) +enum devlink_attr_selftest_id { + DEVLINK_ATTR_SELFTEST_ID_UNSPEC, + DEVLINK_ATTR_SELFTEST_ID_FLASH, /* flag */ + + __DEVLINK_ATTR_SELFTEST_ID_MAX, + DEVLINK_ATTR_SELFTEST_ID_MAX = __DEVLINK_ATTR_SELFTEST_ID_MAX - 1 +}; + +enum devlink_selftest_status { + DEVLINK_SELFTEST_STATUS_SKIP, + DEVLINK_SELFTEST_STATUS_PASS, + DEVLINK_SELFTEST_STATUS_FAIL +}; + +enum devlink_attr_selftest_result { + DEVLINK_ATTR_SELFTEST_RESULT_UNSPEC, + DEVLINK_ATTR_SELFTEST_RESULT, /* nested */ + DEVLINK_ATTR_SELFTEST_RESULT_ID, /* u32, enum devlink_attr_selftest_id */ + DEVLINK_ATTR_SELFTEST_RESULT_STATUS, /* u8, enum devlink_selftest_status */ + + __DEVLINK_ATTR_SELFTEST_RESULT_MAX, + DEVLINK_ATTR_SELFTEST_RESULT_MAX = __DEVLINK_ATTR_SELFTEST_RESULT_MAX - 1 +}; + /** * enum devlink_trap_action - Packet trap action. * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not @@ -578,6 +605,8 @@ enum devlink_attr { DEVLINK_ATTR_NESTED_DEVLINK, /* nested */ + DEVLINK_ATTR_SELFTESTS, /* nested */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index ca4c9939d569..efeba223b9b8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -201,6 +201,10 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ DEVLINK_PORT_FN_STATE_ACTIVE), }; +static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, +}; + static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); #define DEVLINK_REGISTERED XA_MARK_1 @@ -4826,6 +4830,206 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb, return ret; } +static int +devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct nlattr *selftests; + void *hdr; + int err; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, + DEVLINK_CMD_SELFTESTS_GET); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto err_cancel_msg; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + if (devlink->ops->selftest_check(devlink, i, extack)) { + err = nla_put_flag(msg, i); + if (err) + goto err_cancel_msg; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->selftest_check) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, + info->snd_seq, 0, info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_selftests_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + unsigned long index; + int idx = 0; + int err = 0; + + mutex_lock(&devlink_mutex); + devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { + if (idx < start || !devlink->ops->selftest_check) + goto inc; + + devl_lock(devlink); + err = devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + devl_unlock(devlink); + if (err) { + devlink_put(devlink); + break; + } +inc: + idx++; + devlink_put(devlink); + } + mutex_unlock(&devlink_mutex); + + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, + enum devlink_selftest_status test_status) +{ + struct nlattr *result_attr; + + result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); + if (!result_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || + nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, + test_status)) + goto nla_put_failure; + + nla_nest_end(skb, result_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, result_attr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *attrs, *selftests; + struct sk_buff *msg; + void *hdr; + int err; + int i; + + if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_SELFTESTS]) { + NL_SET_ERR_MSG_MOD(info->extack, "selftest required"); + return -EINVAL; + } + + attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; + + err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, + devlink_selftest_nl_policy, info->extack); + if (err < 0) + return err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto genlmsg_cancel; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + enum devlink_selftest_status test_status; + + if (nla_get_flag(tb[i])) { + if (!devlink->ops->selftest_check(devlink, i, + info->extack)) { + if (devlink_selftest_result_put(msg, i, + DEVLINK_SELFTEST_STATUS_SKIP)) + goto selftests_nest_cancel; + continue; + } + + test_status = devlink->ops->selftest_run(devlink, i, + info->extack); + if (devlink_selftest_result_put(msg, i, test_status)) + goto selftests_nest_cancel; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +selftests_nest_cancel: + nla_nest_cancel(msg, selftests); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return err; +} + static const struct devlink_param devlink_param_generic[] = { { .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, @@ -8969,6 +9173,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -9328,6 +9533,17 @@ static const struct genl_small_ops devlink_nl_ops[] = { .doit = devlink_nl_cmd_trap_policer_set_doit, .flags = GENL_ADMIN_PERM, }, + { + .cmd = DEVLINK_CMD_SELFTESTS_GET, + .doit = devlink_nl_cmd_selftests_get_doit, + .dumpit = devlink_nl_cmd_selftests_get_dumpit + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_SELFTESTS_RUN, + .doit = devlink_nl_cmd_selftests_run, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From b07c8cdbe918aa17da864da9a89b22afaed0393e Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 27 Jul 2022 20:54:05 +0200 Subject: seg6: add support for SRv6 H.Encaps.Red behavior The SRv6 H.Encaps.Red behavior described in [1] is an optimization of the SRv6 H.Encaps behavior [2]. H.Encaps.Red reduces the length of the SRH by excluding the first segment (SID) in the SRH of the pushed IPv6 header. The first SID is only placed in the IPv6 Destination Address field of the pushed IPv6 header. When the SRv6 Policy only contains one SID the SRH is omitted, unless there is an HMAC TLV to be carried. [1] - https://datatracker.ietf.org/doc/html/rfc8986#section-5.2 [2] - https://datatracker.ietf.org/doc/html/rfc8986#section-5.1 Signed-off-by: Andrea Mayer Signed-off-by: Anton Makarov Signed-off-by: David S. Miller --- include/uapi/linux/seg6_iptunnel.h | 1 + net/ipv6/seg6_iptunnel.c | 128 ++++++++++++++++++++++++++++++++++++- 2 files changed, 128 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index eb815e0d0ac3..538152a7b2c3 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -35,6 +35,7 @@ enum { SEG6_IPTUN_MODE_INLINE, SEG6_IPTUN_MODE_ENCAP, SEG6_IPTUN_MODE_L2ENCAP, + SEG6_IPTUN_MODE_ENCAP_RED, }; #endif diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index e756ba705fd9..454bd8a838e6 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -36,6 +36,7 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) case SEG6_IPTUN_MODE_INLINE: break; case SEG6_IPTUN_MODE_ENCAP: + case SEG6_IPTUN_MODE_ENCAP_RED: head = sizeof(struct ipv6hdr); break; case SEG6_IPTUN_MODE_L2ENCAP: @@ -197,6 +198,124 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } EXPORT_SYMBOL_GPL(seg6_do_srh_encap); +/* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */ +static int seg6_do_srh_encap_red(struct sk_buff *skb, + struct ipv6_sr_hdr *osrh, int proto) +{ + __u8 first_seg = osrh->first_segment; + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); + struct ipv6hdr *hdr, *inner_hdr; + int hdrlen = ipv6_optlen(osrh); + int red_tlv_offset, tlv_offset; + struct ipv6_sr_hdr *isrh; + bool skip_srh = false; + __be32 flowlabel; + int tot_len, err; + int red_hdrlen; + int tlvs_len; + + if (first_seg > 0) { + red_hdrlen = hdrlen - sizeof(struct in6_addr); + } else { + /* NOTE: if tag/flags and/or other TLVs are introduced in the + * seg6_iptunnel infrastructure, they should be considered when + * deciding to skip the SRH. + */ + skip_srh = !sr_has_hmac(osrh); + + red_hdrlen = skip_srh ? 0 : hdrlen; + } + + tot_len = red_hdrlen + sizeof(struct ipv6hdr); + + err = skb_cow_head(skb, tot_len + skb->mac_len); + if (unlikely(err)) + return err; + + inner_hdr = ipv6_hdr(skb); + flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); + + skb_push(skb, tot_len); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + hdr = ipv6_hdr(skb); + + /* based on seg6_do_srh_encap() */ + if (skb->protocol == htons(ETH_P_IPV6)) { + ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), + flowlabel); + hdr->hop_limit = inner_hdr->hop_limit; + } else { + ip6_flow_hdr(hdr, 0, flowlabel); + hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + IP6CB(skb)->iif = skb->skb_iif; + } + + /* no matter if we have to skip the SRH or not, the first segment + * always comes in the pushed IPv6 header. + */ + hdr->daddr = osrh->segments[first_seg]; + + if (skip_srh) { + hdr->nexthdr = proto; + + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + goto out; + } + + /* we cannot skip the SRH, slow path */ + + hdr->nexthdr = NEXTHDR_ROUTING; + isrh = (void *)hdr + sizeof(struct ipv6hdr); + + if (unlikely(!first_seg)) { + /* this is a very rare case; we have only one SID but + * we cannot skip the SRH since we are carrying some + * other info. + */ + memcpy(isrh, osrh, hdrlen); + goto srcaddr; + } + + tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr); + red_tlv_offset = tlv_offset - sizeof(struct in6_addr); + + memcpy(isrh, osrh, red_tlv_offset); + + tlvs_len = hdrlen - tlv_offset; + if (unlikely(tlvs_len > 0)) { + const void *s = (const void *)osrh + tlv_offset; + void *d = (void *)isrh + red_tlv_offset; + + memcpy(d, s, tlvs_len); + } + + --isrh->first_segment; + isrh->hdrlen -= 2; + +srcaddr: + isrh->nexthdr = proto; + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); + +#ifdef CONFIG_IPV6_SEG6_HMAC + if (unlikely(!skip_srh && sr_has_hmac(isrh))) { + err = seg6_push_hmac(net, &hdr->saddr, isrh); + if (unlikely(err)) + return err; + } +#endif + +out: + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + + skb_postpush_rcsum(skb, hdr, tot_len); + + return 0; +} + /* insert an SRH within an IPv6 packet, just after the IPv6 header */ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { @@ -269,6 +388,7 @@ static int seg6_do_srh(struct sk_buff *skb) return err; break; case SEG6_IPTUN_MODE_ENCAP: + case SEG6_IPTUN_MODE_ENCAP_RED: err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6); if (err) return err; @@ -280,7 +400,11 @@ static int seg6_do_srh(struct sk_buff *skb) else return -EINVAL; - err = seg6_do_srh_encap(skb, tinfo->srh, proto); + if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP) + err = seg6_do_srh_encap(skb, tinfo->srh, proto); + else + err = seg6_do_srh_encap_red(skb, tinfo->srh, proto); + if (err) return err; @@ -517,6 +641,8 @@ static int seg6_build_state(struct net *net, struct nlattr *nla, break; case SEG6_IPTUN_MODE_L2ENCAP: break; + case SEG6_IPTUN_MODE_ENCAP_RED: + break; default: return -EINVAL; } -- cgit v1.2.3 From 13f0296be8ece1189cbc4383a45ba97cafaecc09 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 27 Jul 2022 20:54:06 +0200 Subject: seg6: add support for SRv6 H.L2Encaps.Red behavior The SRv6 H.L2Encaps.Red behavior described in [1] is an optimization of the SRv6 H.L2Encaps behavior [2]. H.L2Encaps.Red reduces the length of the SRH by excluding the first segment (SID) in the SRH of the pushed IPv6 header. The first SID is only placed in the IPv6 Destination Address field of the pushed IPv6 header. When the SRv6 Policy only contains one SID the SRH is omitted, unless there is an HMAC TLV to be carried. [1] - https://datatracker.ietf.org/doc/html/rfc8986#section-5.4 [2] - https://datatracker.ietf.org/doc/html/rfc8986#section-5.3 Signed-off-by: Andrea Mayer Signed-off-by: Anton Makarov Signed-off-by: David S. Miller --- include/uapi/linux/seg6_iptunnel.h | 1 + net/ipv6/seg6_iptunnel.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index 538152a7b2c3..a9fa777f16de 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -36,6 +36,7 @@ enum { SEG6_IPTUN_MODE_ENCAP, SEG6_IPTUN_MODE_L2ENCAP, SEG6_IPTUN_MODE_ENCAP_RED, + SEG6_IPTUN_MODE_L2ENCAP_RED, }; #endif diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 454bd8a838e6..34db881204d2 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -40,6 +40,7 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) head = sizeof(struct ipv6hdr); break; case SEG6_IPTUN_MODE_L2ENCAP: + case SEG6_IPTUN_MODE_L2ENCAP_RED: return 0; } @@ -413,6 +414,7 @@ static int seg6_do_srh(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); break; case SEG6_IPTUN_MODE_L2ENCAP: + case SEG6_IPTUN_MODE_L2ENCAP_RED: if (!skb_mac_header_was_set(skb)) return -EINVAL; @@ -422,7 +424,13 @@ static int seg6_do_srh(struct sk_buff *skb) skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); - err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET); + if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP) + err = seg6_do_srh_encap(skb, tinfo->srh, + IPPROTO_ETHERNET); + else + err = seg6_do_srh_encap_red(skb, tinfo->srh, + IPPROTO_ETHERNET); + if (err) return err; @@ -643,6 +651,8 @@ static int seg6_build_state(struct net *net, struct nlattr *nla, break; case SEG6_IPTUN_MODE_ENCAP_RED: break; + case SEG6_IPTUN_MODE_L2ENCAP_RED: + break; default: return -EINVAL; } -- cgit v1.2.3 From 8a061562e2f2b32bfb5bff5bf3afc64e37d95a27 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 29 Jul 2022 17:14:53 +0530 Subject: RISC-V: KVM: Add extensible CSR emulation framework We add an extensible CSR emulation framework which is based upon the existing system instruction emulation. This will be useful to upcoming AIA, PMU, Nested and other virtualization features. The CSR emulation framework also has provision to emulate CSR in user space but this will be used only in very specific cases such as AIA IMSIC CSR emulation in user space or vendor specific CSR emulation in user space. By default, all CSRs not handled by KVM RISC-V will be redirected back to Guest VCPU as illegal instruction trap. Signed-off-by: Anup Patel Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_host.h | 5 + arch/riscv/include/asm/kvm_vcpu_insn.h | 6 ++ arch/riscv/kvm/vcpu.c | 34 ++++--- arch/riscv/kvm/vcpu_insn.c | 172 ++++++++++++++++++++++++++++++++- include/uapi/linux/kvm.h | 8 ++ 5 files changed, 209 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index d482d771eba4..59a0cf2ca7b9 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -65,6 +65,8 @@ struct kvm_vcpu_stat { u64 wfi_exit_stat; u64 mmio_exit_user; u64 mmio_exit_kernel; + u64 csr_exit_user; + u64 csr_exit_kernel; u64 exits; }; @@ -210,6 +212,9 @@ struct kvm_vcpu_arch { /* MMIO instruction details */ struct kvm_mmio_decode mmio_decode; + /* CSR instruction details */ + struct kvm_csr_decode csr_decode; + /* SBI context */ struct kvm_sbi_context sbi_context; diff --git a/arch/riscv/include/asm/kvm_vcpu_insn.h b/arch/riscv/include/asm/kvm_vcpu_insn.h index 3351eb61a251..350011c83581 100644 --- a/arch/riscv/include/asm/kvm_vcpu_insn.h +++ b/arch/riscv/include/asm/kvm_vcpu_insn.h @@ -18,6 +18,11 @@ struct kvm_mmio_decode { int return_handled; }; +struct kvm_csr_decode { + unsigned long insn; + int return_handled; +}; + /* Return values used by function emulating a particular instruction */ enum kvm_insn_return { KVM_INSN_EXIT_TO_USER_SPACE = 0, @@ -28,6 +33,7 @@ enum kvm_insn_return { }; void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_cpu_trap *trap); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a3c051cb070c..3c95924d38c7 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -26,6 +26,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, wfi_exit_stat), STATS_DESC_COUNTER(VCPU, mmio_exit_user), STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), + STATS_DESC_COUNTER(VCPU, csr_exit_user), + STATS_DESC_COUNTER(VCPU, csr_exit_kernel), STATS_DESC_COUNTER(VCPU, exits) }; @@ -899,22 +901,26 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_vcpu_srcu_read_lock(vcpu); - /* Process MMIO value returned from user-space */ - if (run->exit_reason == KVM_EXIT_MMIO) { + switch (run->exit_reason) { + case KVM_EXIT_MMIO: + /* Process MMIO value returned from user-space */ ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); - if (ret) { - kvm_vcpu_srcu_read_unlock(vcpu); - return ret; - } - } - - /* Process SBI value returned from user-space */ - if (run->exit_reason == KVM_EXIT_RISCV_SBI) { + break; + case KVM_EXIT_RISCV_SBI: + /* Process SBI value returned from user-space */ ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); - if (ret) { - kvm_vcpu_srcu_read_unlock(vcpu); - return ret; - } + break; + case KVM_EXIT_RISCV_CSR: + /* Process CSR value returned from user-space */ + ret = kvm_riscv_vcpu_csr_return(vcpu, vcpu->run); + break; + default: + ret = 0; + break; + } + if (ret) { + kvm_vcpu_srcu_read_unlock(vcpu); + return ret; } if (run->immediate_exit) { diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 75ca62a7fba5..7eb90a47b571 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -14,6 +14,19 @@ #define INSN_MASK_WFI 0xffffffff #define INSN_MATCH_WFI 0x10500073 +#define INSN_MATCH_CSRRW 0x1073 +#define INSN_MASK_CSRRW 0x707f +#define INSN_MATCH_CSRRS 0x2073 +#define INSN_MASK_CSRRS 0x707f +#define INSN_MATCH_CSRRC 0x3073 +#define INSN_MASK_CSRRC 0x707f +#define INSN_MATCH_CSRRWI 0x5073 +#define INSN_MASK_CSRRWI 0x707f +#define INSN_MATCH_CSRRSI 0x6073 +#define INSN_MASK_CSRRSI 0x707f +#define INSN_MATCH_CSRRCI 0x7073 +#define INSN_MASK_CSRRCI 0x707f + #define INSN_MATCH_LB 0x3 #define INSN_MASK_LB 0x707f #define INSN_MATCH_LH 0x1003 @@ -71,6 +84,7 @@ #define SH_RS1 15 #define SH_RS2 20 #define SH_RS2C 2 +#define MASK_RX 0x1f #define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) #define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \ @@ -104,7 +118,7 @@ #define REG_PTR(insn, pos, regs) \ ((ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))) -#define GET_RM(insn) (((insn) >> 12) & 7) +#define GET_FUNCT3(insn) (((insn) >> 12) & 7) #define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) #define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) @@ -116,7 +130,6 @@ #define IMM_I(insn) ((s32)(insn) >> 20) #define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \ (s32)(((insn) >> 7) & 0x1f)) -#define MASK_FUNCT3 0x7000 struct insn_func { unsigned long mask; @@ -189,7 +202,162 @@ static int wfi_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) return KVM_INSN_CONTINUE_NEXT_SEPC; } +struct csr_func { + unsigned int base; + unsigned int count; + /* + * Possible return values are as same as "func" callback in + * "struct insn_func". + */ + int (*func)(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +}; + +static const struct csr_func csr_funcs[] = { }; + +/** + * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space + * emulation or in-kernel emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the CSR data + * + * Returns > 0 upon failure and 0 upon success + */ +int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong insn; + + if (vcpu->arch.csr_decode.return_handled) + return 0; + vcpu->arch.csr_decode.return_handled = 1; + + /* Update destination register for CSR reads */ + insn = vcpu->arch.csr_decode.insn; + if ((insn >> SH_RD) & MASK_RX) + SET_RD(insn, &vcpu->arch.guest_context, + run->riscv_csr.ret_value); + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += INSN_LEN(insn); + + return 0; +} + +static int csr_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + int i, rc = KVM_INSN_ILLEGAL_TRAP; + unsigned int csr_num = insn >> SH_RS2; + unsigned int rs1_num = (insn >> SH_RS1) & MASK_RX; + ulong rs1_val = GET_RS1(insn, &vcpu->arch.guest_context); + const struct csr_func *tcfn, *cfn = NULL; + ulong val = 0, wr_mask = 0, new_val = 0; + + /* Decode the CSR instruction */ + switch (GET_FUNCT3(insn)) { + case GET_FUNCT3(INSN_MATCH_CSRRW): + wr_mask = -1UL; + new_val = rs1_val; + break; + case GET_FUNCT3(INSN_MATCH_CSRRS): + wr_mask = rs1_val; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRC): + wr_mask = rs1_val; + new_val = 0; + break; + case GET_FUNCT3(INSN_MATCH_CSRRWI): + wr_mask = -1UL; + new_val = rs1_num; + break; + case GET_FUNCT3(INSN_MATCH_CSRRSI): + wr_mask = rs1_num; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRCI): + wr_mask = rs1_num; + new_val = 0; + break; + default: + return rc; + } + + /* Save instruction decode info */ + vcpu->arch.csr_decode.insn = insn; + vcpu->arch.csr_decode.return_handled = 0; + + /* Update CSR details in kvm_run struct */ + run->riscv_csr.csr_num = csr_num; + run->riscv_csr.new_value = new_val; + run->riscv_csr.write_mask = wr_mask; + run->riscv_csr.ret_value = 0; + + /* Find in-kernel CSR function */ + for (i = 0; i < ARRAY_SIZE(csr_funcs); i++) { + tcfn = &csr_funcs[i]; + if ((tcfn->base <= csr_num) && + (csr_num < (tcfn->base + tcfn->count))) { + cfn = tcfn; + break; + } + } + + /* First try in-kernel CSR emulation */ + if (cfn && cfn->func) { + rc = cfn->func(vcpu, csr_num, &val, new_val, wr_mask); + if (rc > KVM_INSN_EXIT_TO_USER_SPACE) { + if (rc == KVM_INSN_CONTINUE_NEXT_SEPC) { + run->riscv_csr.ret_value = val; + vcpu->stat.csr_exit_kernel++; + kvm_riscv_vcpu_csr_return(vcpu, run); + rc = KVM_INSN_CONTINUE_SAME_SEPC; + } + return rc; + } + } + + /* Exit to user-space for CSR emulation */ + if (rc <= KVM_INSN_EXIT_TO_USER_SPACE) { + vcpu->stat.csr_exit_user++; + run->exit_reason = KVM_EXIT_RISCV_CSR; + } + + return rc; +} + static const struct insn_func system_opcode_funcs[] = { + { + .mask = INSN_MASK_CSRRW, + .match = INSN_MATCH_CSRRW, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRS, + .match = INSN_MATCH_CSRRS, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRC, + .match = INSN_MATCH_CSRRC, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRWI, + .match = INSN_MATCH_CSRRWI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRSI, + .match = INSN_MATCH_CSRRSI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRCI, + .match = INSN_MATCH_CSRRCI, + .func = csr_insn, + }, { .mask = INSN_MASK_WFI, .match = INSN_MATCH_WFI, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 860f867c50c0..0c1f42a40fd3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -270,6 +270,7 @@ struct kvm_xen_exit { #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 #define KVM_EXIT_RISCV_SBI 35 +#define KVM_EXIT_RISCV_CSR 36 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -496,6 +497,13 @@ struct kvm_run { unsigned long args[6]; unsigned long ret[2]; } riscv_sbi; + /* KVM_EXIT_RISCV_CSR */ + struct { + unsigned long csr_num; + unsigned long new_value; + unsigned long write_mask; + unsigned long ret_value; + } riscv_csr; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From 68f2736a858324c3ec852f6c2cddd9d1c777357d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 7 Jun 2022 15:38:48 -0400 Subject: mm: Convert all PageMovable users to movable_operations These drivers are rather uncomfortably hammered into the address_space_operations hole. They aren't filesystems and don't behave like filesystems. They just need their own movable_operations structure, which we can point to directly from page->mapping. Signed-off-by: Matthew Wilcox (Oracle) --- Documentation/filesystems/locking.rst | 4 -- Documentation/filesystems/vfs.rst | 12 ---- Documentation/vm/page_migration.rst | 113 +++------------------------------- arch/powerpc/platforms/pseries/cmm.c | 60 +----------------- drivers/misc/vmw_balloon.c | 61 +----------------- drivers/virtio/virtio_balloon.c | 47 +------------- include/linux/balloon_compaction.h | 6 +- include/linux/fs.h | 2 - include/linux/migrate.h | 56 +++++++++++++++-- include/linux/page-flags.h | 2 +- include/uapi/linux/magic.h | 4 -- mm/balloon_compaction.c | 10 ++- mm/compaction.c | 29 ++++----- mm/migrate.c | 24 ++++---- mm/util.c | 4 +- mm/z3fold.c | 84 +++---------------------- mm/zsmalloc.c | 102 +++++++----------------------- 17 files changed, 134 insertions(+), 486 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index c0fe711f14d3..9963d9600b71 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -252,9 +252,7 @@ prototypes:: bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *); int (*direct_IO)(struct kiocb *, struct iov_iter *iter); - bool (*isolate_page) (struct page *, isolate_mode_t); int (*migratepage)(struct address_space *, struct page *, struct page *); - void (*putback_page) (struct page *); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count); int (*error_remove_page)(struct address_space *, struct page *); @@ -280,9 +278,7 @@ invalidate_folio: yes exclusive release_folio: yes free_folio: yes direct_IO: -isolate_page: yes migratepage: yes (both) -putback_page: yes launder_folio: yes is_partially_uptodate: yes error_remove_page: yes diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index a08c652467d7..b51665cdabc4 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -737,12 +737,8 @@ cache in your filesystem. The following members are defined: bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); - /* isolate a page for migration */ - bool (*isolate_page) (struct page *, isolate_mode_t); /* migrate the contents of a page to the specified target */ int (*migratepage) (struct page *, struct page *); - /* put migration-failed page back to right list */ - void (*putback_page) (struct page *); int (*launder_folio) (struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, @@ -930,11 +926,6 @@ cache in your filesystem. The following members are defined: data directly between the storage and the application's address space. -``isolate_page`` - Called by the VM when isolating a movable non-lru page. If page - is successfully isolated, VM marks the page as PG_isolated via - __SetPageIsolated. - ``migrate_page`` This is used to compact the physical memory usage. If the VM wants to relocate a page (maybe off a memory card that is @@ -942,9 +933,6 @@ cache in your filesystem. The following members are defined: page to this function. migrate_page should transfer any private data across and update any references that it has to the page. -``putback_page`` - Called by the VM when isolated page's migration fails. - ``launder_folio`` Called before freeing a folio - it writes back the dirty folio. To prevent redirtying the folio, it is kept locked during the diff --git a/Documentation/vm/page_migration.rst b/Documentation/vm/page_migration.rst index 8c5cb8147e55..11493bad7112 100644 --- a/Documentation/vm/page_migration.rst +++ b/Documentation/vm/page_migration.rst @@ -152,110 +152,15 @@ Steps: Non-LRU page migration ====================== -Although migration originally aimed for reducing the latency of memory accesses -for NUMA, compaction also uses migration to create high-order pages. +Although migration originally aimed for reducing the latency of memory +accesses for NUMA, compaction also uses migration to create high-order +pages. For compaction purposes, it is also useful to be able to move +non-LRU pages, such as zsmalloc and virtio-balloon pages. -Current problem of the implementation is that it is designed to migrate only -*LRU* pages. However, there are potential non-LRU pages which can be migrated -in drivers, for example, zsmalloc, virtio-balloon pages. - -For virtio-balloon pages, some parts of migration code path have been hooked -up and added virtio-balloon specific functions to intercept migration logics. -It's too specific to a driver so other drivers who want to make their pages -movable would have to add their own specific hooks in the migration path. - -To overcome the problem, VM supports non-LRU page migration which provides -generic functions for non-LRU movable pages without driver specific hooks -in the migration path. - -If a driver wants to make its pages movable, it should define three functions -which are function pointers of struct address_space_operations. - -1. ``bool (*isolate_page) (struct page *page, isolate_mode_t mode);`` - - What VM expects from isolate_page() function of driver is to return *true* - if driver isolates the page successfully. On returning true, VM marks the page - as PG_isolated so concurrent isolation in several CPUs skip the page - for isolation. If a driver cannot isolate the page, it should return *false*. - - Once page is successfully isolated, VM uses page.lru fields so driver - shouldn't expect to preserve values in those fields. - -2. ``int (*migratepage) (struct address_space *mapping,`` -| ``struct page *newpage, struct page *oldpage, enum migrate_mode);`` - - After isolation, VM calls migratepage() of driver with the isolated page. - The function of migratepage() is to move the contents of the old page to the - new page - and set up fields of struct page newpage. Keep in mind that you should - indicate to the VM the oldpage is no longer movable via __ClearPageMovable() - under page_lock if you migrated the oldpage successfully and returned - MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver - can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time - because VM interprets -EAGAIN as "temporary migration failure". On returning - any error except -EAGAIN, VM will give up the page migration without - retrying. - - Driver shouldn't touch the page.lru field while in the migratepage() function. - -3. ``void (*putback_page)(struct page *);`` - - If migration fails on the isolated page, VM should return the isolated page - to the driver so VM calls the driver's putback_page() with the isolated page. - In this function, the driver should put the isolated page back into its own data - structure. - -Non-LRU movable page flags - - There are two page flags for supporting non-LRU movable page. - - * PG_movable - - Driver should use the function below to make page movable under page_lock:: - - void __SetPageMovable(struct page *page, struct address_space *mapping) - - It needs argument of address_space for registering migration - family functions which will be called by VM. Exactly speaking, - PG_movable is not a real flag of struct page. Rather, VM - reuses the page->mapping's lower bits to represent it:: - - #define PAGE_MAPPING_MOVABLE 0x2 - page->mapping = page->mapping | PAGE_MAPPING_MOVABLE; - - so driver shouldn't access page->mapping directly. Instead, driver should - use page_mapping() which masks off the low two bits of page->mapping under - page lock so it can get the right struct address_space. - - For testing of non-LRU movable pages, VM supports __PageMovable() function. - However, it doesn't guarantee to identify non-LRU movable pages because - the page->mapping field is unified with other variables in struct page. - If the driver releases the page after isolation by VM, page->mapping - doesn't have a stable value although it has PAGE_MAPPING_MOVABLE set - (look at __ClearPageMovable). But __PageMovable() is cheap to call whether - page is LRU or non-LRU movable once the page has been isolated because LRU - pages can never have PAGE_MAPPING_MOVABLE set in page->mapping. It is also - good for just peeking to test non-LRU movable pages before more expensive - checking with lock_page() in pfn scanning to select a victim. - - For guaranteeing non-LRU movable page, VM provides PageMovable() function. - Unlike __PageMovable(), PageMovable() validates page->mapping and - mapping->a_ops->isolate_page under lock_page(). The lock_page() prevents - sudden destroying of page->mapping. - - Drivers using __SetPageMovable() should clear the flag via - __ClearMovablePage() under page_lock() before the releasing the page. - - * PG_isolated - - To prevent concurrent isolation among several CPUs, VM marks isolated page - as PG_isolated under lock_page(). So if a CPU encounters PG_isolated - non-LRU movable page, it can skip it. Driver doesn't need to manipulate the - flag because VM will set/clear it automatically. Keep in mind that if the - driver sees a PG_isolated page, it means the page has been isolated by the - VM so it shouldn't touch the page.lru field. - The PG_isolated flag is aliased with the PG_reclaim flag so drivers - shouldn't use PG_isolated for its own purposes. +If a driver wants to make its pages movable, it should define a struct +movable_operations. It then needs to call __SetPageMovable() on each +page that it may be able to move. This uses the ``page->mapping`` field, +so this field is not available for the driver to use for other purposes. Monitoring Migration ===================== @@ -286,3 +191,5 @@ THP_MIGRATION_FAIL and PGMIGRATE_FAIL to increase. Christoph Lameter, May 8, 2006. Minchan Kim, Mar 28, 2016. + +.. kernel-doc:: include/linux/migrate.h diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 15ed8206c463..5f4037c1d7fe 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -19,9 +19,6 @@ #include #include #include -#include -#include -#include #include #include #include @@ -500,19 +497,6 @@ static struct notifier_block cmm_mem_nb = { }; #ifdef CONFIG_BALLOON_COMPACTION -static struct vfsmount *balloon_mnt; - -static int cmm_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, PPC_CMM_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type balloon_fs = { - .name = "ppc-cmm", - .init_fs_context = cmm_init_fs_context, - .kill_sb = kill_anon_super, -}; - static int cmm_migratepage(struct balloon_dev_info *b_dev_info, struct page *newpage, struct page *page, enum migrate_mode mode) @@ -564,47 +548,13 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, return MIGRATEPAGE_SUCCESS; } -static int cmm_balloon_compaction_init(void) +static void cmm_balloon_compaction_init(void) { - int rc; - balloon_devinfo_init(&b_dev_info); b_dev_info.migratepage = cmm_migratepage; - - balloon_mnt = kern_mount(&balloon_fs); - if (IS_ERR(balloon_mnt)) { - rc = PTR_ERR(balloon_mnt); - balloon_mnt = NULL; - return rc; - } - - b_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb); - if (IS_ERR(b_dev_info.inode)) { - rc = PTR_ERR(b_dev_info.inode); - b_dev_info.inode = NULL; - kern_unmount(balloon_mnt); - balloon_mnt = NULL; - return rc; - } - - b_dev_info.inode->i_mapping->a_ops = &balloon_aops; - return 0; -} -static void cmm_balloon_compaction_deinit(void) -{ - if (b_dev_info.inode) - iput(b_dev_info.inode); - b_dev_info.inode = NULL; - kern_unmount(balloon_mnt); - balloon_mnt = NULL; } #else /* CONFIG_BALLOON_COMPACTION */ -static int cmm_balloon_compaction_init(void) -{ - return 0; -} - -static void cmm_balloon_compaction_deinit(void) +static void cmm_balloon_compaction_init(void) { } #endif /* CONFIG_BALLOON_COMPACTION */ @@ -622,9 +572,7 @@ static int cmm_init(void) if (!firmware_has_feature(FW_FEATURE_CMO) && !simulate) return -EOPNOTSUPP; - rc = cmm_balloon_compaction_init(); - if (rc) - return rc; + cmm_balloon_compaction_init(); rc = register_oom_notifier(&cmm_oom_nb); if (rc < 0) @@ -658,7 +606,6 @@ out_reboot_notifier: out_oom_notifier: unregister_oom_notifier(&cmm_oom_nb); out_balloon_compaction: - cmm_balloon_compaction_deinit(); return rc; } @@ -677,7 +624,6 @@ static void cmm_exit(void) unregister_memory_notifier(&cmm_mem_nb); cmm_free_pages(atomic_long_read(&loaned_pages)); cmm_unregister_sysfs(&cmm_dev); - cmm_balloon_compaction_deinit(); } /** diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 086ce77d9074..85dd6aa33df6 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -29,8 +29,6 @@ #include #include #include -#include -#include #include #include #include @@ -1730,20 +1728,6 @@ static inline void vmballoon_debugfs_exit(struct vmballoon *b) #ifdef CONFIG_BALLOON_COMPACTION - -static int vmballoon_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, BALLOON_VMW_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type vmballoon_fs = { - .name = "balloon-vmware", - .init_fs_context = vmballoon_init_fs_context, - .kill_sb = kill_anon_super, -}; - -static struct vfsmount *vmballoon_mnt; - /** * vmballoon_migratepage() - migrates a balloon page. * @b_dev_info: balloon device information descriptor. @@ -1862,21 +1846,6 @@ out_unlock: return ret; } -/** - * vmballoon_compaction_deinit() - removes compaction related data. - * - * @b: pointer to the balloon. - */ -static void vmballoon_compaction_deinit(struct vmballoon *b) -{ - if (!IS_ERR(b->b_dev_info.inode)) - iput(b->b_dev_info.inode); - - b->b_dev_info.inode = NULL; - kern_unmount(vmballoon_mnt); - vmballoon_mnt = NULL; -} - /** * vmballoon_compaction_init() - initialized compaction for the balloon. * @@ -1888,33 +1857,15 @@ static void vmballoon_compaction_deinit(struct vmballoon *b) * * Return: zero on success or error code on failure. */ -static __init int vmballoon_compaction_init(struct vmballoon *b) +static __init void vmballoon_compaction_init(struct vmballoon *b) { - vmballoon_mnt = kern_mount(&vmballoon_fs); - if (IS_ERR(vmballoon_mnt)) - return PTR_ERR(vmballoon_mnt); - b->b_dev_info.migratepage = vmballoon_migratepage; - b->b_dev_info.inode = alloc_anon_inode(vmballoon_mnt->mnt_sb); - - if (IS_ERR(b->b_dev_info.inode)) - return PTR_ERR(b->b_dev_info.inode); - - b->b_dev_info.inode->i_mapping->a_ops = &balloon_aops; - return 0; } #else /* CONFIG_BALLOON_COMPACTION */ - -static void vmballoon_compaction_deinit(struct vmballoon *b) -{ -} - -static int vmballoon_compaction_init(struct vmballoon *b) +static inline void vmballoon_compaction_init(struct vmballoon *b) { - return 0; } - #endif /* CONFIG_BALLOON_COMPACTION */ static int __init vmballoon_init(void) @@ -1939,9 +1890,7 @@ static int __init vmballoon_init(void) * balloon_devinfo_init() . */ balloon_devinfo_init(&balloon.b_dev_info); - error = vmballoon_compaction_init(&balloon); - if (error) - goto fail; + vmballoon_compaction_init(&balloon); INIT_LIST_HEAD(&balloon.huge_pages); spin_lock_init(&balloon.comm_lock); @@ -1958,7 +1907,6 @@ static int __init vmballoon_init(void) return 0; fail: vmballoon_unregister_shrinker(&balloon); - vmballoon_compaction_deinit(&balloon); return error; } @@ -1985,8 +1933,5 @@ static void __exit vmballoon_exit(void) */ vmballoon_send_start(&balloon, 0); vmballoon_pop(&balloon); - - /* Only once we popped the balloon, compaction can be deinit */ - vmballoon_compaction_deinit(&balloon); } module_exit(vmballoon_exit); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index b9737da6c4dd..bd360b91e9d3 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -17,9 +17,6 @@ #include #include #include -#include -#include -#include #include /* @@ -42,10 +39,6 @@ (1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT)) #define VIRTIO_BALLOON_HINT_BLOCK_PAGES (1 << VIRTIO_BALLOON_HINT_BLOCK_ORDER) -#ifdef CONFIG_BALLOON_COMPACTION -static struct vfsmount *balloon_mnt; -#endif - enum virtio_balloon_vq { VIRTIO_BALLOON_VQ_INFLATE, VIRTIO_BALLOON_VQ_DEFLATE, @@ -805,18 +798,6 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, return MIGRATEPAGE_SUCCESS; } - -static int balloon_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, BALLOON_KVM_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type balloon_fs = { - .name = "balloon-kvm", - .init_fs_context = balloon_init_fs_context, - .kill_sb = kill_anon_super, -}; - #endif /* CONFIG_BALLOON_COMPACTION */ static unsigned long shrink_free_pages(struct virtio_balloon *vb, @@ -909,19 +890,7 @@ static int virtballoon_probe(struct virtio_device *vdev) goto out_free_vb; #ifdef CONFIG_BALLOON_COMPACTION - balloon_mnt = kern_mount(&balloon_fs); - if (IS_ERR(balloon_mnt)) { - err = PTR_ERR(balloon_mnt); - goto out_del_vqs; - } - vb->vb_dev_info.migratepage = virtballoon_migratepage; - vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb); - if (IS_ERR(vb->vb_dev_info.inode)) { - err = PTR_ERR(vb->vb_dev_info.inode); - goto out_kern_unmount; - } - vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops; #endif if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { /* @@ -930,13 +899,13 @@ static int virtballoon_probe(struct virtio_device *vdev) */ if (virtqueue_get_vring_size(vb->free_page_vq) < 2) { err = -ENOSPC; - goto out_iput; + goto out_del_vqs; } vb->balloon_wq = alloc_workqueue("balloon-wq", WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0); if (!vb->balloon_wq) { err = -ENOMEM; - goto out_iput; + goto out_del_vqs; } INIT_WORK(&vb->report_free_page_work, report_free_page_func); vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP; @@ -1030,13 +999,7 @@ out_unregister_shrinker: out_del_balloon_wq: if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) destroy_workqueue(vb->balloon_wq); -out_iput: -#ifdef CONFIG_BALLOON_COMPACTION - iput(vb->vb_dev_info.inode); -out_kern_unmount: - kern_unmount(balloon_mnt); out_del_vqs: -#endif vdev->config->del_vqs(vdev); out_free_vb: kfree(vb); @@ -1083,12 +1046,6 @@ static void virtballoon_remove(struct virtio_device *vdev) } remove_common(vb); -#ifdef CONFIG_BALLOON_COMPACTION - if (vb->vb_dev_info.inode) - iput(vb->vb_dev_info.inode); - - kern_unmount(balloon_mnt); -#endif kfree(vb); } diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index edb7f6d41faa..5ca2d5699620 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -57,7 +57,6 @@ struct balloon_dev_info { struct list_head pages; /* Pages enqueued & handled to Host */ int (*migratepage)(struct balloon_dev_info *, struct page *newpage, struct page *page, enum migrate_mode mode); - struct inode *inode; }; extern struct page *balloon_page_alloc(void); @@ -75,11 +74,10 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) spin_lock_init(&balloon->pages_lock); INIT_LIST_HEAD(&balloon->pages); balloon->migratepage = NULL; - balloon->inode = NULL; } #ifdef CONFIG_BALLOON_COMPACTION -extern const struct address_space_operations balloon_aops; +extern const struct movable_operations balloon_mops; /* * balloon_page_insert - insert a page into the balloon's page list and make @@ -94,7 +92,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { __SetPageOffline(page); - __SetPageMovable(page, balloon->inode->i_mapping); + __SetPageMovable(page, &balloon_mops); set_page_private(page, (unsigned long)balloon); list_add(&page->lru, &balloon->pages); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ad5e3520fae..5d8ee3155ca2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -367,8 +367,6 @@ struct address_space_operations { */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); - bool (*isolate_page)(struct page *, isolate_mode_t); - void (*putback_page)(struct page *); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 069a89e847f3..82c735ba6109 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,6 +19,43 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 +/** + * struct movable_operations - Driver page migration + * @isolate_page: + * The VM calls this function to prepare the page to be moved. The page + * is locked and the driver should not unlock it. The driver should + * return ``true`` if the page is movable and ``false`` if it is not + * currently movable. After this function returns, the VM uses the + * page->lru field, so the driver must preserve any information which + * is usually stored here. + * + * @migrate_page: + * After isolation, the VM calls this function with the isolated + * @src page. The driver should copy the contents of the + * @src page to the @dst page and set up the fields of @dst page. + * Both pages are locked. + * If page migration is successful, the driver should call + * __ClearPageMovable(@src) and return MIGRATEPAGE_SUCCESS. + * If the driver cannot migrate the page at the moment, it can return + * -EAGAIN. The VM interprets this as a temporary migration failure and + * will retry it later. Any other error value is a permanent migration + * failure and migration will not be retried. + * The driver shouldn't touch the @src->lru field while in the + * migrate_page() function. It may write to @dst->lru. + * + * @putback_page: + * If migration fails on the isolated page, the VM informs the driver + * that the page is no longer a candidate for migration by calling + * this function. The driver should put the isolated page back into + * its own data structure. + */ +struct movable_operations { + bool (*isolate_page)(struct page *, isolate_mode_t); + int (*migrate_page)(struct page *dst, struct page *src, + enum migrate_mode); + void (*putback_page)(struct page *); +}; + /* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; @@ -91,13 +128,13 @@ static inline int next_demotion_node(int node) #endif #ifdef CONFIG_COMPACTION -extern int PageMovable(struct page *page); -extern void __SetPageMovable(struct page *page, struct address_space *mapping); -extern void __ClearPageMovable(struct page *page); +bool PageMovable(struct page *page); +void __SetPageMovable(struct page *page, const struct movable_operations *ops); +void __ClearPageMovable(struct page *page); #else -static inline int PageMovable(struct page *page) { return 0; } +static inline bool PageMovable(struct page *page) { return false; } static inline void __SetPageMovable(struct page *page, - struct address_space *mapping) + const struct movable_operations *ops) { } static inline void __ClearPageMovable(struct page *page) @@ -110,6 +147,15 @@ static inline bool folio_test_movable(struct folio *folio) return PageMovable(&folio->page); } +static inline +const struct movable_operations *page_movable_ops(struct page *page) +{ + VM_BUG_ON(!__PageMovable(page)); + + return (const struct movable_operations *) + ((unsigned long)page->mapping - PAGE_MAPPING_MOVABLE); +} + #ifdef CONFIG_NUMA_BALANCING extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e66f7aa3191d..3f5490f6f038 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -639,7 +639,7 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable - * page and then page->mapping points a struct address_space. + * page and then page->mapping points to a struct movable_operations. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index f724129c0425..6325d1d0e90f 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -98,12 +98,8 @@ /* Since UDF 2.01 is ISO 13346 based... */ #define UDF_SUPER_MAGIC 0x15013346 -#define BALLOON_KVM_MAGIC 0x13661366 -#define ZSMALLOC_MAGIC 0x58295829 #define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */ #define DEVMEM_MAGIC 0x454d444d /* "DMEM" */ -#define Z3FOLD_MAGIC 0x33 -#define PPC_CMM_MAGIC 0xc7571590 #define SECRETMEM_MAGIC 0x5345434d /* "SECM" */ #endif /* __LINUX_MAGIC_H__ */ diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 4b8eab4b3f45..22c96fed70b5 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -228,10 +228,8 @@ static void balloon_page_putback(struct page *page) spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); } - /* move_to_new_page() counterpart for a ballooned page */ -static int balloon_page_migrate(struct address_space *mapping, - struct page *newpage, struct page *page, +static int balloon_page_migrate(struct page *newpage, struct page *page, enum migrate_mode mode) { struct balloon_dev_info *balloon = balloon_page_device(page); @@ -250,11 +248,11 @@ static int balloon_page_migrate(struct address_space *mapping, return balloon->migratepage(balloon, newpage, page, mode); } -const struct address_space_operations balloon_aops = { - .migratepage = balloon_page_migrate, +const struct movable_operations balloon_mops = { + .migrate_page = balloon_page_migrate, .isolate_page = balloon_page_isolate, .putback_page = balloon_page_putback, }; -EXPORT_SYMBOL_GPL(balloon_aops); +EXPORT_SYMBOL_GPL(balloon_mops); #endif /* CONFIG_BALLOON_COMPACTION */ diff --git a/mm/compaction.c b/mm/compaction.c index 1f89b969c12b..f23efba1d118 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -110,28 +110,27 @@ static void split_map_pages(struct list_head *list) } #ifdef CONFIG_COMPACTION - -int PageMovable(struct page *page) +bool PageMovable(struct page *page) { - struct address_space *mapping; + const struct movable_operations *mops; VM_BUG_ON_PAGE(!PageLocked(page), page); if (!__PageMovable(page)) - return 0; + return false; - mapping = page_mapping(page); - if (mapping && mapping->a_ops && mapping->a_ops->isolate_page) - return 1; + mops = page_movable_ops(page); + if (mops) + return true; - return 0; + return false; } EXPORT_SYMBOL(PageMovable); -void __SetPageMovable(struct page *page, struct address_space *mapping) +void __SetPageMovable(struct page *page, const struct movable_operations *mops) { VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page); - page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE); + VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page); + page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE); } EXPORT_SYMBOL(__SetPageMovable); @@ -139,12 +138,10 @@ void __ClearPageMovable(struct page *page) { VM_BUG_ON_PAGE(!PageMovable(page), page); /* - * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE - * flag so that VM can catch up released page by driver after isolation. - * With it, VM migration doesn't try to put it back. + * This page still has the type of a movable page, but it's + * actually not movable any more. */ - page->mapping = (void *)((unsigned long)page->mapping & - PAGE_MAPPING_MOVABLE); + page->mapping = (void *)PAGE_MAPPING_MOVABLE; } EXPORT_SYMBOL(__ClearPageMovable); diff --git a/mm/migrate.c b/mm/migrate.c index 6c1ea61f39d8..491f03747832 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -59,7 +59,7 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) { - struct address_space *mapping; + const struct movable_operations *mops; /* * Avoid burning cycles with pages that are yet under __free_pages(), @@ -97,10 +97,10 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) if (!PageMovable(page) || PageIsolated(page)) goto out_no_isolated; - mapping = page_mapping(page); - VM_BUG_ON_PAGE(!mapping, page); + mops = page_movable_ops(page); + VM_BUG_ON_PAGE(!mops, page); - if (!mapping->a_ops->isolate_page(page, mode)) + if (!mops->isolate_page(page, mode)) goto out_no_isolated; /* Driver shouldn't use PG_isolated bit of page->flags */ @@ -120,10 +120,9 @@ out: static void putback_movable_page(struct page *page) { - struct address_space *mapping; + const struct movable_operations *mops = page_movable_ops(page); - mapping = page_mapping(page); - mapping->a_ops->putback_page(page); + mops->putback_page(page); ClearPageIsolated(page); } @@ -846,16 +845,15 @@ static int fallback_migrate_page(struct address_space *mapping, static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { - struct address_space *mapping; int rc = -EAGAIN; bool is_lru = !__PageMovable(&src->page); VM_BUG_ON_FOLIO(!folio_test_locked(src), src); VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); - mapping = folio_mapping(src); - if (likely(is_lru)) { + struct address_space *mapping = folio_mapping(src); + if (!mapping) rc = migrate_page(mapping, &dst->page, &src->page, mode); else if (mapping->a_ops->migratepage) @@ -872,6 +870,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, rc = fallback_migrate_page(mapping, &dst->page, &src->page, mode); } else { + const struct movable_operations *mops; + /* * In case of non-lru page, it could be released after * isolation step. In that case, we shouldn't try migration. @@ -883,8 +883,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, goto out; } - rc = mapping->a_ops->migratepage(mapping, &dst->page, - &src->page, mode); + mops = page_movable_ops(&src->page); + rc = mops->migrate_page(&dst->page, &src->page, mode); WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && !folio_test_isolated(src)); } diff --git a/mm/util.c b/mm/util.c index 0837570c9225..53af0e79d3e4 100644 --- a/mm/util.c +++ b/mm/util.c @@ -804,10 +804,10 @@ struct address_space *folio_mapping(struct folio *folio) return swap_address_space(folio_swap_entry(folio)); mapping = folio->mapping; - if ((unsigned long)mapping & PAGE_MAPPING_ANON) + if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; - return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); + return mapping; } EXPORT_SYMBOL(folio_mapping); diff --git a/mm/z3fold.c b/mm/z3fold.c index f41f8b0d9e9a..cf71da10d04e 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -34,15 +34,11 @@ #include #include #include -#include -#include -#include #include #include #include #include #include -#include #include /* @@ -149,7 +145,6 @@ struct z3fold_header { * @compact_wq: workqueue for page layout background optimization * @release_wq: workqueue for safe page release * @work: work_struct for safe page release - * @inode: inode for z3fold pseudo filesystem * * This structure is allocated at pool creation time and maintains metadata * pertaining to a particular z3fold pool. @@ -169,7 +164,6 @@ struct z3fold_pool { struct workqueue_struct *compact_wq; struct workqueue_struct *release_wq; struct work_struct work; - struct inode *inode; }; /* @@ -334,54 +328,6 @@ static inline void free_handle(unsigned long handle, struct z3fold_header *zhdr) } } -static int z3fold_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, Z3FOLD_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type z3fold_fs = { - .name = "z3fold", - .init_fs_context = z3fold_init_fs_context, - .kill_sb = kill_anon_super, -}; - -static struct vfsmount *z3fold_mnt; -static int __init z3fold_mount(void) -{ - int ret = 0; - - z3fold_mnt = kern_mount(&z3fold_fs); - if (IS_ERR(z3fold_mnt)) - ret = PTR_ERR(z3fold_mnt); - - return ret; -} - -static void z3fold_unmount(void) -{ - kern_unmount(z3fold_mnt); -} - -static const struct address_space_operations z3fold_aops; -static int z3fold_register_migration(struct z3fold_pool *pool) -{ - pool->inode = alloc_anon_inode(z3fold_mnt->mnt_sb); - if (IS_ERR(pool->inode)) { - pool->inode = NULL; - return 1; - } - - pool->inode->i_mapping->private_data = pool; - pool->inode->i_mapping->a_ops = &z3fold_aops; - return 0; -} - -static void z3fold_unregister_migration(struct z3fold_pool *pool) -{ - if (pool->inode) - iput(pool->inode); -} - /* Initializes the z3fold header of a newly allocated z3fold page */ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, struct z3fold_pool *pool, gfp_t gfp) @@ -1002,14 +948,10 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, pool->release_wq = create_singlethread_workqueue(pool->name); if (!pool->release_wq) goto out_wq; - if (z3fold_register_migration(pool)) - goto out_rwq; INIT_WORK(&pool->work, free_pages_work); pool->ops = ops; return pool; -out_rwq: - destroy_workqueue(pool->release_wq); out_wq: destroy_workqueue(pool->compact_wq); out_unbuddied: @@ -1043,11 +985,12 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); - z3fold_unregister_migration(pool); free_percpu(pool->unbuddied); kfree(pool); } +static const struct movable_operations z3fold_mops; + /** * z3fold_alloc() - allocates a region of a given size * @pool: z3fold pool from which to allocate @@ -1117,11 +1060,11 @@ retry: } if (can_sleep) { lock_page(page); - __SetPageMovable(page, pool->inode->i_mapping); + __SetPageMovable(page, &z3fold_mops); unlock_page(page); } else { WARN_ON(!trylock_page(page)); - __SetPageMovable(page, pool->inode->i_mapping); + __SetPageMovable(page, &z3fold_mops); unlock_page(page); } z3fold_page_lock(zhdr); @@ -1554,12 +1497,11 @@ out: return false; } -static int z3fold_page_migrate(struct address_space *mapping, struct page *newpage, - struct page *page, enum migrate_mode mode) +static int z3fold_page_migrate(struct page *newpage, struct page *page, + enum migrate_mode mode) { struct z3fold_header *zhdr, *new_zhdr; struct z3fold_pool *pool; - struct address_space *new_mapping; VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); @@ -1592,7 +1534,6 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa * so we only have to reinitialize it. */ INIT_LIST_HEAD(&new_zhdr->buddy); - new_mapping = page_mapping(page); __ClearPageMovable(page); get_page(newpage); @@ -1608,7 +1549,7 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa spin_lock(&pool->lock); list_add(&newpage->lru, &pool->lru); spin_unlock(&pool->lock); - __SetPageMovable(newpage, new_mapping); + __SetPageMovable(newpage, &z3fold_mops); z3fold_page_unlock(new_zhdr); queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work); @@ -1642,9 +1583,9 @@ static void z3fold_page_putback(struct page *page) z3fold_page_unlock(zhdr); } -static const struct address_space_operations z3fold_aops = { +static const struct movable_operations z3fold_mops = { .isolate_page = z3fold_page_isolate, - .migratepage = z3fold_page_migrate, + .migrate_page = z3fold_page_migrate, .putback_page = z3fold_page_putback, }; @@ -1746,17 +1687,11 @@ MODULE_ALIAS("zpool-z3fold"); static int __init init_z3fold(void) { - int ret; - /* * Make sure the z3fold header is not larger than the page size and * there has remaining spaces for its buddy. */ BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE - CHUNK_SIZE); - ret = z3fold_mount(); - if (ret) - return ret; - zpool_register_driver(&z3fold_zpool_driver); return 0; @@ -1764,7 +1699,6 @@ static int __init init_z3fold(void) static void __exit exit_z3fold(void) { - z3fold_unmount(); zpool_unregister_driver(&z3fold_zpool_driver); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 5d5fc04385b8..71d6edcbea48 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -41,7 +41,6 @@ #include #include #include -#include #include #include #include @@ -59,8 +58,6 @@ #include #include #include -#include -#include #include #include #include @@ -177,10 +174,6 @@ struct zs_size_stat { static struct dentry *zs_stat_root; #endif -#ifdef CONFIG_COMPACTION -static struct vfsmount *zsmalloc_mnt; -#endif - /* * We assign a page to ZS_ALMOST_EMPTY fullness group when: * n <= N / f, where @@ -252,7 +245,6 @@ struct zs_pool { struct dentry *stat_dentry; #endif #ifdef CONFIG_COMPACTION - struct inode *inode; struct work_struct free_work; #endif /* protect page/zspage migration */ @@ -271,6 +263,7 @@ struct zspage { unsigned int freeobj; struct page *first_page; struct list_head list; /* fullness list */ + struct zs_pool *pool; #ifdef CONFIG_COMPACTION rwlock_t lock; #endif @@ -295,8 +288,6 @@ static bool ZsHugePage(struct zspage *zspage) } #ifdef CONFIG_COMPACTION -static int zs_register_migration(struct zs_pool *pool); -static void zs_unregister_migration(struct zs_pool *pool); static void migrate_lock_init(struct zspage *zspage); static void migrate_read_lock(struct zspage *zspage); static void migrate_read_unlock(struct zspage *zspage); @@ -307,10 +298,6 @@ static void kick_deferred_free(struct zs_pool *pool); static void init_deferred_free(struct zs_pool *pool); static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); #else -static int zsmalloc_mount(void) { return 0; } -static void zsmalloc_unmount(void) {} -static int zs_register_migration(struct zs_pool *pool) { return 0; } -static void zs_unregister_migration(struct zs_pool *pool) {} static void migrate_lock_init(struct zspage *zspage) {} static void migrate_read_lock(struct zspage *zspage) {} static void migrate_read_unlock(struct zspage *zspage) {} @@ -1083,6 +1070,7 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, create_page_chain(class, zspage, pages); init_zspage(class, zspage); + zspage->pool = pool; return zspage; } @@ -1754,33 +1742,6 @@ static void lock_zspage(struct zspage *zspage) migrate_read_unlock(zspage); } -static int zs_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, ZSMALLOC_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type zsmalloc_fs = { - .name = "zsmalloc", - .init_fs_context = zs_init_fs_context, - .kill_sb = kill_anon_super, -}; - -static int zsmalloc_mount(void) -{ - int ret = 0; - - zsmalloc_mnt = kern_mount(&zsmalloc_fs); - if (IS_ERR(zsmalloc_mnt)) - ret = PTR_ERR(zsmalloc_mnt); - - return ret; -} - -static void zsmalloc_unmount(void) -{ - kern_unmount(zsmalloc_mnt); -} - static void migrate_lock_init(struct zspage *zspage) { rwlock_init(&zspage->lock); @@ -1823,6 +1784,8 @@ static void dec_zspage_isolation(struct zspage *zspage) zspage->isolated--; } +static const struct movable_operations zsmalloc_mops; + static void replace_sub_page(struct size_class *class, struct zspage *zspage, struct page *newpage, struct page *oldpage) { @@ -1843,7 +1806,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage, set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); if (unlikely(ZsHugePage(zspage))) newpage->index = oldpage->index; - __SetPageMovable(newpage, page_mapping(oldpage)); + __SetPageMovable(newpage, &zsmalloc_mops); } static bool zs_page_isolate(struct page *page, isolate_mode_t mode) @@ -1865,8 +1828,8 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) return true; } -static int zs_page_migrate(struct address_space *mapping, struct page *newpage, - struct page *page, enum migrate_mode mode) +static int zs_page_migrate(struct page *newpage, struct page *page, + enum migrate_mode mode) { struct zs_pool *pool; struct size_class *class; @@ -1889,14 +1852,15 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); - pool = mapping->private_data; + /* The page is locked, so this pointer must remain valid */ + zspage = get_zspage(page); + pool = zspage->pool; /* * The pool migrate_lock protects the race between zpage migration * and zs_free. */ write_lock(&pool->migrate_lock); - zspage = get_zspage(page); class = zspage_class(pool, zspage); /* @@ -1964,31 +1928,12 @@ static void zs_page_putback(struct page *page) migrate_write_unlock(zspage); } -static const struct address_space_operations zsmalloc_aops = { +static const struct movable_operations zsmalloc_mops = { .isolate_page = zs_page_isolate, - .migratepage = zs_page_migrate, + .migrate_page = zs_page_migrate, .putback_page = zs_page_putback, }; -static int zs_register_migration(struct zs_pool *pool) -{ - pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb); - if (IS_ERR(pool->inode)) { - pool->inode = NULL; - return 1; - } - - pool->inode->i_mapping->private_data = pool; - pool->inode->i_mapping->a_ops = &zsmalloc_aops; - return 0; -} - -static void zs_unregister_migration(struct zs_pool *pool) -{ - flush_work(&pool->free_work); - iput(pool->inode); -} - /* * Caller should hold page_lock of all pages in the zspage * In here, we cannot use zspage meta data. @@ -2032,6 +1977,11 @@ static void kick_deferred_free(struct zs_pool *pool) schedule_work(&pool->free_work); } +static void zs_flush_migration(struct zs_pool *pool) +{ + flush_work(&pool->free_work); +} + static void init_deferred_free(struct zs_pool *pool) { INIT_WORK(&pool->free_work, async_free_zspage); @@ -2043,10 +1993,12 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) do { WARN_ON(!trylock_page(page)); - __SetPageMovable(page, pool->inode->i_mapping); + __SetPageMovable(page, &zsmalloc_mops); unlock_page(page); } while ((page = get_next_page(page)) != NULL); } +#else +static inline void zs_flush_migration(struct zs_pool *pool) { } #endif /* @@ -2324,9 +2276,6 @@ struct zs_pool *zs_create_pool(const char *name) /* debug only, don't abort if it fails */ zs_pool_stat_create(pool, name); - if (zs_register_migration(pool)) - goto err; - /* * Not critical since shrinker is only used to trigger internal * defragmentation of the pool which is pretty optional thing. If @@ -2348,7 +2297,7 @@ void zs_destroy_pool(struct zs_pool *pool) int i; zs_unregister_shrinker(pool); - zs_unregister_migration(pool); + zs_flush_migration(pool); zs_pool_stat_destroy(pool); for (i = 0; i < ZS_SIZE_CLASSES; i++) { @@ -2380,14 +2329,10 @@ static int __init zs_init(void) { int ret; - ret = zsmalloc_mount(); - if (ret) - goto out; - ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare", zs_cpu_prepare, zs_cpu_dead); if (ret) - goto hp_setup_fail; + goto out; #ifdef CONFIG_ZPOOL zpool_register_driver(&zs_zpool_driver); @@ -2397,8 +2342,6 @@ static int __init zs_init(void) return 0; -hp_setup_fail: - zsmalloc_unmount(); out: return ret; } @@ -2408,7 +2351,6 @@ static void __exit zs_exit(void) #ifdef CONFIG_ZPOOL zpool_unregister_driver(&zs_zpool_driver); #endif - zsmalloc_unmount(); cpuhp_remove_state(CPUHP_MM_ZS_PREPARE); zs_stat_exit(); -- cgit v1.2.3 From 0aa73170eba5eae638c1b96a05eba533f030b5cb Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 30 Jul 2022 17:27:49 +0800 Subject: ublk_drv: add SET_PARAMS/GET_PARAMS control command Add two commands to set/get parameters generically. One important goal of ublk is to provide generic framework for making block device by userspace flexibly. As one generic block device, there are still lots of block parameters, such as max_sectors, write_cache/fua, discard related limits, zoned parameters, ...., so this patch starts to add generic mechanism for set/get device parameters. Both generic block parameters(all kinds of queue settings) and ublk feature parameters can be covered with this way, then it becomes quite easy to extend in future. Add two parameter types are used so far: basic(covers basic queue setting and misc settings which can't be grouped easily) and discard, basic type must be set, and discard type becomes optional now This way provides mechanism to simulate any kind of generic block device from userspace easily, from both block queue setting viewpoint or ublk feature viewpoint. The style of putting all parameters together is suggested by Christoph. Suggested-by: Christoph Hellwig Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220730092750.1118167-4-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 205 ++++++++++++++++++++++++++++++++++++++---- include/uapi/linux/ublk_cmd.h | 47 ++++++++++ 2 files changed, 234 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index ae98e81b21ce..20ad83b25318 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -49,6 +49,9 @@ /* All UBLK_F_* have to be included into UBLK_F_ALL */ #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_URING_CMD_COMP_IN_TASK) +/* All UBLK_PARAM_TYPE_* should be included here */ +#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) + struct ublk_rq_data { struct callback_head work; }; @@ -137,6 +140,8 @@ struct ublk_device { spinlock_t mm_lock; struct mm_struct *mm; + struct ublk_params params; + struct completion completion; unsigned int nr_queues_ready; atomic_t nr_aborted_queues; @@ -149,6 +154,12 @@ struct ublk_device { struct work_struct stop_work; }; +/* header of ublk_params */ +struct ublk_params_header { + __u32 len; + __u32 types; +}; + static dev_t ublk_chr_devt; static struct class *ublk_chr_class; @@ -160,6 +171,91 @@ static DEFINE_MUTEX(ublk_ctl_mutex); static struct miscdevice ublk_misc; +static void ublk_dev_param_basic_apply(struct ublk_device *ub) +{ + struct request_queue *q = ub->ub_disk->queue; + const struct ublk_param_basic *p = &ub->params.basic; + + blk_queue_logical_block_size(q, 1 << p->logical_bs_shift); + blk_queue_physical_block_size(q, 1 << p->physical_bs_shift); + blk_queue_io_min(q, 1 << p->io_min_shift); + blk_queue_io_opt(q, 1 << p->io_opt_shift); + + blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE, + p->attrs & UBLK_ATTR_FUA); + if (p->attrs & UBLK_ATTR_ROTATIONAL) + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + else + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + + blk_queue_max_hw_sectors(q, p->max_sectors); + blk_queue_chunk_sectors(q, p->chunk_sectors); + blk_queue_virt_boundary(q, p->virt_boundary_mask); + + if (p->attrs & UBLK_ATTR_READ_ONLY) + set_disk_ro(ub->ub_disk, true); + + set_capacity(ub->ub_disk, p->dev_sectors); +} + +static void ublk_dev_param_discard_apply(struct ublk_device *ub) +{ + struct request_queue *q = ub->ub_disk->queue; + const struct ublk_param_discard *p = &ub->params.discard; + + q->limits.discard_alignment = p->discard_alignment; + q->limits.discard_granularity = p->discard_granularity; + blk_queue_max_discard_sectors(q, p->max_discard_sectors); + blk_queue_max_write_zeroes_sectors(q, + p->max_write_zeroes_sectors); + blk_queue_max_discard_segments(q, p->max_discard_segments); +} + +static int ublk_validate_params(const struct ublk_device *ub) +{ + /* basic param is the only one which must be set */ + if (ub->params.types & UBLK_PARAM_TYPE_BASIC) { + const struct ublk_param_basic *p = &ub->params.basic; + + if (p->logical_bs_shift > PAGE_SHIFT) + return -EINVAL; + + if (p->logical_bs_shift > p->physical_bs_shift) + return -EINVAL; + + if (p->max_sectors > (ub->dev_info.rq_max_blocks << + (ub->bs_shift - 9))) + return -EINVAL; + } else + return -EINVAL; + + if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) { + const struct ublk_param_discard *p = &ub->params.discard; + + /* So far, only support single segment discard */ + if (p->max_discard_sectors && p->max_discard_segments != 1) + return -EINVAL; + + if (!p->discard_granularity) + return -EINVAL; + } + + return 0; +} + +static int ublk_apply_params(struct ublk_device *ub) +{ + if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC)) + return -EINVAL; + + ublk_dev_param_basic_apply(ub); + + if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) + ublk_dev_param_discard_apply(ub); + + return 0; +} + static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) { if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) && @@ -1138,7 +1234,6 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) { struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; int ublksrv_pid = (int)header->data[0]; - unsigned long dev_blocks = header->data[1]; struct ublk_device *ub; struct gendisk *disk; int ret = -EINVAL; @@ -1161,10 +1256,6 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) goto out_unlock; } - /* We may get disk size updated */ - if (dev_blocks) - ub->dev_info.dev_blocks = dev_blocks; - disk = blk_mq_alloc_disk(&ub->tag_set, ub); if (IS_ERR(disk)) { ret = PTR_ERR(disk); @@ -1174,19 +1265,13 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) disk->fops = &ub_fops; disk->private_data = ub; - blk_queue_logical_block_size(disk->queue, ub->dev_info.block_size); - blk_queue_physical_block_size(disk->queue, ub->dev_info.block_size); - blk_queue_io_min(disk->queue, ub->dev_info.block_size); - blk_queue_max_hw_sectors(disk->queue, - ub->dev_info.rq_max_blocks << (ub->bs_shift - 9)); - disk->queue->limits.discard_granularity = PAGE_SIZE; - blk_queue_max_discard_sectors(disk->queue, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(disk->queue, UINT_MAX >> 9); - - set_capacity(disk, ub->dev_info.dev_blocks << (ub->bs_shift - 9)); - ub->dev_info.ublksrv_pid = ublksrv_pid; ub->ub_disk = disk; + + ret = ublk_apply_params(ub); + if (ret) + goto out_put_disk; + get_device(&ub->cdev_dev); ret = add_disk(disk); if (ret) { @@ -1195,11 +1280,13 @@ static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd) * called in case of add_disk failure. */ ublk_put_device(ub); - put_disk(disk); - goto out_unlock; + goto out_put_disk; } set_bit(UB_STATE_USED, &ub->state); ub->dev_info.state = UBLK_S_DEV_LIVE; +out_put_disk: + if (ret) + put_disk(disk); out_unlock: mutex_unlock(&ub->mutex); ublk_put_device(ub); @@ -1447,6 +1534,82 @@ static int ublk_ctrl_get_dev_info(struct io_uring_cmd *cmd) return ret; } +static int ublk_ctrl_get_params(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct ublk_params_header ph; + struct ublk_device *ub; + int ret; + + if (header->len <= sizeof(ph) || !header->addr) + return -EINVAL; + + if (copy_from_user(&ph, argp, sizeof(ph))) + return -EFAULT; + + if (ph.len > header->len || !ph.len) + return -EINVAL; + + if (ph.len > sizeof(struct ublk_params)) + ph.len = sizeof(struct ublk_params); + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return -EINVAL; + + mutex_lock(&ub->mutex); + if (copy_to_user(argp, &ub->params, ph.len)) + ret = -EFAULT; + else + ret = 0; + mutex_unlock(&ub->mutex); + + ublk_put_device(ub); + return ret; +} + +static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + void __user *argp = (void __user *)(unsigned long)header->addr; + struct ublk_params_header ph; + struct ublk_device *ub; + int ret = -EFAULT; + + if (header->len <= sizeof(ph) || !header->addr) + return -EINVAL; + + if (copy_from_user(&ph, argp, sizeof(ph))) + return -EFAULT; + + if (ph.len > header->len || !ph.len || !ph.types) + return -EINVAL; + + if (ph.len > sizeof(struct ublk_params)) + ph.len = sizeof(struct ublk_params); + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return -EINVAL; + + /* parameters can only be changed when device isn't live */ + mutex_lock(&ub->mutex); + if (ub->dev_info.state == UBLK_S_DEV_LIVE) { + ret = -EACCES; + } else if (copy_from_user(&ub->params, argp, ph.len)) { + ret = -EFAULT; + } else { + /* clear all we don't support yet */ + ub->params.types &= UBLK_PARAM_TYPE_ALL; + ret = ublk_validate_params(ub); + } + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + + return ret; +} + static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -1482,6 +1645,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, case UBLK_CMD_GET_QUEUE_AFFINITY: ret = ublk_ctrl_get_queue_affinity(cmd); break; + case UBLK_CMD_GET_PARAMS: + ret = ublk_ctrl_get_params(cmd); + break; + case UBLK_CMD_SET_PARAMS: + ret = ublk_ctrl_set_params(cmd); + break; default: break; } diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index ca33092354ab..54d065426f06 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -15,6 +15,8 @@ #define UBLK_CMD_DEL_DEV 0x05 #define UBLK_CMD_START_DEV 0x06 #define UBLK_CMD_STOP_DEV 0x07 +#define UBLK_CMD_SET_PARAMS 0x08 +#define UBLK_CMD_GET_PARAMS 0x09 /* * IO commands, issued by ublk server, and handled by ublk driver. @@ -158,4 +160,49 @@ struct ublksrv_io_cmd { __u64 addr; }; +struct ublk_param_basic { +#define UBLK_ATTR_READ_ONLY (1 << 0) +#define UBLK_ATTR_ROTATIONAL (1 << 1) +#define UBLK_ATTR_VOLATILE_CACHE (1 << 2) +#define UBLK_ATTR_FUA (1 << 3) + __u32 attrs; + __u8 logical_bs_shift; + __u8 physical_bs_shift; + __u8 io_opt_shift; + __u8 io_min_shift; + + __u32 max_sectors; + __u32 chunk_sectors; + + __u64 dev_sectors; + __u64 virt_boundary_mask; +}; + +struct ublk_param_discard { + __u32 discard_alignment; + + __u32 discard_granularity; + __u32 max_discard_sectors; + + __u32 max_write_zeroes_sectors; + __u16 max_discard_segments; + __u16 reserved0; +}; + +struct ublk_params { + /* + * Total length of parameters, userspace has to set 'len' for both + * SET_PARAMS and GET_PARAMS command, and driver may update len + * if two sides use different version of 'ublk_params', same with + * 'types' fields. + */ + __u32 len; +#define UBLK_PARAM_TYPE_BASIC (1 << 0) +#define UBLK_PARAM_TYPE_DISCARD (1 << 1) + __u32 types; /* types of parameter included */ + + struct ublk_param_basic basic; + struct ublk_param_discard discard; +}; + #endif -- cgit v1.2.3 From 4bf9cbf3e93426e9ebe136dabd6ca392ca92cfcb Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 30 Jul 2022 17:27:50 +0800 Subject: ublk_drv: cleanup ublksrv_ctrl_dev_info Remove all block device related info from ublksrv_ctrl_dev_info, meantime reduce its size into 64 bytes because: 1) ublksrv_ctrl_dev_info becomes cleaner without including any block related info 2) generic set/get parameter command can be used to set block related setting easily and cleanly 3) generic set/get parameter command can be used for extending ublk without needing more info in ublksrv_ctrl_dev_info Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220730092750.1118167-5-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 18 +++++++----------- include/uapi/linux/ublk_cmd.h | 15 ++++++++------- 2 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 20ad83b25318..2b3cd671a653 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -122,7 +122,6 @@ struct ublk_device { char *__queues; unsigned short queue_size; - unsigned short bs_shift; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; @@ -223,8 +222,7 @@ static int ublk_validate_params(const struct ublk_device *ub) if (p->logical_bs_shift > p->physical_bs_shift) return -EINVAL; - if (p->max_sectors > (ub->dev_info.rq_max_blocks << - (ub->bs_shift - 9))) + if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9)) return -EINVAL; } else return -EINVAL; @@ -1185,13 +1183,13 @@ static void ublk_stop_work_fn(struct work_struct *work) ublk_stop_dev(ub); } -/* align maximum I/O size to PAGE_SIZE */ +/* align max io buffer size with PAGE_SIZE */ static void ublk_align_max_io_size(struct ublk_device *ub) { - unsigned int max_rq_bytes = ub->dev_info.rq_max_blocks << ub->bs_shift; + unsigned int max_io_bytes = ub->dev_info.max_io_buf_bytes; - ub->dev_info.rq_max_blocks = - round_down(max_rq_bytes, PAGE_SIZE) >> ub->bs_shift; + ub->dev_info.max_io_buf_bytes = + round_down(max_io_bytes, PAGE_SIZE); } static int ublk_add_tag_set(struct ublk_device *ub) @@ -1348,9 +1346,8 @@ static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) { pr_devel("%s: dev id %d flags %llx\n", __func__, info->dev_id, info->flags); - pr_devel("\t nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n", - info->nr_hw_queues, info->queue_depth, - info->block_size, info->dev_blocks); + pr_devel("\t nr_hw_queues %d queue_depth %d\n", + info->nr_hw_queues, info->queue_depth); } static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) @@ -1410,7 +1407,6 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; - ub->bs_shift = ilog2(ub->dev_info.block_size); ub->dev_info.nr_hw_queues = min_t(unsigned int, ub->dev_info.nr_hw_queues, nr_cpu_ids); ublk_align_max_io_size(ub); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 54d065426f06..57d86d0e8c5b 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -80,22 +80,23 @@ struct ublksrv_ctrl_cmd { struct ublksrv_ctrl_dev_info { __u16 nr_hw_queues; __u16 queue_depth; - __u16 block_size; __u16 state; + __u16 pad0; - __u32 rq_max_blocks; + __u32 max_io_buf_bytes; __u32 dev_id; - __u64 dev_blocks; - __s32 ublksrv_pid; - __s32 reserved0; + __u32 pad1; + __u64 flags; - __u64 flags_reserved; /* For ublksrv internal use, invisible to ublk driver */ __u64 ublksrv_flags; - __u64 reserved1[9]; + + __u64 reserved0; + __u64 reserved1; + __u64 reserved2; }; #define UBLK_IO_OP_READ 0 -- cgit v1.2.3 From 4e18403d9485a43e1b54397df258b8df7dac9a83 Mon Sep 17 00:00:00 2001 From: ZiyangZhang Date: Thu, 28 Jul 2022 20:39:15 +0800 Subject: ublk_cmd.h: add one new ublk command: UBLK_IO_NEED_GET_DATA Add one new ublk command: UBLK_IO_NEED_GET_DATA. It is prepared for a new feature designed for a user application who wants to allocate IO buffer and set IO buffer address only after it receives an IO request from ublksrv. Reviewed-by: Ming Lei Signed-off-by: ZiyangZhang Link: https://lore.kernel.org/r/c8a64b6b51c78340da7daa9e1054608695e79619.1659011443.git.ZiyangZhang@linux.alibaba.com Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 57d86d0e8c5b..677edaab2b66 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -30,12 +30,21 @@ * this IO request, request's handling result is committed to ublk * driver, meantime FETCH_REQ is piggyback, and FETCH_REQ has to be * handled before completing io request. + * + * NEED_GET_DATA: only used for write requests to set io addr and copy data + * When NEED_GET_DATA is set, ublksrv has to issue UBLK_IO_NEED_GET_DATA + * command after ublk driver returns UBLK_IO_RES_NEED_GET_DATA. + * + * It is only used if ublksrv set UBLK_F_NEED_GET_DATA flag + * while starting a ublk device. */ #define UBLK_IO_FETCH_REQ 0x20 #define UBLK_IO_COMMIT_AND_FETCH_REQ 0x21 +#define UBLK_IO_NEED_GET_DATA 0x22 /* only ABORT means that no re-fetch */ #define UBLK_IO_RES_OK 0 +#define UBLK_IO_RES_NEED_GET_DATA 1 #define UBLK_IO_RES_ABORT (-ENODEV) #define UBLKSRV_CMD_BUF_OFFSET 0 @@ -56,6 +65,15 @@ */ #define UBLK_F_URING_CMD_COMP_IN_TASK (1ULL << 1) +/* + * User should issue io cmd again for write requests to + * set io buffer address and copy data from bio vectors + * to the userspace io buffer. + * + * In this mode, task_work is not used. + */ +#define UBLK_F_NEED_GET_DATA (1UL << 2) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 36d763509be326bb383b1b1852a129ff58d74e3b Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Wed, 27 Jul 2022 17:40:53 +0200 Subject: xfrm: fix XFRMA_LASTUSED comment It is a __u64, internally time64_t. Fixes: bf825f81b454 ("xfrm: introduce basic mark infrastructure") Signed-off-by: Antony Antony Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 65e13a099b1a..a9f5d884560a 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -296,7 +296,7 @@ enum xfrm_attr_type_t { XFRMA_ETIMER_THRESH, XFRMA_SRCADDR, /* xfrm_address_t */ XFRMA_COADDR, /* xfrm_address_t */ - XFRMA_LASTUSED, /* unsigned long */ + XFRMA_LASTUSED, /* __u64 */ XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */ XFRMA_MIGRATE, XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */ -- cgit v1.2.3 From 23339e5752d01a4b5e122759b002cf896d26f6c1 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Mon, 1 Aug 2022 10:08:08 -0700 Subject: f2fs: revive F2FS_IOC_ABORT_VOLATILE_WRITE F2FS_IOC_ABORT_VOLATILE_WRITE was used to abort a atomic write before. However it was removed accidentally. So revive it by changing the name, since volatile write had gone. Signed-off-by: Daeho Jeong Fiexes: 7bc155fec5b3("f2fs: kill volatile write support") Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 30 ++++++++++++++++++++++++++++-- include/uapi/linux/f2fs.h | 2 +- 2 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8098ed890e94..29711e5b6983 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2109,6 +2109,31 @@ unlock_out: return ret; } +static int f2fs_ioc_abort_atomic_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + int ret; + + if (!inode_owner_or_capable(mnt_userns, inode)) + return -EACCES; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + + if (f2fs_is_atomic_file(inode)) + f2fs_abort_atomic_write(inode, true); + + inode_unlock(inode); + + mnt_drop_write_file(filp); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + return ret; +} + static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -4054,9 +4079,10 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_start_atomic_write(filp); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); + case F2FS_IOC_ABORT_ATOMIC_WRITE: + return f2fs_ioc_abort_atomic_write(filp); case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: return -EOPNOTSUPP; case F2FS_IOC_SHUTDOWN: return f2fs_ioc_shutdown(filp, arg); @@ -4725,7 +4751,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_COMMIT_ATOMIC_WRITE: case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_ABORT_ATOMIC_WRITE: case F2FS_IOC_SHUTDOWN: case FITRIM: case FS_IOC_SET_ENCRYPTION_POLICY: diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index 352a822d4370..3121d127d5aa 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -13,7 +13,7 @@ #define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2) #define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3) #define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) -#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) +#define F2FS_IOC_ABORT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 5) #define F2FS_IOC_GARBAGE_COLLECT _IOW(F2FS_IOCTL_MAGIC, 6, __u32) #define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) #define F2FS_IOC_DEFRAGMENT _IOWR(F2FS_IOCTL_MAGIC, 8, \ -- cgit v1.2.3 From 134941683b89d05b5e5c28c817c95049ba409d01 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 6 Aug 2022 17:39:20 +0200 Subject: netfilter: ip6t_LOG: Fix a typo in a comment s/_IPT_LOG_H/_IP6T_LOG_H/ While at it add some surrounding space to ease reading. Signed-off-by: Christophe JAILLET Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter_ipv6/ip6t_LOG.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h index 23e91a9c2583..0b7b16dbdec2 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h @@ -17,4 +17,4 @@ struct ip6t_log_info { char prefix[30]; }; -#endif /*_IPT_LOG_H*/ +#endif /* _IP6T_LOG_H */ -- cgit v1.2.3 From f329a0ebeaba4ffe91d431e0ac1ca7f9165872a4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 9 Aug 2022 16:27:40 -0700 Subject: genetlink: correct uAPI defines Commit 50a896cf2d6f ("genetlink: properly support per-op policy dumping") seems to have copy'n'pasted things a little incorrectly. The #define CTRL_ATTR_MCAST_GRP_MAX should have stayed right after the previous enum. The new CTRL_ATTR_POLICY_* needs its own define for MAX and that max should not contain the superfluous _DUMP in the name. We probably can't do anything about the CTRL_ATTR_POLICY_DUMP_MAX any more, there's likely code which uses it. For consistency (*cough* codegen *cough*) let's add the correctly name define nonetheless. Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/uapi/linux/genetlink.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index d83f214b4134..ddba3ca01e39 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -87,6 +87,8 @@ enum { __CTRL_ATTR_MCAST_GRP_MAX, }; +#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) + enum { CTRL_ATTR_POLICY_UNSPEC, CTRL_ATTR_POLICY_DO, @@ -96,7 +98,6 @@ enum { CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1 }; -#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) - +#define CTRL_ATTR_POLICY_MAX (__CTRL_ATTR_POLICY_DUMP_MAX - 1) #endif /* _UAPI__LINUX_GENERIC_NETLINK_H */ -- cgit v1.2.3 From ea024594b1dc5b6719c1400ae154690f5c203996 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:45 +0800 Subject: virtio_pci: struct virtio_pci_common_cfg add queue_notify_data Add queue_notify_data in struct virtio_pci_common_cfg, which comes from here https://github.com/oasis-tcs/virtio-spec/issues/89 In order not to affect the API, add a dedicated structure struct virtio_pci_modern_common_cfg to virtio_pci_modern.h. Since I want to add queue_reset after queue_notify_data, I submitted this patch first. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-26-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 7 +++++++ include/uapi/linux/virtio_pci.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index eb2bd9b4077d..41f5a018bd94 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -5,6 +5,13 @@ #include #include +struct virtio_pci_modern_common_cfg { + struct virtio_pci_common_cfg cfg; + + __le16 queue_notify_data; /* read-write */ + __le16 padding; +}; + struct virtio_pci_modern_device { struct pci_dev *pci_dev; diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 3a86f36d7e3d..f5981a874481 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -202,6 +202,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_AVAILHI 44 #define VIRTIO_PCI_COMMON_Q_USEDLO 48 #define VIRTIO_PCI_COMMON_Q_USEDHI 52 +#define VIRTIO_PCI_COMMON_Q_NDATA 56 #endif /* VIRTIO_PCI_NO_MODERN */ -- cgit v1.2.3 From d94587b5bb5c4bba32fbc2bd92c86cc6de25167f Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:47 +0800 Subject: virtio: queue_reset: add VIRTIO_F_RING_RESET Added VIRTIO_F_RING_RESET, it came from here https://github.com/oasis-tcs/virtio-spec/issues/124 https://github.com/oasis-tcs/virtio-spec/issues/139 This feature indicates that the driver can reset a queue individually. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-28-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_config.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index f0fb0ae021c0..3c05162bc988 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -52,7 +52,7 @@ * rest are per-device feature bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 38 +#define VIRTIO_TRANSPORT_F_END 41 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -98,4 +98,9 @@ * Does the device support Single Root I/O Virtualization? */ #define VIRTIO_F_SR_IOV 37 + +/* + * This feature indicates that the driver can reset a queue individually. + */ +#define VIRTIO_F_RING_RESET 40 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From 0cdd450e70510c9e13af8099e9f6c1467e6a0b91 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:49 +0800 Subject: virtio_pci: struct virtio_pci_common_cfg add queue_reset Add queue_reset in virtio_pci_modern_common_cfg. https://github.com/oasis-tcs/virtio-spec/issues/124 https://github.com/oasis-tcs/virtio-spec/issues/139 Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-30-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 2 +- include/uapi/linux/virtio_pci.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index 41f5a018bd94..05123b9a606f 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -9,7 +9,7 @@ struct virtio_pci_modern_common_cfg { struct virtio_pci_common_cfg cfg; __le16 queue_notify_data; /* read-write */ - __le16 padding; + __le16 queue_reset; /* read-write */ }; struct virtio_pci_modern_device { diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index f5981a874481..f703afc7ad31 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -203,6 +203,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_USEDLO 48 #define VIRTIO_PCI_COMMON_Q_USEDHI 52 #define VIRTIO_PCI_COMMON_Q_NDATA 56 +#define VIRTIO_PCI_COMMON_Q_RESET 58 #endif /* VIRTIO_PCI_NO_MODERN */ -- cgit v1.2.3 From 699b045a8e43bd1063db4795be685bfd659649dc Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Mon, 18 Jul 2022 12:11:02 +0300 Subject: net: virtio_net: notifications coalescing support New VirtIO network feature: VIRTIO_NET_F_NOTF_COAL. Control a Virtio network device notifications coalescing parameters using the control virtqueue. A device that supports this fetature can receive VIRTIO_NET_CTRL_NOTF_COAL control commands. - VIRTIO_NET_CTRL_NOTF_COAL_TX_SET: Ask the network device to change the following parameters: - tx_usecs: Maximum number of usecs to delay a TX notification. - tx_max_packets: Maximum number of packets to send before a TX notification. - VIRTIO_NET_CTRL_NOTF_COAL_RX_SET: Ask the network device to change the following parameters: - rx_usecs: Maximum number of usecs to delay a RX notification. - rx_max_packets: Maximum number of packets to receive before a RX notification. VirtIO spec. patch: https://lists.oasis-open.org/archives/virtio-comment/202206/msg00100.html Signed-off-by: Alvaro Karsz Message-Id: <20220718091102.498774-1-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Jakub Kicinski Acked-by: Jason Wang --- drivers/net/virtio_net.c | 111 ++++++++++++++++++++++++++++++++++------ include/uapi/linux/virtio_net.h | 34 +++++++++++- 2 files changed, 129 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 16783ed782c5..d9c434b00e9b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -270,6 +270,12 @@ struct virtnet_info { u8 duplex; u32 speed; + /* Interrupt coalescing settings */ + u32 tx_usecs; + u32 rx_usecs; + u32 tx_max_packets; + u32 rx_max_packets; + unsigned long guest_offloads; unsigned long guest_offloads_capable; @@ -2737,27 +2743,89 @@ static int virtnet_get_link_ksettings(struct net_device *dev, return 0; } +static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, + struct ethtool_coalesce *ec) +{ + struct scatterlist sgs_tx, sgs_rx; + struct virtio_net_ctrl_coal_tx coal_tx; + struct virtio_net_ctrl_coal_rx coal_rx; + + coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); + coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); + sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx)); + + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, + VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, + &sgs_tx)) + return -EINVAL; + + /* Save parameters */ + vi->tx_usecs = ec->tx_coalesce_usecs; + vi->tx_max_packets = ec->tx_max_coalesced_frames; + + coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); + coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); + sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx)); + + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, + VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, + &sgs_rx)) + return -EINVAL; + + /* Save parameters */ + vi->rx_usecs = ec->rx_coalesce_usecs; + vi->rx_max_packets = ec->rx_max_coalesced_frames; + + return 0; +} + +static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) +{ + /* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL + * feature is negotiated. + */ + if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs) + return -EOPNOTSUPP; + + if (ec->tx_max_coalesced_frames > 1 || + ec->rx_max_coalesced_frames != 1) + return -EINVAL; + + return 0; +} + static int virtnet_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); - int i, napi_weight; - - if (ec->tx_max_coalesced_frames > 1 || - ec->rx_max_coalesced_frames != 1) - return -EINVAL; + int ret, i, napi_weight; + bool update_napi = false; + /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; if (napi_weight ^ vi->sq[0].napi.weight) { if (dev->flags & IFF_UP) return -EBUSY; + else + update_napi = true; + } + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) + ret = virtnet_send_notf_coal_cmds(vi, ec); + else + ret = virtnet_coal_params_supported(ec); + + if (ret) + return ret; + + if (update_napi) { for (i = 0; i < vi->max_queue_pairs; i++) vi->sq[i].napi.weight = napi_weight; } - return 0; + return ret; } static int virtnet_get_coalesce(struct net_device *dev, @@ -2765,16 +2833,19 @@ static int virtnet_get_coalesce(struct net_device *dev, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { - struct ethtool_coalesce ec_default = { - .cmd = ETHTOOL_GCOALESCE, - .rx_max_coalesced_frames = 1, - }; struct virtnet_info *vi = netdev_priv(dev); - memcpy(ec, &ec_default, sizeof(ec_default)); + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { + ec->rx_coalesce_usecs = vi->rx_usecs; + ec->tx_coalesce_usecs = vi->tx_usecs; + ec->tx_max_coalesced_frames = vi->tx_max_packets; + ec->rx_max_coalesced_frames = vi->rx_max_packets; + } else { + ec->rx_max_coalesced_frames = 1; - if (vi->sq[0].napi.weight) - ec->tx_max_coalesced_frames = 1; + if (vi->sq[0].napi.weight) + ec->tx_max_coalesced_frames = 1; + } return 0; } @@ -2893,7 +2964,8 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) } static const struct ethtool_ops virtnet_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES, + .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USECS, .get_drvinfo = virtnet_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = virtnet_get_ringparam, @@ -3606,6 +3678,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev) VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL, "VIRTIO_NET_F_CTRL_VQ"))) { return false; } @@ -3742,6 +3816,13 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) vi->mergeable_rx_bufs = true; + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { + vi->rx_usecs = 0; + vi->tx_usecs = 0; + vi->tx_max_packets = 0; + vi->rx_max_packets = 0; + } + if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; @@ -3977,7 +4058,7 @@ static struct virtio_device_id id_table[] = { VIRTIO_NET_F_CTRL_MAC_ADDR, \ VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \ VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \ - VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT + VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL static unsigned int features[] = { VIRTNET_FEATURES, diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 3f55a4215f11..29ced55514d4 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -56,7 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ - +#define VIRTIO_NET_F_NOTF_COAL 53 /* Guest can handle notifications coalescing */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -355,4 +355,36 @@ struct virtio_net_hash_config { #define VIRTIO_NET_CTRL_GUEST_OFFLOADS 5 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET 0 +/* + * Control notifications coalescing. + * + * Request the device to change the notifications coalescing parameters. + * + * Available with the VIRTIO_NET_F_NOTF_COAL feature bit. + */ +#define VIRTIO_NET_CTRL_NOTF_COAL 6 +/* + * Set the tx-usecs/tx-max-packets patameters. + * tx-usecs - Maximum number of usecs to delay a TX notification. + * tx-max-packets - Maximum number of packets to send before a TX notification. + */ +struct virtio_net_ctrl_coal_tx { + __le32 tx_max_packets; + __le32 tx_usecs; +}; + +#define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET 0 + +/* + * Set the rx-usecs/rx-max-packets patameters. + * rx-usecs - Maximum number of usecs to delay a RX notification. + * rx-max-frames - Maximum number of packets to receive before a RX notification. + */ +struct virtio_net_ctrl_coal_rx { + __le32 rx_max_packets; + __le32 rx_usecs; +}; + +#define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET 1 + #endif /* _UAPI_LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From 79a463be9e0051997508d52cf411ed5e91d657f6 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Wed, 3 Aug 2022 12:55:22 +0800 Subject: vduse: Support registering userspace memory for IOVA regions Introduce two ioctls: VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM to support registering and de-registering userspace memory for IOVA regions. Now it only supports registering userspace memory for bounce buffer region in virtio-vdpa case. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20220803045523.23851-5-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_user/vduse_dev.c | 141 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/vduse.h | 23 ++++++ 2 files changed, 164 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 3bc27de58f46..eedff0a3885a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #include #include #include @@ -64,6 +66,13 @@ struct vduse_vdpa { struct vduse_dev *dev; }; +struct vduse_umem { + unsigned long iova; + unsigned long npages; + struct page **pages; + struct mm_struct *mm; +}; + struct vduse_dev { struct vduse_vdpa *vdev; struct device *dev; @@ -95,6 +104,8 @@ struct vduse_dev { u8 status; u32 vq_num; u32 vq_align; + struct vduse_umem *umem; + struct mutex mem_lock; }; struct vduse_dev_msg { @@ -917,6 +928,102 @@ unlock: return ret; } +static int vduse_dev_dereg_umem(struct vduse_dev *dev, + u64 iova, u64 size) +{ + int ret; + + mutex_lock(&dev->mem_lock); + ret = -ENOENT; + if (!dev->umem) + goto unlock; + + ret = -EINVAL; + if (dev->umem->iova != iova || size != dev->domain->bounce_size) + goto unlock; + + vduse_domain_remove_user_bounce_pages(dev->domain); + unpin_user_pages_dirty_lock(dev->umem->pages, + dev->umem->npages, true); + atomic64_sub(dev->umem->npages, &dev->umem->mm->pinned_vm); + mmdrop(dev->umem->mm); + vfree(dev->umem->pages); + kfree(dev->umem); + dev->umem = NULL; + ret = 0; +unlock: + mutex_unlock(&dev->mem_lock); + return ret; +} + +static int vduse_dev_reg_umem(struct vduse_dev *dev, + u64 iova, u64 uaddr, u64 size) +{ + struct page **page_list = NULL; + struct vduse_umem *umem = NULL; + long pinned = 0; + unsigned long npages, lock_limit; + int ret; + + if (!dev->domain->bounce_map || + size != dev->domain->bounce_size || + iova != 0 || uaddr & ~PAGE_MASK) + return -EINVAL; + + mutex_lock(&dev->mem_lock); + ret = -EEXIST; + if (dev->umem) + goto unlock; + + ret = -ENOMEM; + npages = size >> PAGE_SHIFT; + page_list = __vmalloc(array_size(npages, sizeof(struct page *)), + GFP_KERNEL_ACCOUNT); + umem = kzalloc(sizeof(*umem), GFP_KERNEL); + if (!page_list || !umem) + goto unlock; + + mmap_read_lock(current->mm); + + lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK)); + if (npages + atomic64_read(¤t->mm->pinned_vm) > lock_limit) + goto out; + + pinned = pin_user_pages(uaddr, npages, FOLL_LONGTERM | FOLL_WRITE, + page_list, NULL); + if (pinned != npages) { + ret = pinned < 0 ? pinned : -ENOMEM; + goto out; + } + + ret = vduse_domain_add_user_bounce_pages(dev->domain, + page_list, pinned); + if (ret) + goto out; + + atomic64_add(npages, ¤t->mm->pinned_vm); + + umem->pages = page_list; + umem->npages = pinned; + umem->iova = iova; + umem->mm = current->mm; + mmgrab(current->mm); + + dev->umem = umem; +out: + if (ret && pinned > 0) + unpin_user_pages(page_list, pinned); + + mmap_read_unlock(current->mm); +unlock: + if (ret) { + vfree(page_list); + kfree(umem); + } + mutex_unlock(&dev->mem_lock); + return ret; +} + static long vduse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1089,6 +1196,38 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject); break; } + case VDUSE_IOTLB_REG_UMEM: { + struct vduse_iova_umem umem; + + ret = -EFAULT; + if (copy_from_user(&umem, argp, sizeof(umem))) + break; + + ret = -EINVAL; + if (!is_mem_zero((const char *)umem.reserved, + sizeof(umem.reserved))) + break; + + ret = vduse_dev_reg_umem(dev, umem.iova, + umem.uaddr, umem.size); + break; + } + case VDUSE_IOTLB_DEREG_UMEM: { + struct vduse_iova_umem umem; + + ret = -EFAULT; + if (copy_from_user(&umem, argp, sizeof(umem))) + break; + + ret = -EINVAL; + if (!is_mem_zero((const char *)umem.reserved, + sizeof(umem.reserved))) + break; + + ret = vduse_dev_dereg_umem(dev, umem.iova, + umem.size); + break; + } default: ret = -ENOIOCTLCMD; break; @@ -1101,6 +1240,7 @@ static int vduse_dev_release(struct inode *inode, struct file *file) { struct vduse_dev *dev = file->private_data; + vduse_dev_dereg_umem(dev, 0, dev->domain->bounce_size); spin_lock(&dev->msg_lock); /* Make sure the inflight messages can processed after reconncection */ list_splice_init(&dev->recv_list, &dev->send_list); @@ -1163,6 +1303,7 @@ static struct vduse_dev *vduse_dev_create(void) return NULL; mutex_init(&dev->lock); + mutex_init(&dev->mem_lock); spin_lock_init(&dev->msg_lock); INIT_LIST_HEAD(&dev->send_list); INIT_LIST_HEAD(&dev->recv_list); diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 7cfe1c1280c0..9885e0571f09 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -210,6 +210,29 @@ struct vduse_vq_eventfd { */ #define VDUSE_VQ_INJECT_IRQ _IOW(VDUSE_BASE, 0x17, __u32) +/** + * struct vduse_iova_umem - userspace memory configuration for one IOVA region + * @uaddr: start address of userspace memory, it must be aligned to page size + * @iova: start of the IOVA region + * @size: size of the IOVA region + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM + * ioctls to register/de-register userspace memory for IOVA regions + */ +struct vduse_iova_umem { + __u64 uaddr; + __u64 iova; + __u64 size; + __u64 reserved[3]; +}; + +/* Register userspace memory for IOVA regions */ +#define VDUSE_IOTLB_REG_UMEM _IOW(VDUSE_BASE, 0x18, struct vduse_iova_umem) + +/* De-register the userspace memory. Caller should set iova and size field. */ +#define VDUSE_IOTLB_DEREG_UMEM _IOW(VDUSE_BASE, 0x19, struct vduse_iova_umem) + /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ /** -- cgit v1.2.3 From ad146355bfad627bd0717ece73997c6c93b1b82e Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Wed, 3 Aug 2022 12:55:23 +0800 Subject: vduse: Support querying information of IOVA regions This introduces a new ioctl: VDUSE_IOTLB_GET_INFO to support querying some information of IOVA regions. Now it can be used to query whether the IOVA region supports userspace memory registration. Signed-off-by: Xie Yongji Message-Id: <20220803045523.23851-6-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 39 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/vduse.h | 24 +++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index eedff0a3885a..41c0b29739f1 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1228,6 +1228,45 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, umem.size); break; } + case VDUSE_IOTLB_GET_INFO: { + struct vduse_iova_info info; + struct vhost_iotlb_map *map; + struct vduse_iova_domain *domain = dev->domain; + + ret = -EFAULT; + if (copy_from_user(&info, argp, sizeof(info))) + break; + + ret = -EINVAL; + if (info.start > info.last) + break; + + if (!is_mem_zero((const char *)info.reserved, + sizeof(info.reserved))) + break; + + spin_lock(&domain->iotlb_lock); + map = vhost_iotlb_itree_first(domain->iotlb, + info.start, info.last); + if (map) { + info.start = map->start; + info.last = map->last; + info.capability = 0; + if (domain->bounce_map && map->start == 0 && + map->last == domain->bounce_size - 1) + info.capability |= VDUSE_IOVA_CAP_UMEM; + } + spin_unlock(&domain->iotlb_lock); + if (!map) + break; + + ret = -EFAULT; + if (copy_to_user(argp, &info, sizeof(info))) + break; + + ret = 0; + break; + } default: ret = -ENOIOCTLCMD; break; diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 9885e0571f09..11bd48c72c6c 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -233,6 +233,30 @@ struct vduse_iova_umem { /* De-register the userspace memory. Caller should set iova and size field. */ #define VDUSE_IOTLB_DEREG_UMEM _IOW(VDUSE_BASE, 0x19, struct vduse_iova_umem) +/** + * struct vduse_iova_info - information of one IOVA region + * @start: start of the IOVA region + * @last: last of the IOVA region + * @capability: capability of the IOVA regsion + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of + * one IOVA region. + */ +struct vduse_iova_info { + __u64 start; + __u64 last; +#define VDUSE_IOVA_CAP_UMEM (1 << 0) + __u64 capability; + __u64 reserved[3]; +}; + +/* + * Find the first IOVA region that overlaps with the range [start, last] + * and return some information on it. Caller should set start and last fields. + */ +#define VDUSE_IOTLB_GET_INFO _IOWR(VDUSE_BASE, 0x1a, struct vduse_iova_info) + /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ /** -- cgit v1.2.3 From 0723f1df5c3ec8a1112d150dab98e149361ef488 Mon Sep 17 00:00:00 2001 From: Eugenio Pérez Date: Wed, 10 Aug 2022 19:15:10 +0200 Subject: vhost-vdpa: introduce SUSPEND backend feature bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userland knows if it can suspend the device or not by checking this feature bit. It's only offered if the vdpa driver backend implements the suspend() operation callback, and to offer it or userland to ack it if the backend does not offer that callback is an error. Signed-off-by: Eugenio Pérez Message-Id: <20220810171512.2343333-3-eperezma@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 16 +++++++++++++++- include/uapi/linux/vhost_types.h | 2 ++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 2c997d77d266..092752fea8e1 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -347,6 +347,14 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v, return 0; } +static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->suspend; +} + static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; @@ -577,7 +585,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if (cmd == VHOST_SET_BACKEND_FEATURES) { if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (features & ~VHOST_VDPA_BACKEND_FEATURES) + if (features & ~(VHOST_VDPA_BACKEND_FEATURES | + BIT_ULL(VHOST_BACKEND_F_SUSPEND))) + return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) && + !vhost_vdpa_can_suspend(v)) return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; @@ -628,6 +640,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, break; case VHOST_GET_BACKEND_FEATURES: features = VHOST_VDPA_BACKEND_FEATURES; + if (vhost_vdpa_can_suspend(v)) + features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; break; diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 634cee485abb..1bdd6e363f4c 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -161,5 +161,7 @@ struct vhost_vdpa_iova_range { * message */ #define VHOST_BACKEND_F_IOTLB_ASID 0x3 +/* Device can be suspended */ +#define VHOST_BACKEND_F_SUSPEND 0x4 #endif -- cgit v1.2.3 From f345a0143b4dd1cfc850009c6979a3801b86a06f Mon Sep 17 00:00:00 2001 From: Eugenio Pérez Date: Wed, 10 Aug 2022 19:15:11 +0200 Subject: vhost-vdpa: uAPI to suspend the device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ioctl adds support for suspending the device from userspace. This is a must before getting virtqueue indexes (base) for live migration, since the device could modify them after userland gets them. There are individual ways to perform that action for some devices (VHOST_NET_SET_BACKEND, VHOST_VSOCK_SET_RUNNING, ...) but there was no way to perform it for any vhost device (and, in particular, vhost-vdpa). After a successful return of the ioctl call the device must not process more virtqueue descriptors. The device can answer to read or writes of config fields as if it were not suspended. In particular, writing to "queue_enable" with a value of 1 will not make the device start processing buffers of the virtqueue. Signed-off-by: Eugenio Pérez Message-Id: <20220810171512.2343333-4-eperezma@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 19 +++++++++++++++++++ include/uapi/linux/vhost.h | 9 +++++++++ 2 files changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 092752fea8e1..166044642fd5 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -478,6 +478,22 @@ static long vhost_vdpa_get_vqs_count(struct vhost_vdpa *v, u32 __user *argp) return 0; } +/* After a successful return of ioctl the device must not process more + * virtqueue descriptors. The device can answer to read or writes of config + * fields as if it were not suspended. In particular, writing to "queue_enable" + * with a value of 1 will not make the device start processing buffers. + */ +static long vhost_vdpa_suspend(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!ops->suspend) + return -EOPNOTSUPP; + + return ops->suspend(vdpa); +} + static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -654,6 +670,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_GET_VQS_COUNT: r = vhost_vdpa_get_vqs_count(v, argp); break; + case VHOST_VDPA_SUSPEND: + r = vhost_vdpa_suspend(v); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index cab645d4a645..f9f115a7c75b 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -171,4 +171,13 @@ #define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ struct vhost_vring_state) +/* Suspend a device so it does not process virtqueue requests anymore + * + * After the return of ioctl the device must preserve all the necessary state + * (the virtqueue vring base plus the possible device specific states) that is + * required for restoring in the future. The device must not change its + * configuration after that point. + */ +#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) + #endif -- cgit v1.2.3 From c2e75634cbe368065f140dd30bf8b1a0355158fd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 10 Aug 2022 09:45:47 -0700 Subject: net: atm: bring back zatm uAPI Jiri reports that linux-atm does not build without this header. Bring it back. It's completely dead code but we can't break the build for user space :( Reported-by: Jiri Slaby Fixes: 052e1f01bfae ("net: atm: remove support for ZeitNet ZN122x ATM devices") Link: https://lore.kernel.org/all/8576aef3-37e4-8bae-bab5-08f82a78efd3@kernel.org/ Link: https://lore.kernel.org/r/20220810164547.484378-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/atm_zatm.h | 47 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/uapi/linux/atm_zatm.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h new file mode 100644 index 000000000000..5135027b93c1 --- /dev/null +++ b/include/uapi/linux/atm_zatm.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by + driver-specific utilities) */ + +/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ + + +#ifndef LINUX_ATM_ZATM_H +#define LINUX_ATM_ZATM_H + +/* + * Note: non-kernel programs including this file must also include + * sys/types.h for struct timeval + */ + +#include +#include + +#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) + /* get pool statistics */ +#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc) + /* get statistics and zero */ +#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc) + /* set pool parameters */ + +struct zatm_pool_info { + int ref_count; /* free buffer pool usage counters */ + int low_water,high_water; /* refill parameters */ + int rqa_count,rqu_count; /* queue condition counters */ + int offset,next_off; /* alignment optimizations: offset */ + int next_cnt,next_thres; /* repetition counter and threshold */ +}; + +struct zatm_pool_req { + int pool_num; /* pool number */ + struct zatm_pool_info info; /* actual information */ +}; + +#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ +#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ +#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ +#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */ + +#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to + record; must be 2^n */ + +#endif -- cgit v1.2.3 From 5c669c4a4c6aa0489848093c93b8029f5c5c75ec Mon Sep 17 00:00:00 2001 From: Ricardo Cañuelo Date: Wed, 10 Aug 2022 11:40:03 +0200 Subject: virtio: kerneldocs fixes and enhancements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix variable names in some kerneldocs, naming in others. Add kerneldocs for struct vring_desc and vring_interrupt. Signed-off-by: Ricardo Cañuelo Message-Id: <20220810094004.1250-2-ricardo.canuelo@collabora.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h | 6 +++--- include/linux/virtio_config.h | 6 +++--- include/uapi/linux/virtio_ring.h | 16 +++++++++++----- 4 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index d66c8e6d0ef3..4620e9d79dde 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2426,6 +2426,14 @@ static inline bool more_used(const struct vring_virtqueue *vq) return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq); } +/** + * vring_interrupt - notify a virtqueue on an interrupt + * @irq: the IRQ number (ignored) + * @_vq: the struct virtqueue to notify + * + * Calls the callback function of @_vq to process the virtqueue + * notification. + */ irqreturn_t vring_interrupt(int irq, void *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index a3f73bb6733e..dcab9c7e8784 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -11,7 +11,7 @@ #include /** - * virtqueue - a queue to register buffers for sending or receiving. + * struct virtqueue - a queue to register buffers for sending or receiving. * @list: the chain of virtqueues for this device * @callback: the function to call when buffers are consumed (can be NULL). * @name: the name of this virtqueue (mainly for debugging) @@ -97,7 +97,7 @@ int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); /** - * virtio_device - representation of a device using virtio + * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) * @config_enabled: configuration change reporting enabled @@ -156,7 +156,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); list_for_each_entry(vq, &vdev->vqs, list) /** - * virtio_driver - operations for a virtio I/O driver + * struct virtio_driver - operations for a virtio I/O driver * @driver: underlying device driver (populate name and owner). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 36ec7be1f480..4b517649cfe8 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -239,7 +239,7 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks - * @vdev: the device + * @dev: the virtio device */ static inline void virtio_synchronize_cbs(struct virtio_device *dev) @@ -258,7 +258,7 @@ void virtio_synchronize_cbs(struct virtio_device *dev) /** * virtio_device_ready - enable vq use in probe function - * @vdev: the device + * @dev: the virtio device * * Driver must call this to use vqs in the probe function. * @@ -306,7 +306,7 @@ const char *virtio_bus_name(struct virtio_device *vdev) /** * virtqueue_set_affinity - setting affinity for a virtqueue * @vq: the virtqueue - * @cpu: the cpu no. + * @cpu_mask: the cpu mask * * Pay attention the function are best-effort: the affinity hint may not be set * due to config support, irq type and sharing. diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 476d3e5c0fe7..f8c20d3de8da 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -93,15 +93,21 @@ #define VRING_USED_ALIGN_SIZE 4 #define VRING_DESC_ALIGN_SIZE 16 -/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ +/** + * struct vring_desc - Virtio ring descriptors, + * 16 bytes long. These can chain together via @next. + * + * @addr: buffer address (guest-physical) + * @len: buffer length + * @flags: descriptor flags + * @next: index of the next descriptor in the chain, + * if the VRING_DESC_F_NEXT flag is set. We chain unused + * descriptors via this, too. + */ struct vring_desc { - /* Address (guest-physical). */ __virtio64 addr; - /* Length. */ __virtio32 len; - /* The flags as indicated above. */ __virtio16 flags; - /* We chain unused descriptors via this, too */ __virtio16 next; }; -- cgit v1.2.3 From 3024d95a4c521c278a7504ee9e80c57c3a9750e0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 17 Aug 2022 23:32:09 +0200 Subject: bpf: Partially revert flexible-array member replacement Partially revert 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members") given it breaks BPF UAPI. For example, BPF CI run reveals build breakage under LLVM: [...] CLNG-BPF [test_maps] map_ptr_kern.o CLNG-BPF [test_maps] btf__core_reloc_arrays___diff_arr_val_sz.o CLNG-BPF [test_maps] test_bpf_cookie.o progs/map_ptr_kern.c:314:26: error: field 'trie_key' with variable sized type 'struct bpf_lpm_trie_key' not at the end of a struct or class is a GNU extension [-Werror,-Wgnu-variable-sized-type-not-at-end] struct bpf_lpm_trie_key trie_key; ^ CLNG-BPF [test_maps] btf__core_reloc_type_based___diff.o 1 error generated. make: *** [Makefile:521: /tmp/runner/work/bpf/bpf/tools/testing/selftests/bpf/map_ptr_kern.o] Error 1 make: *** Waiting for unfinished jobs.... [...] Typical usage of the bpf_lpm_trie_key is that the struct gets embedded into a user defined key for the LPM BPF map, from the selftest example: struct bpf_lpm_trie_key { <-- UAPI exported struct __u32 prefixlen; __u8 data[]; }; struct lpm_key { <-- BPF program defined struct struct bpf_lpm_trie_key trie_key; __u32 data; }; Undo this for BPF until a different solution can be found. It's the only flexible- array member case in the UAPI header. This was discovered in BPF CI after Dave reported that the include/uapi/linux/bpf.h header was out of sync with tools/include/uapi/linux/bpf.h after 94dfc73e7cf4. And the subsequent sync attempt failed CI. Fixes: 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members") Reported-by: Dave Marchevsky Signed-off-by: Daniel Borkmann Cc: Gustavo A. R. Silva Link: https://lore.kernel.org/bpf/22aebc88-da67-f086-e620-dd4a16e2bc69@iogearbox.net --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bf9ba1329be..59a217ca2dfd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -79,7 +79,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { -- cgit v1.2.3 From e1d0c6d05afdcff01ace698edb3b8808db1dc066 Mon Sep 17 00:00:00 2001 From: Ammar Faizi Date: Tue, 23 Aug 2022 18:45:49 +0700 Subject: io_uring: uapi: Add `extern "C"` in io_uring.h for liburing Make it easy for liburing to integrate uapi header with the kernel. Previously, when this header changes, the liburing side can't directly copy this header file due to some small differences. Sync them. Link: https://lore.kernel.org/io-uring/f1feef16-6ea2-0653-238f-4aaee35060b6@kernel.dk Cc: Bart Van Assche Cc: Dylan Yudaken Cc: Facebook Kernel Team Signed-off-by: Ammar Faizi Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1463cfecb56b..9e0b5c8d92ce 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -12,6 +12,10 @@ #include #include +#ifdef __cplusplus +extern "C" { +#endif + /* * IO submission data structure (Submission Queue Entry) */ @@ -661,4 +665,8 @@ struct io_uring_recvmsg_out { __u32 flags; }; +#ifdef __cplusplus +} +#endif + #endif -- cgit v1.2.3 From fce1c23f629173e0db78b79a74f2052044a00e65 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Tue, 23 Aug 2022 10:39:47 +0300 Subject: net: virtio_net: fix notification coalescing comments Fix wording in comments for the notifications coalescing feature. Signed-off-by: Alvaro Karsz Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20220823073947.14774-1-alvaro.karsz@solid-run.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/virtio_net.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 29ced55514d4..6cb842ea8979 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -56,7 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ -#define VIRTIO_NET_F_NOTF_COAL 53 /* Guest can handle notifications coalescing */ +#define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -364,24 +364,24 @@ struct virtio_net_hash_config { */ #define VIRTIO_NET_CTRL_NOTF_COAL 6 /* - * Set the tx-usecs/tx-max-packets patameters. - * tx-usecs - Maximum number of usecs to delay a TX notification. - * tx-max-packets - Maximum number of packets to send before a TX notification. + * Set the tx-usecs/tx-max-packets parameters. */ struct virtio_net_ctrl_coal_tx { + /* Maximum number of packets to send before a TX notification */ __le32 tx_max_packets; + /* Maximum number of usecs to delay a TX notification */ __le32 tx_usecs; }; #define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET 0 /* - * Set the rx-usecs/rx-max-packets patameters. - * rx-usecs - Maximum number of usecs to delay a RX notification. - * rx-max-frames - Maximum number of packets to receive before a RX notification. + * Set the rx-usecs/rx-max-packets parameters. */ struct virtio_net_ctrl_coal_rx { + /* Maximum number of packets to receive before a RX notification */ __le32 rx_max_packets; + /* Maximum number of usecs to delay a RX notification */ __le32 rx_usecs; }; -- cgit v1.2.3 From 23c12d5fc02fb0712c64f3e87a27fcfa78e8af9c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 1 Sep 2022 11:54:01 +0100 Subject: Revert "io_uring: add zc notification flush requests" This reverts commit 492dddb4f6e3a5839c27d41ff1fecdbe6c3ab851. Soon we won't have the very notion of notification flushing, so remove notification flushing requests. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8850334ca56e65b413cb34fd158db81d7b2865a3.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 - io_uring/rsrc.c | 38 -------------------------------------- 2 files changed, 39 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 9e0b5c8d92ce..18ae5caf1773 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -301,7 +301,6 @@ enum io_uring_op { */ enum { IORING_RSRC_UPDATE_FILES, - IORING_RSRC_UPDATE_NOTIF, }; /* diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 71359a4d0bd4..048f7483fe8a 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -15,7 +15,6 @@ #include "io_uring.h" #include "openclose.h" #include "rsrc.h" -#include "notif.h" struct io_rsrc_update { struct file *file; @@ -741,41 +740,6 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } -static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update); - struct io_ring_ctx *ctx = req->ctx; - unsigned len = up->nr_args; - unsigned idx_end, idx = up->offset; - int ret = 0; - - io_ring_submit_lock(ctx, issue_flags); - if (unlikely(check_add_overflow(idx, len, &idx_end))) { - ret = -EOVERFLOW; - goto out; - } - if (unlikely(idx_end > ctx->nr_notif_slots)) { - ret = -EINVAL; - goto out; - } - - for (; idx < idx_end; idx++) { - struct io_notif_slot *slot = &ctx->notif_slots[idx]; - - if (!slot->notif) - continue; - if (up->arg) - slot->tag = up->arg; - io_notif_slot_flush_submit(slot, issue_flags); - } -out: - io_ring_submit_unlock(ctx, issue_flags); - if (ret < 0) - req_set_fail(req); - io_req_set_res(req, ret, 0); - return IOU_OK; -} - int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update); @@ -783,8 +747,6 @@ int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) switch (up->type) { case IORING_RSRC_UPDATE_FILES: return io_files_update(req, issue_flags); - case IORING_RSRC_UPDATE_NOTIF: - return io_notif_update(req, issue_flags); } return -EINVAL; } -- cgit v1.2.3 From d9808ceb3129b811becebdee3ec96d189c83e56c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 1 Sep 2022 11:54:02 +0100 Subject: Revert "io_uring: rename IORING_OP_FILES_UPDATE" This reverts commit 4379d5f15b3fd4224c37841029178aa8082a242e. We removed notification flushing, also cleanup uapi preparation changes to not pollute it. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/89edc3905350f91e1b6e26d9dbf42ee44fd451a2.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 +----------- io_uring/opdef.c | 9 ++++----- io_uring/rsrc.c | 17 ++--------------- io_uring/rsrc.h | 4 ++-- 4 files changed, 9 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 18ae5caf1773..111b651366bd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -178,8 +178,7 @@ enum io_uring_op { IORING_OP_FALLOCATE, IORING_OP_OPENAT, IORING_OP_CLOSE, - IORING_OP_RSRC_UPDATE, - IORING_OP_FILES_UPDATE = IORING_OP_RSRC_UPDATE, + IORING_OP_FILES_UPDATE, IORING_OP_STATX, IORING_OP_READ, IORING_OP_WRITE, @@ -228,7 +227,6 @@ enum io_uring_op { #define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) - /* * sqe->splice_flags * extends splice(2) flags @@ -295,14 +293,6 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) - -/* - * IORING_OP_RSRC_UPDATE flags - */ -enum { - IORING_RSRC_UPDATE_FILES, -}; - /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 41410126c1c6..10b301ccf5cd 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -246,13 +246,12 @@ const struct io_op_def io_op_defs[] = { .prep = io_close_prep, .issue = io_close, }, - [IORING_OP_RSRC_UPDATE] = { + [IORING_OP_FILES_UPDATE] = { .audit_skip = 1, .iopoll = 1, - .name = "RSRC_UPDATE", - .prep = io_rsrc_update_prep, - .issue = io_rsrc_update, - .ioprio = 1, + .name = "FILES_UPDATE", + .prep = io_files_update_prep, + .issue = io_files_update, }, [IORING_OP_STATX] = { .audit_skip = 1, diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 048f7483fe8a..cf3272113214 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -21,7 +21,6 @@ struct io_rsrc_update { u64 arg; u32 nr_args; u32 offset; - int type; }; static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, @@ -654,7 +653,7 @@ __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; } -int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update); @@ -668,7 +667,6 @@ int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!up->nr_args) return -EINVAL; up->arg = READ_ONCE(sqe->addr); - up->type = READ_ONCE(sqe->ioprio); return 0; } @@ -711,7 +709,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req, return ret; } -static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update); struct io_ring_ctx *ctx = req->ctx; @@ -740,17 +738,6 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } -int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) -{ - struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update); - - switch (up->type) { - case IORING_RSRC_UPDATE_FILES: - return io_files_update(req, issue_flags); - } - return -EINVAL; -} - int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index f3a9a177941f..9bce15665444 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -167,8 +167,8 @@ static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) return &data->tags[table_idx][off]; } -int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags); -int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_files_update(struct io_kiocb *req, unsigned int issue_flags); +int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int __io_account_mem(struct user_struct *user, unsigned long nr_pages); -- cgit v1.2.3 From 57f332246afa5929bdf2e7a5facddedb43549be4 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 1 Sep 2022 11:54:03 +0100 Subject: io_uring/notif: remove notif registration We're going to remove the userspace exposed zerocopy notification API, remove notification registration. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/6ff00b97be99869c386958a990593c9c31cf105b.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ----- io_uring/io_uring.c | 10 ------ io_uring/net.c | 4 +-- io_uring/notif.c | 71 ------------------------------------------- io_uring/notif.h | 11 ------- 5 files changed, 1 insertion(+), 103 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 111b651366bd..b11c57b0ebb5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -279,14 +279,10 @@ enum io_uring_op { * * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in * the buf_index field. - * - * IORING_RECVSEND_NOTIF_FLUSH Flush a notification after a successful - * successful. Only for zerocopy sends. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) -#define IORING_RECVSEND_NOTIF_FLUSH (1U << 3) /* * accept flags stored in sqe->ioprio @@ -474,10 +470,6 @@ enum { /* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE = 25, - /* zerocopy notification API */ - IORING_REGISTER_NOTIFIERS = 26, - IORING_UNREGISTER_NOTIFIERS = 27, - /* this goes last */ IORING_REGISTER_LAST }; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 77616279000b..c2e06a3aa18d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2640,7 +2640,6 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); if (ctx->rings) io_poll_remove_all(ctx, NULL, true); - io_notif_unregister(ctx); mutex_unlock(&ctx->uring_lock); /* failed during ring init, it couldn't have issued any requests */ @@ -3839,15 +3838,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_file_alloc_range(ctx, arg); break; - case IORING_REGISTER_NOTIFIERS: - ret = io_notif_register(ctx, arg, nr_args); - break; - case IORING_UNREGISTER_NOTIFIERS: - ret = -EINVAL; - if (arg || nr_args) - break; - ret = io_notif_unregister(ctx); - break; default: ret = -EINVAL; break; diff --git a/io_uring/net.c b/io_uring/net.c index 7a5468cc905e..aac6997b7d88 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -889,7 +889,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) zc->flags = READ_ONCE(sqe->ioprio); if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | - IORING_RECVSEND_FIXED_BUF | IORING_RECVSEND_NOTIF_FLUSH)) + IORING_RECVSEND_FIXED_BUF)) return -EINVAL; if (zc->flags & IORING_RECVSEND_FIXED_BUF) { unsigned idx = READ_ONCE(sqe->buf_index); @@ -1063,8 +1063,6 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) if (ret == -ERESTARTSYS) ret = -EINTR; req_set_fail(req); - } else if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH) { - io_notif_slot_flush_submit(notif_slot, 0); } if (ret >= 0) diff --git a/io_uring/notif.c b/io_uring/notif.c index 96f076b175e0..11f45640684a 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -86,74 +86,3 @@ void io_notif_slot_flush(struct io_notif_slot *slot) io_req_task_work_add(notif); } } - -__cold int io_notif_unregister(struct io_ring_ctx *ctx) - __must_hold(&ctx->uring_lock) -{ - int i; - - if (!ctx->notif_slots) - return -ENXIO; - - for (i = 0; i < ctx->nr_notif_slots; i++) { - struct io_notif_slot *slot = &ctx->notif_slots[i]; - struct io_kiocb *notif = slot->notif; - struct io_notif_data *nd; - - if (!notif) - continue; - nd = io_notif_to_data(notif); - slot->notif = NULL; - if (!refcount_dec_and_test(&nd->uarg.refcnt)) - continue; - notif->io_task_work.func = __io_notif_complete_tw; - io_req_task_work_add(notif); - } - - kvfree(ctx->notif_slots); - ctx->notif_slots = NULL; - ctx->nr_notif_slots = 0; - return 0; -} - -__cold int io_notif_register(struct io_ring_ctx *ctx, - void __user *arg, unsigned int size) - __must_hold(&ctx->uring_lock) -{ - struct io_uring_notification_slot __user *slots; - struct io_uring_notification_slot slot; - struct io_uring_notification_register reg; - unsigned i; - - if (ctx->nr_notif_slots) - return -EBUSY; - if (size != sizeof(reg)) - return -EINVAL; - if (copy_from_user(®, arg, sizeof(reg))) - return -EFAULT; - if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS) - return -EINVAL; - if (reg.resv || reg.resv2 || reg.resv3) - return -EINVAL; - - slots = u64_to_user_ptr(reg.data); - ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]), - GFP_KERNEL_ACCOUNT); - if (!ctx->notif_slots) - return -ENOMEM; - - for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) { - struct io_notif_slot *notif_slot = &ctx->notif_slots[i]; - - if (copy_from_user(&slot, &slots[i], sizeof(slot))) { - io_notif_unregister(ctx); - return -EFAULT; - } - if (slot.resv[0] | slot.resv[1] | slot.resv[2]) { - io_notif_unregister(ctx); - return -EINVAL; - } - notif_slot->tag = slot.tag; - } - return 0; -} diff --git a/io_uring/notif.h b/io_uring/notif.h index 80f6445e0c2b..8380eeff2f2e 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -8,7 +8,6 @@ #include "rsrc.h" #define IO_NOTIF_SPLICE_BATCH 32 -#define IORING_MAX_NOTIF_SLOTS (1U << 15) struct io_notif_data { struct file *file; @@ -36,10 +35,6 @@ struct io_notif_slot { u32 seq; }; -int io_notif_register(struct io_ring_ctx *ctx, - void __user *arg, unsigned int size); -int io_notif_unregister(struct io_ring_ctx *ctx); - void io_notif_slot_flush(struct io_notif_slot *slot); struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx, struct io_notif_slot *slot); @@ -67,12 +62,6 @@ static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx, return &ctx->notif_slots[idx]; } -static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot, - unsigned int issue_flags) -{ - io_notif_slot_flush(slot); -} - static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len) { struct io_ring_ctx *ctx = notif->ctx; -- cgit v1.2.3 From b48c312be05e83b55a4d58bf61f80b4a3288fb7e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 1 Sep 2022 11:54:04 +0100 Subject: io_uring/net: simplify zerocopy send user API Following user feedback, this patch simplifies zerocopy send API. One of the main complaints is that the current API is difficult with the userspace managing notification slots, and then send retries with error handling make it even worse. Instead of keeping notification slots change it to the per-request notifications model, which posts both completion and notification CQEs for each request when any data has been sent, and only one CQE if it fails. All notification CQEs will have IORING_CQE_F_NOTIF set and IORING_CQE_F_MORE in completion CQEs indicates whether to wait a notification or not. IOSQE_CQE_SKIP_SUCCESS is disallowed with zerocopy sends for now. This is less flexible, but greatly simplifies the user API and also the kernel implementation. We reuse notif helpers in this patch, but in the future there won't be need for keeping two requests. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/95287640ab98fc9417370afb16e310677c63e6ce.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 ++++-- io_uring/io_uring.c | 4 ++-- io_uring/net.c | 53 +++++++++++++++++++++++++++---------------- io_uring/net.h | 1 + io_uring/notif.c | 12 ++-------- io_uring/notif.h | 43 ++--------------------------------- io_uring/opdef.c | 3 ++- 7 files changed, 47 insertions(+), 76 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b11c57b0ebb5..6b83177fd41d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -71,8 +71,8 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; struct { - __u16 notification_idx; __u16 addr_len; + __u16 __pad3[1]; }; }; union { @@ -205,7 +205,7 @@ enum io_uring_op { IORING_OP_GETXATTR, IORING_OP_SOCKET, IORING_OP_URING_CMD, - IORING_OP_SENDZC_NOTIF, + IORING_OP_SEND_ZC, /* this goes last, obviously */ IORING_OP_LAST, @@ -326,10 +326,13 @@ struct io_uring_cqe { * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv + * IORING_CQE_F_NOTIF Set for notification CQEs. Can be used to distinct + * them from sends. */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) #define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) +#define IORING_CQE_F_NOTIF (1U << 3) enum { IORING_CQE_BUFFER_SHIFT = 16, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index c2e06a3aa18d..f9be9b7eb654 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3923,8 +3923,8 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); - BUILD_BUG_SQE_ELEM(44, __u16, notification_idx); - BUILD_BUG_SQE_ELEM(46, __u16, addr_len); + BUILD_BUG_SQE_ELEM(44, __u16, addr_len); + BUILD_BUG_SQE_ELEM(46, __u16, __pad3[0]); BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd); BUILD_BUG_SQE_ELEM(56, __u64, __pad2); diff --git a/io_uring/net.c b/io_uring/net.c index aac6997b7d88..7047c1342541 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -65,12 +65,12 @@ struct io_sendzc { struct file *file; void __user *buf; size_t len; - u16 slot_idx; unsigned msg_flags; unsigned flags; unsigned addr_len; void __user *addr; size_t done_io; + struct io_kiocb *notif; }; #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) @@ -879,12 +879,26 @@ out_free: return ret; } +void io_sendzc_cleanup(struct io_kiocb *req) +{ + struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc); + + zc->notif->flags |= REQ_F_CQE_SKIP; + io_notif_flush(zc->notif); + zc->notif = NULL; +} + int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc); struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *notif; - if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)) + if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3) || + READ_ONCE(sqe->__pad3[0])) + return -EINVAL; + /* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */ + if (req->flags & REQ_F_CQE_SKIP) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); @@ -900,11 +914,17 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = READ_ONCE(ctx->user_bufs[idx]); io_req_set_rsrc_node(req, ctx, 0); } + notif = zc->notif = io_alloc_notif(ctx); + if (!notif) + return -ENOMEM; + notif->cqe.user_data = req->cqe.user_data; + notif->cqe.res = 0; + notif->cqe.flags = IORING_CQE_F_NOTIF; + req->flags |= REQ_F_NEED_CLEANUP; zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); zc->len = READ_ONCE(sqe->len); zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; - zc->slot_idx = READ_ONCE(sqe->notification_idx); if (zc->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; @@ -976,33 +996,20 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb, int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) { struct sockaddr_storage __address, *addr = NULL; - struct io_ring_ctx *ctx = req->ctx; struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc); - struct io_notif_slot *notif_slot; - struct io_kiocb *notif; struct msghdr msg; struct iovec iov; struct socket *sock; - unsigned msg_flags; + unsigned msg_flags, cflags; int ret, min_ret = 0; if (!(req->flags & REQ_F_POLLED) && (zc->flags & IORING_RECVSEND_POLL_FIRST)) return -EAGAIN; - - if (issue_flags & IO_URING_F_UNLOCKED) - return -EAGAIN; sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; - notif_slot = io_get_notif_slot(ctx, zc->slot_idx); - if (!notif_slot) - return -EINVAL; - notif = io_get_notif(ctx, notif_slot); - if (!notif) - return -ENOMEM; - msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; @@ -1033,7 +1040,7 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) &msg.msg_iter); if (unlikely(ret)) return ret; - ret = io_notif_account_mem(notif, zc->len); + ret = io_notif_account_mem(zc->notif, zc->len); if (unlikely(ret)) return ret; } @@ -1045,7 +1052,7 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&msg.msg_iter); msg.msg_flags = msg_flags; - msg.msg_ubuf = &io_notif_to_data(notif)->uarg; + msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg; msg.sg_from_iter = io_sg_from_iter; ret = sock_sendmsg(sock, &msg); @@ -1060,6 +1067,8 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_addr(req, addr, issue_flags); } + if (ret < 0 && !zc->done_io) + zc->notif->flags |= REQ_F_CQE_SKIP; if (ret == -ERESTARTSYS) ret = -EINTR; req_set_fail(req); @@ -1069,7 +1078,11 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) ret += zc->done_io; else if (zc->done_io) ret = zc->done_io; - io_req_set_res(req, ret, 0); + + io_notif_flush(zc->notif); + req->flags &= ~REQ_F_NEED_CLEANUP; + cflags = ret >= 0 ? IORING_CQE_F_MORE : 0; + io_req_set_res(req, ret, cflags); return IOU_OK; } diff --git a/io_uring/net.h b/io_uring/net.h index f91f56c6eeac..d744a0a874e7 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -55,6 +55,7 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags); int io_sendzc(struct io_kiocb *req, unsigned int issue_flags); int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +void io_sendzc_cleanup(struct io_kiocb *req); void io_netmsg_cache_free(struct io_cache_entry *entry); #else diff --git a/io_uring/notif.c b/io_uring/notif.c index 11f45640684a..38d77165edc3 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -42,8 +42,7 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb, } } -struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx, - struct io_notif_slot *slot) +struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { struct io_kiocb *notif; @@ -59,27 +58,20 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx, io_get_task_refs(1); notif->rsrc_node = NULL; io_req_set_rsrc_node(notif, ctx, 0); - notif->cqe.user_data = slot->tag; - notif->cqe.flags = slot->seq++; - notif->cqe.res = 0; nd = io_notif_to_data(notif); nd->account_pages = 0; nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; nd->uarg.callback = io_uring_tx_zerocopy_callback; - /* master ref owned by io_notif_slot, will be dropped on flush */ refcount_set(&nd->uarg.refcnt, 1); return notif; } -void io_notif_slot_flush(struct io_notif_slot *slot) +void io_notif_flush(struct io_kiocb *notif) __must_hold(&slot->notif->ctx->uring_lock) { - struct io_kiocb *notif = slot->notif; struct io_notif_data *nd = io_notif_to_data(notif); - slot->notif = NULL; - /* drop slot's master ref */ if (refcount_dec_and_test(&nd->uarg.refcnt)) { notif->io_task_work.func = __io_notif_complete_tw; diff --git a/io_uring/notif.h b/io_uring/notif.h index 8380eeff2f2e..5b4d710c8ca5 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -15,53 +15,14 @@ struct io_notif_data { unsigned long account_pages; }; -struct io_notif_slot { - /* - * Current/active notifier. A slot holds only one active notifier at a - * time and keeps one reference to it. Flush releases the reference and - * lazily replaces it with a new notifier. - */ - struct io_kiocb *notif; - - /* - * Default ->user_data for this slot notifiers CQEs - */ - u64 tag; - /* - * Notifiers of a slot live in generations, we create a new notifier - * only after flushing the previous one. Track the sequential number - * for all notifiers and copy it into notifiers's cqe->cflags - */ - u32 seq; -}; - -void io_notif_slot_flush(struct io_notif_slot *slot); -struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx, - struct io_notif_slot *slot); +void io_notif_flush(struct io_kiocb *notif); +struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx); static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif) { return io_kiocb_to_cmd(notif, struct io_notif_data); } -static inline struct io_kiocb *io_get_notif(struct io_ring_ctx *ctx, - struct io_notif_slot *slot) -{ - if (!slot->notif) - slot->notif = io_alloc_notif(ctx, slot); - return slot->notif; -} - -static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx, - unsigned idx) - __must_hold(&ctx->uring_lock) -{ - if (idx >= ctx->nr_notif_slots) - return NULL; - idx = array_index_nospec(idx, ctx->nr_notif_slots); - return &ctx->notif_slots[idx]; -} - static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len) { struct io_ring_ctx *ctx = notif->ctx; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 10b301ccf5cd..c61494e0a602 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -470,7 +470,7 @@ const struct io_op_def io_op_defs[] = { .issue = io_uring_cmd, .prep_async = io_uring_cmd_prep_async, }, - [IORING_OP_SENDZC_NOTIF] = { + [IORING_OP_SEND_ZC] = { .name = "SENDZC_NOTIF", .needs_file = 1, .unbound_nonreg_file = 1, @@ -483,6 +483,7 @@ const struct io_op_def io_op_defs[] = { .prep = io_sendzc_prep, .issue = io_sendzc, .prep_async = io_sendzc_prep_async, + .cleanup = io_sendzc_cleanup, #else .prep = io_eopnotsupp_prep, #endif -- cgit v1.2.3